diff --git a/.devcontainer/devcontainer.json b/.devcontainer/devcontainer.json index 64c85c1101e6e6..fb11c82bb96d9c 100644 --- a/.devcontainer/devcontainer.json +++ b/.devcontainer/devcontainer.json @@ -1,13 +1,10 @@ { - "image": "ghcr.io/python/devcontainer:2024.09.25.11038928730", + "image": "ghcr.io/python/devcontainer:latest", "onCreateCommand": [ // Install common tooling. "dnf", "install", "-y", - "which", - "zsh", - "fish", // For umask fix below. "/usr/bin/setfacl" ], diff --git a/.editorconfig b/.editorconfig index 5b04b32a89e3d2..ab1f7ce8425769 100644 --- a/.editorconfig +++ b/.editorconfig @@ -1,11 +1,11 @@ root = true -[*.{py,c,cpp,h,js,rst,md,yml,yaml}] +[*.{py,c,cpp,h,js,rst,md,yml,yaml,toml,gram}] trim_trailing_whitespace = true insert_final_newline = true indent_style = space -[*.{py,c,cpp,h}] +[*.{py,c,cpp,h,toml,gram}] indent_size = 4 [*.rst] diff --git a/.gitattributes b/.gitattributes index 2f5a030981fb94..70aaadf5e3b520 100644 --- a/.gitattributes +++ b/.gitattributes @@ -10,6 +10,7 @@ *.ico binary *.jpg binary *.pck binary +*.pdf binary *.png binary *.psd binary *.tar binary @@ -33,6 +34,9 @@ Lib/test/xmltestdata/* noeol Lib/venv/scripts/common/activate text eol=lf Lib/venv/scripts/posix/* text eol=lf +# Prevent GitHub's web conflict editor from converting LF to CRLF +*.rst text eol=lf + # CRLF files [attr]dos text eol=crlf @@ -67,6 +71,7 @@ PCbuild/readme.txt dos **/clinic/*.cpp.h generated **/clinic/*.h.h generated *_db.h generated +Doc/c-api/lifecycle.dot.svg generated Doc/data/stable_abi.dat generated Doc/library/token-list.inc generated Include/internal/pycore_ast.h generated @@ -80,7 +85,10 @@ Include/opcode.h generated Include/opcode_ids.h generated Include/token.h generated Lib/_opcode_metadata.py generated +Lib/idlelib/help.html generated Lib/keyword.py generated +Lib/pydoc_data/topics.py generated +Lib/pydoc_data/module_docs.py generated Lib/test/certdata/*.pem generated Lib/test/certdata/*.0 generated Lib/test/levenshtein_examples.json generated @@ -101,3 +109,5 @@ Python/stdlib_module_names.h generated Tools/peg_generator/pegen/grammar_parser.py generated aclocal.m4 generated configure generated +*.min.js generated +package-lock.json generated diff --git a/.github/CODEOWNERS b/.github/CODEOWNERS index 16331b65e52979..b54e5791367ca7 100644 --- a/.github/CODEOWNERS +++ b/.github/CODEOWNERS @@ -5,10 +5,13 @@ # https://git-scm.com/docs/gitignore#_pattern_format # GitHub -.github/** @ezio-melotti @hugovk @AA-Turner +.github/** @ezio-melotti @hugovk @AA-Turner @webknjaz +.github/workflows/jit.yml @savannahostrowski +Tools/build/compute-changes.py @AA-Turner @hugovk @webknjaz +Lib/test/test_tools/test_compute_changes.py @AA-Turner @hugovk @webknjaz # pre-commit -.pre-commit-config.yaml @hugovk @AlexWaygood +.pre-commit-config.yaml @hugovk .ruff.toml @hugovk @AlexWaygood @AA-Turner # Build system @@ -16,6 +19,10 @@ configure* @erlend-aasland @corona10 Makefile.pre.in @erlend-aasland Modules/Setup* @erlend-aasland +# generate-build-details +Tools/build/generate-build-details.py @FFY00 +Lib/test/test_build_details.py @FFY00 + # argparse **/*argparse* @savannahostrowski @@ -27,6 +34,7 @@ Modules/Setup* @erlend-aasland **/*genobject* @markshannon **/*hamt* @1st1 **/*jit* @brandtbucher @savannahostrowski +Python/perf_jit_trampoline.c # Exclude the owners of "**/*jit*", above. Objects/set* @rhettinger Objects/dict* @methane @markshannon Objects/typevarobject.c @JelleZijlstra @@ -53,6 +61,7 @@ Lib/test/test_type_*.py @JelleZijlstra Lib/test/test_capi/test_misc.py @markshannon Lib/test/test_pyrepl/* @pablogsal @lysnikolaou @ambv Tools/c-analyzer/ @ericsnowcurrently +Tools/check-c-api-docs/ @ZeroIntensity # dbm **/*dbm* @corona10 @erlend-aasland @serhiy-storchaka @@ -155,6 +164,7 @@ Doc/c-api/module.rst @ericsnowcurrently # Dates and times **/*datetime* @pganssle @abalkin **/*str*time* @pganssle @abalkin +Doc/library/datetime-* @pganssle Doc/library/time.rst @pganssle @abalkin Lib/test/test_time.py @pganssle @abalkin Modules/timemodule.c @pganssle @abalkin @@ -203,7 +213,7 @@ Lib/test/test_ast/ @eclips4 **/*multiprocessing* @gpshead # SQLite 3 -**/*sqlite* @berkerpeksag @erlend-aasland +**/*sqlite* @erlend-aasland # subprocess /Lib/subprocess.py @gpshead @@ -281,14 +291,21 @@ Doc/howto/clinic.rst @erlend-aasland # Subinterpreters **/*interpreteridobject.* @ericsnowcurrently **/*crossinterp* @ericsnowcurrently -Lib/test/support/interpreters/ @ericsnowcurrently Modules/_interp*module.c @ericsnowcurrently +Lib/test/test__interp*.py @ericsnowcurrently +Lib/concurrent/interpreters/ @ericsnowcurrently +Lib/test/support/channels.py @ericsnowcurrently +Doc/library/concurrent.interpreters.rst @ericsnowcurrently Lib/test/test_interpreters/ @ericsnowcurrently +Lib/concurrent/futures/interpreter.py @ericsnowcurrently # Android **/*Android* @mhsmith @freakboy3742 **/*android* @mhsmith @freakboy3742 +# Apple +/Apple @freakboy3742 + # iOS (but not termios) **/iOS* @freakboy3742 **/ios* @freakboy3742 @@ -298,7 +315,12 @@ Lib/test/test_interpreters/ @ericsnowcurrently **/*-ios* @freakboy3742 # WebAssembly -/Tools/wasm/ @brettcannon @freakboy3742 +/Platforms/emscripten @freakboy3742 +/Tools/wasm/README.md @brettcannon @freakboy3742 +/Tools/wasm/wasi-env @brettcannon +/Tools/wasm/wasi_build.py @brettcannon +/Tools/wasm/emscripten @freakboy3742 +/Tools/wasm/wasi @brettcannon # SBOM /Misc/externals.spdx.json @sethmlarson @@ -326,3 +348,8 @@ Modules/_xxtestfuzz/ @ammaraskar **/*templateobject* @lysnikolaou **/*templatelib* @lysnikolaou **/*tstring* @lysnikolaou + +# Remote debugging +Python/remote_debug.h @pablogsal +Python/remote_debugging.c @pablogsal +Modules/_remote_debugging_module.c @pablogsal @ambv @1st1 diff --git a/.github/actionlint.yaml b/.github/actionlint.yaml index 68aae196357414..61ee08db9919bb 100644 --- a/.github/actionlint.yaml +++ b/.github/actionlint.yaml @@ -1,9 +1,12 @@ -self-hosted-runner: - # Pending https://github.com/rhysd/actionlint/issues/533 - labels: ["windows-11-arm"] - config-variables: null +# Pending release of actionlint > 1.7.12 for ubuntu-26.04* support: +# https://github.com/rhysd/actionlint/pull/683 +self-hosted-runner: + labels: + - ubuntu-26.04 + - ubuntu-26.04-arm + paths: .github/workflows/**/*.yml: ignore: diff --git a/.github/dependabot.yml b/.github/dependabot.yml index c8a3165d690364..7f3376f8ddb1e2 100644 --- a/.github/dependabot.yml +++ b/.github/dependabot.yml @@ -12,6 +12,11 @@ updates: update-types: - "version-update:semver-minor" - "version-update:semver-patch" + cooldown: + # https://blog.yossarian.net/2025/11/21/We-should-all-be-using-dependency-cooldowns + # Cooldowns protect against supply chain attacks by avoiding the + # highest-risk window immediately after new releases. + default-days: 14 - package-ecosystem: "pip" directory: "/Tools/" schedule: @@ -19,3 +24,5 @@ updates: labels: - "skip issue" - "skip news" + cooldown: + default-days: 14 diff --git a/.github/workflows/add-issue-header.yml b/.github/workflows/add-issue-header.yml index 3cbc23af578d10..55eb6bf33b8128 100644 --- a/.github/workflows/add-issue-header.yml +++ b/.github/workflows/add-issue-header.yml @@ -12,15 +12,17 @@ on: # Only ever run once - opened +permissions: + contents: read jobs: add-header: - runs-on: ubuntu-latest + runs-on: ubuntu-slim permissions: issues: write timeout-minutes: 5 steps: - - uses: actions/github-script@v7 + - uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8.0.0 with: # language=JavaScript script: | diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml index b192508c78685c..f531d8e02c123c 100644 --- a/.github/workflows/build.yml +++ b/.github/workflows/build.yml @@ -15,7 +15,13 @@ permissions: contents: read concurrency: - group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}-reusable + # https://docs.github.com/en/actions/writing-workflows/workflow-syntax-for-github-actions#concurrency + # 'group' must be a key uniquely representing a PR or push event. + # github.workflow is the workflow name + # github.actor is the user invoking the workflow + # github.head_ref is the source branch of the PR or otherwise blank + # github.run_id is a unique number for the current run + group: ${{ github.workflow }}-${{ github.actor }}-${{ github.head_ref || github.run_id }} cancel-in-progress: true env: @@ -43,11 +49,58 @@ jobs: if: fromJSON(needs.build-context.outputs.run-docs) uses: ./.github/workflows/reusable-docs.yml + check-abi: + name: 'Check if the ABI has changed' + runs-on: ubuntu-22.04 # 24.04 causes spurious errors + needs: build-context + if: needs.build-context.outputs.run-tests == 'true' + steps: + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + persist-credentials: false + - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0 + with: + python-version: '3.x' + - name: Install dependencies + run: | + sudo ./.github/workflows/posix-deps-apt.sh + sudo apt-get install -yq --no-install-recommends abigail-tools + - name: Build CPython + env: + CFLAGS: -g3 -O0 + run: | + # Build Python with the libpython dynamic library + ./configure --enable-shared + make -j4 + - name: Check for changes in the ABI + id: check + run: | + if ! make check-abidump; then + echo "Generated ABI file is not up to date." + echo "Please add the release manager of this branch as a reviewer of this PR." + echo "" + echo "The up to date ABI file should be attached to this build as an artifact." + echo "" + echo "To learn more about this check: https://devguide.python.org/getting-started/setup-building/index.html#regenerate-the-abi-dump" + echo "" + exit 1 + fi + - name: Generate updated ABI files + if: ${{ failure() && steps.check.conclusion == 'failure' }} + run: | + make regen-abidump + - uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6.0.0 + name: Publish updated ABI files + if: ${{ failure() && steps.check.conclusion == 'failure' }} + with: + name: abi-data + path: ./Doc/data/*.abi + check-autoconf-regen: name: 'Check if Autoconf files are up to date' # Don't use ubuntu-latest but a specific version to make the job # reproducible: to get the same tools versions (autoconf, aclocal, ...) - runs-on: ubuntu-24.04 + runs-on: ubuntu-26.04 container: image: ghcr.io/python/autoconf:2025.01.02.12581854023 timeout-minutes: 60 @@ -58,7 +111,7 @@ jobs: run: | apt update && apt install git -yq git config --global --add safe.directory "$GITHUB_WORKSPACE" - - uses: actions/checkout@v4 + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 with: fetch-depth: 1 persist-credentials: false @@ -90,33 +143,21 @@ jobs: name: 'Check if generated files are up to date' # Don't use ubuntu-latest but a specific version to make the job # reproducible: to get the same tools versions (autoconf, aclocal, ...) - runs-on: ubuntu-24.04 + runs-on: ubuntu-26.04 timeout-minutes: 60 needs: build-context if: needs.build-context.outputs.run-tests == 'true' steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 with: persist-credentials: false - - uses: actions/setup-python@v5 + - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0 with: python-version: '3.x' - name: Runner image version run: echo "IMAGE_OS_VERSION=${ImageOS}-${ImageVersion}" >> "$GITHUB_ENV" - - name: Restore config.cache - uses: actions/cache@v4 - with: - path: config.cache - # Include env.pythonLocation in key to avoid changes in environment when setup-python updates Python - key: ${{ github.job }}-${{ env.IMAGE_OS_VERSION }}-${{ needs.build-context.outputs.config-hash }}-${{ env.pythonLocation }} - name: Install dependencies run: sudo ./.github/workflows/posix-deps-apt.sh - - name: Add ccache to PATH - run: echo "PATH=/usr/lib/ccache:$PATH" >> "$GITHUB_ENV" - - name: Configure ccache action - uses: hendrikmuhs/ccache-action@v1.2 - with: - save: false - name: Configure CPython run: | # Build Python with the libpython dynamic library @@ -124,7 +165,7 @@ jobs: - name: Build CPython run: | make -j4 regen-all - make regen-stdlib-module-names regen-sbom regen-unicodedata + make regen-stdlib-module-names regen-sbom - name: Check for changes run: | git add -u @@ -147,6 +188,14 @@ jobs: if: github.event_name == 'pull_request' # $GITHUB_EVENT_NAME run: make check-c-globals + check-c-api-docs: + name: C API Docs + needs: build-context + if: >- + needs.build-context.outputs.run-tests == 'true' + || needs.build-context.outputs.run-docs == 'true' + uses: ./.github/workflows/reusable-check-c-api-docs.yml + build-windows: name: >- Windows @@ -172,8 +221,8 @@ jobs: free-threading: ${{ matrix.free-threading }} build-windows-msi: - name: >- # ${{ '' } is a hack to nest jobs under the same sidebar category - Windows MSI${{ '' }} + # ${{ '' } is a hack to nest jobs under the same sidebar category. + name: Windows MSI${{ '' }} # zizmor: ignore[obfuscation] needs: build-context if: fromJSON(needs.build-context.outputs.run-windows-msi) strategy: @@ -192,32 +241,23 @@ jobs: macOS ${{ fromJSON(matrix.free-threading) && '(free-threading)' || '' }} needs: build-context - if: needs.build-context.outputs.run-tests == 'true' + if: needs.build-context.outputs.run-macos == 'true' strategy: fail-fast: false matrix: - # Cirrus and macos-14 are M1, macos-13 is default GHA Intel. - # macOS 13 only runs tests against the GIL-enabled CPython. - # Cirrus used for upstream, macos-14 for forks. + # macos-26 is Apple Silicon, macos-26-intel is Intel. + # macos-26-intel only runs tests against the GIL-enabled CPython. os: - - ghcr.io/cirruslabs/macos-runner:sonoma - - macos-14 - - macos-13 - is-fork: # only used for the exclusion trick - - ${{ github.repository_owner != 'python' }} + - macos-26 + - macos-26-intel free-threading: - false - true exclude: - - os: ghcr.io/cirruslabs/macos-runner:sonoma - is-fork: true - - os: macos-14 - is-fork: false - - os: macos-13 + - os: macos-26-intel free-threading: true uses: ./.github/workflows/reusable-macos.yml with: - config_hash: ${{ needs.build-context.outputs.config-hash }} free-threading: ${{ matrix.free-threading }} os: ${{ matrix.os }} @@ -227,7 +267,7 @@ jobs: ${{ fromJSON(matrix.free-threading) && '(free-threading)' || '' }} ${{ fromJSON(matrix.bolt) && '(bolt)' || '' }} needs: build-context - if: needs.build-context.outputs.run-tests == 'true' + if: needs.build-context.outputs.run-ubuntu == 'true' strategy: fail-fast: false matrix: @@ -237,6 +277,8 @@ jobs: free-threading: - false - true + # For BOLT jobs, https://apt.llvm.org/llvm.sh doesn't support LLVM 19 + # on Ubuntu 26.04, so stick to Ubuntu 24.04 until LLVM is upgraded. os: - ubuntu-24.04 - ubuntu-24.04-arm @@ -249,92 +291,145 @@ jobs: bolt: true uses: ./.github/workflows/reusable-ubuntu.yml with: - config_hash: ${{ needs.build-context.outputs.config-hash }} bolt-optimizations: ${{ matrix.bolt }} free-threading: ${{ matrix.free-threading }} os: ${{ matrix.os }} + build-ubuntu-installed: + name: 'Ubuntu (installed)' + needs: build-context + if: needs.build-context.outputs.run-ubuntu == 'true' + uses: ./.github/workflows/reusable-install.yml + build-ubuntu-ssltests: - name: 'Ubuntu SSL tests with OpenSSL' + name: 'Ubuntu SSL tests' runs-on: ${{ matrix.os }} timeout-minutes: 60 needs: build-context - if: needs.build-context.outputs.run-tests == 'true' + if: needs.build-context.outputs.run-ubuntu == 'true' strategy: fail-fast: false matrix: - os: [ubuntu-24.04] - openssl_ver: [3.0.16, 3.1.8, 3.2.4, 3.3.3, 3.4.1] - # See Tools/ssl/make_ssl_data.py for notes on adding a new version + os: [ubuntu-26.04] + ssllib: + # See Tools/ssl/make_ssl_data.py for notes on adding a new version + ## OpenSSL + # Keep 1.1.1w in our list despite it being upstream EOL and otherwise + # unsupported as it most resembles other 1.1.1-work-a-like ssl APIs + # supported by important vendors such as AWS-LC. + - { name: openssl, version: 1.1.1w } + - { name: openssl, version: 3.0.21 } + - { name: openssl, version: 3.4.6 } + - { name: openssl, version: 3.5.7 } + - { name: openssl, version: 3.6.3 } env: - OPENSSL_VER: ${{ matrix.openssl_ver }} + SSLLIB_VER: ${{ matrix.ssllib.version }} MULTISSL_DIR: ${{ github.workspace }}/multissl - OPENSSL_DIR: ${{ github.workspace }}/multissl/openssl/${{ matrix.openssl_ver }} - LD_LIBRARY_PATH: ${{ github.workspace }}/multissl/openssl/${{ matrix.openssl_ver }}/lib + SSLLIB_DIR: ${{ github.workspace }}/multissl/${{ matrix.ssllib.name }}/${{ matrix.ssllib.version }} + LD_LIBRARY_PATH: ${{ github.workspace }}/multissl/${{ matrix.ssllib.name }}/${{ matrix.ssllib.version }}/lib steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 with: persist-credentials: false - name: Runner image version run: echo "IMAGE_OS_VERSION=${ImageOS}-${ImageVersion}" >> "$GITHUB_ENV" - - name: Restore config.cache - uses: actions/cache@v4 - with: - path: config.cache - key: ${{ github.job }}-${{ env.IMAGE_OS_VERSION }}-${{ needs.build-context.outputs.config-hash }} - name: Register gcc problem matcher run: echo "::add-matcher::.github/problem-matchers/gcc.json" - name: Install dependencies run: sudo ./.github/workflows/posix-deps-apt.sh - - name: Configure OpenSSL env vars - run: | - echo "MULTISSL_DIR=${GITHUB_WORKSPACE}/multissl" >> "$GITHUB_ENV" - echo "OPENSSL_DIR=${GITHUB_WORKSPACE}/multissl/openssl/${OPENSSL_VER}" >> "$GITHUB_ENV" - echo "LD_LIBRARY_PATH=${GITHUB_WORKSPACE}/multissl/openssl/${OPENSSL_VER}/lib" >> "$GITHUB_ENV" - - name: 'Restore OpenSSL build' - id: cache-openssl - uses: actions/cache@v4 + - name: 'Restore SSL library build' + id: cache-ssl-lib + uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4 with: - path: ./multissl/openssl/${{ env.OPENSSL_VER }} - key: ${{ matrix.os }}-multissl-openssl-${{ env.OPENSSL_VER }} - - name: Install OpenSSL - if: steps.cache-openssl.outputs.cache-hit != 'true' - run: python3 Tools/ssl/multissltests.py --steps=library --base-directory "$MULTISSL_DIR" --openssl "$OPENSSL_VER" --system Linux - - name: Add ccache to PATH + path: ./multissl/${{ matrix.ssllib.name }}/${{ matrix.ssllib.version }} + key: ${{ matrix.os }}-multissl-${{ matrix.ssllib.name }}-${{ matrix.ssllib.version }} + - name: Install SSL Library + if: steps.cache-ssl-lib.outputs.cache-hit != 'true' run: | - echo "PATH=/usr/lib/ccache:$PATH" >> "$GITHUB_ENV" - - name: Configure ccache action - uses: hendrikmuhs/ccache-action@v1.2 - with: - save: false + python3 Tools/ssl/multissltests.py \ + --steps=library \ + --base-directory "$MULTISSL_DIR" \ + '--${{ matrix.ssllib.name }}' '${{ matrix.ssllib.version }}' \ + --system Linux - name: Configure CPython - run: ./configure CFLAGS="-fdiagnostics-format=json" --config-cache --enable-slower-safety --with-pydebug --with-openssl="$OPENSSL_DIR" + run: | + ./configure CFLAGS="-fdiagnostics-format=json" \ + --config-cache \ + --enable-slower-safety \ + --with-pydebug \ + --with-openssl="$SSLLIB_DIR" \ + --with-builtin-hashlib-hashes=blake2 \ + --with-ssl-default-suites=openssl - name: Build CPython run: make -j4 - name: Display build info run: make pythoninfo + - name: Verify python is linked to the right lib + run: | + ./python -c 'import ssl; print(ssl.OPENSSL_VERSION)' \ + | grep -iE '${{ matrix.ssllib.name }}.*${{ matrix.ssllib.version }}' - name: SSL tests run: ./python Lib/test/ssltests.py + build-android: + name: Android (${{ matrix.arch }}) + needs: build-context + if: needs.build-context.outputs.run-android == 'true' + timeout-minutes: 60 + strategy: + fail-fast: false + matrix: + include: + - arch: aarch64 + runs-on: macos-26 + - arch: x86_64 + runs-on: ubuntu-26.04 + + runs-on: ${{ matrix.runs-on }} + steps: + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + persist-credentials: false + - name: Build and test + run: ./Android/android.py ci --fast-ci ${{ matrix.arch }}-linux-android + + build-ios: + name: iOS + needs: build-context + if: needs.build-context.outputs.run-ios == 'true' + timeout-minutes: 60 + runs-on: macos-26 + steps: + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + persist-credentials: false + + - name: Build and test + run: python3 Apple ci iOS --fast-ci + + build-emscripten: + name: 'Emscripten' + needs: build-context + if: needs.build-context.outputs.run-emscripten == 'true' + uses: ./.github/workflows/reusable-emscripten.yml + build-wasi: name: 'WASI' needs: build-context - if: needs.build-context.outputs.run-tests == 'true' + if: needs.build-context.outputs.run-wasi == 'true' uses: ./.github/workflows/reusable-wasi.yml - with: - config_hash: ${{ needs.build-context.outputs.config-hash }} test-hypothesis: name: "Hypothesis tests on Ubuntu" - runs-on: ubuntu-24.04 + runs-on: ubuntu-26.04 timeout-minutes: 60 needs: build-context - if: needs.build-context.outputs.run-tests == 'true' + if: needs.build-context.outputs.run-ubuntu == 'true' env: - OPENSSL_VER: 3.0.16 + OPENSSL_VER: 3.5.7 PYTHONSTRICTEXTENSIONBUILD: 1 steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 with: persist-credentials: false - name: Register gcc problem matcher @@ -348,20 +443,13 @@ jobs: echo "LD_LIBRARY_PATH=${GITHUB_WORKSPACE}/multissl/openssl/${OPENSSL_VER}/lib" >> "$GITHUB_ENV" - name: 'Restore OpenSSL build' id: cache-openssl - uses: actions/cache@v4 + uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4 with: path: ./multissl/openssl/${{ env.OPENSSL_VER }} key: ${{ runner.os }}-multissl-openssl-${{ env.OPENSSL_VER }} - name: Install OpenSSL if: steps.cache-openssl.outputs.cache-hit != 'true' run: python3 Tools/ssl/multissltests.py --steps=library --base-directory "$MULTISSL_DIR" --openssl "$OPENSSL_VER" --system Linux - - name: Add ccache to PATH - run: | - echo "PATH=/usr/lib/ccache:$PATH" >> "$GITHUB_ENV" - - name: Configure ccache action - uses: hendrikmuhs/ccache-action@v1.2 - with: - save: false - name: Setup directory envs for out-of-tree builds run: | echo "CPYTHON_RO_SRCDIR=$(realpath -m "${GITHUB_WORKSPACE}"/../cpython-ro-srcdir)" >> "$GITHUB_ENV" @@ -372,11 +460,6 @@ jobs: run: sudo mount --bind -o ro "$GITHUB_WORKSPACE" "$CPYTHON_RO_SRCDIR" - name: Runner image version run: echo "IMAGE_OS_VERSION=${ImageOS}-${ImageVersion}" >> "$GITHUB_ENV" - - name: Restore config.cache - uses: actions/cache@v4 - with: - path: ${{ env.CPYTHON_BUILDDIR }}/config.cache - key: ${{ github.job }}-${{ env.IMAGE_OS_VERSION }}-${{ needs.build-context.outputs.config-hash }} - name: Configure CPython out-of-tree working-directory: ${{ env.CPYTHON_BUILDDIR }} run: | @@ -407,7 +490,7 @@ jobs: ./python -m venv "$VENV_LOC" && "$VENV_PYTHON" -m pip install -r "${GITHUB_WORKSPACE}/Tools/requirements-hypothesis.txt" - name: 'Restore Hypothesis database' id: cache-hypothesis-database - uses: actions/cache@v4 + uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4 with: path: ${{ env.CPYTHON_BUILDDIR }}/.hypothesis/ key: hypothesis-database-${{ github.head_ref || github.run_id }} @@ -434,7 +517,7 @@ jobs: -x test_subprocess \ -x test_signal \ -x test_sysconfig - - uses: actions/upload-artifact@v4 + - uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6.0.0 if: always() with: name: hypothesis-example-db @@ -445,34 +528,25 @@ jobs: runs-on: ${{ matrix.os }} timeout-minutes: 60 needs: build-context - if: needs.build-context.outputs.run-tests == 'true' + if: needs.build-context.outputs.run-ubuntu == 'true' strategy: fail-fast: false matrix: - os: [ubuntu-24.04] + os: [ubuntu-26.04] env: - OPENSSL_VER: 3.0.16 + OPENSSL_VER: 3.5.7 PYTHONSTRICTEXTENSIONBUILD: 1 ASAN_OPTIONS: detect_leaks=0:allocator_may_return_null=1:handle_segv=0 steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 with: persist-credentials: false - name: Runner image version run: echo "IMAGE_OS_VERSION=${ImageOS}-${ImageVersion}" >> "$GITHUB_ENV" - - name: Restore config.cache - uses: actions/cache@v4 - with: - path: config.cache - key: ${{ github.job }}-${{ env.IMAGE_OS_VERSION }}-${{ needs.build-context.outputs.config-hash }} - name: Register gcc problem matcher run: echo "::add-matcher::.github/problem-matchers/gcc.json" - name: Install dependencies run: sudo ./.github/workflows/posix-deps-apt.sh - - name: Set up GCC-10 for ASAN - uses: egor-tensin/setup-gcc@v1 - with: - version: 10 - name: Configure OpenSSL env vars run: | echo "MULTISSL_DIR=${GITHUB_WORKSPACE}/multissl" >> "$GITHUB_ENV" @@ -480,21 +554,13 @@ jobs: echo "LD_LIBRARY_PATH=${GITHUB_WORKSPACE}/multissl/openssl/${OPENSSL_VER}/lib" >> "$GITHUB_ENV" - name: 'Restore OpenSSL build' id: cache-openssl - uses: actions/cache@v4 + uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4 with: path: ./multissl/openssl/${{ env.OPENSSL_VER }} key: ${{ matrix.os }}-multissl-openssl-${{ env.OPENSSL_VER }} - name: Install OpenSSL if: steps.cache-openssl.outputs.cache-hit != 'true' run: python3 Tools/ssl/multissltests.py --steps=library --base-directory "$MULTISSL_DIR" --openssl "$OPENSSL_VER" --system Linux - - name: Add ccache to PATH - run: | - echo "PATH=/usr/lib/ccache:$PATH" >> "$GITHUB_ENV" - - name: Configure ccache action - uses: hendrikmuhs/ccache-action@v1.2 - with: - save: ${{ github.event_name == 'push' }} - max-size: "200M" - name: Configure CPython run: ./configure --config-cache --with-address-sanitizer --without-pymalloc - name: Build CPython @@ -504,40 +570,42 @@ jobs: - name: Tests run: xvfb-run make ci - build-tsan: - name: >- - Thread sanitizer - ${{ fromJSON(matrix.free-threading) && '(free-threading)' || '' }} + build-san: + # ${{ '' } is a hack to nest jobs under the same sidebar category. + name: Sanitizers${{ '' }} # zizmor: ignore[obfuscation] needs: build-context - if: needs.build-context.outputs.run-tests == 'true' + if: needs.build-context.outputs.run-ubuntu == 'true' strategy: fail-fast: false matrix: + check-name: + - Thread free-threading: - false - true - uses: ./.github/workflows/reusable-tsan.yml + sanitizer: + - TSan + include: + - check-name: Undefined behavior + sanitizer: UBSan + free-threading: false + uses: ./.github/workflows/reusable-san.yml with: - config_hash: ${{ needs.build-context.outputs.config-hash }} + sanitizer: ${{ matrix.sanitizer }} free-threading: ${{ matrix.free-threading }} cross-build-linux: name: Cross build Linux - runs-on: ubuntu-latest + runs-on: ubuntu-26.04 timeout-minutes: 60 needs: build-context - if: needs.build-context.outputs.run-tests == 'true' + if: needs.build-context.outputs.run-ubuntu == 'true' steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 with: persist-credentials: false - name: Runner image version run: echo "IMAGE_OS_VERSION=${ImageOS}-${ImageVersion}" >> "$GITHUB_ENV" - - name: Restore config.cache - uses: actions/cache@v4 - with: - path: config.cache - key: ${{ github.job }}-${{ env.IMAGE_OS_VERSION }}-${{ needs.build-context.outputs.config-hash }} - name: Register gcc problem matcher run: echo "::add-matcher::.github/problem-matchers/gcc.json" - name: Set build dir @@ -557,49 +625,56 @@ jobs: run: ./configure --prefix="$BUILD_DIR/cross-python" --with-build-python="$BUILD_DIR/host-python/bin/python3" - name: Install cross Python run: make -j8 install + - name: Display build info + run: | + "$BUILD_DIR/cross-python/bin/python3" -m test.pythoninfo - name: Run test subset with host build run: | "$BUILD_DIR/cross-python/bin/python3" -m test test_sysconfig test_site test_embed - # CIFuzz job based on https://google.github.io/oss-fuzz/getting-started/continuous-integration/ cifuzz: - name: CIFuzz - runs-on: ubuntu-latest - timeout-minutes: 60 + # ${{ '' } is a hack to nest jobs under the same sidebar category. + name: CIFuzz${{ '' }} # zizmor: ignore[obfuscation] needs: build-context - if: needs.build-context.outputs.run-ci-fuzz == 'true' + if: >- + needs.build-context.outputs.run-ci-fuzz == 'true' + || needs.build-context.outputs.run-ci-fuzz-stdlib == 'true' permissions: + contents: read security-events: write strategy: fail-fast: false matrix: - sanitizer: [address, undefined, memory] - steps: - - name: Build fuzzers (${{ matrix.sanitizer }}) - id: build - uses: google/oss-fuzz/infra/cifuzz/actions/build_fuzzers@master - with: - oss-fuzz-project-name: cpython3 - sanitizer: ${{ matrix.sanitizer }} - - name: Run fuzzers (${{ matrix.sanitizer }}) - uses: google/oss-fuzz/infra/cifuzz/actions/run_fuzzers@master - with: - fuzz-seconds: 600 - oss-fuzz-project-name: cpython3 - output-sarif: true - sanitizer: ${{ matrix.sanitizer }} - - name: Upload crash - if: failure() && steps.build.outcome == 'success' - uses: actions/upload-artifact@v4 - with: - name: ${{ matrix.sanitizer }}-artifacts - path: ./out/artifacts - - name: Upload SARIF - if: always() && steps.build.outcome == 'success' - uses: github/codeql-action/upload-sarif@v3 - with: - sarif_file: cifuzz-sarif/results.sarif - checkout_path: cifuzz-sarif + sanitizer: + - address + oss-fuzz-project-name: + - cpython3 + - python3-libraries + include: + - sanitizer: undefined + oss-fuzz-project-name: cpython3 + - sanitizer: memory + oss-fuzz-project-name: cpython3 + exclude: + # Note that the 'no-exclude' sentinel below is to prevent + # an empty string value from excluding all jobs and causing + # GHA to create a 'default' matrix entry with all empty values. + - oss-fuzz-project-name: >- + ${{ + needs.build-context.outputs.run-ci-fuzz == 'true' + && 'no-exclude' + || 'cpython3' + }} + - oss-fuzz-project-name: >- + ${{ + needs.build-context.outputs.run-ci-fuzz-stdlib == 'true' + && 'no-exclude' + || 'python3-libraries' + }} + uses: ./.github/workflows/reusable-cifuzz.yml + with: + oss-fuzz-project-name: ${{ matrix.oss-fuzz-project-name }} + sanitizer: ${{ matrix.sanitizer }} all-required-green: # This job does nothing and is only used for the branch protection name: All required checks pass @@ -610,15 +685,19 @@ jobs: - check-docs - check-autoconf-regen - check-generated-files + - check-c-api-docs - build-windows - build-windows-msi - build-macos - build-ubuntu + - build-ubuntu-installed - build-ubuntu-ssltests + - build-ios + - build-emscripten - build-wasi - test-hypothesis - build-asan - - build-tsan + - build-san - cross-build-linux - cifuzz if: always() @@ -628,46 +707,51 @@ jobs: uses: re-actors/alls-green@05ac9388f0aebcb5727afa17fcccfecd6f8ec5fe with: allowed-failures: >- + build-android, + build-emscripten, build-windows-msi, build-ubuntu-ssltests, test-hypothesis, cifuzz, allowed-skips: >- - ${{ - !fromJSON(needs.build-context.outputs.run-docs) - && ' - check-docs, - ' - || '' - }} + ${{ !fromJSON(needs.build-context.outputs.run-docs) && 'check-docs,' || '' }} ${{ needs.build-context.outputs.run-tests != 'true' && ' check-autoconf-regen, check-generated-files, - build-macos, - build-ubuntu, - build-ubuntu-ssltests, - build-wasi, - test-hypothesis, - build-asan, - build-tsan, - cross-build-linux, ' || '' }} ${{ - !fromJSON(needs.build-context.outputs.run-windows-tests) - && ' - build-windows, - ' + !fromJSON(needs.build-context.outputs.run-tests) + && !fromJSON(needs.build-context.outputs.run-docs) + && 'check-c-api-docs,' || '' }} + ${{ !fromJSON(needs.build-context.outputs.run-windows-tests) && 'build-windows,' || '' }} ${{ !fromJSON(needs.build-context.outputs.run-ci-fuzz) + && !fromJSON(needs.build-context.outputs.run-ci-fuzz-stdlib) + && 'cifuzz,' || + '' + }} + ${{ !fromJSON(needs.build-context.outputs.run-macos) && 'build-macos,' || '' }} + ${{ + !fromJSON(needs.build-context.outputs.run-ubuntu) && ' - cifuzz, + build-ubuntu, + build-ubuntu-installed, + build-ubuntu-ssltests, + test-hypothesis, + build-asan, + build-san, + cross-build-linux, ' || '' }} + ${{ !fromJSON(needs.build-context.outputs.run-android) && 'build-android,' || '' }} + ${{ !fromJSON(needs.build-context.outputs.run-ios) && 'build-ios,' || '' }} + ${{ !fromJSON(needs.build-context.outputs.run-emscripten) && 'build-emscripten,' || '' }} + ${{ !fromJSON(needs.build-context.outputs.run-wasi) && 'build-wasi,' || '' }} jobs: ${{ toJSON(needs) }} diff --git a/.github/workflows/documentation-links.yml b/.github/workflows/documentation-links.yml deleted file mode 100644 index a09a30587b35eb..00000000000000 --- a/.github/workflows/documentation-links.yml +++ /dev/null @@ -1,28 +0,0 @@ -name: Read the Docs PR preview -# Automatically edits a pull request's descriptions with a link -# to the documentation's preview on Read the Docs. - -on: - pull_request_target: - types: - - opened - paths: - - 'Doc/**' - - '.github/workflows/doc.yml' - -concurrency: - group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }} - cancel-in-progress: true - -jobs: - documentation-links: - runs-on: ubuntu-latest - permissions: - pull-requests: write - timeout-minutes: 5 - - steps: - - uses: readthedocs/actions/preview@v1 - with: - project-slug: "cpython-previews" - single-version: "true" diff --git a/.github/workflows/jit.yml b/.github/workflows/jit.yml index 116e0c1e945e38..27846f8843e792 100644 --- a/.github/workflows/jit.yml +++ b/.github/workflows/jit.yml @@ -1,7 +1,7 @@ name: JIT on: pull_request: - paths: + paths: &paths - '**jit**' - 'Python/bytecodes.c' - 'Python/optimizer*.c' @@ -9,13 +9,7 @@ on: - '!**/*.md' - '!**/*.ini' push: - paths: - - '**jit**' - - 'Python/bytecodes.c' - - 'Python/optimizer*.c' - - '!Python/perf_jit_trampoline.c' - - '!**/*.md' - - '!**/*.ini' + paths: *paths workflow_dispatch: permissions: @@ -27,14 +21,15 @@ concurrency: env: FORCE_COLOR: 1 + LLVM_VERSION: 19 jobs: interpreter: name: Interpreter (Debug) - runs-on: ubuntu-24.04 - timeout-minutes: 90 + runs-on: ubuntu-26.04 + timeout-minutes: 60 steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 with: persist-credentials: false - name: Build tier two interpreter @@ -44,11 +39,12 @@ jobs: - name: Test tier two interpreter run: | ./python -m test --multiprocess 0 --timeout 4500 --verbose2 --verbose3 - jit: + + windows: name: ${{ matrix.target }} (${{ matrix.debug && 'Debug' || 'Release' }}) - needs: interpreter + runs-on: ${{ matrix.runner }} - timeout-minutes: 90 + timeout-minutes: 60 strategy: fail-fast: false matrix: @@ -56,100 +52,151 @@ jobs: - i686-pc-windows-msvc/msvc - x86_64-pc-windows-msvc/msvc - aarch64-pc-windows-msvc/msvc - - x86_64-apple-darwin/clang - - aarch64-apple-darwin/clang - - x86_64-unknown-linux-gnu/gcc - - aarch64-unknown-linux-gnu/gcc debug: - true - false - llvm: - - 19 include: - target: i686-pc-windows-msvc/msvc architecture: Win32 - runner: windows-latest + runner: windows-2022 - target: x86_64-pc-windows-msvc/msvc architecture: x64 - runner: windows-latest + runner: windows-2022 - target: aarch64-pc-windows-msvc/msvc architecture: ARM64 runner: windows-11-arm - - target: x86_64-apple-darwin/clang - architecture: x86_64 - runner: macos-13 - - target: aarch64-apple-darwin/clang - architecture: aarch64 - runner: macos-14 - - target: x86_64-unknown-linux-gnu/gcc - architecture: x86_64 - runner: ubuntu-24.04 - - target: aarch64-unknown-linux-gnu/gcc - architecture: aarch64 - runner: ubuntu-24.04-arm steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 with: persist-credentials: false - - uses: actions/setup-python@v5 + - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0 with: python-version: '3.11' - # PCbuild downloads LLVM automatically: - - name: Windows - if: runner.os == 'Windows' + - name: Build run: | ./PCbuild/build.bat --experimental-jit ${{ matrix.debug && '-d' || '' }} -p ${{ matrix.architecture }} + - name: Test + run: | ./PCbuild/rt.bat ${{ matrix.debug && '-d' || '' }} -p ${{ matrix.architecture }} -q --multiprocess 0 --timeout 4500 --verbose2 --verbose3 - # The `find` line is required as a result of https://github.com/actions/runner-images/issues/9966. - # This is a bug in the macOS runner image where the pre-installed Python is installed in the same - # directory as the Homebrew Python, which causes the build to fail for macos-13. This line removes - # the symlink to the pre-installed Python so that the Homebrew Python is used instead. - - name: macOS - if: runner.os == 'macOS' + macos: + name: ${{ matrix.target }} (${{ matrix.debug && 'Debug' || 'Release' }}) + + runs-on: ${{ matrix.runner }} + timeout-minutes: 60 + strategy: + fail-fast: false + matrix: + target: + - x86_64-apple-darwin/clang + - aarch64-apple-darwin/clang + debug: + - true + - false + include: + - target: x86_64-apple-darwin/clang + runner: macos-26-intel + - target: aarch64-apple-darwin/clang + runner: macos-26 + steps: + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + persist-credentials: false + - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0 + with: + python-version: '3.11' + - name: Install LLVM run: | brew update - find /usr/local/bin -lname '*/Library/Frameworks/Python.framework/*' -delete - brew install llvm@${{ matrix.llvm }} + brew install llvm@${{ env.LLVM_VERSION }} + - name: Build + run: | export SDKROOT="$(xcrun --show-sdk-path)" + # Set MACOSX_DEPLOYMENT_TARGET and -Werror=unguarded-availability to + # make sure we don't break downstream distributors (like uv): + export CFLAGS_JIT='-Werror=unguarded-availability' + export MACOSX_DEPLOYMENT_TARGET=10.15 ./configure --enable-experimental-jit --enable-universalsdk --with-universal-archs=universal2 ${{ matrix.debug && '--with-pydebug' || '' }} make all --jobs 4 + - name: Test + run: | ./python.exe -m test --multiprocess 0 --timeout 4500 --verbose2 --verbose3 - - name: Linux - if: runner.os == 'Linux' + linux: + name: ${{ matrix.target }} (${{ matrix.debug && 'Debug' || 'Release' }}) + + runs-on: ${{ matrix.runner }} + timeout-minutes: 60 + strategy: + fail-fast: false + matrix: + target: + - x86_64-unknown-linux-gnu/gcc + - aarch64-unknown-linux-gnu/gcc + debug: + - true + - false + include: + # https://apt.llvm.org/llvm.sh doesn't support LLVM 19 + # on Ubuntu 26.04, so stick to Ubuntu 24.04 until LLVM is upgraded. + - target: x86_64-unknown-linux-gnu/gcc + runner: ubuntu-24.04 + - target: aarch64-unknown-linux-gnu/gcc + runner: ubuntu-24.04-arm + steps: + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + persist-credentials: false + - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0 + with: + python-version: '3.11' + - name: Build run: | - sudo bash -c "$(wget -O - https://apt.llvm.org/llvm.sh)" ./llvm.sh ${{ matrix.llvm }} - export PATH="$(llvm-config-${{ matrix.llvm }} --bindir):$PATH" + sudo bash -c "$(wget -O - https://apt.llvm.org/llvm.sh)" ./llvm.sh ${{ env.LLVM_VERSION }} + export PATH="$(llvm-config-${{ env.LLVM_VERSION }} --bindir):$PATH" ./configure --enable-experimental-jit ${{ matrix.debug && '--with-pydebug' || '' }} make all --jobs 4 + - name: Test + run: | ./python -m test --multiprocess 0 --timeout 4500 --verbose2 --verbose3 - # XXX: GH-133171 - # jit-with-disabled-gil: - # name: Free-Threaded (Debug) - # needs: interpreter - # runs-on: ubuntu-24.04 - # timeout-minutes: 90 - # strategy: - # fail-fast: false - # matrix: - # llvm: - # - 19 - # steps: - # - uses: actions/checkout@v4 - # with: - # persist-credentials: false - # - uses: actions/setup-python@v5 - # with: - # python-version: '3.11' - # - name: Build with JIT enabled and GIL disabled - # run: | - # sudo bash -c "$(wget -O - https://apt.llvm.org/llvm.sh)" ./llvm.sh ${{ matrix.llvm }} - # export PATH="$(llvm-config-${{ matrix.llvm }} --bindir):$PATH" - # ./configure --enable-experimental-jit --with-pydebug --disable-gil - # make all --jobs 4 - # - name: Run tests - # run: | - # ./python -m test --multiprocess 0 --timeout 4500 --verbose2 --verbose3 + linux-extras: + name: ${{ matrix.name }} + + # https://apt.llvm.org/llvm.sh doesn't support LLVM 19 on Ubuntu 26.04, + # so stick to Ubuntu 24.04 until LLVM is upgraded. + runs-on: ubuntu-24.04 + timeout-minutes: 60 + strategy: + fail-fast: false + matrix: + include: + + - name: JIT without optimizations (Debug) + configure_flags: --enable-experimental-jit --with-pydebug + test_env: "PYTHON_UOPS_OPTIMIZE=0" + - name: JIT with tail calling interpreter + configure_flags: --enable-experimental-jit --with-tail-call-interp --with-pydebug + use_clang: true + run_tests: false + steps: + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + persist-credentials: false + - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0 + with: + python-version: '3.11' + - name: Build + run: | + sudo bash -c "$(wget -O - https://apt.llvm.org/llvm.sh)" ./llvm.sh ${{ env.LLVM_VERSION }} + export PATH="$(llvm-config-${{ env.LLVM_VERSION }} --bindir):$PATH" + if [ "${{ matrix.use_clang }}" = "true" ]; then + export CC=clang-${{ env.LLVM_VERSION }} + fi + ./configure ${{ matrix.configure_flags }} + make all --jobs 4 + - name: Test + if: matrix.run_tests != false + run: | + ${{ matrix.test_env }} ./python -m test --multiprocess 0 --timeout 4500 --verbose2 --verbose3 diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml index d74ce8fcc256dc..e9a4eb2b0808cb 100644 --- a/.github/workflows/lint.yml +++ b/.github/workflows/lint.yml @@ -19,10 +19,7 @@ jobs: timeout-minutes: 10 steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 with: persist-credentials: false - - uses: actions/setup-python@v5 - with: - python-version: "3.x" - - uses: pre-commit/action@v3.0.1 + - uses: j178/prek-action@0bb87d7f00b0c99306c8bcb8b8beba1eb581c037 # v1.1.1 diff --git a/.github/workflows/mypy.yml b/.github/workflows/mypy.yml index 908daaf3a6019a..bbcd57eedf2643 100644 --- a/.github/workflows/mypy.yml +++ b/.github/workflows/mypy.yml @@ -13,13 +13,24 @@ on: - "Lib/test/libregrtest/**" - "Lib/tomllib/**" - "Misc/mypy/**" + - "Tools/build/check_extension_modules.py" + - "Tools/build/check_warnings.py" + - "Tools/build/compute-changes.py" + - "Tools/build/deepfreeze.py" + - "Tools/build/generate-build-details.py" + - "Tools/build/generate_levenshtein_examples.py" - "Tools/build/generate_sbom.py" + - "Tools/build/generate_stdlib_module_names.py" + - "Tools/build/mypy.ini" + - "Tools/build/umarshal.py" + - "Tools/build/update_file.py" + - "Tools/build/verify_ensurepip_wheels.py" - "Tools/cases_generator/**" + - "Tools/check-c-api-docs/**" - "Tools/clinic/**" - "Tools/jit/**" - "Tools/peg_generator/**" - "Tools/requirements-dev.txt" - - "Tools/wasm/**" workflow_dispatch: permissions: @@ -48,20 +59,20 @@ jobs: "Lib/tomllib", "Tools/build", "Tools/cases_generator", + "Tools/check-c-api-docs", "Tools/clinic", "Tools/jit", "Tools/peg_generator", - "Tools/wasm", ] steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 with: persist-credentials: false - - uses: actions/setup-python@v5 + - uses: astral-sh/setup-uv@08807647e7069bb48b6ef5acd8ec9567f424441b # v8.1.0 with: python-version: "3.13" - cache: pip - cache-dependency-path: Tools/requirements-dev.txt - - run: pip install -r Tools/requirements-dev.txt + activate-environment: true + cache-dependency-glob: Tools/requirements-dev.txt + - run: uv pip install -r Tools/requirements-dev.txt - run: python3 Misc/mypy/make_symlinks.py --symlink - - run: mypy --config-file ${{ matrix.target }}/mypy.ini + - run: mypy --num-workers 4 --config-file ${{ matrix.target }}/mypy.ini diff --git a/.github/workflows/new-bugs-announce-notifier.yml b/.github/workflows/new-bugs-announce-notifier.yml index 9f1a8a824e5f19..ea175ed20d1e7b 100644 --- a/.github/workflows/new-bugs-announce-notifier.yml +++ b/.github/workflows/new-bugs-announce-notifier.yml @@ -6,19 +6,21 @@ on: - opened permissions: - issues: read + contents: read jobs: notify-new-bugs-announce: - runs-on: ubuntu-latest + runs-on: ubuntu-slim + permissions: + issues: read timeout-minutes: 10 steps: - - uses: actions/setup-node@v4 + - uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0 with: node-version: 20 - run: npm install mailgun.js form-data - name: Send notification - uses: actions/github-script@v7 + uses: actions/github-script@ed597411d8f924073f98dfc5c65a23a2325f34cd # v8.0.0 env: MAILGUN_API_KEY: ${{ secrets.MAILGUN_PYTHON_ORG_MAILGUN_KEY }} with: diff --git a/.github/workflows/posix-deps-apt.sh b/.github/workflows/posix-deps-apt.sh index d5538cd9367ec6..3b3d90e198360e 100755 --- a/.github/workflows/posix-deps-apt.sh +++ b/.github/workflows/posix-deps-apt.sh @@ -1,24 +1,23 @@ #!/bin/sh apt-get update -apt-get -yq install \ +apt-get -yq --no-install-recommends install \ build-essential \ pkg-config \ - ccache \ + curl \ gdb \ lcov \ libb2-dev \ libbz2-dev \ libffi-dev \ - libgdbm-dev \ libgdbm-compat-dev \ + libgdbm-dev \ liblzma-dev \ libncurses5-dev \ libreadline6-dev \ libsqlite3-dev \ libssl-dev \ - lzma \ - lzma-dev \ + libzstd-dev \ strace \ tk-dev \ uuid-dev \ diff --git a/.github/workflows/project-updater.yml b/.github/workflows/project-updater.yml index 1d9d637ec848a6..710424a28f2824 100644 --- a/.github/workflows/project-updater.yml +++ b/.github/workflows/project-updater.yml @@ -24,7 +24,7 @@ jobs: - { project: 32, label: sprint } steps: - - uses: actions/add-to-project@v1.0.0 + - uses: actions/add-to-project@244f685bbc3b7adfa8466e08b698b5577571133e # v1.0.2 with: project-url: https://github.com/orgs/python/projects/${{ matrix.project }} github-token: ${{ secrets.ADD_TO_PROJECT_PAT }} diff --git a/.github/workflows/regen-abidump.sh b/.github/workflows/regen-abidump.sh index 251bb3857ecfcb..75a1a72e370202 100644 --- a/.github/workflows/regen-abidump.sh +++ b/.github/workflows/regen-abidump.sh @@ -2,7 +2,7 @@ set -ex export DEBIAN_FRONTEND=noninteractive ./.github/workflows/posix-deps-apt.sh -apt-get install -yq abigail-tools python3 +apt-get install -yq --no-install-recommends abigail-tools python3 export CFLAGS="-g3 -O0" ./configure --enable-shared && make make regen-abidump diff --git a/.github/workflows/require-pr-label.yml b/.github/workflows/require-pr-label.yml index 7e534c58c798d1..8af254c10786e1 100644 --- a/.github/workflows/require-pr-label.yml +++ b/.github/workflows/require-pr-label.yml @@ -4,18 +4,21 @@ on: pull_request: types: [opened, reopened, labeled, unlabeled, synchronize] +permissions: + contents: read + jobs: label-dnm: name: DO-NOT-MERGE if: github.repository_owner == 'python' - runs-on: ubuntu-latest + runs-on: ubuntu-slim permissions: pull-requests: read timeout-minutes: 10 steps: - name: Check there's no DO-NOT-MERGE - uses: mheap/github-action-required-labels@v5 + uses: mheap/github-action-required-labels@0ac283b4e65c1fb28ce6079dea5546ceca98ccbe # v5.5.2 with: mode: exactly count: 0 @@ -25,7 +28,7 @@ jobs: label-reviews: name: Unresolved review if: github.repository_owner == 'python' - runs-on: ubuntu-latest + runs-on: ubuntu-slim permissions: pull-requests: read timeout-minutes: 10 @@ -33,7 +36,7 @@ jobs: steps: # Check that the PR is not awaiting changes from the author due to previous review. - name: Check there's no required changes - uses: mheap/github-action-required-labels@v5 + uses: mheap/github-action-required-labels@0ac283b4e65c1fb28ce6079dea5546ceca98ccbe # v5.5.2 with: mode: exactly count: 0 @@ -42,7 +45,7 @@ jobs: awaiting change review - id: is-feature name: Check whether this PR is a feature (contains a "type-feature" label) - uses: mheap/github-action-required-labels@v5 + uses: mheap/github-action-required-labels@0ac283b4e65c1fb28ce6079dea5546ceca98ccbe # v5.5.2 with: mode: exactly count: 1 @@ -53,7 +56,7 @@ jobs: - id: awaiting-merge if: steps.is-feature.outputs.status == 'success' name: Check for complete review - uses: mheap/github-action-required-labels@v5 + uses: mheap/github-action-required-labels@0ac283b4e65c1fb28ce6079dea5546ceca98ccbe # v5.5.2 with: mode: exactly count: 1 diff --git a/.github/workflows/reusable-check-c-api-docs.yml b/.github/workflows/reusable-check-c-api-docs.yml new file mode 100644 index 00000000000000..db030c80008b1e --- /dev/null +++ b/.github/workflows/reusable-check-c-api-docs.yml @@ -0,0 +1,25 @@ +name: Reusable C API Docs Check + +on: + workflow_call: + +permissions: + contents: read + +env: + FORCE_COLOR: 1 + +jobs: + check-c-api-docs: + name: 'Check if all C APIs are documented' + runs-on: ubuntu-latest + timeout-minutes: 5 + steps: + - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 + with: + persist-credentials: false + - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0 + with: + python-version: '3.x' + - name: Check for undocumented C APIs + run: python Tools/check-c-api-docs/main.py diff --git a/.github/workflows/reusable-cifuzz.yml b/.github/workflows/reusable-cifuzz.yml new file mode 100644 index 00000000000000..9b49e7fd26f007 --- /dev/null +++ b/.github/workflows/reusable-cifuzz.yml @@ -0,0 +1,49 @@ +# CIFuzz job based on https://google.github.io/oss-fuzz/getting-started/continuous-integration/ +name: Reusable CIFuzz + +on: + workflow_call: + inputs: + oss-fuzz-project-name: + description: OSS-Fuzz project name + required: true + type: string + sanitizer: + description: OSS-Fuzz sanitizer + required: true + type: string + +permissions: + contents: read + +jobs: + cifuzz: + name: ${{ inputs.oss-fuzz-project-name }} (${{ inputs.sanitizer }}) + runs-on: ubuntu-latest + timeout-minutes: 60 + steps: + - name: Build fuzzers (${{ inputs.sanitizer }}) + id: build + uses: google/oss-fuzz/infra/cifuzz/actions/build_fuzzers@ed23f8af80ff82b25ca67cd9b101e690b8897b3f # master + with: + oss-fuzz-project-name: ${{ inputs.oss-fuzz-project-name }} + sanitizer: ${{ inputs.sanitizer }} + - name: Run fuzzers (${{ inputs.sanitizer }}) + uses: google/oss-fuzz/infra/cifuzz/actions/run_fuzzers@ed23f8af80ff82b25ca67cd9b101e690b8897b3f # master + with: + fuzz-seconds: 600 + oss-fuzz-project-name: ${{ inputs.oss-fuzz-project-name }} + output-sarif: true + sanitizer: ${{ inputs.sanitizer }} + - name: Upload crash + if: failure() && steps.build.outcome == 'success' + uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6.0.0 + with: + name: ${{ inputs.sanitizer }}-artifacts + path: ./out/artifacts + - name: Upload SARIF + if: always() && steps.build.outcome == 'success' + uses: github/codeql-action/upload-sarif@c10b8064de6f491fea524254123dbe5e09572f13 # v4.35.1 + with: + sarif_file: cifuzz-sarif/results.sarif + checkout_path: cifuzz-sarif diff --git a/.github/workflows/reusable-context.yml b/.github/workflows/reusable-context.yml index 73dc254edc5fbc..08c31981d47208 100644 --- a/.github/workflows/reusable-context.yml +++ b/.github/workflows/reusable-context.yml @@ -17,24 +17,45 @@ on: # yamllint disable-line rule:truthy # || 'falsy-branch' # }} # - config-hash: - description: Config hash value for use in cache keys - value: ${{ jobs.compute-changes.outputs.config-hash }} # str + run-android: + description: Whether to run the Android tests + value: ${{ jobs.compute-changes.outputs.run-android }} # bool + run-ci-fuzz: + description: Whether to run the CIFuzz job for 'cpython' fuzzer + value: ${{ jobs.compute-changes.outputs.run-ci-fuzz }} # bool + run-ci-fuzz-stdlib: + description: Whether to run the CIFuzz job for 'python3-libraries' fuzzer + value: ${{ jobs.compute-changes.outputs.run-ci-fuzz-stdlib }} # bool run-docs: description: Whether to build the docs value: ${{ jobs.compute-changes.outputs.run-docs }} # bool + run-ios: + description: Whether to run the iOS tests + value: ${{ jobs.compute-changes.outputs.run-ios }} # bool + run-macos: + description: Whether to run the macOS tests + value: ${{ jobs.compute-changes.outputs.run-macos }} # bool run-tests: description: Whether to run the regular tests value: ${{ jobs.compute-changes.outputs.run-tests }} # bool - run-windows-tests: - description: Whether to run the Windows tests - value: ${{ jobs.compute-changes.outputs.run-windows-tests }} # bool + run-ubuntu: + description: Whether to run the Ubuntu tests + value: ${{ jobs.compute-changes.outputs.run-ubuntu }} # bool + run-emscripten: + description: Whether to run the Emscripten tests + value: ${{ jobs.compute-changes.outputs.run-emscripten }} # bool + run-wasi: + description: Whether to run the WASI tests + value: ${{ jobs.compute-changes.outputs.run-wasi }} # bool run-windows-msi: description: Whether to run the MSI installer smoke tests value: ${{ jobs.compute-changes.outputs.run-windows-msi }} # bool - run-ci-fuzz: - description: Whether to run the CIFuzz job - value: ${{ jobs.compute-changes.outputs.run-ci-fuzz }} # bool + run-windows-tests: + description: Whether to run the Windows tests + value: ${{ jobs.compute-changes.outputs.run-windows-tests }} # bool + +permissions: + contents: read jobs: compute-changes: @@ -42,22 +63,28 @@ jobs: runs-on: ubuntu-latest timeout-minutes: 10 outputs: - config-hash: ${{ steps.config-hash.outputs.hash }} + run-android: ${{ steps.changes.outputs.run-android }} run-ci-fuzz: ${{ steps.changes.outputs.run-ci-fuzz }} + run-ci-fuzz-stdlib: ${{ steps.changes.outputs.run-ci-fuzz-stdlib }} run-docs: ${{ steps.changes.outputs.run-docs }} + run-ios: ${{ steps.changes.outputs.run-ios }} + run-macos: ${{ steps.changes.outputs.run-macos }} run-tests: ${{ steps.changes.outputs.run-tests }} + run-ubuntu: ${{ steps.changes.outputs.run-ubuntu }} + run-emscripten: ${{ steps.changes.outputs.run-emscripten }} + run-wasi: ${{ steps.changes.outputs.run-wasi }} run-windows-msi: ${{ steps.changes.outputs.run-windows-msi }} run-windows-tests: ${{ steps.changes.outputs.run-windows-tests }} steps: - name: Set up Python - uses: actions/setup-python@v5 + uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0 with: python-version: "3" - run: >- echo '${{ github.event_name }}' - - uses: actions/checkout@v4 + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 with: persist-credentials: false ref: >- @@ -67,6 +94,15 @@ jobs: || '' }} + - name: 'Downgrade Git' + # Temporarily downgrade to 2.43 until 2.55 is in the runner image, + # to avoid "fatal: shallow file has changed since we read it" bug. + # See https://github.com/python/cpython/issues/151365. + if: github.event_name == 'pull_request' + run: | + sudo apt-get install -y --allow-downgrades 'git=1:2.43.*' 'git-man=1:2.43.*' + git --version + # Adapted from https://github.com/actions/checkout/issues/520#issuecomment-1167205721 - name: Fetch commits to get branch diff if: github.event_name == 'pull_request' @@ -97,10 +133,6 @@ jobs: run: python Tools/build/compute-changes.py env: GITHUB_DEFAULT_BRANCH: ${{ github.event.repository.default_branch }} + GITHUB_EVENT_NAME: ${{ github.event_name }} CCF_TARGET_REF: ${{ github.base_ref || github.event.repository.default_branch }} CCF_HEAD_REF: ${{ github.event.pull_request.head.sha || github.sha }} - - - name: Compute hash for config cache key - id: config-hash - run: | - echo "hash=${{ hashFiles('configure', 'configure.ac', '.github/workflows/build.yml') }}" >> "$GITHUB_OUTPUT" diff --git a/.github/workflows/reusable-docs.yml b/.github/workflows/reusable-docs.yml index 657e0a6bf662f7..60c951867bc645 100644 --- a/.github/workflows/reusable-docs.yml +++ b/.github/workflows/reusable-docs.yml @@ -3,6 +3,17 @@ name: Reusable Docs on: workflow_call: workflow_dispatch: + # Pushes to CPython branches seed the pip caches under the exact keys every + # docs PR restores from. Without a branch-scoped copy, each PR saves a + # duplicate into its own refs/pull/N/merge scope that nothing else can read. + push: + branches: + - main + - '3.*' + paths: + - 'Doc/pylock.toml' + - 'Doc/requirements.txt' + - '.github/workflows/reusable-docs.yml' permissions: contents: read @@ -27,7 +38,7 @@ jobs: refspec_pr: '+${{ github.event.pull_request.head.sha }}:remotes/origin/${{ github.event.pull_request.head.ref }}' steps: - name: 'Check out latest PR branch commit' - uses: actions/checkout@v4 + uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 with: persist-credentials: false ref: >- @@ -36,6 +47,14 @@ jobs: && github.event.pull_request.head.sha || '' }} + - name: 'Downgrade Git' + # Temporarily downgrade to 2.43 until 2.55 is in the runner image, + # to avoid "fatal: shallow file has changed since we read it" bug. + # See https://github.com/python/cpython/issues/151365. + if: github.event_name == 'pull_request' + run: | + sudo apt-get install -y --allow-downgrades 'git=1:2.43.*' 'git-man=1:2.43.*' + git --version # Adapted from https://github.com/actions/checkout/issues/520#issuecomment-1167205721 - name: 'Fetch commits to get branch diff' if: github.event_name == 'pull_request' @@ -52,7 +71,7 @@ jobs: git fetch origin "${refspec_base}" --shallow-since="${DATE}" \ --no-tags --prune --no-recurse-submodules - name: 'Set up Python' - uses: actions/setup-python@v5 + uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0 with: python-version: '3' cache: 'pip' @@ -66,7 +85,7 @@ jobs: run: | set -Eeuo pipefail # Build docs with the nit-picky option; write warnings to file - make -C Doc/ PYTHON=../python SPHINXOPTS="--quiet --nitpicky --fail-on-warning --warning-file sphinx-warnings.txt" html + make -C Doc/ PYTHON=../python SPHINXOPTS="--quiet --nitpicky --warning-file sphinx-warnings.txt" html - name: 'Check warnings' if: github.event_name == 'pull_request' run: | @@ -79,20 +98,20 @@ jobs: # Run "doctest" on HEAD as new syntax doesn't exist in the latest stable release doctest: name: 'Doctest' - runs-on: ubuntu-24.04 + runs-on: ubuntu-26.04 timeout-minutes: 60 steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 with: persist-credentials: false - - uses: actions/cache@v4 + - uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4 with: path: ~/.cache/pip key: ubuntu-doc-${{ hashFiles('Doc/requirements.txt') }} restore-keys: | ubuntu-doc- - name: 'Install Dependencies' - run: sudo ./.github/workflows/posix-deps-apt.sh && sudo apt-get install wamerican + run: sudo ./.github/workflows/posix-deps-apt.sh && sudo apt-get install --no-install-recommends wamerican - name: 'Configure CPython' run: ./configure --with-pydebug - name: 'Build CPython' @@ -102,3 +121,30 @@ jobs: # Use "xvfb-run" since some doctest tests open GUI windows - name: 'Run documentation doctest' run: xvfb-run make -C Doc/ PYTHON=../python SPHINXERRORHANDLING="--fail-on-warning" doctest + + check-epub: + name: 'Check EPUB' + runs-on: ubuntu-latest + timeout-minutes: 30 + steps: + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + persist-credentials: false + - name: 'Set up Python' + uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0 + with: + python-version: '3' + cache: 'pip' + cache-dependency-path: 'Doc/requirements.txt' + - name: 'Install build dependencies' + run: | + make -C Doc/ venv + python -m pip install epubcheck + - name: 'Build EPUB documentation' + run: make -C Doc/ PYTHON=../python epub + - name: 'Run epubcheck' + continue-on-error: true + run: epubcheck Doc/build/epub/Python.epub &> Doc/epubcheck.txt + - run: cat Doc/epubcheck.txt + - name: 'Check for fatal errors in EPUB' + run: python Doc/tools/check-epub.py diff --git a/.github/workflows/reusable-emscripten.yml b/.github/workflows/reusable-emscripten.yml new file mode 100644 index 00000000000000..b15169164572b4 --- /dev/null +++ b/.github/workflows/reusable-emscripten.yml @@ -0,0 +1,81 @@ +name: Reusable Emscripten + +on: + workflow_call: + +permissions: + contents: read + +env: + FORCE_COLOR: 1 + +jobs: + build-emscripten-reusable: + name: 'build and test' + runs-on: ubuntu-26.04 + timeout-minutes: 40 + steps: + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + persist-credentials: false + - name: "Read Emscripten config" + id: emscripten-config + shell: python + run: | + import hashlib + import json + import os + import tomllib + from pathlib import Path + + config = tomllib.loads(Path("Platforms/emscripten/config.toml").read_text()) + h = hashlib.sha256() + h.update(json.dumps(config["dependencies"], sort_keys=True).encode()) + h.update(Path("Platforms/emscripten/make_libffi.sh").read_bytes()) + h.update(b'1') # Update to explicitly bust cache + emsdk_cache = Path(os.environ["RUNNER_TEMP"]) / "emsdk-cache" + with open(os.environ["GITHUB_OUTPUT"], "a") as f: + f.write(f"emscripten-version={config['emscripten-version']}\n") + f.write(f"node-version={config['node-version']}\n") + f.write(f"deps-hash={h.hexdigest()}\n") + with open(os.environ["GITHUB_ENV"], "a") as f: + f.write(f"EMSDK_CACHE={emsdk_cache}\n") + - name: "Install Node.js" + uses: actions/setup-node@53b83947a5a98c8d113130e565377fae1a50d02f # v6.3.0 + with: + node-version: ${{ steps.emscripten-config.outputs.node-version }} + - name: "Cache Emscripten SDK" + id: emsdk-cache + uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4 + with: + path: ${{ env.EMSDK_CACHE }} + key: emsdk-${{ steps.emscripten-config.outputs.emscripten-version }}-${{ steps.emscripten-config.outputs.deps-hash }} + restore-keys: emsdk-${{ steps.emscripten-config.outputs.emscripten-version }} + - name: "Install Python" + uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0 + with: + python-version: '3.x' + - name: "Runner image version" + run: echo "IMAGE_OS_VERSION=${ImageOS}-${ImageVersion}" >> "$GITHUB_ENV" + - name: "Install Emscripten" + run: python3 Platforms/emscripten install-emscripten + - name: "Configure build Python" + run: python3 Platforms/emscripten configure-build-python -- --config-cache --with-pydebug + - name: "Make build Python" + run: python3 Platforms/emscripten make-build-python + - name: "Display build info of the build Python" + run: python3 Platforms/emscripten pythoninfo-build + - name: "Make dependencies" + run: >- + python3 Platforms/emscripten make-dependencies + ${{ steps.emsdk-cache.outputs.cache-hit == 'true' && '--check-up-to-date' || '' }} + - name: "Configure host/Emscripten Python" + run: python3 Platforms/emscripten configure-host --host-runner node -- --config-cache + - name: "Make host/Emscripten Python" + run: python3 Platforms/emscripten make-host + - name: "Display build info of the host/Emscripten Python" + run: python3 Platforms/emscripten pythoninfo-host + - name: "Test" + run: python3 Platforms/emscripten run --test + - name: "Test Repl" + run: Platforms/emscripten/browser_test/run_test.sh diff --git a/.github/workflows/reusable-install.yml b/.github/workflows/reusable-install.yml new file mode 100644 index 00000000000000..337da684882d29 --- /dev/null +++ b/.github/workflows/reusable-install.yml @@ -0,0 +1,44 @@ +name: Reusable Ubuntu (installed) + +on: + workflow_call: + +permissions: + contents: read + +env: + FORCE_COLOR: 1 + +jobs: + build-install-test: + name: build, install and test + runs-on: ubuntu-26.04-arm + timeout-minutes: 60 + env: + PYTHONSTRICTEXTENSIONBUILD: 1 + steps: + - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 + with: + persist-credentials: false + - name: Register gcc problem matcher + run: echo "::add-matcher::.github/problem-matchers/gcc.json" + - name: Set install dir + run: + echo "INSTALL_DIR=$(realpath "${GITHUB_WORKSPACE}/../installed-python")" >> "$GITHUB_ENV" + - name: Install dependencies + run: sudo ./.github/workflows/posix-deps-apt.sh + - name: Configure CPython + run: ./configure --config-cache --prefix="$INSTALL_DIR" + - name: Build CPython + run: make -j + - name: Install CPython + run: make install + - name: Set installed interpreter + run: | + ldversion=$(./python -c 'import sysconfig; print(sysconfig.get_config_var("LDVERSION"))') + echo "INSTALLED_PYTHON=${INSTALL_DIR}/bin/python${ldversion}" >> "$GITHUB_ENV" + - name: Display build info + run: | + "$INSTALLED_PYTHON" -m test.pythoninfo + - name: Test the installed Python + run: xvfb-run "$INSTALLED_PYTHON" -m test --fast-ci --timeout=900 diff --git a/.github/workflows/reusable-macos.yml b/.github/workflows/reusable-macos.yml index de0c40221364ad..6cb427a03713cf 100644 --- a/.github/workflows/reusable-macos.yml +++ b/.github/workflows/reusable-macos.yml @@ -3,9 +3,6 @@ name: Reusable macOS on: workflow_call: inputs: - config_hash: - required: true - type: string free-threading: required: false type: boolean @@ -15,6 +12,9 @@ on: required: true type: string +permissions: + contents: read + env: FORCE_COLOR: 1 @@ -31,19 +31,15 @@ jobs: PYTHONSTRICTEXTENSIONBUILD: 1 TERM: linux steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 with: persist-credentials: false - name: Runner image version run: echo "IMAGE_OS_VERSION=${ImageOS}-${ImageVersion}" >> "$GITHUB_ENV" - - name: Restore config.cache - uses: actions/cache@v4 - with: - path: config.cache - key: ${{ github.job }}-${{ env.IMAGE_OS_VERSION }}-${{ inputs.config_hash }} - name: Install Homebrew dependencies run: | - brew install pkg-config openssl@3.0 xz gdbm tcl-tk@8 make + brew bundle --file=Misc/Brewfile + brew install make # Because alternate versions are not symlinked into place by default: brew link --overwrite tcl-tk@8 - name: Configure CPython @@ -60,15 +56,15 @@ jobs: --prefix=/opt/python-dev \ --with-openssl="$(brew --prefix openssl@3.0)" - name: Build CPython - if : ${{ inputs.free-threading || inputs.os != 'macos-13' }} + if : ${{ inputs.free-threading || inputs.os != 'macos-26-intel' }} run: gmake -j8 - name: Build CPython for compiler warning check - if : ${{ !inputs.free-threading && inputs.os == 'macos-13' }} + if : ${{ !inputs.free-threading && inputs.os == 'macos-26-intel' }} run: set -o pipefail; gmake -j8 --output-sync 2>&1 | tee compiler_output_macos.txt - name: Display build info run: make pythoninfo - name: Check compiler warnings - if : ${{ !inputs.free-threading && inputs.os == 'macos-13' }} + if : ${{ !inputs.free-threading && inputs.os == 'macos-26-intel' }} run: >- python3 Tools/build/check_warnings.py --compiler-output-file-path=compiler_output_macos.txt diff --git a/.github/workflows/reusable-san.yml b/.github/workflows/reusable-san.yml new file mode 100644 index 00000000000000..8a9c7d86462f4f --- /dev/null +++ b/.github/workflows/reusable-san.yml @@ -0,0 +1,138 @@ +name: Reusable Sanitizer + +on: + workflow_call: + inputs: + sanitizer: + required: true + type: string + free-threading: + description: Whether to use free-threaded mode + required: false + type: boolean + default: false + +permissions: + contents: read + +env: + FORCE_COLOR: 1 + OPENSSL_VER: 3.5.7 + +jobs: + build-san-reusable: + name: >- + ${{ inputs.sanitizer }}${{ + inputs.free-threading + && ' (free-threading)' + || '' + }} + # https://apt.llvm.org/llvm.sh doesn't support LLVM 20 on Ubuntu 26.04, + # so stick to Ubuntu 24.04 until LLVM is upgraded. + runs-on: ubuntu-24.04 + timeout-minutes: 60 + steps: + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + persist-credentials: false + - name: Runner image version + run: echo "IMAGE_OS_VERSION=${ImageOS}-${ImageVersion}" >> "$GITHUB_ENV" + - name: Install dependencies + run: | + sudo ./.github/workflows/posix-deps-apt.sh + # Install clang + wget https://apt.llvm.org/llvm.sh + chmod +x llvm.sh + sudo ./llvm.sh 20 + sudo update-alternatives --install /usr/bin/clang clang /usr/bin/clang-20 100 + sudo update-alternatives --set clang /usr/bin/clang-20 + sudo update-alternatives --install /usr/bin/clang++ clang++ /usr/bin/clang++-20 100 + sudo update-alternatives --set clang++ /usr/bin/clang++-20 + echo "CC=clang" >> "$GITHUB_ENV" + echo "CXX=clang++" >> "$GITHUB_ENV" + - name: TSan option setup + if: inputs.sanitizer == 'TSan' + run: | + sudo sysctl -w vm.mmap_rnd_bits=28 # Reduce ASLR to avoid TSan crashing + + echo "MULTISSL_DIR=${GITHUB_WORKSPACE}/multissl" >> "$GITHUB_ENV" + echo "OPENSSL_DIR=${GITHUB_WORKSPACE}/multissl/openssl/${OPENSSL_VER}" >> "$GITHUB_ENV" + echo "TSAN_OPTIONS=${SAN_LOG_OPTION} suppressions=${GITHUB_WORKSPACE}/Tools/tsan/suppressions${SUPPRESSIONS_SUFFIX}.txt handle_segv=0" >> "$GITHUB_ENV" + env: + SAN_LOG_OPTION: log_path=${{ github.workspace }}/san_log + SUPPRESSIONS_SUFFIX: >- + ${{ + inputs.free-threading + && '_free_threading' + || '' + }} + - name: UBSan option setup + if: inputs.sanitizer != 'TSan' + run: >- + echo + "UBSAN_OPTIONS=${SAN_LOG_OPTION}" + >> "$GITHUB_ENV" + env: + SAN_LOG_OPTION: log_path=${{ github.workspace }}/san_log + - name: Add ccache to PATH + run: | + echo "PATH=/usr/lib/ccache:$PATH" >> "$GITHUB_ENV" + - name: 'Restore OpenSSL build (TSan)' + id: cache-openssl + if: inputs.sanitizer == 'TSan' + uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4 + with: + path: ./multissl/openssl/${{ env.OPENSSL_VER }} + key: ${{ env.IMAGE_OS_VERSION }}-multissl-openssl-tsan-${{ env.OPENSSL_VER }} + - name: Install OpenSSL (TSan) + if: >- + inputs.sanitizer == 'TSan' + && steps.cache-openssl.outputs.cache-hit != 'true' + run: >- + python3 Tools/ssl/multissltests.py + --steps=library + --base-directory="${MULTISSL_DIR}" + --openssl="${OPENSSL_VER}" + --system=Linux + --tsan + - name: Configure CPython + run: >- + ./configure + --config-cache + ${{ + inputs.sanitizer == 'TSan' + && '--with-thread-sanitizer' + || '--with-undefined-behavior-sanitizer' + }} + --with-pydebug + ${{ inputs.sanitizer == 'TSan' && '--with-openssl="$OPENSSL_DIR" --with-openssl-rpath=auto' || '' }} + ${{ inputs.free-threading && '--disable-gil' || '' }} + - name: Build CPython + run: make -j4 + - name: Display build info + run: make pythoninfo + - name: Tests + run: >- + ./python -m test + ${{ inputs.sanitizer == 'TSan' && '--tsan' || '' }} + -j4 -W --timeout=900 --slowest + - name: Parallel tests + if: >- + inputs.sanitizer == 'TSan' + && inputs.free-threading + run: ./python -m test --tsan-parallel --parallel-threads=4 -j4 -W --timeout=600 --slowest + - name: Display logs + if: always() + run: find "${GITHUB_WORKSPACE}" -name 'san_log.*' | xargs head -n 1000 + - name: Archive logs + if: always() + uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6.0.0 + with: + name: >- + ${{ inputs.sanitizer }}-logs-${{ + inputs.free-threading + && 'free-threading' + || 'default' + }} + path: san_log.* + if-no-files-found: ignore diff --git a/.github/workflows/reusable-tsan.yml b/.github/workflows/reusable-tsan.yml deleted file mode 100644 index 6a58e5305f8e09..00000000000000 --- a/.github/workflows/reusable-tsan.yml +++ /dev/null @@ -1,94 +0,0 @@ -name: Reusable Thread Sanitizer - -on: - workflow_call: - inputs: - config_hash: - required: true - type: string - free-threading: - description: Whether to use free-threaded mode - required: false - type: boolean - default: false - -env: - FORCE_COLOR: 1 - -jobs: - build-tsan-reusable: - name: 'Thread sanitizer' - runs-on: ubuntu-24.04 - timeout-minutes: 60 - steps: - - uses: actions/checkout@v4 - with: - persist-credentials: false - - name: Runner image version - run: echo "IMAGE_OS_VERSION=${ImageOS}-${ImageVersion}" >> "$GITHUB_ENV" - - name: Restore config.cache - uses: actions/cache@v4 - with: - path: config.cache - key: ${{ github.job }}-${{ env.IMAGE_OS_VERSION }}-${{ inputs.config_hash }} - - name: Install dependencies - run: | - sudo ./.github/workflows/posix-deps-apt.sh - # Install clang-18 - wget https://apt.llvm.org/llvm.sh - chmod +x llvm.sh - sudo ./llvm.sh 17 # gh-121946: llvm-18 package is temporarily broken - sudo update-alternatives --install /usr/bin/clang clang /usr/bin/clang-17 100 - sudo update-alternatives --set clang /usr/bin/clang-17 - sudo update-alternatives --install /usr/bin/clang++ clang++ /usr/bin/clang++-17 100 - sudo update-alternatives --set clang++ /usr/bin/clang++-17 - # Reduce ASLR to avoid TSAN crashing - sudo sysctl -w vm.mmap_rnd_bits=28 - - name: TSAN option setup - run: | - echo "TSAN_OPTIONS=log_path=${GITHUB_WORKSPACE}/tsan_log suppressions=${GITHUB_WORKSPACE}/Tools/tsan/suppressions${{ - fromJSON(inputs.free-threading) - && '_free_threading' - || '' - }}.txt handle_segv=0" >> "$GITHUB_ENV" - echo "CC=clang" >> "$GITHUB_ENV" - echo "CXX=clang++" >> "$GITHUB_ENV" - - name: Add ccache to PATH - run: | - echo "PATH=/usr/lib/ccache:$PATH" >> "$GITHUB_ENV" - - name: Configure ccache action - uses: hendrikmuhs/ccache-action@v1.2 - with: - save: ${{ github.event_name == 'push' }} - max-size: "200M" - - name: Configure CPython - run: >- - ./configure - --config-cache - --with-thread-sanitizer - --with-pydebug - ${{ fromJSON(inputs.free-threading) && '--disable-gil' || '' }} - - name: Build CPython - run: make -j4 - - name: Display build info - run: make pythoninfo - - name: Tests - run: ./python -m test --tsan -j4 - - name: Parallel tests - if: fromJSON(inputs.free-threading) - run: ./python -m test --tsan-parallel --parallel-threads=4 -j4 - - name: Display TSAN logs - if: always() - run: find "${GITHUB_WORKSPACE}" -name 'tsan_log.*' | xargs head -n 1000 - - name: Archive TSAN logs - if: always() - uses: actions/upload-artifact@v4 - with: - name: >- - tsan-logs-${{ - fromJSON(inputs.free-threading) - && 'free-threading' - || 'default' - }} - path: tsan_log.* - if-no-files-found: ignore diff --git a/.github/workflows/reusable-ubuntu.yml b/.github/workflows/reusable-ubuntu.yml index 76b19fd5d1a72e..28a176275cc467 100644 --- a/.github/workflows/reusable-ubuntu.yml +++ b/.github/workflows/reusable-ubuntu.yml @@ -3,9 +3,6 @@ name: Reusable Ubuntu on: workflow_call: inputs: - config_hash: - required: true - type: string bolt-optimizations: description: Whether to enable BOLT optimizations required: false @@ -17,9 +14,12 @@ on: type: boolean default: false os: - description: OS to run the job - required: true - type: string + description: OS to run the job + required: true + type: string + +permissions: + contents: read env: FORCE_COLOR: 1 @@ -30,11 +30,11 @@ jobs: runs-on: ${{ inputs.os }} timeout-minutes: 60 env: - OPENSSL_VER: 3.0.15 + OPENSSL_VER: 3.5.7 PYTHONSTRICTEXTENSIONBUILD: 1 TERM: linux steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 with: persist-credentials: false - name: Register gcc problem matcher @@ -42,10 +42,12 @@ jobs: - name: Install dependencies run: sudo ./.github/workflows/posix-deps-apt.sh - name: Install Clang and BOLT - if: ${{ fromJSON(inputs.bolt-optimizations) }} + if: inputs.bolt-optimizations + # For BOLT jobs, https://apt.llvm.org/llvm.sh doesn't support LLVM 19 + # on Ubuntu 26.04, so stick to Ubuntu 24.04 until LLVM is upgraded. run: | sudo bash -c "$(wget -O - https://apt.llvm.org/llvm.sh)" ./llvm.sh 19 - sudo apt-get install bolt-19 + sudo apt-get install --no-install-recommends bolt-19 echo PATH="$(llvm-config-19 --bindir):$PATH" >> $GITHUB_ENV - name: Configure OpenSSL env vars run: | @@ -54,21 +56,13 @@ jobs: echo "LD_LIBRARY_PATH=${GITHUB_WORKSPACE}/multissl/openssl/${OPENSSL_VER}/lib" >> "$GITHUB_ENV" - name: 'Restore OpenSSL build' id: cache-openssl - uses: actions/cache@v4 + uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4 with: path: ./multissl/openssl/${{ env.OPENSSL_VER }} key: ${{ inputs.os }}-multissl-openssl-${{ env.OPENSSL_VER }} - name: Install OpenSSL if: steps.cache-openssl.outputs.cache-hit != 'true' run: python3 Tools/ssl/multissltests.py --steps=library --base-directory "$MULTISSL_DIR" --openssl "$OPENSSL_VER" --system Linux - - name: Add ccache to PATH - run: | - echo "PATH=/usr/lib/ccache:$PATH" >> "$GITHUB_ENV" - - name: Configure ccache action - uses: hendrikmuhs/ccache-action@v1.2 - with: - save: ${{ github.event_name == 'push' }} - max-size: "200M" - name: Setup directory envs for out-of-tree builds run: | echo "CPYTHON_RO_SRCDIR=$(realpath -m "${GITHUB_WORKSPACE}"/../cpython-ro-srcdir)" >> "$GITHUB_ENV" @@ -79,11 +73,6 @@ jobs: run: sudo mount --bind -o ro "$GITHUB_WORKSPACE" "$CPYTHON_RO_SRCDIR" - name: Runner image version run: echo "IMAGE_OS_VERSION=${ImageOS}-${ImageVersion}" >> "$GITHUB_ENV" - - name: Restore config.cache - uses: actions/cache@v4 - with: - path: ${{ env.CPYTHON_BUILDDIR }}/config.cache - key: ${{ github.job }}-${{ env.IMAGE_OS_VERSION }}-${{ inputs.config_hash }} - name: Configure CPython out-of-tree working-directory: ${{ env.CPYTHON_BUILDDIR }} # `test_unpickle_module_race` writes to the source directory, which is @@ -96,10 +85,10 @@ jobs: --enable-slower-safety --enable-safety --with-openssl="$OPENSSL_DIR" - ${{ fromJSON(inputs.free-threading) && '--disable-gil' || '' }} - ${{ fromJSON(inputs.bolt-optimizations) && '--enable-bolt' || '' }} + ${{ inputs.free-threading && '--disable-gil' || '' }} + ${{ inputs.bolt-optimizations && '--enable-bolt' || '' }} - name: Build CPython out-of-tree - if: ${{ inputs.free-threading }} + if: inputs.free-threading working-directory: ${{ env.CPYTHON_BUILDDIR }} run: make -j - name: Build CPython out-of-tree (for compiler warning check) diff --git a/.github/workflows/reusable-wasi.yml b/.github/workflows/reusable-wasi.yml index 6beb91e66d4027..bd08c120fd00ee 100644 --- a/.github/workflows/reusable-wasi.yml +++ b/.github/workflows/reusable-wasi.yml @@ -2,10 +2,9 @@ name: Reusable WASI on: workflow_call: - inputs: - config_hash: - required: true - type: string + +permissions: + contents: read env: FORCE_COLOR: 1 @@ -13,26 +12,25 @@ env: jobs: build-wasi-reusable: name: 'build and test' - runs-on: ubuntu-24.04 + runs-on: ubuntu-26.04 timeout-minutes: 60 env: - WASMTIME_VERSION: 22.0.0 + WASMTIME_VERSION: 38.0.3 WASI_SDK_VERSION: 24 WASI_SDK_PATH: /opt/wasi-sdk - CROSS_BUILD_PYTHON: cross-build/build CROSS_BUILD_WASI: cross-build/wasm32-wasip1 steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 with: persist-credentials: false # No problem resolver registered as one doesn't currently exist for Clang. - name: "Install wasmtime" - uses: bytecodealliance/actions/wasmtime/setup@v1 + uses: bytecodealliance/actions/wasmtime/setup@9152e710e9f7182e4c29ad218e4f335a7b203613 # v1.1.3 with: version: ${{ env.WASMTIME_VERSION }} - name: "Restore WASI SDK" id: cache-wasi-sdk - uses: actions/cache@v4 + uses: actions/cache@668228422ae6a00e4ad889ee87cd7109ec5666a7 # v5.0.4 with: path: ${{ env.WASI_SDK_PATH }} key: ${{ runner.os }}-wasi-sdk-${{ env.WASI_SDK_VERSION }} @@ -42,43 +40,24 @@ jobs: mkdir "${WASI_SDK_PATH}" && \ curl -s -S --location "https://github.com/WebAssembly/wasi-sdk/releases/download/wasi-sdk-${WASI_SDK_VERSION}/wasi-sdk-${WASI_SDK_VERSION}.0-x86_64-linux.tar.gz" | \ tar --strip-components 1 --directory "${WASI_SDK_PATH}" --extract --gunzip - - name: "Configure ccache action" - uses: hendrikmuhs/ccache-action@v1.2 - with: - save: ${{ github.event_name == 'push' }} - max-size: "200M" - - name: "Add ccache to PATH" - run: echo "PATH=/usr/lib/ccache:$PATH" >> "$GITHUB_ENV" - name: "Install Python" - uses: actions/setup-python@v5 + uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0 with: python-version: '3.x' - name: "Runner image version" run: echo "IMAGE_OS_VERSION=${ImageOS}-${ImageVersion}" >> "$GITHUB_ENV" - - name: "Restore Python build config.cache" - uses: actions/cache@v4 - with: - path: ${{ env.CROSS_BUILD_PYTHON }}/config.cache - # Include env.pythonLocation in key to avoid changes in environment when setup-python updates Python. - # Include the hash of `Tools/wasm/wasi.py` as it may change the environment variables. - # (Make sure to keep the key in sync with the other config.cache step below.) - key: ${{ github.job }}-${{ env.IMAGE_OS_VERSION }}-${{ env.WASI_SDK_VERSION }}-${{ env.WASMTIME_VERSION }}-${{ inputs.config_hash }}-${{ hashFiles('Tools/wasm/wasi.py') }}-${{ env.pythonLocation }} - name: "Configure build Python" - run: python3 Tools/wasm/wasi.py configure-build-python -- --config-cache --with-pydebug + run: python3 Tools/wasm/wasi configure-build-python -- --config-cache --with-pydebug - name: "Make build Python" - run: python3 Tools/wasm/wasi.py make-build-python - - name: "Restore host config.cache" - uses: actions/cache@v4 - with: - path: ${{ env.CROSS_BUILD_WASI }}/config.cache - # Should be kept in sync with the other config.cache step above. - key: ${{ github.job }}-${{ env.IMAGE_OS_VERSION }}-${{ env.WASI_SDK_VERSION }}-${{ env.WASMTIME_VERSION }}-${{ inputs.config_hash }}-${{ hashFiles('Tools/wasm/wasi.py') }}-${{ env.pythonLocation }} - - name: "Configure host" + run: python3 Tools/wasm/wasi make-build-python + - name: "Display build info of the build Python" + run: python3 Tools/wasm/wasi pythoninfo-build + - name: "Configure host/WASI Python" # `--with-pydebug` inferred from configure-build-python - run: python3 Tools/wasm/wasi.py configure-host -- --config-cache - - name: "Make host" - run: python3 Tools/wasm/wasi.py make-host - - name: "Display build info" - run: make --directory "${CROSS_BUILD_WASI}" pythoninfo + run: python3 Tools/wasm/wasi configure-host -- --config-cache + - name: "Make host/WASI Python" + run: python3 Tools/wasm/wasi make-host + - name: "Display build info of the host/WASI Python" + run: python3 Tools/wasm/wasi pythoninfo-host - name: "Test" run: make --directory "${CROSS_BUILD_WASI}" test diff --git a/.github/workflows/reusable-windows-msi.yml b/.github/workflows/reusable-windows-msi.yml index a50de344bba4da..420c9cd909a5e9 100644 --- a/.github/workflows/reusable-windows-msi.yml +++ b/.github/workflows/reusable-windows-msi.yml @@ -17,13 +17,13 @@ env: jobs: build: name: installer for ${{ inputs.arch }} - runs-on: ${{ inputs.arch == 'arm64' && 'windows-11-arm' || 'windows-latest' }} + runs-on: ${{ inputs.arch == 'arm64' && 'windows-11-arm' || 'windows-2022' }} timeout-minutes: 60 env: ARCH: ${{ inputs.arch }} IncludeFreethreaded: true steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 with: persist-credentials: false - name: Build CPython installer diff --git a/.github/workflows/reusable-windows.yml b/.github/workflows/reusable-windows.yml index 37c802095b0f2f..6643243feeebf6 100644 --- a/.github/workflows/reusable-windows.yml +++ b/.github/workflows/reusable-windows.yml @@ -13,6 +13,9 @@ on: type: boolean default: false +permissions: + contents: read + env: FORCE_COLOR: 1 IncludeUwp: >- @@ -21,12 +24,12 @@ env: jobs: build: name: Build and test (${{ inputs.arch }}) - runs-on: ${{ inputs.arch == 'arm64' && 'windows-11-arm' || 'windows-latest' }} + runs-on: ${{ inputs.arch == 'arm64' && 'windows-11-arm' || 'windows-2022' }} timeout-minutes: 60 env: ARCH: ${{ inputs.arch }} steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 with: persist-credentials: false - name: Register MSVC problem matcher @@ -37,7 +40,7 @@ jobs: .\\PCbuild\\build.bat -e -d -v -p "${ARCH}" - ${{ fromJSON(inputs.free-threading) && '--disable-gil' || '' }} + ${{ inputs.free-threading && '--disable-gil' || '' }} shell: bash - name: Display build info run: .\\python.bat -m test.pythoninfo @@ -46,5 +49,5 @@ jobs: .\\PCbuild\\rt.bat -p "${ARCH}" -d -q --fast-ci - ${{ fromJSON(inputs.free-threading) && '--disable-gil' || '' }} + ${{ inputs.free-threading && '--disable-gil' || '' }} shell: bash diff --git a/.github/workflows/stale.yml b/.github/workflows/stale.yml index febb2dd823a8fe..56193a901ce076 100644 --- a/.github/workflows/stale.yml +++ b/.github/workflows/stale.yml @@ -4,17 +4,20 @@ on: schedule: - cron: "0 */6 * * *" +permissions: + contents: read + jobs: stale: if: github.repository_owner == 'python' - runs-on: ubuntu-latest + runs-on: ubuntu-slim permissions: pull-requests: write timeout-minutes: 10 steps: - name: "Check PRs" - uses: actions/stale@v9 + uses: actions/stale@5bef64f19d7facfb25b37b414482c7164d639639 # v9.1.0 with: repo-token: ${{ secrets.GITHUB_TOKEN }} stale-pr-message: 'This PR is stale because it has been open for 30 days with no activity.' diff --git a/.github/workflows/tail-call.yml b/.github/workflows/tail-call.yml index 4636372e26c41b..8fd63d7a6f8988 100644 --- a/.github/workflows/tail-call.yml +++ b/.github/workflows/tail-call.yml @@ -1,19 +1,14 @@ name: Tail calling interpreter on: pull_request: - paths: + paths: &paths - '.github/workflows/tail-call.yml' - 'Python/bytecodes.c' - 'Python/ceval.c' - 'Python/ceval_macros.h' - 'Python/generated_cases.c.h' push: - paths: - - '.github/workflows/tail-call.yml' - - 'Python/bytecodes.c' - - 'Python/ceval.c' - - 'Python/ceval_macros.h' - - 'Python/generated_cases.c.h' + paths: *paths workflow_dispatch: permissions: @@ -25,116 +20,106 @@ concurrency: env: FORCE_COLOR: 1 + LLVM_VERSION: 20 jobs: - tail-call: + windows: name: ${{ matrix.target }} runs-on: ${{ matrix.runner }} - timeout-minutes: 90 + timeout-minutes: 60 strategy: fail-fast: false matrix: - target: -# Un-comment as we add support for more platforms for tail-calling interpreters. -# - i686-pc-windows-msvc/msvc - - x86_64-pc-windows-msvc/msvc -# - aarch64-pc-windows-msvc/msvc - - x86_64-apple-darwin/clang - - aarch64-apple-darwin/clang - - x86_64-unknown-linux-gnu/gcc - - aarch64-unknown-linux-gnu/gcc - - free-threading - llvm: - - 20 include: -# - target: i686-pc-windows-msvc/msvc -# architecture: Win32 -# runner: windows-latest - target: x86_64-pc-windows-msvc/msvc architecture: x64 - runner: windows-latest -# - target: aarch64-pc-windows-msvc/msvc -# architecture: ARM64 -# runner: windows-latest - - target: x86_64-apple-darwin/clang - architecture: x86_64 - runner: macos-13 - - target: aarch64-apple-darwin/clang - architecture: aarch64 - runner: macos-14 - - target: x86_64-unknown-linux-gnu/gcc - architecture: x86_64 - runner: ubuntu-24.04 - - target: aarch64-unknown-linux-gnu/gcc - architecture: aarch64 - runner: ubuntu-24.04-arm - - target: free-threading - architecture: x86_64 - runner: ubuntu-24.04 + runner: windows-2022 + build_flags: "" + run_tests: true steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 with: persist-credentials: false - - uses: actions/setup-python@v5 + - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0 with: python-version: '3.11' - - - name: Native Windows (debug) - if: runner.os == 'Windows' && matrix.architecture != 'ARM64' - shell: cmd + - name: Build + shell: pwsh run: | - choco install llvm --allow-downgrade --no-progress --version ${{ matrix.llvm }}.1.0 - set PlatformToolset=clangcl - set LLVMToolsVersion=${{ matrix.llvm }}.1.0 - set LLVMInstallDir=C:\Program Files\LLVM - call ./PCbuild/build.bat --tail-call-interp -d -p ${{ matrix.architecture }} - call ./PCbuild/rt.bat -d -p ${{ matrix.architecture }} -q --multiprocess 0 --timeout 4500 --verbose2 --verbose3 - - # No tests (yet): - - name: Emulated Windows (release) - if: runner.os == 'Windows' && matrix.architecture == 'ARM64' - shell: cmd + choco install llvm --allow-downgrade --no-progress --version ${{ env.LLVM_VERSION }}.1.0 + $env:PlatformToolset = "clangcl" + $env:LLVMToolsVersion = "${{ env.LLVM_VERSION }}.1.0" + $env:LLVMInstallDir = "C:\Program Files\LLVM" + ./PCbuild/build.bat --tail-call-interp ${{ matrix.build_flags }} -c Release -p ${{ matrix.architecture }} + - name: Test + if: matrix.run_tests + shell: pwsh run: | - choco install llvm --allow-downgrade --no-progress --version ${{ matrix.llvm }}.1.0 - set PlatformToolset=clangcl - set LLVMToolsVersion=${{ matrix.llvm }}.1.0 - set LLVMInstallDir=C:\Program Files\LLVM - ./PCbuild/build.bat --tail-call-interp -p ${{ matrix.architecture }} + ./PCbuild/rt.bat -p ${{ matrix.architecture }} -q --multiprocess 0 --timeout 4500 --verbose2 --verbose3 - # The `find` line is required as a result of https://github.com/actions/runner-images/issues/9966. - # This is a bug in the macOS runner image where the pre-installed Python is installed in the same - # directory as the Homebrew Python, which causes the build to fail for macos-13. This line removes - # the symlink to the pre-installed Python so that the Homebrew Python is used instead. - # Note: when a new LLVM is released, the homebrew installation directory changes, so the builds will fail. - # We either need to upgrade LLVM or change the directory being pointed to. - - name: Native macOS (release) - if: runner.os == 'macOS' + macos: + name: ${{ matrix.target }} + runs-on: ${{ matrix.runner }} + timeout-minutes: 60 + strategy: + fail-fast: false + matrix: + include: + - target: x86_64-apple-darwin/clang + runner: macos-26-intel + - target: aarch64-apple-darwin/clang + runner: macos-26 + steps: + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + persist-credentials: false + - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0 + with: + python-version: '3.11' + - name: Install dependencies run: | brew update - find /usr/local/bin -lname '*/Library/Frameworks/Python.framework/*' -delete - brew install llvm@${{ matrix.llvm }} + brew install llvm@${{ env.LLVM_VERSION }} + - name: Build + run: | export SDKROOT="$(xcrun --show-sdk-path)" - export PATH="/usr/local/opt/llvm/bin:$PATH" - export PATH="/opt/homebrew/opt/llvm/bin:$PATH" - CC=clang-20 ./configure --with-tail-call-interp + export PATH="/usr/local/opt/llvm@${{ env.LLVM_VERSION }}/bin:$PATH" + export PATH="/opt/homebrew/opt/llvm@${{ env.LLVM_VERSION }}/bin:$PATH" + CC=clang-${{ env.LLVM_VERSION }} ./configure --with-tail-call-interp make all --jobs 4 + - name: Test + run: | ./python.exe -m test --multiprocess 0 --timeout 4500 --verbose2 --verbose3 - - name: Native Linux (debug) - if: runner.os == 'Linux' && matrix.target != 'free-threading' + linux: + name: ${{ matrix.target }} + runs-on: ${{ matrix.runner }} + timeout-minutes: 60 + strategy: + fail-fast: false + matrix: + include: + - target: x86_64-unknown-linux-gnu/gcc + runner: ubuntu-26.04 + configure_flags: --with-pydebug + - target: x86_64-unknown-linux-gnu/gcc-free-threading + runner: ubuntu-26.04 + configure_flags: --disable-gil + - target: aarch64-unknown-linux-gnu/gcc + runner: ubuntu-26.04-arm + configure_flags: --with-pydebug + steps: + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + persist-credentials: false + - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0 + with: + python-version: '3.11' + - name: Build run: | - sudo bash -c "$(wget -O - https://apt.llvm.org/llvm.sh)" ./llvm.sh ${{ matrix.llvm }} - export PATH="$(llvm-config-${{ matrix.llvm }} --bindir):$PATH" - CC=clang-20 ./configure --with-tail-call-interp --with-pydebug + # On ubuntu-26.04 image, clang is clang-21 by default + CC=clang-${{ env.LLVM_VERSION }} ./configure --with-tail-call-interp ${{ matrix.configure_flags }} make all --jobs 4 - ./python -m test --multiprocess 0 --timeout 4500 --verbose2 --verbose3 - - - name: Native Linux with free-threading (release) - if: matrix.target == 'free-threading' + - name: Test run: | - sudo bash -c "$(wget -O - https://apt.llvm.org/llvm.sh)" ./llvm.sh ${{ matrix.llvm }} - export PATH="$(llvm-config-${{ matrix.llvm }} --bindir):$PATH" - CC=clang-20 ./configure --with-tail-call-interp --disable-gil - make all --jobs 4 ./python -m test --multiprocess 0 --timeout 4500 --verbose2 --verbose3 - diff --git a/.github/workflows/verify-ensurepip-wheels.yml b/.github/workflows/verify-ensurepip-wheels.yml index 463e7bf3355cc3..cb40f6abc0b3b7 100644 --- a/.github/workflows/verify-ensurepip-wheels.yml +++ b/.github/workflows/verify-ensurepip-wheels.yml @@ -25,10 +25,10 @@ jobs: runs-on: ubuntu-latest timeout-minutes: 10 steps: - - uses: actions/checkout@v4 + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 with: persist-credentials: false - - uses: actions/setup-python@v5 + - uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0 with: python-version: '3' - name: Compare checksum of bundled wheels to the ones published on PyPI diff --git a/.github/workflows/verify-expat.yml b/.github/workflows/verify-expat.yml new file mode 100644 index 00000000000000..158e8f10377cad --- /dev/null +++ b/.github/workflows/verify-expat.yml @@ -0,0 +1,32 @@ +name: Verify bundled libexpat + +on: + workflow_dispatch: + push: + paths: + - 'Modules/expat/**' + - '.github/workflows/verify-expat.yml' + pull_request: + paths: + - 'Modules/expat/**' + - '.github/workflows/verify-expat.yml' + +permissions: + contents: read + +concurrency: + group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }} + cancel-in-progress: true + +jobs: + verify: + runs-on: ubuntu-slim + timeout-minutes: 5 + steps: + - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + persist-credentials: false + - name: Download and verify bundled libexpat files + run: | + ./Modules/expat/refresh.sh + git diff --exit-code Modules/expat/ diff --git a/.github/zizmor.yml b/.github/zizmor.yml index 9b42b47cc85545..7c776d5ea1f941 100644 --- a/.github/zizmor.yml +++ b/.github/zizmor.yml @@ -1,10 +1,6 @@ -# Configuration for the zizmor static analysis tool, run via pre-commit in CI -# https://woodruffw.github.io/zizmor/configuration/ +# Configuration for the zizmor static analysis tool, run via prek in CI +# https://docs.zizmor.sh/configuration/ rules: dangerous-triggers: ignore: - documentation-links.yml - unpinned-uses: - config: - policies: - "*": ref-pin diff --git a/.gitignore b/.gitignore index 2a6f249275c32e..67043c33d1b6e5 100644 --- a/.gitignore +++ b/.gitignore @@ -71,16 +71,15 @@ Lib/test/data/* /Makefile /Makefile.pre /iOSTestbed.* -iOS/Frameworks/ -iOS/Resources/Info.plist -iOS/testbed/build -iOS/testbed/Python.xcframework/ios-*/bin -iOS/testbed/Python.xcframework/ios-*/include -iOS/testbed/Python.xcframework/ios-*/lib -iOS/testbed/Python.xcframework/ios-*/Python.framework -iOS/testbed/iOSTestbed.xcodeproj/project.xcworkspace -iOS/testbed/iOSTestbed.xcodeproj/xcuserdata -iOS/testbed/iOSTestbed.xcodeproj/xcshareddata +Apple/iOS/Frameworks/ +Apple/iOS/Resources/Info.plist +Apple/testbed/build +Apple/testbed/Python.xcframework/*/bin +Apple/testbed/Python.xcframework/*/include +Apple/testbed/Python.xcframework/*/lib +Apple/testbed/Python.xcframework/*/Python.framework +Apple/testbed/*Testbed.xcodeproj/project.xcworkspace +Apple/testbed/*Testbed.xcodeproj/xcuserdata Mac/Makefile Mac/PythonLauncher/Info.plist Mac/PythonLauncher/Makefile @@ -135,10 +134,10 @@ Tools/unicode/data/ /config.log /config.status /config.status.lineno -# hendrikmuhs/ccache-action@v1 /.ccache -/cross-build/ +/cross-build*/ /jit_stencils*.h +/jit_unwind_info*.h /platform /profile-clean-stamp /profile-run-stamp @@ -171,5 +170,6 @@ Python/frozen_modules/MANIFEST /python !/Python/ -# main branch only: ABI files are not checked/maintained. -Doc/data/python*.abi +# People's custom https://docs.anthropic.com/en/docs/claude-code/memory configs. +/.claude/ +CLAUDE.local.md diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index 7ad829c94d50f3..8d65323022554d 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -1,41 +1,71 @@ repos: - repo: https://github.com/astral-sh/ruff-pre-commit - rev: v0.11.8 + rev: a27a2e47c7751b639d2b5badf0ef6ff11fee893f # frozen: v0.15.4 hooks: - - id: ruff + - id: ruff-check + name: Run Ruff (lint) on Apple/ + args: [--exit-non-zero-on-fix, --config=Apple/.ruff.toml] + files: ^Apple/ + - id: ruff-check name: Run Ruff (lint) on Doc/ args: [--exit-non-zero-on-fix] files: ^Doc/ - - id: ruff + - id: ruff-check name: Run Ruff (lint) on Lib/test/ args: [--exit-non-zero-on-fix] files: ^Lib/test/ - - id: ruff + - id: ruff-check name: Run Ruff (lint) on Tools/build/ args: [--exit-non-zero-on-fix, --config=Tools/build/.ruff.toml] files: ^Tools/build/ - - id: ruff + - id: ruff-check + name: Run Ruff (lint) on Tools/i18n/ + args: [--exit-non-zero-on-fix, --config=Tools/i18n/.ruff.toml] + files: ^Tools/i18n/ + - id: ruff-check name: Run Ruff (lint) on Argument Clinic args: [--exit-non-zero-on-fix, --config=Tools/clinic/.ruff.toml] files: ^Tools/clinic/|Lib/test/test_clinic.py + - id: ruff-check + name: Run Ruff (lint) on Tools/peg_generator/ + args: [--exit-non-zero-on-fix, --config=Tools/peg_generator/.ruff.toml] + files: ^Tools/peg_generator/ + - id: ruff-check + name: Run Ruff (lint) on Tools/wasm/ + args: [--exit-non-zero-on-fix, --config=Tools/wasm/.ruff.toml] + files: ^Tools/wasm/ + - id: ruff-format + name: Run Ruff (format) on Apple/ + args: [--exit-non-zero-on-fix, --config=Apple/.ruff.toml] + files: ^Apple - id: ruff-format name: Run Ruff (format) on Doc/ - args: [--check] + args: [--exit-non-zero-on-fix] files: ^Doc/ - id: ruff-format name: Run Ruff (format) on Tools/build/check_warnings.py - args: [--check, --config=Tools/build/.ruff.toml] + args: [--exit-non-zero-on-fix, --config=Tools/build/.ruff.toml] files: ^Tools/build/check_warnings.py + - id: ruff-format + name: Run Ruff (format) on Tools/wasm/ + args: [--exit-non-zero-on-fix, --config=Tools/wasm/.ruff.toml] + files: ^Tools/wasm/ - repo: https://github.com/psf/black-pre-commit-mirror - rev: 25.1.0 + rev: ea488cebbfd88a5f50b8bd95d5c829d0bb76feb8 # frozen: 26.1.0 hooks: - id: black name: Run Black on Tools/jit/ files: ^Tools/jit/ + - repo: https://github.com/Lucas-C/pre-commit-hooks + rev: ad1b27d73581aa16cca06fc4a0761fc563ffe8e8 # frozen: v1.5.6 + hooks: + - id: remove-tabs + types: [python] + - repo: https://github.com/pre-commit/pre-commit-hooks - rev: v5.0.0 + rev: 3e8a8703264a2f4a69428a0aa4dcb512790b2c8c # frozen: v6.0.0 hooks: - id: check-case-conflict - id: check-merge-conflict @@ -43,30 +73,37 @@ repos: exclude: ^Lib/test/test_tomllib/ - id: check-yaml - id: end-of-file-fixer - types: [python] + types_or: [python, yaml] exclude: Lib/test/tokenizedata/coding20731.py + - id: end-of-file-fixer + files: '^\.github/CODEOWNERS$' + - id: mixed-line-ending + args: [--fix=auto] + exclude: '^Lib/test/.*data/' + - id: trailing-whitespace + types_or: [c, inc, python, rst, yaml] - id: trailing-whitespace - types_or: [c, inc, python, rst] + files: '^\.github/CODEOWNERS|\.(gram)$' - repo: https://github.com/python-jsonschema/check-jsonschema - rev: 0.33.0 + rev: 9f48a48aa91a6040d749ad68ec70907d907a5a7f # frozen: 0.37.0 hooks: - id: check-dependabot - id: check-github-workflows - id: check-readthedocs - repo: https://github.com/rhysd/actionlint - rev: v1.7.7 + rev: 914e7df21a07ef503a81201c76d2b11c789d3fca # frozen: v1.7.12 hooks: - id: actionlint - - repo: https://github.com/woodruffw/zizmor-pre-commit - rev: v1.6.0 + - repo: https://github.com/zizmorcore/zizmor-pre-commit + rev: b546b77c44c466a54a42af5499dcc0dcc1a3193f # frozen: v1.22.0 hooks: - id: zizmor - repo: https://github.com/sphinx-contrib/sphinx-lint - rev: v1.0.0 + rev: c883505f64b59c3c5c9375191e4ad9f98e727ccd # frozen: v1.0.2 hooks: - id: sphinx-lint args: [--enable=default-role] diff --git a/.readthedocs.yml b/.readthedocs.yml index a57de00544e4e3..038417e4bb3438 100644 --- a/.readthedocs.yml +++ b/.readthedocs.yml @@ -11,25 +11,50 @@ build: os: ubuntu-24.04 tools: python: "3" + apt_packages: + - jq - commands: - # https://docs.readthedocs.io/en/stable/build-customization.html#cancel-build-based-on-a-condition - # - # Cancel building pull requests when there aren't changes in the Doc directory. - # - # If there are no changes (git diff exits with 0) we force the command to return with 183. - # This is a special exit code on Read the Docs that will cancel the build immediately. - - | - if [ "$READTHEDOCS_VERSION_TYPE" = "external" ] && [ "$(git diff --quiet origin/main -- Doc/ .readthedocs.yml; echo $?)" -eq 0 ]; - then - echo "No changes to Doc/ - exiting the build."; - exit 183; - fi - - - asdf plugin add uv - - asdf install uv latest - - asdf global uv latest - - make -C Doc venv html - - mkdir _readthedocs - - mv Doc/build/html _readthedocs/html - + jobs: + post_system_dependencies: + # https://docs.readthedocs.com/platform/stable/guides/build/skip-build.html#skip-builds-based-on-conditions + # + # Cancel building pull requests when there are no changes in the Doc + # directory or RTD configuration, or if we can't cleanly merge the base + # branch. + - | + set -eEux; + if [ "$READTHEDOCS_VERSION_TYPE" = "external" ]; + then + base_branch=$(wget -qO- "https://api.github.com/repos/python/cpython/pulls/$READTHEDOCS_VERSION" | jq -er ".base.ref"); + git fetch --depth=50 origin $base_branch:origin-$base_branch; + for attempt in $(seq 10); + do + if ! git merge-base HEAD origin-$base_branch; + then + git fetch --deepen=50 origin $base_branch; + else + break; + fi; + done; + if ! git -c "user.name=rtd" -c "user.email=no-reply@readthedocs.org" merge --no-stat --no-edit origin-$base_branch; + then + echo "Unsuccessful merge with '$base_branch' branch, skipping the build"; + exit 183; + fi; + if git diff --exit-code --stat origin-$base_branch -- Doc/ .readthedocs.yml; + then + echo "No changes to Doc/ - skipping the build."; + exit 183; + fi; + fi; + create_environment: + - echo "Skipping default environment creation" + install: + - asdf plugin add uv + - asdf install uv latest + - asdf global uv latest + build: + html: + - make -C Doc venv html + - mkdir -p "$READTHEDOCS_OUTPUT" + - mv Doc/build/html "$READTHEDOCS_OUTPUT/" diff --git a/Android/README.md b/Android/README.md index 6cabd6ba5d6844..271ef94d0b40df 100644 --- a/Android/README.md +++ b/Android/README.md @@ -31,7 +31,8 @@ any packages it needs. The script also requires the following commands to be on the `PATH`: * `curl` -* `java` (or set the `JAVA_HOME` environment variable) +* `java` (or set the `JAVA_HOME` environment variable). + Java versions 17, 21 and 25 are supported. ## Building @@ -96,18 +97,12 @@ similar to the `Android` directory of the CPython source tree. ## Testing -The Python test suite can be run on Linux, macOS, or Windows: +The Python test suite can be run on Linux, macOS, or Windows. -* On Linux, the emulator needs access to the KVM virtualization interface, and - a DISPLAY environment variable pointing at an X server. Xvfb is acceptable. - -The test suite can usually be run on a device with 2 GB of RAM, but this is -borderline, so you may need to increase it to 4 GB. As of Android -Studio Koala, 2 GB is the default for all emulators, although the user interface -may indicate otherwise. Locate the emulator's directory under `~/.android/avd`, -and find `hw.ramSize` in both config.ini and hardware-qemu.ini. Either set these -manually to the same value, or use the Android Studio Device Manager, which will -update both files. +On Linux, the emulator needs access to the KVM virtualization interface. This may +require adding your user to a group, or changing your udev rules. On GitHub +Actions, the test script will do this automatically using the commands shown +[here](https://github.blog/changelog/2024-04-02-github-actions-hardware-accelerated-android-virtualization-now-available/). You can run the test suite either: @@ -156,6 +151,10 @@ repository's `Lib` directory will be picked up immediately. Changes in C files, and architecture-specific files such as sysconfigdata, will not take effect until you re-run `android.py make-host` or `build`. +The testbed app can also be used to test third-party packages. For more details, +run `android.py test --help`, paying attention to the options `--site-packages`, +`--cwd`, `-c` and `-m`. + ## Using in your own app diff --git a/Android/android-env.sh b/Android/android-env.sh index bab4130c9e92d0..59ce2eeb7d6224 100644 --- a/Android/android-env.sh +++ b/Android/android-env.sh @@ -3,11 +3,11 @@ : "${HOST:?}" # GNU target triplet # You may also override the following: -: "${api_level:=24}" # Minimum Android API level the build will run on +: "${ANDROID_API_LEVEL:=24}" # Minimum Android API level the build will run on : "${PREFIX:-}" # Path in which to find required libraries -# Print all messages on stderr so they're visible when running within build-wheel. +# Print all messages on stderr so they're visible when stdout is captured. log() { echo "$1" >&2 } @@ -24,10 +24,10 @@ fail() { # * https://android.googlesource.com/platform/ndk/+/ndk-rXX-release/docs/BuildSystemMaintainers.md # where XX is the NDK version. Do a diff against the version you're upgrading from, e.g.: # https://android.googlesource.com/platform/ndk/+/ndk-r25-release..ndk-r26-release/docs/BuildSystemMaintainers.md -ndk_version=27.1.12297006 +ndk_version=27.3.13750724 ndk=$ANDROID_HOME/ndk/$ndk_version -if ! [ -e "$ndk" ]; then +if ! [ -e "$ndk/package.xml" ]; then log "Installing NDK - this may take several minutes" yes | "$ANDROID_HOME/cmdline-tools/latest/bin/sdkmanager" "ndk;$ndk_version" fi @@ -43,7 +43,7 @@ fi toolchain=$(echo "$ndk"/toolchains/llvm/prebuilt/*) export AR="$toolchain/bin/llvm-ar" export AS="$toolchain/bin/llvm-as" -export CC="$toolchain/bin/${clang_triplet}${api_level}-clang" +export CC="$toolchain/bin/${clang_triplet}${ANDROID_API_LEVEL}-clang" export CXX="${CC}++" export LD="$toolchain/bin/ld" export NM="$toolchain/bin/llvm-nm" diff --git a/Android/android.py b/Android/android.py index 3f48b42aa17571..73b7a1361d61b6 100755 --- a/Android/android.py +++ b/Android/android.py @@ -2,7 +2,9 @@ import asyncio import argparse +import json import os +import platform import re import shlex import shutil @@ -13,8 +15,9 @@ from asyncio import wait_for from contextlib import asynccontextmanager from datetime import datetime, timezone +from enum import IntEnum, auto from glob import glob -from os.path import basename, relpath +from os.path import abspath, basename, relpath from pathlib import Path from subprocess import CalledProcessError from tempfile import TemporaryDirectory @@ -22,11 +25,21 @@ SCRIPT_NAME = Path(__file__).name ANDROID_DIR = Path(__file__).resolve().parent -CHECKOUT = ANDROID_DIR.parent -TESTBED_DIR = ANDROID_DIR / "testbed" -CROSS_BUILD_DIR = CHECKOUT / "cross-build" +PYTHON_DIR = ANDROID_DIR.parent +in_source_tree = ( + ANDROID_DIR.name == "Android" and (PYTHON_DIR / "pyconfig.h.in").exists() +) -HOSTS = ["aarch64-linux-android", "x86_64-linux-android"] +ENV_SCRIPT = ANDROID_DIR / "android-env.sh" +TESTBED_DIR = ANDROID_DIR / "testbed" +CROSS_BUILD_DIR = PYTHON_DIR / "cross-build" + +HOSTS = [ + "aarch64-linux-android", + "arm-linux-androideabi", + "i686-linux-android", + "x86_64-linux-android", +] APP_ID = "org.python.testbed" DECODE_ARGS = ("UTF-8", "backslashreplace") @@ -46,7 +59,32 @@ + (".bat" if os.name == "nt" else "") ) -logcat_started = False +# Whether we've seen any output from Python yet. +python_started = False + +# Buffer for verbose output which will be displayed only if a test fails and +# there has been no output from Python. +hidden_output = [] + + +# Based on android/log.h in the NDK. +class LogPriority(IntEnum): + UNKNOWN = 0 + DEFAULT = auto() + VERBOSE = auto() + DEBUG = auto() + INFO = auto() + WARN = auto() + ERROR = auto() + FATAL = auto() + SILENT = auto() + + +def log_verbose(context, line, stream=sys.stdout): + if context.verbose: + stream.write(line) + else: + hidden_output.append((stream, line)) def delete_glob(pattern): @@ -76,39 +114,67 @@ def run(command, *, host=None, env=None, log=True, **kwargs): kwargs.setdefault("check", True) if env is None: env = os.environ.copy() - original_env = env.copy() if host: - env_script = ANDROID_DIR / "android-env.sh" - env_output = subprocess.run( - f"set -eu; " - f"HOST={host}; " - f"PREFIX={subdir(host)}/prefix; " - f". {env_script}; " - f"export", - check=True, shell=True, text=True, stdout=subprocess.PIPE - ).stdout - - for line in env_output.splitlines(): - # We don't require every line to match, as there may be some other - # output from installing the NDK. - if match := re.search( - "^(declare -x |export )?(\\w+)=['\"]?(.*?)['\"]?$", line - ): - key, value = match[2], match[3] - if env.get(key) != value: - print(line) - env[key] = value - - if env == original_env: - raise ValueError(f"Found no variables in {env_script.name} output:\n" - + env_output) + host_env = android_env(host) + print_env(host_env) + env.update(host_env) if log: - print(">", " ".join(map(str, command))) + print(">", join_command(command)) return subprocess.run(command, env=env, **kwargs) +# Format a command so it can be copied into a shell. Like shlex.join, but also +# accepts arguments which are Paths, or a single string/Path outside of a list. +def join_command(args): + if isinstance(args, (str, Path)): + return str(args) + else: + return shlex.join(map(str, args)) + + +# Format the environment so it can be pasted into a shell. +def print_env(env): + for key, value in sorted(env.items()): + print(f"export {key}={shlex.quote(value)}") + + +def android_env(host): + if host: + prefix = subdir(host) / "prefix" + else: + prefix = ANDROID_DIR / "prefix" + sysconfig_files = prefix.glob("lib/python*/_sysconfigdata__android_*.py") + sysconfig_filename = next(sysconfig_files).name + host = re.fullmatch(r"_sysconfigdata__android_(.+).py", sysconfig_filename)[1] + + env_output = subprocess.run( + f"set -eu; " + f"HOST={host}; " + f"PREFIX={prefix}; " + f". {ENV_SCRIPT}; " + f"export", + check=True, shell=True, stdout=subprocess.PIPE, encoding='utf-8', + ).stdout + + env = {} + for line in env_output.splitlines(): + # We don't require every line to match, as there may be some other + # output from installing the NDK. + if match := re.search( + "^(declare -x |export )?(\\w+)=['\"]?(.*?)['\"]?$", line + ): + key, value = match[2], match[3] + if os.environ.get(key) != value: + env[key] = value + + if not env: + raise ValueError(f"Found no variables in {ENV_SCRIPT.name} output:\n" + + env_output) + return env + + def build_python_path(): """The path to the build Python binary.""" build_dir = subdir("build") @@ -127,7 +193,7 @@ def configure_build_python(context): clean("build") os.chdir(subdir("build", create=True)) - command = [relpath(CHECKOUT / "configure")] + command = [relpath(PYTHON_DIR / "configure")] if context.args: command.extend(context.args) run(command) @@ -138,37 +204,65 @@ def make_build_python(context): run(["make", "-j", str(os.cpu_count())]) -def unpack_deps(host, prefix_dir): +def pythoninfo_build_python(context): + os.chdir(subdir("build")) + run(["make", "pythoninfo"]) + + +# To create new builds of these dependencies, usually all that's necessary is to +# push a tag to the cpython-android-source-deps repository, and GitHub Actions +# will do the rest. +# +# If you're a member of the Python core team, and you'd like to be able to push +# these tags yourself, please contact Malcolm Smith or Russell Keith-Magee. +def unpack_deps(host, prefix_dir, cache_dir): + os.chdir(prefix_dir) deps_url = "https://github.com/beeware/cpython-android-source-deps/releases/download" - for name_ver in ["bzip2-1.0.8-2", "libffi-3.4.4-3", "openssl-3.0.15-4", - "sqlite-3.49.1-0", "xz-5.4.6-1"]: + for name_ver in [ + "bzip2-1.0.8-3", + "libffi-3.4.4-3", + "openssl-3.5.7-0", + "sqlite-3.50.4-0", + "xz-5.4.6-1", + "zstd-1.5.7-2" + ]: filename = f"{name_ver}-{host}.tar.gz" - download(f"{deps_url}/{name_ver}/{filename}") - shutil.unpack_archive(filename, prefix_dir) - os.remove(filename) + out_path = download(f"{deps_url}/{name_ver}/{filename}", cache_dir) + shutil.unpack_archive(out_path) -def download(url, target_dir="."): - out_path = f"{target_dir}/{basename(url)}" - run(["curl", "-Lf", "--retry", "5", "--retry-all-errors", "-o", out_path, url]) +def download(url, cache_dir): + out_path = cache_dir / basename(url) + cache_dir.mkdir(parents=True, exist_ok=True) + if not out_path.is_file(): + run(["curl", "-Lf", "--retry", "5", "--retry-all-errors", "-o", out_path, url]) + else: + print(f"Using cached version of {basename(url)}") return out_path -def configure_host_python(context): +def configure_host_python(context, host=None): + if host is None: + host = context.host if context.clean: - clean(context.host) + clean(host) - host_dir = subdir(context.host, create=True) + host_dir = subdir(host, create=True) prefix_dir = host_dir / "prefix" if not prefix_dir.exists(): prefix_dir.mkdir() - unpack_deps(context.host, prefix_dir) + cache_dir = ( + Path(context.cache_dir).resolve() + if context.cache_dir + else CROSS_BUILD_DIR / "downloads" + ) + unpack_deps(host, prefix_dir, cache_dir) os.chdir(host_dir) command = [ # Basic cross-compiling configuration - relpath(CHECKOUT / "configure"), - f"--host={context.host}", + relpath(PYTHON_DIR / "configure"), + f"--host={host}", f"--build={sysconfig.get_config_var('BUILD_GNU_TYPE')}", f"--with-build-python={build_python_path()}", "--without-ensurepip", @@ -184,37 +278,84 @@ def configure_host_python(context): if context.args: command.extend(context.args) - run(command, host=context.host) + run(command, host=host) -def make_host_python(context): +def make_host_python(context, host=None): + if host is None: + host = context.host # The CFLAGS and LDFLAGS set in android-env include the prefix dir, so # delete any previous Python installation to prevent it being used during # the build. - host_dir = subdir(context.host) + host_dir = subdir(host) prefix_dir = host_dir / "prefix" for pattern in ("include/python*", "lib/libpython*", "lib/python*"): delete_glob(f"{prefix_dir}/{pattern}") + # The Android environment variables were already captured in the Makefile by + # `configure`, and passing them again when running `make` may cause some + # flags to be duplicated. So we don't use the `host` argument here. os.chdir(host_dir) - run(["make", "-j", str(os.cpu_count())], host=context.host) - run(["make", "install", f"prefix={prefix_dir}"], host=context.host) + run(["make", "-j", str(os.cpu_count())]) + + # The `make install` output is very verbose and rarely useful, so + # suppress it by default. + run( + ["make", "install", f"prefix={prefix_dir}"], + capture_output=not context.verbose, + ) + +def build_targets(context): + if context.target in {"all", "build"}: + configure_build_python(context) + make_build_python(context) + pythoninfo_build_python(context) -def build_all(context): - steps = [configure_build_python, make_build_python, configure_host_python, - make_host_python] - for step in steps: - step(context) + for host in HOSTS: + if context.target in {"all", "hosts", host}: + configure_host_python(context, host) + make_host_python(context, host) def clean(host): delete_glob(CROSS_BUILD_DIR / host) -def clean_all(context): - for host in HOSTS + ["build"]: - clean(host) +def clean_targets(context): + if context.target in {"all", "build"}: + clean("build") + + for host in HOSTS: + if context.target in {"all", "hosts", host}: + clean(host) + + +def setup_ci(): + if "GITHUB_ACTIONS" in os.environ: + # Enable emulator hardware acceleration + # (https://github.blog/changelog/2024-04-02-github-actions-hardware-accelerated-android-virtualization-now-available/). + if platform.system() == "Linux": + run( + ["sudo", "tee", "/etc/udev/rules.d/99-kvm4all.rules"], + input='KERNEL=="kvm", GROUP="kvm", MODE="0666", OPTIONS+="static_node=kvm"\n', + text=True, + ) + run(["sudo", "udevadm", "control", "--reload-rules"]) + run(["sudo", "udevadm", "trigger", "--name-match=kvm"]) + + # Free up disk space by deleting unused versions of the NDK + # (https://github.com/freakboy3742/pyspamsum/pull/108). + for line in ENV_SCRIPT.read_text().splitlines(): + if match := re.fullmatch(r"ndk_version=(.+)", line): + ndk_version = match[1] + break + else: + raise ValueError(f"Failed to find NDK version in {ENV_SCRIPT.name}") + + for item in (android_home / "ndk").iterdir(): + if item.name[0].isdigit() and item.name != ndk_version: + delete_glob(item) def setup_sdk(): @@ -228,7 +369,12 @@ def setup_sdk(): if not all((android_home / "licenses" / path).exists() for path in [ "android-sdk-arm-dbt-license", "android-sdk-license" ]): - run([sdkmanager, "--licenses"], text=True, input="y\n" * 100) + run( + [sdkmanager, "--licenses"], + text=True, + capture_output=True, + input="y\n" * 100, + ) # Gradle may install this automatically, but we can't rely on that because # we need to run adb within the logcat task. @@ -244,10 +390,10 @@ def setup_testbed(): if all((TESTBED_DIR / path).exists() for path in paths): return - # The wrapper version isn't important, as any version of the wrapper can - # download any version of Gradle. The Gradle version actually used for the - # build is specified in testbed/gradle/wrapper/gradle-wrapper.properties. - version = "8.9.0" + # Any version of the wrapper can run any reasonably close version of Gradle, so this + # doesn't need to match the Gradle version used for the build, which is specified in + # testbed/gradle/wrapper/gradle-wrapper.properties. + version = "9.5.0" for path in paths: out_path = TESTBED_DIR / path @@ -259,17 +405,6 @@ def setup_testbed(): os.chmod(out_path, 0o755) -# run_testbed will build the app automatically, but it's useful to have this as -# a separate command to allow running the app outside of this script. -def build_testbed(context): - setup_sdk() - setup_testbed() - run( - [gradlew, "--console", "plain", "packageDebug", "packageDebugAndroidTest"], - cwd=TESTBED_DIR, - ) - - # Work around a bug involving sys.exit and TaskGroups # (https://github.com/python/cpython/issues/101515). def exit(*args): @@ -410,19 +545,23 @@ async def logcat_task(context, initial_devices): pid = await wait_for(find_pid(serial), startup_timeout) # `--pid` requires API level 24 or higher. - args = [adb, "-s", serial, "logcat", "--pid", pid, "--format", "tag"] - hidden_output = [] + # + # `--binary` mode is used in order to detect which messages end with a + # newline, which most of the other modes don't indicate (except `--format + # long`). For example, every time pytest runs a test, it prints a "." and + # flushes the stream. Each "." becomes a separate log message, but we should + # show them all on the same line. + args = [adb, "-s", serial, "logcat", "--pid", pid, "--binary"] + logcat_started = False async with async_process( - *args, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, + *args, stdout=subprocess.PIPE, stderr=None ) as process: - while line := (await process.stdout.readline()).decode(*DECODE_ARGS): - if match := re.fullmatch(r"([A-Z])/(.*)", line, re.DOTALL): - level, message = match.groups() - else: - # If the regex doesn't match, this is probably the second or - # subsequent line of a multi-line message. Python won't produce - # such messages, but other components might. - level, message = None, line + while True: + try: + priority, tag, message = await read_logcat(process.stdout) + logcat_started = True + except asyncio.IncompleteReadError: + break # Exclude high-volume messages which are rarely useful. if context.verbose < 2 and "from python test_syslog" in message: @@ -430,36 +569,70 @@ async def logcat_task(context, initial_devices): # Put high-level messages on stderr so they're highlighted in the # buildbot logs. This will include Python's own stderr. - stream = ( - sys.stderr - if level in ["W", "E", "F"] # WARNING, ERROR, FATAL (aka ASSERT) - else sys.stdout - ) - - # To simplify automated processing of the output, e.g. a buildbot - # posting a failure notice on a GitHub PR, we strip the level and - # tag indicators from Python's stdout and stderr. - for prefix in ["python.stdout: ", "python.stderr: "]: - if message.startswith(prefix): - global logcat_started - logcat_started = True - stream.write(message.removeprefix(prefix)) - break + stream = sys.stderr if priority >= LogPriority.WARN else sys.stdout + + # The app's stdout and stderr should be passed through transparently + # to our own corresponding streams. + if tag in ["python.stdout", "python.stderr"]: + global python_started + python_started = True + stream.write(message) + stream.flush() else: - if context.verbose: - # Non-Python messages add a lot of noise, but they may - # sometimes help explain a failure. - stream.write(line) - else: - hidden_output.append(line) + # Non-Python messages add a lot of noise, but they may + # sometimes help explain a failure. Format them in the same way + # as `logcat --format tag`. + formatted = f"{priority.name[0]}/{tag}: {message}" + if not formatted.endswith("\n"): + formatted += "\n" + log_verbose(context, formatted, stream) # If the device disconnects while logcat is running, which always # happens in --managed mode, some versions of adb return non-zero. # Distinguish this from a logcat startup error by checking whether we've - # received a message from Python yet. + # received any logcat messages yet. status = await wait_for(process.wait(), timeout=1) if status != 0 and not logcat_started: - raise CalledProcessError(status, args, "".join(hidden_output)) + raise CalledProcessError(status, args) + + +# Read one binary log message from the given StreamReader. The message format is +# described at https://android.stackexchange.com/a/74660. All supported versions +# of Android use format version 2 or later. +async def read_logcat(stream): + async def read_bytes(size): + return await stream.readexactly(size) + + async def read_int(size): + return int.from_bytes(await read_bytes(size), "little") + + payload_len = await read_int(2) + if payload_len < 2: + # 1 byte for priority, 1 byte for null terminator of tag. + raise ValueError(f"payload length {payload_len} is too short") + + header_len = await read_int(2) + if header_len < 4: + raise ValueError(f"header length {header_len} is too short") + await read_bytes(header_len - 4) # Ignore other header fields. + + priority_int = await read_int(1) + try: + priority = LogPriority(priority_int) + except ValueError: + priority = LogPriority.UNKNOWN + + payload = await read_bytes(payload_len - 1) + payload_fields = payload.split(b"\0") + if len(payload_fields) < 2: + raise ValueError( + f"payload {payload!r} does not contain at least 2 " + f"null-separated fields" + ) + tag, message, *_ = [ + field.decode(*DECODE_ARGS) for field in payload_fields + ] + return priority, tag, message def stop_app(serial): @@ -474,12 +647,42 @@ async def gradle_task(context): task_prefix = "connected" env["ANDROID_SERIAL"] = context.connected + # Ensure that CROSS_BUILD_DIR is in the Gradle environment, regardless + # of whether it was set by environment variable or `--cross-build-dir`. + env["CROSS_BUILD_DIR"] = CROSS_BUILD_DIR + + if context.ci_mode: + context.args[0:0] = [ + # See _add_ci_python_opts in libregrtest/main.py. + "-W", "error", "-bb", "-E", + + # Randomization is disabled because order-dependent failures are + # much less likely to pass on a rerun in single-process mode. + "-m", "test", + f"--{context.ci_mode}-ci", "--single-process", "--no-randomize" + ] + + if not any(arg in context.args for arg in ["-c", "-m"]): + context.args[0:0] = ["-m", "test"] + args = [ gradlew, "--console", "plain", f"{task_prefix}DebugAndroidTest", - "-Pandroid.testInstrumentationRunnerArguments.pythonArgs=" - + shlex.join(context.args), + ] + [ + f"-P{name}={value}" + for name, value in [ + ("python.sitePackages", context.site_packages), + ("python.cwd", context.cwd), + ( + "android.testInstrumentationRunnerArguments.pythonArgs", + json.dumps(context.args), + ), + ] + if value ] - hidden_output = [] + if context.verbose >= 2: + args.append("--info") + log_verbose(context, f"> {join_command(args)}\n") + try: async with async_process( *args, cwd=TESTBED_DIR, env=env, @@ -488,10 +691,10 @@ async def gradle_task(context): while line := (await process.stdout.readline()).decode(*DECODE_ARGS): # Gradle may take several minutes to install SDK packages, so # it's worth showing those messages even in non-verbose mode. - if context.verbose or line.startswith('Preparing "Install'): + if line.startswith('Preparing "Install'): sys.stdout.write(line) else: - hidden_output.append(line) + log_verbose(context, line) status = await wait_for(process.wait(), timeout=1) if status == 0: @@ -499,17 +702,13 @@ async def gradle_task(context): else: raise CalledProcessError(status, args) finally: - # If logcat never started, then something has gone badly wrong, so the - # user probably wants to see the Gradle output even in non-verbose mode. - if hidden_output and not logcat_started: - sys.stdout.write("".join(hidden_output)) - # Gradle does not stop the tests when interrupted. if context.connected: stop_app(context.connected) async def run_testbed(context): + setup_ci() setup_sdk() setup_testbed() @@ -533,6 +732,12 @@ async def run_testbed(context): except* MySystemExit as e: raise SystemExit(*e.exceptions[0].args) from None except* CalledProcessError as e: + # If Python produced no output, then the user probably wants to see the + # verbose output to explain why the test failed. + if not python_started: + for stream, line in hidden_output: + stream.write(line) + # Extract it from the ExceptionGroup so it can be handled by `main`. raise e.exceptions[0] @@ -597,11 +802,65 @@ def package(context): else: shutil.copy2(src, dst, follow_symlinks=False) + # Strip debug information. + if not context.debug: + so_files = glob(f"{temp_dir}/**/*.so", recursive=True) + run([android_env(context.host)["STRIP"], *so_files], log=False) + dist_dir = subdir(context.host, "dist", create=True) package_path = shutil.make_archive( f"{dist_dir}/python-{version}-{context.host}", "gztar", temp_dir ) print(f"Wrote {package_path}") + return package_path + + +def ci(context): + for step in [ + configure_build_python, + make_build_python, + pythoninfo_build_python, + configure_host_python, + make_host_python, + package, + ]: + caption = ( + step.__name__.replace("_", " ") + .capitalize() + .replace("python", "Python") + ) + print(f"::group::{caption}") + result = step(context) + if step is package: + package_path = result + print("::endgroup::") + + if ( + "GITHUB_ACTIONS" in os.environ + and (platform.system(), platform.machine()) != ("Linux", "x86_64") + ): + print( + "Skipping tests: GitHub Actions does not support the Android " + "emulator on this platform." + ) + else: + with TemporaryDirectory(prefix=SCRIPT_NAME) as temp_dir: + print("::group::Tests") + + # Prove the package is self-contained by using it to run the tests. + shutil.unpack_archive(package_path, temp_dir) + launcher_args = [ + "--managed", "maxVersion", "-v", f"--{context.ci_mode}-ci" + ] + run( + ["./android.py", "test", *launcher_args], + cwd=temp_dir + ) + print("::endgroup::") + + +def env(context): + print_env(android_env(getattr(context, "host", None))) # Handle SIGTERM the same way as SIGINT. This ensures that if we're terminated @@ -615,45 +874,96 @@ def signal_handler(*args): def parse_args(): parser = argparse.ArgumentParser() - subcommands = parser.add_subparsers(dest="subcommand") + subcommands = parser.add_subparsers(dest="subcommand", required=True) + + def add_parser(*args, **kwargs): + parser = subcommands.add_parser(*args, **kwargs) + parser.add_argument( + "--cross-build-dir", + action="store", + default=os.environ.get("CROSS_BUILD_DIR"), + dest="cross_build_dir", + type=Path, + help=( + "Path to the cross-build directory " + f"(default: {CROSS_BUILD_DIR}). Can also be set " + "with the CROSS_BUILD_DIR environment variable." + ), + ) + parser.add_argument( + "-v", "--verbose", action="count", default=0, + help="Show verbose output. Use twice to be even more verbose.") + return parser # Subcommands - build = subcommands.add_parser("build", help="Build everything") - configure_build = subcommands.add_parser("configure-build", - help="Run `configure` for the " - "build Python") - make_build = subcommands.add_parser("make-build", - help="Run `make` for the build Python") - configure_host = subcommands.add_parser("configure-host", - help="Run `configure` for Android") - make_host = subcommands.add_parser("make-host", - help="Run `make` for Android") - subcommands.add_parser( - "clean", help="Delete all build and prefix directories") - subcommands.add_parser( - "build-testbed", help="Build the testbed app") - test = subcommands.add_parser( - "test", help="Run the test suite") - package = subcommands.add_parser("package", help="Make a release package") + build = add_parser( + "build", + help="Run configure and make for the selected target" + ) + configure_build = add_parser( + "configure-build", help="Run `configure` for the build Python") + add_parser( + "make-build", help="Run `make` for the build Python") + add_parser( + "pythoninfo-build", help="Display build info of the build Python") + configure_host = add_parser( + "configure-host", help="Run `configure` for Android") + make_host = add_parser( + "make-host", help="Run `make` for Android") + + clean = add_parser( + "clean", + help="Delete build directories for the selected target" + ) + + test = add_parser("test", help="Run the testbed app") + package = add_parser("package", help="Make a release package") + ci = add_parser("ci", help="Run build, package and test") + env = add_parser("env", help="Print environment variables") # Common arguments - for subcommand in build, configure_build, configure_host: + # --cache-dir option + for cmd in [configure_host, build, ci]: + cmd.add_argument( + "--cache-dir", + default=os.environ.get("CACHE_DIR"), + help="The directory to store cached downloads.", + ) + + # --clean option + for subcommand in [build, configure_build, configure_host, ci]: subcommand.add_argument( "--clean", action="store_true", default=False, dest="clean", - help="Delete the relevant build and prefix directories first") - for subcommand in [build, configure_host, make_host, package]: + help="Delete the relevant build directories first") + + # Allow "all", "build" and "hosts" targets for some commands + for subcommand in [clean, build]: + subcommand.add_argument( + "target", + nargs="?", + default="all", + choices=["all", "build", "hosts"] + HOSTS, + help=( + "The host triplet (e.g., aarch64-linux-android), " + "or 'build' for just the build platform, or 'hosts' for all " + "host platforms, or 'all' for the build platform and all " + "hosts. Defaults to 'all'" + ), + ) + + host_commands = [configure_host, make_host, package, ci] + if in_source_tree: + host_commands.append(env) + for subcommand in host_commands: subcommand.add_argument( "host", metavar="HOST", choices=HOSTS, help="Host triplet: choices=[%(choices)s]") - for subcommand in build, configure_build, configure_host: + + for subcommand in [build, configure_build, configure_host, ci]: subcommand.add_argument("args", nargs="*", help="Extra arguments to pass to `configure`") # Test arguments - test.add_argument( - "-v", "--verbose", action="count", default=0, - help="Show Gradle output, and non-Python logcat messages. " - "Use twice to include high-volume messages which are rarely useful.") device_group = test.add_mutually_exclusive_group(required=True) device_group.add_argument( "--connected", metavar="SERIAL", help="Run on a connected device. " @@ -661,9 +971,34 @@ def parse_args(): device_group.add_argument( "--managed", metavar="NAME", help="Run on a Gradle-managed device. " "These are defined in `managedDevices` in testbed/app/build.gradle.kts.") + + test.add_argument( + "--site-packages", metavar="DIR", type=abspath, + help="Directory to copy as the app's site-packages.") + test.add_argument( + "--cwd", metavar="DIR", type=abspath, + help="Directory to copy as the app's working directory.") test.add_argument( - "args", nargs="*", help=f"Arguments for `python -m test`. " - f"Separate them from {SCRIPT_NAME}'s own arguments with `--`.") + "args", nargs="*", help=f"Python command-line arguments. " + f"Separate them from {SCRIPT_NAME}'s own arguments with `--`. " + f"If neither -c nor -m are included, `-m test` will be prepended, " + f"which will run Python's own test suite.") + + # Package arguments. + for subcommand in [package, ci]: + subcommand.add_argument( + "-g", action="store_true", default=False, dest="debug", + help="Include debug information in package") + + # CI arguments + for subcommand in [test, ci]: + group = subcommand.add_mutually_exclusive_group(required=subcommand is ci) + group.add_argument( + "--fast-ci", action="store_const", dest="ci_mode", const="fast", + help="Add test arguments for GitHub Actions") + group.add_argument( + "--slow-ci", action="store_const", dest="ci_mode", const="slow", + help="Add test arguments for buildbots") return parser.parse_args() @@ -678,16 +1013,24 @@ def main(): stream.reconfigure(line_buffering=True) context = parse_args() + + # Set the CROSS_BUILD_DIR if an argument was provided + if context.cross_build_dir: + global CROSS_BUILD_DIR + CROSS_BUILD_DIR = context.cross_build_dir.resolve() + dispatch = { "configure-build": configure_build_python, "make-build": make_build_python, + "pythoninfo-build": pythoninfo_build_python, "configure-host": configure_host_python, "make-host": make_host_python, - "build": build_all, - "clean": clean_all, - "build-testbed": build_testbed, + "build": build_targets, + "clean": clean_targets, "test": run_testbed, "package": package, + "ci": ci, + "env": env, } try: @@ -702,20 +1045,17 @@ def main(): def print_called_process_error(e): for stream_name in ["stdout", "stderr"]: content = getattr(e, stream_name) + if isinstance(content, bytes): + content = content.decode(*DECODE_ARGS) stream = getattr(sys, stream_name) if content: stream.write(content) if not content.endswith("\n"): stream.write("\n") - # Format the command so it can be copied into a shell. shlex uses single - # quotes, so we surround the whole command with double quotes. - args_joined = ( - e.cmd if isinstance(e.cmd, str) - else " ".join(shlex.quote(str(arg)) for arg in e.cmd) - ) + # shlex uses single quotes, so we surround the command with double quotes. print( - f'Command "{args_joined}" returned exit status {e.returncode}' + f'Command "{join_command(e.cmd)}" returned exit status {e.returncode}' ) diff --git a/Android/testbed/app/build.gradle.kts b/Android/testbed/app/build.gradle.kts index c627cb1b0e0b22..e724ba7dbc9d1c 100644 --- a/Android/testbed/app/build.gradle.kts +++ b/Android/testbed/app/build.gradle.kts @@ -3,21 +3,30 @@ import kotlin.math.max plugins { id("com.android.application") - id("org.jetbrains.kotlin.android") } val ANDROID_DIR = file("../..") val PYTHON_DIR = ANDROID_DIR.parentFile!! -val PYTHON_CROSS_DIR = file("$PYTHON_DIR/cross-build") +val PYTHON_CROSS_DIR = file(System.getenv("CROSS_BUILD_DIR") ?: "$PYTHON_DIR/cross-build") val inSourceTree = ( ANDROID_DIR.name == "Android" && file("$PYTHON_DIR/pyconfig.h.in").exists() ) val KNOWN_ABIS = mapOf( "aarch64-linux-android" to "arm64-v8a", + "arm-linux-androideabi" to "armeabi-v7a", + "i686-linux-android" to "x86", "x86_64-linux-android" to "x86_64", ) +val osArch = System.getProperty("os.arch") +val NATIVE_ABI = mapOf( + "aarch64" to "arm64-v8a", + "amd64" to "x86_64", + "arm64" to "arm64-v8a", + "x86_64" to "x86_64", +)[osArch] ?: throw GradleException("Unknown os.arch '$osArch'") + // Discover prefixes. val prefixes = ArrayList() if (inSourceTree) { @@ -47,7 +56,7 @@ for ((i, prefix) in prefixes.withIndex()) { val libDir = file("$prefix/lib") val version = run { for (filename in libDir.list()!!) { - """python(\d+\.\d+)""".toRegex().matchEntire(filename)?.let { + """python(\d+\.\d+[a-z]*)""".toRegex().matchEntire(filename)?.let { return@run it.groupValues[1] } } @@ -64,9 +73,10 @@ for ((i, prefix) in prefixes.withIndex()) { val libPythonDir = file("$libDir/python$pythonVersion") val triplet = run { for (filename in libPythonDir.list()!!) { - """_sysconfigdata__android_(.+).py""".toRegex().matchEntire(filename)?.let { - return@run it.groupValues[1] - } + """_sysconfigdata_[a-z]*_android_(.+).py""".toRegex() + .matchEntire(filename)?.let { + return@run it.groupValues[1] + } } throw GradleException("Failed to find Python triplet in $libPythonDir") } @@ -78,20 +88,29 @@ android { val androidEnvFile = file("../../android-env.sh").absoluteFile namespace = "org.python.testbed" - compileSdk = 34 + compileSdk = 35 defaultConfig { applicationId = "org.python.testbed" minSdk = androidEnvFile.useLines { for (line in it) { - """api_level:=(\d+)""".toRegex().find(line)?.let { + """ANDROID_API_LEVEL:=(\d+)""".toRegex().find(line)?.let { return@useLines it.groupValues[1].toInt() } } throw GradleException("Failed to find API level in $androidEnvFile") } - targetSdk = 34 + + // This controls the API level of the maxVersion managed emulator, which is used + // by CI and cibuildwheel. + // * 32 has intermittent failures accessing the internet (#142387). + // * 33 has excessive buffering in the logcat client + // (https://cs.android.com/android/_/android/platform/system/logging/+/d340721894f223327339010df59b0ac514308826). + // * 34 consumes too much disk space on GitHub Actions (#142289), though switching to the + // "default" image may be a workaround. + // * 36 and later are not available as aosp_atd images yet. + targetSdk = 35 versionCode = 1 versionName = "1.0" @@ -124,21 +143,17 @@ android { path("src/main/c/CMakeLists.txt") } - // Set this property to something non-empty, otherwise it'll use the default - // list, which ignores asset directories beginning with an underscore. - aaptOptions.ignoreAssetsPattern = ".git" - compileOptions { sourceCompatibility = JavaVersion.VERSION_1_8 targetCompatibility = JavaVersion.VERSION_1_8 } - kotlinOptions { - jvmTarget = "1.8" - } testOptions { managedDevices { localDevices { + // systemImageSource should use what its documentation calls an + // "explicit source", i.e. the sdkmanager package name format, because + // that will be required in CreateEmulatorTask below. create("minVersion") { device = "Small Phone" @@ -147,13 +162,13 @@ android { // ATD devices are smaller and faster, but have a minimum // API level of 30. - systemImageSource = if (apiLevel >= 30) "aosp-atd" else "aosp" + systemImageSource = if (apiLevel >= 30) "aosp_atd" else "default" } create("maxVersion") { device = "Small Phone" apiLevel = defaultConfig.targetSdk!! - systemImageSource = "aosp-atd" + systemImageSource = "aosp_atd" } } @@ -168,6 +183,12 @@ android { } } } + androidResources { + // Set this property to something nonexistent but non-empty. Otherwise it'll use + // the default list, which ignores asset directories beginning with an + // underscore, and maybe also other files required by tests. + ignoreAssetsPattern = "android-testbed-dont-ignore-anything" + } } dependencies { @@ -179,6 +200,138 @@ dependencies { } +afterEvaluate { + // Every new emulator has a maximum of 2 GB RAM, regardless of its hardware profile + // (https://cs.android.com/android-studio/platform/tools/base/+/refs/tags/studio-2025.3.2:sdklib/src/main/java/com/android/sdklib/internal/avd/EmulatedProperties.java;l=68). + // This is barely enough to test Python, and not enough to test Pandas + // (https://github.com/python/cpython/pull/137186#issuecomment-3136301023, + // https://github.com/pandas-dev/pandas/pull/63405#issuecomment-3667846159). + // So we'll increase it by editing the emulator configuration files. + // + // If the emulator doesn't exist yet, we want to edit it after it's created, but + // before it starts for the first time. Otherwise it'll need to be cold-booted + // again, which would slow down the first run, which is likely the only run in CI + // environments. But the Setup task both creates and starts the emulator if it + // doesn't already exist. So we create it ourselves before the Setup task runs. + for (device in android.testOptions.managedDevices.localDevices) { + val createTask = tasks.register("${device.name}Create") { + this.device = device.device + apiLevel = device.apiLevel + systemImageSource = device.systemImageSource + abi = NATIVE_ABI + } + tasks.named("${device.name}Setup") { + dependsOn(createTask) + } + } +} + +abstract class CreateEmulatorTask : DefaultTask() { + @get:Input abstract val device: Property + @get:Input abstract val apiLevel: Property + @get:Input abstract val systemImageSource: Property + @get:Input abstract val abi: Property + @get:Inject abstract val execOps: ExecOperations + + private val avdName by lazy { + listOf( + "dev${apiLevel.get()}", + systemImageSource.get(), + abi.get(), + device.get().replace(' ', '_'), + ).joinToString("_") + } + + private val avdDir by lazy { + // XDG_CONFIG_HOME is respected by both avdmanager and Gradle. + val userHome = System.getenv("ANDROID_USER_HOME") ?: ( + (System.getenv("XDG_CONFIG_HOME") ?: System.getProperty("user.home")!!) + + "/.android" + ) + File("$userHome/avd/gradle-managed", "$avdName.avd") + } + + @TaskAction + fun run() { + if (!avdDir.exists()) { + createAvd() + } + updateAvd() + } + + fun createAvd() { + val systemImage = listOf( + "system-images", + "android-${apiLevel.get()}", + systemImageSource.get(), + abi.get(), + ).joinToString(";") + + runCmdlineTool("sdkmanager", systemImage) + runCmdlineTool( + "avdmanager", "create", "avd", + "--name", avdName, + "--path", avdDir, + "--device", device.get().lowercase().replace(" ", "_"), + "--package", systemImage, + ) + + val iniName = "$avdName.ini" + if (!File(avdDir.parentFile.parentFile, iniName).renameTo( + File(avdDir.parentFile, iniName) + )) { + throw GradleException("Failed to rename $iniName") + } + } + + fun updateAvd() { + for (filename in listOf( + "config.ini", // Created by avdmanager; always exists + "hardware-qemu.ini", // Created on first run; might not exist + )) { + val iniFile = File(avdDir, filename) + if (!iniFile.exists()) { + if (filename == "config.ini") { + throw GradleException("$iniFile does not exist") + } + continue + } + + val iniText = iniFile.readText() + val pattern = Regex( + """^\s*hw.ramSize\s*=\s*(.+?)\s*$""", RegexOption.MULTILINE + ) + val matches = pattern.findAll(iniText).toList() + if (matches.size != 1) { + throw GradleException( + "Found ${matches.size} instances of $pattern in $iniFile; expected 1" + ) + } + + val expectedRam = "4096" + if (matches[0].groupValues[1] != expectedRam) { + iniFile.writeText( + iniText.replace(pattern, "hw.ramSize = $expectedRam") + ) + } + } + } + + fun runCmdlineTool(tool: String, vararg args: Any) { + val androidHome = System.getenv("ANDROID_HOME")!! + val exeSuffix = + if (System.getProperty("os.name").lowercase().startsWith("win")) ".exe" + else "" + val command = + listOf("$androidHome/cmdline-tools/latest/bin/$tool$exeSuffix", *args) + println(command.joinToString(" ")) + execOps.exec { + commandLine(command) + } + } +} + + // Create some custom tasks to copy Python and its standard library from // elsewhere in the repository. androidComponents.onVariants { variant -> @@ -205,11 +358,35 @@ androidComponents.onVariants { variant -> into("site-packages") { from("$projectDir/src/main/python") + + val sitePackages = findProperty("python.sitePackages") as String? + if (!sitePackages.isNullOrEmpty()) { + if (!file(sitePackages).exists()) { + throw GradleException("$sitePackages does not exist") + } + from(sitePackages) + } } duplicatesStrategy = DuplicatesStrategy.EXCLUDE exclude("**/__pycache__") } + + into("cwd") { + val cwd = findProperty("python.cwd") as String? + if (!cwd.isNullOrEmpty()) { + if (!file(cwd).exists()) { + throw GradleException("$cwd does not exist") + } + from(cwd) + } + } + + // A filename ending with .gz will be automatically decompressed + // while building the APK. Avoid this by adding a dash to the end, + // and add an extra dash to any filenames that already end with one. + // This will be undone in MainActivity.kt. + rename(""".*(\.gz|-)""", "$0-") } } diff --git a/Android/testbed/app/src/androidTest/java/org/python/testbed/PythonSuite.kt b/Android/testbed/app/src/androidTest/java/org/python/testbed/PythonSuite.kt index 0e888ab71d87da..e57243566f91dc 100644 --- a/Android/testbed/app/src/androidTest/java/org/python/testbed/PythonSuite.kt +++ b/Android/testbed/app/src/androidTest/java/org/python/testbed/PythonSuite.kt @@ -17,11 +17,11 @@ class PythonSuite { fun testPython() { val start = System.currentTimeMillis() try { - val context = + val status = PythonTestRunner( InstrumentationRegistry.getInstrumentation().targetContext - val args = - InstrumentationRegistry.getArguments().getString("pythonArgs", "") - val status = PythonTestRunner(context).run(args) + ).run( + InstrumentationRegistry.getArguments().getString("pythonArgs")!!, + ) assertEquals(0, status) } finally { // Make sure the process lives long enough for the test script to diff --git a/Android/testbed/app/src/main/c/main_activity.c b/Android/testbed/app/src/main/c/main_activity.c index ec7f93a3e5ee13..7f024f0a348b61 100644 --- a/Android/testbed/app/src/main/c/main_activity.c +++ b/Android/testbed/app/src/main/c/main_activity.c @@ -3,6 +3,7 @@ #include #include #include +#include #include #include #include @@ -15,6 +16,13 @@ static void throw_runtime_exception(JNIEnv *env, const char *message) { message); } +static void throw_errno(JNIEnv *env, const char *error_prefix) { + char error_message[1024]; + snprintf(error_message, sizeof(error_message), + "%s: %s", error_prefix, strerror(errno)); + throw_runtime_exception(env, error_message); +} + // --- Stdio redirection ------------------------------------------------------ @@ -95,10 +103,7 @@ JNIEXPORT void JNICALL Java_org_python_testbed_PythonTestRunner_redirectStdioToL for (StreamInfo *si = STREAMS; si->file; si++) { char *error_prefix; if ((error_prefix = redirect_stream(si))) { - char error_message[1024]; - snprintf(error_message, sizeof(error_message), - "%s: %s", error_prefix, strerror(errno)); - throw_runtime_exception(env, error_message); + throw_errno(env, error_prefix); return; } } @@ -107,13 +112,38 @@ JNIEXPORT void JNICALL Java_org_python_testbed_PythonTestRunner_redirectStdioToL // --- Python initialization --------------------------------------------------- -static PyStatus set_config_string( - JNIEnv *env, PyConfig *config, wchar_t **config_str, jstring value -) { - const char *value_utf8 = (*env)->GetStringUTFChars(env, value, NULL); - PyStatus status = PyConfig_SetBytesString(config, config_str, value_utf8); - (*env)->ReleaseStringUTFChars(env, value, value_utf8); - return status; +static char *init_signals() { + // Some tests use SIGUSR1, but that's blocked by default in an Android app in + // order to make it available to `sigwait` in the Signal Catcher thread. + // (https://cs.android.com/android/platform/superproject/+/android14-qpr3-release:art/runtime/signal_catcher.cc). + // That thread's functionality is only useful for debugging the JVM, so disabling + // it should not weaken the tests. + // + // There's no safe way of stopping the thread completely (#123982), but simply + // unblocking SIGUSR1 is enough to fix most tests. + // + // However, in tests that generate multiple different signals in quick + // succession, it's possible for SIGUSR1 to arrive while the main thread is busy + // running the C-level handler for a different signal. In that case, the SIGUSR1 + // may be sent to the Signal Catcher thread instead, which will generate a log + // message containing the text "reacting to signal". + // + // Such tests may need to be changed in one of the following ways: + // * Use a signal other than SIGUSR1 (e.g. test_stress_delivery_simultaneous in + // test_signal.py). + // * Send the signal to a specific thread rather than the whole process (e.g. + // test_signals in test_threadsignals.py. + sigset_t set; + if (sigemptyset(&set)) { + return "sigemptyset"; + } + if (sigaddset(&set, SIGUSR1)) { + return "sigaddset"; + } + if ((errno = pthread_sigmask(SIG_UNBLOCK, &set, NULL))) { + return "pthread_sigmask"; + } + return NULL; } static void throw_status(JNIEnv *env, PyStatus status) { @@ -121,27 +151,47 @@ static void throw_status(JNIEnv *env, PyStatus status) { } JNIEXPORT int JNICALL Java_org_python_testbed_PythonTestRunner_runPython( - JNIEnv *env, jobject obj, jstring home, jstring runModule + JNIEnv *env, jobject obj, jstring home, jarray args ) { + const char *home_utf8 = (*env)->GetStringUTFChars(env, home, NULL); + char cwd[PATH_MAX]; + snprintf(cwd, sizeof(cwd), "%s/%s", home_utf8, "cwd"); + if (chdir(cwd)) { + throw_errno(env, "chdir"); + return 1; + } + + char *error_prefix; + if ((error_prefix = init_signals())) { + throw_errno(env, error_prefix); + return 1; + } + PyConfig config; PyStatus status; - PyConfig_InitIsolatedConfig(&config); + PyConfig_InitPythonConfig(&config); - status = set_config_string(env, &config, &config.home, home); - if (PyStatus_Exception(status)) { + jsize argc = (*env)->GetArrayLength(env, args); + const char *argv[argc + 1]; + for (int i = 0; i < argc; i++) { + jobject arg = (*env)->GetObjectArrayElement(env, args, i); + argv[i] = (*env)->GetStringUTFChars(env, arg, NULL); + } + argv[argc] = NULL; + + // PyConfig_SetBytesArgv "must be called before other methods, since the + // preinitialization configuration depends on command line arguments" + if (PyStatus_Exception(status = PyConfig_SetBytesArgv(&config, argc, (char**)argv))) { throw_status(env, status); return 1; } - status = set_config_string(env, &config, &config.run_module, runModule); + status = PyConfig_SetBytesString(&config, &config.home, home_utf8); if (PyStatus_Exception(status)) { throw_status(env, status); return 1; } - // Some tests generate SIGPIPE and SIGXFSZ, which should be ignored. - config.install_signal_handlers = 1; - status = Py_InitializeFromConfig(&config); if (PyStatus_Exception(status)) { throw_status(env, status); diff --git a/Android/testbed/app/src/main/java/org/python/testbed/MainActivity.kt b/Android/testbed/app/src/main/java/org/python/testbed/MainActivity.kt index c4bf6cbe83d8cd..c8fe3acd849ac7 100644 --- a/Android/testbed/app/src/main/java/org/python/testbed/MainActivity.kt +++ b/Android/testbed/app/src/main/java/org/python/testbed/MainActivity.kt @@ -5,6 +5,7 @@ import android.os.* import android.system.Os import android.widget.TextView import androidx.appcompat.app.* +import org.json.JSONArray import java.io.* @@ -15,18 +16,24 @@ class MainActivity : AppCompatActivity() { override fun onCreate(savedInstanceState: Bundle?) { super.onCreate(savedInstanceState) setContentView(R.layout.activity_main) - val status = PythonTestRunner(this).run("-W -uall") + val status = PythonTestRunner(this).run("""["-m", "test", "-W", "-uall"]""") findViewById(R.id.tvHello).text = "Exit status $status" } } class PythonTestRunner(val context: Context) { - /** @param args Extra arguments for `python -m test`. - * @return The Python exit status: zero if the tests passed, nonzero if - * they failed. */ - fun run(args: String = "") : Int { - Os.setenv("PYTHON_ARGS", args, true) + /** Run Python. + * + * @param args Python command-line, encoded as JSON. + * @return The Python exit status: zero on success, nonzero on failure. */ + fun run(args: String) : Int { + // Argument 0 is a placeholder for the executable name in embedded mode. + val argsJsonArray = JSONArray(args) + val argsStringArray = Array(argsJsonArray.length() + 1) { i -> + if (i == 0) "" + else argsJsonArray.getString(i - 1) + } // Python needs this variable to help it find the temporary directory, // but Android only sets it on API level 33 and later. @@ -35,9 +42,7 @@ class PythonTestRunner(val context: Context) { val pythonHome = extractAssets() System.loadLibrary("main_activity") redirectStdioToLogcat() - - // The main module is in src/main/python/main.py. - return runPython(pythonHome.toString(), "main") + return runPython(pythonHome.toString(), argsStringArray) } private fun extractAssets() : File { @@ -46,6 +51,13 @@ class PythonTestRunner(val context: Context) { throw RuntimeException("Failed to delete $pythonHome") } extractAssetDir("python", context.filesDir) + + // Empty directories are lost in the asset packing/unpacking process. + val cwd = File(pythonHome, "cwd") + if (!cwd.exists()) { + cwd.mkdir() + } + return pythonHome } @@ -67,7 +79,9 @@ class PythonTestRunner(val context: Context) { continue } input.use { - File(targetSubdir, name).outputStream().use { output -> + // Undo the .gz workaround from build.gradle.kts. + val outputName = name.replace(Regex("""(.*)-"""), "$1") + File(targetSubdir, outputName).outputStream().use { output -> input.copyTo(output) } } @@ -75,5 +89,5 @@ class PythonTestRunner(val context: Context) { } private external fun redirectStdioToLogcat() - private external fun runPython(home: String, runModule: String) : Int + private external fun runPython(home: String, args: Array) : Int } diff --git a/Android/testbed/app/src/main/python/main.py b/Android/testbed/app/src/main/python/main.py deleted file mode 100644 index d6941b14412fcc..00000000000000 --- a/Android/testbed/app/src/main/python/main.py +++ /dev/null @@ -1,32 +0,0 @@ -import os -import runpy -import shlex -import signal -import sys - -# Some tests use SIGUSR1, but that's blocked by default in an Android app in -# order to make it available to `sigwait` in the Signal Catcher thread. -# (https://cs.android.com/android/platform/superproject/+/android14-qpr3-release:art/runtime/signal_catcher.cc). -# That thread's functionality is only useful for debugging the JVM, so disabling -# it should not weaken the tests. -# -# There's no safe way of stopping the thread completely (#123982), but simply -# unblocking SIGUSR1 is enough to fix most tests. -# -# However, in tests that generate multiple different signals in quick -# succession, it's possible for SIGUSR1 to arrive while the main thread is busy -# running the C-level handler for a different signal. In that case, the SIGUSR1 -# may be sent to the Signal Catcher thread instead, which will generate a log -# message containing the text "reacting to signal". -# -# Such tests may need to be changed in one of the following ways: -# * Use a signal other than SIGUSR1 (e.g. test_stress_delivery_simultaneous in -# test_signal.py). -# * Send the signal to a specific thread rather than the whole process (e.g. -# test_signals in test_threadsignals.py. -signal.pthread_sigmask(signal.SIG_UNBLOCK, [signal.SIGUSR1]) - -sys.argv[1:] = shlex.split(os.environ["PYTHON_ARGS"]) - -# The test module will call sys.exit to indicate whether the tests passed. -runpy.run_module("test") diff --git a/Android/testbed/build.gradle.kts b/Android/testbed/build.gradle.kts index 4d1d6f87594da3..3c48be4bb58513 100644 --- a/Android/testbed/build.gradle.kts +++ b/Android/testbed/build.gradle.kts @@ -1,5 +1,4 @@ // Top-level build file where you can add configuration options common to all sub-projects/modules. plugins { - id("com.android.application") version "8.6.1" apply false - id("org.jetbrains.kotlin.android") version "1.9.22" apply false + id("com.android.application") version "9.3.1" apply false } diff --git a/Android/testbed/gradle.properties b/Android/testbed/gradle.properties index e9f345c8c26250..22821df5110013 100644 --- a/Android/testbed/gradle.properties +++ b/Android/testbed/gradle.properties @@ -11,16 +11,8 @@ org.gradle.jvmargs=-Xmx2048m -Dfile.encoding=UTF-8 # This option should only be used with decoupled projects. More details, visit # http://www.gradle.org/docs/current/userguide/multi_project_builds.html#sec:decoupled_projects # org.gradle.parallel=true -# AndroidX package structure to make it clearer which packages are bundled with the -# Android operating system, and which are packaged with your app's APK -# https://developer.android.com/topic/libraries/support-library/androidx-rn -android.useAndroidX=true # Kotlin code style for this project: "official" or "obsolete": kotlin.code.style=official -# Enables namespacing of each library's R class so that its R class includes only the -# resources declared in the library itself and none from the library's dependencies, -# thereby reducing the size of the R class for that library -android.nonTransitiveRClass=true # By default, the app will be uninstalled after the tests finish (apparently # after 10 seconds in case of an unclean shutdown). We disable this, because diff --git a/Android/testbed/gradle/wrapper/gradle-wrapper.properties b/Android/testbed/gradle/wrapper/gradle-wrapper.properties index 36529c896426b0..6632d9e5c1c404 100644 --- a/Android/testbed/gradle/wrapper/gradle-wrapper.properties +++ b/Android/testbed/gradle/wrapper/gradle-wrapper.properties @@ -1,6 +1,6 @@ #Mon Feb 19 20:29:06 GMT 2024 distributionBase=GRADLE_USER_HOME distributionPath=wrapper/dists -distributionUrl=https\://services.gradle.org/distributions/gradle-8.7-bin.zip +distributionUrl=https\://services.gradle.org/distributions/gradle-9.5.0-bin.zip zipStoreBase=GRADLE_USER_HOME zipStorePath=wrapper/dists diff --git a/Apple/.ruff.toml b/Apple/.ruff.toml new file mode 100644 index 00000000000000..4cdc39ebee4be9 --- /dev/null +++ b/Apple/.ruff.toml @@ -0,0 +1,22 @@ +extend = "../.ruff.toml" # Inherit the project-wide settings + +[format] +preview = true +docstring-code-format = true + +[lint] +select = [ + "C4", # flake8-comprehensions + "E", # pycodestyle + "F", # pyflakes + "I", # isort + "ISC", # flake8-implicit-str-concat + "LOG", # flake8-logging + "PGH", # pygrep-hooks + "PT", # flake8-pytest-style + "PYI", # flake8-pyi + "RUF100", # Ban unused `# noqa` comments + "UP", # pyupgrade + "W", # pycodestyle + "YTT", # flake8-2020 +] diff --git a/Apple/__main__.py b/Apple/__main__.py new file mode 100644 index 00000000000000..ec67265e02a081 --- /dev/null +++ b/Apple/__main__.py @@ -0,0 +1,1119 @@ +#!/usr/bin/env python3 +########################################################################## +# Apple XCframework build script +# +# This script simplifies the process of configuring, compiling and packaging an +# XCframework for an Apple platform. +# +# At present, it only supports iOS, but it has been constructed so that it +# could be used on any Apple platform. +# +# The simplest entry point is: +# +# $ python Apple ci iOS +# +# which will: +# * Clean any pre-existing build artefacts +# * Configure and make a Python that can be used for the build +# * Configure and make a Python for each supported iOS architecture and ABI +# * Combine the outputs of the builds from the previous step into a single +# XCframework, merging binaries into a "fat" binary if necessary +# * Clone a copy of the testbed, configured to use the XCframework +# * Construct a tarball containing the release artefacts +# * Run the test suite using the generated XCframework. +# +# This is the complete sequence that would be needed in CI to build and test +# a candidate release artefact. +# +# Each individual step can be invoked individually - there are commands to +# clean, configure-build, make-build, configure-host, make-host, package, and +# test. +# +# There is also a build command that can be used to combine the configure and +# make steps for the build Python, an individual host, all hosts, or all +# builds. +########################################################################## +from __future__ import annotations + +import argparse +import os +import platform +import re +import shlex +import shutil +import signal +import subprocess +import sys +import sysconfig +import time +from collections.abc import Callable, Sequence +from contextlib import contextmanager +from datetime import datetime, timezone +from os.path import basename, relpath +from pathlib import Path +from subprocess import CalledProcessError + +EnvironmentT = dict[str, str] +ArgsT = Sequence[str | Path] + +SCRIPT_NAME = Path(__file__).name +PYTHON_DIR = Path(__file__).resolve().parent.parent + +CROSS_BUILD_DIR = PYTHON_DIR / "cross-build" + +HOSTS: dict[str, dict[str, dict[str, str]]] = { + # Structure of this data: + # * Platform identifier + # * an XCframework slice that must exist for that platform + # * a host triple: the multiarch spec for that host + "iOS": { + "ios-arm64": { + "arm64-apple-ios": "arm64-iphoneos", + }, + "ios-arm64_x86_64-simulator": { + "arm64-apple-ios-simulator": "arm64-iphonesimulator", + "x86_64-apple-ios-simulator": "x86_64-iphonesimulator", + }, + }, +} + + +def subdir(name: str, create: bool = False) -> Path: + """Ensure that a cross-build directory for the given name exists.""" + path = CROSS_BUILD_DIR / name + if not path.exists(): + if not create: + sys.exit( + f"{path} does not exist. Create it by running the appropriate " + f"`configure` subcommand of {SCRIPT_NAME}." + ) + else: + path.mkdir(parents=True) + return path + + +def run( + command: ArgsT, + *, + host: str | None = None, + env: EnvironmentT | None = None, + log: bool | None = True, + **kwargs, +) -> subprocess.CompletedProcess: + """Run a command in an Apple development environment. + + Optionally logs the executed command to the console. + """ + kwargs.setdefault("check", True) + if env is None: + env = os.environ.copy() + + if host: + host_env = apple_env(host) + print_env(host_env) + env.update(host_env) + + if log: + print(">", join_command(command)) + return subprocess.run(command, env=env, **kwargs) + + +def join_command(args: str | Path | ArgsT) -> str: + """Format a command so it can be copied into a shell. + + Similar to `shlex.join`, but also accepts arguments which are Paths, or a + single string/Path outside of a list. + """ + if isinstance(args, (str, Path)): + return str(args) + else: + return shlex.join(map(str, args)) + + +def print_env(env: EnvironmentT) -> None: + """Format the environment so it can be pasted into a shell.""" + for key, value in sorted(env.items()): + print(f"export {key}={shlex.quote(value)}") + + +def apple_env(host: str) -> EnvironmentT: + """Construct an Apple development environment for the given host.""" + env = { + "PATH": ":".join([ + str(PYTHON_DIR / "Apple/iOS/Resources/bin"), + str(subdir(host) / "prefix"), + "/usr/bin", + "/bin", + "/usr/sbin", + "/sbin", + "/Library/Apple/usr/bin", + ]), + } + + return env + + +def delete_path(name: str) -> None: + """Delete the named cross-build directory, if it exists.""" + path = CROSS_BUILD_DIR / name + if path.exists(): + print(f"Deleting {path} ...") + shutil.rmtree(path) + + +def all_host_triples(platform: str) -> list[str]: + """Return all host triples for the given platform. + + The host triples are the platform definitions used as input to configure + (e.g., "arm64-apple-ios-simulator"). + """ + triples = [] + for slice_name, slice_parts in HOSTS[platform].items(): + triples.extend(list(slice_parts)) + return triples + + +def clean(context: argparse.Namespace, target: str | None = None) -> None: + """The implementation of the "clean" command.""" + if target is None: + target = context.host + + # If we're explicitly targeting the build, there's no platform or + # distribution artefacts. If we're cleaning tests, we keep all built + # artefacts. Otherwise, the built artefacts must be dirty, so we remove + # them. + if target not in {"build", "test"}: + paths = ["dist", context.platform] + list(HOSTS[context.platform]) + else: + paths = [] + + if target in {"all", "build"}: + paths.append("build") + + if target in {"all", "hosts"}: + paths.extend(all_host_triples(context.platform)) + elif target not in {"build", "test", "package"}: + paths.append(target) + + if target in {"all", "hosts", "test"}: + paths.extend([ + path.name + for path in CROSS_BUILD_DIR.glob(f"{context.platform}-testbed.*") + ]) + + for path in paths: + delete_path(path) + + +def build_python_path() -> Path: + """The path to the build Python binary.""" + build_dir = subdir("build") + binary = build_dir / "python" + if not binary.is_file(): + binary = binary.with_suffix(".exe") + if not binary.is_file(): + raise FileNotFoundError( + f"Unable to find `python(.exe)` in {build_dir}" + ) + + return binary + + +@contextmanager +def group(text: str): + """A context manager that outputs a log marker around a section of a build. + + If running in a GitHub Actions environment, the GitHub syntax for + collapsible log sections is used. + """ + if "GITHUB_ACTIONS" in os.environ: + print(f"::group::{text}") + else: + print(f"===== {text} " + "=" * (70 - len(text))) + + yield + + if "GITHUB_ACTIONS" in os.environ: + print("::endgroup::") + else: + print() + + +@contextmanager +def cwd(subdir: Path): + """A context manager that sets the current working directory.""" + orig = os.getcwd() + os.chdir(subdir) + yield + os.chdir(orig) + + +def configure_build_python(context: argparse.Namespace) -> None: + """The implementation of the "configure-build" command.""" + if context.clean: + clean(context, "build") + + with ( + group("Configuring build Python"), + cwd(subdir("build", create=True)), + ): + command = [relpath(PYTHON_DIR / "configure")] + if context.args: + command.extend(context.args) + run(command) + + +def make_build_python(context: argparse.Namespace) -> None: + """The implementation of the "make-build" command.""" + with ( + group("Compiling build Python"), + cwd(subdir("build")), + ): + run(["make", "-j", str(os.cpu_count())]) + + +def pythoninfo_build_python(context: argparse.Namespace) -> None: + """The implementation of the "pythoninfo-build" command.""" + with ( + group("Display build info of the build Python"), + cwd(subdir("build")), + ): + run(["make", "pythoninfo"]) + + +def apple_target(host: str) -> str: + """Return the Apple platform identifier for a given host triple.""" + for _, platform_slices in HOSTS.items(): + for slice_name, slice_parts in platform_slices.items(): + for host_triple, multiarch in slice_parts.items(): + if host == host_triple: + return ".".join(multiarch.split("-")[::-1]) + + raise KeyError(host) + + +def apple_multiarch(host: str) -> str: + """Return the multiarch descriptor for a given host triple.""" + for _, platform_slices in HOSTS.items(): + for slice_name, slice_parts in platform_slices.items(): + for host_triple, multiarch in slice_parts.items(): + if host == host_triple: + return multiarch + + raise KeyError(host) + + +def unpack_deps( + platform: str, + host: str, + prefix_dir: Path, + cache_dir: Path, +) -> None: + """Unpack binary dependencies into a provided directory. + + Downloads binaries if they aren't already present. Downloads will be stored + in provided cache directory. + + On iOS, as a safety mechanism, any dynamic libraries will be purged from + the unpacked dependencies. + """ + # To create new builds of these dependencies, usually all that's necessary + # is to push a tag to the cpython-apple-source-deps repository, and GitHub + # Actions will do the rest. + # + # If you're a member of the Python core team, and you'd like to be able to + # push these tags yourself, please contact Malcolm Smith or Russell + # Keith-Magee. + deps_url = "https://github.com/beeware/cpython-apple-source-deps/releases/download" + for name_ver in [ + "BZip2-1.0.8-2", + "libFFI-3.4.7-2", + "OpenSSL-3.5.7-1", + "XZ-5.6.4-2", + "mpdecimal-4.0.0-2", + "zstd-1.5.7-1", + ]: + filename = f"{name_ver.lower()}-{apple_target(host)}.tar.gz" + archive_path = download( + f"{deps_url}/{name_ver}/{filename}", + target_dir=cache_dir, + ) + shutil.unpack_archive(archive_path, prefix_dir) + + # Dynamic libraries will be preferentially linked over static; + # On iOS, ensure that no dylibs are available in the prefix folder. + if platform == "iOS": + for dylib in prefix_dir.glob("**/*.dylib"): + dylib.unlink() + + +def download(url: str, target_dir: Path) -> Path: + """Download the specified URL into the given directory. + + :return: The path to the downloaded archive. + """ + target_path = Path(target_dir).resolve() + target_path.mkdir(exist_ok=True, parents=True) + + out_path = target_path / basename(url) + if not Path(out_path).is_file(): + run([ + "curl", + "-Lf", + "--retry", + "5", + "--retry-all-errors", + "-o", + out_path, + url, + ]) + else: + print(f"Using cached version of {basename(url)}") + return out_path + + +def configure_host_python( + context: argparse.Namespace, + host: str | None = None, +) -> None: + """The implementation of the "configure-host" command.""" + if host is None: + host = context.host + + if context.clean: + clean(context, host) + + host_dir = subdir(host, create=True) + prefix_dir = host_dir / "prefix" + + with group(f"Downloading dependencies ({host})"): + if not prefix_dir.exists(): + prefix_dir.mkdir() + cache_dir = ( + Path(context.cache_dir).resolve() + if context.cache_dir + else CROSS_BUILD_DIR / "downloads" + ) + unpack_deps(context.platform, host, prefix_dir, cache_dir) + else: + print("Dependencies already installed") + + with ( + group(f"Configuring host Python ({host})"), + cwd(host_dir), + ): + command = [ + # Basic cross-compiling configuration + relpath(PYTHON_DIR / "configure"), + f"--host={host}", + f"--build={sysconfig.get_config_var('BUILD_GNU_TYPE')}", + f"--with-build-python={build_python_path()}", + "--with-system-libmpdec", + "--enable-framework", + # Dependent libraries. + f"--with-openssl={prefix_dir}", + f"LIBLZMA_CFLAGS=-I{prefix_dir}/include", + f"LIBLZMA_LIBS=-L{prefix_dir}/lib -llzma", + f"LIBFFI_CFLAGS=-I{prefix_dir}/include", + f"LIBFFI_LIBS=-L{prefix_dir}/lib -lffi", + f"LIBMPDEC_CFLAGS=-I{prefix_dir}/include", + f"LIBMPDEC_LIBS=-L{prefix_dir}/lib -lmpdec", + f"LIBZSTD_CFLAGS=-I{prefix_dir}/include", + f"LIBZSTD_LIBS=-L{prefix_dir}/lib -lzstd", + ] + + if context.args: + command.extend(context.args) + run(command, host=host) + + +def make_host_python( + context: argparse.Namespace, + host: str | None = None, +) -> None: + """The implementation of the "make-host" command.""" + if host is None: + host = context.host + + with ( + group(f"Compiling host Python ({host})"), + cwd(subdir(host)), + ): + run(["make", "-j", str(os.cpu_count())], host=host) + run(["make", "install"], host=host) + + +def framework_path(host_triple: str, multiarch: str) -> Path: + """The path to a built single-architecture framework product. + + :param host_triple: The host triple (e.g., arm64-apple-ios-simulator) + :param multiarch: The multiarch identifier (e.g., arm64-simulator) + """ + return CROSS_BUILD_DIR / f"{host_triple}/Apple/iOS/Frameworks/{multiarch}" + + +def package_version(prefix_path: Path) -> str: + """Extract the Python version being built from patchlevel.h.""" + for path in prefix_path.glob("**/patchlevel.h"): + text = path.read_text(encoding="utf-8") + if match := re.search( + r'\n\s*#define\s+PY_VERSION\s+"(.+)"\s*\n', text + ): + version = match[1] + # If not building against a tagged commit, add a timestamp to the + # version. Follow the PyPA version number rules, as this will make + # it easier to process with other tools. The version will have a + # `+` suffix once any official release has been made; a freshly + # forked main branch will have a version of 3.X.0a0. + if version.endswith("a0"): + version += "+" + if version.endswith("+"): + version += datetime.now(timezone.utc).strftime("%Y%m%d.%H%M%S") + + return version + + sys.exit("Unable to determine Python version being packaged.") + + +def lib_platform_files(dirname, names): + """A file filter that ignores platform-specific files in lib.""" + path = Path(dirname) + if ( + path.parts[-3] == "lib" + and path.parts[-2].startswith("python") + and path.parts[-1] == "lib-dynload" + ): + return names + elif path.parts[-2] == "lib" and path.parts[-1].startswith("python"): + ignored_names = { + name + for name in names + if ( + name.startswith("_sysconfigdata_") + or name.startswith("_sysconfig_vars_") + or name == "build-details.json" + ) + } + elif path.parts[-1] == "lib": + ignored_names = { + name + for name in names + if name.startswith("libpython") and name.endswith(".dylib") + } + else: + ignored_names = set() + + return ignored_names + + +def lib_non_platform_files(dirname, names): + """A file filter that ignores anything *except* platform-specific files + in the lib directory. + """ + path = Path(dirname) + if path.parts[-2] == "lib" and path.parts[-1].startswith("python"): + return ( + set(names) - lib_platform_files(dirname, names) - {"lib-dynload"} + ) + else: + return set() + + +def create_xcframework(platform: str) -> str: + """Build an XCframework from the component parts for the platform. + + :return: The version number of the Python version that was packaged. + """ + package_path = CROSS_BUILD_DIR / platform + try: + package_path.mkdir() + except FileExistsError: + raise RuntimeError( + f"{platform} XCframework already exists; do you need to run " + "with --clean?" + ) from None + + frameworks = [] + # Merge Frameworks for each component SDK. If there's only one architecture + # for the SDK, we can use the compiled Python.framework as-is. However, if + # there's more than architecture, we need to merge the individual built + # frameworks into a merged "fat" framework. + for slice_name, slice_parts in HOSTS[platform].items(): + # Some parts are the same across all slices, so we use can any of the + # host frameworks as the source for the merged version. Use the first + # one on the list, as it's as representative as any other. + first_host_triple, first_multiarch = next(iter(slice_parts.items())) + first_framework = ( + framework_path(first_host_triple, first_multiarch) + / "Python.framework" + ) + + if len(slice_parts) == 1: + # The first framework is the only framework, so copy it. + print(f"Copying framework for {slice_name}...") + frameworks.append(first_framework) + else: + print(f"Merging framework for {slice_name}...") + slice_path = CROSS_BUILD_DIR / slice_name + slice_framework = slice_path / "Python.framework" + slice_framework.mkdir(exist_ok=True, parents=True) + + # Copy the Info.plist + shutil.copy( + first_framework / "Info.plist", + slice_framework / "Info.plist", + ) + + # Copy the headers + shutil.copytree( + first_framework / "Headers", + slice_framework / "Headers", + ) + + # Create the "fat" library binary for the slice + run( + ["lipo", "-create", "-output", slice_framework / "Python"] + + [ + ( + framework_path(host_triple, multiarch) + / "Python.framework/Python" + ) + for host_triple, multiarch in slice_parts.items() + ] + ) + + # Add this merged slice to the list to be added to the XCframework + frameworks.append(slice_framework) + + print() + print("Build XCframework...") + cmd = [ + "xcodebuild", + "-create-xcframework", + "-output", + package_path / "Python.xcframework", + ] + for framework in frameworks: + cmd.extend(["-framework", framework]) + + run(cmd) + + # Extract the package version from the merged framework + version = package_version(package_path / "Python.xcframework") + version_tag = ".".join(version.split(".")[:2]) + + # On non-macOS platforms, each framework in XCframework only contains the + # headers, libPython, plus an Info.plist. Other resources like the standard + # library and binary shims aren't allowed to live in framework; they need + # to be copied in separately. + print() + print("Copy additional resources...") + has_common_stdlib = False + for slice_name, slice_parts in HOSTS[platform].items(): + # Some parts are the same across all slices, so we can any of the + # host frameworks as the source for the merged version. + first_host_triple, first_multiarch = next(iter(slice_parts.items())) + first_path = framework_path(first_host_triple, first_multiarch) + first_framework = first_path / "Python.framework" + + slice_path = package_path / f"Python.xcframework/{slice_name}" + slice_framework = slice_path / "Python.framework" + + # Copy the binary helpers + print(f" - {slice_name} binaries") + shutil.copytree(first_path / "bin", slice_path / "bin") + + # Copy the include path (a symlink to the framework headers) + print(f" - {slice_name} include files") + shutil.copytree( + first_path / "include", + slice_path / "include", + symlinks=True, + ) + + # Copy in the cross-architecture pyconfig.h + shutil.copy( + PYTHON_DIR / f"Apple/{platform}/Resources/pyconfig.h", + slice_framework / "Headers/pyconfig.h", + ) + + print(f" - {slice_name} shared library") + # Create a simlink for the fat library + shared_lib = slice_path / f"lib/libpython{version_tag}.dylib" + shared_lib.parent.mkdir() + shared_lib.symlink_to("../Python.framework/Python") + + print(f" - {slice_name} architecture-specific files") + for host_triple, multiarch in slice_parts.items(): + print(f" - {multiarch} standard library") + arch, _ = multiarch.split("-", 1) + + if not has_common_stdlib: + print(" - using this architecture as the common stdlib") + shutil.copytree( + framework_path(host_triple, multiarch) / "lib", + package_path / "Python.xcframework/lib", + ignore=lib_platform_files, + symlinks=True, + ) + has_common_stdlib = True + + shutil.copytree( + framework_path(host_triple, multiarch) / "lib", + slice_path / f"lib-{arch}", + ignore=lib_non_platform_files, + symlinks=True, + ) + + # Copy the host's pyconfig.h to an architecture-specific name. + arch = multiarch.split("-")[0] + host_path = ( + CROSS_BUILD_DIR + / host_triple + / "Apple/iOS/Frameworks" + / multiarch + ) + host_framework = host_path / "Python.framework" + shutil.copy( + host_framework / "Headers/pyconfig.h", + slice_framework / f"Headers/pyconfig-{arch}.h", + ) + + # Apple identifies certain libraries as "security risks"; if you + # statically link those libraries into a Framework, you become + # responsible for providing a privacy manifest for that framework. + xcprivacy_file = { + "OpenSSL": subdir(host_triple) + / "prefix/share/OpenSSL.xcprivacy" + } + print(f" - {multiarch} xcprivacy files") + for module, lib in [ + ("_hashlib", "OpenSSL"), + ("_ssl", "OpenSSL"), + ]: + shutil.copy( + xcprivacy_file[lib], + slice_path + / f"lib-{arch}/python{version_tag}" + / f"lib-dynload/{module}.xcprivacy", + ) + + print(" - build tools") + shutil.copytree( + PYTHON_DIR / "Apple/testbed/Python.xcframework/build", + package_path / "Python.xcframework/build", + ) + + return version + + +def package(context: argparse.Namespace) -> None: + """The implementation of the "package" command.""" + if context.clean: + clean(context, "package") + + with group("Building package"): + # Create an XCframework + version = create_xcframework(context.platform) + + # Clone testbed + print() + run([ + sys.executable, + "Apple/testbed", + "clone", + "--platform", + context.platform, + "--framework", + CROSS_BUILD_DIR / context.platform / "Python.xcframework", + CROSS_BUILD_DIR / context.platform / "testbed", + ]) + + # Build the final archive + archive_name = ( + CROSS_BUILD_DIR + / "dist" + / f"python-{version}-{context.platform}-XCframework" + ) + + print() + print("Create package archive...") + shutil.make_archive( + str(CROSS_BUILD_DIR / archive_name), + format="gztar", + root_dir=CROSS_BUILD_DIR / context.platform, + base_dir=".", + ) + print() + print(f"{archive_name.relative_to(PYTHON_DIR)}.tar.gz created.") + + +def build(context: argparse.Namespace, host: str | None = None) -> None: + """The implementation of the "build" command.""" + if host is None: + host = context.host + + if context.clean: + clean(context, host) + + if host in {"all", "build"}: + for step in [ + configure_build_python, + make_build_python, + pythoninfo_build_python, + ]: + step(context) + + if host == "build": + hosts = [] + elif host in {"all", "hosts"}: + hosts = all_host_triples(context.platform) + else: + hosts = [host] + + for step_host in hosts: + for step in [ + configure_host_python, + make_host_python, + ]: + step(context, host=step_host) + + if host == "all": + package(context) + + +def test(context: argparse.Namespace, host: str | None = None) -> None: # noqa: PT028 + """The implementation of the "test" command.""" + if host is None: + host = context.host + + if context.clean: + clean(context, "test") + + with group(f"Test {'XCframework' if host in {'all', 'hosts'} else host}"): + timestamp = str(time.time_ns())[:-6] + testbed_dir = ( + CROSS_BUILD_DIR / f"{context.platform}-testbed.{timestamp}" + ) + if host in {"all", "hosts"}: + framework_path = ( + CROSS_BUILD_DIR / context.platform / "Python.xcframework" + ) + else: + build_arch = platform.machine() + host_arch = host.split("-")[0] + + if not host.endswith("-simulator"): + print("Skipping test suite non-simulator build.") + return + elif build_arch != host_arch: + print( + f"Skipping test suite for an {host_arch} build " + f"on an {build_arch} machine." + ) + return + else: + framework_path = ( + CROSS_BUILD_DIR + / host + / f"Apple/{context.platform}" + / f"Frameworks/{apple_multiarch(host)}" + ) + + run([ + sys.executable, + "Apple/testbed", + "clone", + "--platform", + context.platform, + "--framework", + framework_path, + testbed_dir, + ]) + + run( + [ + sys.executable, + testbed_dir, + "run", + "--verbose", + ] + + ( + ["--simulator", str(context.simulator)] + if context.simulator + else [] + ) + + [ + "--", + "test", + f"--{context.ci_mode or 'fast'}-ci", + "--single-process", + "--no-randomize", + # Timeout handling requires subprocesses; explicitly setting + # the timeout to -1 disables the faulthandler. + "--timeout=-1", + # Adding Python options requires the use of a subprocess to + # start a new Python interpreter. + "--dont-add-python-opts", + ] + ) + + +def apple_sim_host(platform_name: str) -> str: + """Determine the native simulator target for this platform.""" + for _, slice_parts in HOSTS[platform_name].items(): + for host_triple in slice_parts: + parts = host_triple.split("-") + if parts[0] == platform.machine() and parts[-1] == "simulator": + return host_triple + + raise KeyError(platform_name) + + +def ci(context: argparse.Namespace) -> None: + """The implementation of the "ci" command. + + In "Fast" mode, this compiles the build python, and the simulator for the + build machine's architecture; and runs the test suite with `--fast-ci` + configuration. + + In "Slow" mode, it compiles the build python, plus all candidate + architectures (both device and simulator); then runs the test suite with + `--slow-ci` configuration. + """ + clean(context, "all") + if context.ci_mode == "slow": + # In slow mode, build and test the full XCframework + build(context, host="all") + test(context, host="all") + else: + # In fast mode, just build the simulator platform. + sim_host = apple_sim_host(context.platform) + build(context, host="build") + build(context, host=sim_host) + test(context, host=sim_host) + + +def parse_args() -> argparse.Namespace: + parser = argparse.ArgumentParser( + description=( + "A tool for managing the build, package and test process of " + "CPython on Apple platforms." + ), + ) + parser.suggest_on_error = True + subcommands = parser.add_subparsers(dest="subcommand", required=True) + + clean = subcommands.add_parser( + "clean", + help="Delete all build directories", + ) + + configure_build = subcommands.add_parser( + "configure-build", help="Run `configure` for the build Python" + ) + make_build = subcommands.add_parser( + "make-build", help="Run `make` for the build Python" + ) + pythoninfo_build = subcommands.add_parser( + "pythoninfo-build", help="Display build info of the build Python" + ) + configure_host = subcommands.add_parser( + "configure-host", + help="Run `configure` for a specific platform and target", + ) + make_host = subcommands.add_parser( + "make-host", + help="Run `make` for a specific platform and target", + ) + package = subcommands.add_parser( + "package", + help="Create a release package for the platform", + ) + build = subcommands.add_parser( + "build", + help="Build all platform targets and create the XCframework", + ) + test = subcommands.add_parser( + "test", + help="Run the testbed for a specific platform", + ) + ci = subcommands.add_parser( + "ci", + help="Run build, package, and test", + ) + + # platform argument + for cmd in [clean, configure_host, make_host, package, build, test, ci]: + cmd.add_argument( + "platform", + choices=HOSTS.keys(), + help="The target platform to build", + ) + + # host triple argument + for cmd in [configure_host, make_host]: + cmd.add_argument( + "host", + help="The host triple to build (e.g., arm64-apple-ios-simulator)", + ) + # optional host triple argument + for cmd in [clean, build, test]: + cmd.add_argument( + "host", + nargs="?", + default="all", + help=( + "The host triple to build (e.g., arm64-apple-ios-simulator), " + "or 'build' for just the build platform, or 'hosts' for all " + "host platforms, or 'all' for the build platform and all " + "hosts. Defaults to 'all'" + ), + ) + + # --cross-build-dir argument + for cmd in [ + clean, + configure_build, + make_build, + pythoninfo_build, + configure_host, + make_host, + build, + package, + test, + ci, + ]: + cmd.add_argument( + "--cross-build-dir", + action="store", + default=os.environ.get("CROSS_BUILD_DIR"), + dest="cross_build_dir", + type=Path, + help=( + "Path to the cross-build directory " + f"(default: {CROSS_BUILD_DIR}). Can also be set " + "with the CROSS_BUILD_DIR environment variable." + ), + ) + + # --clean option + for cmd in [configure_build, configure_host, build, package, test, ci]: + cmd.add_argument( + "--clean", + action="store_true", + default=False, + dest="clean", + help="Delete the relevant build directories first", + ) + + # --cache-dir option + for cmd in [configure_host, build, ci]: + cmd.add_argument( + "--cache-dir", + default=os.environ.get("CACHE_DIR"), + help="The directory to store cached downloads.", + ) + + # --simulator option + for cmd in [test, ci]: + cmd.add_argument( + "--simulator", + help=( + "The name of the simulator to use (eg: 'iPhone 16e'). " + "Defaults to the most recently released 'entry level' " + "iPhone device. Device architecture and OS version can also " + "be specified; e.g., " + "`--simulator 'iPhone 16 Pro,arch=arm64,OS=26.0'` would " + "run on an ARM64 iPhone 16 Pro simulator running iOS 26.0." + ), + ) + group = cmd.add_mutually_exclusive_group() + group.add_argument( + "--fast-ci", + action="store_const", + dest="ci_mode", + const="fast", + help="Add test arguments for GitHub Actions", + ) + group.add_argument( + "--slow-ci", + action="store_const", + dest="ci_mode", + const="slow", + help="Add test arguments for buildbots", + ) + + for subcommand in [configure_build, configure_host, build, ci]: + subcommand.add_argument( + "args", nargs="*", help="Extra arguments to pass to `configure`" + ) + + return parser.parse_args() + + +def print_called_process_error(e: subprocess.CalledProcessError) -> None: + for stream_name in ["stdout", "stderr"]: + content = getattr(e, stream_name) + stream = getattr(sys, stream_name) + if content: + stream.write(content) + if not content.endswith("\n"): + stream.write("\n") + + # shlex uses single quotes, so we surround the command with double quotes. + print( + f'Command "{join_command(e.cmd)}" returned exit status {e.returncode}' + ) + + +def main() -> None: + # Handle SIGTERM the same way as SIGINT. This ensures that if we're + # terminated by the buildbot worker, we'll make an attempt to clean up our + # subprocesses. + def signal_handler(*args): + os.kill(os.getpid(), signal.SIGINT) + + signal.signal(signal.SIGTERM, signal_handler) + + # Process command line arguments + context = parse_args() + + # Set the CROSS_BUILD_DIR if an argument was provided + if context.cross_build_dir: + global CROSS_BUILD_DIR + CROSS_BUILD_DIR = context.cross_build_dir.resolve() + + dispatch: dict[str, Callable] = { + "clean": clean, + "configure-build": configure_build_python, + "make-build": make_build_python, + "pythoninfo-build": pythoninfo_build_python, + "configure-host": configure_host_python, + "make-host": make_host_python, + "package": package, + "build": build, + "test": test, + "ci": ci, + } + + try: + dispatch[context.subcommand](context) + except CalledProcessError as e: + print() + print_called_process_error(e) + sys.exit(1) + except RuntimeError as e: + print() + print(e) + sys.exit(2) + + +if __name__ == "__main__": + # Under the buildbot, stdout is not a TTY, but we must still flush after + # every line to make sure our output appears in the correct order relative + # to the output of our subprocesses. + for stream in [sys.stdout, sys.stderr]: + stream.reconfigure(line_buffering=True) + + main() diff --git a/Apple/iOS/README.md b/Apple/iOS/README.md new file mode 100644 index 00000000000000..7ee257b5d648f4 --- /dev/null +++ b/Apple/iOS/README.md @@ -0,0 +1,339 @@ +# Python on iOS README + +**iOS support is [tier 3](https://peps.python.org/pep-0011/#tier-3).** + +This document provides a quick overview of some iOS specific features in the +Python distribution. + +These instructions are only needed if you're planning to compile Python for iOS +yourself. Most users should *not* need to do this. If you're looking to +experiment with writing an iOS app in Python, tools such as [BeeWare's +Briefcase](https://briefcase.readthedocs.io) and [Kivy's +Buildozer](https://buildozer.readthedocs.io) will provide a much more +approachable user experience. + +## Compilers for building on iOS + +Building for iOS requires the use of Apple's Xcode tooling. It is strongly +recommended that you use the most recent stable release of Xcode. This will +require the use of the most (or second-most) recently released macOS version, +as Apple does not maintain Xcode for older macOS versions. The Xcode Command +Line Tools are not sufficient for iOS development; you need a *full* Xcode +install. + +If you want to run your code on the iOS simulator, you'll also need to install +an iOS Simulator Platform. You should be prompted to select an iOS Simulator +Platform when you first run Xcode. Alternatively, you can add an iOS Simulator +Platform by selecting an open the Platforms tab of the Xcode Settings panel. + +## Building Python on iOS + +### ABIs and Architectures + +iOS apps can be deployed on physical devices, and on the iOS simulator. Although +the API used on these devices is identical, the ABI is different - you need to +link against different libraries for an iOS device build (`iphoneos`) or an +iOS simulator build (`iphonesimulator`). + +Apple uses the `XCframework` format to allow specifying a single dependency +that supports multiple ABIs. An `XCframework` is a wrapper around multiple +ABI-specific frameworks that share a common API. + +iOS can also support different CPU architectures within each ABI. At present, +there is only a single supported architecture on physical devices - ARM64. +However, the *simulator* supports 2 architectures - ARM64 (for running on Apple +Silicon machines), and x86_64 (for running on older Intel-based machines). + +To support multiple CPU architectures on a single platform, Apple uses a "fat +binary" format - a single physical file that contains support for multiple +architectures. It is possible to compile and use a "thin" single architecture +version of a binary for testing purposes; however, the "thin" binary will not be +portable to machines using other architectures. + +### Building a multi-architecture iOS XCframework + +The `Apple` subfolder of the Python repository acts as a build script that +can be used to coordinate the compilation of a complete iOS XCframework. To use +it, run:: + + python Apple build iOS + +This will: + +* Configure and compile a version of Python to run on the build machine +* Download pre-compiled binary dependencies for each platform +* Configure and build a `Python.framework` for each required architecture and + iOS SDK +* Merge the multiple `Python.framework` folders into a single `Python.xcframework` +* Produce a `.tar.gz` archive in the `cross-build/dist` folder containing + the `Python.xcframework`, plus a copy of the Testbed app pre-configured to + use the XCframework. + +The `Apple` build script has other entry points that will perform the +individual parts of the overall `build` target, plus targets to test the +build, clean the `cross-build` folder of iOS build products, and perform a +complete "build and test" CI run. The `--clean` flag can also be used on +individual commands to ensure that a stale build product are removed before +building. + +### Building a single-architecture framework + +If you're using the `Apple` build script, you won't need to build +individual frameworks. However, if you do need to manually configure an iOS +Python build for a single framework, the following options are available. + +#### iOS specific arguments to configure + +* `--enable-framework[=DIR]` + + This argument specifies the location where the Python.framework will be + installed. If `DIR` is not specified, the framework will be installed into + a subdirectory of the `iOS/Frameworks` folder. + + This argument *must* be provided when configuring iOS builds. iOS does not + support non-framework builds. + +* `--with-framework-name=NAME` + + Specify the name for the Python framework; defaults to `Python`. + + > [!NOTE] + > Unless you know what you're doing, changing the name of the Python + > framework on iOS is not advised. If you use this option, you won't be able + > to run the `Apple` build script without making significant manual + > alterations, and you won't be able to use any binary packages unless you + > compile them yourself using your own framework name. + +#### Building Python for iOS + +The Python build system will create a `Python.framework` that supports a +*single* ABI with a *single* architecture. Unlike macOS, iOS does not allow a +framework to contain non-library content, so the iOS build will produce a +`bin` and `lib` folder in the same output folder as `Python.framework`. +The `lib` folder will be needed at runtime to support the Python library. + +If you want to use Python in a real iOS project, you need to produce multiple +`Python.framework` builds, one for each ABI and architecture. iOS builds of +Python *must* be constructed as framework builds. To support this, you must +provide the `--enable-framework` flag when configuring the build. The build +also requires the use of cross-compilation. The minimal commands for building +Python for the ARM64 iOS simulator will look something like: +``` +export PATH="$(pwd)/Apple/iOS/Resources/bin:/usr/bin:/bin:/usr/sbin:/sbin:/Library/Apple/usr/bin" +./configure \ + --enable-framework \ + --host=arm64-apple-ios-simulator \ + --build=arm64-apple-darwin \ + --with-build-python=/path/to/python.exe +make +make install +``` + +In this invocation: + +* `Apple/iOS/Resources/bin` has been added to the path, providing some shims for the + compilers and linkers needed by the build. Xcode requires the use of `xcrun` + to invoke compiler tooling. However, if `xcrun` is pre-evaluated and the + result passed to `configure`, these results can embed user- and + version-specific paths into the sysconfig data, which limits the portability + of the compiled Python. Alternatively, if `xcrun` is used *as* the compiler, + it requires that compiler variables like `CC` include spaces, which can + cause significant problems with many C configuration systems which assume that + `CC` will be a single executable. + + To work around this problem, the `Apple/iOS/Resources/bin` folder contains some + wrapper scripts that present as simple compilers and linkers, but wrap + underlying calls to `xcrun`. This allows configure to use a `CC` + definition without spaces, and without user- or version-specific paths, while + retaining the ability to adapt to the local Xcode install. These scripts are + included in the `bin` directory of an iOS install. + + These scripts will, by default, use the currently active Xcode installation. + If you want to use a different Xcode installation, you can use + `xcode-select` to set a new default Xcode globally, or you can use the + `DEVELOPER_DIR` environment variable to specify an Xcode install. The + scripts will use the default `iphoneos`/`iphonesimulator` SDK version for + the select Xcode install; if you want to use a different SDK, you can set the + `IOS_SDK_VERSION` environment variable. (e.g, setting + `IOS_SDK_VERSION=17.1` would cause the scripts to use the `iphoneos17.1` + and `iphonesimulator17.1` SDKs, regardless of the Xcode default.) + + The path has also been cleared of any user customizations. A common source of + bugs is for tools like Homebrew to accidentally leak macOS binaries into an iOS + build. Resetting the path to a known "bare bones" value is the easiest way to + avoid these problems. + +* `--host` is the architecture and ABI that you want to build, in GNU compiler + triple format. This will be one of: + + - `arm64-apple-ios` for ARM64 iOS devices. + - `arm64-apple-ios-simulator` for the iOS simulator running on Apple + Silicon devices. + - `x86_64-apple-ios-simulator` for the iOS simulator running on Intel + devices. + +* `--build` is the GNU compiler triple for the machine that will be running + the compiler. This is one of: + + - `arm64-apple-darwin` for Apple Silicon devices. + - `x86_64-apple-darwin` for Intel devices. + +* `/path/to/python.exe` is the path to a Python binary on the machine that + will be running the compiler. This is needed because the Python compilation + process involves running some Python code. On a normal desktop build of + Python, you can compile a python interpreter and then use that interpreter to + run Python code. However, the binaries produced for iOS won't run on macOS, so + you need to provide an external Python interpreter. This interpreter must be + the same version as the Python that is being compiled. To be completely safe, + this should be the *exact* same commit hash. However, the longer a Python + release has been stable, the more likely it is that this constraint can be + relaxed - the same micro version will often be sufficient. + +* The `install` target for iOS builds is slightly different to other + platforms. On most platforms, `make install` will install the build into + the final runtime location. This won't be the case for iOS, as the final + runtime location will be on a physical device. + + However, you still need to run the `install` target for iOS builds, as it + performs some final framework assembly steps. The location specified with + `--enable-framework` will be the location where `make install` will + assemble the complete iOS framework. This completed framework can then + be copied and relocated as required. + +For a full CPython build, you also need to specify the paths to iOS builds of +the binary libraries that CPython depends on (such as XZ, LibFFI and OpenSSL). +This can be done by defining library specific environment variables (such as +`LIBLZMA_CFLAGS`, `LIBLZMA_LIBS`), and the `--with-openssl` configure +option. Versions of these libraries pre-compiled for iOS can be found in [this +repository](https://github.com/beeware/cpython-apple-source-deps/releases). +LibFFI is especially important, as many parts of the standard library +(including the `platform`, `sysconfig` and `webbrowser` modules) require +the use of the `ctypes` module at runtime. + +By default, Python will be compiled with an iOS deployment target (i.e., the +minimum supported iOS version) of 13.0. To specify a different deployment +target, provide the version number as part of the `--host` argument - for +example, `--host=arm64-apple-ios15.4-simulator` would compile an ARM64 +simulator build with a deployment target of 15.4. + +## Testing Python on iOS + +### Testing a multi-architecture framework + +Once you have a built an XCframework, you can test that framework by running: + + $ python Apple test iOS + +This test will attempt to find an "SE-class" simulator (i.e., an iPhone SE, or +iPhone 16e, or similar), and run the test suite on the most recent version of +iOS that is available. You can specify a simulator using the `--simulator` +command line argument, providing the name of the simulator (e.g., `--simulator +'iPhone 16 Pro'`). You can also use this argument to control the OS version used +for testing; `--simulator 'iPhone 16 Pro,OS=18.2'` would attempt to run the +tests on an iPhone 16 Pro running iOS 18.2. + +If the test runner is executed on GitHub Actions, the `GITHUB_ACTIONS` +environment variable will be exposed to the iOS process at runtime. + +### Testing a single-architecture framework + +The `Apple/testbed` folder that contains an Xcode project that is able to run +the Python test suite on Apple platforms. This project converts the Python test +suite into a single test case in Xcode's XCTest framework. The single XCTest +passes if the test suite passes. + +To run the test suite, configure a Python build for an iOS simulator (i.e., +`--host=arm64-apple-ios-simulator` or `--host=x86_64-apple-ios-simulator` +), specifying a framework build (i.e. `--enable-framework`). Ensure that your +`PATH` has been configured to include the `Apple/iOS/Resources/bin` folder and +exclude any non-iOS tools, then run: +``` +make all +make install +make testios +``` + +This will: + +* Build an iOS framework for your chosen architecture; +* Finalize the single-platform framework; +* Make a clean copy of the testbed project; +* Install the Python iOS framework into the copy of the testbed project; and +* Run the test suite on an "entry-level device" simulator (i.e., an iPhone SE, + iPhone 16e, or a similar). + +On success, the test suite will exit and report successful completion of the +test suite. On a 2022 M1 MacBook Pro, the test suite takes approximately 15 +minutes to run; a couple of extra minutes is required to compile the testbed +project, and then boot and prepare the iOS simulator. + +### Debugging test failures + +Running `python Apple test iOS` generates a standalone version of the +`Apple/testbed` project, and runs the full test suite. It does this using +`Apple/testbed` itself - the folder is an executable module that can be used +to create and run a clone of the testbed project. The standalone version of the +testbed will be created in a directory named +`cross-build/iOS-testbed.`. + +You can generate your own standalone testbed instance by running: +``` +python cross-build/iOS/testbed clone my-testbed +``` + +In this invocation, `my-testbed` is the name of the folder for the new +testbed clone. + +If you've built your own XCframework, or you only want to test a single architecture, +you can construct a standalone testbed instance by running: +``` +python Apple/testbed clone --platform iOS --framework my-testbed +``` + +The framework path can be the path path to a `Python.xcframework`, or the +path to a folder that contains a single-platform `Python.framework`. + +You can then use the `my-testbed` folder to run the Python test suite, +passing in any command line arguments you may require. For example, if you're +trying to diagnose a failure in the `os` module, you might run: +``` +python my-testbed run -- test -W test_os +``` + +This is the equivalent of running `python -m test -W test_os` on a desktop +Python build. Any arguments after the `--` will be passed to testbed as if +they were arguments to `python -m` on a desktop machine. + +### Testing in Xcode + +You can also open the testbed project in Xcode by running: +``` +open my-testbed/iOSTestbed.xcodeproj +``` + +This will allow you to use the full Xcode suite of tools for debugging. + +The arguments used to run the test suite are defined as part of the test plan. +To modify the test plan, select the test plan node of the project tree (it +should be the first child of the root node), and select the "Configurations" +tab. Modify the "Arguments Passed On Launch" value to change the testing +arguments. + +The test plan also disables parallel testing, and specifies the use of the +`Testbed.lldbinit` file for providing configuration of the debugger. The +default debugger configuration disables automatic breakpoints on the +`SIGINT`, `SIGUSR1`, `SIGUSR2`, and `SIGXFSZ` signals. + +### Testing on an iOS device + +To test on an iOS device, the app needs to be signed with known developer +credentials. To obtain these credentials, you must have an iOS Developer +account, and your Xcode install will need to be logged into your account (see +the Accounts tab of the Preferences dialog). + +Once the project is open, and you're signed into your Apple Developer account, +select the root node of the project tree (labeled "iOSTestbed"), then the +"Signing & Capabilities" tab in the details page. Select a development team +(this will likely be your own name), and plug in a physical device to your +macOS machine with a USB cable. You should then be able to select your physical +device from the list of targets in the pulldown in the Xcode titlebar. diff --git a/iOS/Resources/Info.plist.in b/Apple/iOS/Resources/Info.plist.in similarity index 100% rename from iOS/Resources/Info.plist.in rename to Apple/iOS/Resources/Info.plist.in diff --git a/Apple/iOS/Resources/bin/arm64-apple-ios-ar b/Apple/iOS/Resources/bin/arm64-apple-ios-ar new file mode 100755 index 00000000000000..3cf3eb218741fa --- /dev/null +++ b/Apple/iOS/Resources/bin/arm64-apple-ios-ar @@ -0,0 +1,2 @@ +#!/bin/sh +xcrun --sdk iphoneos${IOS_SDK_VERSION} ar "$@" diff --git a/Apple/iOS/Resources/bin/arm64-apple-ios-clang b/Apple/iOS/Resources/bin/arm64-apple-ios-clang new file mode 100755 index 00000000000000..f50d5b5142fc76 --- /dev/null +++ b/Apple/iOS/Resources/bin/arm64-apple-ios-clang @@ -0,0 +1,2 @@ +#!/bin/sh +xcrun --sdk iphoneos${IOS_SDK_VERSION} clang -target arm64-apple-ios${IPHONEOS_DEPLOYMENT_TARGET} "$@" diff --git a/Apple/iOS/Resources/bin/arm64-apple-ios-clang++ b/Apple/iOS/Resources/bin/arm64-apple-ios-clang++ new file mode 100755 index 00000000000000..0794731d7dcbda --- /dev/null +++ b/Apple/iOS/Resources/bin/arm64-apple-ios-clang++ @@ -0,0 +1,2 @@ +#!/bin/sh +xcrun --sdk iphoneos${IOS_SDK_VERSION} clang++ -target arm64-apple-ios${IPHONEOS_DEPLOYMENT_TARGET} "$@" diff --git a/Apple/iOS/Resources/bin/arm64-apple-ios-cpp b/Apple/iOS/Resources/bin/arm64-apple-ios-cpp new file mode 100755 index 00000000000000..24fa1506bab827 --- /dev/null +++ b/Apple/iOS/Resources/bin/arm64-apple-ios-cpp @@ -0,0 +1,2 @@ +#!/bin/sh +xcrun --sdk iphoneos${IOS_SDK_VERSION} clang -target arm64-apple-ios${IPHONEOS_DEPLOYMENT_TARGET} -E "$@" diff --git a/Apple/iOS/Resources/bin/arm64-apple-ios-simulator-ar b/Apple/iOS/Resources/bin/arm64-apple-ios-simulator-ar new file mode 100755 index 00000000000000..b836b6db9025bb --- /dev/null +++ b/Apple/iOS/Resources/bin/arm64-apple-ios-simulator-ar @@ -0,0 +1,2 @@ +#!/bin/sh +xcrun --sdk iphonesimulator${IOS_SDK_VERSION} ar "$@" diff --git a/Apple/iOS/Resources/bin/arm64-apple-ios-simulator-clang b/Apple/iOS/Resources/bin/arm64-apple-ios-simulator-clang new file mode 100755 index 00000000000000..4891a00876e0bd --- /dev/null +++ b/Apple/iOS/Resources/bin/arm64-apple-ios-simulator-clang @@ -0,0 +1,2 @@ +#!/bin/sh +xcrun --sdk iphonesimulator${IOS_SDK_VERSION} clang -target arm64-apple-ios${IPHONEOS_DEPLOYMENT_TARGET}-simulator "$@" diff --git a/Apple/iOS/Resources/bin/arm64-apple-ios-simulator-clang++ b/Apple/iOS/Resources/bin/arm64-apple-ios-simulator-clang++ new file mode 100755 index 00000000000000..58b2a5f6f18c2b --- /dev/null +++ b/Apple/iOS/Resources/bin/arm64-apple-ios-simulator-clang++ @@ -0,0 +1,2 @@ +#!/bin/sh +xcrun --sdk iphonesimulator${IOS_SDK_VERSION} clang++ -target arm64-apple-ios${IPHONEOS_DEPLOYMENT_TARGET}-simulator "$@" diff --git a/Apple/iOS/Resources/bin/arm64-apple-ios-simulator-cpp b/Apple/iOS/Resources/bin/arm64-apple-ios-simulator-cpp new file mode 100755 index 00000000000000..c9df94e8b7c837 --- /dev/null +++ b/Apple/iOS/Resources/bin/arm64-apple-ios-simulator-cpp @@ -0,0 +1,2 @@ +#!/bin/sh +xcrun --sdk iphonesimulator${IOS_SDK_VERSION} clang -target arm64-apple-ios${IPHONEOS_DEPLOYMENT_TARGET}-simulator -E "$@" diff --git a/Apple/iOS/Resources/bin/arm64-apple-ios-simulator-strip b/Apple/iOS/Resources/bin/arm64-apple-ios-simulator-strip new file mode 100755 index 00000000000000..fd59d309b73a20 --- /dev/null +++ b/Apple/iOS/Resources/bin/arm64-apple-ios-simulator-strip @@ -0,0 +1,2 @@ +#!/bin/sh +xcrun --sdk iphonesimulator${IOS_SDK_VERSION} strip -arch arm64 "$@" diff --git a/Apple/iOS/Resources/bin/arm64-apple-ios-strip b/Apple/iOS/Resources/bin/arm64-apple-ios-strip new file mode 100755 index 00000000000000..75e823a3d02d61 --- /dev/null +++ b/Apple/iOS/Resources/bin/arm64-apple-ios-strip @@ -0,0 +1,2 @@ +#!/bin/sh +xcrun --sdk iphoneos${IOS_SDK_VERSION} strip -arch arm64 "$@" diff --git a/Apple/iOS/Resources/bin/x86_64-apple-ios-simulator-ar b/Apple/iOS/Resources/bin/x86_64-apple-ios-simulator-ar new file mode 100755 index 00000000000000..b836b6db9025bb --- /dev/null +++ b/Apple/iOS/Resources/bin/x86_64-apple-ios-simulator-ar @@ -0,0 +1,2 @@ +#!/bin/sh +xcrun --sdk iphonesimulator${IOS_SDK_VERSION} ar "$@" diff --git a/Apple/iOS/Resources/bin/x86_64-apple-ios-simulator-clang b/Apple/iOS/Resources/bin/x86_64-apple-ios-simulator-clang new file mode 100755 index 00000000000000..f4739a7b945d01 --- /dev/null +++ b/Apple/iOS/Resources/bin/x86_64-apple-ios-simulator-clang @@ -0,0 +1,2 @@ +#!/bin/sh +xcrun --sdk iphonesimulator${IOS_SDK_VERSION} clang -target x86_64-apple-ios${IPHONEOS_DEPLOYMENT_TARGET}-simulator "$@" diff --git a/Apple/iOS/Resources/bin/x86_64-apple-ios-simulator-clang++ b/Apple/iOS/Resources/bin/x86_64-apple-ios-simulator-clang++ new file mode 100755 index 00000000000000..c348ae4c10395b --- /dev/null +++ b/Apple/iOS/Resources/bin/x86_64-apple-ios-simulator-clang++ @@ -0,0 +1,2 @@ +#!/bin/sh +xcrun --sdk iphonesimulator${IOS_SDK_VERSION} clang++ -target x86_64-apple-ios${IPHONEOS_DEPLOYMENT_TARGET}-simulator "$@" diff --git a/Apple/iOS/Resources/bin/x86_64-apple-ios-simulator-cpp b/Apple/iOS/Resources/bin/x86_64-apple-ios-simulator-cpp new file mode 100755 index 00000000000000..6d7f8084c9fdcc --- /dev/null +++ b/Apple/iOS/Resources/bin/x86_64-apple-ios-simulator-cpp @@ -0,0 +1,2 @@ +#!/bin/sh +xcrun --sdk iphonesimulator${IOS_SDK_VERSION} clang -target x86_64-apple-ios${IPHONEOS_DEPLOYMENT_TARGET}-simulator -E "$@" diff --git a/Apple/iOS/Resources/bin/x86_64-apple-ios-simulator-strip b/Apple/iOS/Resources/bin/x86_64-apple-ios-simulator-strip new file mode 100755 index 00000000000000..c5cfb28929195a --- /dev/null +++ b/Apple/iOS/Resources/bin/x86_64-apple-ios-simulator-strip @@ -0,0 +1,2 @@ +#!/bin/sh +xcrun --sdk iphonesimulator${IOS_SDK_VERSION} strip -arch x86_64 "$@" diff --git a/iOS/Resources/pyconfig.h b/Apple/iOS/Resources/pyconfig.h similarity index 100% rename from iOS/Resources/pyconfig.h rename to Apple/iOS/Resources/pyconfig.h diff --git a/iOS/testbed/Python.xcframework/Info.plist b/Apple/testbed/Python.xcframework/Info.plist similarity index 100% rename from iOS/testbed/Python.xcframework/Info.plist rename to Apple/testbed/Python.xcframework/Info.plist diff --git a/iOS/Resources/dylib-Info-template.plist b/Apple/testbed/Python.xcframework/build/iOS-dylib-Info-template.plist similarity index 96% rename from iOS/Resources/dylib-Info-template.plist rename to Apple/testbed/Python.xcframework/build/iOS-dylib-Info-template.plist index f652e272f71c88..d6caa01c1e44b9 100644 --- a/iOS/Resources/dylib-Info-template.plist +++ b/Apple/testbed/Python.xcframework/build/iOS-dylib-Info-template.plist @@ -19,7 +19,7 @@ iPhoneOS MinimumOSVersion - 12.0 + 13.0 CFBundleVersion 1 diff --git a/Apple/testbed/Python.xcframework/build/utils.sh b/Apple/testbed/Python.xcframework/build/utils.sh new file mode 100755 index 00000000000000..e54471f68b7cb2 --- /dev/null +++ b/Apple/testbed/Python.xcframework/build/utils.sh @@ -0,0 +1,151 @@ +# Utility methods for use in an Xcode project. +# +# An iOS XCframework cannot include any content other than the library binary +# and relevant metadata. However, Python requires a standard library at runtime. +# Therefore, it is necessary to add a build step to an Xcode app target that +# processes the standard library and puts the content into the final app. +# +# In general, these tools will be invoked after bundle resources have been +# copied into the app, but before framework embedding (and signing). +# +# The following is an example script, assuming that: +# * Python.xcframework is in the root of the project +# * There is an `app` folder that contains the app code +# * There is an `app_packages` folder that contains installed Python packages. +# ----- +# set -e +# source $PROJECT_DIR/Python.xcframework/build/build_utils.sh +# install_python Python.xcframework app app_packages +# ----- + +# Copy the standard library from the XCframework into the app bundle. +# +# Accepts one argument: +# 1. The path, relative to the root of the Xcode project, where the Python +# XCframework can be found. +install_stdlib() { + PYTHON_XCFRAMEWORK_PATH=$1 + + mkdir -p "$CODESIGNING_FOLDER_PATH/python/lib" + if [ "$EFFECTIVE_PLATFORM_NAME" = "-iphonesimulator" ]; then + echo "Installing Python modules for iOS Simulator" + if [ -d "$PROJECT_DIR/$PYTHON_XCFRAMEWORK_PATH/ios-arm64-simulator" ]; then + SLICE_FOLDER="ios-arm64-simulator" + else + SLICE_FOLDER="ios-arm64_x86_64-simulator" + fi + else + echo "Installing Python modules for iOS Device" + SLICE_FOLDER="ios-arm64" + fi + + # If the XCframework has a shared lib folder, then it's a full framework. + # Copy both the common and slice-specific part of the lib directory. + # Otherwise, it's a single-arch framework; use the "full" lib folder. + # Don't include any libpython symlink; that can't be included at runtime + if [ -d "$PROJECT_DIR/$PYTHON_XCFRAMEWORK_PATH/lib" ]; then + rsync -au --delete "$PROJECT_DIR/$PYTHON_XCFRAMEWORK_PATH/lib/" "$CODESIGNING_FOLDER_PATH/python/lib/" --exclude 'libpython*.dylib' + rsync -au "$PROJECT_DIR/$PYTHON_XCFRAMEWORK_PATH/$SLICE_FOLDER/lib-$ARCHS/" "$CODESIGNING_FOLDER_PATH/python/lib/" --exclude 'libpython*.dylib' + else + rsync -au --delete "$PROJECT_DIR/$PYTHON_XCFRAMEWORK_PATH/$SLICE_FOLDER/lib/" "$CODESIGNING_FOLDER_PATH/python/lib/" --exclude 'libpython*.dylib' + fi +} + +# Convert a single .so library into a framework that iOS can load. +# +# Accepts three arguments: +# 1. The path, relative to the root of the Xcode project, where the Python +# XCframework can be found. +# 2. The base path, relative to the installed location in the app bundle, that +# needs to be processed. Any .so file found in this path (or a subdirectory +# of it) will be processed. +# 2. The full path to a single .so file to process. This path should include +# the base path. +install_dylib () { + PYTHON_XCFRAMEWORK_PATH=$1 + INSTALL_BASE=$2 + FULL_EXT=$3 + + # The name of the extension file + EXT=$(basename "$FULL_EXT") + # The name and location of the module + MODULE_PATH=$(dirname "$FULL_EXT") + MODULE_NAME=$(echo $EXT | cut -d "." -f 1) + # The location of the extension file, relative to the bundle + RELATIVE_EXT=${FULL_EXT#$CODESIGNING_FOLDER_PATH/} + # The path to the extension file, relative to the install base + PYTHON_EXT=${RELATIVE_EXT/$INSTALL_BASE/} + # The full dotted name of the extension module, constructed from the file path. + FULL_MODULE_NAME=$(echo $PYTHON_EXT | cut -d "." -f 1 | tr "/" "."); + # A bundle identifier; not actually used, but required by Xcode framework packaging + FRAMEWORK_BUNDLE_ID=$(echo $PRODUCT_BUNDLE_IDENTIFIER.$FULL_MODULE_NAME | tr "_" "-") + # The name of the framework folder. + FRAMEWORK_FOLDER="Frameworks/$FULL_MODULE_NAME.framework" + + # If the framework folder doesn't exist, create it. + if [ ! -d "$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER" ]; then + echo "Creating framework for $RELATIVE_EXT" + mkdir -p "$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER" + cp "$PROJECT_DIR/$PYTHON_XCFRAMEWORK_PATH/build/$PLATFORM_FAMILY_NAME-dylib-Info-template.plist" "$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER/Info.plist" + plutil -replace CFBundleExecutable -string "$FULL_MODULE_NAME" "$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER/Info.plist" + plutil -replace CFBundleIdentifier -string "$FRAMEWORK_BUNDLE_ID" "$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER/Info.plist" + fi + + echo "Installing binary for $FRAMEWORK_FOLDER/$FULL_MODULE_NAME" + mv "$FULL_EXT" "$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER/$FULL_MODULE_NAME" + # Create a placeholder .fwork file where the .so was + echo "$FRAMEWORK_FOLDER/$FULL_MODULE_NAME" > ${FULL_EXT%.so}.fwork + # Create a back reference to the .so file location in the framework + echo "${RELATIVE_EXT%.so}.fwork" > "$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER/$FULL_MODULE_NAME.origin" + + # If the framework provides an xcprivacy file, install it. + if [ -e "$MODULE_PATH/$MODULE_NAME.xcprivacy" ]; then + echo "Installing XCPrivacy file for $FRAMEWORK_FOLDER/$FULL_MODULE_NAME" + XCPRIVACY_FILE="$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER/PrivacyInfo.xcprivacy" + if [ -e "$XCPRIVACY_FILE" ]; then + rm -rf "$XCPRIVACY_FILE" + fi + mv "$MODULE_PATH/$MODULE_NAME.xcprivacy" "$XCPRIVACY_FILE" + fi + + echo "Signing framework as $EXPANDED_CODE_SIGN_IDENTITY_NAME ($EXPANDED_CODE_SIGN_IDENTITY)..." + /usr/bin/codesign --force --sign "$EXPANDED_CODE_SIGN_IDENTITY" ${OTHER_CODE_SIGN_FLAGS:-} -o runtime --timestamp=none --preserve-metadata=identifier,entitlements,flags --generate-entitlement-der "$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER" +} + +# Process all the dynamic libraries in a path into Framework format. +# +# Accepts two arguments: +# 1. The path, relative to the root of the Xcode project, where the Python +# XCframework can be found. +# 2. The base path, relative to the installed location in the app bundle, that +# needs to be processed. Any .so file found in this path (or a subdirectory +# of it) will be processed. +process_dylibs () { + PYTHON_XCFRAMEWORK_PATH=$1 + LIB_PATH=$2 + find "$CODESIGNING_FOLDER_PATH/$LIB_PATH" -name "*.so" | while read FULL_EXT; do + install_dylib $PYTHON_XCFRAMEWORK_PATH "$LIB_PATH/" "$FULL_EXT" + done +} + +# The entry point for post-processing a Python XCframework. +# +# Accepts 1 or more arguments: +# 1. The path, relative to the root of the Xcode project, where the Python +# XCframework can be found. If the XCframework is in the root of the project, +# 2+. The path of a package, relative to the root of the packaged app, that contains +# library content that should be processed for binary libraries. +install_python() { + PYTHON_XCFRAMEWORK_PATH=$1 + shift + + install_stdlib $PYTHON_XCFRAMEWORK_PATH + PYTHON_VER=$(ls -1 "$CODESIGNING_FOLDER_PATH/python/lib" | grep -E "^python3\.\d+$") + echo "Install Python $PYTHON_VER standard library extension modules..." + process_dylibs $PYTHON_XCFRAMEWORK_PATH python/lib/$PYTHON_VER/lib-dynload + + for package_path in $@; do + echo "Installing $package_path extension modules ..." + process_dylibs $PYTHON_XCFRAMEWORK_PATH $package_path + done +} diff --git a/iOS/testbed/Python.xcframework/ios-arm64/README b/Apple/testbed/Python.xcframework/ios-arm64/README similarity index 100% rename from iOS/testbed/Python.xcframework/ios-arm64/README rename to Apple/testbed/Python.xcframework/ios-arm64/README diff --git a/iOS/testbed/Python.xcframework/ios-arm64_x86_64-simulator/README b/Apple/testbed/Python.xcframework/ios-arm64_x86_64-simulator/README similarity index 100% rename from iOS/testbed/Python.xcframework/ios-arm64_x86_64-simulator/README rename to Apple/testbed/Python.xcframework/ios-arm64_x86_64-simulator/README diff --git a/Apple/testbed/Testbed.lldbinit b/Apple/testbed/Testbed.lldbinit new file mode 100644 index 00000000000000..4cf00dd0f9de1d --- /dev/null +++ b/Apple/testbed/Testbed.lldbinit @@ -0,0 +1,4 @@ +process handle SIGINT -n true -p true -s false +process handle SIGUSR1 -n true -p true -s false +process handle SIGUSR2 -n true -p true -s false +process handle SIGXFSZ -n true -p true -s false diff --git a/iOS/testbed/iOSTestbedTests/iOSTestbedTests.m b/Apple/testbed/TestbedTests/TestbedTests.m similarity index 69% rename from iOS/testbed/iOSTestbedTests/iOSTestbedTests.m rename to Apple/testbed/TestbedTests/TestbedTests.m index dd6e76f9496fe0..f7788c47f2c229 100644 --- a/iOS/testbed/iOSTestbedTests/iOSTestbedTests.m +++ b/Apple/testbed/TestbedTests/TestbedTests.m @@ -1,11 +1,11 @@ #import #import -@interface iOSTestbedTests : XCTestCase +@interface TestbedTests : XCTestCase @end -@implementation iOSTestbedTests +@implementation TestbedTests - (void)testPython { @@ -15,6 +15,11 @@ - (void)testPython { PyStatus status; PyPreConfig preconfig; PyConfig config; + PyObject *app_packages_path; + PyObject *method_args; + PyObject *result; + PyObject *site_module; + PyObject *site_addsitedir_attr; PyObject *sys_module; PyObject *sys_path_attr; NSArray *test_args; @@ -30,19 +35,26 @@ - (void)testPython { setenv("NO_COLOR", "1", true); setenv("PYTHON_COLORS", "0", true); + if (getenv("GITHUB_ACTIONS")) { + NSLog(@"Running in a GitHub Actions environment"); + } // Arguments to pass into the test suite runner. // argv[0] must identify the process; any subsequent arg // will be handled as if it were an argument to `python -m test` - test_args = [[NSBundle mainBundle] objectForInfoDictionaryKey:@"TestArgs"]; + // The processInfo arguments contain the binary that is running, + // followed by the arguments defined in the test plan. This means: + // run_module = test_args[1] + // argv = ["Testbed"] + test_args[2:] + test_args = [[NSProcessInfo processInfo] arguments]; if (test_args == NULL) { NSLog(@"Unable to identify test arguments."); } - argv = malloc(sizeof(char *) * ([test_args count] + 1)); - argv[0] = "iOSTestbed"; - for (int i = 1; i < [test_args count]; i++) { - argv[i] = [[test_args objectAtIndex:i] UTF8String]; + NSLog(@"Test arguments: %@", test_args); + argv = malloc(sizeof(char *) * ([test_args count] - 1)); + argv[0] = "Testbed"; + for (int i = 1; i < [test_args count] - 1; i++) { + argv[i] = [[test_args objectAtIndex:i+1] UTF8String]; } - NSLog(@"Test command: %@", test_args); // Generate an isolated Python configuration. NSLog(@"Configuring isolated Python..."); @@ -63,7 +75,7 @@ - (void)testPython { // Ensure that signal handlers are installed config.install_signal_handlers = 1; // Run the test module. - config.run_module = Py_DecodeLocale([[test_args objectAtIndex:0] UTF8String], NULL); + config.run_module = Py_DecodeLocale([[test_args objectAtIndex:1] UTF8String], NULL); // For debugging - enable verbose mode. // config.verbose = 1; @@ -96,7 +108,7 @@ - (void)testPython { } NSLog(@"Configure argc/argv..."); - status = PyConfig_SetBytesArgv(&config, [test_args count], (char**) argv); + status = PyConfig_SetBytesArgv(&config, [test_args count] - 1, (char**) argv); if (PyStatus_Exception(status)) { XCTFail(@"Unable to configure argc/argv: %s", status.err_msg); PyConfig_Clear(&config); @@ -111,29 +123,55 @@ - (void)testPython { return; } - sys_module = PyImport_ImportModule("sys"); - if (sys_module == NULL) { - XCTFail(@"Could not import sys module"); + // Add app_packages as a site directory. This both adds to sys.path, + // and ensures that any .pth files in that directory will be executed. + site_module = PyImport_ImportModule("site"); + if (site_module == NULL) { + XCTFail(@"Could not import site module"); return; } - sys_path_attr = PyObject_GetAttrString(sys_module, "path"); - if (sys_path_attr == NULL) { - XCTFail(@"Could not access sys.path"); + site_addsitedir_attr = PyObject_GetAttrString(site_module, "addsitedir"); + if (site_addsitedir_attr == NULL || !PyCallable_Check(site_addsitedir_attr)) { + XCTFail(@"Could not access site.addsitedir"); return; } - // Add the app packages path path = [NSString stringWithFormat:@"%@/app_packages", resourcePath, nil]; NSLog(@"App packages path: %@", path); wtmp_str = Py_DecodeLocale([path UTF8String], NULL); - failed = PyList_Insert(sys_path_attr, 0, PyUnicode_FromString([path UTF8String])); - if (failed) { - XCTFail(@"Unable to add app packages to sys.path"); + app_packages_path = PyUnicode_FromWideChar(wtmp_str, wcslen(wtmp_str)); + if (app_packages_path == NULL) { + XCTFail(@"Could not convert app_packages path to unicode"); return; } PyMem_RawFree(wtmp_str); + method_args = Py_BuildValue("(O)", app_packages_path); + if (method_args == NULL) { + XCTFail(@"Could not create arguments for site.addsitedir"); + return; + } + + result = PyObject_CallObject(site_addsitedir_attr, method_args); + if (result == NULL) { + XCTFail(@"Could not add app_packages directory using site.addsitedir"); + return; + } + + // Add test code to sys.path + sys_module = PyImport_ImportModule("sys"); + if (sys_module == NULL) { + XCTFail(@"Could not import sys module"); + return; + } + + sys_path_attr = PyObject_GetAttrString(sys_module, "path"); + if (sys_path_attr == NULL) { + XCTFail(@"Could not access sys.path"); + return; + } + path = [NSString stringWithFormat:@"%@/app", resourcePath, nil]; NSLog(@"App path: %@", path); wtmp_str = Py_DecodeLocale([path UTF8String], NULL); diff --git a/Apple/testbed/__main__.py b/Apple/testbed/__main__.py new file mode 100644 index 00000000000000..797b522678f9d7 --- /dev/null +++ b/Apple/testbed/__main__.py @@ -0,0 +1,441 @@ +import argparse +import json +import os +import re +import shlex +import shutil +import subprocess +import sys +from pathlib import Path + +TEST_SLICES = { + "iOS": "ios-arm64_x86_64-simulator", +} + +DECODE_ARGS = ("UTF-8", "backslashreplace") + +# The system log prefixes each line: +# 2025-01-17 16:14:29.093742+0800 iOSTestbed[23987:1fd393b4] ... +# 2025-01-17 16:14:29.093742+0800 iOSTestbed[23987:1fd393b4] ... + +LOG_PREFIX_REGEX = re.compile( + r"^\d{4}-\d{2}-\d{2}" # YYYY-MM-DD + r"\s+\d+:\d{2}:\d{2}\.\d+\+\d{4}" # HH:MM:SS.ssssss+ZZZZ + r"\s+iOSTestbed\[\d+:\w+\] " # Process/thread ID +) + + +# Select a simulator device to use. +def select_simulator_device(platform): + # List the testing simulators, in JSON format + raw_json = subprocess.check_output(["xcrun", "simctl", "list", "-j"]) + json_data = json.loads(raw_json) + + if platform == "iOS": + # Any iOS device will do; we'll look for "SE" devices - but the name + # isn't consistent over time. Older Xcode versions will use "iPhone SE + # (Nth generation)"; As of 2025, they've started using "iPhone 16e". + # + # When Xcode is updated after a new release, new devices will be + # available and old ones will be dropped from the set available on the + # latest iOS version. Select the one with the highest minimum runtime + # version - this is an indicator of the "newest" released device, which + # should always be supported on the "most recent" iOS version. + se_simulators = sorted( + (devicetype["minRuntimeVersion"], devicetype["name"]) + for devicetype in json_data["devicetypes"] + if devicetype["productFamily"] == "iPhone" + and ( + ( + "iPhone " in devicetype["name"] + and devicetype["name"].endswith("e") + ) + or "iPhone SE " in devicetype["name"] + ) + ) + simulator = se_simulators[-1][1] + else: + raise ValueError(f"Unknown platform {platform}") + + return simulator + + +def xcode_test(location: Path, platform: str, simulator: str, verbose: bool): + # Build and run the test suite on the named simulator. + args = [ + "-project", + str(location / f"{platform}Testbed.xcodeproj"), + "-scheme", + f"{platform}Testbed", + "-destination", + f"platform={platform} Simulator,name={simulator}", + "-derivedDataPath", + str(location / "DerivedData"), + ] + verbosity_args = [] if verbose else ["-quiet"] + + print("Building test project...") + subprocess.run( + ["xcodebuild", "build-for-testing"] + args + verbosity_args, + check=True, + ) + + # Any environment variable prefixed with TEST_RUNNER_ is exposed into the + # test runner environment. There are some variables (like those identifying + # CI platforms) that can be useful to have access to. + test_env = os.environ.copy() + if "GITHUB_ACTIONS" in os.environ: + test_env["TEST_RUNNER_GITHUB_ACTIONS"] = os.environ["GITHUB_ACTIONS"] + + print("Running test project...") + # Test execution *can't* be run -quiet; verbose mode + # is how we see the output of the test output. + process = subprocess.Popen( + ["xcodebuild", "test-without-building"] + args, + stdout=subprocess.PIPE, + stderr=subprocess.STDOUT, + env=test_env, + ) + while line := (process.stdout.readline()).decode(*DECODE_ARGS): + # Strip the timestamp/process prefix from each log line + line = LOG_PREFIX_REGEX.sub("", line) + sys.stdout.write(line) + sys.stdout.flush() + + status = process.wait(timeout=5) + exit(status) + + +def copy(src, tgt): + """An all-purpose copy. + + If src is a file, it is copied. If src is a symlink, it is copied *as a + symlink*. If src is a directory, the full tree is duplicated, with symlinks + being preserved. + """ + if src.is_file() or src.is_symlink(): + shutil.copyfile(src, tgt, follow_symlinks=False) + else: + shutil.copytree(src, tgt, symlinks=True) + + +def clone_testbed( + source: Path, + target: Path, + framework: Path, + platform: str, + apps: list[Path], +) -> None: + if target.exists(): + print(f"{target} already exists; aborting without creating project.") + sys.exit(10) + + if framework is None: + if not ( + source / "Python.xcframework" / TEST_SLICES[platform] / "bin" + ).is_dir(): + print( + f"The testbed being cloned ({source}) does not contain " + "a framework with slices. Re-run with --framework" + ) + sys.exit(11) + else: + if not framework.is_dir(): + print(f"{framework} does not exist.") + sys.exit(12) + elif not ( + framework.suffix == ".xcframework" + or (framework / "Python.framework").is_dir() + ): + print( + f"{framework} is not an XCframework, " + f"or a simulator slice of a framework build." + ) + sys.exit(13) + + print("Cloning testbed project:") + print(f" Cloning {source}...", end="") + # Only copy the files for the platform being cloned plus the files common + # to all platforms. The XCframework will be copied later, if needed. + target.mkdir(parents=True) + + for name in [ + "__main__.py", + "TestbedTests", + "Testbed.lldbinit", + f"{platform}Testbed", + f"{platform}Testbed.xcodeproj", + f"{platform}Testbed.xctestplan", + ]: + copy(source / name, target / name) + + print(" done") + + orig_xc_framework_path = source / "Python.xcframework" + xc_framework_path = target / "Python.xcframework" + test_framework_path = xc_framework_path / TEST_SLICES[platform] + if framework is not None: + if framework.suffix == ".xcframework": + print(" Installing XCFramework...", end="") + xc_framework_path.symlink_to( + framework.relative_to(xc_framework_path.parent, walk_up=True) + ) + print(" done") + else: + print(" Installing simulator framework...", end="") + # We're only installing a slice of a framework; we need + # to do a full tree copy to make sure we don't damage + # symlinked content. + shutil.copytree(orig_xc_framework_path, xc_framework_path) + if test_framework_path.is_dir(): + shutil.rmtree(test_framework_path) + else: + test_framework_path.unlink(missing_ok=True) + test_framework_path.symlink_to( + framework.relative_to(test_framework_path.parent, walk_up=True) + ) + print(" done") + else: + copy(orig_xc_framework_path, xc_framework_path) + + if ( + xc_framework_path.is_symlink() + and not xc_framework_path.readlink().is_absolute() + ): + # XCFramework is a relative symlink. Rewrite the symlink relative + # to the new location. + print(" Rewriting symlink to XCframework...", end="") + resolved_xc_framework_path = ( + source / xc_framework_path.readlink() + ).resolve() + xc_framework_path.unlink() + xc_framework_path.symlink_to( + resolved_xc_framework_path.relative_to( + xc_framework_path.parent, walk_up=True + ) + ) + print(" done") + elif ( + test_framework_path.is_symlink() + and not test_framework_path.readlink().is_absolute() + ): + print(" Rewriting symlink to simulator framework...", end="") + # Simulator framework is a relative symlink. Rewrite the symlink + # relative to the new location. + orig_test_framework_path = ( + source / "Python.XCframework" / test_framework_path.readlink() + ).resolve() + test_framework_path.unlink() + test_framework_path.symlink_to( + orig_test_framework_path.relative_to( + test_framework_path.parent, walk_up=True + ) + ) + print(" done") + else: + print(" Using pre-existing Python framework.") + + for app_src in apps: + print(f" Installing app {app_src.name!r}...", end="") + app_target = target / f"Testbed/app/{app_src.name}" + if app_target.is_dir(): + shutil.rmtree(app_target) + shutil.copytree(app_src, app_target) + print(" done") + + print(f"Successfully cloned testbed: {target.resolve()}") + + +def update_test_plan(testbed_path, platform, args): + # Modify the test plan to use the requested test arguments. + test_plan_path = testbed_path / f"{platform}Testbed.xctestplan" + with test_plan_path.open("r", encoding="utf-8") as f: + test_plan = json.load(f) + + test_plan["defaultOptions"]["commandLineArgumentEntries"] = [ + {"argument": shlex.quote(arg)} for arg in args + ] + + with test_plan_path.open("w", encoding="utf-8") as f: + json.dump(test_plan, f, indent=2) + + +def run_testbed( + platform: str, + simulator: str | None, + args: list[str], + verbose: bool = False, +): + location = Path(__file__).parent + print("Updating test plan...", end="") + update_test_plan(location, platform, args) + print(" done.") + + # xcodebuild doesn't guarantee that the CoreSimulatorService daemon is + # running prior to using a simulator, but calling `xcrun simctl list` does. + # Determining the default simulator that *would* be used is a cheap action; + # so use that as a way to ensure that the CoreSimulatorService daemon is + # running. + default_simulator = select_simulator_device(platform) + if simulator is None: + simulator = default_simulator + print(f"Running test on {simulator}") + + xcode_test( + location, + platform=platform, + simulator=simulator, + verbose=verbose, + ) + + +def main(): + # Look for directories like `iOSTestbed` as an indicator of the platforms + # that the testbed folder supports. The original source testbed can support + # many platforms, but when cloned, only one platform is preserved. + available_platforms = [ + platform + for platform in ["iOS"] + if (Path(__file__).parent / f"{platform}Testbed").is_dir() + ] + + parser = argparse.ArgumentParser( + description=( + "Manages the process of testing an Apple Python project " + "through Xcode." + ), + ) + + subcommands = parser.add_subparsers(dest="subcommand") + clone = subcommands.add_parser( + "clone", + description=( + "Clone the testbed project, copying in a Python framework and" + "any specified application code." + ), + help="Clone a testbed project to a new location.", + ) + clone.add_argument( + "--framework", + help=( + "The location of the XCFramework (or simulator-only slice of an " + "XCFramework) to use when running the testbed" + ), + ) + clone.add_argument( + "--platform", + dest="platform", + choices=available_platforms, + default=available_platforms[0], + help=f"The platform to target (default: {available_platforms[0]})", + ) + clone.add_argument( + "--app", + dest="apps", + action="append", + default=[], + help="The location of any code to include in the testbed project", + ) + clone.add_argument( + "location", + help="The path where the testbed will be cloned.", + ) + + run = subcommands.add_parser( + "run", + usage=( + "%(prog)s [-h] [--simulator SIMULATOR] -- " + " [ ...]" + ), + description=( + "Run a testbed project. The arguments provided after `--` will be " + "passed to the running iOS process as if they were arguments to " + "`python -m`." + ), + help="Run a testbed project", + ) + run.add_argument( + "--platform", + dest="platform", + choices=available_platforms, + default=available_platforms[0], + help=f"The platform to target (default: {available_platforms[0]})", + ) + run.add_argument( + "--simulator", + help=( + "The name of the simulator to use (eg: 'iPhone 16e'). Defaults to " + "the most recently released 'entry level' iPhone device. Device " + "architecture and OS version can also be specified; e.g., " + "`--simulator 'iPhone 16 Pro,arch=arm64,OS=26.0'` would run on " + "an ARM64 iPhone 16 Pro simulator running iOS 26.0." + ), + ) + run.add_argument( + "-v", + "--verbose", + action="store_true", + help="Enable verbose output", + ) + + try: + pos = sys.argv.index("--") + testbed_args = sys.argv[1:pos] + test_args = sys.argv[pos + 1 :] + except ValueError: + testbed_args = sys.argv[1:] + test_args = [] + + context = parser.parse_args(testbed_args) + + if context.subcommand == "clone": + clone_testbed( + source=Path(__file__).parent.resolve(), + target=Path(context.location).resolve(), + framework=Path(context.framework).resolve() + if context.framework + else None, + platform=context.platform, + apps=[Path(app) for app in context.apps], + ) + elif context.subcommand == "run": + if test_args: + if not ( + Path(__file__).parent + / "Python.xcframework" + / TEST_SLICES[context.platform] + / "bin" + ).is_dir(): + print( + "Testbed does not contain a compiled Python framework. " + f"Use `python {sys.argv[0]} clone ...` to create a " + "runnable clone of this testbed." + ) + sys.exit(20) + + run_testbed( + platform=context.platform, + simulator=context.simulator, + verbose=context.verbose, + args=test_args, + ) + else: + print( + "Must specify test arguments " + f"(e.g., {sys.argv[0]} run -- test)" + ) + print() + parser.print_help(sys.stderr) + sys.exit(21) + else: + parser.print_help(sys.stderr) + sys.exit(1) + + +if __name__ == "__main__": + # Under the buildbot, stdout is not a TTY, but we must still flush after + # every line to make sure our output appears in the correct order relative + # to the output of our subprocesses. + for stream in [sys.stdout, sys.stderr]: + stream.reconfigure(line_buffering=True) + main() diff --git a/iOS/testbed/iOSTestbed.xcodeproj/project.pbxproj b/Apple/testbed/iOSTestbed.xcodeproj/project.pbxproj similarity index 78% rename from iOS/testbed/iOSTestbed.xcodeproj/project.pbxproj rename to Apple/testbed/iOSTestbed.xcodeproj/project.pbxproj index c7d63909ee2453..f8835a3bc587df 100644 --- a/iOS/testbed/iOSTestbed.xcodeproj/project.pbxproj +++ b/Apple/testbed/iOSTestbed.xcodeproj/project.pbxproj @@ -11,12 +11,11 @@ 607A66222B0EFA390010BFC8 /* Assets.xcassets in Resources */ = {isa = PBXBuildFile; fileRef = 607A66212B0EFA390010BFC8 /* Assets.xcassets */; }; 607A66252B0EFA390010BFC8 /* LaunchScreen.storyboard in Resources */ = {isa = PBXBuildFile; fileRef = 607A66232B0EFA390010BFC8 /* LaunchScreen.storyboard */; }; 607A66282B0EFA390010BFC8 /* main.m in Sources */ = {isa = PBXBuildFile; fileRef = 607A66272B0EFA390010BFC8 /* main.m */; }; - 607A66322B0EFA3A0010BFC8 /* iOSTestbedTests.m in Sources */ = {isa = PBXBuildFile; fileRef = 607A66312B0EFA3A0010BFC8 /* iOSTestbedTests.m */; }; + 607A66322B0EFA3A0010BFC8 /* TestbedTests.m in Sources */ = {isa = PBXBuildFile; fileRef = 607A66312B0EFA3A0010BFC8 /* TestbedTests.m */; }; 607A664C2B0EFC080010BFC8 /* Python.xcframework in Frameworks */ = {isa = PBXBuildFile; fileRef = 607A664A2B0EFB310010BFC8 /* Python.xcframework */; }; 607A664D2B0EFC080010BFC8 /* Python.xcframework in Embed Frameworks */ = {isa = PBXBuildFile; fileRef = 607A664A2B0EFB310010BFC8 /* Python.xcframework */; settings = {ATTRIBUTES = (CodeSignOnCopy, RemoveHeadersOnCopy, ); }; }; 607A66502B0EFFE00010BFC8 /* Python.xcframework in Frameworks */ = {isa = PBXBuildFile; fileRef = 607A664A2B0EFB310010BFC8 /* Python.xcframework */; }; 607A66512B0EFFE00010BFC8 /* Python.xcframework in Embed Frameworks */ = {isa = PBXBuildFile; fileRef = 607A664A2B0EFB310010BFC8 /* Python.xcframework */; settings = {ATTRIBUTES = (CodeSignOnCopy, RemoveHeadersOnCopy, ); }; }; - 607A66582B0F079F0010BFC8 /* dylib-Info-template.plist in Resources */ = {isa = PBXBuildFile; fileRef = 607A66572B0F079F0010BFC8 /* dylib-Info-template.plist */; }; 608619542CB77BA900F46182 /* app_packages in Resources */ = {isa = PBXBuildFile; fileRef = 608619532CB77BA900F46182 /* app_packages */; }; 608619562CB7819B00F46182 /* app in Resources */ = {isa = PBXBuildFile; fileRef = 608619552CB7819B00F46182 /* app */; }; /* End PBXBuildFile section */ @@ -64,12 +63,12 @@ 607A66242B0EFA390010BFC8 /* Base */ = {isa = PBXFileReference; lastKnownFileType = file.storyboard; name = Base; path = Base.lproj/LaunchScreen.storyboard; sourceTree = ""; }; 607A66272B0EFA390010BFC8 /* main.m */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.objc; path = main.m; sourceTree = ""; }; 607A662D2B0EFA3A0010BFC8 /* iOSTestbedTests.xctest */ = {isa = PBXFileReference; explicitFileType = wrapper.cfbundle; includeInIndex = 0; path = iOSTestbedTests.xctest; sourceTree = BUILT_PRODUCTS_DIR; }; - 607A66312B0EFA3A0010BFC8 /* iOSTestbedTests.m */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.objc; path = iOSTestbedTests.m; sourceTree = ""; }; + 607A66312B0EFA3A0010BFC8 /* TestbedTests.m */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.c.objc; path = TestbedTests.m; sourceTree = ""; }; 607A664A2B0EFB310010BFC8 /* Python.xcframework */ = {isa = PBXFileReference; lastKnownFileType = wrapper.xcframework; path = Python.xcframework; sourceTree = ""; }; - 607A66572B0F079F0010BFC8 /* dylib-Info-template.plist */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = text.plist.xml; path = "dylib-Info-template.plist"; sourceTree = ""; }; 607A66592B0F08600010BFC8 /* iOSTestbed-Info.plist */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = text.plist.xml; path = "iOSTestbed-Info.plist"; sourceTree = ""; }; 608619532CB77BA900F46182 /* app_packages */ = {isa = PBXFileReference; lastKnownFileType = folder; path = app_packages; sourceTree = ""; }; 608619552CB7819B00F46182 /* app */ = {isa = PBXFileReference; lastKnownFileType = folder; path = app; sourceTree = ""; }; + 60FE0EFB2E56BB6D00524F87 /* iOSTestbed.xctestplan */ = {isa = PBXFileReference; lastKnownFileType = text; path = iOSTestbed.xctestplan; sourceTree = ""; }; /* End PBXFileReference section */ /* Begin PBXFrameworksBuildPhase section */ @@ -95,9 +94,10 @@ 607A66092B0EFA380010BFC8 = { isa = PBXGroup; children = ( + 60FE0EFB2E56BB6D00524F87 /* iOSTestbed.xctestplan */, 607A664A2B0EFB310010BFC8 /* Python.xcframework */, 607A66142B0EFA380010BFC8 /* iOSTestbed */, - 607A66302B0EFA3A0010BFC8 /* iOSTestbedTests */, + 607A66302B0EFA3A0010BFC8 /* TestbedTests */, 607A66132B0EFA380010BFC8 /* Products */, 607A664F2B0EFFE00010BFC8 /* Frameworks */, ); @@ -118,7 +118,6 @@ 608619552CB7819B00F46182 /* app */, 608619532CB77BA900F46182 /* app_packages */, 607A66592B0F08600010BFC8 /* iOSTestbed-Info.plist */, - 607A66572B0F079F0010BFC8 /* dylib-Info-template.plist */, 607A66152B0EFA380010BFC8 /* AppDelegate.h */, 607A66162B0EFA380010BFC8 /* AppDelegate.m */, 607A66212B0EFA390010BFC8 /* Assets.xcassets */, @@ -128,12 +127,12 @@ path = iOSTestbed; sourceTree = ""; }; - 607A66302B0EFA3A0010BFC8 /* iOSTestbedTests */ = { + 607A66302B0EFA3A0010BFC8 /* TestbedTests */ = { isa = PBXGroup; children = ( - 607A66312B0EFA3A0010BFC8 /* iOSTestbedTests.m */, + 607A66312B0EFA3A0010BFC8 /* TestbedTests.m */, ); - path = iOSTestbedTests; + path = TestbedTests; sourceTree = ""; }; 607A664F2B0EFFE00010BFC8 /* Frameworks */ = { @@ -153,8 +152,7 @@ 607A660E2B0EFA380010BFC8 /* Sources */, 607A660F2B0EFA380010BFC8 /* Frameworks */, 607A66102B0EFA380010BFC8 /* Resources */, - 607A66552B0F061D0010BFC8 /* Install Target Specific Python Standard Library */, - 607A66562B0F06200010BFC8 /* Prepare Python Binary Modules */, + 607A66552B0F061D0010BFC8 /* Process Python libraries */, 607A664E2B0EFC080010BFC8 /* Embed Frameworks */, ); buildRules = ( @@ -228,7 +226,6 @@ buildActionMask = 2147483647; files = ( 607A66252B0EFA390010BFC8 /* LaunchScreen.storyboard in Resources */, - 607A66582B0F079F0010BFC8 /* dylib-Info-template.plist in Resources */, 608619562CB7819B00F46182 /* app in Resources */, 607A66222B0EFA390010BFC8 /* Assets.xcassets in Resources */, 608619542CB77BA900F46182 /* app_packages in Resources */, @@ -245,7 +242,7 @@ /* End PBXResourcesBuildPhase section */ /* Begin PBXShellScriptBuildPhase section */ - 607A66552B0F061D0010BFC8 /* Install Target Specific Python Standard Library */ = { + 607A66552B0F061D0010BFC8 /* Process Python libraries */ = { isa = PBXShellScriptBuildPhase; alwaysOutOfDate = 1; buildActionMask = 2147483647; @@ -255,34 +252,14 @@ ); inputPaths = ( ); - name = "Install Target Specific Python Standard Library"; + name = "Process Python libraries"; outputFileListPaths = ( ); outputPaths = ( ); runOnlyForDeploymentPostprocessing = 0; shellPath = /bin/sh; - shellScript = "set -e\n\nmkdir -p \"$CODESIGNING_FOLDER_PATH/python/lib\"\nif [ \"$EFFECTIVE_PLATFORM_NAME\" = \"-iphonesimulator\" ]; then\n echo \"Installing Python modules for iOS Simulator\"\n rsync -au --delete \"$PROJECT_DIR/Python.xcframework/ios-arm64_x86_64-simulator/lib/\" \"$CODESIGNING_FOLDER_PATH/python/lib/\" \nelse\n echo \"Installing Python modules for iOS Device\"\n rsync -au --delete \"$PROJECT_DIR/Python.xcframework/ios-arm64/lib/\" \"$CODESIGNING_FOLDER_PATH/python/lib/\" \nfi\n"; - showEnvVarsInLog = 0; - }; - 607A66562B0F06200010BFC8 /* Prepare Python Binary Modules */ = { - isa = PBXShellScriptBuildPhase; - alwaysOutOfDate = 1; - buildActionMask = 2147483647; - files = ( - ); - inputFileListPaths = ( - ); - inputPaths = ( - ); - name = "Prepare Python Binary Modules"; - outputFileListPaths = ( - ); - outputPaths = ( - ); - runOnlyForDeploymentPostprocessing = 0; - shellPath = /bin/sh; - shellScript = "set -e\n\ninstall_dylib () {\n INSTALL_BASE=$1\n FULL_EXT=$2\n\n # The name of the extension file\n EXT=$(basename \"$FULL_EXT\")\n # The location of the extension file, relative to the bundle\n RELATIVE_EXT=${FULL_EXT#$CODESIGNING_FOLDER_PATH/} \n # The path to the extension file, relative to the install base\n PYTHON_EXT=${RELATIVE_EXT/$INSTALL_BASE/}\n # The full dotted name of the extension module, constructed from the file path.\n FULL_MODULE_NAME=$(echo $PYTHON_EXT | cut -d \".\" -f 1 | tr \"/\" \".\"); \n # A bundle identifier; not actually used, but required by Xcode framework packaging\n FRAMEWORK_BUNDLE_ID=$(echo $PRODUCT_BUNDLE_IDENTIFIER.$FULL_MODULE_NAME | tr \"_\" \"-\")\n # The name of the framework folder.\n FRAMEWORK_FOLDER=\"Frameworks/$FULL_MODULE_NAME.framework\"\n\n # If the framework folder doesn't exist, create it.\n if [ ! -d \"$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER\" ]; then\n echo \"Creating framework for $RELATIVE_EXT\" \n mkdir -p \"$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER\"\n cp \"$CODESIGNING_FOLDER_PATH/dylib-Info-template.plist\" \"$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER/Info.plist\"\n plutil -replace CFBundleExecutable -string \"$FULL_MODULE_NAME\" \"$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER/Info.plist\"\n plutil -replace CFBundleIdentifier -string \"$FRAMEWORK_BUNDLE_ID\" \"$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER/Info.plist\"\n fi\n \n echo \"Installing binary for $FRAMEWORK_FOLDER/$FULL_MODULE_NAME\" \n mv \"$FULL_EXT\" \"$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER/$FULL_MODULE_NAME\"\n # Create a placeholder .fwork file where the .so was\n echo \"$FRAMEWORK_FOLDER/$FULL_MODULE_NAME\" > ${FULL_EXT%.so}.fwork\n # Create a back reference to the .so file location in the framework\n echo \"${RELATIVE_EXT%.so}.fwork\" > \"$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER/$FULL_MODULE_NAME.origin\" \n}\n\nPYTHON_VER=$(ls -1 \"$CODESIGNING_FOLDER_PATH/python/lib\")\necho \"Install Python $PYTHON_VER standard library extension modules...\"\nfind \"$CODESIGNING_FOLDER_PATH/python/lib/$PYTHON_VER/lib-dynload\" -name \"*.so\" | while read FULL_EXT; do\n install_dylib python/lib/$PYTHON_VER/lib-dynload/ \"$FULL_EXT\"\ndone\necho \"Install app package extension modules...\"\nfind \"$CODESIGNING_FOLDER_PATH/app_packages\" -name \"*.so\" | while read FULL_EXT; do\n install_dylib app_packages/ \"$FULL_EXT\"\ndone\necho \"Install app extension modules...\"\nfind \"$CODESIGNING_FOLDER_PATH/app\" -name \"*.so\" | while read FULL_EXT; do\n install_dylib app/ \"$FULL_EXT\"\ndone\n\n# Clean up dylib template \nrm -f \"$CODESIGNING_FOLDER_PATH/dylib-Info-template.plist\"\necho \"Signing frameworks as $EXPANDED_CODE_SIGN_IDENTITY_NAME ($EXPANDED_CODE_SIGN_IDENTITY)...\"\nfind \"$CODESIGNING_FOLDER_PATH/Frameworks\" -name \"*.framework\" -exec /usr/bin/codesign --force --sign \"$EXPANDED_CODE_SIGN_IDENTITY\" ${OTHER_CODE_SIGN_FLAGS:-} -o runtime --timestamp=none --preserve-metadata=identifier,entitlements,flags --generate-entitlement-der \"{}\" \\; \n"; + shellScript = "set -e\nsource $PROJECT_DIR/Python.xcframework/build/utils.sh\ninstall_python Python.xcframework app app_packages\n"; showEnvVarsInLog = 0; }; /* End PBXShellScriptBuildPhase section */ @@ -301,7 +278,7 @@ isa = PBXSourcesBuildPhase; buildActionMask = 2147483647; files = ( - 607A66322B0EFA3A0010BFC8 /* iOSTestbedTests.m in Sources */, + 607A66322B0EFA3A0010BFC8 /* TestbedTests.m in Sources */, ); runOnlyForDeploymentPostprocessing = 0; }; @@ -379,7 +356,7 @@ GCC_WARN_UNINITIALIZED_AUTOS = YES_AGGRESSIVE; GCC_WARN_UNUSED_FUNCTION = YES; GCC_WARN_UNUSED_VARIABLE = YES; - IPHONEOS_DEPLOYMENT_TARGET = 12.0; + IPHONEOS_DEPLOYMENT_TARGET = 13.0; LOCALIZATION_PREFERS_STRING_CATALOGS = YES; MTL_ENABLE_DEBUG_INFO = INCLUDE_SOURCE; MTL_FAST_MATH = YES; @@ -434,7 +411,7 @@ GCC_WARN_UNINITIALIZED_AUTOS = YES_AGGRESSIVE; GCC_WARN_UNUSED_FUNCTION = YES; GCC_WARN_UNUSED_VARIABLE = YES; - IPHONEOS_DEPLOYMENT_TARGET = 12.0; + IPHONEOS_DEPLOYMENT_TARGET = 13.0; LOCALIZATION_PREFERS_STRING_CATALOGS = YES; MTL_ENABLE_DEBUG_INFO = NO; MTL_FAST_MATH = YES; @@ -460,7 +437,7 @@ INFOPLIST_KEY_UIMainStoryboardFile = Main; INFOPLIST_KEY_UISupportedInterfaceOrientations_iPad = "UIInterfaceOrientationPortrait UIInterfaceOrientationPortraitUpsideDown UIInterfaceOrientationLandscapeLeft UIInterfaceOrientationLandscapeRight"; INFOPLIST_KEY_UISupportedInterfaceOrientations_iPhone = "UIInterfaceOrientationPortrait UIInterfaceOrientationLandscapeLeft UIInterfaceOrientationLandscapeRight"; - IPHONEOS_DEPLOYMENT_TARGET = 12.0; + IPHONEOS_DEPLOYMENT_TARGET = 13.0; LD_RUNPATH_SEARCH_PATHS = ( "$(inherited)", "@executable_path/Frameworks", @@ -491,7 +468,7 @@ INFOPLIST_KEY_UIMainStoryboardFile = Main; INFOPLIST_KEY_UISupportedInterfaceOrientations_iPad = "UIInterfaceOrientationPortrait UIInterfaceOrientationPortraitUpsideDown UIInterfaceOrientationLandscapeLeft UIInterfaceOrientationLandscapeRight"; INFOPLIST_KEY_UISupportedInterfaceOrientations_iPhone = "UIInterfaceOrientationPortrait UIInterfaceOrientationLandscapeLeft UIInterfaceOrientationLandscapeRight"; - IPHONEOS_DEPLOYMENT_TARGET = 12.0; + IPHONEOS_DEPLOYMENT_TARGET = 13.0; LD_RUNPATH_SEARCH_PATHS = ( "$(inherited)", "@executable_path/Frameworks", @@ -514,7 +491,7 @@ DEVELOPMENT_TEAM = 3HEZE76D99; GENERATE_INFOPLIST_FILE = YES; HEADER_SEARCH_PATHS = "\"$(BUILT_PRODUCTS_DIR)/Python.framework/Headers\""; - IPHONEOS_DEPLOYMENT_TARGET = 12.0; + IPHONEOS_DEPLOYMENT_TARGET = 13.0; MARKETING_VERSION = 1.0; PRODUCT_BUNDLE_IDENTIFIER = org.python.iOSTestbedTests; PRODUCT_NAME = "$(TARGET_NAME)"; @@ -534,7 +511,7 @@ DEVELOPMENT_TEAM = 3HEZE76D99; GENERATE_INFOPLIST_FILE = YES; HEADER_SEARCH_PATHS = "\"$(BUILT_PRODUCTS_DIR)/Python.framework/Headers\""; - IPHONEOS_DEPLOYMENT_TARGET = 12.0; + IPHONEOS_DEPLOYMENT_TARGET = 13.0; MARKETING_VERSION = 1.0; PRODUCT_BUNDLE_IDENTIFIER = org.python.iOSTestbedTests; PRODUCT_NAME = "$(TARGET_NAME)"; diff --git a/Apple/testbed/iOSTestbed.xcodeproj/xcshareddata/xcschemes/iOSTestbed.xcscheme b/Apple/testbed/iOSTestbed.xcodeproj/xcshareddata/xcschemes/iOSTestbed.xcscheme new file mode 100644 index 00000000000000..3c330a4152bf92 --- /dev/null +++ b/Apple/testbed/iOSTestbed.xcodeproj/xcshareddata/xcschemes/iOSTestbed.xcscheme @@ -0,0 +1,97 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/Apple/testbed/iOSTestbed.xctestplan b/Apple/testbed/iOSTestbed.xctestplan new file mode 100644 index 00000000000000..0c4ab9eb2bad30 --- /dev/null +++ b/Apple/testbed/iOSTestbed.xctestplan @@ -0,0 +1,46 @@ +{ + "configurations" : [ + { + "id" : "F5A95CE4-1ADE-4A6E-A0E1-CDBAE26DF0C5", + "name" : "Test Scheme Action", + "options" : { + + } + } + ], + "defaultOptions" : { + "commandLineArgumentEntries" : [ + { + "argument" : "test" + }, + { + "argument" : "-uall" + }, + { + "argument" : "--single-process" + }, + { + "argument" : "--rerun" + }, + { + "argument" : "-W" + } + ], + "targetForVariableExpansion" : { + "containerPath" : "container:iOSTestbed.xcodeproj", + "identifier" : "607A66112B0EFA380010BFC8", + "name" : "iOSTestbed" + } + }, + "testTargets" : [ + { + "parallelizable" : false, + "target" : { + "containerPath" : "container:iOSTestbed.xcodeproj", + "identifier" : "607A662C2B0EFA3A0010BFC8", + "name" : "iOSTestbedTests" + } + } + ], + "version" : 1 +} diff --git a/iOS/testbed/iOSTestbed/AppDelegate.h b/Apple/testbed/iOSTestbed/AppDelegate.h similarity index 100% rename from iOS/testbed/iOSTestbed/AppDelegate.h rename to Apple/testbed/iOSTestbed/AppDelegate.h diff --git a/iOS/testbed/iOSTestbed/AppDelegate.m b/Apple/testbed/iOSTestbed/AppDelegate.m similarity index 100% rename from iOS/testbed/iOSTestbed/AppDelegate.m rename to Apple/testbed/iOSTestbed/AppDelegate.m diff --git a/iOS/testbed/iOSTestbed/Assets.xcassets/AccentColor.colorset/Contents.json b/Apple/testbed/iOSTestbed/Assets.xcassets/AccentColor.colorset/Contents.json similarity index 100% rename from iOS/testbed/iOSTestbed/Assets.xcassets/AccentColor.colorset/Contents.json rename to Apple/testbed/iOSTestbed/Assets.xcassets/AccentColor.colorset/Contents.json diff --git a/iOS/testbed/iOSTestbed/Assets.xcassets/AppIcon.appiconset/Contents.json b/Apple/testbed/iOSTestbed/Assets.xcassets/AppIcon.appiconset/Contents.json similarity index 100% rename from iOS/testbed/iOSTestbed/Assets.xcassets/AppIcon.appiconset/Contents.json rename to Apple/testbed/iOSTestbed/Assets.xcassets/AppIcon.appiconset/Contents.json diff --git a/iOS/testbed/iOSTestbed/Assets.xcassets/Contents.json b/Apple/testbed/iOSTestbed/Assets.xcassets/Contents.json similarity index 100% rename from iOS/testbed/iOSTestbed/Assets.xcassets/Contents.json rename to Apple/testbed/iOSTestbed/Assets.xcassets/Contents.json diff --git a/iOS/testbed/iOSTestbed/Base.lproj/LaunchScreen.storyboard b/Apple/testbed/iOSTestbed/Base.lproj/LaunchScreen.storyboard similarity index 100% rename from iOS/testbed/iOSTestbed/Base.lproj/LaunchScreen.storyboard rename to Apple/testbed/iOSTestbed/Base.lproj/LaunchScreen.storyboard diff --git a/iOS/testbed/iOSTestbed/app/README b/Apple/testbed/iOSTestbed/app/README similarity index 92% rename from iOS/testbed/iOSTestbed/app/README rename to Apple/testbed/iOSTestbed/app/README index af22c685f87976..46c0e8e2a29a1c 100644 --- a/iOS/testbed/iOSTestbed/app/README +++ b/Apple/testbed/iOSTestbed/app/README @@ -1,7 +1,7 @@ This folder can contain any Python application code. During the build, any binary modules found in this folder will be processed into -iOS Framework form. +Framework form. When the test suite runs, this folder will be on the PYTHONPATH, and will be the working directory for the test suite. diff --git a/iOS/testbed/iOSTestbed/app_packages/README b/Apple/testbed/iOSTestbed/app_packages/README similarity index 92% rename from iOS/testbed/iOSTestbed/app_packages/README rename to Apple/testbed/iOSTestbed/app_packages/README index 42d7fdeb813250..02c2beccfbdaed 100644 --- a/iOS/testbed/iOSTestbed/app_packages/README +++ b/Apple/testbed/iOSTestbed/app_packages/README @@ -2,6 +2,6 @@ This folder can be a target for installing any Python dependencies needed by the test suite. During the build, any binary modules found in this folder will be processed into -iOS Framework form. +Framework form. When the test suite runs, this folder will be on the PYTHONPATH. diff --git a/iOS/testbed/iOSTestbed/iOSTestbed-Info.plist b/Apple/testbed/iOSTestbed/iOSTestbed-Info.plist similarity index 74% rename from iOS/testbed/iOSTestbed/iOSTestbed-Info.plist rename to Apple/testbed/iOSTestbed/iOSTestbed-Info.plist index a582f42a212783..fea45e1fad6f6f 100644 --- a/iOS/testbed/iOSTestbed/iOSTestbed-Info.plist +++ b/Apple/testbed/iOSTestbed/iOSTestbed-Info.plist @@ -41,18 +41,6 @@ UIInterfaceOrientationLandscapeLeft UIInterfaceOrientationLandscapeRight - TestArgs - - test - -uall - --single-process - --rerun - -W - - UIApplicationSceneManifest UIApplicationSupportsMultipleScenes diff --git a/iOS/testbed/iOSTestbed/main.m b/Apple/testbed/iOSTestbed/main.m similarity index 100% rename from iOS/testbed/iOSTestbed/main.m rename to Apple/testbed/iOSTestbed/main.m diff --git a/Doc/.ruff.toml b/Doc/.ruff.toml index 3e676e13c3f41a..6b573fd58d089b 100644 --- a/Doc/.ruff.toml +++ b/Doc/.ruff.toml @@ -32,6 +32,9 @@ ignore = [ "E501", # Ignore line length errors (we use auto-formatting) ] +[lint.per-file-ignores] +"tools/check-html-ids.py" = ["I001"] # Unsorted imports + [format] preview = true quote-style = "preserve" diff --git a/Doc/Makefile b/Doc/Makefile index c8a749a02a89ec..6eb466a3417626 100644 --- a/Doc/Makefile +++ b/Doc/Makefile @@ -58,7 +58,7 @@ build: @if [ -f ../Misc/NEWS ] ; then \ echo "Using existing Misc/NEWS file"; \ cp ../Misc/NEWS build/NEWS; \ - elif $(BLURB) help >/dev/null 2>&1 && $(SPHINXBUILD) --version >/dev/null 2>&1; then \ + elif $(BLURB) --version && $(SPHINXBUILD) --version ; then \ if [ -d ../Misc/NEWS.d ]; then \ echo "Building NEWS from Misc/NEWS.d with blurb"; \ $(BLURB) merge -f build/NEWS; \ @@ -89,7 +89,8 @@ htmlhelp: build .PHONY: latex latex: BUILDER = latex -latex: build +latex: _ensure-sphinxcontrib-svg2pdfconverter + $(MAKE) build BUILDER=$(BUILDER) @echo "Build finished; the LaTeX files are in build/latex." @echo "Run \`make all-pdf' or \`make all-ps' in that directory to" \ "run these through (pdf)latex." @@ -140,7 +141,8 @@ doctest: pydoc-topics: BUILDER = pydoc-topics pydoc-topics: build @echo "Building finished; now run this:" \ - "cp build/pydoc-topics/topics.py ../Lib/pydoc_data/topics.py" + "cp build/pydoc-topics/topics.py ../Lib/pydoc_data/topics.py" \ + "&& cp build/pydoc-topics/module_docs.py ../Lib/pydoc_data/module_docs.py" .PHONY: gettext gettext: BUILDER = gettext @@ -170,6 +172,7 @@ venv: echo "venv already exists."; \ echo "To recreate it, remove it first with \`make clean-venv'."; \ else \ + set -e; \ echo "Creating venv in $(VENVDIR)"; \ if $(UV) --version >/dev/null 2>&1; then \ $(UV) venv --python=$(PYTHON) $(VENVDIR); \ @@ -183,7 +186,7 @@ venv: fi .PHONY: dist-no-html -dist-no-html: dist-text dist-pdf dist-epub dist-texinfo +dist-no-html: dist-text dist-epub dist-texinfo .PHONY: dist dist: @@ -229,7 +232,7 @@ dist-text: @echo "Build finished and archived!" .PHONY: dist-pdf -dist-pdf: +dist-pdf: _ensure-sphinxcontrib-svg2pdfconverter # archive the A4 latex @echo "Building LaTeX (A4 paper)..." mkdir -p dist @@ -240,7 +243,8 @@ dist-pdf: # as otherwise the full latexmk process is run twice. # ($$ is needed to escape the $; https://www.gnu.org/software/make/manual/make.html#Basics-of-Variable-References) -sed -i 's/: all-$$(FMT)/:/' build/latex/Makefile - (cd build/latex; $(MAKE) clean && $(MAKE) --jobs=$$((`nproc`+1)) --output-sync LATEXMKOPTS='-quiet' all-pdf && $(MAKE) FMT=pdf zip bz2) + if [ -n "$(filter output-sync,$(value .FEATURES))" ]; then OUTPUTSYNC=--output-sync; else OUTPUTSYNC=; fi && \ + (cd build/latex; $(MAKE) clean && $(MAKE) --jobs=$$((`getconf _NPROCESSORS_ONLN`+1)) $$OUTPUTSYNC LATEXMKOPTS='-quiet' all-pdf && $(MAKE) FMT=pdf zip bz2) cp build/latex/docs-pdf.zip dist/python-$(DISTVERSION)-docs-pdf-a4.zip cp build/latex/docs-pdf.tar.bz2 dist/python-$(DISTVERSION)-docs-pdf-a4.tar.bz2 @echo "Build finished and archived!" @@ -289,6 +293,10 @@ _ensure-pre-commit: _ensure-sphinx-autobuild: $(MAKE) _ensure-package PACKAGE=sphinx-autobuild +.PHONY: _ensure-sphinxcontrib-svg2pdfconverter +_ensure-sphinxcontrib-svg2pdfconverter: + $(MAKE) _ensure-package PACKAGE=sphinxcontrib-svg2pdfconverter + .PHONY: check check: _ensure-pre-commit $(VENVDIR)/bin/python3 -m pre_commit run --all-files @@ -333,3 +341,9 @@ autobuild-stable-html: exit 1;; \ esac @$(MAKE) autobuild-dev-html + +# Collect HTML IDs to a JSON document +.PHONY: html-ids +html-ids: + $(PYTHON) tools/check-html-ids.py collect build/html \ + -o build/html/html-ids.json.gz diff --git a/Doc/bugs.rst b/Doc/bugs.rst index 5d0f68ca69675e..9f2b9876ba51dc 100644 --- a/Doc/bugs.rst +++ b/Doc/bugs.rst @@ -9,7 +9,7 @@ stability. In order to maintain this reputation, the developers would like to know of any deficiencies you find in Python. It can be sometimes faster to fix bugs yourself and contribute patches to -Python as it streamlines the process and involves less people. Learn how to +Python as it streamlines the process and involves fewer people. Learn how to :ref:`contribute `. Documentation bugs @@ -19,6 +19,12 @@ If you find a bug in this documentation or would like to propose an improvement, please submit a bug report on the :ref:`issue tracker `. If you have a suggestion on how to fix it, include that as well. +.. only:: translation + + If the bug or suggested improvement concerns the translation of this + documentation, submit the report to the + `translation’s repository `_ instead. + You can also open a discussion item on our `Documentation Discourse forum `_. diff --git a/Doc/c-api/allocation.rst b/Doc/c-api/allocation.rst index 7cbc99ad145ad4..5f7a9152eccfc0 100644 --- a/Doc/c-api/allocation.rst +++ b/Doc/c-api/allocation.rst @@ -2,7 +2,7 @@ .. _allocating-objects: -Allocating Objects on the Heap +Allocating objects on the heap ============================== @@ -16,7 +16,20 @@ Allocating Objects on the Heap Initialize a newly allocated object *op* with its type and initial reference. Returns the initialized object. Other fields of the object are - not affected. + not initialized. Despite its name, this function is unrelated to the + object's :meth:`~object.__init__` method (:c:member:`~PyTypeObject.tp_init` + slot). Specifically, this function does **not** call the object's + :meth:`!__init__` method. + + In general, consider this function to be a low-level routine. Use + :c:member:`~PyTypeObject.tp_alloc` where possible. + For implementing :c:member:`!tp_alloc` for your type, prefer + :c:func:`PyType_GenericAlloc` or :c:func:`PyObject_New`. + + .. note:: + + This function only initializes the object's memory corresponding to the + initial :c:type:`PyObject` structure. It does not zero the rest. .. c:function:: PyVarObject* PyObject_InitVar(PyVarObject *op, PyTypeObject *type, Py_ssize_t size) @@ -24,43 +37,108 @@ Allocating Objects on the Heap This does everything :c:func:`PyObject_Init` does, and also initializes the length information for a variable-size object. + .. note:: + + This function only initializes some of the object's memory. It does not + zero the rest. + .. c:macro:: PyObject_New(TYPE, typeobj) - Allocate a new Python object using the C structure type *TYPE* - and the Python type object *typeobj* (``PyTypeObject*``). - Fields not defined by the Python object header are not initialized. - The caller will own the only reference to the object - (i.e. its reference count will be one). - The size of the memory allocation is determined from the - :c:member:`~PyTypeObject.tp_basicsize` field of the type object. + Allocates a new Python object using the C structure type *TYPE* and the + Python type object *typeobj* (``PyTypeObject*``) by calling + :c:func:`PyObject_Malloc` to allocate memory and initializing it like + :c:func:`PyObject_Init`. The caller will own the only reference to the + object (i.e. its reference count will be one). + + Avoid calling this directly to allocate memory for an object; call the type's + :c:member:`~PyTypeObject.tp_alloc` slot instead. + + When populating a type's :c:member:`~PyTypeObject.tp_alloc` slot, + :c:func:`PyType_GenericAlloc` is preferred over a custom function that + simply calls this macro. + + This macro does not call :c:member:`~PyTypeObject.tp_alloc`, + :c:member:`~PyTypeObject.tp_new` (:meth:`~object.__new__`), or + :c:member:`~PyTypeObject.tp_init` (:meth:`~object.__init__`). + + This cannot be used for objects with :c:macro:`Py_TPFLAGS_HAVE_GC` set in + :c:member:`~PyTypeObject.tp_flags`; use :c:macro:`PyObject_GC_New` instead. + + Memory allocated by this macro must be freed with :c:func:`PyObject_Free` + (usually called via the object's :c:member:`~PyTypeObject.tp_free` slot). + + .. note:: + + The returned memory is not guaranteed to have been completely zeroed + before it was initialized. + + .. note:: + + This macro does not construct a fully initialized object of the given + type; it merely allocates memory and prepares it for further + initialization by :c:member:`~PyTypeObject.tp_init`. To construct a + fully initialized object, call *typeobj* instead. For example:: - Note that this function is unsuitable if *typeobj* has - :c:macro:`Py_TPFLAGS_HAVE_GC` set. For such objects, - use :c:func:`PyObject_GC_New` instead. + PyObject *foo = PyObject_CallNoArgs((PyObject *)&PyFoo_Type); + + .. seealso:: + + * :c:func:`PyObject_Free` + * :c:macro:`PyObject_GC_New` + * :c:func:`PyType_GenericAlloc` + * :c:member:`~PyTypeObject.tp_alloc` .. c:macro:: PyObject_NewVar(TYPE, typeobj, size) - Allocate a new Python object using the C structure type *TYPE* and the - Python type object *typeobj* (``PyTypeObject*``). - Fields not defined by the Python object header - are not initialized. The allocated memory allows for the *TYPE* structure - plus *size* (``Py_ssize_t``) fields of the size - given by the :c:member:`~PyTypeObject.tp_itemsize` field of - *typeobj*. This is useful for implementing objects like tuples, which are - able to determine their size at construction time. Embedding the array of - fields into the same allocation decreases the number of allocations, - improving the memory management efficiency. + Like :c:macro:`PyObject_New` except: + + * It allocates enough memory for the *TYPE* structure plus *size* + (``Py_ssize_t``) fields of the size given by the + :c:member:`~PyTypeObject.tp_itemsize` field of *typeobj*. + * The memory is initialized like :c:func:`PyObject_InitVar`. + + This is useful for implementing objects like tuples, which are able to + determine their size at construction time. Embedding the array of fields + into the same allocation decreases the number of allocations, improving the + memory management efficiency. + + Avoid calling this directly to allocate memory for an object; call the type's + :c:member:`~PyTypeObject.tp_alloc` slot instead. + + When populating a type's :c:member:`~PyTypeObject.tp_alloc` slot, + :c:func:`PyType_GenericAlloc` is preferred over a custom function that + simply calls this macro. + + This cannot be used for objects with :c:macro:`Py_TPFLAGS_HAVE_GC` set in + :c:member:`~PyTypeObject.tp_flags`; use :c:macro:`PyObject_GC_NewVar` + instead. - Note that this function is unsuitable if *typeobj* has - :c:macro:`Py_TPFLAGS_HAVE_GC` set. For such objects, - use :c:func:`PyObject_GC_NewVar` instead. + Memory allocated by this function must be freed with :c:func:`PyObject_Free` + (usually called via the object's :c:member:`~PyTypeObject.tp_free` slot). + .. note:: -.. c:function:: void PyObject_Del(void *op) + The returned memory is not guaranteed to have been completely zeroed + before it was initialized. + + .. note:: + + This macro does not construct a fully initialized object of the given + type; it merely allocates memory and prepares it for further + initialization by :c:member:`~PyTypeObject.tp_init`. To construct a + fully initialized object, call *typeobj* instead. For example:: + + PyObject *list_instance = PyObject_CallNoArgs((PyObject *)&PyList_Type); + + .. seealso:: + + * :c:func:`PyObject_Free` + * :c:macro:`PyObject_GC_NewVar` + * :c:func:`PyType_GenericAlloc` + * :c:member:`~PyTypeObject.tp_alloc` - Same as :c:func:`PyObject_Free`. .. c:var:: PyObject _Py_NoneStruct @@ -71,6 +149,40 @@ Allocating Objects on the Heap .. seealso:: - :c:func:`PyModule_Create` + :ref:`moduleobjects` To allocate and create extension modules. + +Soft-deprecated aliases +^^^^^^^^^^^^^^^^^^^^^^^ + +.. soft-deprecated:: 3.10 + +These are aliases to existing functions and macros. +They exist solely for backwards compatibility. + + +.. list-table:: + :widths: auto + :header-rows: 1 + + * * Soft-deprecated alias + * Function + * * .. c:macro:: PyObject_NEW(type, typeobj) + * :c:macro:`PyObject_New` + * * .. c:macro:: PyObject_NEW_VAR(type, typeobj, n) + * :c:macro:`PyObject_NewVar` + * * .. c:macro:: PyObject_INIT(op, typeobj) + * :c:func:`PyObject_Init` + * * .. c:macro:: PyObject_INIT_VAR(op, typeobj, n) + * :c:func:`PyObject_InitVar` + * * .. c:macro:: PyObject_MALLOC(n) + * :c:func:`PyObject_Malloc` + * * .. c:macro:: PyObject_REALLOC(p, n) + * :c:func:`PyObject_Realloc` + * * .. c:macro:: PyObject_FREE(p) + * :c:func:`PyObject_Free` + * * .. c:macro:: PyObject_DEL(p) + * :c:func:`PyObject_Free` + * * .. c:macro:: PyObject_Del(p) + * :c:func:`PyObject_Free` diff --git a/Doc/c-api/apiabiversion.rst b/Doc/c-api/apiabiversion.rst index 96050f59bd5250..6396a424f44d14 100644 --- a/Doc/c-api/apiabiversion.rst +++ b/Doc/c-api/apiabiversion.rst @@ -46,6 +46,8 @@ See :ref:`stable` for a discussion of API and ABI stability across versions. Use this for numeric comparisons, for example, ``#if PY_VERSION_HEX >= ...``. +These macros are defined in :source:`Include/patchlevel.h`. + Run-time version ---------------- diff --git a/Doc/c-api/arg.rst b/Doc/c-api/arg.rst index 3bbc990b6329c0..a56b85fb135f4b 100644 --- a/Doc/c-api/arg.rst +++ b/Doc/c-api/arg.rst @@ -113,18 +113,14 @@ There are three ways strings and buffers can be converted to C: ``z`` (:class:`str` or ``None``) [const char \*] Like ``s``, but the Python object may also be ``None``, in which case the C pointer is set to ``NULL``. - It is the same as ``s?`` with the C pointer was initialized to ``NULL``. ``z*`` (:class:`str`, :term:`bytes-like object` or ``None``) [Py_buffer] Like ``s*``, but the Python object may also be ``None``, in which case the ``buf`` member of the :c:type:`Py_buffer` structure is set to ``NULL``. - It is the same as ``s*?`` with the ``buf`` member of the :c:type:`Py_buffer` - structure was initialized to ``NULL``. ``z#`` (:class:`str`, read-only :term:`bytes-like object` or ``None``) [const char \*, :c:type:`Py_ssize_t`] Like ``s#``, but the Python object may also be ``None``, in which case the C pointer is set to ``NULL``. - It is the same as ``s#?`` with the C pointer was initialized to ``NULL``. ``y`` (read-only :term:`bytes-like object`) [const char \*] This format converts a bytes-like object to a C pointer to a @@ -164,7 +160,7 @@ There are three ways strings and buffers can be converted to C: ``w*`` (read-write :term:`bytes-like object`) [Py_buffer] This format accepts any object which implements the read-write buffer interface. It fills a :c:type:`Py_buffer` structure provided by the caller. - The buffer may contain embedded null bytes. The caller have to call + The buffer may contain embedded null bytes. The caller has to call :c:func:`PyBuffer_Release` when it is done with the buffer. ``es`` (:class:`str`) [const char \*encoding, char \*\*buffer] @@ -387,17 +383,6 @@ Other objects Non-tuple sequences are deprecated if *items* contains format units which store a borrowed buffer or a borrowed reference. -``unit?`` (anything or ``None``) [*matching-variable(s)*] - ``?`` modifies the behavior of the preceding format unit. - The C variable(s) corresponding to that parameter should be initialized - to their default value --- when the argument is ``None``, - :c:func:`PyArg_ParseTuple` does not touch the contents of the corresponding - C variable(s). - If the argument is not ``None``, it is parsed according to the specified - format unit. - - .. versionadded:: 3.14 - A few other characters have a meaning in a format string. These may not occur inside nested parentheses. They are: @@ -407,13 +392,18 @@ inside nested parentheses. They are: their default value --- when an optional argument is not specified, :c:func:`PyArg_ParseTuple` does not touch the contents of the corresponding C variable(s). + For example, the format string ``"OO|OO"`` corresponds to the Python + signature ``f(a, b, c=None, d=None)``. ``$`` :c:func:`PyArg_ParseTupleAndKeywords` only: Indicates that the remaining arguments in the Python argument list are - keyword-only. Currently, all keyword-only arguments must also be optional - arguments, so ``|`` must always be specified before ``$`` in the format - string. + keyword-only. + They are optional if ``|`` was specified before ``$``, and required otherwise. + ``|`` cannot be specified after ``$``. + For example, the format string ``"O|O$O"`` corresponds to the Python + signature ``f(a, b=None, *, c=None)``, + and the format string ``"OO$OO"`` corresponds to ``f(a, b, *, c, d)``. .. versionadded:: 3.3 @@ -685,6 +675,13 @@ Building values ``p`` (:class:`bool`) [int] Convert a C :c:expr:`int` to a Python :class:`bool` object. + + Be aware that this format requires an ``int`` argument. + Unlike most other contexts in C, variadic arguments are not coerced to + a suitable type automatically. + You can convert another type (for example, a pointer or a float) to a + suitable ``int`` value using ``(x) ? 1 : 0`` or ``!!x``. + .. versionadded:: 3.14 ``c`` (:class:`bytes` of length 1) [char] diff --git a/Doc/c-api/buffer.rst b/Doc/c-api/buffer.rst index d3081894eadaf5..22f54cfee81a99 100644 --- a/Doc/c-api/buffer.rst +++ b/Doc/c-api/buffer.rst @@ -261,6 +261,12 @@ readonly, format MUST be consistent for all consumers. For example, :c:expr:`PyBUF_SIMPLE | PyBUF_WRITABLE` can be used to request a simple writable buffer. + .. c:macro:: PyBUF_WRITEABLE + + This is an alias to :c:macro:`PyBUF_WRITABLE`. + + .. soft-deprecated:: 3.13 + .. c:macro:: PyBUF_FORMAT Controls the :c:member:`~Py_buffer.format` field. If set, this field MUST diff --git a/Doc/c-api/bytearray.rst b/Doc/c-api/bytearray.rst index e2b22ec3c794ae..2b36da997d4295 100644 --- a/Doc/c-api/bytearray.rst +++ b/Doc/c-api/bytearray.rst @@ -44,6 +44,10 @@ Direct API functions On failure, return ``NULL`` with an exception set. + .. note:: + If the object implements the buffer protocol, then the buffer + must not be mutated while the bytearray object is being created. + .. c:function:: PyObject* PyByteArray_FromStringAndSize(const char *string, Py_ssize_t len) @@ -58,6 +62,10 @@ Direct API functions On failure, return ``NULL`` with an exception set. + .. note:: + If the object implements the buffer protocol, then the buffer + must not be mutated while the bytearray object is being created. + .. c:function:: Py_ssize_t PyByteArray_Size(PyObject *bytearray) @@ -70,6 +78,9 @@ Direct API functions ``NULL`` pointer. The returned array always has an extra null byte appended. + .. note:: + It is not thread-safe to mutate the bytearray object while using the returned char array. + .. c:function:: int PyByteArray_Resize(PyObject *bytearray, Py_ssize_t len) @@ -89,6 +100,9 @@ These macros trade safety for speed and they don't check pointers. Similar to :c:func:`PyByteArray_AsString`, but without error checking. + .. note:: + It is not thread-safe to mutate the bytearray object while using the returned char array. + .. c:function:: Py_ssize_t PyByteArray_GET_SIZE(PyObject *bytearray) diff --git a/Doc/c-api/bytes.rst b/Doc/c-api/bytes.rst index d47beee68eaa33..b90d030719eca5 100644 --- a/Doc/c-api/bytes.rst +++ b/Doc/c-api/bytes.rst @@ -123,6 +123,10 @@ called with a non-bytes parameter. Return the bytes representation of object *o* that implements the buffer protocol. + .. note:: + If the object implements the buffer protocol, then the buffer + must not be mutated while the bytes object is being created. + .. c:function:: Py_ssize_t PyBytes_Size(PyObject *o) @@ -176,11 +180,15 @@ called with a non-bytes parameter. .. c:function:: void PyBytes_Concat(PyObject **bytes, PyObject *newpart) Create a new bytes object in *\*bytes* containing the contents of *newpart* - appended to *bytes*; the caller will own the new reference. The reference to - the old value of *bytes* will be stolen. If the new object cannot be - created, the old reference to *bytes* will still be discarded and the value - of *\*bytes* will be set to ``NULL``; the appropriate exception will be set. + appended to *bytes*; the caller will own the new reference. + The reference to the old value of *bytes* will be ":term:`stolen `". + If the new object cannot be created, the old reference to *bytes* will still + be "stolen", the value of *\*bytes* will be set to ``NULL``, and + the appropriate exception will be set. + .. note:: + If *newpart* implements the buffer protocol, then the buffer + must not be mutated while the new bytes object is being created. .. c:function:: void PyBytes_ConcatAndDel(PyObject **bytes, PyObject *newpart) @@ -188,6 +196,10 @@ called with a non-bytes parameter. appended to *bytes*. This version releases the :term:`strong reference` to *newpart* (i.e. decrements its reference count). + .. note:: + If *newpart* implements the buffer protocol, then the buffer + must not be mutated while the new bytes object is being created. + .. c:function:: PyObject* PyBytes_Join(PyObject *sep, PyObject *iterable) @@ -206,6 +218,9 @@ called with a non-bytes parameter. .. versionadded:: 3.14 + .. note:: + If *iterable* objects implement the buffer protocol, then the buffers + must not be mutated while the new bytes object is being created. .. c:function:: int _PyBytes_Resize(PyObject **bytes, Py_ssize_t newsize) @@ -219,3 +234,38 @@ called with a non-bytes parameter. reallocation fails, the original bytes object at *\*bytes* is deallocated, *\*bytes* is set to ``NULL``, :exc:`MemoryError` is set, and ``-1`` is returned. + + +.. c:function:: PyObject *PyBytes_Repr(PyObject *bytes, int smartquotes) + + Get the string representation of *bytes*. This function is currently used to + implement :meth:`!bytes.__repr__` in Python. + + This function does not do type checking; it is undefined behavior to pass + *bytes* as a non-bytes object or ``NULL``. + + If *smartquotes* is true, the representation will use a double-quoted string + instead of single-quoted string when single-quotes are present in *bytes*. + For example, the byte string ``'Python'`` would be represented as + ``b"'Python'"`` when *smartquotes* is true, or ``b'\'Python\''`` when it is + false. + + On success, this function returns a :term:`strong reference` to a + :class:`str` object containing the representation. On failure, this + returns ``NULL`` with an exception set. + + +.. c:function:: PyObject *PyBytes_DecodeEscape(const char *s, Py_ssize_t len, const char *errors, Py_ssize_t unicode, const char *recode_encoding) + + Unescape a backslash-escaped string *s*. *s* must not be ``NULL``. + *len* must be the size of *s*. + + *errors* must be one of ``"strict"``, ``"replace"``, or ``"ignore"``. If + *errors* is ``NULL``, then ``"strict"`` is used by default. + + On success, this function returns a :term:`strong reference` to a Python + :class:`bytes` object containing the unescaped string. On failure, this + function returns ``NULL`` with an exception set. + + .. versionchanged:: 3.9 + *unicode* and *recode_encoding* are now unused. diff --git a/Doc/c-api/call.rst b/Doc/c-api/call.rst index 7198d6bc056eb4..9838879a528934 100644 --- a/Doc/c-api/call.rst +++ b/Doc/c-api/call.rst @@ -347,6 +347,8 @@ please see individual documentation for details. .. versionadded:: 3.9 +.. c:function:: PyObject* _PyObject_Vectorcall(PyObject *callable, PyObject *const *args, size_t nargsf, PyObject *kwnames) + :no-typesetting: .. c:function:: PyObject* PyObject_Vectorcall(PyObject *callable, PyObject *const *args, size_t nargsf, PyObject *kwnames) @@ -358,7 +360,12 @@ please see individual documentation for details. Return the result of the call on success, or raise an exception and return *NULL* on failure. - .. versionadded:: 3.9 + .. versionadded:: 3.8 as ``_PyObject_Vectorcall`` + + .. versionchanged:: 3.9 + + Renamed to the current name, without the leading underscore. + The old provisional name is :term:`soft deprecated`. .. c:function:: PyObject* PyObject_VectorcallDict(PyObject *callable, PyObject *const *args, size_t nargsf, PyObject *kwdict) diff --git a/Doc/c-api/capsule.rst b/Doc/c-api/capsule.rst index cdb8aa33e9fd32..03a848d68ed7ab 100644 --- a/Doc/c-api/capsule.rst +++ b/Doc/c-api/capsule.rst @@ -15,13 +15,19 @@ Refer to :ref:`using-capsules` for more information on using these objects. .. c:type:: PyCapsule This subtype of :c:type:`PyObject` represents an opaque value, useful for C - extension modules who need to pass an opaque value (as a :c:expr:`void*` + extension modules which need to pass an opaque value (as a :c:expr:`void*` pointer) through Python code to other C code. It is often used to make a C function pointer defined in one module available to other modules, so the regular import mechanism can be used to access C APIs defined in dynamically loaded modules. +.. c:var:: PyTypeObject PyCapsule_Type + + The type object corresponding to capsule objects. This is the same object + as :class:`types.CapsuleType` in the Python layer. + + .. c:type:: PyCapsule_Destructor The type of a destructor callback for a capsule. Defined as:: @@ -105,9 +111,19 @@ Refer to :ref:`using-capsules` for more information on using these objects. ``module.attribute``. The *name* stored in the capsule must match this string exactly. + This function splits *name* on the ``.`` character, and imports the first + element. It then processes further elements using attribute lookups. + Return the capsule's internal *pointer* on success. On failure, set an exception and return ``NULL``. + .. note:: + + If *name* points to an attribute of some submodule or subpackage, this + submodule or subpackage must be previously imported using other means + (for example, by using :c:func:`PyImport_ImportModule`) for the + attribute lookups to succeed. + .. versionchanged:: 3.3 *no_block* has no effect anymore. diff --git a/Doc/c-api/cell.rst b/Doc/c-api/cell.rst index 61eb994c370946..2501ed9580df89 100644 --- a/Doc/c-api/cell.rst +++ b/Doc/c-api/cell.rst @@ -7,7 +7,7 @@ Cell Objects "Cell" objects are used to implement variables referenced by multiple scopes. For each such variable, a cell object is created to store the value; the local -variables of each stack frame that references the value contains a reference to +variables of each stack frame that references the value contain a reference to the cells from outer scopes which also use that variable. When the value is accessed, the value contained in the cell is used instead of the cell object itself. This de-referencing of the cell object requires support from the diff --git a/Doc/c-api/code.rst b/Doc/c-api/code.rst index 6eae24b38fae48..3ffbd9dc170939 100644 --- a/Doc/c-api/code.rst +++ b/Doc/c-api/code.rst @@ -69,13 +69,14 @@ bound into a function. The old name is deprecated, but will remain available until the signature changes again. +.. c:function:: PyCodeObject* PyCode_NewWithPosOnlyArgs(...) + :no-typesetting: + .. c:function:: PyCodeObject* PyUnstable_Code_NewWithPosOnlyArgs(int argcount, int posonlyargcount, int kwonlyargcount, int nlocals, int stacksize, int flags, PyObject *code, PyObject *consts, PyObject *names, PyObject *varnames, PyObject *freevars, PyObject *cellvars, PyObject *filename, PyObject *name, PyObject *qualname, int firstlineno, PyObject *linetable, PyObject *exceptiontable) Similar to :c:func:`PyUnstable_Code_New`, but with an extra "posonlyargcount" for positional-only arguments. The same caveats that apply to ``PyUnstable_Code_New`` also apply to this function. - .. index:: single: PyCode_NewWithPosOnlyArgs (C function) - .. versionadded:: 3.8 as ``PyCode_NewWithPosOnlyArgs`` .. versionchanged:: 3.11 @@ -182,7 +183,7 @@ bound into a function. Type of a code object watcher callback function. If *event* is ``PY_CODE_EVENT_CREATE``, then the callback is invoked - after `co` has been fully initialized. Otherwise, the callback is invoked + after *co* has been fully initialized. Otherwise, the callback is invoked before the destruction of *co* takes place, so the prior state of *co* can be inspected. @@ -211,6 +212,84 @@ bound into a function. .. versionadded:: 3.12 +.. c:function:: PyObject *PyCode_Optimize(PyObject *code, PyObject *consts, PyObject *names, PyObject *lnotab_obj) + + This is a function that does nothing. + + Prior to Python 3.10, this function would perform basic optimizations to a + code object. + + .. versionchanged:: 3.10 + This function now does nothing. + + .. soft-deprecated:: 3.13 + + +.. _c_codeobject_flags: + +Code Object Flags +----------------- + +Code objects contain a bit-field of flags, which can be retrieved as the +:attr:`~codeobject.co_flags` Python attribute (for example using +:c:func:`PyObject_GetAttrString`), and set using a *flags* argument to +:c:func:`PyUnstable_Code_New` and similar functions. + +Flags whose names start with ``CO_FUTURE_`` correspond to features normally +selectable by :ref:`future statements `. These flags can be used in +:c:member:`PyCompilerFlags.cf_flags`. +Note that many ``CO_FUTURE_`` flags are mandatory in current versions of +Python, and setting them has no effect. + +The following flags are available. +For their meaning, see the linked documentation of their Python equivalents. + + +.. list-table:: + :widths: auto + :header-rows: 1 + + * * Flag + * Meaning + * * .. c:macro:: CO_OPTIMIZED + * :py:data:`inspect.CO_OPTIMIZED` + * * .. c:macro:: CO_NEWLOCALS + * :py:data:`inspect.CO_NEWLOCALS` + * * .. c:macro:: CO_VARARGS + * :py:data:`inspect.CO_VARARGS` + * * .. c:macro:: CO_VARKEYWORDS + * :py:data:`inspect.CO_VARKEYWORDS` + * * .. c:macro:: CO_NESTED + * :py:data:`inspect.CO_NESTED` + * * .. c:macro:: CO_GENERATOR + * :py:data:`inspect.CO_GENERATOR` + * * .. c:macro:: CO_COROUTINE + * :py:data:`inspect.CO_COROUTINE` + * * .. c:macro:: CO_ITERABLE_COROUTINE + * :py:data:`inspect.CO_ITERABLE_COROUTINE` + * * .. c:macro:: CO_ASYNC_GENERATOR + * :py:data:`inspect.CO_ASYNC_GENERATOR` + * * .. c:macro:: CO_HAS_DOCSTRING + * :py:data:`inspect.CO_HAS_DOCSTRING` + * * .. c:macro:: CO_METHOD + * :py:data:`inspect.CO_METHOD` + + * * .. c:macro:: CO_FUTURE_DIVISION + * no effect (:py:data:`__future__.division`) + * * .. c:macro:: CO_FUTURE_ABSOLUTE_IMPORT + * no effect (:py:data:`__future__.absolute_import`) + * * .. c:macro:: CO_FUTURE_WITH_STATEMENT + * no effect (:py:data:`__future__.with_statement`) + * * .. c:macro:: CO_FUTURE_PRINT_FUNCTION + * no effect (:py:data:`__future__.print_function`) + * * .. c:macro:: CO_FUTURE_UNICODE_LITERALS + * no effect (:py:data:`__future__.unicode_literals`) + * * .. c:macro:: CO_FUTURE_GENERATOR_STOP + * no effect (:py:data:`__future__.generator_stop`) + * * .. c:macro:: CO_FUTURE_ANNOTATIONS + * :py:data:`__future__.annotations` + + Extra information ----------------- @@ -222,9 +301,12 @@ These functions are part of the unstable C API tier: this functionality is a CPython implementation detail, and the API may change without deprecation warnings. +.. c:function:: Py_ssize_t _PyEval_RequestCodeExtraIndex(freefunc free) + :no-typesetting: + .. c:function:: Py_ssize_t PyUnstable_Eval_RequestCodeExtraIndex(freefunc free) - Return a new an opaque index value used to adding data to code objects. + Return a new opaque index value used to adding data to code objects. You generally call this function once (per interpreter) and use the result with ``PyCode_GetExtra`` and ``PyCode_SetExtra`` to manipulate @@ -234,8 +316,6 @@ may change without deprecation warnings. *free* will be called on non-``NULL`` data stored under the new index. Use :c:func:`Py_DecRef` when storing :c:type:`PyObject`. - .. index:: single: _PyEval_RequestCodeExtraIndex (C function) - .. versionadded:: 3.6 as ``_PyEval_RequestCodeExtraIndex`` .. versionchanged:: 3.12 @@ -244,6 +324,9 @@ may change without deprecation warnings. The old private name is deprecated, but will be available until the API changes. +.. c:function:: int _PyCode_GetExtra(PyObject *code, Py_ssize_t index, void **extra) + :no-typesetting: + .. c:function:: int PyUnstable_Code_GetExtra(PyObject *code, Py_ssize_t index, void **extra) Set *extra* to the extra data stored under the given index. @@ -252,8 +335,6 @@ may change without deprecation warnings. If no data was set under the index, set *extra* to ``NULL`` and return 0 without setting an exception. - .. index:: single: _PyCode_GetExtra (C function) - .. versionadded:: 3.6 as ``_PyCode_GetExtra`` .. versionchanged:: 3.12 @@ -262,13 +343,14 @@ may change without deprecation warnings. The old private name is deprecated, but will be available until the API changes. +.. c:function:: int _PyCode_SetExtra(PyObject *code, Py_ssize_t index, void *extra) + :no-typesetting: + .. c:function:: int PyUnstable_Code_SetExtra(PyObject *code, Py_ssize_t index, void *extra) Set the extra data stored under the given index to *extra*. Return 0 on success. Set an exception and return -1 on failure. - .. index:: single: _PyCode_SetExtra (C function) - .. versionadded:: 3.6 as ``_PyCode_SetExtra`` .. versionchanged:: 3.12 diff --git a/Doc/c-api/codec.rst b/Doc/c-api/codec.rst index 8ae5c4fecd6248..35ee048bd5fa9f 100644 --- a/Doc/c-api/codec.rst +++ b/Doc/c-api/codec.rst @@ -7,7 +7,7 @@ Codec registry and support functions Register a new codec search function. - As side effect, this tries to load the :mod:`!encodings` package, if not yet + As a side effect, this tries to load the :mod:`!encodings` package, if not yet done, to make sure that it is always first in the list of search functions. .. c:function:: int PyCodec_Unregister(PyObject *search_function) @@ -39,7 +39,7 @@ Codec registry and support functions *object* is passed through the decoder function found for the given *encoding* using the error handling method defined by *errors*. *errors* may be ``NULL`` to use the default method defined for the codec. Raises a - :exc:`LookupError` if no encoder can be found. + :exc:`LookupError` if no decoder can be found. Codec lookup API @@ -129,3 +129,13 @@ Registry API for Unicode encoding error handlers Replace the unicode encode error with ``\N{...}`` escapes. .. versionadded:: 3.5 + + +Codec utility variables +----------------------- + +.. c:var:: const char *Py_hexdigits + + A string constant containing the lowercase hexadecimal digits: ``"0123456789abcdef"``. + + .. versionadded:: 3.3 diff --git a/Doc/c-api/concrete.rst b/Doc/c-api/concrete.rst index 880f7b15ce68e8..1746fe95eaaca9 100644 --- a/Doc/c-api/concrete.rst +++ b/Doc/c-api/concrete.rst @@ -109,11 +109,20 @@ Other Objects descriptor.rst slice.rst memoryview.rst + picklebuffer.rst weakref.rst capsule.rst frame.rst gen.rst coro.rst contextvars.rst - datetime.rst typehints.rst + + +C API for extension modules +=========================== + +.. toctree:: + + curses.rst + datetime.rst diff --git a/Doc/c-api/conversion.rst b/Doc/c-api/conversion.rst index c92ef4c653a675..794e45af66316f 100644 --- a/Doc/c-api/conversion.rst +++ b/Doc/c-api/conversion.rst @@ -41,7 +41,7 @@ The return value (*rv*) for these functions should be interpreted as follows: ``rv + 1`` bytes would have been needed to succeed. ``str[size-1]`` is ``'\0'`` in this case. -* When ``rv < 0``, "something bad happened." ``str[size-1]`` is ``'\0'`` in +* When ``rv < 0``, the output conversion failed and ``str[size-1]`` is ``'\0'`` in this case too, but the rest of *str* is undefined. The exact cause of the error depends on the underlying platform. @@ -128,22 +128,46 @@ The following functions provide locale-independent string to number conversions. must be 0 and is ignored. The ``'r'`` format code specifies the standard :func:`repr` format. - *flags* can be zero or more of the values ``Py_DTSF_SIGN``, - ``Py_DTSF_ADD_DOT_0``, or ``Py_DTSF_ALT``, or-ed together: + *flags* can be zero or more of the following values or-ed together: - * ``Py_DTSF_SIGN`` means to always precede the returned string with a sign - character, even if *val* is non-negative. + .. c:namespace:: NULL - * ``Py_DTSF_ADD_DOT_0`` means to ensure that the returned string will not look - like an integer. + .. c:macro:: Py_DTSF_SIGN - * ``Py_DTSF_ALT`` means to apply "alternate" formatting rules. See the - documentation for the :c:func:`PyOS_snprintf` ``'#'`` specifier for - details. + Always precede the returned string with a sign + character, even if *val* is non-negative. - If *ptype* is non-``NULL``, then the value it points to will be set to one of - ``Py_DTST_FINITE``, ``Py_DTST_INFINITE``, or ``Py_DTST_NAN``, signifying that - *val* is a finite number, an infinite number, or not a number, respectively. + .. c:macro:: Py_DTSF_ADD_DOT_0 + + Ensure that the returned string will not look like an integer. + + .. c:macro:: Py_DTSF_ALT + + Apply "alternate" formatting rules. + See the documentation for the :c:func:`PyOS_snprintf` ``'#'`` specifier for + details. + + .. c:macro:: Py_DTSF_NO_NEG_0 + + Negative zero is converted to positive zero. + + .. versionadded:: 3.11 + + If *ptype* is non-``NULL``, then the value it points to will be set to one + of the following constants depending on the type of *val*: + + .. list-table:: + :header-rows: 1 + :align: left + + * - *\*ptype* + - type of *val* + * - .. c:macro:: Py_DTST_FINITE + - finite number + * - .. c:macro:: Py_DTST_INFINITE + - infinite number + * - .. c:macro:: Py_DTST_NAN + - not a number The return value is a pointer to *buffer* with the converted string or ``NULL`` if the conversion failed. The caller is responsible for freeing the @@ -152,13 +176,85 @@ The following functions provide locale-independent string to number conversions. .. versionadded:: 3.1 -.. c:function:: int PyOS_stricmp(const char *s1, const char *s2) +.. c:function:: int PyOS_mystricmp(const char *str1, const char *str2) + int PyOS_mystrnicmp(const char *str1, const char *str2, Py_ssize_t size) + + Case insensitive comparison of strings. These functions work almost + identically to :c:func:`!strcmp` and :c:func:`!strncmp` (respectively), + except that they ignore the case of ASCII characters. + + Return ``0`` if the strings are equal, a negative value if *str1* sorts + lexicographically before *str2*, or a positive value if it sorts after. + + In the *str1* or *str2* arguments, a NUL byte marks the end of the string. + For :c:func:`!PyOS_mystrnicmp`, the *size* argument gives the maximum size + of the string, as if NUL was present at the index given by *size*. + + These functions do not use the locale. + + +.. c:function:: int PyOS_stricmp(const char *str1, const char *str2) + int PyOS_strnicmp(const char *str1, const char *str2, Py_ssize_t size) + + Case insensitive comparison of strings. + + On Windows, these are aliases of :c:func:`!stricmp` and :c:func:`!strnicmp`, + respectively. + + On other platforms, they are aliases of :c:func:`PyOS_mystricmp` and + :c:func:`PyOS_mystrnicmp`, respectively. + + +Character classification and conversion +======================================= + +The following macros provide locale-independent (unlike the C standard library +``ctype.h``) character classification and conversion. +The argument must be a signed or unsigned :c:expr:`char`. + + +.. c:macro:: Py_ISALNUM(c) + + Return true if the character *c* is an alphanumeric character. + + +.. c:macro:: Py_ISALPHA(c) + + Return true if the character *c* is an alphabetic character (``a-z`` and ``A-Z``). + + +.. c:macro:: Py_ISDIGIT(c) + + Return true if the character *c* is a decimal digit (``0-9``). + + +.. c:macro:: Py_ISLOWER(c) + + Return true if the character *c* is a lowercase ASCII letter (``a-z``). + + +.. c:macro:: Py_ISUPPER(c) + + Return true if the character *c* is an uppercase ASCII letter (``A-Z``). + + +.. c:macro:: Py_ISSPACE(c) + + Return true if the character *c* is a whitespace character (space, tab, + carriage return, newline, vertical tab, or form feed). + + +.. c:macro:: Py_ISXDIGIT(c) + + Return true if the character *c* is a hexadecimal digit (``0-9``, ``a-f``, and + ``A-F``). + + +.. c:macro:: Py_TOLOWER(c) - Case insensitive comparison of strings. The function works almost - identically to :c:func:`!strcmp` except that it ignores the case. + Return the lowercase equivalent of the character *c*. -.. c:function:: int PyOS_strnicmp(const char *s1, const char *s2, Py_ssize_t size) +.. c:macro:: Py_TOUPPER(c) - Case insensitive comparison of strings. The function works almost - identically to :c:func:`!strncmp` except that it ignores the case. + Return the uppercase equivalent of the character *c*. diff --git a/Doc/c-api/curses.rst b/Doc/c-api/curses.rst new file mode 100644 index 00000000000000..5a1697c43cc969 --- /dev/null +++ b/Doc/c-api/curses.rst @@ -0,0 +1,138 @@ +.. highlight:: c + +Curses C API +------------ + +:mod:`curses` exposes a small C interface for extension modules. +Consumers must include the header file :file:`py_curses.h` (which is not +included by default by :file:`Python.h`) and :c:func:`import_curses` must +be invoked, usually as part of the module initialisation function, to populate +:c:var:`PyCurses_API`. + +.. warning:: + + Neither the C API nor the pure Python :mod:`curses` module are compatible + with subinterpreters. + +.. c:macro:: import_curses() + + Import the curses C API. The macro does not need a semi-colon to be called. + + On success, populate the :c:var:`PyCurses_API` pointer. + + On failure, set :c:var:`PyCurses_API` to NULL and set an exception. + The caller must check if an error occurred via :c:func:`PyErr_Occurred`: + + .. code-block:: + + import_curses(); // semi-colon is optional but recommended + if (PyErr_Occurred()) { /* cleanup */ } + + +.. c:var:: void **PyCurses_API + + Dynamically allocated object containing the curses C API. + This variable is only available once :c:macro:`import_curses` succeeds. + + ``PyCurses_API[0]`` corresponds to :c:data:`PyCursesWindow_Type`. + + ``PyCurses_API[1]``, ``PyCurses_API[2]``, and ``PyCurses_API[3]`` + are pointers to predicate functions of type ``int (*)(void)``. + + When called, these predicates return whether :func:`curses.setupterm`, + :func:`curses.initscr`, and :func:`curses.start_color` have been called + respectively. + + See also the convenience macros :c:macro:`PyCursesSetupTermCalled`, + :c:macro:`PyCursesInitialised`, and :c:macro:`PyCursesInitialisedColor`. + + .. note:: + + The number of entries in this structure is subject to changes. + Consider using :c:macro:`PyCurses_API_pointers` to check if + new fields are available or not. + + +.. c:macro:: PyCurses_API_pointers + + The number of accessible fields (``4``) in :c:var:`PyCurses_API`. + This number is incremented whenever new fields are added. + + +.. c:var:: PyTypeObject PyCursesWindow_Type + + The :ref:`heap type ` corresponding to :class:`curses.window`. + + +.. c:function:: int PyCursesWindow_Check(PyObject *op) + + Return true if *op* is a :class:`curses.window` instance, false otherwise. + + +The following macros are convenience macros expanding into C statements. +In particular, they can only be used as ``macro;`` or ``macro``, but not +``macro()`` or ``macro();``. + +.. c:macro:: PyCursesSetupTermCalled + + Macro checking if :func:`curses.setupterm` has been called. + + The macro expansion is roughly equivalent to: + + .. code-block:: + + { + typedef int (*predicate_t)(void); + predicate_t was_setupterm_called = (predicate_t)PyCurses_API[1]; + if (!was_setupterm_called()) { + return NULL; + } + } + + +.. c:macro:: PyCursesInitialised + + Macro checking if :func:`curses.initscr` has been called. + + The macro expansion is roughly equivalent to: + + .. code-block:: + + { + typedef int (*predicate_t)(void); + predicate_t was_initscr_called = (predicate_t)PyCurses_API[2]; + if (!was_initscr_called()) { + return NULL; + } + } + + +.. c:macro:: PyCursesInitialisedColor + + Macro checking if :func:`curses.start_color` has been called. + + The macro expansion is roughly equivalent to: + + .. code-block:: + + { + typedef int (*predicate_t)(void); + predicate_t was_start_color_called = (predicate_t)PyCurses_API[3]; + if (!was_start_color_called()) { + return NULL; + } + } + + +Internal data +------------- + +The following objects are exposed by the C API but should be considered +internal-only. + +.. c:macro:: PyCurses_CAPSULE_NAME + + Name of the curses capsule to pass to :c:func:`PyCapsule_Import`. + + Internal usage only. Use :c:macro:`import_curses` instead. + diff --git a/Doc/c-api/datetime.rst b/Doc/c-api/datetime.rst index d2d4d5309c7098..127d7c9c91a3d5 100644 --- a/Doc/c-api/datetime.rst +++ b/Doc/c-api/datetime.rst @@ -8,11 +8,42 @@ DateTime Objects Various date and time objects are supplied by the :mod:`datetime` module. Before using any of these functions, the header file :file:`datetime.h` must be included in your source (note that this is not included by :file:`Python.h`), -and the macro :c:macro:`!PyDateTime_IMPORT` must be invoked, usually as part of +and the macro :c:macro:`PyDateTime_IMPORT` must be invoked, usually as part of the module initialisation function. The macro puts a pointer to a C structure -into a static variable, :c:data:`!PyDateTimeAPI`, that is used by the following +into a static variable, :c:data:`PyDateTimeAPI`, that is used by the following macros. +.. c:macro:: PyDateTime_IMPORT() + + Import the datetime C API. + + On success, populate the :c:var:`PyDateTimeAPI` pointer. + On failure, set :c:var:`PyDateTimeAPI` to ``NULL`` and set an exception. + The caller must check if an error occurred via :c:func:`PyErr_Occurred`: + + .. code-block:: + + PyDateTime_IMPORT; + if (PyErr_Occurred()) { /* cleanup */ } + + .. warning:: + + This is not compatible with subinterpreters. + +.. c:type:: PyDateTime_CAPI + + Structure containing the fields for the datetime C API. + + The fields of this structure are private and subject to change. + + Do not use this directly; prefer ``PyDateTime_*`` APIs instead. + +.. c:var:: PyDateTime_CAPI *PyDateTimeAPI + + Dynamically allocated object containing the datetime C API. + + This variable is only available once :c:macro:`PyDateTime_IMPORT` succeeds. + .. c:type:: PyDateTime_Date This subtype of :c:type:`PyObject` represents a Python date object. @@ -46,7 +77,7 @@ macros. .. c:var:: PyTypeObject PyDateTime_DeltaType - This instance of :c:type:`PyTypeObject` represents Python type for + This instance of :c:type:`PyTypeObject` represents the Python type for the difference between two datetime values; it is the same object as :class:`datetime.timedelta` in the Python layer. @@ -325,3 +356,16 @@ Macros for the convenience of modules implementing the DB API: Create and return a new :class:`datetime.date` object given an argument tuple suitable for passing to :meth:`datetime.date.fromtimestamp`. + + +Internal data +------------- + +The following symbols are exposed by the C API but should be considered +internal-only. + +.. c:macro:: PyDateTime_CAPSULE_NAME + + Name of the datetime capsule to pass to :c:func:`PyCapsule_Import`. + + Internal usage only. Use :c:macro:`PyDateTime_IMPORT` instead. diff --git a/Doc/c-api/descriptor.rst b/Doc/c-api/descriptor.rst index b32c113e5f0457..813741f3eda51a 100644 --- a/Doc/c-api/descriptor.rst +++ b/Doc/c-api/descriptor.rst @@ -8,8 +8,6 @@ Descriptor Objects "Descriptors" are objects that describe some attribute of an object. They are found in the dictionary of type objects. -.. XXX document these! - .. c:var:: PyTypeObject PyProperty_Type The type object for the built-in descriptor types. @@ -17,24 +15,178 @@ found in the dictionary of type objects. .. c:function:: PyObject* PyDescr_NewGetSet(PyTypeObject *type, struct PyGetSetDef *getset) + Create a new get-set descriptor for extension type *type* from the + :c:type:`PyGetSetDef` structure *getset*. + + Get-set descriptors expose attributes implemented by C getter and setter + functions rather than stored directly in the instance. This is the same kind + of descriptor created for entries in :c:member:`~PyTypeObject.tp_getset`, and + it appears in Python as a :class:`types.GetSetDescriptorType` object. + + On success, return a :term:`strong reference` to the descriptor. Return + ``NULL`` with an exception set on failure. + +.. c:function:: PyObject* PyDescr_NewMember(PyTypeObject *type, struct PyMemberDef *member) + + Create a new member descriptor for extension type *type* from the + :c:type:`PyMemberDef` structure *member*. + + Member descriptors expose fields in the type's C struct as Python + attributes. This is the same kind of descriptor created for entries in + :c:member:`~PyTypeObject.tp_members`, and it appears in Python as a + :class:`types.MemberDescriptorType` object. + + On success, return a :term:`strong reference` to the descriptor. Return + ``NULL`` with an exception set on failure. -.. c:function:: PyObject* PyDescr_NewMember(PyTypeObject *type, struct PyMemberDef *meth) +.. c:var:: PyTypeObject PyMemberDescr_Type + + The type object for member descriptor objects created from + :c:type:`PyMemberDef` structures. These descriptors expose fields of a + C struct as attributes on a type, and correspond + to :class:`types.MemberDescriptorType` objects in Python. + + + +.. c:var:: PyTypeObject PyGetSetDescr_Type + + The type object for get/set descriptor objects created from + :c:type:`PyGetSetDef` structures. These descriptors implement attributes + whose value is computed by C getter and setter functions, and are used + for many built-in type attributes. They correspond to + :class:`types.GetSetDescriptorType` objects in Python. .. c:function:: PyObject* PyDescr_NewMethod(PyTypeObject *type, struct PyMethodDef *meth) + Create a new method descriptor for extension type *type* from the + :c:type:`PyMethodDef` structure *meth*. + + Method descriptors expose C functions as methods on a type. This is the same + kind of descriptor created for entries in + :c:member:`~PyTypeObject.tp_methods`, and it appears in Python as a + :class:`types.MethodDescriptorType` object. + + On success, return a :term:`strong reference` to the descriptor. Return + ``NULL`` with an exception set on failure. + +.. c:var:: PyTypeObject PyMethodDescr_Type + + The type object for method descriptor objects created from + :c:type:`PyMethodDef` structures. These descriptors expose C functions as + methods on a type, and correspond to :class:`types.MethodDescriptorType` + objects in Python. + + +.. c:struct:: wrapperbase + + Describes a slot wrapper used by :c:func:`PyDescr_NewWrapper`. + + Each ``wrapperbase`` record stores the Python-visible name and metadata for a + special method implemented by a type slot, together with the wrapper + function used to adapt that slot to Python's calling convention. + +.. c:function:: PyObject* PyDescr_NewWrapper(PyTypeObject *type, struct wrapperbase *base, void *wrapped) + + Create a new wrapper descriptor for extension type *type* from the + :c:struct:`wrapperbase` structure *base* and the wrapped slot function + pointer + *wrapped*. + + Wrapper descriptors expose special methods implemented by type slots. This + is the same kind of descriptor that CPython creates for slot-based special + methods such as ``__repr__`` or ``__add__``, and it appears in Python as a + :class:`types.WrapperDescriptorType` object. + + On success, return a :term:`strong reference` to the descriptor. Return + ``NULL`` with an exception set on failure. + +.. c:var:: PyTypeObject PyWrapperDescr_Type -.. c:function:: PyObject* PyDescr_NewWrapper(PyTypeObject *type, struct wrapperbase *wrapper, void *wrapped) + The type object for wrapper descriptor objects created by + :c:func:`PyDescr_NewWrapper` and :c:func:`PyWrapper_New`. Wrapper + descriptors are used internally to expose special methods implemented + via wrapper structures, and appear in Python as + :class:`types.WrapperDescriptorType` objects. .. c:function:: PyObject* PyDescr_NewClassMethod(PyTypeObject *type, PyMethodDef *method) + Create a new class method descriptor for extension type *type* from the + :c:type:`PyMethodDef` structure *method*. + + Class method descriptors expose C methods that receive the class rather than + an instance when accessed. This is the same kind of descriptor created for + ``METH_CLASS`` entries in :c:member:`~PyTypeObject.tp_methods`, and it + appears in Python as a :class:`types.ClassMethodDescriptorType` object. + + On success, return a :term:`strong reference` to the descriptor. Return + ``NULL`` with an exception set on failure. .. c:function:: int PyDescr_IsData(PyObject *descr) - Return non-zero if the descriptor objects *descr* describes a data attribute, or + Return non-zero if the descriptor object *descr* describes a data attribute, or ``0`` if it describes a method. *descr* must be a descriptor object; there is no error checking. -.. c:function:: PyObject* PyWrapper_New(PyObject *, PyObject *) +.. c:function:: PyObject* PyWrapper_New(PyObject *d, PyObject *self) + + Create a new bound wrapper object from the wrapper descriptor *d* and the + instance *self*. + + This is the bound form of a wrapper descriptor created by + :c:func:`PyDescr_NewWrapper`. CPython creates these objects when a slot + wrapper is accessed through an instance, and they appear in Python as + :class:`types.MethodWrapperType` objects. + + On success, return a :term:`strong reference` to the wrapper object. Return + ``NULL`` with an exception set on failure. + +Built-in descriptors +^^^^^^^^^^^^^^^^^^^^ + +.. c:var:: PyTypeObject PySuper_Type + + The type object for super objects. This is the same object as + :class:`super` in the Python layer. + + +.. c:var:: PyTypeObject PyClassMethod_Type + + The type of class method objects. This is the same object as + :class:`classmethod` in the Python layer. + + +.. c:var:: PyTypeObject PyClassMethodDescr_Type + + The type object for C-level class method descriptor objects. + This is the type of the descriptors created for :func:`classmethod` defined + in C extension types, and corresponds to + :class:`types.ClassMethodDescriptorType` objects in Python. + + +.. c:function:: PyObject *PyClassMethod_New(PyObject *callable) + + Create a new :class:`classmethod` object wrapping *callable*. + *callable* must be a callable object and must not be ``NULL``. + + On success, this function returns a :term:`strong reference` to a new class + method descriptor. On failure, this function returns ``NULL`` with an + exception set. + + +.. c:var:: PyTypeObject PyStaticMethod_Type + + The type of static method objects. This is the same object as + :class:`staticmethod` in the Python layer. + + +.. c:function:: PyObject *PyStaticMethod_New(PyObject *callable) + + Create a new :class:`staticmethod` object wrapping *callable*. + *callable* must be a callable object and must not be ``NULL``. + + On success, this function returns a :term:`strong reference` to a new static + method descriptor. On failure, this function returns ``NULL`` with an + exception set. diff --git a/Doc/c-api/dict.rst b/Doc/c-api/dict.rst index e55c5c80cb83c0..4c19af0d3a806e 100644 --- a/Doc/c-api/dict.rst +++ b/Doc/c-api/dict.rst @@ -43,6 +43,17 @@ Dictionary Objects prevent modification of the dictionary for non-dynamic class types. +.. c:var:: PyTypeObject PyDictProxy_Type + + The type object for mapping proxy objects created by + :c:func:`PyDictProxy_New` and for the read-only ``__dict__`` attribute + of many built-in types. A :c:type:`PyDictProxy_Type` instance provides a + dynamic, read-only view of an underlying dictionary: changes to the + underlying dictionary are reflected in the proxy, but the proxy itself + does not support mutation operations. This corresponds to + :class:`types.MappingProxyType` in Python. + + .. c:function:: void PyDict_Clear(PyObject *p) Empty an existing dictionary of all key-value pairs. @@ -50,10 +61,15 @@ Dictionary Objects .. c:function:: int PyDict_Contains(PyObject *p, PyObject *key) - Determine if dictionary *p* contains *key*. If an item in *p* is matches + Determine if dictionary *p* contains *key*. If an item in *p* matches *key*, return ``1``, otherwise return ``0``. On error, return ``-1``. This is equivalent to the Python expression ``key in p``. + .. note:: + + The operation is atomic on :term:`free threading ` + when *key* is :class:`str`, :class:`int`, :class:`float`, :class:`bool` or :class:`bytes`. + .. c:function:: int PyDict_ContainsString(PyObject *p, const char *key) @@ -73,8 +89,13 @@ Dictionary Objects Insert *val* into the dictionary *p* with a key of *key*. *key* must be :term:`hashable`; if it isn't, :exc:`TypeError` will be raised. Return - ``0`` on success or ``-1`` on failure. This function *does not* steal a - reference to *val*. + ``0`` on success or ``-1`` on failure. + This function *does not* ":term:`steal`" a reference to *val*. + + .. note:: + + The operation is atomic on :term:`free threading ` + when *key* is :class:`str`, :class:`int`, :class:`float`, :class:`bool` or :class:`bytes`. .. c:function:: int PyDict_SetItemString(PyObject *p, const char *key, PyObject *val) @@ -91,6 +112,11 @@ Dictionary Objects If *key* is not in the dictionary, :exc:`KeyError` is raised. Return ``0`` on success or ``-1`` on failure. + .. note:: + + The operation is atomic on :term:`free threading ` + when *key* is :class:`str`, :class:`int`, :class:`float`, :class:`bool` or :class:`bytes`. + .. c:function:: int PyDict_DelItemString(PyObject *p, const char *key) @@ -107,7 +133,12 @@ Dictionary Objects * If the key is present, set *\*result* to a new :term:`strong reference` to the value and return ``1``. * If the key is missing, set *\*result* to ``NULL`` and return ``0``. - * On error, raise an exception and return ``-1``. + * On error, raise an exception, set *\*result* to ``NULL`` and return ``-1``. + + .. note:: + + The operation is atomic on :term:`free threading ` + when *key* is :class:`str`, :class:`int`, :class:`float`, :class:`bool` or :class:`bytes`. .. versionadded:: 3.13 @@ -126,6 +157,13 @@ Dictionary Objects :meth:`~object.__eq__` methods are silently ignored. Prefer the :c:func:`PyDict_GetItemWithError` function instead. + .. note:: + + In the :term:`free-threaded build`, the returned + :term:`borrowed reference` may become invalid if another thread modifies + the dictionary concurrently. Prefer :c:func:`PyDict_GetItemRef`, which + returns a :term:`strong reference`. + .. versionchanged:: 3.10 Calling this API without an :term:`attached thread state` had been allowed for historical reason. It is no longer allowed. @@ -138,6 +176,13 @@ Dictionary Objects occurred. Return ``NULL`` **without** an exception set if the key wasn't present. + .. note:: + + In the :term:`free-threaded build`, the returned + :term:`borrowed reference` may become invalid if another thread modifies + the dictionary concurrently. Prefer :c:func:`PyDict_GetItemRef`, which + returns a :term:`strong reference`. + .. c:function:: PyObject* PyDict_GetItemString(PyObject *p, const char *key) @@ -153,6 +198,13 @@ Dictionary Objects Prefer using the :c:func:`PyDict_GetItemWithError` function with your own :c:func:`PyUnicode_FromString` *key* instead. + .. note:: + + In the :term:`free-threaded build`, the returned + :term:`borrowed reference` may become invalid if another thread modifies + the dictionary concurrently. Prefer :c:func:`PyDict_GetItemStringRef`, + which returns a :term:`strong reference`. + .. c:function:: int PyDict_GetItemStringRef(PyObject *p, const char *key, PyObject **result) @@ -173,6 +225,14 @@ Dictionary Objects .. versionadded:: 3.4 + .. note:: + + In the :term:`free-threaded build`, the returned + :term:`borrowed reference` may become invalid if another thread modifies + the dictionary concurrently. Prefer :c:func:`PyDict_SetDefaultRef`, + which returns a :term:`strong reference`. + + .. c:function:: int PyDict_SetDefaultRef(PyObject *p, PyObject *key, PyObject *default_value, PyObject **result) @@ -192,13 +252,18 @@ Dictionary Objects These may refer to the same object: in that case you hold two separate references to it. + .. note:: + + The operation is atomic on :term:`free threading ` + when *key* is :class:`str`, :class:`int`, :class:`float`, :class:`bool` or :class:`bytes`. + .. versionadded:: 3.13 .. c:function:: int PyDict_Pop(PyObject *p, PyObject *key, PyObject **result) Remove *key* from dictionary *p* and optionally return the removed value. - Do not raise :exc:`KeyError` if the key missing. + Do not raise :exc:`KeyError` if the key is missing. - If the key is present, set *\*result* to a new reference to the removed value if *result* is not ``NULL``, and return ``1``. @@ -207,7 +272,12 @@ Dictionary Objects - On error, raise an exception and return ``-1``. Similar to :meth:`dict.pop`, but without the default value and - not raising :exc:`KeyError` if the key missing. + not raising :exc:`KeyError` if the key is missing. + + .. note:: + + The operation is atomic on :term:`free threading ` + when *key* is :class:`str`, :class:`int`, :class:`float`, :class:`bool` or :class:`bytes`. .. versionadded:: 3.13 @@ -245,6 +315,11 @@ Dictionary Objects ``len(p)`` on a dictionary. +.. c:function:: Py_ssize_t PyDict_GET_SIZE(PyObject *p) + + Similar to :c:func:`PyDict_Size`, but without error checking. + + .. c:function:: int PyDict_Next(PyObject *p, Py_ssize_t *ppos, PyObject **pkey, PyObject **pvalue) Iterate over all key-value pairs in the dictionary *p*. The @@ -301,6 +376,15 @@ Dictionary Objects } Py_END_CRITICAL_SECTION(); + .. note:: + + On the free-threaded build, this function can be used safely inside a + critical section. However, the references returned for *pkey* and *pvalue* + are :term:`borrowed ` and are only valid while the + critical section is held. If you need to use these objects outside the + critical section or when the critical section can be suspended, create a + :term:`strong reference ` (for example, using + :c:func:`Py_NewRef`). .. c:function:: int PyDict_Merge(PyObject *a, PyObject *b, int override) @@ -311,6 +395,13 @@ Dictionary Objects only be added if there is not a matching key in *a*. Return ``0`` on success or ``-1`` if an exception was raised. + .. note:: + + In the :term:`free-threaded build`, when *b* is a + :class:`dict` (with the standard iterator), both *a* and *b* are locked + for the duration of the operation. When *b* is a non-dict mapping, only + *a* is locked; *b* may be concurrently modified by another thread. + .. c:function:: int PyDict_Update(PyObject *a, PyObject *b) @@ -320,6 +411,13 @@ Dictionary Objects argument has no "keys" attribute. Return ``0`` on success or ``-1`` if an exception was raised. + .. note:: + + In the :term:`free-threaded build`, when *b* is a + :class:`dict` (with the standard iterator), both *a* and *b* are locked + for the duration of the operation. When *b* is a non-dict mapping, only + *a* is locked; *b* may be concurrently modified by another thread. + .. c:function:: int PyDict_MergeFromSeq2(PyObject *a, PyObject *seq2, int override) @@ -335,6 +433,13 @@ Dictionary Objects if override or key not in a: a[key] = value + .. note:: + + In the :term:`free-threaded ` build, only *a* is locked. + The iteration over *seq2* is not synchronized; *seq2* may be concurrently + modified by another thread. + + .. c:function:: int PyDict_AddWatcher(PyDict_WatchCallback callback) Register *callback* as a dictionary watcher. Return a non-negative integer @@ -342,6 +447,13 @@ Dictionary Objects of error (e.g. no more watcher IDs available), return ``-1`` and set an exception. + .. note:: + + This function is not internally synchronized. In the + :term:`free-threaded ` build, callers should ensure no + concurrent calls to :c:func:`PyDict_AddWatcher` or + :c:func:`PyDict_ClearWatcher` are in progress. + .. versionadded:: 3.12 .. c:function:: int PyDict_ClearWatcher(int watcher_id) @@ -350,6 +462,13 @@ Dictionary Objects :c:func:`PyDict_AddWatcher`. Return ``0`` on success, ``-1`` on error (e.g. if the given *watcher_id* was never registered.) + .. note:: + + This function is not internally synchronized. In the + :term:`free-threaded ` build, callers should ensure no + concurrent calls to :c:func:`PyDict_AddWatcher` or + :c:func:`PyDict_ClearWatcher` are in progress. + .. versionadded:: 3.12 .. c:function:: int PyDict_Watch(int watcher_id, PyObject *dict) @@ -417,3 +536,138 @@ Dictionary Objects it before returning. .. versionadded:: 3.12 + + +Dictionary View Objects +^^^^^^^^^^^^^^^^^^^^^^^ + +.. c:function:: int PyDictViewSet_Check(PyObject *op) + + Return true if *op* is a view of a set inside a dictionary. This is currently + equivalent to :c:expr:`PyDictKeys_Check(op) || PyDictItems_Check(op)`. This + function always succeeds. + + +.. c:var:: PyTypeObject PyDictKeys_Type + + Type object for a view of dictionary keys. In Python, this is the type of + the object returned by :meth:`dict.keys`. + + +.. c:function:: int PyDictKeys_Check(PyObject *op) + + Return true if *op* is an instance of a dictionary keys view. This function + always succeeds. + + +.. c:var:: PyTypeObject PyDictValues_Type + + Type object for a view of dictionary values. In Python, this is the type of + the object returned by :meth:`dict.values`. + + +.. c:function:: int PyDictValues_Check(PyObject *op) + + Return true if *op* is an instance of a dictionary values view. This function + always succeeds. + + +.. c:var:: PyTypeObject PyDictItems_Type + + Type object for a view of dictionary items. In Python, this is the type of + the object returned by :meth:`dict.items`. + + +.. c:function:: int PyDictItems_Check(PyObject *op) + + Return true if *op* is an instance of a dictionary items view. This function + always succeeds. + + +Ordered Dictionaries +^^^^^^^^^^^^^^^^^^^^ + +Python's C API provides interface for :class:`collections.OrderedDict` from C. +Since Python 3.7, dictionaries are ordered by default, so there is usually +little need for these functions; prefer ``PyDict*`` where possible. + + +.. c:var:: PyTypeObject PyODict_Type + + Type object for ordered dictionaries. This is the same object as + :class:`collections.OrderedDict` in the Python layer. + + +.. c:function:: int PyODict_Check(PyObject *od) + + Return true if *od* is an ordered dictionary object or an instance of a + subtype of the :class:`~collections.OrderedDict` type. This function + always succeeds. + + +.. c:function:: int PyODict_CheckExact(PyObject *od) + + Return true if *od* is an ordered dictionary object, but not an instance of + a subtype of the :class:`~collections.OrderedDict` type. + This function always succeeds. + + +.. c:var:: PyTypeObject PyODictKeys_Type + + Analogous to :c:type:`PyDictKeys_Type` for ordered dictionaries. + + +.. c:var:: PyTypeObject PyODictValues_Type + + Analogous to :c:type:`PyDictValues_Type` for ordered dictionaries. + + +.. c:var:: PyTypeObject PyODictItems_Type + + Analogous to :c:type:`PyDictItems_Type` for ordered dictionaries. + + +.. c:function:: PyObject *PyODict_New(void) + + Return a new empty ordered dictionary, or ``NULL`` on failure. + + This is analogous to :c:func:`PyDict_New`. + + +.. c:function:: int PyODict_SetItem(PyObject *od, PyObject *key, PyObject *value) + + Insert *value* into the ordered dictionary *od* with a key of *key*. + Return ``0`` on success or ``-1`` with an exception set on failure. + + This is analogous to :c:func:`PyDict_SetItem`. + + +.. c:function:: int PyODict_DelItem(PyObject *od, PyObject *key) + + Remove the entry in the ordered dictionary *od* with key *key*. + Return ``0`` on success or ``-1`` with an exception set on failure. + + This is analogous to :c:func:`PyDict_DelItem`. + + +These are :term:`soft deprecated` aliases to ``PyDict`` APIs: + + +.. list-table:: + :widths: auto + :header-rows: 1 + + * * ``PyODict`` + * ``PyDict`` + * * .. c:macro:: PyODict_GetItem(od, key) + * :c:func:`PyDict_GetItem` + * * .. c:macro:: PyODict_GetItemWithError(od, key) + * :c:func:`PyDict_GetItemWithError` + * * .. c:macro:: PyODict_GetItemString(od, key) + * :c:func:`PyDict_GetItemString` + * * .. c:macro:: PyODict_Contains(od, key) + * :c:func:`PyDict_Contains` + * * .. c:macro:: PyODict_Size(od) + * :c:func:`PyDict_Size` + * * .. c:macro:: PyODict_SIZE(od) + * :c:func:`PyDict_GET_SIZE` diff --git a/Doc/c-api/exceptions.rst b/Doc/c-api/exceptions.rst index c8e1b5c2461738..1b9c7ede393f5c 100644 --- a/Doc/c-api/exceptions.rst +++ b/Doc/c-api/exceptions.rst @@ -119,6 +119,21 @@ Printing and clearing .. versionadded:: 3.12 +.. c:function:: void PyErr_Display(PyObject *unused, PyObject *value, PyObject *tb) + + Legacy variant of :c:func:`PyErr_DisplayException`. + + Print the exception *value* with its traceback to :data:`sys.stderr`. + If *value* has no traceback set, *tb* is used as its traceback. + The first argument is ignored. + + If :data:`sys.stderr` is ``None``, nothing is printed. + If :data:`sys.stderr` is not set, the exception is dumped to the + C ``stderr`` stream instead. + + .. deprecated:: 3.12 + Use :c:func:`PyErr_DisplayException` instead. + Raising exceptions ================== @@ -309,6 +324,14 @@ For convenience, some of these functions will always return a .. versionadded:: 3.4 +.. c:function:: void PyErr_RangedSyntaxLocationObject(PyObject *filename, int lineno, int col_offset, int end_lineno, int end_col_offset) + + Similar to :c:func:`PyErr_SyntaxLocationObject`, but also sets the + *end_lineno* and *end_col_offset* information for the current exception. + + .. versionadded:: 3.10 + + .. c:function:: void PyErr_SyntaxLocationEx(const char *filename, int lineno, int col_offset) Like :c:func:`PyErr_SyntaxLocationObject`, but *filename* is a byte string @@ -331,6 +354,23 @@ For convenience, some of these functions will always return a use. +.. c:function:: PyObject *PyErr_ProgramTextObject(PyObject *filename, int lineno) + + Get the source line in *filename* at line *lineno*. *filename* should be a + Python :class:`str` object. + + On success, this function returns a Python string object with the found line. + On failure, this function returns ``NULL`` without an exception set. + + +.. c:function:: PyObject *PyErr_ProgramText(const char *filename, int lineno) + + Similar to :c:func:`PyErr_ProgramTextObject`, but *filename* is a + :c:expr:`const char *`, which is decoded with the + :term:`filesystem encoding and error handler`, instead of a + Python object reference. + + Issuing warnings ================ @@ -387,13 +427,22 @@ an error value). .. c:function:: int PyErr_WarnFormat(PyObject *category, Py_ssize_t stack_level, const char *format, ...) - Function similar to :c:func:`PyErr_WarnEx`, but use + Function similar to :c:func:`PyErr_WarnEx`, but uses :c:func:`PyUnicode_FromFormat` to format the warning message. *format* is an ASCII-encoded string. .. versionadded:: 3.2 +.. c:function:: int PyErr_WarnExplicitFormat(PyObject *category, const char *filename, int lineno, const char *module, PyObject *registry, const char *format, ...) + + Similar to :c:func:`PyErr_WarnExplicit`, but uses + :c:func:`PyUnicode_FromFormat` to format the warning message. *format* is + an ASCII-encoded string. + + .. versionadded:: 3.2 + + .. c:function:: int PyErr_ResourceWarning(PyObject *source, Py_ssize_t stack_level, const char *format, ...) Function similar to :c:func:`PyErr_WarnFormat`, but *category* is @@ -465,11 +514,12 @@ Querying the error indicator .. c:function:: void PyErr_SetRaisedException(PyObject *exc) Set *exc* as the exception currently being raised, - clearing the existing exception if one is set. + clearing the existing exception if one is set. If *exc* is ``NULL``, + just clear the existing exception. - .. warning:: + *exc* must be a valid exception or ``NULL``. - This call steals a reference to *exc*, which must be a valid exception. + This call ":term:`steals `" a reference to *exc*. .. versionadded:: 3.12 @@ -607,7 +657,8 @@ Querying the error indicator Set the exception info, as known from ``sys.exc_info()``. This refers to an exception that was *already caught*, not to an exception that was - freshly raised. This function steals the references of the arguments. + freshly raised. This function ":term:`steals `" the references + of the arguments. To clear the exception state, pass ``NULL`` for all three arguments. This function is kept for backwards compatibility. Prefer using :c:func:`PyErr_SetHandledException`. @@ -624,8 +675,8 @@ Querying the error indicator .. versionchanged:: 3.11 The ``type`` and ``traceback`` arguments are no longer used and can be NULL. The interpreter now derives them from the exception - instance (the ``value`` argument). The function still steals - references of all three arguments. + instance (the ``value`` argument). The function still + ":term:`steals `" references of all three arguments. Signal Handling @@ -639,28 +690,46 @@ Signal Handling single: SIGINT (C macro) single: KeyboardInterrupt (built-in exception) - This function interacts with Python's signal handling. + Handle external interruptions, such as signals or activating a debugger, + whose processing has been delayed until it is safe + to run Python code and/or raise exceptions. - If the function is called from the main thread and under the main Python - interpreter, it checks whether a signal has been sent to the processes - and if so, invokes the corresponding signal handler. If the :mod:`signal` - module is supported, this can invoke a signal handler written in Python. + For example, pressing :kbd:`Ctrl-C` causes a terminal to send the + :py:data:`signal.SIGINT` signal. + This function executes the corresponding Python signal handler, which, + by default, raises the :exc:`KeyboardInterrupt` exception. - The function attempts to handle all pending signals, and then returns ``0``. - However, if a Python signal handler raises an exception, the error - indicator is set and the function returns ``-1`` immediately (such that - other pending signals may not have been handled yet: they will be on the - next :c:func:`PyErr_CheckSignals()` invocation). + :c:func:`!PyErr_CheckSignals` should be called by long-running C code + frequently enough so that the response appears immediate to humans. - If the function is called from a non-main thread, or under a non-main - Python interpreter, it does nothing and returns ``0``. + Handlers invoked by this function currently include: - This function can be called by long-running C code that wants to - be interruptible by user requests (such as by pressing Ctrl-C). + - Signal handlers, including Python functions registered using + the :mod:`signal` module. - .. note:: - The default Python signal handler for :c:macro:`!SIGINT` raises the - :exc:`KeyboardInterrupt` exception. + Signal handlers are only run in the main thread of the main interpreter. + + (This is where the function got the name: originally, signals + were the only way to interrupt the interpreter.) + + - Running the garbage collector, if necessary. + + - Executing a pending :ref:`remote debugger ` script. + + If any handler raises an exception, immediately return ``-1`` with that + exception set. + Any remaining interruptions are left to be processed on the next + :c:func:`PyErr_CheckSignals()` invocation, if appropriate. + + If all handlers finish successfully, or there are no handlers to run, + return ``0``. + + .. versionchanged:: 3.12 + This function may now invoke the garbage collector. + + .. versionchanged:: 3.14 + This function may now execute a remote debugger script, if remote + debugging is enabled. .. c:function:: void PyErr_SetInterrupt() @@ -749,9 +818,30 @@ Exception Classes .. versionadded:: 3.2 +.. c:function:: int PyExceptionClass_Check(PyObject *ob) + + Return non-zero if *ob* is an exception class, zero otherwise. This function always succeeds. + + +.. c:function:: const char *PyExceptionClass_Name(PyObject *ob) + + Return :c:member:`~PyTypeObject.tp_name` of the exception class *ob*. + + Exception Objects ================= +.. c:function:: int PyExceptionInstance_Check(PyObject *op) + + Return true if *op* is an instance of :class:`BaseException`, false + otherwise. This function always succeeds. + + +.. c:macro:: PyExceptionInstance_Class(op) + + Equivalent to :c:func:`Py_TYPE(op) `. + + .. c:function:: PyObject* PyException_GetTraceback(PyObject *ex) Return the traceback associated with the exception as a new reference, as @@ -778,7 +868,7 @@ Exception Objects Set the context associated with the exception to *ctx*. Use ``NULL`` to clear it. There is no type check to make sure that *ctx* is an exception instance. - This steals a reference to *ctx*. + This ":term:`steals `" a reference to *ctx*. .. c:function:: PyObject* PyException_GetCause(PyObject *ex) @@ -793,7 +883,8 @@ Exception Objects Set the cause associated with the exception to *cause*. Use ``NULL`` to clear it. There is no type check to make sure that *cause* is either an exception - instance or ``None``. This steals a reference to *cause*. + instance or ``None``. + This ":term:`steals `" a reference to *cause*. The :attr:`~BaseException.__suppress_context__` attribute is implicitly set to ``True`` by this function. @@ -929,6 +1020,9 @@ because the :ref:`call protocol ` takes care of recursion handling. be concatenated to the :exc:`RecursionError` message caused by the recursion depth limit. + .. seealso:: + The :c:func:`PyUnstable_ThreadState_SetStackProtection` function. + .. versionchanged:: 3.9 This function is now also available in the :ref:`limited API `. @@ -944,7 +1038,7 @@ Properly implementing :c:member:`~PyTypeObject.tp_repr` for container types requ special recursion handling. In addition to protecting the stack, :c:member:`~PyTypeObject.tp_repr` also needs to track objects to prevent cycles. The following two functions facilitate this functionality. Effectively, -these are the C equivalent to :func:`reprlib.recursive_repr`. +these are the C equivalent to :deco:`reprlib.recursive_repr`. .. c:function:: int Py_ReprEnter(PyObject *object) @@ -969,184 +1063,159 @@ these are the C equivalent to :func:`reprlib.recursive_repr`. Ends a :c:func:`Py_ReprEnter`. Must be called once for each invocation of :c:func:`Py_ReprEnter` that returns zero. +.. c:function:: int Py_GetRecursionLimit(void) + + Get the recursion limit for the current interpreter. It can be set with + :c:func:`Py_SetRecursionLimit`. The recursion limit prevents the + Python interpreter stack from growing infinitely. + + This function cannot fail, and the caller must hold an + :term:`attached thread state`. + + .. seealso:: + :py:func:`sys.getrecursionlimit` + +.. c:function:: void Py_SetRecursionLimit(int new_limit) + + Set the recursion limit for the current interpreter. + + This function cannot fail, and the caller must hold an + :term:`attached thread state`. + + .. seealso:: + :py:func:`sys.setrecursionlimit` .. _standardexceptions: -Standard Exceptions -=================== - -All standard Python exceptions are available as global variables whose names are -``PyExc_`` followed by the Python exception name. These have the type -:c:expr:`PyObject*`; they are all class objects. For completeness, here are all -the variables: - -.. index:: - single: PyExc_BaseException (C var) - single: PyExc_Exception (C var) - single: PyExc_ArithmeticError (C var) - single: PyExc_AssertionError (C var) - single: PyExc_AttributeError (C var) - single: PyExc_BlockingIOError (C var) - single: PyExc_BrokenPipeError (C var) - single: PyExc_BufferError (C var) - single: PyExc_ChildProcessError (C var) - single: PyExc_ConnectionAbortedError (C var) - single: PyExc_ConnectionError (C var) - single: PyExc_ConnectionRefusedError (C var) - single: PyExc_ConnectionResetError (C var) - single: PyExc_EOFError (C var) - single: PyExc_FileExistsError (C var) - single: PyExc_FileNotFoundError (C var) - single: PyExc_FloatingPointError (C var) - single: PyExc_GeneratorExit (C var) - single: PyExc_ImportError (C var) - single: PyExc_IndentationError (C var) - single: PyExc_IndexError (C var) - single: PyExc_InterruptedError (C var) - single: PyExc_IsADirectoryError (C var) - single: PyExc_KeyError (C var) - single: PyExc_KeyboardInterrupt (C var) - single: PyExc_LookupError (C var) - single: PyExc_MemoryError (C var) - single: PyExc_ModuleNotFoundError (C var) - single: PyExc_NameError (C var) - single: PyExc_NotADirectoryError (C var) - single: PyExc_NotImplementedError (C var) - single: PyExc_OSError (C var) - single: PyExc_OverflowError (C var) - single: PyExc_PermissionError (C var) - single: PyExc_ProcessLookupError (C var) - single: PyExc_PythonFinalizationError (C var) - single: PyExc_RecursionError (C var) - single: PyExc_ReferenceError (C var) - single: PyExc_RuntimeError (C var) - single: PyExc_StopAsyncIteration (C var) - single: PyExc_StopIteration (C var) - single: PyExc_SyntaxError (C var) - single: PyExc_SystemError (C var) - single: PyExc_SystemExit (C var) - single: PyExc_TabError (C var) - single: PyExc_TimeoutError (C var) - single: PyExc_TypeError (C var) - single: PyExc_UnboundLocalError (C var) - single: PyExc_UnicodeDecodeError (C var) - single: PyExc_UnicodeEncodeError (C var) - single: PyExc_UnicodeError (C var) - single: PyExc_UnicodeTranslateError (C var) - single: PyExc_ValueError (C var) - single: PyExc_ZeroDivisionError (C var) - -+-----------------------------------------+---------------------------------+----------+ -| C Name | Python Name | Notes | -+=========================================+=================================+==========+ -| :c:data:`PyExc_BaseException` | :exc:`BaseException` | [1]_ | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_Exception` | :exc:`Exception` | [1]_ | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_ArithmeticError` | :exc:`ArithmeticError` | [1]_ | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_AssertionError` | :exc:`AssertionError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_AttributeError` | :exc:`AttributeError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_BlockingIOError` | :exc:`BlockingIOError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_BrokenPipeError` | :exc:`BrokenPipeError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_BufferError` | :exc:`BufferError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_ChildProcessError` | :exc:`ChildProcessError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_ConnectionAbortedError` | :exc:`ConnectionAbortedError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_ConnectionError` | :exc:`ConnectionError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_ConnectionRefusedError` | :exc:`ConnectionRefusedError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_ConnectionResetError` | :exc:`ConnectionResetError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_EOFError` | :exc:`EOFError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_FileExistsError` | :exc:`FileExistsError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_FileNotFoundError` | :exc:`FileNotFoundError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_FloatingPointError` | :exc:`FloatingPointError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_GeneratorExit` | :exc:`GeneratorExit` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_ImportError` | :exc:`ImportError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_IndentationError` | :exc:`IndentationError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_IndexError` | :exc:`IndexError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_InterruptedError` | :exc:`InterruptedError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_IsADirectoryError` | :exc:`IsADirectoryError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_KeyError` | :exc:`KeyError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_KeyboardInterrupt` | :exc:`KeyboardInterrupt` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_LookupError` | :exc:`LookupError` | [1]_ | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_MemoryError` | :exc:`MemoryError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_ModuleNotFoundError` | :exc:`ModuleNotFoundError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_NameError` | :exc:`NameError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_NotADirectoryError` | :exc:`NotADirectoryError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_NotImplementedError` | :exc:`NotImplementedError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_OSError` | :exc:`OSError` | [1]_ | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_OverflowError` | :exc:`OverflowError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_PermissionError` | :exc:`PermissionError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_ProcessLookupError` | :exc:`ProcessLookupError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_PythonFinalizationError` | :exc:`PythonFinalizationError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_RecursionError` | :exc:`RecursionError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_ReferenceError` | :exc:`ReferenceError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_RuntimeError` | :exc:`RuntimeError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_StopAsyncIteration` | :exc:`StopAsyncIteration` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_StopIteration` | :exc:`StopIteration` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_SyntaxError` | :exc:`SyntaxError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_SystemError` | :exc:`SystemError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_SystemExit` | :exc:`SystemExit` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_TabError` | :exc:`TabError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_TimeoutError` | :exc:`TimeoutError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_TypeError` | :exc:`TypeError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_UnboundLocalError` | :exc:`UnboundLocalError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_UnicodeDecodeError` | :exc:`UnicodeDecodeError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_UnicodeEncodeError` | :exc:`UnicodeEncodeError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_UnicodeError` | :exc:`UnicodeError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_UnicodeTranslateError` | :exc:`UnicodeTranslateError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_ValueError` | :exc:`ValueError` | | -+-----------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_ZeroDivisionError` | :exc:`ZeroDivisionError` | | -+-----------------------------------------+---------------------------------+----------+ +Exception and warning types +=========================== + +All standard Python exceptions and warning categories are available as global +variables whose names are ``PyExc_`` followed by the Python exception name. +These have the type :c:expr:`PyObject*`; they are all class objects. + +For completeness, here are all the variables: + +Exception types +--------------- + +.. list-table:: + :align: left + :widths: auto + :header-rows: 1 + + * * C name + * Python name + * * .. c:var:: PyObject *PyExc_BaseException + * :exc:`BaseException` + * * .. c:var:: PyObject *PyExc_BaseExceptionGroup + * :exc:`BaseExceptionGroup` + * * .. c:var:: PyObject *PyExc_Exception + * :exc:`Exception` + * * .. c:var:: PyObject *PyExc_ArithmeticError + * :exc:`ArithmeticError` + * * .. c:var:: PyObject *PyExc_AssertionError + * :exc:`AssertionError` + * * .. c:var:: PyObject *PyExc_AttributeError + * :exc:`AttributeError` + * * .. c:var:: PyObject *PyExc_BlockingIOError + * :exc:`BlockingIOError` + * * .. c:var:: PyObject *PyExc_BrokenPipeError + * :exc:`BrokenPipeError` + * * .. c:var:: PyObject *PyExc_BufferError + * :exc:`BufferError` + * * .. c:var:: PyObject *PyExc_ChildProcessError + * :exc:`ChildProcessError` + * * .. c:var:: PyObject *PyExc_ConnectionAbortedError + * :exc:`ConnectionAbortedError` + * * .. c:var:: PyObject *PyExc_ConnectionError + * :exc:`ConnectionError` + * * .. c:var:: PyObject *PyExc_ConnectionRefusedError + * :exc:`ConnectionRefusedError` + * * .. c:var:: PyObject *PyExc_ConnectionResetError + * :exc:`ConnectionResetError` + * * .. c:var:: PyObject *PyExc_EOFError + * :exc:`EOFError` + * * .. c:var:: PyObject *PyExc_FileExistsError + * :exc:`FileExistsError` + * * .. c:var:: PyObject *PyExc_FileNotFoundError + * :exc:`FileNotFoundError` + * * .. c:var:: PyObject *PyExc_FloatingPointError + * :exc:`FloatingPointError` + * * .. c:var:: PyObject *PyExc_GeneratorExit + * :exc:`GeneratorExit` + * * .. c:var:: PyObject *PyExc_ImportError + * :exc:`ImportError` + * * .. c:var:: PyObject *PyExc_IndentationError + * :exc:`IndentationError` + * * .. c:var:: PyObject *PyExc_IndexError + * :exc:`IndexError` + * * .. c:var:: PyObject *PyExc_InterruptedError + * :exc:`InterruptedError` + * * .. c:var:: PyObject *PyExc_IsADirectoryError + * :exc:`IsADirectoryError` + * * .. c:var:: PyObject *PyExc_KeyError + * :exc:`KeyError` + * * .. c:var:: PyObject *PyExc_KeyboardInterrupt + * :exc:`KeyboardInterrupt` + * * .. c:var:: PyObject *PyExc_LookupError + * :exc:`LookupError` + * * .. c:var:: PyObject *PyExc_MemoryError + * :exc:`MemoryError` + * * .. c:var:: PyObject *PyExc_ModuleNotFoundError + * :exc:`ModuleNotFoundError` + * * .. c:var:: PyObject *PyExc_NameError + * :exc:`NameError` + * * .. c:var:: PyObject *PyExc_NotADirectoryError + * :exc:`NotADirectoryError` + * * .. c:var:: PyObject *PyExc_NotImplementedError + * :exc:`NotImplementedError` + * * .. c:var:: PyObject *PyExc_OSError + * :exc:`OSError` + * * .. c:var:: PyObject *PyExc_OverflowError + * :exc:`OverflowError` + * * .. c:var:: PyObject *PyExc_PermissionError + * :exc:`PermissionError` + * * .. c:var:: PyObject *PyExc_ProcessLookupError + * :exc:`ProcessLookupError` + * * .. c:var:: PyObject *PyExc_PythonFinalizationError + * :exc:`PythonFinalizationError` + * * .. c:var:: PyObject *PyExc_RecursionError + * :exc:`RecursionError` + * * .. c:var:: PyObject *PyExc_ReferenceError + * :exc:`ReferenceError` + * * .. c:var:: PyObject *PyExc_RuntimeError + * :exc:`RuntimeError` + * * .. c:var:: PyObject *PyExc_StopAsyncIteration + * :exc:`StopAsyncIteration` + * * .. c:var:: PyObject *PyExc_StopIteration + * :exc:`StopIteration` + * * .. c:var:: PyObject *PyExc_SyntaxError + * :exc:`SyntaxError` + * * .. c:var:: PyObject *PyExc_SystemError + * :exc:`SystemError` + * * .. c:var:: PyObject *PyExc_SystemExit + * :exc:`SystemExit` + * * .. c:var:: PyObject *PyExc_TabError + * :exc:`TabError` + * * .. c:var:: PyObject *PyExc_TimeoutError + * :exc:`TimeoutError` + * * .. c:var:: PyObject *PyExc_TypeError + * :exc:`TypeError` + * * .. c:var:: PyObject *PyExc_UnboundLocalError + * :exc:`UnboundLocalError` + * * .. c:var:: PyObject *PyExc_UnicodeDecodeError + * :exc:`UnicodeDecodeError` + * * .. c:var:: PyObject *PyExc_UnicodeEncodeError + * :exc:`UnicodeEncodeError` + * * .. c:var:: PyObject *PyExc_UnicodeError + * :exc:`UnicodeError` + * * .. c:var:: PyObject *PyExc_UnicodeTranslateError + * :exc:`UnicodeTranslateError` + * * .. c:var:: PyObject *PyExc_ValueError + * :exc:`ValueError` + * * .. c:var:: PyObject *PyExc_ZeroDivisionError + * :exc:`ZeroDivisionError` .. versionadded:: 3.3 :c:data:`PyExc_BlockingIOError`, :c:data:`PyExc_BrokenPipeError`, @@ -1164,88 +1233,116 @@ the variables: .. versionadded:: 3.6 :c:data:`PyExc_ModuleNotFoundError`. -These are compatibility aliases to :c:data:`PyExc_OSError`: +.. versionadded:: 3.11 + :c:data:`PyExc_BaseExceptionGroup`. + -.. index:: - single: PyExc_EnvironmentError (C var) - single: PyExc_IOError (C var) - single: PyExc_WindowsError (C var) +OSError aliases +--------------- -+-------------------------------------+----------+ -| C Name | Notes | -+=====================================+==========+ -| :c:data:`!PyExc_EnvironmentError` | | -+-------------------------------------+----------+ -| :c:data:`!PyExc_IOError` | | -+-------------------------------------+----------+ -| :c:data:`!PyExc_WindowsError` | [2]_ | -+-------------------------------------+----------+ +The following are a compatibility aliases to :c:data:`PyExc_OSError`. .. versionchanged:: 3.3 These aliases used to be separate exception types. +.. list-table:: + :align: left + :widths: auto + :header-rows: 1 + + * * C name + * Python name + * Notes + * * .. c:var:: PyObject *PyExc_EnvironmentError + * :exc:`OSError` + * + * * .. c:var:: PyObject *PyExc_IOError + * :exc:`OSError` + * + * * .. c:var:: PyObject *PyExc_WindowsError + * :exc:`OSError` + * [win]_ + Notes: -.. [1] - This is a base class for other standard exceptions. +.. [win] + :c:var:`!PyExc_WindowsError` is only defined on Windows; protect code that + uses this by testing that the preprocessor macro ``MS_WINDOWS`` is defined. -.. [2] - Only defined on Windows; protect code that uses this by testing that the - preprocessor macro ``MS_WINDOWS`` is defined. .. _standardwarningcategories: -Standard Warning Categories -=========================== - -All standard Python warning categories are available as global variables whose -names are ``PyExc_`` followed by the Python exception name. These have the type -:c:expr:`PyObject*`; they are all class objects. For completeness, here are all -the variables: - -.. index:: - single: PyExc_Warning (C var) - single: PyExc_BytesWarning (C var) - single: PyExc_DeprecationWarning (C var) - single: PyExc_FutureWarning (C var) - single: PyExc_ImportWarning (C var) - single: PyExc_PendingDeprecationWarning (C var) - single: PyExc_ResourceWarning (C var) - single: PyExc_RuntimeWarning (C var) - single: PyExc_SyntaxWarning (C var) - single: PyExc_UnicodeWarning (C var) - single: PyExc_UserWarning (C var) - -+------------------------------------------+---------------------------------+----------+ -| C Name | Python Name | Notes | -+==========================================+=================================+==========+ -| :c:data:`PyExc_Warning` | :exc:`Warning` | [3]_ | -+------------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_BytesWarning` | :exc:`BytesWarning` | | -+------------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_DeprecationWarning` | :exc:`DeprecationWarning` | | -+------------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_FutureWarning` | :exc:`FutureWarning` | | -+------------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_ImportWarning` | :exc:`ImportWarning` | | -+------------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_PendingDeprecationWarning`| :exc:`PendingDeprecationWarning`| | -+------------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_ResourceWarning` | :exc:`ResourceWarning` | | -+------------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_RuntimeWarning` | :exc:`RuntimeWarning` | | -+------------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_SyntaxWarning` | :exc:`SyntaxWarning` | | -+------------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_UnicodeWarning` | :exc:`UnicodeWarning` | | -+------------------------------------------+---------------------------------+----------+ -| :c:data:`PyExc_UserWarning` | :exc:`UserWarning` | | -+------------------------------------------+---------------------------------+----------+ +Warning types +------------- + +.. list-table:: + :align: left + :widths: auto + :header-rows: 1 + + * * C name + * Python name + * * .. c:var:: PyObject *PyExc_Warning + * :exc:`Warning` + * * .. c:var:: PyObject *PyExc_BytesWarning + * :exc:`BytesWarning` + * * .. c:var:: PyObject *PyExc_DeprecationWarning + * :exc:`DeprecationWarning` + * * .. c:var:: PyObject *PyExc_EncodingWarning + * :exc:`EncodingWarning` + * * .. c:var:: PyObject *PyExc_FutureWarning + * :exc:`FutureWarning` + * * .. c:var:: PyObject *PyExc_ImportWarning + * :exc:`ImportWarning` + * * .. c:var:: PyObject *PyExc_PendingDeprecationWarning + * :exc:`PendingDeprecationWarning` + * * .. c:var:: PyObject *PyExc_ResourceWarning + * :exc:`ResourceWarning` + * * .. c:var:: PyObject *PyExc_RuntimeWarning + * :exc:`RuntimeWarning` + * * .. c:var:: PyObject *PyExc_SyntaxWarning + * :exc:`SyntaxWarning` + * * .. c:var:: PyObject *PyExc_UnicodeWarning + * :exc:`UnicodeWarning` + * * .. c:var:: PyObject *PyExc_UserWarning + * :exc:`UserWarning` .. versionadded:: 3.2 :c:data:`PyExc_ResourceWarning`. -Notes: +.. versionadded:: 3.10 + :c:data:`PyExc_EncodingWarning`. + + +Tracebacks +========== + +.. c:var:: PyTypeObject PyTraceBack_Type + + Type object for traceback objects. This is available as + :class:`types.TracebackType` in the Python layer. + + +.. c:function:: int PyTraceBack_Check(PyObject *op) + + Return true if *op* is a traceback object, false otherwise. This function + does not account for subtypes. + + +.. c:function:: int PyTraceBack_Here(PyFrameObject *f) + + Replace the :attr:`~BaseException.__traceback__` attribute on the current + exception with a new traceback prepending *f* to the existing chain. + + Calling this function without an exception set is undefined behavior. + + This function returns ``0`` on success, and returns ``-1`` with an + exception set on failure. + + +.. c:function:: int PyTraceBack_Print(PyObject *tb, PyObject *f) + + Write the traceback *tb* into the file *f*. -.. [3] - This is a base class for other standard warning categories. + This function returns ``0`` on success, and returns ``-1`` with an + exception set on failure. diff --git a/Doc/c-api/extension-modules.rst b/Doc/c-api/extension-modules.rst new file mode 100644 index 00000000000000..3d331e6ec12f76 --- /dev/null +++ b/Doc/c-api/extension-modules.rst @@ -0,0 +1,247 @@ +.. highlight:: c + +.. _extension-modules: + +Defining extension modules +-------------------------- + +A C extension for CPython is a shared library (for example, a ``.so`` file +on Linux, ``.pyd`` DLL on Windows), which is loadable into the Python process +(for example, it is compiled with compatible compiler settings), and which +exports an :ref:`initialization function `. + +To be importable by default (that is, by +:py:class:`importlib.machinery.ExtensionFileLoader`), +the shared library must be available on :py:attr:`sys.path`, +and must be named after the module name plus an extension listed in +:py:attr:`importlib.machinery.EXTENSION_SUFFIXES`. + +.. note:: + + Building, packaging and distributing extension modules is best done with + third-party tools, and is out of scope of this document. + One suitable tool is Setuptools, whose documentation can be found at + https://setuptools.pypa.io/en/latest/setuptools.html. + +Normally, the initialization function returns a module definition initialized +using :c:func:`PyModuleDef_Init`. +This allows splitting the creation process into several phases: + +- Before any substantial code is executed, Python can determine which + capabilities the module supports, and it can adjust the environment or + refuse loading an incompatible extension. +- By default, Python itself creates the module object -- that is, it does + the equivalent of :py:meth:`object.__new__` for classes. + It also sets initial attributes like :attr:`~module.__package__` and + :attr:`~module.__loader__`. +- Afterwards, the module object is initialized using extension-specific + code -- the equivalent of :py:meth:`~object.__init__` on classes. + +This is called *multi-phase initialization* to distinguish it from the legacy +(but still supported) *single-phase initialization* scheme, +where the initialization function returns a fully constructed module. +See the :ref:`single-phase-initialization section below ` +for details. + +.. versionchanged:: 3.5 + + Added support for multi-phase initialization (:pep:`489`). + + +Multiple module instances +......................... + +By default, extension modules are not singletons. +For example, if the :py:attr:`sys.modules` entry is removed and the module +is re-imported, a new module object is created, and typically populated with +fresh method and type objects. +The old module is subject to normal garbage collection. +This mirrors the behavior of pure-Python modules. + +Additional module instances may be created in +:ref:`sub-interpreters ` +or after Python runtime reinitialization +(:c:func:`Py_Finalize` and :c:func:`Py_Initialize`). +In these cases, sharing Python objects between module instances would likely +cause crashes or undefined behavior. + +To avoid such issues, each instance of an extension module should +be *isolated*: changes to one instance should not implicitly affect the others, +and all state owned by the module, including references to Python objects, +should be specific to a particular module instance. +See :ref:`isolating-extensions-howto` for more details and a practical guide. + +A simpler way to avoid these issues is +:ref:`raising an error on repeated initialization `. + +All modules are expected to support +:ref:`sub-interpreters `, or otherwise explicitly +signal a lack of support. +This is usually achieved by isolation or blocking repeated initialization, +as above. +A module may also be limited to the main interpreter using +the :c:data:`Py_mod_multiple_interpreters` slot. + + +.. _extension-export-hook: + +Initialization function +....................... + +The initialization function defined by an extension module has the +following signature: + +.. c:function:: PyObject* PyInit_modulename(void) + +Its name should be :samp:`PyInit_{}`, with ```` replaced by the +name of the module. + +For modules with ASCII-only names, the function must instead be named +:samp:`PyInit_{}`, with ```` replaced by the name of the module. +When using :ref:`multi-phase-initialization`, non-ASCII module names +are allowed. In this case, the initialization function name is +:samp:`PyInitU_{}`, with ```` encoded using Python's +*punycode* encoding with hyphens replaced by underscores. In Python: + +.. code-block:: python + + def initfunc_name(name): + try: + suffix = b'_' + name.encode('ascii') + except UnicodeEncodeError: + suffix = b'U_' + name.encode('punycode').replace(b'-', b'_') + return b'PyInit' + suffix + +It is recommended to define the initialization function using a helper macro: + +.. c:macro:: PyMODINIT_FUNC + + Declare an extension module initialization function. + This macro: + + * specifies the :c:expr:`PyObject*` return type, + * adds any special linkage declarations required by the platform, and + * for C++, declares the function as ``extern "C"``. + +For example, a module called ``spam`` would be defined like this:: + + static struct PyModuleDef spam_module = { + .m_base = PyModuleDef_HEAD_INIT, + .m_name = "spam", + ... + }; + + PyMODINIT_FUNC + PyInit_spam(void) + { + return PyModuleDef_Init(&spam_module); + } + +It is possible to export multiple modules from a single shared library by +defining multiple initialization functions. However, importing them requires +using symbolic links or a custom importer, because by default only the +function corresponding to the filename is found. +See the `Multiple modules in one library `__ +section in :pep:`489` for details. + +The initialization function is typically the only non-\ ``static`` +item defined in the module's C source. + + +.. _multi-phase-initialization: + +Multi-phase initialization +.......................... + +Normally, the :ref:`initialization function ` +(``PyInit_modulename``) returns a :c:type:`PyModuleDef` instance with +non-``NULL`` :c:member:`~PyModuleDef.m_slots`. +Before it is returned, the ``PyModuleDef`` instance must be initialized +using the following function: + + +.. c:function:: PyObject* PyModuleDef_Init(PyModuleDef *def) + + Ensure a module definition is a properly initialized Python object that + correctly reports its type and a reference count. + + Return *def* cast to ``PyObject*``, or ``NULL`` if an error occurred. + + Calling this function is required for :ref:`multi-phase-initialization`. + It should not be used in other contexts. + + Note that Python assumes that ``PyModuleDef`` structures are statically + allocated. + This function may return either a new reference or a borrowed one; + this reference must not be released. + + .. versionadded:: 3.5 + + +.. _single-phase-initialization: + +Legacy single-phase initialization +.................................. + +.. attention:: + Single-phase initialization is a legacy mechanism to initialize extension + modules, with known drawbacks and design flaws. Extension module authors + are encouraged to use multi-phase initialization instead. + +In single-phase initialization, the +:ref:`initialization function ` (``PyInit_modulename``) +should create, populate and return a module object. +This is typically done using :c:func:`PyModule_Create` and functions like +:c:func:`PyModule_AddObjectRef`. + +Single-phase initialization differs from the :ref:`default ` +in the following ways: + +* Single-phase modules are, or rather *contain*, “singletons”. + + When the module is first initialized, Python saves the contents of + the module's ``__dict__`` (that is, typically, the module's functions and + types). + + For subsequent imports, Python does not call the initialization function + again. + Instead, it creates a new module object with a new ``__dict__``, and copies + the saved contents to it. + For example, given a single-phase module ``_testsinglephase`` + [#testsinglephase]_ that defines a function ``sum`` and an exception class + ``error``: + + .. code-block:: python + + >>> import sys + >>> import _testsinglephase as one + >>> del sys.modules['_testsinglephase'] + >>> import _testsinglephase as two + >>> one is two + False + >>> one.__dict__ is two.__dict__ + False + >>> one.sum is two.sum + True + >>> one.error is two.error + True + + The exact behavior should be considered a CPython implementation detail. + +* To work around the fact that ``PyInit_modulename`` does not take a *spec* + argument, some state of the import machinery is saved and applied to the + first suitable module created during the ``PyInit_modulename`` call. + Specifically, when a sub-module is imported, this mechanism prepends the + parent package name to the name of the module. + + A single-phase ``PyInit_modulename`` function should create “its” module + object as soon as possible, before any other module objects can be created. + +* Non-ASCII module names (``PyInitU_modulename``) are not supported. + +* Single-phase modules support module lookup functions like + :c:func:`PyState_FindModule`. + +.. [#testsinglephase] ``_testsinglephase`` is an internal module used + in CPython's self-test suite; your installation may or may not + include it. diff --git a/Doc/c-api/file.rst b/Doc/c-api/file.rst index e9019a0d500f7e..dcafefdc045872 100644 --- a/Doc/c-api/file.rst +++ b/Doc/c-api/file.rst @@ -2,7 +2,7 @@ .. _fileobjects: -File Objects +File objects ------------ .. index:: pair: object; file @@ -93,6 +93,29 @@ the :mod:`io` APIs instead. .. versionadded:: 3.8 +.. c:function:: PyObject *PyFile_OpenCodeObject(PyObject *path) + + Open *path* with the mode ``'rb'``. *path* must be a Python :class:`str` + object. The behavior of this function may be overridden by + :c:func:`PyFile_SetOpenCodeHook` to allow for some preprocessing of the + text. + + This is analogous to :func:`io.open_code` in Python. + + On success, this function returns a :term:`strong reference` to a Python + file object. On failure, this function returns ``NULL`` with an exception + set. + + .. versionadded:: 3.8 + + +.. c:function:: PyObject *PyFile_OpenCode(const char *path) + + Similar to :c:func:`PyFile_OpenCodeObject`, but *path* is a + UTF-8 encoded :c:expr:`const char*`. + + .. versionadded:: 3.8 + .. c:function:: int PyFile_WriteObject(PyObject *obj, PyObject *p, int flags) @@ -100,11 +123,34 @@ the :mod:`io` APIs instead. Write object *obj* to file object *p*. The only supported flag for *flags* is :c:macro:`Py_PRINT_RAW`; if given, the :func:`str` of the object is written - instead of the :func:`repr`. Return ``0`` on success or ``-1`` on failure; the - appropriate exception will be set. + instead of the :func:`repr`. + + If *obj* is ``NULL``, write the string ``""``. + Return ``0`` on success or ``-1`` on failure; the + appropriate exception will be set. .. c:function:: int PyFile_WriteString(const char *s, PyObject *p) Write string *s* to file object *p*. Return ``0`` on success or ``-1`` on failure; the appropriate exception will be set. + + +Soft-deprecated API +^^^^^^^^^^^^^^^^^^^ + +.. soft-deprecated:: 3.15 + +These are APIs that were included in Python's C API +by mistake. They are documented solely for completeness; use other +``PyFile*`` APIs instead. + +.. c:function:: PyObject *PyFile_NewStdPrinter(int fd) + + Use :c:func:`PyFile_FromFd` with defaults (``fd, NULL, "w", -1, NULL, NULL, NULL, 0``) instead. + +.. c:var:: PyTypeObject PyStdPrinter_Type + + Type of file-like objects used internally at Python startup when :py:mod:`io` is + not yet available. + Use Python :py:func:`open` or :c:func:`PyFile_FromFd` to create file objects instead. diff --git a/Doc/c-api/float.rst b/Doc/c-api/float.rst index c5a7653efca26b..420f7f9401fcc4 100644 --- a/Doc/c-api/float.rst +++ b/Doc/c-api/float.rst @@ -78,6 +78,104 @@ Floating-Point Objects Return the minimum normalized positive float *DBL_MIN* as C :c:expr:`double`. +.. c:macro:: Py_INFINITY + + This macro expands to a constant expression of type :c:expr:`double`, that + represents the positive infinity. + + On most platforms, this is equivalent to the :c:macro:`!INFINITY` macro from + the C11 standard ```` header. + + +.. c:macro:: Py_NAN + + This macro expands to a constant expression of type :c:expr:`double`, that + represents a quiet not-a-number (qNaN) value. + + On most platforms, this is equivalent to the :c:macro:`!NAN` macro from + the C11 standard ```` header. + + +.. c:macro:: Py_HUGE_VAL + + Equivalent to :c:macro:`!INFINITY`. + + .. deprecated:: 3.14 + The macro is :term:`soft deprecated`. + + +.. c:macro:: Py_MATH_E + + The definition (accurate for a :c:expr:`double` type) of the :data:`math.e` constant. + + +.. c:macro:: Py_MATH_El + + High precision (long double) definition of :data:`~math.e` constant. + + +.. c:macro:: Py_MATH_PI + + The definition (accurate for a :c:expr:`double` type) of the :data:`math.pi` constant. + + +.. c:macro:: Py_MATH_PIl + + High precision (long double) definition of :data:`~math.pi` constant. + + +.. c:macro:: Py_MATH_TAU + + The definition (accurate for a :c:expr:`double` type) of the :data:`math.tau` constant. + + .. versionadded:: 3.6 + + +.. c:macro:: Py_RETURN_NAN + + Return :data:`math.nan` from a function. + + On most platforms, this is equivalent to ``return PyFloat_FromDouble(NAN)``. + + +.. c:macro:: Py_RETURN_INF(sign) + + Return :data:`math.inf` or :data:`-math.inf ` from a function, + depending on the sign of *sign*. + + On most platforms, this is equivalent to the following:: + + return PyFloat_FromDouble(copysign(INFINITY, sign)); + + +.. c:macro:: Py_IS_FINITE(X) + + Return ``1`` if the given floating-point number *X* is finite, + that is, it is normal, subnormal or zero, but not infinite or NaN. + Return ``0`` otherwise. + + .. deprecated:: 3.14 + The macro is :term:`soft deprecated`. Use :c:macro:`!isfinite` instead. + + +.. c:macro:: Py_IS_INFINITY(X) + + Return ``1`` if the given floating-point number *X* is positive or negative + infinity. Return ``0`` otherwise. + + .. deprecated:: 3.14 + The macro is :term:`soft deprecated`. Use :c:macro:`!isinf` instead. + + +.. c:macro:: Py_IS_NAN(X) + + Return ``1`` if the given floating-point number *X* is a not-a-number (NaN) + value. Return ``0`` otherwise. + + .. deprecated:: 3.14 + The macro is :term:`soft deprecated`. Use :c:macro:`!isnan` instead. + + Pack and Unpack functions ------------------------- @@ -96,8 +194,8 @@ NaNs (if such things exist on the platform) isn't handled correctly, and attempting to unpack a bytes string containing an IEEE INF or NaN will raise an exception. -Note that NaNs type may not be preserved on IEEE platforms (silent NaN become -quiet), for example on x86 systems in 32-bit mode. +Note that NaN type may not be preserved on IEEE platforms (signaling NaNs become +quiet NaNs), for example on x86 systems in 32-bit mode. On non-IEEE platforms with more precision, or larger dynamic range, than IEEE 754 supports, not all values can be packed; on non-IEEE platforms with less @@ -111,7 +209,7 @@ Pack functions The pack routines write 2, 4 or 8 bytes, starting at *p*. *le* is an :c:expr:`int` argument, non-zero if you want the bytes string in little-endian -format (exponent last, at ``p+1``, ``p+3``, or ``p+6`` ``p+7``), zero if you +format (exponent last, at ``p+1``, ``p+3``, or ``p+6`` and ``p+7``), zero if you want big-endian format (exponent first, at *p*). The :c:macro:`PY_BIG_ENDIAN` constant can be used to use the native endian: it is equal to ``1`` on big endian processor, or ``0`` on little endian processor. @@ -124,15 +222,15 @@ There are two problems on non-IEEE platforms: * What this does is undefined if *x* is a NaN or infinity. * ``-0.0`` and ``+0.0`` produce the same bytes string. -.. c:function:: int PyFloat_Pack2(double x, unsigned char *p, int le) +.. c:function:: int PyFloat_Pack2(double x, char *p, int le) Pack a C double as the IEEE 754 binary16 half-precision format. -.. c:function:: int PyFloat_Pack4(double x, unsigned char *p, int le) +.. c:function:: int PyFloat_Pack4(double x, char *p, int le) Pack a C double as the IEEE 754 binary32 single precision format. -.. c:function:: int PyFloat_Pack8(double x, unsigned char *p, int le) +.. c:function:: int PyFloat_Pack8(double x, char *p, int le) Pack a C double as the IEEE 754 binary64 double precision format. @@ -154,14 +252,14 @@ Return value: The unpacked double. On error, this is ``-1.0`` and Note that on a non-IEEE platform this will refuse to unpack a bytes string that represents a NaN or infinity. -.. c:function:: double PyFloat_Unpack2(const unsigned char *p, int le) +.. c:function:: double PyFloat_Unpack2(const char *p, int le) Unpack the IEEE 754 binary16 half-precision format as a C double. -.. c:function:: double PyFloat_Unpack4(const unsigned char *p, int le) +.. c:function:: double PyFloat_Unpack4(const char *p, int le) Unpack the IEEE 754 binary32 single precision format as a C double. -.. c:function:: double PyFloat_Unpack8(const unsigned char *p, int le) +.. c:function:: double PyFloat_Unpack8(const char *p, int le) Unpack the IEEE 754 binary64 double precision format as a C double. diff --git a/Doc/c-api/frame.rst b/Doc/c-api/frame.rst index 1a52e146a69751..70a610cea82d06 100644 --- a/Doc/c-api/frame.rst +++ b/Doc/c-api/frame.rst @@ -1,6 +1,6 @@ .. highlight:: c -Frame Objects +Frame objects ------------- .. c:type:: PyFrameObject @@ -29,6 +29,12 @@ See also :ref:`Reflection `. Previously, this type was only available after including ````. +.. c:function:: PyFrameObject *PyFrame_New(PyThreadState *tstate, PyCodeObject *code, PyObject *globals, PyObject *locals) + + Create a new frame object. This function returns a :term:`strong reference` + to the new frame object on success, and returns ``NULL`` with an exception + set on failure. + .. c:function:: int PyFrame_Check(PyObject *obj) Return non-zero if *obj* is a frame object. @@ -44,6 +50,7 @@ See also :ref:`Reflection `. Return a :term:`strong reference`, or ``NULL`` if *frame* has no outer frame. + This raises no exceptions. .. versionadded:: 3.9 @@ -140,7 +147,7 @@ See also :ref:`Reflection `. Return the line number that *frame* is currently executing. -Frame Locals Proxies +Frame locals proxies ^^^^^^^^^^^^^^^^^^^^ .. versionadded:: 3.13 @@ -161,7 +168,52 @@ See :pep:`667` for more information. Return non-zero if *obj* is a frame :func:`locals` proxy. -Internal Frames + +Legacy local variable APIs +^^^^^^^^^^^^^^^^^^^^^^^^^^ + +These APIs are :term:`soft deprecated`. As of Python 3.13, they do nothing. +They exist solely for backwards compatibility. + + +.. c:function:: void PyFrame_LocalsToFast(PyFrameObject *f, int clear) + + Prior to Python 3.13, this function would copy the :attr:`~frame.f_locals` + attribute of *f* to the internal "fast" array of local variables, allowing + changes in frame objects to be visible to the interpreter. If *clear* was + true, this function would process variables that were unset in the locals + dictionary. + + .. soft-deprecated:: 3.13 + This function now does nothing. + + +.. c:function:: void PyFrame_FastToLocals(PyFrameObject *f) + + Prior to Python 3.13, this function would copy the internal "fast" array + of local variables (which is used by the interpreter) to the + :attr:`~frame.f_locals` attribute of *f*, allowing changes in local + variables to be visible to frame objects. + + .. soft-deprecated:: 3.13 + This function now does nothing. + + +.. c:function:: int PyFrame_FastToLocalsWithError(PyFrameObject *f) + + Prior to Python 3.13, this function was similar to + :c:func:`PyFrame_FastToLocals`, but would return ``0`` on success, and + ``-1`` with an exception set on failure. + + .. soft-deprecated:: 3.13 + This function now does nothing. + + +.. seealso:: + :pep:`667` + + +Internal frames ^^^^^^^^^^^^^^^ Unless using :pep:`523`, you will not need this. @@ -193,3 +245,39 @@ Unless using :pep:`523`, you will not need this. .. versionadded:: 3.12 +.. c:var:: const PyTypeObject *PyUnstable_ExecutableKinds + + An array of executable kinds (executor types) for frames, used for internal + debugging and tracing. + + Tools like debuggers and profilers can use this to identify the type of execution + context associated with a frame (such as to filter out internal frames). + The entries are indexed by the following constants: + + .. list-table:: + :header-rows: 1 + :widths: auto + + * - Constant + - Description + * - .. c:macro:: PyUnstable_EXECUTABLE_KIND_SKIP + - The frame is internal (For example: inlined) and should be skipped by tools. + * - .. c:macro:: PyUnstable_EXECUTABLE_KIND_PY_FUNCTION + - The frame corresponds to a standard Python function. + * - .. c:macro:: PyUnstable_EXECUTABLE_KIND_BUILTIN_FUNCTION + - The frame corresponds to a function defined in native code. + * - .. c:macro:: PyUnstable_EXECUTABLE_KIND_METHOD_DESCRIPTOR + - The frame corresponds to a method on a class instance. + + Note that reading the executable kind from a frame is currently only + possible with undocumented internal APIs. + + .. versionadded:: 3.13 + + +.. c:macro:: PyUnstable_EXECUTABLE_KINDS + + The number of entries in :c:data:`PyUnstable_ExecutableKinds`. + + .. versionadded:: 3.13 + diff --git a/Doc/c-api/function.rst b/Doc/c-api/function.rst index 58792edeed25e3..7908e4f8561aeb 100644 --- a/Doc/c-api/function.rst +++ b/Doc/c-api/function.rst @@ -95,6 +95,22 @@ There are a few functions specific to Python functions. .. versionadded:: 3.12 + +.. c:function:: PyObject* PyFunction_GetKwDefaults(PyObject *op) + + Return the keyword-only argument default values of the function object *op*. This can be a + dictionary of arguments or ``NULL``. + + +.. c:function:: int PyFunction_SetKwDefaults(PyObject *op, PyObject *defaults) + + Set the keyword-only argument default values of the function object *op*. + *defaults* must be a dictionary of keyword-only arguments or ``Py_None``. + + This function returns ``0`` on success, and returns ``-1`` with an exception + set on failure. + + .. c:function:: PyObject* PyFunction_GetClosure(PyObject *op) Return the closure associated with the function object *op*. This can be ``NULL`` @@ -123,6 +139,19 @@ There are a few functions specific to Python functions. Raises :exc:`SystemError` and returns ``-1`` on failure. +.. c:function:: PyObject *PyFunction_GET_CODE(PyObject *op) + PyObject *PyFunction_GET_GLOBALS(PyObject *op) + PyObject *PyFunction_GET_MODULE(PyObject *op) + PyObject *PyFunction_GET_DEFAULTS(PyObject *op) + PyObject *PyFunction_GET_KW_DEFAULTS(PyObject *op) + PyObject *PyFunction_GET_CLOSURE(PyObject *op) + PyObject *PyFunction_GET_ANNOTATIONS(PyObject *op) + + These functions are similar to their ``PyFunction_Get*`` counterparts, but + do not do type checking. Passing anything other than an instance of + :c:data:`PyFunction_Type` is undefined behavior. + + .. c:function:: int PyFunction_AddWatcher(PyFunction_WatchCallback callback) Register *callback* as a function watcher for the current interpreter. @@ -169,7 +198,7 @@ There are a few functions specific to Python functions. unpredictable effects, including infinite recursion. If *event* is ``PyFunction_EVENT_CREATE``, then the callback is invoked - after `func` has been fully initialized. Otherwise, the callback is invoked + after *func* has been fully initialized. Otherwise, the callback is invoked before the modification to *func* takes place, so the prior state of *func* can be inspected. The runtime is permitted to optimize away the creation of function objects when possible. In such cases no event will be emitted. diff --git a/Doc/c-api/gcsupport.rst b/Doc/c-api/gcsupport.rst index d1f0982b818931..fed795b1e8c963 100644 --- a/Doc/c-api/gcsupport.rst +++ b/Doc/c-api/gcsupport.rst @@ -57,11 +57,49 @@ rules: Analogous to :c:macro:`PyObject_New` but for container objects with the :c:macro:`Py_TPFLAGS_HAVE_GC` flag set. + Do not call this directly to allocate memory for an object; call the type's + :c:member:`~PyTypeObject.tp_alloc` slot instead. + + When populating a type's :c:member:`~PyTypeObject.tp_alloc` slot, + :c:func:`PyType_GenericAlloc` is preferred over a custom function that + simply calls this macro. + + Memory allocated by this macro must be freed with + :c:func:`PyObject_GC_Del` (usually called via the object's + :c:member:`~PyTypeObject.tp_free` slot). + + .. seealso:: + + * :c:func:`PyObject_GC_Del` + * :c:macro:`PyObject_New` + * :c:func:`PyType_GenericAlloc` + * :c:member:`~PyTypeObject.tp_alloc` + + .. c:macro:: PyObject_GC_NewVar(TYPE, typeobj, size) Analogous to :c:macro:`PyObject_NewVar` but for container objects with the :c:macro:`Py_TPFLAGS_HAVE_GC` flag set. + Do not call this directly to allocate memory for an object; call the type's + :c:member:`~PyTypeObject.tp_alloc` slot instead. + + When populating a type's :c:member:`~PyTypeObject.tp_alloc` slot, + :c:func:`PyType_GenericAlloc` is preferred over a custom function that + simply calls this macro. + + Memory allocated by this macro must be freed with + :c:func:`PyObject_GC_Del` (usually called via the object's + :c:member:`~PyTypeObject.tp_free` slot). + + .. seealso:: + + * :c:func:`PyObject_GC_Del` + * :c:macro:`PyObject_NewVar` + * :c:func:`PyType_GenericAlloc` + * :c:member:`~PyTypeObject.tp_alloc` + + .. c:function:: PyObject* PyUnstable_Object_GC_NewWithExtraData(PyTypeObject *type, size_t extra_size) Analogous to :c:macro:`PyObject_GC_New` but allocates *extra_size* @@ -73,6 +111,10 @@ rules: The extra data will be deallocated with the object, but otherwise it is not managed by Python. + Memory allocated by this function must be freed with + :c:func:`PyObject_GC_Del` (usually called via the object's + :c:member:`~PyTypeObject.tp_free` slot). + .. warning:: The function is marked as unstable because the final mechanism for reserving extra data after an instance is not yet decided. @@ -136,6 +178,21 @@ rules: Releases memory allocated to an object using :c:macro:`PyObject_GC_New` or :c:macro:`PyObject_GC_NewVar`. + Do not call this directly to free an object's memory; call the type's + :c:member:`~PyTypeObject.tp_free` slot instead. + + Do not use this for memory allocated by :c:macro:`PyObject_New`, + :c:macro:`PyObject_NewVar`, or related allocation functions; use + :c:func:`PyObject_Free` instead. + + .. seealso:: + + * :c:func:`PyObject_Free` is the non-GC equivalent of this function. + * :c:macro:`PyObject_GC_New` + * :c:macro:`PyObject_GC_NewVar` + * :c:func:`PyType_GenericAlloc` + * :c:member:`~PyTypeObject.tp_free` + .. c:function:: void PyObject_GC_UnTrack(void *op) @@ -175,14 +232,18 @@ The :c:member:`~PyTypeObject.tp_traverse` handler must have the following type: object argument. If *visit* returns a non-zero value that value should be returned immediately. + The traversal function must not have any side effects. Implementations + may not modify the reference counts of any Python objects nor create or + destroy any Python objects. + To simplify writing :c:member:`~PyTypeObject.tp_traverse` handlers, a :c:func:`Py_VISIT` macro is provided. In order to use this macro, the :c:member:`~PyTypeObject.tp_traverse` implementation must name its arguments exactly *visit* and *arg*: -.. c:function:: void Py_VISIT(PyObject *o) +.. c:macro:: Py_VISIT(o) - If *o* is not ``NULL``, call the *visit* callback, with arguments *o* + If the :c:expr:`PyObject *` *o* is not ``NULL``, call the *visit* callback, with arguments *o* and *arg*. If *visit* returns a non-zero value, then return it. Using this macro, :c:member:`~PyTypeObject.tp_traverse` handlers look like:: diff --git a/Doc/c-api/gen.rst b/Doc/c-api/gen.rst index 0eb5922f6da75f..8648d529170c82 100644 --- a/Doc/c-api/gen.rst +++ b/Doc/c-api/gen.rst @@ -35,12 +35,65 @@ than explicitly calling :c:func:`PyGen_New` or :c:func:`PyGen_NewWithQualName`. .. c:function:: PyObject* PyGen_New(PyFrameObject *frame) Create and return a new generator object based on the *frame* object. - A reference to *frame* is stolen by this function. The argument must not be - ``NULL``. + A reference to *frame* is ":term:`stolen `" by this function (even + on error). The argument must not be ``NULL``. .. c:function:: PyObject* PyGen_NewWithQualName(PyFrameObject *frame, PyObject *name, PyObject *qualname) Create and return a new generator object based on the *frame* object, with ``__name__`` and ``__qualname__`` set to *name* and *qualname*. - A reference to *frame* is stolen by this function. The *frame* argument + A reference to *frame* is ":term:`stolen `" by this function (even + on error). The *frame* argument must not be ``NULL``. + + +.. c:function:: PyCodeObject* PyGen_GetCode(PyGenObject *gen) + + Return a new :term:`strong reference` to the code object wrapped by *gen*. + This function always succeeds. + + +Asynchronous Generator Objects +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. seealso:: + :pep:`525` + +.. c:var:: PyTypeObject PyAsyncGen_Type + + The type object corresponding to asynchronous generator objects. This is + available as :class:`types.AsyncGeneratorType` in the Python layer. + + .. versionadded:: 3.6 + +.. c:function:: PyObject *PyAsyncGen_New(PyFrameObject *frame, PyObject *name, PyObject *qualname) + + Create a new asynchronous generator wrapping *frame*, with ``__name__`` and + ``__qualname__`` set to *name* and *qualname*. + *frame* is ":term:`stolen `" by this function (even on error) and must not be ``NULL``. + + On success, this function returns a :term:`strong reference` to the + new asynchronous generator. On failure, this function returns ``NULL`` + with an exception set. + + .. versionadded:: 3.6 + +.. c:function:: int PyAsyncGen_CheckExact(PyObject *op) + + Return true if *op* is an asynchronous generator object, false otherwise. + This function always succeeds. + + .. versionadded:: 3.6 + + +Deprecated API +^^^^^^^^^^^^^^ + +.. c:macro:: PyAsyncGenASend_CheckExact(op) + + This is an API that was included in Python's C API + by mistake. + + It is solely here for completeness; do not use this API. + + .. soft-deprecated:: 3.14 diff --git a/Doc/c-api/hash.rst b/Doc/c-api/hash.rst index 00f8cb887dc7eb..1ad712b0ce4f2b 100644 --- a/Doc/c-api/hash.rst +++ b/Doc/c-api/hash.rst @@ -11,47 +11,103 @@ See also the :c:member:`PyTypeObject.tp_hash` member and :ref:`numeric-hash`. .. versionadded:: 3.2 + .. c:type:: Py_uhash_t Hash value type: unsigned integer. .. versionadded:: 3.2 + +.. c:macro:: Py_HASH_ALGORITHM + + A numerical value indicating the algorithm for hashing of :class:`str`, + :class:`bytes`, and :class:`memoryview`. + + The algorithm name is exposed by :data:`sys.hash_info.algorithm`. + + .. versionadded:: 3.4 + + +.. c:macro:: Py_HASH_FNV + Py_HASH_SIPHASH24 + Py_HASH_SIPHASH13 + + Numerical values to compare to :c:macro:`Py_HASH_ALGORITHM` to determine + which algorithm is used for hashing. The hash algorithm can be configured + via the configure :option:`--with-hash-algorithm` option. + + .. versionadded:: 3.4 + Add :c:macro:`!Py_HASH_FNV` and :c:macro:`!Py_HASH_SIPHASH24`. + + .. versionadded:: 3.11 + Add :c:macro:`!Py_HASH_SIPHASH13`. + + +.. c:macro:: Py_HASH_CUTOFF + + Buffers of length in range ``[1, Py_HASH_CUTOFF)`` are hashed using DJBX33A + instead of the algorithm described by :c:macro:`Py_HASH_ALGORITHM`. + + - A :c:macro:`!Py_HASH_CUTOFF` of 0 disables the optimization. + - :c:macro:`!Py_HASH_CUTOFF` must be non-negative and less or equal than 7. + + 32-bit platforms should use a cutoff smaller than 64-bit platforms because + it is easier to create colliding strings. A cutoff of 7 on 64-bit platforms + and 5 on 32-bit platforms should provide a decent safety margin. + + This corresponds to the :data:`sys.hash_info.cutoff` constant. + + .. versionadded:: 3.4 + + .. c:macro:: PyHASH_MODULUS - The `Mersenne prime `_ ``P = 2**n -1``, used for numeric hash scheme. + The `Mersenne prime `_ ``P = 2**n -1``, + used for numeric hash scheme. + + This corresponds to the :data:`sys.hash_info.modulus` constant. .. versionadded:: 3.13 + .. c:macro:: PyHASH_BITS The exponent ``n`` of ``P`` in :c:macro:`PyHASH_MODULUS`. .. versionadded:: 3.13 + .. c:macro:: PyHASH_MULTIPLIER Prime multiplier used in string and various other hashes. .. versionadded:: 3.13 + .. c:macro:: PyHASH_INF The hash value returned for a positive infinity. + This corresponds to the :data:`sys.hash_info.inf` constant. + .. versionadded:: 3.13 + .. c:macro:: PyHASH_IMAG The multiplier used for the imaginary part of a complex number. + This corresponds to the :data:`sys.hash_info.imag` constant. + .. versionadded:: 3.13 + .. c:type:: PyHash_FuncDef Hash function definition used by :c:func:`PyHash_GetFuncDef`. - .. c::member:: Py_hash_t (*const hash)(const void *, Py_ssize_t) + .. c:member:: Py_hash_t (*const hash)(const void *, Py_ssize_t) Hash function. @@ -59,14 +115,20 @@ See also the :c:member:`PyTypeObject.tp_hash` member and :ref:`numeric-hash`. Hash function name (UTF-8 encoded string). + This corresponds to the :data:`sys.hash_info.algorithm` constant. + .. c:member:: const int hash_bits Internal size of the hash value in bits. + This corresponds to the :data:`sys.hash_info.hash_bits` constant. + .. c:member:: const int seed_bits Size of seed input in bits. + This corresponds to the :data:`sys.hash_info.seed_bits` constant. + .. versionadded:: 3.4 diff --git a/Doc/c-api/import.rst b/Doc/c-api/import.rst index 1cab3ce3061ec9..369e95dd02251b 100644 --- a/Doc/c-api/import.rst +++ b/Doc/c-api/import.rst @@ -327,6 +327,13 @@ Importing Modules initialization. +.. c:var:: struct _inittab *PyImport_Inittab + + The table of built-in modules used by Python initialization. Do not use this directly; + use :c:func:`PyImport_AppendInittab` and :c:func:`PyImport_ExtendInittab` + instead. + + .. c:function:: PyObject* PyImport_ImportModuleAttr(PyObject *mod_name, PyObject *attr_name) Import the module *mod_name* and get its attribute *attr_name*. diff --git a/Doc/c-api/index.rst b/Doc/c-api/index.rst index ba56b03c6ac8e7..eabe00f4004001 100644 --- a/Doc/c-api/index.rst +++ b/Doc/c-api/index.rst @@ -1,7 +1,7 @@ .. _c-api-index: ################################## - Python/C API Reference Manual + Python/C API reference manual ################################## This manual documents the API used by C and C++ programmers who want to write @@ -17,10 +17,16 @@ document the API functions in detail. veryhigh.rst refcounting.rst exceptions.rst + extension-modules.rst utilities.rst abstract.rst concrete.rst - init.rst + interp-lifecycle.rst + threads.rst + synchronization.rst + tls.rst + subinterpreters.rst + profiling.rst init_config.rst memory.rst objimpl.rst diff --git a/Doc/c-api/init.rst b/Doc/c-api/init.rst index 52f64a61006b74..e56c67f95348c7 100644 --- a/Doc/c-api/init.rst +++ b/Doc/c-api/init.rst @@ -1,2519 +1,13 @@ -.. highlight:: c +:orphan: +Initialization, finalization, and threads +========================================= -.. _initialization: +This page has been split up into the following: -***************************************** -Initialization, Finalization, and Threads -***************************************** - -See :ref:`Python Initialization Configuration ` for details -on how to configure the interpreter prior to initialization. - -.. _pre-init-safe: - -Before Python Initialization -============================ - -In an application embedding Python, the :c:func:`Py_Initialize` function must -be called before using any other Python/C API functions; with the exception of -a few functions and the :ref:`global configuration variables -`. - -The following functions can be safely called before Python is initialized: - -* Functions that initialize the interpreter: - - * :c:func:`Py_Initialize` - * :c:func:`Py_InitializeEx` - * :c:func:`Py_InitializeFromConfig` - * :c:func:`Py_BytesMain` - * :c:func:`Py_Main` - * the runtime pre-initialization functions covered in :ref:`init-config` - -* Configuration functions: - - * :c:func:`PyImport_AppendInittab` - * :c:func:`PyImport_ExtendInittab` - * :c:func:`!PyInitFrozenExtensions` - * :c:func:`PyMem_SetAllocator` - * :c:func:`PyMem_SetupDebugHooks` - * :c:func:`PyObject_SetArenaAllocator` - * :c:func:`Py_SetProgramName` - * :c:func:`Py_SetPythonHome` - * :c:func:`PySys_ResetWarnOptions` - * the configuration functions covered in :ref:`init-config` - -* Informative functions: - - * :c:func:`Py_IsInitialized` - * :c:func:`PyMem_GetAllocator` - * :c:func:`PyObject_GetArenaAllocator` - * :c:func:`Py_GetBuildInfo` - * :c:func:`Py_GetCompiler` - * :c:func:`Py_GetCopyright` - * :c:func:`Py_GetPlatform` - * :c:func:`Py_GetVersion` - * :c:func:`Py_IsInitialized` - -* Utilities: - - * :c:func:`Py_DecodeLocale` - * the status reporting and utility functions covered in :ref:`init-config` - -* Memory allocators: - - * :c:func:`PyMem_RawMalloc` - * :c:func:`PyMem_RawRealloc` - * :c:func:`PyMem_RawCalloc` - * :c:func:`PyMem_RawFree` - -* Synchronization: - - * :c:func:`PyMutex_Lock` - * :c:func:`PyMutex_Unlock` - -.. note:: - - Despite their apparent similarity to some of the functions listed above, - the following functions **should not be called** before the interpreter has - been initialized: :c:func:`Py_EncodeLocale`, :c:func:`Py_GetPath`, - :c:func:`Py_GetPrefix`, :c:func:`Py_GetExecPrefix`, - :c:func:`Py_GetProgramFullPath`, :c:func:`Py_GetPythonHome`, - :c:func:`Py_GetProgramName`, :c:func:`PyEval_InitThreads`, and - :c:func:`Py_RunMain`. - - -.. _global-conf-vars: - -Global configuration variables -============================== - -Python has variables for the global configuration to control different features -and options. By default, these flags are controlled by :ref:`command line -options `. - -When a flag is set by an option, the value of the flag is the number of times -that the option was set. For example, ``-b`` sets :c:data:`Py_BytesWarningFlag` -to 1 and ``-bb`` sets :c:data:`Py_BytesWarningFlag` to 2. - -.. c:var:: int Py_BytesWarningFlag - - This API is kept for backward compatibility: setting - :c:member:`PyConfig.bytes_warning` should be used instead, see :ref:`Python - Initialization Configuration `. - - Issue a warning when comparing :class:`bytes` or :class:`bytearray` with - :class:`str` or :class:`bytes` with :class:`int`. Issue an error if greater - or equal to ``2``. - - Set by the :option:`-b` option. - - .. deprecated-removed:: 3.12 3.15 - -.. c:var:: int Py_DebugFlag - - This API is kept for backward compatibility: setting - :c:member:`PyConfig.parser_debug` should be used instead, see :ref:`Python - Initialization Configuration `. - - Turn on parser debugging output (for expert only, depending on compilation - options). - - Set by the :option:`-d` option and the :envvar:`PYTHONDEBUG` environment - variable. - - .. deprecated-removed:: 3.12 3.15 - -.. c:var:: int Py_DontWriteBytecodeFlag - - This API is kept for backward compatibility: setting - :c:member:`PyConfig.write_bytecode` should be used instead, see :ref:`Python - Initialization Configuration `. - - If set to non-zero, Python won't try to write ``.pyc`` files on the - import of source modules. - - Set by the :option:`-B` option and the :envvar:`PYTHONDONTWRITEBYTECODE` - environment variable. - - .. deprecated-removed:: 3.12 3.15 - -.. c:var:: int Py_FrozenFlag - - This API is kept for backward compatibility: setting - :c:member:`PyConfig.pathconfig_warnings` should be used instead, see - :ref:`Python Initialization Configuration `. - - Suppress error messages when calculating the module search path in - :c:func:`Py_GetPath`. - - Private flag used by ``_freeze_module`` and ``frozenmain`` programs. - - .. deprecated-removed:: 3.12 3.15 - -.. c:var:: int Py_HashRandomizationFlag - - This API is kept for backward compatibility: setting - :c:member:`PyConfig.hash_seed` and :c:member:`PyConfig.use_hash_seed` should - be used instead, see :ref:`Python Initialization Configuration - `. - - Set to ``1`` if the :envvar:`PYTHONHASHSEED` environment variable is set to - a non-empty string. - - If the flag is non-zero, read the :envvar:`PYTHONHASHSEED` environment - variable to initialize the secret hash seed. - - .. deprecated-removed:: 3.12 3.15 - -.. c:var:: int Py_IgnoreEnvironmentFlag - - This API is kept for backward compatibility: setting - :c:member:`PyConfig.use_environment` should be used instead, see - :ref:`Python Initialization Configuration `. - - Ignore all :envvar:`!PYTHON*` environment variables, e.g. - :envvar:`PYTHONPATH` and :envvar:`PYTHONHOME`, that might be set. - - Set by the :option:`-E` and :option:`-I` options. - - .. deprecated-removed:: 3.12 3.15 - -.. c:var:: int Py_InspectFlag - - This API is kept for backward compatibility: setting - :c:member:`PyConfig.inspect` should be used instead, see - :ref:`Python Initialization Configuration `. - - When a script is passed as first argument or the :option:`-c` option is used, - enter interactive mode after executing the script or the command, even when - :data:`sys.stdin` does not appear to be a terminal. - - Set by the :option:`-i` option and the :envvar:`PYTHONINSPECT` environment - variable. - - .. deprecated-removed:: 3.12 3.15 - -.. c:var:: int Py_InteractiveFlag - - This API is kept for backward compatibility: setting - :c:member:`PyConfig.interactive` should be used instead, see - :ref:`Python Initialization Configuration `. - - Set by the :option:`-i` option. - - .. deprecated:: 3.12 - -.. c:var:: int Py_IsolatedFlag - - This API is kept for backward compatibility: setting - :c:member:`PyConfig.isolated` should be used instead, see - :ref:`Python Initialization Configuration `. - - Run Python in isolated mode. In isolated mode :data:`sys.path` contains - neither the script's directory nor the user's site-packages directory. - - Set by the :option:`-I` option. - - .. versionadded:: 3.4 - - .. deprecated-removed:: 3.12 3.15 - -.. c:var:: int Py_LegacyWindowsFSEncodingFlag - - This API is kept for backward compatibility: setting - :c:member:`PyPreConfig.legacy_windows_fs_encoding` should be used instead, see - :ref:`Python Initialization Configuration `. - - If the flag is non-zero, use the ``mbcs`` encoding with ``replace`` error - handler, instead of the UTF-8 encoding with ``surrogatepass`` error handler, - for the :term:`filesystem encoding and error handler`. - - Set to ``1`` if the :envvar:`PYTHONLEGACYWINDOWSFSENCODING` environment - variable is set to a non-empty string. - - See :pep:`529` for more details. - - .. availability:: Windows. - - .. deprecated-removed:: 3.12 3.15 - -.. c:var:: int Py_LegacyWindowsStdioFlag - - This API is kept for backward compatibility: setting - :c:member:`PyConfig.legacy_windows_stdio` should be used instead, see - :ref:`Python Initialization Configuration `. - - If the flag is non-zero, use :class:`io.FileIO` instead of - :class:`!io._WindowsConsoleIO` for :mod:`sys` standard streams. - - Set to ``1`` if the :envvar:`PYTHONLEGACYWINDOWSSTDIO` environment - variable is set to a non-empty string. - - See :pep:`528` for more details. - - .. availability:: Windows. - - .. deprecated-removed:: 3.12 3.15 - -.. c:var:: int Py_NoSiteFlag - - This API is kept for backward compatibility: setting - :c:member:`PyConfig.site_import` should be used instead, see - :ref:`Python Initialization Configuration `. - - Disable the import of the module :mod:`site` and the site-dependent - manipulations of :data:`sys.path` that it entails. Also disable these - manipulations if :mod:`site` is explicitly imported later (call - :func:`site.main` if you want them to be triggered). - - Set by the :option:`-S` option. - - .. deprecated-removed:: 3.12 3.15 - -.. c:var:: int Py_NoUserSiteDirectory - - This API is kept for backward compatibility: setting - :c:member:`PyConfig.user_site_directory` should be used instead, see - :ref:`Python Initialization Configuration `. - - Don't add the :data:`user site-packages directory ` to - :data:`sys.path`. - - Set by the :option:`-s` and :option:`-I` options, and the - :envvar:`PYTHONNOUSERSITE` environment variable. - - .. deprecated-removed:: 3.12 3.15 - -.. c:var:: int Py_OptimizeFlag - - This API is kept for backward compatibility: setting - :c:member:`PyConfig.optimization_level` should be used instead, see - :ref:`Python Initialization Configuration `. - - Set by the :option:`-O` option and the :envvar:`PYTHONOPTIMIZE` environment - variable. - - .. deprecated-removed:: 3.12 3.15 - -.. c:var:: int Py_QuietFlag - - This API is kept for backward compatibility: setting - :c:member:`PyConfig.quiet` should be used instead, see :ref:`Python - Initialization Configuration `. - - Don't display the copyright and version messages even in interactive mode. - - Set by the :option:`-q` option. - - .. versionadded:: 3.2 - - .. deprecated-removed:: 3.12 3.15 - -.. c:var:: int Py_UnbufferedStdioFlag - - This API is kept for backward compatibility: setting - :c:member:`PyConfig.buffered_stdio` should be used instead, see :ref:`Python - Initialization Configuration `. - - Force the stdout and stderr streams to be unbuffered. - - Set by the :option:`-u` option and the :envvar:`PYTHONUNBUFFERED` - environment variable. - - .. deprecated-removed:: 3.12 3.15 - -.. c:var:: int Py_VerboseFlag - - This API is kept for backward compatibility: setting - :c:member:`PyConfig.verbose` should be used instead, see :ref:`Python - Initialization Configuration `. - - Print a message each time a module is initialized, showing the place - (filename or built-in module) from which it is loaded. If greater or equal - to ``2``, print a message for each file that is checked for when - searching for a module. Also provides information on module cleanup at exit. - - Set by the :option:`-v` option and the :envvar:`PYTHONVERBOSE` environment - variable. - - .. deprecated-removed:: 3.12 3.15 - - -Initializing and finalizing the interpreter -=========================================== - - -.. c:function:: void Py_Initialize() - - .. index:: - single: PyEval_InitThreads() - single: modules (in module sys) - single: path (in module sys) - pair: module; builtins - pair: module; __main__ - pair: module; sys - triple: module; search; path - single: Py_FinalizeEx (C function) - - Initialize the Python interpreter. In an application embedding Python, - this should be called before using any other Python/C API functions; see - :ref:`Before Python Initialization ` for the few exceptions. - - This initializes the table of loaded modules (``sys.modules``), and creates - the fundamental modules :mod:`builtins`, :mod:`__main__` and :mod:`sys`. - It also initializes the module search path (``sys.path``). It does not set - ``sys.argv``; use the :ref:`Python Initialization Configuration ` - API for that. This is a no-op when called for a second time (without calling - :c:func:`Py_FinalizeEx` first). There is no return value; it is a fatal - error if the initialization fails. - - Use :c:func:`Py_InitializeFromConfig` to customize the - :ref:`Python Initialization Configuration `. - - .. note:: - On Windows, changes the console mode from ``O_TEXT`` to ``O_BINARY``, - which will also affect non-Python uses of the console using the C Runtime. - - -.. c:function:: void Py_InitializeEx(int initsigs) - - This function works like :c:func:`Py_Initialize` if *initsigs* is ``1``. If - *initsigs* is ``0``, it skips initialization registration of signal handlers, - which may be useful when CPython is embedded as part of a larger application. - - Use :c:func:`Py_InitializeFromConfig` to customize the - :ref:`Python Initialization Configuration `. - - -.. c:function:: PyStatus Py_InitializeFromConfig(const PyConfig *config) - - Initialize Python from *config* configuration, as described in - :ref:`init-from-config`. - - See the :ref:`init-config` section for details on pre-initializing the - interpreter, populating the runtime configuration structure, and querying - the returned status structure. - - -.. c:function:: int Py_IsInitialized() - - Return true (nonzero) when the Python interpreter has been initialized, false - (zero) if not. After :c:func:`Py_FinalizeEx` is called, this returns false until - :c:func:`Py_Initialize` is called again. - - -.. c:function:: int Py_IsFinalizing() - - Return true (non-zero) if the main Python interpreter is - :term:`shutting down `. Return false (zero) otherwise. - - .. versionadded:: 3.13 - - -.. c:function:: int Py_FinalizeEx() - - Undo all initializations made by :c:func:`Py_Initialize` and subsequent use of - Python/C API functions, and destroy all sub-interpreters (see - :c:func:`Py_NewInterpreter` below) that were created and not yet destroyed since - the last call to :c:func:`Py_Initialize`. This is a no-op when called for a second - time (without calling :c:func:`Py_Initialize` again first). - - Since this is the reverse of :c:func:`Py_Initialize`, it should be called - in the same thread with the same interpreter active. That means - the main thread and the main interpreter. - This should never be called while :c:func:`Py_RunMain` is running. - - Normally the return value is ``0``. - If there were errors during finalization (flushing buffered data), - ``-1`` is returned. - - Note that Python will do a best effort at freeing all memory allocated by the Python - interpreter. Therefore, any C-Extension should make sure to correctly clean up all - of the preveiously allocated PyObjects before using them in subsequent calls to - :c:func:`Py_Initialize`. Otherwise it could introduce vulnerabilities and incorrect - behavior. - - This function is provided for a number of reasons. An embedding application - might want to restart Python without having to restart the application itself. - An application that has loaded the Python interpreter from a dynamically - loadable library (or DLL) might want to free all memory allocated by Python - before unloading the DLL. During a hunt for memory leaks in an application a - developer might want to free all memory allocated by Python before exiting from - the application. - - **Bugs and caveats:** The destruction of modules and objects in modules is done - in random order; this may cause destructors (:meth:`~object.__del__` methods) to fail - when they depend on other objects (even functions) or modules. Dynamically - loaded extension modules loaded by Python are not unloaded. Small amounts of - memory allocated by the Python interpreter may not be freed (if you find a leak, - please report it). Memory tied up in circular references between objects is not - freed. Interned strings will all be deallocated regardless of their reference count. - Some memory allocated by extension modules may not be freed. Some extensions may not - work properly if their initialization routine is called more than once; this can - happen if an application calls :c:func:`Py_Initialize` and :c:func:`Py_FinalizeEx` - more than once. :c:func:`Py_FinalizeEx` must not be called recursively from - within itself. Therefore, it must not be called by any code that may be run - as part of the interpreter shutdown process, such as :py:mod:`atexit` - handlers, object finalizers, or any code that may be run while flushing the - stdout and stderr files. - - .. audit-event:: cpython._PySys_ClearAuditHooks "" c.Py_FinalizeEx - - .. versionadded:: 3.6 - - -.. c:function:: void Py_Finalize() - - This is a backwards-compatible version of :c:func:`Py_FinalizeEx` that - disregards the return value. - - -.. c:function:: int Py_BytesMain(int argc, char **argv) - - Similar to :c:func:`Py_Main` but *argv* is an array of bytes strings, - allowing the calling application to delegate the text decoding step to - the CPython runtime. - - .. versionadded:: 3.8 - - -.. c:function:: int Py_Main(int argc, wchar_t **argv) - - The main program for the standard interpreter, encapsulating a full - initialization/finalization cycle, as well as additional - behaviour to implement reading configurations settings from the environment - and command line, and then executing ``__main__`` in accordance with - :ref:`using-on-cmdline`. - - This is made available for programs which wish to support the full CPython - command line interface, rather than just embedding a Python runtime in a - larger application. - - The *argc* and *argv* parameters are similar to those which are passed to a - C program's :c:func:`main` function, except that the *argv* entries are first - converted to ``wchar_t`` using :c:func:`Py_DecodeLocale`. It is also - important to note that the argument list entries may be modified to point to - strings other than those passed in (however, the contents of the strings - pointed to by the argument list are not modified). - - The return value will be ``0`` if the interpreter exits normally (i.e., - without an exception), ``1`` if the interpreter exits due to an exception, - or ``2`` if the argument list does not represent a valid Python command - line. - - Note that if an otherwise unhandled :exc:`SystemExit` is raised, this - function will not return ``1``, but exit the process, as long as - ``Py_InspectFlag`` is not set. If ``Py_InspectFlag`` is set, execution will - drop into the interactive Python prompt, at which point a second otherwise - unhandled :exc:`SystemExit` will still exit the process, while any other - means of exiting will set the return value as described above. - - In terms of the CPython runtime configuration APIs documented in the - :ref:`runtime configuration ` section (and without accounting - for error handling), ``Py_Main`` is approximately equivalent to:: - - PyConfig config; - PyConfig_InitPythonConfig(&config); - PyConfig_SetArgv(&config, argc, argv); - Py_InitializeFromConfig(&config); - PyConfig_Clear(&config); - - Py_RunMain(); - - In normal usage, an embedding application will call this function - *instead* of calling :c:func:`Py_Initialize`, :c:func:`Py_InitializeEx` or - :c:func:`Py_InitializeFromConfig` directly, and all settings will be applied - as described elsewhere in this documentation. If this function is instead - called *after* a preceding runtime initialization API call, then exactly - which environmental and command line configuration settings will be updated - is version dependent (as it depends on which settings correctly support - being modified after they have already been set once when the runtime was - first initialized). - - -.. c:function:: int Py_RunMain(void) - - Executes the main module in a fully configured CPython runtime. - - Executes the command (:c:member:`PyConfig.run_command`), the script - (:c:member:`PyConfig.run_filename`) or the module - (:c:member:`PyConfig.run_module`) specified on the command line or in the - configuration. If none of these values are set, runs the interactive Python - prompt (REPL) using the ``__main__`` module's global namespace. - - If :c:member:`PyConfig.inspect` is not set (the default), the return value - will be ``0`` if the interpreter exits normally (that is, without raising - an exception), or ``1`` if the interpreter exits due to an exception. If an - otherwise unhandled :exc:`SystemExit` is raised, the function will immediately - exit the process instead of returning ``1``. - - If :c:member:`PyConfig.inspect` is set (such as when the :option:`-i` option - is used), rather than returning when the interpreter exits, execution will - instead resume in an interactive Python prompt (REPL) using the ``__main__`` - module's global namespace. If the interpreter exited with an exception, it - is immediately raised in the REPL session. The function return value is - then determined by the way the *REPL session* terminates: returning ``0`` - if the session terminates without raising an unhandled exception, exiting - immediately for an unhandled :exc:`SystemExit`, and returning ``1`` for - any other unhandled exception. - - This function always finalizes the Python interpreter regardless of whether - it returns a value or immediately exits the process due to an unhandled - :exc:`SystemExit` exception. - - See :ref:`Python Configuration ` for an example of a - customized Python that always runs in isolated mode using - :c:func:`Py_RunMain`. - -.. c:function:: int PyUnstable_AtExit(PyInterpreterState *interp, void (*func)(void *), void *data) - - Register an :mod:`atexit` callback for the target interpreter *interp*. - This is similar to :c:func:`Py_AtExit`, but takes an explicit interpreter and - data pointer for the callback. - - There must be an :term:`attached thread state` for *interp*. - - .. versionadded:: 3.13 - -Process-wide parameters -======================= - - -.. c:function:: void Py_SetProgramName(const wchar_t *name) - - .. index:: - single: Py_Initialize() - single: main() - single: Py_GetPath() - - This API is kept for backward compatibility: setting - :c:member:`PyConfig.program_name` should be used instead, see :ref:`Python - Initialization Configuration `. - - This function should be called before :c:func:`Py_Initialize` is called for - the first time, if it is called at all. It tells the interpreter the value - of the ``argv[0]`` argument to the :c:func:`main` function of the program - (converted to wide characters). - This is used by :c:func:`Py_GetPath` and some other functions below to find - the Python run-time libraries relative to the interpreter executable. The - default value is ``'python'``. The argument should point to a - zero-terminated wide character string in static storage whose contents will not - change for the duration of the program's execution. No code in the Python - interpreter will change the contents of this storage. - - Use :c:func:`Py_DecodeLocale` to decode a bytes string to get a - :c:expr:`wchar_t*` string. - - .. deprecated-removed:: 3.11 3.15 - - -.. c:function:: wchar_t* Py_GetProgramName() - - Return the program name set with :c:member:`PyConfig.program_name`, or the default. - The returned string points into static storage; the caller should not modify its - value. - - This function should not be called before :c:func:`Py_Initialize`, otherwise - it returns ``NULL``. - - .. versionchanged:: 3.10 - It now returns ``NULL`` if called before :c:func:`Py_Initialize`. - - .. deprecated-removed:: 3.13 3.15 - Use :c:func:`PyConfig_Get("executable") ` - (:data:`sys.executable`) instead. - - -.. c:function:: wchar_t* Py_GetPrefix() - - Return the *prefix* for installed platform-independent files. This is derived - through a number of complicated rules from the program name set with - :c:member:`PyConfig.program_name` and some environment variables; for example, if the - program name is ``'/usr/local/bin/python'``, the prefix is ``'/usr/local'``. The - returned string points into static storage; the caller should not modify its - value. This corresponds to the :makevar:`prefix` variable in the top-level - :file:`Makefile` and the :option:`--prefix` argument to the :program:`configure` - script at build time. The value is available to Python code as ``sys.base_prefix``. - It is only useful on Unix. See also the next function. - - This function should not be called before :c:func:`Py_Initialize`, otherwise - it returns ``NULL``. - - .. versionchanged:: 3.10 - It now returns ``NULL`` if called before :c:func:`Py_Initialize`. - - .. deprecated-removed:: 3.13 3.15 - Use :c:func:`PyConfig_Get("base_prefix") ` - (:data:`sys.base_prefix`) instead. Use :c:func:`PyConfig_Get("prefix") - ` (:data:`sys.prefix`) if :ref:`virtual environments - ` need to be handled. - - -.. c:function:: wchar_t* Py_GetExecPrefix() - - Return the *exec-prefix* for installed platform-*dependent* files. This is - derived through a number of complicated rules from the program name set with - :c:member:`PyConfig.program_name` and some environment variables; for example, if the - program name is ``'/usr/local/bin/python'``, the exec-prefix is - ``'/usr/local'``. The returned string points into static storage; the caller - should not modify its value. This corresponds to the :makevar:`exec_prefix` - variable in the top-level :file:`Makefile` and the ``--exec-prefix`` - argument to the :program:`configure` script at build time. The value is - available to Python code as ``sys.base_exec_prefix``. It is only useful on - Unix. - - Background: The exec-prefix differs from the prefix when platform dependent - files (such as executables and shared libraries) are installed in a different - directory tree. In a typical installation, platform dependent files may be - installed in the :file:`/usr/local/plat` subtree while platform independent may - be installed in :file:`/usr/local`. - - Generally speaking, a platform is a combination of hardware and software - families, e.g. Sparc machines running the Solaris 2.x operating system are - considered the same platform, but Intel machines running Solaris 2.x are another - platform, and Intel machines running Linux are yet another platform. Different - major revisions of the same operating system generally also form different - platforms. Non-Unix operating systems are a different story; the installation - strategies on those systems are so different that the prefix and exec-prefix are - meaningless, and set to the empty string. Note that compiled Python bytecode - files are platform independent (but not independent from the Python version by - which they were compiled!). - - System administrators will know how to configure the :program:`mount` or - :program:`automount` programs to share :file:`/usr/local` between platforms - while having :file:`/usr/local/plat` be a different filesystem for each - platform. - - This function should not be called before :c:func:`Py_Initialize`, otherwise - it returns ``NULL``. - - .. versionchanged:: 3.10 - It now returns ``NULL`` if called before :c:func:`Py_Initialize`. - - .. deprecated-removed:: 3.13 3.15 - Use :c:func:`PyConfig_Get("base_exec_prefix") ` - (:data:`sys.base_exec_prefix`) instead. Use - :c:func:`PyConfig_Get("exec_prefix") ` - (:data:`sys.exec_prefix`) if :ref:`virtual environments ` need - to be handled. - -.. c:function:: wchar_t* Py_GetProgramFullPath() - - .. index:: - single: executable (in module sys) - - Return the full program name of the Python executable; this is computed as a - side-effect of deriving the default module search path from the program name - (set by :c:member:`PyConfig.program_name`). The returned string points into - static storage; the caller should not modify its value. The value is available - to Python code as ``sys.executable``. - - This function should not be called before :c:func:`Py_Initialize`, otherwise - it returns ``NULL``. - - .. versionchanged:: 3.10 - It now returns ``NULL`` if called before :c:func:`Py_Initialize`. - - .. deprecated-removed:: 3.13 3.15 - Use :c:func:`PyConfig_Get("executable") ` - (:data:`sys.executable`) instead. - - -.. c:function:: wchar_t* Py_GetPath() - - .. index:: - triple: module; search; path - single: path (in module sys) - - Return the default module search path; this is computed from the program name - (set by :c:member:`PyConfig.program_name`) and some environment variables. - The returned string consists of a series of directory names separated by a - platform dependent delimiter character. The delimiter character is ``':'`` - on Unix and macOS, ``';'`` on Windows. The returned string points into - static storage; the caller should not modify its value. The list - :data:`sys.path` is initialized with this value on interpreter startup; it - can be (and usually is) modified later to change the search path for loading - modules. - - This function should not be called before :c:func:`Py_Initialize`, otherwise - it returns ``NULL``. - - .. XXX should give the exact rules - - .. versionchanged:: 3.10 - It now returns ``NULL`` if called before :c:func:`Py_Initialize`. - - .. deprecated-removed:: 3.13 3.15 - Use :c:func:`PyConfig_Get("module_search_paths") ` - (:data:`sys.path`) instead. - -.. c:function:: const char* Py_GetVersion() - - Return the version of this Python interpreter. This is a string that looks - something like :: - - "3.0a5+ (py3k:63103M, May 12 2008, 00:53:55) \n[GCC 4.2.3]" - - .. index:: single: version (in module sys) - - The first word (up to the first space character) is the current Python version; - the first characters are the major and minor version separated by a - period. The returned string points into static storage; the caller should not - modify its value. The value is available to Python code as :data:`sys.version`. - - See also the :c:var:`Py_Version` constant. - - -.. c:function:: const char* Py_GetPlatform() - - .. index:: single: platform (in module sys) - - Return the platform identifier for the current platform. On Unix, this is - formed from the "official" name of the operating system, converted to lower - case, followed by the major revision number; e.g., for Solaris 2.x, which is - also known as SunOS 5.x, the value is ``'sunos5'``. On macOS, it is - ``'darwin'``. On Windows, it is ``'win'``. The returned string points into - static storage; the caller should not modify its value. The value is available - to Python code as ``sys.platform``. - - -.. c:function:: const char* Py_GetCopyright() - - Return the official copyright string for the current Python version, for example - - ``'Copyright 1991-1995 Stichting Mathematisch Centrum, Amsterdam'`` - - .. index:: single: copyright (in module sys) - - The returned string points into static storage; the caller should not modify its - value. The value is available to Python code as ``sys.copyright``. - - -.. c:function:: const char* Py_GetCompiler() - - Return an indication of the compiler used to build the current Python version, - in square brackets, for example:: - - "[GCC 2.7.2.2]" - - .. index:: single: version (in module sys) - - The returned string points into static storage; the caller should not modify its - value. The value is available to Python code as part of the variable - ``sys.version``. - - -.. c:function:: const char* Py_GetBuildInfo() - - Return information about the sequence number and build date and time of the - current Python interpreter instance, for example :: - - "#67, Aug 1 1997, 22:34:28" - - .. index:: single: version (in module sys) - - The returned string points into static storage; the caller should not modify its - value. The value is available to Python code as part of the variable - ``sys.version``. - - -.. c:function:: void PySys_SetArgvEx(int argc, wchar_t **argv, int updatepath) - - .. index:: - single: main() - single: Py_FatalError() - single: argv (in module sys) - - This API is kept for backward compatibility: setting - :c:member:`PyConfig.argv`, :c:member:`PyConfig.parse_argv` and - :c:member:`PyConfig.safe_path` should be used instead, see :ref:`Python - Initialization Configuration `. - - Set :data:`sys.argv` based on *argc* and *argv*. These parameters are - similar to those passed to the program's :c:func:`main` function with the - difference that the first entry should refer to the script file to be - executed rather than the executable hosting the Python interpreter. If there - isn't a script that will be run, the first entry in *argv* can be an empty - string. If this function fails to initialize :data:`sys.argv`, a fatal - condition is signalled using :c:func:`Py_FatalError`. - - If *updatepath* is zero, this is all the function does. If *updatepath* - is non-zero, the function also modifies :data:`sys.path` according to the - following algorithm: - - - If the name of an existing script is passed in ``argv[0]``, the absolute - path of the directory where the script is located is prepended to - :data:`sys.path`. - - Otherwise (that is, if *argc* is ``0`` or ``argv[0]`` doesn't point - to an existing file name), an empty string is prepended to - :data:`sys.path`, which is the same as prepending the current working - directory (``"."``). - - Use :c:func:`Py_DecodeLocale` to decode a bytes string to get a - :c:expr:`wchar_t*` string. - - See also :c:member:`PyConfig.orig_argv` and :c:member:`PyConfig.argv` - members of the :ref:`Python Initialization Configuration `. - - .. note:: - It is recommended that applications embedding the Python interpreter - for purposes other than executing a single script pass ``0`` as *updatepath*, - and update :data:`sys.path` themselves if desired. - See :cve:`2008-5983`. - - On versions before 3.1.3, you can achieve the same effect by manually - popping the first :data:`sys.path` element after having called - :c:func:`PySys_SetArgv`, for example using:: - - PyRun_SimpleString("import sys; sys.path.pop(0)\n"); - - .. versionadded:: 3.1.3 - - .. XXX impl. doesn't seem consistent in allowing ``0``/``NULL`` for the params; - check w/ Guido. - - .. deprecated-removed:: 3.11 3.15 - - -.. c:function:: void PySys_SetArgv(int argc, wchar_t **argv) - - This API is kept for backward compatibility: setting - :c:member:`PyConfig.argv` and :c:member:`PyConfig.parse_argv` should be used - instead, see :ref:`Python Initialization Configuration `. - - This function works like :c:func:`PySys_SetArgvEx` with *updatepath* set - to ``1`` unless the :program:`python` interpreter was started with the - :option:`-I`. - - Use :c:func:`Py_DecodeLocale` to decode a bytes string to get a - :c:expr:`wchar_t*` string. - - See also :c:member:`PyConfig.orig_argv` and :c:member:`PyConfig.argv` - members of the :ref:`Python Initialization Configuration `. - - .. versionchanged:: 3.4 The *updatepath* value depends on :option:`-I`. - - .. deprecated-removed:: 3.11 3.15 - - -.. c:function:: void Py_SetPythonHome(const wchar_t *home) - - This API is kept for backward compatibility: setting - :c:member:`PyConfig.home` should be used instead, see :ref:`Python - Initialization Configuration `. - - Set the default "home" directory, that is, the location of the standard - Python libraries. See :envvar:`PYTHONHOME` for the meaning of the - argument string. - - The argument should point to a zero-terminated character string in static - storage whose contents will not change for the duration of the program's - execution. No code in the Python interpreter will change the contents of - this storage. - - Use :c:func:`Py_DecodeLocale` to decode a bytes string to get a - :c:expr:`wchar_t*` string. - - .. deprecated-removed:: 3.11 3.15 - - -.. c:function:: wchar_t* Py_GetPythonHome() - - Return the default "home", that is, the value set by - :c:member:`PyConfig.home`, or the value of the :envvar:`PYTHONHOME` - environment variable if it is set. - - This function should not be called before :c:func:`Py_Initialize`, otherwise - it returns ``NULL``. - - .. versionchanged:: 3.10 - It now returns ``NULL`` if called before :c:func:`Py_Initialize`. - - .. deprecated-removed:: 3.13 3.15 - Use :c:func:`PyConfig_Get("home") ` or the - :envvar:`PYTHONHOME` environment variable instead. - - -.. _threads: - -Thread State and the Global Interpreter Lock -============================================ - -.. index:: - single: global interpreter lock - single: interpreter lock - single: lock, interpreter - -Unless on a :term:`free-threaded ` build of :term:`CPython`, -the Python interpreter is not fully thread-safe. In order to support -multi-threaded Python programs, there's a global lock, called the :term:`global -interpreter lock` or :term:`GIL`, that must be held by the current thread before -it can safely access Python objects. Without the lock, even the simplest -operations could cause problems in a multi-threaded program: for example, when -two threads simultaneously increment the reference count of the same object, the -reference count could end up being incremented only once instead of twice. - -.. index:: single: setswitchinterval (in module sys) - -Therefore, the rule exists that only the thread that has acquired the -:term:`GIL` may operate on Python objects or call Python/C API functions. -In order to emulate concurrency of execution, the interpreter regularly -tries to switch threads (see :func:`sys.setswitchinterval`). The lock is also -released around potentially blocking I/O operations like reading or writing -a file, so that other Python threads can run in the meantime. - -.. index:: - single: PyThreadState (C type) - -The Python interpreter keeps some thread-specific bookkeeping information -inside a data structure called :c:type:`PyThreadState`, known as a :term:`thread state`. -Each OS thread has a thread-local pointer to a :c:type:`PyThreadState`; a thread state -referenced by this pointer is considered to be :term:`attached `. - -A thread can only have one :term:`attached thread state` at a time. An attached -thread state is typically analogous with holding the :term:`GIL`, except on -:term:`free-threaded ` builds. On builds with the :term:`GIL` enabled, -:term:`attaching ` a thread state will block until the :term:`GIL` -can be acquired. However, even on builds with the :term:`GIL` disabled, it is still required -to have an attached thread state to call most of the C API. - -In general, there will always be an :term:`attached thread state` when using Python's C API. -Only in some specific cases (such as in a :c:macro:`Py_BEGIN_ALLOW_THREADS` block) will the -thread not have an attached thread state. If uncertain, check if :c:func:`PyThreadState_GetUnchecked` returns -``NULL``. - -Detaching the thread state from extension code ----------------------------------------------- - -Most extension code manipulating the :term:`thread state` has the following simple -structure:: - - Save the thread state in a local variable. - ... Do some blocking I/O operation ... - Restore the thread state from the local variable. - -This is so common that a pair of macros exists to simplify it:: - - Py_BEGIN_ALLOW_THREADS - ... Do some blocking I/O operation ... - Py_END_ALLOW_THREADS - -.. index:: - single: Py_BEGIN_ALLOW_THREADS (C macro) - single: Py_END_ALLOW_THREADS (C macro) - -The :c:macro:`Py_BEGIN_ALLOW_THREADS` macro opens a new block and declares a -hidden local variable; the :c:macro:`Py_END_ALLOW_THREADS` macro closes the -block. - -The block above expands to the following code:: - - PyThreadState *_save; - - _save = PyEval_SaveThread(); - ... Do some blocking I/O operation ... - PyEval_RestoreThread(_save); - -.. index:: - single: PyEval_RestoreThread (C function) - single: PyEval_SaveThread (C function) - -Here is how these functions work: - -The :term:`attached thread state` holds the :term:`GIL` for the entire interpreter. When detaching -the :term:`attached thread state`, the :term:`GIL` is released, allowing other threads to attach -a thread state to their own thread, thus getting the :term:`GIL` and can start executing. -The pointer to the prior :term:`attached thread state` is stored as a local variable. -Upon reaching :c:macro:`Py_END_ALLOW_THREADS`, the thread state that was -previously :term:`attached ` is passed to :c:func:`PyEval_RestoreThread`. -This function will block until another releases its :term:`thread state `, -thus allowing the old :term:`thread state ` to get re-attached and the -C API can be called again. - -For :term:`free-threaded ` builds, the :term:`GIL` is normally -out of the question, but detaching the :term:`thread state ` is still required -for blocking I/O and long operations. The difference is that threads don't have to wait for the :term:`GIL` -to be released to attach their thread state, allowing true multi-core parallelism. - -.. note:: - Calling system I/O functions is the most common use case for detaching - the :term:`thread state `, but it can also be useful before calling - long-running computations which don't need access to Python objects, such - as compression or cryptographic functions operating over memory buffers. - For example, the standard :mod:`zlib` and :mod:`hashlib` modules detach the - :term:`thread state ` when compressing or hashing data. - - -.. _gilstate: - -Non-Python created threads --------------------------- - -When threads are created using the dedicated Python APIs (such as the -:mod:`threading` module), a thread state is automatically associated to them -and the code showed above is therefore correct. However, when threads are -created from C (for example by a third-party library with its own thread -management), they don't hold the :term:`GIL`, because they don't have an -:term:`attached thread state`. - -If you need to call Python code from these threads (often this will be part -of a callback API provided by the aforementioned third-party library), -you must first register these threads with the interpreter by -creating an :term:`attached thread state` before you can start using the Python/C -API. When you are done, you should detach the :term:`thread state `, and -finally free it. - -The :c:func:`PyGILState_Ensure` and :c:func:`PyGILState_Release` functions do -all of the above automatically. The typical idiom for calling into Python -from a C thread is:: - - PyGILState_STATE gstate; - gstate = PyGILState_Ensure(); - - /* Perform Python actions here. */ - result = CallSomeFunction(); - /* evaluate result or handle exception */ - - /* Release the thread. No Python API allowed beyond this point. */ - PyGILState_Release(gstate); - -Note that the ``PyGILState_*`` functions assume there is only one global -interpreter (created automatically by :c:func:`Py_Initialize`). Python -supports the creation of additional interpreters (using -:c:func:`Py_NewInterpreter`), but mixing multiple interpreters and the -``PyGILState_*`` API is unsupported. - - -.. _fork-and-threads: - -Cautions about fork() ---------------------- - -Another important thing to note about threads is their behaviour in the face -of the C :c:func:`fork` call. On most systems with :c:func:`fork`, after a -process forks only the thread that issued the fork will exist. This has a -concrete impact both on how locks must be handled and on all stored state -in CPython's runtime. - -The fact that only the "current" thread remains -means any locks held by other threads will never be released. Python solves -this for :func:`os.fork` by acquiring the locks it uses internally before -the fork, and releasing them afterwards. In addition, it resets any -:ref:`lock-objects` in the child. When extending or embedding Python, there -is no way to inform Python of additional (non-Python) locks that need to be -acquired before or reset after a fork. OS facilities such as -:c:func:`!pthread_atfork` would need to be used to accomplish the same thing. -Additionally, when extending or embedding Python, calling :c:func:`fork` -directly rather than through :func:`os.fork` (and returning to or calling -into Python) may result in a deadlock by one of Python's internal locks -being held by a thread that is defunct after the fork. -:c:func:`PyOS_AfterFork_Child` tries to reset the necessary locks, but is not -always able to. - -The fact that all other threads go away also means that CPython's -runtime state there must be cleaned up properly, which :func:`os.fork` -does. This means finalizing all other :c:type:`PyThreadState` objects -belonging to the current interpreter and all other -:c:type:`PyInterpreterState` objects. Due to this and the special -nature of the :ref:`"main" interpreter `, -:c:func:`fork` should only be called in that interpreter's "main" -thread, where the CPython global runtime was originally initialized. -The only exception is if :c:func:`exec` will be called immediately -after. - -.. _cautions-regarding-runtime-finalization: - -Cautions regarding runtime finalization ---------------------------------------- - -In the late stage of :term:`interpreter shutdown`, after attempting to wait for -non-daemon threads to exit (though this can be interrupted by -:class:`KeyboardInterrupt`) and running the :mod:`atexit` functions, the runtime -is marked as *finalizing*: :c:func:`Py_IsFinalizing` and -:func:`sys.is_finalizing` return true. At this point, only the *finalization -thread* that initiated finalization (typically the main thread) is allowed to -acquire the :term:`GIL`. - -If any thread, other than the finalization thread, attempts to attach a :term:`thread state` -during finalization, either explicitly or -implicitly, the thread enters **a permanently blocked state** -where it remains until the program exits. In most cases this is harmless, but this can result -in deadlock if a later stage of finalization attempts to acquire a lock owned by the -blocked thread, or otherwise waits on the blocked thread. - -Gross? Yes. This prevents random crashes and/or unexpectedly skipped C++ -finalizations further up the call stack when such threads were forcibly exited -here in CPython 3.13 and earlier. The CPython runtime :term:`thread state` C APIs -have never had any error reporting or handling expectations at :term:`thread state` -attachment time that would've allowed for graceful exit from this situation. Changing that -would require new stable C APIs and rewriting the majority of C code in the -CPython ecosystem to use those with error handling. - - -High-level API --------------- - -These are the most commonly used types and functions when writing C extension -code, or when embedding the Python interpreter: - -.. c:type:: PyInterpreterState - - This data structure represents the state shared by a number of cooperating - threads. Threads belonging to the same interpreter share their module - administration and a few other internal items. There are no public members in - this structure. - - Threads belonging to different interpreters initially share nothing, except - process state like available memory, open file descriptors and such. The global - interpreter lock is also shared by all threads, regardless of to which - interpreter they belong. - - -.. c:type:: PyThreadState - - This data structure represents the state of a single thread. The only public - data member is: - - .. c:member:: PyInterpreterState *interp - - This thread's interpreter state. - - -.. c:function:: void PyEval_InitThreads() - - .. index:: - single: PyEval_AcquireThread() - single: PyEval_ReleaseThread() - single: PyEval_SaveThread() - single: PyEval_RestoreThread() - - Deprecated function which does nothing. - - In Python 3.6 and older, this function created the GIL if it didn't exist. - - .. versionchanged:: 3.9 - The function now does nothing. - - .. versionchanged:: 3.7 - This function is now called by :c:func:`Py_Initialize()`, so you don't - have to call it yourself anymore. - - .. versionchanged:: 3.2 - This function cannot be called before :c:func:`Py_Initialize()` anymore. - - .. deprecated:: 3.9 - - .. index:: pair: module; _thread - - -.. c:function:: PyThreadState* PyEval_SaveThread() - - Detach the :term:`attached thread state` and return it. - The thread will have no :term:`thread state` upon returning. - - -.. c:function:: void PyEval_RestoreThread(PyThreadState *tstate) - - Set the :term:`attached thread state` to *tstate*. - The passed :term:`thread state` **should not** be :term:`attached `, - otherwise deadlock ensues. *tstate* will be attached upon returning. - - .. note:: - Calling this function from a thread when the runtime is finalizing will - hang the thread until the program exits, even if the thread was not - created by Python. Refer to - :ref:`cautions-regarding-runtime-finalization` for more details. - - .. versionchanged:: 3.14 - Hangs the current thread, rather than terminating it, if called while the - interpreter is finalizing. - -.. c:function:: PyThreadState* PyThreadState_Get() - - Return the :term:`attached thread state`. If the thread has no attached - thread state, (such as when inside of :c:macro:`Py_BEGIN_ALLOW_THREADS` - block), then this issues a fatal error (so that the caller needn't check - for ``NULL``). - - See also :c:func:`PyThreadState_GetUnchecked`. - -.. c:function:: PyThreadState* PyThreadState_GetUnchecked() - - Similar to :c:func:`PyThreadState_Get`, but don't kill the process with a - fatal error if it is NULL. The caller is responsible to check if the result - is NULL. - - .. versionadded:: 3.13 - In Python 3.5 to 3.12, the function was private and known as - ``_PyThreadState_UncheckedGet()``. - - -.. c:function:: PyThreadState* PyThreadState_Swap(PyThreadState *tstate) - - Set the :term:`attached thread state` to *tstate*, and return the - :term:`thread state` that was attached prior to calling. - - This function is safe to call without an :term:`attached thread state`; it - will simply return ``NULL`` indicating that there was no prior thread state. - - .. seealso: - :c:func:`PyEval_ReleaseThread` - - -The following functions use thread-local storage, and are not compatible -with sub-interpreters: - -.. c:function:: PyGILState_STATE PyGILState_Ensure() - - Ensure that the current thread is ready to call the Python C API regardless - of the current state of Python, or of the :term:`attached thread state`. This may - be called as many times as desired by a thread as long as each call is - matched with a call to :c:func:`PyGILState_Release`. In general, other - thread-related APIs may be used between :c:func:`PyGILState_Ensure` and - :c:func:`PyGILState_Release` calls as long as the thread state is restored to - its previous state before the Release(). For example, normal usage of the - :c:macro:`Py_BEGIN_ALLOW_THREADS` and :c:macro:`Py_END_ALLOW_THREADS` macros is - acceptable. - - The return value is an opaque "handle" to the :term:`attached thread state` when - :c:func:`PyGILState_Ensure` was called, and must be passed to - :c:func:`PyGILState_Release` to ensure Python is left in the same state. Even - though recursive calls are allowed, these handles *cannot* be shared - each - unique call to :c:func:`PyGILState_Ensure` must save the handle for its call - to :c:func:`PyGILState_Release`. - - When the function returns, there will be an :term:`attached thread state` - and the thread will be able to call arbitrary Python code. Failure is a fatal error. - - .. note:: - Calling this function from a thread when the runtime is finalizing will - hang the thread until the program exits, even if the thread was not - created by Python. Refer to - :ref:`cautions-regarding-runtime-finalization` for more details. - - .. versionchanged:: 3.14 - Hangs the current thread, rather than terminating it, if called while the - interpreter is finalizing. - -.. c:function:: void PyGILState_Release(PyGILState_STATE) - - Release any resources previously acquired. After this call, Python's state will - be the same as it was prior to the corresponding :c:func:`PyGILState_Ensure` call - (but generally this state will be unknown to the caller, hence the use of the - GILState API). - - Every call to :c:func:`PyGILState_Ensure` must be matched by a call to - :c:func:`PyGILState_Release` on the same thread. - - -.. c:function:: PyThreadState* PyGILState_GetThisThreadState() - - Get the :term:`attached thread state` for this thread. May return ``NULL`` if no - GILState API has been used on the current thread. Note that the main thread - always has such a thread-state, even if no auto-thread-state call has been - made on the main thread. This is mainly a helper/diagnostic function. - - .. seealso: :c:func:`PyThreadState_Get`` - - -.. c:function:: int PyGILState_Check() - - Return ``1`` if the current thread is holding the :term:`GIL` and ``0`` otherwise. - This function can be called from any thread at any time. - Only if it has had its Python thread state initialized and currently is - holding the :term:`GIL` will it return ``1``. - This is mainly a helper/diagnostic function. It can be useful - for example in callback contexts or memory allocation functions when - knowing that the :term:`GIL` is locked can allow the caller to perform sensitive - actions or otherwise behave differently. - - .. versionadded:: 3.4 - - -The following macros are normally used without a trailing semicolon; look for -example usage in the Python source distribution. - - -.. c:macro:: Py_BEGIN_ALLOW_THREADS - - This macro expands to ``{ PyThreadState *_save; _save = PyEval_SaveThread();``. - Note that it contains an opening brace; it must be matched with a following - :c:macro:`Py_END_ALLOW_THREADS` macro. See above for further discussion of this - macro. - - -.. c:macro:: Py_END_ALLOW_THREADS - - This macro expands to ``PyEval_RestoreThread(_save); }``. Note that it contains - a closing brace; it must be matched with an earlier - :c:macro:`Py_BEGIN_ALLOW_THREADS` macro. See above for further discussion of - this macro. - - -.. c:macro:: Py_BLOCK_THREADS - - This macro expands to ``PyEval_RestoreThread(_save);``: it is equivalent to - :c:macro:`Py_END_ALLOW_THREADS` without the closing brace. - - -.. c:macro:: Py_UNBLOCK_THREADS - - This macro expands to ``_save = PyEval_SaveThread();``: it is equivalent to - :c:macro:`Py_BEGIN_ALLOW_THREADS` without the opening brace and variable - declaration. - - -Low-level API -------------- - -All of the following functions must be called after :c:func:`Py_Initialize`. - -.. versionchanged:: 3.7 - :c:func:`Py_Initialize()` now initializes the :term:`GIL` - and sets an :term:`attached thread state`. - - -.. c:function:: PyInterpreterState* PyInterpreterState_New() - - Create a new interpreter state object. An :term:`attached thread state` is not needed, - but may optionally exist if it is necessary to serialize calls to this - function. - - .. audit-event:: cpython.PyInterpreterState_New "" c.PyInterpreterState_New - - -.. c:function:: void PyInterpreterState_Clear(PyInterpreterState *interp) - - Reset all information in an interpreter state object. There must be - an :term:`attached thread state` for the the interpreter. - - .. audit-event:: cpython.PyInterpreterState_Clear "" c.PyInterpreterState_Clear - - -.. c:function:: void PyInterpreterState_Delete(PyInterpreterState *interp) - - Destroy an interpreter state object. There **should not** be an - :term:`attached thread state` for the target interpreter. The interpreter - state must have been reset with a previous call to :c:func:`PyInterpreterState_Clear`. - - -.. c:function:: PyThreadState* PyThreadState_New(PyInterpreterState *interp) - - Create a new thread state object belonging to the given interpreter object. - An :term:`attached thread state` is not needed. - -.. c:function:: void PyThreadState_Clear(PyThreadState *tstate) - - Reset all information in a :term:`thread state` object. *tstate* - must be :term:`attached ` - - .. versionchanged:: 3.9 - This function now calls the :c:member:`PyThreadState.on_delete` callback. - Previously, that happened in :c:func:`PyThreadState_Delete`. - - .. versionchanged:: 3.13 - The :c:member:`PyThreadState.on_delete` callback was removed. - - -.. c:function:: void PyThreadState_Delete(PyThreadState *tstate) - - Destroy a :term:`thread state` object. *tstate* should not - be :term:`attached ` to any thread. - *tstate* must have been reset with a previous call to - :c:func:`PyThreadState_Clear`. - - -.. c:function:: void PyThreadState_DeleteCurrent(void) - - Detach the :term:`attached thread state` (which must have been reset - with a previous call to :c:func:`PyThreadState_Clear`) and then destroy it. - - No :term:`thread state` will be :term:`attached ` upon - returning. - -.. c:function:: PyFrameObject* PyThreadState_GetFrame(PyThreadState *tstate) - - Get the current frame of the Python thread state *tstate*. - - Return a :term:`strong reference`. Return ``NULL`` if no frame is currently - executing. - - See also :c:func:`PyEval_GetFrame`. - - *tstate* must not be ``NULL``, and must be :term:`attached `. - - .. versionadded:: 3.9 - - -.. c:function:: uint64_t PyThreadState_GetID(PyThreadState *tstate) - - Get the unique :term:`thread state` identifier of the Python thread state *tstate*. - - *tstate* must not be ``NULL``, and must be :term:`attached `. - - .. versionadded:: 3.9 - - -.. c:function:: PyInterpreterState* PyThreadState_GetInterpreter(PyThreadState *tstate) - - Get the interpreter of the Python thread state *tstate*. - - *tstate* must not be ``NULL``, and must be :term:`attached `. - - .. versionadded:: 3.9 - - -.. c:function:: void PyThreadState_EnterTracing(PyThreadState *tstate) - - Suspend tracing and profiling in the Python thread state *tstate*. - - Resume them using the :c:func:`PyThreadState_LeaveTracing` function. - - .. versionadded:: 3.11 - - -.. c:function:: void PyThreadState_LeaveTracing(PyThreadState *tstate) - - Resume tracing and profiling in the Python thread state *tstate* suspended - by the :c:func:`PyThreadState_EnterTracing` function. - - See also :c:func:`PyEval_SetTrace` and :c:func:`PyEval_SetProfile` - functions. - - .. versionadded:: 3.11 - - -.. c:function:: PyInterpreterState* PyInterpreterState_Get(void) - - Get the current interpreter. - - Issue a fatal error if there no :term:`attached thread state`. - It cannot return NULL. - - .. versionadded:: 3.9 - - -.. c:function:: int64_t PyInterpreterState_GetID(PyInterpreterState *interp) - - Return the interpreter's unique ID. If there was any error in doing - so then ``-1`` is returned and an error is set. - - The caller must have an :term:`attached thread state`. - - .. versionadded:: 3.7 - - -.. c:function:: PyObject* PyInterpreterState_GetDict(PyInterpreterState *interp) - - Return a dictionary in which interpreter-specific data may be stored. - If this function returns ``NULL`` then no exception has been raised and - the caller should assume no interpreter-specific dict is available. - - This is not a replacement for :c:func:`PyModule_GetState()`, which - extensions should use to store interpreter-specific state information. - - .. versionadded:: 3.8 - - -.. c:type:: PyObject* (*_PyFrameEvalFunction)(PyThreadState *tstate, _PyInterpreterFrame *frame, int throwflag) - - Type of a frame evaluation function. - - The *throwflag* parameter is used by the ``throw()`` method of generators: - if non-zero, handle the current exception. - - .. versionchanged:: 3.9 - The function now takes a *tstate* parameter. - - .. versionchanged:: 3.11 - The *frame* parameter changed from ``PyFrameObject*`` to ``_PyInterpreterFrame*``. - -.. c:function:: _PyFrameEvalFunction _PyInterpreterState_GetEvalFrameFunc(PyInterpreterState *interp) - - Get the frame evaluation function. - - See the :pep:`523` "Adding a frame evaluation API to CPython". - - .. versionadded:: 3.9 - -.. c:function:: void _PyInterpreterState_SetEvalFrameFunc(PyInterpreterState *interp, _PyFrameEvalFunction eval_frame) - - Set the frame evaluation function. - - See the :pep:`523` "Adding a frame evaluation API to CPython". - - .. versionadded:: 3.9 - - -.. c:function:: PyObject* PyThreadState_GetDict() - - Return a dictionary in which extensions can store thread-specific state - information. Each extension should use a unique key to use to store state in - the dictionary. It is okay to call this function when no :term:`thread state` - is :term:`attached `. If this function returns - ``NULL``, no exception has been raised and the caller should assume no - thread state is attached. - - -.. c:function:: int PyThreadState_SetAsyncExc(unsigned long id, PyObject *exc) - - Asynchronously raise an exception in a thread. The *id* argument is the thread - id of the target thread; *exc* is the exception object to be raised. This - function does not steal any references to *exc*. To prevent naive misuse, you - must write your own C extension to call this. Must be called with an :term:`attached thread state`. - Returns the number of thread states modified; this is normally one, but will be - zero if the thread id isn't found. If *exc* is ``NULL``, the pending - exception (if any) for the thread is cleared. This raises no exceptions. - - .. versionchanged:: 3.7 - The type of the *id* parameter changed from :c:expr:`long` to - :c:expr:`unsigned long`. - -.. c:function:: void PyEval_AcquireThread(PyThreadState *tstate) - - :term:`Attach ` *tstate* to the current thread, - which must not be ``NULL`` or already :term:`attached `. - - The calling thread must not already have an :term:`attached thread state`. - - .. note:: - Calling this function from a thread when the runtime is finalizing will - hang the thread until the program exits, even if the thread was not - created by Python. Refer to - :ref:`cautions-regarding-runtime-finalization` for more details. - - .. versionchanged:: 3.8 - Updated to be consistent with :c:func:`PyEval_RestoreThread`, - :c:func:`Py_END_ALLOW_THREADS`, and :c:func:`PyGILState_Ensure`, - and terminate the current thread if called while the interpreter is finalizing. - - .. versionchanged:: 3.14 - Hangs the current thread, rather than terminating it, if called while the - interpreter is finalizing. - - :c:func:`PyEval_RestoreThread` is a higher-level function which is always - available (even when threads have not been initialized). - - -.. c:function:: void PyEval_ReleaseThread(PyThreadState *tstate) - - Detach the :term:`attached thread state`. - The *tstate* argument, which must not be ``NULL``, is only used to check - that it represents the :term:`attached thread state` --- if it isn't, a fatal error is - reported. - - :c:func:`PyEval_SaveThread` is a higher-level function which is always - available (even when threads have not been initialized). - - -.. _sub-interpreter-support: - -Sub-interpreter support -======================= - -While in most uses, you will only embed a single Python interpreter, there -are cases where you need to create several independent interpreters in the -same process and perhaps even in the same thread. Sub-interpreters allow -you to do that. - -The "main" interpreter is the first one created when the runtime initializes. -It is usually the only Python interpreter in a process. Unlike sub-interpreters, -the main interpreter has unique process-global responsibilities like signal -handling. It is also responsible for execution during runtime initialization and -is usually the active interpreter during runtime finalization. The -:c:func:`PyInterpreterState_Main` function returns a pointer to its state. - -You can switch between sub-interpreters using the :c:func:`PyThreadState_Swap` -function. You can create and destroy them using the following functions: - - -.. c:type:: PyInterpreterConfig - - Structure containing most parameters to configure a sub-interpreter. - Its values are used only in :c:func:`Py_NewInterpreterFromConfig` and - never modified by the runtime. - - .. versionadded:: 3.12 - - Structure fields: - - .. c:member:: int use_main_obmalloc - - If this is ``0`` then the sub-interpreter will use its own - "object" allocator state. - Otherwise it will use (share) the main interpreter's. - - If this is ``0`` then - :c:member:`~PyInterpreterConfig.check_multi_interp_extensions` - must be ``1`` (non-zero). - If this is ``1`` then :c:member:`~PyInterpreterConfig.gil` - must not be :c:macro:`PyInterpreterConfig_OWN_GIL`. - - .. c:member:: int allow_fork - - If this is ``0`` then the runtime will not support forking the - process in any thread where the sub-interpreter is currently active. - Otherwise fork is unrestricted. - - Note that the :mod:`subprocess` module still works - when fork is disallowed. - - .. c:member:: int allow_exec - - If this is ``0`` then the runtime will not support replacing the - current process via exec (e.g. :func:`os.execv`) in any thread - where the sub-interpreter is currently active. - Otherwise exec is unrestricted. - - Note that the :mod:`subprocess` module still works - when exec is disallowed. - - .. c:member:: int allow_threads - - If this is ``0`` then the sub-interpreter's :mod:`threading` module - won't create threads. - Otherwise threads are allowed. - - .. c:member:: int allow_daemon_threads - - If this is ``0`` then the sub-interpreter's :mod:`threading` module - won't create daemon threads. - Otherwise daemon threads are allowed (as long as - :c:member:`~PyInterpreterConfig.allow_threads` is non-zero). - - .. c:member:: int check_multi_interp_extensions - - If this is ``0`` then all extension modules may be imported, - including legacy (single-phase init) modules, - in any thread where the sub-interpreter is currently active. - Otherwise only multi-phase init extension modules - (see :pep:`489`) may be imported. - (Also see :c:macro:`Py_mod_multiple_interpreters`.) - - This must be ``1`` (non-zero) if - :c:member:`~PyInterpreterConfig.use_main_obmalloc` is ``0``. - - .. c:member:: int gil - - This determines the operation of the GIL for the sub-interpreter. - It may be one of the following: - - .. c:namespace:: NULL - - .. c:macro:: PyInterpreterConfig_DEFAULT_GIL - - Use the default selection (:c:macro:`PyInterpreterConfig_SHARED_GIL`). - - .. c:macro:: PyInterpreterConfig_SHARED_GIL - - Use (share) the main interpreter's GIL. - - .. c:macro:: PyInterpreterConfig_OWN_GIL - - Use the sub-interpreter's own GIL. - - If this is :c:macro:`PyInterpreterConfig_OWN_GIL` then - :c:member:`PyInterpreterConfig.use_main_obmalloc` must be ``0``. - - -.. c:function:: PyStatus Py_NewInterpreterFromConfig(PyThreadState **tstate_p, const PyInterpreterConfig *config) - - .. index:: - pair: module; builtins - pair: module; __main__ - pair: module; sys - single: stdout (in module sys) - single: stderr (in module sys) - single: stdin (in module sys) - - Create a new sub-interpreter. This is an (almost) totally separate environment - for the execution of Python code. In particular, the new interpreter has - separate, independent versions of all imported modules, including the - fundamental modules :mod:`builtins`, :mod:`__main__` and :mod:`sys`. The - table of loaded modules (``sys.modules``) and the module search path - (``sys.path``) are also separate. The new environment has no ``sys.argv`` - variable. It has new standard I/O stream file objects ``sys.stdin``, - ``sys.stdout`` and ``sys.stderr`` (however these refer to the same underlying - file descriptors). - - The given *config* controls the options with which the interpreter - is initialized. - - Upon success, *tstate_p* will be set to the first :term:`thread state` - created in the new sub-interpreter. This thread state is - :term:`attached `. - Note that no actual thread is created; see the discussion of thread states - below. If creation of the new interpreter is unsuccessful, - *tstate_p* is set to ``NULL``; - no exception is set since the exception state is stored in the - :term:`attached thread state`, which might not exist. - - Like all other Python/C API functions, an :term:`attached thread state` - must be present before calling this function, but it might be detached upon - returning. On success, the returned thread state will be :term:`attached `. - If the sub-interpreter is created with its own :term:`GIL` then the - :term:`attached thread state` of the calling interpreter will be detached. - When the function returns, the new interpreter's :term:`thread state` - will be :term:`attached ` to the current thread and - the previous interpreter's :term:`attached thread state` will remain detached. - - .. versionadded:: 3.12 - - Sub-interpreters are most effective when isolated from each other, - with certain functionality restricted:: - - PyInterpreterConfig config = { - .use_main_obmalloc = 0, - .allow_fork = 0, - .allow_exec = 0, - .allow_threads = 1, - .allow_daemon_threads = 0, - .check_multi_interp_extensions = 1, - .gil = PyInterpreterConfig_OWN_GIL, - }; - PyThreadState *tstate = NULL; - PyStatus status = Py_NewInterpreterFromConfig(&tstate, &config); - if (PyStatus_Exception(status)) { - Py_ExitStatusException(status); - } - - Note that the config is used only briefly and does not get modified. - During initialization the config's values are converted into various - :c:type:`PyInterpreterState` values. A read-only copy of the config - may be stored internally on the :c:type:`PyInterpreterState`. - - .. index:: - single: Py_FinalizeEx (C function) - single: Py_Initialize (C function) - - Extension modules are shared between (sub-)interpreters as follows: - - * For modules using multi-phase initialization, - e.g. :c:func:`PyModule_FromDefAndSpec`, a separate module object is - created and initialized for each interpreter. - Only C-level static and global variables are shared between these - module objects. - - * For modules using single-phase initialization, - e.g. :c:func:`PyModule_Create`, the first time a particular extension - is imported, it is initialized normally, and a (shallow) copy of its - module's dictionary is squirreled away. - When the same extension is imported by another (sub-)interpreter, a new - module is initialized and filled with the contents of this copy; the - extension's ``init`` function is not called. - Objects in the module's dictionary thus end up shared across - (sub-)interpreters, which might cause unwanted behavior (see - `Bugs and caveats`_ below). - - Note that this is different from what happens when an extension is - imported after the interpreter has been completely re-initialized by - calling :c:func:`Py_FinalizeEx` and :c:func:`Py_Initialize`; in that - case, the extension's ``initmodule`` function *is* called again. - As with multi-phase initialization, this means that only C-level static - and global variables are shared between these modules. - - .. index:: single: close (in module os) - - -.. c:function:: PyThreadState* Py_NewInterpreter(void) - - .. index:: - pair: module; builtins - pair: module; __main__ - pair: module; sys - single: stdout (in module sys) - single: stderr (in module sys) - single: stdin (in module sys) - - Create a new sub-interpreter. This is essentially just a wrapper - around :c:func:`Py_NewInterpreterFromConfig` with a config that - preserves the existing behavior. The result is an unisolated - sub-interpreter that shares the main interpreter's GIL, allows - fork/exec, allows daemon threads, and allows single-phase init - modules. - - -.. c:function:: void Py_EndInterpreter(PyThreadState *tstate) - - .. index:: single: Py_FinalizeEx (C function) - - Destroy the (sub-)interpreter represented by the given :term:`thread state`. - The given thread state must be :term:`attached `. - When the call returns, there will be no :term:`attached thread state`. - All thread states associated with this interpreter are destroyed. - - :c:func:`Py_FinalizeEx` will destroy all sub-interpreters that - haven't been explicitly destroyed at that point. - - -A Per-Interpreter GIL ---------------------- - -Using :c:func:`Py_NewInterpreterFromConfig` you can create -a sub-interpreter that is completely isolated from other interpreters, -including having its own GIL. The most important benefit of this -isolation is that such an interpreter can execute Python code without -being blocked by other interpreters or blocking any others. Thus a -single Python process can truly take advantage of multiple CPU cores -when running Python code. The isolation also encourages a different -approach to concurrency than that of just using threads. -(See :pep:`554`.) - -Using an isolated interpreter requires vigilance in preserving that -isolation. That especially means not sharing any objects or mutable -state without guarantees about thread-safety. Even objects that are -otherwise immutable (e.g. ``None``, ``(1, 5)``) can't normally be shared -because of the refcount. One simple but less-efficient approach around -this is to use a global lock around all use of some state (or object). -Alternately, effectively immutable objects (like integers or strings) -can be made safe in spite of their refcounts by making them :term:`immortal`. -In fact, this has been done for the builtin singletons, small integers, -and a number of other builtin objects. - -If you preserve isolation then you will have access to proper multi-core -computing without the complications that come with free-threading. -Failure to preserve isolation will expose you to the full consequences -of free-threading, including races and hard-to-debug crashes. - -Aside from that, one of the main challenges of using multiple isolated -interpreters is how to communicate between them safely (not break -isolation) and efficiently. The runtime and stdlib do not provide -any standard approach to this yet. A future stdlib module would help -mitigate the effort of preserving isolation and expose effective tools -for communicating (and sharing) data between interpreters. - -.. versionadded:: 3.12 - - -Bugs and caveats ----------------- - -Because sub-interpreters (and the main interpreter) are part of the same -process, the insulation between them isn't perfect --- for example, using -low-level file operations like :func:`os.close` they can -(accidentally or maliciously) affect each other's open files. Because of the -way extensions are shared between (sub-)interpreters, some extensions may not -work properly; this is especially likely when using single-phase initialization -or (static) global variables. -It is possible to insert objects created in one sub-interpreter into -a namespace of another (sub-)interpreter; this should be avoided if possible. - -Special care should be taken to avoid sharing user-defined functions, -methods, instances or classes between sub-interpreters, since import -operations executed by such objects may affect the wrong (sub-)interpreter's -dictionary of loaded modules. It is equally important to avoid sharing -objects from which the above are reachable. - -Also note that combining this functionality with ``PyGILState_*`` APIs -is delicate, because these APIs assume a bijection between Python thread states -and OS-level threads, an assumption broken by the presence of sub-interpreters. -It is highly recommended that you don't switch sub-interpreters between a pair -of matching :c:func:`PyGILState_Ensure` and :c:func:`PyGILState_Release` calls. -Furthermore, extensions (such as :mod:`ctypes`) using these APIs to allow calling -of Python code from non-Python created threads will probably be broken when using -sub-interpreters. - - -Asynchronous Notifications -========================== - -A mechanism is provided to make asynchronous notifications to the main -interpreter thread. These notifications take the form of a function -pointer and a void pointer argument. - - -.. c:function:: int Py_AddPendingCall(int (*func)(void *), void *arg) - - Schedule a function to be called from the main interpreter thread. On - success, ``0`` is returned and *func* is queued for being called in the - main thread. On failure, ``-1`` is returned without setting any exception. - - When successfully queued, *func* will be *eventually* called from the - main interpreter thread with the argument *arg*. It will be called - asynchronously with respect to normally running Python code, but with - both these conditions met: - - * on a :term:`bytecode` boundary; - * with the main thread holding an :term:`attached thread state` - (*func* can therefore use the full C API). - - *func* must return ``0`` on success, or ``-1`` on failure with an exception - set. *func* won't be interrupted to perform another asynchronous - notification recursively, but it can still be interrupted to switch - threads if the :term:`thread state ` is detached. - - This function doesn't need an :term:`attached thread state`. However, to call this - function in a subinterpreter, the caller must have an :term:`attached thread state`. - Otherwise, the function *func* can be scheduled to be called from the wrong interpreter. - - .. warning:: - This is a low-level function, only useful for very special cases. - There is no guarantee that *func* will be called as quick as - possible. If the main thread is busy executing a system call, - *func* won't be called before the system call returns. This - function is generally **not** suitable for calling Python code from - arbitrary C threads. Instead, use the :ref:`PyGILState API`. - - .. versionadded:: 3.1 - - .. versionchanged:: 3.9 - If this function is called in a subinterpreter, the function *func* is - now scheduled to be called from the subinterpreter, rather than being - called from the main interpreter. Each subinterpreter now has its own - list of scheduled calls. - -.. _profiling: - -Profiling and Tracing -===================== - -.. sectionauthor:: Fred L. Drake, Jr. - - -The Python interpreter provides some low-level support for attaching profiling -and execution tracing facilities. These are used for profiling, debugging, and -coverage analysis tools. - -This C interface allows the profiling or tracing code to avoid the overhead of -calling through Python-level callable objects, making a direct C function call -instead. The essential attributes of the facility have not changed; the -interface allows trace functions to be installed per-thread, and the basic -events reported to the trace function are the same as had been reported to the -Python-level trace functions in previous versions. - - -.. c:type:: int (*Py_tracefunc)(PyObject *obj, PyFrameObject *frame, int what, PyObject *arg) - - The type of the trace function registered using :c:func:`PyEval_SetProfile` and - :c:func:`PyEval_SetTrace`. The first parameter is the object passed to the - registration function as *obj*, *frame* is the frame object to which the event - pertains, *what* is one of the constants :c:data:`PyTrace_CALL`, - :c:data:`PyTrace_EXCEPTION`, :c:data:`PyTrace_LINE`, :c:data:`PyTrace_RETURN`, - :c:data:`PyTrace_C_CALL`, :c:data:`PyTrace_C_EXCEPTION`, :c:data:`PyTrace_C_RETURN`, - or :c:data:`PyTrace_OPCODE`, and *arg* depends on the value of *what*: - - +-------------------------------+----------------------------------------+ - | Value of *what* | Meaning of *arg* | - +===============================+========================================+ - | :c:data:`PyTrace_CALL` | Always :c:data:`Py_None`. | - +-------------------------------+----------------------------------------+ - | :c:data:`PyTrace_EXCEPTION` | Exception information as returned by | - | | :func:`sys.exc_info`. | - +-------------------------------+----------------------------------------+ - | :c:data:`PyTrace_LINE` | Always :c:data:`Py_None`. | - +-------------------------------+----------------------------------------+ - | :c:data:`PyTrace_RETURN` | Value being returned to the caller, | - | | or ``NULL`` if caused by an exception. | - +-------------------------------+----------------------------------------+ - | :c:data:`PyTrace_C_CALL` | Function object being called. | - +-------------------------------+----------------------------------------+ - | :c:data:`PyTrace_C_EXCEPTION` | Function object being called. | - +-------------------------------+----------------------------------------+ - | :c:data:`PyTrace_C_RETURN` | Function object being called. | - +-------------------------------+----------------------------------------+ - | :c:data:`PyTrace_OPCODE` | Always :c:data:`Py_None`. | - +-------------------------------+----------------------------------------+ - -.. c:var:: int PyTrace_CALL - - The value of the *what* parameter to a :c:type:`Py_tracefunc` function when a new - call to a function or method is being reported, or a new entry into a generator. - Note that the creation of the iterator for a generator function is not reported - as there is no control transfer to the Python bytecode in the corresponding - frame. - - -.. c:var:: int PyTrace_EXCEPTION - - The value of the *what* parameter to a :c:type:`Py_tracefunc` function when an - exception has been raised. The callback function is called with this value for - *what* when after any bytecode is processed after which the exception becomes - set within the frame being executed. The effect of this is that as exception - propagation causes the Python stack to unwind, the callback is called upon - return to each frame as the exception propagates. Only trace functions receives - these events; they are not needed by the profiler. - - -.. c:var:: int PyTrace_LINE - - The value passed as the *what* parameter to a :c:type:`Py_tracefunc` function - (but not a profiling function) when a line-number event is being reported. - It may be disabled for a frame by setting :attr:`~frame.f_trace_lines` to - *0* on that frame. - - -.. c:var:: int PyTrace_RETURN - - The value for the *what* parameter to :c:type:`Py_tracefunc` functions when a - call is about to return. - - -.. c:var:: int PyTrace_C_CALL - - The value for the *what* parameter to :c:type:`Py_tracefunc` functions when a C - function is about to be called. - - -.. c:var:: int PyTrace_C_EXCEPTION - - The value for the *what* parameter to :c:type:`Py_tracefunc` functions when a C - function has raised an exception. - - -.. c:var:: int PyTrace_C_RETURN - - The value for the *what* parameter to :c:type:`Py_tracefunc` functions when a C - function has returned. - - -.. c:var:: int PyTrace_OPCODE - - The value for the *what* parameter to :c:type:`Py_tracefunc` functions (but not - profiling functions) when a new opcode is about to be executed. This event is - not emitted by default: it must be explicitly requested by setting - :attr:`~frame.f_trace_opcodes` to *1* on the frame. - - -.. c:function:: void PyEval_SetProfile(Py_tracefunc func, PyObject *obj) - - Set the profiler function to *func*. The *obj* parameter is passed to the - function as its first parameter, and may be any Python object, or ``NULL``. If - the profile function needs to maintain state, using a different value for *obj* - for each thread provides a convenient and thread-safe place to store it. The - profile function is called for all monitored events except :c:data:`PyTrace_LINE` - :c:data:`PyTrace_OPCODE` and :c:data:`PyTrace_EXCEPTION`. - - See also the :func:`sys.setprofile` function. - - The caller must have an :term:`attached thread state`. - -.. c:function:: void PyEval_SetProfileAllThreads(Py_tracefunc func, PyObject *obj) - - Like :c:func:`PyEval_SetProfile` but sets the profile function in all running threads - belonging to the current interpreter instead of the setting it only on the current thread. - - The caller must have an :term:`attached thread state`. - - As :c:func:`PyEval_SetProfile`, this function ignores any exceptions raised while - setting the profile functions in all threads. - -.. versionadded:: 3.12 - - -.. c:function:: void PyEval_SetTrace(Py_tracefunc func, PyObject *obj) - - Set the tracing function to *func*. This is similar to - :c:func:`PyEval_SetProfile`, except the tracing function does receive line-number - events and per-opcode events, but does not receive any event related to C function - objects being called. Any trace function registered using :c:func:`PyEval_SetTrace` - will not receive :c:data:`PyTrace_C_CALL`, :c:data:`PyTrace_C_EXCEPTION` or - :c:data:`PyTrace_C_RETURN` as a value for the *what* parameter. - - See also the :func:`sys.settrace` function. - - The caller must have an :term:`attached thread state`. - -.. c:function:: void PyEval_SetTraceAllThreads(Py_tracefunc func, PyObject *obj) - - Like :c:func:`PyEval_SetTrace` but sets the tracing function in all running threads - belonging to the current interpreter instead of the setting it only on the current thread. - - The caller must have an :term:`attached thread state`. - - As :c:func:`PyEval_SetTrace`, this function ignores any exceptions raised while - setting the trace functions in all threads. - -.. versionadded:: 3.12 - -Reference tracing -================= - -.. versionadded:: 3.13 - -.. c:type:: int (*PyRefTracer)(PyObject *, int event, void* data) - - The type of the trace function registered using :c:func:`PyRefTracer_SetTracer`. - The first parameter is a Python object that has been just created (when **event** - is set to :c:data:`PyRefTracer_CREATE`) or about to be destroyed (when **event** - is set to :c:data:`PyRefTracer_DESTROY`). The **data** argument is the opaque pointer - that was provided when :c:func:`PyRefTracer_SetTracer` was called. - -.. versionadded:: 3.13 - -.. c:var:: int PyRefTracer_CREATE - - The value for the *event* parameter to :c:type:`PyRefTracer` functions when a Python - object has been created. - -.. c:var:: int PyRefTracer_DESTROY - - The value for the *event* parameter to :c:type:`PyRefTracer` functions when a Python - object has been destroyed. - -.. c:function:: int PyRefTracer_SetTracer(PyRefTracer tracer, void *data) - - Register a reference tracer function. The function will be called when a new - Python has been created or when an object is going to be destroyed. If - **data** is provided it must be an opaque pointer that will be provided when - the tracer function is called. Return ``0`` on success. Set an exception and - return ``-1`` on error. - - Not that tracer functions **must not** create Python objects inside or - otherwise the call will be re-entrant. The tracer also **must not** clear - any existing exception or set an exception. A :term:`thread state` will be active - every time the tracer function is called. - - There must be an :term:`attached thread state` when calling this function. - -.. versionadded:: 3.13 - -.. c:function:: PyRefTracer PyRefTracer_GetTracer(void** data) - - Get the registered reference tracer function and the value of the opaque data - pointer that was registered when :c:func:`PyRefTracer_SetTracer` was called. - If no tracer was registered this function will return NULL and will set the - **data** pointer to NULL. - - There must be an :term:`attached thread state` when calling this function. - -.. versionadded:: 3.13 - -.. _advanced-debugging: - -Advanced Debugger Support -========================= - -.. sectionauthor:: Fred L. Drake, Jr. - - -These functions are only intended to be used by advanced debugging tools. - - -.. c:function:: PyInterpreterState* PyInterpreterState_Head() - - Return the interpreter state object at the head of the list of all such objects. - - -.. c:function:: PyInterpreterState* PyInterpreterState_Main() - - Return the main interpreter state object. - - -.. c:function:: PyInterpreterState* PyInterpreterState_Next(PyInterpreterState *interp) - - Return the next interpreter state object after *interp* from the list of all - such objects. - - -.. c:function:: PyThreadState * PyInterpreterState_ThreadHead(PyInterpreterState *interp) - - Return the pointer to the first :c:type:`PyThreadState` object in the list of - threads associated with the interpreter *interp*. - - -.. c:function:: PyThreadState* PyThreadState_Next(PyThreadState *tstate) - - Return the next thread state object after *tstate* from the list of all such - objects belonging to the same :c:type:`PyInterpreterState` object. - - -.. _thread-local-storage: - -Thread Local Storage Support -============================ - -.. sectionauthor:: Masayuki Yamamoto - -The Python interpreter provides low-level support for thread-local storage -(TLS) which wraps the underlying native TLS implementation to support the -Python-level thread local storage API (:class:`threading.local`). The -CPython C level APIs are similar to those offered by pthreads and Windows: -use a thread key and functions to associate a :c:expr:`void*` value per -thread. - -A :term:`thread state` does *not* need to be :term:`attached ` -when calling these functions; they suppl their own locking. - -Note that :file:`Python.h` does not include the declaration of the TLS APIs, -you need to include :file:`pythread.h` to use thread-local storage. - -.. note:: - None of these API functions handle memory management on behalf of the - :c:expr:`void*` values. You need to allocate and deallocate them yourself. - If the :c:expr:`void*` values happen to be :c:expr:`PyObject*`, these - functions don't do refcount operations on them either. - -.. _thread-specific-storage-api: - -Thread Specific Storage (TSS) API ---------------------------------- - -TSS API is introduced to supersede the use of the existing TLS API within the -CPython interpreter. This API uses a new type :c:type:`Py_tss_t` instead of -:c:expr:`int` to represent thread keys. - -.. versionadded:: 3.7 - -.. seealso:: "A New C-API for Thread-Local Storage in CPython" (:pep:`539`) - - -.. c:type:: Py_tss_t - - This data structure represents the state of a thread key, the definition of - which may depend on the underlying TLS implementation, and it has an - internal field representing the key's initialization state. There are no - public members in this structure. - - When :ref:`Py_LIMITED_API ` is not defined, static allocation of - this type by :c:macro:`Py_tss_NEEDS_INIT` is allowed. - - -.. c:macro:: Py_tss_NEEDS_INIT - - This macro expands to the initializer for :c:type:`Py_tss_t` variables. - Note that this macro won't be defined with :ref:`Py_LIMITED_API `. - - -Dynamic Allocation -~~~~~~~~~~~~~~~~~~ - -Dynamic allocation of the :c:type:`Py_tss_t`, required in extension modules -built with :ref:`Py_LIMITED_API `, where static allocation of this type -is not possible due to its implementation being opaque at build time. - - -.. c:function:: Py_tss_t* PyThread_tss_alloc() - - Return a value which is the same state as a value initialized with - :c:macro:`Py_tss_NEEDS_INIT`, or ``NULL`` in the case of dynamic allocation - failure. - - -.. c:function:: void PyThread_tss_free(Py_tss_t *key) - - Free the given *key* allocated by :c:func:`PyThread_tss_alloc`, after - first calling :c:func:`PyThread_tss_delete` to ensure any associated - thread locals have been unassigned. This is a no-op if the *key* - argument is ``NULL``. - - .. note:: - A freed key becomes a dangling pointer. You should reset the key to - ``NULL``. - - -Methods -~~~~~~~ - -The parameter *key* of these functions must not be ``NULL``. Moreover, the -behaviors of :c:func:`PyThread_tss_set` and :c:func:`PyThread_tss_get` are -undefined if the given :c:type:`Py_tss_t` has not been initialized by -:c:func:`PyThread_tss_create`. - - -.. c:function:: int PyThread_tss_is_created(Py_tss_t *key) - - Return a non-zero value if the given :c:type:`Py_tss_t` has been initialized - by :c:func:`PyThread_tss_create`. - - -.. c:function:: int PyThread_tss_create(Py_tss_t *key) - - Return a zero value on successful initialization of a TSS key. The behavior - is undefined if the value pointed to by the *key* argument is not - initialized by :c:macro:`Py_tss_NEEDS_INIT`. This function can be called - repeatedly on the same key -- calling it on an already initialized key is a - no-op and immediately returns success. - - -.. c:function:: void PyThread_tss_delete(Py_tss_t *key) - - Destroy a TSS key to forget the values associated with the key across all - threads, and change the key's initialization state to uninitialized. A - destroyed key is able to be initialized again by - :c:func:`PyThread_tss_create`. This function can be called repeatedly on - the same key -- calling it on an already destroyed key is a no-op. - - -.. c:function:: int PyThread_tss_set(Py_tss_t *key, void *value) - - Return a zero value to indicate successfully associating a :c:expr:`void*` - value with a TSS key in the current thread. Each thread has a distinct - mapping of the key to a :c:expr:`void*` value. - - -.. c:function:: void* PyThread_tss_get(Py_tss_t *key) - - Return the :c:expr:`void*` value associated with a TSS key in the current - thread. This returns ``NULL`` if no value is associated with the key in the - current thread. - - -.. _thread-local-storage-api: - -Thread Local Storage (TLS) API ------------------------------- - -.. deprecated:: 3.7 - This API is superseded by - :ref:`Thread Specific Storage (TSS) API `. - -.. note:: - This version of the API does not support platforms where the native TLS key - is defined in a way that cannot be safely cast to ``int``. On such platforms, - :c:func:`PyThread_create_key` will return immediately with a failure status, - and the other TLS functions will all be no-ops on such platforms. - -Due to the compatibility problem noted above, this version of the API should not -be used in new code. - -.. c:function:: int PyThread_create_key() -.. c:function:: void PyThread_delete_key(int key) -.. c:function:: int PyThread_set_key_value(int key, void *value) -.. c:function:: void* PyThread_get_key_value(int key) -.. c:function:: void PyThread_delete_key_value(int key) -.. c:function:: void PyThread_ReInitTLS() - -Synchronization Primitives -========================== - -The C-API provides a basic mutual exclusion lock. - -.. c:type:: PyMutex - - A mutual exclusion lock. The :c:type:`!PyMutex` should be initialized to - zero to represent the unlocked state. For example:: - - PyMutex mutex = {0}; - - Instances of :c:type:`!PyMutex` should not be copied or moved. Both the - contents and address of a :c:type:`!PyMutex` are meaningful, and it must - remain at a fixed, writable location in memory. - - .. note:: - - A :c:type:`!PyMutex` currently occupies one byte, but the size should be - considered unstable. The size may change in future Python releases - without a deprecation period. - - .. versionadded:: 3.13 - -.. c:function:: void PyMutex_Lock(PyMutex *m) - - Lock mutex *m*. If another thread has already locked it, the calling - thread will block until the mutex is unlocked. While blocked, the thread - will temporarily detach the :term:`thread state ` if one exists. - - .. versionadded:: 3.13 - -.. c:function:: void PyMutex_Unlock(PyMutex *m) - - Unlock mutex *m*. The mutex must be locked --- otherwise, the function will - issue a fatal error. - - .. versionadded:: 3.13 - -.. _python-critical-section-api: - -Python Critical Section API ---------------------------- - -The critical section API provides a deadlock avoidance layer on top of -per-object locks for :term:`free-threaded ` CPython. They are -intended to replace reliance on the :term:`global interpreter lock`, and are -no-ops in versions of Python with the global interpreter lock. - -Critical sections avoid deadlocks by implicitly suspending active critical -sections and releasing the locks during calls to :c:func:`PyEval_SaveThread`. -When :c:func:`PyEval_RestoreThread` is called, the most recent critical section -is resumed, and its locks reacquired. This means the critical section API -provides weaker guarantees than traditional locks -- they are useful because -their behavior is similar to the :term:`GIL`. - -The functions and structs used by the macros are exposed for cases -where C macros are not available. They should only be used as in the -given macro expansions. Note that the sizes and contents of the structures may -change in future Python versions. - -.. note:: - - Operations that need to lock two objects at once must use - :c:macro:`Py_BEGIN_CRITICAL_SECTION2`. You *cannot* use nested critical - sections to lock more than one object at once, because the inner critical - section may suspend the outer critical sections. This API does not provide - a way to lock more than two objects at once. - -Example usage:: - - static PyObject * - set_field(MyObject *self, PyObject *value) - { - Py_BEGIN_CRITICAL_SECTION(self); - Py_SETREF(self->field, Py_XNewRef(value)); - Py_END_CRITICAL_SECTION(); - Py_RETURN_NONE; - } - -In the above example, :c:macro:`Py_SETREF` calls :c:macro:`Py_DECREF`, which -can call arbitrary code through an object's deallocation function. The critical -section API avoids potential deadlocks due to reentrancy and lock ordering -by allowing the runtime to temporarily suspend the critical section if the -code triggered by the finalizer blocks and calls :c:func:`PyEval_SaveThread`. - -.. c:macro:: Py_BEGIN_CRITICAL_SECTION(op) - - Acquires the per-object lock for the object *op* and begins a - critical section. - - In the free-threaded build, this macro expands to:: - - { - PyCriticalSection _py_cs; - PyCriticalSection_Begin(&_py_cs, (PyObject*)(op)) - - In the default build, this macro expands to ``{``. - - .. versionadded:: 3.13 - -.. c:macro:: Py_END_CRITICAL_SECTION() - - Ends the critical section and releases the per-object lock. - - In the free-threaded build, this macro expands to:: - - PyCriticalSection_End(&_py_cs); - } - - In the default build, this macro expands to ``}``. - - .. versionadded:: 3.13 - -.. c:macro:: Py_BEGIN_CRITICAL_SECTION2(a, b) - - Acquires the per-objects locks for the objects *a* and *b* and begins a - critical section. The locks are acquired in a consistent order (lowest - address first) to avoid lock ordering deadlocks. - - In the free-threaded build, this macro expands to:: - - { - PyCriticalSection2 _py_cs2; - PyCriticalSection2_Begin(&_py_cs2, (PyObject*)(a), (PyObject*)(b)) - - In the default build, this macro expands to ``{``. - - .. versionadded:: 3.13 - -.. c:macro:: Py_END_CRITICAL_SECTION2() - - Ends the critical section and releases the per-object locks. - - In the free-threaded build, this macro expands to:: - - PyCriticalSection2_End(&_py_cs2); - } - - In the default build, this macro expands to ``}``. - - .. versionadded:: 3.13 +- :ref:`initialization` +- :ref:`threads` +- :ref:`synchronization` +- :ref:`thread-local-storage` +- :ref:`sub-interpreter-support` +- :ref:`profiling` diff --git a/Doc/c-api/init_config.rst b/Doc/c-api/init_config.rst index e1931655618b1c..21f1ebc030186c 100644 --- a/Doc/c-api/init_config.rst +++ b/Doc/c-api/init_config.rst @@ -102,7 +102,7 @@ Error Handling * Set *\*err_msg* and return ``1`` if an error is set. * Set *\*err_msg* to ``NULL`` and return ``0`` otherwise. - An error message is an UTF-8 encoded string. + An error message is a UTF-8 encoded string. If *config* has an exit code, format the exit code as an error message. @@ -544,9 +544,9 @@ Configuration Options Visibility: -* Public: Can by get by :c:func:`PyConfig_Get` and set by +* Public: Can be retrieved by :c:func:`PyConfig_Get` and set by :c:func:`PyConfig_Set`. -* Read-only: Can by get by :c:func:`PyConfig_Get`, but cannot be set by +* Read-only: Can be retrieved by :c:func:`PyConfig_Get`, but cannot be set by :c:func:`PyConfig_Set`. @@ -623,6 +623,10 @@ Some options are read from the :mod:`sys` attributes. For example, the option .. versionadded:: 3.14 + .. versionchanged:: 3.14.7 + The function now replaces :data:`sys.flags` (create a new object), + instead of modifying :data:`sys.flags` in-place. + .. _pyconfig_api: @@ -1155,7 +1159,7 @@ PyConfig Most ``PyConfig`` methods :ref:`preinitialize Python ` if needed. In that case, the Python preinitialization configuration - (:c:type:`PyPreConfig`) in based on the :c:type:`PyConfig`. If configuration + (:c:type:`PyPreConfig`) is based on the :c:type:`PyConfig`. If configuration fields which are in common with :c:type:`PyPreConfig` are tuned, they must be set before calling a :c:type:`PyConfig` method: @@ -1233,9 +1237,9 @@ PyConfig .. c:member:: wchar_t* base_executable - Python base executable: :data:`sys._base_executable`. + Python base executable: ``sys._base_executable``. - Set by the :envvar:`__PYVENV_LAUNCHER__` environment variable. + Set by the ``__PYVENV_LAUNCHER__`` environment variable. Set from :c:member:`PyConfig.executable` if ``NULL``. @@ -1741,7 +1745,7 @@ PyConfig * On macOS, use :envvar:`PYTHONEXECUTABLE` environment variable if set. * If the ``WITH_NEXT_FRAMEWORK`` macro is defined, use - :envvar:`__PYVENV_LAUNCHER__` environment variable if set. + ``__PYVENV_LAUNCHER__`` environment variable if set. * Use ``argv[0]`` of :c:member:`~PyConfig.argv` if available and non-empty. * Otherwise, use ``L"python"`` on Windows, or ``L"python3"`` on other @@ -1977,8 +1981,7 @@ PyConfig The :mod:`warnings` module adds :data:`sys.warnoptions` in the reverse order: the last :c:member:`PyConfig.warnoptions` item becomes the first - item of :data:`warnings.filters` which is checked first (highest - priority). + item of ``warnings.filters`` which is checked first (highest priority). The :option:`-W` command line options adds its value to :c:member:`~PyConfig.warnoptions`, it can be used multiple times. diff --git a/Doc/c-api/interp-lifecycle.rst b/Doc/c-api/interp-lifecycle.rst new file mode 100644 index 00000000000000..f8c8fdaa05b46f --- /dev/null +++ b/Doc/c-api/interp-lifecycle.rst @@ -0,0 +1,956 @@ +.. highlight:: c + +.. _initialization: + +Interpreter initialization and finalization +=========================================== + +See :ref:`Python Initialization Configuration ` for details +on how to configure the interpreter prior to initialization. + +.. _pre-init-safe: + +Before Python initialization +---------------------------- + +In an application embedding Python, the :c:func:`Py_Initialize` function must +be called before using any other Python/C API functions; with the exception of +a few functions and the :ref:`global configuration variables +`. + +The following functions can be safely called before Python is initialized: + +* Functions that initialize the interpreter: + + * :c:func:`Py_Initialize` + * :c:func:`Py_InitializeEx` + * :c:func:`Py_InitializeFromConfig` + * :c:func:`Py_BytesMain` + * :c:func:`Py_Main` + * the runtime pre-initialization functions covered in :ref:`init-config` + +* Configuration functions: + + * :c:func:`PyImport_AppendInittab` + * :c:func:`PyImport_ExtendInittab` + * :c:func:`!PyInitFrozenExtensions` + * :c:func:`PyMem_SetAllocator` + * :c:func:`PyMem_SetupDebugHooks` + * :c:func:`PyObject_SetArenaAllocator` + * :c:func:`Py_SetProgramName` + * :c:func:`Py_SetPythonHome` + * the configuration functions covered in :ref:`init-config` + +* Informative functions: + + * :c:func:`Py_IsInitialized` + * :c:func:`PyMem_GetAllocator` + * :c:func:`PyObject_GetArenaAllocator` + * :c:func:`Py_GetBuildInfo` + * :c:func:`Py_GetCompiler` + * :c:func:`Py_GetCopyright` + * :c:func:`Py_GetPlatform` + * :c:func:`Py_GetVersion` + * :c:func:`Py_IsInitialized` + +* Utilities: + + * :c:func:`Py_DecodeLocale` + * the status reporting and utility functions covered in :ref:`init-config` + +* Memory allocators: + + * :c:func:`PyMem_RawMalloc` + * :c:func:`PyMem_RawRealloc` + * :c:func:`PyMem_RawCalloc` + * :c:func:`PyMem_RawFree` + +* Synchronization: + + * :c:func:`PyMutex_Lock` + * :c:func:`PyMutex_Unlock` + +.. note:: + + Despite their apparent similarity to some of the functions listed above, + the following functions **should not be called** before the interpreter has + been initialized: :c:func:`Py_EncodeLocale`, :c:func:`PyEval_InitThreads`, and + :c:func:`Py_RunMain`. + + +.. _global-conf-vars: + +Global configuration variables +------------------------------ + +Python has variables for the global configuration to control different features +and options. By default, these flags are controlled by :ref:`command line +options `. + +When a flag is set by an option, the value of the flag is the number of times +that the option was set. For example, ``-b`` sets :c:data:`Py_BytesWarningFlag` +to 1 and ``-bb`` sets :c:data:`Py_BytesWarningFlag` to 2. + + +.. c:var:: int Py_BytesWarningFlag + + This API is kept for backward compatibility: setting + :c:member:`PyConfig.bytes_warning` should be used instead, see :ref:`Python + Initialization Configuration `. + + Issue a warning when comparing :class:`bytes` or :class:`bytearray` with + :class:`str` or :class:`bytes` with :class:`int`. Issue an error if greater + or equal to ``2``. + + Set by the :option:`-b` option. + + .. deprecated-removed:: 3.12 3.15 + + +.. c:var:: int Py_DebugFlag + + This API is kept for backward compatibility: setting + :c:member:`PyConfig.parser_debug` should be used instead, see :ref:`Python + Initialization Configuration `. + + Turn on parser debugging output (for expert only, depending on compilation + options). + + Set by the :option:`-d` option and the :envvar:`PYTHONDEBUG` environment + variable. + + .. deprecated-removed:: 3.12 3.15 + + +.. c:var:: int Py_DontWriteBytecodeFlag + + This API is kept for backward compatibility: setting + :c:member:`PyConfig.write_bytecode` should be used instead, see :ref:`Python + Initialization Configuration `. + + If set to non-zero, Python won't try to write ``.pyc`` files on the + import of source modules. + + Set by the :option:`-B` option and the :envvar:`PYTHONDONTWRITEBYTECODE` + environment variable. + + .. deprecated-removed:: 3.12 3.15 + + +.. c:var:: int Py_FrozenFlag + + This API is kept for backward compatibility: setting + :c:member:`PyConfig.pathconfig_warnings` should be used instead, see + :ref:`Python Initialization Configuration `. + + Private flag used by ``_freeze_module`` and ``frozenmain`` programs. + + .. deprecated-removed:: 3.12 3.15 + + +.. c:var:: int Py_HashRandomizationFlag + + This API is kept for backward compatibility: setting + :c:member:`PyConfig.hash_seed` and :c:member:`PyConfig.use_hash_seed` should + be used instead, see :ref:`Python Initialization Configuration + `. + + Set to ``1`` if the :envvar:`PYTHONHASHSEED` environment variable is set to + a non-empty string. + + If the flag is non-zero, read the :envvar:`PYTHONHASHSEED` environment + variable to initialize the secret hash seed. + + .. deprecated-removed:: 3.12 3.15 + + +.. c:var:: int Py_IgnoreEnvironmentFlag + + This API is kept for backward compatibility: setting + :c:member:`PyConfig.use_environment` should be used instead, see + :ref:`Python Initialization Configuration `. + + Ignore all :envvar:`!PYTHON*` environment variables, e.g. + :envvar:`PYTHONPATH` and :envvar:`PYTHONHOME`, that might be set. + + Set by the :option:`-E` and :option:`-I` options. + + .. deprecated-removed:: 3.12 3.15 + + +.. c:var:: int Py_InspectFlag + + This API is kept for backward compatibility: setting + :c:member:`PyConfig.inspect` should be used instead, see + :ref:`Python Initialization Configuration `. + + When a script is passed as first argument or the :option:`-c` option is used, + enter interactive mode after executing the script or the command, even when + :data:`sys.stdin` does not appear to be a terminal. + + Set by the :option:`-i` option and the :envvar:`PYTHONINSPECT` environment + variable. + + .. deprecated-removed:: 3.12 3.15 + + +.. c:var:: int Py_InteractiveFlag + + This API is kept for backward compatibility: setting + :c:member:`PyConfig.interactive` should be used instead, see + :ref:`Python Initialization Configuration `. + + Set by the :option:`-i` option. + + .. deprecated-removed:: 3.12 3.15 + + +.. c:var:: int Py_IsolatedFlag + + This API is kept for backward compatibility: setting + :c:member:`PyConfig.isolated` should be used instead, see + :ref:`Python Initialization Configuration `. + + Run Python in isolated mode. In isolated mode :data:`sys.path` contains + neither the script's directory nor the user's site-packages directory. + + Set by the :option:`-I` option. + + .. versionadded:: 3.4 + + .. deprecated-removed:: 3.12 3.15 + + +.. c:var:: int Py_LegacyWindowsFSEncodingFlag + + This API is kept for backward compatibility: setting + :c:member:`PyPreConfig.legacy_windows_fs_encoding` should be used instead, see + :ref:`Python Initialization Configuration `. + + If the flag is non-zero, use the ``mbcs`` encoding with ``replace`` error + handler, instead of the UTF-8 encoding with ``surrogatepass`` error handler, + for the :term:`filesystem encoding and error handler`. + + Set to ``1`` if the :envvar:`PYTHONLEGACYWINDOWSFSENCODING` environment + variable is set to a non-empty string. + + See :pep:`529` for more details. + + .. availability:: Windows. + + .. deprecated-removed:: 3.12 3.15 + + +.. c:var:: int Py_LegacyWindowsStdioFlag + + This API is kept for backward compatibility: setting + :c:member:`PyConfig.legacy_windows_stdio` should be used instead, see + :ref:`Python Initialization Configuration `. + + If the flag is non-zero, use :class:`io.FileIO` instead of + :class:`!io._WindowsConsoleIO` for :mod:`sys` standard streams. + + Set to ``1`` if the :envvar:`PYTHONLEGACYWINDOWSSTDIO` environment + variable is set to a non-empty string. + + See :pep:`528` for more details. + + .. availability:: Windows. + + .. deprecated-removed:: 3.12 3.15 + + +.. c:var:: int Py_NoSiteFlag + + This API is kept for backward compatibility: setting + :c:member:`PyConfig.site_import` should be used instead, see + :ref:`Python Initialization Configuration `. + + Disable the import of the module :mod:`site` and the site-dependent + manipulations of :data:`sys.path` that it entails. Also disable these + manipulations if :mod:`site` is explicitly imported later (call + :func:`site.main` if you want them to be triggered). + + Set by the :option:`-S` option. + + .. deprecated-removed:: 3.12 3.15 + + +.. c:var:: int Py_NoUserSiteDirectory + + This API is kept for backward compatibility: setting + :c:member:`PyConfig.user_site_directory` should be used instead, see + :ref:`Python Initialization Configuration `. + + Don't add the :data:`user site-packages directory ` to + :data:`sys.path`. + + Set by the :option:`-s` and :option:`-I` options, and the + :envvar:`PYTHONNOUSERSITE` environment variable. + + .. deprecated-removed:: 3.12 3.15 + + +.. c:var:: int Py_OptimizeFlag + + This API is kept for backward compatibility: setting + :c:member:`PyConfig.optimization_level` should be used instead, see + :ref:`Python Initialization Configuration `. + + Set by the :option:`-O` option and the :envvar:`PYTHONOPTIMIZE` environment + variable. + + .. deprecated-removed:: 3.12 3.15 + + +.. c:var:: int Py_QuietFlag + + This API is kept for backward compatibility: setting + :c:member:`PyConfig.quiet` should be used instead, see :ref:`Python + Initialization Configuration `. + + Don't display the copyright and version messages even in interactive mode. + + Set by the :option:`-q` option. + + .. versionadded:: 3.2 + + .. deprecated-removed:: 3.12 3.15 + + +.. c:var:: int Py_UnbufferedStdioFlag + + This API is kept for backward compatibility: setting + :c:member:`PyConfig.buffered_stdio` should be used instead, see :ref:`Python + Initialization Configuration `. + + Force the stdout and stderr streams to be unbuffered. + + Set by the :option:`-u` option and the :envvar:`PYTHONUNBUFFERED` + environment variable. + + .. deprecated-removed:: 3.12 3.15 + + +.. c:var:: int Py_VerboseFlag + + This API is kept for backward compatibility: setting + :c:member:`PyConfig.verbose` should be used instead, see :ref:`Python + Initialization Configuration `. + + Print a message each time a module is initialized, showing the place + (filename or built-in module) from which it is loaded. If greater or equal + to ``2``, print a message for each file that is checked for when + searching for a module. Also provides information on module cleanup at exit. + + Set by the :option:`-v` option and the :envvar:`PYTHONVERBOSE` environment + variable. + + .. deprecated-removed:: 3.12 3.15 + + +Initializing and finalizing the interpreter +------------------------------------------- + +.. c:function:: void Py_Initialize() + + .. index:: + single: PyEval_InitThreads() + single: modules (in module sys) + single: path (in module sys) + pair: module; builtins + pair: module; __main__ + pair: module; sys + triple: module; search; path + single: Py_FinalizeEx (C function) + + Initialize the Python interpreter. In an application embedding Python, + this should be called before using any other Python/C API functions; see + :ref:`Before Python Initialization ` for the few exceptions. + + This initializes the table of loaded modules (``sys.modules``), and creates + the fundamental modules :mod:`builtins`, :mod:`__main__` and :mod:`sys`. + It also initializes the module search path (``sys.path``). It does not set + ``sys.argv``; use the :ref:`Python Initialization Configuration ` + API for that. This is a no-op when called for a second time (without calling + :c:func:`Py_FinalizeEx` first). There is no return value; it is a fatal + error if the initialization fails. + + Use :c:func:`Py_InitializeFromConfig` to customize the + :ref:`Python Initialization Configuration `. + + .. note:: + On Windows, changes the console mode from ``O_TEXT`` to ``O_BINARY``, + which will also affect non-Python uses of the console using the C Runtime. + + +.. c:function:: void Py_InitializeEx(int initsigs) + + This function works like :c:func:`Py_Initialize` if *initsigs* is ``1``. If + *initsigs* is ``0``, it skips initialization registration of signal handlers, + which may be useful when CPython is embedded as part of a larger application. + + Use :c:func:`Py_InitializeFromConfig` to customize the + :ref:`Python Initialization Configuration `. + + +.. c:function:: PyStatus Py_InitializeFromConfig(const PyConfig *config) + + Initialize Python from *config* configuration, as described in + :ref:`init-from-config`. + + See the :ref:`init-config` section for details on pre-initializing the + interpreter, populating the runtime configuration structure, and querying + the returned status structure. + + +.. c:function:: int Py_IsInitialized() + + Return true (nonzero) when the Python interpreter has been initialized, false + (zero) if not. After :c:func:`Py_FinalizeEx` is called, this returns false until + :c:func:`Py_Initialize` is called again. + + +.. c:function:: int Py_IsFinalizing() + + Return true (non-zero) if the main Python interpreter is + :term:`shutting down `. Return false (zero) otherwise. + + .. versionadded:: 3.13 + + +.. c:function:: int Py_FinalizeEx() + + Undo all initializations made by :c:func:`Py_Initialize` and subsequent use of + Python/C API functions, and destroy all sub-interpreters (see + :c:func:`Py_NewInterpreter` below) that were created and not yet destroyed since + the last call to :c:func:`Py_Initialize`. This is a no-op when called for a second + time (without calling :c:func:`Py_Initialize` again first). + + Since this is the reverse of :c:func:`Py_Initialize`, it should be called + in the same thread with the same interpreter active. That means + the main thread and the main interpreter. + This should never be called while :c:func:`Py_RunMain` is running. + + Normally the return value is ``0``. + If there were errors during finalization (flushing buffered data), + ``-1`` is returned. + + Note that Python will do a best effort at freeing all memory allocated by the Python + interpreter. Therefore, any C-Extension should make sure to correctly clean up all + of the previously allocated PyObjects before using them in subsequent calls to + :c:func:`Py_Initialize`. Otherwise it could introduce vulnerabilities and incorrect + behavior. + + This function is provided for a number of reasons. An embedding application + might want to restart Python without having to restart the application itself. + An application that has loaded the Python interpreter from a dynamically + loadable library (or DLL) might want to free all memory allocated by Python + before unloading the DLL. During a hunt for memory leaks in an application a + developer might want to free all memory allocated by Python before exiting from + the application. + + **Bugs and caveats:** The destruction of modules and objects in modules is done + in random order; this may cause destructors (:meth:`~object.__del__` methods) to fail + when they depend on other objects (even functions) or modules. Dynamically + loaded extension modules loaded by Python are not unloaded. Small amounts of + memory allocated by the Python interpreter may not be freed (if you find a leak, + please report it). Memory tied up in circular references between objects is not + freed. Interned strings will all be deallocated regardless of their reference count. + Some memory allocated by extension modules may not be freed. Some extensions may not + work properly if their initialization routine is called more than once; this can + happen if an application calls :c:func:`Py_Initialize` and :c:func:`Py_FinalizeEx` + more than once. :c:func:`Py_FinalizeEx` must not be called recursively from + within itself. Therefore, it must not be called by any code that may be run + as part of the interpreter shutdown process, such as :py:mod:`atexit` + handlers, object finalizers, or any code that may be run while flushing the + stdout and stderr files. + + .. audit-event:: cpython._PySys_ClearAuditHooks "" c.Py_FinalizeEx + + .. versionadded:: 3.6 + + +.. c:function:: void Py_Finalize() + + This is a backwards-compatible version of :c:func:`Py_FinalizeEx` that + disregards the return value. + + +.. c:function:: int Py_BytesMain(int argc, char **argv) + + Similar to :c:func:`Py_Main` but *argv* is an array of bytes strings, + allowing the calling application to delegate the text decoding step to + the CPython runtime. + + .. versionadded:: 3.8 + + +.. c:function:: int Py_Main(int argc, wchar_t **argv) + + The main program for the standard interpreter, encapsulating a full + initialization/finalization cycle, as well as additional + behaviour to implement reading configurations settings from the environment + and command line, and then executing ``__main__`` in accordance with + :ref:`using-on-cmdline`. + + This is made available for programs which wish to support the full CPython + command line interface, rather than just embedding a Python runtime in a + larger application. + + The *argc* and *argv* parameters are similar to those which are passed to a + C program's :c:func:`main` function, except that the *argv* entries are first + converted to ``wchar_t`` using :c:func:`Py_DecodeLocale`. It is also + important to note that the argument list entries may be modified to point to + strings other than those passed in (however, the contents of the strings + pointed to by the argument list are not modified). + + The return value is ``2`` if the argument list does not represent a valid + Python command line, and otherwise the same as :c:func:`Py_RunMain`. + + In terms of the CPython runtime configuration APIs documented in the + :ref:`runtime configuration ` section (and without accounting + for error handling), ``Py_Main`` is approximately equivalent to:: + + PyConfig config; + PyConfig_InitPythonConfig(&config); + PyConfig_SetArgv(&config, argc, argv); + Py_InitializeFromConfig(&config); + PyConfig_Clear(&config); + + Py_RunMain(); + + In normal usage, an embedding application will call this function + *instead* of calling :c:func:`Py_Initialize`, :c:func:`Py_InitializeEx` or + :c:func:`Py_InitializeFromConfig` directly, and all settings will be applied + as described elsewhere in this documentation. If this function is instead + called *after* a preceding runtime initialization API call, then exactly + which environmental and command line configuration settings will be updated + is version dependent (as it depends on which settings correctly support + being modified after they have already been set once when the runtime was + first initialized). + + +.. c:function:: int Py_RunMain(void) + + Executes the main module in a fully configured CPython runtime. + + Executes the command (:c:member:`PyConfig.run_command`), the script + (:c:member:`PyConfig.run_filename`) or the module + (:c:member:`PyConfig.run_module`) specified on the command line or in the + configuration. If none of these values are set, runs the interactive Python + prompt (REPL) using the ``__main__`` module's global namespace. + + If :c:member:`PyConfig.inspect` is not set (the default), the return value + will be ``0`` if the interpreter exits normally (that is, without raising + an exception), the exit status of an unhandled :exc:`SystemExit`, or ``1`` + for any other unhandled exception. + + If :c:member:`PyConfig.inspect` is set (such as when the :option:`-i` option + is used), rather than returning when the interpreter exits, execution will + instead resume in an interactive Python prompt (REPL) using the ``__main__`` + module's global namespace. If the interpreter exited with an exception, it + is immediately raised in the REPL session. The function return value is + then determined by the way the *REPL session* terminates: ``0``, ``1``, or + the status of a :exc:`SystemExit`, as specified above. + + This function always finalizes the Python interpreter before it returns. + + See :ref:`Python Configuration ` for an example of a + customized Python that always runs in isolated mode using + :c:func:`Py_RunMain`. + +.. c:function:: int PyUnstable_AtExit(PyInterpreterState *interp, void (*func)(void *), void *data) + + Register an :mod:`atexit` callback for the target interpreter *interp*. + This is similar to :c:func:`Py_AtExit`, but takes an explicit interpreter and + data pointer for the callback. + + There must be an :term:`attached thread state` for *interp*. + + .. versionadded:: 3.13 + + +.. _cautions-regarding-runtime-finalization: + +Cautions regarding runtime finalization +--------------------------------------- + +In the late stage of :term:`interpreter shutdown`, after attempting to wait for +non-daemon threads to exit (though this can be interrupted by +:class:`KeyboardInterrupt`) and running the :mod:`atexit` functions, the runtime +is marked as *finalizing*: :c:func:`Py_IsFinalizing` and +:func:`sys.is_finalizing` return true. At this point, only the *finalization +thread* that initiated finalization (typically the main thread) is allowed to +acquire the :term:`GIL`. + +If any thread, other than the finalization thread, attempts to attach a :term:`thread state` +during finalization, either explicitly or +implicitly, the thread enters **a permanently blocked state** +where it remains until the program exits. In most cases this is harmless, but this can result +in deadlock if a later stage of finalization attempts to acquire a lock owned by the +blocked thread, or otherwise waits on the blocked thread. + +Gross? Yes. This prevents random crashes and/or unexpectedly skipped C++ +finalizations further up the call stack when such threads were forcibly exited +here in CPython 3.13 and earlier. The CPython runtime :term:`thread state` C APIs +have never had any error reporting or handling expectations at :term:`thread state` +attachment time that would've allowed for graceful exit from this situation. Changing that +would require new stable C APIs and rewriting the majority of C code in the +CPython ecosystem to use those with error handling. + + +Process-wide parameters +----------------------- + +.. c:function:: void Py_SetProgramName(const wchar_t *name) + + .. index:: + single: Py_Initialize() + single: main() + single: Py_GetPath() + + This API is kept for backward compatibility: setting + :c:member:`PyConfig.program_name` should be used instead, see :ref:`Python + Initialization Configuration `. + + This function should be called before :c:func:`Py_Initialize` is called for + the first time, if it is called at all. It tells the interpreter the value + of the ``argv[0]`` argument to the :c:func:`main` function of the program + (converted to wide characters). + This is used by :c:func:`Py_GetPath` and some other functions below to find + the Python run-time libraries relative to the interpreter executable. The + default value is ``'python'``. The argument should point to a + zero-terminated wide character string in static storage whose contents will not + change for the duration of the program's execution. No code in the Python + interpreter will change the contents of this storage. + + Use :c:func:`Py_DecodeLocale` to decode a bytes string to get a + :c:expr:`wchar_t*` string. + + .. deprecated-removed:: 3.11 3.15 + + +.. c:function:: wchar_t* Py_GetProgramName() + + Return the program name set with :c:member:`PyConfig.program_name`, or the default. + The returned string points into static storage; the caller should not modify its + value. + + This function should not be called before :c:func:`Py_Initialize`, otherwise + it returns ``NULL``. + + .. versionchanged:: 3.10 + It now returns ``NULL`` if called before :c:func:`Py_Initialize`. + + .. deprecated-removed:: 3.13 3.15 + Use :c:func:`PyConfig_Get("executable") ` + (:data:`sys.executable`) instead. + + +.. c:function:: wchar_t* Py_GetPrefix() + + Return the *prefix* for installed platform-independent files. This is derived + through a number of complicated rules from the program name set with + :c:member:`PyConfig.program_name` and some environment variables; for example, if the + program name is ``'/usr/local/bin/python'``, the prefix is ``'/usr/local'``. The + returned string points into static storage; the caller should not modify its + value. This corresponds to the :makevar:`prefix` variable in the top-level + :file:`Makefile` and the :option:`--prefix` argument to the :program:`configure` + script at build time. The value is available to Python code as ``sys.base_prefix``. + It is only useful on Unix. See also the next function. + + This function should not be called before :c:func:`Py_Initialize`, otherwise + it returns ``NULL``. + + .. versionchanged:: 3.10 + It now returns ``NULL`` if called before :c:func:`Py_Initialize`. + + .. deprecated-removed:: 3.13 3.15 + Use :c:func:`PyConfig_Get("base_prefix") ` + (:data:`sys.base_prefix`) instead. Use :c:func:`PyConfig_Get("prefix") + ` (:data:`sys.prefix`) if :ref:`virtual environments + ` need to be handled. + + +.. c:function:: wchar_t* Py_GetExecPrefix() + + Return the *exec-prefix* for installed platform-*dependent* files. This is + derived through a number of complicated rules from the program name set with + :c:member:`PyConfig.program_name` and some environment variables; for example, if the + program name is ``'/usr/local/bin/python'``, the exec-prefix is + ``'/usr/local'``. The returned string points into static storage; the caller + should not modify its value. This corresponds to the :makevar:`exec_prefix` + variable in the top-level :file:`Makefile` and the ``--exec-prefix`` + argument to the :program:`configure` script at build time. The value is + available to Python code as ``sys.base_exec_prefix``. It is only useful on + Unix. + + Background: The exec-prefix differs from the prefix when platform dependent + files (such as executables and shared libraries) are installed in a different + directory tree. In a typical installation, platform dependent files may be + installed in the :file:`/usr/local/plat` subtree while platform independent may + be installed in :file:`/usr/local`. + + Generally speaking, a platform is a combination of hardware and software + families, e.g. Sparc machines running the Solaris 2.x operating system are + considered the same platform, but Intel machines running Solaris 2.x are another + platform, and Intel machines running Linux are yet another platform. Different + major revisions of the same operating system generally also form different + platforms. Non-Unix operating systems are a different story; the installation + strategies on those systems are so different that the prefix and exec-prefix are + meaningless, and set to the empty string. Note that compiled Python bytecode + files are platform independent (but not independent from the Python version by + which they were compiled!). + + System administrators will know how to configure the :program:`mount` or + :program:`automount` programs to share :file:`/usr/local` between platforms + while having :file:`/usr/local/plat` be a different filesystem for each + platform. + + This function should not be called before :c:func:`Py_Initialize`, otherwise + it returns ``NULL``. + + .. versionchanged:: 3.10 + It now returns ``NULL`` if called before :c:func:`Py_Initialize`. + + .. deprecated-removed:: 3.13 3.15 + Use :c:func:`PyConfig_Get("base_exec_prefix") ` + (:data:`sys.base_exec_prefix`) instead. Use + :c:func:`PyConfig_Get("exec_prefix") ` + (:data:`sys.exec_prefix`) if :ref:`virtual environments ` need + to be handled. + + +.. c:function:: wchar_t* Py_GetProgramFullPath() + + .. index:: + single: executable (in module sys) + + Return the full program name of the Python executable; this is computed as a + side-effect of deriving the default module search path from the program name + (set by :c:member:`PyConfig.program_name`). The returned string points into + static storage; the caller should not modify its value. The value is available + to Python code as ``sys.executable``. + + This function should not be called before :c:func:`Py_Initialize`, otherwise + it returns ``NULL``. + + .. versionchanged:: 3.10 + It now returns ``NULL`` if called before :c:func:`Py_Initialize`. + + .. deprecated-removed:: 3.13 3.15 + Use :c:func:`PyConfig_Get("executable") ` + (:data:`sys.executable`) instead. + + +.. c:function:: wchar_t* Py_GetPath() + + .. index:: + triple: module; search; path + single: path (in module sys) + + Return the default module search path; this is computed from the program name + (set by :c:member:`PyConfig.program_name`) and some environment variables. + The returned string consists of a series of directory names separated by a + platform dependent delimiter character. The delimiter character is ``':'`` + on Unix and macOS, ``';'`` on Windows. The returned string points into + static storage; the caller should not modify its value. The list + :data:`sys.path` is initialized with this value on interpreter startup; it + can be (and usually is) modified later to change the search path for loading + modules. + + This function should not be called before :c:func:`Py_Initialize`, otherwise + it returns ``NULL``. + + .. XXX should give the exact rules + + .. versionchanged:: 3.10 + It now returns ``NULL`` if called before :c:func:`Py_Initialize`. + + .. deprecated-removed:: 3.13 3.15 + Use :c:func:`PyConfig_Get("module_search_paths") ` + (:data:`sys.path`) instead. + +.. c:function:: const char* Py_GetVersion() + + Return the version of this Python interpreter. This is a string that looks + something like :: + + "3.0a5+ (py3k:63103M, May 12 2008, 00:53:55) \n[GCC 4.2.3]" + + .. index:: single: version (in module sys) + + The first word (up to the first space character) is the current Python version; + the first characters are the major and minor version separated by a + period. The returned string points into static storage; the caller should not + modify its value. The value is available to Python code as :data:`sys.version`. + + See also the :c:var:`Py_Version` constant. + + +.. c:function:: const char* Py_GetPlatform() + + .. index:: single: platform (in module sys) + + Return the platform identifier for the current platform. On Unix, this is + formed from the "official" name of the operating system, converted to lower + case, followed by the major revision number; e.g., for Solaris 2.x, which is + also known as SunOS 5.x, the value is ``'sunos5'``. On macOS, it is + ``'darwin'``. On Windows, it is ``'win'``. The returned string points into + static storage; the caller should not modify its value. The value is available + to Python code as ``sys.platform``. + + +.. c:function:: const char* Py_GetCopyright() + + Return the official copyright string for the current Python version, for example + + ``'Copyright 1991-1995 Stichting Mathematisch Centrum, Amsterdam'`` + + .. index:: single: copyright (in module sys) + + The returned string points into static storage; the caller should not modify its + value. The value is available to Python code as ``sys.copyright``. + + +.. c:function:: const char* Py_GetCompiler() + + Return an indication of the compiler used to build the current Python version, + in square brackets, for example:: + + "[GCC 2.7.2.2]" + + .. index:: single: version (in module sys) + + The returned string points into static storage; the caller should not modify its + value. The value is available to Python code as part of the variable + ``sys.version``. + + +.. c:function:: const char* Py_GetBuildInfo() + + Return information about the sequence number and build date and time of the + current Python interpreter instance, for example :: + + "#67, Aug 1 1997, 22:34:28" + + .. index:: single: version (in module sys) + + The returned string points into static storage; the caller should not modify its + value. The value is available to Python code as part of the variable + ``sys.version``. + + +.. c:function:: void PySys_SetArgvEx(int argc, wchar_t **argv, int updatepath) + + .. index:: + single: main() + single: Py_FatalError() + single: argv (in module sys) + + This API is kept for backward compatibility: setting + :c:member:`PyConfig.argv`, :c:member:`PyConfig.parse_argv` and + :c:member:`PyConfig.safe_path` should be used instead, see :ref:`Python + Initialization Configuration `. + + Set :data:`sys.argv` based on *argc* and *argv*. These parameters are + similar to those passed to the program's :c:func:`main` function with the + difference that the first entry should refer to the script file to be + executed rather than the executable hosting the Python interpreter. If there + isn't a script that will be run, the first entry in *argv* can be an empty + string. If this function fails to initialize :data:`sys.argv`, a fatal + condition is signalled using :c:func:`Py_FatalError`. + + If *updatepath* is zero, this is all the function does. If *updatepath* + is non-zero, the function also modifies :data:`sys.path` according to the + following algorithm: + + - If the name of an existing script is passed in ``argv[0]``, the absolute + path of the directory where the script is located is prepended to + :data:`sys.path`. + - Otherwise (that is, if *argc* is ``0`` or ``argv[0]`` doesn't point + to an existing file name), an empty string is prepended to + :data:`sys.path`, which is the same as prepending the current working + directory (``"."``). + + Use :c:func:`Py_DecodeLocale` to decode a bytes string to get a + :c:expr:`wchar_t*` string. + + See also :c:member:`PyConfig.orig_argv` and :c:member:`PyConfig.argv` + members of the :ref:`Python Initialization Configuration `. + + .. note:: + It is recommended that applications embedding the Python interpreter + for purposes other than executing a single script pass ``0`` as *updatepath*, + and update :data:`sys.path` themselves if desired. + See :cve:`2008-5983`. + + On versions before 3.1.3, you can achieve the same effect by manually + popping the first :data:`sys.path` element after having called + :c:func:`PySys_SetArgv`, for example using:: + + PyRun_SimpleString("import sys; sys.path.pop(0)\n"); + + .. versionadded:: 3.1.3 + + .. deprecated-removed:: 3.11 3.15 + + +.. c:function:: void PySys_SetArgv(int argc, wchar_t **argv) + + This API is kept for backward compatibility: setting + :c:member:`PyConfig.argv` and :c:member:`PyConfig.parse_argv` should be used + instead, see :ref:`Python Initialization Configuration `. + + This function works like :c:func:`PySys_SetArgvEx` with *updatepath* set + to ``1`` unless the :program:`python` interpreter was started with the + :option:`-I`. + + Use :c:func:`Py_DecodeLocale` to decode a bytes string to get a + :c:expr:`wchar_t*` string. + + See also :c:member:`PyConfig.orig_argv` and :c:member:`PyConfig.argv` + members of the :ref:`Python Initialization Configuration `. + + .. versionchanged:: 3.4 The *updatepath* value depends on :option:`-I`. + + .. deprecated-removed:: 3.11 3.15 + + +.. c:function:: void Py_SetPythonHome(const wchar_t *home) + + This API is kept for backward compatibility: setting + :c:member:`PyConfig.home` should be used instead, see :ref:`Python + Initialization Configuration `. + + Set the default "home" directory, that is, the location of the standard + Python libraries. See :envvar:`PYTHONHOME` for the meaning of the + argument string. + + The argument should point to a zero-terminated character string in static + storage whose contents will not change for the duration of the program's + execution. No code in the Python interpreter will change the contents of + this storage. + + Use :c:func:`Py_DecodeLocale` to decode a bytes string to get a + :c:expr:`wchar_t*` string. + + .. deprecated-removed:: 3.11 3.15 + + +.. c:function:: wchar_t* Py_GetPythonHome() + + Return the default "home", that is, the value set by + :c:member:`PyConfig.home`, or the value of the :envvar:`PYTHONHOME` + environment variable if it is set. + + This function should not be called before :c:func:`Py_Initialize`, otherwise + it returns ``NULL``. + + .. versionchanged:: 3.10 + It now returns ``NULL`` if called before :c:func:`Py_Initialize`. + + .. deprecated-removed:: 3.13 3.15 + Use :c:func:`PyConfig_Get("home") ` or the + :envvar:`PYTHONHOME` environment variable instead. diff --git a/Doc/c-api/intro.rst b/Doc/c-api/intro.rst index c8c60eb9f48f45..fd025999db9d9c 100644 --- a/Doc/c-api/intro.rst +++ b/Doc/c-api/intro.rst @@ -111,45 +111,284 @@ Useful macros ============= Several useful macros are defined in the Python header files. Many are -defined closer to where they are useful (e.g. :c:macro:`Py_RETURN_NONE`). +defined closer to where they are useful (for example, :c:macro:`Py_RETURN_NONE`, +:c:macro:`PyMODINIT_FUNC`). Others of a more general utility are defined here. This is not necessarily a complete listing. -.. c:macro:: PyMODINIT_FUNC +.. c:macro:: Py_CAN_START_THREADS - Declare an extension module ``PyInit`` initialization function. The function - return type is :c:expr:`PyObject*`. The macro declares any special linkage - declarations required by the platform, and for C++ declares the function as - ``extern "C"``. + If this macro is defined, then the current system is able to start threads. - The initialization function must be named :samp:`PyInit_{name}`, where - *name* is the name of the module, and should be the only non-\ ``static`` - item defined in the module file. Example:: + Currently, all systems supported by CPython (per :pep:`11`), with the + exception of some WebAssembly platforms, support starting threads. - static struct PyModuleDef spam_module = { - PyModuleDef_HEAD_INIT, - .m_name = "spam", - ... - }; + .. versionadded:: 3.13 - PyMODINIT_FUNC - PyInit_spam(void) - { - return PyModule_Create(&spam_module); - } +.. c:macro:: Py_GETENV(s) + + Like :samp:`getenv({s})`, but returns ``NULL`` if :option:`-E` was passed + on the command line (see :c:member:`PyConfig.use_environment`). + + +Docstring macros +---------------- + +.. c:macro:: PyDoc_STRVAR(name, str) + + Creates a variable with name *name* that can be used in docstrings. + If Python is built without docstrings (:option:`--without-doc-strings`), + the value will be an empty string. + + Example:: + + PyDoc_STRVAR(pop_doc, "Remove and return the rightmost element."); + + static PyMethodDef deque_methods[] = { + // ... + {"pop", (PyCFunction)deque_pop, METH_NOARGS, pop_doc}, + // ... + } + + Expands to :samp:`PyDoc_VAR({name}) = PyDoc_STR({str})`. + +.. c:macro:: PyDoc_STR(str) + + Expands to the given input string, or an empty string + if docstrings are disabled (:option:`--without-doc-strings`). + + Example:: + + static PyMethodDef pysqlite_row_methods[] = { + {"keys", (PyCFunction)pysqlite_row_keys, METH_NOARGS, + PyDoc_STR("Returns the keys of the row.")}, + {NULL, NULL} + }; + +.. c:macro:: PyDoc_VAR(name) + + Declares a static character array variable with the given *name*. + Expands to :samp:`static const char {name}[]` + + For example:: + PyDoc_VAR(python_doc) = PyDoc_STR( + "A genus of constricting snakes in the Pythonidae family native " + "to the tropics and subtropics of the Eastern Hemisphere."); + + +General utility macros +---------------------- + +The following macros are for common tasks not specific to Python. + +.. c:macro:: Py_UNUSED(arg) + + Use this for unused arguments in a function definition to silence compiler + warnings. Example: ``int func(int a, int Py_UNUSED(b)) { return a; }``. + + .. versionadded:: 3.4 + +.. c:macro:: Py_GCC_ATTRIBUTE(name) + + Use a GCC attribute *name*, hiding it from compilers that don't support GCC + attributes (such as MSVC). + + This expands to :samp:`__attribute__(({name)})` on a GCC compiler, + and expands to nothing on compilers that don't support GCC attributes. + + +Numeric utilities +^^^^^^^^^^^^^^^^^ .. c:macro:: Py_ABS(x) Return the absolute value of ``x``. + The argument may be evaluated more than once. + Consequently, do not pass an expression with side-effects directly + to this macro. + + If the result cannot be represented (for example, if ``x`` has + :c:macro:`!INT_MIN` value for :c:expr:`int` type), the behavior is + undefined. + + Corresponds roughly to :samp:`(({x}) < 0 ? -({x}) : ({x}))` + + .. versionadded:: 3.3 + +.. c:macro:: Py_MAX(x, y) + Py_MIN(x, y) + + Return the larger or smaller of the arguments, respectively. + + Any arguments may be evaluated more than once. + Consequently, do not pass an expression with side-effects directly + to this macro. + + :c:macro:`!Py_MAX` corresponds roughly to + :samp:`((({x}) > ({y})) ? ({x}) : ({y}))`. + + .. versionadded:: 3.3 + +.. c:macro:: Py_ARITHMETIC_RIGHT_SHIFT(type, integer, positions) + + Similar to :samp:`{integer} >> {positions}`, but forces sign extension, + as the C standard does not define whether a right-shift of a signed + integer will perform sign extension or a zero-fill. + + *integer* should be any signed integer type. + *positions* is the number of positions to shift to the right. + + Both *integer* and *positions* can be evaluated more than once; + consequently, avoid directly passing a function call or some other + operation with side-effects to this macro. Instead, store the result as a + variable and then pass it. + + *type* is unused and only kept for backwards compatibility. Historically, + *type* was used to cast *integer*. + + .. versionchanged:: 3.1 + + This macro is now valid for all signed integer types, not just those for + which ``unsigned type`` is legal. As a result, *type* is no longer + used. + +.. c:macro:: Py_CHARMASK(c) + + Argument must be a character or an integer in the range [-128, 127] or [0, + 255]. This macro returns ``c`` cast to an ``unsigned char``. + + +Assertion utilities +^^^^^^^^^^^^^^^^^^^ + +.. c:macro:: Py_UNREACHABLE() + + Use this when you have a code path that cannot be reached by design. + For example, in the ``default:`` clause in a ``switch`` statement for which + all possible values are covered in ``case`` statements. Use this in places + where you might be tempted to put an ``assert(0)`` or ``abort()`` call. + + In release mode, the macro helps the compiler to optimize the code, and + avoids a warning about unreachable code. For example, the macro is + implemented with ``__builtin_unreachable()`` on GCC in release mode. + + In debug mode, and on unsupported compilers, the macro expands to a call to + :c:func:`Py_FatalError`. + + A use for ``Py_UNREACHABLE()`` is following a call to a function that + never returns but that is not declared ``_Noreturn``. + + If a code path is very unlikely code but can be reached under exceptional + case, this macro must not be used. For example, under low memory condition + or if a system call returns a value out of the expected range. In this + case, it's better to report the error to the caller. If the error cannot + be reported to caller, :c:func:`Py_FatalError` can be used. + + .. versionadded:: 3.7 + +.. c:macro:: Py_SAFE_DOWNCAST(value, larger, smaller) + + Cast *value* to type *smaller* from type *larger*, validating that no + information was lost. + + On release builds of Python, this is roughly equivalent to + :samp:`(({smaller}) {value})` + (in C++, :samp:`static_cast<{smaller}>({value})` will be used instead). + + On debug builds (implying that :c:macro:`Py_DEBUG` is defined), this asserts + that no information was lost with the cast from *larger* to *smaller*. + + *value*, *larger*, and *smaller* may all be evaluated more than once in the + expression; consequently, do not pass an expression with side-effects + directly to this macro. + +.. c:macro:: Py_BUILD_ASSERT(cond) + + Asserts a compile-time condition *cond*, as a statement. + The build will fail if the condition is false or cannot be evaluated at compile time. + + Corresponds roughly to :samp:`static_assert({cond})` on C23 and above. + + For example:: + + Py_BUILD_ASSERT(sizeof(PyTime_t) == sizeof(int64_t)); + .. versionadded:: 3.3 +.. c:macro:: Py_BUILD_ASSERT_EXPR(cond) + + Asserts a compile-time condition *cond*, as an expression that evaluates to ``0``. + The build will fail if the condition is false or cannot be evaluated at compile time. + + For example:: + + #define foo_to_char(foo) \ + ((char *)(foo) + Py_BUILD_ASSERT_EXPR(offsetof(struct foo, string) == 0)) + + .. versionadded:: 3.3 + + +Type size utilities +^^^^^^^^^^^^^^^^^^^ + +.. c:macro:: Py_ARRAY_LENGTH(array) + + Compute the length of a statically allocated C array at compile time. + + The *array* argument must be a C array with a size known at compile time. + Passing an array with an unknown size, such as a heap-allocated array, + will result in a compilation error on some compilers, or otherwise produce + incorrect results. + + This is roughly equivalent to:: + + sizeof(array) / sizeof((array)[0]) + +.. c:macro:: Py_MEMBER_SIZE(type, member) + + Return the size of a structure (*type*) *member* in bytes. + + Corresponds roughly to :samp:`sizeof((({type} *)NULL)->{member})`. + + .. versionadded:: 3.6 + + +Macro definition utilities +^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. c:macro:: Py_FORCE_EXPANSION(X) + + This is equivalent to :samp:`{X}`, which is useful for token-pasting in + macros, as macro expansions in *X* are forcefully evaluated by the + preprocessor. + +.. c:macro:: Py_STRINGIFY(x) + + Convert ``x`` to a C string. For example, ``Py_STRINGIFY(123)`` returns + ``"123"``. + + .. versionadded:: 3.4 + + +Declaration utilities +--------------------- + +The following macros can be used in declarations. +They are most useful for defining the C API itself, and have limited use +for extension authors. +Most of them expand to compiler-specific spellings of common extensions +to the C language. + .. c:macro:: Py_ALWAYS_INLINE Ask the compiler to always inline a static inline function. The compiler can ignore it and decide to not inline the function. + Corresponds to ``always_inline`` attribute in GCC and ``__forceinline`` + in MSVC. + It can be used to inline performance critical static inline functions when building Python in debug mode with function inlining disabled. For example, MSC disables function inlining when building in debug mode. @@ -167,15 +406,24 @@ complete listing. .. versionadded:: 3.11 -.. c:macro:: Py_CHARMASK(c) +.. c:macro:: Py_NO_INLINE - Argument must be a character or an integer in the range [-128, 127] or [0, - 255]. This macro returns ``c`` cast to an ``unsigned char``. + Disable inlining on a function. For example, it reduces the C stack + consumption: useful on LTO+PGO builds which heavily inline code (see + :issue:`33720`). + + Corresponds to the ``noinline`` attribute/specification on GCC and MSVC. + + Usage:: + + Py_NO_INLINE static int random(void) { return 4; } + + .. versionadded:: 3.11 .. c:macro:: Py_DEPRECATED(version) - Use this for deprecated declarations. The macro must be placed before the - symbol name. + Use this to declare APIs that were deprecated in a specific CPython version. + The macro must be placed before the symbol name. Example:: @@ -184,110 +432,97 @@ complete listing. .. versionchanged:: 3.8 MSVC support was added. -.. c:macro:: Py_GETENV(s) +.. c:macro:: Py_LOCAL(type) - Like ``getenv(s)``, but returns ``NULL`` if :option:`-E` was passed on the - command line (see :c:member:`PyConfig.use_environment`). + Declare a function returning the specified *type* using a fast-calling + qualifier for functions that are local to the current file. + Semantically, this is equivalent to :samp:`static {type}`. -.. c:macro:: Py_MAX(x, y) +.. c:macro:: Py_LOCAL_INLINE(type) - Return the maximum value between ``x`` and ``y``. + Equivalent to :c:macro:`Py_LOCAL` but additionally requests the function + be inlined. - .. versionadded:: 3.3 +.. c:macro:: Py_LOCAL_SYMBOL -.. c:macro:: Py_MEMBER_SIZE(type, member) + Macro used to declare a symbol as local to the shared library (hidden). + On supported platforms, it ensures the symbol is not exported. - Return the size of a structure (``type``) ``member`` in bytes. + On compatible versions of GCC/Clang, it + expands to ``__attribute__((visibility("hidden")))``. - .. versionadded:: 3.6 +.. c:macro:: Py_EXPORTED_SYMBOL -.. c:macro:: Py_MIN(x, y) + Macro used to declare a symbol (function or data) as exported. + On Windows, this expands to ``__declspec(dllexport)``. + On compatible versions of GCC/Clang, it + expands to ``__attribute__((visibility("default")))``. + This macro is for defining the C API itself; extension modules should not use it. - Return the minimum value between ``x`` and ``y``. - .. versionadded:: 3.3 +.. c:macro:: Py_IMPORTED_SYMBOL -.. c:macro:: Py_NO_INLINE + Macro used to declare a symbol as imported. + On Windows, this expands to ``__declspec(dllimport)``. + This macro is for defining the C API itself; extension modules should not use it. - Disable inlining on a function. For example, it reduces the C stack - consumption: useful on LTO+PGO builds which heavily inline code (see - :issue:`33720`). - Usage:: +.. c:macro:: PyAPI_FUNC(type) - Py_NO_INLINE static int random(void) { return 4; } + Macro used by CPython to declare a function as part of the C API. + Its expansion depends on the platform and build configuration. + This macro is intended for defining CPython's C API itself; + extension modules should not use it for their own symbols. - .. versionadded:: 3.11 -.. c:macro:: Py_STRINGIFY(x) +.. c:macro:: PyAPI_DATA(type) - Convert ``x`` to a C string. E.g. ``Py_STRINGIFY(123)`` returns - ``"123"``. + Macro used by CPython to declare a public global variable as part of the C API. + Its expansion depends on the platform and build configuration. + This macro is intended for defining CPython's C API itself; + extension modules should not use it for their own symbols. - .. versionadded:: 3.4 -.. c:macro:: Py_UNREACHABLE() +Outdated macros +--------------- - Use this when you have a code path that cannot be reached by design. - For example, in the ``default:`` clause in a ``switch`` statement for which - all possible values are covered in ``case`` statements. Use this in places - where you might be tempted to put an ``assert(0)`` or ``abort()`` call. +The following macros have been used to features that have been standardized +in C11. - In release mode, the macro helps the compiler to optimize the code, and - avoids a warning about unreachable code. For example, the macro is - implemented with ``__builtin_unreachable()`` on GCC in release mode. +.. c:macro:: Py_ALIGNED(num) - A use for ``Py_UNREACHABLE()`` is following a call a function that - never returns but that is not declared :c:macro:`_Py_NO_RETURN`. + Specify alignment to *num* bytes on compilers that support it. - If a code path is very unlikely code but can be reached under exceptional - case, this macro must not be used. For example, under low memory condition - or if a system call returns a value out of the expected range. In this - case, it's better to report the error to the caller. If the error cannot - be reported to caller, :c:func:`Py_FatalError` can be used. + Consider using the C11 standard ``_Alignas`` specifier over this macro. - .. versionadded:: 3.7 +.. c:macro:: Py_LL(number) + Py_ULL(number) -.. c:macro:: Py_UNUSED(arg) + Use *number* as a ``long long`` or ``unsigned long long`` integer literal, + respectively. - Use this for unused arguments in a function definition to silence compiler - warnings. Example: ``int func(int a, int Py_UNUSED(b)) { return a; }``. + Expands to *number* followed by ``LL`` or ``LLU``, respectively, but will + expand to some compiler-specific suffixes on some older compilers. - .. versionadded:: 3.4 + Consider using the C99 standard suffixes ``LL`` and ``LLU`` directly. -.. c:macro:: PyDoc_STRVAR(name, str) +.. c:macro:: Py_MEMCPY(dest, src, n) - Creates a variable with name ``name`` that can be used in docstrings. - If Python is built without docstrings, the value will be empty. + This is an alias to :c:func:`!memcpy`. - Use :c:macro:`PyDoc_STRVAR` for docstrings to support building - Python without docstrings, as specified in :pep:`7`. + .. soft-deprecated:: 3.14 + Use :c:func:`!memcpy` directly instead. - Example:: +.. c:macro:: Py_VA_COPY - PyDoc_STRVAR(pop_doc, "Remove and return the rightmost element."); + This is an alias to the C99-standard ``va_copy`` function. - static PyMethodDef deque_methods[] = { - // ... - {"pop", (PyCFunction)deque_pop, METH_NOARGS, pop_doc}, - // ... - } + Historically, this would use a compiler-specific method to copy a ``va_list``. -.. c:macro:: PyDoc_STR(str) + .. versionchanged:: 3.6 + This is now an alias to ``va_copy``. - Creates a docstring for the given input string or an empty string - if docstrings are disabled. - - Use :c:macro:`PyDoc_STR` in specifying docstrings to support - building Python without docstrings, as specified in :pep:`7`. - - Example:: - - static PyMethodDef pysqlite_row_methods[] = { - {"keys", (PyCFunction)pysqlite_row_keys, METH_NOARGS, - PyDoc_STR("Returns the keys of the row.")}, - {NULL, NULL} - }; + .. soft-deprecated:: 3.14 .. _api-objects: @@ -406,9 +641,12 @@ the caller is said to *borrow* the reference. Nothing needs to be done for a Conversely, when a calling function passes in a reference to an object, there are two possibilities: the function *steals* a reference to the object, or it -does not. *Stealing a reference* means that when you pass a reference to a -function, that function assumes that it now owns that reference, and you are not -responsible for it any longer. +does not. + +*Stealing a reference* means that when you pass a reference to a +function, that function assumes that it now owns that reference. +Since the new owner can use :c:func:`!Py_DECREF` at its discretion, +you (the caller) must not use that reference after the call. .. index:: single: PyList_SetItem (C function) @@ -835,7 +1073,7 @@ in the Unix build, compiler optimization is disabled. In addition to the reference count debugging described below, extra checks are performed, see :ref:`Python Debug Build `. -Defining :c:macro:`Py_TRACE_REFS` enables reference tracing +Defining ``Py_TRACE_REFS`` enables reference tracing (see the :option:`configure --with-trace-refs option <--with-trace-refs>`). When defined, a circular doubly linked list of active objects is maintained by adding two extra fields to every :c:type:`PyObject`. Total allocations are tracked as well. Upon @@ -844,3 +1082,41 @@ after every statement run by the interpreter.) Please refer to :file:`Misc/SpecialBuilds.txt` in the Python source distribution for more detailed information. + + +.. _c-api-tools: + +Recommended third party tools +============================= + +The following third party tools offer both simpler and more sophisticated +approaches to creating C, C++ and Rust extensions for Python: + +* `Cython `_ +* `cffi `_ +* `HPy `_ +* `nanobind `_ (C++) +* `Numba `_ +* `pybind11 `_ (C++) +* `PyO3 `_ (Rust) +* `SWIG `_ + +Using tools such as these can help avoid writing code that is tightly bound to +a particular version of CPython, avoid reference counting errors, and focus +more on your own code than on using the CPython API. In general, new versions +of Python can be supported by updating the tool, and your code will often use +newer and more efficient APIs automatically. Some tools also support compiling +for other implementations of Python from a single set of sources. + +These projects are not supported by the same people who maintain Python, and +issues need to be raised with the projects directly. Remember to check that the +project is still maintained and supported, as the list above may become +outdated. + +.. seealso:: + + `Python Packaging User Guide: Binary Extensions `_ + The Python Packaging User Guide not only covers several available + tools that simplify the creation of binary extensions, but also + discusses the various reasons why creating an extension module may be + desirable in the first place. diff --git a/Doc/c-api/iterator.rst b/Doc/c-api/iterator.rst index 6b7ba8c9979163..bfbfe3c9279980 100644 --- a/Doc/c-api/iterator.rst +++ b/Doc/c-api/iterator.rst @@ -50,3 +50,72 @@ sentinel value is returned. callable object that can be called with no parameters; each call to it should return the next item in the iteration. When *callable* returns a value equal to *sentinel*, the iteration will be terminated. + + +Range Objects +^^^^^^^^^^^^^ + +.. c:var:: PyTypeObject PyRange_Type + + The type object for :class:`range` objects. + + +.. c:function:: int PyRange_Check(PyObject *o) + + Return true if the object *o* is an instance of a :class:`range` object. + This function always succeeds. + + +Builtin Iterator Types +^^^^^^^^^^^^^^^^^^^^^^ + +These are built-in iteration types that are included in Python's C API, but +provide no additional functions. They are here for completeness. + + +.. list-table:: + :widths: auto + :header-rows: 1 + + * * C type + * Python type + * * .. c:var:: PyTypeObject PyEnum_Type + * :py:class:`enumerate` + * * .. c:var:: PyTypeObject PyFilter_Type + * :py:class:`filter` + * * .. c:var:: PyTypeObject PyMap_Type + * :py:class:`map` + * * .. c:var:: PyTypeObject PyReversed_Type + * :py:class:`reversed` + * * .. c:var:: PyTypeObject PyZip_Type + * :py:class:`zip` + + +Other Iterator Objects +^^^^^^^^^^^^^^^^^^^^^^ + +.. c:var:: PyTypeObject PyByteArrayIter_Type +.. c:var:: PyTypeObject PyBytesIter_Type +.. c:var:: PyTypeObject PyListIter_Type +.. c:var:: PyTypeObject PyListRevIter_Type +.. c:var:: PyTypeObject PySetIter_Type +.. c:var:: PyTypeObject PyTupleIter_Type +.. c:var:: PyTypeObject PyRangeIter_Type +.. c:var:: PyTypeObject PyLongRangeIter_Type +.. c:var:: PyTypeObject PyDictIterKey_Type +.. c:var:: PyTypeObject PyDictRevIterKey_Type +.. c:var:: PyTypeObject PyDictIterValue_Type +.. c:var:: PyTypeObject PyDictRevIterValue_Type +.. c:var:: PyTypeObject PyDictIterItem_Type +.. c:var:: PyTypeObject PyDictRevIterItem_Type +.. c:var:: PyTypeObject PyODictIter_Type + + Type objects for iterators of various built-in objects. + + Do not create instances of these directly; prefer calling + :c:func:`PyObject_GetIter` instead. + + Note that there is no guarantee that a given built-in type uses a given iterator + type. For example, iterating over :class:`range` will use one of two iterator + types depending on the size of the range. Other types may start using a + similar scheme in the future, without warning. diff --git a/Doc/c-api/lifecycle.dot b/Doc/c-api/lifecycle.dot new file mode 100644 index 00000000000000..dca9f87e9e0aca --- /dev/null +++ b/Doc/c-api/lifecycle.dot @@ -0,0 +1,156 @@ +digraph "Life Events" { + graph [ + fontnames="svg" + fontsize=12.0 + id="life_events_graph" + layout="dot" + margin="0,0" + ranksep=0.25 + stylesheet="lifecycle.dot.css" + ] + node [ + fontname="Courier" + fontsize=12.0 + ] + edge [ + fontname="Times-Italic" + fontsize=12.0 + ] + + "start" [fontname="Times-Italic" shape=plain label=< start > style=invis] + { + rank="same" + "tp_new" [href="typeobj.html#c.PyTypeObject.tp_new" target="_top"] + "tp_alloc" [href="typeobj.html#c.PyTypeObject.tp_alloc" target="_top"] + } + "tp_init" [href="typeobj.html#c.PyTypeObject.tp_init" target="_top"] + "reachable" [fontname="Times-Italic" shape=box] + "tp_traverse" [ + href="typeobj.html#c.PyTypeObject.tp_traverse" + ordering="in" + target="_top" + ] + "finalized?" [ + fontname="Times-Italic" + label=finalized?> + ordering="in" + shape=diamond + tooltip="marked as finalized?" + ] + "tp_finalize" [ + href="typeobj.html#c.PyTypeObject.tp_finalize" + ordering="in" + target="_top" + ] + "tp_clear" [href="typeobj.html#c.PyTypeObject.tp_clear" target="_top"] + "uncollectable" [ + fontname="Times-Italic" + label=(leaked)> + shape=box + tooltip="uncollectable (leaked)" + ] + "tp_dealloc" [ + href="typeobj.html#c.PyTypeObject.tp_dealloc" + ordering="in" + target="_top" + ] + "tp_free" [href="typeobj.html#c.PyTypeObject.tp_free" target="_top"] + + "start" -> "tp_new" [ + label=< type call > + ] + "tp_new" -> "tp_alloc" [ + label=< direct call > arrowhead=empty + labeltooltip="tp_new to tp_alloc: direct call" + tooltip="tp_new to tp_alloc: direct call" + ] + "tp_new" -> "tp_init" [tooltip="tp_new to tp_init"] + "tp_init" -> "reachable" [tooltip="tp_init to reachable"] + "reachable" -> "tp_traverse" [ + dir="back" + label=< not in a
cyclic
isolate > + labeltooltip="tp_traverse to reachable: not in a cyclic isolate" + tooltip="tp_traverse to reachable: not in a cyclic isolate" + ] + "reachable" -> "tp_traverse" [ + label=< periodic
cyclic isolate
detection > + labeltooltip="reachable to tp_traverse: periodic cyclic isolate detection" + tooltip="reachable to tp_traverse: periodic cyclic isolate detection" + ] + "reachable" -> "tp_init" [tooltip="reachable to tp_init"] + "reachable" -> "tp_finalize" [ + dir="back" + label=< resurrected
(maybe remove
finalized mark) > + labeltooltip="tp_finalize to reachable: resurrected (maybe remove finalized mark)" + tooltip="tp_finalize to reachable: resurrected (maybe remove finalized mark)" + ] + "tp_traverse" -> "finalized?" [ + label=< cyclic
isolate > + labeltooltip="tp_traverse to finalized?: cyclic isolate" + tooltip="tp_traverse to finalized?: cyclic isolate" + ] + "reachable" -> "finalized?" [ + label=< no refs > + labeltooltip="reachable to finalized?: no refs" + tooltip="reachable to finalized?: no refs" + ] + "finalized?" -> "tp_finalize" [ + label=< no (mark
as finalized) > + labeltooltip="finalized? to tp_finalize: no (mark as finalized)" + tooltip="finalized? to tp_finalize: no (mark as finalized)" + ] + "finalized?" -> "tp_clear" [ + label=< yes > + labeltooltip="finalized? to tp_clear: yes" + tooltip="finalized? to tp_clear: yes" + ] + "tp_finalize" -> "tp_clear" [ + label=< no refs or
cyclic isolate > + labeltooltip="tp_finalize to tp_clear: no refs or cyclic isolate" + tooltip="tp_finalize to tp_clear: no refs or cyclic isolate" + ] + "tp_finalize" -> "tp_dealloc" [ + arrowtail=empty + dir="back" + href="lifecycle.html#c.PyObject_CallFinalizerFromDealloc" + style=dashed + label=< recommended
call (see
explanation)> + labeltooltip="tp_dealloc to tp_finalize: recommended call (see explanation)" + target="_top" + tooltip="tp_dealloc to tp_finalize: recommended call (see explanation)" + ] + "tp_finalize" -> "tp_dealloc" [ + label=< no refs > + labeltooltip="tp_finalize to tp_dealloc: no refs" + tooltip="tp_finalize to tp_dealloc: no refs" + ] + "tp_clear" -> "tp_dealloc" [ + label=< no refs > + labeltooltip="tp_clear to tp_dealloc: no refs" + tooltip="tp_clear to tp_dealloc: no refs" + ] + "tp_clear" -> "uncollectable" [ + label=< cyclic
isolate > + labeltooltip="tp_clear to uncollectable: cyclic isolate" + tooltip="tp_clear to uncollectable: cyclic isolate" + ] + "uncollectable" -> "tp_dealloc" [ + style=invis + tooltip="uncollectable to tp_dealloc" + ] + "reachable" -> "uncollectable" [ + label=< cyclic
isolate
(no GC
support) > + labeltooltip="reachable to uncollectable: cyclic isolate (no GC support)" + tooltip="reachable to uncollectable: cyclic isolate (no GC support)" + ] + "reachable" -> "tp_dealloc" [ + label=< no refs> + labeltooltip="reachable to tp_dealloc: no refs" + ] + "tp_dealloc" -> "tp_free" [ + arrowhead=empty + label=< direct call > + labeltooltip="tp_dealloc to tp_free: direct call" + tooltip="tp_dealloc to tp_free: direct call" + ] +} diff --git a/Doc/c-api/lifecycle.dot.css b/Doc/c-api/lifecycle.dot.css new file mode 100644 index 00000000000000..3abf95b74da6ba --- /dev/null +++ b/Doc/c-api/lifecycle.dot.css @@ -0,0 +1,21 @@ +#life_events_graph { + --svg-fgcolor: currentcolor; + --svg-bgcolor: transparent; +} +#life_events_graph a { + color: inherit; +} +#life_events_graph [stroke="black"] { + stroke: var(--svg-fgcolor); +} +#life_events_graph text, +#life_events_graph [fill="black"] { + fill: var(--svg-fgcolor); +} +#life_events_graph [fill="white"] { + fill: var(--svg-bgcolor); +} +#life_events_graph [fill="none"] { + /* On links, setting fill will make the entire shape clickable */ + fill: var(--svg-bgcolor); +} diff --git a/Doc/c-api/lifecycle.dot.svg b/Doc/c-api/lifecycle.dot.svg new file mode 100644 index 00000000000000..7ace27dfcba113 --- /dev/null +++ b/Doc/c-api/lifecycle.dot.svg @@ -0,0 +1,374 @@ + + + + + + + +Life Events + + + + +tp_new + + +tp_new + + + + + +start->tp_new + + + + + + +    type call   + + + + + +tp_alloc + + +tp_alloc + + + + + +tp_new->tp_alloc + + + + + + +  direct call   + + + + + +tp_init + + +tp_init + + + + + +tp_new->tp_init + + + + + + + + +reachable + +reachable + + + +tp_init->reachable + + + + + + + + +reachable->tp_init + + + + + + + + +tp_traverse + + +tp_traverse + + + + + +reachable->tp_traverse + + + + + + +  not in a   +  cyclic   +  isolate   + + + + + +reachable->tp_traverse + + + + + + +  periodic   +  cyclic isolate    +  detection   + + + + + +finalized? + + +marked as +finalized? + + + + + +reachable->finalized? + + + + + + +  no refs   + + + + + +tp_finalize + + +tp_finalize + + + + + +reachable->tp_finalize + + + + + + +  resurrected   +  (maybe remove   +  finalized mark)   + + + + + +uncollectable + + +uncollectable +(leaked) + + + + + +reachable->uncollectable + + + + + + +  cyclic   +  isolate   +  (no GC   +  support)   + + + + + +tp_dealloc + + +tp_dealloc + + + + + +reachable->tp_dealloc + + + +  no refs + + + + + +tp_traverse->finalized? + + + + + + +  cyclic   +  isolate   + + + + + +finalized?->tp_finalize + + + + + + +  no (mark   +  as finalized)   + + + + + +tp_clear + + +tp_clear + + + + + +finalized?->tp_clear + + + + + + +  yes   + + + + + +tp_finalize->tp_clear + + + + + + +  no refs or    +  cyclic isolate   + + + + + +tp_finalize->tp_dealloc + + + + + + +  recommended +  call (see +  explanation) + + + + + +tp_finalize->tp_dealloc + + + + + + +   no refs   + + + + + +tp_clear->uncollectable + + + + + + +  cyclic   +  isolate   + + + + + +tp_clear->tp_dealloc + + + + + + +  no refs   + + + + + + +tp_free + + +tp_free + + + + + +tp_dealloc->tp_free + + + + + + +    direct call   + + + + + diff --git a/Doc/c-api/lifecycle.rst b/Doc/c-api/lifecycle.rst new file mode 100644 index 00000000000000..5e3dca29f2ad90 --- /dev/null +++ b/Doc/c-api/lifecycle.rst @@ -0,0 +1,268 @@ +.. highlight:: c + +.. _life-cycle: + +Object Life Cycle +================= + +This section explains how a type's slots relate to each other throughout the +life of an object. It is not intended to be a complete canonical reference for +the slots; instead, refer to the slot-specific documentation in +:ref:`type-structs` for details about a particular slot. + + +Life Events +----------- + +The figure below illustrates the order of events that can occur throughout an +object's life. An arrow from *A* to *B* indicates that event *B* can occur +after event *A* has occurred, with the arrow's label indicating the condition +that must be true for *B* to occur after *A*. + +.. only:: builder_html + + .. raw:: html + + + + .. raw:: html + :file: lifecycle.dot.svg + + .. raw:: html + + + +.. only:: not builder_html + + .. image:: lifecycle.dot.svg + :align: center + :class: invert-in-dark-mode + :alt: Diagram showing events in an object's life. Explained in detail below. + +.. container:: + :name: life-events-graph-description + + Explanation: + + * When a new object is constructed by calling its type: + + #. :c:member:`~PyTypeObject.tp_new` is called to create a new object. + #. :c:member:`~PyTypeObject.tp_alloc` is directly called by + :c:member:`~PyTypeObject.tp_new` to allocate the memory for the new + object. + #. :c:member:`~PyTypeObject.tp_init` initializes the newly created object. + :c:member:`!tp_init` can be called again to re-initialize an object, if + desired. The :c:member:`!tp_init` call can also be skipped entirely, + for example by Python code calling :py:meth:`~object.__new__`. + + * After :c:member:`!tp_init` completes, the object is ready to use. + * Some time after the last reference to an object is removed: + + #. If an object is not marked as *finalized*, it might be finalized by + marking it as *finalized* and calling its + :c:member:`~PyTypeObject.tp_finalize` function. Python does + *not* finalize an object when the last reference to it is deleted; use + :c:func:`PyObject_CallFinalizerFromDealloc` to ensure that + :c:member:`~PyTypeObject.tp_finalize` is always called. + #. If the object is marked as finalized, + :c:member:`~PyTypeObject.tp_clear` might be called by the garbage collector + to clear references held by the object. It is *not* called when the + object's reference count reaches zero. + #. :c:member:`~PyTypeObject.tp_dealloc` is called to destroy the object. + To avoid code duplication, :c:member:`~PyTypeObject.tp_dealloc` typically + calls into :c:member:`~PyTypeObject.tp_clear` to free up the object's + references. + #. When :c:member:`~PyTypeObject.tp_dealloc` finishes object destruction, + it directly calls :c:member:`~PyTypeObject.tp_free` (usually set to + :c:func:`PyObject_Free` or :c:func:`PyObject_GC_Del` automatically as + appropriate for the type) to deallocate the memory. + + * The :c:member:`~PyTypeObject.tp_finalize` function is permitted to add a + reference to the object if desired. If it does, the object is + *resurrected*, preventing its pending destruction. (Only + :c:member:`!tp_finalize` is allowed to resurrect an object; + :c:member:`~PyTypeObject.tp_clear` and + :c:member:`~PyTypeObject.tp_dealloc` cannot without calling into + :c:member:`!tp_finalize`.) Resurrecting an object may + or may not cause the object's *finalized* mark to be removed. Currently, + Python does not remove the *finalized* mark from a resurrected object if + it supports garbage collection (i.e., the :c:macro:`Py_TPFLAGS_HAVE_GC` + flag is set) but does remove the mark if the object does not support + garbage collection; either or both of these behaviors may change in the + future. + * :c:member:`~PyTypeObject.tp_dealloc` can optionally call + :c:member:`~PyTypeObject.tp_finalize` via + :c:func:`PyObject_CallFinalizerFromDealloc` if it wishes to reuse that + code to help with object destruction. This is recommended because it + guarantees that :c:member:`!tp_finalize` is always called before + destruction. See the :c:member:`~PyTypeObject.tp_dealloc` documentation + for example code. + * If the object is a member of a :term:`cyclic isolate` and either + :c:member:`~PyTypeObject.tp_clear` fails to break the reference cycle or + the cyclic isolate is not detected (perhaps :func:`gc.disable` was called, + or the :c:macro:`Py_TPFLAGS_HAVE_GC` flag was erroneously omitted in one + of the involved types), the objects remain indefinitely uncollectable + (they "leak"). See :data:`gc.garbage`. + + If the object is marked as supporting garbage collection (the + :c:macro:`Py_TPFLAGS_HAVE_GC` flag is set in + :c:member:`~PyTypeObject.tp_flags`), the following events are also possible: + + * The garbage collector occasionally calls + :c:member:`~PyTypeObject.tp_traverse` to identify :term:`cyclic isolates + `. + * When the garbage collector discovers a :term:`cyclic isolate`, it + finalizes one of the objects in the group by marking it as *finalized* and + calling its :c:member:`~PyTypeObject.tp_finalize` function, if it has one. + This repeats until the cyclic isolate doesn't exist or all of the objects + have been finalized. + * :c:member:`~PyTypeObject.tp_finalize` is permitted to resurrect the object + by adding a reference from outside the :term:`cyclic isolate`. The new + reference causes the group of objects to no longer form a cyclic isolate + (the reference cycle may still exist, but if it does the objects are no + longer isolated). + * When the garbage collector discovers a :term:`cyclic isolate` and all of + the objects in the group have already been marked as *finalized*, the + garbage collector clears one or more of the uncleared objects in the group + (possibly concurrently) by calling each's + :c:member:`~PyTypeObject.tp_clear` function. This repeats as long as the + cyclic isolate still exists and not all of the objects have been cleared. + + +Cyclic Isolate Destruction +-------------------------- + +Listed below are the stages of life of a hypothetical :term:`cyclic isolate` +that continues to exist after each member object is finalized or cleared. It +is a memory leak if a cyclic isolate progresses through all of these stages; it should +vanish once all objects are cleared, if not sooner. A cyclic isolate can +vanish either because the reference cycle is broken or because the objects are +no longer isolated due to finalizer resurrection (see +:c:member:`~PyTypeObject.tp_finalize`). + +0. **Reachable** (not yet a cyclic isolate): All objects are in their normal, + reachable state. A reference cycle could exist, but an external reference + means the objects are not yet isolated. +#. **Unreachable but consistent:** The final reference from outside the cyclic + group of objects has been removed, causing the objects to become isolated + (thus a cyclic isolate is born). None of the group's objects have been + finalized or cleared yet. The cyclic isolate remains at this stage until + some future run of the garbage collector (not necessarily the next run + because the next run might not scan every object). +#. **Mix of finalized and not finalized:** Objects in a cyclic isolate are + finalized one at a time, which means that there is a period of time when the + cyclic isolate is composed of a mix of finalized and non-finalized objects. + Finalization order is unspecified, so it can appear random. A finalized + object must behave in a sane manner when non-finalized objects interact with + it, and a non-finalized object must be able to tolerate the finalization of + an arbitrary subset of its referents. +#. **All finalized:** All objects in a cyclic isolate are finalized before any + of them are cleared. +#. **Mix of finalized and cleared:** The objects can be cleared serially or + concurrently (but with the :term:`GIL` held); either way, some will finish + before others. A finalized object must be able to tolerate the clearing of + a subset of its referents. :pep:`442` calls this stage "cyclic trash". +#. **Leaked:** If a cyclic isolate still exists after all objects in the group + have been finalized and cleared, then the objects remain indefinitely + uncollectable (see :data:`gc.garbage`). It is a bug if a cyclic isolate + reaches this stage---it means the :c:member:`~PyTypeObject.tp_clear` methods + of the participating objects have failed to break the reference cycle as + required. + +If :c:member:`~PyTypeObject.tp_clear` did not exist, then Python would have no +way to safely break a reference cycle. Simply destroying an object in a cyclic +isolate would result in a dangling pointer, triggering undefined behavior when +an object referencing the destroyed object is itself destroyed. The clearing +step makes object destruction a two-phase process: first +:c:member:`~PyTypeObject.tp_clear` is called to partially destroy the objects +enough to detangle them from each other, then +:c:member:`~PyTypeObject.tp_dealloc` is called to complete the destruction. + +Unlike clearing, finalization is not a phase of destruction. A finalized +object must still behave properly by continuing to fulfill its design +contracts. An object's finalizer is allowed to execute arbitrary Python code, +and is even allowed to prevent the impending destruction by adding a reference. +The finalizer is only related to destruction by call order---if it runs, it runs +before destruction, which starts with :c:member:`~PyTypeObject.tp_clear` (if +called) and concludes with :c:member:`~PyTypeObject.tp_dealloc`. + +The finalization step is not necessary to safely reclaim the objects in a +cyclic isolate, but its existence makes it easier to design types that behave +in a sane manner when objects are cleared. Clearing an object might +necessarily leave it in a broken, partially destroyed state---it might be +unsafe to call any of the cleared object's methods or access any of its +attributes. With finalization, only finalized objects can possibly interact +with cleared objects; non-finalized objects are guaranteed to interact with +only non-cleared (but potentially finalized) objects. + +To summarize the possible interactions: + +* A non-finalized object might have references to or from non-finalized and + finalized objects, but not to or from cleared objects. +* A finalized object might have references to or from non-finalized, finalized, + and cleared objects. +* A cleared object might have references to or from finalized and cleared + objects, but not to or from non-finalized objects. + +Without any reference cycles, an object can be simply destroyed once its last +reference is deleted; the finalization and clearing steps are not necessary to +safely reclaim unused objects. However, it can be useful to automatically call +:c:member:`~PyTypeObject.tp_finalize` and :c:member:`~PyTypeObject.tp_clear` +before destruction anyway because type design is simplified when all objects +always experience the same series of events regardless of whether they +participated in a cyclic isolate. Python currently only calls +:c:member:`~PyTypeObject.tp_finalize` and :c:member:`~PyTypeObject.tp_clear` as +needed to destroy a cyclic isolate; this may change in a future version. + + +Functions +--------- + +To allocate and free memory, see :ref:`allocating-objects`. + + +.. c:function:: void PyObject_CallFinalizer(PyObject *op) + + Finalizes the object as described in :c:member:`~PyTypeObject.tp_finalize`. + Call this function (or :c:func:`PyObject_CallFinalizerFromDealloc`) instead + of calling :c:member:`~PyTypeObject.tp_finalize` directly because this + function may deduplicate multiple calls to :c:member:`!tp_finalize`. + Currently, calls are only deduplicated if the type supports garbage + collection (i.e., the :c:macro:`Py_TPFLAGS_HAVE_GC` flag is set); this may + change in the future. + + .. versionadded:: 3.4 + + +.. c:function:: int PyObject_CallFinalizerFromDealloc(PyObject *op) + + Same as :c:func:`PyObject_CallFinalizer` but meant to be called at the + beginning of the object's destructor (:c:member:`~PyTypeObject.tp_dealloc`). + There must not be any references to the object. If the object's finalizer + resurrects the object, this function returns -1; no further destruction + should happen. Otherwise, this function returns 0 and destruction can + continue normally. + + .. versionadded:: 3.4 + + .. seealso:: + + :c:member:`~PyTypeObject.tp_dealloc` for example code. diff --git a/Doc/c-api/list.rst b/Doc/c-api/list.rst index 758415a76e5cb4..21769c4c5c869c 100644 --- a/Doc/c-api/list.rst +++ b/Doc/c-api/list.rst @@ -74,11 +74,25 @@ List Objects Like :c:func:`PyList_GetItemRef`, but returns a :term:`borrowed reference` instead of a :term:`strong reference`. + .. note:: + + In the :term:`free-threaded build`, the returned + :term:`borrowed reference` may become invalid if another thread modifies + the list concurrently. Prefer :c:func:`PyList_GetItemRef`, which returns + a :term:`strong reference`. + .. c:function:: PyObject* PyList_GET_ITEM(PyObject *list, Py_ssize_t i) Similar to :c:func:`PyList_GetItem`, but without error checking. + .. note:: + + In the :term:`free-threaded build`, the returned + :term:`borrowed reference` may become invalid if another thread modifies + the list concurrently. Prefer :c:func:`PyList_GetItemRef`, which returns + a :term:`strong reference`. + .. c:function:: int PyList_SetItem(PyObject *list, Py_ssize_t index, PyObject *item) @@ -88,8 +102,10 @@ List Objects .. note:: - This function "steals" a reference to *item* and discards a reference to - an item already in the list at the affected position. + This function ":term:`steals `" a reference to *item*, + even on error. + On success, it discards a reference to an item already in the list + at the affected position (unless it was ``NULL``). .. c:function:: void PyList_SET_ITEM(PyObject *list, Py_ssize_t i, PyObject *o) @@ -103,11 +119,19 @@ List Objects .. note:: - This macro "steals" a reference to *item*, and, unlike + This macro ":term:`steals `" a reference to *item*, and, unlike :c:func:`PyList_SetItem`, does *not* discard a reference to any item that is being replaced; any reference in *list* at position *i* will be leaked. + .. note:: + + In the :term:`free-threaded build`, this macro has no internal + synchronization. It is normally only used to fill in new lists where no + other thread has a reference to the list. If the list may be shared, + use :c:func:`PyList_SetItem` instead, which uses a :term:`per-object + lock`. + .. c:function:: int PyList_Insert(PyObject *list, Py_ssize_t index, PyObject *item) @@ -138,6 +162,12 @@ List Objects Return ``0`` on success, ``-1`` on failure. Indexing from the end of the list is not supported. + .. note:: + + In the :term:`free-threaded build`, when *itemlist* is a :class:`list`, + both *list* and *itemlist* are locked for the duration of the operation. + For other iterables (or ``NULL``), only *list* is locked. + .. c:function:: int PyList_Extend(PyObject *list, PyObject *iterable) @@ -150,6 +180,14 @@ List Objects .. versionadded:: 3.13 + .. note:: + + In the :term:`free-threaded build`, when *iterable* is a :class:`list`, + :class:`set`, :class:`dict`, or dict view, both *list* and *iterable* + (or its underlying dict) are locked for the duration of the operation. + For other iterables, only *list* is locked; *iterable* may be + concurrently modified by another thread. + .. c:function:: int PyList_Clear(PyObject *list) @@ -168,6 +206,14 @@ List Objects Sort the items of *list* in place. Return ``0`` on success, ``-1`` on failure. This is equivalent to ``list.sort()``. + .. note:: + + In the :term:`free-threaded build`, element comparison via + :meth:`~object.__lt__` can execute arbitrary Python code, during which + the :term:`per-object lock` may be temporarily released. For built-in + types (:class:`str`, :class:`int`, :class:`float`), the lock is not + released during comparison. + .. c:function:: int PyList_Reverse(PyObject *list) diff --git a/Doc/c-api/long.rst b/Doc/c-api/long.rst index 25d9e62e387279..f026fd6561d8da 100644 --- a/Doc/c-api/long.rst +++ b/Doc/c-api/long.rst @@ -40,9 +40,11 @@ distinguished from a number. Use :c:func:`PyErr_Occurred` to disambiguate. Return a new :c:type:`PyLongObject` object from *v*, or ``NULL`` on failure. - The current implementation keeps an array of integer objects for all integers - between ``-5`` and ``256``. When you create an int in that range you actually - just get back a reference to the existing object. + .. impl-detail:: + + CPython keeps an array of integer objects for all integers + between ``-5`` and ``256``. When you create an int in that range + you actually just get back a reference to the existing object. .. c:function:: PyObject* PyLong_FromUnsignedLong(unsigned long v) @@ -69,6 +71,12 @@ distinguished from a number. Use :c:func:`PyErr_Occurred` to disambiguate. on failure. +.. c:function:: PyObject* PyLong_FromUnsignedLongLong(unsigned long long v) + + Return a new :c:type:`PyLongObject` object from a C :c:expr:`unsigned long long`, + or ``NULL`` on failure. + + .. c:function:: PyObject* PyLong_FromInt32(int32_t value) PyObject* PyLong_FromInt64(int64_t value) @@ -79,12 +87,6 @@ distinguished from a number. Use :c:func:`PyErr_Occurred` to disambiguate. .. versionadded:: 3.14 -.. c:function:: PyObject* PyLong_FromUnsignedLongLong(unsigned long long v) - - Return a new :c:type:`PyLongObject` object from a C :c:expr:`unsigned long long`, - or ``NULL`` on failure. - - .. c:function:: PyObject* PyLong_FromUInt32(uint32_t value) PyObject* PyLong_FromUInt64(uint64_t value) @@ -159,6 +161,17 @@ distinguished from a number. Use :c:func:`PyErr_Occurred` to disambiguate. .. versionadded:: 3.13 +.. c:macro:: PyLong_FromPid(pid) + + Macro for creating a Python integer from a process identifier. + + This can be defined as an alias to :c:func:`PyLong_FromLong` or + :c:func:`PyLong_FromLongLong`, depending on the size of the system's + PID type. + + .. versionadded:: 3.2 + + .. c:function:: long PyLong_AsLong(PyObject *obj) .. index:: @@ -184,12 +197,10 @@ distinguished from a number. Use :c:func:`PyErr_Occurred` to disambiguate. .. c:function:: long PyLong_AS_LONG(PyObject *obj) - A :term:`soft deprecated` alias. Exactly equivalent to the preferred ``PyLong_AsLong``. In particular, it can fail with :exc:`OverflowError` or another exception. - .. deprecated:: 3.14 - The function is soft deprecated. + .. soft-deprecated:: 3.14 .. c:function:: int PyLong_AsInt(PyObject *obj) @@ -372,6 +383,10 @@ distinguished from a number. Use :c:func:`PyErr_Occurred` to disambiguate. Set *\*value* to a signed C :c:expr:`int32_t` or :c:expr:`int64_t` representation of *obj*. + If *obj* is not an instance of :c:type:`PyLongObject`, first call its + :meth:`~object.__index__` method (if present) to convert it to a + :c:type:`PyLongObject`. + If the *obj* value is out of range, raise an :exc:`OverflowError`. Set *\*value* and return ``0`` on success. @@ -436,10 +451,10 @@ distinguished from a number. Use :c:func:`PyErr_Occurred` to disambiguate. Otherwise, returns the number of bytes required to store the value. If this is equal to or less than *n_bytes*, the entire value was copied. - All *n_bytes* of the buffer are written: large buffers are padded with - zeroes. + All *n_bytes* of the buffer are written: remaining bytes filled by + copies of the sign bit. - If the returned value is greater than than *n_bytes*, the value was + If the returned value is greater than *n_bytes*, the value was truncated: as many of the lowest bits of the value as could fit are written, and the higher bits are ignored. This matches the typical behavior of a C-style downcast. @@ -569,6 +584,17 @@ distinguished from a number. Use :c:func:`PyErr_Occurred` to disambiguate. .. versionadded:: 3.13 +.. c:macro:: PyLong_AsPid(pid) + + Macro for converting a Python integer into a process identifier. + + This can be defined as an alias to :c:func:`PyLong_AsLong`, + :c:func:`PyLong_FromLongLong`, or :c:func:`PyLong_AsInt`, depending on the + size of the system's PID type. + + .. versionadded:: 3.2 + + .. c:function:: int PyLong_GetSign(PyObject *obj, int *sign) Get the sign of the integer object *obj*. @@ -827,3 +853,31 @@ The :c:type:`PyLongWriter` API can be used to import an integer. If *writer* is ``NULL``, no operation is performed. The writer instance and the *digits* array are invalid after the call. + + +Deprecated API +^^^^^^^^^^^^^^ + +These macros are :term:`soft deprecated`. They describe parameters +of the internal representation of :c:type:`PyLongObject` instances. + +Use :c:func:`PyLong_GetNativeLayout` instead, along with :c:func:`PyLong_Export` +to read integer data or :c:type:`PyLongWriter` to write it. +These currently use the same layout, but are designed to continue working correctly +even if CPython's internal integer representation changes. + + +.. c:macro:: PyLong_SHIFT + + This is equivalent to :c:member:`~PyLongLayout.bits_per_digit` in + the output of :c:func:`PyLong_GetNativeLayout`. + + +.. c:macro:: PyLong_BASE + + This is currently equivalent to :c:expr:`1 << PyLong_SHIFT`. + + +.. c:macro:: PyLong_MASK + + This is currently equivalent to :c:expr:`(1 << PyLong_SHIFT) - 1` diff --git a/Doc/c-api/mapping.rst b/Doc/c-api/mapping.rst index 1f55c0aa955c75..2476ebb9b69dce 100644 --- a/Doc/c-api/mapping.rst +++ b/Doc/c-api/mapping.rst @@ -102,7 +102,7 @@ See also :c:func:`PyObject_GetItem`, :c:func:`PyObject_SetItem` and .. note:: - Exceptions which occur when this calls :meth:`~object.__getitem__` + Exceptions which occur when this calls the :meth:`~object.__getitem__` method are silently ignored. For proper error handling, use :c:func:`PyMapping_HasKeyWithError`, :c:func:`PyMapping_GetOptionalItem` or :c:func:`PyObject_GetItem()` instead. @@ -116,7 +116,7 @@ See also :c:func:`PyObject_GetItem`, :c:func:`PyObject_SetItem` and .. note:: - Exceptions that occur when this calls :meth:`~object.__getitem__` + Exceptions that occur when this calls the :meth:`~object.__getitem__` method or while creating the temporary :class:`str` object are silently ignored. For proper error handling, use :c:func:`PyMapping_HasKeyStringWithError`, diff --git a/Doc/c-api/marshal.rst b/Doc/c-api/marshal.rst index 61218a1bf6f171..668a163b2df5a1 100644 --- a/Doc/c-api/marshal.rst +++ b/Doc/c-api/marshal.rst @@ -82,7 +82,7 @@ The following functions allow marshalled values to be read back in. assumes that no further objects will be read from the file, allowing it to aggressively load file data into memory so that the de-serialization can operate from data in memory rather than reading a byte at a time from the - file. Only use these variant if you are certain that you won't be reading + file. Only use this variant if you are certain that you won't be reading anything else from the file. On error, sets the appropriate exception (:exc:`EOFError`, :exc:`ValueError` diff --git a/Doc/c-api/memory.rst b/Doc/c-api/memory.rst index 64ae35daa703b8..af77528f369562 100644 --- a/Doc/c-api/memory.rst +++ b/Doc/c-api/memory.rst @@ -81,7 +81,7 @@ memory footprint as a whole. Consequently, under certain circumstances, the Python memory manager may or may not trigger appropriate actions, like garbage collection, memory compaction or other preventive procedures. Note that by using the C library allocator as shown in the previous example, the allocated memory -for the I/O buffer escapes completely the Python memory manager. +for the I/O buffer completely escapes the Python memory manager. .. seealso:: @@ -102,7 +102,7 @@ All allocating functions belong to one of three different "domains" (see also strategies and are optimized for different purposes. The specific details on how every domain allocates memory or what internal functions each domain calls is considered an implementation detail, but for debugging purposes a simplified -table can be found at :ref:`here `. +table can be found at :ref:`default-memory-allocators`. The APIs used to allocate and free a block of memory must be from the same domain. For example, :c:func:`PyMem_Free` must be used to free memory allocated using :c:func:`PyMem_Malloc`. @@ -161,7 +161,7 @@ zero bytes. .. c:function:: void* PyMem_RawCalloc(size_t nelem, size_t elsize) - Allocates *nelem* elements each whose size in bytes is *elsize* and returns + Allocates *nelem* elements each of size *elsize* bytes and returns a pointer of type :c:expr:`void*` to the allocated memory, or ``NULL`` if the request fails. The memory is initialized to zeros. @@ -208,8 +208,11 @@ The following function sets, modeled after the ANSI C standard, but specifying behavior when requesting zero bytes, are available for allocating and releasing memory from the Python heap. -The :ref:`default memory allocator ` uses the -:ref:`pymalloc memory allocator `. +In the GIL-enabled build (default build) the +:ref:`default memory allocator ` uses the +:ref:`pymalloc memory allocator `, whereas in the +:term:`free-threaded build`, the default is the +:ref:`mimalloc memory allocator ` instead. .. warning:: @@ -219,6 +222,11 @@ The :ref:`default memory allocator ` uses the The default allocator is now pymalloc instead of system :c:func:`malloc`. +.. versionchanged:: 3.13 + + In the :term:`free-threaded ` build, the default allocator + is now :ref:`mimalloc `. + .. c:function:: void* PyMem_Malloc(size_t n) Allocates *n* bytes and returns a pointer of type :c:expr:`void*` to the @@ -231,7 +239,7 @@ The :ref:`default memory allocator ` uses the .. c:function:: void* PyMem_Calloc(size_t nelem, size_t elsize) - Allocates *nelem* elements each whose size in bytes is *elsize* and returns + Allocates *nelem* elements each of size *elsize* bytes and returns a pointer of type :c:expr:`void*` to the allocated memory, or ``NULL`` if the request fails. The memory is initialized to zeros. @@ -293,17 +301,39 @@ The following type-oriented macros are provided for convenience. Note that Same as :c:func:`PyMem_Free`. -In addition, the following macro sets are provided for calling the Python memory -allocator directly, without involving the C API functions listed above. However, -note that their use does not preserve binary compatibility across Python -versions and is therefore deprecated in extension modules. -* ``PyMem_MALLOC(size)`` -* ``PyMem_NEW(type, size)`` -* ``PyMem_REALLOC(ptr, size)`` -* ``PyMem_RESIZE(ptr, type, size)`` -* ``PyMem_FREE(ptr)`` -* ``PyMem_DEL(ptr)`` +Deprecated aliases +------------------ + +These are :term:`soft deprecated` aliases to existing functions and macros. +They exist solely for backwards compatibility. + +.. list-table:: + :widths: auto + :header-rows: 1 + + * * Deprecated alias + * Corresponding function or macro + * * .. c:macro:: PyMem_MALLOC(size) + * :c:func:`PyMem_Malloc` + * * .. c:macro:: PyMem_NEW(type, size) + * :c:macro:`PyMem_New` + * * .. c:macro:: PyMem_REALLOC(ptr, size) + * :c:func:`PyMem_Realloc` + * * .. c:macro:: PyMem_RESIZE(ptr, type, size) + * :c:macro:`PyMem_Resize` + * * .. c:macro:: PyMem_FREE(ptr) + * :c:func:`PyMem_Free` + * * .. c:macro:: PyMem_DEL(ptr) + * :c:func:`PyMem_Free` + +.. versionchanged:: 3.4 + + The macros are now aliases of the corresponding functions and macros. + Previously, their behavior was the same, but their use did not necessarily + preserve binary compatibility across Python versions. + +.. deprecated:: 2.0 .. _objectinterface: @@ -322,7 +352,9 @@ memory from the Python heap. the :ref:`Customize Memory Allocators ` section. The :ref:`default object allocator ` uses the -:ref:`pymalloc memory allocator `. +:ref:`pymalloc memory allocator `. In the +:term:`free-threaded ` build, the default is the +:ref:`mimalloc memory allocator ` instead. .. warning:: @@ -340,7 +372,7 @@ The :ref:`default object allocator ` uses the .. c:function:: void* PyObject_Calloc(size_t nelem, size_t elsize) - Allocates *nelem* elements each whose size in bytes is *elsize* and returns + Allocates *nelem* elements each of size *elsize* bytes and returns a pointer of type :c:expr:`void*` to the allocated memory, or ``NULL`` if the request fails. The memory is initialized to zeros. @@ -376,6 +408,24 @@ The :ref:`default object allocator ` uses the If *p* is ``NULL``, no operation is performed. + Do not call this directly to free an object's memory; call the type's + :c:member:`~PyTypeObject.tp_free` slot instead. + + Do not use this for memory allocated by :c:macro:`PyObject_GC_New` or + :c:macro:`PyObject_GC_NewVar`; use :c:func:`PyObject_GC_Del` instead. + + .. seealso:: + + * :c:func:`PyObject_GC_Del` is the equivalent of this function for memory + allocated by types that support garbage collection. + * :c:func:`PyObject_Malloc` + * :c:func:`PyObject_Realloc` + * :c:func:`PyObject_Calloc` + * :c:macro:`PyObject_New` + * :c:macro:`PyObject_NewVar` + * :c:func:`PyType_GenericAlloc` + * :c:member:`~PyTypeObject.tp_free` + .. _default-memory-allocators: @@ -384,14 +434,16 @@ Default Memory Allocators Default memory allocators: -=============================== ==================== ================== ===================== ==================== -Configuration Name PyMem_RawMalloc PyMem_Malloc PyObject_Malloc -=============================== ==================== ================== ===================== ==================== -Release build ``"pymalloc"`` ``malloc`` ``pymalloc`` ``pymalloc`` -Debug build ``"pymalloc_debug"`` ``malloc`` + debug ``pymalloc`` + debug ``pymalloc`` + debug -Release build, without pymalloc ``"malloc"`` ``malloc`` ``malloc`` ``malloc`` -Debug build, without pymalloc ``"malloc_debug"`` ``malloc`` + debug ``malloc`` + debug ``malloc`` + debug -=============================== ==================== ================== ===================== ==================== +=================================== ======================= ==================== ====================== ====================== +Configuration Name PyMem_RawMalloc PyMem_Malloc PyObject_Malloc +=================================== ======================= ==================== ====================== ====================== +Release build ``"pymalloc"`` ``malloc`` ``pymalloc`` ``pymalloc`` +Debug build ``"pymalloc_debug"`` ``malloc`` + debug ``pymalloc`` + debug ``pymalloc`` + debug +Release build, without pymalloc ``"malloc"`` ``malloc`` ``malloc`` ``malloc`` +Debug build, without pymalloc ``"malloc_debug"`` ``malloc`` + debug ``malloc`` + debug ``malloc`` + debug +Free-threaded build ``"mimalloc"`` ``mimalloc`` ``mimalloc`` ``mimalloc`` +Free-threaded debug build ``"mimalloc_debug"`` ``mimalloc`` + debug ``mimalloc`` + debug ``mimalloc`` + debug +=================================== ======================= ==================== ====================== ====================== Legend: @@ -399,8 +451,7 @@ Legend: * ``malloc``: system allocators from the standard C library, C functions: :c:func:`malloc`, :c:func:`calloc`, :c:func:`realloc` and :c:func:`free`. * ``pymalloc``: :ref:`pymalloc memory allocator `. -* ``mimalloc``: :ref:`mimalloc memory allocator `. The pymalloc - allocator will be used if mimalloc support isn't available. +* ``mimalloc``: :ref:`mimalloc memory allocator `. * "+ debug": with :ref:`debug hooks on the Python memory allocators `. * "Debug build": :ref:`Python build in debug mode `. @@ -654,6 +705,10 @@ This allocator is disabled if Python is configured with the :option:`--without-pymalloc` option. It can also be disabled at runtime using the :envvar:`PYTHONMALLOC` environment variable (ex: ``PYTHONMALLOC=malloc``). +Typically, it makes sense to disable the pymalloc allocator when building +Python with AddressSanitizer (:option:`--with-address-sanitizer`) which helps +uncover low level bugs within the C code. + Customize pymalloc Arena Allocator ---------------------------------- @@ -689,9 +744,27 @@ The mimalloc allocator .. versionadded:: 3.13 -Python supports the mimalloc allocator when the underlying platform support is available. -mimalloc "is a general purpose allocator with excellent performance characteristics. -Initially developed by Daan Leijen for the runtime systems of the Koka and Lean languages." +Python supports the `mimalloc `__ +allocator when the underlying platform support is available. +mimalloc is a general purpose allocator with excellent performance +characteristics, initially developed by Daan Leijen for the runtime systems +of the Koka and Lean languages. + +Unlike :ref:`pymalloc `, which is optimized for small objects (512 +bytes or fewer), mimalloc handles allocations of any size. + +In the :term:`free-threaded ` build, mimalloc is the default +and **required** allocator for the :c:macro:`PYMEM_DOMAIN_MEM` and +:c:macro:`PYMEM_DOMAIN_OBJ` domains. It cannot be disabled in free-threaded +builds. The free-threaded build uses per-thread mimalloc heaps, which allows +allocation and deallocation to proceed without locking in most cases. + +In the default (non-free-threaded) build, mimalloc is available but not the +default allocator. It can be selected at runtime using +:envvar:`PYTHONMALLOC`\ ``=mimalloc`` (or ``mimalloc_debug`` to include +:ref:`debug hooks `). It can be disabled at build time +using the :option:`--without-mimalloc` configure option, but this option +cannot be combined with :option:`--disable-gil`. tracemalloc C API ================= diff --git a/Doc/c-api/memoryview.rst b/Doc/c-api/memoryview.rst index f6038032805259..e4ac8b57673407 100644 --- a/Doc/c-api/memoryview.rst +++ b/Doc/c-api/memoryview.rst @@ -13,6 +13,12 @@ A :class:`memoryview` object exposes the C level :ref:`buffer interface any other object. +.. c:var:: PyTypeObject PyMemoryView_Type + + This instance of :c:type:`PyTypeObject` represents the Python memoryview + type. This is the same object as :class:`memoryview` in the Python layer. + + .. c:function:: PyObject *PyMemoryView_FromObject(PyObject *obj) Create a memoryview object from an object that provides the buffer interface. diff --git a/Doc/c-api/module.rst b/Doc/c-api/module.rst index f7f4d37d4c721f..51e81917b2cfeb 100644 --- a/Doc/c-api/module.rst +++ b/Doc/c-api/module.rst @@ -13,7 +13,7 @@ Module Objects .. index:: single: ModuleType (in module types) This instance of :c:type:`PyTypeObject` represents the Python module type. This - is exposed to Python programs as ``types.ModuleType``. + is exposed to Python programs as :py:class:`types.ModuleType`. .. c:function:: int PyModule_Check(PyObject *p) @@ -71,6 +71,9 @@ Module Objects ``PyObject_*`` functions rather than directly manipulate a module's :attr:`~object.__dict__`. + The returned reference is borrowed from the module; it is valid until + the module is destroyed. + .. c:function:: PyObject* PyModule_GetNameObject(PyObject *module) @@ -90,6 +93,10 @@ Module Objects Similar to :c:func:`PyModule_GetNameObject` but return the name encoded to ``'utf-8'``. + The returned buffer is only valid until the module is renamed or destroyed. + Note that Python code may rename a module by setting its :py:attr:`~module.__name__` + attribute. + .. c:function:: void* PyModule_GetState(PyObject *module) Return the "state" of the module, that is, a pointer to the block of memory @@ -102,6 +109,10 @@ Module Objects Return a pointer to the :c:type:`PyModuleDef` struct from which the module was created, or ``NULL`` if the module wasn't created from a definition. + On error, return ``NULL`` with an exception set. + Use :c:func:`PyErr_Occurred` to tell this case apart from a missing + :c:type:`!PyModuleDef`. + .. c:function:: PyObject* PyModule_GetFilenameObject(PyObject *module) @@ -122,30 +133,44 @@ Module Objects Similar to :c:func:`PyModule_GetFilenameObject` but return the filename encoded to 'utf-8'. + The returned buffer is only valid until the module's :py:attr:`~module.__file__` attribute + is reassigned or the module is destroyed. + .. deprecated:: 3.2 :c:func:`PyModule_GetFilename` raises :exc:`UnicodeEncodeError` on unencodable filenames, use :c:func:`PyModule_GetFilenameObject` instead. -.. _initializing-modules: +.. _pymoduledef: -Initializing C modules -^^^^^^^^^^^^^^^^^^^^^^ +Module definitions +------------------ -Modules objects are usually created from extension modules (shared libraries -which export an initialization function), or compiled-in modules -(where the initialization function is added using :c:func:`PyImport_AppendInittab`). -See :ref:`building` or :ref:`extending-with-embedding` for details. +The functions in the previous section work on any module object, including +modules imported from Python code. -The initialization function can either pass a module definition instance -to :c:func:`PyModule_Create`, and return the resulting module object, -or request "multi-phase initialization" by returning the definition struct itself. +Modules defined using the C API typically use a *module definition*, +:c:type:`PyModuleDef` -- a statically allocated, constant “description" of +how a module should be created. + +The definition is usually used to define an extension's “main” module object +(see :ref:`extension-modules` for details). +It is also used to +:ref:`create extension modules dynamically `. + +Unlike :c:func:`PyModule_New`, the definition allows management of +*module state* -- a piece of memory that is allocated and cleared together +with the module object. +Unlike the module's Python attributes, Python code cannot replace or delete +data stored in module state. .. c:type:: PyModuleDef The module definition struct, which holds all information needed to create - a module object. There is usually only one statically initialized variable - of this type for each module. + a module object. + This structure must be statically allocated (or be otherwise guaranteed + to be valid while any modules created from it exist). + Usually, there is only one variable of this type for each extension module. .. c:member:: PyModuleDef_Base m_base @@ -170,13 +195,15 @@ or request "multi-phase initialization" by returning the definition struct itsel and freed when the module object is deallocated, after the :c:member:`~PyModuleDef.m_free` function has been called, if present. - Setting ``m_size`` to ``-1`` means that the module does not support - sub-interpreters, because it has global state. - Setting it to a non-negative value means that the module can be re-initialized and specifies the additional amount of memory it requires - for its state. Non-negative ``m_size`` is required for multi-phase - initialization. + for its state. + + Setting ``m_size`` to ``-1`` means that the module does not support + sub-interpreters, because it has global state. + Negative ``m_size`` is only allowed when using + :ref:`legacy single-phase initialization ` + or when :ref:`creating modules dynamically `. See :PEP:`3121` for more details. @@ -189,7 +216,7 @@ or request "multi-phase initialization" by returning the definition struct itsel An array of slot definitions for multi-phase initialization, terminated by a ``{0, NULL}`` entry. - When using single-phase initialization, *m_slots* must be ``NULL``. + When using legacy single-phase initialization, *m_slots* must be ``NULL``. .. versionchanged:: 3.5 @@ -249,78 +276,14 @@ or request "multi-phase initialization" by returning the definition struct itsel .. versionchanged:: 3.9 No longer called before the module state is allocated. -Single-phase initialization -........................... - -The module initialization function may create and return the module object -directly. This is referred to as "single-phase initialization", and uses one -of the following two module creation functions: -.. c:function:: PyObject* PyModule_Create(PyModuleDef *def) - - Create a new module object, given the definition in *def*. This behaves - like :c:func:`PyModule_Create2` with *module_api_version* set to - :c:macro:`PYTHON_API_VERSION`. +.. c:var:: PyTypeObject PyModuleDef_Type + The type of ``PyModuleDef`` objects. -.. c:function:: PyObject* PyModule_Create2(PyModuleDef *def, int module_api_version) - - Create a new module object, given the definition in *def*, assuming the - API version *module_api_version*. If that version does not match the version - of the running interpreter, a :exc:`RuntimeWarning` is emitted. - Return ``NULL`` with an exception set on error. - - .. note:: - - Most uses of this function should be using :c:func:`PyModule_Create` - instead; only use this if you are sure you need it. - -Before it is returned from in the initialization function, the resulting module -object is typically populated using functions like :c:func:`PyModule_AddObjectRef`. - -.. _multi-phase-initialization: - -Multi-phase initialization -.......................... - -An alternate way to specify extensions is to request "multi-phase initialization". -Extension modules created this way behave more like Python modules: the -initialization is split between the *creation phase*, when the module object -is created, and the *execution phase*, when it is populated. -The distinction is similar to the :py:meth:`!__new__` and :py:meth:`!__init__` methods -of classes. - -Unlike modules created using single-phase initialization, these modules are not -singletons: if the *sys.modules* entry is removed and the module is re-imported, -a new module object is created, and the old module is subject to normal garbage -collection -- as with Python modules. -By default, multiple modules created from the same definition should be -independent: changes to one should not affect the others. -This means that all state should be specific to the module object (using e.g. -using :c:func:`PyModule_GetState`), or its contents (such as the module's -:attr:`~object.__dict__` or individual classes created with :c:func:`PyType_FromSpec`). - -All modules created using multi-phase initialization are expected to support -:ref:`sub-interpreters `. Making sure multiple modules -are independent is typically enough to achieve this. - -To request multi-phase initialization, the initialization function -(PyInit_modulename) returns a :c:type:`PyModuleDef` instance with non-empty -:c:member:`~PyModuleDef.m_slots`. Before it is returned, the ``PyModuleDef`` -instance must be initialized with the following function: - -.. c:function:: PyObject* PyModuleDef_Init(PyModuleDef *def) - - Ensures a module definition is a properly initialized Python object that - correctly reports its type and reference count. - - Returns *def* cast to ``PyObject*``, or ``NULL`` if an error occurred. - - .. versionadded:: 3.5 - -The *m_slots* member of the module definition must point to an array of -``PyModuleDef_Slot`` structures: +Module slots +............ .. c:type:: PyModuleDef_Slot @@ -334,8 +297,6 @@ The *m_slots* member of the module definition must point to an array of .. versionadded:: 3.5 -The *m_slots* array must be terminated by a slot with id 0. - The available slot types are: .. c:macro:: Py_mod_create @@ -372,6 +333,8 @@ The available slot types are: ``PyModuleDef`` has non-``NULL`` ``m_traverse``, ``m_clear``, ``m_free``; non-zero ``m_size``; or slots other than ``Py_mod_create``. + .. versionadded:: 3.5 + .. c:macro:: Py_mod_exec Specifies a function that is called to *execute* the module. @@ -386,6 +349,8 @@ The available slot types are: If multiple ``Py_mod_exec`` slots are specified, they are processed in the order they appear in the *m_slots* array. + .. versionadded:: 3.5 + .. c:macro:: Py_mod_multiple_interpreters Specifies one of the following values: @@ -446,21 +411,48 @@ The available slot types are: .. versionadded:: 3.13 -See :PEP:`489` for more details on multi-phase initialization. -Low-level module creation functions -................................... +.. _moduledef-dynamic: + +Creating extension modules dynamically +-------------------------------------- -The following functions are called under the hood when using multi-phase -initialization. They can be used directly, for example when creating module -objects dynamically. Note that both ``PyModule_FromDefAndSpec`` and -``PyModule_ExecDef`` must be called to fully initialize a module. +The following functions may be used to create a module outside of an +extension's :ref:`initialization function `. +They are also used in +:ref:`single-phase initialization `. + +.. c:function:: PyObject* PyModule_Create(PyModuleDef *def) + + Create a new module object, given the definition in *def*. + This is a macro that calls :c:func:`PyModule_Create2` with + *module_api_version* set to :c:macro:`PYTHON_API_VERSION`, or + to :c:macro:`PYTHON_ABI_VERSION` if using the + :ref:`limited API `. + +.. c:function:: PyObject* PyModule_Create2(PyModuleDef *def, int module_api_version) + + Create a new module object, given the definition in *def*, assuming the + API version *module_api_version*. If that version does not match the version + of the running interpreter, a :exc:`RuntimeWarning` is emitted. + + Return ``NULL`` with an exception set on error. + + This function does not support slots. + The :c:member:`~PyModuleDef.m_slots` member of *def* must be ``NULL``. + + + .. note:: + + Most uses of this function should be using :c:func:`PyModule_Create` + instead; only use this if you are sure you need it. .. c:function:: PyObject * PyModule_FromDefAndSpec(PyModuleDef *def, PyObject *spec) - Create a new module object, given the definition in *def* and the - ModuleSpec *spec*. This behaves like :c:func:`PyModule_FromDefAndSpec2` - with *module_api_version* set to :c:macro:`PYTHON_API_VERSION`. + This macro calls :c:func:`PyModule_FromDefAndSpec2` with + *module_api_version* set to :c:macro:`PYTHON_API_VERSION`, or + to :c:macro:`PYTHON_ABI_VERSION` if using the + :ref:`limited API `. .. versionadded:: 3.5 @@ -473,6 +465,10 @@ objects dynamically. Note that both ``PyModule_FromDefAndSpec`` and Return ``NULL`` with an exception set on error. + Note that this does not process execution slots (:c:data:`Py_mod_exec`). + Both ``PyModule_FromDefAndSpec`` and ``PyModule_ExecDef`` must be called + to fully initialize a module. + .. note:: Most uses of this function should be using :c:func:`PyModule_FromDefAndSpec` @@ -486,35 +482,29 @@ objects dynamically. Note that both ``PyModule_FromDefAndSpec`` and .. versionadded:: 3.5 -.. c:function:: int PyModule_SetDocString(PyObject *module, const char *docstring) +.. c:macro:: PYTHON_API_VERSION - Set the docstring for *module* to *docstring*. - This function is called automatically when creating a module from - ``PyModuleDef``, using either ``PyModule_Create`` or - ``PyModule_FromDefAndSpec``. + The C API version. Defined for backwards compatibility. - .. versionadded:: 3.5 + Currently, this constant is not updated in new Python versions, and is not + useful for versioning. This may change in the future. -.. c:function:: int PyModule_AddFunctions(PyObject *module, PyMethodDef *functions) +.. c:macro:: PYTHON_ABI_VERSION - Add the functions from the ``NULL`` terminated *functions* array to *module*. - Refer to the :c:type:`PyMethodDef` documentation for details on individual - entries (due to the lack of a shared module namespace, module level - "functions" implemented in C typically receive the module as their first - parameter, making them similar to instance methods on Python classes). - This function is called automatically when creating a module from - ``PyModuleDef``, using either ``PyModule_Create`` or - ``PyModule_FromDefAndSpec``. + Defined as ``3`` for backwards compatibility. + + Currently, this constant is not updated in new Python versions, and is not + useful for versioning. This may change in the future. - .. versionadded:: 3.5 Support functions -................. +----------------- -The module initialization function (if using single phase initialization) or -a function called from a module execution slot (if using multi-phase -initialization), can use the following functions to help initialize the module -state: +The following functions are provided to help initialize a module +state. +They are intended for a module's execution slots (:c:data:`Py_mod_exec`), +the initialization function for legacy :ref:`single-phase initialization `, +or code that creates modules dynamically. .. c:function:: int PyModule_AddObjectRef(PyObject *module, const char *name, PyObject *value) @@ -569,8 +559,8 @@ state: .. c:function:: int PyModule_Add(PyObject *module, const char *name, PyObject *value) - Similar to :c:func:`PyModule_AddObjectRef`, but "steals" a reference - to *value*. + Similar to :c:func:`PyModule_AddObjectRef`, but ":term:`steals `" + a reference to *value* (even on error). It can be called with a result of function that returns a new reference without bothering to check its result or even saving it to a variable. @@ -585,8 +575,8 @@ state: .. c:function:: int PyModule_AddObject(PyObject *module, const char *name, PyObject *value) - Similar to :c:func:`PyModule_AddObjectRef`, but steals a reference to - *value* on success (if it returns ``0``). + Similar to :c:func:`PyModule_AddObjectRef`, but :term:`steals ` + a reference to *value* on success (if it returns ``0``). The new :c:func:`PyModule_Add` or :c:func:`PyModule_AddObjectRef` functions are recommended, since it is @@ -614,9 +604,7 @@ state: // PyModule_AddObject() stole a reference to obj: // Py_XDECREF(obj) is not needed here. - .. deprecated:: 3.13 - - :c:func:`PyModule_AddObject` is :term:`soft deprecated`. + .. soft-deprecated:: 3.13 .. c:function:: int PyModule_AddIntConstant(PyObject *module, const char *name, long value) @@ -663,12 +651,45 @@ state: .. versionadded:: 3.9 +.. c:function:: int PyModule_AddFunctions(PyObject *module, PyMethodDef *functions) + + Add the functions from the ``NULL`` terminated *functions* array to *module*. + Refer to the :c:type:`PyMethodDef` documentation for details on individual + entries (due to the lack of a shared module namespace, module level + "functions" implemented in C typically receive the module as their first + parameter, making them similar to instance methods on Python classes). + + This function is called automatically when creating a module from + ``PyModuleDef`` (such as when using :ref:`multi-phase-initialization`, + ``PyModule_Create``, or ``PyModule_FromDefAndSpec``). + Some module authors may prefer defining functions in multiple + :c:type:`PyMethodDef` arrays; in that case they should call this function + directly. + + The *functions* array must be statically allocated (or otherwise guaranteed + to outlive the module object). + + .. versionadded:: 3.5 + +.. c:function:: int PyModule_SetDocString(PyObject *module, const char *docstring) + + Set the docstring for *module* to *docstring*. + This function is called automatically when creating a module from + ``PyModuleDef`` (such as when using :ref:`multi-phase-initialization`, + ``PyModule_Create``, or ``PyModule_FromDefAndSpec``). + + Return ``0`` on success. + Return ``-1`` with an exception set on error. + + .. versionadded:: 3.5 + .. c:function:: int PyUnstable_Module_SetGIL(PyObject *module, void *gil) Indicate that *module* does or does not support running without the global interpreter lock (GIL), using one of the values from :c:macro:`Py_mod_gil`. It must be called during *module*'s initialization - function. If this function is not called during module initialization, the + function when using :ref:`single-phase-initialization`. + If this function is not called during module initialization, the import machinery assumes the module does not support running without the GIL. This function is only available in Python builds configured with :option:`--disable-gil`. @@ -677,10 +698,11 @@ state: .. versionadded:: 3.13 -Module lookup -^^^^^^^^^^^^^ +Module lookup (single-phase initialization) +........................................... -Single-phase initialization creates singleton modules that can be looked up +The legacy :ref:`single-phase initialization ` +initialization scheme creates singleton modules that can be looked up in the context of the current interpreter. This allows the module object to be retrieved later with only a reference to the module definition. @@ -701,7 +723,8 @@ since multiple such modules can be created from a single definition. Only effective on modules created using single-phase initialization. - Python calls ``PyState_AddModule`` automatically after importing a module, + Python calls ``PyState_AddModule`` automatically after importing a module + that uses :ref:`single-phase initialization `, so it is unnecessary (but harmless) to call it from module initialization code. An explicit call is needed only if the module's own init code subsequently calls ``PyState_FindModule``. @@ -709,6 +732,9 @@ since multiple such modules can be created from a single definition. mechanisms (either by calling it directly, or by referring to its implementation for details of the required state updates). + If a module was attached previously using the same *def*, it is replaced + by the new *module*. + The caller must have an :term:`attached thread state`. Return ``-1`` with an exception set on error, ``0`` on success. diff --git a/Doc/c-api/monitoring.rst b/Doc/c-api/monitoring.rst index 7926148302af0b..4bfcb86abf58ed 100644 --- a/Doc/c-api/monitoring.rst +++ b/Doc/c-api/monitoring.rst @@ -136,7 +136,7 @@ Managing the Monitoring State ----------------------------- Monitoring states can be managed with the help of monitoring scopes. A scope -would typically correspond to a python function. +would typically correspond to a Python function. .. c:function:: int PyMonitoring_EnterScope(PyMonitoringState *state_array, uint64_t *version, const uint8_t *event_types, Py_ssize_t length) @@ -205,6 +205,4 @@ would typically correspond to a python function. .. versionadded:: 3.13 - .. deprecated:: 3.14 - - This function is :term:`soft deprecated`. + .. soft-deprecated:: 3.14 diff --git a/Doc/c-api/object.rst b/Doc/c-api/object.rst index 0fd159f1eb87f8..44e1220d109d05 100644 --- a/Doc/c-api/object.rst +++ b/Doc/c-api/object.rst @@ -73,7 +73,7 @@ Object Protocol Flag to be used with multiple functions that print the object (like :c:func:`PyObject_Print` and :c:func:`PyFile_WriteObject`). - If passed, these function would use the :func:`str` of the object + If passed, these functions use the :func:`str` of the object instead of the :func:`repr`. @@ -319,6 +319,8 @@ Object Protocol representation on success, ``NULL`` on failure. This is the equivalent of the Python expression ``repr(o)``. Called by the :func:`repr` built-in function. + If argument is ``NULL``, return the string ``''``. + .. versionchanged:: 3.4 This function now includes a debug assertion to help ensure that it does not silently discard an active exception. @@ -333,6 +335,8 @@ Object Protocol a string similar to that returned by :c:func:`PyObject_Repr` in Python 2. Called by the :func:`ascii` built-in function. + If argument is ``NULL``, return the string ``''``. + .. index:: string; PyObject_Str (C function) @@ -343,6 +347,8 @@ Object Protocol Python expression ``str(o)``. Called by the :func:`str` built-in function and, therefore, by the :func:`print` function. + If argument is ``NULL``, return the string ``''``. + .. versionchanged:: 3.4 This function now includes a debug assertion to help ensure that it does not silently discard an active exception. @@ -358,6 +364,8 @@ Object Protocol a TypeError is raised when *o* is an integer instead of a zero-initialized bytes object. + If argument is ``NULL``, return the :class:`bytes` object ``b''``. + .. c:function:: int PyObject_IsSubclass(PyObject *derived, PyObject *cls) @@ -585,7 +593,7 @@ Object Protocol Clear the managed dictionary of *obj*. - This function must only be called in a traverse function of the type which + This function must only be called in a clear function of the type which has the :c:macro:`Py_TPFLAGS_MANAGED_DICT` flag set. .. versionadded:: 3.13 @@ -596,12 +604,13 @@ Object Protocol if supported by the runtime. In the :term:`free-threaded ` build, this allows the interpreter to avoid reference count adjustments to *obj*, which may improve multi-threaded performance. The tradeoff is - that *obj* will only be deallocated by the tracing garbage collector. + that *obj* will only be deallocated by the tracing garbage collector, and + not when the interpreter no longer has any references to it. - This function returns ``1`` if deferred reference counting is enabled on *obj* - (including when it was enabled before the call), + This function returns ``1`` if deferred reference counting is enabled on *obj*, and ``0`` if deferred reference counting is not supported or if the hint was - ignored by the runtime. This function is thread-safe, and cannot fail. + ignored by the interpreter, such as when deferred reference counting is already + enabled on *obj*. This function is thread-safe, and cannot fail. This function does nothing on builds with the :term:`GIL` enabled, which do not support deferred reference counting. This also does nothing if *obj* is not @@ -609,7 +618,8 @@ Object Protocol :c:func:`PyObject_GC_IsTracked`). This function is intended to be used soon after *obj* is created, - by the code that creates it. + by the code that creates it, such as in the object's :c:member:`~PyTypeObject.tp_new` + slot. .. versionadded:: 3.14 @@ -665,10 +675,10 @@ Object Protocol :c:func:`PyUnstable_EnableTryIncRef` must have been called earlier on *obj* or this function may spuriously return ``0`` in the - :term:`free threading` build. + :term:`free-threaded build`. This function is logically equivalent to the following C code, except that - it behaves atomically in the :term:`free threading` build:: + it behaves atomically in the :term:`free-threaded build`:: if (Py_REFCNT(op) > 0) { Py_INCREF(op); @@ -745,10 +755,10 @@ Object Protocol On GIL-enabled builds, this function is equivalent to :c:expr:`Py_REFCNT(op) == 1`. - On a :term:`free threaded ` build, this checks if *op*'s + On a :term:`free-threaded build`, this checks if *op*'s :term:`reference count` is equal to one and additionally checks if *op* is only used by this thread. :c:expr:`Py_REFCNT(op) == 1` is **not** - thread-safe on free threaded builds; prefer this function. + thread-safe on free-threaded builds; prefer this function. The caller must hold an :term:`attached thread state`, despite the fact that this function doesn't call into the Python interpreter. This function diff --git a/Doc/c-api/objimpl.rst b/Doc/c-api/objimpl.rst index 8bd8c107c98bdf..83de4248039949 100644 --- a/Doc/c-api/objimpl.rst +++ b/Doc/c-api/objimpl.rst @@ -12,6 +12,7 @@ object types. .. toctree:: allocation.rst + lifecycle.rst structures.rst typeobj.rst gcsupport.rst diff --git a/Doc/c-api/perfmaps.rst b/Doc/c-api/perfmaps.rst index 77b5e3c0876bbb..68c2578906ff09 100644 --- a/Doc/c-api/perfmaps.rst +++ b/Doc/c-api/perfmaps.rst @@ -48,3 +48,43 @@ Note that holding an :term:`attached thread state` is not required for these API This is called by the runtime itself during interpreter shut-down. In general, there shouldn't be a reason to explicitly call this, except to handle specific scenarios such as forking. + +.. c:function:: int PyUnstable_CopyPerfMapFile(const char *parent_filename) + + Open the ``/tmp/perf-$pid.map`` file and append the content of *parent_filename* + to it. + + This function is available on all platforms but only generates output on platforms + that support perf maps (currently only Linux). On other platforms, it does nothing. + + .. versionadded:: 3.13 + +.. c:function:: int PyUnstable_PerfTrampoline_CompileCode(PyCodeObject *code) + + Compile the given code object using the current perf trampoline. + + The "current" trampoline is the one set by the runtime or the most recent + :c:func:`PyUnstable_PerfTrampoline_SetPersistAfterFork` call. + + If no trampoline is set, falls back to normal compilation (no perf map entry). + + :param code: The code object to compile. + :return: 0 on success, -1 on failure. + + .. versionadded:: 3.13 + +.. c:function:: int PyUnstable_PerfTrampoline_SetPersistAfterFork(int enable) + + Set whether the perf trampoline should persist after a fork. + + * If ``enable`` is true (non-zero): perf map file remains open/valid post-fork. + Child process inherits all existing perf map entries. + * If ``enable`` is false (zero): perf map closes post-fork. + Child process gets empty perf map. + + Default: false (clears on fork). + + :param enable: 1 to enable, 0 to disable. + :return: 0 on success, -1 on failure. + + .. versionadded:: 3.13 diff --git a/Doc/c-api/picklebuffer.rst b/Doc/c-api/picklebuffer.rst new file mode 100644 index 00000000000000..9e2d92341b0f93 --- /dev/null +++ b/Doc/c-api/picklebuffer.rst @@ -0,0 +1,59 @@ +.. highlight:: c + +.. _picklebuffer-objects: + +.. index:: + pair: object; PickleBuffer + +Pickle buffer objects +--------------------- + +.. versionadded:: 3.8 + +A :class:`pickle.PickleBuffer` object wraps a :ref:`buffer-providing object +` for out-of-band data transfer with the :mod:`pickle` module. + + +.. c:var:: PyTypeObject PyPickleBuffer_Type + + This instance of :c:type:`PyTypeObject` represents the Python pickle buffer type. + This is the same object as :class:`pickle.PickleBuffer` in the Python layer. + + +.. c:function:: int PyPickleBuffer_Check(PyObject *op) + + Return true if *op* is a pickle buffer instance. + This function always succeeds. + + +.. c:function:: PyObject *PyPickleBuffer_FromObject(PyObject *obj) + + Create a pickle buffer from the object *obj*. + + This function will fail if *obj* doesn't support the :ref:`buffer protocol `. + + On success, return a new pickle buffer instance. + On failure, set an exception and return ``NULL``. + + Analogous to calling :class:`pickle.PickleBuffer` with *obj* in Python. + + +.. c:function:: const Py_buffer *PyPickleBuffer_GetBuffer(PyObject *picklebuf) + + Get a pointer to the underlying :c:type:`Py_buffer` that the pickle buffer wraps. + + The returned pointer is valid as long as *picklebuf* is alive and has not been + released. The caller must not modify or free the returned :c:type:`Py_buffer`. + If the pickle buffer has been released, raise :exc:`ValueError`. + + On success, return a pointer to the buffer view. + On failure, set an exception and return ``NULL``. + + +.. c:function:: int PyPickleBuffer_Release(PyObject *picklebuf) + + Release the underlying buffer held by the pickle buffer. + + Return ``0`` on success. On failure, set an exception and return ``-1``. + + Analogous to calling :meth:`pickle.PickleBuffer.release` in Python. diff --git a/Doc/c-api/profiling.rst b/Doc/c-api/profiling.rst new file mode 100644 index 00000000000000..0200f2eac6d908 --- /dev/null +++ b/Doc/c-api/profiling.rst @@ -0,0 +1,239 @@ +.. highlight:: c + +.. _profiling: + +Profiling and tracing +===================== + +The Python interpreter provides some low-level support for attaching profiling +and execution tracing facilities. These are used for profiling, debugging, and +coverage analysis tools. + +This C interface allows the profiling or tracing code to avoid the overhead of +calling through Python-level callable objects, making a direct C function call +instead. The essential attributes of the facility have not changed; the +interface allows trace functions to be installed per-thread, and the basic +events reported to the trace function are the same as had been reported to the +Python-level trace functions in previous versions. + + +.. c:type:: int (*Py_tracefunc)(PyObject *obj, PyFrameObject *frame, int what, PyObject *arg) + + The type of the trace function registered using :c:func:`PyEval_SetProfile` and + :c:func:`PyEval_SetTrace`. The first parameter is the object passed to the + registration function as *obj*, *frame* is the frame object to which the event + pertains, *what* is one of the constants :c:data:`PyTrace_CALL`, + :c:data:`PyTrace_EXCEPTION`, :c:data:`PyTrace_LINE`, :c:data:`PyTrace_RETURN`, + :c:data:`PyTrace_C_CALL`, :c:data:`PyTrace_C_EXCEPTION`, :c:data:`PyTrace_C_RETURN`, + or :c:data:`PyTrace_OPCODE`, and *arg* depends on the value of *what*: + + +-------------------------------+----------------------------------------+ + | Value of *what* | Meaning of *arg* | + +===============================+========================================+ + | :c:data:`PyTrace_CALL` | Always :c:data:`Py_None`. | + +-------------------------------+----------------------------------------+ + | :c:data:`PyTrace_EXCEPTION` | Exception information as returned by | + | | :func:`sys.exc_info`. | + +-------------------------------+----------------------------------------+ + | :c:data:`PyTrace_LINE` | Always :c:data:`Py_None`. | + +-------------------------------+----------------------------------------+ + | :c:data:`PyTrace_RETURN` | Value being returned to the caller, | + | | or ``NULL`` if caused by an exception. | + +-------------------------------+----------------------------------------+ + | :c:data:`PyTrace_C_CALL` | Function object being called. | + +-------------------------------+----------------------------------------+ + | :c:data:`PyTrace_C_EXCEPTION` | Function object being called. | + +-------------------------------+----------------------------------------+ + | :c:data:`PyTrace_C_RETURN` | Function object being called. | + +-------------------------------+----------------------------------------+ + | :c:data:`PyTrace_OPCODE` | Always :c:data:`Py_None`. | + +-------------------------------+----------------------------------------+ + +.. c:var:: int PyTrace_CALL + + The value of the *what* parameter to a :c:type:`Py_tracefunc` function when a new + call to a function or method is being reported, or a new entry into a generator. + Note that the creation of the iterator for a generator function is not reported + as there is no control transfer to the Python bytecode in the corresponding + frame. + + +.. c:var:: int PyTrace_EXCEPTION + + The value of the *what* parameter to a :c:type:`Py_tracefunc` function when an + exception has been raised. The callback function is called with this value for + *what* when after any bytecode is processed after which the exception becomes + set within the frame being executed. The effect of this is that as exception + propagation causes the Python stack to unwind, the callback is called upon + return to each frame as the exception propagates. Only trace functions receive + these events; they are not needed by the profiler. + + +.. c:var:: int PyTrace_LINE + + The value passed as the *what* parameter to a :c:type:`Py_tracefunc` function + (but not a profiling function) when a line-number event is being reported. + It may be disabled for a frame by setting :attr:`~frame.f_trace_lines` to + *0* on that frame. + + +.. c:var:: int PyTrace_RETURN + + The value for the *what* parameter to :c:type:`Py_tracefunc` functions when a + call is about to return. + + +.. c:var:: int PyTrace_C_CALL + + The value for the *what* parameter to :c:type:`Py_tracefunc` functions when a C + function is about to be called. + + +.. c:var:: int PyTrace_C_EXCEPTION + + The value for the *what* parameter to :c:type:`Py_tracefunc` functions when a C + function has raised an exception. + + +.. c:var:: int PyTrace_C_RETURN + + The value for the *what* parameter to :c:type:`Py_tracefunc` functions when a C + function has returned. + + +.. c:var:: int PyTrace_OPCODE + + The value for the *what* parameter to :c:type:`Py_tracefunc` functions (but not + profiling functions) when a new opcode is about to be executed. This event is + not emitted by default: it must be explicitly requested by setting + :attr:`~frame.f_trace_opcodes` to *1* on the frame. + + +.. c:function:: void PyEval_SetProfile(Py_tracefunc func, PyObject *obj) + + Set the profiler function to *func*. The *obj* parameter is passed to the + function as its first parameter, and may be any Python object, or ``NULL``. If + the profile function needs to maintain state, using a different value for *obj* + for each thread provides a convenient and thread-safe place to store it. The + profile function is called for all monitored events except :c:data:`PyTrace_LINE` + :c:data:`PyTrace_OPCODE` and :c:data:`PyTrace_EXCEPTION`. + + See also the :func:`sys.setprofile` function. + + The caller must have an :term:`attached thread state`. + + +.. c:function:: void PyEval_SetProfileAllThreads(Py_tracefunc func, PyObject *obj) + + Like :c:func:`PyEval_SetProfile` but sets the profile function in all running threads + belonging to the current interpreter instead of the setting it only on the current thread. + + The caller must have an :term:`attached thread state`. + + As :c:func:`PyEval_SetProfile`, this function ignores any exceptions raised while + setting the profile functions in all threads. + +.. versionadded:: 3.12 + + +.. c:function:: void PyEval_SetTrace(Py_tracefunc func, PyObject *obj) + + Set the tracing function to *func*. This is similar to + :c:func:`PyEval_SetProfile`, except the tracing function does receive line-number + events and per-opcode events, but does not receive any event related to C function + objects being called. Any trace function registered using :c:func:`PyEval_SetTrace` + will not receive :c:data:`PyTrace_C_CALL`, :c:data:`PyTrace_C_EXCEPTION` or + :c:data:`PyTrace_C_RETURN` as a value for the *what* parameter. + + See also the :func:`sys.settrace` function. + + The caller must have an :term:`attached thread state`. + + +.. c:function:: void PyEval_SetTraceAllThreads(Py_tracefunc func, PyObject *obj) + + Like :c:func:`PyEval_SetTrace` but sets the tracing function in all running threads + belonging to the current interpreter instead of the setting it only on the current thread. + + The caller must have an :term:`attached thread state`. + + As :c:func:`PyEval_SetTrace`, this function ignores any exceptions raised while + setting the trace functions in all threads. + +.. versionadded:: 3.12 + + +Reference tracing +================= + +.. versionadded:: 3.13 + + +.. c:type:: int (*PyRefTracer)(PyObject *, int event, void* data) + + The type of the trace function registered using :c:func:`PyRefTracer_SetTracer`. + The first parameter is a Python object that has been just created (when **event** + is set to :c:data:`PyRefTracer_CREATE`) or about to be destroyed (when **event** + is set to :c:data:`PyRefTracer_DESTROY`). The **data** argument is the opaque pointer + that was provided when :c:func:`PyRefTracer_SetTracer` was called. + + If a new tracing function is registered replacing the current one, a call to the + trace function will be made with the object set to **NULL** and **event** set to + :c:data:`PyRefTracer_TRACKER_REMOVED`. This will happen just before the new + function is registered. + +.. versionadded:: 3.13 + + +.. c:var:: int PyRefTracer_CREATE + + The value for the *event* parameter to :c:type:`PyRefTracer` functions when a Python + object has been created. + + +.. c:var:: int PyRefTracer_DESTROY + + The value for the *event* parameter to :c:type:`PyRefTracer` functions when a Python + object has been destroyed. + + +.. c:var:: int PyRefTracer_TRACKER_REMOVED + + The value for the *event* parameter to :c:type:`PyRefTracer` functions when the + current tracer is about to be replaced by a new one. + + .. versionadded:: 3.14 + + +.. c:function:: int PyRefTracer_SetTracer(PyRefTracer tracer, void *data) + + Register a reference tracer function. The function will be called when a new + Python object has been created or when an object is going to be destroyed. If + **data** is provided it must be an opaque pointer that will be provided when + the tracer function is called. Return ``0`` on success. Set an exception and + return ``-1`` on error. + + Note that tracer functions **must not** create Python objects inside or + otherwise the call will be re-entrant. The tracer also **must not** clear + any existing exception or set an exception. A :term:`thread state` will be active + every time the tracer function is called. + + There must be an :term:`attached thread state` when calling this function. + + If another tracer function was already registered, the old function will be + called with **event** set to :c:data:`PyRefTracer_TRACKER_REMOVED` just before + the new function is registered. + +.. versionadded:: 3.13 + + +.. c:function:: PyRefTracer PyRefTracer_GetTracer(void** data) + + Get the registered reference tracer function and the value of the opaque data + pointer that was registered when :c:func:`PyRefTracer_SetTracer` was called. + If no tracer was registered this function will return NULL and will set the + **data** pointer to NULL. + + There must be an :term:`attached thread state` when calling this function. + +.. versionadded:: 3.13 diff --git a/Doc/c-api/refcounting.rst b/Doc/c-api/refcounting.rst index b23f016f9b0a06..4d56a92bf2af79 100644 --- a/Doc/c-api/refcounting.rst +++ b/Doc/c-api/refcounting.rst @@ -25,7 +25,7 @@ of Python objects. .. note:: - On :term:`free threaded ` builds of Python, returning 1 + On :term:`free-threaded builds ` of Python, returning 1 isn't sufficient to determine if it's safe to treat *o* as having no access by other threads. Use :c:func:`PyUnstable_Object_IsUniquelyReferenced` for that instead. @@ -210,7 +210,7 @@ of Python objects. Py_SETREF(dst, src); - That arranges to set *dst* to *src* _before_ releasing the reference + That arranges to set *dst* to *src* *before* releasing the reference to the old value of *dst*, so that any code triggered as a side-effect of *dst* getting torn down no longer believes *dst* points to a valid object. diff --git a/Doc/c-api/sequence.rst b/Doc/c-api/sequence.rst index df5bf6b64a93a0..90490cf6749b59 100644 --- a/Doc/c-api/sequence.rst +++ b/Doc/c-api/sequence.rst @@ -67,7 +67,7 @@ Sequence Protocol Assign object *v* to the *i*\ th element of *o*. Raise an exception and return ``-1`` on failure; return ``0`` on success. This is the equivalent of the Python statement ``o[i] = v``. This function *does - not* steal a reference to *v*. + not* ":term:`steal`" a reference to *v*. If *v* is ``NULL``, the element is deleted, but this feature is deprecated in favour of using :c:func:`PySequence_DelItem`. @@ -109,9 +109,8 @@ Sequence Protocol Alias for :c:func:`PySequence_Contains`. - .. deprecated:: 3.14 - The function is :term:`soft deprecated` and should no longer be used to - write new code. + .. soft-deprecated:: 3.14 + The function should no longer be used to write new code. .. c:function:: Py_ssize_t PySequence_Index(PyObject *o, PyObject *value) diff --git a/Doc/c-api/set.rst b/Doc/c-api/set.rst index cba823aa027bd6..a44d49ecd1857e 100644 --- a/Doc/c-api/set.rst +++ b/Doc/c-api/set.rst @@ -92,6 +92,11 @@ the constructor functions work with any iterable Python object. actually iterable. The constructor is also useful for copying a set (``c=set(s)``). + .. note:: + + The operation is atomic on :term:`free threading ` + when *iterable* is a :class:`set`, :class:`frozenset` or :class:`dict`. + .. c:function:: PyObject* PyFrozenSet_New(PyObject *iterable) @@ -100,6 +105,11 @@ the constructor functions work with any iterable Python object. set on success or ``NULL`` on failure. Raise :exc:`TypeError` if *iterable* is not actually iterable. + .. note:: + + The operation is atomic on :term:`free threading ` + when *iterable* is a :class:`set`, :class:`frozenset` or :class:`dict`. + The following functions and macros are available for instances of :class:`set` or :class:`frozenset` or instances of their subtypes. @@ -127,6 +137,10 @@ or :class:`frozenset` or instances of their subtypes. the *key* is unhashable. Raise :exc:`SystemError` if *anyset* is not a :class:`set`, :class:`frozenset`, or an instance of a subtype. + .. note:: + + The operation is atomic on :term:`free threading ` + when *key* is :class:`str`, :class:`int`, :class:`float`, :class:`bool` or :class:`bytes`. .. c:function:: int PySet_Add(PyObject *set, PyObject *key) @@ -138,6 +152,12 @@ or :class:`frozenset` or instances of their subtypes. :exc:`SystemError` if *set* is not an instance of :class:`set` or its subtype. + .. note:: + + The operation is atomic on :term:`free threading ` + when *key* is :class:`str`, :class:`int`, :class:`float`, :class:`bool` or :class:`bytes`. + + The following functions are available for instances of :class:`set` or its subtypes but not for instances of :class:`frozenset` or its subtypes. @@ -147,11 +167,16 @@ subtypes but not for instances of :class:`frozenset` or its subtypes. Return ``1`` if found and removed, ``0`` if not found (no action taken), and ``-1`` if an error is encountered. Does not raise :exc:`KeyError` for missing keys. Raise a - :exc:`TypeError` if the *key* is unhashable. Unlike the Python :meth:`~frozenset.discard` + :exc:`TypeError` if the *key* is unhashable. Unlike the Python :meth:`~set.discard` method, this function does not automatically convert unhashable sets into temporary frozensets. Raise :exc:`SystemError` if *set* is not an instance of :class:`set` or its subtype. + .. note:: + + The operation is atomic on :term:`free threading ` + when *key* is :class:`str`, :class:`int`, :class:`float`, :class:`bool` or :class:`bytes`. + .. c:function:: PyObject* PySet_Pop(PyObject *set) @@ -166,3 +191,28 @@ subtypes but not for instances of :class:`frozenset` or its subtypes. Empty an existing set of all elements. Return ``0`` on success. Return ``-1`` and raise :exc:`SystemError` if *set* is not an instance of :class:`set` or its subtype. + + .. note:: + + In the :term:`free-threaded build`, the set is emptied before its entries + are cleared, so other threads will observe an empty set rather than + intermediate states. + + +Deprecated API +^^^^^^^^^^^^^^ + +.. c:macro:: PySet_MINSIZE + + A constant representing the size of an internal + preallocated table inside :c:type:`PySetObject` instances. + + This is documented solely for completeness, as there are no guarantees + that a given version of CPython uses preallocated tables with a fixed + size. + In code that does not deal with unstable set internals, + :c:macro:`!PySet_MINSIZE` can be replaced with a small constant like ``8``. + + If looking for the size of a set, use :c:func:`PySet_Size` instead. + + .. soft-deprecated:: 3.14 diff --git a/Doc/c-api/stable.rst b/Doc/c-api/stable.rst index 124e58cf950b7a..9b65e0b8d23d93 100644 --- a/Doc/c-api/stable.rst +++ b/Doc/c-api/stable.rst @@ -51,6 +51,7 @@ It is generally intended for specialized, low-level tools like debuggers. Projects that use this API are expected to follow CPython development and spend extra effort adjusting to changes. +.. _stable-application-binary-interface: Stable Application Binary Interface =================================== diff --git a/Doc/c-api/structures.rst b/Doc/c-api/structures.rst index 987bc167c68d6c..40557251a79c0a 100644 --- a/Doc/c-api/structures.rst +++ b/Doc/c-api/structures.rst @@ -28,18 +28,52 @@ under :ref:`reference counting `. object. In a normal "release" build, it contains only the object's reference count and a pointer to the corresponding type object. Nothing is actually declared to be a :c:type:`PyObject`, but every pointer - to a Python object can be cast to a :c:expr:`PyObject*`. Access to the - members must be done by using the macros :c:macro:`Py_REFCNT` and - :c:macro:`Py_TYPE`. + to a Python object can be cast to a :c:expr:`PyObject*`. + + The members must not be accessed directly; instead use macros such as + :c:macro:`Py_REFCNT` and :c:macro:`Py_TYPE`. + + .. c:member:: Py_ssize_t ob_refcnt + + The object's reference count, as returned by :c:macro:`Py_REFCNT`. + Do not use this field directly; instead use functions and macros such as + :c:macro:`!Py_REFCNT`, :c:func:`Py_INCREF` and :c:func:`Py_DecRef`. + + The field type may be different from ``Py_ssize_t``, depending on + build configuration and platform. + + .. c:member:: PyTypeObject* ob_type + + The object's type. + Do not use this field directly; use :c:macro:`Py_TYPE` and + :c:func:`Py_SET_TYPE` instead. .. c:type:: PyVarObject - This is an extension of :c:type:`PyObject` that adds the :c:member:`~PyVarObject.ob_size` - field. This is only used for objects that have some notion of *length*. - This type does not often appear in the Python/C API. - Access to the members must be done by using the macros - :c:macro:`Py_REFCNT`, :c:macro:`Py_TYPE`, and :c:macro:`Py_SIZE`. + An extension of :c:type:`PyObject` that adds the + :c:member:`~PyVarObject.ob_size` field. + This is intended for objects that have some notion of *length*. + + As with :c:type:`!PyObject`, the members must not be accessed directly; + instead use macros such as :c:macro:`Py_SIZE`, :c:macro:`Py_REFCNT` and + :c:macro:`Py_TYPE`. + + .. c:member:: Py_ssize_t ob_size + + A size field, whose contents should be considered an object's internal + implementation detail. + + Do not use this field directly; use :c:macro:`Py_SIZE` instead. + + Object creation functions such as :c:func:`PyObject_NewVar` will + generally set this field to the requested size (number of items). + After creation, arbitrary values can be stored in :c:member:`!ob_size` + using :c:macro:`Py_SET_SIZE`. + + To get an object's publicly exposed length, as returned by + the Python function :py:func:`len`, use :c:func:`PyObject_Length` + instead. .. c:macro:: PyObject_HEAD @@ -103,9 +137,8 @@ under :ref:`reference counting `. Get the type of the Python object *o*. - Return a :term:`borrowed reference`. - - Use the :c:func:`Py_SET_TYPE` function to set an object type. + The returned reference is :term:`borrowed ` from *o*. + Do not release it with :c:func:`Py_DECREF` or similar. .. versionchanged:: 3.11 :c:func:`Py_TYPE()` is changed to an inline static function. @@ -122,16 +155,26 @@ under :ref:`reference counting `. .. c:function:: void Py_SET_TYPE(PyObject *o, PyTypeObject *type) - Set the object *o* type to *type*. + Set the type of object *o* to *type*, without any checking or reference + counting. + + This is a very low-level operation. + Consider instead setting the Python attribute :attr:`~object.__class__` + using :c:func:`PyObject_SetAttrString` or similar. + + Note that assigning an incompatible type can lead to undefined behavior. + + If *type* is a :ref:`heap type `, the caller must create a + new reference to it. + Similarly, if the old type of *o* is a heap type, the caller must release + a reference to that type. .. versionadded:: 3.9 .. c:function:: Py_ssize_t Py_SIZE(PyVarObject *o) - Get the size of the Python object *o*. - - Use the :c:func:`Py_SET_SIZE` function to set an object size. + Get the :c:member:`~PyVarObject.ob_size` field of *o*. .. versionchanged:: 3.11 :c:func:`Py_SIZE()` is changed to an inline static function. @@ -140,7 +183,7 @@ under :ref:`reference counting `. .. c:function:: void Py_SET_SIZE(PyVarObject *o, Py_ssize_t size) - Set the object *o* size to *size*. + Set the :c:member:`~PyVarObject.ob_size` field of *o* to *size*. .. versionadded:: 3.9 @@ -365,7 +408,7 @@ There are these calling conventions: These two constants are not used to indicate the calling convention but the -binding when use with methods of classes. These may not be used for functions +binding when used with methods of classes. These may not be used for functions defined for modules. At most one of these flags may be set for any given method. @@ -376,8 +419,8 @@ method. The method will be passed the type object as the first parameter rather than an instance of the type. This is used to create *class methods*, - similar to what is created when using the :func:`classmethod` built-in - function. + similar to what is created when using the :deco:`classmethod` built-in + decorator. .. c:macro:: METH_STATIC @@ -386,7 +429,7 @@ method. The method will be passed ``NULL`` as the first parameter rather than an instance of the type. This is used to create *static methods*, similar to - what is created when using the :func:`staticmethod` built-in function. + what is created when using the :deco:`staticmethod` built-in decorator. One other constant controls whether a method is loaded in place of another definition with the same method name. @@ -404,6 +447,25 @@ definition with the same method name. slot. This is helpful because calls to PyCFunctions are optimized more than wrapper object calls. + +.. c:var:: PyTypeObject PyCMethod_Type + + The type object corresponding to Python C method objects. This is + available as :class:`types.BuiltinMethodType` in the Python layer. + + +.. c:function:: int PyCMethod_Check(PyObject *op) + + Return true if *op* is an instance of the :c:type:`PyCMethod_Type` type + or a subtype of it. This function always succeeds. + + +.. c:function:: int PyCMethod_CheckExact(PyObject *op) + + This is the same as :c:func:`PyCMethod_Check`, but does not account for + subtypes. + + .. c:function:: PyObject * PyCMethod_New(PyMethodDef *ml, PyObject *self, PyObject *module, PyTypeObject *cls) Turn *ml* into a Python :term:`callable` object. @@ -429,6 +491,24 @@ definition with the same method name. .. versionadded:: 3.9 +.. c:var:: PyTypeObject PyCFunction_Type + + The type object corresponding to Python C function objects. This is + available as :class:`types.BuiltinFunctionType` in the Python layer. + + +.. c:function:: int PyCFunction_Check(PyObject *op) + + Return true if *op* is an instance of the :c:type:`PyCFunction_Type` type + or a subtype of it. This function always succeeds. + + +.. c:function:: int PyCFunction_CheckExact(PyObject *op) + + This is the same as :c:func:`PyCFunction_Check`, but does not account for + subtypes. + + .. c:function:: PyObject * PyCFunction_NewEx(PyMethodDef *ml, PyObject *self, PyObject *module) Equivalent to ``PyCMethod_New(ml, self, module, NULL)``. @@ -439,6 +519,62 @@ definition with the same method name. Equivalent to ``PyCMethod_New(ml, self, NULL, NULL)``. +.. c:function:: int PyCFunction_GetFlags(PyObject *func) + + Get the function's flags on *func* as they were passed to + :c:member:`~PyMethodDef.ml_flags`. + + If *func* is not a C function object, this fails with an exception. + *func* must not be ``NULL``. + + This function returns the function's flags on success, and ``-1`` with an + exception set on failure. + + +.. c:function:: int PyCFunction_GET_FLAGS(PyObject *func) + + This is the same as :c:func:`PyCFunction_GetFlags`, but without error + or type checking. + + +.. c:function:: PyCFunction PyCFunction_GetFunction(PyObject *func) + + Get the function pointer on *func* as it was passed to + :c:member:`~PyMethodDef.ml_meth`. + + If *func* is not a C function object, this fails with an exception. + *func* must not be ``NULL``. + + This function returns the function pointer on success, and ``NULL`` with an + exception set on failure. + + +.. c:function:: int PyCFunction_GET_FUNCTION(PyObject *func) + + This is the same as :c:func:`PyCFunction_GetFunction`, but without error + or type checking. + + +.. c:function:: PyObject *PyCFunction_GetSelf(PyObject *func) + + Get the "self" object on *func*. This is the object that would be passed + to the first argument of a :c:type:`PyCFunction`. For C function objects + created through a :c:type:`PyMethodDef` on a :c:type:`PyModuleDef`, this + is the resulting module object. + + If *func* is not a C function object, this fails with an exception. + *func* must not be ``NULL``. + + This function returns a :term:`borrowed reference` to the "self" object + on success, and ``NULL`` with an exception set on failure. + + +.. c:function:: PyObject *PyCFunction_GET_SELF(PyObject *func) + + This is the same as :c:func:`PyCFunction_GetSelf`, but without error or + type checking. + + Accessing attributes of extension types --------------------------------------- @@ -562,14 +698,12 @@ The following flags can be used with :c:member:`PyMemberDef.flags`: entry indicates an offset from the subclass-specific data, rather than from ``PyObject``. - Can only be used as part of :c:member:`Py_tp_members ` + Can only be used as part of the :c:data:`Py_tp_members` :c:type:`slot ` when creating a class using negative :c:member:`~PyType_Spec.basicsize`. It is mandatory in that case. - - This flag is only used in :c:type:`PyType_Slot`. - When setting :c:member:`~PyTypeObject.tp_members` during - class creation, Python clears it and sets + When setting :c:member:`~PyTypeObject.tp_members` from the slot during + class creation, Python clears the flag and sets :c:member:`PyMemberDef.offset` to the offset from the ``PyObject`` struct. .. index:: diff --git a/Doc/c-api/subinterpreters.rst b/Doc/c-api/subinterpreters.rst new file mode 100644 index 00000000000000..44e3fc96841aac --- /dev/null +++ b/Doc/c-api/subinterpreters.rst @@ -0,0 +1,470 @@ +.. highlight:: c + +.. _sub-interpreter-support: + +Multiple interpreters in a Python process +========================================= + +While in most uses, you will only embed a single Python interpreter, there +are cases where you need to create several independent interpreters in the +same process and perhaps even in the same thread. Sub-interpreters allow +you to do that. + +The "main" interpreter is the first one created when the runtime initializes. +It is usually the only Python interpreter in a process. Unlike sub-interpreters, +the main interpreter has unique process-global responsibilities like signal +handling. It is also responsible for execution during runtime initialization and +is usually the active interpreter during runtime finalization. The +:c:func:`PyInterpreterState_Main` function returns a pointer to its state. + +You can switch between sub-interpreters using the :c:func:`PyThreadState_Swap` +function. You can create and destroy them using the following functions: + + +.. c:type:: PyInterpreterConfig + + Structure containing most parameters to configure a sub-interpreter. + Its values are used only in :c:func:`Py_NewInterpreterFromConfig` and + never modified by the runtime. + + .. versionadded:: 3.12 + + Structure fields: + + .. c:member:: int use_main_obmalloc + + If this is ``0`` then the sub-interpreter will use its own + "object" allocator state. + Otherwise it will use (share) the main interpreter's. + + If this is ``0`` then + :c:member:`~PyInterpreterConfig.check_multi_interp_extensions` + must be ``1`` (non-zero). + If this is ``1`` then :c:member:`~PyInterpreterConfig.gil` + must not be :c:macro:`PyInterpreterConfig_OWN_GIL`. + + .. c:member:: int allow_fork + + If this is ``0`` then the runtime will not support forking the + process in any thread where the sub-interpreter is currently active. + Otherwise fork is unrestricted. + + Note that the :mod:`subprocess` module still works + when fork is disallowed. + + .. c:member:: int allow_exec + + If this is ``0`` then the runtime will not support replacing the + current process via exec (e.g. :func:`os.execv`) in any thread + where the sub-interpreter is currently active. + Otherwise exec is unrestricted. + + Note that the :mod:`subprocess` module still works + when exec is disallowed. + + .. c:member:: int allow_threads + + If this is ``0`` then the sub-interpreter's :mod:`threading` module + won't create threads. + Otherwise threads are allowed. + + .. c:member:: int allow_daemon_threads + + If this is ``0`` then the sub-interpreter's :mod:`threading` module + won't create daemon threads. + Otherwise daemon threads are allowed (as long as + :c:member:`~PyInterpreterConfig.allow_threads` is non-zero). + + .. c:member:: int check_multi_interp_extensions + + If this is ``0`` then all extension modules may be imported, + including legacy (single-phase init) modules, + in any thread where the sub-interpreter is currently active. + Otherwise only multi-phase init extension modules + (see :pep:`489`) may be imported. + (Also see :c:macro:`Py_mod_multiple_interpreters`.) + + This must be ``1`` (non-zero) if + :c:member:`~PyInterpreterConfig.use_main_obmalloc` is ``0``. + + .. c:member:: int gil + + This determines the operation of the GIL for the sub-interpreter. + It may be one of the following: + + .. c:namespace:: NULL + + .. c:macro:: PyInterpreterConfig_DEFAULT_GIL + + Use the default selection (:c:macro:`PyInterpreterConfig_SHARED_GIL`). + + .. c:macro:: PyInterpreterConfig_SHARED_GIL + + Use (share) the main interpreter's GIL. + + .. c:macro:: PyInterpreterConfig_OWN_GIL + + Use the sub-interpreter's own GIL. + + If this is :c:macro:`PyInterpreterConfig_OWN_GIL` then + :c:member:`PyInterpreterConfig.use_main_obmalloc` must be ``0``. + + +.. c:function:: PyStatus Py_NewInterpreterFromConfig(PyThreadState **tstate_p, const PyInterpreterConfig *config) + + .. index:: + pair: module; builtins + pair: module; __main__ + pair: module; sys + single: stdout (in module sys) + single: stderr (in module sys) + single: stdin (in module sys) + + Create a new sub-interpreter. This is an (almost) totally separate environment + for the execution of Python code. In particular, the new interpreter has + separate, independent versions of all imported modules, including the + fundamental modules :mod:`builtins`, :mod:`__main__` and :mod:`sys`. The + table of loaded modules (``sys.modules``) and the module search path + (``sys.path``) are also separate. The new environment has no ``sys.argv`` + variable. It has new standard I/O stream file objects ``sys.stdin``, + ``sys.stdout`` and ``sys.stderr`` (however these refer to the same underlying + file descriptors). + + The given *config* controls the options with which the interpreter + is initialized. + + Upon success, *tstate_p* will be set to the first :term:`thread state` + created in the new sub-interpreter. This thread state is + :term:`attached `. + Note that no actual thread is created; see the discussion of thread states + below. If creation of the new interpreter is unsuccessful, + *tstate_p* is set to ``NULL``; + no exception is set since the exception state is stored in the + :term:`attached thread state`, which might not exist. + + Like all other Python/C API functions, an :term:`attached thread state` + must be present before calling this function, but it might be detached upon + returning. On success, the returned thread state will be :term:`attached `. + If the sub-interpreter is created with its own :term:`GIL` then the + :term:`attached thread state` of the calling interpreter will be detached. + When the function returns, the new interpreter's :term:`thread state` + will be :term:`attached ` to the current thread and + the previous interpreter's :term:`attached thread state` will remain detached. + + .. versionadded:: 3.12 + + Sub-interpreters are most effective when isolated from each other, + with certain functionality restricted:: + + PyInterpreterConfig config = { + .use_main_obmalloc = 0, + .allow_fork = 0, + .allow_exec = 0, + .allow_threads = 1, + .allow_daemon_threads = 0, + .check_multi_interp_extensions = 1, + .gil = PyInterpreterConfig_OWN_GIL, + }; + PyThreadState *tstate = NULL; + PyStatus status = Py_NewInterpreterFromConfig(&tstate, &config); + if (PyStatus_Exception(status)) { + Py_ExitStatusException(status); + } + + Note that the config is used only briefly and does not get modified. + During initialization the config's values are converted into various + :c:type:`PyInterpreterState` values. A read-only copy of the config + may be stored internally on the :c:type:`PyInterpreterState`. + + .. index:: + single: Py_FinalizeEx (C function) + single: Py_Initialize (C function) + + Extension modules are shared between (sub-)interpreters as follows: + + * For modules using multi-phase initialization, + e.g. :c:func:`PyModule_FromDefAndSpec`, a separate module object is + created and initialized for each interpreter. + Only C-level static and global variables are shared between these + module objects. + + * For modules using legacy + :ref:`single-phase initialization `, + e.g. :c:func:`PyModule_Create`, the first time a particular extension + is imported, it is initialized normally, and a (shallow) copy of its + module's dictionary is squirreled away. + When the same extension is imported by another (sub-)interpreter, a new + module is initialized and filled with the contents of this copy; the + extension's ``init`` function is not called. + Objects in the module's dictionary thus end up shared across + (sub-)interpreters, which might cause unwanted behavior (see + `Bugs and caveats`_ below). + + Note that this is different from what happens when an extension is + imported after the interpreter has been completely re-initialized by + calling :c:func:`Py_FinalizeEx` and :c:func:`Py_Initialize`; in that + case, the extension's ``initmodule`` function *is* called again. + As with multi-phase initialization, this means that only C-level static + and global variables are shared between these modules. + + .. index:: single: close (in module os) + + +.. c:function:: PyThreadState* Py_NewInterpreter(void) + + .. index:: + pair: module; builtins + pair: module; __main__ + pair: module; sys + single: stdout (in module sys) + single: stderr (in module sys) + single: stdin (in module sys) + + Create a new sub-interpreter. This is essentially just a wrapper + around :c:func:`Py_NewInterpreterFromConfig` with a config that + preserves the existing behavior. The result is an unisolated + sub-interpreter that shares the main interpreter's GIL, allows + fork/exec, allows daemon threads, and allows single-phase init + modules. + + +.. c:function:: void Py_EndInterpreter(PyThreadState *tstate) + + .. index:: single: Py_FinalizeEx (C function) + + Destroy the (sub-)interpreter represented by the given :term:`thread state`. + The given thread state must be :term:`attached `. + When the call returns, there will be no :term:`attached thread state`. + All thread states associated with this interpreter are destroyed. + + :c:func:`Py_FinalizeEx` will destroy all sub-interpreters that + haven't been explicitly destroyed at that point. + + +.. _per-interpreter-gil: + +A per-interpreter GIL +--------------------- + +.. versionadded:: 3.12 + +Using :c:func:`Py_NewInterpreterFromConfig` you can create +a sub-interpreter that is completely isolated from other interpreters, +including having its own GIL. The most important benefit of this +isolation is that such an interpreter can execute Python code without +being blocked by other interpreters or blocking any others. Thus a +single Python process can truly take advantage of multiple CPU cores +when running Python code. The isolation also encourages a different +approach to concurrency than that of just using threads. +(See :pep:`554` and :pep:`684`.) + +Using an isolated interpreter requires vigilance in preserving that +isolation. That especially means not sharing any objects or mutable +state without guarantees about thread-safety. Even objects that are +otherwise immutable (e.g. ``None``, ``(1, 5)``) can't normally be shared +because of the refcount. One simple but less-efficient approach around +this is to use a global lock around all use of some state (or object). +Alternately, effectively immutable objects (like integers or strings) +can be made safe in spite of their refcounts by making them :term:`immortal`. +In fact, this has been done for the builtin singletons, small integers, +and a number of other builtin objects. + +If you preserve isolation then you will have access to proper multi-core +computing without the complications that come with free-threading. +Failure to preserve isolation will expose you to the full consequences +of free-threading, including races and hard-to-debug crashes. + +Aside from that, one of the main challenges of using multiple isolated +interpreters is how to communicate between them safely (not break +isolation) and efficiently. The runtime and stdlib do not provide +any standard approach to this yet. A future stdlib module would help +mitigate the effort of preserving isolation and expose effective tools +for communicating (and sharing) data between interpreters. + + +Bugs and caveats +---------------- + +Because sub-interpreters (and the main interpreter) are part of the same +process, the insulation between them isn't perfect --- for example, using +low-level file operations like :func:`os.close` they can +(accidentally or maliciously) affect each other's open files. Because of the +way extensions are shared between (sub-)interpreters, some extensions may not +work properly; this is especially likely when using single-phase initialization +or (static) global variables. +It is possible to insert objects created in one sub-interpreter into +a namespace of another (sub-)interpreter; this should be avoided if possible. + +Special care should be taken to avoid sharing user-defined functions, +methods, instances or classes between sub-interpreters, since import +operations executed by such objects may affect the wrong (sub-)interpreter's +dictionary of loaded modules. It is equally important to avoid sharing +objects from which the above are reachable. + +Also note that combining this functionality with ``PyGILState_*`` APIs +is delicate, because these APIs assume a bijection between Python thread states +and OS-level threads, an assumption broken by the presence of sub-interpreters. +It is highly recommended that you don't switch sub-interpreters between a pair +of matching :c:func:`PyGILState_Ensure` and :c:func:`PyGILState_Release` calls. +Furthermore, extensions (such as :mod:`ctypes`) using these APIs to allow calling +of Python code from non-Python created threads will probably be broken when using +sub-interpreters. + + +High-level APIs +--------------- + +.. c:type:: PyInterpreterState + + This data structure represents the state shared by a number of cooperating + threads. Threads belonging to the same interpreter share their module + administration and a few other internal items. There are no public members in + this structure. + + Threads belonging to different interpreters initially share nothing, except + process state like available memory, open file descriptors and such. The global + interpreter lock is also shared by all threads, regardless of to which + interpreter they belong. + + .. versionchanged:: 3.12 + + :pep:`684` introduced the possibility + of a :ref:`per-interpreter GIL `. + See :c:func:`Py_NewInterpreterFromConfig`. + + +.. c:function:: PyInterpreterState* PyInterpreterState_Get(void) + + Get the current interpreter. + + Issue a fatal error if there is no :term:`attached thread state`. + It cannot return NULL. + + .. versionadded:: 3.9 + + +.. c:function:: int64_t PyInterpreterState_GetID(PyInterpreterState *interp) + + Return the interpreter's unique ID. If there was any error in doing + so then ``-1`` is returned and an error is set. + + The caller must have an :term:`attached thread state`. + + .. versionadded:: 3.7 + + +.. c:function:: PyObject* PyInterpreterState_GetDict(PyInterpreterState *interp) + + Return a dictionary in which interpreter-specific data may be stored. + If this function returns ``NULL`` then no exception has been raised and + the caller should assume no interpreter-specific dict is available. + + This is not a replacement for :c:func:`PyModule_GetState()`, which + extensions should use to store interpreter-specific state information. + + The returned dictionary is borrowed from the interpreter and is valid until + interpreter shutdown. + + .. versionadded:: 3.8 + + +.. c:type:: PyObject* (*_PyFrameEvalFunction)(PyThreadState *tstate, _PyInterpreterFrame *frame, int throwflag) + + Type of a frame evaluation function. + + The *throwflag* parameter is used by the ``throw()`` method of generators: + if non-zero, handle the current exception. + + .. versionchanged:: 3.9 + The function now takes a *tstate* parameter. + + .. versionchanged:: 3.11 + The *frame* parameter changed from ``PyFrameObject*`` to ``_PyInterpreterFrame*``. + + +.. c:function:: _PyFrameEvalFunction _PyInterpreterState_GetEvalFrameFunc(PyInterpreterState *interp) + + Get the frame evaluation function. + + See the :pep:`523` "Adding a frame evaluation API to CPython". + + .. versionadded:: 3.9 + + +.. c:function:: void _PyInterpreterState_SetEvalFrameFunc(PyInterpreterState *interp, _PyFrameEvalFunction eval_frame) + + Set the frame evaluation function. + + See the :pep:`523` "Adding a frame evaluation API to CPython". + + .. versionadded:: 3.9 + + +Low-level APIs +-------------- + +All of the following functions must be called after :c:func:`Py_Initialize`. + +.. versionchanged:: 3.7 + :c:func:`Py_Initialize()` now initializes the :term:`GIL` + and sets an :term:`attached thread state`. + + +.. c:function:: PyInterpreterState* PyInterpreterState_New() + + Create a new interpreter state object. An :term:`attached thread state` is not needed, + but may optionally exist if it is necessary to serialize calls to this + function. + + .. audit-event:: cpython.PyInterpreterState_New "" c.PyInterpreterState_New + + +.. c:function:: void PyInterpreterState_Clear(PyInterpreterState *interp) + + Reset all information in an interpreter state object. There must be + an :term:`attached thread state` for the interpreter. + + .. audit-event:: cpython.PyInterpreterState_Clear "" c.PyInterpreterState_Clear + + +.. c:function:: void PyInterpreterState_Delete(PyInterpreterState *interp) + + Destroy an interpreter state object. There **should not** be an + :term:`attached thread state` for the target interpreter. The interpreter + state must have been reset with a previous call to :c:func:`PyInterpreterState_Clear`. + + +.. _advanced-debugging: + +Advanced debugger support +------------------------- + +These functions are only intended to be used by advanced debugging tools. + + +.. c:function:: PyInterpreterState* PyInterpreterState_Head() + + Return the interpreter state object at the head of the list of all such objects. + + +.. c:function:: PyInterpreterState* PyInterpreterState_Main() + + Return the main interpreter state object. + + +.. c:function:: PyInterpreterState* PyInterpreterState_Next(PyInterpreterState *interp) + + Return the next interpreter state object after *interp* from the list of all + such objects. + + +.. c:function:: PyThreadState * PyInterpreterState_ThreadHead(PyInterpreterState *interp) + + Return the pointer to the first :c:type:`PyThreadState` object in the list of + threads associated with the interpreter *interp*. + + +.. c:function:: PyThreadState* PyThreadState_Next(PyThreadState *tstate) + + Return the next thread state object after *tstate* from the list of all such + objects belonging to the same :c:type:`PyInterpreterState` object. diff --git a/Doc/c-api/synchronization.rst b/Doc/c-api/synchronization.rst new file mode 100644 index 00000000000000..954ac55e53813f --- /dev/null +++ b/Doc/c-api/synchronization.rst @@ -0,0 +1,301 @@ +.. highlight:: c + +.. _synchronization: + +Synchronization primitives +========================== + +The C-API provides a basic mutual exclusion lock. + +.. c:type:: PyMutex + + A mutual exclusion lock. The :c:type:`!PyMutex` should be initialized to + zero to represent the unlocked state. For example:: + + PyMutex mutex = {0}; + + Instances of :c:type:`!PyMutex` should not be copied or moved. Both the + contents and address of a :c:type:`!PyMutex` are meaningful, and it must + remain at a fixed, writable location in memory. + + .. note:: + + A :c:type:`!PyMutex` currently occupies one byte, but the size should be + considered unstable. The size may change in future Python releases + without a deprecation period. + + .. versionadded:: 3.13 + +.. c:function:: void PyMutex_Lock(PyMutex *m) + + Lock mutex *m*. If another thread has already locked it, the calling + thread will block until the mutex is unlocked. While blocked, the thread + will temporarily detach the :term:`thread state ` if one exists. + + .. versionadded:: 3.13 + +.. c:function:: void PyMutex_Unlock(PyMutex *m) + + Unlock mutex *m*. The mutex must be locked --- otherwise, the function will + issue a fatal error. + + .. versionadded:: 3.13 + +.. c:function:: int PyMutex_IsLocked(PyMutex *m) + + Returns non-zero if the mutex *m* is currently locked, zero otherwise. + + .. note:: + + This function is intended for use in assertions and debugging only and + should not be used to make concurrency control decisions, as the lock + state may change immediately after the check. + + .. versionadded:: 3.14 + +.. _python-critical-section-api: + +Python critical section API +--------------------------- + +The critical section API provides a deadlock avoidance layer on top of +per-object locks for :term:`free-threaded ` CPython. They are +intended to replace reliance on the :term:`global interpreter lock`, and are +no-ops in versions of Python with the global interpreter lock. + +Critical sections are intended to be used for custom types implemented +in C-API extensions. They should generally not be used with built-in types like +:class:`list` and :class:`dict` because their public C-APIs +already use critical sections internally, with the notable +exception of :c:func:`PyDict_Next`, which requires critical section +to be acquired externally. + +Critical sections avoid deadlocks by implicitly suspending active critical +sections, hence, they do not provide exclusive access such as provided by +traditional locks like :c:type:`PyMutex`. When a critical section is started, +the per-object lock for the object is acquired. If the code executed inside the +critical section calls C-API functions then it can suspend the critical section thereby +releasing the per-object lock, so other threads can acquire the per-object lock +for the same object. + +Variants that accept :c:type:`PyMutex` pointers rather than Python objects are also +available. Use these variants to start a critical section in a situation where +there is no :c:type:`PyObject` -- for example, when working with a C type that +does not extend or wrap :c:type:`PyObject` but still needs to call into the C +API in a manner that might lead to deadlocks. + +The functions and structs used by the macros are exposed for cases +where C macros are not available. They should only be used as in the +given macro expansions. Note that the sizes and contents of the structures may +change in future Python versions. + +.. note:: + + Operations that need to lock two objects at once must use + :c:macro:`Py_BEGIN_CRITICAL_SECTION2`. You *cannot* use nested critical + sections to lock more than one object at once, because the inner critical + section may suspend the outer critical sections. This API does not provide + a way to lock more than two objects at once. + +Example usage:: + + static PyObject * + set_field(MyObject *self, PyObject *value) + { + Py_BEGIN_CRITICAL_SECTION(self); + Py_SETREF(self->field, Py_XNewRef(value)); + Py_END_CRITICAL_SECTION(); + Py_RETURN_NONE; + } + +In the above example, :c:macro:`Py_SETREF` calls :c:macro:`Py_DECREF`, which +can call arbitrary code through an object's deallocation function. The critical +section API avoids potential deadlocks due to reentrancy and lock ordering +by allowing the runtime to temporarily suspend the critical section if the +code triggered by the finalizer blocks and calls :c:func:`PyEval_SaveThread`. + +.. c:macro:: Py_BEGIN_CRITICAL_SECTION(op) + + Acquires the per-object lock for the object *op* and begins a + critical section. + + In the free-threaded build, this macro expands to:: + + { + PyCriticalSection _py_cs; + PyCriticalSection_Begin(&_py_cs, (PyObject*)(op)) + + In the default build, this macro expands to ``{``. + + .. versionadded:: 3.13 + +.. c:macro:: Py_BEGIN_CRITICAL_SECTION_MUTEX(m) + + Locks the mutex *m* and begins a critical section. + + In the free-threaded build, this macro expands to:: + + { + PyCriticalSection _py_cs; + PyCriticalSection_BeginMutex(&_py_cs, m) + + Note that unlike :c:macro:`Py_BEGIN_CRITICAL_SECTION`, there is no cast for + the argument of the macro - it must be a :c:type:`PyMutex` pointer. + + On the default build, this macro expands to ``{``. + + .. versionadded:: 3.14 + +.. c:macro:: Py_END_CRITICAL_SECTION() + + Ends the critical section and releases the per-object lock. + + In the free-threaded build, this macro expands to:: + + PyCriticalSection_End(&_py_cs); + } + + In the default build, this macro expands to ``}``. + + .. versionadded:: 3.13 + +.. c:macro:: Py_BEGIN_CRITICAL_SECTION2(a, b) + + Acquires the per-object locks for the objects *a* and *b* and begins a + critical section. The locks are acquired in a consistent order (lowest + address first) to avoid lock ordering deadlocks. + + In the free-threaded build, this macro expands to:: + + { + PyCriticalSection2 _py_cs2; + PyCriticalSection2_Begin(&_py_cs2, (PyObject*)(a), (PyObject*)(b)) + + In the default build, this macro expands to ``{``. + + .. versionadded:: 3.13 + +.. c:macro:: Py_BEGIN_CRITICAL_SECTION2_MUTEX(m1, m2) + + Locks the mutexes *m1* and *m2* and begins a critical section. + + In the free-threaded build, this macro expands to:: + + { + PyCriticalSection2 _py_cs2; + PyCriticalSection2_BeginMutex(&_py_cs2, m1, m2) + + Note that unlike :c:macro:`Py_BEGIN_CRITICAL_SECTION2`, there is no cast for + the arguments of the macro - they must be :c:type:`PyMutex` pointers. + + On the default build, this macro expands to ``{``. + + .. versionadded:: 3.14 + +.. c:macro:: Py_END_CRITICAL_SECTION2() + + Ends the critical section and releases the per-object locks. + + In the free-threaded build, this macro expands to:: + + PyCriticalSection2_End(&_py_cs2); + } + + In the default build, this macro expands to ``}``. + + .. versionadded:: 3.13 + + +Legacy locking APIs +------------------- + +These APIs are obsolete since Python 3.13 with the introduction of +:c:type:`PyMutex`. + + +.. c:type:: PyThread_type_lock + + A pointer to a mutual exclusion lock. + + +.. c:type:: PyLockStatus + + The result of acquiring a lock with a timeout. + + .. c:namespace:: NULL + + .. c:enumerator:: PY_LOCK_FAILURE + + Failed to acquire the lock. + + .. c:enumerator:: PY_LOCK_ACQUIRED + + The lock was successfully acquired. + + .. c:enumerator:: PY_LOCK_INTR + + The lock was interrupted by a signal. + + +.. c:function:: PyThread_type_lock PyThread_allocate_lock(void) + + Allocate a new lock. + + On success, this function returns a lock; on failure, this + function returns ``0`` without an exception set. + + The caller does not need to hold an :term:`attached thread state`. + + +.. c:function:: void PyThread_free_lock(PyThread_type_lock lock) + + Destroy *lock*. The lock should not be held by any thread when calling + this. + + The caller does not need to hold an :term:`attached thread state`. + + +.. c:function:: PyLockStatus PyThread_acquire_lock_timed(PyThread_type_lock lock, long long microseconds, int intr_flag) + + Acquire *lock* with a timeout. + + This will wait for *microseconds* microseconds to acquire the lock. If the + timeout expires, this function returns :c:enumerator:`PY_LOCK_FAILURE`. + If *microseconds* is ``-1``, this will wait indefinitely until the lock has + been released. + + If *intr_flag* is ``1``, acquiring the lock may be interrupted by a signal, + in which case this function returns :c:enumerator:`PY_LOCK_INTR`. Upon + interruption, it's generally expected that the caller makes a call to + :c:func:`Py_MakePendingCalls` to propagate an exception to Python code. + + If the lock is successfully acquired, this function returns + :c:enumerator:`PY_LOCK_ACQUIRED`. + + The caller does not need to hold an :term:`attached thread state`. + + +.. c:function:: int PyThread_acquire_lock(PyThread_type_lock lock, int waitflag) + + Acquire *lock*. + + If *waitflag* is ``1`` and another thread currently holds the lock, this + function will wait until the lock can be acquired and will always return + ``1``. + + If *waitflag* is ``0`` and another thread holds the lock, this function will + not wait and instead return ``0``. If the lock is not held by any other + thread, then this function will acquire it and return ``1``. + + Unlike :c:func:`PyThread_acquire_lock_timed`, acquiring the lock cannot be + interrupted by a signal. + + The caller does not need to hold an :term:`attached thread state`. + + +.. c:function:: int PyThread_release_lock(PyThread_type_lock lock) + + Release *lock*. If *lock* is not held, then this function issues a + fatal error. + + The caller does not need to hold an :term:`attached thread state`. diff --git a/Doc/c-api/sys.rst b/Doc/c-api/sys.rst index b3c89800e386ff..3a8cfd95b03513 100644 --- a/Doc/c-api/sys.rst +++ b/Doc/c-api/sys.rst @@ -123,6 +123,24 @@ Operating System Utilities This is a thin wrapper around either :c:func:`!sigaction` or :c:func:`!signal`. Do not call those functions directly! + +.. c:function:: int PyOS_InterruptOccurred(void) + + Check if a :c:macro:`!SIGINT` signal has been received. + + Returns ``1`` if a :c:macro:`!SIGINT` has occurred and clears the signal flag, + or ``0`` otherwise. + + In most cases, you should prefer :c:func:`PyErr_CheckSignals` over this function. + :c:func:`!PyErr_CheckSignals` invokes the appropriate signal handlers + for all pending signals, allowing Python code to handle the signal properly. + This function only detects :c:macro:`!SIGINT` and does not invoke any Python + signal handlers. + + This function is async-signal-safe and this function cannot fail. + The caller must hold an :term:`attached thread state`. + + .. c:function:: wchar_t* Py_DecodeLocale(const char* arg, size_t *size) .. warning:: diff --git a/Doc/c-api/threads.rst b/Doc/c-api/threads.rst new file mode 100644 index 00000000000000..7a528d712a3edd --- /dev/null +++ b/Doc/c-api/threads.rst @@ -0,0 +1,867 @@ +.. highlight:: c + +.. _threads: + +Thread states and the global interpreter lock +============================================= + +.. index:: + single: global interpreter lock + single: interpreter lock + single: lock, interpreter + +Unless on a :term:`free-threaded build` of :term:`CPython`, +the Python interpreter is generally not thread-safe. In order to support +multi-threaded Python programs, there's a global lock, called the :term:`global +interpreter lock` or :term:`GIL`, that must be held by a thread before +accessing Python objects. Without the lock, even the simplest operations +could cause problems in a multi-threaded program: for example, when +two threads simultaneously increment the reference count of the same object, the +reference count could end up being incremented only once instead of twice. + +As such, only a thread that holds the GIL may operate on Python objects or +invoke Python's C API. + +.. index:: single: setswitchinterval (in module sys) + +In order to emulate concurrency, the interpreter regularly tries to switch +threads between bytecode instructions (see :func:`sys.setswitchinterval`). +This is why locks are also necessary for thread-safety in pure-Python code. + +Additionally, the global interpreter lock is released around blocking I/O +operations, such as reading or writing to a file. From the C API, this is done +by :ref:`detaching the thread state `. + + +.. index:: + single: PyThreadState (C type) + +The Python interpreter keeps some thread-local information inside +a data structure called :c:type:`PyThreadState`, known as a :term:`thread state`. +Each thread has a thread-local pointer to a :c:type:`PyThreadState`; a thread state +referenced by this pointer is considered to be :term:`attached `. + +A thread can only have one :term:`attached thread state` at a time. An attached +thread state is typically analogous with holding the GIL, except on +free-threaded builds. On builds with the GIL enabled, attaching a thread state +will block until the GIL can be acquired. However, even on builds with the GIL +disabled, it is still required to have an attached thread state, as the interpreter +needs to keep track of which threads may access Python objects. + +.. note:: + + Even on the free-threaded build, attaching a thread state may block, as the + GIL can be re-enabled or threads might be temporarily suspended (such as during + a garbage collection). + +Generally, there will always be an attached thread state when using Python's +C API, including during embedding and when implementing methods, so it's uncommon +to need to set up a thread state on your own. Only in some specific cases, such +as in a :c:macro:`Py_BEGIN_ALLOW_THREADS` block or in a fresh thread, will the +thread not have an attached thread state. +If uncertain, check if :c:func:`PyThreadState_GetUnchecked` returns ``NULL``. + +If it turns out that you do need to create a thread state, call :c:func:`PyThreadState_New` +followed by :c:func:`PyThreadState_Swap`, or use the dangerous +:c:func:`PyGILState_Ensure` function. + + +.. _detaching-thread-state: + +Detaching the thread state from extension code +---------------------------------------------- + +Most extension code manipulating the :term:`thread state` has the following simple +structure:: + + Save the thread state in a local variable. + ... Do some blocking I/O operation ... + Restore the thread state from the local variable. + +This is so common that a pair of macros exists to simplify it:: + + Py_BEGIN_ALLOW_THREADS + ... Do some blocking I/O operation ... + Py_END_ALLOW_THREADS + +.. index:: + single: Py_BEGIN_ALLOW_THREADS (C macro) + single: Py_END_ALLOW_THREADS (C macro) + +The :c:macro:`Py_BEGIN_ALLOW_THREADS` macro opens a new block and declares a +hidden local variable; the :c:macro:`Py_END_ALLOW_THREADS` macro closes the +block. + +The block above expands to the following code:: + + PyThreadState *_save; + + _save = PyEval_SaveThread(); + ... Do some blocking I/O operation ... + PyEval_RestoreThread(_save); + +.. index:: + single: PyEval_RestoreThread (C function) + single: PyEval_SaveThread (C function) + +Here is how these functions work: + +The attached thread state implies that the GIL is held for the interpreter. +To detach it, :c:func:`PyEval_SaveThread` is called and the result is stored +in a local variable. + +By detaching the thread state, the GIL is released, which allows other threads +to attach to the interpreter and execute while the current thread performs +blocking I/O. When the I/O operation is complete, the old thread state is +reattached by calling :c:func:`PyEval_RestoreThread`, which will wait until +the GIL can be acquired. + +.. note:: + Performing blocking I/O is the most common use case for detaching + the thread state, but it is also useful to call it over long-running + native code that doesn't need access to Python objects or Python's C API. + For example, the standard :mod:`zlib` and :mod:`hashlib` modules detach the + :term:`thread state ` when compressing or hashing + data. + +On a :term:`free-threaded build`, the :term:`GIL` is usually out of the question, +but **detaching the thread state is still required**, because the interpreter +periodically needs to block all threads to get a consistent view of Python objects +without the risk of race conditions. +For example, CPython currently suspends all threads for a short period of time +while running the garbage collector. + +.. warning:: + + Detaching the thread state can lead to unexpected behavior during interpreter + finalization. See :ref:`cautions-regarding-runtime-finalization` for more + details. + + +APIs +^^^^ + +The following macros are normally used without a trailing semicolon; look for +example usage in the Python source distribution. + +.. note:: + + These macros are still necessary on the :term:`free-threaded build` to prevent + deadlocks. + +.. c:macro:: Py_BEGIN_ALLOW_THREADS + + This macro expands to ``{ PyThreadState *_save; _save = PyEval_SaveThread();``. + Note that it contains an opening brace; it must be matched with a following + :c:macro:`Py_END_ALLOW_THREADS` macro. See above for further discussion of this + macro. + + +.. c:macro:: Py_END_ALLOW_THREADS + + This macro expands to ``PyEval_RestoreThread(_save); }``. Note that it contains + a closing brace; it must be matched with an earlier + :c:macro:`Py_BEGIN_ALLOW_THREADS` macro. See above for further discussion of + this macro. + + +.. c:macro:: Py_BLOCK_THREADS + + This macro expands to ``PyEval_RestoreThread(_save);``: it is equivalent to + :c:macro:`Py_END_ALLOW_THREADS` without the closing brace. + + +.. c:macro:: Py_UNBLOCK_THREADS + + This macro expands to ``_save = PyEval_SaveThread();``: it is equivalent to + :c:macro:`Py_BEGIN_ALLOW_THREADS` without the opening brace and variable + declaration. + + +Non-Python created threads +-------------------------- + +When threads are created using the dedicated Python APIs (such as the +:mod:`threading` module), a thread state is automatically associated with them, +However, when a thread is created from native code (for example, by a +third-party library with its own thread management), it doesn't hold an +attached thread state. + +If you need to call Python code from these threads (often this will be part +of a callback API provided by the aforementioned third-party library), +you must first register these threads with the interpreter by +creating a new thread state and attaching it. + +The most robust way to do this is through :c:func:`PyThreadState_New` followed +by :c:func:`PyThreadState_Swap`. + +.. note:: + ``PyThreadState_New`` requires an argument pointing to the desired + interpreter; such a pointer can be acquired via a call to + :c:func:`PyInterpreterState_Get` from the code where the thread was + created. + +For example:: + + /* The return value of PyInterpreterState_Get() from the + function that created this thread. */ + PyInterpreterState *interp = thread_data->interp; + + /* Create a new thread state for the interpreter. It does not start out + attached. */ + PyThreadState *tstate = PyThreadState_New(interp); + + /* Attach the thread state, which will acquire the GIL. */ + PyThreadState_Swap(tstate); + + /* Perform Python actions here. */ + result = CallSomeFunction(); + /* evaluate result or handle exception */ + + /* Destroy the thread state. No Python API allowed beyond this point. */ + PyThreadState_Clear(tstate); + PyThreadState_DeleteCurrent(); + +.. warning:: + + If the interpreter finalized before ``PyThreadState_Swap`` was called, then + ``interp`` will be a dangling pointer! + +.. _gilstate: + +Legacy API +---------- + +Another common pattern to call Python code from a non-Python thread is to use +:c:func:`PyGILState_Ensure` followed by a call to :c:func:`PyGILState_Release`. + +These functions do not work well when multiple interpreters exist in the Python +process. If no Python interpreter has ever been used in the current thread (which +is common for threads created outside Python), ``PyGILState_Ensure`` will create +and attach a thread state for the "main" interpreter (the first interpreter in +the Python process). + +Additionally, these functions have thread-safety issues during interpreter +finalization. Using ``PyGILState_Ensure`` during finalization will likely +crash the process. + +Usage of these functions look like such:: + + PyGILState_STATE gstate; + gstate = PyGILState_Ensure(); + + /* Perform Python actions here. */ + result = CallSomeFunction(); + /* evaluate result or handle exception */ + + /* Release the thread. No Python API allowed beyond this point. */ + PyGILState_Release(gstate); + + +.. _fork-and-threads: + +Cautions about fork() +--------------------- + +Another important thing to note about threads is their behaviour in the face +of the C :c:func:`fork` call. On most systems with :c:func:`fork`, after a +process forks only the thread that issued the fork will exist. This has a +concrete impact both on how locks must be handled and on all stored state +in CPython's runtime. + +The fact that only the "current" thread remains +means any locks held by other threads will never be released. Python solves +this for :func:`os.fork` by acquiring the locks it uses internally before +the fork, and releasing them afterwards. In addition, it resets any +:ref:`lock-objects` in the child. When extending or embedding Python, there +is no way to inform Python of additional (non-Python) locks that need to be +acquired before or reset after a fork. OS facilities such as +:c:func:`!pthread_atfork` would need to be used to accomplish the same thing. +Additionally, when extending or embedding Python, calling :c:func:`fork` +directly rather than through :func:`os.fork` (and returning to or calling +into Python) may result in a deadlock by one of Python's internal locks +being held by a thread that is defunct after the fork. +:c:func:`PyOS_AfterFork_Child` tries to reset the necessary locks, but is not +always able to. + +The fact that all other threads go away also means that CPython's +runtime state there must be cleaned up properly, which :func:`os.fork` +does. This means finalizing all other :c:type:`PyThreadState` objects +belonging to the current interpreter and all other +:c:type:`PyInterpreterState` objects. Due to this and the special +nature of the :ref:`"main" interpreter `, +:c:func:`fork` should only be called in that interpreter's "main" +thread, where the CPython global runtime was originally initialized. +The only exception is if :c:func:`exec` will be called immediately +after. + + +High-level APIs +--------------- + +These are the most commonly used types and functions when writing multi-threaded +C extensions. + + +.. c:type:: PyThreadState + + This data structure represents the state of a single thread. The only public + data member is: + + .. c:member:: PyInterpreterState *interp + + This thread's interpreter state. + + +.. c:function:: void PyEval_InitThreads() + + .. index:: + single: PyEval_AcquireThread() + single: PyEval_ReleaseThread() + single: PyEval_SaveThread() + single: PyEval_RestoreThread() + + Deprecated function which does nothing. + + In Python 3.6 and older, this function created the GIL if it didn't exist. + + .. versionchanged:: 3.9 + The function now does nothing. + + .. versionchanged:: 3.7 + This function is now called by :c:func:`Py_Initialize()`, so you don't + have to call it yourself anymore. + + .. versionchanged:: 3.2 + This function cannot be called before :c:func:`Py_Initialize()` anymore. + + .. deprecated:: 3.9 + + .. index:: pair: module; _thread + + +.. c:function:: PyThreadState* PyEval_SaveThread() + + Detach the :term:`attached thread state` and return it. + The thread will have no :term:`thread state` upon returning. + + +.. c:function:: void PyEval_RestoreThread(PyThreadState *tstate) + + Set the :term:`attached thread state` to *tstate*. + The passed :term:`thread state` **should not** be :term:`attached `, + otherwise deadlock ensues. *tstate* will be attached upon returning. + + .. note:: + Calling this function from a thread when the runtime is finalizing will + hang the thread until the program exits, even if the thread was not + created by Python. Refer to + :ref:`cautions-regarding-runtime-finalization` for more details. + + .. versionchanged:: 3.14 + Hangs the current thread, rather than terminating it, if called while the + interpreter is finalizing. + +.. c:function:: PyThreadState* PyThreadState_Get() + + Return the :term:`attached thread state`. If the thread has no attached + thread state, (such as when inside of :c:macro:`Py_BEGIN_ALLOW_THREADS` + block), then this issues a fatal error (so that the caller needn't check + for ``NULL``). + + See also :c:func:`PyThreadState_GetUnchecked`. + +.. c:function:: PyThreadState* PyThreadState_GetUnchecked() + + Similar to :c:func:`PyThreadState_Get`, but don't kill the process with a + fatal error if it is NULL. The caller is responsible to check if the result + is NULL. + + .. versionadded:: 3.13 + In Python 3.5 to 3.12, the function was private and known as + ``_PyThreadState_UncheckedGet()``. + + +.. c:function:: PyThreadState* PyThreadState_Swap(PyThreadState *tstate) + + Set the :term:`attached thread state` to *tstate*, and return the + :term:`thread state` that was attached prior to calling. + + This function is safe to call without an :term:`attached thread state`; it + will simply return ``NULL`` indicating that there was no prior thread state. + + .. seealso:: + :c:func:`PyEval_ReleaseThread` + + .. note:: + Similar to :c:func:`PyGILState_Ensure`, this function will hang the + thread if the runtime is finalizing. + + +GIL-state APIs +-------------- + +The following functions use thread-local storage, and are not compatible +with sub-interpreters: + +.. c:type:: PyGILState_STATE + + The type of the value returned by :c:func:`PyGILState_Ensure` and passed to + :c:func:`PyGILState_Release`. + + .. c:enumerator:: PyGILState_LOCKED + + The GIL was already held when :c:func:`PyGILState_Ensure` was called. + + .. c:enumerator:: PyGILState_UNLOCKED + + The GIL was not held when :c:func:`PyGILState_Ensure` was called. + +.. c:function:: PyGILState_STATE PyGILState_Ensure() + + Ensure that the current thread is ready to call the Python C API regardless + of the current state of Python, or of the :term:`attached thread state`. This may + be called as many times as desired by a thread as long as each call is + matched with a call to :c:func:`PyGILState_Release`. In general, other + thread-related APIs may be used between :c:func:`PyGILState_Ensure` and + :c:func:`PyGILState_Release` calls as long as the thread state is restored to + its previous state before the Release(). For example, normal usage of the + :c:macro:`Py_BEGIN_ALLOW_THREADS` and :c:macro:`Py_END_ALLOW_THREADS` macros is + acceptable. + + The return value is an opaque "handle" to the :term:`attached thread state` when + :c:func:`PyGILState_Ensure` was called, and must be passed to + :c:func:`PyGILState_Release` to ensure Python is left in the same state. Even + though recursive calls are allowed, these handles *cannot* be shared - each + unique call to :c:func:`PyGILState_Ensure` must save the handle for its call + to :c:func:`PyGILState_Release`. + + When the function returns, there will be an :term:`attached thread state` + and the thread will be able to call arbitrary Python code. Failure is a fatal error. + + .. warning:: + Calling this function when the runtime is finalizing is unsafe. Doing + so will either hang the thread until the program ends, or fully crash + the interpreter in rare cases. Refer to + :ref:`cautions-regarding-runtime-finalization` for more details. + + .. versionchanged:: 3.14 + Hangs the current thread, rather than terminating it, if called while the + interpreter is finalizing. + +.. c:function:: void PyGILState_Release(PyGILState_STATE) + + Release any resources previously acquired. After this call, Python's state will + be the same as it was prior to the corresponding :c:func:`PyGILState_Ensure` call + (but generally this state will be unknown to the caller, hence the use of the + GILState API). + + Every call to :c:func:`PyGILState_Ensure` must be matched by a call to + :c:func:`PyGILState_Release` on the same thread. + +.. c:function:: PyThreadState* PyGILState_GetThisThreadState() + + Get the :term:`attached thread state` for this thread. May return ``NULL`` if no + GILState API has been used on the current thread. Note that the main thread + always has such a thread-state, even if no auto-thread-state call has been + made on the main thread. This is mainly a helper/diagnostic function. + + .. note:: + This function may return non-``NULL`` even when the :term:`thread state` + is detached. + Prefer :c:func:`PyThreadState_Get` or :c:func:`PyThreadState_GetUnchecked` + for most cases. + + .. seealso:: :c:func:`PyThreadState_Get` + +.. c:function:: int PyGILState_Check() + + Return ``1`` if the current thread is holding the :term:`GIL` and ``0`` otherwise. + This function can be called from any thread at any time. + Only if it has had its :term:`thread state ` initialized + via :c:func:`PyGILState_Ensure` will it return ``1``. + This is mainly a helper/diagnostic function. It can be useful + for example in callback contexts or memory allocation functions when + knowing that the :term:`GIL` is locked can allow the caller to perform sensitive + actions or otherwise behave differently. + + .. note:: + If the current Python process has ever created a subinterpreter, this + function will *always* return ``1``. Prefer :c:func:`PyThreadState_GetUnchecked` + for most cases. + + .. versionadded:: 3.4 + + +Low-level APIs +-------------- + +.. c:function:: PyThreadState* PyThreadState_New(PyInterpreterState *interp) + + Create a new thread state object belonging to the given interpreter object. + An :term:`attached thread state` is not needed. + +.. c:function:: void PyThreadState_Clear(PyThreadState *tstate) + + Reset all information in a :term:`thread state` object. *tstate* + must be :term:`attached ` + + .. versionchanged:: 3.9 + This function now calls the :c:member:`!PyThreadState.on_delete` callback. + Previously, that happened in :c:func:`PyThreadState_Delete`. + + .. versionchanged:: 3.13 + The :c:member:`!PyThreadState.on_delete` callback was removed. + + +.. c:function:: void PyThreadState_Delete(PyThreadState *tstate) + + Destroy a :term:`thread state` object. *tstate* should not + be :term:`attached ` to any thread. + *tstate* must have been reset with a previous call to + :c:func:`PyThreadState_Clear`. + + +.. c:function:: void PyThreadState_DeleteCurrent(void) + + Detach the :term:`attached thread state` (which must have been reset + with a previous call to :c:func:`PyThreadState_Clear`) and then destroy it. + + No :term:`thread state` will be :term:`attached ` upon + returning. + +.. c:function:: PyFrameObject* PyThreadState_GetFrame(PyThreadState *tstate) + + Get the current frame of the Python thread state *tstate*. + + Return a :term:`strong reference`. Return ``NULL`` if no frame is currently + executing. + + See also :c:func:`PyEval_GetFrame`. + + *tstate* must not be ``NULL``, and must be :term:`attached `. + + .. versionadded:: 3.9 + + +.. c:function:: uint64_t PyThreadState_GetID(PyThreadState *tstate) + + Get the unique :term:`thread state` identifier of the Python thread state *tstate*. + + *tstate* must not be ``NULL``, and must be :term:`attached `. + + .. versionadded:: 3.9 + + +.. c:function:: PyInterpreterState* PyThreadState_GetInterpreter(PyThreadState *tstate) + + Get the interpreter of the Python thread state *tstate*. + + *tstate* must not be ``NULL``, and must be :term:`attached `. + + .. versionadded:: 3.9 + + +.. c:function:: void PyThreadState_EnterTracing(PyThreadState *tstate) + + Suspend tracing and profiling in the Python thread state *tstate*. + + Resume them using the :c:func:`PyThreadState_LeaveTracing` function. + + .. versionadded:: 3.11 + + +.. c:function:: void PyThreadState_LeaveTracing(PyThreadState *tstate) + + Resume tracing and profiling in the Python thread state *tstate* suspended + by the :c:func:`PyThreadState_EnterTracing` function. + + See also :c:func:`PyEval_SetTrace` and :c:func:`PyEval_SetProfile` + functions. + + .. versionadded:: 3.11 + + +.. c:function:: int PyUnstable_ThreadState_SetStackProtection(PyThreadState *tstate, void *stack_start_addr, size_t stack_size) + + Set the stack protection start address and stack protection size + of a Python thread state. + + On success, return ``0``. + On failure, set an exception and return ``-1``. + + CPython implements :ref:`recursion control ` for C code by raising + :py:exc:`RecursionError` when it notices that the machine execution stack is close + to overflow. See for example the :c:func:`Py_EnterRecursiveCall` function. + For this, it needs to know the location of the current thread's stack, which it + normally gets from the operating system. + When the stack is changed, for example using context switching techniques like the + Boost library's ``boost::context``, you must call + :c:func:`~PyUnstable_ThreadState_SetStackProtection` to inform CPython of the change. + + Call :c:func:`~PyUnstable_ThreadState_SetStackProtection` either before + or after changing the stack. + Do not call any other Python C API between the call and the stack + change. + + See :c:func:`PyUnstable_ThreadState_ResetStackProtection` for undoing this operation. + + .. versionadded:: 3.15 + + +.. c:function:: void PyUnstable_ThreadState_ResetStackProtection(PyThreadState *tstate) + + Reset the stack protection start address and stack protection size + of a Python thread state to the operating system defaults. + + See :c:func:`PyUnstable_ThreadState_SetStackProtection` for an explanation. + + .. versionadded:: 3.15 + + +.. c:function:: PyObject* PyThreadState_GetDict() + + Return a dictionary in which extensions can store thread-specific state + information. Each extension should use a unique key to use to store state in + the dictionary. It is okay to call this function when no :term:`thread state` + is :term:`attached `. If this function returns + ``NULL``, no exception has been raised and the caller should assume no + thread state is attached. + + +.. c:function:: void PyEval_AcquireThread(PyThreadState *tstate) + + :term:`Attach ` *tstate* to the current thread, + which must not be ``NULL`` or already :term:`attached `. + + The calling thread must not already have an :term:`attached thread state`. + + .. note:: + Calling this function from a thread when the runtime is finalizing will + hang the thread until the program exits, even if the thread was not + created by Python. Refer to + :ref:`cautions-regarding-runtime-finalization` for more details. + + .. versionchanged:: 3.8 + Updated to be consistent with :c:func:`PyEval_RestoreThread`, + :c:func:`Py_END_ALLOW_THREADS`, and :c:func:`PyGILState_Ensure`, + and terminate the current thread if called while the interpreter is finalizing. + + .. versionchanged:: 3.14 + Hangs the current thread, rather than terminating it, if called while the + interpreter is finalizing. + + :c:func:`PyEval_RestoreThread` is a higher-level function which is always + available (even when threads have not been initialized). + + +.. c:function:: void PyEval_ReleaseThread(PyThreadState *tstate) + + Detach the :term:`attached thread state`. + The *tstate* argument, which must not be ``NULL``, is only used to check + that it represents the :term:`attached thread state` --- if it isn't, a fatal error is + reported. + + :c:func:`PyEval_SaveThread` is a higher-level function which is always + available (even when threads have not been initialized). + + +Asynchronous notifications +========================== + +A mechanism is provided to make asynchronous notifications to the main +interpreter thread. These notifications take the form of a function +pointer and a void pointer argument. + + +.. c:function:: int Py_AddPendingCall(int (*func)(void *), void *arg) + + Schedule a function to be called from the main interpreter thread. On + success, ``0`` is returned and *func* is queued for being called in the + main thread. On failure, ``-1`` is returned without setting any exception. + + When successfully queued, *func* will be *eventually* called from the + main interpreter thread with the argument *arg*. It will be called + asynchronously with respect to normally running Python code, but with + both these conditions met: + + * on a :term:`bytecode` boundary; + * with the main thread holding an :term:`attached thread state` + (*func* can therefore use the full C API). + + *func* must return ``0`` on success, or ``-1`` on failure with an exception + set. *func* won't be interrupted to perform another asynchronous + notification recursively, but it can still be interrupted to switch + threads if the :term:`thread state ` is detached. + + This function doesn't need an :term:`attached thread state`. However, to call this + function in a subinterpreter, the caller must have an :term:`attached thread state`. + Otherwise, the function *func* can be scheduled to be called from the wrong interpreter. + + .. warning:: + This is a low-level function, only useful for very special cases. + There is no guarantee that *func* will be called as quick as + possible. If the main thread is busy executing a system call, + *func* won't be called before the system call returns. This + function is generally **not** suitable for calling Python code from + arbitrary C threads. Instead, use the :ref:`PyGILState API`. + + .. versionadded:: 3.1 + + .. versionchanged:: 3.9 + If this function is called in a subinterpreter, the function *func* is + now scheduled to be called from the subinterpreter, rather than being + called from the main interpreter. Each subinterpreter now has its own + list of scheduled calls. + + .. versionchanged:: 3.12 + This function now always schedules *func* to be run in the main + interpreter. + + +.. c:function:: int Py_MakePendingCalls(void) + + Execute all pending calls. This is usually executed automatically by the + interpreter. + + This function returns ``0`` on success, and returns ``-1`` with an exception + set on failure. + + If this is not called in the main thread of the main + interpreter, this function does nothing and returns ``0``. + The caller must hold an :term:`attached thread state`. + + .. versionadded:: 3.1 + + .. versionchanged:: 3.12 + This function only runs pending calls in the main interpreter. + + +.. c:function:: int PyThreadState_SetAsyncExc(unsigned long id, PyObject *exc) + + Asynchronously raise an exception in a thread. The *id* argument is the thread + id of the target thread; *exc* is the exception object to be raised. This + function does not :term:`steal` any references to *exc*. To prevent naive misuse, you + must write your own C extension to call this. Must be called with an :term:`attached thread state`. + Returns the number of thread states modified; this is normally one, but will be + zero if the thread id isn't found. If *exc* is ``NULL``, the pending + exception (if any) for the thread is cleared. This raises no exceptions. + + .. versionchanged:: 3.7 + The type of the *id* parameter changed from :c:expr:`long` to + :c:expr:`unsigned long`. + + +Operating system thread APIs +============================ + +.. c:macro:: PYTHREAD_INVALID_THREAD_ID + + Sentinel value for an invalid thread ID. + + This is currently equivalent to ``(unsigned long)-1``. + + +.. c:function:: unsigned long PyThread_start_new_thread(void (*func)(void *), void *arg) + + Start function *func* in a new thread with argument *arg*. + The resulting thread is not intended to be joined. + + *func* must not be ``NULL``, but *arg* may be ``NULL``. + + On success, this function returns the identifier of the new thread; on failure, + this returns :c:macro:`PYTHREAD_INVALID_THREAD_ID`. + + The caller does not need to hold an :term:`attached thread state`. + + +.. c:function:: unsigned long PyThread_get_thread_ident(void) + + Return the identifier of the current thread, which will never be zero. + + This function cannot fail, and the caller does not need to hold an + :term:`attached thread state`. + + .. seealso:: + :py:func:`threading.get_ident` + + +.. c:function:: PyObject *PyThread_GetInfo(void) + + Get general information about the current thread in the form of a + :ref:`struct sequence ` object. This information is + accessible as :py:attr:`sys.thread_info` in Python. + + On success, this returns a new :term:`strong reference` to the thread + information; on failure, this returns ``NULL`` with an exception set. + + The caller must hold an :term:`attached thread state`. + + +.. c:macro:: PY_HAVE_THREAD_NATIVE_ID + + This macro is defined when the system supports native thread IDs. + + +.. c:function:: unsigned long PyThread_get_thread_native_id(void) + + Get the native identifier of the current thread as it was assigned by the operating + system's kernel, which will never be less than zero. + + This function is only available when :c:macro:`PY_HAVE_THREAD_NATIVE_ID` is + defined. + + This function cannot fail, and the caller does not need to hold an + :term:`attached thread state`. + + .. seealso:: + :py:func:`threading.get_native_id` + + +.. c:function:: void PyThread_exit_thread(void) + + Terminate the current thread. This function is generally considered unsafe + and should be avoided. It is kept solely for backwards compatibility. + + This function is only safe to call if all functions in the full call + stack are written to safely allow it. + + .. warning:: + + If the current system uses POSIX threads (also known as "pthreads"), + this calls :manpage:`pthread_exit(3)`, which attempts to unwind the stack + and call C++ destructors on some libc implementations. However, if a + ``noexcept`` function is reached, it may terminate the process. + Other systems, such as macOS, do unwinding. + + On Windows, this function calls ``_endthreadex()``, which kills the thread + without calling C++ destructors. + + In any case, there is a risk of corruption on the thread's stack. + + .. deprecated:: 3.14 + + +.. c:function:: void PyThread_init_thread(void) + + Initialize ``PyThread*`` APIs. Python executes this function automatically, + so there's little need to call it from an extension module. + + +.. c:function:: int PyThread_set_stacksize(size_t size) + + Set the stack size of the current thread to *size* bytes. + + This function returns ``0`` on success, ``-1`` if *size* is invalid, or + ``-2`` if the system does not support changing the stack size. This function + does not set exceptions. + + The caller does not need to hold an :term:`attached thread state`. + + +.. c:function:: size_t PyThread_get_stacksize(void) + + Return the stack size of the current thread in bytes, or ``0`` if the system's + default stack size is in use. + + The caller does not need to hold an :term:`attached thread state`. diff --git a/Doc/c-api/tls.rst b/Doc/c-api/tls.rst new file mode 100644 index 00000000000000..93ac5557141e25 --- /dev/null +++ b/Doc/c-api/tls.rst @@ -0,0 +1,155 @@ +.. highlight:: c + +.. _thread-local-storage: + +Thread-local storage support +============================ + +The Python interpreter provides low-level support for thread-local storage +(TLS) which wraps the underlying native TLS implementation to support the +Python-level thread-local storage API (:class:`threading.local`). The +CPython C level APIs are similar to those offered by pthreads and Windows: +use a thread key and functions to associate a :c:expr:`void*` value per +thread. + +A :term:`thread state` does *not* need to be :term:`attached ` +when calling these functions; they supply their own locking. + +Note that :file:`Python.h` does not include the declaration of the TLS APIs, +you need to include :file:`pythread.h` to use thread-local storage. + +.. note:: + None of these API functions handle memory management on behalf of the + :c:expr:`void*` values. You need to allocate and deallocate them yourself. + If the :c:expr:`void*` values happen to be :c:expr:`PyObject*`, these + functions don't do refcount operations on them either. + +.. _thread-specific-storage-api: + +Thread-specific storage API +--------------------------- + +The thread-specific storage (TSS) API was introduced to supersede the use of the existing TLS API within the +CPython interpreter. This API uses a new type :c:type:`Py_tss_t` instead of +:c:expr:`int` to represent thread keys. + +.. versionadded:: 3.7 + +.. seealso:: "A New C-API for Thread-Local Storage in CPython" (:pep:`539`) + + +.. c:type:: Py_tss_t + + This data structure represents the state of a thread key, the definition of + which may depend on the underlying TLS implementation, and it has an + internal field representing the key's initialization state. There are no + public members in this structure. + + When :ref:`Py_LIMITED_API ` is not defined, static allocation of + this type by :c:macro:`Py_tss_NEEDS_INIT` is allowed. + + +.. c:macro:: Py_tss_NEEDS_INIT + + This macro expands to the initializer for :c:type:`Py_tss_t` variables. + Note that this macro won't be defined with :ref:`Py_LIMITED_API `. + + +Dynamic allocation +------------------ + +Dynamic allocation of the :c:type:`Py_tss_t`, required in extension modules +built with :ref:`Py_LIMITED_API `, where static allocation of this type +is not possible due to its implementation being opaque at build time. + + +.. c:function:: Py_tss_t* PyThread_tss_alloc() + + Return a value which is the same state as a value initialized with + :c:macro:`Py_tss_NEEDS_INIT`, or ``NULL`` in the case of dynamic allocation + failure. + + +.. c:function:: void PyThread_tss_free(Py_tss_t *key) + + Free the given *key* allocated by :c:func:`PyThread_tss_alloc`, after + first calling :c:func:`PyThread_tss_delete` to ensure any associated + thread locals have been unassigned. This is a no-op if the *key* + argument is ``NULL``. + + .. note:: + A freed key becomes a dangling pointer. You should reset the key to + ``NULL``. + + +Methods +------- + +The parameter *key* of these functions must not be ``NULL``. Moreover, the +behaviors of :c:func:`PyThread_tss_set` and :c:func:`PyThread_tss_get` are +undefined if the given :c:type:`Py_tss_t` has not been initialized by +:c:func:`PyThread_tss_create`. + + +.. c:function:: int PyThread_tss_is_created(Py_tss_t *key) + + Return a non-zero value if the given :c:type:`Py_tss_t` has been initialized + by :c:func:`PyThread_tss_create`. + + +.. c:function:: int PyThread_tss_create(Py_tss_t *key) + + Return a zero value on successful initialization of a TSS key. The behavior + is undefined if the value pointed to by the *key* argument is not + initialized by :c:macro:`Py_tss_NEEDS_INIT`. This function can be called + repeatedly on the same key -- calling it on an already initialized key is a + no-op and immediately returns success. + + +.. c:function:: void PyThread_tss_delete(Py_tss_t *key) + + Destroy a TSS key to forget the values associated with the key across all + threads, and change the key's initialization state to uninitialized. A + destroyed key is able to be initialized again by + :c:func:`PyThread_tss_create`. This function can be called repeatedly on + the same key -- calling it on an already destroyed key is a no-op. + + +.. c:function:: int PyThread_tss_set(Py_tss_t *key, void *value) + + Return a zero value to indicate successfully associating a :c:expr:`void*` + value with a TSS key in the current thread. Each thread has a distinct + mapping of the key to a :c:expr:`void*` value. + + +.. c:function:: void* PyThread_tss_get(Py_tss_t *key) + + Return the :c:expr:`void*` value associated with a TSS key in the current + thread. This returns ``NULL`` if no value is associated with the key in the + current thread. + + +.. _thread-local-storage-api: + +Legacy APIs +----------- + +.. deprecated:: 3.7 + This API is superseded by the + :ref:`thread-specific storage (TSS) API `. + +.. note:: + This version of the API does not support platforms where the native TLS key + is defined in a way that cannot be safely cast to ``int``. On such platforms, + :c:func:`PyThread_create_key` will return immediately with a failure status, + and the other TLS functions will all be no-ops on such platforms. + +Due to the compatibility problem noted above, this version of the API should not +be used in new code. + +.. c:function:: int PyThread_create_key() +.. c:function:: void PyThread_delete_key(int key) +.. c:function:: int PyThread_set_key_value(int key, void *value) +.. c:function:: void* PyThread_get_key_value(int key) +.. c:function:: void PyThread_delete_key_value(int key) +.. c:function:: void PyThread_ReInitTLS() diff --git a/Doc/c-api/tuple.rst b/Doc/c-api/tuple.rst index 815afddad19df1..157b303d0b903f 100644 --- a/Doc/c-api/tuple.rst +++ b/Doc/c-api/tuple.rst @@ -48,7 +48,7 @@ Tuple Objects .. c:function:: Py_ssize_t PyTuple_Size(PyObject *p) Take a pointer to a tuple object, and return the size of that tuple. - On error, return ``-1`` and with an exception set. + On error, return ``-1`` with an exception set. .. c:function:: Py_ssize_t PyTuple_GET_SIZE(PyObject *p) @@ -90,8 +90,9 @@ Tuple Objects .. note:: - This function "steals" a reference to *o* and discards a reference to - an item already in the tuple at the affected position. + This function ":term:`steals `" a reference to *o* and discards + a reference to an item already in the tuple at the affected position + (unless it was NULL). .. c:function:: void PyTuple_SET_ITEM(PyObject *p, Py_ssize_t pos, PyObject *o) @@ -104,7 +105,7 @@ Tuple Objects .. note:: - This function "steals" a reference to *o*, and, unlike + This function ":term:`steals `" a reference to *o*, and, unlike :c:func:`PyTuple_SetItem`, does *not* discard a reference to any item that is being replaced; any reference in the tuple at position *pos* will be leaked. @@ -244,7 +245,7 @@ type. .. note:: - This function "steals" a reference to *o*. + This function ":term:`steals `" a reference to *o*. .. c:function:: void PyStructSequence_SET_ITEM(PyObject *p, Py_ssize_t *pos, PyObject *o) diff --git a/Doc/c-api/type.rst b/Doc/c-api/type.rst index ec2867b0ce09ba..1eb2f1f3dd07da 100644 --- a/Doc/c-api/type.rst +++ b/Doc/c-api/type.rst @@ -116,6 +116,20 @@ Type Objects .. versionadded:: 3.12 +.. c:function:: int PyType_Unwatch(int watcher_id, PyObject *type) + + Mark *type* as not watched. This undoes a previous call to + :c:func:`PyType_Watch`. *type* must not be ``NULL``. + + An extension should never call this function with a *watcher_id* that was + not returned to it by a previous call to :c:func:`PyType_AddWatcher`. + + On success, this function returns ``0``. On failure, this function returns + ``-1`` with an exception set. + + .. versionadded:: 3.12 + + .. c:type:: int (*PyType_WatchCallback)(PyObject *type) Type of a type-watcher callback function. @@ -133,6 +147,18 @@ Type Objects Type features are denoted by single bit flags. +.. c:function:: int PyType_FastSubclass(PyTypeObject *type, int flag) + + Return non-zero if the type object *type* sets the subclass flag *flag*. + Subclass flags are denoted by + :c:macro:`Py_TPFLAGS_*_SUBCLASS `. + This function is used by many ``_Check`` functions for common types. + + .. seealso:: + :c:func:`PyObject_TypeCheck`, which is used as a slower alternative in + ``_Check`` functions for types that don't come with subclass flags. + + .. c:function:: int PyType_IS_GC(PyTypeObject *o) Return true if the type object includes support for the cycle detector; this @@ -151,14 +177,31 @@ Type Objects .. c:function:: PyObject* PyType_GenericAlloc(PyTypeObject *type, Py_ssize_t nitems) - Generic handler for the :c:member:`~PyTypeObject.tp_alloc` slot of a type object. Use - Python's default memory allocation mechanism to allocate a new instance and - initialize all its contents to ``NULL``. + Generic handler for the :c:member:`~PyTypeObject.tp_alloc` slot of a type + object. Uses Python's default memory allocation mechanism to allocate memory + for a new instance, zeros the memory, then initializes the memory as if by + calling :c:func:`PyObject_Init` or :c:func:`PyObject_InitVar`. + + Do not call this directly to allocate memory for an object; call the type's + :c:member:`~PyTypeObject.tp_alloc` slot instead. + + For types that support garbage collection (i.e., the + :c:macro:`Py_TPFLAGS_HAVE_GC` flag is set), this function behaves like + :c:macro:`PyObject_GC_New` or :c:macro:`PyObject_GC_NewVar` (except the + memory is guaranteed to be zeroed before initialization), and should be + paired with :c:func:`PyObject_GC_Del` in :c:member:`~PyTypeObject.tp_free`. + Otherwise, it behaves like :c:macro:`PyObject_New` or + :c:macro:`PyObject_NewVar` (except the memory is guaranteed to be zeroed + before initialization) and should be paired with :c:func:`PyObject_Free` in + :c:member:`~PyTypeObject.tp_free`. + .. c:function:: PyObject* PyType_GenericNew(PyTypeObject *type, PyObject *args, PyObject *kwds) - Generic handler for the :c:member:`~PyTypeObject.tp_new` slot of a type object. Create a - new instance using the type's :c:member:`~PyTypeObject.tp_alloc` slot. + Generic handler for the :c:member:`~PyTypeObject.tp_new` slot of a type + object. Creates a new instance using the type's + :c:member:`~PyTypeObject.tp_alloc` slot and returns the resulting object. + .. c:function:: int PyType_Ready(PyTypeObject *type) @@ -176,6 +219,7 @@ Type Objects GC protocol itself by at least implementing the :c:member:`~PyTypeObject.tp_traverse` handle. + .. c:function:: PyObject* PyType_GetName(PyTypeObject *type) Return the type's name. Equivalent to getting the type's @@ -183,6 +227,7 @@ Type Objects .. versionadded:: 3.11 + .. c:function:: PyObject* PyType_GetQualName(PyTypeObject *type) Return the type's qualified name. Equivalent to getting the @@ -198,6 +243,7 @@ Type Objects .. versionadded:: 3.13 + .. c:function:: PyObject* PyType_GetModuleName(PyTypeObject *type) Return the type's module name. Equivalent to getting the @@ -205,6 +251,7 @@ Type Objects .. versionadded:: 3.13 + .. c:function:: void* PyType_GetSlot(PyTypeObject *type, int slot) Return the function pointer stored in the given slot. If the @@ -221,11 +268,16 @@ Type Objects :c:func:`PyType_GetSlot` can now accept all types. Previously, it was limited to :ref:`heap types `. + .. c:function:: PyObject* PyType_GetModule(PyTypeObject *type) Return the module object associated with the given type when the type was created using :c:func:`PyType_FromModuleAndSpec`. + The returned reference is :term:`borrowed ` from *type*, + and will be valid as long as you hold a reference to *type*. + Do not release it with :c:func:`Py_DECREF` or similar. + If no module is associated with the given type, sets :py:class:`TypeError` and returns ``NULL``. @@ -240,6 +292,7 @@ Type Objects .. versionadded:: 3.9 + .. c:function:: void* PyType_GetModuleState(PyTypeObject *type) Return the state of the module object associated with the given type. @@ -254,6 +307,7 @@ Type Objects .. versionadded:: 3.9 + .. c:function:: PyObject* PyType_GetModuleByDef(PyTypeObject *type, struct PyModuleDef *def) Find the first superclass whose module was created from @@ -267,8 +321,13 @@ Type Objects and other places where a method's defining class cannot be passed using the :c:type:`PyCMethod` calling convention. + The returned reference is :term:`borrowed ` from *type*, + and will be valid as long as you hold a reference to *type*. + Do not release it with :c:func:`Py_DECREF` or similar. + .. versionadded:: 3.11 + .. c:function:: int PyType_GetBaseByToken(PyTypeObject *type, void *token, PyTypeObject **result) Find the first superclass in *type*'s :term:`method resolution order` whose @@ -287,6 +346,7 @@ Type Objects .. versionadded:: 3.14 + .. c:function:: int PyUnstable_Type_AssignVersionTag(PyTypeObject *type) Attempt to assign a version tag to the given type. @@ -297,6 +357,16 @@ Type Objects .. versionadded:: 3.12 +.. c:function:: int PyType_SUPPORTS_WEAKREFS(PyTypeObject *type) + + Return true if instances of *type* support creating weak references, false + otherwise. This function always succeeds. *type* must not be ``NULL``. + + .. seealso:: + * :ref:`weakrefobjects` + * :py:mod:`weakref` + + Creating Heap-Allocated Types ............................. @@ -317,8 +387,8 @@ The following functions and structs are used to create The *bases* argument can be used to specify base classes; it can either be only one class or a tuple of classes. - If *bases* is ``NULL``, the *Py_tp_bases* slot is used instead. - If that also is ``NULL``, the *Py_tp_base* slot is used instead. + If *bases* is ``NULL``, the :c:data:`Py_tp_bases` slot is used instead. + If that also is ``NULL``, the :c:data:`Py_tp_base` slot is used instead. If that also is ``NULL``, the new type derives from :class:`object`. The *module* argument can be used to record the module in which the new @@ -345,6 +415,7 @@ The following functions and structs are used to create .. versionadded:: 3.12 + .. c:function:: PyObject* PyType_FromModuleAndSpec(PyObject *module, PyType_Spec *spec, PyObject *bases) Equivalent to ``PyType_FromMetaclass(NULL, module, spec, bases)``. @@ -371,6 +442,7 @@ The following functions and structs are used to create Creating classes whose metaclass overrides :c:member:`~PyTypeObject.tp_new` is no longer allowed. + .. c:function:: PyObject* PyType_FromSpecWithBases(PyType_Spec *spec, PyObject *bases) Equivalent to ``PyType_FromMetaclass(NULL, NULL, spec, bases)``. @@ -392,6 +464,7 @@ The following functions and structs are used to create Creating classes whose metaclass overrides :c:member:`~PyTypeObject.tp_new` is no longer allowed. + .. c:function:: PyObject* PyType_FromSpec(PyType_Spec *spec) Equivalent to ``PyType_FromMetaclass(NULL, NULL, spec, NULL)``. @@ -412,6 +485,7 @@ The following functions and structs are used to create Creating classes whose metaclass overrides :c:member:`~PyTypeObject.tp_new` is no longer allowed. + .. c:function:: int PyType_Freeze(PyTypeObject *type) Make a type immutable: set the :c:macro:`Py_TPFLAGS_IMMUTABLETYPE` flag. @@ -477,7 +551,7 @@ The following functions and structs are used to create in the following situations: - The base is not variable-sized (its - :c:member:`~PyTypeObject.tp_itemsize`). + :c:member:`~PyTypeObject.tp_itemsize` is zero). - The requested :c:member:`PyType_Spec.basicsize` is positive, suggesting that the memory layout of the base class is known. - The requested :c:member:`PyType_Spec.basicsize` is zero, @@ -520,9 +594,9 @@ The following functions and structs are used to create :c:type:`PyAsyncMethods` with an added ``Py_`` prefix. For example, use: - * ``Py_tp_dealloc`` to set :c:member:`PyTypeObject.tp_dealloc` - * ``Py_nb_add`` to set :c:member:`PyNumberMethods.nb_add` - * ``Py_sq_length`` to set :c:member:`PySequenceMethods.sq_length` + * :c:data:`Py_tp_dealloc` to set :c:member:`PyTypeObject.tp_dealloc` + * :c:data:`Py_nb_add` to set :c:member:`PyNumberMethods.nb_add` + * :c:data:`Py_sq_length` to set :c:member:`PySequenceMethods.sq_length` An additional slot is supported that does not correspond to a :c:type:`!PyTypeObject` struct field: @@ -541,7 +615,7 @@ The following functions and structs are used to create If it is not possible to switch to a ``MANAGED`` flag (for example, for vectorcall or to support Python older than 3.12), specify the - offset in :c:member:`Py_tp_members `. + offset in :c:data:`Py_tp_members`. See :ref:`PyMemberDef documentation ` for details. @@ -568,8 +642,8 @@ The following functions and structs are used to create under the :ref:`limited API `. .. versionchanged:: 3.14 - The field :c:member:`~PyTypeObject.tp_vectorcall` can now set - using ``Py_tp_vectorcall``. See the field's documentation + The field :c:member:`~PyTypeObject.tp_vectorcall` can now be set + using :c:data:`Py_tp_vectorcall`. See the field's documentation for details. .. c:member:: void *pfunc @@ -579,10 +653,11 @@ The following functions and structs are used to create *pfunc* values may not be ``NULL``, except for the following slots: - * ``Py_tp_doc`` + * :c:data:`Py_tp_doc` * :c:data:`Py_tp_token` (for clarity, prefer :c:data:`Py_TP_USE_SPEC` rather than ``NULL``) + .. c:macro:: Py_tp_token A :c:member:`~PyType_Slot.slot` that records a static memory layout ID diff --git a/Doc/c-api/typehints.rst b/Doc/c-api/typehints.rst index 98fe68737deb81..ec2fba6da8b043 100644 --- a/Doc/c-api/typehints.rst +++ b/Doc/c-api/typehints.rst @@ -31,7 +31,7 @@ two types exist -- :ref:`GenericAlias ` and static PyMethodDef my_obj_methods[] = { // Other methods. ... - {"__class_getitem__", Py_GenericAlias, METH_O|METH_CLASS, "See PEP 585"} + {"__class_getitem__", Py_GenericAlias, METH_O|METH_CLASS, "my_obj is generic over its contained type"} ... } diff --git a/Doc/c-api/typeobj.rst b/Doc/c-api/typeobj.rst index 3b9f07778d5ace..4d69821ba9dfae 100644 --- a/Doc/c-api/typeobj.rst +++ b/Doc/c-api/typeobj.rst @@ -79,7 +79,7 @@ Quick Reference | :c:member:`~PyTypeObject.tp_setattro` | :c:type:`setattrofunc` | __setattr__, | X | X | | G | | | | __delattr__ | | | | | +------------------------------------------------+-----------------------------------+-------------------+---+---+---+---+ - | :c:member:`~PyTypeObject.tp_as_buffer` | :c:type:`PyBufferProcs` * | | | | | % | + | :c:member:`~PyTypeObject.tp_as_buffer` | :c:type:`PyBufferProcs` * | :ref:`sub-slots` | | | | % | +------------------------------------------------+-----------------------------------+-------------------+---+---+---+---+ | :c:member:`~PyTypeObject.tp_flags` | unsigned long | | X | X | | ? | +------------------------------------------------+-----------------------------------+-------------------+---+---+---+---+ @@ -325,9 +325,10 @@ sub-slots +---------------------------------------------------------+-----------------------------------+---------------+ | | +---------------------------------------------------------+-----------------------------------+---------------+ - | :c:member:`~PyBufferProcs.bf_getbuffer` | :c:func:`getbufferproc` | | + | :c:member:`~PyBufferProcs.bf_getbuffer` | :c:func:`getbufferproc` | __buffer__ | +---------------------------------------------------------+-----------------------------------+---------------+ - | :c:member:`~PyBufferProcs.bf_releasebuffer` | :c:func:`releasebufferproc` | | + | :c:member:`~PyBufferProcs.bf_releasebuffer` | :c:func:`releasebufferproc` | __release_\ | + | | | buffer\__ | +---------------------------------------------------------+-----------------------------------+---------------+ .. _slot-typedefs-table: @@ -491,9 +492,9 @@ metatype) initializes :c:member:`~PyTypeObject.tp_itemsize`, which means that it type objects) *must* have the :c:member:`~PyVarObject.ob_size` field. -.. c:member:: Py_ssize_t PyObject.ob_refcnt +:c:member:`PyObject.ob_refcnt` - This is the type object's reference count, initialized to ``1`` by the + The type object's reference count is initialized to ``1`` by the ``PyObject_HEAD_INIT`` macro. Note that for :ref:`statically allocated type objects `, the type's instances (objects whose :c:member:`~PyObject.ob_type` points back to the type) do *not* count as references. But for @@ -505,7 +506,7 @@ type objects) *must* have the :c:member:`~PyVarObject.ob_size` field. This field is not inherited by subtypes. -.. c:member:: PyTypeObject* PyObject.ob_type +:c:member:`PyObject.ob_type` This is the type's type, in other words its metatype. It is initialized by the argument to the ``PyObject_HEAD_INIT`` macro, and its value should normally be @@ -531,14 +532,13 @@ type objects) *must* have the :c:member:`~PyVarObject.ob_size` field. PyVarObject Slots ----------------- -.. c:member:: Py_ssize_t PyVarObject.ob_size +:c:member:`PyVarObject.ob_size` For :ref:`statically allocated type objects `, this should be initialized to zero. For :ref:`dynamically allocated type objects `, this field has a special internal meaning. - This field should be accessed using the :c:func:`Py_SIZE()` and - :c:func:`Py_SET_SIZE()` macros. + This field should be accessed using the :c:func:`Py_SIZE()` macro. **Inheritance:** @@ -676,77 +676,144 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: destructor PyTypeObject.tp_dealloc - A pointer to the instance destructor function. This function must be defined - unless the type guarantees that its instances will never be deallocated (as is - the case for the singletons ``None`` and ``Ellipsis``). The function signature is:: + .. corresponding-type-slot:: Py_tp_dealloc + + A pointer to the instance destructor function. The function signature is:: void tp_dealloc(PyObject *self); - The destructor function is called by the :c:func:`Py_DECREF` and - :c:func:`Py_XDECREF` macros when the new reference count is zero. At this point, - the instance is still in existence, but there are no references to it. The - destructor function should free all references which the instance owns, free all - memory buffers owned by the instance (using the freeing function corresponding - to the allocation function used to allocate the buffer), and call the type's - :c:member:`~PyTypeObject.tp_free` function. If the type is not subtypable - (doesn't have the :c:macro:`Py_TPFLAGS_BASETYPE` flag bit set), it is - permissible to call the object deallocator directly instead of via - :c:member:`~PyTypeObject.tp_free`. The object deallocator should be the one used to allocate the - instance; this is normally :c:func:`PyObject_Free` if the instance was allocated - using :c:macro:`PyObject_New` or :c:macro:`PyObject_NewVar`, or - :c:func:`PyObject_GC_Del` if the instance was allocated using - :c:macro:`PyObject_GC_New` or :c:macro:`PyObject_GC_NewVar`. - - If the type supports garbage collection (has the :c:macro:`Py_TPFLAGS_HAVE_GC` - flag bit set), the destructor should call :c:func:`PyObject_GC_UnTrack` - before clearing any member fields. + The destructor function should remove all references which the instance owns + (e.g., call :c:func:`Py_CLEAR`), free all memory buffers owned by the + instance, and call the type's :c:member:`~PyTypeObject.tp_free` function to + free the object itself. + + If you may call functions that may set the error indicator, you must use + :c:func:`PyErr_GetRaisedException` and :c:func:`PyErr_SetRaisedException` + to ensure you don't clobber a preexisting error indicator (the deallocation + could have occurred while processing a different error): .. code-block:: c static void - foo_dealloc(PyObject *op) + foo_dealloc(foo_object *self) { + PyObject *et, *ev, *etb; + PyObject *exc = PyErr_GetRaisedException(); + ... + PyErr_SetRaisedException(exc); + } + + The dealloc handler itself must not raise an exception; if it hits an error + case it should call :c:func:`PyErr_FormatUnraisable` to log (and clear) an + unraisable exception. + + No guarantees are made about when an object is destroyed, except: + + * Python will destroy an object immediately or some time after the final + reference to the object is deleted, unless its finalizer + (:c:member:`~PyTypeObject.tp_finalize`) subsequently resurrects the + object. + * An object will not be destroyed while it is being automatically finalized + (:c:member:`~PyTypeObject.tp_finalize`) or automatically cleared + (:c:member:`~PyTypeObject.tp_clear`). + + CPython currently destroys an object immediately from :c:func:`Py_DECREF` + when the new reference count is zero, but this may change in a future + version. + + It is recommended to call :c:func:`PyObject_CallFinalizerFromDealloc` at the + beginning of :c:member:`!tp_dealloc` to guarantee that the object is always + finalized before destruction. + + If the type supports garbage collection (the :c:macro:`Py_TPFLAGS_HAVE_GC` + flag is set), the destructor should call :c:func:`PyObject_GC_UnTrack` + before clearing any member fields. + + It is permissible to call :c:member:`~PyTypeObject.tp_clear` from + :c:member:`!tp_dealloc` to reduce code duplication and to guarantee that the + object is always cleared before destruction. Beware that + :c:member:`!tp_clear` might have already been called. + + If the type is heap allocated (:c:macro:`Py_TPFLAGS_HEAPTYPE`), the + deallocator should release the owned reference to its type object (via + :c:func:`Py_DECREF`) after calling the type deallocator. See the example + code below.:: + + static void + foo_dealloc(PyObject *op) + { foo_object *self = (foo_object *) op; PyObject_GC_UnTrack(self); Py_CLEAR(self->ref); Py_TYPE(self)->tp_free(self); - } + } - Finally, if the type is heap allocated (:c:macro:`Py_TPFLAGS_HEAPTYPE`), the - deallocator should release the owned reference to its type object - (via :c:func:`Py_DECREF`) after - calling the type deallocator. In order to avoid dangling pointers, the - recommended way to achieve this is: + :c:member:`!tp_dealloc` must leave the exception status unchanged. If it + needs to call something that might raise an exception, the exception state + must be backed up first and restored later (after logging any exceptions + with :c:func:`PyErr_WriteUnraisable`). - .. code-block:: c + Example:: - static void - foo_dealloc(PyObject *op) - { - PyTypeObject *tp = Py_TYPE(op); - // free references and buffers here - tp->tp_free(op); - Py_DECREF(tp); - } + static void + foo_dealloc(PyObject *self) + { + PyObject *exc = PyErr_GetRaisedException(); - .. warning:: + if (PyObject_CallFinalizerFromDealloc(self) < 0) { + // self was resurrected. + goto done; + } + + PyTypeObject *tp = Py_TYPE(self); + + if (tp->tp_flags & Py_TPFLAGS_HAVE_GC) { + PyObject_GC_UnTrack(self); + } + + // Optional, but convenient to avoid code duplication. + if (tp->tp_clear && tp->tp_clear(self) < 0) { + PyErr_WriteUnraisable(self); + } - In a garbage collected Python, :c:member:`!tp_dealloc` may be called from - any Python thread, not just the thread which created the object (if the - object becomes part of a refcount cycle, that cycle might be collected by - a garbage collection on any thread). This is not a problem for Python - API calls, since the thread on which :c:member:`!tp_dealloc` is called - with an :term:`attached thread state`. However, if the object being - destroyed in turn destroys objects from some other C or C++ library, care - should be taken to ensure that destroying those objects on the thread - which called :c:member:`!tp_dealloc` will not violate any assumptions of - the library. + // Any additional destruction goes here. + + tp->tp_free(self); + self = NULL; // In case PyErr_WriteUnraisable() is called below. + + if (tp->tp_flags & Py_TPFLAGS_HEAPTYPE) { + Py_CLEAR(tp); + } + + done: + // Optional, if something was called that might have raised an + // exception. + if (PyErr_Occurred()) { + PyErr_WriteUnraisable(self); + } + PyErr_SetRaisedException(exc); + } + + :c:member:`!tp_dealloc` may be called from + any Python thread, not just the thread which created the object (if the + object becomes part of a refcount cycle, that cycle might be collected by + a garbage collection on any thread). This is not a problem for Python + API calls, since the thread on which :c:member:`!tp_dealloc` is called + with an :term:`attached thread state`. However, if the object being + destroyed in turn destroys objects from some other C library, care + should be taken to ensure that destroying those objects on the thread + which called :c:member:`!tp_dealloc` will not violate any assumptions of + the library. **Inheritance:** This field is inherited by subtypes. + .. seealso:: + + :ref:`life-cycle` for details about how this slot relates to other slots. + .. c:member:: Py_ssize_t PyTypeObject.tp_vectorcall_offset @@ -795,6 +862,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: getattrfunc PyTypeObject.tp_getattr + .. corresponding-type-slot:: Py_tp_getattr + An optional pointer to the get-attribute-string function. This field is deprecated. When it is defined, it should point to a function @@ -812,6 +881,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: setattrfunc PyTypeObject.tp_setattr + .. corresponding-type-slot:: Py_tp_setattr + An optional pointer to the function for setting and deleting attributes. This field is deprecated. When it is defined, it should point to a function @@ -844,6 +915,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: reprfunc PyTypeObject.tp_repr + .. corresponding-type-slot:: Py_tp_repr + .. index:: pair: built-in function; repr An optional pointer to a function that implements the built-in function @@ -909,6 +982,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: hashfunc PyTypeObject.tp_hash + .. corresponding-type-slot:: Py_tp_hash + .. index:: pair: built-in function; hash An optional pointer to a function that implements the built-in function @@ -950,6 +1025,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: ternaryfunc PyTypeObject.tp_call + .. corresponding-type-slot:: Py_tp_call + An optional pointer to a function that implements calling the object. This should be ``NULL`` if the object is not callable. The signature is the same as for :c:func:`PyObject_Call`:: @@ -963,6 +1040,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: reprfunc PyTypeObject.tp_str + .. corresponding-type-slot:: Py_tp_str + An optional pointer to a function that implements the built-in operation :func:`str`. (Note that :class:`str` is a type now, and :func:`str` calls the constructor for that type. This constructor calls :c:func:`PyObject_Str` to do @@ -988,6 +1067,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: getattrofunc PyTypeObject.tp_getattro + .. corresponding-type-slot:: Py_tp_getattro + An optional pointer to the get-attribute function. The signature is the same as for :c:func:`PyObject_GetAttr`:: @@ -1012,6 +1093,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: setattrofunc PyTypeObject.tp_setattro + .. corresponding-type-slot:: Py_tp_setattro + An optional pointer to the function for setting and deleting attributes. The signature is the same as for :c:func:`PyObject_SetAttr`:: @@ -1137,11 +1220,11 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:macro:: Py_TPFLAGS_HAVE_GC This bit is set when the object supports garbage collection. If this bit - is set, instances must be created using :c:macro:`PyObject_GC_New` and - destroyed using :c:func:`PyObject_GC_Del`. More information in section - :ref:`supporting-cycle-detection`. This bit also implies that the - GC-related fields :c:member:`~PyTypeObject.tp_traverse` and :c:member:`~PyTypeObject.tp_clear` are present in - the type object. + is set, memory for new instances (see :c:member:`~PyTypeObject.tp_alloc`) + must be allocated using :c:macro:`PyObject_GC_New` or + :c:func:`PyType_GenericAlloc` and deallocated (see + :c:member:`~PyTypeObject.tp_free`) using :c:func:`PyObject_GC_Del`. More + information in section :ref:`supporting-cycle-detection`. **Inheritance:** @@ -1192,7 +1275,7 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:macro:: Py_TPFLAGS_MANAGED_DICT - This bit indicates that instances of the class have a `~object.__dict__` + This bit indicates that instances of the class have a :attr:`~object.__dict__` attribute, and that the space for the dictionary is managed by the VM. If this flag is set, :c:macro:`Py_TPFLAGS_HAVE_GC` should also be set. @@ -1253,8 +1336,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:macro:: Py_TPFLAGS_BASE_EXC_SUBCLASS .. c:macro:: Py_TPFLAGS_TYPE_SUBCLASS - These flags are used by functions such as - :c:func:`PyLong_Check` to quickly determine if a type is a subclass + Functions such as :c:func:`PyLong_Check` will call :c:func:`PyType_FastSubclass` + with one of these flags to quickly determine if a type is a subclass of a built-in type; such specific checks are faster than a generic check, like :c:func:`PyObject_IsInstance`. Custom types that inherit from built-ins should have their :c:member:`~PyTypeObject.tp_flags` @@ -1275,6 +1358,9 @@ and :c:data:`PyType_Type` effectively act as defaults.) type structure. + .. c:macro:: _Py_TPFLAGS_HAVE_VECTORCALL + :no-typesetting: + .. c:macro:: Py_TPFLAGS_HAVE_VECTORCALL This bit is set when the class implements @@ -1286,7 +1372,12 @@ and :c:data:`PyType_Type` effectively act as defaults.) This bit is inherited if :c:member:`~PyTypeObject.tp_call` is also inherited. - .. versionadded:: 3.9 + .. versionadded:: 3.8 as ``_Py_TPFLAGS_HAVE_VECTORCALL`` + + .. versionchanged:: 3.9 + + Renamed to the current name, without the leading underscore. + The old provisional name is :term:`soft deprecated`. .. versionchanged:: 3.12 @@ -1393,8 +1484,58 @@ and :c:data:`PyType_Type` effectively act as defaults.) It will be removed in a future version of CPython + .. c:macro:: Py_TPFLAGS_HAVE_VERSION_TAG + + This macro does nothing. + Historically, this would indicate that the + :c:member:`~PyTypeObject.tp_version_tag` field was available and + initialized. + + .. soft-deprecated:: 3.13 + + + .. c:macro:: Py_TPFLAGS_INLINE_VALUES + + This bit indicates that instances of this type will have an "inline values" + array (containing the object's attributes) placed directly after the end + of the object. + + This requires that :c:macro:`Py_TPFLAGS_HAVE_GC` is set. + + **Inheritance:** + + This flag is not inherited. + + .. versionadded:: 3.13 + + + .. c:macro:: Py_TPFLAGS_IS_ABSTRACT + + This bit indicates that this is an abstract type and therefore cannot + be instantiated. + + **Inheritance:** + + This flag is not inherited. + + .. seealso:: + :mod:`abc` + + + .. c:macro:: Py_TPFLAGS_HAVE_STACKLESS_EXTENSION + + Internal. Do not set or unset this flag. + Historically, this was a reserved flag for use in Stackless Python. + + .. warning:: + This flag is present in header files, but is not be used. + This may be removed in a future version of CPython. + + .. c:member:: const char* PyTypeObject.tp_doc + .. corresponding-type-slot:: Py_tp_doc + An optional pointer to a NUL-terminated C string giving the docstring for this type object. This is exposed as the :attr:`~type.__doc__` attribute on the type and instances of the type. @@ -1406,6 +1547,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: traverseproc PyTypeObject.tp_traverse + .. corresponding-type-slot:: Py_tp_traverse + An optional pointer to a traversal function for the garbage collector. This is only used if the :c:macro:`Py_TPFLAGS_HAVE_GC` flag bit is set. The signature is:: @@ -1467,6 +1610,11 @@ and :c:data:`PyType_Type` effectively act as defaults.) but the instance has no strong reference to the elements inside it, as they are allowed to be removed even if the instance is still alive). + .. warning:: + The traversal function must not have any side effects. It must not + modify the reference counts of any Python objects nor create or destroy + any Python objects. + Note that :c:func:`Py_VISIT` requires the *visit* and *arg* parameters to :c:func:`!local_traverse` to have these specific names; don't name them just anything. @@ -1478,6 +1626,11 @@ and :c:data:`PyType_Type` effectively act as defaults.) heap-allocated superclass). If they do not, the type object may not be garbage-collected. + .. note:: + + The :c:member:`~PyTypeObject.tp_traverse` function can be called from any + thread. + .. versionchanged:: 3.9 Heap-allocated types are expected to visit ``Py_TYPE(self)`` in @@ -1497,20 +1650,103 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: inquiry PyTypeObject.tp_clear - An optional pointer to a clear function for the garbage collector. This is only - used if the :c:macro:`Py_TPFLAGS_HAVE_GC` flag bit is set. The signature is:: + .. corresponding-type-slot:: Py_tp_clear + + An optional pointer to a clear function. The signature is:: int tp_clear(PyObject *); - The :c:member:`~PyTypeObject.tp_clear` member function is used to break reference cycles in cyclic - garbage detected by the garbage collector. Taken together, all :c:member:`~PyTypeObject.tp_clear` - functions in the system must combine to break all reference cycles. This is - subtle, and if in any doubt supply a :c:member:`~PyTypeObject.tp_clear` function. For example, - the tuple type does not implement a :c:member:`~PyTypeObject.tp_clear` function, because it's - possible to prove that no reference cycle can be composed entirely of tuples. - Therefore the :c:member:`~PyTypeObject.tp_clear` functions of other types must be sufficient to - break any cycle containing a tuple. This isn't immediately obvious, and there's - rarely a good reason to avoid implementing :c:member:`~PyTypeObject.tp_clear`. + The purpose of this function is to break reference cycles that are causing a + :term:`cyclic isolate` so that the objects can be safely destroyed. A + cleared object is a partially destroyed object; the object is not obligated + to satisfy design invariants held during normal use. + + :c:member:`!tp_clear` does not need to delete references to objects that + can't participate in reference cycles, such as Python strings or Python + integers. However, it may be convenient to clear all references, and write + the type's :c:member:`~PyTypeObject.tp_dealloc` function to invoke + :c:member:`!tp_clear` to avoid code duplication. (Beware that + :c:member:`!tp_clear` might have already been called. Prefer calling + idempotent functions like :c:func:`Py_CLEAR`.) + + Any non-trivial cleanup should be performed in + :c:member:`~PyTypeObject.tp_finalize` instead of :c:member:`!tp_clear`. + + .. note:: + + If :c:member:`!tp_clear` fails to break a reference cycle then the + objects in the :term:`cyclic isolate` may remain indefinitely + uncollectable ("leak"). See :data:`gc.garbage`. + + .. note:: + + Referents (direct and indirect) might have already been cleared; they are + not guaranteed to be in a consistent state. + + .. note:: + + The :c:member:`~PyTypeObject.tp_clear` function can be called from any + thread. + + .. note:: + + An object is not guaranteed to be automatically cleared before its + destructor (:c:member:`~PyTypeObject.tp_dealloc`) is called. + + This function differs from the destructor + (:c:member:`~PyTypeObject.tp_dealloc`) in the following ways: + + * The purpose of clearing an object is to remove references to other objects + that might participate in a reference cycle. The purpose of the + destructor, on the other hand, is a superset: it must release *all* + resources it owns, including references to objects that cannot participate + in a reference cycle (e.g., integers) as well as the object's own memory + (by calling :c:member:`~PyTypeObject.tp_free`). + * When :c:member:`!tp_clear` is called, other objects might still hold + references to the object being cleared. Because of this, + :c:member:`!tp_clear` must not deallocate the object's own memory + (:c:member:`~PyTypeObject.tp_free`). The destructor, on the other hand, + is only called when no (strong) references exist, and as such, must + safely destroy the object itself by deallocating it. + * :c:member:`!tp_clear` might never be automatically called. An object's + destructor, on the other hand, will be automatically called some time + after the object becomes unreachable (i.e., either there are no references + to the object or the object is a member of a :term:`cyclic isolate`). + + No guarantees are made about when, if, or how often Python automatically + clears an object, except: + + * Python will not automatically clear an object if it is reachable, i.e., + there is a reference to it and it is not a member of a :term:`cyclic + isolate`. + * Python will not automatically clear an object if it has not been + automatically finalized (see :c:member:`~PyTypeObject.tp_finalize`). (If + the finalizer resurrected the object, the object may or may not be + automatically finalized again before it is cleared.) + * If an object is a member of a :term:`cyclic isolate`, Python will not + automatically clear it if any member of the cyclic isolate has not yet + been automatically finalized (:c:member:`~PyTypeObject.tp_finalize`). + * Python will not destroy an object until after any automatic calls to its + :c:member:`!tp_clear` function have returned. This ensures that the act + of breaking a reference cycle does not invalidate the ``self`` pointer + while :c:member:`!tp_clear` is still executing. + * Python will not automatically call :c:member:`!tp_clear` multiple times + concurrently. + + CPython currently only automatically clears objects as needed to break + reference cycles in a :term:`cyclic isolate`, but future versions might + clear objects regularly before their destruction. + + Taken together, all :c:member:`~PyTypeObject.tp_clear` functions in the + system must combine to break all reference cycles. This is subtle, and if + in any doubt supply a :c:member:`~PyTypeObject.tp_clear` function. For + example, the tuple type does not implement a + :c:member:`~PyTypeObject.tp_clear` function, because it's possible to prove + that no reference cycle can be composed entirely of tuples. Therefore the + :c:member:`~PyTypeObject.tp_clear` functions of other types are responsible + for breaking any cycle containing a tuple. This isn't immediately obvious, + and there's rarely a good reason to avoid implementing + :c:member:`~PyTypeObject.tp_clear`. Implementations of :c:member:`~PyTypeObject.tp_clear` should drop the instance's references to those of its members that may be Python objects, and set its pointers to those @@ -1540,23 +1776,11 @@ and :c:data:`PyType_Type` effectively act as defaults.) :c:func:`Py_CLEAR` macro performs the operations in a safe order. If the :c:macro:`Py_TPFLAGS_MANAGED_DICT` bit is set in the - :c:member:`~PyTypeObject.tp_flags` field, the traverse function must call + :c:member:`~PyTypeObject.tp_flags` field, the clear function must call :c:func:`PyObject_ClearManagedDict` like this:: PyObject_ClearManagedDict((PyObject*)self); - Note that :c:member:`~PyTypeObject.tp_clear` is not *always* called - before an instance is deallocated. For example, when reference counting - is enough to determine that an object is no longer used, the cyclic garbage - collector is not involved and :c:member:`~PyTypeObject.tp_dealloc` is - called directly. - - Because the goal of :c:member:`~PyTypeObject.tp_clear` functions is to break reference cycles, - it's not necessary to clear contained objects like Python strings or Python - integers, which can't participate in reference cycles. On the other hand, it may - be convenient to clear all contained Python objects, and write the type's - :c:member:`~PyTypeObject.tp_dealloc` function to invoke :c:member:`~PyTypeObject.tp_clear`. - More information about Python's garbage collection scheme can be found in section :ref:`supporting-cycle-detection`. @@ -1569,9 +1793,15 @@ and :c:data:`PyType_Type` effectively act as defaults.) :c:member:`~PyTypeObject.tp_clear` are all inherited from the base type if they are all zero in the subtype. + .. seealso:: + + :ref:`life-cycle` for details about how this slot relates to other slots. + .. c:member:: richcmpfunc PyTypeObject.tp_richcompare + .. corresponding-type-slot:: Py_tp_richcompare + An optional pointer to the rich comparison function, whose signature is:: PyObject *tp_richcompare(PyObject *self, PyObject *other, int op); @@ -1674,6 +1904,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: getiterfunc PyTypeObject.tp_iter + .. corresponding-type-slot:: Py_tp_iter + An optional pointer to a function that returns an :term:`iterator` for the object. Its presence normally signals that the instances of this type are :term:`iterable` (although sequences may be iterable without this function). @@ -1689,6 +1921,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: iternextfunc PyTypeObject.tp_iternext + .. corresponding-type-slot:: Py_tp_iternext + An optional pointer to a function that returns the next item in an :term:`iterator`. The signature is:: @@ -1712,6 +1946,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: struct PyMethodDef* PyTypeObject.tp_methods + .. corresponding-type-slot:: Py_tp_methods + An optional pointer to a static ``NULL``-terminated array of :c:type:`PyMethodDef` structures, declaring regular methods of this type. @@ -1726,6 +1962,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: struct PyMemberDef* PyTypeObject.tp_members + .. corresponding-type-slot:: Py_tp_members + An optional pointer to a static ``NULL``-terminated array of :c:type:`PyMemberDef` structures, declaring regular data members (fields or slots) of instances of this type. @@ -1741,6 +1979,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: struct PyGetSetDef* PyTypeObject.tp_getset + .. corresponding-type-slot:: Py_tp_getset + An optional pointer to a static ``NULL``-terminated array of :c:type:`PyGetSetDef` structures, declaring computed attributes of instances of this type. @@ -1755,6 +1995,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: PyTypeObject* PyTypeObject.tp_base + .. corresponding-type-slot:: Py_tp_base + An optional pointer to a base type from which type properties are inherited. At this level, only single inheritance is supported; multiple inheritance require dynamically creating a type object by calling the metatype. @@ -1827,6 +2069,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: descrgetfunc PyTypeObject.tp_descr_get + .. corresponding-type-slot:: Py_tp_descr_get + An optional pointer to a "descriptor get" function. The function signature is:: @@ -1842,6 +2086,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: descrsetfunc PyTypeObject.tp_descr_set + .. corresponding-type-slot:: Py_tp_descr_set + An optional pointer to a function for setting and deleting a descriptor's value. @@ -1902,6 +2148,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: initproc PyTypeObject.tp_init + .. corresponding-type-slot:: Py_tp_init + An optional pointer to an instance initialization function. This function corresponds to the :meth:`~object.__init__` method of classes. Like @@ -1937,6 +2185,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: allocfunc PyTypeObject.tp_alloc + .. corresponding-type-slot:: Py_tp_alloc + An optional pointer to an instance allocation function. The function signature is:: @@ -1945,22 +2195,23 @@ and :c:data:`PyType_Type` effectively act as defaults.) **Inheritance:** - This field is inherited by static subtypes, but not by dynamic - subtypes (subtypes created by a class statement). + Static subtypes inherit this slot, which will be + :c:func:`PyType_GenericAlloc` if inherited from :class:`object`. + + :ref:`Heap subtypes ` do not inherit this slot. **Default:** - For dynamic subtypes, this field is always set to - :c:func:`PyType_GenericAlloc`, to force a standard heap - allocation strategy. + For heap subtypes, this field is always set to + :c:func:`PyType_GenericAlloc`. - For static subtypes, :c:data:`PyBaseObject_Type` uses - :c:func:`PyType_GenericAlloc`. That is the recommended value - for all statically defined types. + For static subtypes, this slot is inherited (see above). .. c:member:: newfunc PyTypeObject.tp_new + .. corresponding-type-slot:: Py_tp_new + An optional pointer to an instance creation function. The function signature is:: @@ -2000,28 +2251,39 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: freefunc PyTypeObject.tp_free + .. corresponding-type-slot:: Py_tp_free + An optional pointer to an instance deallocation function. Its signature is:: void tp_free(void *self); - An initializer that is compatible with this signature is :c:func:`PyObject_Free`. + This function must free the memory allocated by + :c:member:`~PyTypeObject.tp_alloc`. **Inheritance:** - This field is inherited by static subtypes, but not by dynamic - subtypes (subtypes created by a class statement) + Static subtypes inherit this slot, which will be :c:func:`PyObject_Free` if + inherited from :class:`object`. Exception: If the type supports garbage + collection (i.e., the :c:macro:`Py_TPFLAGS_HAVE_GC` flag is set in + :c:member:`~PyTypeObject.tp_flags`) and it would inherit + :c:func:`PyObject_Free`, then this slot is not inherited but instead defaults + to :c:func:`PyObject_GC_Del`. + + :ref:`Heap subtypes ` do not inherit this slot. **Default:** - In dynamic subtypes, this field is set to a deallocator suitable to - match :c:func:`PyType_GenericAlloc` and the value of the - :c:macro:`Py_TPFLAGS_HAVE_GC` flag bit. + For :ref:`heap subtypes `, this slot defaults to a deallocator suitable to match + :c:func:`PyType_GenericAlloc` and the value of the + :c:macro:`Py_TPFLAGS_HAVE_GC` flag. - For static subtypes, :c:data:`PyBaseObject_Type` uses :c:func:`PyObject_Free`. + For static subtypes, this slot is inherited (see above). .. c:member:: inquiry PyTypeObject.tp_is_gc + .. corresponding-type-slot:: Py_tp_is_gc + An optional pointer to a function called by the garbage collector. The garbage collector needs to know whether a particular object is collectible @@ -2050,12 +2312,14 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: PyObject* PyTypeObject.tp_bases + .. corresponding-type-slot:: Py_tp_bases + Tuple of base types. This field should be set to ``NULL`` and treated as read-only. Python will fill it in when the type is :c:func:`initialized `. - For dynamically created classes, the ``Py_tp_bases`` + For dynamically created classes, the :c:data:`Py_tp_bases` :c:type:`slot ` can be used instead of the *bases* argument of :c:func:`PyType_FromSpecWithBases`. The argument form is preferred. @@ -2130,6 +2394,8 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: destructor PyTypeObject.tp_del + .. corresponding-type-slot:: Py_tp_del + This field is deprecated. Use :c:member:`~PyTypeObject.tp_finalize` instead. @@ -2144,29 +2410,140 @@ and :c:data:`PyType_Type` effectively act as defaults.) .. c:member:: destructor PyTypeObject.tp_finalize - An optional pointer to an instance finalization function. Its signature is:: + .. corresponding-type-slot:: Py_tp_finalize + + An optional pointer to an instance finalization function. This is the C + implementation of the :meth:`~object.__del__` special method. Its signature + is:: void tp_finalize(PyObject *self); - If :c:member:`~PyTypeObject.tp_finalize` is set, the interpreter calls it once when - finalizing an instance. It is called either from the garbage - collector (if the instance is part of an isolated reference cycle) or - just before the object is deallocated. Either way, it is guaranteed - to be called before attempting to break reference cycles, ensuring - that it finds the object in a sane state. + The primary purpose of finalization is to perform any non-trivial cleanup + that must be performed before the object is destroyed, while the object and + any other objects it directly or indirectly references are still in a + consistent state. The finalizer is allowed to execute + arbitrary Python code. + + Before Python automatically finalizes an object, some of the object's direct + or indirect referents might have themselves been automatically finalized. + However, none of the referents will have been automatically cleared + (:c:member:`~PyTypeObject.tp_clear`) yet. + + Other non-finalized objects might still be using a finalized object, so the + finalizer must leave the object in a sane state (e.g., invariants are still + met). + + .. note:: + + After Python automatically finalizes an object, Python might start + automatically clearing (:c:member:`~PyTypeObject.tp_clear`) the object + and its referents (direct and indirect). Cleared objects are not + guaranteed to be in a consistent state; a finalized object must be able + to tolerate cleared referents. + + .. note:: + + An object is not guaranteed to be automatically finalized before its + destructor (:c:member:`~PyTypeObject.tp_dealloc`) is called. It is + recommended to call :c:func:`PyObject_CallFinalizerFromDealloc` at the + beginning of :c:member:`!tp_dealloc` to guarantee that the object is + always finalized before destruction. + + .. note:: + + The :c:member:`~PyTypeObject.tp_finalize` function can be called from any + thread, although the :term:`GIL` will be held. - :c:member:`~PyTypeObject.tp_finalize` should not mutate the current exception status; - therefore, a recommended way to write a non-trivial finalizer is:: + .. note:: + + The :c:member:`!tp_finalize` function can be called during shutdown, + after some global variables have been deleted. See the documentation of + the :meth:`~object.__del__` method for details. + + When Python finalizes an object, it behaves like the following algorithm: + + #. Python might mark the object as *finalized*. Currently, Python always + marks objects whose type supports garbage collection (i.e., the + :c:macro:`Py_TPFLAGS_HAVE_GC` flag is set in + :c:member:`~PyTypeObject.tp_flags`) and never marks other types of + objects; this might change in a future version. + #. If the object is not marked as *finalized* and its + :c:member:`!tp_finalize` finalizer function is non-``NULL``, the + finalizer function is called. + #. If the finalizer function was called and the finalizer made the object + reachable (i.e., there is a reference to the object and it is not a + member of a :term:`cyclic isolate`), then the finalizer is said to have + *resurrected* the object. It is unspecified whether the finalizer can + also resurrect the object by adding a new reference to the object that + does not make it reachable, i.e., the object is (still) a member of a + cyclic isolate. + #. If the finalizer resurrected the object, the object's pending destruction + is canceled and the object's *finalized* mark might be removed if + present. Currently, Python never removes the *finalized* mark; this + might change in a future version. + + *Automatic finalization* refers to any finalization performed by Python + except via calls to :c:func:`PyObject_CallFinalizer` or + :c:func:`PyObject_CallFinalizerFromDealloc`. No guarantees are made about + when, if, or how often an object is automatically finalized, except: + + * Python will not automatically finalize an object if it is reachable, i.e., + there is a reference to it and it is not a member of a :term:`cyclic + isolate`. + * Python will not automatically finalize an object if finalizing it would + not mark the object as *finalized*. Currently, this applies to objects + whose type does not support garbage collection, i.e., the + :c:macro:`Py_TPFLAGS_HAVE_GC` flag is not set. Such objects can still be + manually finalized by calling :c:func:`PyObject_CallFinalizer` or + :c:func:`PyObject_CallFinalizerFromDealloc`. + * Python will not automatically finalize any two members of a :term:`cyclic + isolate` concurrently. + * Python will not automatically finalize an object after it has + automatically cleared (:c:member:`~PyTypeObject.tp_clear`) the object. + * If an object is a member of a :term:`cyclic isolate`, Python will not + automatically finalize it after automatically clearing (see + :c:member:`~PyTypeObject.tp_clear`) any other member. + * Python will automatically finalize every member of a :term:`cyclic + isolate` before it automatically clears (see + :c:member:`~PyTypeObject.tp_clear`) any of them. + * If Python is going to automatically clear an object + (:c:member:`~PyTypeObject.tp_clear`), it will automatically finalize the + object first. + + Python currently only automatically finalizes objects that are members of a + :term:`cyclic isolate`, but future versions might finalize objects regularly + before their destruction. + + To manually finalize an object, do not call this function directly; call + :c:func:`PyObject_CallFinalizer` or + :c:func:`PyObject_CallFinalizerFromDealloc` instead. + + :c:member:`~PyTypeObject.tp_finalize` should leave the current exception + status unchanged. The recommended way to write a non-trivial finalizer is + to back up the exception at the beginning by calling + :c:func:`PyErr_GetRaisedException` and restore the exception at the end by + calling :c:func:`PyErr_SetRaisedException`. If an exception is encountered + in the middle of the finalizer, log and clear it with + :c:func:`PyErr_WriteUnraisable` or :c:func:`PyErr_FormatUnraisable`. For + example:: static void - local_finalize(PyObject *self) + foo_finalize(PyObject *self) { - /* Save the current exception, if any. */ + // Save the current exception, if any. PyObject *exc = PyErr_GetRaisedException(); - /* ... */ + // ... - /* Restore the saved exception. */ + if (do_something_that_might_raise() != success_indicator) { + PyErr_WriteUnraisable(self); + goto done; + } + + done: + // Restore the saved exception. This silently discards any exception + // raised above, so be sure to call PyErr_WriteUnraisable first if + // necessary. PyErr_SetRaisedException(exc); } @@ -2182,11 +2559,19 @@ and :c:data:`PyType_Type` effectively act as defaults.) :c:macro:`Py_TPFLAGS_HAVE_FINALIZE` flags bit in order for this field to be used. This is no longer required. - .. seealso:: "Safe object finalization" (:pep:`442`) + .. seealso:: + + * :pep:`442`: "Safe object finalization" + * :ref:`life-cycle` for details about how this slot relates to other + slots. + * :c:func:`PyObject_CallFinalizer` + * :c:func:`PyObject_CallFinalizerFromDealloc` .. c:member:: vectorcallfunc PyTypeObject.tp_vectorcall + .. corresponding-type-slot:: Py_tp_vectorcall + A :ref:`vectorcall function ` to use for calls of this type object (rather than instances). In other words, ``tp_vectorcall`` can be used to optimize ``type.__call__``, @@ -2352,42 +2737,148 @@ Number Object Structures Python 3.0.1. .. c:member:: binaryfunc PyNumberMethods.nb_add + + .. corresponding-type-slot:: Py_nb_add + .. c:member:: binaryfunc PyNumberMethods.nb_subtract + + .. corresponding-type-slot:: Py_nb_subtract + .. c:member:: binaryfunc PyNumberMethods.nb_multiply + + .. corresponding-type-slot:: Py_nb_multiply + .. c:member:: binaryfunc PyNumberMethods.nb_remainder + + .. corresponding-type-slot:: Py_nb_remainder + .. c:member:: binaryfunc PyNumberMethods.nb_divmod + + .. corresponding-type-slot:: Py_nb_divmod + .. c:member:: ternaryfunc PyNumberMethods.nb_power + + .. corresponding-type-slot:: Py_nb_power + .. c:member:: unaryfunc PyNumberMethods.nb_negative + + .. corresponding-type-slot:: Py_nb_negative + .. c:member:: unaryfunc PyNumberMethods.nb_positive + + .. corresponding-type-slot:: Py_nb_positive + .. c:member:: unaryfunc PyNumberMethods.nb_absolute + + .. corresponding-type-slot:: Py_nb_absolute + .. c:member:: inquiry PyNumberMethods.nb_bool + + .. corresponding-type-slot:: Py_nb_bool + .. c:member:: unaryfunc PyNumberMethods.nb_invert + + .. corresponding-type-slot:: Py_nb_invert + .. c:member:: binaryfunc PyNumberMethods.nb_lshift + + .. corresponding-type-slot:: Py_nb_lshift + .. c:member:: binaryfunc PyNumberMethods.nb_rshift + + .. corresponding-type-slot:: Py_nb_rshift + .. c:member:: binaryfunc PyNumberMethods.nb_and + + .. corresponding-type-slot:: Py_nb_and + .. c:member:: binaryfunc PyNumberMethods.nb_xor + + .. corresponding-type-slot:: Py_nb_xor + .. c:member:: binaryfunc PyNumberMethods.nb_or + + .. corresponding-type-slot:: Py_nb_or + .. c:member:: unaryfunc PyNumberMethods.nb_int + + .. corresponding-type-slot:: Py_nb_int + .. c:member:: void *PyNumberMethods.nb_reserved + .. c:member:: unaryfunc PyNumberMethods.nb_float + + .. corresponding-type-slot:: Py_nb_float + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_add + + .. corresponding-type-slot:: Py_nb_inplace_add + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_subtract + + .. corresponding-type-slot:: Py_nb_inplace_subtract + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_multiply + + .. corresponding-type-slot:: Py_nb_inplace_multiply + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_remainder + + .. corresponding-type-slot:: Py_nb_inplace_remainder + .. c:member:: ternaryfunc PyNumberMethods.nb_inplace_power + + .. corresponding-type-slot:: Py_nb_inplace_power + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_lshift + + .. corresponding-type-slot:: Py_nb_inplace_lshift + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_rshift + + .. corresponding-type-slot:: Py_nb_inplace_rshift + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_and + + .. corresponding-type-slot:: Py_nb_inplace_and + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_xor + + .. corresponding-type-slot:: Py_nb_inplace_xor + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_or + + .. corresponding-type-slot:: Py_nb_inplace_or + .. c:member:: binaryfunc PyNumberMethods.nb_floor_divide + + .. corresponding-type-slot:: Py_nb_floor_divide + .. c:member:: binaryfunc PyNumberMethods.nb_true_divide + + .. corresponding-type-slot:: Py_nb_true_divide + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_floor_divide + + .. corresponding-type-slot:: Py_nb_inplace_floor_divide + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_true_divide + + .. corresponding-type-slot:: Py_nb_inplace_true_divide + .. c:member:: unaryfunc PyNumberMethods.nb_index + + .. corresponding-type-slot:: Py_nb_index + .. c:member:: binaryfunc PyNumberMethods.nb_matrix_multiply + + .. corresponding-type-slot:: Py_nb_matrix_multiply + .. c:member:: binaryfunc PyNumberMethods.nb_inplace_matrix_multiply + .. corresponding-type-slot:: Py_nb_inplace_matrix_multiply + + .. _mapping-structs: @@ -2404,12 +2895,16 @@ Mapping Object Structures .. c:member:: lenfunc PyMappingMethods.mp_length + .. corresponding-type-slot:: Py_mp_length + This function is used by :c:func:`PyMapping_Size` and :c:func:`PyObject_Size`, and has the same signature. This slot may be set to ``NULL`` if the object has no defined length. .. c:member:: binaryfunc PyMappingMethods.mp_subscript + .. corresponding-type-slot:: Py_mp_subscript + This function is used by :c:func:`PyObject_GetItem` and :c:func:`PySequence_GetSlice`, and has the same signature as :c:func:`!PyObject_GetItem`. This slot must be filled for the @@ -2418,6 +2913,8 @@ Mapping Object Structures .. c:member:: objobjargproc PyMappingMethods.mp_ass_subscript + .. corresponding-type-slot:: Py_mp_ass_subscript + This function is used by :c:func:`PyObject_SetItem`, :c:func:`PyObject_DelItem`, :c:func:`PySequence_SetSlice` and :c:func:`PySequence_DelSlice`. It has the same signature as @@ -2441,6 +2938,8 @@ Sequence Object Structures .. c:member:: lenfunc PySequenceMethods.sq_length + .. corresponding-type-slot:: Py_sq_length + This function is used by :c:func:`PySequence_Size` and :c:func:`PyObject_Size`, and has the same signature. It is also used for handling negative indices via the :c:member:`~PySequenceMethods.sq_item` @@ -2448,18 +2947,24 @@ Sequence Object Structures .. c:member:: binaryfunc PySequenceMethods.sq_concat + .. corresponding-type-slot:: Py_sq_concat + This function is used by :c:func:`PySequence_Concat` and has the same signature. It is also used by the ``+`` operator, after trying the numeric addition via the :c:member:`~PyNumberMethods.nb_add` slot. .. c:member:: ssizeargfunc PySequenceMethods.sq_repeat + .. corresponding-type-slot:: Py_sq_repeat + This function is used by :c:func:`PySequence_Repeat` and has the same signature. It is also used by the ``*`` operator, after trying numeric multiplication via the :c:member:`~PyNumberMethods.nb_multiply` slot. .. c:member:: ssizeargfunc PySequenceMethods.sq_item + .. corresponding-type-slot:: Py_sq_item + This function is used by :c:func:`PySequence_GetItem` and has the same signature. It is also used by :c:func:`PyObject_GetItem`, after trying the subscription via the :c:member:`~PyMappingMethods.mp_subscript` slot. @@ -2473,6 +2978,8 @@ Sequence Object Structures .. c:member:: ssizeobjargproc PySequenceMethods.sq_ass_item + .. corresponding-type-slot:: Py_sq_ass_item + This function is used by :c:func:`PySequence_SetItem` and has the same signature. It is also used by :c:func:`PyObject_SetItem` and :c:func:`PyObject_DelItem`, after trying the item assignment and deletion @@ -2482,6 +2989,8 @@ Sequence Object Structures .. c:member:: objobjproc PySequenceMethods.sq_contains + .. corresponding-type-slot:: Py_sq_contains + This function may be used by :c:func:`PySequence_Contains` and has the same signature. This slot may be left to ``NULL``, in this case :c:func:`!PySequence_Contains` simply traverses the sequence until it @@ -2489,6 +2998,8 @@ Sequence Object Structures .. c:member:: binaryfunc PySequenceMethods.sq_inplace_concat + .. corresponding-type-slot:: Py_sq_inplace_concat + This function is used by :c:func:`PySequence_InPlaceConcat` and has the same signature. It should modify its first operand, and return it. This slot may be left to ``NULL``, in this case :c:func:`!PySequence_InPlaceConcat` @@ -2498,6 +3009,8 @@ Sequence Object Structures .. c:member:: ssizeargfunc PySequenceMethods.sq_inplace_repeat + .. corresponding-type-slot:: Py_sq_inplace_repeat + This function is used by :c:func:`PySequence_InPlaceRepeat` and has the same signature. It should modify its first operand, and return it. This slot may be left to ``NULL``, in this case :c:func:`!PySequence_InPlaceRepeat` @@ -2523,6 +3036,8 @@ Buffer Object Structures .. c:member:: getbufferproc PyBufferProcs.bf_getbuffer + .. corresponding-type-slot:: Py_bf_getbuffer + The signature of this function is:: int (PyObject *exporter, Py_buffer *view, int flags); @@ -2532,24 +3047,42 @@ Buffer Object Structures steps: (1) Check if the request can be met. If not, raise :exc:`BufferError`, - set :c:expr:`view->obj` to ``NULL`` and return ``-1``. + set ``view->obj`` to ``NULL`` and return ``-1``. (2) Fill in the requested fields. (3) Increment an internal counter for the number of exports. - (4) Set :c:expr:`view->obj` to *exporter* and increment :c:expr:`view->obj`. + (4) Set ``view->obj`` to *exporter* and increment ``view->obj``. (5) Return ``0``. + **Thread safety:** + + In the :term:`free-threaded build`, implementations must ensure: + + * The export counter increment in step (3) is atomic. + + * The underlying buffer data remains valid and at a stable memory + location for the lifetime of all exports. + + * For objects that support resizing or reallocation (such as + :class:`bytearray`), the export counter is checked atomically before + such operations, and :exc:`BufferError` is raised if exports exist. + + * The function is safe to call concurrently from multiple threads. + + See also :ref:`thread-safety-memoryview` for the Python-level + thread safety guarantees of :class:`memoryview` objects. + If *exporter* is part of a chain or tree of buffer providers, two main schemes can be used: * Re-export: Each member of the tree acts as the exporting object and - sets :c:expr:`view->obj` to a new reference to itself. + sets ``view->obj`` to a new reference to itself. * Redirect: The buffer request is redirected to the root object of the - tree. Here, :c:expr:`view->obj` will be a new reference to the root + tree. Here, ``view->obj`` will be a new reference to the root object. The individual fields of *view* are described in section @@ -2572,6 +3105,8 @@ Buffer Object Structures .. c:member:: releasebufferproc PyBufferProcs.bf_releasebuffer + .. corresponding-type-slot:: Py_bf_releasebuffer + The signature of this function is:: void (PyObject *exporter, Py_buffer *view); @@ -2585,13 +3120,23 @@ Buffer Object Structures (2) If the counter is ``0``, free all memory associated with *view*. + **Thread safety:** + + In the :term:`free-threaded build`: + + * The export counter decrement in step (1) must be atomic. + + * Resource cleanup when the counter reaches zero must be done atomically, + as the final release may race with concurrent releases from other + threads and deallocation must only happen once. + The exporter MUST use the :c:member:`~Py_buffer.internal` field to keep track of buffer-specific resources. This field is guaranteed to remain constant, while a consumer MAY pass a copy of the original buffer as the *view* argument. - This function MUST NOT decrement :c:expr:`view->obj`, since that is + This function MUST NOT decrement ``view->obj``, since that is done automatically in :c:func:`PyBuffer_Release` (this scheme is useful for breaking reference cycles). @@ -2626,6 +3171,8 @@ Async Object Structures .. c:member:: unaryfunc PyAsyncMethods.am_await + .. corresponding-type-slot:: Py_am_await + The signature of this function is:: PyObject *am_await(PyObject *self); @@ -2637,6 +3184,8 @@ Async Object Structures .. c:member:: unaryfunc PyAsyncMethods.am_aiter + .. corresponding-type-slot:: Py_am_aiter + The signature of this function is:: PyObject *am_aiter(PyObject *self); @@ -2649,6 +3198,8 @@ Async Object Structures .. c:member:: unaryfunc PyAsyncMethods.am_anext + .. corresponding-type-slot:: Py_am_anext + The signature of this function is:: PyObject *am_anext(PyObject *self); @@ -2659,6 +3210,8 @@ Async Object Structures .. c:member:: sendfunc PyAsyncMethods.am_send + .. corresponding-type-slot:: Py_am_send + The signature of this function is:: PySendResult am_send(PyObject *self, PyObject *arg, PyObject **result); diff --git a/Doc/c-api/unicode.rst b/Doc/c-api/unicode.rst index 95987e872ce639..aa2288fb77dc38 100644 --- a/Doc/c-api/unicode.rst +++ b/Doc/c-api/unicode.rst @@ -65,6 +65,27 @@ Python: .. versionadded:: 3.3 + The structure of a particular object can be determined using the following + macros. + The macros cannot fail; their behavior is undefined if their argument + is not a Python Unicode object. + + .. c:namespace:: NULL + + .. c:macro:: PyUnicode_IS_COMPACT(o) + + True if *o* uses the :c:struct:`PyCompactUnicodeObject` structure. + + .. versionadded:: 3.3 + + + .. c:macro:: PyUnicode_IS_COMPACT_ASCII(o) + + True if *o* uses the :c:struct:`PyASCIIObject` structure. + + .. versionadded:: 3.3 + + The following APIs are C macros and static inlined functions for fast checks and access to internal read-only data of Unicode objects: @@ -305,12 +326,22 @@ These APIs can be used to work with surrogates: Check if *ch* is a low surrogate (``0xDC00 <= ch <= 0xDFFF``). +.. c:function:: Py_UCS4 Py_UNICODE_HIGH_SURROGATE(Py_UCS4 ch) + + Return the high UTF-16 surrogate (``0xD800`` to ``0xDBFF``) for a Unicode + code point in the range ``[0x10000; 0x10FFFF]``. + +.. c:function:: Py_UCS4 Py_UNICODE_LOW_SURROGATE(Py_UCS4 ch) + + Return the low UTF-16 surrogate (``0xDC00`` to ``0xDFFF``) for a Unicode + code point in the range ``[0x10000; 0x10FFFF]``. + .. c:function:: Py_UCS4 Py_UNICODE_JOIN_SURROGATES(Py_UCS4 high, Py_UCS4 low) Join two surrogate code points and return a single :c:type:`Py_UCS4` value. *high* and *low* are respectively the leading and trailing surrogates in a - surrogate pair. *high* must be in the range [0xD800; 0xDBFF] and *low* must - be in the range [0xDC00; 0xDFFF]. + surrogate pair. *high* must be in the range ``[0xD800; 0xDBFF]`` and *low* must + be in the range ``[0xDC00; 0xDFFF]``. Creating and accessing Unicode strings @@ -632,7 +663,8 @@ APIs: Append the string *right* to the end of *p_left*. *p_left* must point to a :term:`strong reference` to a Unicode object; - :c:func:`!PyUnicode_Append` releases ("steals") this reference. + :c:func:`!PyUnicode_Append` releases (":term:`steals `") + this reference. On error, set *\*p_left* to ``NULL`` and set an exception. @@ -645,6 +677,17 @@ APIs: difference being that it decrements the reference count of *right* by one. +.. c:function:: PyObject* PyUnicode_BuildEncodingMap(PyObject* string) + + Return a mapping suitable for decoding a custom single-byte encoding. + Given a Unicode string *string* of up to 256 characters representing an encoding + table, returns either a compact internal mapping object or a dictionary + mapping character ordinals to byte values. Raises a :exc:`TypeError` and + return ``NULL`` on invalid input. + + .. versionadded:: 3.2 + + .. c:function:: const char* PyUnicode_GetDefaultEncoding(void) Return the name of the default string encoding, ``"utf-8"``. @@ -707,7 +750,7 @@ APIs: The string must not have been “used” yet. See :c:func:`PyUnicode_New` for details. - Return the number of written character, or return ``-1`` and raise an + Return the number of written characters, or return ``-1`` and raise an exception on error. .. versionadded:: 3.3 @@ -720,7 +763,7 @@ APIs: Return ``0`` on success, ``-1`` on error with an exception set. This function checks that *unicode* is a Unicode object, that the index is - not out of bounds, and that the object's reference count is one). + not out of bounds, and that the object's reference count is one. See :c:func:`PyUnicode_WRITE` for a version that skips these checks, making them your responsibility. @@ -1119,7 +1162,7 @@ These are the UTF-8 codec APIs: .. versionadded:: 3.3 .. versionchanged:: 3.7 - The return type is now ``const char *`` rather of ``char *``. + The return type is now ``const char *`` rather than ``char *``. .. versionchanged:: 3.10 This function is a part of the :ref:`limited API `. @@ -1141,7 +1184,7 @@ These are the UTF-8 codec APIs: .. versionadded:: 3.3 .. versionchanged:: 3.7 - The return type is now ``const char *`` rather of ``char *``. + The return type is now ``const char *`` rather than ``char *``. UTF-32 Codecs @@ -1450,10 +1493,6 @@ the user settings on the machine running the codec. .. versionadded:: 3.3 -Methods & Slots -""""""""""""""" - - .. _unicodemethodsandslots: Methods and Slot Functions @@ -1715,10 +1754,6 @@ They all return ``NULL`` or ``-1`` if an exception occurs. from user input, prefer calling :c:func:`PyUnicode_FromString` and :c:func:`PyUnicode_InternInPlace` directly. - .. impl-detail:: - - Strings interned this way are made :term:`immortal`. - .. c:function:: unsigned int PyUnicode_CHECK_INTERNED(PyObject *str) @@ -1795,9 +1830,22 @@ object. See also :c:func:`PyUnicodeWriter_DecodeUTF8Stateful`. +.. c:function:: int PyUnicodeWriter_WriteASCII(PyUnicodeWriter *writer, const char *str, Py_ssize_t size) + + Write the ASCII string *str* into *writer*. + + *size* is the string length in bytes. If *size* is equal to ``-1``, call + ``strlen(str)`` to get the string length. + + *str* must only contain ASCII characters. The behavior is undefined if + *str* contains non-ASCII characters. + + On success, return ``0``. + On error, set an exception, leave the writer unchanged, and return ``-1``. + .. c:function:: int PyUnicodeWriter_WriteWideChar(PyUnicodeWriter *writer, const wchar_t *str, Py_ssize_t size) - Writer the wide string *str* into *writer*. + Write the wide string *str* into *writer*. *size* is a number of wide characters. If *size* is equal to ``-1``, call ``wcslen(str)`` to get the string length. @@ -1821,13 +1869,23 @@ object. On success, return ``0``. On error, set an exception, leave the writer unchanged, and return ``-1``. + To write a :class:`str` subclass which overrides the :meth:`~object.__str__` + method, :c:func:`PyUnicode_FromObject` can be used to get the original + string. + .. c:function:: int PyUnicodeWriter_WriteRepr(PyUnicodeWriter *writer, PyObject *obj) Call :c:func:`PyObject_Repr` on *obj* and write the output into *writer*. + If *obj* is ``NULL``, write the string ``""`` into *writer*. + On success, return ``0``. On error, set an exception, leave the writer unchanged, and return ``-1``. + .. versionchanged:: 3.14.4 + + Added support for ``NULL``. + .. c:function:: int PyUnicodeWriter_WriteSubstring(PyUnicodeWriter *writer, PyObject *str, Py_ssize_t start, Py_ssize_t end) Write the substring ``str[start:end]`` into *writer*. diff --git a/Doc/c-api/veryhigh.rst b/Doc/c-api/veryhigh.rst index 1ef4181d52eb10..bba5c7f8ecf775 100644 --- a/Doc/c-api/veryhigh.rst +++ b/Doc/c-api/veryhigh.rst @@ -13,8 +13,9 @@ the interpreter. Several of these functions accept a start symbol from the grammar as a parameter. The available start symbols are :c:data:`Py_eval_input`, -:c:data:`Py_file_input`, and :c:data:`Py_single_input`. These are described -following the functions which accept them as parameters. +:c:data:`Py_file_input`, :c:data:`Py_single_input`, and +:c:data:`Py_func_type_input`. These are described following the functions +which accept them as parameters. Note also that several of these functions take :c:expr:`FILE*` parameters. One particular issue which needs to be handled carefully is that the :c:type:`FILE` @@ -99,18 +100,12 @@ the same library that the Python runtime is using. Otherwise, Python may not handle script file with LF line ending correctly. -.. c:function:: int PyRun_InteractiveOne(FILE *fp, const char *filename) - - This is a simplified interface to :c:func:`PyRun_InteractiveOneFlags` below, - leaving *flags* set to ``NULL``. - - -.. c:function:: int PyRun_InteractiveOneFlags(FILE *fp, const char *filename, PyCompilerFlags *flags) +.. c:function:: int PyRun_InteractiveOneObject(FILE *fp, PyObject *filename, PyCompilerFlags *flags) Read and execute a single statement from a file associated with an interactive device according to the *flags* argument. The user will be - prompted using ``sys.ps1`` and ``sys.ps2``. *filename* is decoded from the - :term:`filesystem encoding and error handler`. + prompted using ``sys.ps1`` and ``sys.ps2``. *filename* must be a Python + :class:`str` object. Returns ``0`` when the input was executed successfully, ``-1`` if there was an exception, or an error code @@ -119,6 +114,19 @@ the same library that the Python runtime is using. :file:`Python.h`, so must be included specifically if needed.) +.. c:function:: int PyRun_InteractiveOne(FILE *fp, const char *filename) + + This is a simplified interface to :c:func:`PyRun_InteractiveOneFlags` below, + leaving *flags* set to ``NULL``. + + +.. c:function:: int PyRun_InteractiveOneFlags(FILE *fp, const char *filename, PyCompilerFlags *flags) + + Similar to :c:func:`PyRun_InteractiveOneObject`, but *filename* is a + :c:expr:`const char*`, which is decoded from the + :term:`filesystem encoding and error handler`. + + .. c:function:: int PyRun_InteractiveLoop(FILE *fp, const char *filename) This is a simplified interface to :c:func:`PyRun_InteractiveLoopFlags` below, @@ -140,7 +148,7 @@ the same library that the Python runtime is using. interpreter prompt is about to become idle and wait for user input from the terminal. The return value is ignored. Overriding this hook can be used to integrate the interpreter's prompt with other - event loops, as done in the :file:`Modules/_tkinter.c` in the + event loops, as done in :file:`Modules/_tkinter.c` in the Python source code. .. versionchanged:: 3.12 @@ -183,7 +191,7 @@ the same library that the Python runtime is using. objects *globals* and *locals* with the compiler flags specified by *flags*. *globals* must be a dictionary; *locals* can be any object that implements the mapping protocol. The parameter *start* specifies - the start token that should be used to parse the source code. + the start symbol and must be one of the :ref:`available start symbols `. Returns the result of executing the code as a Python object, or ``NULL`` if an exception was raised. @@ -231,9 +239,9 @@ the same library that the Python runtime is using. .. c:function:: PyObject* Py_CompileStringObject(const char *str, PyObject *filename, int start, PyCompilerFlags *flags, int optimize) Parse and compile the Python source code in *str*, returning the resulting code - object. The start token is given by *start*; this can be used to constrain the - code which can be compiled and should be :c:data:`Py_eval_input`, - :c:data:`Py_file_input`, or :c:data:`Py_single_input`. The filename specified by + object. The start symbol is given by *start*; this can be used to constrain the + code which can be compiled and should be :ref:`available start symbols + `. The filename specified by *filename* is used to construct the code object and may appear in tracebacks or :exc:`SyntaxError` exception messages. This returns ``NULL`` if the code cannot be parsed or compiled. @@ -296,32 +304,6 @@ the same library that the Python runtime is using. true on success, false on failure. -.. c:var:: int Py_eval_input - - .. index:: single: Py_CompileString (C function) - - The start symbol from the Python grammar for isolated expressions; for use with - :c:func:`Py_CompileString`. - - -.. c:var:: int Py_file_input - - .. index:: single: Py_CompileString (C function) - - The start symbol from the Python grammar for sequences of statements as read - from a file or other source; for use with :c:func:`Py_CompileString`. This is - the symbol to use when compiling arbitrarily long Python source code. - - -.. c:var:: int Py_single_input - - .. index:: single: Py_CompileString (C function) - - The start symbol from the Python grammar for a single statement; for use with - :c:func:`Py_CompileString`. This is the symbol used for the interactive - interpreter loop. - - .. c:struct:: PyCompilerFlags This is the structure used to hold compiler flags. In cases where code is only @@ -361,7 +343,210 @@ the same library that the Python runtime is using. :py:mod:`!ast` Python module, which exports these constants under the same names. - .. c:var:: int CO_FUTURE_DIVISION + .. rubric:: Low-level flags + + The following flags and masks serve narrow needs of the standard + library and interactive interpreters. Code outside the standard + library rarely has a reason to use them. They are considered + implementation details and may change at any time. + + .. c:macro:: PyCF_ALLOW_INCOMPLETE_INPUT + + This flag is a private interface between the compiler and the + :mod:`codeop` module. Do not use it; its behavior is unsupported + and may change without warning. + + With this flag set, when compilation fails because the source text + ends where more input is expected, for example in the middle of an + indented block or an unterminated string literal, the error raised + is the undocumented ``_IncompleteInputError``, a subclass of + :exc:`SyntaxError`. The :mod:`codeop` module sets this flag, + together with :c:macro:`PyCF_DONT_IMPLY_DEDENT`, to tell input + that is incomplete apart from input with a real syntax error, so + that interactive interpreters know when to prompt for another + line instead of reporting an error. + + .. versionadded:: 3.11 + + .. c:macro:: PyCF_DONT_IMPLY_DEDENT + + By default, when compiling with the :c:var:`Py_single_input` start + symbol, reaching the end of the source text implicitly closes any + open indented blocks. With this flag set, open blocks are only + closed if the last line of the source ends with a newline; otherwise, + compilation fails with a :exc:`SyntaxError`: + + .. code-block:: c + + PyCompilerFlags flags = { + .cf_flags = 0, + .cf_feature_version = PY_MINOR_VERSION, + }; + const char *source = "if a:\n pass"; + + /* The "if" block is closed implicitly; + this returns a code object: */ + Py_CompileStringFlags(source, "", Py_single_input, &flags); + + /* With the flag, this fails with a SyntaxError, + because the last line does not end with a newline: */ + flags.cf_flags = PyCF_DONT_IMPLY_DEDENT; + Py_CompileStringFlags(source, "", Py_single_input, &flags); + + The :mod:`codeop` module uses this flag to detect incomplete + interactive input. While the user is still typing inside an + indented block, the source does not yet end with a newline, so it + fails to compile and the user is prompted for another line. + + .. c:macro:: PyCF_IGNORE_COOKIE + + Read the source text as UTF-8, ignoring its :pep:`263` encoding + declaration ("coding cookie"), if any: + + .. code-block:: c + + PyCompilerFlags flags = { + .cf_flags = 0, + .cf_feature_version = PY_MINOR_VERSION, + }; + const char *source = "# coding: latin-1\ns = '\xe9'\n"; + + /* The coding cookie is honored: byte 0xE9 is decoded as + Latin-1, and this returns a code object that sets s to "é": */ + Py_CompileStringFlags(source, "", Py_file_input, &flags); + + /* With the flag, the cookie is ignored and compilation fails + with a SyntaxError, because 0xE9 is not valid UTF-8: */ + flags.cf_flags = PyCF_IGNORE_COOKIE; + Py_CompileStringFlags(source, "", Py_file_input, &flags); + + The :func:`compile`, :func:`eval` and :func:`exec` built-in functions + set this flag when the source is a :class:`str` object, because they + pass the text to the parser encoded as UTF-8. + + .. c:macro:: PyCF_SOURCE_IS_UTF8 + + Mark the source text as known to be UTF-8 encoded. + The :func:`compile`, :func:`eval` and :func:`exec` built-in functions + set this flag, but it currently has no effect. + + The "``PyCF``" flags above can be combined with "``CO_FUTURE``" flags such + as :c:macro:`CO_FUTURE_ANNOTATIONS` to enable features normally + selectable using :ref:`future statements `. + See :ref:`c_codeobject_flags` for a complete list. + + The following masks combine several flags: + + .. c:macro:: PyCF_MASK + + Bitmask of all ``CO_FUTURE`` flags (see :ref:`c_codeobject_flags`), + which select features normally enabled by + :ref:`future statements `. + When code compiled with a ``PyCompilerFlags *flags`` argument + contains a ``from __future__ import`` statement, the flag for the + imported feature is added to *flags*, so that code executed later + in the same context inherits it. + + .. c:macro:: PyCF_MASK_OBSOLETE + + Do not use this mask in new code. It is kept only so that old + code passing its flags to :func:`compile` keeps working. + + Bitmask of flags for obsolete future features that no longer + have any effect. + + .. c:macro:: PyCF_COMPILE_MASK + + Bitmask of all ``PyCF`` flags that change how the source is + compiled, such as :c:macro:`PyCF_ONLY_AST`. + The :func:`compile` built-in function uses this mask to validate + its *flags* argument. + + +.. _start-symbols: + +Available start symbols +^^^^^^^^^^^^^^^^^^^^^^^ + + +.. c:var:: int Py_eval_input + + .. index:: single: Py_CompileString (C function) + + The start symbol from the Python grammar for isolated expressions; for use with + :c:func:`Py_CompileString`. + + +.. c:var:: int Py_file_input + + .. index:: single: Py_CompileString (C function) + + The start symbol from the Python grammar for sequences of statements as read + from a file or other source; for use with :c:func:`Py_CompileString`. This is + the symbol to use when compiling arbitrarily long Python source code. + + +.. c:var:: int Py_single_input + + .. index:: single: Py_CompileString (C function) + + The start symbol from the Python grammar for a single statement; for use with + :c:func:`Py_CompileString`. This is the symbol used for the interactive + interpreter loop. + + +.. c:var:: int Py_func_type_input + + .. index:: single: Py_CompileString (C function) + + The start symbol from the Python grammar for a function type; for use with + :c:func:`Py_CompileString`. This is used to parse "signature type comments" + from :pep:`484`. + + This requires the :c:macro:`PyCF_ONLY_AST` flag to be set. + + .. seealso:: + * :py:class:`ast.FunctionType` + * :pep:`484` + + .. versionadded:: 3.8 + + +Stack Effects +^^^^^^^^^^^^^ + +.. seealso:: + :py:func:`dis.stack_effect` + + +.. c:macro:: PY_INVALID_STACK_EFFECT + + Sentinel value representing an invalid stack effect. + + This is currently equivalent to ``INT_MAX``. + + .. versionadded:: 3.8 + + +.. c:function:: int PyCompile_OpcodeStackEffect(int opcode, int oparg) + + Compute the stack effect of *opcode* with argument *oparg*. + + On success, this function returns the stack effect; on failure, this + returns :c:macro:`PY_INVALID_STACK_EFFECT`. + + .. versionadded:: 3.4 + + +.. c:function:: int PyCompile_OpcodeStackEffectWithJump(int opcode, int oparg, int jump) + + Similar to :c:func:`PyCompile_OpcodeStackEffect`, but don't include the + stack effect of jumping if *jump* is zero. + + If *jump* is ``0``, this will not include the stack effect of jumping, but + if *jump* is ``1`` or ``-1``, this will include it. + + On success, this function returns the stack effect; on failure, this + returns :c:macro:`PY_INVALID_STACK_EFFECT`. - This bit can be set in *flags* to cause division operator ``/`` to be - interpreted as "true division" according to :pep:`238`. + .. versionadded:: 3.8 diff --git a/Doc/c-api/weakref.rst b/Doc/c-api/weakref.rst index c3c6cf413dcef5..28b93add912b3a 100644 --- a/Doc/c-api/weakref.rst +++ b/Doc/c-api/weakref.rst @@ -19,7 +19,14 @@ as much as it can. .. c:function:: int PyWeakref_CheckRef(PyObject *ob) - Return non-zero if *ob* is a reference object. This function always succeeds. + Return non-zero if *ob* is a reference object or a subclass of the reference + type. This function always succeeds. + + +.. c:function:: int PyWeakref_CheckRefExact(PyObject *ob) + + Return non-zero if *ob* is a reference object, but not a subclass of the + reference type. This function always succeeds. .. c:function:: int PyWeakref_CheckProxy(PyObject *ob) @@ -35,8 +42,12 @@ as much as it can. callable object that receives notification when *ob* is garbage collected; it should accept a single parameter, which will be the weak reference object itself. *callback* may also be ``None`` or ``NULL``. If *ob* is not a - weakly referenceable object, or if *callback* is not callable, ``None``, or - ``NULL``, this will return ``NULL`` and raise :exc:`TypeError`. + weakly referenceable object, this will raise :exc:`TypeError` and return + ``NULL``. + + .. seealso:: + :c:func:`PyType_SUPPORTS_WEAKREFS` for checking if *ob* is weakly + referenceable. .. c:function:: PyObject* PyWeakref_NewProxy(PyObject *ob, PyObject *callback) @@ -47,8 +58,12 @@ as much as it can. be a callable object that receives notification when *ob* is garbage collected; it should accept a single parameter, which will be the weak reference object itself. *callback* may also be ``None`` or ``NULL``. If *ob* - is not a weakly referenceable object, or if *callback* is not callable, - ``None``, or ``NULL``, this will return ``NULL`` and raise :exc:`TypeError`. + weakly referenceable object, this will raise :exc:`TypeError` and return + ``NULL``. + + .. seealso:: + :c:func:`PyType_SUPPORTS_WEAKREFS` for checking if *ob* is weakly + referenceable. .. c:function:: int PyWeakref_GetRef(PyObject *ref, PyObject **pobj) diff --git a/Doc/conf.py b/Doc/conf.py index 467961dd5e2bff..98e5531585d3f6 100644 --- a/Doc/conf.py +++ b/Doc/conf.py @@ -8,15 +8,13 @@ import os import sys -from importlib import import_module from importlib.util import find_spec # Make our custom extensions available to Sphinx sys.path.append(os.path.abspath('tools/extensions')) sys.path.append(os.path.abspath('includes')) -# Python specific content from Doc/Tools/extensions/pyspecific.py -from pyspecific import SOURCE_URI +from patchlevel import get_header_version_info, get_version_info # General configuration # --------------------- @@ -42,8 +40,10 @@ # Skip if downstream redistributors haven't installed them _OPTIONAL_EXTENSIONS = ( + 'linklint.ext', 'notfound.extension', 'sphinxext.opengraph', + 'sphinxcontrib.rsvgconverter', ) for optional_ext in _OPTIONAL_EXTENSIONS: try: @@ -70,15 +70,20 @@ # General substitutions. project = 'Python' copyright = "2001 Python Software Foundation" +_doc_authors = 'Python documentation authors' # We look for the Include/patchlevel.h file in the current Python source tree # and replace the values accordingly. # See Doc/tools/extensions/patchlevel.py -version, release = import_module('patchlevel').get_version_info() +version, release = get_version_info() rst_epilog = f""" .. |python_version_literal| replace:: ``Python {version}`` .. |python_x_dot_y_literal| replace:: ``python{version}`` +.. |python_x_dot_y_t_literal| replace:: ``python{version}t`` +.. |python_x_dot_y_t_literal_config| replace:: ``python{version}t-config`` +.. |x_dot_y_b2_literal| replace:: ``{version}.0b2`` +.. |applications_python_version_literal| replace:: ``/Applications/Python {version}/`` .. |usr_local_bin_python_x_dot_y_literal| replace:: ``/usr/local/bin/python{version}`` .. Apparently this how you hack together a formatted link: @@ -170,6 +175,7 @@ ('c:type', '__int64'), ('c:type', 'unsigned __int64'), ('c:type', 'double'), + ('c:type', '_Float16'), # Standard C structures ('c:struct', 'in6_addr'), ('c:struct', 'in_addr'), @@ -217,99 +223,18 @@ ('envvar', 'USER'), ('envvar', 'USERNAME'), ('envvar', 'USERPROFILE'), - # Deprecated function that was never documented: - ('py:func', 'getargspec'), - ('py:func', 'inspect.getargspec'), - # Undocumented modules that users shouldn't have to worry about - # (implementation details of `os.path`): - ('py:mod', 'ntpath'), - ('py:mod', 'posixpath'), ] # Temporary undocumented names. # In future this list must be empty. nitpick_ignore += [ - # C API: Standard Python exception classes - ('c:data', 'PyExc_ArithmeticError'), - ('c:data', 'PyExc_AssertionError'), - ('c:data', 'PyExc_AttributeError'), - ('c:data', 'PyExc_BaseException'), - ('c:data', 'PyExc_BlockingIOError'), - ('c:data', 'PyExc_BrokenPipeError'), - ('c:data', 'PyExc_BufferError'), - ('c:data', 'PyExc_ChildProcessError'), - ('c:data', 'PyExc_ConnectionAbortedError'), - ('c:data', 'PyExc_ConnectionError'), - ('c:data', 'PyExc_ConnectionRefusedError'), - ('c:data', 'PyExc_ConnectionResetError'), - ('c:data', 'PyExc_EOFError'), - ('c:data', 'PyExc_Exception'), - ('c:data', 'PyExc_FileExistsError'), - ('c:data', 'PyExc_FileNotFoundError'), - ('c:data', 'PyExc_FloatingPointError'), - ('c:data', 'PyExc_GeneratorExit'), - ('c:data', 'PyExc_ImportError'), - ('c:data', 'PyExc_IndentationError'), - ('c:data', 'PyExc_IndexError'), - ('c:data', 'PyExc_InterruptedError'), - ('c:data', 'PyExc_IsADirectoryError'), - ('c:data', 'PyExc_KeyboardInterrupt'), - ('c:data', 'PyExc_KeyError'), - ('c:data', 'PyExc_LookupError'), - ('c:data', 'PyExc_MemoryError'), - ('c:data', 'PyExc_ModuleNotFoundError'), - ('c:data', 'PyExc_NameError'), - ('c:data', 'PyExc_NotADirectoryError'), - ('c:data', 'PyExc_NotImplementedError'), - ('c:data', 'PyExc_OSError'), - ('c:data', 'PyExc_OverflowError'), - ('c:data', 'PyExc_PermissionError'), - ('c:data', 'PyExc_ProcessLookupError'), - ('c:data', 'PyExc_PythonFinalizationError'), - ('c:data', 'PyExc_RecursionError'), - ('c:data', 'PyExc_ReferenceError'), - ('c:data', 'PyExc_RuntimeError'), - ('c:data', 'PyExc_StopAsyncIteration'), - ('c:data', 'PyExc_StopIteration'), - ('c:data', 'PyExc_SyntaxError'), - ('c:data', 'PyExc_SystemError'), - ('c:data', 'PyExc_SystemExit'), - ('c:data', 'PyExc_TabError'), - ('c:data', 'PyExc_TimeoutError'), - ('c:data', 'PyExc_TypeError'), - ('c:data', 'PyExc_UnboundLocalError'), - ('c:data', 'PyExc_UnicodeDecodeError'), - ('c:data', 'PyExc_UnicodeEncodeError'), - ('c:data', 'PyExc_UnicodeError'), - ('c:data', 'PyExc_UnicodeTranslateError'), - ('c:data', 'PyExc_ValueError'), - ('c:data', 'PyExc_ZeroDivisionError'), - # C API: Standard Python warning classes - ('c:data', 'PyExc_BytesWarning'), - ('c:data', 'PyExc_DeprecationWarning'), - ('c:data', 'PyExc_FutureWarning'), - ('c:data', 'PyExc_ImportWarning'), - ('c:data', 'PyExc_PendingDeprecationWarning'), - ('c:data', 'PyExc_ResourceWarning'), - ('c:data', 'PyExc_RuntimeWarning'), - ('c:data', 'PyExc_SyntaxWarning'), - ('c:data', 'PyExc_UnicodeWarning'), - ('c:data', 'PyExc_UserWarning'), - ('c:data', 'PyExc_Warning'), - # Undocumented public C macros - ('c:macro', 'Py_BUILD_ASSERT'), - ('c:macro', 'Py_BUILD_ASSERT_EXPR'), # Do not error nit-picky mode builds when _SubParsersAction.add_parser cannot # be resolved, as the method is currently undocumented. For context, see # https://github.com/python/cpython/pull/103289. ('py:meth', '_SubParsersAction.add_parser'), # Attributes/methods/etc. that definitely should be documented better, # but are deferred for now: - ('py:attr', '__annotations__'), - ('py:meth', '__missing__'), ('py:attr', '__wrapped__'), - ('py:attr', 'decimal.Context.clamp'), - ('py:meth', 'index'), # list.index, tuple.index, etc. ] # gh-106948: Copy standard C types declared in the "c:type" domain and C @@ -433,73 +358,79 @@ 'papersize': 'a4paper', # The font size ('10pt', '11pt' or '12pt'). 'pointsize': '10pt', + 'maxlistdepth': '8', # See https://github.com/python/cpython/issues/139588 } # Grouping the document tree into LaTeX files. List of tuples # (source start file, target name, title, author, document class [howto/manual]). -_stdauthor = 'Guido van Rossum and the Python development team' latex_documents = [ - ('c-api/index', 'c-api.tex', 'The Python/C API', _stdauthor, 'manual'), + ('c-api/index', 'c-api.tex', 'The Python/C API', _doc_authors, 'manual'), ( 'extending/index', 'extending.tex', 'Extending and Embedding Python', - _stdauthor, + _doc_authors, 'manual', ), ( 'installing/index', 'installing.tex', 'Installing Python Modules', - _stdauthor, + _doc_authors, 'manual', ), ( 'library/index', 'library.tex', 'The Python Library Reference', - _stdauthor, + _doc_authors, 'manual', ), ( 'reference/index', 'reference.tex', 'The Python Language Reference', - _stdauthor, + _doc_authors, 'manual', ), ( 'tutorial/index', 'tutorial.tex', 'Python Tutorial', - _stdauthor, + _doc_authors, 'manual', ), ( 'using/index', 'using.tex', 'Python Setup and Usage', - _stdauthor, + _doc_authors, 'manual', ), ( 'faq/index', 'faq.tex', 'Python Frequently Asked Questions', - _stdauthor, + _doc_authors, 'manual', ), ( 'whatsnew/' + version, 'whatsnew.tex', 'What\'s New in Python', - 'A. M. Kuchling', + _doc_authors, 'howto', ), ] # Collect all HOWTOs individually latex_documents.extend( - ('howto/' + fn[:-4], 'howto-' + fn[:-4] + '.tex', '', _stdauthor, 'howto') + ( + 'howto/' + fn[:-4], + 'howto-' + fn[:-4] + '.tex', + '', + _doc_authors, + 'howto', + ) for fn in os.listdir('howto') if fn.endswith('.rst') and fn != 'index.rst' ) @@ -510,13 +441,33 @@ # Options for Epub output # ----------------------- -epub_author = 'Python Documentation Authors' +epub_author = _doc_authors epub_publisher = 'Python Software Foundation' +epub_exclude_files = ('index.xhtml', 'download.xhtml') # index pages are not valid xhtml # https://github.com/sphinx-doc/sphinx/issues/12359 epub_use_index = False +# translation tag +# --------------- + +language_code = None +for arg in sys.argv: + if arg.startswith('language='): + language_code = arg.split('=', 1)[1] + +if language_code: + tags.add('translation') # noqa: F821 + + rst_epilog += f"""\ +.. _TRANSLATION_REPO: https://github.com/python/python-docs-{language_code.replace("_", "-").lower()} +""" # noqa: F821 +else: + rst_epilog += """\ +.. _TRANSLATION_REPO: https://github.com/python +""" + # Options for the coverage checker # -------------------------------- @@ -602,15 +553,20 @@ r'https://unix.org/version2/whatsnew/lp64_wp.html', ] + # Options for sphinx.ext.extlinks # ------------------------------- +v = get_header_version_info() +branch = "main" if v.releaselevel == "alpha" else f"{v.major}.{v.minor}" + # This config is a dictionary of external sites, # mapping unique short aliases to a base URL and a prefix. # https://www.sphinx-doc.org/en/master/usage/extensions/extlinks.html extlinks = { + "oss-fuzz": ("https://issues.oss-fuzz.com/issues/%s", "#%s"), "pypi": ("https://pypi.org/project/%s/", "%s"), - "source": (SOURCE_URI, "%s"), + "source": (f"https://github.com/python/cpython/tree/{branch}/%s", "%s"), } extlinks_detect_hardcoded_links = True @@ -620,6 +576,18 @@ # Relative filename of the data files refcount_file = 'data/refcounts.dat' stable_abi_file = 'data/stable_abi.dat' +threadsafety_file = 'data/threadsafety.dat' + +# Options for notfound.extension +# ------------------------------- + +if not os.getenv("READTHEDOCS"): + if language_code: + notfound_urls_prefix = ( + f'/{language_code.replace("_", "-").lower()}/{version}/' + ) + else: + notfound_urls_prefix = f'/{version}/' # Options for sphinxext-opengraph # ------------------------------- @@ -630,13 +598,11 @@ 'image': '_static/og-image.png', 'line_color': '#3776ab', } -ogp_custom_meta_tags = [ - '', -] +ogp_custom_meta_tags = ('',) if 'create-social-cards' not in tags: # noqa: F821 # Define a static preview image when not creating social cards ogp_image = '_static/og-image.png' - ogp_custom_meta_tags += [ + ogp_custom_meta_tags += ( '', '', - ] + ) diff --git a/Doc/data/python3.14.abi b/Doc/data/python3.14.abi new file mode 100644 index 00000000000000..52432e8ea6ef04 --- /dev/null +++ b/Doc/data/python3.14.abi @@ -0,0 +1,31729 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/Doc/data/refcounts.dat b/Doc/data/refcounts.dat index ca99b9e6d37141..48b800fdf9a533 100644 --- a/Doc/data/refcounts.dat +++ b/Doc/data/refcounts.dat @@ -963,21 +963,45 @@ PyFunction_Check:PyObject*:o:0: PyFunction_GetAnnotations:PyObject*::0: PyFunction_GetAnnotations:PyObject*:op:0: +PyFunction_GET_ANNOTATIONS:PyObject*::0: +PyFunction_GET_ANNOTATIONS:PyObject*:op:0: + PyFunction_GetClosure:PyObject*::0: PyFunction_GetClosure:PyObject*:op:0: +PyFunction_GET_CLOSURE:PyObject*::0: +PyFunction_GET_CLOSURE:PyObject*:op:0: + PyFunction_GetCode:PyObject*::0: PyFunction_GetCode:PyObject*:op:0: +PyFunction_GET_CODE:PyObject*::0: +PyFunction_GET_CODE:PyObject*:op:0: + PyFunction_GetDefaults:PyObject*::0: PyFunction_GetDefaults:PyObject*:op:0: +PyFunction_GET_DEFAULTS:PyObject*::0: +PyFunction_GET_DEFAULTS:PyObject*:op:0: + +PyFunction_GetKwDefaults:PyObject*::0: +PyFunction_GetKwDefaults:PyObject*:op:0: + +PyFunction_GET_KW_DEFAULTS:PyObject*::0: +PyFunction_GET_KW_DEFAULTS:PyObject*:op:0: + PyFunction_GetGlobals:PyObject*::0: PyFunction_GetGlobals:PyObject*:op:0: +PyFunction_GET_GLOBALS:PyObject*::0: +PyFunction_GET_GLOBALS:PyObject*:op:0: + PyFunction_GetModule:PyObject*::0: PyFunction_GetModule:PyObject*:op:0: +PyFunction_GET_MODULE:PyObject*::0: +PyFunction_GET_MODULE:PyObject*:op:0: + PyFunction_New:PyObject*::+1: PyFunction_New:PyObject*:code:+1: PyFunction_New:PyObject*:globals:+1: @@ -1120,6 +1144,9 @@ PyInterpreterState_Clear:PyInterpreterState*:interp:: PyInterpreterState_Delete:void::: PyInterpreterState_Delete:PyInterpreterState*:interp:: +PyInterpreterState_GetDict:PyObject*::0: +PyInterpreterState_GetDict:PyInterpreterState*:interp:: + PyInterpreterState_GetID:int64_t::: PyInterpreterState_GetID:PyInterpreterState*:interp:: @@ -1492,9 +1519,6 @@ PyModule_SetDocString:int::: PyModule_SetDocString:PyObject*:module:0: PyModule_SetDocString:const char*:docstring:: -PyModuleDef_Init:PyObject*::0: -PyModuleDef_Init:PyModuleDef*:def:: - PyNumber_Absolute:PyObject*::+1: PyNumber_Absolute:PyObject*:o:0: @@ -2391,6 +2415,13 @@ PyType_GetFlags:PyTypeObject*:type:0: PyType_GetName:PyObject*::+1: PyType_GetName:PyTypeObject*:type:0: +PyType_GetModule:PyObject*::0: +PyType_GetModule:PyTypeObject*:type:0: + +PyType_GetModuleByDef:PyObject*::0: +PyType_GetModuleByDef:PyTypeObject*:type:0: +PyType_GetModuleByDef:PyModuleDef*:def:: + PyType_GetQualName:PyObject*::+1: PyType_GetQualName:PyTypeObject*:type:0: @@ -2781,6 +2812,9 @@ PyUnicode_AppendAndDel:void::: PyUnicode_AppendAndDel:PyObject**:p_left:0: PyUnicode_AppendAndDel:PyObject*:right:-1: +PyUnicode_BuildEncodingMap:PyObject*::+1: +PyUnicode_BuildEncodingMap:PyObject*:string::: + PyUnicode_GetDefaultEncoding:const char*::: PyUnicode_GetDefaultEncoding::void:: diff --git a/Doc/data/stable_abi.dat b/Doc/data/stable_abi.dat index 3d68487d07baf2..5fd69346ffb5e0 100644 --- a/Doc/data/stable_abi.dat +++ b/Doc/data/stable_abi.dat @@ -1,4 +1,12 @@ role,name,added,ifdef_note,struct_abi_kind +macro,METH_CLASS,3.2,, +macro,METH_COEXIST,3.2,, +macro,METH_FASTCALL,3.10,, +macro,METH_METHOD,3.7,, +macro,METH_NOARGS,3.2,, +macro,METH_O,3.2,, +macro,METH_STATIC,3.2,, +macro,METH_VARARGS,3.2,, macro,PY_VECTORCALL_ARGUMENTS_OFFSET,3.12,, func,PyAIter_Check,3.10,, func,PyArg_Parse,3.2,, @@ -8,6 +16,26 @@ func,PyArg_UnpackTuple,3.2,, func,PyArg_VaParse,3.2,, func,PyArg_VaParseTupleAndKeywords,3.2,, func,PyArg_ValidateKeywordArguments,3.2,, +macro,PyBUF_ANY_CONTIGUOUS,3.11,, +macro,PyBUF_CONTIG,3.11,, +macro,PyBUF_CONTIG_RO,3.11,, +macro,PyBUF_C_CONTIGUOUS,3.11,, +macro,PyBUF_FORMAT,3.11,, +macro,PyBUF_FULL,3.11,, +macro,PyBUF_FULL_RO,3.11,, +macro,PyBUF_F_CONTIGUOUS,3.11,, +macro,PyBUF_INDIRECT,3.11,, +macro,PyBUF_MAX_NDIM,3.11,, +macro,PyBUF_ND,3.11,, +macro,PyBUF_READ,3.11,, +macro,PyBUF_RECORDS,3.11,, +macro,PyBUF_RECORDS_RO,3.11,, +macro,PyBUF_SIMPLE,3.11,, +macro,PyBUF_STRIDED,3.11,, +macro,PyBUF_STRIDED_RO,3.11,, +macro,PyBUF_STRIDES,3.11,, +macro,PyBUF_WRITABLE,3.11,, +macro,PyBUF_WRITE,3.11,, data,PyBaseObject_Type,3.2,, func,PyBool_FromLong,3.2,, data,PyBool_Type,3.2,, @@ -426,6 +454,7 @@ data,PyMethodDescr_Type,3.2,, type,PyModuleDef,3.2,,full-abi type,PyModuleDef_Base,3.2,,full-abi func,PyModuleDef_Init,3.5,, +type,PyModuleDef_Slot,3.5,,full-abi data,PyModuleDef_Type,3.5,, func,PyModule_Add,3.13,, func,PyModule_AddFunctions,3.7,, @@ -836,6 +865,14 @@ func,PyWeakref_NewRef,3.2,, data,PyWrapperDescr_Type,3.2,, func,PyWrapper_New,3.2,, data,PyZip_Type,3.2,, +macro,Py_ASNATIVEBYTES_ALLOW_INDEX,3.14,, +macro,Py_ASNATIVEBYTES_BIG_ENDIAN,3.14,, +macro,Py_ASNATIVEBYTES_DEFAULTS,3.14,, +macro,Py_ASNATIVEBYTES_LITTLE_ENDIAN,3.14,, +macro,Py_ASNATIVEBYTES_NATIVE_ENDIAN,3.14,, +macro,Py_ASNATIVEBYTES_REJECT_NEGATIVE,3.14,, +macro,Py_ASNATIVEBYTES_UNSIGNED_BUFFER,3.14,, +macro,Py_AUDIT_READ,3.12,, func,Py_AddPendingCall,3.2,, func,Py_AtExit,3.2,, macro,Py_BEGIN_ALLOW_THREADS,3.2,, @@ -888,22 +925,136 @@ func,Py_NewInterpreter,3.2,, func,Py_NewRef,3.10,, func,Py_PACK_FULL_VERSION,3.14,, func,Py_PACK_VERSION,3.14,, +macro,Py_READONLY,3.12,, func,Py_REFCNT,3.14,, +macro,Py_RELATIVE_OFFSET,3.12,, func,Py_ReprEnter,3.2,, func,Py_ReprLeave,3.2,, func,Py_SetProgramName,3.2,, func,Py_SetPythonHome,3.2,, func,Py_SetRecursionLimit,3.2,, +macro,Py_TPFLAGS_BASETYPE,3.2,, +macro,Py_TPFLAGS_DEFAULT,3.2,, +macro,Py_TPFLAGS_HAVE_GC,3.2,, +macro,Py_TPFLAGS_HAVE_VECTORCALL,3.12,, +macro,Py_TPFLAGS_ITEMS_AT_END,3.12,, +macro,Py_TPFLAGS_METHOD_DESCRIPTOR,3.8,, +macro,Py_TP_USE_SPEC,3.14,, func,Py_TYPE,3.14,, +macro,Py_T_BOOL,3.12,, +macro,Py_T_BYTE,3.12,, +macro,Py_T_CHAR,3.12,, +macro,Py_T_DOUBLE,3.12,, +macro,Py_T_FLOAT,3.12,, +macro,Py_T_INT,3.12,, +macro,Py_T_LONG,3.12,, +macro,Py_T_LONGLONG,3.12,, +macro,Py_T_OBJECT_EX,3.12,, +macro,Py_T_PYSSIZET,3.12,, +macro,Py_T_SHORT,3.12,, +macro,Py_T_STRING,3.12,, +macro,Py_T_STRING_INPLACE,3.12,, +macro,Py_T_UBYTE,3.12,, +macro,Py_T_UINT,3.12,, +macro,Py_T_ULONG,3.12,, +macro,Py_T_ULONGLONG,3.12,, +macro,Py_T_USHORT,3.12,, type,Py_UCS4,3.2,, macro,Py_UNBLOCK_THREADS,3.2,, data,Py_UTF8Mode,3.8,, func,Py_VaBuildValue,3.2,, data,Py_Version,3.11,, func,Py_XNewRef,3.10,, +macro,Py_am_aiter,3.5,, +macro,Py_am_anext,3.5,, +macro,Py_am_await,3.5,, +macro,Py_am_send,3.10,, +macro,Py_bf_getbuffer,3.11,, +macro,Py_bf_releasebuffer,3.11,, type,Py_buffer,3.11,,full-abi type,Py_intptr_t,3.2,, +macro,Py_mod_create,3.5,, +macro,Py_mod_exec,3.5,, +macro,Py_mod_gil,3.13,, +macro,Py_mod_multiple_interpreters,3.12,, +macro,Py_mp_ass_subscript,3.2,, +macro,Py_mp_length,3.2,, +macro,Py_mp_subscript,3.2,, +macro,Py_nb_absolute,3.2,, +macro,Py_nb_add,3.2,, +macro,Py_nb_and,3.2,, +macro,Py_nb_bool,3.2,, +macro,Py_nb_divmod,3.2,, +macro,Py_nb_float,3.2,, +macro,Py_nb_floor_divide,3.2,, +macro,Py_nb_index,3.2,, +macro,Py_nb_inplace_add,3.2,, +macro,Py_nb_inplace_and,3.2,, +macro,Py_nb_inplace_floor_divide,3.2,, +macro,Py_nb_inplace_lshift,3.2,, +macro,Py_nb_inplace_matrix_multiply,3.5,, +macro,Py_nb_inplace_multiply,3.2,, +macro,Py_nb_inplace_or,3.2,, +macro,Py_nb_inplace_power,3.2,, +macro,Py_nb_inplace_remainder,3.2,, +macro,Py_nb_inplace_rshift,3.2,, +macro,Py_nb_inplace_subtract,3.2,, +macro,Py_nb_inplace_true_divide,3.2,, +macro,Py_nb_inplace_xor,3.2,, +macro,Py_nb_int,3.2,, +macro,Py_nb_invert,3.2,, +macro,Py_nb_lshift,3.2,, +macro,Py_nb_matrix_multiply,3.5,, +macro,Py_nb_multiply,3.2,, +macro,Py_nb_negative,3.2,, +macro,Py_nb_or,3.2,, +macro,Py_nb_positive,3.2,, +macro,Py_nb_power,3.2,, +macro,Py_nb_remainder,3.2,, +macro,Py_nb_rshift,3.2,, +macro,Py_nb_subtract,3.2,, +macro,Py_nb_true_divide,3.2,, +macro,Py_nb_xor,3.2,, +macro,Py_sq_ass_item,3.2,, +macro,Py_sq_concat,3.2,, +macro,Py_sq_contains,3.2,, +macro,Py_sq_inplace_concat,3.2,, +macro,Py_sq_inplace_repeat,3.2,, +macro,Py_sq_item,3.2,, +macro,Py_sq_length,3.2,, +macro,Py_sq_repeat,3.2,, type,Py_ssize_t,3.2,, +macro,Py_tp_alloc,3.2,, +macro,Py_tp_base,3.2,, +macro,Py_tp_bases,3.2,, +macro,Py_tp_call,3.2,, +macro,Py_tp_clear,3.2,, +macro,Py_tp_dealloc,3.2,, +macro,Py_tp_del,3.2,, +macro,Py_tp_descr_get,3.2,, +macro,Py_tp_descr_set,3.2,, +macro,Py_tp_doc,3.2,, +macro,Py_tp_finalize,3.5,, +macro,Py_tp_free,3.2,, +macro,Py_tp_getattr,3.2,, +macro,Py_tp_getattro,3.2,, +macro,Py_tp_getset,3.2,, +macro,Py_tp_hash,3.2,, +macro,Py_tp_init,3.2,, +macro,Py_tp_is_gc,3.2,, +macro,Py_tp_iter,3.2,, +macro,Py_tp_iternext,3.2,, +macro,Py_tp_members,3.2,, +macro,Py_tp_methods,3.2,, +macro,Py_tp_new,3.2,, +macro,Py_tp_repr,3.2,, +macro,Py_tp_richcompare,3.2,, +macro,Py_tp_setattr,3.2,, +macro,Py_tp_setattro,3.2,, +macro,Py_tp_str,3.2,, +macro,Py_tp_token,3.14,, +macro,Py_tp_traverse,3.2,, +macro,Py_tp_vectorcall,3.14,, type,Py_uintptr_t,3.2,, type,allocfunc,3.2,, type,binaryfunc,3.2,, diff --git a/Doc/data/threadsafety.dat b/Doc/data/threadsafety.dat new file mode 100644 index 00000000000000..7f9110620db4f3 --- /dev/null +++ b/Doc/data/threadsafety.dat @@ -0,0 +1,239 @@ +# Thread safety annotations for C API functions. +# +# Each line has the form: +# function_name : level +# +# Where level is one of: +# incompatible -- not safe even with external locking +# compatible -- safe if the caller serializes all access with external locks +# distinct -- safe on distinct objects without external synchronization +# shared -- safe for concurrent use on the same object +# atomic -- atomic +# +# Lines beginning with '#' are ignored. +# The function name must match the C domain identifier used in the documentation. + +# Synchronization primitives (Doc/c-api/synchronization.rst) +PyMutex_Lock:atomic: +PyMutex_Unlock:atomic: +PyMutex_IsLocked:atomic: + + +# Dictionary objects (Doc/c-api/dict.rst) + +# Type checks - read ob_type pointer, always safe +PyDict_Check:atomic: +PyDict_CheckExact:atomic: + +# Creation - pure allocation, no shared state +PyDict_New:atomic: + +# Lock-free lookups - use _Py_dict_lookup_threadsafe(), no locking. +# Atomic with simple types. +PyDict_Contains:shared: +PyDict_ContainsString:atomic: +PyDict_GetItemRef:shared: +PyDict_GetItemStringRef:atomic: +PyDict_Size:atomic: +PyDict_GET_SIZE:atomic: + +# Borrowed-reference lookups - lock-free dict access but returned +# borrowed reference is unsafe in free-threaded builds without +# external synchronization +PyDict_GetItem:compatible: +PyDict_GetItemWithError:compatible: +PyDict_GetItemString:compatible: +PyDict_SetDefault:compatible: + +# Iteration - no locking; returns borrowed refs +PyDict_Next:compatible: + +# Single-item mutations - protected by per-object critical section +PyDict_SetItem:shared: +PyDict_SetItemString:atomic: +PyDict_DelItem:shared: +PyDict_DelItemString:atomic: +PyDict_SetDefaultRef:shared: +PyDict_Pop:shared: +PyDict_PopString:atomic: + +# Bulk reads - hold per-object lock for duration +PyDict_Clear:atomic: +PyDict_Copy:atomic: +PyDict_Keys:atomic: +PyDict_Values:atomic: +PyDict_Items:atomic: + +# Merge/update - lock target dict; also lock source when it is a dict +PyDict_Update:shared: +PyDict_Merge:shared: +PyDict_MergeFromSeq2:shared: + +# Watcher registration - no synchronization on interpreter state +PyDict_AddWatcher:compatible: +PyDict_ClearWatcher:compatible: + +# Per-dict watcher tags - non-atomic RMW on _ma_watcher_tag; +# safe on distinct dicts only +PyDict_Watch:distinct: +PyDict_Unwatch:distinct: + + +# List objects (Doc/c-api/list.rst) + +# Type checks - read ob_type pointer, always safe +PyList_Check:atomic: +PyList_CheckExact:atomic: + +# Creation - pure allocation, no shared state +PyList_New:atomic: + +# Size - uses atomic load on free-threaded builds +PyList_Size:atomic: +PyList_GET_SIZE:atomic: + +# Strong-reference lookup - lock-free with atomic ops +PyList_GetItemRef:atomic: + +# Borrowed-reference lookups - no locking; returned borrowed +# reference is unsafe in free-threaded builds without +# external synchronization +PyList_GetItem:compatible: +PyList_GET_ITEM:compatible: + +# Single-item mutations - hold per-object lock for duration; +# appear atomic to lock-free readers +PyList_SetItem:atomic: +PyList_Append:atomic: + +# Insert - protected by per-object critical section; shifts +# elements so lock-free readers may observe intermediate states +PyList_Insert:shared: + +# Initialization macro - no synchronization; normally only used +# to fill in new lists where there is no previous content +PyList_SET_ITEM:compatible: + +# Bulk operations - hold per-object lock for duration +PyList_GetSlice:atomic: +PyList_AsTuple:atomic: +PyList_Clear:atomic: + +# Reverse - protected by per-object critical section; swaps +# elements so lock-free readers may observe intermediate states +PyList_Reverse:shared: + +# Slice assignment - lock target list; also lock source when it +# is a list +PyList_SetSlice:shared: + +# Sort - per-object lock held; the list is emptied before sorting +# so other threads may observe an empty list, but they won't see the +# intermediate states of the sort +PyList_Sort:shared: + +# Extend - lock target list; also lock source when it is a +# list, set, or dict +PyList_Extend:shared: + +# Creation - pure allocation, no shared state +PyBytes_FromString:atomic: +PyBytes_FromStringAndSize:atomic: +PyBytes_DecodeEscape:atomic: + +# Creation from formatting C primitives - pure allocation, no shared state +PyBytes_FromFormat:atomic: +PyBytes_FromFormatV:atomic: + +# Creation from object - uses buffer protocol so may call arbitrary code; +# safe as long as the buffer is not mutated by another thread during the operation +PyBytes_FromObject:shared: + +# Size - uses atomic load on free-threaded builds +PyBytes_Size:atomic: +PyBytes_GET_SIZE:atomic: + +# Raw data - no locking; mutating it is unsafe if the bytes object is shared between threads +PyBytes_AsString:compatible: +PyBytes_AS_STRING:compatible: +PyBytes_AsStringAndSize:compatible: + +# Concatenation - uses buffer protocol; safe as long as buffer is not mutated by another thread during the operation +PyBytes_Concat:shared: +PyBytes_ConcatAndDel:shared: +PyBytes_Join:shared: + +# Resizing - safe if the object is unique +_PyBytes_Resize:distinct: + +# Repr - atomic as bytes are immutable +PyBytes_Repr:atomic: + +# Creation from object - may call arbitrary code +PyByteArray_FromObject:shared: + +# Creation - pure allocation, no shared state +PyByteArray_FromStringAndSize:atomic: + +# Concatenation - uses buffer protocol; safe as long as buffer is not mutated by another thread during the operation +PyByteArray_Concat:shared: + +# Size - uses atomic load on free-threaded builds +PyByteArray_Size:atomic: +PyByteArray_GET_SIZE:atomic: + +# Raw data - no locking; mutating it is unsafe if the bytearray object is shared between threads +PyByteArray_AsString:compatible: +PyByteArray_AS_STRING:compatible: + +# Creation - may iterate the iterable argument, calling arbitrary code. +# Atomic for sets, frozensets, dicts, and frozendicts. +PySet_New:shared: +PyFrozenSet_New:shared: + +# Size - uses atomic load on free-threaded builds +PySet_Size:atomic: +PySet_GET_SIZE:atomic: + +# Contains - lock-free, atomic with simple types +PySet_Contains:shared: + +# Mutations - hold per-object lock for duration +# atomic with simple types +PySet_Add:shared: +PySet_Discard:shared: + +# Pop - hold per-object lock for duration +PySet_Pop:atomic: + +# Clear - empties the set before clearing +PySet_Clear:atomic: + +# Capsule objects (Doc/c-api/capsule.rst) + +# Type check - read ob_type pointer, always safe +PyCapsule_CheckExact:atomic: + +# Creation - pure allocation, no shared state +PyCapsule_New:atomic: + +# Validation - reads pointer and name fields; safe on distinct objects +PyCapsule_IsValid:distinct: + +# Getters - read struct fields; safe on distinct objects but +# concurrent access to the same capsule requires external synchronization +PyCapsule_GetPointer:distinct: +PyCapsule_GetName:distinct: +PyCapsule_GetDestructor:distinct: +PyCapsule_GetContext:distinct: + +# Setters - write struct fields; safe on distinct objects but +# concurrent access to the same capsule requires external synchronization +PyCapsule_SetPointer:distinct: +PyCapsule_SetName:distinct: +PyCapsule_SetDestructor:distinct: +PyCapsule_SetContext:distinct: + +# Import - looks up a capsule from a module attribute and +# calls PyCapsule_GetPointer; may call arbitrary code +PyCapsule_Import:compatible: diff --git a/Doc/deprecations/c-api-pending-removal-in-3.15.rst b/Doc/deprecations/c-api-pending-removal-in-3.15.rst index a5cc8f1d5b3475..bac80289cdfb3d 100644 --- a/Doc/deprecations/c-api-pending-removal-in-3.15.rst +++ b/Doc/deprecations/c-api-pending-removal-in-3.15.rst @@ -1,7 +1,6 @@ Pending removal in Python 3.15 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -* The bundled copy of ``libmpdecimal``. * The :c:func:`PyImport_ImportModuleNoBlock`: Use :c:func:`PyImport_ImportModule` instead. * :c:func:`PyWeakref_GetObject` and :c:func:`PyWeakref_GET_OBJECT`: diff --git a/Doc/deprecations/c-api-pending-removal-in-3.16.rst b/Doc/deprecations/c-api-pending-removal-in-3.16.rst new file mode 100644 index 00000000000000..9453f83799c43d --- /dev/null +++ b/Doc/deprecations/c-api-pending-removal-in-3.16.rst @@ -0,0 +1,4 @@ +Pending removal in Python 3.16 +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +* The bundled copy of ``libmpdec``. diff --git a/Doc/deprecations/c-api-pending-removal-in-3.18.rst b/Doc/deprecations/c-api-pending-removal-in-3.18.rst index 564cfb79a0b513..022aee93aa70c4 100644 --- a/Doc/deprecations/c-api-pending-removal-in-3.18.rst +++ b/Doc/deprecations/c-api-pending-removal-in-3.18.rst @@ -1,11 +1,12 @@ Pending removal in Python 3.18 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -* Deprecated private functions (:gh:`128863`): +* The following private functions are deprecated + and planned for removal in Python 3.18: * :c:func:`!_PyBytes_Join`: use :c:func:`PyBytes_Join`. * :c:func:`!_PyDict_GetItemStringWithError`: use :c:func:`PyDict_GetItemStringRef`. - * :c:func:`!_PyDict_Pop()`: :c:func:`PyDict_Pop`. + * :c:func:`!_PyDict_Pop()`: use :c:func:`PyDict_Pop`. * :c:func:`!_PyLong_Sign()`: use :c:func:`PyLong_GetSign`. * :c:func:`!_PyLong_FromDigits` and :c:func:`!_PyLong_New`: use :c:func:`PyLongWriter_Create`. @@ -31,7 +32,7 @@ Pending removal in Python 3.18 :c:func:`PyUnicodeWriter_WriteSubstring(writer, str, start, end) `. * :c:func:`!_PyUnicodeWriter_WriteASCIIString`: replace ``_PyUnicodeWriter_WriteASCIIString(&writer, str)`` with - :c:func:`PyUnicodeWriter_WriteUTF8(writer, str) `. + :c:func:`PyUnicodeWriter_WriteASCII(writer, str) `. * :c:func:`!_PyUnicodeWriter_WriteLatin1String`: replace ``_PyUnicodeWriter_WriteLatin1String(&writer, str)`` with :c:func:`PyUnicodeWriter_WriteUTF8(writer, str) `. @@ -41,5 +42,6 @@ Pending removal in Python 3.18 * :c:func:`!_Py_fopen_obj`: use :c:func:`Py_fopen`. The `pythoncapi-compat project - `__ can be used to get these - new public functions on Python 3.13 and older. + `__ can be used to get + these new public functions on Python 3.13 and older. + (Contributed by Victor Stinner in :gh:`128863`.) diff --git a/Doc/deprecations/index.rst b/Doc/deprecations/index.rst index d064f2bec42c22..c891b0339916cb 100644 --- a/Doc/deprecations/index.rst +++ b/Doc/deprecations/index.rst @@ -7,6 +7,8 @@ Deprecations .. include:: pending-removal-in-3.17.rst +.. include:: pending-removal-in-3.18.rst + .. include:: pending-removal-in-3.19.rst .. include:: pending-removal-in-future.rst diff --git a/Doc/deprecations/pending-removal-in-3.13.rst b/Doc/deprecations/pending-removal-in-3.13.rst index 2fd2f12cc6a2c4..d5b8c80e8f9aa0 100644 --- a/Doc/deprecations/pending-removal-in-3.13.rst +++ b/Doc/deprecations/pending-removal-in-3.13.rst @@ -38,15 +38,3 @@ APIs: * :meth:`!unittest.TestProgram.usageExit` (:gh:`67048`) * :class:`!webbrowser.MacOSX` (:gh:`86421`) * :class:`classmethod` descriptor chaining (:gh:`89519`) -* :mod:`importlib.resources` deprecated methods: - - * ``contents()`` - * ``is_resource()`` - * ``open_binary()`` - * ``open_text()`` - * ``path()`` - * ``read_binary()`` - * ``read_text()`` - - Use :func:`importlib.resources.files` instead. Refer to `importlib-resources: Migrating from Legacy - `_ (:gh:`106531`) diff --git a/Doc/deprecations/pending-removal-in-3.14.rst b/Doc/deprecations/pending-removal-in-3.14.rst index 6159fa48848285..171758156ab117 100644 --- a/Doc/deprecations/pending-removal-in-3.14.rst +++ b/Doc/deprecations/pending-removal-in-3.14.rst @@ -38,12 +38,6 @@ Pending removal in Python 3.14 is no current event loop set and it decides to create one. (Contributed by Serhiy Storchaka and Guido van Rossum in :gh:`100160`.) -* :mod:`collections.abc`: Deprecated :class:`!collections.abc.ByteString`. - Prefer :class:`!Sequence` or :class:`~collections.abc.Buffer`. - For use in typing, prefer a union, like ``bytes | bytearray``, - or :class:`collections.abc.Buffer`. - (Contributed by Shantanu Jain in :gh:`91896`.) - * :mod:`email`: Deprecated the *isdst* parameter in :func:`email.utils.localtime`. (Contributed by Alan Williams in :gh:`72346`.) @@ -78,7 +72,7 @@ Pending removal in Python 3.14 :meth:`~pathlib.PurePath.relative_to`: passing additional arguments is deprecated. -* :mod:`pkgutil`: :func:`!pkgutil.find_loader` and :func:!pkgutil.get_loader` +* :mod:`pkgutil`: :func:`!pkgutil.find_loader` and :func:`!pkgutil.get_loader` now raise :exc:`DeprecationWarning`; use :func:`importlib.util.find_spec` instead. (Contributed by Nikita Sobolev in :gh:`97850`.) @@ -96,9 +90,6 @@ Pending removal in Python 3.14 if :ref:`named placeholders ` are used and *parameters* is a sequence instead of a :class:`dict`. -* :mod:`typing`: :class:`!typing.ByteString`, deprecated since Python 3.9, - now causes a :exc:`DeprecationWarning` to be emitted when it is used. - * :mod:`urllib`: :class:`!urllib.parse.Quoter` is deprecated: it was not intended to be a public API. diff --git a/Doc/deprecations/pending-removal-in-3.15.rst b/Doc/deprecations/pending-removal-in-3.15.rst index 7b32275ad86760..b840ad140800f4 100644 --- a/Doc/deprecations/pending-removal-in-3.15.rst +++ b/Doc/deprecations/pending-removal-in-3.15.rst @@ -33,16 +33,6 @@ Pending removal in Python 3.15 * ``load_module()`` method: use ``exec_module()`` instead. -* :class:`locale`: - - * The :func:`~locale.getdefaultlocale` function - has been deprecated since Python 3.11. - Its removal was originally planned for Python 3.13 (:gh:`90817`), - but has been postponed to Python 3.15. - Use :func:`~locale.getlocale`, :func:`~locale.setlocale`, - and :func:`~locale.getencoding` instead. - (Contributed by Hugo van Kemenade in :gh:`111187`.) - * :mod:`pathlib`: * :meth:`.PurePath.is_reserved` @@ -64,7 +54,7 @@ Pending removal in Python 3.15 * :func:`~threading.RLock` will take no arguments in Python 3.15. Passing any arguments has been deprecated since Python 3.14, - as the Python version does not permit any arguments, + as the Python version does not permit any arguments, but the C version allows any number of positional or keyword arguments, ignoring every argument. @@ -85,7 +75,14 @@ Pending removal in Python 3.15 has been deprecated since Python 3.13. Use the class-based syntax or the functional syntax instead. - * The :func:`typing.no_type_check_decorator` decorator function + * When using the functional syntax of :class:`~typing.TypedDict`\s, failing + to pass a value to the *fields* parameter (``TD = TypedDict("TD")``) or + passing ``None`` (``TD = TypedDict("TD", None)``) has been deprecated + since Python 3.13. + Use ``class TD(TypedDict): pass`` or ``TD = TypedDict("TD", {})`` + to create a TypedDict with zero field. + + * The :deco:`typing.no_type_check_decorator` decorator function has been deprecated since Python 3.13. After eight years in the :mod:`typing` module, it has yet to be supported by any major type checker. diff --git a/Doc/deprecations/pending-removal-in-3.17.rst b/Doc/deprecations/pending-removal-in-3.17.rst index 370b98307e5228..0a1c2f08cab3bd 100644 --- a/Doc/deprecations/pending-removal-in-3.17.rst +++ b/Doc/deprecations/pending-removal-in-3.17.rst @@ -1,6 +1,28 @@ Pending removal in Python 3.17 ------------------------------ +* :mod:`collections.abc`: + + - :class:`collections.abc.ByteString` is scheduled for removal in Python 3.17. + + Use ``isinstance(obj, collections.abc.Buffer)`` to test if ``obj`` + implements the :ref:`buffer protocol ` at runtime. For use + in type annotations, either use :class:`~collections.abc.Buffer` or a union + that explicitly specifies the types your code supports (e.g., + ``bytes | bytearray | memoryview``). + + :class:`!ByteString` was originally intended to be an abstract class that + would serve as a supertype of both :class:`bytes` and :class:`bytearray`. + However, since the ABC never had any methods, knowing that an object was an + instance of :class:`!ByteString` never actually told you anything useful + about the object. Other common buffer types such as :class:`memoryview` + were also never understood as subtypes of :class:`!ByteString` (either at + runtime or by static type checkers). + + See :pep:`PEP 688 <688#current-options>` for more details. + (Contributed by Shantanu Jain in :gh:`91896`.) + + * :mod:`typing`: - Before Python 3.14, old-style unions were implemented using the private class @@ -8,3 +30,22 @@ Pending removal in Python 3.17 but it has been retained for backward compatibility, with removal scheduled for Python 3.17. Users should use documented introspection helpers like :func:`typing.get_origin` and :func:`typing.get_args` instead of relying on private implementation details. + - :class:`typing.ByteString`, deprecated since Python 3.9, is scheduled for removal in + Python 3.17. + + Use ``isinstance(obj, collections.abc.Buffer)`` to test if ``obj`` + implements the :ref:`buffer protocol ` at runtime. For use + in type annotations, either use :class:`~collections.abc.Buffer` or a union + that explicitly specifies the types your code supports (e.g., + ``bytes | bytearray | memoryview``). + + :class:`!ByteString` was originally intended to be an abstract class that + would serve as a supertype of both :class:`bytes` and :class:`bytearray`. + However, since the ABC never had any methods, knowing that an object was an + instance of :class:`!ByteString` never actually told you anything useful + about the object. Other common buffer types such as :class:`memoryview` + were also never understood as subtypes of :class:`!ByteString` (either at + runtime or by static type checkers). + + See :pep:`PEP 688 <688#current-options>` for more details. + (Contributed by Shantanu Jain in :gh:`91896`.) diff --git a/Doc/deprecations/pending-removal-in-3.18.rst b/Doc/deprecations/pending-removal-in-3.18.rst new file mode 100644 index 00000000000000..3e799219478424 --- /dev/null +++ b/Doc/deprecations/pending-removal-in-3.18.rst @@ -0,0 +1,9 @@ +Pending removal in Python 3.18 +------------------------------ + +* :mod:`decimal`: + + * The non-standard and undocumented :class:`~decimal.Decimal` format + specifier ``'N'``, which is only supported in the :mod:`!decimal` module's + C implementation, has been deprecated since Python 3.13. + (Contributed by Serhiy Storchaka in :gh:`89902`.) diff --git a/Doc/deprecations/pending-removal-in-future.rst b/Doc/deprecations/pending-removal-in-future.rst index 4c4a368baca955..d9a2d50378e92b 100644 --- a/Doc/deprecations/pending-removal-in-future.rst +++ b/Doc/deprecations/pending-removal-in-future.rst @@ -15,7 +15,6 @@ although there is currently no date scheduled for their removal. * :mod:`builtins`: - * ``bool(NotImplemented)``. * Generators: ``throw(type, exc, tb)`` and ``athrow(type, exc, tb)`` signature is deprecated: use ``throw(exc)`` and ``athrow(exc)`` instead, the single argument signature. @@ -36,7 +35,6 @@ although there is currently no date scheduled for their removal. * Support for ``__complex__()`` method returning a strict subclass of :class:`complex`: these methods will be required to return an instance of :class:`complex`. - * Delegation of ``int()`` to ``__trunc__()`` method. * Passing a complex number as the *real* or *imag* argument in the :func:`complex` constructor is now deprecated; it should only be passed as a single positional argument. diff --git a/Doc/extending/building.rst b/Doc/extending/building.rst index ddde567f6f3efa..098dde39ea597e 100644 --- a/Doc/extending/building.rst +++ b/Doc/extending/building.rst @@ -6,41 +6,10 @@ Building C and C++ Extensions ***************************** -A C extension for CPython is a shared library (e.g. a ``.so`` file on Linux, -``.pyd`` on Windows), which exports an *initialization function*. +A C extension for CPython is a shared library (for example, a ``.so`` file on +Linux, ``.pyd`` on Windows), which exports an *initialization function*. -To be importable, the shared library must be available on :envvar:`PYTHONPATH`, -and must be named after the module name, with an appropriate extension. -When using setuptools, the correct filename is generated automatically. - -The initialization function has the signature: - -.. c:function:: PyObject* PyInit_modulename(void) - -It returns either a fully initialized module, or a :c:type:`PyModuleDef` -instance. See :ref:`initializing-modules` for details. - -.. highlight:: python - -For modules with ASCII-only names, the function must be named -``PyInit_``, with ```` replaced by the name of the -module. When using :ref:`multi-phase-initialization`, non-ASCII module names -are allowed. In this case, the initialization function name is -``PyInitU_``, with ```` encoded using Python's -*punycode* encoding with hyphens replaced by underscores. In Python:: - - def initfunc_name(name): - try: - suffix = b'_' + name.encode('ascii') - except UnicodeEncodeError: - suffix = b'U_' + name.encode('punycode').replace(b'-', b'_') - return b'PyInit' + suffix - -It is possible to export multiple modules from a single shared library by -defining multiple initialization functions. However, importing them requires -using symbolic links or a custom importer, because by default only the -function corresponding to the filename is found. -See the *"Multiple modules in one library"* section in :pep:`489` for details. +See :ref:`extension-modules` for details. .. highlight:: c @@ -51,7 +20,11 @@ See the *"Multiple modules in one library"* section in :pep:`489` for details. Building C and C++ Extensions with setuptools ============================================= -Python 3.12 and newer no longer come with distutils. Please refer to the -``setuptools`` documentation at -https://setuptools.readthedocs.io/en/latest/setuptools.html -to learn more about how build and distribute C/C++ extensions with setuptools. + +Building, packaging and distributing extension modules is best done with +third-party tools, and is out of scope of this document. +One suitable tool is Setuptools, whose documentation can be found at +https://setuptools.pypa.io/en/latest/setuptools.html. + +The :mod:`distutils` module, which was included in the standard library +until Python 3.12, is now maintained as part of Setuptools. diff --git a/Doc/extending/embedding.rst b/Doc/extending/embedding.rst index b777862da79f14..cb41889437c8b0 100644 --- a/Doc/extending/embedding.rst +++ b/Doc/extending/embedding.rst @@ -245,21 +245,23 @@ Python extension. For example:: return PyLong_FromLong(numargs); } - static PyMethodDef EmbMethods[] = { + static PyMethodDef emb_module_methods[] = { {"numargs", emb_numargs, METH_VARARGS, "Return the number of arguments received by the process."}, {NULL, NULL, 0, NULL} }; - static PyModuleDef EmbModule = { - PyModuleDef_HEAD_INIT, "emb", NULL, -1, EmbMethods, - NULL, NULL, NULL, NULL + static struct PyModuleDef emb_module = { + .m_base = PyModuleDef_HEAD_INIT, + .m_name = "emb", + .m_size = 0, + .m_methods = emb_module_methods, }; static PyObject* PyInit_emb(void) { - return PyModule_Create(&EmbModule); + return PyModuleDef_Init(&emb_module); } Insert the above code just above the :c:func:`main` function. Also, insert the diff --git a/Doc/extending/extending.rst b/Doc/extending/extending.rst index b0493bed75b151..6518e20cafbc9e 100644 --- a/Doc/extending/extending.rst +++ b/Doc/extending/extending.rst @@ -75,12 +75,37 @@ the module and a copyright notice if you like). See :ref:`arg-parsing-string-and-buffers` for a description of this macro. All user-visible symbols defined by :file:`Python.h` have a prefix of ``Py`` or -``PY``, except those defined in standard header files. For convenience, and -since they are used extensively by the Python interpreter, ``"Python.h"`` -includes a few standard header files: ````, ````, -````, and ````. If the latter header file does not exist on -your system, it declares the functions :c:func:`malloc`, :c:func:`free` and -:c:func:`realloc` directly. +``PY``, except those defined in standard header files. + +.. tip:: + + For backward compatibility, :file:`Python.h` includes several standard header files. + C extensions should include the standard headers that they use, + and should not rely on these implicit includes. + If using the limited C API version 3.13 or newer, the implicit includes are: + + * ```` + * ```` (on Windows) + * ```` + * ```` + * ```` + * ```` + * ```` + * ```` (if present) + + If :c:macro:`Py_LIMITED_API` is not defined, or is set to version 3.12 or older, + the headers below are also included: + + * ```` + * ```` (on POSIX) + + If :c:macro:`Py_LIMITED_API` is not defined, or is set to version 3.10 or older, + the headers below are also included: + + * ```` + * ```` + * ```` + * ```` The next thing we add to our module file is the C function that will be called when the Python expression ``spam.system(string)`` is evaluated (we'll see @@ -203,31 +228,57 @@ function usually raises :c:data:`PyExc_TypeError`. If you have an argument whos value must be in a particular range or must satisfy other conditions, :c:data:`PyExc_ValueError` is appropriate. -You can also define a new exception that is unique to your module. For this, you -usually declare a static object variable at the beginning of your file:: +You can also define a new exception that is unique to your module. +The simplest way to do this is to declare a static global object variable at +the beginning of the file:: - static PyObject *SpamError; + static PyObject *SpamError = NULL; -and initialize it in your module's initialization function (:c:func:`!PyInit_spam`) -with an exception object:: +and initialize it by calling :c:func:`PyErr_NewException` in the module's +:c:data:`Py_mod_exec` function (:c:func:`!spam_module_exec`):: - PyMODINIT_FUNC - PyInit_spam(void) - { - PyObject *m; + SpamError = PyErr_NewException("spam.error", NULL, NULL); - m = PyModule_Create(&spammodule); - if (m == NULL) - return NULL; +Since :c:data:`!SpamError` is a global variable, it will be overwritten every time +the module is reinitialized, when the :c:data:`Py_mod_exec` function is called. + +For now, let's avoid the issue: we will block repeated initialization by raising an +:py:exc:`ImportError`:: + static PyObject *SpamError = NULL; + + static int + spam_module_exec(PyObject *m) + { + if (SpamError != NULL) { + PyErr_SetString(PyExc_ImportError, + "cannot initialize spam module more than once"); + return -1; + } SpamError = PyErr_NewException("spam.error", NULL, NULL); - if (PyModule_AddObjectRef(m, "error", SpamError) < 0) { - Py_CLEAR(SpamError); - Py_DECREF(m); - return NULL; + if (PyModule_AddObjectRef(m, "SpamError", SpamError) < 0) { + return -1; } - return m; + return 0; + } + + static PyModuleDef_Slot spam_module_slots[] = { + {Py_mod_exec, spam_module_exec}, + {0, NULL} + }; + + static struct PyModuleDef spam_module = { + .m_base = PyModuleDef_HEAD_INIT, + .m_name = "spam", + .m_size = 0, // non-negative + .m_slots = spam_module_slots, + }; + + PyMODINIT_FUNC + PyInit_spam(void) + { + return PyModuleDef_Init(&spam_module); } Note that the Python name for the exception object is :exc:`!spam.error`. The @@ -242,6 +293,11 @@ needed to ensure that it will not be discarded, causing :c:data:`!SpamError` to become a dangling pointer. Should it become a dangling pointer, C code which raises the exception could cause a core dump or other unintended side effects. +For now, the :c:func:`Py_DECREF` call to remove this reference is missing. +Even when the Python interpreter shuts down, the global :c:data:`!SpamError` +variable will not be garbage-collected. It will "leak". +We did, however, ensure that this will happen at most once per process. + We discuss the use of :c:macro:`PyMODINIT_FUNC` as a function return type later in this sample. @@ -318,7 +374,7 @@ The Module's Method Table and Initialization Function I promised to show how :c:func:`!spam_system` is called from Python programs. First, we need to list its name and address in a "method table":: - static PyMethodDef SpamMethods[] = { + static PyMethodDef spam_methods[] = { ... {"system", spam_system, METH_VARARGS, "Execute a shell command."}, @@ -343,13 +399,10 @@ function. The method table must be referenced in the module definition structure:: - static struct PyModuleDef spammodule = { - PyModuleDef_HEAD_INIT, - "spam", /* name of module */ - spam_doc, /* module documentation, may be NULL */ - -1, /* size of per-interpreter state of the module, - or -1 if the module keeps state in global variables. */ - SpamMethods + static struct PyModuleDef spam_module = { + ... + .m_methods = spam_methods, + ... }; This structure, in turn, must be passed to the interpreter in the module's @@ -360,23 +413,17 @@ only non-\ ``static`` item defined in the module file:: PyMODINIT_FUNC PyInit_spam(void) { - return PyModule_Create(&spammodule); + return PyModuleDef_Init(&spam_module); } Note that :c:macro:`PyMODINIT_FUNC` declares the function as ``PyObject *`` return type, declares any special linkage declarations required by the platform, and for C++ declares the function as ``extern "C"``. -When the Python program imports module :mod:`!spam` for the first time, -:c:func:`!PyInit_spam` is called. (See below for comments about embedding Python.) -It calls :c:func:`PyModule_Create`, which returns a module object, and -inserts built-in function objects into the newly created module based upon the -table (an array of :c:type:`PyMethodDef` structures) found in the module definition. -:c:func:`PyModule_Create` returns a pointer to the module object -that it creates. It may abort with a fatal error for -certain errors, or return ``NULL`` if the module could not be initialized -satisfactorily. The init function must return the module object to its caller, -so that it then gets inserted into ``sys.modules``. +:c:func:`!PyInit_spam` is called when each interpreter imports its module +:mod:`!spam` for the first time. (See below for comments about embedding Python.) +A pointer to the module definition must be returned via :c:func:`PyModuleDef_Init`, +so that the import machinery can create the module and store it in ``sys.modules``. When embedding Python, the :c:func:`!PyInit_spam` function is not called automatically unless there's an entry in the :c:data:`PyImport_Inittab` table. @@ -433,23 +480,19 @@ optionally followed by an import of the module:: .. note:: - Removing entries from ``sys.modules`` or importing compiled modules into - multiple interpreters within a process (or following a :c:func:`fork` without an - intervening :c:func:`exec`) can create problems for some extension modules. - Extension module authors should exercise caution when initializing internal data - structures. + If you declare a global variable or a local static one, the module may + experience unintended side-effects on re-initialisation, for example when + removing entries from ``sys.modules`` or importing compiled modules into + multiple interpreters within a process + (or following a :c:func:`fork` without an intervening :c:func:`exec`). + If module state is not yet fully :ref:`isolated `, + authors should consider marking the module as having no support for subinterpreters + (via :c:macro:`Py_MOD_MULTIPLE_INTERPRETERS_NOT_SUPPORTED`). A more substantial example module is included in the Python source distribution -as :file:`Modules/xxmodule.c`. This file may be used as a template or simply +as :file:`Modules/xxlimited.c`. This file may be used as a template or simply read as an example. -.. note:: - - Unlike our ``spam`` example, ``xxmodule`` uses *multi-phase initialization* - (new in Python 3.5), where a PyModuleDef structure is returned from - ``PyInit_spam``, and creation of the module is left to the import machinery. - For details on multi-phase initialization, see :PEP:`489`. - .. _compilation: @@ -502,10 +545,8 @@ calling the Python callback functions from a C callback. Other uses are also imaginable. Fortunately, the Python interpreter is easily called recursively, and there is a -standard interface to call a Python function. (I won't dwell on how to call the -Python parser with a particular string as input --- if you're interested, have a -look at the implementation of the :option:`-c` command line option in -:file:`Modules/main.c` from the Python source code.) +standard interface to call a Python function. (If you're interested in how to call the +Python parser with a particular string as input, see :ref:`veryhigh`.) Calling a Python function is easy. First, the Python program must somehow pass you the Python function object. You should provide a function (or some other @@ -790,18 +831,17 @@ Philbrick (philbrick@hks.com):: {NULL, NULL, 0, NULL} /* sentinel */ }; - static struct PyModuleDef keywdargmodule = { - PyModuleDef_HEAD_INIT, - "keywdarg", - NULL, - -1, - keywdarg_methods + static struct PyModuleDef keywdarg_module = { + .m_base = PyModuleDef_HEAD_INIT, + .m_name = "keywdarg", + .m_size = 0, + .m_methods = keywdarg_methods, }; PyMODINIT_FUNC PyInit_keywdarg(void) { - return PyModule_Create(&keywdargmodule); + return PyModuleDef_Init(&keywdarg_module); } @@ -896,7 +936,7 @@ and the object is freed. An alternative strategy is called :dfn:`automatic garbage collection`. (Sometimes, reference counting is also referred to as a garbage collection -strategy, hence my use of "automatic" to distinguish the two.) The big +strategy, hence the use of "automatic" to distinguish the two.) The big advantage of automatic garbage collection is that the user doesn't need to call :c:func:`free` explicitly. (Another claimed advantage is an improvement in speed or memory usage --- this is no hard fact however.) The disadvantage is that for @@ -1042,7 +1082,14 @@ references to all its items, so when item 1 is replaced, it has to dispose of the original item 1. Now let's suppose the original item 1 was an instance of a user-defined class, and let's further suppose that the class defined a :meth:`!__del__` method. If this class instance has a reference count of 1, -disposing of it will call its :meth:`!__del__` method. +disposing of it will call its :meth:`!__del__` method. Internally, +:c:func:`PyList_SetItem` calls :c:func:`Py_DECREF` on the replaced item, +which invokes replaced item's corresponding +:c:member:`~PyTypeObject.tp_dealloc` function. During +deallocation, :c:member:`~PyTypeObject.tp_dealloc` calls +:c:member:`~PyTypeObject.tp_finalize`, which is mapped to the +:meth:`!__del__` method for class instances (see :pep:`442`). This entire +sequence happens synchronously within the :c:func:`PyList_SetItem` call. Since it is written in Python, the :meth:`!__del__` method can execute arbitrary Python code. Could it perhaps do something to invalidate the reference to @@ -1072,8 +1119,9 @@ why his :meth:`!__del__` methods would fail... The second case of problems with a borrowed reference is a variant involving threads. Normally, multiple threads in the Python interpreter can't get in each -other's way, because there is a global lock protecting Python's entire object -space. However, it is possible to temporarily release this lock using the macro +other's way, because there is a :term:`global lock ` +protecting Python's entire object space. +However, it is possible to temporarily release this lock using the macro :c:macro:`Py_BEGIN_ALLOW_THREADS`, and to re-acquire it using :c:macro:`Py_END_ALLOW_THREADS`. This is common around blocking I/O calls, to let other threads use the processor while waiting for the I/O to complete. @@ -1259,20 +1307,15 @@ two more lines must be added:: #include "spammodule.h" The ``#define`` is used to tell the header file that it is being included in the -exporting module, not a client module. Finally, the module's initialization -function must take care of initializing the C API pointer array:: +exporting module, not a client module. Finally, the module's :c:data:`mod_exec +` function must take care of initializing the C API pointer array:: - PyMODINIT_FUNC - PyInit_spam(void) + static int + spam_module_exec(PyObject *m) { - PyObject *m; static void *PySpam_API[PySpam_API_pointers]; PyObject *c_api_object; - m = PyModule_Create(&spammodule); - if (m == NULL) - return NULL; - /* Initialize the C API pointer array */ PySpam_API[PySpam_System_NUM] = (void *)PySpam_System; @@ -1280,11 +1323,10 @@ function must take care of initializing the C API pointer array:: c_api_object = PyCapsule_New((void *)PySpam_API, "spam._C_API", NULL); if (PyModule_Add(m, "_C_API", c_api_object) < 0) { - Py_DECREF(m); - return NULL; + return -1; } - return m; + return 0; } Note that ``PySpam_API`` is declared ``static``; otherwise the pointer @@ -1343,20 +1385,16 @@ like this:: All that a client module must do in order to have access to the function :c:func:`!PySpam_System` is to call the function (or rather macro) -:c:func:`!import_spam` in its initialization function:: +:c:func:`!import_spam` in its :c:data:`mod_exec ` function:: - PyMODINIT_FUNC - PyInit_client(void) + static int + client_module_exec(PyObject *m) { - PyObject *m; - - m = PyModule_Create(&clientmodule); - if (m == NULL) - return NULL; - if (import_spam() < 0) - return NULL; + if (import_spam() < 0) { + return -1; + } /* additional initialization can happen here */ - return m; + return 0; } The main disadvantage of this approach is that the file :file:`spammodule.h` is @@ -1367,7 +1405,7 @@ Finally it should be mentioned that Capsules offer additional functionality, which is especially useful for memory allocation and deallocation of the pointer stored in a Capsule. The details are described in the Python/C API Reference Manual in the section :ref:`capsules` and in the implementation of Capsules (files -:file:`Include/pycapsule.h` and :file:`Objects/pycapsule.c` in the Python source +:file:`Include/pycapsule.h` and :file:`Objects/capsule.c` in the Python source code distribution). .. rubric:: Footnotes diff --git a/Doc/extending/index.rst b/Doc/extending/index.rst index 01b4df6d44acff..4cc2c96d8d5b47 100644 --- a/Doc/extending/index.rst +++ b/Doc/extending/index.rst @@ -26,19 +26,9 @@ Recommended third party tools ============================= This guide only covers the basic tools for creating extensions provided -as part of this version of CPython. Third party tools like -`Cython `_, `cffi `_, -`SWIG `_ and `Numba `_ -offer both simpler and more sophisticated approaches to creating C and C++ -extensions for Python. - -.. seealso:: - - `Python Packaging User Guide: Binary Extensions `_ - The Python Packaging User Guide not only covers several available - tools that simplify the creation of binary extensions, but also - discusses the various reasons why creating an extension module may be - desirable in the first place. +as part of this version of CPython. Some :ref:`third party tools +` offer both simpler and more sophisticated approaches to creating +C and C++ extensions for Python. Creating extensions without third party tools @@ -49,6 +39,10 @@ assistance from third party tools. It is intended primarily for creators of those tools, rather than being a recommended way to create your own C extensions. +.. seealso:: + + :pep:`489` -- Multi-phase extension module initialization + .. toctree:: :maxdepth: 2 :numbered: diff --git a/Doc/extending/newtypes_tutorial.rst b/Doc/extending/newtypes_tutorial.rst index 3fc91841416d71..3bbee33bd50698 100644 --- a/Doc/extending/newtypes_tutorial.rst +++ b/Doc/extending/newtypes_tutorial.rst @@ -55,8 +55,10 @@ from the previous chapter. This file defines three things: #. How the :class:`!Custom` **type** behaves: this is the ``CustomType`` struct, which defines a set of flags and function pointers that the interpreter inspects when specific operations are requested. -#. How to initialize the :mod:`!custom` module: this is the ``PyInit_custom`` - function and the associated ``custommodule`` struct. +#. How to define and execute the :mod:`!custom` module: this is the + ``PyInit_custom`` function and the associated ``custom_module`` struct for + defining the module, and the ``custom_module_exec`` function to set up + a fresh module object. The first bit is:: @@ -171,18 +173,18 @@ implementation provided by the API function :c:func:`PyType_GenericNew`. :: .tp_new = PyType_GenericNew, Everything else in the file should be familiar, except for some code in -:c:func:`!PyInit_custom`:: +:c:func:`!custom_module_exec`:: - if (PyType_Ready(&CustomType) < 0) - return; + if (PyType_Ready(&CustomType) < 0) { + return -1; + } This initializes the :class:`!Custom` type, filling in a number of members to the appropriate default values, including :c:member:`~PyObject.ob_type` that we initially set to ``NULL``. :: if (PyModule_AddObjectRef(m, "Custom", (PyObject *) &CustomType) < 0) { - Py_DECREF(m); - return NULL; + return -1; } This adds the type to the module dictionary. This allows us to create @@ -275,7 +277,7 @@ be an instance of a subclass. The explicit cast to ``CustomObject *`` above is needed because we defined ``Custom_dealloc`` to take a ``PyObject *`` argument, as the ``tp_dealloc`` function pointer expects to receive a ``PyObject *`` argument. - By assigning to the the ``tp_dealloc`` slot of a type, we declare + By assigning to the ``tp_dealloc`` slot of a type, we declare that it can only be called with instances of our ``CustomObject`` class, so the cast to ``(CustomObject *)`` is safe. This is object-oriented polymorphism, in C! @@ -875,27 +877,22 @@ but let the base class handle it by calling its own :c:member:`~PyTypeObject.tp_ The :c:type:`PyTypeObject` struct supports a :c:member:`~PyTypeObject.tp_base` specifying the type's concrete base class. Due to cross-platform compiler issues, you can't fill that field directly with a reference to -:c:type:`PyList_Type`; it should be done later in the module initialization +:c:type:`PyList_Type`; it should be done in the :c:data:`Py_mod_exec` function:: - PyMODINIT_FUNC - PyInit_sublist(void) + static int + sublist_module_exec(PyObject *m) { - PyObject* m; SubListType.tp_base = &PyList_Type; - if (PyType_Ready(&SubListType) < 0) - return NULL; - - m = PyModule_Create(&sublistmodule); - if (m == NULL) - return NULL; + if (PyType_Ready(&SubListType) < 0) { + return -1; + } if (PyModule_AddObjectRef(m, "SubList", (PyObject *) &SubListType) < 0) { - Py_DECREF(m); - return NULL; + return -1; } - return m; + return 0; } Before calling :c:func:`PyType_Ready`, the type structure must have the diff --git a/Doc/extending/windows.rst b/Doc/extending/windows.rst index 56aa44e4e58c83..a97c6182553c30 100644 --- a/Doc/extending/windows.rst +++ b/Doc/extending/windows.rst @@ -121,7 +121,7 @@ When creating DLLs in Windows, you can use the CPython library in two ways: :file:`Python.h` triggers an implicit, configure-aware link with the library. The header file chooses :file:`pythonXY_d.lib` for Debug, :file:`pythonXY.lib` for Release, and :file:`pythonX.lib` for Release with - the `Limited API `_ enabled. + the :ref:`Limited API ` enabled. To build two DLLs, spam and ni (which uses C functions found in spam), you could use these commands:: diff --git a/Doc/faq/design.rst b/Doc/faq/design.rst index e2710fab9cf800..3872a9ab9364f9 100644 --- a/Doc/faq/design.rst +++ b/Doc/faq/design.rst @@ -263,6 +263,8 @@ In general, structured switch statements execute one block of code when an expression has a particular value or set of values. Since Python 3.10 one can easily match literal values, or constants within a namespace, with a ``match ... case`` statement. +See :ref:`the specification ` and :ref:`the tutorial ` +for more information about :keyword:`match` statements. An older alternative is a sequence of ``if... elif... elif... else``. For cases where you need to choose from a very large number of possibilities, @@ -589,9 +591,9 @@ exhaustive test suites that exercise every line of code in a module. An appropriate testing discipline can help build large complex applications in Python as well as having interface specifications would. In fact, it can be better because an interface specification cannot test certain properties of a -program. For example, the :meth:`!list.append` method is expected to add new elements +program. For example, the :meth:`list.append` method is expected to add new elements to the end of some internal list; an interface specification cannot test that -your :meth:`!list.append` implementation will actually do this correctly, but it's +your :meth:`list.append` implementation will actually do this correctly, but it's trivial to check this property in a test suite. Writing test suites is very helpful, and you might want to design your code to diff --git a/Doc/faq/extending.rst b/Doc/faq/extending.rst index 3147fda7c37124..1d5abed2317b0c 100644 --- a/Doc/faq/extending.rst +++ b/Doc/faq/extending.rst @@ -37,24 +37,9 @@ Writing C is hard; are there any alternatives? ---------------------------------------------- There are a number of alternatives to writing your own C extensions, depending -on what you're trying to do. - -.. XXX make sure these all work - -`Cython `_ and its relative `Pyrex -`_ are compilers -that accept a slightly modified form of Python and generate the corresponding -C code. Cython and Pyrex make it possible to write an extension without having -to learn Python's C API. - -If you need to interface to some C or C++ library for which no Python extension -currently exists, you can try wrapping the library's data types and functions -with a tool such as `SWIG `_. `SIP -`__, `CXX -`_ `Boost -`_, or `Weave -`_ are also -alternatives for wrapping C++ libraries. +on what you're trying to do. :ref:`Recommended third party tools ` +offer both simpler and more sophisticated approaches to creating C and C++ +extensions for Python. How can I execute arbitrary Python statements from C? diff --git a/Doc/faq/general.rst b/Doc/faq/general.rst index 578777d7f23621..698f2117ff5c64 100644 --- a/Doc/faq/general.rst +++ b/Doc/faq/general.rst @@ -186,7 +186,7 @@ How do I get documentation on Python? ------------------------------------- The standard documentation for the current stable version of Python is available -at https://docs.python.org/3/. PDF, plain text, and downloadable HTML versions are +at https://docs.python.org/3/. EPUB, plain text, and downloadable HTML versions are also available at https://docs.python.org/3/download.html. The documentation is written in reStructuredText and processed by `the Sphinx diff --git a/Doc/faq/programming.rst b/Doc/faq/programming.rst index 9f9e4fab685b19..adc4ad2e2bb744 100644 --- a/Doc/faq/programming.rst +++ b/Doc/faq/programming.rst @@ -8,11 +8,11 @@ Programming FAQ .. contents:: -General Questions +General questions ================= -Is there a source code level debugger with breakpoints, single-stepping, etc.? ------------------------------------------------------------------------------- +Is there a source code-level debugger with breakpoints and single-stepping? +--------------------------------------------------------------------------- Yes. @@ -25,8 +25,7 @@ Reference Manual `. You can also write your own debugger by using the code for pdb as an example. The IDLE interactive development environment, which is part of the standard -Python distribution (normally available as -`Tools/scripts/idle3 `_), +Python distribution (normally available as :mod:`idlelib`), includes a graphical debugger. PythonWin is a Python IDE that includes a GUI debugger based on pdb. The @@ -48,7 +47,6 @@ There are a number of commercial Python IDEs that include graphical debuggers. They include: * `Wing IDE `_ -* `Komodo IDE `_ * `PyCharm `_ @@ -57,13 +55,15 @@ Are there tools to help find bugs or perform static analysis? Yes. -`Pylint `_ and -`Pyflakes `_ do basic checking that will +`Ruff `__, +`Pylint `__ and +`Pyflakes `__ do basic checking that will help you catch bugs sooner. -Static type checkers such as `Mypy `_, -`Pyre `_, and -`Pytype `_ can check type hints in Python +Static type checkers such as `mypy `__, +`ty `__, +`Pyrefly `__, and +`pytype `__ can check type hints in Python source code. @@ -79,7 +79,7 @@ set of modules required by a program and bind these modules together with a Python binary to produce a single executable. One is to use the freeze tool, which is included in the Python source tree as -`Tools/freeze `_. +:source:`Tools/freeze`. It converts Python byte code to C arrays; with a C compiler you can embed all your modules into a new program, which is then linked with the standard Python modules. @@ -103,6 +103,7 @@ executables: * `py2app `_ (macOS only) * `py2exe `_ (Windows only) + Are there coding standards or a style guide for Python programs? ---------------------------------------------------------------- @@ -110,7 +111,7 @@ Yes. The coding style required for standard library modules is documented as :pep:`8`. -Core Language +Core language ============= .. _faq-unboundlocalerror: @@ -143,7 +144,7 @@ results in an :exc:`!UnboundLocalError`: >>> foo() Traceback (most recent call last): ... - UnboundLocalError: local variable 'x' referenced before assignment + UnboundLocalError: cannot access local variable 'x' where it is not associated with a value This is because when you make an assignment to a variable in a scope, that variable becomes local to that scope and shadows any similarly named variable @@ -208,7 +209,7 @@ Why do lambdas defined in a loop with different values all return the same resul ---------------------------------------------------------------------------------- Assume you use a for loop to define a few different lambdas (or even plain -functions), e.g.:: +functions), for example:: >>> squares = [] >>> for x in range(5): @@ -227,7 +228,7 @@ they all return ``16``:: This happens because ``x`` is not local to the lambdas, but is defined in the outer scope, and it is accessed when the lambda is called --- not when it is defined. At the end of the loop, the value of ``x`` is ``4``, so all the -functions now return ``4**2``, i.e. ``16``. You can also verify this by +functions now return ``4**2``, that is ``16``. You can also verify this by changing the value of ``x`` and see how the results of the lambdas change:: >>> x = 8 @@ -298,9 +299,9 @@ using multiple imports per line uses less screen space. It's good practice if you import modules in the following order: -1. standard library modules -- e.g. :mod:`sys`, :mod:`os`, :mod:`argparse`, :mod:`re` +1. standard library modules -- such as :mod:`sys`, :mod:`os`, :mod:`argparse`, :mod:`re` 2. third-party library modules (anything installed in Python's site-packages - directory) -- e.g. :mod:`!dateutil`, :mod:`!requests`, :mod:`!PIL.Image` + directory) -- such as :pypi:`dateutil`, :pypi:`requests`, :pypi:`tzdata` 3. locally developed modules It is sometimes necessary to move imports to a function or class to avoid @@ -454,7 +455,7 @@ There are two factors that produce this result: (the list), and both ``x`` and ``y`` refer to it. 2) Lists are :term:`mutable`, which means that you can change their content. -After the call to :meth:`!append`, the content of the mutable object has +After the call to :meth:`~sequence.append`, the content of the mutable object has changed from ``[]`` to ``[10]``. Since both the variables refer to the same object, using either name accesses the modified value ``[10]``. @@ -494,11 +495,11 @@ new objects). In other words: -* If we have a mutable object (:class:`list`, :class:`dict`, :class:`set`, - etc.), we can use some specific operations to mutate it and all the variables +* If we have a mutable object (such as :class:`list`, :class:`dict`, :class:`set`), + we can use some specific operations to mutate it and all the variables that refer to it will see the change. -* If we have an immutable object (:class:`str`, :class:`int`, :class:`tuple`, - etc.), all the variables that refer to it will always see the same value, +* If we have an immutable object (such as :class:`str`, :class:`int`, :class:`tuple`), + all the variables that refer to it will always see the same value, but operations that transform that value into a new value always return a new object. @@ -511,7 +512,7 @@ How do I write a function with output parameters (call by reference)? Remember that arguments are passed by assignment in Python. Since assignment just creates references to objects, there's no alias between an argument name in -the caller and callee, and so no call-by-reference per se. You can achieve the +the caller and callee, and consequently no call-by-reference. You can achieve the desired effect in a number of ways. 1) By returning a tuple of the results:: @@ -714,8 +715,8 @@ not:: "a" in ("b", "a") -The same is true of the various assignment operators (``=``, ``+=`` etc). They -are not truly operators but syntactic delimiters in assignment statements. +The same is true of the various assignment operators (``=``, ``+=``, and so on). +They are not truly operators but syntactic delimiters in assignment statements. Is there an equivalent of C's "?:" ternary operator? @@ -868,9 +869,9 @@ with either a space or parentheses. How do I convert a string to a number? -------------------------------------- -For integers, use the built-in :func:`int` type constructor, e.g. ``int('144') +For integers, use the built-in :func:`int` type constructor, for example, ``int('144') == 144``. Similarly, :func:`float` converts to a floating-point number, -e.g. ``float('144') == 144.0``. +for example, ``float('144') == 144.0``. By default, these interpret the number as decimal, so that ``int('0144') == 144`` holds true, and ``int('0x144')`` raises :exc:`ValueError`. ``int(string, @@ -887,18 +888,18 @@ unwanted side effects. For example, someone could pass directory. :func:`eval` also has the effect of interpreting numbers as Python expressions, -so that e.g. ``eval('09')`` gives a syntax error because Python does not allow +so that, for example, ``eval('09')`` gives a syntax error because Python does not allow leading '0' in a decimal number (except '0'). How do I convert a number to a string? -------------------------------------- -To convert, e.g., the number ``144`` to the string ``'144'``, use the built-in type +For example, to convert the number ``144`` to the string ``'144'``, use the built-in type constructor :func:`str`. If you want a hexadecimal or octal representation, use the built-in functions :func:`hex` or :func:`oct`. For fancy formatting, see -the :ref:`f-strings` and :ref:`formatstrings` sections, -e.g. ``"{:04d}".format(144)`` yields +the :ref:`f-strings` and :ref:`formatstrings` sections. +For example, ``"{:04d}".format(144)`` yields ``'0144'`` and ``"{:.3f}".format(1.0/3.0)`` yields ``'0.333'``. @@ -908,7 +909,7 @@ How do I modify a string in place? You can't, because strings are immutable. In most situations, you should simply construct a new string from the various parts you want to assemble it from. However, if you need an object with the ability to modify in-place -unicode data, try using an :class:`io.StringIO` object or the :mod:`array` +Unicode data, try using an :class:`io.StringIO` object or the :mod:`array` module:: >>> import io @@ -1066,13 +1067,14 @@ the raw string:: Also see the specification in the :ref:`language reference `. + Performance =========== My program is too slow. How do I speed it up? --------------------------------------------- -That's a tough one, in general. First, here are a list of things to +That's a tough one, in general. First, here is a list of things to remember before diving further: * Performance characteristics vary across Python implementations. This FAQ @@ -1125,6 +1127,7 @@ yourself. The wiki page devoted to `performance tips `_. + .. _efficient_string_concatenation: What is the most efficient way to concatenate many strings together? @@ -1143,7 +1146,7 @@ them into a list and call :meth:`str.join` at the end:: chunks.append(s) result = ''.join(chunks) -(another reasonably efficient idiom is to use :class:`io.StringIO`) +(Another reasonably efficient idiom is to use :class:`io.StringIO`.) To accumulate many :class:`bytes` objects, the recommended idiom is to extend a :class:`bytearray` object using in-place concatenation (the ``+=`` operator):: @@ -1153,7 +1156,7 @@ a :class:`bytearray` object using in-place concatenation (the ``+=`` operator):: result += b -Sequences (Tuples/Lists) +Sequences (tuples/lists) ======================== How do I convert between tuples and lists? @@ -1217,8 +1220,8 @@ list, deleting duplicates as you go:: else: last = mylist[i] -If all elements of the list may be used as set keys (i.e. they are all -:term:`hashable`) this is often faster :: +If all elements of the list may be used as set keys (that is, they are all +:term:`hashable`) this is often faster:: mylist = list(set(mylist)) @@ -1226,13 +1229,13 @@ This converts the list into a set, thereby removing duplicates, and then back into a list. -How do you remove multiple items from a list --------------------------------------------- +How do you remove multiple items from a list? +--------------------------------------------- As with removing duplicates, explicitly iterating in reverse with a delete condition is one possibility. However, it is easier and faster to use slice replacement with an implicit or explicit forward iteration. -Here are three variations.:: +Here are three variations:: mylist[:] = filter(keep_function, mylist) mylist[:] = (x for x in mylist if keep_condition) @@ -1254,7 +1257,7 @@ difference is that a Python list can contain objects of many different types. The ``array`` module also provides methods for creating arrays of fixed types with compact representations, but they are slower to index than lists. Also note that `NumPy `_ -and other third party packages define array-like structures with +and other third-party packages define array-like structures with various characteristics as well. To get Lisp-style linked lists, you can emulate *cons cells* using tuples:: @@ -1324,7 +1327,7 @@ Or, you can use an extension that provides a matrix datatype; `NumPy How do I apply a method or function to a sequence of objects? ------------------------------------------------------------- -To call a method or function and accumulate the return values is a list, +To call a method or function and accumulate the return values in a list, a :term:`list comprehension` is an elegant solution:: result = [obj.method() for obj in mylist] @@ -1340,6 +1343,7 @@ a plain :keyword:`for` loop will suffice:: for obj in mylist: function(obj) + .. _faq-augmented-assignment-tuple-error: Why does a_tuple[i] += ['item'] raise an exception when the addition works? @@ -1397,9 +1401,9 @@ To see why this happens, you need to know that (a) if an object implements an :meth:`~object.__iadd__` magic method, it gets called when the ``+=`` augmented assignment is executed, and its return value is what gets used in the assignment statement; -and (b) for lists, :meth:`!__iadd__` is equivalent to calling :meth:`!extend` on the list -and returning the list. That's why we say that for lists, ``+=`` is a -"shorthand" for :meth:`!list.extend`:: +and (b) for lists, :meth:`!__iadd__` is equivalent to calling +:meth:`~sequence.extend` on the list and returning the list. +That's why we say that for lists, ``+=`` is a "shorthand" for :meth:`list.extend`:: >>> a_list = [] >>> a_list += [1] @@ -1444,7 +1448,7 @@ How can I sort one list by values from another list? ---------------------------------------------------- Merge them into an iterator of tuples, sort the resulting list, and then pick -out the element you want. :: +out the element you want. >>> list1 = ["what", "I'm", "sorting", "by"] >>> list2 = ["something", "else", "to", "sort"] @@ -1504,14 +1508,15 @@ How do I check if an object is an instance of a given class or of a subclass of Use the built-in function :func:`isinstance(obj, cls) `. You can check if an object is an instance of any of a number of classes by providing a tuple instead of a -single class, e.g. ``isinstance(obj, (class1, class2, ...))``, and can also -check whether an object is one of Python's built-in types, e.g. +single class, for example, ``isinstance(obj, (class1, class2, ...))``, and can also +check whether an object is one of Python's built-in types, for example, ``isinstance(obj, str)`` or ``isinstance(obj, (int, float, complex))``. Note that :func:`isinstance` also checks for virtual inheritance from an :term:`abstract base class`. So, the test will return ``True`` for a registered class even if hasn't directly or indirectly inherited from it. To -test for "true inheritance", scan the :term:`MRO` of the class: +test for "true inheritance", scan the :term:`method resolution order` (MRO) of +the class: .. testcode:: @@ -1574,7 +1579,7 @@ call it:: What is delegation? ------------------- -Delegation is an object oriented technique (also called a design pattern). +Delegation is an object-oriented technique (also called a design pattern). Let's say you have an object ``x`` and want to change the behaviour of just one of its methods. You can create a new class that provides a new implementation of the method you're interested in changing and delegates all other methods to @@ -1645,7 +1650,7 @@ How can I organize my code to make it easier to change the base class? You could assign the base class to an alias and derive from the alias. Then all you have to change is the value assigned to the alias. Incidentally, this trick -is also handy if you want to decide dynamically (e.g. depending on availability +is also handy if you want to decide dynamically (such as depending on availability of resources) which base class to use. Example:: class Base: @@ -1710,9 +1715,9 @@ How can I overload constructors (or methods) in Python? This answer actually applies to all methods, but the question usually comes up first in the context of constructors. -In C++ you'd write +In C++ you'd write: -.. code-block:: c +.. code-block:: c++ class C { C() { cout << "No arguments\n"; } @@ -1731,7 +1736,7 @@ default arguments. For example:: This is not entirely equivalent, but close enough in practice. -You could also try a variable-length argument list, e.g. :: +You could also try a variable-length argument list, for example:: def __init__(self, *args): ... @@ -1774,6 +1779,7 @@ to use private variable names at all. The :ref:`private name mangling specifications ` for details and special cases. + My class defines __del__ but it is not called when I delete the object. ----------------------------------------------------------------------- @@ -1783,7 +1789,7 @@ The :keyword:`del` statement does not necessarily call :meth:`~object.__del__` - decrements the object's reference count, and if this reaches zero :meth:`!__del__` is called. -If your data structures contain circular links (e.g. a tree where each child has +If your data structures contain circular links (for example, a tree where each child has a parent reference and each parent has a list of children) the reference counts will never go back to zero. Once in a while Python runs an algorithm to detect such cycles, but the garbage collector might run some time after the last @@ -1852,6 +1858,8 @@ to the object: 13891296 +.. _faq-identity-with-is: + When can I rely on identity tests with the *is* operator? --------------------------------------------------------- @@ -1883,9 +1891,9 @@ are preferred. In particular, identity tests should not be used to check constants such as :class:`int` and :class:`str` which aren't guaranteed to be singletons:: - >>> a = 1000 - >>> b = 500 - >>> c = b + 500 + >>> a = 10_000_000 + >>> b = 5_000_000 + >>> c = b + 5_000_000 >>> a is c False @@ -1954,9 +1962,9 @@ parent class: .. testcode:: - from datetime import date + import datetime as dt - class FirstOfMonthDate(date): + class FirstOfMonthDate(dt.date): "Always choose the first day of the month" def __new__(cls, year, month, day): return super().__new__(cls, year, month, 1) @@ -1995,11 +2003,11 @@ How do I cache method calls? ---------------------------- The two principal tools for caching methods are -:func:`functools.cached_property` and :func:`functools.lru_cache`. The +:deco:`functools.cached_property` and :deco:`functools.lru_cache`. The former stores results at the instance level and the latter at the class level. -The *cached_property* approach only works with methods that do not take +The ``cached_property`` approach only works with methods that do not take any arguments. It does not create a reference to the instance. The cached method result will be kept only as long as the instance is alive. @@ -2008,7 +2016,7 @@ method result will be released right away. The disadvantage is that if instances accumulate, so too will the accumulated method results. They can grow without bound. -The *lru_cache* approach works with methods that have :term:`hashable` +The ``lru_cache`` approach works with methods that have :term:`hashable` arguments. It creates a reference to the instance unless special efforts are made to pass in weak references. @@ -2042,11 +2050,11 @@ This example shows the various techniques:: # Depends on the station_id, date, and units. The above example assumes that the *station_id* never changes. If the -relevant instance attributes are mutable, the *cached_property* approach +relevant instance attributes are mutable, the ``cached_property`` approach can't be made to work because it cannot detect changes to the attributes. -To make the *lru_cache* approach work when the *station_id* is mutable, +To make the ``lru_cache`` approach work when the *station_id* is mutable, the class needs to define the :meth:`~object.__eq__` and :meth:`~object.__hash__` methods so that the cache can detect relevant attribute updates:: @@ -2092,10 +2100,10 @@ one user but run as another, such as if you are testing with a web server. Unless the :envvar:`PYTHONDONTWRITEBYTECODE` environment variable is set, creation of a .pyc file is automatic if you're importing a module and Python -has the ability (permissions, free space, etc...) to create a ``__pycache__`` +has the ability (permissions, free space, and so on) to create a ``__pycache__`` subdirectory and write the compiled module to that subdirectory. -Running Python on a top level script is not considered an import and no +Running Python on a top-level script is not considered an import and no ``.pyc`` will be created. For example, if you have a top-level module ``foo.py`` that imports another module ``xyz.py``, when you run ``foo`` (by typing ``python foo.py`` as a shell command), a ``.pyc`` will be created for @@ -2114,7 +2122,7 @@ the ``compile()`` function in that module interactively:: This will write the ``.pyc`` to a ``__pycache__`` subdirectory in the same location as ``foo.py`` (or you can override that with the optional parameter -``cfile``). +*cfile*). You can also automatically compile all files in a directory or directories using the :mod:`compileall` module. You can do it from the shell prompt by running @@ -2219,7 +2227,7 @@ changed module, do this:: importlib.reload(modname) Warning: this technique is not 100% fool-proof. In particular, modules -containing statements like :: +containing statements like:: from modname import some_objects diff --git a/Doc/glossary.rst b/Doc/glossary.rst index 0b26e18efd7f1b..bb00a4f02f0efd 100644 --- a/Doc/glossary.rst +++ b/Doc/glossary.rst @@ -21,7 +21,9 @@ Glossary right delimiters (parentheses, square brackets, curly braces or triple quotes), or after specifying a decorator. - * The :const:`Ellipsis` built-in constant. + .. index:: single: ...; ellipsis literal + + * The three dots form of the :ref:`Ellipsis ` object. abstract base class Abstract base classes complement :term:`duck-typing` by @@ -37,10 +39,11 @@ Glossary ABCs with the :mod:`abc` module. annotate function - A function that can be called to retrieve the :term:`annotations ` - of an object. This function is accessible as the :attr:`~object.__annotate__` - attribute of functions, classes, and modules. Annotate functions are a - subset of :term:`evaluate functions `. + A callable that can be called to retrieve the :term:`annotations ` of + an object. Annotate functions are usually :term:`functions `, + automatically generated as the :attr:`~object.__annotate__` attribute of functions, + classes, and modules. Annotate functions are a subset of + :term:`evaluate functions `. annotation A label associated with a variable, a class @@ -93,21 +96,24 @@ Glossary :meth:`~object.__aexit__` methods. Introduced by :pep:`492`. asynchronous generator - A function which returns an :term:`asynchronous generator iterator`. It - looks like a coroutine function defined with :keyword:`async def` except - that it contains :keyword:`yield` expressions for producing a series of - values usable in an :keyword:`async for` loop. - - Usually refers to an asynchronous generator function, but may refer to an - *asynchronous generator iterator* in some contexts. In cases where the - intended meaning isn't clear, using the full terms avoids ambiguity. + Informally used to mean either an :term:`asynchronous generator + function` or an :term:`asynchronous generator iterator`, depending on + context. The formal terms :term:`asynchronous generator function` and + :term:`asynchronous generator iterator` are uncommon in practice; + "asynchronous generator" alone is almost always sufficient. + + asynchronous generator function + A function which returns an :term:`asynchronous generator iterator`. + It looks like a coroutine function defined with :keyword:`async def` + except that it contains :keyword:`yield` expressions for producing a + series of values usable in an :keyword:`async for` loop. See :pep:`525`. An asynchronous generator function may contain :keyword:`await` expressions as well as :keyword:`async for`, and :keyword:`async with` statements. asynchronous generator iterator - An object created by a :term:`asynchronous generator` function. + An object created by an :term:`asynchronous generator function`. This is an :term:`asynchronous iterator` which when called using the :meth:`~object.__anext__` method returns an awaitable object which will execute @@ -132,6 +138,14 @@ Glossary iterator's :meth:`~object.__anext__` method until it raises a :exc:`StopAsyncIteration` exception. Introduced by :pep:`492`. + atomic operation + An operation that appears to execute as a single, indivisible step: no + other thread can observe it half-done, and its effects become visible all + at once. Python does not guarantee that high-level statements are atomic + (for example, ``x += 1`` performs multiple bytecode operations and is not + atomic). Atomicity is only guaranteed where explicitly documented. See + also :term:`race condition` and :term:`data race`. + attached thread state A :term:`thread state` that is active for the current OS thread. @@ -150,9 +164,9 @@ Glossary On most builds of Python, having an attached thread state implies that the caller holds the :term:`GIL` for the current interpreter, so only one OS thread can have an attached thread state at a given moment. In - :term:`free-threaded ` builds of Python, threads can concurrently - hold an attached thread state, allowing for true parallelism of the bytecode - interpreter. + :term:`free-threaded builds ` of Python, threads can + concurrently hold an attached thread state, allowing for true parallelism of + the bytecode interpreter. attribute A value associated with an object which is usually referenced by name @@ -287,6 +301,22 @@ Glossary advanced mathematical feature. If you're not aware of a need for them, it's almost certain you can safely ignore them. + concurrency + The ability of a computer program to perform multiple tasks at the same + time. Python provides libraries for writing programs that make use of + different forms of concurrency. :mod:`asyncio` is a library for dealing + with asynchronous tasks and coroutines. :mod:`threading` provides + access to operating system threads and :mod:`multiprocessing` to + operating system processes. Multi-core processors can execute threads and + processes on different CPU cores at the same time (see + :term:`parallelism`). + + concurrent modification + When multiple threads modify shared data at the same time. Concurrent + modification without proper synchronization can cause + :term:`race conditions `, and might also trigger a + :term:`data race `, data corruption, or both. + context This term has different meanings depending on where and how it is used. Some common meanings: @@ -355,10 +385,38 @@ Glossary tasks (see :mod:`asyncio`) associate each task with a context which becomes the current context whenever the task starts or resumes execution. + cyclic isolate + A subgroup of one or more objects that reference each other in a reference + cycle, but are not referenced by objects outside the group. The goal of + the :term:`cyclic garbage collector ` is to identify these groups and break the reference + cycles so that the memory can be reclaimed. + + data race + A situation where multiple threads access the same memory location + concurrently, at least one of the accesses is a write, and the threads + do not use any synchronization to control their access. Data races + lead to :term:`non-deterministic` behavior and can cause data corruption. + Proper use of :term:`locks ` and other :term:`synchronization primitives + ` prevents data races. Note that data races + can only happen in native code, but that :term:`native code` might be + exposed in a Python API. See also :term:`race condition` and + :term:`thread-safe`. + + deadlock + A situation in which two or more tasks (threads, processes, or coroutines) + wait indefinitely for each other to release resources or complete actions, + preventing any from making progress. For example, if thread A holds lock + 1 and waits for lock 2, while thread B holds lock 2 and waits for lock 1, + both threads will wait indefinitely. In Python this often arises from + acquiring multiple locks in conflicting orders or from circular + join/await dependencies. Deadlocks can be avoided by always acquiring + multiple :term:`locks ` in a consistent order. See also + :term:`lock` and :term:`reentrant`. + decorator A function returning another function, usually applied as a function transformation using the ``@wrapper`` syntax. Common examples for - decorators are :func:`classmethod` and :func:`staticmethod`. + decorators are :deco:`classmethod` and :deco:`staticmethod`. The decorator syntax is merely syntactic sugar, the following two function definitions are semantically equivalent:: @@ -429,6 +487,11 @@ Glossary with :term:`abstract base classes `.) Instead, it typically employs :func:`hasattr` tests or :term:`EAFP` programming. + dunder + An informal short-hand for "double underscore", used when talking about a + :term:`special method`. For example, ``__init__`` is often pronounced + "dunder init". + EAFP Easier to ask for forgiveness than permission. This common Python coding style assumes the existence of valid keys or attributes and catches @@ -456,7 +519,8 @@ Glossary core and with user code. f-string - String literals prefixed with ``'f'`` or ``'F'`` are commonly called + f-strings + String literals prefixed with ``f`` or ``F`` are commonly called "f-strings" which is short for :ref:`formatted string literals `. See also :pep:`498`. @@ -520,6 +584,13 @@ Glossary the :term:`global interpreter lock` which allows only one thread to execute Python bytecode at a time. See :pep:`703`. + free-threaded build + + A build of :term:`CPython` that supports :term:`free threading`, + configured using the :option:`--disable-gil` option before compilation. + + See :ref:`freethreading-python-howto`. + free variable Formally, as defined in the :ref:`language execution model `, a free variable is any variable used in a namespace which is not a local variable in that @@ -573,23 +644,33 @@ Glossary .. index:: single: generator generator - A function which returns a :term:`generator iterator`. It looks like a - normal function except that it contains :keyword:`yield` expressions - for producing a series of values usable in a for-loop or that can be - retrieved one at a time with the :func:`next` function. + Informally used to mean either a :term:`generator function` or a + :term:`generator iterator`, depending on context. The formal terms + :term:`generator function` and :term:`generator iterator` are uncommon + in practice; "generator" alone is almost always sufficient. - Usually refers to a generator function, but may refer to a - *generator iterator* in some contexts. In cases where the intended - meaning isn't clear, using the full terms avoids ambiguity. + .. index:: single: generator function + + generator function + A function which returns a :term:`generator` object. It looks like a + normal function except that it contains :keyword:`yield` expressions + for producing a series of values usable in a :keyword:`for`\-loop or + that can be retrieved one at a time with the :func:`next` function. + See :ref:`yieldexpr`. generator iterator - An object created by a :term:`generator` function. + An object created by a :term:`generator function` or a + :term:`generator expression`. Each :keyword:`yield` temporarily suspends processing, remembering the - execution state (including local variables and pending - try-statements). When the *generator iterator* resumes, it picks up where - it left off (in contrast to functions which start fresh on every - invocation). + execution state (including local variables and pending try-statements). + When the *generator iterator* resumes, it picks up where it left off + (in contrast to functions which start fresh on every invocation). + + Generator iterators also implement the :meth:`~generator.send` method + to send a value into the suspended generator, and the + :meth:`~generator.throw` method to raise an exception at the point + where the generator was paused. See :ref:`generator-methods`. .. index:: single: generator expression @@ -608,7 +689,7 @@ Glossary determined by the dispatch algorithm. See also the :term:`single dispatch` glossary entry, the - :func:`functools.singledispatch` decorator, and :pep:`443`. + :deco:`functools.singledispatch` decorator, and :pep:`443`. generic type A :term:`type` that can be parameterized; typically a @@ -648,6 +729,14 @@ Glossary requires the GIL to be held in order to use it. This refers to having an :term:`attached thread state`. + global state + Data that is accessible throughout a program, such as module-level + variables, class variables, or C static variables in :term:`extension modules + `. In multi-threaded programs, global state shared + between threads typically requires synchronization to avoid + :term:`race conditions ` and + :term:`data races `. + hash-based pyc A bytecode cache file that uses the hash rather than the last-modified time of the corresponding source file to determine its validity. See @@ -692,7 +781,9 @@ Glossary tuples. Such an object cannot be altered. A new object has to be created if a different value has to be stored. They play an important role in places where a constant hash value is needed, for example as a key - in a dictionary. + in a dictionary. Immutable objects are inherently :term:`thread-safe` + because their state cannot be modified after creation, eliminating concerns + about improperly synchronized :term:`concurrent modification`. import path A list of locations (or :term:`path entries `) that are @@ -709,6 +800,19 @@ Glossary An object that both finds and loads a module; both a :term:`finder` and :term:`loader` object. + index + A numeric value that represents the position of an element in + a :term:`sequence`. + + In Python, indexing starts at zero. + For example, ``things[0]`` names the *first* element of ``things``; + ``things[1]`` names the second one. + + In some contexts, Python allows negative indexes for counting from the + end of a sequence, and indexing using :term:`slices `. + + See also :term:`subscript`. + interactive Python has an interactive interpreter which means you can enter statements and expressions at the interpreter prompt, immediately @@ -782,9 +886,13 @@ Glossary CPython does not consistently apply the requirement that an iterator define :meth:`~iterator.__iter__`. - And also please note that the free-threading CPython does not guarantee - the thread-safety of iterator operations. + And also please note that :term:`free-threaded ` + CPython does not guarantee :term:`thread-safe` behavior of iterator + operations. + key + A value that identifies an entry in a :term:`mapping`. + See also :term:`subscript`. key function A key function or collation function is a callable that returns a value @@ -799,7 +907,7 @@ Glossary :func:`itertools.groupby`. There are several ways to create a key function. For example. the - :meth:`str.lower` method can serve as a key function for case insensitive + :meth:`str.casefold` method can serve as a key function for case insensitive sorts. Alternatively, a key function can be built from a :keyword:`lambda` expression such as ``lambda r: (r[0], r[2])``. Also, :func:`operator.attrgetter`, :func:`operator.itemgetter`, and @@ -821,10 +929,11 @@ Glossary :keyword:`if` statements. In a multi-threaded environment, the LBYL approach can risk introducing a - race condition between "the looking" and "the leaping". For example, the - code, ``if key in mapping: return mapping[key]`` can fail if another + :term:`race condition` between "the looking" and "the leaping". For example, + the code, ``if key in mapping: return mapping[key]`` can fail if another thread removes *key* from *mapping* after the test, but before the lookup. - This issue can be solved with locks or by using the EAFP approach. + This issue can be solved with :term:`locks ` or by using the + :term:`EAFP` approach. See also :term:`thread-safe`. lexical analyzer @@ -843,6 +952,29 @@ Glossary clause is optional. If omitted, all elements in ``range(256)`` are processed. + lock + A :term:`synchronization primitive` that allows only one thread at a + time to access a shared resource. A thread must acquire a lock before + accessing the protected resource and release it afterward. If a thread + attempts to acquire a lock that is already held by another thread, it + will block until the lock becomes available. Python's :mod:`threading` + module provides :class:`~threading.Lock` (a basic lock) and + :class:`~threading.RLock` (a :term:`reentrant` lock). Locks are used + to prevent :term:`race conditions ` and ensure + :term:`thread-safe` access to shared data. Alternative design patterns + to locks exist such as queues, producer/consumer patterns, and + thread-local state. See also :term:`deadlock`, and :term:`reentrant`. + + lock-free + An operation that does not acquire any :term:`lock` and uses atomic CPU + instructions to ensure correctness. Lock-free operations can execute + concurrently without blocking each other and cannot be blocked by + operations that hold locks. In :term:`free-threaded ` + Python, built-in types like :class:`dict` and :class:`list` provide + lock-free read operations, which means other threads may observe + intermediate states during multi-step modifications even when those + modifications hold the :term:`per-object lock`. + loader An object that loads a module. It must define the :meth:`!exec_module` and :meth:`!create_module` methods @@ -928,8 +1060,11 @@ Glossary See :term:`method resolution order`. mutable - Mutable objects can change their value but keep their :func:`id`. See - also :term:`immutable`. + An :term:`object` with state that is allowed to change during the course + of the program. In multi-threaded programs, mutable objects that are + shared between threads require careful synchronization to avoid + :term:`race conditions `. See also :term:`immutable`, + :term:`thread-safe`, and :term:`concurrent modification`. named tuple The term "named tuple" applies to any type or class that inherits from @@ -981,6 +1116,13 @@ Glossary See also :term:`module`. + native code + Code that is compiled to machine instructions and runs directly on the + processor, as opposed to code that is interpreted or runs in a virtual + machine. In the context of Python, native code typically refers to + C, C++, Rust or Fortran code in :term:`extension modules ` + that can be called from Python. See also :term:`extension module`. + nested scope The ability to refer to a variable in an enclosing definition. For instance, a function defined inside another function can refer to @@ -997,6 +1139,15 @@ Glossary properties, :meth:`~object.__getattribute__`, class methods, and static methods. + non-deterministic + Behavior where the outcome of a program can vary between executions with + the same inputs. In multi-threaded programs, non-deterministic behavior + often results from :term:`race conditions ` where the + relative timing or interleaving of threads affects the result. + Proper synchronization using :term:`locks ` and other + :term:`synchronization primitives ` helps + ensure deterministic behavior. + object Any data with state (attributes or value) and defined behavior (methods). Also the ultimate base class of any :term:`new-style @@ -1011,6 +1162,15 @@ Glossary applied to all scopes, only those relying on a known set of local and nonlocal variable names are restricted to optimized scopes. + optional module + An :term:`extension module` that is part of the :term:`standard library`, + but may be absent in some builds of :term:`CPython`, + usually due to missing third-party libraries or because the module + is not available for a given platform. + + See :ref:`optional-module-requirements` for a list of optional modules + that require third-party libraries. + package A Python :term:`module` which can contain submodules or recursively, subpackages. Technically, a package is a Python module with a @@ -1018,6 +1178,16 @@ Glossary See also :term:`regular package` and :term:`namespace package`. + parallelism + Executing multiple operations at the same time (e.g. on multiple CPU + cores). In Python builds with the + :term:`global interpreter lock (GIL) `, only one + thread runs Python bytecode at a time, so taking advantage of multiple + CPU cores typically involves multiple processes + (e.g. :mod:`multiprocessing`) or native extensions that release the GIL. + In :term:`free-threaded ` Python, multiple Python threads + can run Python code simultaneously on different cores. + parameter A named entity in a :term:`function` (or method) definition that specifies an :term:`argument` (or in some cases, arguments) that the @@ -1071,6 +1241,16 @@ Glossary `, the :class:`inspect.Parameter` class, the :ref:`function` section, and :pep:`362`. + per-object lock + A :term:`lock` associated with an individual object instance rather than + a global lock shared across all objects. In :term:`free-threaded + ` Python, built-in types like :class:`dict` and + :class:`list` use per-object locks to allow concurrent operations on + different objects while serializing operations on the same object. + Operations that hold the per-object lock prevent other locking operations + on the same object from proceeding, but do not block :term:`lock-free` + operations. + path entry A single location on the :term:`import path` which the :term:`path based finder` consults to find modules for importing. @@ -1192,6 +1372,18 @@ Glossary >>> email.mime.text.__name__ 'email.mime.text' + race condition + A condition of a program where the behavior + depends on the relative timing or ordering of events, particularly in + multi-threaded programs. Race conditions can lead to + :term:`non-deterministic` behavior and bugs that are difficult to + reproduce. A :term:`data race` is a specific type of race condition + involving unsynchronized access to shared memory. The :term:`LBYL` + coding style is particularly susceptible to race conditions in + multi-threaded code. Using :term:`locks ` and other + :term:`synchronization primitives ` + helps prevent race conditions. + reference count The number of references to an object. When the reference count of an object drops to zero, it is deallocated. Some objects are @@ -1202,12 +1394,36 @@ Glossary :func:`sys.getrefcount` function to return the reference count for a particular object. + In :term:`CPython`, reference counts are not considered to be stable + or well-defined values; the number of references to an object, and how + that number is affected by Python code, may be different between + versions. + regular package A traditional :term:`package`, such as a directory containing an ``__init__.py`` file. See also :term:`namespace package`. + reentrant + A property of a function or :term:`lock` that allows it to be called or + acquired multiple times by the same thread without causing errors or a + :term:`deadlock`. + + For functions, reentrancy means the function can be safely called again + before a previous invocation has completed, which is important when + functions may be called recursively or from signal handlers. Thread-unsafe + functions may be :term:`non-deterministic` if they're called reentrantly in a + multithreaded program. + + For locks, Python's :class:`threading.RLock` (reentrant lock) is + reentrant, meaning a thread that already holds the lock can acquire it + again without blocking. In contrast, :class:`threading.Lock` is not + reentrant - attempting to acquire it twice from the same thread will cause + a deadlock. + + See also :term:`lock` and :term:`deadlock`. + REPL An acronym for the "read–eval–print loop", another name for the :term:`interactive` interpreter shell. @@ -1232,8 +1448,9 @@ Glossary The :class:`collections.abc.Sequence` abstract base class defines a much richer interface that goes beyond just :meth:`~object.__getitem__` and :meth:`~object.__len__`, adding - :meth:`!count`, :meth:`!index`, :meth:`~object.__contains__`, and - :meth:`~object.__reversed__`. Types that implement this expanded + :meth:`~sequence.count`, :meth:`~sequence.index`, + :meth:`~object.__contains__`, and :meth:`~object.__reversed__`. + Types that implement this expanded interface can be registered explicitly using :func:`~abc.ABCMeta.register`. For more documentation on sequence methods generally, see @@ -1250,10 +1467,11 @@ Glossary chosen based on the type of a single argument. slice - An object usually containing a portion of a :term:`sequence`. A slice is - created using the subscript notation, ``[]`` with colons between numbers - when several are given, such as in ``variable_name[1:3:5]``. The bracket - (subscript) notation uses :class:`slice` objects internally. + An object of type :class:`slice`, used to describe a portion of + a :term:`sequence`. + A slice object is created when using the :ref:`slicing ` form + of :ref:`subscript notation `, with colons inside square + brackets, such as in ``variable_name[1:3:5]``. soft deprecated A soft deprecated API should not be used in new code, @@ -1274,6 +1492,16 @@ Glossary and ending with double underscores. Special methods are documented in :ref:`specialnames`. + standard library + The collection of :term:`packages `, :term:`modules ` + and :term:`extension modules ` distributed as a part + of the official Python interpreter package. The exact membership of the + collection may vary based on platform, available system libraries, or + other criteria. Documentation can be found at :ref:`library-index`. + + See also :data:`sys.stdlib_module_names` for a list of all possible + standard library module names. + statement A statement is part of a suite (a "block" of code). A statement is either an :term:`expression` or one of several constructs with a keyword, such @@ -1284,6 +1512,17 @@ Glossary issues such as incorrect types. See also :term:`type hints ` and the :mod:`typing` module. + stdlib + An abbreviation of :term:`standard library`. + + steal + In Python's C API, "*stealing*" an argument means that ownership of the + argument is transferred to the called function. + The caller must not use that reference after the call. + Generally, functions that "steal" an argument do so even if they fail. + + See :ref:`api-refcountdetails` for a full explanation. + strong reference In Python's C API, a strong reference is a reference to an object which is owned by the code holding the reference. The strong @@ -1298,6 +1537,32 @@ Glossary See also :term:`borrowed reference`. + subscript + The expression in square brackets of a + :ref:`subscription expression `, for example, + the ``3`` in ``items[3]``. + Usually used to select an element of a container. + Also called a :term:`key` when subscripting a :term:`mapping`, + or an :term:`index` when subscripting a :term:`sequence`. + + synchronization primitive + A basic building block for coordinating (synchronizing) the execution of + multiple threads to ensure :term:`thread-safe` access to shared resources. + Python's :mod:`threading` module provides several synchronization primitives + including :class:`~threading.Lock`, :class:`~threading.RLock`, + :class:`~threading.Semaphore`, :class:`~threading.Condition`, + :class:`~threading.Event`, and :class:`~threading.Barrier`. Additionally, + the :mod:`queue` module provides multi-producer, multi-consumer queues + that are especially useful in multithreaded programs. These + primitives help prevent :term:`race conditions ` and + coordinate thread execution. See also :term:`lock`. + + t-string + t-strings + String literals prefixed with ``t`` or ``T`` are commonly called + "t-strings" which is short for + :ref:`template string literals `. + text encoding A string in Python is a sequence of Unicode code points (in range ``U+0000``--``U+10FFFF``). To store or transfer a string, it needs to be @@ -1344,6 +1609,19 @@ Glossary See :ref:`Thread State and the Global Interpreter Lock ` for more information. + thread-safe + A module, function, or class that behaves correctly when used by multiple + threads concurrently. Thread-safe code uses appropriate + :term:`synchronization primitives ` like + :term:`locks ` to protect shared mutable state, or is designed + to avoid shared mutable state entirely. In the + :term:`free-threaded ` build, built-in types like + :class:`dict`, :class:`list`, and :class:`set` use internal locking + to make many operations thread-safe, although thread safety is not + necessarily guaranteed. Code that is not thread-safe may experience + :term:`race conditions ` and :term:`data races ` + when used in multi-threaded programs. + token A small unit of source code, generated by the @@ -1443,6 +1721,11 @@ Glossary A computer defined entirely in software. Python's virtual machine executes the :term:`bytecode` emitted by the bytecode compiler. + walrus operator + A light-hearted way to refer to the :ref:`assignment expression + ` operator ``:=`` because it looks a bit like a + walrus if you turn your head. + Zen of Python Listing of Python design principles and philosophies that are helpful in understanding and using the language. The listing can be found by typing diff --git a/Doc/howto/a-conceptual-overview-of-asyncio.rst b/Doc/howto/a-conceptual-overview-of-asyncio.rst new file mode 100644 index 00000000000000..7c5f8df4558e6a --- /dev/null +++ b/Doc/howto/a-conceptual-overview-of-asyncio.rst @@ -0,0 +1,608 @@ +.. _a-conceptual-overview-of-asyncio: + +**************************************** +A Conceptual Overview of :mod:`!asyncio` +**************************************** + +This :ref:`HOWTO ` article seeks to help you build a sturdy mental +model of how :mod:`asyncio` fundamentally works, helping you understand the +how and why behind the recommended patterns. + +You might be curious about some key :mod:`!asyncio` concepts. +By the end of this article, you'll be able to comfortably answer these questions: + +- What's happening behind the scenes when an object is awaited? +- How does :mod:`!asyncio` differentiate between a task which doesn't need + CPU time (such as a network request or file read) as opposed to a task that + does (such as computing n-factorial)? +- How to write an asynchronous variant of an operation, such as + an async sleep or database request. + +.. seealso:: + + * The `guide `_ that inspired this HOWTO article, by Alexander Nordin. + * This in-depth `YouTube tutorial series `_ on + ``asyncio`` created by Python core team member, Łukasz Langa. + * `500 Lines or Less: A Web Crawler With asyncio Coroutines `_ by A. + Jesse Jiryu Davis and Guido van Rossum. + +-------------------------------------------- +A conceptual overview part 1: the high-level +-------------------------------------------- + +In part 1, we'll cover the main, high-level building blocks of :mod:`!asyncio`: +the event loop, coroutine functions, coroutine objects, tasks, and ``await``. + +========== +Event Loop +========== + +Everything in :mod:`!asyncio` happens relative to the event loop. +It's the star of the show. +It's like an orchestra conductor. +It's behind the scenes managing resources. +Some power is explicitly granted to it, but a lot of its ability to get things +done comes from the respect and cooperation of its worker bees. + +In more technical terms, the event loop contains a collection of jobs to be run. +Some jobs are added directly by you, and some indirectly by :mod:`!asyncio`. +The event loop takes a job from its backlog of work and invokes it (or "gives +it control"), similar to calling a function, and then that job runs. +Once it pauses or completes, it returns control to the event loop. +The event loop will then select another job from its pool and invoke it. +You can *roughly* think of the collection of jobs as a queue: jobs are added and +then processed one at a time, generally (but not always) in order. +This process repeats indefinitely, with the event loop cycling endlessly +onwards. +If there are no more jobs pending execution, the event loop is smart enough to +rest and avoid needlessly wasting CPU cycles, and will come back when there's +more work to be done. + +Effective execution relies on jobs sharing well and cooperating; a greedy job +could hog control and leave the other jobs to starve, rendering the overall +event loop approach rather useless. + +:: + + import asyncio + + # This creates an event loop and indefinitely cycles through + # its collection of jobs. + event_loop = asyncio.new_event_loop() + event_loop.run_forever() + +===================================== +Asynchronous functions and coroutines +===================================== + +This is a basic, boring Python function:: + + def hello_printer(): + print( + "Hi, I am a lowly, simple printer, though I have all I " + "need in life -- \nfresh paper and my dearly beloved octopus " + "partner in crime." + ) + +Calling a regular function invokes its logic or body:: + + >>> hello_printer() + Hi, I am a lowly, simple printer, though I have all I need in life -- + fresh paper and my dearly beloved octopus partner in crime. + +The :ref:`async def `, as opposed to just a plain ``def``, makes +this an asynchronous function (or "coroutine function"). +Calling it creates and returns a :ref:`coroutine ` object. + +:: + + async def loudmouth_penguin(magic_number: int): + print( + "I am a super special talking penguin. Far cooler than that printer. " + f"By the way, my lucky number is: {magic_number}." + ) + +Calling the async function, ``loudmouth_penguin``, does not execute the print statement; +instead, it creates a coroutine object:: + + >>> loudmouth_penguin(magic_number=3) + + +The terms "coroutine function" and "coroutine object" are often conflated +as coroutine. +That can be confusing! +In this article, coroutine specifically refers to a coroutine object, or more +precisely, an instance of :class:`types.CoroutineType` (native coroutine). +Note that coroutines can also exist as instances of +:class:`collections.abc.Coroutine` -- a distinction that matters for type +checking. + +A coroutine represents the function's body or logic. +A coroutine has to be explicitly started; again, merely creating the coroutine +does not start it. +Notably, the coroutine can be paused and resumed at various points within the +function's body. +That pausing and resuming ability is what allows for asynchronous behavior! + +Coroutines and coroutine functions were built by leveraging the functionality +of :term:`generators ` and +:term:`generator functions `. +Recall, a generator function is a function that :keyword:`yield`\s, like this +one:: + + def get_random_number(): + # This would be a bad random number generator! + print("Hi") + yield 1 + print("Hello") + yield 7 + print("Howdy") + yield 4 + ... + +Similar to a coroutine function, calling a generator function does not run it. +Instead, it creates a generator object:: + + >>> get_random_number() + + +You can proceed to the next ``yield`` of a generator by using the +built-in function :func:`next`. +In other words, the generator runs, then pauses. +For example:: + + >>> generator = get_random_number() + >>> next(generator) + Hi + 1 + >>> next(generator) + Hello + 7 + +===== +Tasks +===== + +Roughly speaking, :ref:`tasks ` are coroutines (not coroutine +functions) tied to an event loop. +A task also maintains a list of callback functions whose importance will become +clear in a moment when we discuss :keyword:`await`. +The recommended way to create tasks is via :func:`asyncio.create_task`. + +Creating a task automatically schedules it for execution (by adding a +callback to run it in the event loop's to-do list, that is, collection of jobs). + +:mod:`!asyncio` automatically associates tasks with the event loop for you. +This automatic association was purposely designed into :mod:`!asyncio` for +the sake of simplicity. +Without it, you'd have to keep track of the event loop object and pass it to +any coroutine function that wants to create tasks, adding redundant clutter +to your code. + +:: + + coroutine = loudmouth_penguin(magic_number=5) + # This creates a Task object and schedules its execution via the event loop. + task = asyncio.create_task(coroutine) + +Earlier, we manually created the event loop and set it to run forever. +In practice, it's recommended to use (and common to see) :func:`asyncio.run`, +which takes care of managing the event loop and ensuring the provided +coroutine finishes before advancing. +For example, many async programs follow this setup:: + + import asyncio + + async def main(): + # Perform all sorts of wacky, wild asynchronous things... + ... + + if __name__ == "__main__": + asyncio.run(main()) + # The program will not reach the following print statement until the + # coroutine main() finishes. + print("coroutine main() is done!") + +It's important to be aware that the task itself is not added to the event loop, +only a callback to the task is. +This matters if the task object you created is garbage collected before it's +called by the event loop. +For example, consider this program: + +.. code-block:: + :linenos: + + async def hello(): + print("hello!") + + async def main(): + asyncio.create_task(hello()) + # Other asynchronous instructions which run for a while + # and cede control to the event loop... + ... + + asyncio.run(main()) + +Because there's no reference to the task object created on line 5, it *might* +be garbage collected before the event loop invokes it. +Later instructions in the coroutine ``main()`` hand control back to the event +loop so it can invoke other jobs. +When the event loop eventually tries to run the task, it might fail and +discover the task object does not exist! +This can also happen even if a coroutine keeps a reference to a task but +completes before that task finishes. +When the coroutine exits, local variables go out of scope and may be subject +to garbage collection. +In practice, ``asyncio`` and Python's garbage collector work pretty hard to +ensure this sort of thing doesn't happen. +But that's no reason to be reckless! + +===== +await +===== + +:keyword:`await` is a Python keyword that's commonly used in one of two +different ways:: + + await task + await coroutine + +In a crucial way, the behavior of ``await`` depends on the type of object +being awaited. + +Awaiting a task will cede control from the current task or coroutine to +the event loop. +In the process of relinquishing control, a few important things happen. +We'll use the following code example to illustrate:: + + async def plant_a_tree(): + dig_the_hole_task = asyncio.create_task(dig_the_hole()) + await dig_the_hole_task + + # Other instructions associated with planting a tree. + ... + +In this example, imagine the event loop has passed control to the start of the +coroutine ``plant_a_tree()``. +As seen above, the coroutine creates a task and then awaits it. +The ``await dig_the_hole_task`` instruction adds a callback (which will resume +``plant_a_tree()``) to the ``dig_the_hole_task`` object's list of callbacks. +And then, the instruction cedes control to the event loop. +Some time later, the event loop will pass control to ``dig_the_hole_task`` +and the task will finish whatever it needs to do. +Once the task finishes, it will add its various callbacks to the event loop, +in this case, a call to resume ``plant_a_tree()``. + +Generally speaking, when the awaited task finishes (``dig_the_hole_task``), +the original task or coroutine (``plant_a_tree()``) is added back to the event +loop's to-do list to be resumed. + +This is a basic, yet reliable mental model. +In practice, the control handoffs are slightly more complex, but not by much. +In part 2, we'll walk through the details that make this possible. + +**Unlike tasks, awaiting a coroutine does not hand control back to the event +loop!** +Wrapping a coroutine in a task first, then awaiting that would cede +control. +The behavior of ``await coroutine`` is effectively the same as invoking a +regular, synchronous Python function. +Consider this program:: + + import asyncio + + async def coro_a(): + print("I am coro_a(). Hi!") + + async def coro_b(): + print("I am coro_b(). I sure hope no one hogs the event loop...") + + async def main(): + task_b = asyncio.create_task(coro_b()) + num_repeats = 3 + for _ in range(num_repeats): + await coro_a() + await task_b + + asyncio.run(main()) + +The first statement in the coroutine ``main()`` creates ``task_b`` and schedules +it for execution via the event loop. +Then, ``coro_a()`` is repeatedly awaited. Control never cedes to the +event loop, which is why we see the output of all three ``coro_a()`` +invocations before ``coro_b()``'s output: + +.. code-block:: none + + I am coro_a(). Hi! + I am coro_a(). Hi! + I am coro_a(). Hi! + I am coro_b(). I sure hope no one hogs the event loop... + +If we change ``await coro_a()`` to ``await asyncio.create_task(coro_a())``, the +behavior changes. +The coroutine ``main()`` cedes control to the event loop with that statement. +The event loop then proceeds through its backlog of work, calling ``task_b`` +and then the task which wraps ``coro_a()`` before resuming the coroutine +``main()``. + +.. code-block:: none + + I am coro_b(). I sure hope no one hogs the event loop... + I am coro_a(). Hi! + I am coro_a(). Hi! + I am coro_a(). Hi! + +This behavior of ``await coroutine`` can trip a lot of people up! +That example highlights how using only ``await coroutine`` could +unintentionally hog control from other tasks and effectively stall the event +loop. +:func:`asyncio.run` can help you detect such occurrences via the +``debug=True`` flag, which enables +:ref:`debug mode `. +Among other things, it will log any coroutines that monopolize execution for +100ms or longer. + +The design intentionally trades off some conceptual clarity around usage of +``await`` for improved performance. +Each time a task is awaited, control needs to be passed all the way up the +call stack to the event loop. +That might sound minor, but in a large program with many ``await`` statements and a deep +call stack, that overhead can add up to a meaningful performance drag. + +------------------------------------------------ +A conceptual overview part 2: the nuts and bolts +------------------------------------------------ + +Part 2 goes into detail on the mechanisms :mod:`!asyncio` uses to manage +control flow. +This is where the magic happens. +You'll come away from this section knowing what ``await`` does behind the scenes +and how to make your own asynchronous operators. + +================================ +The inner workings of coroutines +================================ + +:mod:`!asyncio` leverages four components to pass around control. + +:meth:`coroutine.send(arg) ` is the method used to start or +resume a coroutine. +If the coroutine was paused and is now being resumed, the argument ``arg`` +will be sent in as the return value of the ``yield`` statement which originally +paused it. +If the coroutine is being used for the first time (as opposed to being resumed), +``arg`` must be ``None``. + +.. code-block:: + :linenos: + + class Rock: + def __await__(self): + value_sent_in = yield 7 + print(f"Rock.__await__ resuming with value: {value_sent_in}.") + return value_sent_in + + async def main(): + print("Beginning coroutine main().") + rock = Rock() + print("Awaiting rock...") + value_from_rock = await rock + print(f"Coroutine received value: {value_from_rock} from rock.") + return 23 + + coroutine = main() + intermediate_result = coroutine.send(None) + print(f"Coroutine paused and returned intermediate value: {intermediate_result}.") + + print(f"Resuming coroutine and sending in value: 42.") + try: + coroutine.send(42) + except StopIteration as e: + returned_value = e.value + print(f"Coroutine main() finished and provided value: {returned_value}.") + +:ref:`yield `, as usual, pauses execution and returns control +to the caller. +In the example above, the ``yield``, on line 3, is called by +``... = await rock`` on line 11. +More broadly speaking, ``await`` calls the :meth:`~object.__await__` method of +the given object. +``await`` also does one more very special thing: it propagates (or "passes +along") any ``yield``\ s it receives up the call chain. +In this case, that's back to ``... = coroutine.send(None)`` on line 16. + +The coroutine is resumed via the ``coroutine.send(42)`` call on line 21. +The coroutine picks back up from where it ``yield``\ ed (or paused) on line 3 +and executes the remaining statements in its body. +When a coroutine finishes, it raises a :exc:`StopIteration` exception with the +return value attached in the :attr:`~StopIteration.value` attribute. + +That snippet produces this output: + +.. code-block:: none + + Beginning coroutine main(). + Awaiting rock... + Coroutine paused and returned intermediate value: 7. + Resuming coroutine and sending in value: 42. + Rock.__await__ resuming with value: 42. + Coroutine received value: 42 from rock. + Coroutine main() finished and provided value: 23. + +It's worth pausing for a moment here and making sure you followed the various +ways that control flow and values were passed. A lot of important ideas were +covered and it's worth ensuring your understanding is firm. + +The only way to yield (or effectively cede control) from a coroutine is to +``await`` an object that ``yield``\ s in its ``__await__`` method. +That might sound odd to you. You might be thinking: + + 1. What about a ``yield`` directly within the coroutine function? The + coroutine function becomes an + :ref:`async generator function `, a + different beast entirely. + + 2. What about a :ref:`yield from ` within the coroutine function to a (plain) + generator? + That causes the error: ``SyntaxError: yield from not allowed in a coroutine.`` + This was intentionally designed for the sake of simplicity -- mandating only + one way of using coroutines. + Initially ``yield`` was barred as well, but was re-accepted to allow for + async generators. + Despite that, ``yield from`` and ``await`` effectively do the same thing. + +======= +Futures +======= + +A :ref:`future ` is an object meant to represent a +computation's status and result. +The term is a nod to the idea of something still to come or not yet happened, +and the object is a way to keep an eye on that something. + +A future has a few important attributes. One is its state, which can be either +"pending", "cancelled", or "done". +Another is its result, which is set when the state transitions to done. +Unlike a coroutine, a future does not represent the actual computation to be +done; instead, it represents the status and result of that computation, kind of +like a status light (red, yellow, or green) or indicator. + +:class:`asyncio.Task` subclasses :class:`asyncio.Future` in order to gain +these various capabilities. +The prior section said tasks store a list of callbacks, which wasn't entirely +accurate. +It's actually the ``Future`` class that implements this logic, which ``Task`` +inherits. + +Futures may also be used directly (not via tasks). +Tasks mark themselves as done when their coroutine is complete. +Futures are much more versatile and will be marked as done when you say so. +In this way, they're the flexible interface for you to make your own conditions +for waiting and resuming. + +======================== +A homemade asyncio.sleep +======================== + +We'll go through an example of how you could leverage a future to create your +own variant of asynchronous sleep (``async_sleep``) which mimics +:func:`asyncio.sleep`. + +This snippet registers a few tasks with the event loop and then awaits the task +created by ``asyncio.create_task``, which wraps the ``async_sleep(3)`` coroutine. +We want that task to finish only after three seconds have elapsed, but without +preventing other tasks from running. + +:: + + async def other_work(): + print("I like work. Work work.") + + async def main(): + # Add a few other tasks to the event loop, so there's something + # to do while asynchronously sleeping. + work_tasks = [ + asyncio.create_task(other_work()), + asyncio.create_task(other_work()), + asyncio.create_task(other_work()) + ] + print( + "Beginning asynchronous sleep at time: " + f"{datetime.datetime.now().strftime("%H:%M:%S")}." + ) + await asyncio.create_task(async_sleep(3)) + print( + "Done asynchronous sleep at time: " + f"{datetime.datetime.now().strftime("%H:%M:%S")}." + ) + # asyncio.gather effectively awaits each task in the collection. + await asyncio.gather(*work_tasks) + + +Below, we use a future to enable custom control over when that task will be +marked as done. +If :meth:`future.set_result() ` (the method +responsible for marking that future as done) is never called, then this task +will never finish. +We've also enlisted the help of another task, which we'll see in a moment, that +will monitor how much time has elapsed and, accordingly, call +``future.set_result()``. + +:: + + async def async_sleep(seconds: float): + future = asyncio.Future() + time_to_wake = time.time() + seconds + # Add the watcher-task to the event loop. + watcher_task = asyncio.create_task(_sleep_watcher(future, time_to_wake)) + # Block until the future is marked as done. + await future + +Below, we use a rather bare ``YieldToEventLoop()`` object to ``yield`` +from its ``__await__`` method, ceding control to the event loop. +This is effectively the same as calling ``asyncio.sleep(0)``, but this approach +offers more clarity, not to mention it's somewhat cheating to use +``asyncio.sleep`` when showcasing how to implement it! + +As usual, the event loop cycles through its tasks, giving them control +and receiving control back when they pause or finish. +The ``watcher_task``, which runs the coroutine ``_sleep_watcher(...)``, will +be invoked once per full cycle of the event loop. +On each resumption, it'll check the time and if not enough has elapsed, then +it'll pause once again and hand control back to the event loop. +Once enough time has elapsed, ``_sleep_watcher(...)`` +marks the future as done and completes by exiting its +infinite ``while`` loop. +Given this helper task is only invoked once per cycle of the event loop, +you'd be correct to note that this asynchronous sleep will sleep *at least* +three seconds, rather than exactly three seconds. +Note this is also true of ``asyncio.sleep``. + +:: + + class YieldToEventLoop: + def __await__(self): + yield + + async def _sleep_watcher(future, time_to_wake): + while True: + if time.time() >= time_to_wake: + # This marks the future as done. + future.set_result(None) + break + else: + await YieldToEventLoop() + +Here is the full program's output: + +.. code-block:: none + + $ python custom-async-sleep.py + Beginning asynchronous sleep at time: 14:52:22. + I like work. Work work. + I like work. Work work. + I like work. Work work. + Done asynchronous sleep at time: 14:52:25. + +You might feel this implementation of asynchronous sleep was unnecessarily +convoluted. +And, well, it was. +The example was meant to showcase the versatility of futures with a simple +example that could be mimicked for more complex needs. +For reference, you could implement it without futures, like so:: + + async def simpler_async_sleep(seconds): + time_to_wake = time.time() + seconds + while True: + if time.time() >= time_to_wake: + return + else: + await YieldToEventLoop() + +But that's all for now. Hopefully you're ready to more confidently dive into +some async programming or check out advanced topics in the +:mod:`rest of the documentation `. diff --git a/Doc/howto/annotations.rst b/Doc/howto/annotations.rst index 78f3704ba5d000..e2a5aa708d7b63 100644 --- a/Doc/howto/annotations.rst +++ b/Doc/howto/annotations.rst @@ -154,7 +154,7 @@ on an arbitrary object ``o``: as the ``globals``, and ``dict(vars(o))`` as the ``locals``, when calling :func:`eval`. * If ``o`` is a wrapped callable using :func:`functools.update_wrapper`, - :func:`functools.wraps`, or :func:`functools.partial`, iteratively + :deco:`functools.wraps`, or :func:`functools.partial`, iteratively unwrap it by accessing either ``o.__wrapped__`` or ``o.func`` as appropriate, until you have found the root unwrapped function. * If ``o`` is a callable (but not a class), use @@ -248,4 +248,9 @@ quirks by using :func:`annotationlib.get_annotations` on Python 3.14+ or :func:`inspect.get_annotations` on Python 3.10+. On earlier versions of Python, you can avoid these bugs by accessing the annotations from the class's :attr:`~type.__dict__` -(e.g., ``cls.__dict__.get('__annotations__', None)``). +(for example, ``cls.__dict__.get('__annotations__', None)``). + +In some versions of Python, instances of classes may have an ``__annotations__`` +attribute. However, this is not supported functionality. If you need the +annotations of an instance, you can use :func:`type` to access its class +(for example, ``annotationlib.get_annotations(type(myinstance))`` on Python 3.14+). diff --git a/Doc/howto/cporting.rst b/Doc/howto/cporting.rst index 7773620b40b973..cf857aed0425ec 100644 --- a/Doc/howto/cporting.rst +++ b/Doc/howto/cporting.rst @@ -14,13 +14,11 @@ We recommend the following resources for porting extension modules to Python 3: module. * The `Porting guide`_ from the *py3c* project provides opinionated suggestions with supporting code. -* The `Cython`_ and `CFFI`_ libraries offer abstractions over - Python's C API. +* :ref:`Recommended third party tools ` offer abstractions over + the Python's C API. Extensions generally need to be re-written to use one of them, but the library then handles differences between various Python versions and implementations. .. _Migrating C extensions: http://python3porting.com/cextensions.html .. _Porting guide: https://py3c.readthedocs.io/en/latest/guide.html -.. _Cython: https://cython.org/ -.. _CFFI: https://cffi.readthedocs.io/en/latest/ diff --git a/Doc/howto/curses.rst b/Doc/howto/curses.rst index 6994a5328e8149..7e8834161bc484 100644 --- a/Doc/howto/curses.rst +++ b/Doc/howto/curses.rst @@ -55,8 +55,8 @@ code, all the functions described here will probably be available. The older versions of curses carried by some proprietary Unixes may not support everything, though. -The Windows version of Python doesn't include the :mod:`curses` -module. A ported version called :pypi:`UniCurses` is available. +The Windows version of Python doesn't include the :mod:`curses` module. +The third-party :pypi:`windows-curses` package provides the same interface on Windows. The Python curses module diff --git a/Doc/howto/descriptor.rst b/Doc/howto/descriptor.rst index f6c3e473f1c36d..db854752f1a1f9 100644 --- a/Doc/howto/descriptor.rst +++ b/Doc/howto/descriptor.rst @@ -28,7 +28,7 @@ This guide has four major sections: 4) The last section has pure Python equivalents for built-in descriptors that are written in C. Read this if you're curious about how functions turn into bound methods or about the implementation of common tools like - :func:`classmethod`, :func:`staticmethod`, :func:`property`, and + :deco:`classmethod`, :deco:`staticmethod`, :deco:`property`, and :term:`__slots__`. @@ -317,8 +317,8 @@ Descriptors invert that relationship and allow the data being looked-up to have a say in the matter. Descriptors are used throughout the language. It is how functions turn into -bound methods. Common tools like :func:`classmethod`, :func:`staticmethod`, -:func:`property`, and :func:`functools.cached_property` are all implemented as +bound methods. Common tools like :deco:`classmethod`, :deco:`staticmethod`, +:deco:`property`, and :deco:`functools.cached_property` are all implemented as descriptors. @@ -420,7 +420,7 @@ Here are three practical data validation utilities: def validate(self, value): if not isinstance(value, str): - raise TypeError(f'Expected {value!r} to be an str') + raise TypeError(f'Expected {value!r} to be a str') if self.minsize is not None and len(value) < self.minsize: raise ValueError( f'Expected {value!r} to be no smaller than {self.minsize!r}' @@ -1326,7 +1326,7 @@ example calls are unexciting: 30 Using the non-data descriptor protocol, a pure Python version of -:func:`staticmethod` would look like this: +:deco:`staticmethod` would look like this: .. testcode:: @@ -1466,7 +1466,7 @@ Now a new dictionary of unique keys can be constructed like this: {'a': None, 'b': None, 'r': None, 'c': None, 'd': None} Using the non-data descriptor protocol, a pure Python version of -:func:`classmethod` would look like this: +:deco:`classmethod` would look like this: .. testcode:: @@ -1604,7 +1604,7 @@ matters when a large number of instances are going to be created. 4. Improves speed. Reading instance variables is 35% faster with ``__slots__`` (as measured with Python 3.10 on an Apple M1 processor). -5. Blocks tools like :func:`functools.cached_property` which require an +5. Blocks tools like :deco:`functools.cached_property` which require an instance dictionary to function correctly: .. testcode:: @@ -1640,7 +1640,7 @@ by member descriptors: class Member: def __init__(self, name, clsname, offset): - 'Emulate PyMemberDef in Include/structmember.h' + 'Emulate PyMemberDef in Include/descrobject.h' # Also see descr_new() in Objects/descrobject.c self.name = name self.clsname = clsname diff --git a/Doc/howto/enum.rst b/Doc/howto/enum.rst index 6441b7aed1eda8..4d1aafa6e69b90 100644 --- a/Doc/howto/enum.rst +++ b/Doc/howto/enum.rst @@ -105,8 +105,8 @@ The complete :class:`!Weekday` enum now looks like this:: Now we can find out what today is! Observe:: - >>> from datetime import date - >>> Weekday.from_date(date.today()) # doctest: +SKIP + >>> import datetime as dt + >>> Weekday.from_date(dt.date.today()) # doctest: +SKIP Of course, if you're reading this on some other day, you'll see that day instead. @@ -256,7 +256,7 @@ Ensuring unique enumeration values ---------------------------------- By default, enumerations allow multiple names as aliases for the same value. -When this behavior isn't desired, you can use the :func:`unique` decorator:: +When this behavior isn't desired, you can use the :deco:`unique` decorator:: >>> from enum import Enum, unique >>> @unique @@ -509,7 +509,7 @@ to use the standard :func:`repr`. .. note:: - Adding :func:`~dataclasses.dataclass` decorator to :class:`Enum` + Adding :deco:`~dataclasses.dataclass` decorator to :class:`Enum` and its subclasses is not supported. It will not raise any errors, but it will produce very strange results at runtime, such as members being equal to each other:: @@ -965,75 +965,16 @@ want one of them to be the value:: Finer Points -^^^^^^^^^^^^ - -Supported ``__dunder__`` names -"""""""""""""""""""""""""""""" - -:attr:`~enum.EnumType.__members__` is a read-only ordered mapping of ``member_name``:``member`` -items. It is only available on the class. - -:meth:`~object.__new__`, if specified, must create and return the enum members; it is -also a very good idea to set the member's :attr:`~Enum._value_` appropriately. Once -all the members are created it is no longer used. - - -Supported ``_sunder_`` names -"""""""""""""""""""""""""""" +------------ -- :attr:`~Enum._name_` -- name of the member -- :attr:`~Enum._value_` -- value of the member; can be set in ``__new__`` -- :meth:`~Enum._missing_` -- a lookup function used when a value is not found; - may be overridden -- :attr:`~Enum._ignore_` -- a list of names, either as a :class:`list` or a - :class:`str`, that will not be transformed into members, and will be removed - from the final class -- :meth:`~Enum._generate_next_value_` -- used to get an appropriate value for - an enum member; may be overridden -- :meth:`~EnumType._add_alias_` -- adds a new name as an alias to an existing - member. -- :meth:`~EnumType._add_value_alias_` -- adds a new value as an alias to an - existing member. See `MultiValueEnum`_ for an example. +Supported ``__dunder__`` and ``_sunder_`` names +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ - .. note:: - - For standard :class:`Enum` classes the next value chosen is the highest - value seen incremented by one. - - For :class:`Flag` classes the next value chosen will be the next highest - power-of-two. - - .. versionchanged:: 3.13 - Prior versions would use the last seen value instead of the highest value. - -.. versionadded:: 3.6 ``_missing_``, ``_order_``, ``_generate_next_value_`` -.. versionadded:: 3.7 ``_ignore_`` -.. versionadded:: 3.13 ``_add_alias_``, ``_add_value_alias_`` - -To help keep Python 2 / Python 3 code in sync an :attr:`~Enum._order_` attribute can -be provided. It will be checked against the actual order of the enumeration -and raise an error if the two do not match:: - - >>> class Color(Enum): - ... _order_ = 'RED GREEN BLUE' - ... RED = 1 - ... BLUE = 3 - ... GREEN = 2 - ... - Traceback (most recent call last): - ... - TypeError: member order does not match _order_: - ['RED', 'BLUE', 'GREEN'] - ['RED', 'GREEN', 'BLUE'] - -.. note:: - - In Python 2 code the :attr:`~Enum._order_` attribute is necessary as definition - order is lost before it can be recorded. +The supported ``__dunder__`` and ``_sunder_`` names can be found in the :ref:`Enum API documentation `. _Private__names -""""""""""""""" +^^^^^^^^^^^^^^^ :ref:`Private names ` are not converted to enum members, but remain normal attributes. @@ -1042,7 +983,7 @@ but remain normal attributes. ``Enum`` member type -"""""""""""""""""""" +^^^^^^^^^^^^^^^^^^^^ Enum members are instances of their enum class, and are normally accessed as ``EnumClass.member``. In certain situations, such as writing custom enum @@ -1055,7 +996,7 @@ recommended. Creating members that are mixed with other data types -""""""""""""""""""""""""""""""""""""""""""""""""""""" +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ When subclassing other data types, such as :class:`int` or :class:`str`, with an :class:`Enum`, all values after the ``=`` are passed to that data type's @@ -1069,7 +1010,7 @@ constructor. For example:: Boolean value of ``Enum`` classes and members -""""""""""""""""""""""""""""""""""""""""""""" +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Enum classes that are mixed with non-:class:`Enum` types (such as :class:`int`, :class:`str`, etc.) are evaluated according to the mixed-in @@ -1084,7 +1025,7 @@ Plain :class:`Enum` classes always evaluate as :data:`True`. ``Enum`` classes with methods -""""""""""""""""""""""""""""" +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ If you give your enum subclass extra methods, like the `Planet`_ class below, those methods will show up in a :func:`dir` of the member, @@ -1097,7 +1038,7 @@ but not of the class:: Combining members of ``Flag`` -""""""""""""""""""""""""""""" +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Iterating over a combination of :class:`Flag` members will only return the members that are comprised of a single bit:: @@ -1117,7 +1058,7 @@ are comprised of a single bit:: ``Flag`` and ``IntFlag`` minutia -"""""""""""""""""""""""""""""""" +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Using the following snippet for our examples:: @@ -1478,6 +1419,7 @@ alias:: behaviors as well as disallowing aliases. If the only desired change is disallowing aliases, the :func:`unique` decorator can be used instead. +.. _multi-value-enum: MultiValueEnum ^^^^^^^^^^^^^^^^^ @@ -1538,8 +1480,8 @@ TimePeriod An example to show the :attr:`~Enum._ignore_` attribute in use:: - >>> from datetime import timedelta - >>> class Period(timedelta, Enum): + >>> import datetime as dt + >>> class Period(dt.timedelta, Enum): ... "different lengths of time" ... _ignore_ = 'Period i' ... Period = vars() diff --git a/Doc/howto/free-threading-extensions.rst b/Doc/howto/free-threading-extensions.rst index 3f6ee517050bd8..43b8ff26ebde1a 100644 --- a/Doc/howto/free-threading-extensions.rst +++ b/Doc/howto/free-threading-extensions.rst @@ -6,8 +6,8 @@ C API Extension Support for Free Threading ****************************************** -Starting with the 3.13 release, CPython has experimental support for running -with the :term:`global interpreter lock` (GIL) disabled in a configuration +Starting with the 3.13 release, CPython has support for running with +the :term:`global interpreter lock` (GIL) disabled in a configuration called :term:`free threading`. This document describes how to adapt C API extensions to support free threading. @@ -23,6 +23,14 @@ You can use it to enable code that only runs under the free-threaded build:: /* code that only runs in the free-threaded build */ #endif +.. note:: + + On Windows, this macro is not defined automatically, but must be specified + to the compiler when building. The :func:`sysconfig.get_config_var` function + can be used to determine whether the current running interpreter had the + macro defined. + + Module Initialization ===================== @@ -153,6 +161,8 @@ that return :term:`strong references `. +===================================+===================================+ | :c:func:`PyList_GetItem` | :c:func:`PyList_GetItemRef` | +-----------------------------------+-----------------------------------+ +| :c:func:`PyList_GET_ITEM` | :c:func:`PyList_GetItemRef` | ++-----------------------------------+-----------------------------------+ | :c:func:`PyDict_GetItem` | :c:func:`PyDict_GetItemRef` | +-----------------------------------+-----------------------------------+ | :c:func:`PyDict_GetItemWithError` | :c:func:`PyDict_GetItemRef` | @@ -193,7 +203,7 @@ Memory Allocation APIs Python's memory management C API provides functions in three different :ref:`allocation domains `: "raw", "mem", and "object". For thread-safety, the free-threaded build requires that only Python objects -are allocated using the object domain, and that all Python object are +are allocated using the object domain, and that all Python objects are allocated using that domain. This differs from the prior Python versions, where this was only a best practice and not a hard requirement. @@ -334,12 +344,12 @@ This means you cannot rely on nested critical sections to lock multiple objects at once, as the inner critical section may suspend the outer ones. Instead, use :c:macro:`Py_BEGIN_CRITICAL_SECTION2` to lock two objects simultaneously. -Note that the locks described above are only :c:type:`!PyMutex` based locks. +Note that the locks described above are only :c:type:`PyMutex` based locks. The critical section implementation does not know about or affect other locking mechanisms that might be in use, like POSIX mutexes. Also note that while -blocking on any :c:type:`!PyMutex` causes the critical sections to be +blocking on any :c:type:`PyMutex` causes the critical sections to be suspended, only the mutexes that are part of the critical sections are -released. If :c:type:`!PyMutex` is used without a critical section, it will +released. If :c:type:`PyMutex` is used without a critical section, it will not be released and therefore does not get the same deadlock avoidance. Important Considerations @@ -385,10 +395,9 @@ C API extensions need to be built specifically for the free-threaded build. The wheels, shared libraries, and binaries are indicated by a ``t`` suffix. * `pypa/manylinux `_ supports the - free-threaded build, with the ``t`` suffix, such as ``python3.13t``. -* `pypa/cibuildwheel `_ supports the - free-threaded build if you set - `CIBW_FREE_THREADED_SUPPORT `_. + free-threaded build, with the ``t`` suffix, such as ``python3.14t``. +* `pypa/cibuildwheel `_ supports + building wheels for the free-threaded build of Python 3.14 and newer. Limited C API and Stable ABI ............................ diff --git a/Doc/howto/free-threading-python.rst b/Doc/howto/free-threading-python.rst index f7a894ac2cd78e..53bea1db191d76 100644 --- a/Doc/howto/free-threading-python.rst +++ b/Doc/howto/free-threading-python.rst @@ -1,18 +1,19 @@ .. _freethreading-python-howto: -********************************************** -Python experimental support for free threading -********************************************** +********************************* +Python support for free threading +********************************* -Starting with the 3.13 release, CPython has experimental support for a build of +Starting with the 3.13 release, CPython has support for a build of Python called :term:`free threading` where the :term:`global interpreter lock` (GIL) is disabled. Free-threaded execution allows for full utilization of the available processing power by running threads in parallel on available CPU cores. While not all software will benefit from this automatically, programs designed with threading in mind will run faster on multi-core hardware. -**The free-threaded mode is experimental** and work is ongoing to improve it: -expect some bugs and a substantial single-threaded performance hit. +Some third-party packages, in particular ones +with an :term:`extension module`, may not be ready for use in a +free-threaded build, and will re-enable the :term:`GIL`. This document describes the implications of free threading for Python code. See :ref:`freethreading-extensions-howto` for information on @@ -32,7 +33,7 @@ optionally support installing free-threaded Python binaries. The installers are available at https://www.python.org/downloads/. For information on other platforms, see the `Installing a Free-Threaded Python -`_, a +`_, a community-maintained installation guide for installing free-threaded Python. When building CPython from source, the :option:`--disable-gil` configure option @@ -43,7 +44,7 @@ Identifying free-threaded Python ================================ To check if the current interpreter supports free-threading, :option:`python -VV <-V>` -and :data:`sys.version` contain "experimental free-threading build". +and :data:`sys.version` contain "free-threading build". The new :func:`sys._is_gil_enabled` function can be used to check whether the GIL is actually disabled in the running process. @@ -98,60 +99,42 @@ This section describes known limitations of the free-threaded CPython build. Immortalization --------------- -The free-threaded build of the 3.13 release makes some objects :term:`immortal`. +In the free-threaded build, some objects are :term:`immortal`. Immortal objects are not deallocated and have reference counts that are never modified. This is done to avoid reference count contention that would prevent efficient multi-threaded scaling. -An object will be made immortal when a new thread is started for the first time -after the main thread is running. The following objects are immortalized: +As of the 3.14 release, immortalization is limited to: -* :ref:`function ` objects declared at the module level -* :ref:`method ` descriptors -* :ref:`code ` objects -* :term:`module` objects and their dictionaries -* :ref:`classes ` (type objects) - -Because immortal objects are never deallocated, applications that create many -objects of these types may see increased memory usage. This is expected to be -addressed in the 3.14 release. - -Additionally, numeric and string literals in the code as well as strings -returned by :func:`sys.intern` are also immortalized. This behavior is -expected to remain in the 3.14 free-threaded build. +* Code constants: numeric literals, string literals, and tuple literals + composed of other constants. +* Strings interned by :func:`sys.intern`. Frame objects ------------- -It is not safe to access :ref:`frame ` objects from other -threads and doing so may cause your program to crash . This means that -:func:`sys._current_frames` is generally not safe to use in a free-threaded -build. Functions like :func:`inspect.currentframe` and :func:`sys._getframe` -are generally safe as long as the resulting frame object is not passed to -another thread. +It is not safe to access :attr:`frame.f_locals` from a :ref:`frame ` +object if that frame is currently executing in another thread, and doing so may +crash the interpreter. + Iterators --------- -Sharing the same iterator object between multiple threads is generally not -safe and threads may see duplicate or missing elements when iterating or crash -the interpreter. +It is generally not thread-safe to access the same iterator object from +multiple threads concurrently, and threads may see duplicate or missing +elements. Single-threaded performance --------------------------- The free-threaded build has additional overhead when executing Python code -compared to the default GIL-enabled build. In 3.13, this overhead is about -40% on the `pyperformance `_ suite. -Programs that spend most of their time in C extensions or I/O will see -less of an impact. The largest impact is because the specializing adaptive -interpreter (:pep:`659`) is disabled in the free-threaded build. We expect -to re-enable it in a thread-safe way in the 3.14 release. This overhead is -expected to be reduced in upcoming Python release. We are aiming for an -overhead of 10% or less on the pyperformance suite compared to the default -GIL-enabled build. +compared to the default GIL-enabled build. The amount of overhead depends +on the workload and hardware. On the pyperformance benchmark suite, the +average overhead ranges from about 1% on macOS aarch64 to 8% on x86-64 Linux +systems. Behavioral changes @@ -182,3 +165,132 @@ to false. If the flag is true then the :class:`warnings.catch_warnings` context manager uses a context variable for warning filters. If the flag is false then :class:`~warnings.catch_warnings` modifies the global filters list, which is not thread-safe. See the :mod:`warnings` module for more details. + + +Increased memory usage +---------------------- + +The free-threaded build will typically use more memory compared to the default +build. There are multiple reasons for this, mostly due to design decisions. + + +All interned strings are immortal +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +For modern Python versions (since version 2.3), interning a string (e.g. with +:func:`sys.intern`) does not cause it to become immortal. Instead, if the last +reference to that string disappears, it will be removed from the interned +string table. This is not the case for the free-threaded build and any interned +string will become immortal, surviving until interpreter shutdown. + + +Non-GC objects have a larger object header +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +The free-threaded build uses a different :c:type:`PyObject` structure. Instead +of having the GC related information allocated before the :c:type:`PyObject` +structure, like in the default build, the GC related info is part of the normal +object header. For example, on the AMD64 platform, ``None`` uses 32 bytes on +the free-threaded build vs 16 bytes for the default build. GC objects (such as +dicts and lists) are the same size for both builds since the free-threaded +build does not use additional space for the GC info. + + +QSBR can delay freeing of memory +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +In order to safely implement lock-free data structures, a safe memory +reclamation (SMR) scheme is used, known as quiescent state-based reclamation +(QSBR). This means that the memory backing data structures allowing lock-free +access will use QSBR, which defers the free operation, rather than immediately +freeing the memory. Two examples of these data structures are the list object +and the dictionary keys object. See ``InternalDocs/qsbr.md`` in the CPython +source tree for more details on how QSBR is implemented. Running +:func:`gc.collect` should cause all memory being held by QSBR to be actually +freed. Note that even when QSBR frees the memory, the underlying memory +allocator may not immediately return that memory to the OS and so the resident +set size (RSS) of the process might not decrease. + + +mimalloc allocator vs pymalloc +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +The default build will normally use the "pymalloc" memory allocator for small +allocations (512 bytes or smaller). The free-threaded build does not use +pymalloc and allocates all Python objects using the "mimalloc" allocator. The +pymalloc allocator has the following properties that help keep memory usage +low: small per-allocated-block overhead, effective memory fragmentation +prevention, and quick return of free memory to the operating system. The +mimalloc allocator does quite well in these respects as well but can have some +more overhead. + +In the free-threaded build, mimalloc manages memory in a number of separate +heaps (currently four). For example, all GC supporting objects are allocated +from their own heap. Using separate heaps means that free memory in one heap +cannot be used for an allocation that uses another heap. Also, some heaps are +configured to use QSBR (quiescent-state based reclamation) when freeing the +memory that backs up the heap (known as "pages" in mimalloc terminology). The +use of QSBR creates a delay between all memory blocks for a page being freed +and the memory page being released, either for new allocations or back to the +OS. + +The mimalloc allocator also defers returning freed memory back to the OS. You +can reduce that delay by setting the environment variable +:envvar:`!MIMALLOC_PURGE_DELAY` to ``0``. Note that this will likely reduce +the performance of the allocator. + + +Free-threaded reference counting can cause objects to live longer +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +In the default build, when an object's reference count reaches zero, it is +normally deallocated. The free-threaded build uses "biased reference +counting", with a fast-path for objects "owned" by the current thread and a +slow path for other objects. See :pep:`703` for additional details. Any time +an object's reference count ends up in a "queued" state, deallocation can be +deferred. The queued state is cleared from the "eval breaker" section of the +bytecode evaluator. + +The free-threaded build also allows a different mode of reference counting, +known as "deferred reference counting". This mode is enabled by setting a flag +on a per-object basis. Deferred reference counting is enabled for the +following types: + +* module objects +* module top-level functions +* class methods defined in the class scope +* descriptor objects +* thread-local objects, created by :class:`threading.local` + +When deferred reference counting is enabled, references from Python function +stacks are not added to the reference count. This scheme reduces the overhead +of reference counting, especially for objects used from multiple threads. +Because the stack references are not counted, objects with deferred reference +counting are not immediately freed when their internal reference count goes to +zero. Instead, they are examined by the next GC run and, if no stack +references to them are found, they are freed. This means these objects are +freed by the GC and not when their reference count goes to zero, as is typical. + + +Per-thread reference counting can delay freeing objects +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +To avoid contention on the reference count fields of frequently shared +objects, the free-threaded build also uses "per-thread reference counting" +for a few selected object types. Rather than updating a single shared +reference count, each thread maintains its own local reference count array, +indexed by a unique id assigned to the object. The true reference count is +only computed by summing the per-thread counts when the object's local +count drops to zero. Per-thread reference counting is currently used for: + +* heap type objects (classes created in Python) +* code objects +* the ``__dict__`` of module objects + +Because the per-thread counts must be merged back to the object before it +can be deallocated, objects using per-thread reference counting are +typically freed later than they would be in the default build. In +particular, such an object is usually not freed until the thread that +referenced it reaches a safe point (for example, in the "eval breaker" +section of the bytecode evaluator) or exits. Running :func:`gc.collect` +will merge the per-thread counts and allow these objects to be freed. diff --git a/Doc/howto/functional.rst b/Doc/howto/functional.rst index 1f0608fb0fc53f..b78be3bbfbfed9 100644 --- a/Doc/howto/functional.rst +++ b/Doc/howto/functional.rst @@ -4,7 +4,7 @@ Functional Programming HOWTO ******************************** -:Author: A. M. Kuchling +:Author: \A. M. Kuchling :Release: 0.32 In this document, we'll take a tour of Python's features suitable for @@ -602,7 +602,7 @@ generators: raise an exception inside the generator; the exception is raised by the ``yield`` expression where the generator's execution is paused. -* :meth:`~generator.close` raises a :exc:`GeneratorExit` exception inside the +* :meth:`~generator.close` sends a :exc:`GeneratorExit` exception to the generator to terminate the iteration. On receiving this exception, the generator's code must either raise :exc:`GeneratorExit` or :exc:`StopIteration`; catching the exception and doing anything else is @@ -1042,7 +1042,7 @@ first calculation. :: >>> functools.reduce(operator.concat, []) Traceback (most recent call last): ... - TypeError: reduce() of empty sequence with no initial value + TypeError: reduce() of empty iterable with no initial value >>> functools.reduce(operator.mul, [1, 2, 3], 1) 6 >>> functools.reduce(operator.mul, [], 1) @@ -1217,7 +1217,7 @@ flow inside a program. The book uses Scheme for its examples, but many of the design approaches described in these chapters are applicable to functional-style Python code. -https://www.defmacro.org/ramblings/fp.html: A general introduction to functional +https://defmacro.org/2006/06/19/fp.html: A general introduction to functional programming that uses Java examples and has a lengthy historical introduction. https://en.wikipedia.org/wiki/Functional_programming: General Wikipedia entry diff --git a/Doc/howto/index.rst b/Doc/howto/index.rst index f350141004c2db..81fc7e63f35bd7 100644 --- a/Doc/howto/index.rst +++ b/Doc/howto/index.rst @@ -1,3 +1,5 @@ +.. _how-tos: + *************** Python HOWTOs *************** @@ -11,6 +13,7 @@ Python Library Reference. :maxdepth: 1 :hidden: + a-conceptual-overview-of-asyncio.rst cporting.rst curses.rst descriptor.rst @@ -38,6 +41,7 @@ Python Library Reference. General: +* :ref:`a-conceptual-overview-of-asyncio` * :ref:`annotations-howto` * :ref:`argparse-tutorial` * :ref:`descriptorhowto` diff --git a/Doc/howto/instrumentation.rst b/Doc/howto/instrumentation.rst index 6e03ef20a21fa3..06c1ae40da5e67 100644 --- a/Doc/howto/instrumentation.rst +++ b/Doc/howto/instrumentation.rst @@ -269,6 +269,8 @@ should instead read: (assuming a :ref:`debug build ` of CPython 3.6) +.. _static-markers: + Available static markers ------------------------ @@ -339,6 +341,84 @@ Available static markers .. versionadded:: 3.8 +C Entry Points +^^^^^^^^^^^^^^ + +To simplify triggering of DTrace markers, Python's C API comes with a number +of helper functions that mirror each static marker. On builds of Python without +DTrace enabled, these do nothing. + +In general, it is not necessary to call these yourself, as Python will do +it for you. + +.. list-table:: + :widths: 50 25 25 + :header-rows: 1 + + * * C API Function + * Static Marker + * Notes + * * .. c:function:: void PyDTrace_LINE(const char *arg0, const char *arg1, int arg2) + * :c:func:`!line` + * + * * .. c:function:: void PyDTrace_FUNCTION_ENTRY(const char *arg0, const char *arg1, int arg2) + * :c:func:`!function__entry` + * + * * .. c:function:: void PyDTrace_FUNCTION_RETURN(const char *arg0, const char *arg1, int arg2) + * :c:func:`!function__return` + * + * * .. c:function:: void PyDTrace_GC_START(int arg0) + * :c:func:`!gc__start` + * + * * .. c:function:: void PyDTrace_GC_DONE(Py_ssize_t arg0) + * :c:func:`!gc__done` + * + * * .. c:function:: void PyDTrace_INSTANCE_NEW_START(int arg0) + * :c:func:`!instance__new__start` + * Not used by Python + * * .. c:function:: void PyDTrace_INSTANCE_NEW_DONE(int arg0) + * :c:func:`!instance__new__done` + * Not used by Python + * * .. c:function:: void PyDTrace_INSTANCE_DELETE_START(int arg0) + * :c:func:`!instance__delete__start` + * Not used by Python + * * .. c:function:: void PyDTrace_INSTANCE_DELETE_DONE(int arg0) + * :c:func:`!instance__delete__done` + * Not used by Python + * * .. c:function:: void PyDTrace_IMPORT_FIND_LOAD_START(const char *arg0) + * :c:func:`!import__find__load__start` + * + * * .. c:function:: void PyDTrace_IMPORT_FIND_LOAD_DONE(const char *arg0, int arg1) + * :c:func:`!import__find__load__done` + * + * * .. c:function:: void PyDTrace_AUDIT(const char *arg0, void *arg1) + * :c:func:`!audit` + * + + +C Probing Checks +^^^^^^^^^^^^^^^^ + +.. c:function:: int PyDTrace_LINE_ENABLED(void) +.. c:function:: int PyDTrace_FUNCTION_ENTRY_ENABLED(void) +.. c:function:: int PyDTrace_FUNCTION_RETURN_ENABLED(void) +.. c:function:: int PyDTrace_GC_START_ENABLED(void) +.. c:function:: int PyDTrace_GC_DONE_ENABLED(void) +.. c:function:: int PyDTrace_INSTANCE_NEW_START_ENABLED(void) +.. c:function:: int PyDTrace_INSTANCE_NEW_DONE_ENABLED(void) +.. c:function:: int PyDTrace_INSTANCE_DELETE_START_ENABLED(void) +.. c:function:: int PyDTrace_INSTANCE_DELETE_DONE_ENABLED(void) +.. c:function:: int PyDTrace_IMPORT_FIND_LOAD_START_ENABLED(void) +.. c:function:: int PyDTrace_IMPORT_FIND_LOAD_DONE_ENABLED(void) +.. c:function:: int PyDTrace_AUDIT_ENABLED(void) + + All calls to ``PyDTrace`` functions must be guarded by a call to one + of these functions. This allows Python to minimize performance impact + when probing is disabled. + + On builds without DTrace enabled, these functions do nothing and return + ``0``. + SystemTap Tapsets ----------------- diff --git a/Doc/howto/isolating-extensions.rst b/Doc/howto/isolating-extensions.rst index a636e06bda8344..6092c75f48fdef 100644 --- a/Doc/howto/isolating-extensions.rst +++ b/Doc/howto/isolating-extensions.rst @@ -168,7 +168,7 @@ possible, consider explicit locking. If it is necessary to use process-global state, the simplest way to avoid issues with multiple interpreters is to explicitly prevent a module from being loaded more than once per process—see -`Opt-Out: Limiting to One Module Object per Process`_. +:ref:`isolating-extensions-optout`. Managing Per-Module State @@ -207,6 +207,8 @@ An example of a module with per-module state is currently available as example module initialization shown at the bottom of the file. +.. _isolating-extensions-optout: + Opt-Out: Limiting to One Module Object per Process -------------------------------------------------- @@ -215,21 +217,36 @@ multiple interpreters correctly. If this is not yet the case for your module, you can explicitly make your module loadable only once per process. For example:: + // A process-wide flag static int loaded = 0; + // Mutex to provide thread safety (only needed for free-threaded Python) + static PyMutex modinit_mutex = {0}; + static int exec_module(PyObject* module) { + PyMutex_Lock(&modinit_mutex); if (loaded) { + PyMutex_Unlock(&modinit_mutex); PyErr_SetString(PyExc_ImportError, "cannot load module more than once per process"); return -1; } loaded = 1; + PyMutex_Unlock(&modinit_mutex); // ... rest of initialization } +If your module's :c:member:`PyModuleDef.m_clear` function is able to prepare +for future re-initialization, it should clear the ``loaded`` flag. +In this case, your module won't support multiple instances existing +*concurrently*, but it will, for example, support being loaded after +Python runtime shutdown (:c:func:`Py_FinalizeEx`) and re-initialization +(:c:func:`Py_Initialize`). + + Module State Access from Functions ---------------------------------- @@ -336,7 +353,7 @@ garbage collection protocol. That is, heap types should: - Have the :c:macro:`Py_TPFLAGS_HAVE_GC` flag. -- Define a traverse function using ``Py_tp_traverse``, which +- Define a traverse function using :c:data:`Py_tp_traverse`, which visits the type (e.g. using ``Py_VISIT(Py_TYPE(self))``). Please refer to the documentation of @@ -436,7 +453,7 @@ Avoiding ``PyObject_New`` GC-tracked objects need to be allocated using GC-aware functions. -If you use use :c:func:`PyObject_New` or :c:func:`PyObject_NewVar`: +If you use :c:func:`PyObject_New` or :c:func:`PyObject_NewVar`: - Get and call type's :c:member:`~PyTypeObject.tp_alloc` slot, if possible. That is, replace ``TYPE *o = PyObject_New(TYPE, typeobj)`` with:: @@ -609,8 +626,7 @@ Open Issues Several issues around per-module state and heap types are still open. -Discussions about improving the situation are best held on the `capi-sig -mailing list `__. +Discussions about improving the situation are best held on the `discuss forum under c-api tag `__. Per-Class Scope diff --git a/Doc/howto/logging-cookbook.rst b/Doc/howto/logging-cookbook.rst index 7d64a02358adb3..39a7b41c755097 100644 --- a/Doc/howto/logging-cookbook.rst +++ b/Doc/howto/logging-cookbook.rst @@ -229,7 +229,7 @@ messages should not. Here's how you can achieve this:: # tell the handler to use this format console.setFormatter(formatter) # add the handler to the root logger - logging.getLogger('').addHandler(console) + logging.getLogger().addHandler(console) # Now, we can log to the root logger, or any other logger. First the root... logging.info('Jackdaws love my big sphinx of quartz.') @@ -650,7 +650,7 @@ the receiving end. A simple way of doing this is attaching a import logging, logging.handlers - rootLogger = logging.getLogger('') + rootLogger = logging.getLogger() rootLogger.setLevel(logging.DEBUG) socketHandler = logging.handlers.SocketHandler('localhost', logging.handlers.DEFAULT_TCP_LOGGING_PORT) @@ -1549,10 +1549,10 @@ to this (remembering to first import :mod:`concurrent.futures`):: for i in range(10): executor.submit(worker_process, queue, worker_configurer) -Deploying Web applications using Gunicorn and uWSGI +Deploying web applications using Gunicorn and uWSGI ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -When deploying Web applications using `Gunicorn `_ or `uWSGI +When deploying web applications using `Gunicorn `_ or `uWSGI `_ (or similar), multiple worker processes are created to handle client requests. In such environments, avoid creating file-based handlers directly in your web application. Instead, use a @@ -1960,7 +1960,7 @@ Subclass ``QueueListener`` class NNGSocketListener(logging.handlers.QueueListener): def __init__(self, uri, /, *handlers, **kwargs): - # Have a timeout for interruptability, and open a + # Have a timeout for interruptibility, and open a # subscriber socket socket = pynng.Sub0(listen=uri, recv_timeout=500) # The b'' subscription matches all topics @@ -3619,7 +3619,6 @@ detailed information. .. code-block:: python3 - import datetime import logging import random import sys @@ -3854,7 +3853,7 @@ Logging to syslog with RFC5424 support Although :rfc:`5424` dates from 2009, most syslog servers are configured by default to use the older :rfc:`3164`, which hails from 2001. When ``logging`` was added to Python in 2003, it supported the earlier (and only existing) protocol at the time. Since -RFC5424 came out, as there has not been widespread deployment of it in syslog +RFC 5424 came out, as there has not been widespread deployment of it in syslog servers, the :class:`~logging.handlers.SysLogHandler` functionality has not been updated. @@ -3862,7 +3861,7 @@ RFC 5424 contains some useful features such as support for structured data, and need to be able to log to a syslog server with support for it, you can do so with a subclassed handler which looks something like this:: - import datetime + import datetime as dt import logging.handlers import re import socket @@ -3880,7 +3879,7 @@ subclassed handler which looks something like this:: def format(self, record): version = 1 - asctime = datetime.datetime.fromtimestamp(record.created).isoformat() + asctime = dt.datetime.fromtimestamp(record.created).isoformat() m = self.tz_offset.match(time.strftime('%z')) has_offset = False if m and time.timezone: @@ -4078,6 +4077,104 @@ lines. With this approach, you get better output: WARNING:demo: 1/0 WARNING:demo:ZeroDivisionError: division by zero +How to uniformly handle newlines in logging output +-------------------------------------------------- + +Usually, messages that are logged (say to console or file) consist of a single +line of text. However, sometimes there is a need to handle messages with +multiple lines - whether because a logging format string contains newlines, or +logged data contains newlines. If you want to handle such messages uniformly, so +that each line in the logged message appears uniformly formatted as if it was +logged separately, you can do this using a handler mixin, as in the following +snippet: + +.. code-block:: python + + # Assume this is in a module mymixins.py + import copy + + class MultilineMixin: + def emit(self, record): + s = record.getMessage() + if '\n' not in s: + super().emit(record) + else: + lines = s.splitlines() + rec = copy.copy(record) + rec.args = None + for line in lines: + rec.msg = line + super().emit(rec) + +You can use the mixin as in the following script: + +.. code-block:: python + + import logging + + from mymixins import MultilineMixin + + logger = logging.getLogger(__name__) + + class StreamHandler(MultilineMixin, logging.StreamHandler): + pass + + if __name__ == '__main__': + logging.basicConfig(level=logging.DEBUG, format='%(asctime)s %(levelname)-9s %(message)s', + handlers = [StreamHandler()]) + logger.debug('Single line') + logger.debug('Multiple lines:\nfool me once ...') + logger.debug('Another single line') + logger.debug('Multiple lines:\n%s', 'fool me ...\ncan\'t get fooled again') + +The script, when run, prints something like: + +.. code-block:: text + + 2025-07-02 13:54:47,234 DEBUG Single line + 2025-07-02 13:54:47,234 DEBUG Multiple lines: + 2025-07-02 13:54:47,234 DEBUG fool me once ... + 2025-07-02 13:54:47,234 DEBUG Another single line + 2025-07-02 13:54:47,234 DEBUG Multiple lines: + 2025-07-02 13:54:47,234 DEBUG fool me ... + 2025-07-02 13:54:47,234 DEBUG can't get fooled again + +If, on the other hand, you are concerned about `log injection +`_, you can use a +formatter which escapes newlines, as per the following example: + +.. code-block:: python + + import logging + + logger = logging.getLogger(__name__) + + class EscapingFormatter(logging.Formatter): + def format(self, record): + s = super().format(record) + return s.replace('\n', r'\n') + + if __name__ == '__main__': + h = logging.StreamHandler() + h.setFormatter(EscapingFormatter('%(asctime)s %(levelname)-9s %(message)s')) + logging.basicConfig(level=logging.DEBUG, handlers = [h]) + logger.debug('Single line') + logger.debug('Multiple lines:\nfool me once ...') + logger.debug('Another single line') + logger.debug('Multiple lines:\n%s', 'fool me ...\ncan\'t get fooled again') + +You can, of course, use whatever escaping scheme makes the most sense for you. +The script, when run, should produce output like this: + +.. code-block:: text + + 2025-07-09 06:47:33,783 DEBUG Single line + 2025-07-09 06:47:33,783 DEBUG Multiple lines:\nfool me once ... + 2025-07-09 06:47:33,783 DEBUG Another single line + 2025-07-09 06:47:33,783 DEBUG Multiple lines:\nfool me ...\ncan't get fooled again + +Escaping behaviour can't be the stdlib default , as it would break backwards +compatibility. .. patterns-to-avoid: diff --git a/Doc/howto/logging.rst b/Doc/howto/logging.rst index 2982cf88bf97b4..454e2f4930e724 100644 --- a/Doc/howto/logging.rst +++ b/Doc/howto/logging.rst @@ -28,7 +28,7 @@ When to use logging ^^^^^^^^^^^^^^^^^^^ You can access logging functionality by creating a logger via ``logger = -getLogger(__name__)``, and then calling the logger's :meth:`~Logger.debug`, +logging.getLogger(__name__)``, and then calling the logger's :meth:`~Logger.debug`, :meth:`~Logger.info`, :meth:`~Logger.warning`, :meth:`~Logger.error` and :meth:`~Logger.critical` methods. To determine when to use logging, and to see which logger methods to use when, see the table below. It states, for each of a @@ -302,10 +302,10 @@ reading the following sections. If you're ready for that, grab some of your favourite beverage and carry on. If your logging needs are simple, then use the above examples to incorporate -logging into your own scripts, and if you run into problems or don't -understand something, please post a question on the comp.lang.python Usenet -group (available at https://groups.google.com/g/comp.lang.python) and you -should receive help before too long. +logging into your own scripts, and if you run into problems or don't understand +something, please post a question in the Help category of the `Python +discussion forum `_ and you should receive +help before too long. Still here? You can carry on reading the next few sections, which provide a slightly more advanced/in-depth tutorial than the basic one above. After that, diff --git a/Doc/howto/mro.rst b/Doc/howto/mro.rst index 0872bedcd3a2d3..72cc311e30d669 100644 --- a/Doc/howto/mro.rst +++ b/Doc/howto/mro.rst @@ -10,7 +10,7 @@ The Python 2.3 Method Resolution Order The Method Resolution Order discussed here was *introduced* in Python 2.3, but it is still used in later versions -- including Python 3. -By `Michele Simionato `__. +By `Michele Simionato `__. :Abstract: diff --git a/Doc/howto/regex.rst b/Doc/howto/regex.rst index e543f6d5657d79..84ec535ca98e97 100644 --- a/Doc/howto/regex.rst +++ b/Doc/howto/regex.rst @@ -1,7 +1,7 @@ .. _regex-howto: **************************** - Regular Expression HOWTO + Regular expression HOWTO **************************** :Author: A.M. Kuchling @@ -47,7 +47,7 @@ Python code to do the processing; while Python code will be slower than an elaborate regular expression, it will also probably be more understandable. -Simple Patterns +Simple patterns =============== We'll start by learning about the simplest possible regular expressions. Since @@ -59,7 +59,7 @@ expressions (deterministic and non-deterministic finite automata), you can refer to almost any textbook on writing compilers. -Matching Characters +Matching characters ------------------- Most letters and characters will simply match themselves. For example, the @@ -159,7 +159,7 @@ match even a newline. ``.`` is often used where you want to match "any character". -Repeating Things +Repeating things ---------------- Being able to match varying sets of characters is the first thing regular @@ -210,7 +210,7 @@ this RE against the string ``'abcbd'``. | | | ``[bcd]*`` is only matching | | | | ``bc``. | +------+-----------+---------------------------------+ -| 6 | ``abcb`` | Try ``b`` again. This time | +| 7 | ``abcb`` | Try ``b`` again. This time | | | | the character at the | | | | current position is ``'b'``, so | | | | it succeeds. | @@ -255,7 +255,7 @@ is equivalent to ``+``, and ``{0,1}`` is the same as ``?``. It's better to use to read. -Using Regular Expressions +Using regular expressions ========================= Now that we've looked at some simple regular expressions, how do we actually use @@ -264,7 +264,7 @@ expression engine, allowing you to compile REs into objects and then perform matches with them. -Compiling Regular Expressions +Compiling regular expressions ----------------------------- Regular expressions are compiled into pattern objects, which have @@ -295,7 +295,7 @@ disadvantage which is the topic of the next section. .. _the-backslash-plague: -The Backslash Plague +The backslash plague -------------------- As stated earlier, regular expressions use the backslash character (``'\'``) to @@ -335,7 +335,7 @@ expressions will often be written in Python code using this raw string notation. In addition, special escape sequences that are valid in regular expressions, but not valid as Python string literals, now result in a -:exc:`DeprecationWarning` and will eventually become a :exc:`SyntaxError`, +:exc:`SyntaxWarning` and will eventually become a :exc:`SyntaxError`, which means the sequences will be invalid if raw string notation or escaping the backslashes isn't used. @@ -351,7 +351,7 @@ the backslashes isn't used. +-------------------+------------------+ -Performing Matches +Performing matches ------------------ Once you have an object representing a compiled regular expression, what do you @@ -369,10 +369,10 @@ for a complete listing. | | location where this RE matches. | +------------------+-----------------------------------------------+ | ``findall()`` | Find all substrings where the RE matches, and | -| | returns them as a list. | +| | return them as a list. | +------------------+-----------------------------------------------+ | ``finditer()`` | Find all substrings where the RE matches, and | -| | returns them as an :term:`iterator`. | +| | return them as an :term:`iterator`. | +------------------+-----------------------------------------------+ :meth:`~re.Pattern.match` and :meth:`~re.Pattern.search` return ``None`` if no match can be found. If @@ -473,7 +473,7 @@ Two pattern methods return all of the matches for a pattern. The ``r`` prefix, making the literal a raw string literal, is needed in this example because escape sequences in a normal "cooked" string literal that are not recognized by Python, as opposed to regular expressions, now result in a -:exc:`DeprecationWarning` and will eventually become a :exc:`SyntaxError`. See +:exc:`SyntaxWarning` and will eventually become a :exc:`SyntaxError`. See :ref:`the-backslash-plague`. :meth:`~re.Pattern.findall` has to create the entire list before it can be returned as the @@ -491,7 +491,7 @@ result. The :meth:`~re.Pattern.finditer` method returns a sequence of (29, 31) -Module-Level Functions +Module-level functions ---------------------- You don't have to create a pattern object and call its methods; the @@ -518,7 +518,7 @@ Outside of loops, there's not much difference thanks to the internal cache. -Compilation Flags +Compilation flags ----------------- .. currentmodule:: re @@ -642,7 +642,7 @@ of each one. whitespace is in a character class or preceded by an unescaped backslash; this lets you organize and indent the RE more clearly. This flag also lets you put comments within a RE that will be ignored by the engine; comments are marked by - a ``'#'`` that's neither in a character class or preceded by an unescaped + a ``'#'`` that's neither in a character class nor preceded by an unescaped backslash. For example, here's a RE that uses :const:`re.VERBOSE`; see how much easier it @@ -669,7 +669,7 @@ of each one. to understand than the version using :const:`re.VERBOSE`. -More Pattern Power +More pattern power ================== So far we've only covered a part of the features of regular expressions. In @@ -679,7 +679,7 @@ retrieve portions of the text that was matched. .. _more-metacharacters: -More Metacharacters +More metacharacters ------------------- There are some metacharacters that we haven't covered yet. Most of them will be @@ -875,7 +875,7 @@ Backreferences like this aren't often useful for just searching through a string find out that they're *very* useful when performing string substitutions. -Non-capturing and Named Groups +Non-capturing and named groups ------------------------------ Elaborate REs may use many groups, both to capture substrings of interest, and @@ -979,7 +979,7 @@ current point. The regular expression for finding doubled words, 'the the' -Lookahead Assertions +Lookahead assertions -------------------- Another zero-width assertion is the lookahead assertion. Lookahead assertions @@ -1016,7 +1016,9 @@ extension. This regular expression matches ``foo.bar`` and Now, consider complicating the problem a bit; what if you want to match filenames where the extension is not ``bat``? Some incorrect attempts: -``.*[.][^b].*$`` The first attempt above tries to exclude ``bat`` by requiring +``.*[.][^b].*$`` + +The first attempt above tries to exclude ``bat`` by requiring that the first character of the extension is not a ``b``. This is wrong, because the pattern also doesn't match ``foo.bar``. @@ -1043,7 +1045,9 @@ confusing. A negative lookahead cuts through all this confusion: -``.*[.](?!bat$)[^.]*$`` The negative lookahead means: if the expression ``bat`` +``.*[.](?!bat$)[^.]*$`` + +The negative lookahead means: if the expression ``bat`` doesn't match at this point, try the rest of the pattern; if ``bat$`` does match, the whole pattern will fail. The trailing ``$`` is required to ensure that something like ``sample.batch``, where the extension only starts with @@ -1057,7 +1061,7 @@ end in either ``bat`` or ``exe``: ``.*[.](?!bat$|exe$)[^.]*$`` -Modifying Strings +Modifying strings ================= Up to this point, we've simply performed searches against a static string. @@ -1079,7 +1083,7 @@ using the following pattern methods: +------------------+-----------------------------------------------+ -Splitting Strings +Splitting strings ----------------- The :meth:`~re.Pattern.split` method of a pattern splits a string apart @@ -1133,7 +1137,7 @@ argument, but is otherwise the same. :: ['Words', 'words, words.'] -Search and Replace +Search and replace ------------------ Another common task is to find all the matches for a pattern, and replace them @@ -1232,7 +1236,7 @@ pattern object as the first parameter, or use embedded modifiers in the pattern string, e.g. ``sub("(?i)b+", "x", "bbbb BBBB")`` returns ``'x x'``. -Common Problems +Common problems =============== Regular expressions are a powerful tool for some applications, but in some ways @@ -1240,7 +1244,7 @@ their behaviour isn't intuitive and at times they don't behave the way you may expect them to. This section will point out some of the most common pitfalls. -Use String Methods +Use string methods ------------------ Sometimes using the :mod:`re` module is a mistake. If you're matching a fixed @@ -1306,7 +1310,7 @@ string and then backtracking to find a match for the rest of the RE. Use :func:`re.search` instead. -Greedy versus Non-Greedy +Greedy versus non-greedy ------------------------ When repeating a regular expression, as in ``a*``, the resulting action is to @@ -1384,9 +1388,9 @@ Feedback ======== Regular expressions are a complicated topic. Did this document help you -understand them? Were there parts that were unclear, or Problems you +understand them? Were there parts that were unclear, or problems you encountered that weren't covered here? If so, please send suggestions for -improvements to the author. +improvements to the :ref:`issue tracker `. The most complete book on regular expressions is almost certainly Jeffrey Friedl's Mastering Regular Expressions, published by O'Reilly. Unfortunately, diff --git a/Doc/howto/remote_debugging.rst b/Doc/howto/remote_debugging.rst index 3adb6ad03e5445..1d5cf24d062843 100644 --- a/Doc/howto/remote_debugging.rst +++ b/Doc/howto/remote_debugging.rst @@ -3,6 +3,88 @@ Remote debugging attachment protocol ==================================== +This protocol enables external tools to attach to a running CPython process and +execute Python code remotely. + +Most platforms require elevated privileges to attach to another Python process. + +Disabling remote debugging +-------------------------- + +To disable remote debugging support, use any of the following: + +* Set the :envvar:`PYTHON_DISABLE_REMOTE_DEBUG` environment variable to ``1`` before + starting the interpreter. +* Use the :option:`-X disable_remote_debug` command-line option. +* Compile Python with the :option:`--without-remote-debug` build flag. + +.. _permission-requirements: + +Permission requirements +======================= + +Attaching to a running Python process for remote debugging requires elevated +privileges on most platforms. The specific requirements and troubleshooting +steps depend on your operating system: + +.. rubric:: Linux + +The tracer process must have the ``CAP_SYS_PTRACE`` capability or equivalent +privileges. You can only trace processes you own and can signal. Tracing may +fail if the process is already being traced, or if it is running with +set-user-ID or set-group-ID. Security modules like Yama may further restrict +tracing. + +To temporarily relax ptrace restrictions (until reboot), run: + + ``echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope`` + +.. note:: + + Disabling ``ptrace_scope`` reduces system hardening and should only be done + in trusted environments. + +If running inside a container, use ``--cap-add=SYS_PTRACE`` or +``--privileged``, and run as root if needed. + +Try re-running the command with elevated privileges: + + ``sudo -E !!`` + + +.. rubric:: macOS + +To attach to another process, you typically need to run your debugging tool +with elevated privileges. This can be done by using ``sudo`` or running as +root. + +Even when attaching to processes you own, macOS may block debugging unless +the debugger is run with root privileges due to system security restrictions. + + +.. rubric:: Windows + +To attach to another process, you usually need to run your debugging tool +with administrative privileges. Start the command prompt or terminal as +Administrator. + +Some processes may still be inaccessible even with Administrator rights, +unless you have the ``SeDebugPrivilege`` privilege enabled. + +To resolve file or folder access issues, adjust the security permissions: + + 1. Right-click the file or folder and select **Properties**. + 2. Go to the **Security** tab to view users and groups with access. + 3. Click **Edit** to modify permissions. + 4. Select your user account. + 5. In **Permissions**, check **Read** or **Full control** as needed. + 6. Click **Apply**, then **OK** to confirm. + + +.. note:: + + Ensure you've satisfied all :ref:`permission-requirements` before proceeding. + This section describes the low-level protocol that enables external tools to inject and execute a Python script within a running CPython process. @@ -374,13 +456,13 @@ To locate a thread: reliable thread to target. 3. Optionally, use the offset ``interpreter_state.threads_head`` to iterate -through the linked list of all thread states. Each ``PyThreadState`` structure -contains a ``native_thread_id`` field, which may be compared to a target thread -ID to find a specific thread. + through the linked list of all thread states. Each ``PyThreadState`` + structure contains a ``native_thread_id`` field, which may be compared to + a target thread ID to find a specific thread. -1. Once a valid ``PyThreadState`` has been found, its address can be used in -later steps of the protocol, such as writing debugger control fields and -scheduling execution. +4. Once a valid ``PyThreadState`` has been found, its address can be used in + later steps of the protocol, such as writing debugger control fields and + scheduling execution. The following is an example implementation that locates the main thread state:: @@ -454,15 +536,15 @@ its fields are defined by the ``_Py_DebugOffsets`` structure and include the following: - ``debugger_script_path``: A fixed-size buffer that holds the full path to a - Python source file (``.py``). This file must be accessible and readable by - the target process when execution is triggered. + Python source file (``.py``). This file must be accessible and readable by + the target process when execution is triggered. - ``debugger_pending_call``: An integer flag. Setting this to ``1`` tells the - interpreter that a script is ready to be executed. + interpreter that a script is ready to be executed. - ``eval_breaker``: A field checked by the interpreter during execution. - Setting bit 5 (``_PY_EVAL_PLEASE_STOP_BIT``, value ``1U << 5``) in this - field causes the interpreter to pause and check for debugger activity. + Setting bit 5 (``_PY_EVAL_PLEASE_STOP_BIT``, value ``1U << 5``) in this + field causes the interpreter to pause and check for debugger activity. To complete the injection, the debugger must perform the following steps: @@ -543,3 +625,57 @@ To inject and execute a Python script in a remote process: 7. Resume the process (if suspended). The script will execute at the next safe evaluation point. +.. _remote-debugging-threat-model: + +Security and threat model +========================= + +The remote debugging protocol relies on the same operating system primitives +used by native debuggers such as GDB and LLDB. Attaching to a process +requires the **same privileges** that those debuggers require, for example +``ptrace`` / Yama LSM on Linux, ``task_for_pid`` on macOS, and +``SeDebugPrivilege`` on Windows. Python does not introduce any new privilege +escalation path; if an attacker already possesses the permissions needed to +attach to a process, they could equally use GDB to read memory or inject +code. + +The following principles define what is, and is not, considered a security +vulnerability in this feature: + +Attaching requires OS-level privileges + On every supported platform the operating system gates cross-process + memory access behind privilege checks (``CAP_SYS_PTRACE``, root, or + administrator rights). A report that demonstrates an issue only after + these privileges have already been obtained is **not** a vulnerability in + CPython, since the OS security boundary was already crossed. + +Crashes or memory errors when reading a compromised process are not vulnerabilities + A tool that reads internal interpreter state from a target process must + trust that memory to be well-formed. If the target process has been + corrupted or is controlled by an attacker, the debugger or profiler may + crash, produce garbage output, or behave unpredictably. This is the same + risk accepted by every ``ptrace``-based debugger. Bugs in this category + (buffer overflows, segmentation faults, or undefined behaviour triggered + by reading corrupted state) are **not** treated as security issues, though + fixes that improve robustness are welcome. + +Vulnerabilities in the target process are not in scope + If the Python process being debugged has already been compromised, the + attacker already controls execution in that process. Demonstrating further + impact from that starting point does not constitute a vulnerability in the + remote debugging protocol. + +When to use ``PYTHON_DISABLE_REMOTE_DEBUG`` +------------------------------------------- + +The environment variable :envvar:`PYTHON_DISABLE_REMOTE_DEBUG` (and the +equivalent :option:`-X disable_remote_debug` flag) allows operators to disable +the in-process side of the protocol as a **defence-in-depth** measure. This +may be useful in hardened or sandboxed deployment environments where no +debugging or profiling of the process is expected and reducing attack surface +is a priority, even though the OS-level privilege checks already prevent +unprivileged access. + +Setting this variable does **not** affect other OS-level debugging interfaces +(``ptrace``, ``/proc``, ``task_for_pid``, etc.), which remain available +according to their own permission models. diff --git a/Doc/howto/sorting.rst b/Doc/howto/sorting.rst index 70c34cde8a0659..65e862e13e817a 100644 --- a/Doc/howto/sorting.rst +++ b/Doc/howto/sorting.rst @@ -375,7 +375,7 @@ Odds and Ends :meth:`~object.__lt__` is not implemented (see :func:`object.__lt__` for details on the mechanics). To avoid surprises, :pep:`8` recommends that all six comparison methods be implemented. - The :func:`~functools.total_ordering` decorator is provided to make that + The :deco:`~functools.total_ordering` decorator is provided to make that task easier. * Key functions need not depend directly on the objects being sorted. A key diff --git a/Doc/howto/unicode.rst b/Doc/howto/unicode.rst index 254fe729355353..243cc27bac7025 100644 --- a/Doc/howto/unicode.rst +++ b/Doc/howto/unicode.rst @@ -352,6 +352,8 @@ If you don't include such a comment, the default encoding used will be UTF-8 as already mentioned. See also :pep:`263` for more information. +.. _unicode-properties: + Unicode Properties ------------------ diff --git a/Doc/howto/urllib2.rst b/Doc/howto/urllib2.rst index 33a2a7ea89ea07..4e77d2cb407f72 100644 --- a/Doc/howto/urllib2.rst +++ b/Doc/howto/urllib2.rst @@ -15,7 +15,7 @@ Introduction You may also find useful the following article on fetching web resources with Python: - * `Basic Authentication `_ + * `Basic Authentication `__ A tutorial on *Basic Authentication*, with examples in Python. @@ -245,75 +245,27 @@ codes in the 100--299 range indicate success, you will usually only see error codes in the 400--599 range. :attr:`http.server.BaseHTTPRequestHandler.responses` is a useful dictionary of -response codes in that shows all the response codes used by :rfc:`2616`. The -dictionary is reproduced here for convenience :: +response codes that shows all the response codes used by :rfc:`2616`. +An excerpt from the dictionary is shown below :: - # Table mapping response codes to messages; entries have the - # form {code: (shortmessage, longmessage)}. responses = { - 100: ('Continue', 'Request received, please continue'), - 101: ('Switching Protocols', - 'Switching to new protocol; obey Upgrade header'), - - 200: ('OK', 'Request fulfilled, document follows'), - 201: ('Created', 'Document created, URL follows'), - 202: ('Accepted', - 'Request accepted, processing continues off-line'), - 203: ('Non-Authoritative Information', 'Request fulfilled from cache'), - 204: ('No Content', 'Request fulfilled, nothing follows'), - 205: ('Reset Content', 'Clear input form for further input.'), - 206: ('Partial Content', 'Partial content follows.'), - - 300: ('Multiple Choices', - 'Object has several resources -- see URI list'), - 301: ('Moved Permanently', 'Object moved permanently -- see URI list'), - 302: ('Found', 'Object moved temporarily -- see URI list'), - 303: ('See Other', 'Object moved -- see Method and URL list'), - 304: ('Not Modified', - 'Document has not changed since given time'), - 305: ('Use Proxy', - 'You must use proxy specified in Location to access this ' - 'resource.'), - 307: ('Temporary Redirect', - 'Object moved temporarily -- see URI list'), - - 400: ('Bad Request', - 'Bad request syntax or unsupported method'), - 401: ('Unauthorized', - 'No permission -- see authorization schemes'), - 402: ('Payment Required', - 'No payment -- see charging schemes'), - 403: ('Forbidden', - 'Request forbidden -- authorization will not help'), - 404: ('Not Found', 'Nothing matches the given URI'), - 405: ('Method Not Allowed', - 'Specified method is invalid for this server.'), - 406: ('Not Acceptable', 'URI not available in preferred format.'), - 407: ('Proxy Authentication Required', 'You must authenticate with ' - 'this proxy before proceeding.'), - 408: ('Request Timeout', 'Request timed out; try again later.'), - 409: ('Conflict', 'Request conflict.'), - 410: ('Gone', - 'URI no longer exists and has been permanently removed.'), - 411: ('Length Required', 'Client must specify Content-Length.'), - 412: ('Precondition Failed', 'Precondition in headers is false.'), - 413: ('Request Entity Too Large', 'Entity is too large.'), - 414: ('Request-URI Too Long', 'URI is too long.'), - 415: ('Unsupported Media Type', 'Entity body in unsupported format.'), - 416: ('Requested Range Not Satisfiable', - 'Cannot satisfy request range.'), - 417: ('Expectation Failed', - 'Expect condition could not be satisfied.'), - - 500: ('Internal Server Error', 'Server got itself in trouble'), - 501: ('Not Implemented', - 'Server does not support this operation'), - 502: ('Bad Gateway', 'Invalid responses from another server/proxy.'), - 503: ('Service Unavailable', - 'The server cannot process the request due to a high load'), - 504: ('Gateway Timeout', - 'The gateway server did not receive a timely response'), - 505: ('HTTP Version Not Supported', 'Cannot fulfill request.'), + ... + : ('OK', 'Request fulfilled, document follows'), + ... + : ('Forbidden', + 'Request forbidden -- authorization will ' + 'not help'), + : ('Not Found', + 'Nothing matches the given URI'), + ... + : ("I'm a Teapot", + 'Server refuses to brew coffee because ' + 'it is a teapot'), + ... + : ('Service Unavailable', + 'The server cannot process the ' + 'request due to a high load'), + ... } When an error is raised the server responds by returning an HTTP error code diff --git a/Doc/improve-page-nojs.rst b/Doc/improve-page-nojs.rst new file mode 100644 index 00000000000000..91b3a88b95d38b --- /dev/null +++ b/Doc/improve-page-nojs.rst @@ -0,0 +1,29 @@ +:orphan: + +**************************** +Improve a documentation page +**************************** + +.. This is the no-javascript version of this page. The one most people + will see (with JavaScript enabled) is improve-page.rst. If you edit + this page, please also edit that one, and vice versa. + +.. only:: html and not epub + +We are always interested to hear ideas about improvements to the documentation. + +.. only:: translation + + If the bug or suggested improvement concerns the translation of this + documentation, open an issue or edit the page in + `translation's repository `_ instead. + +You have a few ways to ask questions or suggest changes: + +- You can start a discussion about the page on the Python discussion forum. + This link will start a topic in the Documentation category: + `New Documentation topic `_. + +- You can open an issue on the Python GitHub issue tracker. This link will + create a new issue with the "docs" label: + `New docs issue `_. diff --git a/Doc/improve-page.rst b/Doc/improve-page.rst new file mode 100644 index 00000000000000..dc89fcb22fbb59 --- /dev/null +++ b/Doc/improve-page.rst @@ -0,0 +1,65 @@ +:orphan: + +**************************** +Improve a documentation page +**************************** + +.. This is the JavaScript-enabled version of this page. Another version + (for those with JavaScript disabled) is improve-page-nojs.rst. If you + edit this page, please also edit that one, and vice versa. + +.. only:: html and not epub + + .. raw:: html + + + +We are always interested to hear ideas about improvements to the documentation. + +You were reading "PAGETITLE" at ``_. The source for that page is on +`GitHub `_. + +.. only:: translation + + If the bug or suggested improvement concerns the translation of this + documentation, open an issue or edit the page in + `translation's repository `_ instead. + +You have a few ways to ask questions or suggest changes: + +- You can start a discussion about the page on the Python discussion forum. + This link will start a pre-populated topic: + `Question about page "PAGETITLE" `_. + +- You can open an issue on the Python GitHub issue tracker. This link will + create a new pre-populated issue: + `Docs: problem with page "PAGETITLE" `_. + +- You can `edit the page on GitHub `_ + to open a pull request and begin the contribution process. diff --git a/Doc/includes/diff.py b/Doc/includes/diff.py index 001619f5f83fc0..bc4bd58ff3e3f1 100644 --- a/Doc/includes/diff.py +++ b/Doc/includes/diff.py @@ -1,4 +1,4 @@ -""" Command line interface to difflib.py providing diffs in four formats: +""" Command-line interface to difflib.py providing diffs in four formats: * ndiff: lists every line and highlights interline changes. * context: highlights clusters of changes in a before/after format. @@ -8,11 +8,11 @@ """ import sys, os, difflib, argparse -from datetime import datetime, timezone +import datetime as dt def file_mtime(path): - t = datetime.fromtimestamp(os.stat(path).st_mtime, - timezone.utc) + t = dt.datetime.fromtimestamp(os.stat(path).st_mtime, + dt.timezone.utc) return t.astimezone().isoformat() def main(): diff --git a/Doc/includes/newtypes/custom.c b/Doc/includes/newtypes/custom.c index 5253f879360210..039a1a7219349c 100644 --- a/Doc/includes/newtypes/custom.c +++ b/Doc/includes/newtypes/custom.c @@ -16,28 +16,37 @@ static PyTypeObject CustomType = { .tp_new = PyType_GenericNew, }; -static PyModuleDef custommodule = { +static int +custom_module_exec(PyObject *m) +{ + if (PyType_Ready(&CustomType) < 0) { + return -1; + } + + if (PyModule_AddObjectRef(m, "Custom", (PyObject *) &CustomType) < 0) { + return -1; + } + + return 0; +} + +static PyModuleDef_Slot custom_module_slots[] = { + {Py_mod_exec, custom_module_exec}, + // Just use this while using static types + {Py_mod_multiple_interpreters, Py_MOD_MULTIPLE_INTERPRETERS_NOT_SUPPORTED}, + {0, NULL} +}; + +static PyModuleDef custom_module = { .m_base = PyModuleDef_HEAD_INIT, .m_name = "custom", .m_doc = "Example module that creates an extension type.", - .m_size = -1, + .m_size = 0, + .m_slots = custom_module_slots, }; PyMODINIT_FUNC PyInit_custom(void) { - PyObject *m; - if (PyType_Ready(&CustomType) < 0) - return NULL; - - m = PyModule_Create(&custommodule); - if (m == NULL) - return NULL; - - if (PyModule_AddObjectRef(m, "Custom", (PyObject *) &CustomType) < 0) { - Py_DECREF(m); - return NULL; - } - - return m; + return PyModuleDef_Init(&custom_module); } diff --git a/Doc/includes/newtypes/custom2.c b/Doc/includes/newtypes/custom2.c index a87917583ca495..1ff8e707d1b0a0 100644 --- a/Doc/includes/newtypes/custom2.c +++ b/Doc/includes/newtypes/custom2.c @@ -106,28 +106,36 @@ static PyTypeObject CustomType = { .tp_methods = Custom_methods, }; -static PyModuleDef custommodule = { - .m_base =PyModuleDef_HEAD_INIT, +static int +custom_module_exec(PyObject *m) +{ + if (PyType_Ready(&CustomType) < 0) { + return -1; + } + + if (PyModule_AddObjectRef(m, "Custom", (PyObject *) &CustomType) < 0) { + return -1; + } + + return 0; +} + +static PyModuleDef_Slot custom_module_slots[] = { + {Py_mod_exec, custom_module_exec}, + {Py_mod_multiple_interpreters, Py_MOD_MULTIPLE_INTERPRETERS_NOT_SUPPORTED}, + {0, NULL} +}; + +static PyModuleDef custom_module = { + .m_base = PyModuleDef_HEAD_INIT, .m_name = "custom2", .m_doc = "Example module that creates an extension type.", - .m_size = -1, + .m_size = 0, + .m_slots = custom_module_slots, }; PyMODINIT_FUNC PyInit_custom2(void) { - PyObject *m; - if (PyType_Ready(&CustomType) < 0) - return NULL; - - m = PyModule_Create(&custommodule); - if (m == NULL) - return NULL; - - if (PyModule_AddObjectRef(m, "Custom", (PyObject *) &CustomType) < 0) { - Py_DECREF(m); - return NULL; - } - - return m; + return PyModuleDef_Init(&custom_module); } diff --git a/Doc/includes/newtypes/custom3.c b/Doc/includes/newtypes/custom3.c index 854034d4066d20..22f50eb0e1de89 100644 --- a/Doc/includes/newtypes/custom3.c +++ b/Doc/includes/newtypes/custom3.c @@ -151,28 +151,36 @@ static PyTypeObject CustomType = { .tp_getset = Custom_getsetters, }; -static PyModuleDef custommodule = { +static int +custom_module_exec(PyObject *m) +{ + if (PyType_Ready(&CustomType) < 0) { + return -1; + } + + if (PyModule_AddObjectRef(m, "Custom", (PyObject *) &CustomType) < 0) { + return -1; + } + + return 0; +} + +static PyModuleDef_Slot custom_module_slots[] = { + {Py_mod_exec, custom_module_exec}, + {Py_mod_multiple_interpreters, Py_MOD_MULTIPLE_INTERPRETERS_NOT_SUPPORTED}, + {0, NULL} +}; + +static PyModuleDef custom_module = { .m_base = PyModuleDef_HEAD_INIT, .m_name = "custom3", .m_doc = "Example module that creates an extension type.", - .m_size = -1, + .m_size = 0, + .m_slots = custom_module_slots, }; PyMODINIT_FUNC PyInit_custom3(void) { - PyObject *m; - if (PyType_Ready(&CustomType) < 0) - return NULL; - - m = PyModule_Create(&custommodule); - if (m == NULL) - return NULL; - - if (PyModule_AddObjectRef(m, "Custom", (PyObject *) &CustomType) < 0) { - Py_DECREF(m); - return NULL; - } - - return m; + return PyModuleDef_Init(&custom_module); } diff --git a/Doc/includes/newtypes/custom4.c b/Doc/includes/newtypes/custom4.c index a0a1eeb289190b..07585aff5987f3 100644 --- a/Doc/includes/newtypes/custom4.c +++ b/Doc/includes/newtypes/custom4.c @@ -170,28 +170,36 @@ static PyTypeObject CustomType = { .tp_getset = Custom_getsetters, }; -static PyModuleDef custommodule = { +static int +custom_module_exec(PyObject *m) +{ + if (PyType_Ready(&CustomType) < 0) { + return -1; + } + + if (PyModule_AddObjectRef(m, "Custom", (PyObject *) &CustomType) < 0) { + return -1; + } + + return 0; +} + +static PyModuleDef_Slot custom_module_slots[] = { + {Py_mod_exec, custom_module_exec}, + {Py_mod_multiple_interpreters, Py_MOD_MULTIPLE_INTERPRETERS_NOT_SUPPORTED}, + {0, NULL} +}; + +static PyModuleDef custom_module = { .m_base = PyModuleDef_HEAD_INIT, .m_name = "custom4", .m_doc = "Example module that creates an extension type.", - .m_size = -1, + .m_size = 0, + .m_slots = custom_module_slots, }; PyMODINIT_FUNC PyInit_custom4(void) { - PyObject *m; - if (PyType_Ready(&CustomType) < 0) - return NULL; - - m = PyModule_Create(&custommodule); - if (m == NULL) - return NULL; - - if (PyModule_AddObjectRef(m, "Custom", (PyObject *) &CustomType) < 0) { - Py_DECREF(m); - return NULL; - } - - return m; + return PyModuleDef_Init(&custom_module); } diff --git a/Doc/includes/newtypes/sublist.c b/Doc/includes/newtypes/sublist.c index 00664f3454156f..b784456a4ef667 100644 --- a/Doc/includes/newtypes/sublist.c +++ b/Doc/includes/newtypes/sublist.c @@ -31,7 +31,7 @@ SubList_init(PyObject *op, PyObject *args, PyObject *kwds) } static PyTypeObject SubListType = { - PyVarObject_HEAD_INIT(NULL, 0) + .ob_base = PyVarObject_HEAD_INIT(NULL, 0) .tp_name = "sublist.SubList", .tp_doc = PyDoc_STR("SubList objects"), .tp_basicsize = sizeof(SubListObject), @@ -41,29 +41,37 @@ static PyTypeObject SubListType = { .tp_methods = SubList_methods, }; -static PyModuleDef sublistmodule = { - PyModuleDef_HEAD_INIT, +static int +sublist_module_exec(PyObject *m) +{ + SubListType.tp_base = &PyList_Type; + if (PyType_Ready(&SubListType) < 0) { + return -1; + } + + if (PyModule_AddObjectRef(m, "SubList", (PyObject *) &SubListType) < 0) { + return -1; + } + + return 0; +} + +static PyModuleDef_Slot sublist_module_slots[] = { + {Py_mod_exec, sublist_module_exec}, + {Py_mod_multiple_interpreters, Py_MOD_MULTIPLE_INTERPRETERS_NOT_SUPPORTED}, + {0, NULL} +}; + +static PyModuleDef sublist_module = { + .m_base = PyModuleDef_HEAD_INIT, .m_name = "sublist", .m_doc = "Example module that creates an extension type.", - .m_size = -1, + .m_size = 0, + .m_slots = sublist_module_slots, }; PyMODINIT_FUNC PyInit_sublist(void) { - PyObject *m; - SubListType.tp_base = &PyList_Type; - if (PyType_Ready(&SubListType) < 0) - return NULL; - - m = PyModule_Create(&sublistmodule); - if (m == NULL) - return NULL; - - if (PyModule_AddObjectRef(m, "SubList", (PyObject *) &SubListType) < 0) { - Py_DECREF(m); - return NULL; - } - - return m; + return PyModuleDef_Init(&sublist_module); } diff --git a/Doc/includes/optional-module.rst b/Doc/includes/optional-module.rst new file mode 100644 index 00000000000000..262e73f2eaa09f --- /dev/null +++ b/Doc/includes/optional-module.rst @@ -0,0 +1,9 @@ +This is an :term:`optional module`. +If it is missing from your copy of CPython, +look for documentation from your distributor (that is, +whoever provided Python to you). +If you are the distributor, see :ref:`optional-module-requirements`. + +.. Similar notes appear in the docs of the modules: + - zipfile + - tarfile diff --git a/Doc/includes/tzinfo_examples.py b/Doc/includes/tzinfo_examples.py index 1fa6e615e46a76..762b1b62fc871d 100644 --- a/Doc/includes/tzinfo_examples.py +++ b/Doc/includes/tzinfo_examples.py @@ -1,68 +1,70 @@ -from datetime import tzinfo, timedelta, datetime - -ZERO = timedelta(0) -HOUR = timedelta(hours=1) -SECOND = timedelta(seconds=1) +import datetime as dt # A class capturing the platform's idea of local time. # (May result in wrong values on historical times in # timezones where UTC offset and/or the DST rules had # changed in the past.) -import time as _time +import time + +ZERO = dt.timedelta(0) +HOUR = dt.timedelta(hours=1) +SECOND = dt.timedelta(seconds=1) -STDOFFSET = timedelta(seconds = -_time.timezone) -if _time.daylight: - DSTOFFSET = timedelta(seconds = -_time.altzone) +STDOFFSET = dt.timedelta(seconds=-time.timezone) +if time.daylight: + DSTOFFSET = dt.timedelta(seconds=-time.altzone) else: DSTOFFSET = STDOFFSET DSTDIFF = DSTOFFSET - STDOFFSET -class LocalTimezone(tzinfo): - def fromutc(self, dt): - assert dt.tzinfo is self - stamp = (dt - datetime(1970, 1, 1, tzinfo=self)) // SECOND - args = _time.localtime(stamp)[:6] +class LocalTimezone(dt.tzinfo): + + def fromutc(self, when): + assert when.tzinfo is self + stamp = (when - dt.datetime(1970, 1, 1, tzinfo=self)) // SECOND + args = time.localtime(stamp)[:6] dst_diff = DSTDIFF // SECOND # Detect fold - fold = (args == _time.localtime(stamp - dst_diff)) - return datetime(*args, microsecond=dt.microsecond, - tzinfo=self, fold=fold) + fold = (args == time.localtime(stamp - dst_diff)) + return dt.datetime(*args, microsecond=when.microsecond, + tzinfo=self, fold=fold) - def utcoffset(self, dt): - if self._isdst(dt): + def utcoffset(self, when): + if self._isdst(when): return DSTOFFSET else: return STDOFFSET - def dst(self, dt): - if self._isdst(dt): + def dst(self, when): + if self._isdst(when): return DSTDIFF else: return ZERO - def tzname(self, dt): - return _time.tzname[self._isdst(dt)] + def tzname(self, when): + return time.tzname[self._isdst(when)] - def _isdst(self, dt): - tt = (dt.year, dt.month, dt.day, - dt.hour, dt.minute, dt.second, - dt.weekday(), 0, 0) - stamp = _time.mktime(tt) - tt = _time.localtime(stamp) + def _isdst(self, when): + tt = (when.year, when.month, when.day, + when.hour, when.minute, when.second, + when.weekday(), 0, 0) + stamp = time.mktime(tt) + tt = time.localtime(stamp) return tt.tm_isdst > 0 + Local = LocalTimezone() # A complete implementation of current DST rules for major US time zones. -def first_sunday_on_or_after(dt): - days_to_go = 6 - dt.weekday() +def first_sunday_on_or_after(when): + days_to_go = 6 - when.weekday() if days_to_go: - dt += timedelta(days_to_go) - return dt + when += dt.timedelta(days_to_go) + return when # US DST Rules @@ -75,21 +77,22 @@ def first_sunday_on_or_after(dt): # # In the US, since 2007, DST starts at 2am (standard time) on the second # Sunday in March, which is the first Sunday on or after Mar 8. -DSTSTART_2007 = datetime(1, 3, 8, 2) +DSTSTART_2007 = dt.datetime(1, 3, 8, 2) # and ends at 2am (DST time) on the first Sunday of Nov. -DSTEND_2007 = datetime(1, 11, 1, 2) +DSTEND_2007 = dt.datetime(1, 11, 1, 2) # From 1987 to 2006, DST used to start at 2am (standard time) on the first # Sunday in April and to end at 2am (DST time) on the last # Sunday of October, which is the first Sunday on or after Oct 25. -DSTSTART_1987_2006 = datetime(1, 4, 1, 2) -DSTEND_1987_2006 = datetime(1, 10, 25, 2) +DSTSTART_1987_2006 = dt.datetime(1, 4, 1, 2) +DSTEND_1987_2006 = dt.datetime(1, 10, 25, 2) # From 1967 to 1986, DST used to start at 2am (standard time) on the last # Sunday in April (the one on or after April 24) and to end at 2am (DST time) # on the last Sunday of October, which is the first Sunday # on or after Oct 25. -DSTSTART_1967_1986 = datetime(1, 4, 24, 2) +DSTSTART_1967_1986 = dt.datetime(1, 4, 24, 2) DSTEND_1967_1986 = DSTEND_1987_2006 + def us_dst_range(year): # Find start and end times for US DST. For years before 1967, return # start = end for no DST. @@ -100,17 +103,17 @@ def us_dst_range(year): elif 1966 < year < 1987: dststart, dstend = DSTSTART_1967_1986, DSTEND_1967_1986 else: - return (datetime(year, 1, 1), ) * 2 + return (dt.datetime(year, 1, 1), ) * 2 start = first_sunday_on_or_after(dststart.replace(year=year)) end = first_sunday_on_or_after(dstend.replace(year=year)) return start, end -class USTimeZone(tzinfo): +class USTimeZone(dt.tzinfo): def __init__(self, hours, reprname, stdname, dstname): - self.stdoffset = timedelta(hours=hours) + self.stdoffset = dt.timedelta(hours=hours) self.reprname = reprname self.stdname = stdname self.dstname = dstname @@ -118,45 +121,45 @@ def __init__(self, hours, reprname, stdname, dstname): def __repr__(self): return self.reprname - def tzname(self, dt): - if self.dst(dt): + def tzname(self, when): + if self.dst(when): return self.dstname else: return self.stdname - def utcoffset(self, dt): - return self.stdoffset + self.dst(dt) + def utcoffset(self, when): + return self.stdoffset + self.dst(when) - def dst(self, dt): - if dt is None or dt.tzinfo is None: + def dst(self, when): + if when is None or when.tzinfo is None: # An exception may be sensible here, in one or both cases. # It depends on how you want to treat them. The default # fromutc() implementation (called by the default astimezone() - # implementation) passes a datetime with dt.tzinfo is self. + # implementation) passes a datetime with when.tzinfo is self. return ZERO - assert dt.tzinfo is self - start, end = us_dst_range(dt.year) + assert when.tzinfo is self + start, end = us_dst_range(when.year) # Can't compare naive to aware objects, so strip the timezone from - # dt first. - dt = dt.replace(tzinfo=None) - if start + HOUR <= dt < end - HOUR: + # when first. + when = when.replace(tzinfo=None) + if start + HOUR <= when < end - HOUR: # DST is in effect. return HOUR - if end - HOUR <= dt < end: - # Fold (an ambiguous hour): use dt.fold to disambiguate. - return ZERO if dt.fold else HOUR - if start <= dt < start + HOUR: + if end - HOUR <= when < end: + # Fold (an ambiguous hour): use when.fold to disambiguate. + return ZERO if when.fold else HOUR + if start <= when < start + HOUR: # Gap (a non-existent hour): reverse the fold rule. - return HOUR if dt.fold else ZERO + return HOUR if when.fold else ZERO # DST is off. return ZERO - def fromutc(self, dt): - assert dt.tzinfo is self - start, end = us_dst_range(dt.year) + def fromutc(self, when): + assert when.tzinfo is self + start, end = us_dst_range(when.year) start = start.replace(tzinfo=self) end = end.replace(tzinfo=self) - std_time = dt + self.stdoffset + std_time = when + self.stdoffset dst_time = std_time + HOUR if end <= dst_time < end + HOUR: # Repeated hour diff --git a/Doc/installing/index.rst b/Doc/installing/index.rst index a46c1caefe4d8a..c372d9f4741800 100644 --- a/Doc/installing/index.rst +++ b/Doc/installing/index.rst @@ -1,16 +1,14 @@ -.. highlight:: none +.. highlight:: shell .. _installing-index: ************************* -Installing Python Modules +Installing Python modules ************************* -:Email: distutils-sig@python.org - As a popular open source development project, Python has an active supporting community of contributors and users that also make their software -available for other Python developers to use under open source license terms. +available for other Python developers to use under open-source license terms. This allows Python users to share and collaborate effectively, benefiting from the solutions others have already created to common (and sometimes @@ -34,34 +32,24 @@ creating and sharing your own Python projects, refer to the Key terms ========= -* ``pip`` is the preferred installer program. Starting with Python 3.4, it +* :program:`pip` is the preferred installer program. It is included by default with the Python binary installers. * A *virtual environment* is a semi-isolated Python environment that allows packages to be installed for use by a particular application, rather than being installed system wide. -* ``venv`` is the standard tool for creating virtual environments, and has - been part of Python since Python 3.3. Starting with Python 3.4, it - defaults to installing ``pip`` into all created virtual environments. -* ``virtualenv`` is a third party alternative (and predecessor) to - ``venv``. It allows virtual environments to be used on versions of - Python prior to 3.4, which either don't provide ``venv`` at all, or - aren't able to automatically install ``pip`` into created environments. -* The `Python Package Index `__ is a public +* ``venv`` is the standard tool for creating virtual environments. + It defaults to installing :program:`pip` into all created virtual environments. +* ``virtualenv`` is a third-party alternative (and predecessor) to + ``venv``. +* The `Python Package Index (PyPI) `__ is a public repository of open source licensed packages made available for use by other Python users. -* the `Python Packaging Authority +* The `Python Packaging Authority `__ is the group of developers and documentation authors responsible for the maintenance and evolution of the standard packaging tools and the associated metadata and file format standards. They maintain a variety of tools, documentation, and issue trackers on `GitHub `__. -* ``distutils`` is the original build and distribution system first added to - the Python standard library in 1998. While direct use of ``distutils`` is - being phased out, it still laid the foundation for the current packaging - and distribution infrastructure, and it not only remains part of the - standard library, but its name lives on in other ways (such as the name - of the mailing list used to coordinate Python packaging standards - development). .. versionchanged:: 3.5 The use of ``venv`` is now recommended for creating virtual environments. @@ -79,7 +67,7 @@ The standard packaging tools are all designed to be used from the command line. The following command will install the latest version of a module and its -dependencies from the Python Package Index:: +dependencies from PyPI:: python -m pip install SomePackage @@ -106,7 +94,7 @@ explicitly:: python -m pip install --upgrade SomePackage -More information and resources regarding ``pip`` and its capabilities can be +More information and resources regarding :program:`pip` and its capabilities can be found in the `Python Packaging User Guide `__. Creation of virtual environments is done through the :mod:`venv` module. @@ -124,19 +112,6 @@ How do I ...? These are quick answers or links for some common tasks. -... install ``pip`` in versions of Python prior to Python 3.4? --------------------------------------------------------------- - -Python only started bundling ``pip`` with Python 3.4. For earlier versions, -``pip`` needs to be "bootstrapped" as described in the Python Packaging -User Guide. - -.. seealso:: - - `Python Packaging User Guide: Requirements for Installing Packages - `__ - - .. installing-per-user-installation: ... install packages just for the current user? @@ -150,10 +125,10 @@ package just for the current user, rather than for all users of the system. --------------------------------------- A number of scientific Python packages have complex binary dependencies, and -aren't currently easy to install using ``pip`` directly. At this point in -time, it will often be easier for users to install these packages by +aren't currently easy to install using :program:`pip` directly. +It will often be easier for users to install these packages by `other means `__ -rather than attempting to install them with ``pip``. +rather than attempting to install them with :program:`pip`. .. seealso:: @@ -166,29 +141,25 @@ rather than attempting to install them with ``pip``. On Linux, macOS, and other POSIX systems, use the versioned Python commands in combination with the ``-m`` switch to run the appropriate copy of -``pip``:: +:program:`pip`:: - python2 -m pip install SomePackage # default Python 2 - python2.7 -m pip install SomePackage # specifically Python 2.7 - python3 -m pip install SomePackage # default Python 3 - python3.4 -m pip install SomePackage # specifically Python 3.4 + python3 -m pip install SomePackage # default Python 3 + python3.14 -m pip install SomePackage # specifically Python 3.14 -Appropriately versioned ``pip`` commands may also be available. +Appropriately versioned :program:`pip` commands may also be available. -On Windows, use the ``py`` Python launcher in combination with the ``-m`` +On Windows, use the :program:`py` Python launcher in combination with the ``-m`` switch:: - py -2 -m pip install SomePackage # default Python 2 - py -2.7 -m pip install SomePackage # specifically Python 2.7 - py -3 -m pip install SomePackage # default Python 3 - py -3.4 -m pip install SomePackage # specifically Python 3.4 + py -3 -m pip install SomePackage # default Python 3 + py -3.14 -m pip install SomePackage # specifically Python 3.14 .. other questions: Once the Development & Deployment part of PPUG is fleshed out, some of those sections should be linked from new questions here (most notably, we should have a question about avoiding depending on PyPI that links to - https://packaging.python.org/en/latest/mirrors/) + https://packaging.python.org/en/latest/guides/index-mirrors-and-caches/) Common installation issues @@ -201,39 +172,38 @@ On Linux systems, a Python installation will typically be included as part of the distribution. Installing into this Python installation requires root access to the system, and may interfere with the operation of the system package manager and other components of the system if a component -is unexpectedly upgraded using ``pip``. +is unexpectedly upgraded using :program:`pip`. On such systems, it is often better to use a virtual environment or a -per-user installation when installing packages with ``pip``. +per-user installation when installing packages with :program:`pip`. Pip not installed ----------------- -It is possible that ``pip`` does not get installed by default. One potential fix is:: +It is possible that :program:`pip` does not get installed by default. One potential fix is:: python -m ensurepip --default-pip -There are also additional resources for `installing pip. -`__ +There are also additional resources for `installing pip +`__. Installing binary extensions ---------------------------- -Python has typically relied heavily on source based distribution, with end +Python once relied heavily on source-based distribution, with end users being expected to compile extension modules from source as part of the installation process. -With the introduction of support for the binary ``wheel`` format, and the -ability to publish wheels for at least Windows and macOS through the -Python Package Index, this problem is expected to diminish over time, +With the introduction of the binary wheel format, and the +ability to publish wheels through PyPI, this problem is diminishing, as users are more regularly able to install pre-built extensions rather than needing to build them themselves. Some of the solutions for installing `scientific software `__ -that are not yet available as pre-built ``wheel`` files may also help with +that are not yet available as pre-built wheel files may also help with obtaining other binary extensions without needing to build them locally. .. seealso:: diff --git a/Doc/library/__future__.rst b/Doc/library/__future__.rst index 4f3b663006fb28..749e4543c5b823 100644 --- a/Doc/library/__future__.rst +++ b/Doc/library/__future__.rst @@ -15,7 +15,7 @@ before the release in which the feature becomes standard. While these future statements are given additional special meaning by the Python compiler, they are still executed like any other import statement and -the :mod:`__future__` exists and is handled by the import system the same way +the :mod:`!__future__` exists and is handled by the import system the same way any other Python module would be. This design serves three purposes: * To avoid confusing existing tools that analyze import statements and expect to @@ -23,52 +23,66 @@ any other Python module would be. This design serves three purposes: * To document when incompatible changes were introduced, and when they will be --- or were --- made mandatory. This is a form of executable documentation, and - can be inspected programmatically via importing :mod:`__future__` and examining + can be inspected programmatically via importing :mod:`!__future__` and examining its contents. * To ensure that :ref:`future statements ` run under releases prior to - Python 2.1 at least yield runtime exceptions (the import of :mod:`__future__` + Python 2.1 at least yield runtime exceptions (the import of :mod:`!__future__` will fail, because there was no module of that name prior to 2.1). Module Contents --------------- -No feature description will ever be deleted from :mod:`__future__`. Since its +No feature description will ever be deleted from :mod:`!__future__`. Since its introduction in Python 2.1 the following features have found their way into the language using this mechanism: -+------------------+-------------+--------------+---------------------------------------------+ -| feature | optional in | mandatory in | effect | -+==================+=============+==============+=============================================+ -| nested_scopes | 2.1.0b1 | 2.2 | :pep:`227`: | -| | | | *Statically Nested Scopes* | -+------------------+-------------+--------------+---------------------------------------------+ -| generators | 2.2.0a1 | 2.3 | :pep:`255`: | -| | | | *Simple Generators* | -+------------------+-------------+--------------+---------------------------------------------+ -| division | 2.2.0a2 | 3.0 | :pep:`238`: | -| | | | *Changing the Division Operator* | -+------------------+-------------+--------------+---------------------------------------------+ -| absolute_import | 2.5.0a1 | 3.0 | :pep:`328`: | -| | | | *Imports: Multi-Line and Absolute/Relative* | -+------------------+-------------+--------------+---------------------------------------------+ -| with_statement | 2.5.0a1 | 2.6 | :pep:`343`: | -| | | | *The "with" Statement* | -+------------------+-------------+--------------+---------------------------------------------+ -| print_function | 2.6.0a2 | 3.0 | :pep:`3105`: | -| | | | *Make print a function* | -+------------------+-------------+--------------+---------------------------------------------+ -| unicode_literals | 2.6.0a2 | 3.0 | :pep:`3112`: | -| | | | *Bytes literals in Python 3000* | -+------------------+-------------+--------------+---------------------------------------------+ -| generator_stop | 3.5.0b1 | 3.7 | :pep:`479`: | -| | | | *StopIteration handling inside generators* | -+------------------+-------------+--------------+---------------------------------------------+ -| annotations | 3.7.0b1 | Never [1]_ | :pep:`563`: | -| | | | *Postponed evaluation of annotations*, | -| | | | :pep:`649`: *Deferred evaluation of | -| | | | annotations using descriptors* | -+------------------+-------------+--------------+---------------------------------------------+ + +.. list-table:: + :widths: auto + :header-rows: 1 + + * * feature + * optional in + * mandatory in + * effect + * * .. data:: nested_scopes + * 2.1.0b1 + * 2.2 + * :pep:`227`: *Statically Nested Scopes* + * * .. data:: generators + * 2.2.0a1 + * 2.3 + * :pep:`255`: *Simple Generators* + * * .. data:: division + * 2.2.0a2 + * 3.0 + * :pep:`238`: *Changing the Division Operator* + * * .. data:: absolute_import + * 2.5.0a1 + * 3.0 + * :pep:`328`: *Imports: Multi-Line and Absolute/Relative* + * * .. data:: with_statement + * 2.5.0a1 + * 2.6 + * :pep:`343`: *The “with” Statement* + * * .. data:: print_function + * 2.6.0a2 + * 3.0 + * :pep:`3105`: *Make print a function* + * * .. data:: unicode_literals + * 2.6.0a2 + * 3.0 + * :pep:`3112`: *Bytes literals in Python 3000* + * * .. data:: generator_stop + * 3.5.0b1 + * 3.7 + * :pep:`479`: *StopIteration handling inside generators* + * * .. data:: annotations + * 3.7.0b1 + * Never [1]_ + * :pep:`563`: *Postponed evaluation of annotations*, + :pep:`649`: *Deferred evaluation of annotations using descriptors* .. XXX Adding a new entry? Remember to update simple_stmts.rst, too. diff --git a/Doc/library/_thread.rst b/Doc/library/_thread.rst index ed29ac70035597..c48e6437ec21ad 100644 --- a/Doc/library/_thread.rst +++ b/Doc/library/_thread.rst @@ -36,11 +36,6 @@ This module defines the following constants and functions: This is now a synonym of the built-in :exc:`RuntimeError`. -.. data:: LockType - - This is the type of lock objects. - - .. function:: start_new_thread(function, args[, kwargs]) Start a new thread and return its identifier. The thread executes the @@ -159,58 +154,66 @@ This module defines the following constants and functions: .. versionadded:: 3.2 -Lock objects have the following methods: +.. raw:: html + + + + + +.. class:: LockType -.. method:: lock.acquire(blocking=True, timeout=-1) + This is the type of lock objects. - Without any optional argument, this method acquires the lock unconditionally, if - necessary waiting until it is released by another thread (only one thread at a - time can acquire a lock --- that's their reason for existence). + Lock objects have the following methods: - If the *blocking* argument is present, the action depends on its - value: if it is false, the lock is only acquired if it can be acquired - immediately without waiting, while if it is true, the lock is acquired - unconditionally as above. + .. method:: acquire(blocking=True, timeout=-1) - If the floating-point *timeout* argument is present and positive, it - specifies the maximum wait time in seconds before returning. A negative - *timeout* argument specifies an unbounded wait. You cannot specify - a *timeout* if *blocking* is false. + Without any optional argument, this method acquires the lock unconditionally, if + necessary waiting until it is released by another thread (only one thread at a + time can acquire a lock --- that's their reason for existence). - The return value is ``True`` if the lock is acquired successfully, - ``False`` if not. + If the *blocking* argument is present, the action depends on its + value: if it is false, the lock is only acquired if it can be acquired + immediately without waiting, while if it is true, the lock is acquired + unconditionally as above. - .. versionchanged:: 3.2 - The *timeout* parameter is new. + If the floating-point *timeout* argument is present and positive, it + specifies the maximum wait time in seconds before returning. A negative + *timeout* argument specifies an unbounded wait. You cannot specify + a *timeout* if *blocking* is false. - .. versionchanged:: 3.2 - Lock acquires can now be interrupted by signals on POSIX. + The return value is ``True`` if the lock is acquired successfully, + ``False`` if not. - .. versionchanged:: 3.14 - Lock acquires can now be interrupted by signals on Windows. + .. versionchanged:: 3.2 + The *timeout* parameter is new. + .. versionchanged:: 3.2 + Lock acquires can now be interrupted by signals on POSIX. -.. method:: lock.release() + .. versionchanged:: 3.14 + Lock acquires can now be interrupted by signals on Windows. - Releases the lock. The lock must have been acquired earlier, but not - necessarily by the same thread. + .. method:: release() + Releases the lock. The lock must have been acquired earlier, but not + necessarily by the same thread. -.. method:: lock.locked() + .. method:: locked() - Return the status of the lock: ``True`` if it has been acquired by some thread, - ``False`` if not. + Return the status of the lock: ``True`` if it has been acquired by some thread, + ``False`` if not. -In addition to these methods, lock objects can also be used via the -:keyword:`with` statement, e.g.:: + In addition to these methods, lock objects can also be used via the + :keyword:`with` statement, e.g.:: - import _thread + import _thread - a_lock = _thread.allocate_lock() + a_lock = _thread.allocate_lock() - with a_lock: - print("a_lock is locked while this executes") + with a_lock: + print("a_lock is locked while this executes") **Caveats:** diff --git a/Doc/library/abc.rst b/Doc/library/abc.rst index 49e541a9d9b1cb..4b3c9f2b73d7a7 100644 --- a/Doc/library/abc.rst +++ b/Doc/library/abc.rst @@ -170,17 +170,17 @@ The :mod:`!abc` module also provides the following decorator: or is derived from it. A class that has a metaclass derived from :class:`!ABCMeta` cannot be instantiated unless all of its abstract methods and properties are overridden. The abstract methods can be called using any - of the normal 'super' call mechanisms. :func:`!abstractmethod` may be used + of the normal 'super' call mechanisms. :deco:`!abstractmethod` may be used to declare abstract methods for properties and descriptors. Dynamically adding abstract methods to a class, or attempting to modify the abstraction status of a method or class once it is created, are only supported using the :func:`update_abstractmethods` function. The - :func:`!abstractmethod` only affects subclasses derived using regular + :deco:`!abstractmethod` only affects subclasses derived using regular inheritance; "virtual subclasses" registered with the ABC's :meth:`~ABCMeta.register` method are not affected. - When :func:`!abstractmethod` is applied in combination with other method + When :deco:`!abstractmethod` is applied in combination with other method descriptors, it should be applied as the innermost decorator, as shown in the following usage examples:: @@ -218,7 +218,7 @@ The :mod:`!abc` module also provides the following decorator: the descriptor must identify itself as abstract using :attr:`!__isabstractmethod__`. In general, this attribute should be ``True`` if any of the methods used to compose the descriptor are abstract. For - example, Python's built-in :class:`property` does the equivalent of:: + example, Python's built-in :deco:`property` does the equivalent of:: class Descriptor: ... @@ -242,13 +242,13 @@ The :mod:`!abc` module also supports the following legacy decorators: .. versionadded:: 3.2 .. deprecated:: 3.3 - It is now possible to use :class:`classmethod` with - :func:`abstractmethod`, making this decorator redundant. + It is now possible to use :deco:`classmethod` with + :deco:`abstractmethod`, making this decorator redundant. - A subclass of the built-in :func:`classmethod`, indicating an abstract - classmethod. Otherwise it is similar to :func:`abstractmethod`. + A subclass of the built-in :class:`classmethod`, indicating an abstract + classmethod. Otherwise it is similar to :deco:`abstractmethod`. - This special case is deprecated, as the :func:`classmethod` decorator + This special case is deprecated, as the :deco:`classmethod` decorator is now correctly identified as abstract when applied to an abstract method:: @@ -263,13 +263,13 @@ The :mod:`!abc` module also supports the following legacy decorators: .. versionadded:: 3.2 .. deprecated:: 3.3 - It is now possible to use :class:`staticmethod` with - :func:`abstractmethod`, making this decorator redundant. + It is now possible to use :deco:`staticmethod` with + :deco:`abstractmethod`, making this decorator redundant. - A subclass of the built-in :func:`staticmethod`, indicating an abstract - staticmethod. Otherwise it is similar to :func:`abstractmethod`. + A subclass of the built-in :class:`staticmethod`, indicating an abstract + staticmethod. Otherwise it is similar to :deco:`abstractmethod`. - This special case is deprecated, as the :func:`staticmethod` decorator + This special case is deprecated, as the :deco:`staticmethod` decorator is now correctly identified as abstract when applied to an abstract method:: @@ -283,14 +283,14 @@ The :mod:`!abc` module also supports the following legacy decorators: .. decorator:: abstractproperty .. deprecated:: 3.3 - It is now possible to use :class:`property`, :meth:`property.getter`, - :meth:`property.setter` and :meth:`property.deleter` with - :func:`abstractmethod`, making this decorator redundant. + It is now possible to use :deco:`property`, :deco:`property.getter`, + :deco:`property.setter` and :deco:`property.deleter` with + :deco:`abstractmethod`, making this decorator redundant. - A subclass of the built-in :func:`property`, indicating an abstract + A subclass of the built-in :class:`property`, indicating an abstract property. - This special case is deprecated, as the :func:`property` decorator + This special case is deprecated, as the :deco:`property` decorator is now correctly identified as abstract when applied to an abstract method:: diff --git a/Doc/library/annotationlib.rst b/Doc/library/annotationlib.rst index ff9578b6088f28..5703564c5a7d5d 100644 --- a/Doc/library/annotationlib.rst +++ b/Doc/library/annotationlib.rst @@ -4,6 +4,7 @@ .. module:: annotationlib :synopsis: Functionality for introspecting annotations +.. versionadded:: 3.14 **Source code:** :source:`Lib/annotationlib.py` @@ -45,6 +46,10 @@ and :func:`call_annotate_function`, as well as the :func:`call_evaluate_function` function for working with :term:`evaluate functions `. +.. caution:: + + Most functionality in this module can execute arbitrary code; see + :ref:`the security section ` for more information. .. seealso:: @@ -127,16 +132,27 @@ Classes Values are the result of evaluating the annotation expressions. - .. attribute:: FORWARDREF + .. attribute:: VALUE_WITH_FAKE_GLOBALS :value: 2 + Special value used to signal that an annotate function is being + evaluated in a special environment with fake globals. When passed this + value, annotate functions should either return the same value as for + the :attr:`Format.VALUE` format, or raise :exc:`NotImplementedError` + to signal that they do not support execution in this environment. + This format is only used internally and should not be passed to + the functions in this module. + + .. attribute:: FORWARDREF + :value: 3 + Values are real annotation values (as per :attr:`Format.VALUE` format) for defined values, and :class:`ForwardRef` proxies for undefined values. Real objects may contain references to :class:`ForwardRef` proxy objects. .. attribute:: STRING - :value: 3 + :value: 4 Values are the text string of the annotation as it appears in the source code, up to modifications including, but not restricted to, @@ -144,17 +160,6 @@ Classes The exact values of these strings may change in future versions of Python. - .. attribute:: VALUE_WITH_FAKE_GLOBALS - :value: 4 - - Special value used to signal that an annotate function is being - evaluated in a special environment with fake globals. When passed this - value, annotate functions should either return the same value as for - the :attr:`Format.VALUE` format, or raise :exc:`NotImplementedError` - to signal that they do not support execution in this environment. - This format is only used internally and should not be passed to - the functions in this module. - .. versionadded:: 3.14 .. class:: ForwardRef @@ -211,6 +216,10 @@ Classes means may not have any information about their scope, so passing arguments to this method may be necessary to evaluate them successfully. + If no *owner*, *globals*, *locals*, or *type_params* are provided and the + :class:`~ForwardRef` does not contain information about its origin, + empty globals and locals dictionaries are used. + .. versionadded:: 3.14 @@ -226,8 +235,8 @@ Functions annotate functions that support the :attr:`~Format.STRING` format but do not have access to the code creating the annotations. - For example, this is used to implement the :attr:`~Format.STRING` for - :class:`typing.TypedDict` classes created through the functional syntax: + For example, this is used to implement the :attr:`~Format.STRING` format + for :class:`typing.TypedDict` classes created through the functional syntax: .. doctest:: @@ -331,14 +340,29 @@ Functions * VALUE: :attr:`!object.__annotations__` is tried first; if that does not exist, the :attr:`!object.__annotate__` function is called if it exists. + * FORWARDREF: If :attr:`!object.__annotations__` exists and can be evaluated successfully, it is used; otherwise, the :attr:`!object.__annotate__` function is called. If it does not exist either, :attr:`!object.__annotations__` is tried again and any error from accessing it is re-raised. + + * When calling :attr:`!object.__annotate__` it is first called with :attr:`~Format.FORWARDREF`. + If this is not implemented, it will then check if :attr:`~Format.VALUE_WITH_FAKE_GLOBALS` + is supported and use that in the fake globals environment. + If neither of these formats are supported, it will fall back to using :attr:`~Format.VALUE`. + If :attr:`~Format.VALUE` fails, the error from this call will be raised. + * STRING: If :attr:`!object.__annotate__` exists, it is called first; otherwise, :attr:`!object.__annotations__` is used and stringified using :func:`annotations_to_string`. + * When calling :attr:`!object.__annotate__` it is first called with :attr:`~Format.STRING`. + If this is not implemented, it will then check if :attr:`~Format.VALUE_WITH_FAKE_GLOBALS` + is supported and use that in the fake globals environment. + If neither of these formats are supported, it will fall back to using :attr:`~Format.VALUE` + with the result converted using :func:`annotations_to_string`. + If :attr:`~Format.VALUE` fails, the error from this call will be raised. + Returns a dict. :func:`!get_annotations` returns a new dict every time it's called; calling it twice on the same object will return two different but equivalent dicts. @@ -485,3 +509,212 @@ annotations from the class and puts them in a separate attribute: typ.classvars = classvars # Store the ClassVars in a separate attribute return typ + +Creating a custom callable annotate function +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Custom :term:`annotate functions ` may be literal functions like those +automatically generated for functions, classes, and modules. Or, they may wish to utilise +the encapsulation provided by classes, in which case any :term:`callable` can be used as +an :term:`annotate function`. + +To provide the :attr:`~Format.VALUE`, :attr:`~Format.STRING`, or +:attr:`~Format.FORWARDREF` formats directly, an :term:`annotate function` must provide +the following attribute: + +* A callable ``__call__`` with signature ``__call__(format, /) -> dict``, that does not + raise a :exc:`NotImplementedError` when called with a supported format. + +To provide the :attr:`~Format.VALUE_WITH_FAKE_GLOBALS` format, which is used to +automatically generate :attr:`~Format.STRING` or :attr:`~Format.FORWARDREF` if they are +not supported directly, :term:`annotate functions ` must provide the +following attributes: + +* A callable ``__call__`` with signature ``__call__(format, /) -> dict``, that does not + raise a :exc:`NotImplementedError` when called with + :attr:`~Format.VALUE_WITH_FAKE_GLOBALS`. +* A :ref:`code object ` ``__code__`` containing the compiled code for the + annotate function. +* Optional: A tuple of the function's positional defaults ``__kwdefaults__``, if the + function represented by ``__code__`` uses any positional defaults. +* Optional: A dict of the function's keyword defaults ``__defaults__``, if the function + represented by ``__code__`` uses any keyword defaults. +* Optional: All other :ref:`function attributes `. + +.. code-block:: python + + class Annotate: + called_formats = [] + + def __call__(self, format=None, /, *, _self=None): + # When called with fake globals, `_self` will be the + # actual self value, and `self` will be the format. + if _self is not None: + self, format = _self, self + + self.called_formats.append(format) + if format <= 2: # VALUE or VALUE_WITH_FAKE_GLOBALS + return {"x": MyType} + raise NotImplementedError + + __code__ = __call__.__code__ + __defaults__ = (None,) + __kwdefaults__ = property(lambda self: dict(_self=self)) + + __globals__ = {} + __builtins__ = {} + __closure__ = None + +This can then be called with: + +.. code-block:: pycon + + >>> from annotationlib import call_annotate_function, Format + >>> call_annotate_function(Annotate(), format=Format.STRING) + {'x': 'MyType'} + +Or used as the annotate function for an object: + +.. code-block:: pycon + + >>> from annotationlib import get_annotations, Format + >>> class C: + ... pass + >>> C.__annotate__ = Annotate() + >>> get_annotations(Annotate(), format=Format.STRING) + {'x': 'MyType'} + + +Limitations of the ``STRING`` format +------------------------------------ + +The :attr:`~Format.STRING` format is meant to approximate the source code +of the annotation, but the implementation strategy used means that it is not +always possible to recover the exact source code. + +First, the stringifier of course cannot recover any information that is not present in +the compiled code, including comments, whitespace, parenthesization, and operations that +get simplified by the compiler. + +Second, the stringifier can intercept almost all operations that involve names looked +up in some scope, but it cannot intercept operations that operate fully on constants. +As a corollary, this also means it is not safe to request the ``STRING`` format on +untrusted code: Python is powerful enough that it is possible to achieve arbitrary +code execution even with no access to any globals or builtins. For example: + +.. code-block:: pycon + + >>> def f(x: (1).__class__.__base__.__subclasses__()[-1].__init__.__builtins__["print"]("Hello world")): pass + ... + >>> annotationlib.get_annotations(f, format=annotationlib.Format.STRING) + Hello world + {'x': 'None'} + +.. note:: + This particular example works as of the time of writing, but it relies on + implementation details and is not guaranteed to work in the future. + +Among the different kinds of expressions that exist in Python, +as represented by the :mod:`ast` module, some expressions are supported, +meaning that the ``STRING`` format can generally recover the original source code; +others are unsupported, meaning that they may result in incorrect output or an error. + +The following are supported (sometimes with caveats): + +* :class:`ast.BinOp` +* :class:`ast.UnaryOp` + + * :class:`ast.Invert` (``~``), :class:`ast.UAdd` (``+``), and :class:`ast.USub` (``-``) are supported + * :class:`ast.Not` (``not``) is not supported + +* :class:`ast.Dict` (except when using ``**`` unpacking) +* :class:`ast.Set` +* :class:`ast.Compare` + + * :class:`ast.Eq` and :class:`ast.NotEq` are supported + * :class:`ast.Lt`, :class:`ast.LtE`, :class:`ast.Gt`, and :class:`ast.GtE` are supported, but the operand may be flipped + * :class:`ast.Is`, :class:`ast.IsNot`, :class:`ast.In`, and :class:`ast.NotIn` are not supported + +* :class:`ast.Call` (except when using ``**`` unpacking) +* :class:`ast.Constant` (though not the exact representation of the constant; for example, escape + sequences in strings are lost; hexadecimal numbers are converted to decimal) +* :class:`ast.Attribute` (assuming the value is not a constant) +* :class:`ast.Subscript` (assuming the value is not a constant) +* :class:`ast.Starred` (``*`` unpacking) +* :class:`ast.Name` +* :class:`ast.List` +* :class:`ast.Tuple` +* :class:`ast.Slice` + +The following are unsupported, but throw an informative error when encountered by the +stringifier: + +* :class:`ast.FormattedValue` (f-strings; error is not detected if conversion specifiers like ``!r`` + are used) +* :class:`ast.JoinedStr` (f-strings) + +The following are unsupported and result in incorrect output: + +* :class:`ast.BoolOp` (``and`` and ``or``) +* :class:`ast.IfExp` +* :class:`ast.Lambda` +* :class:`ast.ListComp` +* :class:`ast.SetComp` +* :class:`ast.DictComp` +* :class:`ast.GeneratorExp` + +The following are disallowed in annotation scopes and therefore not relevant: + +* :class:`ast.NamedExpr` (``:=``) +* :class:`ast.Await` +* :class:`ast.Yield` +* :class:`ast.YieldFrom` + + +Limitations of the ``FORWARDREF`` format +---------------------------------------- + +The :attr:`~Format.FORWARDREF` format aims to produce real values as much +as possible, with anything that cannot be resolved replaced with +:class:`ForwardRef` objects. It is affected by broadly the same Limitations +as the :attr:`~Format.STRING` format: annotations that perform operations on +literals or that use unsupported expression types may raise exceptions when +evaluated using the :attr:`~Format.FORWARDREF` format. + +Below are a few examples of the behavior with unsupported expressions: + +.. code-block:: pycon + + >>> from annotationlib import get_annotations, Format + >>> def zerodiv(x: 1 / 0): ... + >>> get_annotations(zerodiv, format=Format.STRING) + Traceback (most recent call last): + ... + ZeroDivisionError: division by zero + >>> get_annotations(zerodiv, format=Format.FORWARDREF) + Traceback (most recent call last): + ... + ZeroDivisionError: division by zero + >>> def ifexp(x: 1 if y else 0): ... + >>> get_annotations(ifexp, format=Format.STRING) + {'x': '1'} + +.. _annotationlib-security: + +Security implications of introspecting annotations +-------------------------------------------------- + +Much of the functionality in this module involves executing code related to annotations, +which can then do arbitrary things. For example, +:func:`get_annotations` may call an arbitrary :term:`annotate function`, and +:meth:`ForwardRef.evaluate` may call :func:`eval` on an arbitrary string. Code contained +in an annotation might make arbitrary system calls, enter an infinite loop, or perform any +other operation. This is also true for any access of the :attr:`~object.__annotations__` attribute, +and for various functions in the :mod:`typing` module that work with annotations, such as +:func:`typing.get_type_hints`. + +Any security issue arising from this also applies immediately after importing +code that may contain untrusted annotations: importing code can always cause arbitrary operations +to be performed. However, it is unsafe to accept strings or other input from an untrusted source and +pass them to any of the APIs for introspecting annotations, for example by editing an +``__annotations__`` dictionary or directly creating a :class:`ForwardRef` object. diff --git a/Doc/library/archiving.rst b/Doc/library/archiving.rst index c9284949af4972..da0b3f8c3e7693 100644 --- a/Doc/library/archiving.rst +++ b/Doc/library/archiving.rst @@ -5,13 +5,15 @@ Data Compression and Archiving ****************************** The modules described in this chapter support data compression with the zlib, -gzip, bzip2 and lzma algorithms, and the creation of ZIP- and tar-format +gzip, bzip2, lzma, and zstd algorithms, and the creation of ZIP- and tar-format archives. See also :ref:`archiving-operations` provided by the :mod:`shutil` module. .. toctree:: + compression.rst + compression.zstd.rst zlib.rst gzip.rst bz2.rst diff --git a/Doc/library/argparse.rst b/Doc/library/argparse.rst index 29396c7a0366a1..6e3d0fea9ec9b0 100644 --- a/Doc/library/argparse.rst +++ b/Doc/library/argparse.rst @@ -13,7 +13,7 @@ .. note:: - While :mod:`argparse` is the default recommended standard library module + While :mod:`!argparse` is the default recommended standard library module for implementing basic command line applications, authors with more exacting requirements for exactly how their command line applications behave may find it doesn't provide the necessary level of control. @@ -74,7 +74,7 @@ ArgumentParser objects prefix_chars='-', fromfile_prefix_chars=None, \ argument_default=None, conflict_handler='error', \ add_help=True, allow_abbrev=True, exit_on_error=True, \ - *, suggest_on_error=False, color=False) + *, suggest_on_error=False, color=True) Create a new :class:`ArgumentParser` object. All parameters should be passed as keyword arguments. Each parameter has its own more detailed description @@ -119,7 +119,7 @@ ArgumentParser objects * suggest_on_error_ - Enables suggestions for mistyped argument choices and subparser names (default: ``False``) - * color_ - Allow color output (default: ``False``) + * color_ - Allow color output (default: ``True``) .. versionchanged:: 3.5 *allow_abbrev* parameter was added. @@ -434,12 +434,17 @@ arguments they contain. For example:: >>> parser.parse_args(['-f', 'foo', '@args.txt']) Namespace(f='bar') -Arguments read from a file must by default be one per line (but see also +Arguments read from a file must be one per line by default (but see also :meth:`~ArgumentParser.convert_arg_line_to_args`) and are treated as if they were in the same place as the original file referencing argument on the command line. So in the example above, the expression ``['-f', 'foo', '@args.txt']`` is considered equivalent to the expression ``['-f', 'foo', '-f', 'bar']``. +.. note:: + + Each line is treated as a single argument, so an empty line is read as an + empty string (``''``). + :class:`ArgumentParser` uses :term:`filesystem encoding and error handler` to read the file containing arguments. @@ -598,13 +603,11 @@ subparser names, the feature can be enabled by setting ``suggest_on_error`` to ``True``. Note that this only applies for arguments when the choices specified are strings:: - >>> parser = argparse.ArgumentParser(description='Process some integers.', - suggest_on_error=True) - >>> parser.add_argument('--action', choices=['sum', 'max']) - >>> parser.add_argument('integers', metavar='N', type=int, nargs='+', - ... help='an integer for the accumulator') - >>> parser.parse_args(['--action', 'sumn', 1, 2, 3]) - tester.py: error: argument --action: invalid choice: 'sumn', maybe you meant 'sum'? (choose from 'sum', 'max') + >>> parser = argparse.ArgumentParser(suggest_on_error=True) + >>> parser.add_argument('--action', choices=['debug', 'dryrun']) + >>> parser.parse_args(['--action', 'debugg']) + usage: tester.py [-h] [--action {debug,dryrun}] + tester.py: error: argument --action: invalid choice: 'debugg', maybe you meant 'debug'? (choose from debug, dryrun) If you're writing code that needs to be compatible with older Python versions and want to opportunistically use ``suggest_on_error`` when it's available, you @@ -620,26 +623,30 @@ keyword argument:: color ^^^^^ -By default, the help message is printed in plain text. If you want to allow -color in help messages, you can enable it by setting ``color`` to ``True``:: +By default, the help message is printed in color using `ANSI escape sequences +`__. +If you want plain text help messages, you can disable this :ref:`in your local +environment `, or in the argument parser itself +by setting ``color`` to ``False``:: >>> parser = argparse.ArgumentParser(description='Process some integers.', - ... color=True) + ... color=False) >>> parser.add_argument('--action', choices=['sum', 'max']) >>> parser.add_argument('integers', metavar='N', type=int, nargs='+', ... help='an integer for the accumulator') >>> parser.parse_args(['--help']) -Even if a CLI author has enabled color, it can be -:ref:`controlled using environment variables `. +Note that when ``color=True``, colored output depends on both environment +variables and terminal capabilities. However, if ``color=False``, colored +output is always disabled, even if environment variables like ``FORCE_COLOR`` +are set. -If you're writing code that needs to be compatible with older Python versions -and want to opportunistically use ``color`` when it's available, you -can set it as an attribute after initializing the parser instead of using the -keyword argument:: +.. note:: - >>> parser = argparse.ArgumentParser(description='Process some integers.') - >>> parser.color = True + Error messages will include color codes when redirecting stderr to a + file. To avoid this, set the |NO_COLOR|_ or :envvar:`PYTHON_COLORS` + environment variable (for example, + ``NO_COLOR=1 python script.py 2> errors.txt``). .. versionadded:: 3.14 @@ -683,6 +690,8 @@ The add_argument() method * deprecated_ - Whether or not use of the argument is deprecated. + The method returns an :class:`Action` object representing the argument. + The following sections describe how each of these are used. @@ -724,13 +733,13 @@ By default, :mod:`!argparse` automatically handles the internal naming and display names of arguments, simplifying the process without requiring additional configuration. As such, you do not need to specify the dest_ and metavar_ parameters. -The dest_ parameter defaults to the argument name with underscores ``_`` -replacing hyphens ``-`` . The metavar_ parameter defaults to the -upper-cased name. For example:: +For optional arguments, the dest_ parameter defaults to the argument name, with +underscores ``_`` replacing hyphens ``-``. The metavar_ parameter defaults to +the upper-cased name. For example:: >>> parser = argparse.ArgumentParser(prog='PROG') >>> parser.add_argument('--foo-bar') - >>> parser.parse_args(['--foo-bar', 'FOO-BAR'] + >>> parser.parse_args(['--foo-bar', 'FOO-BAR']) Namespace(foo_bar='FOO-BAR') >>> parser.print_help() usage: [-h] [--foo-bar FOO-BAR] @@ -765,9 +774,9 @@ how the command-line arguments should be handled. The supplied actions are: Namespace(foo=42) * ``'store_true'`` and ``'store_false'`` - These are special cases of - ``'store_const'`` used for storing the values ``True`` and ``False`` - respectively. In addition, they create default values of ``False`` and - ``True`` respectively:: + ``'store_const'`` that respectively store the values ``True`` and ``False`` + with default values of ``False`` and + ``True``:: >>> parser = argparse.ArgumentParser() >>> parser.add_argument('--foo', action='store_true') @@ -776,19 +785,19 @@ how the command-line arguments should be handled. The supplied actions are: >>> parser.parse_args('--foo --bar'.split()) Namespace(foo=True, bar=False, baz=True) -* ``'append'`` - This stores a list, and appends each argument value to the - list. It is useful to allow an option to be specified multiple times. - If the default value is non-empty, the default elements will be present - in the parsed value for the option, with any values from the - command line appended after those default values. Example usage:: +* ``'append'`` - This appends each argument value to a list. + It is useful for allowing an option to be specified multiple times. + If the default value is a non-empty list, the parsed value will start + with the default list's elements and any values from the command line + will be appended after those default values. Example usage:: >>> parser = argparse.ArgumentParser() - >>> parser.add_argument('--foo', action='append') + >>> parser.add_argument('--foo', action='append', default=['0']) >>> parser.parse_args('--foo 1 --foo 2'.split()) - Namespace(foo=['1', '2']) + Namespace(foo=['0', '1', '2']) -* ``'append_const'`` - This stores a list, and appends the value specified by - the const_ keyword argument to the list; note that the const_ keyword +* ``'append_const'`` - This appends the value specified by + the const_ keyword argument to a list; note that the const_ keyword argument defaults to ``None``. The ``'append_const'`` action is typically useful when multiple arguments need to store constants to the same list. For example:: @@ -799,8 +808,8 @@ how the command-line arguments should be handled. The supplied actions are: >>> parser.parse_args('--str --int'.split()) Namespace(types=[, ]) -* ``'extend'`` - This stores a list and appends each item from the multi-value - argument list to it. +* ``'extend'`` - This appends each item from a multi-value + argument to a list. The ``'extend'`` action is typically used with the nargs_ keyword argument value ``'+'`` or ``'*'``. Note that when nargs_ is ``None`` (the default) or ``'?'``, each @@ -814,7 +823,7 @@ how the command-line arguments should be handled. The supplied actions are: .. versionadded:: 3.8 -* ``'count'`` - This counts the number of times a keyword argument occurs. For +* ``'count'`` - This counts the number of times an argument occurs. For example, this is useful for increasing verbosity levels:: >>> parser = argparse.ArgumentParser() @@ -839,23 +848,11 @@ how the command-line arguments should be handled. The supplied actions are: >>> parser.parse_args(['--version']) PROG 2.0 -Only actions that consume command-line arguments (e.g. ``'store'``, -``'append'`` or ``'extend'``) can be used with positional arguments. - -.. class:: BooleanOptionalAction - - You may also specify an arbitrary action by passing an :class:`Action` subclass or - other object that implements the same interface. The :class:`!BooleanOptionalAction` - is available in :mod:`!argparse` and adds support for boolean actions such as - ``--foo`` and ``--no-foo``:: - - >>> import argparse - >>> parser = argparse.ArgumentParser() - >>> parser.add_argument('--foo', action=argparse.BooleanOptionalAction) - >>> parser.parse_args(['--no-foo']) - Namespace(foo=False) - - .. versionadded:: 3.9 +You may also specify an arbitrary action by passing an :class:`Action` subclass +(e.g. :class:`BooleanOptionalAction`) or other object that implements the same +interface. Only actions that consume command-line arguments (e.g. ``'store'``, +``'append'``, ``'extend'``, or custom actions with non-zero ``nargs``) can be used +with positional arguments. The recommended way to create a custom action is to extend :class:`Action`, overriding the :meth:`!__call__` method and optionally the :meth:`!__init__` and @@ -955,7 +952,7 @@ See also :ref:`specifying-ambiguous-arguments`. The supported values are: .. index:: single: + (plus); in argparse module -* ``'+'``. Just like ``'*'``, all command-line args present are gathered into a +* ``'+'``. Just like ``'*'``, all command-line arguments present are gathered into a list. Additionally, an error message will be generated if there wasn't at least one command-line argument present. For example:: @@ -995,8 +992,8 @@ the various :class:`ArgumentParser` actions. The two most common uses of it are (like ``-f`` or ``--foo``) and ``nargs='?'``. This creates an optional argument that can be followed by zero or one command-line arguments. When parsing the command line, if the option string is encountered with no - command-line argument following it, the value of ``const`` will be assumed to - be ``None`` instead. See the nargs_ description for examples. + command-line argument following it, the value from ``const`` will be used. + See the nargs_ description for examples. .. versionchanged:: 3.11 ``const=None`` by default, including when ``action='append_const'`` or @@ -1050,6 +1047,10 @@ is used when no command-line argument was present:: >>> parser.parse_args([]) Namespace(foo=42) +Because ``nargs='*'`` gathers any supplied values into a list, an absent +positional argument yields an empty list (``[]``). Only a non-``None`` +*default* overrides this (so ``default=None`` still gives ``[]``). + For required_ arguments, the ``default`` value is ignored. For example, this applies to positional arguments with nargs_ values other than ``?`` or ``*``, or optional arguments marked as ``required=True``. @@ -1113,7 +1114,15 @@ User defined functions can be used as well: The :func:`bool` function is not recommended as a type converter. All it does is convert empty strings to ``False`` and non-empty strings to ``True``. -This is usually not what is desired. +This is usually not what is desired:: + + >>> parser = argparse.ArgumentParser() + >>> _ = parser.add_argument('--verbose', type=bool) + >>> parser.parse_args(['--verbose', 'False']) + Namespace(verbose=True) + +See :class:`BooleanOptionalAction` or ``action='store_true'`` for common +alternatives. In general, the ``type`` keyword is a convenience that should only be used for simple conversions that can only raise one of the three supported exceptions. @@ -1156,16 +1165,21 @@ if the argument was not one of the acceptable values:: game.py: error: argument move: invalid choice: 'fire' (choose from 'rock', 'paper', 'scissors') -Note that inclusion in the *choices* sequence is checked after any type_ -conversions have been performed, so the type of the objects in the *choices* -sequence should match the type_ specified. - Any sequence can be passed as the *choices* value, so :class:`list` objects, :class:`tuple` objects, and custom sequences are all supported. Use of :class:`enum.Enum` is not recommended because it is difficult to control its appearance in usage, help, and error messages. +Note that *choices* are checked after any type_ +conversions have been performed, so objects in *choices* +should match the type_ specified. This can make *choices* +appear unfamiliar in usage, help, or error messages. + +To keep *choices* user-friendly, consider a custom type wrapper that +converts and formats values, or omit type_ and handle conversion in +your application code. + Formatted choices override the default *metavar* which is normally derived from *dest*. This is usually what you want because the user never sees the *dest* parameter. If this display isn't desirable (perhaps because there are @@ -1349,6 +1363,10 @@ behavior:: >>> parser.parse_args('--foo XXX'.split()) Namespace(bar='XXX') +Multiple arguments may share the same ``dest``. By default, the value from the +last such argument given on the command line wins. Use ``action='append'`` to +collect values from all of them into a list instead. For conflicting *option +strings* rather than ``dest`` names, see conflict_handler_. .. _deprecated: @@ -1429,6 +1447,21 @@ this API may be passed as the ``action`` parameter to and return a string which will be used when printing the usage of the program. If such method is not provided, a sensible default will be used. +.. class:: BooleanOptionalAction + + A subclass of :class:`Action` for handling boolean flags with positive + and negative options. Adding a single argument such as ``--foo`` automatically + creates both ``--foo`` and ``--no-foo`` options, storing ``True`` and ``False`` + respectively:: + + >>> import argparse + >>> parser = argparse.ArgumentParser() + >>> parser.add_argument('--foo', action=argparse.BooleanOptionalAction) + >>> parser.parse_args(['--no-foo']) + Namespace(foo=False) + + .. versionadded:: 3.9 + The parse_args() method ----------------------- @@ -1508,12 +1541,12 @@ it exits and prints the error along with a usage message:: >>> # invalid option >>> parser.parse_args(['--bar']) usage: PROG [-h] [--foo FOO] [bar] - PROG: error: no such option: --bar + PROG: error: unrecognized arguments: --bar >>> # wrong number of arguments >>> parser.parse_args(['spam', 'badger']) usage: PROG [-h] [--foo FOO] [bar] - PROG: error: extra arguments found: badger + PROG: error: unrecognized arguments: badger Arguments containing ``-`` @@ -1550,7 +1583,7 @@ there are no options in the parser that look like negative numbers:: >>> # negative number options present, so -2 is an option >>> parser.parse_args(['-2']) usage: PROG [-h] [-1 ONE] [foo] - PROG: error: no such option: -2 + PROG: error: unrecognized arguments: -2 >>> # negative number options present, so both -1s are options >>> parser.parse_args(['-1', '-1']) @@ -1568,6 +1601,11 @@ argument:: See also :ref:`the argparse howto on ambiguous arguments ` for more details. +.. versionchanged:: 3.14 + Negative-number matching was expanded to include numbers in scientific + notation (``-2.5e-6``), numbers containing underscores (``-1_234.5``), + and complex numbers (``-1.2e-3j``). + .. _prefix-matching: Argument abbreviations (prefix matching) @@ -1651,7 +1689,7 @@ The Namespace object Other utilities --------------- -Sub-commands +Subcommands ^^^^^^^^^^^^ .. method:: ArgumentParser.add_subparsers(*, [title], [description], [prog], \ @@ -1680,7 +1718,7 @@ Sub-commands * *description* - description for the sub-parser group in help output, by default ``None`` - * *prog* - usage information that will be displayed with sub-command help, + * *prog* - usage information that will be displayed with subcommand help, by default the name of the program and any positional arguments before the subparser argument @@ -1690,7 +1728,7 @@ Sub-commands * action_ - the basic type of action to be taken when this argument is encountered at the command line - * dest_ - name of the attribute under which sub-command name will be + * dest_ - name of the attribute under which subcommand name will be stored; by default ``None`` and no value is stored * required_ - Whether or not a subcommand must be provided, by default @@ -1729,6 +1767,11 @@ Sub-commands present, and when the ``b`` command is specified, only the ``foo`` and ``baz`` attributes are present. + If a subparser defines an argument with the same ``dest`` as the parent + parser, the two share a single namespace attribute, so the parent's value + won't be retained. Users should give them distinct ``dest`` values to + keep both. + Similarly, when a help message is requested from a subparser, only the help for that particular parser will be printed. The help message will not include parent parser or sibling parser messages. (A help message for each @@ -1908,7 +1951,7 @@ FileType objects run and then use the :keyword:`with`-statement to manage the files. .. versionchanged:: 3.4 - Added the *encodings* and *errors* parameters. + Added the *encoding* and *errors* parameters. .. deprecated:: 3.14 @@ -1970,6 +2013,9 @@ Argument groups Note that any arguments not in your user-defined groups will end up back in the usual "positional arguments" and "optional arguments" sections. + Within each argument group, arguments are displayed in help output in the + order in which they are added. + .. deprecated-removed:: 3.11 3.14 Calling :meth:`add_argument_group` on an argument group now raises an exception. This nesting was never supported, often failed to work @@ -2060,7 +2106,9 @@ Parser defaults >>> parser.parse_args(['736']) Namespace(bar=42, baz='badger', foo=736) - Note that parser-level defaults always override argument-level defaults:: + Note that defaults can be set at both the parser level using :meth:`set_defaults` + and at the argument level using :meth:`add_argument`. If both are called for the + same argument, the last default set for an argument is used:: >>> parser = argparse.ArgumentParser() >>> parser.add_argument('--foo', default='bar') @@ -2122,12 +2170,15 @@ Partial parsing .. method:: ArgumentParser.parse_known_args(args=None, namespace=None) - Sometimes a script may only parse a few of the command-line arguments, passing - the remaining arguments on to another script or program. In these cases, the - :meth:`~ArgumentParser.parse_known_args` method can be useful. It works much like - :meth:`~ArgumentParser.parse_args` except that it does not produce an error when - extra arguments are present. Instead, it returns a two item tuple containing - the populated namespace and the list of remaining argument strings. + Sometimes a script only needs to handle a specific set of command-line + arguments, leaving any unrecognized arguments for another script or program. + In these cases, the :meth:`~ArgumentParser.parse_known_args` method can be + useful. + + This method works similarly to :meth:`~ArgumentParser.parse_args`, but it does + not raise an error for extra, unrecognized arguments. Instead, it parses the + known arguments and returns a two item tuple that contains the populated + namespace and the list of any unrecognized arguments. :: @@ -2165,6 +2216,9 @@ Customizing file parsing def convert_arg_line_to_args(self, arg_line): return arg_line.split() + Note that with this override an argument can no longer contain spaces, since + each space-separated word becomes a separate argument. + Exiting methods ^^^^^^^^^^^^^^^ diff --git a/Doc/library/array.rst b/Doc/library/array.rst index e0b1eb89cf6c05..547bdfde87dbb2 100644 --- a/Doc/library/array.rst +++ b/Doc/library/array.rst @@ -9,7 +9,7 @@ -------------- This module defines an object type which can compactly represent an array of -basic values: characters, integers, floating-point numbers. Arrays are sequence +basic values: characters, integers, floating-point numbers. Arrays are mutable :term:`sequence` types and behave very much like lists, except that the type of objects stored in them is constrained. The type is specified at object creation time by using a :dfn:`type code`, which is a single character. The following type codes are @@ -24,7 +24,7 @@ defined: +-----------+--------------------+-------------------+-----------------------+-------+ | ``'u'`` | wchar_t | Unicode character | 2 | \(1) | +-----------+--------------------+-------------------+-----------------------+-------+ -| ``'w'`` | Py_UCS4 | Unicode character | 4 | | +| ``'w'`` | Py_UCS4 | Unicode character | 4 | \(2) | +-----------+--------------------+-------------------+-----------------------+-------+ | ``'h'`` | signed short | int | 2 | | +-----------+--------------------+-------------------+-----------------------+-------+ @@ -60,6 +60,16 @@ Notes: .. deprecated-removed:: 3.3 3.16 Please migrate to ``'w'`` typecode. +(2) + .. versionadded:: 3.13 + +.. seealso:: + + The :ref:`ctypes ` and + :ref:`struct ` modules, + as well as third-party modules like `numpy `__, + use similar -- but slightly different -- type codes. + The actual representation of values is determined by the machine architecture (strictly speaking, by the C implementation). The actual size can be accessed @@ -90,12 +100,14 @@ The module defines the following type: otherwise, the initializer's iterator is passed to the :meth:`extend` method to add initial items to the array. - Array objects support the ordinary sequence operations of indexing, slicing, + Array objects support the ordinary :ref:`mutable ` :term:`sequence` operations of indexing, slicing, concatenation, and multiplication. When using slice assignment, the assigned value must be an array object with the same type code; in all other cases, :exc:`TypeError` is raised. Array objects also implement the buffer interface, and may be used wherever :term:`bytes-like objects ` are supported. + Arrays are :ref:`generic ` over the type of their contents. + .. audit-event:: array.__new__ typecode,initializer array.array @@ -109,9 +121,9 @@ The module defines the following type: The length in bytes of one array item in the internal representation. - .. method:: append(x) + .. method:: append(value, /) - Append a new item with value *x* to the end of the array. + Append a new item with the specified value to the end of the array. .. method:: buffer_info() @@ -141,12 +153,12 @@ The module defines the following type: different byte order. - .. method:: count(x) + .. method:: count(value, /) - Return the number of occurrences of *x* in the array. + Return the number of occurrences of *value* in the array. - .. method:: extend(iterable) + .. method:: extend(iterable, /) Append items from *iterable* to the end of the array. If *iterable* is another array, it must have *exactly* the same type code; if not, :exc:`TypeError` will @@ -154,7 +166,7 @@ The module defines the following type: must be the right type to be appended to the array. - .. method:: frombytes(buffer) + .. method:: frombytes(buffer, /) Appends items from the :term:`bytes-like object`, interpreting its content as an array of machine values (as if it had been read @@ -164,7 +176,7 @@ The module defines the following type: :meth:`!fromstring` is renamed to :meth:`frombytes` for clarity. - .. method:: fromfile(f, n) + .. method:: fromfile(f, n, /) Read *n* items (as machine values) from the :term:`file object` *f* and append them to the end of the array. If less than *n* items are available, @@ -172,13 +184,13 @@ The module defines the following type: inserted into the array. - .. method:: fromlist(list) + .. method:: fromlist(list, /) Append items from the list. This is equivalent to ``for x in list: a.append(x)`` except that if there is a type error, the array is unchanged. - .. method:: fromunicode(s) + .. method:: fromunicode(ustr, /) Extends this array with data from the given Unicode string. The array must have type code ``'u'`` or ``'w'``; otherwise a :exc:`ValueError` is raised. @@ -186,33 +198,33 @@ The module defines the following type: array of some other type. - .. method:: index(x[, start[, stop]]) + .. method:: index(value[, start[, stop]]) Return the smallest *i* such that *i* is the index of the first occurrence of - *x* in the array. The optional arguments *start* and *stop* can be - specified to search for *x* within a subsection of the array. Raise - :exc:`ValueError` if *x* is not found. + *value* in the array. The optional arguments *start* and *stop* can be + specified to search for *value* within a subsection of the array. Raise + :exc:`ValueError` if *value* is not found. .. versionchanged:: 3.10 Added optional *start* and *stop* parameters. - .. method:: insert(i, x) + .. method:: insert(index, value, /) - Insert a new item with value *x* in the array before position *i*. Negative + Insert a new item *value* in the array before position *index*. Negative values are treated as being relative to the end of the array. - .. method:: pop([i]) + .. method:: pop(index=-1, /) Removes the item with the index *i* from the array and returns it. The optional argument defaults to ``-1``, so that by default the last item is removed and returned. - .. method:: remove(x) + .. method:: remove(value, /) - Remove the first occurrence of *x* from the array. + Remove the first occurrence of *value* from the array. .. method:: clear() @@ -237,7 +249,7 @@ The module defines the following type: :meth:`!tostring` is renamed to :meth:`tobytes` for clarity. - .. method:: tofile(f) + .. method:: tofile(f, /) Write all items (as machine values) to the :term:`file object` *f*. diff --git a/Doc/library/ast.rst b/Doc/library/ast.rst index ca9a6b0712c9a2..5338d407ca2259 100644 --- a/Doc/library/ast.rst +++ b/Doc/library/ast.rst @@ -15,7 +15,7 @@ -------------- -The :mod:`ast` module helps Python applications to process trees of the Python +The :mod:`!ast` module helps Python applications to process trees of the Python abstract syntax grammar. The abstract syntax itself might change with each Python release; this module helps to find out programmatically what the current grammar looks like. @@ -46,7 +46,7 @@ Node classes This is the base of all AST node classes. The actual node classes are derived from the :file:`Parser/Python.asdl` file, which is reproduced :ref:`above `. They are defined in the :mod:`!_ast` C - module and re-exported in :mod:`ast`. + module and re-exported in :mod:`!ast`. There is one class defined for each left-hand side symbol in the abstract grammar (for example, :class:`ast.stmt` or :class:`ast.expr`). In addition, @@ -134,17 +134,26 @@ Node classes Simple indices are represented by their value, extended slices are represented as tuples. +.. versionchanged:: 3.13 + + AST node constructors were changed to provide sensible defaults for omitted + fields: optional fields now default to ``None``, list fields default to an + empty list, and fields of type :class:`!ast.expr_context` default to + :class:`Load() `. Previously, omitted attributes would not exist on constructed + nodes (accessing them raised :exc:`AttributeError`). + .. versionchanged:: 3.14 The :meth:`~object.__repr__` output of :class:`~ast.AST` nodes includes the values of the node fields. -.. deprecated:: 3.8 +.. deprecated-removed:: 3.8 3.14 - Old classes :class:`!ast.Num`, :class:`!ast.Str`, :class:`!ast.Bytes`, - :class:`!ast.NameConstant` and :class:`!ast.Ellipsis` are still available, - but they will be removed in future Python releases. In the meantime, - instantiating them will return an instance of a different class. + Previous versions of Python provided the AST classes :class:`!ast.Num`, + :class:`!ast.Str`, :class:`!ast.Bytes`, :class:`!ast.NameConstant` and + :class:`!ast.Ellipsis`, which were deprecated in Python 3.8. These classes + were removed in Python 3.14, and their functionality has been replaced with + :class:`ast.Constant`. .. deprecated:: 3.9 @@ -265,18 +274,25 @@ Root nodes Literals ^^^^^^^^ -.. class:: Constant(value) +.. class:: Constant(value, kind) A constant value. The ``value`` attribute of the ``Constant`` literal contains the - Python object it represents. The values represented can be simple types - such as a number, string or ``None``, but also immutable container types - (tuples and frozensets) if all of their elements are constant. + Python object it represents. The values represented can be instances of :class:`str`, + :class:`bytes`, :class:`int`, :class:`float`, :class:`complex`, and :class:`bool`, + and the constants :data:`None` and :data:`Ellipsis`. + + The ``kind`` attribute is an optional string. For string literals with a + ``u`` prefix, ``kind`` is set to ``'u'``. For all other + constants, ``kind`` is ``None``. .. doctest:: >>> print(ast.dump(ast.parse('123', mode='eval'), indent=4)) Expression( body=Constant(value=123)) + >>> print(ast.dump(ast.parse("u'hello'", mode='eval'), indent=4)) + Expression( + body=Constant(value='hello', kind='u')) .. class:: FormattedValue(value, conversion, format_spec) @@ -290,9 +306,9 @@ Literals * ``conversion`` is an integer: * -1: no formatting - * 115: ``!s`` string formatting - * 114: ``!r`` repr formatting - * 97: ``!a`` ascii formatting + * 97 (``ord('a')``): ``!a`` :func:`ASCII ` formatting + * 114 (``ord('r')``): ``!r`` :func:`repr` formatting + * 115 (``ord('s')``): ``!s`` :func:`string ` formatting * ``format_spec`` is a :class:`JoinedStr` node representing the formatting of the value, or ``None`` if no format was specified. Both @@ -326,6 +342,63 @@ Literals Constant(value='.3')]))])) +.. class:: TemplateStr(values, /) + + .. versionadded:: 3.14 + + Node representing a template string literal, comprising a series of + :class:`Interpolation` and :class:`Constant` nodes. + These nodes may be any order, and do not need to be interleaved. + + .. doctest:: + + >>> expr = ast.parse('t"{name} finished {place:ordinal}"', mode='eval') + >>> print(ast.dump(expr, indent=4)) + Expression( + body=TemplateStr( + values=[ + Interpolation( + value=Name(id='name', ctx=Load()), + str='name', + conversion=-1), + Constant(value=' finished '), + Interpolation( + value=Name(id='place', ctx=Load()), + str='place', + conversion=-1, + format_spec=JoinedStr( + values=[ + Constant(value='ordinal')]))])) + +.. class:: Interpolation(value, str, conversion, format_spec=None) + + .. versionadded:: 3.14 + + Node representing a single interpolation field in a template string literal. + + * ``value`` is any expression node (such as a literal, a variable, or a + function call). + This has the same meaning as ``FormattedValue.value``. + * ``str`` is a constant containing the text of the interpolation expression. + + If ``str`` is set to ``None``, then ``value`` is used to generate code + when calling :func:`ast.unparse`. This no longer guarantees that the + generated code is identical to the original and is intended for code + generation. + * ``conversion`` is an integer: + + * -1: no conversion + * 97 (``ord('a')``): ``!a`` :func:`ASCII ` conversion + * 114 (``ord('r')``): ``!r`` :func:`repr` conversion + * 115 (``ord('s')``): ``!s`` :func:`string ` conversion + + This has the same meaning as ``FormattedValue.conversion``. + * ``format_spec`` is a :class:`JoinedStr` node representing the formatting + of the value, or ``None`` if no format was specified. Both + ``conversion`` and ``format_spec`` can be set at the same time. + This has the same meaning as ``FormattedValue.format_spec``. + + .. class:: List(elts, ctx) Tuple(elts, ctx) @@ -1291,7 +1364,7 @@ Control flow ``try`` blocks which are followed by ``except*`` clauses. The attributes are the same as for :class:`Try` but the :class:`ExceptHandler` nodes in ``handlers`` - are interpreted as ``except*`` blocks rather then ``except``. + are interpreted as ``except*`` blocks rather than ``except``. .. doctest:: @@ -2159,10 +2232,10 @@ Async and await occurrences of the same value (for example, :class:`ast.Add`). -:mod:`ast` helpers ------------------- +:mod:`!ast` helpers +------------------- -Apart from the node classes, the :mod:`ast` module defines these utility functions +Apart from the node classes, the :mod:`!ast` module defines these utility functions and classes for traversing abstract syntax trees: .. function:: parse(source, filename='', mode='exec', *, type_comments=False, feature_version=None, optimize=-1) @@ -2376,12 +2449,12 @@ and classes for traversing abstract syntax trees: during traversal. For this a special visitor exists (:class:`NodeTransformer`) that allows modifications. - .. deprecated:: 3.8 + .. deprecated-removed:: 3.8 3.14 Methods :meth:`!visit_Num`, :meth:`!visit_Str`, :meth:`!visit_Bytes`, - :meth:`!visit_NameConstant` and :meth:`!visit_Ellipsis` are deprecated - now and will not be called in future Python versions. Add the - :meth:`visit_Constant` method to handle all constant nodes. + :meth:`!visit_NameConstant` and :meth:`!visit_Ellipsis` will not be called + in Python 3.14+. Add the :meth:`visit_Constant` method instead to handle + all constant nodes. .. class:: NodeTransformer() @@ -2445,8 +2518,9 @@ and classes for traversing abstract syntax trees: indents that many spaces per level. If *indent* is a string (such as ``"\t"``), that string is used to indent each level. - If *show_empty* is ``False`` (the default), empty lists and fields that are ``None`` - will be omitted from the output. + If *show_empty* is false (the default), optional empty lists will be + omitted from the output. + Optional ``None`` values are always omitted. .. versionchanged:: 3.9 Added the *indent* option. @@ -2482,6 +2556,20 @@ and classes for traversing abstract syntax trees: type_ignores=[]) +.. function:: compare(a, b, /, *, compare_attributes=False) + + Recursively compares two ASTs. + + *compare_attributes* affects whether AST attributes are considered + in the comparison. If *compare_attributes* is ``False`` (default), then + attributes are ignored. Otherwise they must all be equal. This + option is useful to check whether the ASTs are structurally equal but + differ in whitespace or similar details. Attributes include line numbers + and column offsets. + + .. versionadded:: 3.14 + + .. _ast-compiler-flags: Compiler flags @@ -2517,20 +2605,6 @@ effects on the compilation of a program: .. versionadded:: 3.8 -.. function:: compare(a, b, /, *, compare_attributes=False) - - Recursively compares two ASTs. - - *compare_attributes* affects whether AST attributes are considered - in the comparison. If *compare_attributes* is ``False`` (default), then - attributes are ignored. Otherwise they must all be equal. This - option is useful to check whether the ASTs are structurally equal but - differ in whitespace or similar details. Attributes include line numbers - and column offsets. - - .. versionadded:: 3.14 - - .. _ast-cli: Command-line usage @@ -2538,7 +2612,7 @@ Command-line usage .. versionadded:: 3.9 -The :mod:`ast` module can be executed as a script from the command line. +The :mod:`!ast` module can be executed as a script from the command line. It is as simple as: .. code-block:: sh diff --git a/Doc/library/asyncio-dev.rst b/Doc/library/asyncio-dev.rst index 44b507a9811116..f3409bcd2df648 100644 --- a/Doc/library/asyncio-dev.rst +++ b/Doc/library/asyncio-dev.rst @@ -46,10 +46,6 @@ In addition to enabling the debug mode, consider also: When the debug mode is enabled: -* asyncio checks for :ref:`coroutines that were not awaited - ` and logs them; this mitigates - the "forgotten await" pitfall. - * Many non-threadsafe asyncio APIs (such as :meth:`loop.call_soon` and :meth:`loop.call_at` methods) raise an exception if they are called from a wrong thread. @@ -252,3 +248,225 @@ Output in debug mode:: File "../t.py", line 4, in bug raise Exception("not consumed") Exception: not consumed + + +Asynchronous generators best practices +====================================== + +Writing correct and efficient asyncio code requires awareness of certain pitfalls. +This section outlines essential best practices that can save you hours of debugging. + + +Close asynchronous generators explicitly +---------------------------------------- + +It is recommended to manually close the +:term:`asynchronous generator `. If a generator +exits early - for example, due to an exception raised in the body of +an ``async for`` loop - its asynchronous cleanup code may run in an +unexpected context. This can occur after the tasks it depends on have completed, +or during the event loop shutdown when the async-generator's garbage collection +hook is called. + +To avoid this, explicitly close the generator by calling its +:meth:`~agen.aclose` method, or use the :func:`contextlib.aclosing` +context manager:: + + import asyncio + import contextlib + + async def gen(): + yield 1 + yield 2 + + async def func(): + async with contextlib.aclosing(gen()) as g: + async for x in g: + break # Don't iterate until the end + + asyncio.run(func()) + +As noted above, the cleanup code for these asynchronous generators is deferred. +The following example demonstrates that the finalization of an asynchronous +generator can occur in an unexpected order:: + + import asyncio + work_done = False + + async def cursor(): + try: + yield 1 + finally: + assert work_done + + async def rows(): + global work_done + try: + yield 2 + finally: + await asyncio.sleep(0.1) # immitate some async work + work_done = True + + + async def main(): + async for c in cursor(): + async for r in rows(): + break + break + + asyncio.run(main()) + +For this example, we get the following output:: + + unhandled exception during asyncio.run() shutdown + task: ()> exception=AssertionError()> + Traceback (most recent call last): + File "example.py", line 6, in cursor + yield 1 + asyncio.exceptions.CancelledError + + During handling of the above exception, another exception occurred: + + Traceback (most recent call last): + File "example.py", line 8, in cursor + assert work_done + ^^^^^^^^^ + AssertionError + +The ``cursor()`` asynchronous generator was finalized before the ``rows`` +generator - an unexpected behavior. + +The example can be fixed by explicitly closing the +``cursor`` and ``rows`` async-generators:: + + async def main(): + async with contextlib.aclosing(cursor()) as cursor_gen: + async for c in cursor_gen: + async with contextlib.aclosing(rows()) as rows_gen: + async for r in rows_gen: + break + break + + +Create asynchronous generators only when the event loop is running +------------------------------------------------------------------ + +It is recommended to create +:term:`asynchronous generators ` only after +the event loop has been created. + +To ensure that asynchronous generators close reliably, the event loop uses the +:func:`sys.set_asyncgen_hooks` function to register callback functions. These +callbacks update the list of running asynchronous generators to keep it in a +consistent state. + +When the :meth:`loop.shutdown_asyncgens() ` +function is called, the running generators are stopped gracefully and the +list is cleared. + +The asynchronous generator invokes the corresponding system hook during its +first iteration. At the same time, the generator records that the hook has +been called and does not call it again. + +Therefore, if iteration begins before the event loop is created, +the event loop will not be able to add the generator to its list of active +generators because the hooks are set after the generator attempts to call them. +Consequently, the event loop will not be able to terminate the generator +if necessary. + +Consider the following example:: + + import asyncio + + async def agenfn(): + try: + yield 10 + finally: + await asyncio.sleep(0) + + + with asyncio.Runner() as runner: + agen = agenfn() + print(runner.run(anext(agen))) + del agen + +Output:: + + 10 + Exception ignored while closing generator : + Traceback (most recent call last): + File "example.py", line 13, in + del agen + ^^^^ + RuntimeError: async generator ignored GeneratorExit + +This example can be fixed as follows:: + + import asyncio + + async def agenfn(): + try: + yield 10 + finally: + await asyncio.sleep(0) + + async def main(): + agen = agenfn() + print(await anext(agen)) + del agen + + asyncio.run(main()) + + +Avoid concurrent iteration and closure of the same generator +------------------------------------------------------------ + +Async generators may be reentered while another +:meth:`~agen.__anext__` / :meth:`~agen.athrow` / :meth:`~agen.aclose` call is in +progress. This may lead to an inconsistent state of the async generator and can +cause errors. + +Let's consider the following example:: + + import asyncio + + async def consumer(): + for idx in range(100): + await asyncio.sleep(0) + message = yield idx + print('received', message) + + async def amain(): + agenerator = consumer() + await agenerator.asend(None) + + fa = asyncio.create_task(agenerator.asend('A')) + fb = asyncio.create_task(agenerator.asend('B')) + await fa + await fb + + asyncio.run(amain()) + +Output:: + + received A + Traceback (most recent call last): + File "test.py", line 38, in + asyncio.run(amain()) + ~~~~~~~~~~~^^^^^^^^^ + File "Lib/asyncio/runners.py", line 204, in run + return runner.run(main) + ~~~~~~~~~~^^^^^^ + File "Lib/asyncio/runners.py", line 127, in run + return self._loop.run_until_complete(task) + ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^ + File "Lib/asyncio/base_events.py", line 719, in run_until_complete + return future.result() + ~~~~~~~~~~~~~^^ + File "test.py", line 36, in amain + await fb + RuntimeError: anext(): asynchronous generator is already running + + +Therefore, it is recommended to avoid using asynchronous generators in parallel +tasks or across multiple event loops. diff --git a/Doc/library/asyncio-eventloop.rst b/Doc/library/asyncio-eventloop.rst index 21f7d0547af1dd..d7dd2171de9a59 100644 --- a/Doc/library/asyncio-eventloop.rst +++ b/Doc/library/asyncio-eventloop.rst @@ -4,7 +4,7 @@ .. _asyncio-event-loop: ========== -Event Loop +Event loop ========== **Source code:** :source:`Lib/asyncio/events.py`, @@ -105,7 +105,7 @@ This documentation page contains the following sections: .. _asyncio-event-loop-methods: -Event Loop Methods +Event loop methods ================== Event loops have **low-level** APIs for the following: @@ -297,13 +297,20 @@ clocks to track time. are called is undefined. The optional positional *args* will be passed to the callback when - it is called. If you want the callback to be called with keyword - arguments use :func:`functools.partial`. + it is called. Use :func:`functools.partial` + :ref:`to pass keyword arguments ` to + *callback*. An optional keyword-only *context* argument allows specifying a custom :class:`contextvars.Context` for the *callback* to run in. The current context is used when no *context* is provided. + .. note:: + + For performance, callbacks scheduled with :meth:`loop.call_later` + may run up to one clock-resolution early (see + ``time.get_clock_info('monotonic').resolution``). + .. versionchanged:: 3.7 The *context* keyword-only parameter was added. See :pep:`567` for more details. @@ -324,6 +331,12 @@ clocks to track time. An instance of :class:`asyncio.TimerHandle` is returned which can be used to cancel the callback. + .. note:: + + For performance, callbacks scheduled with :meth:`loop.call_at` + may run up to one clock-resolution early (see + ``time.get_clock_info('monotonic').resolution``). + .. versionchanged:: 3.7 The *context* keyword-only parameter was added. See :pep:`567` for more details. @@ -348,7 +361,7 @@ clocks to track time. The :func:`asyncio.sleep` function. -Creating Futures and Tasks +Creating futures and tasks ^^^^^^^^^^^^^^^^^^^^^^^^^^ .. method:: loop.create_future() @@ -361,7 +374,7 @@ Creating Futures and Tasks .. versionadded:: 3.5.2 -.. method:: loop.create_task(coro, *, name=None, context=None, eager_start=None) +.. method:: loop.create_task(coro, *, name=None, context=None, eager_start=None, **kwargs) Schedule the execution of :ref:`coroutine ` *coro*. Return a :class:`Task` object. @@ -370,6 +383,10 @@ Creating Futures and Tasks for interoperability. In this case, the result type is a subclass of :class:`Task`. + The full function signature is largely the same as that of the + :class:`Task` constructor (or factory) - all of the keyword arguments to + this function are passed through to that interface. + If the *name* argument is provided and not ``None``, it is set as the name of the task using :meth:`Task.set_name`. @@ -388,8 +405,15 @@ Creating Futures and Tasks .. versionchanged:: 3.11 Added the *context* parameter. + .. versionchanged:: 3.13.3 + Added ``kwargs`` which passes on arbitrary extra parameters, including ``name`` and ``context``. + + .. versionchanged:: 3.13.4 + Rolled back the change that passes on *name* and *context* (if it is None), + while still passing on other arbitrary keyword arguments (to avoid breaking backwards compatibility with 3.13.3). + .. versionchanged:: 3.14 - Added the *eager_start* parameter. + All *kwargs* are now passed on. The *eager_start* parameter works with eager task factories. .. method:: loop.set_task_factory(factory) @@ -402,6 +426,16 @@ Creating Futures and Tasks event loop, and *coro* is a coroutine object. The callable must pass on all *kwargs*, and return a :class:`asyncio.Task`-compatible object. + .. versionchanged:: 3.13.3 + Required that all *kwargs* are passed on to :class:`asyncio.Task`. + + .. versionchanged:: 3.13.4 + *name* is no longer passed to task factories. *context* is no longer passed + to task factories if it is ``None``. + + .. versionchanged:: 3.14 + *name* and *context* are now unconditionally passed on to task factories again. + .. method:: loop.get_task_factory() Return a task factory or ``None`` if the default one is in use. @@ -590,6 +624,12 @@ Opening network connections to bind the socket locally. The *local_host* and *local_port* are looked up using :meth:`getaddrinfo`. + .. note:: + + On Windows, when using the proactor event loop with ``local_addr=None``, + an :exc:`OSError` with :attr:`!errno.WSAEINVAL` will be raised + when running it. + * *remote_addr*, if given, is a ``(remote_host, remote_port)`` tuple used to connect the socket to a remote address. The *remote_host* and *remote_port* are looked up using :meth:`getaddrinfo`. @@ -922,7 +962,7 @@ Transferring files .. versionadded:: 3.7 -TLS Upgrade +TLS upgrade ^^^^^^^^^^^ .. method:: loop.start_tls(transport, protocol, \ @@ -995,8 +1035,8 @@ Watching file descriptors .. method:: loop.add_writer(fd, callback, *args) Start monitoring the *fd* file descriptor for write availability and - invoke *callback* with the specified arguments once *fd* is available for - writing. + invoke *callback* with the specified arguments *args* once *fd* is + available for writing. Any preexisting callback registered for *fd* is cancelled and replaced by *callback*. @@ -1116,12 +1156,21 @@ convenient. *sock* must be a non-blocking socket. + With :class:`SelectorEventLoop`, *address* does not need to be resolved: + for :const:`~socket.AF_INET` and :const:`~socket.AF_INET6` sockets, + ``sock_connect`` first checks whether *address* is already resolved by + calling :func:`socket.inet_pton`, and uses :meth:`loop.getaddrinfo` to + resolve it if it is not. + + :class:`ProactorEventLoop`, the default event loop on Windows, does not + resolve *address*. The host must already be a numeric IP address; passing + a host name raises :exc:`OSError`. Resolve the address with + :meth:`loop.getaddrinfo` first, or use :meth:`loop.create_connection`, + which resolves the address on every platform. + .. versionchanged:: 3.5.2 - ``address`` no longer needs to be resolved. ``sock_connect`` - will try to check if the *address* is already resolved by calling - :func:`socket.inet_pton`. If not, - :meth:`loop.getaddrinfo` will be used to resolve the - *address*. + With :class:`SelectorEventLoop`, ``address`` no longer needs to be + resolved. .. seealso:: @@ -1225,7 +1274,9 @@ Working with pipes *protocol_factory* must be a callable returning an :ref:`asyncio protocol ` implementation. - *pipe* is a :term:`file-like object `. + *pipe* is a :term:`file-like object `. See + :ref:`Supported pipe objects ` for the objects + supported as *pipe*. Return pair ``(transport, protocol)``, where *transport* supports the :class:`ReadTransport` interface and *protocol* is an object @@ -1242,7 +1293,9 @@ Working with pipes *protocol_factory* must be a callable returning an :ref:`asyncio protocol ` implementation. - *pipe* is :term:`file-like object `. + *pipe* is a :term:`file-like object `. See + :ref:`Supported pipe objects ` for the objects + supported as *pipe*. Return pair ``(transport, protocol)``, where *transport* supports :class:`WriteTransport` interface and *protocol* is an object @@ -1251,6 +1304,33 @@ Working with pipes With :class:`SelectorEventLoop` event loop, the *pipe* is set to non-blocking mode. +.. _asyncio-pipe-objects: + +.. rubric:: Supported pipe objects + +These methods only work with objects the operating system can poll for +readiness or perform overlapped I/O on. Regular files on disk are **not** +supported on any platform. There is no asynchronous file I/O in asyncio; +use :meth:`loop.run_in_executor` to read and write regular files without +blocking the event loop. + +On Unix, with :class:`SelectorEventLoop`, *pipe* must wrap one of the +following: + +* a pipe, such as an end of an :func:`os.pipe` pair or a FIFO created with + :func:`os.mkfifo`; +* a socket; +* a character device, such as a terminal. + +On Windows, where only :class:`ProactorEventLoop` implements these methods, +*pipe* must wrap a handle opened for overlapped I/O (that is, created with the +``FILE_FLAG_OVERLAPPED`` flag), since the handle has to be associated with an +I/O completion port. Handles that were not opened for overlapped I/O are +rejected. In particular, the standard streams (:data:`sys.stdin`, +:data:`sys.stdout` and :data:`sys.stderr`), console handles, and the pipes +created by :func:`os.pipe` are **not** opened for overlapped I/O and therefore +cannot be used with these methods. + .. note:: :class:`SelectorEventLoop` does not support the above methods on @@ -1269,7 +1349,8 @@ Unix signals .. method:: loop.add_signal_handler(signum, callback, *args) - Set *callback* as the handler for the *signum* signal. + Set *callback* as the handler for the *signum* signal, + passing *args* as positional arguments. The callback will be invoked by *loop*, along with other queued callbacks and runnable coroutines of that event loop. Unlike signal handlers @@ -1304,7 +1385,8 @@ Executing code in thread or process pools .. awaitablemethod:: loop.run_in_executor(executor, func, *args) - Arrange for *func* to be called in the specified executor. + Arrange for *func* to be called in the specified executor + passing *args* as positional arguments. The *executor* argument should be an :class:`concurrent.futures.Executor` instance. The default executor is used if *executor* is ``None``. @@ -1389,7 +1471,7 @@ Executing code in thread or process pools :class:`~concurrent.futures.ThreadPoolExecutor`. -Error Handling API +Error handling API ^^^^^^^^^^^^^^^^^^ Allows customizing how exceptions are handled in the event loop. @@ -1492,7 +1574,7 @@ Enabling debug mode The :ref:`debug mode of asyncio `. -Running Subprocesses +Running subprocesses ^^^^^^^^^^^^^^^^^^^^ Methods described in this subsections are low-level. In regular @@ -1592,6 +1674,9 @@ async/await code consider using the high-level conforms to the :class:`asyncio.SubprocessTransport` base class and *protocol* is an object instantiated by the *protocol_factory*. + If the transport is closed or is garbage collected, the child process + is killed if it is still running. + .. method:: loop.subprocess_shell(protocol_factory, cmd, *, \ stdin=subprocess.PIPE, stdout=subprocess.PIPE, \ stderr=subprocess.PIPE, **kwargs) @@ -1615,6 +1700,9 @@ async/await code consider using the high-level conforms to the :class:`SubprocessTransport` base class and *protocol* is an object instantiated by the *protocol_factory*. + If the transport is closed or is garbage collected, the child process + is killed if it is still running. + .. note:: It is the application's responsibility to ensure that all whitespace and special characters are quoted appropriately to avoid `shell injection @@ -1624,7 +1712,7 @@ async/await code consider using the high-level are going to be used to construct shell commands. -Callback Handles +Callback handles ================ .. class:: Handle @@ -1667,7 +1755,7 @@ Callback Handles .. versionadded:: 3.7 -Server Objects +Server objects ============== Server objects are created by :meth:`loop.create_server`, @@ -1796,6 +1884,12 @@ Do not instantiate the :class:`Server` class directly. Wait until the :meth:`close` method completes and all active connections have finished. + .. versionchanged:: 3.12 + ``wait_closed()`` now waits until the server is closed and + all active connections have finished. Previously, it returned + immediately if the server was already closed, even if + connections were still active. + .. attribute:: sockets List of socket-like objects, ``asyncio.trsock.TransportSocket``, which @@ -1810,7 +1904,7 @@ Do not instantiate the :class:`Server` class directly. .. _asyncio-event-loops: .. _asyncio-event-loop-implementations: -Event Loop Implementations +Event loop implementations ========================== asyncio ships with two different event loop implementations: @@ -1923,10 +2017,10 @@ callback uses the :meth:`loop.call_later` method to reschedule itself after 5 seconds, and then stops the event loop:: import asyncio - import datetime + import datetime as dt def display_date(end_time, loop): - print(datetime.datetime.now()) + print(dt.datetime.now()) if (loop.time() + 1.0) < end_time: loop.call_later(1, display_date, end_time, loop) else: @@ -2007,7 +2101,7 @@ Wait until a file descriptor received some data using the Set signal handlers for SIGINT and SIGTERM ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -(This ``signals`` example only works on Unix.) +(This ``signal`` example only works on Unix.) Register handlers for signals :const:`~signal.SIGINT` and :const:`~signal.SIGTERM` using the :meth:`loop.add_signal_handler` method:: diff --git a/Doc/library/asyncio-future.rst b/Doc/library/asyncio-future.rst index 32771ba72e0002..195d99123dbd36 100644 --- a/Doc/library/asyncio-future.rst +++ b/Doc/library/asyncio-future.rst @@ -75,6 +75,7 @@ Future Functions Deprecation warning is emitted if *future* is not a Future-like object and *loop* is not specified and there is no running event loop. +.. _asyncio-future-obj: Future Object ============= @@ -100,6 +101,8 @@ Future Object implementations can inject their own optimized implementations of a Future object. + Futures are :ref:`generic ` over the type of their results. + .. versionchanged:: 3.7 Added support for the :mod:`contextvars` module. @@ -195,6 +198,10 @@ Future Object Otherwise, change the Future's state to *cancelled*, schedule the callbacks, and return ``True``. + The optional string argument *msg* is passed as the argument to the + :exc:`CancelledError` exception raised when a cancelled Future + is awaited. + .. versionchanged:: 3.9 Added the *msg* parameter. diff --git a/Doc/library/asyncio-graph.rst b/Doc/library/asyncio-graph.rst index 5f642a32bf75c2..1a8cdcf6a9e8cb 100644 --- a/Doc/library/asyncio-graph.rst +++ b/Doc/library/asyncio-graph.rst @@ -4,7 +4,7 @@ .. _asyncio-graph: ======================== -Call Graph Introspection +Call graph introspection ======================== **Source code:** :source:`Lib/asyncio/graph.py` @@ -17,6 +17,12 @@ a suspended *future*. These utilities and the underlying machinery can be used from within a Python program or by external profilers and debuggers. +.. seealso:: + + :ref:`asyncio-introspection-tools` + Command-line tools for inspecting tasks in another running Python + process. + .. versionadded:: 3.14 diff --git a/Doc/library/asyncio-platforms.rst b/Doc/library/asyncio-platforms.rst index a2a3114ad6e4c5..0b7c17a2c58479 100644 --- a/Doc/library/asyncio-platforms.rst +++ b/Doc/library/asyncio-platforms.rst @@ -19,6 +19,11 @@ All Platforms * :meth:`loop.add_reader` and :meth:`loop.add_writer` cannot be used to monitor file I/O. +* :meth:`loop.connect_read_pipe` and :meth:`loop.connect_write_pipe` + cannot be used with regular files. See :ref:`Supported pipe objects + ` for the objects that are accepted on each + platform. + Windows ======= @@ -62,6 +67,10 @@ All event loops on Windows do not support the following methods: * The :meth:`loop.add_reader` and :meth:`loop.add_writer` methods are not supported. +* :meth:`loop.connect_read_pipe` and :meth:`loop.connect_write_pipe` only + accept a handle opened for overlapped I/O. + See :ref:`Supported pipe objects ` for which objects are supported. + The resolution of the monotonic clock on Windows is usually around 15.6 milliseconds. The best resolution is 0.5 milliseconds. The resolution depends on the hardware (availability of `HPET diff --git a/Doc/library/asyncio-protocol.rst b/Doc/library/asyncio-protocol.rst index 7c08d65f26bc27..58f77feb311984 100644 --- a/Doc/library/asyncio-protocol.rst +++ b/Doc/library/asyncio-protocol.rst @@ -390,11 +390,11 @@ Subprocess Transports Return the transport for the communication pipe corresponding to the integer file descriptor *fd*: - * ``0``: readable streaming transport of the standard input (*stdin*), + * ``0``: writable streaming transport of the standard input (*stdin*), or :const:`None` if the subprocess was not created with ``stdin=PIPE`` - * ``1``: writable streaming transport of the standard output (*stdout*), + * ``1``: readable streaming transport of the standard output (*stdout*), or :const:`None` if the subprocess was not created with ``stdout=PIPE`` - * ``2``: writable streaming transport of the standard error (*stderr*), + * ``2``: readable streaming transport of the standard error (*stderr*), or :const:`None` if the subprocess was not created with ``stderr=PIPE`` * other *fd*: :const:`None` @@ -1037,7 +1037,7 @@ The subprocess is created by the :meth:`loop.subprocess_exec` method:: # low-level APIs. loop = asyncio.get_running_loop() - code = 'import datetime; print(datetime.datetime.now())' + code = 'import datetime as dt; print(dt.datetime.now())' exit_future = asyncio.Future(loop=loop) # Create the subprocess controlled by DateProtocol; diff --git a/Doc/library/asyncio-queue.rst b/Doc/library/asyncio-queue.rst index d99213aa81d53e..5e3f531f4e482e 100644 --- a/Doc/library/asyncio-queue.rst +++ b/Doc/library/asyncio-queue.rst @@ -71,6 +71,8 @@ Queue Return an item if one is immediately available, else raise :exc:`QueueEmpty`. + Raises :exc:`QueueShutDown` if the queue has been shut down and is empty. + .. method:: join() :async: @@ -96,23 +98,42 @@ Queue If no free slot is immediately available, raise :exc:`QueueFull`. + Raises :exc:`QueueShutDown` if the queue has been shut down. + .. method:: qsize() Return the number of items in the queue. .. method:: shutdown(immediate=False) - Shut down the queue, making :meth:`~Queue.get` and :meth:`~Queue.put` + Put a :class:`Queue` instance into a shutdown mode. + + The queue can no longer grow. + Future calls to :meth:`~Queue.put` raise :exc:`QueueShutDown`. + Currently blocked callers of :meth:`~Queue.put` will be unblocked + and will raise :exc:`QueueShutDown` in the formerly awaiting task. + + If *immediate* is false (the default), the queue can be wound + down normally with :meth:`~Queue.get` calls to extract tasks + that have already been loaded. + + And if :meth:`~Queue.task_done` is called for each remaining task, a + pending :meth:`~Queue.join` will be unblocked normally. + + Once the queue is empty, future calls to :meth:`~Queue.get` will raise :exc:`QueueShutDown`. - By default, :meth:`~Queue.get` on a shut down queue will only - raise once the queue is empty. Set *immediate* to true to make - :meth:`~Queue.get` raise immediately instead. + If *immediate* is true, the queue is terminated immediately. + The queue is drained to be completely empty and the count + of unfinished tasks is reduced by the number of tasks drained. + If unfinished tasks is zero, callers of :meth:`~Queue.join` + are unblocked. Also, blocked callers of :meth:`~Queue.get` + are unblocked and will raise :exc:`QueueShutDown` because the + queue is empty. - All blocked callers of :meth:`~Queue.put` and :meth:`~Queue.get` - will be unblocked. If *immediate* is true, a task will be marked - as done for each remaining item in the queue, which may unblock - callers of :meth:`~Queue.join`. + Use caution when using :meth:`~Queue.join` with *immediate* set + to true. This unblocks the join even when no work has been done + on the tasks, violating the usual invariant for joining a queue. .. versionadded:: 3.13 @@ -129,9 +150,6 @@ Queue call was received for every item that had been :meth:`~Queue.put` into the queue). - ``shutdown(immediate=True)`` calls :meth:`task_done` for each - remaining item in the queue. - Raises :exc:`ValueError` if called more times than there were items placed in the queue. @@ -174,8 +192,9 @@ Exceptions .. exception:: QueueShutDown - Exception raised when :meth:`~Queue.put` or :meth:`~Queue.get` is - called on a queue which has been shut down. + Exception raised when :meth:`~Queue.put`, :meth:`~Queue.put_nowait`, + :meth:`~Queue.get` or :meth:`~Queue.get_nowait` is called + on a queue which has been shut down. .. versionadded:: 3.13 diff --git a/Doc/library/asyncio-stream.rst b/Doc/library/asyncio-stream.rst index c56166cabb9093..dd23b223e1492e 100644 --- a/Doc/library/asyncio-stream.rst +++ b/Doc/library/asyncio-stream.rst @@ -171,13 +171,17 @@ and work with streams: .. function:: start_unix_server(client_connected_cb, path=None, \ *, limit=None, sock=None, backlog=100, ssl=None, \ ssl_handshake_timeout=None, \ - ssl_shutdown_timeout=None, start_serving=True) + ssl_shutdown_timeout=None, start_serving=True, cleanup_socket=True) :async: Start a Unix socket server. Similar to :func:`start_server` but works with Unix sockets. + If *cleanup_socket* is true then the Unix socket will automatically + be removed from the filesystem when the server is closed, unless the + socket has been replaced after the server has been created. + See also the documentation of :meth:`loop.create_unix_server`. .. note:: @@ -198,6 +202,9 @@ and work with streams: .. versionchanged:: 3.11 Added the *ssl_shutdown_timeout* parameter. + .. versionchanged:: 3.13 + Added the *cleanup_socket* parameter. + StreamReader ============ @@ -309,11 +316,15 @@ StreamWriter If that fails, the data is queued in an internal write buffer until it can be sent. + The *data* buffer should be a bytes, bytearray, or C-contiguous one-dimensional + memoryview object. + The method should be used along with the ``drain()`` method:: stream.write(data) await stream.drain() + .. method:: writelines(data) The method writes a list (or any iterable) of bytes to the underlying socket @@ -371,6 +382,16 @@ StreamWriter be resumed. When there is nothing to wait for, the :meth:`drain` returns immediately. + .. note:: + + When the write buffer is below the high watermark, + :meth:`drain` returns immediately without yielding to + the event loop. As a result, code which repeatedly calls + ``write()`` followed by ``await drain()`` may prevent other + tasks from running. To prevent blocking behavior, yield + to the event loop explicitly with ``await asyncio.sleep(0)`` + (see :func:`asyncio.sleep`). + .. method:: start_tls(sslcontext, *, server_hostname=None, \ ssl_handshake_timeout=None, ssl_shutdown_timeout=None) :async: diff --git a/Doc/library/asyncio-subprocess.rst b/Doc/library/asyncio-subprocess.rst index 03e76bc868905e..a6514649bf9a0a 100644 --- a/Doc/library/asyncio-subprocess.rst +++ b/Doc/library/asyncio-subprocess.rst @@ -76,6 +76,9 @@ Creating Subprocesses See the documentation of :meth:`loop.subprocess_exec` for other parameters. + If the process object is garbage collected while the process is still + running, the child process will be killed. + .. versionchanged:: 3.10 Removed the *loop* parameter. @@ -95,6 +98,9 @@ Creating Subprocesses See the documentation of :meth:`loop.subprocess_shell` for other parameters. + If the process object is garbage collected while the process is still + running, the child process will be killed. + .. important:: It is the application's responsibility to ensure that all whitespace and @@ -305,8 +311,16 @@ their completion. A ``None`` value indicates that the process has not terminated yet. - A negative value ``-N`` indicates that the child was terminated - by signal ``N`` (POSIX only). + For processes created with :func:`~asyncio.create_subprocess_exec`, a negative + value ``-N`` indicates that the child was terminated by signal ``N`` + (POSIX only). + + For processes created with :func:`~asyncio.create_subprocess_shell`, the + return code reflects the exit status of the shell itself (e.g. ``/bin/sh``), + which may map signals to codes such as ``128+N``. See the + documentation of the shell (for example, the Bash manual's Exit Status) + for details. + .. _asyncio-subprocess-threads: @@ -345,7 +359,7 @@ function:: import sys async def get_date(): - code = 'import datetime; print(datetime.datetime.now())' + code = 'import datetime as dt; print(dt.datetime.now())' # Create the subprocess; redirect the standard output # into a pipe. diff --git a/Doc/library/asyncio-sync.rst b/Doc/library/asyncio-sync.rst index 968c812ee3c8e6..f9e98e05cab7ac 100644 --- a/Doc/library/asyncio-sync.rst +++ b/Doc/library/asyncio-sync.rst @@ -157,7 +157,7 @@ Event Clear (unset) the event. - Tasks awaiting on :meth:`~Event.wait` will now block until the + Subsequent tasks awaiting on :meth:`~Event.wait` will now block until the :meth:`~Event.set` method is called again. .. method:: is_set() diff --git a/Doc/library/asyncio-task.rst b/Doc/library/asyncio-task.rst index 59acce1990ae04..65cbba08dbcac0 100644 --- a/Doc/library/asyncio-task.rst +++ b/Doc/library/asyncio-task.rst @@ -2,7 +2,7 @@ ==================== -Coroutines and Tasks +Coroutines and tasks ==================== This section outlines high-level asyncio APIs to work with coroutines @@ -231,25 +231,31 @@ A good example of a low-level function that returns a Future object is :meth:`loop.run_in_executor`. -Creating Tasks +Creating tasks ============== **Source code:** :source:`Lib/asyncio/tasks.py` ----------------------------------------------- -.. function:: create_task(coro, *, name=None, context=None) +.. function:: create_task(coro, *, name=None, context=None, eager_start=None, **kwargs) Wrap the *coro* :ref:`coroutine ` into a :class:`Task` and schedule its execution. Return the Task object. - If *name* is not ``None``, it is set as the name of the task using - :meth:`Task.set_name`. + The full function signature is largely the same as that of the + :class:`Task` constructor (or factory) - all of the keyword arguments to + this function are passed through to that interface. An optional keyword-only *context* argument allows specifying a custom :class:`contextvars.Context` for the *coro* to run in. The current context copy is created when no *context* is provided. + An optional keyword-only *eager_start* argument allows specifying + if the task should execute eagerly during the call to create_task, + or be scheduled later. If *eager_start* is not passed the mode set + by :meth:`loop.set_task_factory` will be used. + The task is executed in the loop returned by :func:`get_running_loop`, :exc:`RuntimeError` is raised if there is no running loop in current thread. @@ -282,6 +288,17 @@ Creating Tasks # completion: task.add_done_callback(background_tasks.discard) + Note that this approach never awaits the tasks, so if a task + fails, its exception is never retrieved and asyncio logs a + "Task exception was never retrieved" message when the task is + garbage collected. To avoid this, use :class:`asyncio.TaskGroup` + which keeps a strong reference to each task, awaits them and + propagates their exceptions:: + + async with asyncio.TaskGroup() as tg: + for i in range(10): + tg.create_task(some_coro(param=i)) + .. versionadded:: 3.7 .. versionchanged:: 3.8 @@ -290,8 +307,11 @@ Creating Tasks .. versionchanged:: 3.11 Added the *context* parameter. + .. versionchanged:: 3.14 + Added the *eager_start* parameter by passing on all *kwargs*. + -Task Cancellation +Task cancellation ================= Tasks can easily and safely be cancelled. @@ -315,7 +335,7 @@ remove the cancellation state. .. _taskgroups: -Task Groups +Task groups =========== Task groups combine a task creation API with a convenient @@ -330,7 +350,7 @@ and reliable way to wait for all tasks in the group to finish. .. versionadded:: 3.11 - .. method:: create_task(coro, *, name=None, context=None) + .. method:: create_task(coro, *, name=None, context=None, eager_start=None, **kwargs) Create a task in this task group. The signature matches that of :func:`asyncio.create_task`. @@ -342,6 +362,10 @@ and reliable way to wait for all tasks in the group to finish. Close the given coroutine if the task group is not active. + .. versionchanged:: 3.14 + + Passes on all *kwargs* to :meth:`loop.create_task` + Example:: async def main(): @@ -414,7 +438,7 @@ reported by :meth:`asyncio.Task.cancelling`. Improved handling of simultaneous internal and external cancellations and correct preservation of cancellation counts. -Terminating a Task Group +Terminating a task group ------------------------ While terminating a task group is not natively supported by the standard @@ -485,13 +509,13 @@ Sleeping for 5 seconds:: import asyncio - import datetime + import datetime as dt async def display_date(): loop = asyncio.get_running_loop() end_time = loop.time() + 5.0 while True: - print(datetime.datetime.now()) + print(dt.datetime.now()) if (loop.time() + 1.0) >= end_time: break await asyncio.sleep(1) @@ -506,7 +530,7 @@ Sleeping Raises :exc:`ValueError` if *delay* is :data:`~math.nan`. -Running Tasks Concurrently +Running tasks concurrently ========================== .. awaitablefunction:: gather(*aws, return_exceptions=False) @@ -544,7 +568,7 @@ Running Tasks Concurrently provides stronger safety guarantees than *gather* for scheduling a nesting of subtasks: if a task (or a subtask, a task scheduled by a task) raises an exception, *TaskGroup* will, while *gather* will not, - cancel the remaining scheduled tasks). + cancel the remaining scheduled tasks. .. _asyncio_example_gather: @@ -608,7 +632,7 @@ Running Tasks Concurrently .. _eager-task-factory: -Eager Task Factory +Eager task factory ================== .. function:: eager_task_factory(loop, coro, *, name=None, context=None) @@ -651,7 +675,7 @@ Eager Task Factory .. versionadded:: 3.12 -Shielding From Cancellation +Shielding from cancellation =========================== .. awaitablefunction:: shield(aw) @@ -758,6 +782,9 @@ Timeouts An :ref:`asynchronous context manager ` for cancelling overdue coroutines. + Prefer using :func:`asyncio.timeout` or :func:`asyncio.timeout_at` + rather than instantiating :class:`!Timeout` directly. + ``when`` should be an absolute time at which the context should time out, as measured by the event loop's clock: @@ -878,7 +905,7 @@ Timeouts Raises :exc:`TimeoutError` instead of :exc:`asyncio.TimeoutError`. -Waiting Primitives +Waiting primitives ================== .. function:: wait(aws, *, timeout=None, return_when=ALL_COMPLETED) @@ -926,6 +953,9 @@ Waiting Primitives Unlike :func:`~asyncio.wait_for`, ``wait()`` does not cancel the futures when a timeout occurs. + If ``wait()`` is cancelled, the futures in *aws* are not cancelled + and continue to run. + .. versionchanged:: 3.10 Removed the *loop* parameter. @@ -983,6 +1013,10 @@ Waiting Primitives are done. This is raised by the ``async for`` loop during asynchronous iteration or by the coroutines yielded during plain iteration. + ``as_completed()`` does not cancel the tasks running the supplied + awaitables: if a timeout occurs or the iteration is cancelled, the + remaining tasks continue to run. + .. versionchanged:: 3.10 Removed the *loop* parameter. @@ -998,7 +1032,7 @@ Waiting Primitives or as a plain :term:`iterator` (previously it was only a plain iterator). -Running in Threads +Running in threads ================== .. function:: to_thread(func, /, *args, **kwargs) @@ -1058,7 +1092,7 @@ Running in Threads .. versionadded:: 3.9 -Scheduling From Other Threads +Scheduling from other threads ============================= .. function:: run_coroutine_threadsafe(coro, loop) @@ -1180,8 +1214,9 @@ Introspection .. versionadded:: 3.4 +.. _asyncio-task-obj: -Task Object +Task object =========== .. class:: Task(coro, *, loop=None, name=None, context=None, eager_start=False) @@ -1231,6 +1266,9 @@ Task Object blocks. If the coroutine returns or raises without blocking, the task will be finished eagerly and will skip scheduling to the event loop. + Tasks are :ref:`generic ` over the return type of their wrapped + coroutines. + .. versionchanged:: 3.7 Added support for the :mod:`contextvars` module. diff --git a/Doc/library/asyncio-threading.rst b/Doc/library/asyncio-threading.rst new file mode 100644 index 00000000000000..526901a2e7eb20 --- /dev/null +++ b/Doc/library/asyncio-threading.rst @@ -0,0 +1,154 @@ +.. currentmodule:: asyncio + +.. _asyncio-threading: + +asyncio and free-threaded Python +================================ + +asyncio uses an event loop as a scheduler to enable highly efficient +concurrency by switching between tasks to allow non-blocking I/O +operations. This results in better performance for I/O-bound use +cases. It also allows off-loading CPU-bound work to a thread or +process pool, but that is still limited by the :term:`global +interpreter lock` in CPython. + +However, in :ref:`free-threaded Python `, +the GIL is disabled and Python can run true multi-threaded code. This +means that asyncio can now take advantage of multiple CPU cores without +the limitations imposed by the GIL. + +Since Python 3.14, asyncio has first-class support for free-threaded +Python, and the implementation of asyncio is safe to use in a +multi-threaded environment. + +A single event loop on one core can handle many connections +concurrently, but the Python code that runs to handle each one still +executes serially. Once requests involve a non-trivial amount of +per-request computation, that handling becomes the bottleneck, and a +single core can no longer keep up. Combining asyncio with threads is +most useful here: by running an event loop per thread, the handling of +different requests can run in parallel across multiple CPU cores. It is +also useful when you need to run blocking or CPU-bound code from an +asyncio application. + + +.. seealso:: + + `Scaling asyncio on Free-Threaded Python + `__, + a blog post by Kumar Aditya which explains the internal changes + that make asyncio safe and efficient under free-threaded Python, + together with benchmarks of the resulting improvements. + + +Thread safety considerations +---------------------------- + +While asyncio is designed to be thread-safe in a free-threaded Python +environment, there are still some considerations to keep in mind when +using asyncio with threads: + +1. **Event loop**: Each thread should have its own event loop which + should not be shared across threads. This ensures that the event loop + can manage its own tasks and callbacks without interference from + other threads. + +2. **Task management**: Tasks and futures created in one thread should + not be awaited or manipulated from another thread. + +3. **Thread-safe APIs**: When interacting with asyncio from multiple + threads, it's important to use thread-safe APIs provided by asyncio, + such as :func:`asyncio.run_coroutine_threadsafe` for submitting + coroutines to an event loop from another thread. If you need to + call a callback from a different thread, you can use + :meth:`loop.call_soon_threadsafe` to schedule it safely. + +4. **Synchronization**: The synchronization primitives provided by + asyncio (like :class:`asyncio.Lock` and :class:`asyncio.Event`) + are not designed to be used across threads. If you need to + synchronize between threads, you should use the synchronization + primitives from the :mod:`threading` module instead. + + +Using asyncio with threads +-------------------------- + +asyncio supports running one event loop per thread, which allows you to +take advantage of multiple CPU cores in a free-threaded Python +environment. Each thread can run its own event loop, and tasks can be +scheduled on those loops independently. + +Here's an example of how to use asyncio with threads:: + + import asyncio + import threading + + async def worker(name: str) -> None: + print(f"Worker {name} starting") + await asyncio.sleep(1) + print(f"Worker {name} done") + + def run_loop(name: str) -> None: + asyncio.run(worker(name)) + + threads = [ + threading.Thread(target=run_loop, args=(f"T{i}",)) + for i in range(4) + ] + for t in threads: + t.start() + for t in threads: + t.join() + +In this example, each thread creates its own event loop with +:func:`asyncio.run` and runs a coroutine on it. The threads execute +concurrently, and in a free-threaded build they can run on separate +CPU cores in parallel. + + +Producer/consumer across threads +-------------------------------- + +When a regular (non-asyncio) thread needs to hand work to an asyncio +event loop running in another thread, use a thread-safe primitive such +as :class:`queue.Queue` rather than :class:`asyncio.Queue`, which is +only safe within a single event loop.:: + + import asyncio + import queue + import threading + + def producer(q: queue.Queue[int]) -> None: + for i in range(5): + print(f"Producing {i}") + q.put(i) + q.shutdown() + + async def consumer(q: queue.Queue[int]) -> None: + while True: + try: + item = q.get_nowait() + except queue.Empty: + await asyncio.sleep(0.1) + continue + except queue.ShutDown: + break + print(f"Consumed {item}") + await asyncio.sleep(item) + + q: queue.Queue[int] = queue.Queue() + consumer_thread = threading.Thread( + target=lambda: asyncio.run(consumer(q)) + ) + consumer_thread.start() + producer(q) + consumer_thread.join() + +The producer runs on the main thread while the consumer runs inside an +event loop on its own thread, yet they communicate safely through +``queue.Queue``. When the queue is empty the consumer sleeps briefly +and tries again. When the producer is done it calls +:meth:`~queue.Queue.shutdown`, which causes subsequent +:meth:`~queue.Queue.get_nowait` calls to raise :exc:`queue.ShutDown` +so the consumer can exit cleanly. + diff --git a/Doc/library/asyncio-tools.rst b/Doc/library/asyncio-tools.rst new file mode 100644 index 00000000000000..5ffb9bb414e842 --- /dev/null +++ b/Doc/library/asyncio-tools.rst @@ -0,0 +1,150 @@ +.. currentmodule:: asyncio + +.. _asyncio-introspection-tools: + +================================ +Command-line introspection tools +================================ + +**Source code:** :source:`Lib/asyncio/tools.py` + +------------------------------------- + +The :mod:`!asyncio` module can be invoked as a script via ``python -m +asyncio`` to inspect the task graph of another running Python process without +modifying it or restarting it. The :mod:`!asyncio.tools` submodule implements +this interface. + +The following commands inspect the process identified by ``PID``: + +.. code-block:: shell-session + + $ python -m asyncio pstree PID + $ python -m asyncio ps PID + +The commands read the target process state without executing any code in it. +They are only available on supported platforms and may require permission to +inspect another process. See the :ref:`permission requirements ` for details. + +.. seealso:: + + :ref:`asyncio-graph` + Programmatic APIs for inspecting the async call graph of a task or + future in the current process. + +The command examples below use this program, which creates a task hierarchy +suitable for inspection and prints its process ID: + +.. code-block:: python + :caption: example.py + + import asyncio + import os + + async def play(track): + await asyncio.sleep(3600) + print(f"🎵 Finished: {track}") + + async def album(name, tracks): + async with asyncio.TaskGroup() as tg: + for track in tracks: + tg.create_task(play(track), name=track) + + async def main(): + print(f"PID: {os.getpid()}") + async with asyncio.TaskGroup() as tg: + tg.create_task( + album("Sundowning", ["TNDNBTG", "Levitate"]), + name="Sundowning", + ) + tg.create_task( + album("TMBTE", ["DYWTYLM", "Aqua Regia"]), + name="TMBTE", + ) + + asyncio.run(main()) + +Run the program in one terminal and leave it running: + +.. code-block:: shell-session + + $ python example.py + PID: 12345 + +Then pass the printed process ID to the commands from another terminal. +Thread IDs, task IDs, file paths, and line numbers vary between runs and +source layouts. + +.. versionadded:: 3.14 + +Command-line options +==================== + +.. option:: pstree PID + + Display task and coroutine relationships as a tree. Each task is shown + with its full coroutine stack, nested under the task (if any) that is + awaiting it. This subcommand is useful for quickly identifying which branch + of a task hierarchy is blocked and where in its coroutine stack execution + has paused: + + .. code-block:: shell-session + + $ python -m asyncio pstree 12345 + └── (T) Task-1 + └── main example.py:12 + └── TaskGroup.__aexit__ Lib/asyncio/taskgroups.py:75 + └── TaskGroup._aexit Lib/asyncio/taskgroups.py:124 + ├── (T) Sundowning + │ └── album example.py:7 + │ └── TaskGroup.__aexit__ Lib/asyncio/taskgroups.py:75 + │ └── TaskGroup._aexit Lib/asyncio/taskgroups.py:124 + │ ├── (T) TNDNBTG + │ │ └── play example.py:4 + │ │ └── sleep Lib/asyncio/tasks.py:702 + │ └── (T) Levitate + │ └── play example.py:4 + │ └── sleep Lib/asyncio/tasks.py:702 + └── (T) TMBTE + └── album example.py:7 + └── TaskGroup.__aexit__ Lib/asyncio/taskgroups.py:75 + └── TaskGroup._aexit Lib/asyncio/taskgroups.py:124 + ├── (T) DYWTYLM + │ └── play example.py:4 + │ └── sleep Lib/asyncio/tasks.py:702 + └── (T) Aqua Regia + └── play example.py:4 + └── sleep Lib/asyncio/tasks.py:702 + + If the await graph contains a cycle, ``pstree`` reports an error instead + of printing a tree. A cycle in the await graph is unusual and typically + indicates a programming error: + + .. code-block:: shell-session + + $ python -m asyncio pstree 12345 + ERROR: await-graph contains cycles - cannot print a tree! + + cycle: Task-2 → Task-3 → Task-2 + +.. option:: ps PID + + Display a flat table of all pending tasks in the process *PID*. Each row + shows the event-loop thread ID, task ID and name, coroutine stack, and the + awaiting task's stack, name, and ID, if any. + + This subcommand prints all tasks regardless of whether the await graph + contains cycles: + + .. code-block:: shell-session + + $ python -m asyncio ps 12345 + tid task id task name coroutine stack awaiter chain awaiter name awaiter id + ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ + 18445801 0x10a456060 Task-1 TaskGroup._aexit -> TaskGroup.__aexit__ -> main 0x0 + 18445801 0x10a439f60 Sundowning TaskGroup._aexit -> TaskGroup.__aexit__ -> album TaskGroup._aexit -> TaskGroup.__aexit__ -> main Task-1 0x10a456060 + 18445801 0x10a439d70 TMBTE TaskGroup._aexit -> TaskGroup.__aexit__ -> album TaskGroup._aexit -> TaskGroup.__aexit__ -> main Task-1 0x10a456060 + 18445801 0x10a2a3a80 TNDNBTG sleep -> play TaskGroup._aexit -> TaskGroup.__aexit__ -> album Sundowning 0x10a439f60 + 18445801 0x10a2a38a0 Levitate sleep -> play TaskGroup._aexit -> TaskGroup.__aexit__ -> album Sundowning 0x10a439f60 + 18445801 0x10a2d7150 DYWTYLM sleep -> play TaskGroup._aexit -> TaskGroup.__aexit__ -> album TMBTE 0x10a439d70 + 18445801 0x10a6bdaa0 Aqua Regia sleep -> play TaskGroup._aexit -> TaskGroup.__aexit__ -> album TMBTE 0x10a439d70 diff --git a/Doc/library/asyncio.rst b/Doc/library/asyncio.rst index 7d368dae49dc1d..8d19f49f6a0621 100644 --- a/Doc/library/asyncio.rst +++ b/Doc/library/asyncio.rst @@ -29,6 +29,11 @@ database connection libraries, distributed task queues, etc. asyncio is often a perfect fit for IO-bound and high-level **structured** network code. +.. seealso:: + + :ref:`a-conceptual-overview-of-asyncio` + Explanation of the fundamentals of asyncio. + asyncio provides a set of **high-level** APIs to: * :ref:`run Python coroutines ` concurrently and @@ -42,6 +47,13 @@ asyncio provides a set of **high-level** APIs to: * :ref:`synchronize ` concurrent code; +For **introspection**, asyncio provides APIs and tools for: + +* inspecting the :ref:`async call graph ` of tasks and futures; + +* inspecting tasks in another running Python process with + :ref:`command-line tools `; + Additionally, there are **low-level** APIs for *library and framework developers* to: @@ -74,6 +86,10 @@ You can experiment with an ``asyncio`` concurrent context in the :term:`REPL`: >>> await asyncio.sleep(10, result='hello') 'hello' +This REPL provides limited compatibility with :envvar:`PYTHON_BASIC_REPL`. +It is recommended that the default REPL is used +for full functionality and the latest features. + .. audit-event:: cpython.run_stdin "" "" .. versionchanged:: 3.12.5 (also 3.11.10, 3.10.15, 3.9.20, and 3.8.20) @@ -99,7 +115,13 @@ You can experiment with an ``asyncio`` concurrent context in the :term:`REPL`: asyncio-subprocess.rst asyncio-queue.rst asyncio-exceptions.rst + +.. toctree:: + :caption: Introspection APIs + :maxdepth: 1 + asyncio-graph.rst + asyncio-tools.rst .. toctree:: :caption: Low-level APIs @@ -119,6 +141,7 @@ You can experiment with an ``asyncio`` concurrent context in the :term:`REPL`: asyncio-api-index.rst asyncio-llapi-index.rst asyncio-dev.rst + asyncio-threading.rst .. note:: The source code for asyncio can be found in :source:`Lib/asyncio/`. diff --git a/Doc/library/atexit.rst b/Doc/library/atexit.rst index 02d2f0807df8f6..24a3492ba10c91 100644 --- a/Doc/library/atexit.rst +++ b/Doc/library/atexit.rst @@ -9,9 +9,9 @@ -------------- -The :mod:`atexit` module defines functions to register and unregister cleanup +The :mod:`!atexit` module defines functions to register and unregister cleanup functions. Functions thus registered are automatically executed upon normal -interpreter termination. :mod:`atexit` runs these functions in the *reverse* +interpreter termination. :mod:`!atexit` runs these functions in the *reverse* order in which they were registered; if you register ``A``, ``B``, and ``C``, at interpreter termination time they will be run in the order ``C``, ``B``, ``A``. @@ -64,7 +64,7 @@ a cleanup function is undefined. Remove *func* from the list of functions to be run at interpreter shutdown. :func:`unregister` silently does nothing if *func* was not previously registered. If *func* has been registered more than once, every occurrence - of that function in the :mod:`atexit` call stack will be removed. Equality + of that function in the :mod:`!atexit` call stack will be removed. Equality comparisons (``==``) are used internally during unregistration, so function references do not need to have matching identities. @@ -72,14 +72,14 @@ a cleanup function is undefined. .. seealso:: Module :mod:`readline` - Useful example of :mod:`atexit` to read and write :mod:`readline` history + Useful example of :mod:`!atexit` to read and write :mod:`readline` history files. .. _atexit-example: -:mod:`atexit` Example ---------------------- +:mod:`!atexit` Example +---------------------- The following simple example demonstrates how a module can initialize a counter from a file when it is imported and save the counter's updated value diff --git a/Doc/library/base64.rst b/Doc/library/base64.rst index 834ab2536e6c14..0248fa2f45f2f7 100644 --- a/Doc/library/base64.rst +++ b/Doc/library/base64.rst @@ -15,14 +15,11 @@ This module provides functions for encoding binary data to printable ASCII characters and decoding such encodings back to binary data. -It provides encoding and decoding functions for the encodings specified in -:rfc:`4648`, which defines the Base16, Base32, and Base64 algorithms, -and for the de-facto standard Ascii85 and Base85 encodings. - -The :rfc:`4648` encodings are suitable for encoding binary data so that it can be -safely sent by email, used as parts of URLs, or included as part of an HTTP -POST request. The encoding algorithm is not the same as the -:program:`uuencode` program. +This includes the :ref:`encodings specified in ` +:rfc:`4648` (Base64, Base32 and Base16), the :ref:`Base85 encoding +` specified in `PDF 2.0 +`_, and non-standard variants +of Base85 used elsewhere. There are two interfaces provided by this module. The modern interface supports encoding :term:`bytes-like objects ` to ASCII @@ -30,7 +27,7 @@ supports encoding :term:`bytes-like objects ` to ASCII strings containing ASCII to :class:`bytes`. Both base-64 alphabets defined in :rfc:`4648` (normal, and URL- and filesystem-safe) are supported. -The legacy interface does not support decoding from strings, but it does +The :ref:`legacy interface ` does not support decoding from strings, but it does provide functions for encoding and decoding to and from :term:`file objects `. It only supports the Base64 standard alphabet, and it adds newlines every 76 characters as per :rfc:`2045`. Note that if you are looking @@ -46,7 +43,15 @@ package instead. Any :term:`bytes-like objects ` are now accepted by all encoding and decoding functions in this module. Ascii85/Base85 support added. -The modern interface provides: + +.. _base64-rfc-4648: + +RFC 4648 Encodings +------------------ + +The :rfc:`4648` encodings are suitable for encoding binary data so that it can be +safely sent by email, used as parts of URLs, or included as part of an HTTP +POST request. .. function:: b64encode(s, altchars=None) @@ -181,6 +186,35 @@ The modern interface provides: incorrectly padded or if there are non-alphabet characters present in the input. +.. _base64-base-85: + +Base85 Encodings +----------------- + +Base85 encoding is a family of algorithms which represent four bytes +using five ASCII characters. Originally implemented in the Unix +``btoa(1)`` utility, a version of it was later adopted by Adobe in the +PostScript language and is standardized in PDF 2.0 (ISO 32000-2). +This version, in both its ``btoa`` and PDF variants, is implemented by +:func:`a85encode`. + +A separate version, using a different output character set, was +defined as an April Fool's joke in :rfc:`1924` but is now used by Git +and other software. This version is implemented by :func:`b85encode`. + +Finally, a third version, using yet another output character set +designed for safe inclusion in programming language strings, is +defined by ZeroMQ and implemented here by :func:`z85encode`. + +The functions present in this module differ in how they handle the following: + +* Whether to include and expect enclosing ``<~`` and ``~>`` markers. +* Whether to fold the input into multiple lines. +* The set of ASCII characters used for encoding. +* Compact encodings of sequences of spaces and null bytes. +* The encoding of zero-padding bytes applied to the input. + +Refer to the documentation of the individual functions for more information. .. function:: a85encode(b, *, foldspaces=False, wrapcol=0, pad=False, adobe=False) @@ -189,17 +223,22 @@ The modern interface provides: *foldspaces* is an optional flag that uses the special short sequence 'y' instead of 4 consecutive spaces (ASCII 0x20) as supported by 'btoa'. This - feature is not supported by the "standard" Ascii85 encoding. + feature is not supported by the standard encoding used in PDF. *wrapcol* controls whether the output should have newline (``b'\n'``) characters added to it. If this is non-zero, each output line will be at most this many characters long, excluding the trailing newline. - *pad* controls whether the input is padded to a multiple of 4 - before encoding. Note that the ``btoa`` implementation always pads. + *pad* controls whether zero-padding applied to the end of the input + is fully retained in the output encoding, as done by ``btoa``, + producing an exact multiple of 5 bytes of output. This is not part + of the standard encoding used in PDF, as it does not preserve the + length of the data. - *adobe* controls whether the encoded byte sequence is framed with ``<~`` - and ``~>``, which is used by the Adobe implementation. + *adobe* controls whether the encoded byte sequence is framed with + ``<~`` and ``~>``, as in a PostScript base-85 string literal. Note + that while ASCII85Decode streams in PDF documents *must* be + terminated with ``~>``, they *must not* use a leading ``<~``. .. versionadded:: 3.4 @@ -211,13 +250,14 @@ The modern interface provides: *foldspaces* is a flag that specifies whether the 'y' short sequence should be accepted as shorthand for 4 consecutive spaces (ASCII 0x20). - This feature is not supported by the "standard" Ascii85 encoding. + This feature is not supported by the standard Ascii85 encoding used in + PDF and PostScript. - *adobe* controls whether the input sequence is in Adobe Ascii85 format - (i.e. is framed with <~ and ~>). + *adobe* controls whether the ``<~`` and ``~>`` markers are + present. While the leading ``<~`` is not required, the input must + end with ``~>``, or a :exc:`ValueError` is raised. - *ignorechars* should be a :term:`bytes-like object` or ASCII string - containing characters to ignore + *ignorechars* should be a byte string containing characters to ignore from the input. This should only contain whitespace characters, and by default contains all whitespace characters in ASCII. @@ -229,8 +269,11 @@ The modern interface provides: Encode the :term:`bytes-like object` *b* using base85 (as used in e.g. git-style binary diffs) and return the encoded :class:`bytes`. - If *pad* is true, the input is padded with ``b'\0'`` so its length is a - multiple of 4 bytes before encoding. + The input is padded with ``b'\0'`` so its length is a multiple of 4 + bytes before encoding. If *pad* is true, all the resulting + characters are retained in the output, which will always be a + multiple of 5 bytes, and thus the length of the data may not be + preserved on decoding. .. versionadded:: 3.4 @@ -238,8 +281,7 @@ The modern interface provides: .. function:: b85decode(b) Decode the base85-encoded :term:`bytes-like object` or ASCII string *b* and - return the decoded :class:`bytes`. Padding is implicitly removed, if - necessary. + return the decoded :class:`bytes`. .. versionadded:: 3.4 @@ -247,8 +289,12 @@ The modern interface provides: .. function:: z85encode(s) Encode the :term:`bytes-like object` *s* using Z85 (as used in ZeroMQ) - and return the encoded :class:`bytes`. See `Z85 specification - `_ for more information. + and return the encoded :class:`bytes`. + + The `ZeroMQ specification `_ + requires the length of Z85-encoded data to be a multiple of 5 + bytes. To produce compliant data frames, you must pad the input + data to this function to a multiple of 4 bytes. .. versionadded:: 3.13 @@ -256,13 +302,15 @@ The modern interface provides: .. function:: z85decode(s) Decode the Z85-encoded :term:`bytes-like object` or ASCII string *s* and - return the decoded :class:`bytes`. See `Z85 specification - `_ for more information. + return the decoded :class:`bytes`. .. versionadded:: 3.13 -The legacy interface: +.. _base64-legacy: + +Legacy Interface +---------------- .. function:: decode(input, output) @@ -327,3 +375,11 @@ recommended to review the security section for any code deployed to production. Section 5.2, "Base64 Content-Transfer-Encoding," provides the definition of the base64 encoding. + `ISO 32000-2 Portable document format - Part 2: PDF 2.0 `_ + Section 7.4.3, "ASCII85Decode Filter," provides the definition + of the Ascii85 encoding used in PDF and PostScript, including + the output character set and the details of data length preservation + using zero-padding and partial output groups. + + `ZeroMQ RFC 32/Z85 `_ + The "Formal Specification" section provides the character set used in Z85. diff --git a/Doc/library/bdb.rst b/Doc/library/bdb.rst index 90f042aa377711..8d357f1895290a 100644 --- a/Doc/library/bdb.rst +++ b/Doc/library/bdb.rst @@ -8,7 +8,7 @@ -------------- -The :mod:`bdb` module handles basic debugger functions, like setting breakpoints +The :mod:`!bdb` module handles basic debugger functions, like setting breakpoints or managing execution via the debugger. The following exception is defined: @@ -18,7 +18,7 @@ The following exception is defined: Exception raised by the :class:`Bdb` class for quitting the debugger. -The :mod:`bdb` module also defines two classes: +The :mod:`!bdb` module also defines two classes: .. class:: Breakpoint(self, file, line, temporary=False, cond=None, funcname=None) @@ -240,7 +240,7 @@ The :mod:`bdb` module also defines two classes: Normally derived classes don't override the following methods, but they may if they want to redefine the definition of stopping and breakpoints. - .. method:: is_skipped_line(module_name) + .. method:: is_skipped_module(module_name) Return ``True`` if *module_name* matches any skip pattern. diff --git a/Doc/library/binascii.rst b/Doc/library/binascii.rst index 1bab785684bbab..4cd390d27e44e6 100644 --- a/Doc/library/binascii.rst +++ b/Doc/library/binascii.rst @@ -10,10 +10,10 @@ -------------- -The :mod:`binascii` module contains a number of methods to convert between +The :mod:`!binascii` module contains a number of methods to convert between binary and various ASCII-encoded binary representations. Normally, you will not use these functions directly but use wrapper modules like -:mod:`base64` instead. The :mod:`binascii` module contains +:mod:`base64` instead. The :mod:`!binascii` module contains low-level functions written in C for greater speed that are used by the higher-level modules. @@ -28,7 +28,7 @@ higher-level modules. ASCII-only unicode strings are now accepted by the ``a2b_*`` functions. -The :mod:`binascii` module defines the following functions: +The :mod:`!binascii` module defines the following functions: .. function:: a2b_uu(string) @@ -158,9 +158,8 @@ The :mod:`binascii` module defines the following functions: of hexadecimal digits (which can be upper or lower case), otherwise an :exc:`Error` exception is raised. - Similar functionality (accepting only text string arguments, but more - liberal towards whitespace) is also accessible using the - :meth:`bytes.fromhex` class method. + Similar functionality (but more liberal towards whitespace) is also accessible + using the :meth:`bytes.fromhex` class method. .. exception:: Error diff --git a/Doc/library/bisect.rst b/Doc/library/bisect.rst index 78da563397b625..83eee981c9b4eb 100644 --- a/Doc/library/bisect.rst +++ b/Doc/library/bisect.rst @@ -16,7 +16,7 @@ having to sort the list after each insertion. For long lists of items with expensive comparison operations, this can be an improvement over linear searches or frequent resorting. -The module is called :mod:`bisect` because it uses a basic bisection +The module is called :mod:`!bisect` because it uses a basic bisection algorithm to do its work. Unlike other bisection tools that search for a specific value, the functions in this module are designed to locate an insertion point. Accordingly, the functions never call an :meth:`~object.__eq__` @@ -24,6 +24,16 @@ method to determine whether a value has been found. Instead, the functions only call the :meth:`~object.__lt__` method and will return an insertion point between values in an array. +.. note:: + + The functions in this module are not thread-safe. If multiple threads + concurrently use :mod:`!bisect` functions on the same sequence, this + may result in undefined behaviour. Likewise, if the provided sequence + is mutated by a different thread while a :mod:`!bisect` function + is operating on it, the result is undefined. For example, using + :py:func:`~bisect.insort_left` on the same list from multiple threads + may result in the list becoming unsorted. + .. _bisect functions: The following functions are provided: @@ -73,7 +83,7 @@ The following functions are provided: Insert *x* in *a* in sorted order. This function first runs :py:func:`~bisect.bisect_left` to locate an insertion point. - Next, it runs the :meth:`!insert` method on *a* to insert *x* at the + Next, it runs the :meth:`~sequence.insert` method on *a* to insert *x* at the appropriate position to maintain sort order. To support inserting records in a table, the *key* function (if any) is @@ -93,7 +103,7 @@ The following functions are provided: entries of *x*. This function first runs :py:func:`~bisect.bisect_right` to locate an insertion point. - Next, it runs the :meth:`!insert` method on *a* to insert *x* at the + Next, it runs the :meth:`~sequence.insert` method on *a* to insert *x* at the appropriate position to maintain sort order. To support inserting records in a table, the *key* function (if any) is @@ -122,7 +132,7 @@ thoughts in mind: they are used. Consequently, if the search functions are used in a loop, the key function may be called again and again on the same array elements. If the key function isn't fast, consider wrapping it with - :py:func:`functools.cache` to avoid duplicate computations. Alternatively, + :py:deco:`functools.cache` to avoid duplicate computations. Alternatively, consider searching an array of precomputed keys to locate the insertion point (as shown in the examples section below). @@ -193,9 +203,9 @@ example uses :py:func:`~bisect.bisect` to look up a letter grade for an exam sco based on a set of ordered numeric breakpoints: 90 and up is an 'A', 80 to 89 is a 'B', and so on:: - >>> def grade(score, breakpoints=[60, 70, 80, 90], grades='FDCBA'): - ... i = bisect(breakpoints, score) - ... return grades[i] + >>> def grade(score): + ... i = bisect([60, 70, 80, 90], score) + ... return "FDCBA"[i] ... >>> [grade(score) for score in [33, 99, 77, 70, 89, 90, 100]] ['F', 'A', 'C', 'C', 'B', 'A', 'A'] diff --git a/Doc/library/bz2.rst b/Doc/library/bz2.rst index ebe2e43febaefa..32e223ddbdd8a2 100644 --- a/Doc/library/bz2.rst +++ b/Doc/library/bz2.rst @@ -16,7 +16,7 @@ This module provides a comprehensive interface for compressing and decompressing data using the bzip2 compression algorithm. -The :mod:`bz2` module contains: +The :mod:`!bz2` module contains: * The :func:`.open` function and :class:`BZ2File` class for reading and writing compressed files. @@ -25,6 +25,8 @@ The :mod:`bz2` module contains: * The :func:`compress` and :func:`decompress` functions for one-shot (de)compression. +.. include:: ../includes/optional-module.rst + (De)compression of files ------------------------ @@ -315,7 +317,7 @@ One-shot (de)compression Examples of usage ----------------- -Below are some examples of typical usage of the :mod:`bz2` module. +Below are some examples of typical usage of the :mod:`!bz2` module. Using :func:`compress` and :func:`decompress` to demonstrate round-trip compression: diff --git a/Doc/library/calendar.rst b/Doc/library/calendar.rst index 39090e36ed9c0d..5c3b0afc15fe52 100644 --- a/Doc/library/calendar.rst +++ b/Doc/library/calendar.rst @@ -56,13 +56,13 @@ interpreted as prescribed by the ISO 8601 standard. Year 0 is 1 BC, year -1 is .. method:: setfirstweekday(firstweekday) - Set the first weekday to *firstweekday*, passed as an :class:`int` (0--6) + Set the first weekday to *firstweekday*, passed as an :class:`int` (0--6). Identical to setting the :attr:`~Calendar.firstweekday` property. .. method:: iterweekdays() - Return an iterator for the week day numbers that will be used for one + Return an iterator for the weekday numbers that will be used for one week. The first value from the iterator will be the same as the value of the :attr:`~Calendar.firstweekday` property. @@ -88,7 +88,7 @@ interpreted as prescribed by the ISO 8601 standard. Year 0 is 1 BC, year -1 is Return an iterator for the month *month* in the year *year* similar to :meth:`itermonthdates`, but not restricted by the :class:`datetime.date` range. Days returned will be tuples consisting of a day of the month - number and a week day number. + number and a weekday number. .. method:: itermonthdays3(year, month) @@ -362,7 +362,7 @@ interpreted as prescribed by the ISO 8601 standard. Year 0 is 1 BC, year -1 is For simple text calendars this module provides the following functions. -.. function:: setfirstweekday(weekday) +.. function:: setfirstweekday(firstweekday) Sets the weekday (``0`` is Monday, ``6`` is Sunday) to start each week. The values :const:`MONDAY`, :const:`TUESDAY`, :const:`WEDNESDAY`, :const:`THURSDAY`, @@ -397,15 +397,15 @@ For simple text calendars this module provides the following functions. *month* (``1``--``12``), *day* (``1``--``31``). -.. function:: weekheader(n) +.. function:: weekheader(width) - Return a header containing abbreviated weekday names. *n* specifies the width in + Return a header containing abbreviated weekday names. *width* specifies the width in characters for one weekday. .. function:: monthrange(year, month) - Returns weekday of first day of the month and number of days in month, for the + Returns weekday of first day of the month and number of days in month, for the specified *year* and *month*. @@ -427,12 +427,12 @@ For simple text calendars this module provides the following functions. of the :class:`TextCalendar` class. -.. function:: prcal(year, w=0, l=0, c=6, m=3) +.. function:: prcal(theyear, w=0, l=0, c=6, m=3) Prints the calendar for an entire year as returned by :func:`calendar`. -.. function:: calendar(year, w=2, l=1, c=6, m=3) +.. function:: calendar(theyear, w=2, l=1, c=6, m=3) Returns a 3-column calendar for an entire year as a multi-line string using the :meth:`~TextCalendar.formatyear` of the :class:`TextCalendar` class. @@ -443,11 +443,11 @@ For simple text calendars this module provides the following functions. An unrelated but handy function that takes a time tuple such as returned by the :func:`~time.gmtime` function in the :mod:`time` module, and returns the corresponding Unix timestamp value, assuming an epoch of 1970, and the POSIX - encoding. In fact, :func:`time.gmtime` and :func:`timegm` are each others' + encoding. In fact, :func:`time.gmtime` and :func:`timegm` are each other's inverse. -The :mod:`calendar` module exports the following data attributes: +The :mod:`!calendar` module exports the following data attributes: .. data:: day_name @@ -540,13 +540,18 @@ The :mod:`calendar` module exports the following data attributes: .. versionadded:: 3.12 -The :mod:`calendar` module defines the following exceptions: +The :mod:`!calendar` module defines the following exceptions: .. exception:: IllegalMonthError(month) - A subclass of :exc:`ValueError`, + A subclass of :exc:`ValueError` and :exc:`IndexError`, raised when the given month number is outside of the range 1-12 (inclusive). + .. versionchanged:: 3.12 + :exc:`IllegalMonthError` is now also a subclass of + :exc:`ValueError`. New code should avoid catching + :exc:`IndexError`. + .. attribute:: month The invalid month number. @@ -579,7 +584,7 @@ Command-line usage .. versionadded:: 2.5 -The :mod:`calendar` module can be executed as a script from the command line +The :mod:`!calendar` module can be executed as a script from the command line to interactively print a calendar. .. code-block:: shell diff --git a/Doc/library/cmath.rst b/Doc/library/cmath.rst index 26518a0458fd81..f602003e49b821 100644 --- a/Doc/library/cmath.rst +++ b/Doc/library/cmath.rst @@ -124,7 +124,7 @@ rectangular coordinates to polar coordinates and back. The modulus (absolute value) of a complex number *z* can be computed using the built-in :func:`abs` function. There is no - separate :mod:`cmath` module function for this operation. + separate :mod:`!cmath` module function for this operation. .. function:: polar(z) @@ -338,7 +338,7 @@ Constants .. data:: nan A floating-point "not a number" (NaN) value. Equivalent to - ``float('nan')``. + ``float('nan')``. See also :data:`math.nan`. .. versionadded:: 3.6 @@ -357,7 +357,7 @@ Note that the selection of functions is similar, but not identical, to that in module :mod:`math`. The reason for having two modules is that some users aren't interested in complex numbers, and perhaps don't even know what they are. They would rather have ``math.sqrt(-1)`` raise an exception than return a complex -number. Also note that the functions defined in :mod:`cmath` always return a +number. Also note that the functions defined in :mod:`!cmath` always return a complex number, even if the answer can be expressed as a real number (in which case the complex number has an imaginary part of zero). diff --git a/Doc/library/cmd.rst b/Doc/library/cmd.rst index 66544f82f6ff3f..1757dedabbf633 100644 --- a/Doc/library/cmd.rst +++ b/Doc/library/cmd.rst @@ -245,7 +245,7 @@ Cmd Example .. sectionauthor:: Raymond Hettinger -The :mod:`cmd` module is mainly useful for building custom shells that let a +The :mod:`!cmd` module is mainly useful for building custom shells that let a user work with a program interactively. This section presents a simple example of how to build a shell around a few of diff --git a/Doc/library/cmdline.rst b/Doc/library/cmdline.rst index 16c67ddbf7cec2..c43b10157f9aea 100644 --- a/Doc/library/cmdline.rst +++ b/Doc/library/cmdline.rst @@ -16,17 +16,17 @@ The following modules have a command-line interface. * :ref:`dis ` * :ref:`doctest ` * :mod:`!encodings.rot_13` -* :mod:`ensurepip` +* :ref:`ensurepip ` * :mod:`filecmp` * :mod:`fileinput` * :mod:`ftplib` * :ref:`gzip ` * :ref:`http.server ` -* :mod:`!idlelib` +* :ref:`idlelib ` * :ref:`inspect ` * :ref:`json ` * :ref:`mimetypes ` -* :mod:`pdb` +* :ref:`pdb ` * :ref:`pickle ` * :ref:`pickletools ` * :ref:`platform ` @@ -52,8 +52,8 @@ The following modules have a command-line interface. * :mod:`turtledemo` * :ref:`unittest ` * :ref:`uuid ` -* :mod:`venv` -* :mod:`webbrowser` +* :ref:`venv ` +* :ref:`webbrowser ` * :ref:`zipapp ` * :ref:`zipfile ` diff --git a/Doc/library/cmdlinelibs.rst b/Doc/library/cmdlinelibs.rst index 085d31af7bca1f..32f8c2c9f4ae32 100644 --- a/Doc/library/cmdlinelibs.rst +++ b/Doc/library/cmdlinelibs.rst @@ -1,7 +1,7 @@ .. _cmdlinelibs: ******************************** -Command Line Interface Libraries +Command-line interface libraries ******************************** The modules described in this chapter assist with implementing @@ -19,3 +19,4 @@ Here's an overview: curses.rst curses.ascii.rst curses.panel.rst + cmd.rst diff --git a/Doc/library/code.rst b/Doc/library/code.rst index 8f7692df9fb22d..52587c4dd8f8e8 100644 --- a/Doc/library/code.rst +++ b/Doc/library/code.rst @@ -22,6 +22,12 @@ build applications which provide an interactive interpreter prompt. it defaults to a newly created dictionary with key ``'__name__'`` set to ``'__console__'`` and key ``'__doc__'`` set to ``None``. + Note that functions and classes objects created under an + :class:`!InteractiveInterpreter` instance will belong to the namespace + specified by *locals*. + They are only pickleable if *locals* is the namespace of an existing + module. + .. class:: InteractiveConsole(locals=None, filename="", local_exit=False) diff --git a/Doc/library/codecs.rst b/Doc/library/codecs.rst index 86511602fa5a60..cf17e0d34dc2a6 100644 --- a/Doc/library/codecs.rst +++ b/Doc/library/codecs.rst @@ -53,6 +53,14 @@ any codec: :exc:`UnicodeDecodeError`). Refer to :ref:`codec-base-classes` for more information on codec error handling. +.. function:: charmap_build(string) + + Return a mapping suitable for encoding with a custom single-byte encoding. + Given a :class:`str` *string* of up to 256 characters representing a + decoding table, returns either a compact internal mapping object + ``EncodingMap`` or a :class:`dictionary ` mapping character ordinals + to byte values. Raises a :exc:`TypeError` on invalid input. + The full details for each codec can also be looked up directly: .. function:: lookup(encoding, /) @@ -235,8 +243,8 @@ wider range of codecs when working with binary files: .. function:: iterencode(iterator, encoding, errors='strict', **kwargs) Uses an incremental encoder to iteratively encode the input provided by - *iterator*. This function is a :term:`generator`. - The *errors* argument (as well as any + *iterator*. *iterator* must yield :class:`str` objects. + This function is a :term:`generator`. The *errors* argument (as well as any other keyword argument) is passed through to the incremental encoder. This function requires that the codec accept text :class:`str` objects @@ -247,8 +255,8 @@ wider range of codecs when working with binary files: .. function:: iterdecode(iterator, encoding, errors='strict', **kwargs) Uses an incremental decoder to iteratively decode the input provided by - *iterator*. This function is a :term:`generator`. - The *errors* argument (as well as any + *iterator*. *iterator* must yield :class:`bytes` objects. + This function is a :term:`generator`. The *errors* argument (as well as any other keyword argument) is passed through to the incremental decoder. This function requires that the codec accept :class:`bytes` objects @@ -257,6 +265,20 @@ wider range of codecs when working with binary files: :func:`iterencode`. +.. function:: readbuffer_encode(buffer, errors=None, /) + + Return a :class:`tuple` containing the raw bytes of *buffer*, a + :ref:`buffer-compatible object ` or :class:`str` + (encoded to UTF-8 before processing), and their length in bytes. + + The *errors* argument is ignored. + + .. code-block:: pycon + + >>> codecs.readbuffer_encode(b"Zito") + (b'Zito', 4) + + The module also provides the following constants which are useful for reading and writing to platform dependent files: @@ -288,7 +310,7 @@ and writing to platform dependent files: Codec Base Classes ------------------ -The :mod:`codecs` module defines a set of base classes which define the +The :mod:`!codecs` module defines a set of base classes which define the interfaces for working with codec objects, and can also be used as the basis for custom codec implementations. @@ -960,17 +982,22 @@ defined in Unicode. A simple and straightforward way that can store each Unicode code point, is to store each code point as four consecutive bytes. There are two possibilities: store the bytes in big endian or in little endian order. These two encodings are called ``UTF-32-BE`` and ``UTF-32-LE`` respectively. Their -disadvantage is that if e.g. you use ``UTF-32-BE`` on a little endian machine you -will always have to swap bytes on encoding and decoding. ``UTF-32`` avoids this -problem: bytes will always be in natural endianness. When these bytes are read -by a CPU with a different endianness, then bytes have to be swapped though. To -be able to detect the endianness of a ``UTF-16`` or ``UTF-32`` byte sequence, -there's the so called BOM ("Byte Order Mark"). This is the Unicode character -``U+FEFF``. This character can be prepended to every ``UTF-16`` or ``UTF-32`` -byte sequence. The byte swapped version of this character (``0xFFFE``) is an -illegal character that may not appear in a Unicode text. So when the -first character in a ``UTF-16`` or ``UTF-32`` byte sequence -appears to be a ``U+FFFE`` the bytes have to be swapped on decoding. +disadvantage is that if, for example, you use ``UTF-32-BE`` on a little endian +machine you will always have to swap bytes on encoding and decoding. +Python's ``UTF-16`` and ``UTF-32`` codecs avoid this problem by using the +platform's native byte order when no BOM is present. +Python follows prevailing platform +practice, so native-endian data round-trips without redundant byte swapping, +even though the Unicode Standard defaults to big-endian when the byte order is +unspecified. When these bytes are read by a CPU with a different endianness, +the bytes have to be swapped. To be able to detect the endianness of a +``UTF-16`` or ``UTF-32`` byte sequence, a BOM ("Byte Order Mark") is used. +This is the Unicode character ``U+FEFF``. This character can be prepended to every +``UTF-16`` or ``UTF-32`` byte sequence. The byte swapped version of this character +(``0xFFFE``) is an illegal character that may not appear in a Unicode text. +When the first character of a ``UTF-16`` or ``UTF-32`` byte sequence is +``U+FFFE``, the bytes have to be swapped on decoding. + Unfortunately the character ``U+FEFF`` had a second purpose as a ``ZERO WIDTH NO-BREAK SPACE``: a character that has no width and doesn't allow a word to be split. It can e.g. be used to give hints to a ligature algorithm. @@ -1043,8 +1070,15 @@ or with dictionaries as mapping tables. The following table lists the codecs by name, together with a few common aliases, and the languages for which the encoding is likely used. Neither the list of aliases nor the list of languages is meant to be exhaustive. Notice that spelling alternatives that only differ in -case or use a hyphen instead of an underscore are also valid aliases; therefore, -e.g. ``'utf-8'`` is a valid alias for the ``'utf_8'`` codec. +case or use a hyphen instead of an underscore are also valid aliases +because they are equivalent when normalized by +:func:`~encodings.normalize_encoding`. For example, ``'utf-8'`` is a valid +alias for the ``'utf_8'`` codec. + +.. note:: + + The below table lists the most common aliases, for a complete list + refer to the source :source:`aliases.py ` file. On Windows, ``cpXXX`` codecs are available for all code pages. But only codecs listed in the following table are guarantead to exist on @@ -1118,7 +1152,7 @@ particular, the following variants typically exist: +-----------------+--------------------------------+--------------------------------+ | cp857 | 857, IBM857 | Turkish | +-----------------+--------------------------------+--------------------------------+ -| cp858 | 858, IBM858 | Western Europe | +| cp858 | 858, IBM00858 | Western Europe | +-----------------+--------------------------------+--------------------------------+ | cp860 | 860, IBM860 | Portuguese | +-----------------+--------------------------------+--------------------------------+ @@ -1155,7 +1189,7 @@ particular, the following variants typically exist: | | | | | | | .. versionadded:: 3.4 | +-----------------+--------------------------------+--------------------------------+ -| cp1140 | ibm1140 | Western Europe | +| cp1140 | IBM01140 | Western Europe | +-----------------+--------------------------------+--------------------------------+ | cp1250 | windows-1250 | Central and Eastern Europe | +-----------------+--------------------------------+--------------------------------+ @@ -1222,7 +1256,7 @@ particular, the following variants typically exist: +-----------------+--------------------------------+--------------------------------+ | iso8859_3 | iso-8859-3, latin3, L3 | Esperanto, Maltese | +-----------------+--------------------------------+--------------------------------+ -| iso8859_4 | iso-8859-4, latin4, L4 | Baltic languages | +| iso8859_4 | iso-8859-4, latin4, L4 | Northern Europe | +-----------------+--------------------------------+--------------------------------+ | iso8859_5 | iso-8859-5, cyrillic | Belarusian, Bulgarian, | | | | Macedonian, Russian, Serbian | @@ -1362,6 +1396,14 @@ encodings. | punycode | | Implement :rfc:`3492`. | | | | Stateful codecs are not | | | | supported. | +| | | | +| | | .. warning:: | +| | | | +| | | The decoding and | +| | | encoding algorithms | +| | | scale poorly, so | +| | | limit the length of | +| | | untrusted input. | +--------------------+---------+---------------------------+ | raw_unicode_escape | | Latin-1 encoding with | | | | :samp:`\\u{XXXX}` and | @@ -1373,7 +1415,11 @@ encodings. | | | It is used in the Python | | | | pickle protocol. | +--------------------+---------+---------------------------+ -| undefined | | Raise an exception for | +| undefined | | This Codec should only | +| | | be used for testing | +| | | purposes. | +| | | | +| | | Raise an exception for | | | | all conversions, even | | | | empty strings. The error | | | | handler is ignored. | @@ -1450,6 +1496,36 @@ to :class:`bytes` mappings. They are not supported by :meth:`bytes.decode` Restoration of the aliases for the binary transforms. +.. _standalone-codec-functions: + +Standalone Codec Functions +^^^^^^^^^^^^^^^^^^^^^^^^^^ + +The following functions provide encoding and decoding functionality similar to codecs, +but are not available as named codecs through :func:`codecs.encode` or :func:`codecs.decode`. +They are used internally (for example, by :mod:`pickle`) and behave similarly to the +``string_escape`` codec that was removed in Python 3. + +.. function:: codecs.escape_encode(input, errors=None) + + Encode *input* using escape sequences. Similar to how :func:`repr` on bytes + produces escaped byte values. + + *input* must be a :class:`bytes` object. + + Returns a tuple ``(output, length)`` where *output* is a :class:`bytes` + object and *length* is the number of bytes consumed. + +.. function:: codecs.escape_decode(input, errors=None) + + Decode *input* from escape sequences back to the original bytes. + + *input* must be a :term:`bytes-like object`. + + Returns a tuple ``(output, length)`` where *output* is a :class:`bytes` + object and *length* is the number of bytes consumed. + + .. _text-transforms: Text Transforms @@ -1476,8 +1552,68 @@ mapping. It is not supported by :meth:`str.encode` (which only produces Restoration of the ``rot13`` alias. -:mod:`encodings.idna` --- Internationalized Domain Names in Applications ------------------------------------------------------------------------- +:mod:`!encodings` --- Encodings package +--------------------------------------- + +.. module:: encodings + :synopsis: Encodings package + +This module implements the following functions: + +.. function:: normalize_encoding(encoding) + + Normalize encoding name *encoding*. + + Normalization works as follows: all non-alphanumeric characters except the + dot used for Python package names are collapsed and replaced with a single + underscore, leading and trailing underscores are removed. + For example, ``' -;#'`` becomes ``'_'``. + + Note that *encoding* should be ASCII only. + + +.. note:: + The following functions should not be used directly, except for testing + purposes; :func:`codecs.lookup` should be used instead. + + +.. function:: search_function(encoding) + + Search for the codec module corresponding to the given encoding name + *encoding*. + + This function first normalizes the *encoding* using + :func:`normalize_encoding`, then looks for a corresponding alias. + It attempts to import a codec module from the encodings package using either + the alias or the normalized name. If the module is found and defines a valid + ``getregentry()`` function that returns a :class:`codecs.CodecInfo` object, + the codec is cached and returned. + + If the codec module defines a ``getaliases()`` function any returned aliases + are registered for future use. + + +.. function:: win32_code_page_search_function(encoding) + + Search for a Windows code page encoding *encoding* of the form ``cpXXXX``. + + If the code page is valid and supported, return a :class:`codecs.CodecInfo` + object for it. + + .. availability:: Windows. + + .. versionadded:: 3.14 + + +This module implements the following exception: + +.. exception:: CodecRegistryError + + Raised when a codec is invalid or incompatible. + + +:mod:`!encodings.idna` --- Internationalized Domain Names in Applications +------------------------------------------------------------------------- .. module:: encodings.idna :synopsis: Internationalized Domain Names implementation @@ -1519,7 +1655,7 @@ When receiving host names from the wire (such as in reverse name lookup), no automatic conversion to Unicode is performed: applications wishing to present such host names to the user should decode them to Unicode. -The module :mod:`encodings.idna` also implements the nameprep procedure, which +The module :mod:`!encodings.idna` also implements the nameprep procedure, which performs certain normalizations on host names, to achieve case-insensitivity of international domain names, and to unify similar characters. The nameprep functions can be used directly if desired. @@ -1542,8 +1678,8 @@ functions can be used directly if desired. Convert a label to Unicode, as specified in :rfc:`3490`. -:mod:`encodings.mbcs` --- Windows ANSI codepage ------------------------------------------------ +:mod:`!encodings.mbcs` --- Windows ANSI codepage +------------------------------------------------ .. module:: encodings.mbcs :synopsis: Windows ANSI codepage @@ -1560,8 +1696,8 @@ This module implements the ANSI codepage (CP_ACP). Support any error handler. -:mod:`encodings.utf_8_sig` --- UTF-8 codec with BOM signature -------------------------------------------------------------- +:mod:`!encodings.utf_8_sig` --- UTF-8 codec with BOM signature +-------------------------------------------------------------- .. module:: encodings.utf_8_sig :synopsis: UTF-8 codec with BOM signature diff --git a/Doc/library/codeop.rst b/Doc/library/codeop.rst index 16f674adb4b22b..2e6d65980381ad 100644 --- a/Doc/library/codeop.rst +++ b/Doc/library/codeop.rst @@ -11,7 +11,7 @@ -------------- -The :mod:`codeop` module provides utilities upon which the Python +The :mod:`!codeop` module provides utilities upon which the Python read-eval-print loop can be emulated, as is done in the :mod:`code` module. As a result, you probably don't want to use the module directly; if you want to include such a loop in your program you probably want to use the :mod:`code` @@ -25,7 +25,7 @@ There are two parts to this job: #. Remembering which future statements the user has entered, so subsequent input can be compiled with these in effect. -The :mod:`codeop` module provides a way of doing each of these things, and a way +The :mod:`!codeop` module provides a way of doing each of these things, and a way of doing them both. To do just the former: diff --git a/Doc/library/collections.abc.rst b/Doc/library/collections.abc.rst index daa9af6d1dd9c9..213c79cc41494c 100644 --- a/Doc/library/collections.abc.rst +++ b/Doc/library/collections.abc.rst @@ -140,6 +140,9 @@ ABC Inherits from Abstract Methods Mi ``__len__``, ``insert`` +:class:`ByteString` :class:`Sequence` ``__getitem__``, Inherited :class:`Sequence` methods + ``__len__`` + :class:`Set` :class:`Collection` ``__contains__``, ``__le__``, ``__lt__``, ``__eq__``, ``__ne__``, ``__iter__``, ``__gt__``, ``__ge__``, ``__and__``, ``__or__``, ``__len__`` ``__sub__``, ``__rsub__``, ``__xor__``, ``__rxor__`` @@ -260,21 +263,50 @@ Collections Abstract Base Classes -- Detailed Descriptions .. class:: Sequence MutableSequence + ByteString ABCs for read-only and mutable :term:`sequences `. Implementation note: Some of the mixin methods, such as - :meth:`~container.__iter__`, :meth:`~object.__reversed__` and :meth:`index`, make - repeated calls to the underlying :meth:`~object.__getitem__` method. + :meth:`~container.__iter__`, :meth:`~object.__reversed__`, + and :meth:`~sequence.index` make repeated calls to the underlying + :meth:`~object.__getitem__` method. Consequently, if :meth:`~object.__getitem__` is implemented with constant access speed, the mixin methods will have linear performance; however, if the underlying method is linear (as it would be with a linked list), the mixins will have quadratic performance and will likely need to be overridden. - .. versionchanged:: 3.5 - The index() method added support for *stop* and *start* - arguments. + .. method:: index(value, start=0, stop=None) + + Return first index of *value*. + + Raises :exc:`ValueError` if the value is not present. + + Supporting the *start* and *stop* arguments is optional, but recommended. + + .. versionchanged:: 3.5 + The :meth:`~sequence.index` method gained support for + the *stop* and *start* arguments. + + .. deprecated-removed:: 3.12 3.17 + The :class:`ByteString` ABC has been deprecated. + + Use ``isinstance(obj, collections.abc.Buffer)`` to test if ``obj`` + implements the :ref:`buffer protocol ` at runtime. For use + in type annotations, either use :class:`Buffer` or a union that + explicitly specifies the types your code supports (e.g., + ``bytes | bytearray | memoryview``). + + :class:`!ByteString` was originally intended to be an abstract class that + would serve as a supertype of both :class:`bytes` and :class:`bytearray`. + However, since the ABC never had any methods, knowing that an object was + an instance of :class:`!ByteString` never actually told you anything + useful about the object. Other common buffer types such as + :class:`memoryview` were also never understood as subtypes of + :class:`!ByteString` (either at runtime or by static type checkers). + + See :pep:`PEP 688 <688#current-options>` for more details. .. class:: Set MutableSet @@ -304,7 +336,7 @@ Collections Abstract Base Classes -- Detailed Descriptions .. note:: In CPython, generator-based coroutines (:term:`generators ` - decorated with :func:`@types.coroutine `) are + decorated with :deco:`types.coroutine`) are *awaitables*, even though they do not have an :meth:`~object.__await__` method. Using ``isinstance(gencoro, Awaitable)`` for them will return ``False``. Use :func:`inspect.isawaitable` to detect them. @@ -322,7 +354,7 @@ Collections Abstract Base Classes -- Detailed Descriptions .. note:: In CPython, generator-based coroutines (:term:`generators ` - decorated with :func:`@types.coroutine `) are + decorated with :deco:`types.coroutine`) are *awaitables*, even though they do not have an :meth:`~object.__await__` method. Using ``isinstance(gencoro, Coroutine)`` for them will return ``False``. Use :func:`inspect.isawaitable` to detect them. @@ -427,7 +459,7 @@ Notes on using :class:`Set` and :class:`MutableSet` as a mixin: The :class:`Set` mixin provides a :meth:`!_hash` method to compute a hash value for the set; however, :meth:`~object.__hash__` is not defined because not all sets are :term:`hashable` or immutable. To add set hashability using mixins, - inherit from both :meth:`Set` and :meth:`Hashable`, then define + inherit from both :class:`Set` and :class:`Hashable`, then define ``__hash__ = Set._hash``. .. seealso:: diff --git a/Doc/library/collections.rst b/Doc/library/collections.rst index 5fbdb12f40cafa..db5c49c026c17a 100644 --- a/Doc/library/collections.rst +++ b/Doc/library/collections.rst @@ -240,7 +240,9 @@ For example:: [('the', 1143), ('and', 966), ('to', 762), ('of', 669), ('i', 631), ('you', 554), ('a', 546), ('my', 514), ('hamlet', 471), ('in', 451)] -.. class:: Counter([iterable-or-mapping]) +.. class:: Counter(**kwargs) + Counter(iterable, /, **kwargs) + Counter(mapping, /, **kwargs) A :class:`Counter` is a :class:`dict` subclass for counting :term:`hashable` objects. It is a collection where elements are stored as dictionary keys @@ -290,7 +292,7 @@ For example:: >>> sorted(c.elements()) ['a', 'a', 'a', 'a', 'b', 'b'] - .. method:: most_common([n]) + .. method:: most_common(n=None) Return a list of the *n* most common elements and their counts from the most common to the least. If *n* is omitted or ``None``, @@ -300,7 +302,9 @@ For example:: >>> Counter('abracadabra').most_common(3) [('a', 5), ('b', 2), ('r', 2)] - .. method:: subtract([iterable-or-mapping]) + .. method:: subtract(**kwargs) + subtract(iterable, /, **kwargs) + subtract(mapping, /, **kwargs) Elements are subtracted from an *iterable* or from another *mapping* (or counter). Like :meth:`dict.update` but subtracts counts instead @@ -331,7 +335,9 @@ For example:: This class method is not implemented for :class:`Counter` objects. - .. method:: update([iterable-or-mapping]) + .. method:: update(**kwargs) + update(iterable, /, **kwargs) + update(mapping, /, **kwargs) Elements are counted from an *iterable* or added-in from another *mapping* (or counter). Like :meth:`dict.update` but adds counts @@ -474,17 +480,19 @@ or subtracting from an empty counter. Unix. They are also useful for tracking transactions and other pools of data where only the most recent activity is of interest. + Deques are :ref:`generic ` over the type of their contents. + Deque objects support the following methods: - .. method:: append(x) + .. method:: append(item, /) - Add *x* to the right side of the deque. + Add *item* to the right side of the deque. - .. method:: appendleft(x) + .. method:: appendleft(item, /) - Add *x* to the left side of the deque. + Add *item* to the left side of the deque. .. method:: clear() @@ -499,38 +507,38 @@ or subtracting from an empty counter. .. versionadded:: 3.5 - .. method:: count(x) + .. method:: count(value, /) - Count the number of deque elements equal to *x*. + Count the number of deque elements equal to *value*. .. versionadded:: 3.2 - .. method:: extend(iterable) + .. method:: extend(iterable, /) Extend the right side of the deque by appending elements from the iterable argument. - .. method:: extendleft(iterable) + .. method:: extendleft(iterable, /) Extend the left side of the deque by appending elements from *iterable*. Note, the series of left appends results in reversing the order of elements in the iterable argument. - .. method:: index(x[, start[, stop]]) + .. method:: index(value[, start[, stop]]) - Return the position of *x* in the deque (at or after index *start* + Return the position of *value* in the deque (at or after index *start* and before index *stop*). Returns the first match or raises :exc:`ValueError` if not found. .. versionadded:: 3.5 - .. method:: insert(i, x) + .. method:: insert(index, value, /) - Insert *x* into the deque at position *i*. + Insert *value* into the deque at position *index*. If the insertion would cause a bounded deque to grow beyond *maxlen*, an :exc:`IndexError` is raised. @@ -550,7 +558,7 @@ or subtracting from an empty counter. elements are present, raises an :exc:`IndexError`. - .. method:: remove(value) + .. method:: remove(value, /) Remove the first occurrence of *value*. If not found, raises a :exc:`ValueError`. @@ -563,7 +571,7 @@ or subtracting from an empty counter. .. versionadded:: 3.2 - .. method:: rotate(n=1) + .. method:: rotate(n=1, /) Rotate the deque *n* steps to the right. If *n* is negative, rotate to the left. @@ -715,7 +723,9 @@ stack manipulations such as ``dup``, ``drop``, ``swap``, ``over``, ``pick``, :class:`defaultdict` objects ---------------------------- -.. class:: defaultdict(default_factory=None, /, [...]) +.. class:: defaultdict(default_factory=None, /, **kwargs) + defaultdict(default_factory, mapping, /, **kwargs) + defaultdict(default_factory, iterable, /, **kwargs) Return a new dictionary-like object. :class:`defaultdict` is a subclass of the built-in :class:`dict` class. It overrides one method and adds one writable @@ -727,11 +737,14 @@ stack manipulations such as ``dup``, ``drop``, ``swap``, ``over``, ``pick``, as if they were passed to the :class:`dict` constructor, including keyword arguments. + :class:`!defaultdict`\s are :ref:`generic ` over two types, + signifying (respectively) the types of the dictionary's keys and values. + :class:`defaultdict` objects support the following method in addition to the standard :class:`dict` operations: - .. method:: __missing__(key) + .. method:: __missing__(key, /) If the :attr:`default_factory` attribute is ``None``, this raises a :exc:`KeyError` exception with the *key* as argument. @@ -758,9 +771,9 @@ stack manipulations such as ``dup``, ``drop``, ``swap``, ``over``, ``pick``, .. attribute:: default_factory - This attribute is used by the :meth:`__missing__` method; it is - initialized from the first argument to the constructor, if present, or to - ``None``, if absent. + This attribute is used by the :meth:`~defaultdict.__missing__` method; + it is initialized from the first argument to the constructor, if present, + or to ``None``, if absent. .. versionchanged:: 3.9 Added merge (``|``) and update (``|=``) operators, specified in @@ -783,10 +796,10 @@ sequence of key-value pairs into a dictionary of lists: When each key is encountered for the first time, it is not already in the mapping; so an entry is automatically created using the :attr:`~defaultdict.default_factory` -function which returns an empty :class:`list`. The :meth:`!list.append` +function which returns an empty :class:`list`. The :meth:`list.append` operation then attaches the value to the new list. When keys are encountered again, the look-up proceeds normally (returning the list for that key) and the -:meth:`!list.append` operation adds another value to the list. This technique is +:meth:`list.append` operation adds another value to the list. This technique is simpler and faster than an equivalent technique using :meth:`dict.setdefault`: >>> d = {} @@ -937,7 +950,7 @@ In addition to the methods inherited from tuples, named tuples support three additional methods and two attributes. To prevent conflicts with field names, the method and attribute names start with an underscore. -.. classmethod:: somenamedtuple._make(iterable) +.. classmethod:: somenamedtuple._make(iterable, /) Class method that makes a new instance from an existing sequence or iterable. @@ -1134,7 +1147,9 @@ Some differences from :class:`dict` still remain: * Until Python 3.8, :class:`dict` lacked a :meth:`~object.__reversed__` method. -.. class:: OrderedDict([items]) +.. class:: OrderedDict(**kwargs) + OrderedDict(mapping, /, **kwargs) + OrderedDict(iterable, /, **kwargs) Return an instance of a :class:`dict` subclass that has methods specialized for rearranging dictionary order. @@ -1209,12 +1224,12 @@ original insertion position is changed and moved to the end:: self.move_to_end(key) An :class:`OrderedDict` would also be useful for implementing -variants of :func:`functools.lru_cache`: +variants of :deco:`functools.lru_cache`: .. testcode:: from collections import OrderedDict - from time import time + from time import monotonic class TimeBoundedLRU: "LRU Cache that invalidates and refreshes old entries." @@ -1229,10 +1244,10 @@ variants of :func:`functools.lru_cache`: if args in self.cache: self.cache.move_to_end(args) timestamp, result = self.cache[args] - if time() - timestamp <= self.maxage: + if monotonic() - timestamp <= self.maxage: return result result = self.func(*args) - self.cache[args] = time(), result + self.cache[args] = monotonic(), result if len(self.cache) > self.maxsize: self.cache.popitem(last=False) return result @@ -1315,16 +1330,17 @@ subclass directly from :class:`dict`; however, this class can be easier to work with because the underlying dictionary is accessible as an attribute. -.. class:: UserDict([initialdata]) +.. class:: UserDict(**kwargs) + UserDict(mapping, /, **kwargs) + UserDict(iterable, /, **kwargs) Class that simulates a dictionary. The instance's contents are kept in a regular dictionary, which is accessible via the :attr:`data` attribute of - :class:`UserDict` instances. If *initialdata* is provided, :attr:`data` is - initialized with its contents; note that a reference to *initialdata* will not - be kept, allowing it to be used for other purposes. + :class:`!UserDict` instances. If arguments are provided, they are used to + initialize :attr:`data`, like a regular dictionary. In addition to supporting the methods and operations of mappings, - :class:`UserDict` instances provide the following attribute: + :class:`!UserDict` instances provide the following attribute: .. attribute:: data diff --git a/Doc/library/colorsys.rst b/Doc/library/colorsys.rst index ffebf4e40dd609..2d3dc2b8b57935 100644 --- a/Doc/library/colorsys.rst +++ b/Doc/library/colorsys.rst @@ -10,7 +10,7 @@ -------------- -The :mod:`colorsys` module defines bidirectional conversions of color values +The :mod:`!colorsys` module defines bidirectional conversions of color values between colors expressed in the RGB (Red Green Blue) color space used in computer monitors and three other coordinate systems: YIQ, HLS (Hue Lightness Saturation) and HSV (Hue Saturation Value). Coordinates in all of these color @@ -24,7 +24,7 @@ spaces, the coordinates are all between 0 and 1. https://poynton.ca/ColorFAQ.html and https://www.cambridgeincolour.com/tutorials/color-spaces.htm. -The :mod:`colorsys` module defines the following functions: +The :mod:`!colorsys` module defines the following functions: .. function:: rgb_to_yiq(r, g, b) diff --git a/Doc/library/compileall.rst b/Doc/library/compileall.rst index c42288419c4d2d..ebbbf857e717a4 100644 --- a/Doc/library/compileall.rst +++ b/Doc/library/compileall.rst @@ -56,11 +56,18 @@ compile Python sources. executed. .. option:: -s strip_prefix + + Remove the given prefix from paths recorded in the ``.pyc`` files. + Paths are made relative to the prefix. + + This option can be used with ``-p`` but not with ``-d``. + .. option:: -p prepend_prefix - Remove (``-s``) or append (``-p``) the given prefix of paths - recorded in the ``.pyc`` files. - Cannot be combined with ``-d``. + Prepend the given prefix to paths recorded in the ``.pyc`` files. + Use ``-p /`` to make the paths absolute. + + This option can be used with ``-s`` but not with ``-d``. .. option:: -x regex diff --git a/Doc/library/compression.rst b/Doc/library/compression.rst new file mode 100644 index 00000000000000..98719be9992acc --- /dev/null +++ b/Doc/library/compression.rst @@ -0,0 +1,20 @@ +The :mod:`!compression` package +=============================== + +.. module:: compression + +.. versionadded:: 3.14 + +The :mod:`!compression` package contains the canonical compression modules +containing interfaces to several different compression algorithms. Some of +these modules have historically been available as separate modules; those will +continue to be available under their original names for compatibility reasons, +and will not be removed without a deprecation cycle. The use of modules in +:mod:`!compression` is encouraged where practical. + +* :mod:`!compression.bz2` -- Re-exports :mod:`bz2` +* :mod:`!compression.gzip` -- Re-exports :mod:`gzip` +* :mod:`!compression.lzma` -- Re-exports :mod:`lzma` +* :mod:`!compression.zlib` -- Re-exports :mod:`zlib` +* :mod:`compression.zstd` -- Wrapper for the Zstandard compression library + diff --git a/Doc/library/compression.zstd.rst b/Doc/library/compression.zstd.rst new file mode 100644 index 00000000000000..6cb9a16141b416 --- /dev/null +++ b/Doc/library/compression.zstd.rst @@ -0,0 +1,899 @@ +:mod:`!compression.zstd` --- Compression compatible with the Zstandard format +============================================================================= + +.. module:: compression.zstd + :synopsis: Low-level interface to compression and decompression routines in + the zstd library. + +.. versionadded:: 3.14 + +**Source code:** :source:`Lib/compression/zstd/__init__.py` + +-------------- + +This module provides classes and functions for compressing and decompressing +data using the Zstandard (or *zstd*) compression algorithm. The +`zstd manual `__ +describes Zstandard as "a fast lossless compression algorithm, targeting +real-time compression scenarios at zlib-level and better compression ratios." +Also included is a file interface that supports reading and writing the +contents of ``.zst`` files created by the :program:`zstd` utility, as well as +raw zstd compressed streams. + +The :mod:`!compression.zstd` module contains: + +* The :func:`.open` function and :class:`ZstdFile` class for reading and + writing compressed files. +* The :class:`ZstdCompressor` and :class:`ZstdDecompressor` classes for + incremental (de)compression. +* The :func:`compress` and :func:`decompress` functions for one-shot + (de)compression. +* The :func:`train_dict` and :func:`finalize_dict` functions and the + :class:`ZstdDict` class to train and manage Zstandard dictionaries. +* The :class:`CompressionParameter`, :class:`DecompressionParameter`, and + :class:`Strategy` classes for setting advanced (de)compression parameters. + +.. include:: ../includes/optional-module.rst + + +Exceptions +---------- + +.. exception:: ZstdError + + This exception is raised when an error occurs during compression or + decompression, or while initializing the (de)compressor state. + + +Reading and writing compressed files +------------------------------------ + +.. function:: open(file, /, mode='rb', *, level=None, options=None, \ + zstd_dict=None, encoding=None, errors=None, newline=None) + + Open a Zstandard-compressed file in binary or text mode, returning a + :term:`file object`. + + The *file* argument can be either a file name (given as a + :class:`str`, :class:`bytes` or :term:`path-like ` + object), in which case the named file is opened, or it can be an existing + file object to read from or write to. + + The mode argument can be either ``'rb'`` for reading (default), ``'wb'`` for + overwriting, ``'ab'`` for appending, or ``'xb'`` for exclusive creation. + These can equivalently be given as ``'r'``, ``'w'``, ``'a'``, and ``'x'`` + respectively. You may also open in text mode with ``'rt'``, ``'wt'``, + ``'at'``, and ``'xt'`` respectively. + + When reading, the *options* argument can be a dictionary providing advanced + decompression parameters; see :class:`DecompressionParameter` for detailed + information about supported + parameters. The *zstd_dict* argument is a :class:`ZstdDict` instance to be + used during decompression. When reading, if the *level* + argument is not None, a :exc:`!TypeError` will be raised. + + When writing, the *options* argument can be a dictionary + providing advanced compression parameters; see + :class:`CompressionParameter` for detailed information about supported + parameters. The *level* argument is the compression level to use when + writing compressed data. Only one of *level* or *options* may be non-None. + The *zstd_dict* argument is a :class:`ZstdDict` instance to be used during + compression. + + In binary mode, this function is equivalent to the :class:`ZstdFile` + constructor: ``ZstdFile(file, mode, ...)``. In this case, the + *encoding*, *errors*, and *newline* parameters must not be provided. + + In text mode, a :class:`ZstdFile` object is created, and wrapped in an + :class:`io.TextIOWrapper` instance with the specified encoding, error + handling behavior, and line endings. + + +.. class:: ZstdFile(file, /, mode='rb', *, level=None, options=None, \ + zstd_dict=None) + + Open a Zstandard-compressed file in binary mode. + + A :class:`ZstdFile` can wrap an already-open :term:`file object`, or operate + directly on a named file. The *file* argument specifies either the file + object to wrap, or the name of the file to open (as a :class:`str`, + :class:`bytes` or :term:`path-like ` object). If + wrapping an existing file object, the wrapped file will not be closed when + the :class:`ZstdFile` is closed. + + The *mode* argument can be either ``'rb'`` for reading (default), ``'wb'`` + for overwriting, ``'xb'`` for exclusive creation, or ``'ab'`` for appending. + These can equivalently be given as ``'r'``, ``'w'``, ``'x'`` and ``'a'`` + respectively. + + If *file* is a file object (rather than an actual file name), a mode of + ``'w'`` does not truncate the file, and is instead equivalent to ``'a'``. + + When reading, the *options* argument can be a dictionary + providing advanced decompression parameters; see + :class:`DecompressionParameter` for detailed information about supported + parameters. The *zstd_dict* argument is a :class:`ZstdDict` instance to be + used during decompression. When reading, if the *level* + argument is not None, a :exc:`!TypeError` will be raised. + + When writing, the *options* argument can be a dictionary + providing advanced compression parameters; see + :class:`CompressionParameter` for detailed information about supported + parameters. The *level* argument is the compression level to use when + writing compressed data. Only one of *level* or *options* may be passed. The + *zstd_dict* argument is a :class:`ZstdDict` instance to be used during + compression. + + :class:`!ZstdFile` supports all the members specified by + :class:`io.BufferedIOBase`, except for :meth:`~io.BufferedIOBase.detach` + and :meth:`~io.IOBase.truncate`. + Iteration and the :keyword:`with` statement are supported. + + The following method and attributes are also provided: + + .. method:: peek(size=-1) + + Return buffered data without advancing the file position. At least one + byte of data will be returned, unless EOF has been reached. The exact + number of bytes returned is unspecified (the *size* argument is ignored). + + .. note:: While calling :meth:`peek` does not change the file position of + the :class:`ZstdFile`, it may change the position of the underlying + file object (for example, if the :class:`ZstdFile` was constructed by + passing a file object for *file*). + + .. attribute:: mode + + ``'rb'`` for reading and ``'wb'`` for writing. + + .. attribute:: name + + The name of the Zstandard file. Equivalent to the :attr:`~io.FileIO.name` + attribute of the underlying :term:`file object`. + + +Compressing and decompressing data in memory +-------------------------------------------- + +.. function:: compress(data, level=None, options=None, zstd_dict=None) + + Compress *data* (a :term:`bytes-like object`), returning the compressed + data as a :class:`bytes` object. + + The *level* argument is an integer controlling the level of + compression. *level* is an alternative to setting + :attr:`CompressionParameter.compression_level` in *options*. Use + :meth:`~CompressionParameter.bounds` on + :attr:`~CompressionParameter.compression_level` to get the values that can + be passed for *level*. If advanced compression options are needed, the + *level* argument must be omitted and in the *options* dictionary the + :attr:`!CompressionParameter.compression_level` parameter should be set. + + The *options* argument is a Python dictionary containing advanced + compression parameters. The valid keys and values for compression parameters + are documented as part of the :class:`CompressionParameter` documentation. + + The *zstd_dict* argument is an instance of :class:`ZstdDict` + containing trained data to improve compression efficiency. The + function :func:`train_dict` can be used to generate a Zstandard dictionary. + + +.. function:: decompress(data, zstd_dict=None, options=None) + + Decompress *data* (a :term:`bytes-like object`), returning the uncompressed + data as a :class:`bytes` object. + + The *options* argument is a Python dictionary containing advanced + decompression parameters. The valid keys and values for compression + parameters are documented as part of the :class:`DecompressionParameter` + documentation. + + The *zstd_dict* argument is an instance of :class:`ZstdDict` + containing trained data used during compression. This must be + the same Zstandard dictionary used during compression. + + If *data* is the concatenation of multiple distinct compressed frames, + decompress all of these frames, and return the concatenation of the results. + + +.. class:: ZstdCompressor(level=None, options=None, zstd_dict=None) + + Create a compressor object, which can be used to compress data + incrementally. + + For a more convenient way of compressing a single chunk of data, see the + module-level function :func:`compress`. + + The *level* argument is an integer controlling the level of + compression. *level* is an alternative to setting + :attr:`CompressionParameter.compression_level` in *options*. Use + :meth:`~CompressionParameter.bounds` on + :attr:`~CompressionParameter.compression_level` to get the values that can + be passed for *level*. If advanced compression options are needed, the + *level* argument must be omitted and in the *options* dictionary the + :attr:`!CompressionParameter.compression_level` parameter should be set. + + The *options* argument is a Python dictionary containing advanced + compression parameters. The valid keys and values for compression parameters + are documented as part of the :class:`CompressionParameter` documentation. + + The *zstd_dict* argument is an optional instance of :class:`ZstdDict` + containing trained data to improve compression efficiency. The + function :func:`train_dict` can be used to generate a Zstandard dictionary. + + + .. method:: compress(data, mode=ZstdCompressor.CONTINUE) + + Compress *data* (a :term:`bytes-like object`), returning a :class:`bytes` + object with compressed data if possible, or otherwise an empty + :class:`!bytes` object. Some of *data* may be buffered internally, for + use in later calls to :meth:`!compress` and :meth:`~.flush`. The returned + data should be concatenated with the output of any previous calls to + :meth:`~.compress`. + + The *mode* argument is a :class:`ZstdCompressor` attribute, either + :attr:`~.CONTINUE`, :attr:`~.FLUSH_BLOCK`, + or :attr:`~.FLUSH_FRAME`. + + When all data has been provided to the compressor, call the + :meth:`~.flush` method to finish the compression process. If + :meth:`~.compress` is called with *mode* set to :attr:`~.FLUSH_FRAME`, + :meth:`~.flush` should not be called, as it would write out a new empty + frame. + + .. method:: flush(mode=ZstdCompressor.FLUSH_FRAME) + + Finish the compression process, returning a :class:`bytes` object + containing any data stored in the compressor's internal buffers. + + The *mode* argument is a :class:`ZstdCompressor` attribute, either + :attr:`~.FLUSH_BLOCK`, or :attr:`~.FLUSH_FRAME`. + + .. method:: set_pledged_input_size(size) + + Specify the amount of uncompressed data *size* that will be provided for + the next frame. *size* will be written into the frame header of the next + frame unless :attr:`CompressionParameter.content_size_flag` is ``False`` + or ``0``. A size of ``0`` means that the frame is empty. If *size* is + ``None``, the frame header will omit the frame size. Frames that include + the uncompressed data size require less memory to decompress, especially + at higher compression levels. + + If :attr:`last_mode` is not :attr:`FLUSH_FRAME`, a + :exc:`ValueError` is raised as the compressor is not at the start of + a frame. If the pledged size does not match the actual size of data + provided to :meth:`.compress`, future calls to :meth:`!compress` or + :meth:`flush` may raise :exc:`ZstdError` and the last chunk of data may + be lost. + + After :meth:`flush` or :meth:`.compress` are called with mode + :attr:`FLUSH_FRAME`, the next frame will not include the frame size into + the header unless :meth:`!set_pledged_input_size` is called again. + + .. attribute:: CONTINUE + + Collect more data for compression, which may or may not generate output + immediately. This mode optimizes the compression ratio by maximizing the + amount of data per block and frame. + + .. attribute:: FLUSH_BLOCK + + Complete and write a block to the data stream. The data returned so far + can be immediately decompressed. Past data can still be referenced in + future blocks generated by calls to :meth:`~.compress`, + improving compression. + + .. attribute:: FLUSH_FRAME + + Complete and write out a frame. Future data provided to + :meth:`~.compress` will be written into a new frame and + *cannot* reference past data. + + .. attribute:: last_mode + + The last mode passed to either :meth:`~.compress` or :meth:`~.flush`. + The value can be one of :attr:`~.CONTINUE`, :attr:`~.FLUSH_BLOCK`, or + :attr:`~.FLUSH_FRAME`. The initial value is :attr:`~.FLUSH_FRAME`, + signifying that the compressor is at the start of a new frame. + + +.. class:: ZstdDecompressor(zstd_dict=None, options=None) + + Create a decompressor object, which can be used to decompress data + incrementally. + + For a more convenient way of decompressing an entire compressed stream at + once, see the module-level function :func:`decompress`. + + The *options* argument is a Python dictionary containing advanced + decompression parameters. The valid keys and values for compression + parameters are documented as part of the :class:`DecompressionParameter` + documentation. + + The *zstd_dict* argument is an instance of :class:`ZstdDict` + containing trained data used during compression. This must be + the same Zstandard dictionary used during compression. + + .. note:: + This class does not transparently handle inputs containing multiple + compressed frames, unlike the :func:`decompress` function and + :class:`ZstdFile` class. To decompress a multi-frame input, you should + use :func:`decompress`, :class:`ZstdFile` if working with a + :term:`file object`, or multiple :class:`!ZstdDecompressor` instances. + + .. method:: decompress(data, max_length=-1) + + Decompress *data* (a :term:`bytes-like object`), returning + uncompressed data as bytes. Some of *data* may be buffered + internally, for use in later calls to :meth:`!decompress`. + The returned data should be concatenated with the output of any previous + calls to :meth:`!decompress`. + + If *max_length* is non-negative, the method returns at most *max_length* + bytes of decompressed data. If this limit is reached and further + output can be produced, the :attr:`~.needs_input` attribute will + be set to ``False``. In this case, the next call to + :meth:`~.decompress` may provide *data* as ``b''`` to obtain + more of the output. + + If all of the input data was decompressed and returned (either + because this was less than *max_length* bytes, or because + *max_length* was negative), the :attr:`~.needs_input` attribute + will be set to ``True``. + + Attempting to decompress data after the end of a frame will raise a + :exc:`EOFError`. Any data found after the end of the frame is ignored + and saved in the :attr:`~.unused_data` attribute. + + .. attribute:: eof + + ``True`` if the end-of-stream marker has been reached. + + .. attribute:: unused_data + + Data found after the end of the compressed stream. + + Before the end of the stream is reached, this will be ``b''``. + + .. attribute:: needs_input + + ``False`` if the :meth:`.decompress` method can provide more + decompressed data before requiring new compressed input. + + +Zstandard dictionaries +---------------------- + + +.. function:: train_dict(samples, dict_size) + + Train a Zstandard dictionary, returning a :class:`ZstdDict` instance. + Zstandard dictionaries enable more efficient compression of smaller sizes + of data, which is traditionally difficult to compress due to less + repetition. If you are compressing multiple similar groups of data (such as + similar files), Zstandard dictionaries can improve compression ratios and + speed significantly. + + The *samples* argument (an iterable of :class:`bytes` objects), is the + population of samples used to train the Zstandard dictionary. + + The *dict_size* argument, an integer, is the maximum size (in bytes) the + Zstandard dictionary should be. The Zstandard documentation suggests an + absolute maximum of no more than 100 KB, but the maximum can often be smaller + depending on the data. Larger dictionaries generally slow down compression, + but improve compression ratios. Smaller dictionaries lead to faster + compression, but reduce the compression ratio. + + +.. function:: finalize_dict(zstd_dict, /, samples, dict_size, level) + + An advanced function for converting a "raw content" Zstandard dictionary into + a regular Zstandard dictionary. "Raw content" dictionaries are a sequence of + bytes that do not need to follow the structure of a normal Zstandard + dictionary. + + The *zstd_dict* argument is a :class:`ZstdDict` instance with + the :attr:`~ZstdDict.dict_content` containing the raw dictionary contents. + + The *samples* argument (an iterable of :class:`bytes` objects), contains + sample data for generating the Zstandard dictionary. + + The *dict_size* argument, an integer, is the maximum size (in bytes) the + Zstandard dictionary should be. See :func:`train_dict` for + suggestions on the maximum dictionary size. + + The *level* argument (an integer) is the compression level expected to be + passed to the compressors using this dictionary. The dictionary information + varies for each compression level, so tuning for the proper compression + level can make compression more efficient. + + +.. class:: ZstdDict(dict_content, /, *, is_raw=False) + + A wrapper around Zstandard dictionaries. Dictionaries can be used to improve + the compression of many small chunks of data. Use :func:`train_dict` if you + need to train a new dictionary from sample data. + + The *dict_content* argument (a :term:`bytes-like object`), is the already + trained dictionary information. + + The *is_raw* argument, a boolean, is an advanced parameter controlling the + meaning of *dict_content*. ``True`` means *dict_content* is a "raw content" + dictionary, without any format restrictions. ``False`` means *dict_content* + is an ordinary Zstandard dictionary, created from Zstandard functions, + for example, :func:`train_dict` or the external :program:`zstd` CLI. + + When passing a :class:`!ZstdDict` to a function, the + :attr:`!as_digested_dict` and :attr:`!as_undigested_dict` attributes can + control how the dictionary is loaded by passing them as the ``zstd_dict`` + argument, for example, ``compress(data, zstd_dict=zd.as_digested_dict)``. + Digesting a dictionary is a costly operation that occurs when loading a + Zstandard dictionary. When making multiple calls to compression or + decompression, passing a digested dictionary will reduce the overhead of + loading the dictionary. + + .. list-table:: Difference for compression + :widths: 10 14 10 + :header-rows: 1 + + * - + - Digested dictionary + - Undigested dictionary + * - Advanced parameters of the compressor which may be overridden by + the dictionary's parameters + - ``window_log``, ``hash_log``, ``chain_log``, ``search_log``, + ``min_match``, ``target_length``, ``strategy``, + ``enable_long_distance_matching``, ``ldm_hash_log``, + ``ldm_min_match``, ``ldm_bucket_size_log``, ``ldm_hash_rate_log``, + and some non-public parameters. + - None + * - :class:`!ZstdDict` internally caches the dictionary + - Yes. It's faster when loading a digested dictionary again with the + same compression level. + - No. If you wish to load an undigested dictionary multiple times, + consider reusing a compressor object. + + If passing a :class:`!ZstdDict` without any attribute, an undigested + dictionary is passed by default when compressing and a digested dictionary + is generated if necessary and passed by default when decompressing. + + .. attribute:: dict_content + + The content of the Zstandard dictionary, a ``bytes`` object. It's the + same as the *dict_content* argument in the ``__init__`` method. It can + be used with other programs, such as the ``zstd`` CLI program. + + .. attribute:: dict_id + + Identifier of the Zstandard dictionary, a non-negative int value. + + Non-zero means the dictionary is ordinary, created by Zstandard + functions and following the Zstandard format. + + ``0`` means a "raw content" dictionary, free of any format restriction, + used for advanced users. + + .. note:: + + The meaning of ``0`` for :attr:`!ZstdDict.dict_id` is different + from the ``dictionary_id`` attribute to the :func:`get_frame_info` + function. + + .. attribute:: as_digested_dict + + Load as a digested dictionary. + + .. attribute:: as_undigested_dict + + Load as an undigested dictionary. + + +Advanced parameter control +-------------------------- + +.. class:: CompressionParameter() + + An :class:`~enum.IntEnum` containing the advanced compression parameter + keys that can be used when compressing data. + + The :meth:`~.bounds` method can be used on any attribute to get the valid + values for that parameter. + + Parameters are optional; any omitted parameter will have its value selected + automatically. + + Example getting the lower and upper bound of :attr:`~.compression_level`:: + + lower, upper = CompressionParameter.compression_level.bounds() + + Example setting the :attr:`~.window_log` to the maximum size:: + + _lower, upper = CompressionParameter.window_log.bounds() + options = {CompressionParameter.window_log: upper} + compress(b'venezuelan beaver cheese', options=options) + + .. method:: bounds() + + Return the tuple of int bounds, ``(lower, upper)``, of a compression + parameter. This method should be called on the attribute you wish to + retrieve the bounds of. For example, to get the valid values for + :attr:`~.compression_level`, one may check the result of + ``CompressionParameter.compression_level.bounds()``. + + Both the lower and upper bounds are inclusive. + + .. attribute:: compression_level + + A high-level means of setting other compression parameters that affect + the speed and ratio of compressing data. + + Regular compression levels are greater than ``0``. Values greater than + ``20`` are considered "ultra" compression and require more memory than + other levels. Negative values can be used to trade off faster compression + for worse compression ratios. + + Setting the level to zero uses :attr:`COMPRESSION_LEVEL_DEFAULT`. + + .. attribute:: window_log + + Maximum allowed back-reference distance the compressor can use when + compressing data, expressed as power of two, ``1 << window_log`` bytes. + This parameter greatly influences the memory usage of compression. Higher + values require more memory but gain better compression values. + + A value of zero causes the value to be selected automatically. + + .. attribute:: hash_log + + Size of the initial probe table, as a power of two. The resulting memory + usage is ``1 << (hash_log+2)`` bytes. Larger tables improve compression + ratio of strategies <= :attr:`~Strategy.dfast`, and improve compression + speed of strategies > :attr:`~Strategy.dfast`. + + A value of zero causes the value to be selected automatically. + + .. attribute:: chain_log + + Size of the multi-probe search table, as a power of two. The resulting + memory usage is ``1 << (chain_log+2)`` bytes. Larger tables result in + better and slower compression. This parameter has no effect for the + :attr:`~Strategy.fast` strategy. It's still useful when using + :attr:`~Strategy.dfast` strategy, in which case it defines a secondary + probe table. + + A value of zero causes the value to be selected automatically. + + .. attribute:: search_log + + Number of search attempts, as a power of two. More attempts result in + better and slower compression. This parameter is useless for + :attr:`~Strategy.fast` and :attr:`~Strategy.dfast` strategies. + + A value of zero causes the value to be selected automatically. + + .. attribute:: min_match + + Minimum size of searched matches. Larger values increase compression and + decompression speed, but decrease ratio. Note that Zstandard can still + find matches of smaller size, it just tweaks its search algorithm to look + for this size and larger. For all strategies < :attr:`~Strategy.btopt`, + the effective minimum is ``4``; for all strategies + > :attr:`~Strategy.fast`, the effective maximum is ``6``. + + A value of zero causes the value to be selected automatically. + + .. attribute:: target_length + + The impact of this field depends on the selected :class:`Strategy`. + + For strategies :attr:`~Strategy.btopt`, :attr:`~Strategy.btultra` and + :attr:`~Strategy.btultra2`, the value is the length of a match + considered "good enough" to stop searching. Larger values make + compression ratios better, but compresses slower. + + For strategy :attr:`~Strategy.fast`, it is the distance between match + sampling. Larger values make compression faster, but with a worse + compression ratio. + + A value of zero causes the value to be selected automatically. + + .. attribute:: strategy + + The higher the value of selected strategy, the more complex the + compression technique used by zstd, resulting in higher compression + ratios but slower compression. + + .. seealso:: :class:`Strategy` + + .. attribute:: enable_long_distance_matching + + Long distance matching can be used to improve compression for large + inputs by finding large matches at greater distances. It increases memory + usage and window size. + + ``True`` or ``1`` enable long distance matching while ``False`` or ``0`` + disable it. + + Enabling this parameter increases default + :attr:`~CompressionParameter.window_log` to 128 MiB except when expressly + set to a different value. This setting is enabled by default if + :attr:`!window_log` >= 128 MiB and the compression + strategy >= :attr:`~Strategy.btopt` (compression level 16+). + + .. attribute:: ldm_hash_log + + Size of the table for long distance matching, as a power of two. Larger + values increase memory usage and compression ratio, but decrease + compression speed. + + A value of zero causes the value to be selected automatically. + + .. attribute:: ldm_min_match + + Minimum match size for long distance matcher. Larger or too small values + can often decrease the compression ratio. + + A value of zero causes the value to be selected automatically. + + .. attribute:: ldm_bucket_size_log + + Log size of each bucket in the long distance matcher hash table for + collision resolution. Larger values improve collision resolution but + decrease compression speed. + + A value of zero causes the value to be selected automatically. + + .. attribute:: ldm_hash_rate_log + + Frequency of inserting/looking up entries into the long distance matcher + hash table. Larger values improve compression speed. Deviating far from + the default value will likely result in a compression ratio decrease. + + A value of zero causes the value to be selected automatically. + + .. attribute:: content_size_flag + + Write the size of the data to be compressed into the Zstandard frame + header when known prior to compressing. + + This flag only takes effect under the following scenarios: + + * Calling :func:`compress` for one-shot compression + * Providing all of the data to be compressed in the frame in a single + :meth:`ZstdCompressor.compress` call, with the + :attr:`ZstdCompressor.FLUSH_FRAME` mode. + * Calling :meth:`ZstdCompressor.set_pledged_input_size` with the exact + amount of data that will be provided to the compressor prior to any + calls to :meth:`ZstdCompressor.compress` for the current frame. + :meth:`!ZstdCompressor.set_pledged_input_size` must be called for each + new frame. + + All other compression calls may not write the size information into the + frame header. + + ``True`` or ``1`` enable the content size flag while ``False`` or ``0`` + disable it. + + .. attribute:: checksum_flag + + A four-byte checksum using XXHash64 of the uncompressed content is + written at the end of each frame. Zstandard's decompression code verifies + the checksum. If there is a mismatch a :class:`ZstdError` exception is + raised. + + ``True`` or ``1`` enable checksum generation while ``False`` or ``0`` + disable it. + + .. attribute:: dict_id_flag + + When compressing with a :class:`ZstdDict`, the dictionary's ID is written + into the frame header. + + ``True`` or ``1`` enable storing the dictionary ID while ``False`` or + ``0`` disable it. + + .. attribute:: nb_workers + + Select how many threads will be spawned to compress in parallel. When + :attr:`!nb_workers` > 0, enables multi-threaded compression, a value of + ``1`` means "one-thread multi-threaded mode". More workers improve speed, + but also increase memory usage and slightly reduce compression ratio. + + A value of zero disables multi-threading. + + .. attribute:: job_size + + Size of a compression job, in bytes. This value is enforced only when + :attr:`~CompressionParameter.nb_workers` >= 1. Each compression job is + completed in parallel, so this value can indirectly impact the number of + active threads. + + A value of zero causes the value to be selected automatically. + + .. attribute:: overlap_log + + Sets how much data is reloaded from previous jobs (threads) for new jobs + to be used by the look behind window during compression. This value is + only used when :attr:`~CompressionParameter.nb_workers` >= 1. Acceptable + values vary from 0 to 9. + + * 0 means dynamically set the overlap amount + * 1 means no overlap + * 9 means use a full window size from the previous job + + Each increment halves/doubles the overlap size. "8" means an overlap of + ``window_size/2``, "7" means an overlap of ``window_size/4``, etc. + +.. class:: DecompressionParameter() + + An :class:`~enum.IntEnum` containing the advanced decompression parameter + keys that can be used when decompressing data. Parameters are optional; any + omitted parameter will have its value selected automatically. + + The :meth:`~.bounds` method can be used on any attribute to get the valid + values for that parameter. + + Example setting the :attr:`~.window_log_max` to the maximum size:: + + data = compress(b'Some very long buffer of bytes...') + + _lower, upper = DecompressionParameter.window_log_max.bounds() + + options = {DecompressionParameter.window_log_max: upper} + decompress(data, options=options) + + .. method:: bounds() + + Return the tuple of int bounds, ``(lower, upper)``, of a decompression + parameter. This method should be called on the attribute you wish to + retrieve the bounds of. + + Both the lower and upper bounds are inclusive. + + .. attribute:: window_log_max + + The base-two logarithm of the maximum size of the window used during + decompression. This can be useful to limit the amount of memory used when + decompressing data. A larger maximum window size leads to faster + decompression. + + A value of zero causes the value to be selected automatically. + + +.. class:: Strategy() + + An :class:`~enum.IntEnum` containing strategies for compression. + Higher-numbered strategies correspond to more complex and slower + compression. + + .. note:: + + The values of attributes of :class:`!Strategy` are not necessarily stable + across zstd versions. Only the ordering of the attributes may be relied + upon. The attributes are listed below in order. + + The following strategies are available: + + .. attribute:: fast + + .. attribute:: dfast + + .. attribute:: greedy + + .. attribute:: lazy + + .. attribute:: lazy2 + + .. attribute:: btlazy2 + + .. attribute:: btopt + + .. attribute:: btultra + + .. attribute:: btultra2 + + +Miscellaneous +------------- + +.. function:: get_frame_info(frame_buffer) + + Retrieve a :class:`FrameInfo` object containing metadata about a Zstandard + frame. Frames contain metadata related to the compressed data they hold. + + +.. class:: FrameInfo + + Metadata related to a Zstandard frame. + + .. attribute:: decompressed_size + + The size of the decompressed contents of the frame. + + .. attribute:: dictionary_id + + An integer representing the Zstandard dictionary ID needed for + decompressing the frame. ``0`` means the dictionary ID was not + recorded in the frame header. This may mean that a Zstandard dictionary + is not needed, or that the ID of a required dictionary was not recorded. + + +.. attribute:: COMPRESSION_LEVEL_DEFAULT + + The default compression level for Zstandard: ``3``. + + +.. attribute:: zstd_version_info + + Version number of the runtime zstd library as a tuple of integers + (major, minor, release). + + +Examples +-------- + +Reading in a compressed file: + +.. code-block:: python + + from compression import zstd + + with zstd.open("file.zst") as f: + file_content = f.read() + +Creating a compressed file: + +.. code-block:: python + + from compression import zstd + + data = b"Insert Data Here" + with zstd.open("file.zst", "w") as f: + f.write(data) + +Compressing data in memory: + +.. code-block:: python + + from compression import zstd + + data_in = b"Insert Data Here" + data_out = zstd.compress(data_in) + +Incremental compression: + +.. code-block:: python + + from compression import zstd + + comp = zstd.ZstdCompressor() + out1 = comp.compress(b"Some data\n") + out2 = comp.compress(b"Another piece of data\n") + out3 = comp.compress(b"Even more data\n") + out4 = comp.flush() + # Concatenate all the partial results: + result = b"".join([out1, out2, out3, out4]) + +Writing compressed data to an already-open file: + +.. code-block:: python + + from compression import zstd + + with open("myfile", "wb") as f: + f.write(b"This data will not be compressed\n") + with zstd.open(f, "w") as zstf: + zstf.write(b"This *will* be compressed\n") + f.write(b"Not compressed\n") + +Creating a compressed file using compression parameters: + +.. code-block:: python + + from compression import zstd + + options = { + zstd.CompressionParameter.checksum_flag: 1 + } + with zstd.open("file.zst", "w", options=options) as f: + f.write(b"Mind if I squeeze in?") diff --git a/Doc/library/concurrency.rst b/Doc/library/concurrency.rst index 5be1a1106b09a0..18f9443cbfea20 100644 --- a/Doc/library/concurrency.rst +++ b/Doc/library/concurrency.rst @@ -18,6 +18,7 @@ multitasking). Here's an overview: multiprocessing.shared_memory.rst concurrent.rst concurrent.futures.rst + concurrent.interpreters.rst subprocess.rst sched.rst queue.rst diff --git a/Doc/library/concurrent.futures.rst b/Doc/library/concurrent.futures.rst index 7efae9e628b828..6f0c039d34b612 100644 --- a/Doc/library/concurrent.futures.rst +++ b/Doc/library/concurrent.futures.rst @@ -6,12 +6,13 @@ .. versionadded:: 3.2 -**Source code:** :source:`Lib/concurrent/futures/thread.py` -and :source:`Lib/concurrent/futures/process.py` +**Source code:** :source:`Lib/concurrent/futures/thread.py`, +:source:`Lib/concurrent/futures/process.py`, +and :source:`Lib/concurrent/futures/interpreter.py` -------------- -The :mod:`concurrent.futures` module provides a high-level interface for +The :mod:`!concurrent.futures` module provides a high-level interface for asynchronously executing callables. The asynchronous execution can be performed with threads, using @@ -20,6 +21,11 @@ or separate processes, using :class:`ProcessPoolExecutor`. Each implements the same interface, which is defined by the abstract :class:`Executor` class. +:class:`concurrent.futures.Future` must not be confused with +:class:`asyncio.Future`, which is designed for use with :mod:`asyncio` +tasks and coroutines. See the :doc:`asyncio's Future ` +documentation for a detailed comparison of the two. + .. include:: ../includes/wasm-notavail.rst Executor Objects @@ -100,10 +106,10 @@ Executor Objects executor has started running will be completed prior to this method returning. The remaining futures are cancelled. - You can avoid having to call this method explicitly if you use the - :keyword:`with` statement, which will shutdown the :class:`Executor` - (waiting as if :meth:`Executor.shutdown` were called with *wait* set to - ``True``):: + You can avoid having to call this method explicitly if you use the executor + as a :term:`context manager` via the :keyword:`with` statement, which + will shutdown the :class:`Executor` (waiting as if :meth:`Executor.shutdown` + were called with *wait* set to ``True``):: import shutil with ThreadPoolExecutor(max_workers=4) as e: @@ -150,7 +156,9 @@ And:: print(f.result()) executor = ThreadPoolExecutor(max_workers=1) - executor.submit(wait_on_future) + future = executor.submit(wait_on_future) + # Note: calling future.result() would also cause a deadlock because + # the single worker thread is already waiting for wait_on_future(). .. class:: ThreadPoolExecutor(max_workers=None, thread_name_prefix='', initializer=None, initargs=()) @@ -238,6 +246,8 @@ ThreadPoolExecutor Example InterpreterPoolExecutor ----------------------- +.. versionadded:: 3.14 + The :class:`InterpreterPoolExecutor` class uses a pool of interpreters to execute calls asynchronously. It is a :class:`ThreadPoolExecutor` subclass, which means each worker is running in its own thread. @@ -264,7 +274,7 @@ Each worker's interpreter is isolated from all the other interpreters. "Isolated" means each interpreter has its own runtime state and operates completely independently. For example, if you redirect :data:`sys.stdout` in one interpreter, it will not be automatically -redirected any other interpreter. If you import a module in one +redirected to any other interpreter. If you import a module in one interpreter, it is not automatically imported in any other. You would need to import the module separately in interpreter where you need it. In fact, each module imported in an interpreter is @@ -286,7 +296,7 @@ efficient alternative is to serialize with :mod:`pickle` and then send the bytes over a shared :mod:`socket ` or :func:`pipe `. -.. class:: InterpreterPoolExecutor(max_workers=None, thread_name_prefix='', initializer=None, initargs=(), shared=None) +.. class:: InterpreterPoolExecutor(max_workers=None, thread_name_prefix='', initializer=None, initargs=()) A :class:`ThreadPoolExecutor` subclass that executes calls asynchronously using a pool of at most *max_workers* threads. Each thread runs @@ -303,20 +313,9 @@ the bytes over a shared :mod:`socket ` or and *initargs* using :mod:`pickle` when sending them to the worker's interpreter. - .. note:: - Functions defined in the ``__main__`` module cannot be pickled - and thus cannot be used. - .. note:: The executor may replace uncaught exceptions from *initializer* - with :class:`~concurrent.futures.interpreter.ExecutionFailed`. - - The optional *shared* argument is a :class:`dict` of objects that all - interpreters in the pool share. The *shared* items are added to each - interpreter's ``__main__`` module. Not all objects are shareable. - Shareable objects include the builtin singletons, :class:`str` - and :class:`bytes`, and :class:`memoryview`. See :pep:`734` - for more info. + with :class:`~concurrent.interpreters.ExecutionFailed`. Other caveats from parent :class:`ThreadPoolExecutor` apply here. @@ -325,18 +324,14 @@ except the worker serializes the callable and arguments using :mod:`pickle` when sending them to its interpreter. The worker likewise serializes the return value when sending it back. -.. note:: - Functions defined in the ``__main__`` module cannot be pickled - and thus cannot be used. - When a worker's current task raises an uncaught exception, the worker always tries to preserve the exception as-is. If that is successful then it also sets the ``__cause__`` to a corresponding -:class:`~concurrent.futures.interpreter.ExecutionFailed` +:class:`~concurrent.interpreters.ExecutionFailed` instance, which contains a summary of the original exception. In the uncommon case that the worker is not able to preserve the original as-is then it directly preserves the corresponding -:class:`~concurrent.futures.interpreter.ExecutionFailed` +:class:`~concurrent.interpreters.ExecutionFailed` instance instead. @@ -356,6 +351,11 @@ that :class:`ProcessPoolExecutor` will not work in the interactive interpreter. Calling :class:`Executor` or :class:`Future` methods from a callable submitted to a :class:`ProcessPoolExecutor` will result in deadlock. +Note that the restrictions on functions and arguments needing to picklable as +per :class:`multiprocessing.Process` apply when using :meth:`~Executor.submit` +and :meth:`~Executor.map` on a :class:`ProcessPoolExecutor`. A function defined +in a REPL or a lambda should not be expected to work. + .. class:: ProcessPoolExecutor(max_workers=None, mp_context=None, initializer=None, initargs=(), max_tasks_per_child=None) An :class:`Executor` subclass that executes calls asynchronously using a pool @@ -421,6 +421,11 @@ to a :class:`ProcessPoolExecutor` will result in deadlock. require the *fork* start method for :class:`ProcessPoolExecutor` you must explicitly pass ``mp_context=multiprocessing.get_context("fork")``. + .. versionchanged:: 3.14.7 + Fixed a deadlock (:gh:`115634`) where the executor could hang after + a worker process exited upon reaching its *max_tasks_per_child* + limit while tasks remained queued. + .. method:: terminate_workers() Attempt to terminate all living worker processes immediately by calling @@ -722,15 +727,6 @@ Exception classes .. versionadded:: 3.14 -.. exception:: ExecutionFailed - - Raised from :class:`~concurrent.futures.InterpreterPoolExecutor` when - the given initializer fails or from - :meth:`~concurrent.futures.Executor.submit` when there's an uncaught - exception from the submitted task. - - .. versionadded:: 3.14 - .. currentmodule:: concurrent.futures.process .. exception:: BrokenProcessPool diff --git a/Doc/library/concurrent.interpreters.rst b/Doc/library/concurrent.interpreters.rst new file mode 100644 index 00000000000000..ee3f0f04a06556 --- /dev/null +++ b/Doc/library/concurrent.interpreters.rst @@ -0,0 +1,387 @@ +:mod:`!concurrent.interpreters` --- Multiple interpreters in the same process +============================================================================= + +.. module:: concurrent.interpreters + :synopsis: Multiple interpreters in the same process + +.. moduleauthor:: Eric Snow +.. sectionauthor:: Eric Snow + +.. versionadded:: 3.14 + +**Source code:** :source:`Lib/concurrent/interpreters` + +-------------- + +The :mod:`!concurrent.interpreters` module constructs higher-level +interfaces on top of the lower level :mod:`!_interpreters` module. + +The module is primarily meant to provide a basic API for managing +interpreters (AKA "subinterpreters") and running things in them. +Running mostly involves switching to an interpreter (in the current +thread) and calling a function in that execution context. + +For concurrency, interpreters themselves (and this module) don't +provide much more than isolation, which on its own isn't useful. +Actual concurrency is available separately through +:mod:`threads ` -- see `below `_. + +.. seealso:: + + :class:`~concurrent.futures.InterpreterPoolExecutor` + Combines threads with interpreters in a familiar interface. + + .. XXX Add references to the upcoming HOWTO docs in the seealso block. + + :ref:`isolating-extensions-howto` + How to update an extension module to support multiple interpreters. + + :pep:`554` + + :pep:`734` + + :pep:`684` + +.. XXX Why do we disallow multiple interpreters on WASM? + +.. include:: ../includes/wasm-notavail.rst + + +Key details +----------- + +Before we dive in further, there are a small number of details +to keep in mind about using multiple interpreters: + +* `isolated `_, by default +* no implicit threads +* not all PyPI packages support use in multiple interpreters yet + +.. XXX Are there other relevant details to list? + + +.. _interpreters-intro: + +Introduction +------------ + +An "interpreter" is effectively the execution context of the Python +runtime. It contains all of the state the runtime needs to execute +a program. This includes things like the import state and builtins. +(Each thread, even if there's only the main thread, has some extra +runtime state, in addition to the current interpreter, related to +the current exception and the bytecode eval loop.) + +The concept and functionality of the interpreter have been a part of +Python since version 2.2, but the feature was only available through +the C-API and not well known, and the `isolation `_ +was relatively incomplete until version 3.12. + +.. _interp-isolation: + +Multiple Interpreters and Isolation +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +A Python implementation may support using multiple interpreters in the +same process. CPython has this support. Each interpreter is +effectively isolated from the others (with a limited number of +carefully managed process-global exceptions to the rule). + +That isolation is primarily useful as a strong separation between +distinct logical components of a program, where you want to have +careful control of how those components interact. + +.. note:: + + Interpreters in the same process can technically never be strictly + isolated from one another since there are few restrictions on memory + access within the same process. The Python runtime makes a best + effort at isolation but extension modules may easily violate that. + Therefore, do not use multiple interpreters in security-sensitive + situations, where they shouldn't have access to each other's data. + +Running in an Interpreter +^^^^^^^^^^^^^^^^^^^^^^^^^ + +Running in a different interpreter involves switching to it in the +current thread and then calling some function. The runtime will +execute the function using the current interpreter's state. The +:mod:`!concurrent.interpreters` module provides a basic API for +creating and managing interpreters, as well as the switch-and-call +operation. + +No other threads are automatically started for the operation. +There is `a helper `_ for that though. +There is another dedicated helper for calling the builtin +:func:`exec` in an interpreter. + +When :func:`exec` (or :func:`eval`) are called in an interpreter, +they run using the interpreter's :mod:`!__main__` module as the +"globals" namespace. The same is true for functions that aren't +associated with any module. This is the same as how scripts invoked +from the command-line run in the :mod:`!__main__` module. + + +.. _interp-concurrency: + +Concurrency and Parallelism +^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +As noted earlier, interpreters do not provide any concurrency +on their own. They strictly represent the isolated execution +context the runtime will use *in the current thread*. That isolation +makes them similar to processes, but they still enjoy in-process +efficiency, like threads. + +All that said, interpreters do naturally support certain flavors of +concurrency. +There's a powerful side effect of that isolation. It enables a +different approach to concurrency than you can take with async or +threads. It's a similar concurrency model to CSP or the actor model, +a model which is relatively easy to reason about. + +You can take advantage of that concurrency model in a single thread, +switching back and forth between interpreters, Stackless-style. +However, this model is more useful when you combine interpreters +with multiple threads. This mostly involves starting a new thread, +where you switch to another interpreter and run what you want there. + +Each actual thread in Python, even if you're only running in the main +thread, has its own *current* execution context. Multiple threads can +use the same interpreter or different ones. + +At a high level, you can think of the combination of threads and +interpreters as threads with opt-in sharing. + +As a significant bonus, interpreters are sufficiently isolated that +they do not share the :term:`GIL`, which means combining threads with +multiple interpreters enables full multi-core parallelism. +(This has been the case since Python 3.12.) + +Communication Between Interpreters +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +In practice, multiple interpreters are useful only if we have a way +to communicate between them. This usually involves some form of +message passing, but can even mean sharing data in some carefully +managed way. + +With this in mind, the :mod:`!concurrent.interpreters` module provides +a :class:`queue.Queue` implementation, available through +:func:`create_queue`. + +.. _interp-object-sharing: + +"Sharing" Objects +^^^^^^^^^^^^^^^^^ + +Any data actually shared between interpreters loses the thread-safety +provided by the :term:`GIL`. There are various options for dealing with +this in extension modules. However, from Python code the lack of +thread-safety means objects can't actually be shared, with a few +exceptions. Instead, a copy must be created, which means mutable +objects won't stay in sync. + +By default, most objects are copied with :mod:`pickle` when they are +passed to another interpreter. Nearly all of the immutable builtin +objects are either directly shared or copied efficiently. For example: + +* :const:`None` +* :class:`bool` (:const:`True` and :const:`False`) +* :class:`bytes` +* :class:`str` +* :class:`int` +* :class:`float` +* :class:`tuple` (of similarly supported objects) + +There is a small number of Python types that actually share mutable +data between interpreters: + +* :class:`memoryview` +* :class:`Queue` + + +Reference +--------- + +This module defines the following functions: + +.. function:: list_all() + + Return a :class:`list` of :class:`Interpreter` objects, + one for each existing interpreter. + +.. function:: get_current() + + Return an :class:`Interpreter` object for the currently running + interpreter. + +.. function:: get_main() + + Return an :class:`Interpreter` object for the main interpreter. + This is the interpreter the runtime created to run the :term:`REPL` + or the script given at the command-line. It is usually the only one. + +.. function:: create() + + Initialize a new (idle) Python interpreter + and return a :class:`Interpreter` object for it. + +.. function:: create_queue() + + Initialize a new cross-interpreter queue and return a :class:`Queue` + object for it. + + +Interpreter objects +^^^^^^^^^^^^^^^^^^^ + +.. class:: Interpreter(id) + + A single interpreter in the current process. + + Generally, :class:`Interpreter` shouldn't be called directly. + Instead, use :func:`create` or one of the other module functions. + + .. attribute:: id + + (read-only) + + The underlying interpreter's ID. + + .. attribute:: whence + + (read-only) + + A string describing where the interpreter came from. + + .. method:: is_running() + + Return ``True`` if the interpreter is currently executing code + in its :mod:`!__main__` module and ``False`` otherwise. + + .. method:: close() + + Finalize and destroy the interpreter. + + .. method:: prepare_main(ns=None, **kwargs) + + Bind objects in the interpreter's :mod:`!__main__` module. + + Some objects are actually shared and some are copied efficiently, + but most are copied via :mod:`pickle`. See :ref:`interp-object-sharing`. + + .. method:: exec(code, /, dedent=True) + + Run the given source code in the interpreter (in the current thread). + + .. method:: call(callable, /, *args, **kwargs) + + Return the result of calling running the given function in the + interpreter (in the current thread). + + .. _interp-call-in-thread: + + .. method:: call_in_thread(callable, /, *args, **kwargs) + + Run the given function in the interpreter (in a new thread). + +Exceptions +^^^^^^^^^^ + +.. exception:: InterpreterError + + This exception, a subclass of :exc:`Exception`, is raised when + an interpreter-related error happens. + +.. exception:: InterpreterNotFoundError + + This exception, a subclass of :exc:`InterpreterError`, is raised when + the targeted interpreter no longer exists. + +.. exception:: ExecutionFailed + + This exception, a subclass of :exc:`InterpreterError`, is raised when + the running code raised an uncaught exception. + + .. attribute:: excinfo + + A basic snapshot of the exception raised in the other interpreter. + +.. XXX Document the excinfoattrs? + +.. exception:: NotShareableError + + This exception, a subclass of :exc:`TypeError`, is raised when + an object cannot be sent to another interpreter. + + +Communicating Between Interpreters +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. class:: Queue(id) + + A wrapper around a low-level, cross-interpreter queue, which + implements the :class:`queue.Queue` interface. The underlying queue + can only be created through :func:`create_queue`. + + Some objects are actually shared and some are copied efficiently, + but most are copied via :mod:`pickle`. See :ref:`interp-object-sharing`. + + .. attribute:: id + + (read-only) + + The queue's ID. + + +.. exception:: QueueEmptyError + + This exception, a subclass of :exc:`queue.Empty`, is raised from + :meth:`!Queue.get` and :meth:`!Queue.get_nowait` when the queue + is empty. + +.. exception:: QueueFullError + + This exception, a subclass of :exc:`queue.Full`, is raised from + :meth:`!Queue.put` and :meth:`!Queue.put_nowait` when the queue + is full. + + +Basic usage +----------- + +Creating an interpreter and running code in it:: + + from concurrent import interpreters + + interp = interpreters.create() + + # Run in the current OS thread. + + interp.exec('print("spam!")') + + interp.exec("""if True: + print('spam!') + """) + + from textwrap import dedent + interp.exec(dedent(""" + print('spam!') + """)) + + def run(arg): + return arg + + res = interp.call(run, 'spam!') + print(res) + + def run(): + print('spam!') + + interp.call(run) + + # Run in new OS thread. + + t = interp.call_in_thread(run) + t.join() diff --git a/Doc/library/concurrent.rst b/Doc/library/concurrent.rst index 8caea78bbb57e8..748c72c733bba2 100644 --- a/Doc/library/concurrent.rst +++ b/Doc/library/concurrent.rst @@ -1,6 +1,7 @@ The :mod:`!concurrent` package ============================== -Currently, there is only one module in this package: +This package contains the following modules: * :mod:`concurrent.futures` -- Launching parallel tasks +* :mod:`concurrent.interpreters` -- Multiple interpreters in the same process diff --git a/Doc/library/configparser.rst b/Doc/library/configparser.rst index bb109a9b742cb7..f73252a90265cf 100644 --- a/Doc/library/configparser.rst +++ b/Doc/library/configparser.rst @@ -80,7 +80,7 @@ Let's take a very basic configuration file that looks like this: The structure of INI files is described `in the following section <#supported-ini-file-structure>`_. Essentially, the file consists of sections, each of which contains keys with values. -:mod:`configparser` classes can read and write such files. Let's start by +:mod:`!configparser` classes can read and write such files. Let's start by creating the above configuration file programmatically. .. doctest:: @@ -449,7 +449,7 @@ Mapping Protocol Access .. versionadded:: 3.2 Mapping protocol access is a generic name for functionality that enables using -custom objects as if they were dictionaries. In case of :mod:`configparser`, +custom objects as if they were dictionaries. In case of :mod:`!configparser`, the mapping interface implementation is using the ``parser['section']['option']`` notation. @@ -459,7 +459,7 @@ the original parser on demand. What's even more important is that when values are changed on a section proxy, they are actually mutated in the original parser. -:mod:`configparser` objects behave as close to actual dictionaries as possible. +:mod:`!configparser` objects behave as close to actual dictionaries as possible. The mapping interface is complete and adheres to the :class:`~collections.abc.MutableMapping` ABC. However, there are a few differences that should be taken into account: @@ -507,7 +507,7 @@ Customizing Parser Behaviour ---------------------------- There are nearly as many INI format variants as there are applications using it. -:mod:`configparser` goes a long way to provide support for the largest sensible +:mod:`!configparser` goes a long way to provide support for the largest sensible set of INI styles available. The default functionality is mainly dictated by historical background and it's very likely that you will want to customize some of the features. @@ -560,7 +560,7 @@ the :meth:`!__init__` options: * *allow_no_value*, default value: ``False`` Some configuration files are known to include settings without values, but - which otherwise conform to the syntax supported by :mod:`configparser`. The + which otherwise conform to the syntax supported by :mod:`!configparser`. The *allow_no_value* parameter to the constructor can be used to indicate that such values should be accepted: @@ -615,7 +615,7 @@ the :meth:`!__init__` options: prefixes for whole line comments. .. versionchanged:: 3.2 - In previous versions of :mod:`configparser` behaviour matched + In previous versions of :mod:`!configparser` behaviour matched ``comment_prefixes=('#',';')`` and ``inline_comment_prefixes=(';',)``. Please note that config parsers don't support escaping of comment prefixes so @@ -672,7 +672,7 @@ the :meth:`!__init__` options: parsers in new applications. .. versionchanged:: 3.2 - In previous versions of :mod:`configparser` behaviour matched + In previous versions of :mod:`!configparser` behaviour matched ``strict=False``. * *empty_lines_in_values*, default value: ``True`` @@ -842,7 +842,7 @@ be overridden by subclasses or by attribute assignment. Legacy API Examples ------------------- -Mainly because of backwards compatibility concerns, :mod:`configparser` +Mainly because of backwards compatibility concerns, :mod:`!configparser` provides also a legacy API with explicit ``get``/``set`` methods. While there are valid use cases for the methods outlined below, mapping protocol access is preferred for new projects. The legacy API is at times more advanced, @@ -1378,7 +1378,7 @@ Exceptions .. exception:: Error - Base class for all other :mod:`configparser` exceptions. + Base class for all other :mod:`!configparser` exceptions. .. exception:: NoSectionError diff --git a/Doc/library/constants.rst b/Doc/library/constants.rst index c0ac4ea8412ebd..6f005f98bd3ede 100644 --- a/Doc/library/constants.rst +++ b/Doc/library/constants.rst @@ -22,7 +22,7 @@ A small number of constants live in the built-in namespace. They are: An object frequently used to represent the absence of a value, as when default arguments are not passed to a function. Assignments to ``None`` are illegal and raise a :exc:`SyntaxError`. - ``None`` is the sole instance of the :data:`~types.NoneType` type. + ``None`` is the sole instance of the :class:`~types.NoneType` type. .. data:: NotImplemented @@ -33,7 +33,7 @@ A small number of constants live in the built-in namespace. They are: the other type; may be returned by the in-place binary special methods (e.g. :meth:`~object.__imul__`, :meth:`~object.__iand__`, etc.) for the same purpose. It should not be evaluated in a boolean context. - :data:`!NotImplemented` is the sole instance of the :data:`types.NotImplementedType` type. + :data:`!NotImplemented` is the sole instance of the :class:`types.NotImplementedType` type. .. note:: @@ -65,9 +65,10 @@ A small number of constants live in the built-in namespace. They are: .. index:: single: ...; ellipsis literal .. data:: Ellipsis - The same as the ellipsis literal "``...``". Special value used mostly in conjunction - with extended slicing syntax for user-defined container data types. - ``Ellipsis`` is the sole instance of the :data:`types.EllipsisType` type. + The same as the ellipsis literal "``...``", an object frequently used to + indicate that something is omitted. Assignment to ``Ellipsis`` is possible, but + assignment to ``...`` raises a :exc:`SyntaxError`. + ``Ellipsis`` is the sole instance of the :class:`types.EllipsisType` type. .. data:: __debug__ @@ -97,15 +98,17 @@ should not be used in programs. exit(code=None) Objects that when printed, print a message like "Use quit() or Ctrl-D - (i.e. EOF) to exit", and when called, raise :exc:`SystemExit` with the + (i.e. EOF) to exit", and when accessed directly in the interactive + interpreter or called as functions, raise :exc:`SystemExit` with the specified exit code. .. data:: help :noindex: Object that when printed, prints the message "Type help() for interactive - help, or help(object) for help about object.", and when called, - acts as described :func:`elsewhere `. + help, or help(object) for help about object.", and when accessed directly + in the interactive interpreter, invokes the built-in help system + (see :func:`help`). .. data:: copyright credits diff --git a/Doc/library/contextlib.rst b/Doc/library/contextlib.rst index 176be4ff333955..9cd6358ad1363d 100644 --- a/Doc/library/contextlib.rst +++ b/Doc/library/contextlib.rst @@ -21,9 +21,9 @@ Functions and classes provided: .. class:: AbstractContextManager An :term:`abstract base class` for classes that implement - :meth:`object.__enter__` and :meth:`object.__exit__`. A default - implementation for :meth:`object.__enter__` is provided which returns - ``self`` while :meth:`object.__exit__` is an abstract method which by default + :meth:`~object.__enter__` and :meth:`~object.__exit__`. A default + implementation for :meth:`~object.__enter__` is provided which returns + ``self`` while :meth:`~object.__exit__` is an abstract method which by default returns ``None``. See also the definition of :ref:`typecontextmanager`. .. versionadded:: 3.6 @@ -32,9 +32,9 @@ Functions and classes provided: .. class:: AbstractAsyncContextManager An :term:`abstract base class` for classes that implement - :meth:`object.__aenter__` and :meth:`object.__aexit__`. A default - implementation for :meth:`object.__aenter__` is provided which returns - ``self`` while :meth:`object.__aexit__` is an abstract method which by default + :meth:`~object.__aenter__` and :meth:`~object.__aexit__`. A default + implementation for :meth:`~object.__aenter__` is provided which returns + ``self`` while :meth:`~object.__aexit__` is an abstract method which by default returns ``None``. See also the definition of :ref:`async-context-managers`. @@ -88,11 +88,11 @@ Functions and classes provided: the exception has been handled, and execution will resume with the statement immediately following the :keyword:`!with` statement. - :func:`contextmanager` uses :class:`ContextDecorator` so the context managers + :deco:`contextmanager` uses :class:`ContextDecorator` so the context managers it creates can be used as decorators as well as in :keyword:`with` statements. When used as a decorator, a new generator instance is implicitly created on each function call (this allows the otherwise "one-shot" context managers - created by :func:`contextmanager` to meet the requirement that context + created by :deco:`contextmanager` to meet the requirement that context managers support multiple invocations in order to be used as decorators). .. versionchanged:: 3.2 @@ -101,7 +101,7 @@ Functions and classes provided: .. decorator:: asynccontextmanager - Similar to :func:`~contextlib.contextmanager`, but creates an + Similar to :deco:`~contextlib.contextmanager`, but creates an :ref:`asynchronous context manager `. This function is a :term:`decorator` that can be used to define a factory @@ -128,7 +128,7 @@ Functions and classes provided: .. versionadded:: 3.7 - Context managers defined with :func:`asynccontextmanager` can be used + Context managers defined with :deco:`asynccontextmanager` can be used either as decorators or with :keyword:`async with` statements:: import time @@ -148,11 +148,11 @@ Functions and classes provided: When used as a decorator, a new generator instance is implicitly created on each function call. This allows the otherwise "one-shot" context managers - created by :func:`asynccontextmanager` to meet the requirement that context + created by :deco:`asynccontextmanager` to meet the requirement that context managers support multiple invocations in order to be used as decorators. .. versionchanged:: 3.10 - Async context managers created with :func:`asynccontextmanager` can + Async context managers created with :deco:`asynccontextmanager` can be used as decorators. @@ -228,7 +228,7 @@ Functions and classes provided: .. function:: nullcontext(enter_result=None) - Return a context manager that returns *enter_result* from ``__enter__``, but + Return a context manager that returns *enter_result* from :meth:`~object.__enter__`, but otherwise does nothing. It is intended to be used as a stand-in for an optional context manager, for example:: @@ -335,7 +335,7 @@ Functions and classes provided: For example, the output of :func:`help` normally is sent to *sys.stdout*. You can capture that output in a string by redirecting the output to an :class:`io.StringIO` object. The replacement stream is returned from the - ``__enter__`` method and so is available as the target of the + :meth:`~object.__enter__` method and so is available as the target of the :keyword:`with` statement:: with redirect_stdout(io.StringIO()) as f: @@ -396,10 +396,11 @@ Functions and classes provided: A base class that enables a context manager to also be used as a decorator. Context managers inheriting from ``ContextDecorator`` have to implement - ``__enter__`` and ``__exit__`` as normal. ``__exit__`` retains its optional + :meth:`~object.__enter__` and :meth:`~object.__exit__` as normal. + ``__exit__`` retains its optional exception handling even when used as a decorator. - ``ContextDecorator`` is used by :func:`contextmanager`, so you get this + ``ContextDecorator`` is used by :deco:`contextmanager`, so you get this functionality automatically. Example of ``ContextDecorator``:: @@ -653,7 +654,7 @@ Functions and classes provided: Similar to :meth:`ExitStack.close` but properly handles awaitables. - Continuing the example for :func:`asynccontextmanager`:: + Continuing the example for :deco:`asynccontextmanager`:: async with AsyncExitStack() as stack: connections = [await stack.enter_async_context(get_connection()) @@ -668,7 +669,7 @@ Examples and Recipes -------------------- This section describes some examples and recipes for making effective use of -the tools provided by :mod:`contextlib`. +the tools provided by :mod:`!contextlib`. Supporting a variable number of context managers @@ -697,9 +698,9 @@ context management protocol. Catching exceptions from ``__enter__`` methods ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -It is occasionally desirable to catch exceptions from an ``__enter__`` +It is occasionally desirable to catch exceptions from an :meth:`~object.__enter__` method implementation, *without* inadvertently catching exceptions from -the :keyword:`with` statement body or the context manager's ``__exit__`` +the :keyword:`with` statement body or the context manager's :meth:`~object.__exit__` method. By using :class:`ExitStack` the steps in the context management protocol can be separated slightly in order to allow this:: @@ -911,7 +912,7 @@ Files are an example of effectively single use context managers, since the first :keyword:`with` statement will close the file, preventing any further IO operations using that file object. -Context managers created using :func:`contextmanager` are also single use +Context managers created using :deco:`contextmanager` are also single use context managers, and will complain about the underlying generator failing to yield if an attempt is made to use them a second time:: diff --git a/Doc/library/contextvars.rst b/Doc/library/contextvars.rst index 57580ce026e96a..fffb9f664c0cd7 100644 --- a/Doc/library/contextvars.rst +++ b/Doc/library/contextvars.rst @@ -44,6 +44,9 @@ Context Variables references to context variables which prevents context variables from being properly garbage collected. + :class:`!ContextVar`\s are :ref:`generic ` over the type of + their contained value. + .. attribute:: ContextVar.name The name of the variable. This is a read-only property. @@ -77,6 +80,32 @@ Context Variables to restore the variable to its previous value via the :meth:`ContextVar.reset` method. + For convenience, the token object can be used as a context manager + to avoid calling :meth:`ContextVar.reset` manually:: + + var = ContextVar('var', default='default value') + + with var.set('new value'): + assert var.get() == 'new value' + + assert var.get() == 'default value' + + It is a shorthand for:: + + var = ContextVar('var', default='default value') + + token = var.set('new value') + try: + assert var.get() == 'new value' + finally: + var.reset(token) + + assert var.get() == 'default value' + + .. versionadded:: 3.14 + + Added support for using tokens as context managers. + .. method:: reset(token) Reset the context variable to the value it had before the @@ -93,24 +122,21 @@ Context Variables # After the reset call the var has no value again, so # var.get() would raise a LookupError. + The same *token* cannot be used twice. + .. class:: Token *Token* objects are returned by the :meth:`ContextVar.set` method. They can be passed to the :meth:`ContextVar.reset` method to revert the value of the variable to what it was before the corresponding - *set*. - - The token supports :ref:`context manager protocol ` - to restore the corresponding context variable value at the exit from - :keyword:`with` block:: - - var = ContextVar('var', default='default value') + *set*. A single token cannot reset a context variable more than once. - with var.set('new value'): - assert var.get() == 'new value' + Tokens support the :ref:`context manager protocol ` + to automatically reset context variables. See :meth:`ContextVar.set`. - assert var.get() == 'default value' + Tokens are :ref:`generic ` over the same type as the + :class:`ContextVar` which created them. .. versionadded:: 3.14 diff --git a/Doc/library/copy.rst b/Doc/library/copy.rst index 95b41f988a035b..39fc7800d03a91 100644 --- a/Doc/library/copy.rst +++ b/Doc/library/copy.rst @@ -72,15 +72,19 @@ file, socket, window, or any similar types. It does "copy" functions and classes (shallow and deeply), by returning the original object unchanged; this is compatible with the way these are treated by the :mod:`pickle` module. -Shallow copies of dictionaries can be made using :meth:`dict.copy`, and -of lists by assigning a slice of the entire list, for example, -``copied_list = original_list[:]``. +Shallow copies of many collections can be made using the corresponding +:meth:`!copy` method (such as :meth:`list.copy`, :meth:`dict.copy` or +:meth:`set.copy`), and of sequences (such as lists or bytearrays) by making +a slice of the entire sequence (``sequence[:]``). +However, these methods and slicing can create an instance of the base type +when copying an instance of a subclass, whereas :func:`copy.copy` normally +returns an instance of the same type. .. index:: pair: module; pickle Classes can use the same interfaces to control copying that they use to control pickling. See the description of module :mod:`pickle` for information on these -methods. In fact, the :mod:`copy` module uses the registered +methods. In fact, the :mod:`!copy` module uses the registered pickle functions from the :mod:`copyreg` module. .. index:: @@ -122,6 +126,8 @@ and only supports named tuples created by :func:`~collections.namedtuple`, This method should create a new object of the same type, replacing fields with values from *changes*. + .. versionadded:: 3.13 + .. seealso:: diff --git a/Doc/library/copyreg.rst b/Doc/library/copyreg.rst index 6e3144824ebe91..d59936029da69d 100644 --- a/Doc/library/copyreg.rst +++ b/Doc/library/copyreg.rst @@ -12,7 +12,7 @@ -------------- -The :mod:`copyreg` module offers a way to define functions used while pickling +The :mod:`!copyreg` module offers a way to define functions used while pickling specific objects. The :mod:`pickle` and :mod:`copy` modules use those functions when pickling/copying those objects. The module provides configuration information about object constructors which are not classes. diff --git a/Doc/library/crypt.rst b/Doc/library/crypt.rst index 9ff37196ccf69f..647cb4925f31da 100644 --- a/Doc/library/crypt.rst +++ b/Doc/library/crypt.rst @@ -13,7 +13,7 @@ being deprecated in Python 3.11. The removal was decided in :pep:`594`. Applications can use the :mod:`hashlib` module from the standard library. Other possible replacements are third-party libraries from PyPI: -:pypi:`legacycrypt`, :pypi:`bcrypt`, :pypi:`argon2-cffi`, or :pypi:`passlib`. +:pypi:`legacycrypt`, :pypi:`bcrypt`, or :pypi:`argon2-cffi`. These are not supported or maintained by the Python core team. The last version of Python that provided the :mod:`!crypt` module was diff --git a/Doc/library/csv.rst b/Doc/library/csv.rst index 533cdf13974be6..28d668836a14fe 100644 --- a/Doc/library/csv.rst +++ b/Doc/library/csv.rst @@ -25,14 +25,14 @@ similar enough that it is possible to write a single module which can efficiently manipulate such data, hiding the details of reading and writing the data from the programmer. -The :mod:`csv` module implements classes to read and write tabular data in CSV +The :mod:`!csv` module implements classes to read and write tabular data in CSV format. It allows programmers to say, "write this data in the format preferred by Excel," or "read data from this file which was generated by Excel," without knowing the precise details of the CSV format used by Excel. Programmers can also describe the CSV formats understood by other applications or define their own special-purpose CSV formats. -The :mod:`csv` module's :class:`reader` and :class:`writer` objects read and +The :mod:`!csv` module's :class:`reader` and :class:`writer` objects read and write sequences. Programmers can also read and write data in dictionary form using the :class:`DictReader` and :class:`DictWriter` classes. @@ -47,13 +47,13 @@ using the :class:`DictReader` and :class:`DictWriter` classes. Module Contents --------------- -The :mod:`csv` module defines the following functions: +The :mod:`!csv` module defines the following functions: .. index:: single: universal newlines; csv.reader function -.. function:: reader(csvfile, dialect='excel', **fmtparams) +.. function:: reader(csvfile, /, dialect='excel', **fmtparams) Return a :ref:`reader object ` that will process lines from the given *csvfile*. A csvfile must be an iterable of @@ -70,7 +70,7 @@ The :mod:`csv` module defines the following functions: section :ref:`csv-fmt-params`. Each row read from the csv file is returned as a list of strings. No - automatic data type conversion is performed unless the ``QUOTE_NONNUMERIC`` format + automatic data type conversion is performed unless the :data:`QUOTE_NONNUMERIC` format option is specified (in which case unquoted fields are transformed into floats). A short usage example:: @@ -83,8 +83,15 @@ The :mod:`csv` module defines the following functions: Spam, Spam, Spam, Spam, Spam, Baked Beans Spam, Lovely Spam, Wonderful Spam + where :file:`eggs.csv` contains: -.. function:: writer(csvfile, dialect='excel', **fmtparams) + .. code-block:: text + + Spam Spam Spam Spam Spam |Baked Beans| + Spam |Lovely Spam| |Wonderful Spam| + + +.. function:: writer(csvfile, /, dialect='excel', **fmtparams) Return a writer object responsible for converting the user's data into delimited strings on the given file-like object. *csvfile* can be any object with a @@ -112,8 +119,15 @@ The :mod:`csv` module defines the following functions: spamwriter.writerow(['Spam'] * 5 + ['Baked Beans']) spamwriter.writerow(['Spam', 'Lovely Spam', 'Wonderful Spam']) + which writes :file:`eggs.csv` containing: + + .. code-block:: text + + Spam Spam Spam Spam Spam |Baked Beans| + Spam |Lovely Spam| |Wonderful Spam| -.. function:: register_dialect(name[, dialect[, **fmtparams]]) + +.. function:: register_dialect(name, /, dialect='excel', **fmtparams) Associate *dialect* with *name*. *name* must be a string. The dialect can be specified either by passing a sub-class of :class:`Dialect`, or @@ -139,13 +153,14 @@ The :mod:`csv` module defines the following functions: Return the names of all registered dialects. -.. function:: field_size_limit([new_limit]) +.. function:: field_size_limit() + field_size_limit(new_limit) Returns the current maximum field size allowed by the parser. If *new_limit* is given, this becomes the new limit. -The :mod:`csv` module defines the following classes: +The :mod:`!csv` module defines the following classes: .. class:: DictReader(f, fieldnames=None, restkey=None, restval=None, \ dialect='excel', *args, **kwds) @@ -192,6 +207,14 @@ The :mod:`csv` module defines the following classes: >>> print(row) {'first_name': 'John', 'last_name': 'Cleese'} + where :file:`names.csv` contains: + + .. code-block:: text + + first_name,last_name + Eric,Idle + John,Cleese + .. class:: DictWriter(f, fieldnames, restval='', extrasaction='raise', \ dialect='excel', *args, **kwds) @@ -229,6 +252,15 @@ The :mod:`csv` module defines the following classes: writer.writerow({'first_name': 'Lovely', 'last_name': 'Spam'}) writer.writerow({'first_name': 'Wonderful', 'last_name': 'Spam'}) + which writes :file:`names.csv` containing: + + .. code-block:: text + + first_name,last_name + Baked,Beans + Lovely,Spam + Wonderful,Spam + .. class:: Dialect @@ -282,6 +314,11 @@ The :mod:`csv` module defines the following classes: is given, it is interpreted as a string containing possible valid delimiter characters. + If several delimiters fit the sample equally well --- + for example if both ``','`` and ``';'`` split every row consistently --- + the delimiters listed in the :attr:`~Sniffer.preferred` attribute + are preferred, in that order, + no matter how many times each of them occurs. .. method:: has_header(sample) @@ -294,14 +331,23 @@ The :mod:`csv` module defines the following classes: - the second through n-th rows contain strings where at least one value's length differs from that of the putative header of that column. - Twenty rows after the first row are sampled; if more than half of columns + - rows meet the criteria, :const:`True` is returned. + Twenty-one rows after the header are sampled; if more than half of the + columns + rows meet the criteria, :const:`True` is returned. .. note:: This method is a rough heuristic and may produce both false positives and negatives. + The :class:`Sniffer` class has the following attribute: + + .. attribute:: preferred + + The list of the delimiters preferred for breaking ties, + in the order of preference. + It can be modified. + Its initial value is ``[',', '\t', ';', ' ', ':']``. + An example for :class:`Sniffer` use:: with open('example.csv', newline='') as csvfile: @@ -313,7 +359,7 @@ An example for :class:`Sniffer` use:: .. _csv-constants: -The :mod:`csv` module defines the following constants: +The :mod:`!csv` module defines the following constants: .. data:: QUOTE_ALL @@ -323,23 +369,34 @@ The :mod:`csv` module defines the following constants: .. data:: QUOTE_MINIMAL Instructs :class:`writer` objects to only quote those fields which contain - special characters such as *delimiter*, *quotechar* or any of the characters in - *lineterminator*. + special characters such as *delimiter*, *quotechar*, ``'\r'``, ``'\n'`` + or any of the characters in *lineterminator*. + If *doublequote* is :const:`False` and *escapechar* is set, + the *quotechar* is escaped instead of causing the field to be quoted. .. data:: QUOTE_NONNUMERIC Instructs :class:`writer` objects to quote all non-numeric fields. - Instructs :class:`reader` objects to convert all non-quoted fields to type *float*. + Instructs :class:`reader` objects to convert all non-quoted fields to type :class:`float`. + .. note:: + Some numeric types, such as :class:`bool`, :class:`~fractions.Fraction`, + or :class:`~enum.IntEnum`, have a string representation that cannot be + converted to :class:`float`. + They cannot be read in the :data:`QUOTE_NONNUMERIC` and + :data:`QUOTE_STRINGS` modes. .. data:: QUOTE_NONE - Instructs :class:`writer` objects to never quote fields. When the current - *delimiter* occurs in output data it is preceded by the current *escapechar* - character. If *escapechar* is not set, the writer will raise :exc:`Error` if + Instructs :class:`writer` objects to never quote fields. + When the current *delimiter*, *quotechar*, *escapechar*, ``'\r'``, ``'\n'`` + or any of the characters in *lineterminator* occurs in output data + it is preceded by the current *escapechar* character. + If *escapechar* is not set, the writer will raise :exc:`Error` if any characters that require escaping are encountered. + Set *quotechar* to ``None`` to prevent its escaping. Instructs :class:`reader` objects to perform no special processing of quote characters. @@ -365,7 +422,7 @@ The :mod:`csv` module defines the following constants: .. versionadded:: 3.12 -The :mod:`csv` module defines the following exception: +The :mod:`!csv` module defines the following exception: .. exception:: Error @@ -408,11 +465,22 @@ Dialects support the following attributes: .. attribute:: Dialect.escapechar - A one-character string used by the writer to escape the *delimiter* if *quoting* - is set to :const:`QUOTE_NONE` and the *quotechar* if *doublequote* is - :const:`False`. On reading, the *escapechar* removes any special meaning from + A one-character string used by the writer to escape characters that + require escaping: + + * the *delimiter*, the *quotechar*, ``'\r'``, ``'\n'`` and any of the + characters in *lineterminator* are escaped if *quoting* is set to + :const:`QUOTE_NONE`; + * the *quotechar* is escaped if *doublequote* is :const:`False`; + * the *escapechar* itself. + + On reading, the *escapechar* removes any special meaning from the following character. It defaults to :const:`None`, which disables escaping. + .. versionchanged:: 3.10 + Previously the *escapechar* itself was not escaped, + which lost it on reading. + .. versionchanged:: 3.11 An empty *escapechar* is not allowed. @@ -430,9 +498,12 @@ Dialects support the following attributes: .. attribute:: Dialect.quotechar - A one-character string used to quote fields containing special characters, such - as the *delimiter* or *quotechar*, or which contain new-line characters. It - defaults to ``'"'``. + A one-character string used to quote fields containing special characters, + such as the *delimiter* or the *quotechar*, or which contain new-line + characters (``'\r'``, ``'\n'`` or any of the characters in *lineterminator*). + It defaults to ``'"'``. + Can be set to ``None`` to prevent escaping ``'"'`` if *quoting* is set + to :const:`QUOTE_NONE`. .. versionchanged:: 3.11 An empty *quotechar* is not allowed. @@ -441,13 +512,15 @@ Dialects support the following attributes: Controls when quotes should be generated by the writer and recognised by the reader. It can take on any of the :ref:`QUOTE_\* constants ` - and defaults to :const:`QUOTE_MINIMAL`. + and defaults to :const:`QUOTE_MINIMAL` if *quotechar* is not ``None``, + and :const:`QUOTE_NONE` otherwise. .. attribute:: Dialect.skipinitialspace When :const:`True`, spaces immediately following the *delimiter* are ignored. - The default is :const:`False`. + The default is :const:`False`. When combining ``delimiter=' '`` with + ``skipinitialspace=True``, unquoted empty fields are not allowed. .. attribute:: Dialect.strict @@ -506,7 +579,7 @@ out surrounded by parens. This may cause some problems for other programs which read CSV files (assuming they support complex numbers at all). -.. method:: csvwriter.writerow(row) +.. method:: csvwriter.writerow(row, /) Write the *row* parameter to the writer's file object, formatted according to the current :class:`Dialect`. Return the return value of the call to the @@ -515,7 +588,7 @@ read CSV files (assuming they support complex numbers at all). .. versionchanged:: 3.5 Added support of arbitrary iterables. -.. method:: csvwriter.writerows(rows) +.. method:: csvwriter.writerows(rows, /) Write all elements in *rows* (an iterable of *row* objects as described above) to the writer's file object, formatted according to the current @@ -603,7 +676,7 @@ A slightly more advanced use of the reader --- catching and reporting errors:: for row in reader: print(row) except csv.Error as e: - sys.exit('file {}, line {}: {}'.format(filename, reader.line_num, e)) + sys.exit(f'file {filename}, line {reader.line_num}: {e}') And while the module doesn't directly support parsing strings, it can easily be done:: @@ -616,7 +689,7 @@ done:: .. rubric:: Footnotes .. [1] If ``newline=''`` is not specified, newlines embedded inside quoted fields - will not be interpreted correctly, and on platforms that use ``\r\n`` linendings + will not be interpreted correctly, and on platforms that use ``\r\n`` line endings on write an extra ``\r`` will be added. It should always be safe to specify ``newline=''``, since the csv module does its own (:term:`universal `) newline handling. diff --git a/Doc/library/ctypes.rst b/Doc/library/ctypes.rst index 5b733d5321e907..b65887e2eca1b1 100644 --- a/Doc/library/ctypes.rst +++ b/Doc/library/ctypes.rst @@ -10,20 +10,26 @@ -------------- -:mod:`ctypes` is a foreign function library for Python. It provides C compatible +:mod:`!ctypes` is a foreign function library for Python. It provides C compatible data types, and allows calling functions in DLLs or shared libraries. It can be used to wrap these libraries in pure Python. +.. include:: ../includes/optional-module.rst + +.. warning:: + + :mod:`!ctypes` provides low-level access to native libraries and the + process's memory, bypassing Python's safety mechanisms and allowing + execution of arbitrary native code. + Incorrect use can corrupt data and objects, reveal sensitive information, + cause crashes, or otherwise compromise the running process. + .. _ctypes-ctypes-tutorial: ctypes tutorial --------------- -Note: The code samples in this tutorial use :mod:`doctest` to make sure that -they actually work. Since some code samples behave differently under Linux, -Windows, or macOS, they contain doctest directives in comments. - Note: Some code samples reference the ctypes :class:`c_int` type. On platforms where ``sizeof(long) == sizeof(int)`` it is an alias to :class:`c_long`. So, you should not be confused if :class:`c_long` is printed if you would expect @@ -34,13 +40,16 @@ So, you should not be confused if :class:`c_long` is printed if you would expect Loading dynamic link libraries ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -:mod:`ctypes` exports the *cdll*, and on Windows *windll* and *oledll* +:mod:`!ctypes` exports the :py:data:`~ctypes.cdll`, and on Windows +:py:data:`~ctypes.windll` and :py:data:`~ctypes.oledll` objects, for loading dynamic link libraries. -You load libraries by accessing them as attributes of these objects. *cdll* -loads libraries which export functions using the standard ``cdecl`` calling -convention, while *windll* libraries call functions using the ``stdcall`` -calling convention. *oledll* also uses the ``stdcall`` calling convention, and +You load libraries by accessing them as attributes of these objects. +:py:data:`!cdll` loads libraries which export functions using the +standard ``cdecl`` calling convention, while :py:data:`!windll` +libraries call functions using the ``stdcall`` +calling convention. +:py:data:`~oledll` also uses the ``stdcall`` calling convention, and assumes the functions return a Windows :c:type:`!HRESULT` error code. The error code is used to automatically raise an :class:`OSError` exception when the function call fails. @@ -70,11 +79,13 @@ Windows appends the usual ``.dll`` file suffix automatically. being used by Python. Where possible, use native Python functionality, or else import and use the ``msvcrt`` module. -On Linux, it is required to specify the filename *including* the extension to +Other systems require the filename *including* the extension to load a library, so attribute access can not be used to load libraries. Either the :meth:`~LibraryLoader.LoadLibrary` method of the dll loaders should be used, -or you should load the library by creating an instance of CDLL by calling -the constructor:: +or you should load the library by creating an instance of :py:class:`CDLL` +by calling the constructor. + +For example, on Linux:: >>> cdll.LoadLibrary("libc.so.6") # doctest: +LINUX @@ -83,7 +94,14 @@ the constructor:: >>> -.. XXX Add section for macOS. +On macOS:: + + >>> cdll.LoadLibrary("libc.dylib") # doctest: +MACOS + + >>> libc = CDLL("libc.dylib") # doctest: +MACOS + >>> libc # doctest: +MACOS + + .. _ctypes-accessing-functions-from-loaded-dlls: @@ -180,7 +198,7 @@ handle (passing ``None`` as single argument to call it with a ``NULL`` pointer): To find out the correct calling convention you have to look into the C header file or the documentation for the function you want to call. -On Windows, :mod:`ctypes` uses win32 structured exception handling to prevent +On Windows, :mod:`!ctypes` uses win32 structured exception handling to prevent crashes from general protection faults when functions are called with invalid argument values:: @@ -190,10 +208,8 @@ argument values:: OSError: exception: access violation reading 0x00000020 >>> -There are, however, enough ways to crash Python with :mod:`ctypes`, so you -should be careful anyway. The :mod:`faulthandler` module can be helpful in -debugging crashes (e.g. from segmentation faults produced by erroneous C library -calls). +The :mod:`faulthandler` module can help debug crashes, +such as segmentation faults produced by erroneous C library calls. ``None``, integers, bytes objects and (unicode) strings are the only native Python objects that can directly be used as parameters in these function calls. @@ -203,7 +219,7 @@ as pointer to the memory block that contains their data (:c:expr:`char *` or :c:expr:`int` type, their value is masked to fit into the C type. Before we move on calling functions with other parameter types, we have to learn -more about :mod:`ctypes` data types. +more about :mod:`!ctypes` data types. .. _ctypes-fundamental-data-types: @@ -211,73 +227,166 @@ more about :mod:`ctypes` data types. Fundamental data types ^^^^^^^^^^^^^^^^^^^^^^ -:mod:`ctypes` defines a number of primitive C compatible data types: - -+----------------------+------------------------------------------+----------------------------+ -| ctypes type | C type | Python type | -+======================+==========================================+============================+ -| :class:`c_bool` | :c:expr:`_Bool` | bool (1) | -+----------------------+------------------------------------------+----------------------------+ -| :class:`c_char` | :c:expr:`char` | 1-character bytes object | -+----------------------+------------------------------------------+----------------------------+ -| :class:`c_wchar` | :c:type:`wchar_t` | 1-character string | -+----------------------+------------------------------------------+----------------------------+ -| :class:`c_byte` | :c:expr:`char` | int | -+----------------------+------------------------------------------+----------------------------+ -| :class:`c_ubyte` | :c:expr:`unsigned char` | int | -+----------------------+------------------------------------------+----------------------------+ -| :class:`c_short` | :c:expr:`short` | int | -+----------------------+------------------------------------------+----------------------------+ -| :class:`c_ushort` | :c:expr:`unsigned short` | int | -+----------------------+------------------------------------------+----------------------------+ -| :class:`c_int` | :c:expr:`int` | int | -+----------------------+------------------------------------------+----------------------------+ -| :class:`c_uint` | :c:expr:`unsigned int` | int | -+----------------------+------------------------------------------+----------------------------+ -| :class:`c_long` | :c:expr:`long` | int | -+----------------------+------------------------------------------+----------------------------+ -| :class:`c_ulong` | :c:expr:`unsigned long` | int | -+----------------------+------------------------------------------+----------------------------+ -| :class:`c_longlong` | :c:expr:`__int64` or :c:expr:`long long` | int | -+----------------------+------------------------------------------+----------------------------+ -| :class:`c_ulonglong` | :c:expr:`unsigned __int64` or | int | -| | :c:expr:`unsigned long long` | | -+----------------------+------------------------------------------+----------------------------+ -| :class:`c_size_t` | :c:type:`size_t` | int | -+----------------------+------------------------------------------+----------------------------+ -| :class:`c_ssize_t` | :c:type:`ssize_t` or | int | -| | :c:expr:`Py_ssize_t` | | -+----------------------+------------------------------------------+----------------------------+ -| :class:`c_time_t` | :c:type:`time_t` | int | -+----------------------+------------------------------------------+----------------------------+ -| :class:`c_float` | :c:expr:`float` | float | -+----------------------+------------------------------------------+----------------------------+ -| :class:`c_double` | :c:expr:`double` | float | -+----------------------+------------------------------------------+----------------------------+ -| :class:`c_longdouble`| :c:expr:`long double` | float | -+----------------------+------------------------------------------+----------------------------+ -| :class:`c_char_p` | :c:expr:`char *` (NUL terminated) | bytes object or ``None`` | -+----------------------+------------------------------------------+----------------------------+ -| :class:`c_wchar_p` | :c:expr:`wchar_t *` (NUL terminated) | string or ``None`` | -+----------------------+------------------------------------------+----------------------------+ -| :class:`c_void_p` | :c:expr:`void *` | int or ``None`` | -+----------------------+------------------------------------------+----------------------------+ - -(1) - The constructor accepts any object with a truth value. +:mod:`!ctypes` defines a number of primitive C compatible data types: + +.. list-table:: + :header-rows: 1 + + * - ctypes type + - C type + - Python type + - :py:attr:`~_SimpleCData._type_` + * - :class:`c_bool` + - :c:expr:`_Bool` + - :py:class:`bool` + - ``'?'`` + * - :class:`c_char` + - :c:expr:`char` + - 1-character :py:class:`bytes` + - ``'c'`` + * - :class:`c_wchar` + - :c:type:`wchar_t` + - 1-character :py:class:`str` + - ``'u'`` + * - :class:`c_byte` + - :c:expr:`char` + - :py:class:`int` + - ``'b'`` + * - :class:`c_ubyte` + - :c:expr:`unsigned char` + - :py:class:`int` + - ``'B'`` + * - :class:`c_short` + - :c:expr:`short` + - :py:class:`int` + - ``'h'`` + * - :class:`c_ushort` + - :c:expr:`unsigned short` + - :py:class:`int` + - ``'H'`` + * - :class:`c_int` + - :c:expr:`int` + - :py:class:`int` + - ``'i'`` \* + * - :class:`c_int8` + - :c:type:`int8_t` + - :py:class:`int` + - \* + * - :class:`c_int16` + - :c:type:`int16_t` + - :py:class:`int` + - \* + * - :class:`c_int32` + - :c:type:`int32_t` + - :py:class:`int` + - \* + * - :class:`c_int64` + - :c:type:`int64_t` + - :py:class:`int` + - \* + * - :class:`c_uint` + - :c:expr:`unsigned int` + - :py:class:`int` + - ``'I'`` \* + * - :class:`c_uint8` + - :c:type:`uint8_t` + - :py:class:`int` + - \* + * - :class:`c_uint16` + - :c:type:`uint16_t` + - :py:class:`int` + - \* + * - :class:`c_uint32` + - :c:type:`uint32_t` + - :py:class:`int` + - \* + * - :class:`c_uint64` + - :c:type:`uint64_t` + - :py:class:`int` + - \* + * - :class:`c_long` + - :c:expr:`long` + - :py:class:`int` + - ``'l'`` + * - :class:`c_ulong` + - :c:expr:`unsigned long` + - :py:class:`int` + - ``'L'`` + * - :class:`c_longlong` + - :c:expr:`long long` + - :py:class:`int` + - ``'q'`` \* + * - :class:`c_ulonglong` + - :c:expr:`unsigned long long` + - :py:class:`int` + - ``'Q'`` \* + * - :class:`c_size_t` + - :c:type:`size_t` + - :py:class:`int` + - \* + * - :class:`c_ssize_t` + - :c:type:`Py_ssize_t` + - :py:class:`int` + - \* + * - :class:`c_time_t` + - :c:type:`time_t` + - :py:class:`int` + - \* + * - :class:`c_float` + - :c:expr:`float` + - :py:class:`float` + - ``'f'`` + * - :class:`c_double` + - :c:expr:`double` + - :py:class:`float` + - ``'d'`` + * - :class:`c_longdouble` + - :c:expr:`long double` + - :py:class:`float` + - ``'g'`` \* + * - :class:`c_char_p` + - :c:expr:`char *` (NUL terminated) + - :py:class:`bytes` or ``None`` + - ``'z'`` + * - :class:`c_wchar_p` + - :c:expr:`wchar_t *` (NUL terminated) + - :py:class:`str` or ``None`` + - ``'Z'`` + * - :class:`c_void_p` + - :c:expr:`void *` + - :py:class:`int` or ``None`` + - ``'P'`` + * - :class:`py_object` + - :c:expr:`PyObject *` + - :py:class:`object` + - ``'O'`` + * - :ref:`VARIANT_BOOL ` + - :c:expr:`short int` + - :py:class:`bool` + - ``'v'`` Additionally, if IEC 60559 compatible complex arithmetic (Annex G) is supported in both C and ``libffi``, the following complex types are available: -+----------------------------------+---------------------------------+-----------------+ -| ctypes type | C type | Python type | -+==================================+=================================+=================+ -| :class:`c_float_complex` | :c:expr:`float complex` | complex | -+----------------------------------+---------------------------------+-----------------+ -| :class:`c_double_complex` | :c:expr:`double complex` | complex | -+----------------------------------+---------------------------------+-----------------+ -| :class:`c_longdouble_complex` | :c:expr:`long double complex` | complex | -+----------------------------------+---------------------------------+-----------------+ +.. list-table:: + :header-rows: 1 + + * - ctypes type + - C type + - Python type + - :py:attr:`~_SimpleCData._type_` + * - :class:`c_float_complex` + - :c:expr:`float complex` + - :py:class:`complex` + - ``'F'`` + * - :class:`c_double_complex` + - :c:expr:`double complex` + - :py:class:`complex` + - ``'D'`` + * - :class:`c_longdouble_complex` + - :c:expr:`long double complex` + - :py:class:`complex` + - ``'G'`` All these types can be created by calling them with an optional initializer of @@ -291,6 +400,16 @@ the correct type and value:: c_ushort(65533) >>> +The constructors for numeric types will convert input using +:py:meth:`~object.__bool__`, +:py:meth:`~object.__index__` (for ``int``), +:py:meth:`~object.__float__` or :py:meth:`~object.__complex__`. +This means :py:class:`~ctypes.c_bool` accepts any object with a truth value:: + + >>> empty_list = [] + >>> c_bool(empty_list) + c_bool(False) + Since these types are mutable, their value can also be changed afterwards:: >>> i = c_int(42) @@ -379,7 +498,7 @@ from within *IDLE* or *PythonWin*:: >>> As has been mentioned before, all Python types except integers, strings, and -bytes objects have to be wrapped in their corresponding :mod:`ctypes` type, so +bytes objects have to be wrapped in their corresponding :mod:`!ctypes` type, so that they can be converted to the required C data type:: >>> printf(b"An int %d, a double %f\n", 1234, c_double(3.14)) @@ -413,10 +532,10 @@ specify :attr:`~_CFuncPtr.argtypes` for all variadic functions. Calling functions with your own custom data types ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -You can also customize :mod:`ctypes` argument conversion to allow instances of -your own classes be used as function arguments. :mod:`ctypes` looks for an +You can also customize :mod:`!ctypes` argument conversion to allow instances of +your own classes be used as function arguments. :mod:`!ctypes` looks for an :attr:`!_as_parameter_` attribute and uses this as the function argument. The -attribute must be an integer, string, bytes, a :mod:`ctypes` instance, or an +attribute must be an integer, string, bytes, a :mod:`!ctypes` instance, or an object with an :attr:`!_as_parameter_` attribute:: >>> class Bottles: @@ -430,7 +549,7 @@ object with an :attr:`!_as_parameter_` attribute:: >>> If you don't want to store the instance's data in the :attr:`!_as_parameter_` -instance variable, you could define a :class:`property` which makes the +instance variable, you could define a :deco:`property` which makes the attribute available on request. @@ -472,7 +591,7 @@ the Python object passed to the function call, it should do a typecheck or whatever is needed to make sure this object is acceptable, and then return the object itself, its :attr:`!_as_parameter_` attribute, or whatever you want to pass as the C function argument in this case. Again, the result should be an -integer, string, bytes, a :mod:`ctypes` instance, or an object with an +integer, string, bytes, a :mod:`!ctypes` instance, or an object with an :attr:`!_as_parameter_` attribute. @@ -582,7 +701,7 @@ Sometimes a C api function expects a *pointer* to a data type as parameter, probably to write into the corresponding location, or if the data is too large to be passed by value. This is also known as *passing parameters by reference*. -:mod:`ctypes` exports the :func:`byref` function which is used to pass parameters +:mod:`!ctypes` exports the :func:`byref` function which is used to pass parameters by reference. The same effect can be achieved with the :func:`pointer` function, although :func:`pointer` does a lot more work since it constructs a real pointer object, so it is faster to use :func:`byref` if you don't need the pointer @@ -607,12 +726,12 @@ Structures and unions ^^^^^^^^^^^^^^^^^^^^^ Structures and unions must derive from the :class:`Structure` and :class:`Union` -base classes which are defined in the :mod:`ctypes` module. Each subclass must +base classes which are defined in the :mod:`!ctypes` module. Each subclass must define a :attr:`~Structure._fields_` attribute. :attr:`!_fields_` must be a list of *2-tuples*, containing a *field name* and a *field type*. -The field type must be a :mod:`ctypes` type like :class:`c_int`, or any other -derived :mod:`ctypes` type: structure, union, array, pointer. +The field type must be a :mod:`!ctypes` type like :class:`c_int`, or any other +derived :mod:`!ctypes` type: structure, union, array, pointer. Here is a simple example of a POINT structure, which contains two integers named *x* and *y*, and also shows how to initialize a structure in the constructor:: @@ -671,7 +790,7 @@ See :class:`CField`:: .. warning:: - :mod:`ctypes` does not support passing unions or structures with bit-fields + :mod:`!ctypes` does not support passing unions or structures with bit-fields to functions by value. While this may work on 32-bit x86, it's not guaranteed by the library to work in the general case. Unions and structures with bit-fields should always be passed to functions by pointer. @@ -684,16 +803,12 @@ compiler does it. It is possible to override this behavior entirely by specifyi :attr:`~Structure._layout_` class attribute in the subclass definition; see the attribute documentation for details. -It is possible to specify the maximum alignment for the fields by setting -the :attr:`~Structure._pack_` class attribute to a positive integer. -This matches what ``#pragma pack(n)`` does in MSVC. +It is possible to specify the maximum alignment for the fields and/or for the +structure itself by setting the class attributes :attr:`~Structure._pack_` +and/or :attr:`~Structure._align_`, respectively. +See the attribute documentation for details. -It is also possible to set a minimum alignment for how the subclass itself is packed in the -same way ``#pragma align(n)`` works in MSVC. -This can be achieved by specifying a :attr:`~Structure._align_` class attribute -in the subclass definition. - -:mod:`ctypes` uses the native byte order for Structures and Unions. To build +:mod:`!ctypes` uses the native byte order for Structures and Unions. To build structures with non-native byte order, you can use one of the :class:`BigEndianStructure`, :class:`LittleEndianStructure`, :class:`BigEndianUnion`, and :class:`LittleEndianUnion` base classes. These @@ -714,10 +829,16 @@ item in the :attr:`~Structure._fields_` tuples:: ... ("second_16", c_int, 16)] ... >>> print(Int.first_16) - + >>> print(Int.second_16) - - >>> + + +It is important to note that bit field allocation and layout in memory are not +defined as a C standard; their implementation is compiler-specific. +By default, Python will attempt to match the behavior of a "native" compiler +for the current platform. +See the :attr:`~Structure._layout_` attribute for details on the default +behavior and how to change it. .. _ctypes-arrays: @@ -776,7 +897,7 @@ Pointers ^^^^^^^^ Pointer instances are created by calling the :func:`pointer` function on a -:mod:`ctypes` type:: +:mod:`!ctypes` type:: >>> from ctypes import * >>> i = c_int(42) @@ -790,7 +911,7 @@ returns the object to which the pointer points, the ``i`` object above:: c_long(42) >>> -Note that :mod:`ctypes` does not have OOR (original object return), it constructs a +Note that :mod:`!ctypes` does not have OOR (original object return), it constructs a new, equivalent object each time you retrieve an attribute:: >>> pi.contents is i @@ -834,7 +955,7 @@ item. Behind the scenes, the :func:`pointer` function does more than simply create pointer instances, it has to create pointer *types* first. This is done with the -:func:`POINTER` function, which accepts any :mod:`ctypes` type, and returns a +:func:`POINTER` function, which accepts any :mod:`!ctypes` type, and returns a new type:: >>> PI = POINTER(c_int) @@ -856,7 +977,7 @@ Calling the pointer type without an argument creates a ``NULL`` pointer. False >>> -:mod:`ctypes` checks for ``NULL`` when dereferencing pointers (but dereferencing +:mod:`!ctypes` checks for ``NULL`` when dereferencing pointers (but dereferencing invalid non-\ ``NULL`` pointers would crash Python):: >>> null_ptr[0] @@ -876,7 +997,7 @@ invalid non-\ ``NULL`` pointers would crash Python):: Thread safety without the GIL ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -In Python 3.13, the :term:`GIL` may be disabled on :term:`experimental free threaded ` builds. +From Python 3.13 onward, the :term:`GIL` can be disabled on the :term:`free-threaded build`. In ctypes, reads and writes to a single object concurrently is safe, but not across multiple objects: .. code-block:: pycon @@ -941,7 +1062,7 @@ To set a POINTER type field to ``NULL``, you can assign ``None``:: .. XXX list other conversions... Sometimes you have instances of incompatible types. In C, you can cast one type -into another type. :mod:`ctypes` provides a :func:`cast` function which can be +into another type. :mod:`!ctypes` provides a :func:`cast` function which can be used in the same way. The ``Bar`` structure defined above accepts ``POINTER(c_int)`` pointers or :class:`c_int` arrays for its ``values`` field, but not instances of other types:: @@ -1005,7 +1126,7 @@ work:: >>> because the new ``class cell`` is not available in the class statement itself. -In :mod:`ctypes`, we can define the ``cell`` class and set the +In :mod:`!ctypes`, we can define the ``cell`` class and set the :attr:`~Structure._fields_` attribute later, after the class statement:: >>> from ctypes import * @@ -1039,7 +1160,7 @@ other, and finally follow the pointer chain a few times:: Callback functions ^^^^^^^^^^^^^^^^^^ -:mod:`ctypes` allows creating C callable function pointers from Python callables. +:mod:`!ctypes` allows creating C callable function pointers from Python callables. These are sometimes called *callback functions*. First, you must create a class for the callback function. The class knows the @@ -1138,7 +1259,7 @@ write:: .. note:: Make sure you keep references to :func:`CFUNCTYPE` objects as long as they - are used from C code. :mod:`ctypes` doesn't, and if you don't, they may be + are used from C code. :mod:`!ctypes` doesn't, and if you don't, they may be garbage collected, crashing your program when a callback is made. Also, note that if the callback function is called in a thread created @@ -1157,7 +1278,7 @@ Some shared libraries not only export functions, they also export variables. An example in the Python library itself is the :c:data:`Py_Version`, Python runtime version number encoded in a single constant integer. -:mod:`ctypes` can access values like this with the :meth:`~_CData.in_dll` class methods of +:mod:`!ctypes` can access values like this with the :meth:`~_CData.in_dll` class methods of the type. *pythonapi* is a predefined symbol giving access to the Python C api:: @@ -1176,7 +1297,7 @@ Quoting the docs for that value: tricks with this to provide a dynamically created collection of frozen modules. So manipulating this pointer could even prove useful. To restrict the example -size, we show only how this table can be read with :mod:`ctypes`:: +size, we show only how this table can be read with :mod:`!ctypes`:: >>> from ctypes import * >>> @@ -1222,7 +1343,7 @@ for testing. Try it out with ``import __hello__`` for example. Surprises ^^^^^^^^^ -There are some edges in :mod:`ctypes` where you might expect something other +There are some edges in :mod:`!ctypes` where you might expect something other than what actually happens. Consider the following example:: @@ -1290,7 +1411,7 @@ constructs a new Python object each time! Variable-sized data types ^^^^^^^^^^^^^^^^^^^^^^^^^ -:mod:`ctypes` provides some support for variable-sized arrays and structures. +:mod:`!ctypes` provides some support for variable-sized arrays and structures. The :func:`resize` function can be used to resize the memory buffer of an existing ctypes object. The function takes the object as first argument, and @@ -1324,7 +1445,7 @@ get errors accessing other elements:: IndexError: invalid index >>> -Another way to use variable-sized data types with :mod:`ctypes` is to use the +Another way to use variable-sized data types with :mod:`!ctypes` is to use the dynamic nature of Python, and (re-)define the data type after the required size is already known, on a case by case basis. @@ -1368,6 +1489,9 @@ On Linux, :func:`~ctypes.util.find_library` tries to run external programs (``/sbin/ldconfig``, ``gcc``, ``objdump`` and ``ld``) to find the library file. It returns the filename of the library file. +Note that if the output of these programs does not correspond to the dynamic +linker used by Python, the result of this function may be misleading. + .. versionchanged:: 3.6 On Linux, the value of the environment variable ``LD_LIBRARY_PATH`` is used when searching for libraries, if a library cannot be found by any other means. @@ -1402,7 +1526,7 @@ On Windows, :func:`~ctypes.util.find_library` searches along the system search p returns the full pathname, but since there is no predefined naming scheme a call like ``find_library("c")`` will fail and return ``None``. -If wrapping a shared library with :mod:`ctypes`, it *may* be better to determine +If wrapping a shared library with :mod:`!ctypes`, it *may* be better to determine the shared library name at development time, and hardcode that into the wrapper module instead of using :func:`~ctypes.util.find_library` to locate the library at runtime. @@ -1435,14 +1559,82 @@ Loading shared libraries ^^^^^^^^^^^^^^^^^^^^^^^^ There are several ways to load shared libraries into the Python process. One -way is to instantiate one of the following classes: +way is to instantiate :py:class:`CDLL` or one of its subclasses: .. class:: CDLL(name, mode=DEFAULT_MODE, handle=None, use_errno=False, use_last_error=False, winmode=None) - Instances of this class represent loaded shared libraries. Functions in these - libraries use the standard C calling convention, and are assumed to return - :c:expr:`int`. + Represents a loaded shared library. + + Functions in this library use the standard C calling convention, and are + assumed to return :c:expr:`int`. + The Python :term:`global interpreter lock` is released before calling any + function exported by these libraries, and reacquired afterwards. + For different function behavior, use a subclass: :py:class:`~ctypes.OleDLL`, + :py:class:`~ctypes.WinDLL`, or :py:class:`~ctypes.PyDLL`. + + If you have an existing :py:attr:`handle ` to an already + loaded shared library, it can be passed as the *handle* argument to wrap + the opened library in a new :py:class:`!CDLL` object. + In this case, *name* is only used to set the :py:attr:`~ctypes.CDLL._name` + attribute, but it may be adjusted and/or validated. + + If *handle* is ``None``, the underlying platform's :manpage:`dlopen(3)` or + :c:func:`!LoadLibrary` function is used to load the library into + the process, and to get a handle to it. + + *name* is the pathname of the shared library to open. + If *name* does not contain a path separator, the library is found + in a platform-specific way. + + On non-Windows systems, *name* can be ``None``. In this case, + :c:func:`!dlopen` is called with ``NULL``, which opens the main program + as a "library". + (Some systems do the same is *name* is empty; ``None``/``NULL`` is more + portable.) + + .. admonition:: CPython implementation detail + + Since CPython is linked to ``libc``, a ``None`` *name* is often used + to access the C standard library:: + + >>> printf = ctypes.CDLL(None).printf + >>> printf.argtypes = [ctypes.c_char_p] + >>> printf(b"hello\n") + hello + 6 + + To access the Python C API, prefer :py:data:`ctypes.pythonapi` which + works across platforms. + + The *mode* parameter can be used to specify how the library is loaded. For + details, consult the :manpage:`dlopen(3)` manpage. On Windows, *mode* is + ignored. On posix systems, RTLD_NOW is always added, and is not + configurable. + + The *use_errno* parameter, when set to true, enables a ctypes mechanism that + allows accessing the system :data:`errno` error number in a safe way. + :mod:`!ctypes` maintains a thread-local copy of the system's :data:`errno` + variable; if you call foreign functions created with ``use_errno=True`` then the + :data:`errno` value before the function call is swapped with the ctypes private + copy, the same happens immediately after the function call. + + The function :func:`ctypes.get_errno` returns the value of the ctypes private + copy, and the function :func:`ctypes.set_errno` changes the ctypes private copy + to a new value and returns the former value. + + The *use_last_error* parameter, when set to true, enables the same mechanism for + the Windows error code which is managed by the :func:`GetLastError` and + :func:`!SetLastError` Windows API functions; :func:`ctypes.get_last_error` and + :func:`ctypes.set_last_error` are used to request and change the ctypes private + copy of the windows error code. + + The *winmode* parameter is used on Windows to specify how the library is loaded + (since *mode* is ignored). It takes any value that is valid for the Win32 API + ``LoadLibraryEx`` flags parameter. When omitted, the default is to use the + flags that result in the most secure DLL load, which avoids issues such as DLL + hijacking. Passing the full path to the DLL is the safest way to ensure the + correct library and dependencies are loaded. On Windows creating a :class:`CDLL` instance may fail even if the DLL name exists. When a dependent DLL of the loaded DLL is not found, a @@ -1454,20 +1646,47 @@ way is to instantiate one of the following classes: DLLs and determine which one is not found using Windows debugging and tracing tools. + .. seealso:: + + `Microsoft DUMPBIN tool `_ + -- A tool to find DLL dependents. + + .. versionchanged:: 3.8 + Added *winmode* parameter. + .. versionchanged:: 3.12 The *name* parameter can now be a :term:`path-like object`. -.. seealso:: + Instances of this class have no public methods. Functions exported by the + shared library can be accessed as attributes or by index. Please note that + accessing the function through an attribute caches the result and therefore + accessing it repeatedly returns the same object each time. On the other hand, + accessing it through an index returns a new object each time:: + + >>> from ctypes import CDLL + >>> libc = CDLL("libc.so.6") # On Linux + >>> libc.time == libc.time + True + >>> libc['time'] == libc['time'] + False + + The following public attributes are available. Their name starts with an + underscore to not clash with exported function names: + + .. attribute:: _handle - `Microsoft DUMPBIN tool `_ - -- A tool to find DLL dependents. + The system handle used to access the library. + .. attribute:: _name -.. class:: OleDLL(name, mode=DEFAULT_MODE, handle=None, use_errno=False, use_last_error=False, winmode=None) + The name of the library passed in the constructor. - Instances of this class represent loaded shared libraries, - functions in these libraries use the ``stdcall`` calling convention, and are +.. class:: OleDLL + + See :py:class:`~ctypes.CDLL`, the superclass, for common information. + + Functions in this library use the ``stdcall`` calling convention, and are assumed to return the windows specific :class:`HRESULT` code. :class:`HRESULT` values contain information specifying whether the function call failed or succeeded, together with additional error code. If the return value signals a @@ -1479,133 +1698,51 @@ way is to instantiate one of the following classes: :exc:`WindowsError` used to be raised, which is now an alias of :exc:`OSError`. - .. versionchanged:: 3.12 - - The *name* parameter can now be a :term:`path-like object`. +.. class:: WinDLL -.. class:: WinDLL(name, mode=DEFAULT_MODE, handle=None, use_errno=False, use_last_error=False, winmode=None) + See :py:class:`~ctypes.CDLL`, the superclass, for common information. - Instances of this class represent loaded shared libraries, - functions in these libraries use the ``stdcall`` calling convention, and are + Functions in these libraries use the ``stdcall`` calling convention, and are assumed to return :c:expr:`int` by default. .. availability:: Windows - .. versionchanged:: 3.12 - - The *name* parameter can now be a :term:`path-like object`. - - -The Python :term:`global interpreter lock` is released before calling any -function exported by these libraries, and reacquired afterwards. - +.. class:: PyDLL -.. class:: PyDLL(name, mode=DEFAULT_MODE, handle=None) + See :py:class:`~ctypes.CDLL`, the superclass, for common information. - Instances of this class behave like :class:`CDLL` instances, except that the + When functions in this library are called, the Python GIL is *not* released during the function call, and after the function execution the Python error flag is checked. If the error flag is set, a Python exception is raised. - Thus, this is only useful to call Python C api functions directly. - - .. versionchanged:: 3.12 - - The *name* parameter can now be a :term:`path-like object`. - -All these classes can be instantiated by calling them with at least one -argument, the pathname of the shared library. If you have an existing handle to -an already loaded shared library, it can be passed as the ``handle`` named -parameter, otherwise the underlying platform's :c:func:`!dlopen` or -:c:func:`!LoadLibrary` function is used to load the library into -the process, and to get a handle to it. - -The *mode* parameter can be used to specify how the library is loaded. For -details, consult the :manpage:`dlopen(3)` manpage. On Windows, *mode* is -ignored. On posix systems, RTLD_NOW is always added, and is not -configurable. - -The *use_errno* parameter, when set to true, enables a ctypes mechanism that -allows accessing the system :data:`errno` error number in a safe way. -:mod:`ctypes` maintains a thread-local copy of the system's :data:`errno` -variable; if you call foreign functions created with ``use_errno=True`` then the -:data:`errno` value before the function call is swapped with the ctypes private -copy, the same happens immediately after the function call. - -The function :func:`ctypes.get_errno` returns the value of the ctypes private -copy, and the function :func:`ctypes.set_errno` changes the ctypes private copy -to a new value and returns the former value. - -The *use_last_error* parameter, when set to true, enables the same mechanism for -the Windows error code which is managed by the :func:`GetLastError` and -:func:`!SetLastError` Windows API functions; :func:`ctypes.get_last_error` and -:func:`ctypes.set_last_error` are used to request and change the ctypes private -copy of the windows error code. - -The *winmode* parameter is used on Windows to specify how the library is loaded -(since *mode* is ignored). It takes any value that is valid for the Win32 API -``LoadLibraryEx`` flags parameter. When omitted, the default is to use the -flags that result in the most secure DLL load, which avoids issues such as DLL -hijacking. Passing the full path to the DLL is the safest way to ensure the -correct library and dependencies are loaded. - -.. versionchanged:: 3.8 - Added *winmode* parameter. + Thus, this is only useful to call Python C API functions directly. .. data:: RTLD_GLOBAL - :noindex: Flag to use as *mode* parameter. On platforms where this flag is not available, it is defined as the integer zero. .. data:: RTLD_LOCAL - :noindex: Flag to use as *mode* parameter. On platforms where this is not available, it is the same as *RTLD_GLOBAL*. .. data:: DEFAULT_MODE - :noindex: The default mode which is used to load shared libraries. On OSX 10.3, this is *RTLD_GLOBAL*, otherwise it is the same as *RTLD_LOCAL*. -Instances of these classes have no public methods. Functions exported by the -shared library can be accessed as attributes or by index. Please note that -accessing the function through an attribute caches the result and therefore -accessing it repeatedly returns the same object each time. On the other hand, -accessing it through an index returns a new object each time:: - - >>> from ctypes import CDLL - >>> libc = CDLL("libc.so.6") # On Linux - >>> libc.time == libc.time - True - >>> libc['time'] == libc['time'] - False - -The following public attributes are available, their name starts with an -underscore to not clash with exported function names: - - -.. attribute:: PyDLL._handle - - The system handle used to access the library. - - -.. attribute:: PyDLL._name - - The name of the library passed in the constructor. Shared libraries can also be loaded by using one of the prefabricated objects, which are instances of the :class:`LibraryLoader` class, either by calling the :meth:`~LibraryLoader.LoadLibrary` method, or by retrieving the library as attribute of the loader instance. - .. class:: LibraryLoader(dlltype) Class which loads shared libraries. *dlltype* should be one of the @@ -1624,13 +1761,11 @@ attribute of the loader instance. These prefabricated library loaders are available: .. data:: cdll - :noindex: Creates :class:`CDLL` instances. .. data:: windll - :noindex: Creates :class:`WinDLL` instances. @@ -1638,7 +1773,6 @@ These prefabricated library loaders are available: .. data:: oledll - :noindex: Creates :class:`OleDLL` instances. @@ -1646,7 +1780,6 @@ These prefabricated library loaders are available: .. data:: pydll - :noindex: Creates :class:`PyDLL` instances. @@ -1655,7 +1788,6 @@ For accessing the C Python api directly, a ready-to-use Python shared library object is available: .. data:: pythonapi - :noindex: An instance of :class:`PyDLL` that exposes Python C API functions as attributes. Note that all these functions are assumed to return C @@ -1906,7 +2038,7 @@ the windows header file is this:: LPCWSTR lpCaption, UINT uType); -Here is the wrapping with :mod:`ctypes`:: +Here is the wrapping with :mod:`!ctypes`:: >>> from ctypes import c_int, WINFUNCTYPE, windll >>> from ctypes.wintypes import HWND, LPCWSTR, UINT @@ -1929,7 +2061,7 @@ function retrieves the dimensions of a specified window by copying them into HWND hWnd, LPRECT lpRect); -Here is the wrapping with :mod:`ctypes`:: +Here is the wrapping with :mod:`!ctypes`:: >>> from ctypes import POINTER, WINFUNCTYPE, windll, WinError >>> from ctypes.wintypes import BOOL, HWND, RECT @@ -1957,7 +2089,7 @@ do the error checking, and raises an exception when the api call failed:: >>> If the :attr:`~_CFuncPtr.errcheck` function returns the argument tuple it receives -unchanged, :mod:`ctypes` continues the normal processing it does on the output +unchanged, :mod:`!ctypes` continues the normal processing it does on the output parameters. If you want to return a tuple of window coordinates instead of a ``RECT`` instance, you can retrieve the fields in the function and return them instead, the normal processing will no longer take place:: @@ -2031,35 +2163,55 @@ Utility functions pointer. -.. function:: create_string_buffer(init_or_size, size=None) +.. function:: create_string_buffer(init, size=None) + create_string_buffer(size) This function creates a mutable character buffer. The returned object is a ctypes array of :class:`c_char`. - *init_or_size* must be an integer which specifies the size of the array, or a - bytes object which will be used to initialize the array items. + If *size* is given (and not ``None``), it must be an :class:`int`. + It specifies the size of the returned array. + + If the *init* argument is given, it must be :class:`bytes`. It is used + to initialize the array items. Bytes not initialized this way are + set to zero (NUL). + + If *size* is not given (or if it is ``None``), the buffer is made one element + larger than *init*, effectively adding a NUL terminator. + + If both arguments are given, *size* must not be less than ``len(init)``. + + .. warning:: + + If *size* is equal to ``len(init)``, a NUL terminator is + not added. Do not treat such a buffer as a C string. + + For example:: - If a bytes object is specified as first argument, the buffer is made one item - larger than its length so that the last element in the array is a NUL - termination character. An integer can be passed as second argument which allows - specifying the size of the array if the length of the bytes should not be used. + >>> bytes(create_string_buffer(2)) + b'\x00\x00' + >>> bytes(create_string_buffer(b'ab')) + b'ab\x00' + >>> bytes(create_string_buffer(b'ab', 2)) + b'ab' + >>> bytes(create_string_buffer(b'ab', 4)) + b'ab\x00\x00' + >>> bytes(create_string_buffer(b'abcdef', 2)) + Traceback (most recent call last): + ... + ValueError: byte string too long .. audit-event:: ctypes.create_string_buffer init,size ctypes.create_string_buffer -.. function:: create_unicode_buffer(init_or_size, size=None) +.. function:: create_unicode_buffer(init, size=None) + create_unicode_buffer(size) This function creates a mutable unicode character buffer. The returned object is a ctypes array of :class:`c_wchar`. - *init_or_size* must be an integer which specifies the size of the array, or a - string which will be used to initialize the array items. - - If a string is specified as first argument, the buffer is made one item - larger than the length of the string so that the last element in the array is a - NUL termination character. An integer can be passed as second argument which - allows specifying the size of the array if the length of the string should not - be used. + The function takes the same arguments as :func:`~create_string_buffer` except + *init* must be a string and *size* counts :class:`c_wchar`. .. audit-event:: ctypes.create_unicode_buffer init,size ctypes.create_unicode_buffer @@ -2092,6 +2244,8 @@ Utility functions The exact functionality is system dependent. + See :ref:`ctypes-finding-shared-libraries` for complete documentation. + .. function:: find_msvcrt() :module: ctypes.util @@ -2405,10 +2559,33 @@ Fundamental data types Python bytes object or string. When the ``value`` attribute is retrieved from a ctypes instance, usually - a new object is returned each time. :mod:`ctypes` does *not* implement + a new object is returned each time. :mod:`!ctypes` does *not* implement original object return, always a new object is constructed. The same is true for all other ctypes object instances. + Each subclass has a class attribute: + + .. attribute:: _type_ + + Class attribute that contains an internal type code, as a + single-character string. + See :ref:`ctypes-fundamental-data-types` for a summary. + + Types marked \* in the summary may be (or always are) aliases of a + different :class:`_SimpleCData` subclass, and will not necessarily + use the listed type code. + For example, if the platform's :c:expr:`long`, :c:expr:`long long` + and :c:expr:`time_t` C types are the same, then :class:`c_long`, + :class:`c_longlong` and :class:`c_time_t` all refer to a single class, + :class:`c_long`, whose :attr:`_type_` code is ``'l'``. + The ``'L'`` code will be unused. + + .. seealso:: + + The :mod:`array` and :ref:`struct ` modules, + as well as third-party modules like `numpy `__, + use similar -- but slightly different -- type codes. + Fundamental data types, when returned as foreign function call results, or, for example, by retrieving structure field members or array items, are transparently @@ -2498,7 +2675,7 @@ These are the fundamental ctypes data types: .. class:: c_int8 - Represents the C 8-bit :c:expr:`signed int` datatype. Usually an alias for + Represents the C 8-bit :c:expr:`signed int` datatype. It is an alias for :class:`c_byte`. @@ -2530,6 +2707,8 @@ These are the fundamental ctypes data types: Represents the C :c:expr:`signed long long` datatype. The constructor accepts an optional integer initializer; no overflow checking is done. + On platforms where ``sizeof(long long) == sizeof(long)`` it is an alias + to :class:`c_long`. .. class:: c_short @@ -2541,11 +2720,15 @@ These are the fundamental ctypes data types: .. class:: c_size_t Represents the C :c:type:`size_t` datatype. + Usually an alias for another unsigned integer type. .. class:: c_ssize_t - Represents the C :c:type:`ssize_t` datatype. + Represents the :c:type:`Py_ssize_t` datatype. + This is a signed version of :c:type:`size_t`; + that is, the POSIX :c:type:`ssize_t` type. + Usually an alias for another integer type. .. versionadded:: 3.2 @@ -2553,6 +2736,7 @@ These are the fundamental ctypes data types: .. class:: c_time_t Represents the C :c:type:`time_t` datatype. + Usually an alias for another integer type. .. versionadded:: 3.12 @@ -2573,7 +2757,7 @@ These are the fundamental ctypes data types: .. class:: c_uint8 - Represents the C 8-bit :c:expr:`unsigned int` datatype. Usually an alias for + Represents the C 8-bit :c:expr:`unsigned int` datatype. It is an alias for :class:`c_ubyte`. @@ -2605,6 +2789,8 @@ These are the fundamental ctypes data types: Represents the C :c:expr:`unsigned long long` datatype. The constructor accepts an optional integer initializer; no overflow checking is done. + On platforms where ``sizeof(long long) == sizeof(long)`` it is an alias + to :class:`c_long`. .. class:: c_ushort @@ -2656,8 +2842,11 @@ These are the fundamental ctypes data types: .. versionchanged:: 3.14 :class:`!py_object` is now a :term:`generic type`. +.. _ctypes-wintypes: + The :mod:`!ctypes.wintypes` module provides quite some other Windows specific -data types, for example :c:type:`!HWND`, :c:type:`!WPARAM`, or :c:type:`!DWORD`. +data types, for example :c:type:`!HWND`, :c:type:`!WPARAM`, +:c:type:`!VARIANT_BOOL` or :c:type:`!DWORD`. Some useful structures like :c:type:`!MSG` or :c:type:`!RECT` are also defined. @@ -2704,7 +2893,7 @@ fields, or any other data types containing pointer type fields. Abstract base class for structures in *native* byte order. Concrete structure and union types must be created by subclassing one of these - types, and at least define a :attr:`_fields_` class variable. :mod:`ctypes` will + types, and at least define a :attr:`_fields_` class variable. :mod:`!ctypes` will create :term:`descriptor`\s which allow reading and writing the fields by direct attribute accesses. These are the @@ -2750,11 +2939,18 @@ fields, or any other data types containing pointer type fields. .. attribute:: _pack_ An optional small integer that allows overriding the alignment of - structure fields in the instance. :attr:`_pack_` must already be defined - when :attr:`_fields_` is assigned, otherwise it will have no effect. - Setting this attribute to 0 is the same as not setting it at all. + structure fields in the instance. - This is only implemented for the MSVC-compatible memory layout. + This is only implemented for the MSVC-compatible memory layout + (see :attr:`_layout_`). + + Setting :attr:`!_pack_` to 0 is the same as not setting it at all. + Otherwise, the value must be a positive power of two. + The effect is equivalent to ``#pragma pack(N)`` in C, except + :mod:`!ctypes` may allow larger *n* than what the compiler accepts. + + :attr:`!_pack_` must already be defined + when :attr:`_fields_` is assigned, otherwise it will have no effect. .. deprecated-removed:: 3.14 3.19 @@ -2767,9 +2963,22 @@ fields, or any other data types containing pointer type fields. .. attribute:: _align_ - An optional small integer that allows overriding the alignment of + An optional small integer that allows increasing the alignment of the structure when being packed or unpacked to/from memory. - Setting this attribute to 0 is the same as not setting it at all. + + The value must not be negative. + The effect is equivalent to ``__attribute__((aligned(N)))`` on GCC + or ``#pragma align(N)`` on MSVC, except :mod:`!ctypes` may allow + values that the compiler would reject. + + :attr:`!_align_` can only *increase* a structure's alignment + requirements. Setting it to 0 or 1 has no effect. + + Using values that are not powers of two is discouraged and may lead to + surprising behavior. + + :attr:`!_align_` must already be defined + when :attr:`_fields_` is assigned, otherwise it will have no effect. .. versionadded:: 3.13 @@ -2808,7 +3017,7 @@ fields, or any other data types containing pointer type fields. assigned, otherwise it will have no effect. The fields listed in this variable must be structure or union type fields. - :mod:`ctypes` will create descriptors in the structure type that allows + :mod:`!ctypes` will create descriptors in the structure type that allows accessing the nested fields directly, without the need to create the structure or union field. @@ -2939,7 +3148,7 @@ fields, or any other data types containing pointer type fields. .. attribute:: is_anonymous True if this field is anonymous, that is, it contains nested sub-fields - that should be be merged into a containing structure or union. + that should be merged into a containing structure or union. .. _ctypes-arrays-pointers: @@ -2952,12 +3161,14 @@ Arrays and pointers Abstract base class for arrays. The recommended way to create concrete array types is by multiplying any - :mod:`ctypes` data type with a non-negative integer. Alternatively, you can subclass + :mod:`!ctypes` data type with a non-negative integer. Alternatively, you can subclass this type and define :attr:`_length_` and :attr:`_type_` class variables. Array elements can be read and written using standard subscript and slice accesses; for slice reads, the resulting object is *not* itself an :class:`Array`. + Arrays are :ref:`generic ` over the type of their elements. + .. attribute:: _length_ @@ -2978,10 +3189,10 @@ Arrays and pointers Create an array. Equivalent to ``type * length``, where *type* is a - :mod:`ctypes` data type and *length* an integer. + :mod:`!ctypes` data type and *length* an integer. - This function is :term:`soft deprecated` in favor of multiplication. - There are no plans to remove it. + .. soft-deprecated:: 3.14 + In favor of multiplication. .. class:: _Pointer diff --git a/Doc/library/curses.ascii.rst b/Doc/library/curses.ascii.rst index cb895664ff1b11..86cbbb5a4b7c03 100644 --- a/Doc/library/curses.ascii.rst +++ b/Doc/library/curses.ascii.rst @@ -11,7 +11,7 @@ -------------- -The :mod:`curses.ascii` module supplies name constants for ASCII characters and +The :mod:`!curses.ascii` module supplies name constants for ASCII characters and functions to test membership in various ASCII character classes. The constants supplied are names for control characters as follows: @@ -117,7 +117,7 @@ C library: .. function:: isblank(c) - Checks for an ASCII whitespace character; space or horizontal tab. + Checks for an ASCII blank character; space or horizontal tab. .. function:: iscntrl(c) @@ -133,7 +133,7 @@ C library: .. function:: isgraph(c) - Checks for ASCII any printable character except space. + Checks for any ASCII printable character except space. .. function:: islower(c) @@ -148,7 +148,7 @@ C library: .. function:: ispunct(c) - Checks for any printable ASCII character which is not a space or an alphanumeric + Checks for any ASCII printable character which is not a space or an alphanumeric character. @@ -171,7 +171,8 @@ C library: .. function:: isctrl(c) - Checks for an ASCII control character (ordinal values 0 to 31). + Checks for an ASCII control character (ordinal values 0 to 31). Unlike + :func:`iscntrl`, this does not include the delete character (0x7f). .. function:: ismeta(c) diff --git a/Doc/library/curses.panel.rst b/Doc/library/curses.panel.rst index 11fd841d381f69..58505827e33cb5 100644 --- a/Doc/library/curses.panel.rst +++ b/Doc/library/curses.panel.rst @@ -18,7 +18,15 @@ displayed. Panels can be added, moved up or down in the stack, and removed. Functions --------- -The module :mod:`curses.panel` defines the following functions: +The module :mod:`!curses.panel` defines the following exception: + + +.. exception:: error + + Exception raised when a curses panel library function returns an error. + + +The module :mod:`!curses.panel` defines the following functions: .. function:: bottom_panel() @@ -28,7 +36,8 @@ The module :mod:`curses.panel` defines the following functions: .. function:: new_panel(win) - Returns a panel object, associating it with the given window *win*. Be aware + Returns a panel object, associating it with the given window *win* and + placing the new panel on top of the panel stack. Be aware that you need to keep the returned panel object referenced explicitly. If you don't, the panel object is garbage collected and removed from the panel stack. @@ -46,75 +55,94 @@ The module :mod:`curses.panel` defines the following functions: .. _curses-panel-objects: -Panel Objects +Panel objects ------------- -Panel objects, as returned by :func:`new_panel` above, are windows with a -stacking order. There's always a window associated with a panel which determines -the content, while the panel methods are responsible for the window's depth in -the panel stack. +.. raw:: html + + + + + + + + + + + + + + + +.. class:: panel + + Panel objects, as returned by :func:`new_panel` above, are windows with a + stacking order. There's always a window associated with a panel which + determines the content, while the panel methods are responsible for the + window's depth in the panel stack. -Panel objects have the following methods: + Panel objects have the following methods: -.. method:: Panel.above() +.. method:: panel.above() Returns the panel above the current panel. -.. method:: Panel.below() +.. method:: panel.below() Returns the panel below the current panel. -.. method:: Panel.bottom() +.. method:: panel.bottom() Push the panel to the bottom of the stack. -.. method:: Panel.hidden() +.. method:: panel.hidden() Returns ``True`` if the panel is hidden (not visible), ``False`` otherwise. -.. method:: Panel.hide() +.. method:: panel.hide() Hide the panel. This does not delete the object, it just makes the window on screen invisible. -.. method:: Panel.move(y, x) +.. method:: panel.move(y, x) Move the panel to the screen coordinates ``(y, x)``. -.. method:: Panel.replace(win) +.. method:: panel.replace(win) Change the window associated with the panel to the window *win*. -.. method:: Panel.set_userptr(obj) +.. method:: panel.set_userptr(obj) Set the panel's user pointer to *obj*. This is used to associate an arbitrary piece of data with the panel, and can be any Python object. -.. method:: Panel.show() +.. method:: panel.show() - Display the panel (which might have been hidden). + Display the panel (which might have been hidden), placing it on top of + the panel stack. -.. method:: Panel.top() +.. method:: panel.top() Push panel to the top of the stack. -.. method:: Panel.userptr() +.. method:: panel.userptr() Returns the user pointer for the panel. This might be any Python object. -.. method:: Panel.window() +.. method:: panel.window() Returns the window object associated with the panel. diff --git a/Doc/library/curses.rst b/Doc/library/curses.rst index 137504c51b4358..614e2fa20d03da 100644 --- a/Doc/library/curses.rst +++ b/Doc/library/curses.rst @@ -4,7 +4,6 @@ .. module:: curses :synopsis: An interface to the curses library, providing portable terminal handling. - :platform: Unix .. sectionauthor:: Moshe Zadka .. sectionauthor:: Eric Raymond @@ -13,7 +12,7 @@ -------------- -The :mod:`curses` module provides an interface to the curses library, the +The :mod:`!curses` module provides an interface to the curses library, the de-facto standard for portable advanced terminal handling. While curses is most widely used in the Unix environment, versions are available @@ -23,6 +22,10 @@ Linux and the BSD variants of Unix. .. include:: ../includes/wasm-mobile-notavail.rst +.. include:: ../includes/optional-module.rst + +.. availability:: Unix. + .. note:: Whenever the documentation mentions a *character* it can be specified @@ -31,6 +34,18 @@ Linux and the BSD variants of Unix. Whenever the documentation mentions a *character string* it can be specified as a Unicode string or a byte string. +.. note:: + + Whether curses may be used from several threads + depends on the underlying library and how it was built. + In many implementations, including the default build of ncurses, + the screen state is shared and not thread-safe; + since the blocking and refresh methods + (such as :meth:`~window.getch` and :meth:`~window.refresh`) + release the :term:`GIL`, + unsynchronized use from several threads can then crash the interpreter. + Serialize the calls. + .. seealso:: Module :mod:`curses.ascii` @@ -52,7 +67,7 @@ Linux and the BSD variants of Unix. Functions --------- -The module :mod:`curses` defines the following exception: +The module :mod:`!curses` defines the following exception: .. exception:: error @@ -65,10 +80,10 @@ The module :mod:`curses` defines the following exception: default to the current cursor location. Whenever *attr* is optional, it defaults to :const:`A_NORMAL`. -The module :mod:`curses` defines the following functions: +The module :mod:`!curses` defines the following functions: -.. function:: assume_default_colors(fg, bg) +.. function:: assume_default_colors(fg, bg, /) Allow use of default values for colors on terminals supporting this feature. Use this to support transparency in your application. @@ -80,6 +95,8 @@ The module :mod:`curses` defines the following functions: * Change the definition of the color-pair ``0`` to ``(fg, bg)``. + This is an ncurses extension. + .. versionadded:: 3.14 @@ -116,7 +133,8 @@ The module :mod:`curses` defines the following functions: Return the intensity of the red, green, and blue (RGB) components in the color *color_number*, which must be between ``0`` and ``COLORS - 1``. Return a 3-tuple, containing the R,G,B values for the given color, which will be between - ``0`` (no component) and ``1000`` (maximum amount of component). + ``0`` (no component) and ``1000`` (maximum amount of component). Raise an + exception if the color is not supported. .. function:: color_pair(pair_number) @@ -162,7 +180,7 @@ The module :mod:`curses` defines the following functions: Update the physical screen. The curses library keeps two data structures, one representing the current physical screen contents and a virtual screen - representing the desired next state. The :func:`doupdate` ground updates the + representing the desired next state. The :func:`doupdate` function updates the physical screen to match the virtual screen. The virtual screen may be updated by a :meth:`~window.noutrefresh` call after write @@ -194,7 +212,7 @@ The module :mod:`curses` defines the following functions: .. function:: filter() The :func:`.filter` routine, if used, must be called before :func:`initscr` is - called. The effect is that, during those calls, :envvar:`LINES` is set to ``1``; the + called. The effect is that, during the initialization, :envvar:`LINES` is set to ``1``; the capabilities ``clear``, ``cup``, ``cud``, ``cud1``, ``cuu1``, ``cuu``, ``vpa`` are disabled; and the ``home`` string is set to the value of ``cr``. The effect is that the cursor is confined to the current line, and so are screen updates. This may be used for enabling @@ -240,9 +258,10 @@ The module :mod:`curses` defines the following functions: .. function:: getwin(file) - Read window related data stored in the file by an earlier :func:`window.putwin` call. + Read window-related data stored in the file by an earlier :meth:`window.putwin` call. The routine then creates and initializes a new window using that data, returning - the new window object. + the new window object. The *file* argument must be a file object opened for + reading in binary mode. .. function:: has_colors() @@ -253,7 +272,7 @@ The module :mod:`curses` defines the following functions: Return ``True`` if the module supports extended colors; otherwise, return ``False``. Extended color support allows more than 256 color pairs for - terminals that support more than 16 colors (e.g. xterm-256color). + terminals that support more than 16 colors (for example, xterm-256color). Extended color support requires ncurses version 6.1 or later. @@ -320,12 +339,21 @@ The module :mod:`curses` defines the following functions: Initialize the library. Return a :ref:`window ` object which represents the whole screen. + See :func:`setupterm` for a caveat about calling it before this function. + .. note:: If there is an error opening the terminal, the underlying curses library may cause the interpreter to exit. +.. function:: intrflush(flag) + + If *flag* is ``True``, pressing an interrupt key (interrupt, break, or quit) + will flush all output in the terminal driver queue. If *flag* is ``False``, + no flushing is done. + + .. function:: is_term_resized(nlines, ncols) Return ``True`` if :func:`resize_term` would modify the window structure, @@ -347,6 +375,8 @@ The module :mod:`curses` defines the following functions: bytes object consisting of the prefix ``b'M-'`` followed by the name of the corresponding ASCII character. + Raise a :exc:`ValueError` if *k* is negative. + .. function:: killchar() @@ -372,7 +402,8 @@ The module :mod:`curses` defines the following functions: Set the maximum time in milliseconds that can elapse between press and release events in order for them to be recognized as a click, and return the previous - interval value. The default value is 200 milliseconds, or one fifth of a second. + interval value. The default value is 166 milliseconds, or one sixth of a second. + Use a negative *interval* to obtain the interval value without changing it. .. function:: mousemask(mousemask) @@ -380,7 +411,7 @@ The module :mod:`curses` defines the following functions: Set the mouse events to be reported, and return a tuple ``(availmask, oldmask)``. *availmask* indicates which of the specified mouse events can be reported; on complete failure it returns ``0``. *oldmask* is the previous value of - the given window's mouse event mask. If this function is never called, no mouse + the mouse event mask. If this function is never called, no mouse events are ever reported. @@ -402,7 +433,7 @@ The module :mod:`curses` defines the following functions: methods of a pad require 6 arguments to specify the part of the pad to be displayed and the location on the screen to be used for the display. The arguments are *pminrow*, *pmincol*, *sminrow*, *smincol*, *smaxrow*, *smaxcol*; the *p* - arguments refer to the upper left corner of the pad region to be displayed and + arguments refer to the upper-left corner of the pad region to be displayed and the *s* arguments define a clipping box on the screen within which the pad region is to be displayed. @@ -417,12 +448,14 @@ The module :mod:`curses` defines the following functions: right corner of the screen. -.. function:: nl() +.. function:: nl(flag=True) Enter newline mode. This mode translates the return key into newline on input, and translates newline into return and line-feed on output. Newline mode is initially on. + If *flag* is ``False``, the effect is the same as calling :func:`nonl`. + .. function:: nocbreak() @@ -475,6 +508,8 @@ The module :mod:`curses` defines the following functions: terminfo capability for the current terminal. Note that the output of :func:`putp` always goes to standard output. + :func:`setupterm` (or :func:`initscr`) must be called first. + .. function:: qiflush([flag]) @@ -571,6 +606,17 @@ The module :mod:`curses` defines the following functions: file descriptor to which any initialization sequences will be sent; if not supplied or ``-1``, the file descriptor for ``sys.stdout`` will be used. + Raise a :exc:`curses.error` if the terminal could not be found or its + terminfo database entry could not be read. If the terminal has already + been initialized, this function has no effect. + + .. note:: + + Calling :func:`initscr` after :func:`setupterm` + leaks the terminal that :func:`setupterm` allocated: + the curses library keeps only a single current terminal + and does not free the previously allocated one. + .. function:: start_color() @@ -579,7 +625,7 @@ The module :mod:`curses` defines the following functions: after :func:`initscr`. :func:`start_color` initializes eight basic colors (black, red, green, yellow, - blue, magenta, cyan, and white), and two global variables in the :mod:`curses` + blue, magenta, cyan, and white), and two global variables in the :mod:`!curses` module, :const:`COLORS` and :const:`COLOR_PAIRS`, containing the maximum number of colors and color-pairs the terminal can support. It also restores the colors on the terminal to the values they had when the terminal was just turned on. @@ -605,6 +651,8 @@ The module :mod:`curses` defines the following functions: Boolean capability, or ``0`` if it is canceled or absent from the terminal description. + :func:`setupterm` (or :func:`initscr`) must be called first. + .. function:: tigetnum(capname) @@ -613,6 +661,8 @@ The module :mod:`curses` defines the following functions: numeric capability, or ``-1`` if it is canceled or absent from the terminal description. + :func:`setupterm` (or :func:`initscr`) must be called first. + .. function:: tigetstr(capname) @@ -621,13 +671,17 @@ The module :mod:`curses` defines the following functions: is not a terminfo "string capability", or is canceled or absent from the terminal description. + :func:`setupterm` (or :func:`initscr`) must be called first. + .. function:: tparm(str[, ...]) Instantiate the bytes object *str* with the supplied parameters, where *str* should - be a parameterized string obtained from the terminfo database. E.g. + be a parameterized string obtained from the terminfo database. For example, ``tparm(tigetstr("cup"), 5, 3)`` could result in ``b'\033[6;4H'``, the exact - result depending on terminal type. + result depending on terminal type. Up to nine integer parameters may be supplied. + + :func:`setupterm` (or :func:`initscr`) must be called first. .. function:: typeahead(fd) @@ -713,11 +767,13 @@ The module :mod:`curses` defines the following functions: .. _curses-window-objects: -Window Objects +Window objects -------------- -Window objects, as returned by :func:`initscr` and :func:`newwin` above, have -the following methods and attributes: +.. class:: window + + Window objects, as returned by :func:`initscr` and :func:`newwin` above, have + the following methods and attributes: .. method:: window.addch(ch[, attr]) @@ -730,7 +786,7 @@ the following methods and attributes: .. note:: Writing outside the window, subwindow, or pad raises a :exc:`curses.error`. - Attempting to write to the lower right corner of a window, subwindow, + Attempting to write to the lower-right corner of a window, subwindow, or pad will cause an exception to be raised after the character is printed. @@ -751,15 +807,14 @@ the following methods and attributes: .. note:: * Writing outside the window, subwindow, or pad raises :exc:`curses.error`. - Attempting to write to the lower right corner of a window, subwindow, + Attempting to write to the lower-right corner of a window, subwindow, or pad will cause an exception to be raised after the string is printed. - * A `bug in ncurses `_, the backend - for this Python module, can cause SegFaults when resizing windows. This - is fixed in ncurses-6.1-20190511. If you are stuck with an earlier - ncurses, you can avoid triggering this if you do not call :func:`addstr` - with a *str* that has embedded newlines. Instead, call :func:`addstr` - separately for each line. + * A bug in ncurses, the backend for this Python module, could cause + segfaults when resizing windows. This was fixed in ncurses-6.1-20190511. + If you are stuck with an earlier ncurses, you can avoid triggering it by + not calling :meth:`!addstr` with a *str* that has embedded newlines; + instead, call :meth:`!addstr` separately for each line. .. method:: window.attroff(attr) @@ -770,7 +825,7 @@ the following methods and attributes: .. method:: window.attron(attr) - Add attribute *attr* from the "background" set applied to all writes to the + Add attribute *attr* to the "background" set applied to all writes to the current window. @@ -886,7 +941,8 @@ the following methods and attributes: .. method:: window.delch([y, x]) - Delete any character at ``(y, x)``. + Delete the character under the cursor, or at ``(y, x)`` if specified. All + characters to the right on the same line are shifted one position left. .. method:: window.deleteln() @@ -943,6 +999,7 @@ the following methods and attributes: .. method:: window.getbkgd() Return the given window's current background character/attribute pair. + Its components can be extracted like those of :meth:`inch`. .. method:: window.getch([y, x]) @@ -988,6 +1045,11 @@ the following methods and attributes: window.getstr(y, x, n) Read a bytes object from the user, with primitive line editing capacity. + At most *n* characters are read; + *n* defaults to and cannot exceed 2047. + + .. versionchanged:: 3.14 + The maximum value for *n* was increased from 1023 to 2047. .. method:: window.getyx() @@ -996,11 +1058,12 @@ the following methods and attributes: upper-left corner. -.. method:: window.hline(ch, n) - window.hline(y, x, ch, n) +.. method:: window.hline(ch, n[, attr]) + window.hline(y, x, ch, n[, attr]) Display a horizontal line starting at ``(y, x)`` with length *n* consisting of - the character *ch*. + the character *ch* with attributes *attr*. The line stops at the right edge + of the window if fewer than *n* cells are available. .. method:: window.idcok(flag) @@ -1013,8 +1076,8 @@ the following methods and attributes: .. method:: window.idlok(flag) - If *flag* is ``True``, :mod:`curses` will try and use hardware line - editing facilities. Otherwise, line insertion/deletion are disabled. + If *flag* is ``True``, :mod:`!curses` will try to use hardware line + editing facilities. Otherwise, curses will not use them. .. method:: window.immedok(flag) @@ -1027,15 +1090,24 @@ the following methods and attributes: .. method:: window.inch([y, x]) - Return the character at the given position in the window. The bottom 8 bits are - the character proper, and upper bits are the attributes. + Return the character at the given position in the window. + The bottom 8 bits are the character proper and the upper bits are the attributes; + extract them with the :data:`A_CHARTEXT` and :data:`A_ATTRIBUTES` bit-masks, + and the color pair with :func:`pair_number`. + The character byte is the locale-encoded byte of the cell's character, + consistent with :meth:`instr`. + On a wide-character build, a character that does not fit in a single byte + in the current locale has a character byte of ``0``; + use :meth:`instr` to read such characters. .. method:: window.insch(ch[, attr]) window.insch(y, x, ch[, attr]) - Paint character *ch* at ``(y, x)`` with attributes *attr*, moving the line from - position *x* right by one character. + Insert character *ch* with attributes *attr* before the character under the + cursor, or at ``(y, x)`` if specified. All characters to the right of the + cursor are shifted one position right, with the rightmost character on the + line being lost. The cursor position does not change. .. method:: window.insdelln(nlines) @@ -1076,9 +1148,14 @@ the following methods and attributes: window.instr(y, x[, n]) Return a bytes object of characters, extracted from the window starting at the - current cursor position, or at *y*, *x* if specified. Attributes are stripped + current cursor position, or at *y*, *x* if specified, and stopping at the end + of the line. Attributes and color information are stripped from the characters. If *n* is specified, :meth:`instr` returns a string at most *n* characters long (exclusive of the trailing NUL). + The maximum value for *n* is 2047. + + .. versionchanged:: 3.14 + The maximum value for *n* was increased from 1023 to 2047. .. method:: window.is_linetouched(line) @@ -1097,15 +1174,14 @@ the following methods and attributes: .. method:: window.keypad(flag) If *flag* is ``True``, escape sequences generated by some keys (keypad, function keys) - will be interpreted by :mod:`curses`. If *flag* is ``False``, escape sequences will be + will be interpreted by :mod:`!curses`. If *flag* is ``False``, escape sequences will be left as is in the input stream. .. method:: window.leaveok(flag) If *flag* is ``True``, cursor is left where it is on update, instead of being at "cursor - position." This reduces cursor movement where possible. If possible the cursor - will be made invisible. + position." This reduces cursor movement where possible. If *flag* is ``False``, cursor will always be at "cursor position" after an update. @@ -1126,6 +1202,9 @@ the following methods and attributes: Move the window so its upper-left corner is at ``(new_y, new_x)``. + Moving the window so that any part of it would be off the screen is an error: + the window is not moved and :exc:`curses.error` is raised. + .. method:: window.nodelay(flag) @@ -1141,11 +1220,16 @@ the following methods and attributes: .. method:: window.noutrefresh() + window.noutrefresh(pminrow, pmincol, sminrow, smincol, smaxrow, smaxcol) Mark for refresh but wait. This function updates the data structure representing the desired state of the window, but does not force an update of the physical screen. To accomplish that, call :func:`doupdate`. + The 6 arguments can only be specified, and are then required, when the window + is a pad created with :func:`newpad`; they have the same meaning as for + :meth:`refresh`. + .. method:: window.overlay(destwin[, sminrow, smincol, dminrow, dmincol, dmaxrow, dmaxcol]) @@ -1196,12 +1280,12 @@ the following methods and attributes: Update the display immediately (sync actual screen with previous drawing/deleting methods). - The 6 optional arguments can only be specified when the window is a pad created - with :func:`newpad`. The additional parameters are needed to indicate what part - of the pad and screen are involved. *pminrow* and *pmincol* specify the upper - left-hand corner of the rectangle to be displayed in the pad. *sminrow*, + The 6 arguments can only be specified, and are then required, when the window + is a pad created with :func:`newpad`. The additional parameters are needed to indicate what part + of the pad and screen are involved. *pminrow* and *pmincol* specify the + upper-left corner of the rectangle to be displayed in the pad. *sminrow*, *smincol*, *smaxrow*, and *smaxcol* specify the edges of the rectangle to be - displayed on the screen. The lower right-hand corner of the rectangle to be + displayed on the screen. The lower-right corner of the rectangle to be displayed in the pad is calculated from the screen coordinates, since the rectangles must be the same size. Both rectangles must be entirely contained within their respective structures. Negative values of *pminrow*, *pmincol*, @@ -1218,7 +1302,9 @@ the following methods and attributes: .. method:: window.scroll([lines=1]) - Scroll the screen or scrolling region upward by *lines* lines. + Scroll the screen or scrolling region. Scroll upward by *lines* lines if + *lines* is positive, or downward if it is negative. Scrolling has no effect + unless it has been enabled for the window with :meth:`scrollok`. .. method:: window.scrollok(flag) @@ -1251,15 +1337,17 @@ the following methods and attributes: .. method:: window.subpad(begin_y, begin_x) window.subpad(nlines, ncols, begin_y, begin_x) - Return a sub-window, whose upper-left corner is at ``(begin_y, begin_x)``, and - whose width/height is *ncols*/*nlines*. + Return a sub-pad, whose upper-left corner is at ``(begin_y, begin_x)``, and + whose width/height is *ncols*/*nlines*. The coordinates are relative to the + parent pad (unlike :meth:`subwin`, which uses screen coordinates). This + method is only available for pads created with :func:`newpad`. .. method:: window.subwin(begin_y, begin_x) window.subwin(nlines, ncols, begin_y, begin_x) - Return a sub-window, whose upper-left corner is at ``(begin_y, begin_x)``, and - whose width/height is *ncols*/*nlines*. + Return a sub-window, whose upper-left corner is at the screen-relative + coordinates ``(begin_y, begin_x)``, and whose width/height is *ncols*/*nlines*. By default, the sub-window will extend from the specified position to the lower right corner of the window. @@ -1323,7 +1411,7 @@ the following methods and attributes: Constants --------- -The :mod:`curses` module defines the following data members: +The :mod:`!curses` module defines the following data members: .. data:: ERR @@ -1339,7 +1427,6 @@ The :mod:`curses` module defines the following data members: .. data:: version -.. data:: __version__ A bytes object representing the current version of the module. @@ -1367,14 +1454,14 @@ The :mod:`curses` module defines the following data members: .. data:: COLS - The width of the screen, i.e., the number of columns. + The width of the screen, that is, the number of columns. It is defined only after the call to :func:`initscr`. Updated by :func:`update_lines_cols`, :func:`resizeterm` and :func:`resize_term`. .. data:: LINES - The height of the screen, i.e., the number of lines. + The height of the screen, that is, the number of lines. It is defined only after the call to :func:`initscr`. Updated by :func:`update_lines_cols`, :func:`resizeterm` and :func:`resize_term`. @@ -1677,7 +1764,7 @@ falls back on a crude printable ASCII approximation. +------------------------+------------------------------------------+ | ACS code | Meaning | +========================+==========================================+ -| .. data:: ACS_BBSS | alternate name for upper right corner | +| .. data:: ACS_BBSS | alternate name for upper-right corner | +------------------------+------------------------------------------+ | .. data:: ACS_BLOCK | solid square block | +------------------------+------------------------------------------+ @@ -1685,7 +1772,7 @@ falls back on a crude printable ASCII approximation. +------------------------+------------------------------------------+ | .. data:: ACS_BSBS | alternate name for horizontal line | +------------------------+------------------------------------------+ -| .. data:: ACS_BSSB | alternate name for upper left corner | +| .. data:: ACS_BSSB | alternate name for upper-left corner | +------------------------+------------------------------------------+ | .. data:: ACS_BSSS | alternate name for top tee | +------------------------+------------------------------------------+ @@ -1711,9 +1798,9 @@ falls back on a crude printable ASCII approximation. +------------------------+------------------------------------------+ | .. data:: ACS_LEQUAL | less-than-or-equal-to | +------------------------+------------------------------------------+ -| .. data:: ACS_LLCORNER | lower left-hand corner | +| .. data:: ACS_LLCORNER | lower-left corner | +------------------------+------------------------------------------+ -| .. data:: ACS_LRCORNER | lower right-hand corner | +| .. data:: ACS_LRCORNER | lower-right corner | +------------------------+------------------------------------------+ | .. data:: ACS_LTEE | left tee | +------------------------+------------------------------------------+ @@ -1737,13 +1824,13 @@ falls back on a crude printable ASCII approximation. +------------------------+------------------------------------------+ | .. data:: ACS_S9 | scan line 9 | +------------------------+------------------------------------------+ -| .. data:: ACS_SBBS | alternate name for lower right corner | +| .. data:: ACS_SBBS | alternate name for lower-right corner | +------------------------+------------------------------------------+ | .. data:: ACS_SBSB | alternate name for vertical line | +------------------------+------------------------------------------+ | .. data:: ACS_SBSS | alternate name for right tee | +------------------------+------------------------------------------+ -| .. data:: ACS_SSBB | alternate name for lower left corner | +| .. data:: ACS_SSBB | alternate name for lower-left corner | +------------------------+------------------------------------------+ | .. data:: ACS_SSBS | alternate name for bottom tee | +------------------------+------------------------------------------+ @@ -1757,9 +1844,9 @@ falls back on a crude printable ASCII approximation. +------------------------+------------------------------------------+ | .. data:: ACS_UARROW | up arrow | +------------------------+------------------------------------------+ -| .. data:: ACS_ULCORNER | upper left corner | +| .. data:: ACS_ULCORNER | upper-left corner | +------------------------+------------------------------------------+ -| .. data:: ACS_URCORNER | upper right corner | +| .. data:: ACS_URCORNER | upper-right corner | +------------------------+------------------------------------------+ | .. data:: ACS_VLINE | vertical line | +------------------------+------------------------------------------+ @@ -1783,7 +1870,7 @@ The following table lists mouse button constants used by :meth:`getmouse`: +----------------------------------+---------------------------------------------+ | .. data:: BUTTON_CTRL | Control was down during button state change | +----------------------------------+---------------------------------------------+ -| .. data:: BUTTON_ALT | Control was down during button state change | +| .. data:: BUTTON_ALT | Alt was down during button state change | +----------------------------------+---------------------------------------------+ .. versionchanged:: 3.10 @@ -1813,8 +1900,8 @@ The following table lists the predefined colors: +-------------------------+----------------------------+ -:mod:`curses.textpad` --- Text input widget for curses programs -=============================================================== +:mod:`!curses.textpad` --- Text input widget for curses programs +================================================================ .. module:: curses.textpad :synopsis: Emacs-like input editing in a curses window. @@ -1822,22 +1909,22 @@ The following table lists the predefined colors: .. sectionauthor:: Eric Raymond -The :mod:`curses.textpad` module provides a :class:`Textbox` class that handles +The :mod:`!curses.textpad` module provides a :class:`Textbox` class that handles elementary text editing in a curses window, supporting a set of keybindings resembling those of Emacs (thus, also of Netscape Navigator, BBedit 6.x, FrameMaker, and many other programs). The module also provides a rectangle-drawing function useful for framing text boxes or for other purposes. -The module :mod:`curses.textpad` defines the following function: +The module :mod:`!curses.textpad` defines the following function: .. function:: rectangle(win, uly, ulx, lry, lrx) Draw a rectangle. The first argument must be a window object; the remaining arguments are coordinates relative to that window. The second and third - arguments are the y and x coordinates of the upper left hand corner of the + arguments are the y and x coordinates of the upper-left corner of the rectangle to be drawn; the fourth and fifth arguments are the y and x - coordinates of the lower right hand corner. The rectangle will be drawn using + coordinates of the lower-right corner. The rectangle will be drawn using VT100/IBM PC forms characters on terminals that make this possible (including xterm and most other software terminal emulators). Otherwise it will be drawn with ASCII dashes, vertical bars, and plus signs. @@ -1851,32 +1938,36 @@ Textbox objects You can instantiate a :class:`Textbox` object as follows: -.. class:: Textbox(win) +.. class:: Textbox(win, insert_mode=False) Return a textbox widget object. The *win* argument should be a curses :ref:`window ` object in which the textbox is to - be contained. The edit cursor of the textbox is initially located at the - upper left hand corner of the containing window, with coordinates ``(0, 0)``. + be contained. If *insert_mode* is true, the textbox inserts typed + characters, shifting existing text to the right, rather than overwriting it. + The edit cursor of the textbox is initially located at the + upper-left corner of the containing window, with coordinates ``(0, 0)``. The instance's :attr:`stripspaces` flag is initially on. :class:`Textbox` objects have the following methods: - .. method:: edit([validator]) + .. method:: edit(validate=None) This is the entry point you will normally use. It accepts editing keystrokes until one of the termination keystrokes is entered. If - *validator* is supplied, it must be a function. It will be called for + *validate* is supplied, it must be a function. It will be called for each keystroke entered with the keystroke as a parameter; command dispatch - is done on the result. This method returns the window contents as a + is done on the result. If it returns a false value, the keystroke is + ignored. This method returns the window contents as a string; whether blanks in the window are included is affected by the :attr:`stripspaces` attribute. .. method:: do_command(ch) - Process a single command keystroke. Here are the supported special - keystrokes: + Process a single command keystroke. Returns ``1`` to continue editing, + or ``0`` if a termination keystroke was processed. Here are the supported + special keystrokes: +------------------+-------------------------------------------+ | Keystroke | Action | @@ -1899,7 +1990,8 @@ You can instantiate a :class:`Textbox` object as follows: | :kbd:`Control-H` | Delete character backward. | +------------------+-------------------------------------------+ | :kbd:`Control-J` | Terminate if the window is 1 line, | - | | otherwise insert newline. | + | | otherwise move to the start of the next | + | | line. | +------------------+-------------------------------------------+ | :kbd:`Control-K` | If line is blank, delete it, otherwise | | | clear to end of line. | diff --git a/Doc/library/dataclasses.rst b/Doc/library/dataclasses.rst index 72612211b43d5e..67b20b8a793855 100644 --- a/Doc/library/dataclasses.rst +++ b/Doc/library/dataclasses.rst @@ -103,12 +103,25 @@ Module contents ignored. - *eq*: If true (the default), an :meth:`~object.__eq__` method will be - generated. This method compares the class as if it were a tuple - of its fields, in order. Both instances in the comparison must - be of the identical type. + generated. - If the class already defines :meth:`!__eq__`, this parameter is - ignored. + This method compares the class by comparing each field in order. Both + instances in the comparison must be of the identical type. + + If the class already defines :meth:`!__eq__`, this parameter is ignored. + + .. versionchanged:: 3.13 + The generated ``__eq__`` method now compares each field individually + (for example, ``self.a == other.a and self.b == other.b``), rather than + comparing tuples of fields as in previous versions. + + This change makes the comparison faster but it may alter results in cases + where attributes compare equal by identity but not by value (such as + ``float('nan')``). + + In Python 3.12 and earlier, the comparison was performed by creating + tuples of the fields and comparing them (for example, + ``(self.a, self.b) == (other.a, other.b)``). - *order*: If true (the default is ``False``), :meth:`~object.__lt__`, :meth:`~object.__le__`, :meth:`~object.__gt__`, and :meth:`~object.__ge__` methods will be @@ -121,8 +134,11 @@ Module contents :meth:`!__le__`, :meth:`!__gt__`, or :meth:`!__ge__`, then :exc:`TypeError` is raised. - - *unsafe_hash*: If ``False`` (the default), a :meth:`~object.__hash__` method - is generated according to how *eq* and *frozen* are set. + - *unsafe_hash*: If true, force ``dataclasses`` to create a + :meth:`~object.__hash__` method, even though it may not be safe to do so. + Otherwise, generate a :meth:`~object.__hash__` method according to how + *eq* and *frozen* are set. + The default value is ``False``. :meth:`!__hash__` is used by built-in :meth:`hash`, and when objects are added to hashed collections such as dictionaries and sets. Having a @@ -158,9 +174,11 @@ Module contents :class:`object`, this means it will fall back to id-based hashing). - *frozen*: If true (the default is ``False``), assigning to fields will - generate an exception. This emulates read-only frozen instances. If - :meth:`~object.__setattr__` or :meth:`~object.__delattr__` is defined in the class, then - :exc:`TypeError` is raised. See the discussion below. + generate an exception. This emulates read-only frozen instances. + See the :ref:`discussion ` below. + + If :meth:`~object.__setattr__` or :meth:`~object.__delattr__` is defined in the class + and *frozen* is true, then :exc:`TypeError` is raised. - *match_args*: If true (the default is ``True``), the :attr:`~object.__match_args__` tuple will be created from the list of @@ -304,15 +322,15 @@ Module contents .. versionadded:: 3.10 - - ``doc``: optional docstring for this field. + - *doc*: optional docstring for this field. - .. versionadded:: 3.13 + .. versionadded:: 3.14 If the default value of a field is specified by a call to :func:`!field`, then the class attribute for this field will be replaced by the specified *default* value. If *default* is not provided, then the class attribute will be deleted. The intent is - that after the :func:`@dataclass ` decorator runs, the class + that after the :deco:`dataclass` decorator runs, the class attributes will all contain the default values for the fields, just as if the default value itself were specified. For example, after:: @@ -422,7 +440,7 @@ Module contents :data:`typing.Any` is used for ``type``. The values of *init*, *repr*, *eq*, *order*, *unsafe_hash*, *frozen*, *match_args*, *kw_only*, *slots*, and *weakref_slot* have - the same meaning as they do in :func:`@dataclass `. + the same meaning as they do in :deco:`dataclass`. If *module* is defined, the :attr:`!__module__` attribute of the dataclass is set to that value. @@ -430,12 +448,12 @@ Module contents The *decorator* parameter is a callable that will be used to create the dataclass. It should take the class object as a first argument and the same keyword arguments - as :func:`@dataclass `. By default, the :func:`@dataclass ` + as :deco:`dataclass`. By default, the :deco:`dataclass` function is used. This function is not strictly required, because any Python - mechanism for creating a new class with :attr:`!__annotations__` can - then apply the :func:`@dataclass ` function to convert that class to + mechanism for creating a new class with :attr:`~object.__annotations__` can + then apply the :deco:`dataclass` function to convert that class to a dataclass. This function is provided as a convenience. For example:: @@ -492,7 +510,8 @@ Module contents .. function:: is_dataclass(obj) Return ``True`` if its parameter is a dataclass (including subclasses of a - dataclass) or an instance of one, otherwise return ``False``. + dataclass, but not including :ref:`generic aliases `) + or an instance of one, otherwise return ``False``. If you need to know if a class is an instance of a dataclass (and not a dataclass itself), then add a further check for ``not @@ -564,7 +583,7 @@ Post-init processing def __post_init__(self): self.c = self.a + self.b -The :meth:`~object.__init__` method generated by :func:`@dataclass ` does not call base +The :meth:`~object.__init__` method generated by :deco:`dataclass` does not call base class :meth:`!__init__` methods. If the base class has an :meth:`!__init__` method that has to be called, it is common to call this method in a :meth:`__post_init__` method:: @@ -594,7 +613,7 @@ parameters to :meth:`!__post_init__`. Also see the warning about how Class variables --------------- -One of the few places where :func:`@dataclass ` actually inspects the type +One of the few places where :deco:`dataclass` actually inspects the type of a field is to determine if a field is a class variable as defined in :pep:`526`. It does this by checking if the type of the field is :data:`typing.ClassVar`. If a field is a ``ClassVar``, it is excluded @@ -607,7 +626,7 @@ module-level :func:`fields` function. Init-only variables ------------------- -Another place where :func:`@dataclass ` inspects a type annotation is to +Another place where :deco:`dataclass` inspects a type annotation is to determine if a field is an init-only variable. It does this by seeing if the type of a field is of type :class:`InitVar`. If a field is an :class:`InitVar`, it is considered a pseudo-field called an init-only @@ -641,7 +660,7 @@ Frozen instances ---------------- It is not possible to create truly immutable Python objects. However, -by passing ``frozen=True`` to the :func:`@dataclass ` decorator you can +by passing ``frozen=True`` to the :deco:`dataclass` decorator you can emulate immutability. In that case, dataclasses will add :meth:`~object.__setattr__` and :meth:`~object.__delattr__` methods to the class. These methods will raise a :exc:`FrozenInstanceError` when invoked. @@ -657,7 +676,7 @@ must use :meth:`!object.__setattr__`. Inheritance ----------- -When the dataclass is being created by the :func:`@dataclass ` decorator, +When the dataclass is being created by the :deco:`dataclass` decorator, it looks through all of the class's base classes in reverse MRO (that is, starting at :class:`object`) and, for each dataclass that it finds, adds the fields from that base class to an ordered mapping of fields. @@ -781,7 +800,7 @@ for :attr:`!x` when creating a class instance will share the same copy of :attr:`!x`. Because dataclasses just use normal Python class creation they also share this behavior. There is no general way for Data Classes to detect this condition. Instead, the -:func:`@dataclass ` decorator will raise a :exc:`ValueError` if it +:deco:`dataclass` decorator will raise a :exc:`ValueError` if it detects an unhashable default parameter. The assumption is that if a value is unhashable, it is mutable. This is a partial solution, but it does protect against many common errors. @@ -815,7 +834,7 @@ default value have the following special behaviors: :meth:`~object.__get__` or :meth:`!__set__` method is called rather than returning or overwriting the descriptor object. -* To determine whether a field contains a default value, :func:`@dataclass ` +* To determine whether a field contains a default value, :deco:`dataclass` will call the descriptor's :meth:`!__get__` method using its class access form: ``descriptor.__get__(obj=None, type=cls)``. If the descriptor returns a value in this case, it will be used as the diff --git a/Doc/library/datetime-inheritance.dot b/Doc/library/datetime-inheritance.dot new file mode 100644 index 00000000000000..3c6b9b4beb7ab1 --- /dev/null +++ b/Doc/library/datetime-inheritance.dot @@ -0,0 +1,31 @@ +// Used to generate datetime-inheritance.svg with Graphviz +// (https://graphviz.org/) for the datetime documentation. + +digraph { + comment="Generated with datetime-inheritance.dot" + graph [ + bgcolor="transparent" + fontnames="svg" + layout="dot" + ranksep=0.5 + nodesep=0.5 + splines=line + ] + node [ + fontname="Courier" + fontsize=14.0 + shape=box + style=rounded + margin="0.15,0.07" + ] + edge [ + arrowhead=none + ] + + object -> tzinfo + object -> timedelta + object -> time + object -> date + tzinfo -> timezone + date -> datetime +} diff --git a/Doc/library/datetime-inheritance.svg b/Doc/library/datetime-inheritance.svg new file mode 100644 index 00000000000000..e6b1cf877a574f --- /dev/null +++ b/Doc/library/datetime-inheritance.svg @@ -0,0 +1,84 @@ + + + + + + +datetime class hierarchy + + +object + +object + + + +tzinfo + +tzinfo + + + +object->tzinfo + + + + +timedelta + +timedelta + + + +object->timedelta + + + + +time + +time + + + +object->time + + + + +date + +date + + + +object->date + + + + +timezone + +timezone + + + +tzinfo->timezone + + + + +datetime + +datetime + + + +date->datetime + + + + diff --git a/Doc/library/datetime.rst b/Doc/library/datetime.rst index 1ce2013f05da2e..5e85da49e1c3b8 100644 --- a/Doc/library/datetime.rst +++ b/Doc/library/datetime.rst @@ -12,8 +12,6 @@ -------------- -.. XXX what order should the types be discussed in? - The :mod:`!datetime` module supplies classes for manipulating dates and times. While date and time arithmetic is supported, the focus of the implementation is @@ -38,13 +36,14 @@ on efficient attribute extraction for output formatting and manipulation. Third-party library with expanded time zone and parsing support. Package :pypi:`DateType` - Third-party library that introduces distinct static types to e.g. allow - :term:`static type checkers ` + Third-party library that introduces distinct static types to for example, + allow :term:`static type checkers ` to differentiate between naive and aware datetimes. + .. _datetime-naive-aware: -Aware and Naive Objects +Aware and naive objects ----------------------- Date and time objects may be categorized as "aware" or "naive" depending on @@ -65,7 +64,7 @@ understand and to work with, at the cost of ignoring some aspects of reality. For applications requiring aware objects, :class:`.datetime` and :class:`.time` objects have an optional time zone information attribute, :attr:`!tzinfo`, that -can be set to an instance of a subclass of the abstract :class:`tzinfo` class. +can be set to an instance of a subclass of the abstract :class:`!tzinfo` class. These :class:`tzinfo` objects capture information about the offset from UTC time, the time zone name, and whether daylight saving time is in effect. @@ -77,6 +76,7 @@ detail is up to the application. The rules for time adjustment across the world are more political than rational, change frequently, and there is no standard suitable for every application aside from UTC. + Constants --------- @@ -93,13 +93,15 @@ The :mod:`!datetime` module exports the following constants: The largest year number allowed in a :class:`date` or :class:`.datetime` object. :const:`MAXYEAR` is 9999. + .. data:: UTC Alias for the UTC time zone singleton :attr:`datetime.timezone.utc`. .. versionadded:: 3.11 -Available Types + +Available types --------------- .. class:: date @@ -142,6 +144,7 @@ Available Types time adjustment (for example, to account for time zone and/or daylight saving time). + .. class:: timezone :noindex: @@ -150,19 +153,19 @@ Available Types .. versionadded:: 3.2 + Objects of these types are immutable. -Subclass relationships:: +Subclass relationships: + +.. figure:: datetime-inheritance.svg + :class: invert-in-dark-mode + :align: center + :alt: timedelta, tzinfo, time, and date inherit from object; timezone inherits + from tzinfo; and datetime inherits from date. - object - timedelta - tzinfo - timezone - time - date - datetime -Common Properties +Common properties ^^^^^^^^^^^^^^^^^ The :class:`date`, :class:`.datetime`, :class:`.time`, and :class:`timezone` types @@ -173,7 +176,8 @@ share these common features: dictionary keys. - Objects of these types support efficient pickling via the :mod:`pickle` module. -Determining if an Object is Aware or Naive + +Determining if an object is aware or naive ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Objects of the :class:`date` type are always naive. @@ -197,10 +201,11 @@ Otherwise, ``t`` is naive. The distinction between aware and naive doesn't apply to :class:`timedelta` objects. + .. _datetime-timedelta: -:class:`timedelta` Objects --------------------------- +:class:`!timedelta` objects +--------------------------- A :class:`timedelta` object represents a duration, the difference between two :class:`.datetime` or :class:`date` instances. @@ -229,8 +234,8 @@ A :class:`timedelta` object represents a duration, the difference between two *days*, *seconds* and *microseconds* are "merged" and normalized into those three resulting attributes:: - >>> from datetime import timedelta - >>> delta = timedelta( + >>> import datetime as dt + >>> delta = dt.timedelta( ... days=50, ... seconds=27, ... microseconds=10, @@ -243,6 +248,12 @@ A :class:`timedelta` object represents a duration, the difference between two >>> delta datetime.timedelta(days=64, seconds=29156, microseconds=10) + .. tip:: + ``import datetime as dt`` instead of ``import datetime`` or + ``from datetime import datetime`` to avoid confusion between the module + and the class. See `How I Import Python’s datetime Module + `__. + If any argument is a float and there are fractional microseconds, the fractional microseconds left over from all arguments are combined and their sum is rounded to the nearest microsecond using @@ -256,11 +267,27 @@ A :class:`timedelta` object represents a duration, the difference between two Note that normalization of negative values may be surprising at first. For example:: - >>> from datetime import timedelta - >>> d = timedelta(microseconds=-1) + >>> import datetime as dt + >>> d = dt.timedelta(microseconds=-1) >>> (d.days, d.seconds, d.microseconds) (-1, 86399, 999999) + Since the string representation of :class:`!timedelta` objects can be confusing, + use the following recipe to produce a more readable format: + + .. code-block:: pycon + + >>> def pretty_timedelta(td): + ... if td.days >= 0: + ... return str(td) + ... return f'-({-td!s})' + ... + >>> d = timedelta(hours=-1) + >>> str(d) # not human-friendly + '-1 day, 23:00:00' + >>> pretty_timedelta(d) + '-(1:00:00)' + Class attributes: @@ -280,6 +307,7 @@ Class attributes: The smallest possible difference between non-equal :class:`timedelta` objects, ``timedelta(microseconds=1)``. + Note that, because of normalization, ``timedelta.max`` is greater than ``-timedelta.min``. ``-timedelta.max`` is not representable as a :class:`timedelta` object. @@ -303,13 +331,14 @@ Instance attributes (read-only): .. doctest:: - >>> from datetime import timedelta - >>> duration = timedelta(seconds=11235813) + >>> import datetime as dt + >>> duration = dt.timedelta(seconds=11235813) >>> duration.days, duration.seconds (130, 3813) >>> duration.total_seconds() 11235813.0 + .. attribute:: timedelta.microseconds Between 0 and 999,999 inclusive. @@ -317,8 +346,6 @@ Instance attributes (read-only): Supported operations: -.. XXX this table is too wide! - +--------------------------------+-----------------------------------------------+ | Operation | Result | +================================+===============================================+ @@ -380,7 +407,6 @@ Supported operations: | | call with canonical attribute values. | +--------------------------------+-----------------------------------------------+ - Notes: (1) @@ -416,9 +442,9 @@ objects (see below). .. versionchanged:: 3.2 Floor division and true division of a :class:`timedelta` object by another - :class:`timedelta` object are now supported, as are remainder operations and + :class:`!timedelta` object are now supported, as are remainder operations and the :func:`divmod` function. True division and multiplication of a - :class:`timedelta` object by a :class:`float` object are now supported. + :class:`!timedelta` object by a :class:`float` object are now supported. :class:`timedelta` objects support equality and order comparisons. @@ -431,23 +457,24 @@ Instance methods: Return the total number of seconds contained in the duration. Equivalent to ``td / timedelta(seconds=1)``. For interval units other than seconds, use the - division form directly (e.g. ``td / timedelta(microseconds=1)``). + division form directly (for example, ``td / timedelta(microseconds=1)``). Note that for very large time intervals (greater than 270 years on most platforms) this method will lose microsecond accuracy. .. versionadded:: 3.2 -Examples of usage: :class:`timedelta` -^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Examples of usage: :class:`!timedelta` +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ An additional example of normalization:: >>> # Components of another_year add up to exactly 365 days - >>> from datetime import timedelta - >>> year = timedelta(days=365) - >>> another_year = timedelta(weeks=40, days=84, hours=23, - ... minutes=50, seconds=600) + >>> import datetime as dt + >>> year = dt.timedelta(days=365) + >>> another_year = dt.timedelta(weeks=40, days=84, hours=23, + ... minutes=50, seconds=600) >>> year == another_year True >>> year.total_seconds() @@ -455,8 +482,8 @@ An additional example of normalization:: Examples of :class:`timedelta` arithmetic:: - >>> from datetime import timedelta - >>> year = timedelta(days=365) + >>> import datetime as dt + >>> year = dt.timedelta(days=365) >>> ten_years = 10 * year >>> ten_years datetime.timedelta(days=3650) @@ -469,10 +496,11 @@ Examples of :class:`timedelta` arithmetic:: >>> three_years, three_years.days // 365 (datetime.timedelta(days=1095), 3) + .. _datetime-date: -:class:`date` Objects ---------------------- +:class:`!date` objects +---------------------- A :class:`date` object represents a date (year, month and day) in an idealized calendar, the current Gregorian calendar indefinitely extended in both @@ -501,9 +529,10 @@ Other constructors, all class methods: This is equivalent to ``date.fromtimestamp(time.time())``. + .. classmethod:: date.fromtimestamp(timestamp) - Return the local date corresponding to the POSIX timestamp, such as is + Return the local date corresponding to the POSIX *timestamp*, such as is returned by :func:`time.time`. This may raise :exc:`OverflowError`, if the timestamp is out @@ -522,7 +551,7 @@ Other constructors, all class methods: .. classmethod:: date.fromordinal(ordinal) - Return the date corresponding to the proleptic Gregorian ordinal, where + Return the date corresponding to the proleptic Gregorian *ordinal*, where January 1 of year 1 has ordinal 1. :exc:`ValueError` is raised unless ``1 <= ordinal <= @@ -543,25 +572,27 @@ Other constructors, all class methods: Examples:: - >>> from datetime import date - >>> date.fromisoformat('2019-12-04') + >>> import datetime as dt + >>> dt.date.fromisoformat('2019-12-04') datetime.date(2019, 12, 4) - >>> date.fromisoformat('20191204') + >>> dt.date.fromisoformat('20191204') datetime.date(2019, 12, 4) - >>> date.fromisoformat('2021-W01-1') + >>> dt.date.fromisoformat('2021-W01-1') datetime.date(2021, 1, 4) .. versionadded:: 3.7 .. versionchanged:: 3.11 Previously, this method only supported the format ``YYYY-MM-DD``. + .. classmethod:: date.fromisocalendar(year, week, day) Return a :class:`date` corresponding to the ISO calendar date specified by - year, week and day. This is the inverse of the function :meth:`date.isocalendar`. + *year*, *week* and *day*. This is the inverse of the function :meth:`date.isocalendar`. .. versionadded:: 3.8 + .. classmethod:: date.strptime(date_string, format) Return a :class:`.date` corresponding to *date_string*, parsed according to @@ -587,9 +618,9 @@ Other constructors, all class methods: .. doctest:: - >>> from datetime import date + >>> import datetime as dt >>> date_string = "02/29" - >>> when = date.strptime(f"{date_string};1984", "%m/%d;%Y") # Avoids leap year bug. + >>> when = dt.date.strptime(f"{date_string};1984", "%m/%d;%Y") # Avoids leap year bug. >>> when.strftime("%B %d") # doctest: +SKIP 'February 29' @@ -681,7 +712,7 @@ Notes: In other words, ``date1 < date2`` if and only if ``date1.toordinal() < date2.toordinal()``. - Order comparison between a :class:`!date` object that is not also a + Order comparison between a :class:`date` object that is not also a :class:`.datetime` instance and a :class:`!datetime` object raises :exc:`TypeError`. @@ -704,8 +735,8 @@ Instance methods: Example:: - >>> from datetime import date - >>> d = date(2002, 12, 31) + >>> import datetime as dt + >>> d = dt.date(2002, 12, 31) >>> d.replace(day=26) datetime.date(2002, 12, 26) @@ -763,23 +794,25 @@ Instance methods: For example, 2004 begins on a Thursday, so the first week of ISO year 2004 begins on Monday, 29 Dec 2003 and ends on Sunday, 4 Jan 2004:: - >>> from datetime import date - >>> date(2003, 12, 29).isocalendar() + >>> import datetime as dt + >>> dt.date(2003, 12, 29).isocalendar() datetime.IsoCalendarDate(year=2004, week=1, weekday=1) - >>> date(2004, 1, 4).isocalendar() + >>> dt.date(2004, 1, 4).isocalendar() datetime.IsoCalendarDate(year=2004, week=1, weekday=7) .. versionchanged:: 3.9 Result changed from a tuple to a :term:`named tuple`. + .. method:: date.isoformat() Return a string representing the date in ISO 8601 format, ``YYYY-MM-DD``:: - >>> from datetime import date - >>> date(2002, 12, 4).isoformat() + >>> import datetime as dt + >>> dt.date(2002, 12, 4).isoformat() '2002-12-04' + .. method:: date.__str__() For a date ``d``, ``str(d)`` is equivalent to ``d.isoformat()``. @@ -789,8 +822,8 @@ Instance methods: Return a string representing the date:: - >>> from datetime import date - >>> date(2002, 12, 4).ctime() + >>> import datetime as dt + >>> dt.date(2002, 12, 4).ctime() 'Wed Dec 4 00:00:00 2002' ``d.ctime()`` is equivalent to:: @@ -816,19 +849,20 @@ Instance methods: literals ` and when using :meth:`str.format`. See also :ref:`strftime-strptime-behavior` and :meth:`date.isoformat`. -Examples of Usage: :class:`date` -^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Examples of usage: :class:`!date` +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Example of counting days to an event:: >>> import time - >>> from datetime import date - >>> today = date.today() + >>> import datetime as dt + >>> today = dt.date.today() >>> today datetime.date(2007, 12, 5) - >>> today == date.fromtimestamp(time.time()) + >>> today == dt.date.fromtimestamp(time.time()) True - >>> my_birthday = date(today.year, 6, 24) + >>> my_birthday = dt.date(today.year, 6, 24) >>> if my_birthday < today: ... my_birthday = my_birthday.replace(year=today.year + 1) ... @@ -842,8 +876,8 @@ More examples of working with :class:`date`: .. doctest:: - >>> from datetime import date - >>> d = date.fromordinal(730920) # 730920th day after 1. 1. 0001 + >>> import datetime as dt + >>> d = dt.date.fromordinal(730920) # 730920th day after 1. 1. 0001 >>> d datetime.date(2002, 3, 11) @@ -859,7 +893,7 @@ More examples of working with :class:`date`: >>> 'The {1} is {0:%d}, the {2} is {0:%B}.'.format(d, "day", "month") 'The day is 11, the month is March.' - >>> # Methods for to extracting 'components' under different calendars + >>> # Methods for extracting 'components' under different calendars >>> t = d.timetuple() >>> for i in t: # doctest: +SKIP ... print(i) @@ -886,7 +920,7 @@ More examples of working with :class:`date`: .. _datetime-datetime: -:class:`.datetime` Objects +:class:`!datetime` objects -------------------------- A :class:`.datetime` object is a single object containing all the information @@ -894,7 +928,7 @@ from a :class:`date` object and a :class:`.time` object. Like a :class:`date` object, :class:`.datetime` assumes the current Gregorian calendar extended in both directions; like a :class:`.time` object, -:class:`.datetime` assumes there are exactly 3600\*24 seconds in every day. +:class:`!datetime` assumes there are exactly 3600\*24 seconds in every day. Constructor: @@ -918,6 +952,7 @@ Constructor: .. versionchanged:: 3.6 Added the *fold* parameter. + Other constructors, all class methods: .. classmethod:: datetime.today() @@ -933,6 +968,7 @@ Other constructors, all class methods: This method is functionally equivalent to :meth:`now`, but without a ``tz`` parameter. + .. classmethod:: datetime.now(tz=None) Return the current local date and time. @@ -953,6 +989,7 @@ Other constructors, all class methods: Subsequent calls to :meth:`!datetime.now` may return the same instant depending on the precision of the underlying clock. + .. classmethod:: datetime.utcnow() Return the current UTC date and time, with :attr:`.tzinfo` ``None``. @@ -1040,6 +1077,9 @@ Other constructors, all class methods: :c:func:`gmtime` function. Raise :exc:`OSError` instead of :exc:`ValueError` on :c:func:`gmtime` failure. + .. versionchanged:: 3.15 + Accepts any real number as *timestamp*, not only integer or float. + .. deprecated:: 3.12 Use :meth:`datetime.fromtimestamp` with :const:`UTC` instead. @@ -1060,7 +1100,7 @@ Other constructors, all class methods: are equal to the given :class:`.time` object's. If the *tzinfo* argument is provided, its value is used to set the :attr:`.tzinfo` attribute of the result, otherwise the :attr:`~.time.tzinfo` attribute of the *time* argument - is used. If the *date* argument is a :class:`.datetime` object, its time components + is used. If the *date* argument is a :class:`!datetime` object, its time components and :attr:`.tzinfo` attributes are ignored. For any :class:`.datetime` object ``d``, @@ -1086,24 +1126,24 @@ Other constructors, all class methods: Examples:: - >>> from datetime import datetime - >>> datetime.fromisoformat('2011-11-04') + >>> import datetime as dt + >>> dt.datetime.fromisoformat('2011-11-04') datetime.datetime(2011, 11, 4, 0, 0) - >>> datetime.fromisoformat('20111104') + >>> dt.datetime.fromisoformat('20111104') datetime.datetime(2011, 11, 4, 0, 0) - >>> datetime.fromisoformat('2011-11-04T00:05:23') + >>> dt.datetime.fromisoformat('2011-11-04T00:05:23') datetime.datetime(2011, 11, 4, 0, 5, 23) - >>> datetime.fromisoformat('2011-11-04T00:05:23Z') + >>> dt.datetime.fromisoformat('2011-11-04T00:05:23Z') datetime.datetime(2011, 11, 4, 0, 5, 23, tzinfo=datetime.timezone.utc) - >>> datetime.fromisoformat('20111104T000523') + >>> dt.datetime.fromisoformat('20111104T000523') datetime.datetime(2011, 11, 4, 0, 5, 23) - >>> datetime.fromisoformat('2011-W01-2T00:05:23.283') + >>> dt.datetime.fromisoformat('2011-W01-2T00:05:23.283') datetime.datetime(2011, 1, 4, 0, 5, 23, 283000) - >>> datetime.fromisoformat('2011-11-04 00:05:23.283') + >>> dt.datetime.fromisoformat('2011-11-04 00:05:23.283') datetime.datetime(2011, 11, 4, 0, 5, 23, 283000) - >>> datetime.fromisoformat('2011-11-04 00:05:23.283+00:00') + >>> dt.datetime.fromisoformat('2011-11-04 00:05:23.283+00:00') datetime.datetime(2011, 11, 4, 0, 5, 23, 283000, tzinfo=datetime.timezone.utc) - >>> datetime.fromisoformat('2011-11-04T00:05:23+04:00') # doctest: +NORMALIZE_WHITESPACE + >>> dt.datetime.fromisoformat('2011-11-04T00:05:23+04:00') # doctest: +NORMALIZE_WHITESPACE datetime.datetime(2011, 11, 4, 0, 5, 23, tzinfo=datetime.timezone(datetime.timedelta(seconds=14400))) @@ -1116,12 +1156,13 @@ Other constructors, all class methods: .. classmethod:: datetime.fromisocalendar(year, week, day) Return a :class:`.datetime` corresponding to the ISO calendar date specified - by year, week and day. The non-date components of the datetime are populated + by *year*, *week* and *day*. The non-date components of the datetime are populated with their normal default values. This is the inverse of the function :meth:`datetime.isocalendar`. .. versionadded:: 3.8 + .. classmethod:: datetime.strptime(date_string, format) Return a :class:`.datetime` corresponding to *date_string*, parsed according to @@ -1149,9 +1190,9 @@ Other constructors, all class methods: .. doctest:: - >>> from datetime import datetime + >>> import datetime as dt >>> date_string = "02/29" - >>> when = datetime.strptime(f"{date_string};1984", "%m/%d;%Y") # Avoids leap year bug. + >>> when = dt.datetime.strptime(f"{date_string};1984", "%m/%d;%Y") # Avoids leap year bug. >>> when.strftime("%B %d") # doctest: +SKIP 'February 29' @@ -1229,6 +1270,7 @@ Instance attributes (read-only): .. versionadded:: 3.6 + Supported operations: +---------------------------------------+--------------------------------+ @@ -1264,7 +1306,7 @@ Supported operations: datetime, and no time zone adjustments are done even if the input is aware. (3) - Subtraction of a :class:`.datetime` from a :class:`.datetime` is defined only if + Subtraction of a :class:`.datetime` from a :class:`!datetime` is defined only if both operands are naive, or if both are aware. If one is aware and the other is naive, :exc:`TypeError` is raised. @@ -1282,7 +1324,7 @@ Supported operations: :class:`.datetime` objects are equal if they represent the same date and time, taking into account the time zone. - Naive and aware :class:`!datetime` objects are never equal. + Naive and aware :class:`.datetime` objects are never equal. If both comparands are aware, and have the same :attr:`!tzinfo` attribute, the :attr:`!tzinfo` and :attr:`~.datetime.fold` attributes are ignored and @@ -1290,7 +1332,7 @@ Supported operations: If both comparands are aware and have different :attr:`~.datetime.tzinfo` attributes, the comparison acts as comparands were first converted to UTC datetimes except that the implementation never overflows. - :class:`!datetime` instances in a repeated interval are never equal to + :class:`.datetime` instances in a repeated interval are never equal to :class:`!datetime` instances in other time zone. (5) @@ -1319,6 +1361,7 @@ Supported operations: The default behavior can be changed by overriding the special comparison methods in subclasses. + Instance methods: .. method:: datetime.date() @@ -1474,11 +1517,13 @@ Instance methods: ``datetime.replace(tzinfo=timezone.utc)`` to make it aware, at which point you can use :meth:`.datetime.timetuple`. + .. method:: datetime.toordinal() Return the proleptic Gregorian ordinal of the date. The same as ``self.date().toordinal()``. + .. method:: datetime.timestamp() Return POSIX timestamp corresponding to the :class:`.datetime` @@ -1486,23 +1531,17 @@ Instance methods: returned by :func:`time.time`. Naive :class:`.datetime` instances are assumed to represent local - time and this method relies on the platform C :c:func:`mktime` - function to perform the conversion. Since :class:`.datetime` - supports wider range of values than :c:func:`mktime` on many - platforms, this method may raise :exc:`OverflowError` or :exc:`OSError` - for times far in the past or far in the future. + time and this method relies on platform C functions to perform + the conversion. Since :class:`!datetime` supports a wider range of + values than the platform C functions on many platforms, this + method may raise :exc:`OverflowError` or :exc:`OSError` for times + far in the past or far in the future. For aware :class:`.datetime` instances, the return value is computed as:: (dt - datetime(1970, 1, 1, tzinfo=timezone.utc)).total_seconds() - .. versionadded:: 3.3 - - .. versionchanged:: 3.6 - The :meth:`timestamp` method uses the :attr:`.fold` attribute to - disambiguate the times during a repeated interval. - .. note:: There is no method to obtain the POSIX timestamp directly from a @@ -1517,6 +1556,17 @@ Instance methods: timestamp = (dt - datetime(1970, 1, 1)) / timedelta(seconds=1) + .. versionadded:: 3.3 + + .. versionchanged:: 3.6 + The :meth:`timestamp` method uses the :attr:`.fold` attribute to + disambiguate the times during a repeated interval. + + .. versionchanged:: 3.6 + This method no longer relies on the platform C :c:func:`mktime` + function to perform conversions. + + .. method:: datetime.weekday() Return the day of the week as an integer, where Monday is 0 and Sunday is 6. @@ -1552,24 +1602,24 @@ Instance methods: Examples:: - >>> from datetime import datetime, timezone - >>> datetime(2019, 5, 18, 15, 17, 8, 132263).isoformat() + >>> import datetime as dt + >>> dt.datetime(2019, 5, 18, 15, 17, 8, 132263).isoformat() '2019-05-18T15:17:08.132263' - >>> datetime(2019, 5, 18, 15, 17, tzinfo=timezone.utc).isoformat() + >>> dt.datetime(2019, 5, 18, 15, 17, tzinfo=dt.timezone.utc).isoformat() '2019-05-18T15:17:00+00:00' The optional argument *sep* (default ``'T'``) is a one-character separator, placed between the date and time portions of the result. For example:: - >>> from datetime import tzinfo, timedelta, datetime - >>> class TZ(tzinfo): + >>> import datetime as dt + >>> class TZ(dt.tzinfo): ... """A time zone with an arbitrary, constant -06:39 offset.""" - ... def utcoffset(self, dt): - ... return timedelta(hours=-6, minutes=-39) + ... def utcoffset(self, when): + ... return dt.timedelta(hours=-6, minutes=-39) ... - >>> datetime(2002, 12, 25, tzinfo=TZ()).isoformat(' ') + >>> dt.datetime(2002, 12, 25, tzinfo=TZ()).isoformat(' ') '2002-12-25 00:00:00-06:39' - >>> datetime(2009, 11, 27, microsecond=100, tzinfo=TZ()).isoformat() + >>> dt.datetime(2009, 11, 27, microsecond=100, tzinfo=TZ()).isoformat() '2009-11-27T00:00:00.000100-06:39' The optional argument *timespec* specifies the number of additional @@ -1593,11 +1643,11 @@ Instance methods: :exc:`ValueError` will be raised on an invalid *timespec* argument:: - >>> from datetime import datetime - >>> datetime.now().isoformat(timespec='minutes') # doctest: +SKIP + >>> import datetime as dt + >>> dt.datetime.now().isoformat(timespec='minutes') # doctest: +SKIP '2002-12-25T00:00' - >>> dt = datetime(2015, 1, 1, 12, 30, 59, 0) - >>> dt.isoformat(timespec='microseconds') + >>> my_datetime = dt.datetime(2015, 1, 1, 12, 30, 59, 0) + >>> my_datetime.isoformat(timespec='microseconds') '2015-01-01T12:30:59.000000' .. versionchanged:: 3.6 @@ -1614,8 +1664,8 @@ Instance methods: Return a string representing the date and time:: - >>> from datetime import datetime - >>> datetime(2002, 12, 4, 20, 30, 40).ctime() + >>> import datetime as dt + >>> dt.datetime(2002, 12, 4, 20, 30, 40).ctime() 'Wed Dec 4 20:30:40 2002' The output string will *not* include time zone information, regardless @@ -1645,34 +1695,34 @@ Instance methods: See also :ref:`strftime-strptime-behavior` and :meth:`datetime.isoformat`. -Examples of Usage: :class:`.datetime` +Examples of usage: :class:`!datetime` ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Examples of working with :class:`.datetime` objects: .. doctest:: - >>> from datetime import datetime, date, time, timezone + >>> import datetime as dt >>> # Using datetime.combine() - >>> d = date(2005, 7, 14) - >>> t = time(12, 30) - >>> datetime.combine(d, t) + >>> d = dt.date(2005, 7, 14) + >>> t = dt.time(12, 30) + >>> dt.datetime.combine(d, t) datetime.datetime(2005, 7, 14, 12, 30) >>> # Using datetime.now() - >>> datetime.now() # doctest: +SKIP + >>> dt.datetime.now() # doctest: +SKIP datetime.datetime(2007, 12, 6, 16, 29, 43, 79043) # GMT +1 - >>> datetime.now(timezone.utc) # doctest: +SKIP + >>> dt.datetime.now(dt.timezone.utc) # doctest: +SKIP datetime.datetime(2007, 12, 6, 15, 29, 43, 79060, tzinfo=datetime.timezone.utc) >>> # Using datetime.strptime() - >>> dt = datetime.strptime("21/11/06 16:30", "%d/%m/%y %H:%M") - >>> dt + >>> my_datetime = dt.datetime.strptime("21/11/06 16:30", "%d/%m/%y %H:%M") + >>> my_datetime datetime.datetime(2006, 11, 21, 16, 30) >>> # Using datetime.timetuple() to get tuple of all attributes - >>> tt = dt.timetuple() + >>> tt = my_datetime.timetuple() >>> for it in tt: # doctest: +SKIP ... print(it) ... @@ -1687,7 +1737,7 @@ Examples of working with :class:`.datetime` objects: -1 # dst - method tzinfo.dst() returned None >>> # Date in ISO format - >>> ic = dt.isocalendar() + >>> ic = my_datetime.isocalendar() >>> for it in ic: # doctest: +SKIP ... print(it) ... @@ -1696,55 +1746,55 @@ Examples of working with :class:`.datetime` objects: 2 # ISO weekday >>> # Formatting a datetime - >>> dt.strftime("%A, %d. %B %Y %I:%M%p") + >>> my_datetime.strftime("%A, %d. %B %Y %I:%M%p") 'Tuesday, 21. November 2006 04:30PM' - >>> 'The {1} is {0:%d}, the {2} is {0:%B}, the {3} is {0:%I:%M%p}.'.format(dt, "day", "month", "time") + >>> 'The {1} is {0:%d}, the {2} is {0:%B}, the {3} is {0:%I:%M%p}.'.format(my_datetime, "day", "month", "time") 'The day is 21, the month is November, the time is 04:30PM.' The example below defines a :class:`tzinfo` subclass capturing time zone information for Kabul, Afghanistan, which used +4 UTC until 1945 and then +4:30 UTC thereafter:: - from datetime import timedelta, datetime, tzinfo, timezone + import datetime as dt - class KabulTz(tzinfo): + class KabulTz(dt.tzinfo): # Kabul used +4 until 1945, when they moved to +4:30 - UTC_MOVE_DATE = datetime(1944, 12, 31, 20, tzinfo=timezone.utc) + UTC_MOVE_DATE = dt.datetime(1944, 12, 31, 20, tzinfo=dt.timezone.utc) - def utcoffset(self, dt): - if dt.year < 1945: - return timedelta(hours=4) - elif (1945, 1, 1, 0, 0) <= dt.timetuple()[:5] < (1945, 1, 1, 0, 30): + def utcoffset(self, when): + if when.year < 1945: + return dt.timedelta(hours=4) + elif (1945, 1, 1, 0, 0) <= when.timetuple()[:5] < (1945, 1, 1, 0, 30): # An ambiguous ("imaginary") half-hour range representing # a 'fold' in time due to the shift from +4 to +4:30. - # If dt falls in the imaginary range, use fold to decide how - # to resolve. See PEP495. - return timedelta(hours=4, minutes=(30 if dt.fold else 0)) + # If when falls in the imaginary range, use fold to decide how + # to resolve. See PEP 495. + return dt.timedelta(hours=4, minutes=(30 if when.fold else 0)) else: - return timedelta(hours=4, minutes=30) + return dt.timedelta(hours=4, minutes=30) - def fromutc(self, dt): + def fromutc(self, when): # Follow same validations as in datetime.tzinfo - if not isinstance(dt, datetime): + if not isinstance(when, dt.datetime): raise TypeError("fromutc() requires a datetime argument") - if dt.tzinfo is not self: - raise ValueError("dt.tzinfo is not self") + if when.tzinfo is not self: + raise ValueError("when.tzinfo is not self") # A custom implementation is required for fromutc as # the input to this function is a datetime with utc values # but with a tzinfo set to self. # See datetime.astimezone or fromtimestamp. - if dt.replace(tzinfo=timezone.utc) >= self.UTC_MOVE_DATE: - return dt + timedelta(hours=4, minutes=30) + if when.replace(tzinfo=dt.timezone.utc) >= self.UTC_MOVE_DATE: + return when + dt.timedelta(hours=4, minutes=30) else: - return dt + timedelta(hours=4) + return when + dt.timedelta(hours=4) - def dst(self, dt): + def dst(self, when): # Kabul does not observe daylight saving time. - return timedelta(0) + return dt.timedelta(0) - def tzname(self, dt): - if dt >= self.UTC_MOVE_DATE: + def tzname(self, when): + if when >= self.UTC_MOVE_DATE: return "+04:30" return "+04" @@ -1753,17 +1803,17 @@ Usage of ``KabulTz`` from above:: >>> tz1 = KabulTz() >>> # Datetime before the change - >>> dt1 = datetime(1900, 11, 21, 16, 30, tzinfo=tz1) + >>> dt1 = dt.datetime(1900, 11, 21, 16, 30, tzinfo=tz1) >>> print(dt1.utcoffset()) 4:00:00 >>> # Datetime after the change - >>> dt2 = datetime(2006, 6, 14, 13, 0, tzinfo=tz1) + >>> dt2 = dt.datetime(2006, 6, 14, 13, 0, tzinfo=tz1) >>> print(dt2.utcoffset()) 4:30:00 >>> # Convert datetime to another time zone - >>> dt3 = dt2.astimezone(timezone.utc) + >>> dt3 = dt2.astimezone(dt.timezone.utc) >>> dt3 datetime.datetime(2006, 6, 14, 8, 30, tzinfo=datetime.timezone.utc) >>> dt2 @@ -1771,9 +1821,10 @@ Usage of ``KabulTz`` from above:: >>> dt2 == dt3 True + .. _datetime-time: -:class:`.time` Objects +:class:`!time` objects ---------------------- A :class:`.time` object represents a (local) time of day, independent of any particular @@ -1794,6 +1845,7 @@ day, and subject to adjustment via a :class:`tzinfo` object. If an argument outside those ranges is given, :exc:`ValueError` is raised. All default to 0 except *tzinfo*, which defaults to ``None``. + Class attributes: @@ -1852,6 +1904,7 @@ Instance attributes (read-only): .. versionadded:: 3.6 + :class:`.time` objects support equality and order comparisons, where ``a`` is considered less than ``b`` when ``a`` precedes ``b`` in time. @@ -1874,8 +1927,8 @@ In Boolean contexts, a :class:`.time` object is always considered to be true. .. versionchanged:: 3.5 Before Python 3.5, a :class:`.time` object was considered to be false if it represented midnight in UTC. This behavior was considered obscure and - error-prone and has been removed in Python 3.5. See :issue:`13936` for full - details. + error-prone and has been removed in Python 3.5. See :issue:`13936` for more + information. Other constructors: @@ -1896,22 +1949,22 @@ Other constructors: .. doctest:: - >>> from datetime import time - >>> time.fromisoformat('04:23:01') + >>> import datetime as dt + >>> dt.time.fromisoformat('04:23:01') datetime.time(4, 23, 1) - >>> time.fromisoformat('T04:23:01') + >>> dt.time.fromisoformat('T04:23:01') datetime.time(4, 23, 1) - >>> time.fromisoformat('T042301') + >>> dt.time.fromisoformat('T042301') datetime.time(4, 23, 1) - >>> time.fromisoformat('04:23:01.000384') + >>> dt.time.fromisoformat('04:23:01.000384') datetime.time(4, 23, 1, 384) - >>> time.fromisoformat('04:23:01,000384') + >>> dt.time.fromisoformat('04:23:01,000384') datetime.time(4, 23, 1, 384) - >>> time.fromisoformat('04:23:01+04:00') + >>> dt.time.fromisoformat('04:23:01+04:00') datetime.time(4, 23, 1, tzinfo=datetime.timezone(datetime.timedelta(seconds=14400))) - >>> time.fromisoformat('04:23:01Z') + >>> dt.time.fromisoformat('04:23:01Z') datetime.time(4, 23, 1, tzinfo=datetime.timezone.utc) - >>> time.fromisoformat('04:23:01+00:00') + >>> dt.time.fromisoformat('04:23:01+00:00') datetime.time(4, 23, 1, tzinfo=datetime.timezone.utc) @@ -1920,6 +1973,7 @@ Other constructors: Previously, this method only supported formats that could be emitted by :meth:`time.isoformat`. + .. classmethod:: time.strptime(date_string, format) Return a :class:`.time` corresponding to *date_string*, parsed according to @@ -1944,7 +1998,7 @@ Instance methods: Return a new :class:`.time` with the same values, but with specified parameters updated. Note that ``tzinfo=None`` can be specified to create a - naive :class:`.time` from an aware :class:`.time`, without conversion of the + naive :class:`!time` from an aware :class:`!time`, without conversion of the time data. :class:`.time` objects are also supported by generic function @@ -1985,13 +2039,13 @@ Instance methods: Example:: - >>> from datetime import time - >>> time(hour=12, minute=34, second=56, microsecond=123456).isoformat(timespec='minutes') + >>> import datetime as dt + >>> dt.time(hour=12, minute=34, second=56, microsecond=123456).isoformat(timespec='minutes') '12:34' - >>> dt = time(hour=12, minute=34, second=56, microsecond=0) - >>> dt.isoformat(timespec='microseconds') + >>> my_time = dt.time(hour=12, minute=34, second=56, microsecond=0) + >>> my_time.isoformat(timespec='microseconds') '12:34:56.000000' - >>> dt.isoformat(timespec='auto') + >>> my_time.isoformat(timespec='auto') '12:34:56' .. versionchanged:: 3.6 @@ -2036,29 +2090,31 @@ Instance methods: .. versionchanged:: 3.7 The DST offset is not restricted to a whole number of minutes. + .. method:: time.tzname() If :attr:`.tzinfo` is ``None``, returns ``None``, else returns ``self.tzinfo.tzname(None)``, or raises an exception if the latter doesn't return ``None`` or a string object. -Examples of Usage: :class:`.time` + +Examples of usage: :class:`!time` ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Examples of working with a :class:`.time` object:: - >>> from datetime import time, tzinfo, timedelta - >>> class TZ1(tzinfo): - ... def utcoffset(self, dt): - ... return timedelta(hours=1) - ... def dst(self, dt): - ... return timedelta(0) - ... def tzname(self,dt): + >>> import datetime as dt + >>> class TZ1(dt.tzinfo): + ... def utcoffset(self, when): + ... return dt.timedelta(hours=1) + ... def dst(self, when): + ... return dt.timedelta(0) + ... def tzname(self, when): ... return "+01:00" ... def __repr__(self): ... return f"{self.__class__.__name__}()" ... - >>> t = time(12, 10, 30, tzinfo=TZ1()) + >>> t = dt.time(12, 10, 30, tzinfo=TZ1()) >>> t datetime.time(12, 10, 30, tzinfo=TZ1()) >>> t.isoformat() @@ -2075,25 +2131,25 @@ Examples of working with a :class:`.time` object:: .. _datetime-tzinfo: -:class:`tzinfo` Objects ------------------------ +:class:`!tzinfo` objects +------------------------ .. class:: tzinfo() - This is an abstract base class, meaning that this class should not be + This is an :term:`abstract base class`, meaning that this class should not be instantiated directly. Define a subclass of :class:`tzinfo` to capture information about a particular time zone. An instance of (a concrete subclass of) :class:`tzinfo` can be passed to the constructors for :class:`.datetime` and :class:`.time` objects. The latter objects - view their attributes as being in local time, and the :class:`tzinfo` object + view their attributes as being in local time, and the :class:`!tzinfo` object supports methods revealing offset of local time from UTC, the name of the time zone, and DST offset, all relative to a date or time object passed to them. You need to derive a concrete subclass, and (at least) supply implementations of the standard :class:`tzinfo` methods needed by the :class:`.datetime` methods you use. The :mod:`!datetime` module provides - :class:`timezone`, a simple concrete subclass of :class:`tzinfo` which can + :class:`timezone`, a simple concrete subclass of :class:`!tzinfo` which can represent time zones with fixed offset from UTC such as UTC itself or North American EST and EDT. @@ -2156,31 +2212,35 @@ Examples of working with a :class:`.time` object:: ``tz.utcoffset(dt) - tz.dst(dt)`` must return the same result for every :class:`.datetime` *dt* with ``dt.tzinfo == - tz``. For sane :class:`tzinfo` subclasses, this expression yields the time + tz``. For sane :class:`!tzinfo` subclasses, this expression yields the time zone's "standard offset", which should not depend on the date or the time, but only on geographic location. The implementation of :meth:`datetime.astimezone` relies on this, but cannot detect violations; it's the programmer's - responsibility to ensure it. If a :class:`tzinfo` subclass cannot guarantee + responsibility to ensure it. If a :class:`!tzinfo` subclass cannot guarantee this, it may be able to override the default implementation of :meth:`tzinfo.fromutc` to work correctly with :meth:`~.datetime.astimezone` regardless. Most implementations of :meth:`dst` will probably look like one of these two:: - def dst(self, dt): + import datetime as dt + + def dst(self, when): # a fixed-offset class: doesn't account for DST - return timedelta(0) + return dt.timedelta(0) or:: - def dst(self, dt): + import datetime as dt + + def dst(self, when): # Code to set dston and dstoff to the time zone's DST - # transition times based on the input dt.year, and expressed + # transition times based on the input when.year, and expressed # in standard local time. - if dston <= dt.replace(tzinfo=None) < dstoff: - return timedelta(hours=1) + if dston <= when.replace(tzinfo=None) < dstoff: + return dt.timedelta(hours=1) else: - return timedelta(0) + return dt.timedelta(0) The default implementation of :meth:`dst` raises :exc:`NotImplementedError`. @@ -2197,17 +2257,17 @@ Examples of working with a :class:`.time` object:: valid replies. Return ``None`` if a string name isn't known. Note that this is a method rather than a fixed string primarily because some :class:`tzinfo` subclasses will wish to return different names depending on the specific value - of *dt* passed, especially if the :class:`tzinfo` class is accounting for + of *dt* passed, especially if the :class:`!tzinfo` class is accounting for daylight time. The default implementation of :meth:`tzname` raises :exc:`NotImplementedError`. These methods are called by a :class:`.datetime` or :class:`.time` object, in -response to their methods of the same names. A :class:`.datetime` object passes -itself as the argument, and a :class:`.time` object passes ``None`` as the +response to their methods of the same names. A :class:`!datetime` object passes +itself as the argument, and a :class:`!time` object passes ``None`` as the argument. A :class:`tzinfo` subclass's methods should therefore be prepared to -accept a *dt* argument of ``None``, or of class :class:`.datetime`. +accept a *dt* argument of ``None``, or of class :class:`!datetime`. When ``None`` is passed, it's up to the class designer to decide the best response. For example, returning ``None`` is appropriate if the class wishes to @@ -2215,10 +2275,10 @@ say that time objects don't participate in the :class:`tzinfo` protocols. It may be more useful for ``utcoffset(None)`` to return the standard UTC offset, as there is no other convention for discovering the standard offset. -When a :class:`.datetime` object is passed in response to a :class:`.datetime` +When a :class:`.datetime` object is passed in response to a :class:`!datetime` method, ``dt.tzinfo`` is the same object as *self*. :class:`tzinfo` methods can -rely on this, unless user code calls :class:`tzinfo` methods directly. The -intent is that the :class:`tzinfo` methods interpret *dt* as being in local +rely on this, unless user code calls :class:`!tzinfo` methods directly. The +intent is that the :class:`!tzinfo` methods interpret *dt* as being in local time, and not need worry about objects in other time zones. There is one more :class:`tzinfo` method that a subclass may wish to override: @@ -2246,20 +2306,22 @@ There is one more :class:`tzinfo` method that a subclass may wish to override: Skipping code for error cases, the default :meth:`fromutc` implementation acts like:: - def fromutc(self, dt): - # raise ValueError error if dt.tzinfo is not self - dtoff = dt.utcoffset() - dtdst = dt.dst() + import datetime as dt + + def fromutc(self, when): + # raise ValueError error if when.tzinfo is not self + dtoff = when.utcoffset() + dtdst = when.dst() # raise ValueError if dtoff is None or dtdst is None delta = dtoff - dtdst # this is self's standard offset if delta: - dt += delta # convert to standard local time - dtdst = dt.dst() + when += delta # convert to standard local time + dtdst = when.dst() # raise ValueError if dtdst is None if dtdst: - return dt + dtdst + return when + dtdst else: - return dt + return when In the following :download:`tzinfo_examples.py <../includes/tzinfo_examples.py>` file there are some examples of @@ -2286,9 +2348,9 @@ When DST starts (the "start" line), the local wall clock leaps from 1:59 to ``astimezone(Eastern)`` won't deliver a result with ``hour == 2`` on the day DST begins. For example, at the Spring forward transition of 2016, we get:: - >>> from datetime import datetime, timezone + >>> import datetime as dt >>> from tzinfo_examples import HOUR, Eastern - >>> u0 = datetime(2016, 3, 13, 5, tzinfo=timezone.utc) + >>> u0 = dt.datetime(2016, 3, 13, 5, tzinfo=dt.timezone.utc) >>> for i in range(4): ... u = u0 + i*HOUR ... t = u.astimezone(Eastern) @@ -2311,7 +2373,9 @@ form 5:MM and 6:MM both map to 1:MM when converted to Eastern, but earlier times have the :attr:`~.datetime.fold` attribute set to 0 and the later times have it set to 1. For example, at the Fall back transition of 2016, we get:: - >>> u0 = datetime(2016, 11, 6, 4, tzinfo=timezone.utc) + >>> import datetime as dt + >>> from tzinfo_examples import HOUR, Eastern + >>> u0 = dt.datetime(2016, 11, 6, 4, tzinfo=dt.timezone.utc) >>> for i in range(4): ... u = u0 + i*HOUR ... t = u.astimezone(Eastern) @@ -2328,7 +2392,7 @@ Note that the :class:`.datetime` instances that differ only by the value of the Applications that can't bear wall-time ambiguities should explicitly check the value of the :attr:`~.datetime.fold` attribute or avoid using hybrid :class:`tzinfo` subclasses; there are no ambiguities when using :class:`timezone`, -or any other fixed-offset :class:`tzinfo` subclass (such as a class representing +or any other fixed-offset :class:`!tzinfo` subclass (such as a class representing only EST (fixed offset -5 hours), or only EDT (fixed offset -4 hours)). .. seealso:: @@ -2351,8 +2415,8 @@ only EST (fixed offset -5 hours), or only EDT (fixed offset -4 hours)). .. _datetime-timezone: -:class:`timezone` Objects -------------------------- +:class:`!timezone` objects +-------------------------- The :class:`timezone` class is a subclass of :class:`tzinfo`, each instance of which represents a time zone defined by a fixed offset from @@ -2390,6 +2454,7 @@ where historical changes have been made to civil time. .. versionchanged:: 3.7 The UTC offset is not restricted to a whole number of minutes. + .. method:: timezone.tzname(dt) Return the fixed value specified when the :class:`timezone` instance @@ -2410,11 +2475,13 @@ where historical changes have been made to civil time. Always returns ``None``. + .. method:: timezone.fromutc(dt) Return ``dt + offset``. The *dt* argument must be an aware :class:`.datetime` instance, with ``tzinfo`` set to ``self``. + Class attributes: .. attribute:: timezone.utc @@ -2427,8 +2494,8 @@ Class attributes: .. _strftime-strptime-behavior: -:meth:`~.datetime.strftime` and :meth:`~.datetime.strptime` Behavior --------------------------------------------------------------------- +:meth:`!strftime` and :meth:`!strptime` behavior +------------------------------------------------ :class:`date`, :class:`.datetime`, and :class:`.time` objects all support a ``strftime(format)`` method, to create a string representing the time under the @@ -2454,13 +2521,14 @@ versus :meth:`~.datetime.strptime`: .. _format-codes: -:meth:`~.datetime.strftime` and :meth:`~.datetime.strptime` Format Codes -^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +:meth:`!strftime` and :meth:`!strptime` format codes +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ These methods accept format codes that can be used to parse and format dates:: - >>> datetime.strptime('31/01/22 23:59:59.999999', - ... '%d/%m/%y %H:%M:%S.%f') + >>> import datetime as dt + >>> dt.datetime.strptime('31/01/22 23:59:59.999999', + ... '%d/%m/%y %H:%M:%S.%f') datetime.datetime(2022, 1, 31, 23, 59, 59, 999999) >>> _.strftime('%a %d %b %Y, %I:%M%p') 'Mon 31 Jan 2022, 11:59PM' @@ -2611,16 +2679,55 @@ differences between platforms in handling of unsupported format specifiers. .. versionadded:: 3.12 ``%:z`` was added. -Technical Detail + +Technical detail ^^^^^^^^^^^^^^^^ Broadly speaking, ``d.strftime(fmt)`` acts like the :mod:`time` module's ``time.strftime(fmt, d.timetuple())`` although not all objects support a :meth:`~date.timetuple` method. -For the :meth:`.datetime.strptime` class method, the default value is -``1900-01-01T00:00:00.000``: any components not specified in the format string -will be pulled from the default value. [#]_ +For the :meth:`.datetime.strptime` and :meth:`.date.strptime` class methods, +the default value is ``1900-01-01T00:00:00.000``: any components not specified +in the format string will be pulled from the default value. + +.. note:: + Format strings without separators can be ambiguous for parsing. For + example, with ``%Y%m%d``, the string ``2026111`` may be parsed either as + ``2026-11-01`` or as ``2026-01-11``. + Use separators to ensure the input is parsed as intended. + +.. note:: + When used to parse partial dates lacking a year, :meth:`.datetime.strptime` + and :meth:`.date.strptime` will raise when encountering February 29 because + the default year of 1900 is *not* a leap year. Always add a default leap + year to partial date strings before parsing. + +.. testsetup:: + + # doctest seems to turn the warning into an error which makes it + # show up and require matching and prevents the actual interesting + # exception from being raised. + # Manually apply the catch_warnings context manager + import warnings + catch_warnings = warnings.catch_warnings() + catch_warnings.__enter__() + warnings.simplefilter("ignore") + +.. testcleanup:: + + catch_warnings.__exit__() + +.. doctest:: + + >>> import datetime as dt + >>> value = "2/29" + >>> dt.datetime.strptime(value, "%m/%d") + Traceback (most recent call last): + ... + ValueError: day 29 must be in range 1..28 for month 2 in year 1900 + >>> dt.datetime.strptime(f"1904 {value}", "%Y %m/%d") + datetime.datetime(1904, 2, 29, 0, 0) Using ``datetime.strptime(date_string, format)`` is equivalent to:: @@ -2751,12 +2858,12 @@ Notes: include a year in the format. If the value you need to parse lacks a year, append an explicit dummy leap year. Otherwise your code will raise an exception when it encounters leap day because the default year used by the - parser is not a leap year. Users run into this bug every four years... + parser (1900) is not a leap year. Users run into that bug every leap year. .. doctest:: >>> month_day = "02/29" - >>> datetime.strptime(f"{month_day};1984", "%m/%d;%Y") # No leap year bug. + >>> dt.datetime.strptime(f"{month_day};1984", "%m/%d;%Y") # No leap year bug. datetime.datetime(1984, 2, 29, 0, 0) .. deprecated-removed:: 3.13 3.15 @@ -2767,7 +2874,7 @@ Notes: .. rubric:: Footnotes -.. [#] If, that is, we ignore the effects of Relativity +.. [#] If, that is, we ignore the effects of relativity. .. [#] This matches the definition of the "proleptic Gregorian" calendar in Dershowitz and Reingold's book *Calendrical Calculations*, @@ -2778,5 +2885,3 @@ Notes: .. [#] See R. H. van Gent's `guide to the mathematics of the ISO 8601 calendar `_ for a good explanation. - -.. [#] Passing ``datetime.strptime('Feb 29', '%b %d')`` will fail since 1900 is not a leap year. diff --git a/Doc/library/dbm.rst b/Doc/library/dbm.rst index 36221c026d6d4b..c736ee0d705acc 100644 --- a/Doc/library/dbm.rst +++ b/Doc/library/dbm.rst @@ -8,7 +8,7 @@ -------------- -:mod:`dbm` is a generic interface to variants of the DBM database: +:mod:`!dbm` is a generic interface to variants of the DBM database: * :mod:`dbm.sqlite3` * :mod:`dbm.gnu` @@ -84,10 +84,13 @@ the Oracle Berkeley DB. .. versionchanged:: 3.11 *file* accepts a :term:`path-like object`. -The object returned by :func:`~dbm.open` supports the same basic functionality as a -:class:`dict`; keys and their corresponding values can be stored, retrieved, and -deleted, and the :keyword:`in` operator and the :meth:`!keys` method are -available, as well as :meth:`!get` and :meth:`!setdefault` methods. +The object returned by :func:`~dbm.open` supports the basic +functionality of mutable :term:`mappings `; +keys and their corresponding values can be stored, retrieved, and +deleted, and iteration, the :keyword:`in` operator and methods :meth:`!keys`, +:meth:`!get`, :meth:`!setdefault` and :meth:`!clear` are available. +The :meth:`!keys` method returns a list instead of a view object. +The :meth:`!setdefault` method requires two arguments. Key and values are always stored as :class:`bytes`. This means that when strings are used they are implicitly converted to the default encoding before @@ -98,7 +101,7 @@ will automatically close them when done. .. versionchanged:: 3.2 :meth:`!get` and :meth:`!setdefault` methods are now available for all - :mod:`dbm` backends. + :mod:`!dbm` backends. .. versionchanged:: 3.4 Added native support for the context management protocol to the objects @@ -108,6 +111,10 @@ will automatically close them when done. Deleting a key from a read-only database raises a database module specific exception instead of :exc:`KeyError`. +.. versionchanged:: 3.13 + :meth:`!clear` methods are now available for all :mod:`!dbm` backends. + + The following example records some hostnames and a corresponding title, and then prints out the contents of the database:: @@ -144,11 +151,10 @@ then prints out the contents of the database:: The individual submodules are described in the following sections. -:mod:`dbm.sqlite3` --- SQLite backend for dbm ---------------------------------------------- +:mod:`!dbm.sqlite3` --- SQLite backend for dbm +---------------------------------------------- .. module:: dbm.sqlite3 - :platform: All :synopsis: SQLite backend for dbm .. versionadded:: 3.13 @@ -158,8 +164,8 @@ The individual submodules are described in the following sections. -------------- This module uses the standard library :mod:`sqlite3` module to provide an -SQLite backend for the :mod:`dbm` module. -The files created by :mod:`dbm.sqlite3` can thus be opened by :mod:`sqlite3`, +SQLite backend for the :mod:`!dbm` module. +The files created by :mod:`!dbm.sqlite3` can thus be opened by :mod:`sqlite3`, or any other SQLite browser, including the SQLite CLI. .. include:: ../includes/wasm-notavail.rst @@ -167,9 +173,6 @@ or any other SQLite browser, including the SQLite CLI. .. function:: open(filename, /, flag="r", mode=0o666) Open an SQLite database. - The returned object behaves like a :term:`mapping`, - implements a :meth:`!close` method, - and supports a "closing" context manager via the :keyword:`with` keyword. :param filename: The path to the database to be opened. @@ -186,35 +189,52 @@ or any other SQLite browser, including the SQLite CLI. The Unix file access mode of the file (default: octal ``0o666``), used only when the database has to be created. + The returned database object behaves similar to a mutable :term:`mapping`, + but the :meth:`!keys` method returns a list, and + the :meth:`!setdefault` method requires two arguments. + It also supports a "closing" context manager via the :keyword:`with` keyword. + + The following method is also provided: -:mod:`dbm.gnu` --- GNU database manager ---------------------------------------- + .. method:: sqlite3.close() + + Close the SQLite database. + + +:mod:`!dbm.gnu` --- GNU database manager +---------------------------------------- .. module:: dbm.gnu - :platform: Unix :synopsis: GNU database manager **Source code:** :source:`Lib/dbm/gnu.py` -------------- -The :mod:`dbm.gnu` module provides an interface to the :abbr:`GDBM (GNU dbm)` +The :mod:`!dbm.gnu` module provides an interface to the :abbr:`GDBM (GNU dbm)` library, similar to the :mod:`dbm.ndbm` module, but with additional functionality like crash tolerance. .. note:: - The file formats created by :mod:`dbm.gnu` and :mod:`dbm.ndbm` are incompatible + The file formats created by :mod:`!dbm.gnu` and :mod:`dbm.ndbm` are incompatible and can not be used interchangeably. .. include:: ../includes/wasm-mobile-notavail.rst +.. availability:: Unix. + .. exception:: error - Raised on :mod:`dbm.gnu`-specific errors, such as I/O errors. :exc:`KeyError` is + Raised on :mod:`!dbm.gnu`-specific errors, such as I/O errors. :exc:`KeyError` is raised for general mapping errors like specifying an incorrect key. +.. data:: open_flags + + A string of characters the *flag* parameter of :meth:`~dbm.gnu.open` supports. + + .. function:: open(filename, flag="r", mode=0o666, /) Open a GDBM database and return a :class:`!gdbm` object. @@ -250,14 +270,25 @@ functionality like crash tolerance. .. versionchanged:: 3.11 *filename* accepts a :term:`path-like object`. - .. data:: open_flags + :class:`!gdbm` objects behave similar to mutable :term:`mappings `, + but methods :meth:`!items`, :meth:`!values`, :meth:`!pop`, :meth:`!popitem`, + and :meth:`!update` are not supported, + the :meth:`!keys` method returns a list, and + the :meth:`!setdefault` method requires two arguments. + It also supports a "closing" context manager via the :keyword:`with` keyword. - A string of characters the *flag* parameter of :meth:`~dbm.gnu.open` supports. + .. versionchanged:: 3.2 + Added the :meth:`!get` and :meth:`!setdefault` methods. + + .. versionchanged:: 3.13 + Added the :meth:`!clear` method. - :class:`!gdbm` objects behave similar to :term:`mappings `, - but :meth:`!items` and :meth:`!values` methods are not supported. The following methods are also provided: + .. method:: gdbm.close() + + Close the GDBM database. + .. method:: gdbm.firstkey() It's possible to loop over every key in the database using this method and the @@ -289,36 +320,25 @@ functionality like crash tolerance. When the database has been opened in fast mode, this method forces any unwritten data to be written to the disk. - .. method:: gdbm.close() - - Close the GDBM database. - - .. method:: gdbm.clear() - - Remove all items from the GDBM database. - .. versionadded:: 3.13 - - -:mod:`dbm.ndbm` --- New Database Manager ----------------------------------------- +:mod:`!dbm.ndbm` --- New Database Manager +----------------------------------------- .. module:: dbm.ndbm - :platform: Unix :synopsis: The New Database Manager **Source code:** :source:`Lib/dbm/ndbm.py` -------------- -The :mod:`dbm.ndbm` module provides an interface to the +The :mod:`!dbm.ndbm` module provides an interface to the :abbr:`NDBM (New Database Manager)` library. This module can be used with the "classic" NDBM interface or the :abbr:`GDBM (GNU dbm)` compatibility interface. .. note:: - The file formats created by :mod:`dbm.gnu` and :mod:`dbm.ndbm` are incompatible + The file formats created by :mod:`dbm.gnu` and :mod:`!dbm.ndbm` are incompatible and can not be used interchangeably. .. warning:: @@ -330,9 +350,11 @@ This module can be used with the "classic" NDBM interface or the .. include:: ../includes/wasm-mobile-notavail.rst +.. availability:: Unix. + .. exception:: error - Raised on :mod:`dbm.ndbm`-specific errors, such as I/O errors. :exc:`KeyError` is raised + Raised on :mod:`!dbm.ndbm`-specific errors, such as I/O errors. :exc:`KeyError` is raised for general mapping errors like specifying an incorrect key. @@ -359,26 +381,31 @@ This module can be used with the "classic" NDBM interface or the :param int mode: |mode_param_doc| - :class:`!ndbm` objects behave similar to :term:`mappings `, - but :meth:`!items` and :meth:`!values` methods are not supported. - The following methods are also provided: - .. versionchanged:: 3.11 Accepts :term:`path-like object` for filename. - .. method:: ndbm.close() + :class:`!ndbm` objects behave similar to mutable :term:`mappings `, + but methods :meth:`!items`, :meth:`!values`, :meth:`!pop`, :meth:`!popitem`, + and :meth:`!update` are not supported, + the :meth:`!keys` method returns a list, and + the :meth:`!setdefault` method requires two arguments. + It also supports a "closing" context manager via the :keyword:`with` keyword. - Close the NDBM database. + .. versionchanged:: 3.2 + Added the :meth:`!get` and :meth:`!setdefault` methods. - .. method:: ndbm.clear() + .. versionchanged:: 3.13 + Added the :meth:`!clear` method. - Remove all items from the NDBM database. + The following method is also provided: - .. versionadded:: 3.13 + .. method:: ndbm.close() + + Close the NDBM database. -:mod:`dbm.dumb` --- Portable DBM implementation ------------------------------------------------ +:mod:`!dbm.dumb` --- Portable DBM implementation +------------------------------------------------ .. module:: dbm.dumb :synopsis: Portable implementation of the simple DBM interface. @@ -389,32 +416,29 @@ This module can be used with the "classic" NDBM interface or the .. note:: - The :mod:`dbm.dumb` module is intended as a last resort fallback for the - :mod:`dbm` module when a more robust module is not available. The :mod:`dbm.dumb` + The :mod:`!dbm.dumb` module is intended as a last resort fallback for the + :mod:`!dbm` module when a more robust module is not available. The :mod:`!dbm.dumb` module is not written for speed and is not nearly as heavily used as the other database modules. -------------- -The :mod:`dbm.dumb` module provides a persistent :class:`dict`-like +The :mod:`!dbm.dumb` module provides a persistent :class:`dict`-like interface which is written entirely in Python. -Unlike other :mod:`dbm` backends, such as :mod:`dbm.gnu`, no +Unlike other :mod:`!dbm` backends, such as :mod:`dbm.gnu`, no external library is required. The :mod:`!dbm.dumb` module defines the following: .. exception:: error - Raised on :mod:`dbm.dumb`-specific errors, such as I/O errors. :exc:`KeyError` is + Raised on :mod:`!dbm.dumb`-specific errors, such as I/O errors. :exc:`KeyError` is raised for general mapping errors like specifying an incorrect key. .. function:: open(filename, flag="c", mode=0o666) Open a :mod:`!dbm.dumb` database. - The returned database object behaves similar to a :term:`mapping`, - in addition to providing :meth:`~dumbdbm.sync` and :meth:`~dumbdbm.close` - methods. :param filename: The basename of the database file (without extensions). @@ -448,15 +472,18 @@ The :mod:`!dbm.dumb` module defines the following: .. versionchanged:: 3.11 *filename* accepts a :term:`path-like object`. - In addition to the methods provided by the - :class:`collections.abc.MutableMapping` class, - the following methods are provided: + The returned database object behaves similar to a mutable :term:`mapping`, + but the :meth:`!keys` and :meth:`!items` methods return lists, and + the :meth:`!setdefault` method requires two arguments. + It also supports a "closing" context manager via the :keyword:`with` keyword. - .. method:: dumbdbm.sync() - - Synchronize the on-disk directory and data files. This method is called - by the :meth:`shelve.Shelf.sync` method. + The following methods are also provided: .. method:: dumbdbm.close() Close the database. + + .. method:: dumbdbm.sync() + + Synchronize the on-disk directory and data files. This method is called + by the :meth:`shelve.Shelf.sync` method. diff --git a/Doc/library/decimal.rst b/Doc/library/decimal.rst index f53c1f3467034e..d4c089f5a14414 100644 --- a/Doc/library/decimal.rst +++ b/Doc/library/decimal.rst @@ -2,7 +2,7 @@ ===================================================================== .. module:: decimal - :synopsis: Implementation of the General Decimal Arithmetic Specification. + :synopsis: Implementation of the General Decimal Arithmetic Specification. .. moduleauthor:: Eric Price .. moduleauthor:: Facundo Batista @@ -30,14 +30,16 @@ -------------- -The :mod:`decimal` module provides support for fast correctly rounded +The :mod:`!decimal` module provides support for fast correctly rounded decimal floating-point arithmetic. It offers several advantages over the :class:`float` datatype: -* Decimal "is based on a floating-point model which was designed with people - in mind, and necessarily has a paramount guiding principle -- computers must - provide an arithmetic that works in the same way as the arithmetic that - people learn at school." -- excerpt from the decimal arithmetic specification. +* Decimal "is based on a `floating-point model + `__ which was designed + with people in mind, and necessarily has a paramount guiding principle -- + computers must provide an arithmetic that works in the same way as the + arithmetic that people learn at school." -- excerpt from the decimal + arithmetic specification. * Decimal numbers can be represented exactly. In contrast, numbers like ``1.1`` and ``2.2`` do not have exact representations in binary @@ -121,7 +123,7 @@ reset them before monitoring a calculation. .. _decimal-tutorial: -Quick-start Tutorial +Quick-start tutorial -------------------- The usual start to using decimals is importing the module, viewing the current @@ -238,6 +240,26 @@ floating-point flying circus: >>> c % a Decimal('0.77') +Decimals can be formatted (with :func:`format` built-in or :ref:`f-strings`) in +fixed-point or scientific notation, using the same formatting syntax (see +:ref:`formatspec`) as builtin :class:`float` type: + +.. doctest:: + + >>> format(Decimal('2.675'), "f") + '2.675' + >>> format(Decimal('2.675'), ".2f") + '2.68' + >>> f"{Decimal('2.675'):.2f}" + '2.68' + >>> format(Decimal('2.675'), ".2e") + '2.68e+0' + >>> with localcontext() as ctx: + ... ctx.rounding = ROUND_DOWN + ... print(format(Decimal('2.675'), ".2f")) + ... + 2.67 + And some mathematical functions are also available to Decimal: >>> getcontext().prec = 28 @@ -264,10 +286,10 @@ allows the settings to be changed. This approach meets the needs of most applications. For more advanced work, it may be useful to create alternate contexts using the -Context() constructor. To make an alternate active, use the :func:`setcontext` +:meth:`Context` constructor. To make an alternate active, use the :func:`setcontext` function. -In accordance with the standard, the :mod:`decimal` module provides two ready to +In accordance with the standard, the :mod:`!decimal` module provides two ready to use standard contexts, :const:`BasicContext` and :const:`ExtendedContext`. The former is especially useful for debugging because many of the traps are enabled: @@ -573,7 +595,7 @@ Decimal objects >>> Decimal(321).exp() Decimal('2.561702493119680037517373933E+139') - .. classmethod:: from_float(f) + .. classmethod:: from_float(f, /) Alternative constructor that only accepts instances of :class:`float` or :class:`int`. @@ -600,7 +622,7 @@ Decimal objects .. versionadded:: 3.1 - .. classmethod:: from_number(number) + .. classmethod:: from_number(number, /) Alternative constructor that only accepts instances of :class:`float`, :class:`int` or :class:`Decimal`, but not strings @@ -991,7 +1013,7 @@ Each thread has its own current context which is accessed or changed using the Return the current context for the active thread. -.. function:: setcontext(c) +.. function:: setcontext(c, /) Set the current context for the active thread to *c*. @@ -1096,40 +1118,52 @@ In addition to the three supplied contexts, new contexts can be created with the default values are copied from the :const:`DefaultContext`. If the *flags* field is not specified or is :const:`None`, all flags are cleared. - *prec* is an integer in the range [``1``, :const:`MAX_PREC`] that sets - the precision for arithmetic operations in the context. + .. attribute:: prec + + An integer in the range [``1``, :const:`MAX_PREC`] that sets + the precision for arithmetic operations in the context. + + .. attribute:: rounding + + One of the constants listed in the section `Rounding Modes`_. + + .. attribute:: traps + flags + + Lists of any signals to be set. Generally, new contexts should only set + traps and leave the flags clear. + + .. attribute:: Emin + Emax - The *rounding* option is one of the constants listed in the section - `Rounding Modes`_. + Integers specifying the outer limits allowable for exponents. *Emin* must + be in the range [:const:`MIN_EMIN`, ``0``], *Emax* in the range + [``0``, :const:`MAX_EMAX`]. - The *traps* and *flags* fields list any signals to be set. Generally, new - contexts should only set traps and leave the flags clear. + .. attribute:: capitals - The *Emin* and *Emax* fields are integers specifying the outer limits allowable - for exponents. *Emin* must be in the range [:const:`MIN_EMIN`, ``0``], - *Emax* in the range [``0``, :const:`MAX_EMAX`]. + Either ``0`` or ``1`` (the default). If set to + ``1``, exponents are printed with a capital ``E``; otherwise, a + lowercase ``e`` is used: ``Decimal('6.02e+23')``. - The *capitals* field is either ``0`` or ``1`` (the default). If set to - ``1``, exponents are printed with a capital ``E``; otherwise, a - lowercase ``e`` is used: ``Decimal('6.02e+23')``. + .. attribute:: clamp - The *clamp* field is either ``0`` (the default) or ``1``. - If set to ``1``, the exponent ``e`` of a :class:`Decimal` - instance representable in this context is strictly limited to the - range ``Emin - prec + 1 <= e <= Emax - prec + 1``. If *clamp* is - ``0`` then a weaker condition holds: the adjusted exponent of - the :class:`Decimal` instance is at most :attr:`~Context.Emax`. When *clamp* is - ``1``, a large normal number will, where possible, have its - exponent reduced and a corresponding number of zeros added to its - coefficient, in order to fit the exponent constraints; this - preserves the value of the number but loses information about - significant trailing zeros. For example:: + Either ``0`` (the default) or ``1``. If set to ``1``, the exponent ``e`` + of a :class:`Decimal` instance representable in this context is strictly + limited to the range ``Emin - prec + 1 <= e <= Emax - prec + 1``. + If *clamp* is ``0`` then a weaker condition holds: the adjusted exponent of + the :class:`Decimal` instance is at most :attr:`~Context.Emax`. When *clamp* is + ``1``, a large normal number will, where possible, have its + exponent reduced and a corresponding number of zeros added to its + coefficient, in order to fit the exponent constraints; this + preserves the value of the number but loses information about + significant trailing zeros. For example:: - >>> Context(prec=6, Emax=999, clamp=1).create_decimal('1.23e999') - Decimal('1.23000E+999') + >>> Context(prec=6, Emax=999, clamp=1).create_decimal('1.23e999') + Decimal('1.23000E+999') - A *clamp* value of ``1`` allows compatibility with the - fixed-width decimal interchange formats specified in IEEE 754. + A *clamp* value of ``1`` allows compatibility with the + fixed-width decimal interchange formats specified in IEEE 754. The :class:`Context` class defines several general purpose methods as well as a large number of methods for doing arithmetic directly in a given context. @@ -1156,11 +1190,11 @@ In addition to the three supplied contexts, new contexts can be created with the Return a duplicate of the context. - .. method:: copy_decimal(num) + .. method:: copy_decimal(num, /) Return a copy of the Decimal instance num. - .. method:: create_decimal(num) + .. method:: create_decimal(num='0', /) Creates a new Decimal instance from *num* but using *self* as context. Unlike the :class:`Decimal` constructor, the context precision, @@ -1184,7 +1218,7 @@ In addition to the three supplied contexts, new contexts can be created with the If the argument is a string, no leading or trailing whitespace or underscores are permitted. - .. method:: create_decimal_from_float(f) + .. method:: create_decimal_from_float(f, /) Creates a new Decimal instance from a float *f* but rounding using *self* as the context. Unlike the :meth:`Decimal.from_float` class method, @@ -1222,222 +1256,222 @@ In addition to the three supplied contexts, new contexts can be created with the recounted here. - .. method:: abs(x) + .. method:: abs(x, /) Returns the absolute value of *x*. - .. method:: add(x, y) + .. method:: add(x, y, /) Return the sum of *x* and *y*. - .. method:: canonical(x) + .. method:: canonical(x, /) Returns the same Decimal object *x*. - .. method:: compare(x, y) + .. method:: compare(x, y, /) Compares *x* and *y* numerically. - .. method:: compare_signal(x, y) + .. method:: compare_signal(x, y, /) Compares the values of the two operands numerically. - .. method:: compare_total(x, y) + .. method:: compare_total(x, y, /) Compares two operands using their abstract representation. - .. method:: compare_total_mag(x, y) + .. method:: compare_total_mag(x, y, /) Compares two operands using their abstract representation, ignoring sign. - .. method:: copy_abs(x) + .. method:: copy_abs(x, /) Returns a copy of *x* with the sign set to 0. - .. method:: copy_negate(x) + .. method:: copy_negate(x, /) Returns a copy of *x* with the sign inverted. - .. method:: copy_sign(x, y) + .. method:: copy_sign(x, y, /) Copies the sign from *y* to *x*. - .. method:: divide(x, y) + .. method:: divide(x, y, /) Return *x* divided by *y*. - .. method:: divide_int(x, y) + .. method:: divide_int(x, y, /) Return *x* divided by *y*, truncated to an integer. - .. method:: divmod(x, y) + .. method:: divmod(x, y, /) Divides two numbers and returns the integer part of the result. - .. method:: exp(x) + .. method:: exp(x, /) Returns ``e ** x``. - .. method:: fma(x, y, z) + .. method:: fma(x, y, z, /) Returns *x* multiplied by *y*, plus *z*. - .. method:: is_canonical(x) + .. method:: is_canonical(x, /) Returns ``True`` if *x* is canonical; otherwise returns ``False``. - .. method:: is_finite(x) + .. method:: is_finite(x, /) Returns ``True`` if *x* is finite; otherwise returns ``False``. - .. method:: is_infinite(x) + .. method:: is_infinite(x, /) Returns ``True`` if *x* is infinite; otherwise returns ``False``. - .. method:: is_nan(x) + .. method:: is_nan(x, /) Returns ``True`` if *x* is a qNaN or sNaN; otherwise returns ``False``. - .. method:: is_normal(x) + .. method:: is_normal(x, /) Returns ``True`` if *x* is a normal number; otherwise returns ``False``. - .. method:: is_qnan(x) + .. method:: is_qnan(x, /) Returns ``True`` if *x* is a quiet NaN; otherwise returns ``False``. - .. method:: is_signed(x) + .. method:: is_signed(x, /) Returns ``True`` if *x* is negative; otherwise returns ``False``. - .. method:: is_snan(x) + .. method:: is_snan(x, /) Returns ``True`` if *x* is a signaling NaN; otherwise returns ``False``. - .. method:: is_subnormal(x) + .. method:: is_subnormal(x, /) Returns ``True`` if *x* is subnormal; otherwise returns ``False``. - .. method:: is_zero(x) + .. method:: is_zero(x, /) Returns ``True`` if *x* is a zero; otherwise returns ``False``. - .. method:: ln(x) + .. method:: ln(x, /) Returns the natural (base e) logarithm of *x*. - .. method:: log10(x) + .. method:: log10(x, /) Returns the base 10 logarithm of *x*. - .. method:: logb(x) + .. method:: logb(x, /) Returns the exponent of the magnitude of the operand's MSD. - .. method:: logical_and(x, y) + .. method:: logical_and(x, y, /) Applies the logical operation *and* between each operand's digits. - .. method:: logical_invert(x) + .. method:: logical_invert(x, /) Invert all the digits in *x*. - .. method:: logical_or(x, y) + .. method:: logical_or(x, y, /) Applies the logical operation *or* between each operand's digits. - .. method:: logical_xor(x, y) + .. method:: logical_xor(x, y, /) Applies the logical operation *xor* between each operand's digits. - .. method:: max(x, y) + .. method:: max(x, y, /) Compares two values numerically and returns the maximum. - .. method:: max_mag(x, y) + .. method:: max_mag(x, y, /) Compares the values numerically with their sign ignored. - .. method:: min(x, y) + .. method:: min(x, y, /) Compares two values numerically and returns the minimum. - .. method:: min_mag(x, y) + .. method:: min_mag(x, y, /) Compares the values numerically with their sign ignored. - .. method:: minus(x) + .. method:: minus(x, /) Minus corresponds to the unary prefix minus operator in Python. - .. method:: multiply(x, y) + .. method:: multiply(x, y, /) Return the product of *x* and *y*. - .. method:: next_minus(x) + .. method:: next_minus(x, /) Returns the largest representable number smaller than *x*. - .. method:: next_plus(x) + .. method:: next_plus(x, /) Returns the smallest representable number larger than *x*. - .. method:: next_toward(x, y) + .. method:: next_toward(x, y, /) Returns the number closest to *x*, in direction towards *y*. - .. method:: normalize(x) + .. method:: normalize(x, /) Reduces *x* to its simplest form. - .. method:: number_class(x) + .. method:: number_class(x, /) Returns an indication of the class of *x*. - .. method:: plus(x) + .. method:: plus(x, /) Plus corresponds to the unary prefix plus operator in Python. This operation applies the context precision and rounding, so it is *not* an @@ -1478,7 +1512,7 @@ In addition to the three supplied contexts, new contexts can be created with the always exact. - .. method:: quantize(x, y) + .. method:: quantize(x, y, /) Returns a value equal to *x* (rounded), having the exponent of *y*. @@ -1488,7 +1522,7 @@ In addition to the three supplied contexts, new contexts can be created with the Just returns 10, as this is Decimal, :) - .. method:: remainder(x, y) + .. method:: remainder(x, y, /) Returns the remainder from integer division. @@ -1496,43 +1530,43 @@ In addition to the three supplied contexts, new contexts can be created with the dividend. - .. method:: remainder_near(x, y) + .. method:: remainder_near(x, y, /) Returns ``x - y * n``, where *n* is the integer nearest the exact value of ``x / y`` (if the result is 0 then its sign will be the sign of *x*). - .. method:: rotate(x, y) + .. method:: rotate(x, y, /) Returns a rotated copy of *x*, *y* times. - .. method:: same_quantum(x, y) + .. method:: same_quantum(x, y, /) Returns ``True`` if the two operands have the same exponent. - .. method:: scaleb (x, y) + .. method:: scaleb (x, y, /) Returns the first operand after adding the second value its exp. - .. method:: shift(x, y) + .. method:: shift(x, y, /) Returns a shifted copy of *x*, *y* times. - .. method:: sqrt(x) + .. method:: sqrt(x, /) Square root of a non-negative number to context precision. - .. method:: subtract(x, y) + .. method:: subtract(x, y, /) Return the difference between *x* and *y*. - .. method:: to_eng_string(x) + .. method:: to_eng_string(x, /) Convert to a string, using engineering notation if an exponent is needed. @@ -1541,12 +1575,12 @@ In addition to the three supplied contexts, new contexts can be created with the require the addition of either one or two trailing zeros. - .. method:: to_integral_exact(x) + .. method:: to_integral_exact(x, /) Rounds to an integer. - .. method:: to_sci_string(x) + .. method:: to_sci_string(x, /) Converts a number to a string using scientific notation. @@ -1769,7 +1803,7 @@ The following table summarizes the hierarchy of signals:: .. _decimal-notes: -Floating-Point Notes +Floating-point notes -------------------- @@ -1804,7 +1838,7 @@ properties of addition: >>> u * (v+w) Decimal('0.0060000') -The :mod:`decimal` module makes it possible to restore the identities by +The :mod:`!decimal` module makes it possible to restore the identities by expanding the precision sufficiently to avoid loss of significance: .. doctest:: newcontext @@ -1826,7 +1860,7 @@ expanding the precision sufficiently to avoid loss of significance: Special values ^^^^^^^^^^^^^^ -The number system for the :mod:`decimal` module provides special values +The number system for the :mod:`!decimal` module provides special values including ``NaN``, ``sNaN``, ``-Infinity``, ``Infinity``, and two zeros, ``+0`` and ``-0``. @@ -2088,20 +2122,20 @@ to work with the :class:`Decimal` class:: Decimal FAQ ----------- -Q. It is cumbersome to type ``decimal.Decimal('1234.5')``. Is there a way to +Q: It is cumbersome to type ``decimal.Decimal('1234.5')``. Is there a way to minimize typing when using the interactive interpreter? -A. Some users abbreviate the constructor to just a single letter: +A: Some users abbreviate the constructor to just a single letter: >>> D = decimal.Decimal >>> D('1.23') + D('3.45') Decimal('4.68') -Q. In a fixed-point application with two decimal places, some inputs have many +Q: In a fixed-point application with two decimal places, some inputs have many places and need to be rounded. Others are not supposed to have excess digits and need to be validated. What methods should be used? -A. The :meth:`~Decimal.quantize` method rounds to a fixed number of decimal places. If +A: The :meth:`~Decimal.quantize` method rounds to a fixed number of decimal places. If the :const:`Inexact` trap is set, it is also useful for validation: >>> TWOPLACES = Decimal(10) ** -2 # same as Decimal('0.01') @@ -2119,10 +2153,10 @@ the :const:`Inexact` trap is set, it is also useful for validation: ... Inexact: None -Q. Once I have valid two place inputs, how do I maintain that invariant +Q: Once I have valid two place inputs, how do I maintain that invariant throughout an application? -A. Some operations like addition, subtraction, and multiplication by an integer +A: Some operations like addition, subtraction, and multiplication by an integer will automatically preserve fixed point. Others operations, like division and non-integer multiplication, will change the number of decimal places and need to be followed-up with a :meth:`~Decimal.quantize` step: @@ -2154,21 +2188,21 @@ to handle the :meth:`~Decimal.quantize` step: >>> div(b, a) Decimal('0.03') -Q. There are many ways to express the same value. The numbers ``200``, +Q: There are many ways to express the same value. The numbers ``200``, ``200.000``, ``2E2``, and ``.02E+4`` all have the same value at various precisions. Is there a way to transform them to a single recognizable canonical value? -A. The :meth:`~Decimal.normalize` method maps all equivalent values to a single +A: The :meth:`~Decimal.normalize` method maps all equivalent values to a single representative: >>> values = map(Decimal, '200 200.000 2E2 .02E+4'.split()) >>> [v.normalize() for v in values] [Decimal('2E+2'), Decimal('2E+2'), Decimal('2E+2'), Decimal('2E+2')] -Q. When does rounding occur in a computation? +Q: When does rounding occur in a computation? -A. It occurs *after* the computation. The philosophy of the decimal +A: It occurs *after* the computation. The philosophy of the decimal specification is that numbers are considered exact and are created independent of the current context. They can even have greater precision than current context. Computations process with those @@ -2186,10 +2220,10 @@ applied to the *result* of the computation:: >>> pi + 0 - Decimal('0.00005'). # Intermediate values are rounded Decimal('3.1416') -Q. Some decimal values always print with exponential notation. Is there a way +Q: Some decimal values always print with exponential notation. Is there a way to get a non-exponential representation? -A. For some values, exponential notation is the only way to express the number +A: For some values, exponential notation is the only way to express the number of significant places in the coefficient. For example, expressing ``5.0E+3`` as ``5000`` keeps the value constant but cannot show the original's two-place significance. @@ -2204,9 +2238,9 @@ value unchanged: >>> remove_exponent(Decimal('5E+3')) Decimal('5000') -Q. Is there a way to convert a regular float to a :class:`Decimal`? +Q: Is there a way to convert a regular float to a :class:`Decimal`? -A. Yes, any binary floating-point number can be exactly expressed as a +A: Yes, any binary floating-point number can be exactly expressed as a Decimal though an exact conversion may take more precision than intuition would suggest: @@ -2215,19 +2249,19 @@ suggest: >>> Decimal(math.pi) Decimal('3.141592653589793115997963468544185161590576171875') -Q. Within a complex calculation, how can I make sure that I haven't gotten a +Q: Within a complex calculation, how can I make sure that I haven't gotten a spurious result because of insufficient precision or rounding anomalies. -A. The decimal module makes it easy to test results. A best practice is to +A: The decimal module makes it easy to test results. A best practice is to re-run calculations using greater precision and with various rounding modes. Widely differing results indicate insufficient precision, rounding mode issues, ill-conditioned inputs, or a numerically unstable algorithm. -Q. I noticed that context precision is applied to the results of operations but +Q: I noticed that context precision is applied to the results of operations but not to the inputs. Is there anything to watch out for when mixing values of different precisions? -A. Yes. The principle is that all values are considered to be exact and so is +A: Yes. The principle is that all values are considered to be exact and so is the arithmetic on those values. Only the results are rounded. The advantage for inputs is that "what you type is what you get". A disadvantage is that the results can look odd if you forget that the inputs haven't been rounded: @@ -2255,9 +2289,9 @@ Alternatively, inputs can be rounded upon creation using the >>> Context(prec=5, rounding=ROUND_DOWN).create_decimal('1.2345678') Decimal('1.2345') -Q. Is the CPython implementation fast for large numbers? +Q: Is the CPython implementation fast for large numbers? -A. Yes. In the CPython and PyPy3 implementations, the C/CFFI versions of +A: Yes. In the CPython and PyPy3 implementations, the C/CFFI versions of the decimal module integrate the high speed `libmpdec `_ library for arbitrary precision correctly rounded decimal floating-point arithmetic [#]_. diff --git a/Doc/library/dialog.rst b/Doc/library/dialog.rst index 191e0da12103fa..c50232f1d029cd 100644 --- a/Doc/library/dialog.rst +++ b/Doc/library/dialog.rst @@ -1,31 +1,45 @@ -Tkinter Dialogs +Tkinter dialogs =============== -:mod:`tkinter.simpledialog` --- Standard Tkinter input dialogs -^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +:mod:`!tkinter.simpledialog` --- Standard Tkinter input dialogs +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ .. module:: tkinter.simpledialog - :platform: Tk :synopsis: Simple dialog windows **Source code:** :source:`Lib/tkinter/simpledialog.py` -------------- -The :mod:`tkinter.simpledialog` module contains convenience classes and +The :mod:`!tkinter.simpledialog` module contains convenience classes and functions for creating simple modal dialogs to get a value from the user. -.. function:: askfloat(title, prompt, **kw) - askinteger(title, prompt, **kw) - askstring(title, prompt, **kw) +.. function:: askfloat(title, prompt, *, initialvalue=None, minvalue=None, maxvalue=None, parent=None) + askinteger(title, prompt, *, initialvalue=None, minvalue=None, maxvalue=None, parent=None) + askstring(title, prompt, *, initialvalue=None, show=None, parent=None) - The above three functions provide dialogs that prompt the user to enter a value - of the desired type. + Prompt the user to enter a value of the desired type and return it, or + ``None`` if the dialog is cancelled. + + *title* is the dialog title and *prompt* the message shown above the entry. + *initialvalue* is the value initially placed in the entry. + *parent* is the window over which the dialog is shown. + :func:`askinteger` and :func:`askfloat` also accept *minvalue* and + *maxvalue*, which bound the accepted value. + :func:`askstring` also accepts *show*, a character used to mask the entered + text, for example ``'*'`` to hide a password. .. class:: Dialog(parent, title=None) The base class for custom dialogs. + Instantiating it shows the dialog modally and returns once the user closes + it; the entered value is then available in the :attr:`!result` attribute. + + .. attribute:: result + + The value produced by :meth:`apply`, or ``None`` if the dialog was + cancelled. .. method:: body(master) @@ -37,23 +51,59 @@ functions for creating simple modal dialogs to get a value from the user. Default behaviour adds OK and Cancel buttons. Override for custom button layouts. + .. method:: validate() + + Validate the data entered by the user. + Return true if it is valid, in which case the dialog proceeds to + :meth:`apply`; return false to keep the dialog open. + The default implementation always returns true; override it to check the + input. + + .. method:: apply() + + Process the data entered by the user, for example by storing it in the + :attr:`!result` attribute. + Called after :meth:`validate` succeeds and just before the dialog is + destroyed. + The default implementation does nothing; override it to act on or store + the result. + + .. method:: destroy() + + Destroy the dialog window, clearing the reference to the widget that had + the initial focus. -:mod:`tkinter.filedialog` --- File selection dialogs -^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +.. class:: SimpleDialog(master, text='', buttons=[], default=None, cancel=None, title=None, class_=None) + + A simple modal dialog that displays the message *text* above a row of push + buttons whose labels are given by *buttons*, and returns the index of the + button the user presses. + *default* is the index of the button activated by the Return key, *cancel* + the index returned when the window is closed through the window manager, + *title* the window title, and *class_* the Tk class name of the window. + + .. method:: go() + + Display the dialog, wait until the user presses a button or closes the + window, and return the index of the chosen button. + + + +:mod:`!tkinter.filedialog` --- File selection dialogs +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ .. module:: tkinter.filedialog - :platform: Tk :synopsis: Dialog classes for file selection **Source code:** :source:`Lib/tkinter/filedialog.py` -------------- -The :mod:`tkinter.filedialog` module provides classes and factory functions for +The :mod:`!tkinter.filedialog` module provides classes and factory functions for creating file/directory selection windows. -Native Load/Save Dialogs +Native load/save dialogs ------------------------ The following classes and functions provide file dialog windows that combine a @@ -79,50 +129,62 @@ listed below: **Static factory functions** The below functions when called create a modal, native look-and-feel dialog, -wait for the user's selection, then return the selected value(s) or ``None`` to the -caller. +wait for the user's selection, and return it. +The exact return value depends on the function (see below); when the dialog is +cancelled it is an empty string, an empty tuple or ``None``. +The precise type of this empty value may vary between platforms and Tk +versions, so test the result for truth rather than comparing it with a +specific value. .. function:: askopenfile(mode="r", **options) askopenfiles(mode="r", **options) - The above two functions create an :class:`Open` dialog and return the opened - file object(s) in read-only mode. + Create an :class:`Open` dialog. + :func:`askopenfile` returns the opened file object, or ``None`` if the + dialog is cancelled. + :func:`askopenfiles` returns a list of the opened file objects, or an empty + tuple if cancelled. + The files are opened in mode *mode* (read-only ``'r'`` by default). .. function:: asksaveasfile(mode="w", **options) - Create a :class:`SaveAs` dialog and return a file object opened in write-only mode. + Create a :class:`SaveAs` dialog and return the opened file object, or + ``None`` if the dialog is cancelled. + The file is opened in mode *mode* (``'w'`` by default). .. function:: askopenfilename(**options) askopenfilenames(**options) - The above two functions create an :class:`Open` dialog and return the - selected filename(s) that correspond to existing file(s). + Create an :class:`Open` dialog. + :func:`askopenfilename` returns the selected filename as a string, or an + empty string if the dialog is cancelled. + :func:`askopenfilenames` returns a tuple of the selected filenames, or an + empty tuple if cancelled. .. function:: asksaveasfilename(**options) - Create a :class:`SaveAs` dialog and return the selected filename. + Create a :class:`SaveAs` dialog and return the selected filename as a + string, or an empty string if the dialog is cancelled. .. function:: askdirectory(**options) - | Prompt user to select a directory. - | Additional keyword option: - | *mustexist* - determines if selection must be an existing directory. + Prompt the user to select a directory, and return its path as a string, or + an empty string if the dialog is cancelled. + Additional keyword option: *mustexist* - if true, the user may only select + an existing directory (false by default). .. class:: Open(master=None, **options) SaveAs(master=None, **options) + Directory(master=None, **options) - The above two classes provide native dialog windows for saving and loading - files. + The above three classes provide native dialog windows for loading and saving + files and for selecting a directory. **Convenience classes** The below classes are used for creating file/directory windows from scratch. These do not emulate the native look-and-feel of the platform. -.. class:: Directory(master=None, **options) - - Create a dialog prompting the user to select a directory. - .. note:: The *FileDialog* class should be subclassed for custom event handling and behaviour. @@ -170,6 +232,13 @@ These do not emulate the native look-and-feel of the platform. Exit dialog returning current selection. + .. method:: ok_command() + + Called when the user confirms the current selection. + The base implementation accepts the selection and closes the dialog; + :class:`LoadFileDialog` and :class:`SaveFileDialog` override it to check + the selection first. + .. method:: quit(how=None) Exit dialog returning filename, if any. @@ -204,27 +273,62 @@ These do not emulate the native look-and-feel of the platform. directory. Confirmation is required if an already existing file is selected. -:mod:`tkinter.commondialog` --- Dialog window templates -^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +:mod:`!tkinter.commondialog` --- Dialog window templates +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ .. module:: tkinter.commondialog - :platform: Tk :synopsis: Tkinter base class for dialogs **Source code:** :source:`Lib/tkinter/commondialog.py` -------------- -The :mod:`tkinter.commondialog` module provides the :class:`Dialog` class that +The :mod:`!tkinter.commondialog` module provides the :class:`Dialog` class that is the base class for dialogs defined in other supporting modules. .. class:: Dialog(master=None, **options) - .. method:: show(color=None, **options) + .. method:: show(**options) Render the Dialog window. +:mod:`!tkinter.dialog` --- Classic Tk dialog boxes +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +.. module:: tkinter.dialog + :synopsis: A simple dialog box built on the classic Tk widgets. + +**Source code:** :source:`Lib/tkinter/dialog.py` + +-------------- + +The :mod:`!tkinter.dialog` module provides a simple modal dialog box built on +the classic (non-themed) Tk widgets. + +.. data:: DIALOG_ICON + + The name of a bitmap (``'questhead'``) suitable for use as the *bitmap* + of a :class:`Dialog`. + +.. class:: Dialog(master=None, cnf={}, **kw) + + Display a modal dialog box built from the classic (non-themed) Tk widgets + and wait for the user to press one of its buttons. + The options, given through *cnf* or as keyword arguments, are all required: + *title* (the window title), *text* (the message), *bitmap* (the name of a + bitmap icon, such as :data:`DIALOG_ICON`), *default* (the index of the + default button) and *strings* (the sequence of button labels). + After construction, the :attr:`!num` attribute holds the index of the button + the user pressed. + + .. method:: destroy() + + Do nothing. + The dialog window is destroyed automatically before the constructor + returns, so there is nothing left for this method to do. + + .. seealso:: Modules :mod:`tkinter.messagebox`, :ref:`tut-files` diff --git a/Doc/library/difflib.rst b/Doc/library/difflib.rst index ce948a6860f02c..8219a7cb36bcaf 100644 --- a/Doc/library/difflib.rst +++ b/Doc/library/difflib.rst @@ -17,44 +17,86 @@ -------------- -This module provides classes and functions for comparing sequences. It -can be used for example, for comparing files, and can produce information -about file differences in various formats, including HTML and context and unified -diffs. For comparing directories and files, see also, the :mod:`filecmp` module. - - -.. class:: SequenceMatcher - :noindex: - - This is a flexible class for comparing pairs of sequences of any type, so long - as the sequence elements are :term:`hashable`. The basic algorithm predates, and is a - little fancier than, an algorithm published in the late 1980's by Ratcliff and - Obershelp under the hyperbolic name "gestalt pattern matching." The idea is to - find the longest contiguous matching subsequence that contains no "junk" - elements; these "junk" elements are ones that are uninteresting in some - sense, such as blank lines or whitespace. (Handling junk is an - extension to the Ratcliff and Obershelp algorithm.) The same - idea is then applied recursively to the pieces of the sequences to the left and - to the right of the matching subsequence. This does not yield minimal edit - sequences, but does tend to yield matches that "look right" to people. - - **Timing:** The basic Ratcliff-Obershelp algorithm is cubic time in the worst - case and quadratic time in the expected case. :class:`SequenceMatcher` is - quadratic time for the worst case and has expected-case behavior dependent in a - complicated way on how many elements the sequences have in common; best case - time is linear. - - **Automatic junk heuristic:** :class:`SequenceMatcher` supports a heuristic that - automatically treats certain sequence items as junk. The heuristic counts how many - times each individual item appears in the sequence. If an item's duplicates (after - the first one) account for more than 1% of the sequence and the sequence is at least - 200 items long, this item is marked as "popular" and is treated as junk for - the purpose of sequence matching. This heuristic can be turned off by setting - the ``autojunk`` argument to ``False`` when creating the :class:`SequenceMatcher`. +This module provides classes and functions for comparing sequences. +Most of them compare sequences of text lines (for example lists of strings, +or :term:`file objects `) and +produce :dfn:`diffs` -- reports on the differences. +Diffs can be produced in in various formats, including HTML and context +and unified diffs -- formats produced by tools like +:manpage:`diff ` and :manpage:`git diff `. + +Comparisons are done using a matching algorithm implemented in +:class:`SequenceMatcher` -- a flexible class for comparing pairs of sequences +of any type, not just text, so long as the sequence elements are +:term:`hashable`. + + +.. _difflib-junk: + +Junk heuristic +-------------- + +:mod:`!difflib` uses a :dfn:`junk` heuristic: some items are deemed to be +:dfn:`junk`, and ignored when searching for similarities. +Ideally, these are uninteresting or common items, such as blank lines +or whitespace. + +This heuristic can speed the algorithm up (because it reduces the number of +possible combinations) and it can produce results that are more understandable +for humans (typically breaking on whitespace). +But it can also cause pathological cases: + +- Inappropriately chosen junk items can cause an unexpectedly **large** (but + still correct) result. +- The default heuristic is **asymmetric**: only the second sequence is + inspected when determining what is considered junk, so comparing A to B can + give different results than comparing B to A and reversing the result. + +By default, if the second input sequence is at least 200 items long, items +that account for more than 1% it are considered *junk*. + +Depending on your data, you should consider turning this heuristic off +(setting :class:`~difflib.SequenceMatcher`'s *autojunk* argument to to ``False``) +or tuning it (using the *isjunk* argument, perhaps to one of the +:ref:`predefined functions `). + + +The :mod:`!difflib` algorithm +----------------------------- + +The algorithm used in :class:`SequenceMatcher` predates, and is a little +fancier than, an algorithm published in the late 1980s by Ratcliff and +Obershelp under the hyperbolic name "gestalt pattern matching." +The idea is to find the longest contiguous subsequence common to both inputs, +then recursively handle the pieces of the sequences to the left and to the +right of the matching subsequence. + +.. seealso:: + + `Pattern Matching: The Gestalt Approach `_ + Discussion of a similar algorithm by John W. Ratcliff and D. E. Metzener. This + was published in Dr. Dobb's Journal in July, 1988. + +As an extension to the Ratcliff and Obershelp algorithm, :mod:`!difflib` +searches for the longest *junk-free* contiguous subsequence. +See the :ref:`difflib-junk` section for details. + +.. impl-detail:: Timing + + The basic Ratcliff-Obershelp algorithm is cubic time in the worst + case and quadratic time in the expected case. + :mod:`difflib`'s algorithm is quadratic time for the worst case and has + expected-case behavior dependent in a complicated way on how many elements + the sequences have in common; + best case time is linear. - .. versionchanged:: 3.2 - Added the *autojunk* parameter. +.. _difflib-diff-generation: + +Diff generation +--------------- + +.. _differ-objects: .. class:: Differ @@ -81,6 +123,47 @@ diffs. For comparing directories and files, see also, the :mod:`filecmp` module. and were not present in either input sequence. These lines can be confusing if the sequences contain whitespace characters, such as spaces, tabs or line breaks. + Note that :class:`Differ`\ -generated deltas make no claim to be **minimal** + diffs. To the contrary, minimal diffs are often counter-intuitive for humans, + because they synch up anywhere possible, sometimes at accidental matches + 100 pages apart. + Restricting synch points to contiguous matches preserves some notion of + locality, at the occasional cost of producing a longer diff. + + The :class:`Differ` class has this constructor: + + .. method:: __init__(linejunk=None, charjunk=None) + + Optional keyword parameters *linejunk* and *charjunk* are for filter functions + (or ``None``): + + *linejunk*: A function that accepts a single string argument, and returns true + if the string is junk. The default is ``None``, meaning that no line is + considered junk. + + *charjunk*: A function that accepts a single character argument (a string of + length 1), and returns true if the character is junk. The default is ``None``, + meaning that no character is considered junk. + + These junk-filtering functions speed up matching to find + differences and do not cause any differing lines or characters to + be ignored. Read the description of the + :meth:`~SequenceMatcher.find_longest_match` method's *isjunk* + parameter for an explanation. + + :class:`Differ` objects are used (deltas generated) via a single method: + + + .. method:: Differ.compare(a, b) + + Compare two sequences of lines, and generate the delta (a sequence of lines). + + Each sequence must contain individual single-line strings ending with + newlines. Such sequences can be obtained from the + :meth:`~io.IOBase.readlines` method of file-like objects. The generated + delta also consists of newline-terminated strings, ready to be + printed as-is via the :meth:`~io.IOBase.writelines` method of a + file-like object. .. class:: HtmlDiff @@ -89,6 +172,11 @@ diffs. For comparing directories and files, see also, the :mod:`filecmp` module. with inter-line and intra-line change highlights. The table can be generated in either full or contextual difference mode. + .. warning:: + + The trailing newlines get stripped before the diff, so the result can be + incomplete. See :gh:`71896` for details. + The constructor for this class is: @@ -231,7 +319,7 @@ diffs. For comparing directories and files, see also, the :mod:`filecmp` module. *linejunk*: A function that accepts a single string argument, and returns true if the string is junk, or false if not. The default is ``None``. There is also a module-level function :func:`IS_LINE_JUNK`, which filters out lines - without visible characters, except for at most one pound character (``'#'``) + without visible characters, except for at most one hash character (``'#'``) -- however the underlying :class:`SequenceMatcher` class does a dynamic analysis of which lines are so frequent as to constitute noise, and this usually works better than using this function. @@ -335,6 +423,12 @@ diffs. For comparing directories and files, see also, the :mod:`filecmp` module. .. versionadded:: 3.5 + +.. _difflib-isjunk-functions: + +Junk definition functions +------------------------- + .. function:: IS_LINE_JUNK(line) Return ``True`` for ignorable lines. The line *line* is ignorable if *line* is @@ -349,21 +443,11 @@ diffs. For comparing directories and files, see also, the :mod:`filecmp` module. parameter *charjunk* in :func:`ndiff`. -.. seealso:: - - `Pattern Matching: The Gestalt Approach `_ - Discussion of a similar algorithm by John W. Ratcliff and D. E. Metzener. This - was published in `Dr. Dobb's Journal `_ in July, 1988. - - .. _sequence-matcher: -SequenceMatcher Objects +SequenceMatcher objects ----------------------- -The :class:`SequenceMatcher` class has this constructor: - - .. class:: SequenceMatcher(isjunk=None, a='', b='', autojunk=True) Optional argument *isjunk* must be ``None`` (the default) or a one-argument @@ -549,16 +633,6 @@ The :class:`SequenceMatcher` class has this constructor: to try :meth:`quick_ratio` or :meth:`real_quick_ratio` first to get an upper bound. - .. note:: - - Caution: The result of a :meth:`ratio` call may depend on the order of - the arguments. For instance:: - - >>> SequenceMatcher(None, 'tide', 'diet').ratio() - 0.25 - >>> SequenceMatcher(None, 'diet', 'tide').ratio() - 0.5 - .. method:: quick_ratio() @@ -584,10 +658,13 @@ are always at least as large as :meth:`~SequenceMatcher.ratio`: 1.0 +Examples +-------- + .. _sequencematcher-examples: -SequenceMatcher Examples ------------------------- +SequenceMatcher examples +........................ This example compares two strings, considering blanks to be "junk": @@ -635,59 +712,10 @@ If you want to know how to change the first sequence into the second, use built with :class:`SequenceMatcher`. -.. _differ-objects: - -Differ Objects --------------- - -Note that :class:`Differ`\ -generated deltas make no claim to be **minimal** -diffs. To the contrary, minimal diffs are often counter-intuitive, because they -synch up anywhere possible, sometimes accidental matches 100 pages apart. -Restricting synch points to contiguous matches preserves some notion of -locality, at the occasional cost of producing a longer diff. - -The :class:`Differ` class has this constructor: - - -.. class:: Differ(linejunk=None, charjunk=None) - :noindex: - - Optional keyword parameters *linejunk* and *charjunk* are for filter functions - (or ``None``): - - *linejunk*: A function that accepts a single string argument, and returns true - if the string is junk. The default is ``None``, meaning that no line is - considered junk. - - *charjunk*: A function that accepts a single character argument (a string of - length 1), and returns true if the character is junk. The default is ``None``, - meaning that no character is considered junk. - - These junk-filtering functions speed up matching to find - differences and do not cause any differing lines or characters to - be ignored. Read the description of the - :meth:`~SequenceMatcher.find_longest_match` method's *isjunk* - parameter for an explanation. - - :class:`Differ` objects are used (deltas generated) via a single method: - - - .. method:: Differ.compare(a, b) - - Compare two sequences of lines, and generate the delta (a sequence of lines). - - Each sequence must contain individual single-line strings ending with - newlines. Such sequences can be obtained from the - :meth:`~io.IOBase.readlines` method of file-like objects. The delta - generated also consists of newline-terminated strings, ready to be - printed as-is via the :meth:`~io.IOBase.writelines` method of a - file-like object. - - .. _differ-examples: -Differ Example --------------- +Differ example +.............. This example compares two texts. First we set up the texts, sequences of individual single-line strings ending with newlines (such sequences can also be @@ -754,14 +782,14 @@ As a single multi-line string it looks like this: .. _difflib-interface: A command-line interface to difflib ------------------------------------ +................................... This example shows how to use difflib to create a ``diff``-like utility. .. literalinclude:: ../includes/diff.py ndiff example -------------- +............. This example shows how to use :func:`difflib.ndiff`. diff --git a/Doc/library/dis.rst b/Doc/library/dis.rst index 44767b5dd2d5c9..d6b728b0848dff 100644 --- a/Doc/library/dis.rst +++ b/Doc/library/dis.rst @@ -14,7 +14,7 @@ -------------- -The :mod:`dis` module supports the analysis of CPython :term:`bytecode` by +The :mod:`!dis` module supports the analysis of CPython :term:`bytecode` by disassembling it. The CPython bytecode which this module takes as an input is defined in the file :file:`Include/opcode.h` and used by the compiler and the interpreter. @@ -38,7 +38,7 @@ interpreter. Some instructions are accompanied by one or more inline cache entries, which take the form of :opcode:`CACHE` instructions. These instructions are hidden by default, but can be shown by passing ``show_caches=True`` to - any :mod:`dis` utility. Furthermore, the interpreter now adapts the + any :mod:`!dis` utility. Furthermore, the interpreter now adapts the bytecode to specialize it for different runtime conditions. The adaptive bytecode can be shown by passing ``adaptive=True``. @@ -87,7 +87,7 @@ the following command can be used to display the disassembly of Command-line interface ---------------------- -The :mod:`dis` module can be invoked as a script from the command line: +The :mod:`!dis` module can be invoked as a script from the command line: .. code-block:: sh @@ -223,7 +223,7 @@ Example: Analysis functions ------------------ -The :mod:`dis` module also defines the following analysis functions that convert +The :mod:`!dis` module also defines the following analysis functions that convert the input directly to the desired output. They can be useful if only a single operation is being performed, so the intermediate analysis object isn't useful: @@ -585,6 +585,22 @@ operations on it as if it was a Python list. The top of the stack corresponds to generate line tracing events. +.. opcode:: NOT_TAKEN + + Do nothing code. + Used by the interpreter to record :monitoring-event:`BRANCH_LEFT` + and :monitoring-event:`BRANCH_RIGHT` events for :mod:`sys.monitoring`. + + .. versionadded:: 3.14 + + +.. opcode:: POP_ITER + + Removes the iterator from the top of the stack. + + .. versionadded:: 3.14 + + .. opcode:: POP_TOP Removes the top-of-stack item:: @@ -752,7 +768,7 @@ not have to be) the original ``STACK[-2]``. end = STACK.pop() start = STACK.pop() container = STACK.pop() - values = STACK.pop() + value = STACK.pop() container[start:end] = value .. versionadded:: 3.12 @@ -1094,14 +1110,6 @@ iterations of the loop. .. versionadded:: 3.14 -.. opcode:: LOAD_CONST_IMMORTAL (consti) - - Pushes ``co_consts[consti]`` onto the stack. - Can be used when the constant value is known to be immortal. - - .. versionadded:: 3.14 - - .. opcode:: LOAD_NAME (namei) Pushes the value associated with ``co_names[namei]`` onto the stack. @@ -1128,6 +1136,48 @@ iterations of the loop. .. versionadded:: 3.12 +.. opcode:: BUILD_TEMPLATE + + Constructs a new :class:`~string.templatelib.Template` instance from a tuple + of strings and a tuple of interpolations and pushes the resulting object + onto the stack:: + + interpolations = STACK.pop() + strings = STACK.pop() + STACK.append(_build_template(strings, interpolations)) + + .. versionadded:: 3.14 + + +.. opcode:: BUILD_INTERPOLATION (format) + + Constructs a new :class:`~string.templatelib.Interpolation` instance from a + value and its source expression and pushes the resulting object onto the + stack. + + If no conversion or format specification is present, ``format`` is set to + ``2``. + + If the low bit of ``format`` is set, it indicates that the interpolation + contains a format specification. + + If ``format >> 2`` is non-zero, it indicates that the interpolation + contains a conversion. The value of ``format >> 2`` is the conversion type + (``0`` for no conversion, ``1`` for ``!s``, ``2`` for ``!r``, and + ``3`` for ``!a``):: + + conversion = format >> 2 + if format & 1: + format_spec = STACK.pop() + else: + format_spec = None + expression = STACK.pop() + value = STACK.pop() + STACK.append(_build_interpolation(value, expression, conversion, format_spec)) + + .. versionadded:: 3.14 + + .. opcode:: BUILD_TUPLE (count) Creates a tuple consuming *count* items from the stack, and pushes the @@ -1592,7 +1642,7 @@ iterations of the loop. Pushes a ``NULL`` to the stack. Used in the call sequence to match the ``NULL`` pushed by - :opcode:`LOAD_METHOD` for non-method calls. + :opcode:`!LOAD_METHOD` for non-method calls. .. versionadded:: 3.11 @@ -1623,9 +1673,13 @@ iterations of the loop. * ``0x02`` a dictionary of keyword-only parameters' default values * ``0x04`` a tuple of strings containing parameters' annotations * ``0x08`` a tuple containing cells for free variables, making a closure + * ``0x10`` the :term:`annotate function` for the function object .. versionadded:: 3.13 + .. versionchanged:: 3.14 + Added ``0x10`` to indicate the annotate function for the function object. + .. opcode:: BUILD_SLICE (argc) @@ -1773,7 +1827,7 @@ iterations of the loop. ignore it. Before, only opcodes ``>= HAVE_ARGUMENT`` had an argument. .. versionchanged:: 3.12 - Pseudo instructions were added to the :mod:`dis` module, and for them + Pseudo instructions were added to the :mod:`!dis` module, and for them it is not true that comparison with ``HAVE_ARGUMENT`` indicates whether they use their arg. @@ -1913,14 +1967,20 @@ but are replaced by real opcodes or removed before bytecode is generated. Marks the end of the code block associated with the last ``SETUP_FINALLY``, ``SETUP_CLEANUP`` or ``SETUP_WITH``. + +.. opcode:: LOAD_CONST_IMMORTAL (consti) + + Works as :opcode:`LOAD_CONST`, but is more efficient for immortal objects. + + .. opcode:: JUMP -.. opcode:: JUMP_NO_INTERRUPT + JUMP_NO_INTERRUPT Undirected relative jump instructions which are replaced by their directed (forward/backward) counterparts by the assembler. .. opcode:: JUMP_IF_TRUE -.. opcode:: JUMP_IF_FALSE + JUMP_IF_FALSE Conditional jumps which do not impact the stack. Replaced by the sequence ``COPY 1``, ``TO_BOOL``, ``POP_JUMP_IF_TRUE/FALSE``. @@ -1936,12 +1996,6 @@ but are replaced by real opcodes or removed before bytecode is generated. This opcode is now a pseudo-instruction. -.. opcode:: LOAD_METHOD - - Optimized unbound method lookup. Emitted as a ``LOAD_ATTR`` opcode - with a flag set in the arg. - - .. _opcode_collections: Opcode collections diff --git a/Doc/library/doctest.rst b/Doc/library/doctest.rst index b86fef9fd6f310..a303afe60b7a43 100644 --- a/Doc/library/doctest.rst +++ b/Doc/library/doctest.rst @@ -13,7 +13,7 @@ -------------- -The :mod:`doctest` module searches for pieces of text that look like interactive +The :mod:`!doctest` module searches for pieces of text that look like interactive Python sessions, and then executes those sessions to verify that they work exactly as shown. There are several common ways to use doctest: @@ -85,7 +85,7 @@ Here's a complete but small example module:: import doctest doctest.testmod() -If you run :file:`example.py` directly from the command line, :mod:`doctest` +If you run :file:`example.py` directly from the command line, :mod:`!doctest` works its magic: .. code-block:: shell-session @@ -94,7 +94,7 @@ works its magic: $ There's no output! That's normal, and it means all the examples worked. Pass -``-v`` to the script, and :mod:`doctest` prints a detailed log of what +``-v`` to the script, and :mod:`!doctest` prints a detailed log of what it's trying, and prints a summary at the end: .. code-block:: shell-session @@ -130,7 +130,7 @@ And so on, eventually ending with: Test passed. $ -That's all you need to know to start making productive use of :mod:`doctest`! +That's all you need to know to start making productive use of :mod:`!doctest`! Jump in. The following sections provide full details. Note that there are many examples of doctests in the standard Python test suite and libraries. Especially useful examples can be found in the standard test file @@ -174,7 +174,7 @@ with assorted summaries at the end. You can force verbose mode by passing ``verbose=True`` to :func:`testmod`, or prohibit it by passing ``verbose=False``. In either of those cases, -``sys.argv`` is not examined by :func:`testmod` (so passing ``-v`` or not +:data:`sys.argv` is not examined by :func:`testmod` (so passing ``-v`` or not has no effect). There is also a command line shortcut for running :func:`testmod`, see section @@ -231,7 +231,7 @@ documentation:: As with :func:`testmod`, :func:`testfile` won't display anything unless an example fails. If an example does fail, then the failing example(s) and the cause(s) of the failure(s) are printed to stdout, using the same format as -:func:`testmod`. +:func:`!testmod`. By default, :func:`testfile` looks for files in the calling module's directory. See section :ref:`doctest-basic-api` for a description of the optional arguments @@ -252,7 +252,7 @@ For more information on :func:`testfile`, see section :ref:`doctest-basic-api`. Command-line Usage ------------------ -The :mod:`doctest` module can be invoked as a script from the command line: +The :mod:`!doctest` module can be invoked as a script from the command line: .. code-block:: bash @@ -311,6 +311,13 @@ Which Docstrings Are Examined? The module docstring, and all function, class and method docstrings are searched. Objects imported into the module are not searched. +.. currentmodule:: None + +.. attribute:: module.__test__ + :no-typesetting: + +.. currentmodule:: doctest + In addition, there are cases when you want tests to be part of a module but not part of the help text, which requires that the tests not be included in the docstring. Doctest looks for a module-level variable called ``__test__`` and uses it to locate other @@ -343,6 +350,13 @@ searches them recursively for docstrings, which are then scanned for tests. Any classes found are recursively searched similarly, to test docstrings in their contained methods and nested classes. +.. note:: + + ``doctest`` can only automatically discover classes and functions that are + defined at the module level or inside other classes. + + Since nested classes and functions only exist when an outer function + is called, they cannot be discovered. Define them outside to make them visible. .. _doctest-finding-examples: @@ -436,7 +450,7 @@ The fine print: What's the Execution Context? ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -By default, each time :mod:`doctest` finds a docstring to test, it uses a +By default, each time :mod:`!doctest` finds a docstring to test, it uses a *shallow copy* of :mod:`!M`'s globals, so that running tests doesn't change the module's real globals, and so that one test in :mod:`!M` can't leave behind crumbs that accidentally allow another test to work. This means examples can @@ -533,7 +547,7 @@ Some details you should read once, but won't need to remember: * The interactive shell omits the traceback header line for some :exc:`SyntaxError`\ s. But doctest uses the traceback header line to distinguish exceptions from non-exceptions. So in the rare case where you need - to test a :exc:`SyntaxError` that omits the traceback header, you will need to + to test a :exc:`!SyntaxError` that omits the traceback header, you will need to manually add the traceback header line to your test example. .. index:: single: ^ (caret); marker @@ -716,7 +730,7 @@ The second group of options controls how test failures are reported: There is also a way to register new option flag names, though this isn't -useful unless you intend to extend :mod:`doctest` internals via subclassing: +useful unless you intend to extend :mod:`!doctest` internals via subclassing: .. function:: register_optionflag(name) @@ -819,7 +833,7 @@ disabling an option via ``-`` in a directive can be useful. Warnings ^^^^^^^^ -:mod:`doctest` is serious about requiring exact matches in expected output. If +:mod:`!doctest` is serious about requiring exact matches in expected output. If even a single character doesn't match, the test fails. This will probably surprise you a few times, as you learn exactly what Python does and doesn't guarantee about output. For example, when printing a set, Python doesn't @@ -860,15 +874,15 @@ The :const:`ELLIPSIS` directive gives a nice approach for the last example: Floating-point numbers are also subject to small output variations across -platforms, because Python defers to the platform C library for float formatting, -and C libraries vary widely in quality here. :: +platforms, because Python defers to the platform C library for some +floating-point calculations, and C libraries vary widely in quality here. :: - >>> 1./7 # risky - 0.14285714285714285 - >>> print(1./7) # safer - 0.142857142857 - >>> print(round(1./7, 6)) # much safer - 0.142857 + >>> 1000**0.1 # risky + 1.9952623149688797 + >>> round(1000**0.1, 9) # safer + 1.995262315 + >>> print(f'{1000**0.1:.4f}') # much safer + 1.9953 Numbers of the form ``I/2.**J`` are safe across all platforms, and I often contrive doctest examples to produce numbers of that form:: @@ -938,13 +952,13 @@ and :ref:`doctest-simple-testfile`. Optional argument *verbose* prints lots of stuff if true, and prints only failures if false; by default, or if ``None``, it's true if and only if ``'-v'`` - is in ``sys.argv``. + is in :data:`sys.argv`. Optional argument *report* prints a summary at the end when true, else prints nothing at the end. In verbose mode, the summary is detailed, else the summary is very brief (in fact, empty if all tests passed). - Optional argument *optionflags* (default value 0) takes the + Optional argument *optionflags* (default value ``0``) takes the :ref:`bitwise OR ` of option flags. See section :ref:`doctest-options`. @@ -1021,7 +1035,7 @@ Unittest API ------------ As your collection of doctest'ed modules grows, you'll want a way to run all -their doctests systematically. :mod:`doctest` provides two functions that can +their doctests systematically. :mod:`!doctest` provides two functions that can be used to create :mod:`unittest` test suites from modules and text files containing doctests. To integrate with :mod:`unittest` test discovery, include a :ref:`load_tests ` function in your test module:: @@ -1045,7 +1059,7 @@ from text files and modules with doctests: The returned :class:`unittest.TestSuite` is to be run by the unittest framework and runs the interactive examples in each file. If an example in any file - fails, then the synthesized unit test fails, and a :exc:`failureException` + fails, then the synthesized unit test fails, and a :exc:`~unittest.TestCase.failureException` exception is raised showing the name of the file containing the test and a (sometimes approximate) line number. If all the examples in a file are skipped, then the synthesized unit test is also marked as skipped. @@ -1078,13 +1092,14 @@ from text files and modules with doctests: Optional argument *setUp* specifies a set-up function for the test suite. This is called before running the tests in each file. The *setUp* function - will be passed a :class:`DocTest` object. The setUp function can access the - test globals as the *globs* attribute of the test passed. + will be passed a :class:`DocTest` object. The *setUp* function can access the + test globals as the :attr:`~DocTest.globs` attribute of the test passed. Optional argument *tearDown* specifies a tear-down function for the test suite. This is called after running the tests in each file. The *tearDown* - function will be passed a :class:`DocTest` object. The setUp function can - access the test globals as the *globs* attribute of the test passed. + function will be passed a :class:`DocTest` object. The *tearDown* function can + access the test globals as the :attr:`~DocTest.globs` attribute of the test + passed. Optional argument *globs* is a dictionary containing the initial global variables for the tests. A new copy of this dictionary is created for each @@ -1111,11 +1126,12 @@ from text files and modules with doctests: Convert doctest tests for a module to a :class:`unittest.TestSuite`. The returned :class:`unittest.TestSuite` is to be run by the unittest framework - and runs each doctest in the module. If any of the doctests fail, then the - synthesized unit test fails, and a :exc:`failureException` exception is raised + and runs each doctest in the module. + Each docstring is run as a separate unit test. + If any of the doctests fail, then the synthesized unit test fails, + and a :exc:`unittest.TestCase.failureException` exception is raised showing the name of the file containing the test and a (sometimes approximate) line number. If all the examples in a docstring are skipped, then the - synthesized unit test is also marked as skipped. Optional argument *module* provides the module to be tested. It can be a module object or a (possibly dotted) module name. If not specified, the module calling @@ -1123,7 +1139,7 @@ from text files and modules with doctests: Optional argument *globs* is a dictionary containing the initial global variables for the tests. A new copy of this dictionary is created for each - test. By default, *globs* is a new empty dictionary. + test. By default, *globs* is the module's :attr:`~module.__dict__`. Optional argument *extraglobs* specifies an extra set of global variables, which is merged into *globs*. By default, no extra globals are used. @@ -1132,7 +1148,7 @@ from text files and modules with doctests: drop-in replacement) that is used to extract doctests from the module. Optional arguments *setUp*, *tearDown*, and *optionflags* are the same as for - function :func:`DocFileSuite` above. + function :func:`DocFileSuite` above, but they are called for each docstring. This function uses the same search technique as :func:`testmod`. @@ -1140,12 +1156,6 @@ from text files and modules with doctests: :func:`DocTestSuite` returns an empty :class:`unittest.TestSuite` if *module* contains no docstrings instead of raising :exc:`ValueError`. -.. exception:: failureException - - When doctests which have been converted to unit tests by :func:`DocFileSuite` - or :func:`DocTestSuite` fail, this exception is raised showing the name of - the file containing the test and a (sometimes approximate) line number. - Under the covers, :func:`DocTestSuite` creates a :class:`unittest.TestSuite` out of :class:`!doctest.DocTestCase` instances, and :class:`!DocTestCase` is a subclass of :class:`unittest.TestCase`. :class:`!DocTestCase` isn't documented @@ -1158,21 +1168,21 @@ of :class:`!DocTestCase`. So both ways of creating a :class:`unittest.TestSuite` run instances of :class:`!DocTestCase`. This is important for a subtle reason: when you run -:mod:`doctest` functions yourself, you can control the :mod:`doctest` options in -use directly, by passing option flags to :mod:`doctest` functions. However, if -you're writing a :mod:`unittest` framework, :mod:`unittest` ultimately controls +:mod:`!doctest` functions yourself, you can control the :mod:`!doctest` options in +use directly, by passing option flags to :mod:`!doctest` functions. However, if +you're writing a :mod:`unittest` framework, :mod:`!unittest` ultimately controls when and how tests get run. The framework author typically wants to control -:mod:`doctest` reporting options (perhaps, e.g., specified by command line -options), but there's no way to pass options through :mod:`unittest` to -:mod:`doctest` test runners. +:mod:`!doctest` reporting options (perhaps, e.g., specified by command line +options), but there's no way to pass options through :mod:`!unittest` to +:mod:`!doctest` test runners. -For this reason, :mod:`doctest` also supports a notion of :mod:`doctest` +For this reason, :mod:`!doctest` also supports a notion of :mod:`!doctest` reporting flags specific to :mod:`unittest` support, via this function: .. function:: set_unittest_reportflags(flags) - Set the :mod:`doctest` reporting flags to use. + Set the :mod:`!doctest` reporting flags to use. Argument *flags* takes the :ref:`bitwise OR ` of option flags. See section :ref:`doctest-options`. Only "reporting flags" can be used. @@ -1181,12 +1191,12 @@ reporting flags specific to :mod:`unittest` support, via this function: :mod:`unittest`: the :meth:`!runTest` method of :class:`!DocTestCase` looks at the option flags specified for the test case when the :class:`!DocTestCase` instance was constructed. If no reporting flags were specified (which is the - typical and expected case), :mod:`!doctest`'s :mod:`unittest` reporting flags are + typical and expected case), :mod:`!doctest`'s :mod:`!unittest` reporting flags are :ref:`bitwise ORed ` into the option flags, and the option flags so augmented are passed to the :class:`DocTestRunner` instance created to run the doctest. If any reporting flags were specified when the :class:`!DocTestCase` instance was constructed, :mod:`!doctest`'s - :mod:`unittest` reporting flags are ignored. + :mod:`!unittest` reporting flags are ignored. The value of the :mod:`unittest` reporting flags in effect before the function was called is returned by the function. @@ -1279,7 +1289,7 @@ DocTest Objects .. attribute:: filename The name of the file that this :class:`DocTest` was extracted from; or - ``None`` if the filename is unknown, or if the :class:`DocTest` was not + ``None`` if the filename is unknown, or if the :class:`!DocTest` was not extracted from a file. @@ -1419,10 +1429,10 @@ DocTestFinder objects The globals for each :class:`DocTest` is formed by combining *globs* and *extraglobs* (bindings in *extraglobs* override bindings in *globs*). A new - shallow copy of the globals dictionary is created for each :class:`DocTest`. - If *globs* is not specified, then it defaults to the module's *__dict__*, if - specified, or ``{}`` otherwise. If *extraglobs* is not specified, then it - defaults to ``{}``. + shallow copy of the globals dictionary is created for each :class:`!DocTest`. + If *globs* is not specified, then it defaults to the module's + :attr:`~module.__dict__`, if specified, or ``{}`` otherwise. + If *extraglobs* is not specified, then it defaults to ``{}``. .. _doctest-doctestparser: @@ -1446,7 +1456,7 @@ DocTestParser objects :class:`DocTest` object. *globs*, *name*, *filename*, and *lineno* are attributes for the new - :class:`DocTest` object. See the documentation for :class:`DocTest` for more + :class:`!DocTest` object. See the documentation for :class:`DocTest` for more information. @@ -1461,7 +1471,7 @@ DocTestParser objects Divide the given string into examples and intervening text, and return them as a list of alternating :class:`Example`\ s and strings. Line numbers for the - :class:`Example`\ s are 0-based. The optional argument *name* is a name + :class:`!Example`\ s are 0-based. The optional argument *name* is a name identifying this string, and is only used for error messages. @@ -1501,7 +1511,7 @@ DocTestRunner objects :class:`OutputChecker`. This comparison may be customized with a number of option flags; see section :ref:`doctest-options` for more information. If the option flags are insufficient, then the comparison may also be customized by - passing a subclass of :class:`OutputChecker` to the constructor. + passing a subclass of :class:`!OutputChecker` to the constructor. The test runner's display output can be controlled in two ways. First, an output function can be passed to :meth:`run`; this function will be called @@ -1540,7 +1550,7 @@ DocTestRunner objects output; it should not be called directly. *example* is the example about to be processed. *test* is the test - *containing example*. *out* is the output function that was passed to + containing *example*. *out* is the output function that was passed to :meth:`DocTestRunner.run`. @@ -1889,7 +1899,7 @@ There are two exceptions that may be raised by :class:`DebugRunner` instances: Soapbox ------- -As mentioned in the introduction, :mod:`doctest` has grown to have three primary +As mentioned in the introduction, :mod:`!doctest` has grown to have three primary uses: #. Checking examples in docstrings. @@ -1907,7 +1917,7 @@ this that needs to be learned---it may not be natural at first. Examples should add genuine value to the documentation. A good example can often be worth many words. If done with care, the examples will be invaluable for your users, and will pay back the time it takes to collect them many times over as the years go -by and things change. I'm still amazed at how often one of my :mod:`doctest` +by and things change. I'm still amazed at how often one of my :mod:`!doctest` examples stops working after a "harmless" change. Doctest also makes an excellent tool for regression testing, especially if you @@ -1940,7 +1950,7 @@ several options for organizing tests: containing test cases for the named topics. These functions can be included in the same file as the module, or separated out into a separate test file. -* Define a ``__test__`` dictionary mapping from regression test topics to +* Define a :attr:`~module.__test__` dictionary mapping from regression test topics to docstrings containing test cases. When you have placed your tests in a module, the module can itself be the test diff --git a/Doc/library/email.charset.rst b/Doc/library/email.charset.rst index 6875af2be49d7a..76a57031862c85 100644 --- a/Doc/library/email.charset.rst +++ b/Doc/library/email.charset.rst @@ -19,7 +19,7 @@ registry and several convenience methods for manipulating this registry. Instances of :class:`Charset` are used in several other modules within the :mod:`email` package. -Import this class from the :mod:`email.charset` module. +Import this class from the :mod:`!email.charset` module. .. class:: Charset(input_charset=DEFAULT_CHARSET) @@ -164,7 +164,7 @@ Import this class from the :mod:`email.charset` module. This method allows you to compare two :class:`Charset` instances for inequality. -The :mod:`email.charset` module also provides the following functions for adding +The :mod:`!email.charset` module also provides the following functions for adding new entries to the global character set, alias, and codec registries: diff --git a/Doc/library/email.compat32-message.rst b/Doc/library/email.compat32-message.rst index 4285c436e8da80..11b4d908fcd7d6 100644 --- a/Doc/library/email.compat32-message.rst +++ b/Doc/library/email.compat32-message.rst @@ -96,7 +96,7 @@ Here are the methods of the :class:`Message` class: text = fp.getvalue() If the message object contains binary data that is not encoded according - to RFC standards, the non-compliant data will be replaced by unicode + to RFC standards, the non-compliant data will be replaced by Unicode "unknown character" code points. (See also :meth:`.as_bytes` and :class:`~email.generator.BytesGenerator`.) @@ -181,7 +181,7 @@ Here are the methods of the :class:`Message` class: :meth:`set_payload` instead. This is a legacy method. On the - :class:`~email.emailmessage.EmailMessage` class its functionality is + :class:`~email.message.EmailMessage` class its functionality is replaced by :meth:`~email.message.EmailMessage.set_content` and the related ``make`` and ``add`` methods. @@ -224,7 +224,7 @@ Here are the methods of the :class:`Message` class: ASCII charset. This is a legacy method. On the - :class:`~email.emailmessage.EmailMessage` class its functionality is + :class:`~email.message.EmailMessage` class its functionality is replaced by :meth:`~email.message.EmailMessage.get_content` and :meth:`~email.message.EmailMessage.iter_parts`. @@ -236,7 +236,7 @@ Here are the methods of the :class:`Message` class: the message's default character set; see :meth:`set_charset` for details. This is a legacy method. On the - :class:`~email.emailmessage.EmailMessage` class its functionality is + :class:`~email.message.EmailMessage` class its functionality is replaced by :meth:`~email.message.EmailMessage.set_content`. @@ -265,9 +265,9 @@ Here are the methods of the :class:`Message` class: using that :mailheader:`Content-Transfer-Encoding` and is not modified. This is a legacy method. On the - :class:`~email.emailmessage.EmailMessage` class its functionality is + :class:`~email.message.EmailMessage` class its functionality is replaced by the *charset* parameter of the - :meth:`email.emailmessage.EmailMessage.set_content` method. + :meth:`email.message.EmailMessage.set_content` method. .. method:: get_charset() @@ -276,7 +276,7 @@ Here are the methods of the :class:`Message` class: message's payload. This is a legacy method. On the - :class:`~email.emailmessage.EmailMessage` class it always returns + :class:`~email.message.EmailMessage` class it always returns ``None``. @@ -486,7 +486,7 @@ Here are the methods of the :class:`Message` class: search instead of :mailheader:`Content-Type`. This is a legacy method. On the - :class:`~email.emailmessage.EmailMessage` class its functionality is + :class:`~email.message.EmailMessage` class its functionality is replaced by the *params* property of the individual header objects returned by the header access methods. @@ -524,7 +524,7 @@ Here are the methods of the :class:`Message` class: to ``False``. This is a legacy method. On the - :class:`~email.emailmessage.EmailMessage` class its functionality is + :class:`~email.message.EmailMessage` class its functionality is replaced by the *params* property of the individual header objects returned by the header access methods. @@ -579,7 +579,7 @@ Here are the methods of the :class:`Message` class: header is also added. This is a legacy method. On the - :class:`~email.emailmessage.EmailMessage` class its functionality is + :class:`~email.message.EmailMessage` class its functionality is replaced by the ``make_`` and ``add_`` methods. diff --git a/Doc/library/email.contentmanager.rst b/Doc/library/email.contentmanager.rst index b33fe82a6e4c9f..4b57eed42c3131 100644 --- a/Doc/library/email.contentmanager.rst +++ b/Doc/library/email.contentmanager.rst @@ -99,9 +99,9 @@ Currently the email package provides only one concrete content manager, This content manager provides only a minimum interface beyond that provided by :class:`~email.message.Message` itself: it deals only with text, raw - byte strings, and :class:`~email.message.Message` objects. Nevertheless, it + bytes, and :class:`~email.message.Message` objects. Nevertheless, it provides significant advantages compared to the base API: ``get_content`` on - a text part will return a unicode string without the application needing to + a text part will return a string without the application needing to manually decode it, ``set_content`` provides a rich set of options for controlling the headers added to a part and controlling the content transfer encoding, and it enables the use of the various ``add_`` methods, thereby @@ -114,7 +114,7 @@ Currently the email package provides only one concrete content manager, parts), or a ``bytes`` object (for all other non-multipart types). Raise a :exc:`KeyError` if called on a ``multipart``. If the part is a ``text`` part and *errors* is specified, use it as the error handler when - decoding the payload to unicode. The default error handler is + decoding the payload to a string. The default error handler is ``replace``. .. method:: set_content(msg, <'str'>, subtype="plain", charset='utf-8', \ diff --git a/Doc/library/email.encoders.rst b/Doc/library/email.encoders.rst index 9c8c8c9234ed7a..1a9a1cad3a619e 100644 --- a/Doc/library/email.encoders.rst +++ b/Doc/library/email.encoders.rst @@ -25,7 +25,7 @@ is especially true for :mimetype:`image/\*` and :mimetype:`text/\*` type message containing binary data. The :mod:`email` package provides some convenient encoders in its -:mod:`~email.encoders` module. These encoders are actually used by the +:mod:`!encoders` module. These encoders are actually used by the :class:`~email.mime.audio.MIMEAudio` and :class:`~email.mime.image.MIMEImage` class constructors to provide default encodings. All encoder functions take exactly one argument, the message object to encode. They usually extract the diff --git a/Doc/library/email.errors.rst b/Doc/library/email.errors.rst index 689e7397cbcf1f..2f7c9140cfcbe5 100644 --- a/Doc/library/email.errors.rst +++ b/Doc/library/email.errors.rst @@ -8,7 +8,7 @@ -------------- -The following exception classes are defined in the :mod:`email.errors` module: +The following exception classes are defined in the :mod:`!email.errors` module: .. exception:: MessageError() diff --git a/Doc/library/email.examples.rst b/Doc/library/email.examples.rst index 492a8354d8bf85..7586cbd25f9f3b 100644 --- a/Doc/library/email.examples.rst +++ b/Doc/library/email.examples.rst @@ -7,7 +7,7 @@ Here are a few examples of how to use the :mod:`email` package to read, write, and send simple email messages, as well as more complex MIME messages. First, let's see how to create and send a simple text message (both the -text content and the addresses may contain unicode characters): +text content and the addresses may contain Unicode characters): .. literalinclude:: ../includes/email-simple.py diff --git a/Doc/library/email.generator.rst b/Doc/library/email.generator.rst index a3132d02687bc9..6f4f813a0f84d8 100644 --- a/Doc/library/email.generator.rst +++ b/Doc/library/email.generator.rst @@ -232,7 +232,7 @@ a formatted string representation of a message object. For more detail, see :mod:`email.message`. -The :mod:`email.generator` module also provides a derived class, +The :mod:`!email.generator` module also provides a derived class, :class:`DecodedGenerator`, which is like the :class:`Generator` base class, except that non-\ :mimetype:`text` parts are not serialized, but are instead represented in the output stream by a string derived from a template filled diff --git a/Doc/library/email.header.rst b/Doc/library/email.header.rst index 219fad0d2f6745..65e2d0367fd768 100644 --- a/Doc/library/email.header.rst +++ b/Doc/library/email.header.rst @@ -28,13 +28,13 @@ transferred using only 7-bit ASCII characters, so a slew of RFCs have been written describing how to encode email containing non-ASCII characters into :rfc:`2822`\ -compliant format. These RFCs include :rfc:`2045`, :rfc:`2046`, :rfc:`2047`, and :rfc:`2231`. The :mod:`email` package supports these standards -in its :mod:`email.header` and :mod:`email.charset` modules. +in its :mod:`!email.header` and :mod:`email.charset` modules. If you want to include non-ASCII characters in your email headers, say in the :mailheader:`Subject` or :mailheader:`To` fields, you should use the :class:`Header` class and assign the field in the :class:`~email.message.Message` object to an instance of :class:`Header` instead of using a string for the header -value. Import the :class:`Header` class from the :mod:`email.header` module. +value. Import the :class:`Header` class from the :mod:`!email.header` module. For example:: >>> from email.message import Message @@ -49,7 +49,7 @@ For example:: Notice here how we wanted the :mailheader:`Subject` field to contain a non-ASCII character? We did this by creating a :class:`Header` instance and passing in -the character set that the byte string was encoded in. When the subsequent +the character set to use when encoding it. When the subsequent :class:`~email.message.Message` instance was flattened, the :mailheader:`Subject` field was properly :rfc:`2047` encoded. MIME-aware mail readers would show this header using the embedded ISO-8859-1 character. @@ -150,7 +150,7 @@ Here is the :class:`Header` class description: .. method:: __str__() Returns an approximation of the :class:`Header` as a string, using an - unlimited line length. All pieces are converted to unicode using the + unlimited line length. All pieces are decoded using the specified encoding and joined together appropriately. Any pieces with a charset of ``'unknown-8bit'`` are decoded as ASCII using the ``'replace'`` error handler. @@ -170,7 +170,7 @@ Here is the :class:`Header` class description: This method allows you to compare two :class:`Header` instances for inequality. -The :mod:`email.header` module also provides the following convenient functions. +The :mod:`!email.header` module also provides the following convenient functions. .. function:: decode_header(header) @@ -178,16 +178,36 @@ The :mod:`email.header` module also provides the following convenient functions. Decode a message header value without converting the character set. The header value is in *header*. - This function returns a list of ``(decoded_string, charset)`` pairs containing - each of the decoded parts of the header. *charset* is ``None`` for non-encoded - parts of the header, otherwise a lower case string containing the name of the - character set specified in the encoded string. + For historical reasons, this function may return either: - Here's an example:: + 1. A list of pairs containing each of the decoded parts of the header, + ``(decoded_bytes, charset)``, where *decoded_bytes* is always an instance of + :class:`bytes`, and *charset* is either: + + - A lower case string containing the name of the character set specified. + + - ``None`` for non-encoded parts of the header. + + 2. A list of length 1 containing a pair ``(string, None)``, where + *string* is always an instance of :class:`str`. + + An :exc:`email.errors.HeaderParseError` may be raised when certain decoding + errors occur (e.g. a base64 decoding exception). + + Here are examples: >>> from email.header import decode_header >>> decode_header('=?iso-8859-1?q?p=F6stal?=') [(b'p\xf6stal', 'iso-8859-1')] + >>> decode_header('unencoded_string') + [('unencoded_string', None)] + >>> decode_header('bar =?utf-8?B?ZsOzbw==?=') + [(b'bar ', None), (b'f\xc3\xb3o', 'utf-8')] + + .. note:: + + This function exists for backwards compatibility only. For + new code, we recommend using :class:`email.headerregistry.HeaderRegistry`. .. function:: make_header(decoded_seq, maxlinelen=None, header_name=None, continuation_ws=' ') @@ -203,3 +223,7 @@ The :mod:`email.header` module also provides the following convenient functions. :class:`Header` instance. Optional *maxlinelen*, *header_name*, and *continuation_ws* are as in the :class:`Header` constructor. + .. note:: + + This function exists for backwards compatibility only, and is + not recommended for use in new code. diff --git a/Doc/library/email.headerregistry.rst b/Doc/library/email.headerregistry.rst index 7f8044932fae99..37d24a3ad16bbd 100644 --- a/Doc/library/email.headerregistry.rst +++ b/Doc/library/email.headerregistry.rst @@ -43,7 +43,7 @@ headers. *name* and *value* are passed to ``BaseHeader`` from the :attr:`~email.policy.EmailPolicy.header_factory` call. The string value of - any header object is the *value* fully decoded to unicode. + any header object is the *value* fully decoded to a string. This base class defines the following read-only properties: @@ -96,11 +96,12 @@ headers. ``kwds`` is a dictionary containing one pre-initialized key, ``defects``. ``defects`` is an empty list. The parse method should append any detected defects to this list. On return, the ``kwds`` dictionary *must* contain - values for at least the keys ``decoded`` and ``defects``. ``decoded`` - should be the string value for the header (that is, the header value fully - decoded to unicode). The parse method should assume that *string* may + values for at least the keys ``decoded``, ``defects`` and ``parse_tree``. + ``decoded`` should be the string value for the header (that is, the header + value fully decoded to a string). ``parse_tree`` is set to the parse tree obtained + from parsing the header. The parse method should assume that *string* may contain content-transfer-encoded parts, but should correctly handle all valid - unicode characters as well so that it can parse un-encoded header values. + Unicode characters as well so that it can parse un-encoded header values. ``BaseHeader``'s ``__new__`` then creates the header instance, and calls its ``init`` method. The specialized class only needs to provide an ``init`` @@ -128,7 +129,7 @@ headers. mechanism for encoding non-ASCII text as ASCII characters within a header value. When a *value* containing encoded words is passed to the constructor, the ``UnstructuredHeader`` parser converts such encoded words - into unicode, following the :rfc:`2047` rules for unstructured text. The + into a string, following the :rfc:`2047` rules for unstructured text. The parser uses heuristics to attempt to decode certain non-compliant encoded words. Defects are registered in such cases, as well as defects for issues such as invalid characters within the encoded words or the non-encoded text. @@ -205,8 +206,8 @@ headers. the list of addresses is "flattened" into a one dimensional list). The ``decoded`` value of the header will have all encoded words decoded to - unicode. :class:`~encodings.idna` encoded domain names are also decoded to - unicode. The ``decoded`` value is set by :ref:`joining ` the + a string. :class:`~encodings.idna` encoded domain names are also decoded to + a string. The ``decoded`` value is set by :ref:`joining ` the :class:`str` value of the elements of the ``groups`` attribute with ``', '``. @@ -294,7 +295,7 @@ variant, :attr:`~.BaseHeader.max_count` is set to 1. ``inline`` and ``attachment`` are the only valid values in common use. -.. class:: ContentTransferEncoding +.. class:: ContentTransferEncodingHeader Handles the :mailheader:`Content-Transfer-Encoding` header. @@ -390,7 +391,7 @@ construct structured values to assign to specific headers. *domain*, in which case *username* and *domain* will be parsed from the *addr_spec*. An *addr_spec* must be a properly RFC quoted string; if it is not ``Address`` will raise an error. Unicode characters are allowed and - will be property encoded when serialized. However, per the RFCs, unicode is + will be property encoded when serialized. However, per the RFCs, Unicode is *not* allowed in the username portion of the address. .. attribute:: display_name diff --git a/Doc/library/email.iterators.rst b/Doc/library/email.iterators.rst index 090981d84b4de3..ed300cdb30fdd6 100644 --- a/Doc/library/email.iterators.rst +++ b/Doc/library/email.iterators.rst @@ -10,7 +10,7 @@ Iterating over a message object tree is fairly easy with the :meth:`Message.walk ` method. The -:mod:`email.iterators` module provides some useful higher level iterations over +:mod:`!email.iterators` module provides some useful higher level iterations over message object trees. diff --git a/Doc/library/email.message.rst b/Doc/library/email.message.rst index 71d6e321f387bc..f6908d2e6e9748 100644 --- a/Doc/library/email.message.rst +++ b/Doc/library/email.message.rst @@ -14,7 +14,7 @@ .. versionadded:: 3.6 [1]_ The central class in the :mod:`email` package is the :class:`EmailMessage` -class, imported from the :mod:`email.message` module. It is the base class for +class, imported from the :mod:`!email.message` module. It is the base class for the :mod:`email` object model. :class:`EmailMessage` provides the core functionality for setting and querying header fields, for accessing message bodies, and for creating or modifying structured messages. @@ -57,7 +57,7 @@ message objects. :class:`~email.policy.default` policy, which follows the rules of the email RFCs except for line endings (instead of the RFC mandated ``\r\n``, it uses the Python standard ``\n`` line endings). For more information see the - :mod:`~email.policy` documentation. + :mod:`~email.policy` documentation. [2]_ .. method:: as_string(unixfrom=False, maxheaderlen=None, policy=None) @@ -749,3 +749,9 @@ message objects. .. [1] Originally added in 3.4 as a :term:`provisional module `. Docs for legacy message class moved to :ref:`compat32_message`. + +.. [2] The :class:`EmailMessage` class requires a policy that provides a + ``content_manager`` attribute for content management methods like + ``set_content()`` and ``get_content()`` to work. The legacy + :const:`~email.policy.compat32` policy does not support these methods + and should not be used with :class:`EmailMessage`. diff --git a/Doc/library/email.parser.rst b/Doc/library/email.parser.rst index 439b5c8f34b65a..6a67bf7c8e555d 100644 --- a/Doc/library/email.parser.rst +++ b/Doc/library/email.parser.rst @@ -116,7 +116,7 @@ Here is the API for the :class:`BytesFeedParser`: Works like :class:`BytesFeedParser` except that the input to the :meth:`~BytesFeedParser.feed` method must be a string. This is of limited utility, since the only way for such a message to be valid is for it to - contain only ASCII text or, if :attr:`~email.policy.Policy.utf8` is + contain only ASCII text or, if :attr:`~email.policy.EmailPolicy.utf8` is ``True``, no binary attachments. .. versionchanged:: 3.3 Added the *policy* keyword. @@ -125,10 +125,10 @@ Here is the API for the :class:`BytesFeedParser`: Parser API ^^^^^^^^^^ -The :class:`BytesParser` class, imported from the :mod:`email.parser` module, +The :class:`BytesParser` class, imported from the :mod:`!email.parser` module, provides an API that can be used to parse a message when the complete contents of the message are available in a :term:`bytes-like object` or file. The -:mod:`email.parser` module also provides :class:`Parser` for parsing strings, +:mod:`!email.parser` module also provides :class:`Parser` for parsing strings, and header-only parsers, :class:`BytesHeaderParser` and :class:`HeaderParser`, which can be used if you're only interested in the headers of the message. :class:`BytesHeaderParser` and :class:`HeaderParser` @@ -155,11 +155,11 @@ message body, instead setting the payload to the raw body. Read all the data from the binary file-like object *fp*, parse the resulting bytes, and return the message object. *fp* must support - both the :meth:`~io.IOBase.readline` and the :meth:`~io.IOBase.read` + both the :meth:`~io.IOBase.readline` and the :meth:`~io.BufferedIOBase.read` methods. The bytes contained in *fp* must be formatted as a block of :rfc:`5322` - (or, if :attr:`~email.policy.Policy.utf8` is ``True``, :rfc:`6532`) + (or, if :attr:`~email.policy.EmailPolicy.utf8` is ``True``, :rfc:`6532`) style headers and header continuation lines, optionally preceded by an envelope header. The header block is terminated either by the end of the data or by a blank line. Following the header block is the body of the diff --git a/Doc/library/email.policy.rst b/Doc/library/email.policy.rst index 6b997ee784f6e4..64074d8cbc7d50 100644 --- a/Doc/library/email.policy.rst +++ b/Doc/library/email.policy.rst @@ -493,7 +493,7 @@ added matters. To illustrate:: Otherwise the *name*, and the *value* with any CR or LF characters removed, are passed to the ``header_factory``, and the resulting header object is returned. Any surrogateescaped bytes get turned into - the unicode unknown-character glyph. + the Unicode unknown-character glyph. .. method:: fold(name, value) @@ -588,10 +588,10 @@ the email package is changed from the Python 3.2 API in the following ways: From the application view, this means that any header obtained through the :class:`~email.message.EmailMessage` is a header object with extra -attributes, whose string value is the fully decoded unicode value of the +attributes, whose string value is the fully decoded value of the header. Likewise, a header may be assigned a new value, or a new header -created, using a unicode string, and the policy will take care of converting -the unicode string into the correct RFC encoded form. +created, using a string, and the policy will take care of converting +the string into the correct RFC encoded form. The header objects and their attributes are described in :mod:`~email.headerregistry`. @@ -602,7 +602,7 @@ The header objects and their attributes are described in This concrete :class:`Policy` is the backward compatibility policy. It replicates the behavior of the email package in Python 3.2. The - :mod:`~email.policy` module also defines an instance of this class, + :mod:`!policy` module also defines an instance of this class, :const:`compat32`, that is used as the default policy. Thus the default behavior of the email package is to maintain compatibility with Python 3.2. @@ -662,6 +662,13 @@ The header objects and their attributes are described in An instance of :class:`Compat32`, providing backward compatibility with the behavior of the email package in Python 3.2. + .. note:: + + The :const:`compat32` policy should not be used as a policy for + :class:`~email.message.EmailMessage` objects, and should only be used + to serialize messages that were created using the :const:`compat32` + policy. + .. rubric:: Footnotes diff --git a/Doc/library/email.rst b/Doc/library/email.rst index 66c42e4a5008ee..e1e0a08e6ee934 100644 --- a/Doc/library/email.rst +++ b/Doc/library/email.rst @@ -12,10 +12,10 @@ -------------- -The :mod:`email` package is a library for managing email messages. It is +The :mod:`!email` package is a library for managing email messages. It is specifically *not* designed to do any sending of email messages to SMTP (:rfc:`2821`), NNTP, or other servers; those are functions of modules such as -:mod:`smtplib`. The :mod:`email` package attempts to be as +:mod:`smtplib`. The :mod:`!email` package attempts to be as RFC-compliant as possible, supporting :rfc:`5322` and :rfc:`6532`, as well as such MIME-related RFCs as :rfc:`2045`, :rfc:`2046`, :rfc:`2047`, :rfc:`2183`, and :rfc:`2231`. @@ -57,7 +57,7 @@ server. The email package does its best to hide the details of the various governing RFCs from the application. Conceptually the application should be able to -treat the email message as a structured tree of unicode text and binary +treat the email message as a structured tree of Unicode text and binary attachments, without having to worry about how these are represented when serialized. In practice, however, it is often necessary to be aware of at least some of the rules governing MIME messages and their structure, @@ -68,7 +68,7 @@ high level structure in question, and not the details of how those structures are represented. Since MIME content types are used widely in modern internet software (not just email), this will be a familiar concept to many programmers. -The following sections describe the functionality of the :mod:`email` package. +The following sections describe the functionality of the :mod:`!email` package. We start with the :mod:`~email.message` object model, which is the primary interface an application will use, and follow that with the :mod:`~email.parser` and :mod:`~email.generator` components. Then we cover the @@ -87,7 +87,7 @@ to advanced applications. Following those is a set of examples of using the fundamental parts of the APIs covered in the preceding sections. -The foregoing represent the modern (unicode friendly) API of the email package. +The foregoing represent the modern (Unicode friendly) API of the email package. The remaining sections, starting with the :class:`~email.message.Message` class, cover the legacy :data:`~email.policy.compat32` API that deals much more directly with the details of how email messages are represented. The @@ -102,7 +102,7 @@ compatibility reasons. :class:`~email.message.EmailMessage`/:class:`~email.policy.EmailPolicy` API. -Contents of the :mod:`email` package documentation: +Contents of the :mod:`!email` package documentation: .. toctree:: diff --git a/Doc/library/email.utils.rst b/Doc/library/email.utils.rst index 611549604fda15..ed514c1c58d460 100644 --- a/Doc/library/email.utils.rst +++ b/Doc/library/email.utils.rst @@ -8,7 +8,7 @@ -------------- -There are a couple of useful utilities provided in the :mod:`email.utils` +There are a couple of useful utilities provided in the :mod:`!email.utils` module: .. function:: localtime(dt=None) @@ -205,7 +205,7 @@ of the new API. When a header parameter is encoded in :rfc:`2231` format, :meth:`Message.get_param ` may return a 3-tuple containing the character set, - language, and value. :func:`collapse_rfc2231_value` turns this into a unicode + language, and value. :func:`collapse_rfc2231_value` turns this into a string. Optional *errors* is passed to the *errors* argument of :class:`str`'s :func:`~str.encode` method; it defaults to ``'replace'``. Optional *fallback_charset* specifies the character set to use if the one in the diff --git a/Doc/library/ensurepip.rst b/Doc/library/ensurepip.rst index fa102c4a080103..e0d77229b11802 100644 --- a/Doc/library/ensurepip.rst +++ b/Doc/library/ensurepip.rst @@ -11,7 +11,7 @@ -------------- -The :mod:`ensurepip` package provides support for bootstrapping the ``pip`` +The :mod:`!ensurepip` package provides support for bootstrapping the ``pip`` installer into an existing Python installation or virtual environment. This bootstrapping approach reflects the fact that ``pip`` is an independent project with its own release cycle, and the latest available stable version @@ -30,6 +30,8 @@ when creating a virtual environment) or after explicitly uninstalling needed to bootstrap ``pip`` are included as internal parts of the package. +.. include:: ../includes/optional-module.rst + .. seealso:: :ref:`installing-index` @@ -40,7 +42,9 @@ when creating a virtual environment) or after explicitly uninstalling .. include:: ../includes/wasm-mobile-notavail.rst -Command line interface +.. _ensurepip-cli: + +Command-line interface ---------------------- .. program:: ensurepip @@ -95,7 +99,7 @@ Providing both of the script selection options will trigger an exception. Module API ---------- -:mod:`ensurepip` exposes two functions for programmatic use: +:mod:`!ensurepip` exposes two functions for programmatic use: .. function:: version() diff --git a/Doc/library/enum.rst b/Doc/library/enum.rst index c9b2c7d76b6746..b0581382923efd 100644 --- a/Doc/library/enum.rst +++ b/Doc/library/enum.rst @@ -61,7 +61,7 @@ are not normal Python classes. See --------------- -Module Contents +Module contents --------------- :class:`EnumType` @@ -120,30 +120,30 @@ Module Contents :class:`StrEnum` defaults to the lower-cased version of the member name, while other Enums default to 1 and increase from there. - :func:`~enum.property` + :deco:`~enum.property` Allows :class:`Enum` members to have attributes without conflicting with member names. The ``value`` and ``name`` attributes are implemented this way. - :func:`unique` + :deco:`unique` Enum class decorator that ensures only one name is bound to any one value. - :func:`verify` + :deco:`verify` Enum class decorator that checks user-selectable constraints on an enumeration. - :func:`member` + :deco:`member` Make ``obj`` a member. Can be used as a decorator. - :func:`nonmember` + :deco:`nonmember` Do not make ``obj`` a member. Can be used as a decorator. - :func:`global_enum` + :deco:`global_enum` Modify the :class:`str() ` and :func:`repr` of an enum to show its members as belonging to the module instead of its class, @@ -153,6 +153,12 @@ Module Contents Return a list of all power-of-two integers contained in a flag. + :func:`enum.bin` + + Like built-in :func:`bin`, except negative values are represented in + two's complement, and the leading bit always indicates sign + (``0`` implies positive, ``1`` implies negative). + .. versionadded:: 3.6 ``Flag``, ``IntFlag``, ``auto`` .. versionadded:: 3.11 ``StrEnum``, ``EnumCheck``, ``ReprEnum``, ``FlagBoundary``, ``property``, ``member``, ``nonmember``, ``global_enum``, ``show_flag_values`` @@ -160,7 +166,7 @@ Module Contents --------------- -Data Types +Data types ---------- @@ -175,6 +181,10 @@ Data Types final *enum*, as well as creating the enum members, properly handling duplicates, providing iteration over the enum class, etc. + .. versionadded:: 3.11 + + Before 3.11 ``EnumType`` was called ``EnumMeta``, which is still available as an alias. + .. method:: EnumType.__call__(cls, value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None) This method is called in two different ways: @@ -206,7 +216,7 @@ Data Types >>> Color.RED.value in Color True - .. versionchanged:: 3.12 + .. versionchanged:: 3.12 Before Python 3.12, a ``TypeError`` is raised if a non-Enum-member is used in a containment check. @@ -235,7 +245,7 @@ Data Types .. method:: EnumType.__len__(cls) - Returns the number of member in *cls*:: + Returns the number of members in *cls*:: >>> len(Color) 3 @@ -251,20 +261,6 @@ Data Types >>> list(reversed(Color)) [, , ] - .. method:: EnumType._add_alias_ - - Adds a new name as an alias to an existing member. Raises a - :exc:`NameError` if the name is already assigned to a different member. - - .. method:: EnumType._add_value_alias_ - - Adds a new value as an alias to an existing member. Raises a - :exc:`ValueError` if the value is already linked with a different member. - - .. versionadded:: 3.11 - - Before 3.11 ``EnumType`` was called ``EnumMeta``, which is still available as an alias. - .. class:: Enum @@ -311,6 +307,28 @@ Data Types No longer used, kept for backward compatibility. (class attribute, removed during class creation). + The :attr:`~Enum._order_` attribute can be provided to help keep Python 2 / Python 3 code in sync. + It will be checked against the actual order of the enumeration and raise an error if the two do not match:: + + >>> class Color(Enum): + ... _order_ = 'RED GREEN BLUE' + ... RED = 1 + ... BLUE = 3 + ... GREEN = 2 + ... + Traceback (most recent call last): + ... + TypeError: member order does not match _order_: + ['RED', 'BLUE', 'GREEN'] + ['RED', 'GREEN', 'BLUE'] + + .. note:: + + In Python 2 code the :attr:`~Enum._order_` attribute is necessary as definition + order is lost before it can be recorded. + + .. versionadded:: 3.6 + .. attribute:: Enum._ignore_ ``_ignore_`` is only used during creation and is removed from the @@ -320,12 +338,15 @@ Data Types names will also be removed from the completed enumeration. See :ref:`TimePeriod ` for an example. + .. versionadded:: 3.7 + .. method:: Enum.__dir__(self) Returns ``['__class__', '__doc__', '__module__', 'name', 'value']`` and any public methods defined on *self.__class__*:: - >>> from datetime import date + >>> from enum import Enum + >>> import datetime as dt >>> class Weekday(Enum): ... MONDAY = 1 ... TUESDAY = 2 @@ -336,7 +357,7 @@ Data Types ... SUNDAY = 7 ... @classmethod ... def today(cls): - ... print('today is %s' % cls(date.today().isoweekday()).name) + ... print(f'today is {cls(dt.date.today().isoweekday()).name}') ... >>> dir(Weekday.SATURDAY) ['__class__', '__doc__', '__eq__', '__hash__', '__module__', 'name', 'today', 'value'] @@ -349,9 +370,18 @@ Data Types :last_values: A list of the previous values. A *staticmethod* that is used to determine the next value returned by - :class:`auto`:: + :class:`auto`. - >>> from enum import auto + .. note:: + For standard :class:`Enum` classes the next value chosen is the highest + value seen incremented by one. + + For :class:`Flag` classes the next value chosen will be the next highest + power-of-two. + + This method may be overridden, e.g.:: + + >>> from enum import auto, Enum >>> class PowersOfThree(Enum): ... @staticmethod ... def _generate_next_value_(name, start, count, last_values): @@ -362,6 +392,10 @@ Data Types >>> PowersOfThree.SECOND.value 9 + .. versionadded:: 3.6 + .. versionchanged:: 3.13 + Prior versions would use the last seen value instead of the highest value. + .. method:: Enum.__init__(self, *args, **kwds) By default, does nothing. If multiple values are given in the member @@ -383,7 +417,7 @@ Data Types A *classmethod* for looking up values not found in *cls*. By default it does nothing, but can be overridden to implement custom search behavior:: - >>> from enum import StrEnum + >>> from enum import auto, StrEnum >>> class Build(StrEnum): ... DEBUG = auto() ... OPTIMIZED = auto() @@ -400,6 +434,8 @@ Data Types >>> Build('deBUG') + .. versionadded:: 3.6 + .. method:: Enum.__new__(cls, *args, **kwds) By default, doesn't exist. If specified, either in the enum class @@ -422,6 +458,7 @@ Data Types Returns the string used for *repr()* calls. By default, returns the *Enum* name, member name, and value, but can be overridden:: + >>> from enum import auto, Enum >>> class OtherStyle(Enum): ... ALTERNATE = auto() ... OTHER = auto() @@ -438,6 +475,7 @@ Data Types Returns the string used for *str()* calls. By default, returns the *Enum* name and member name, but can be overridden:: + >>> from enum import auto, Enum >>> class OtherStyle(Enum): ... ALTERNATE = auto() ... OTHER = auto() @@ -453,6 +491,7 @@ Data Types Returns the string used for *format()* and *f-string* calls. By default, returns :meth:`__str__` return value, but can be overridden:: + >>> from enum import auto, Enum >>> class OtherStyle(Enum): ... ALTERNATE = auto() ... OTHER = auto() @@ -470,6 +509,31 @@ Data Types .. versionchanged:: 3.12 Added :ref:`enum-dataclass-support` + .. method:: Enum._add_alias_ + + Adds a new name as an alias to an existing member:: + + >>> Color.RED._add_alias_("ERROR") + >>> Color.ERROR + + + Raises a :exc:`NameError` if the name is already assigned to a different member. + + .. versionadded:: 3.13 + + .. method:: Enum._add_value_alias_ + + Adds a new value as an alias to an existing member:: + + >>> Color.RED._add_value_alias_(42) + >>> Color(42) + + + | Raises a :exc:`ValueError` if the value is already linked with a different member. + | See :ref:`multi-value-enum` for an example. + + .. versionadded:: 3.13 + .. class:: IntEnum @@ -504,16 +568,31 @@ Data Types .. class:: StrEnum - ``StrEnum`` is the same as :class:`Enum`, but its members are also strings and can be used - in most of the same places that a string can be used. The result of any string - operation performed on or with a *StrEnum* member is not part of the enumeration. + *StrEnum* is the same as :class:`Enum`, but its members are also strings and + can be used in most of the same places that a string can be used. The result + of any string operation performed on or with a *StrEnum* member is not part + of the enumeration. + + >>> from enum import StrEnum, auto + >>> class Color(StrEnum): + ... RED = 'r' + ... GREEN = 'g' + ... BLUE = 'b' + ... UNKNOWN = auto() + ... + >>> Color.RED + + >>> Color.UNKNOWN + + >>> str(Color.UNKNOWN) + 'unknown' .. note:: There are places in the stdlib that check for an exact :class:`str` instead of a :class:`str` subclass (i.e. ``type(unknown) == str`` instead of ``isinstance(unknown, str)``), and in those locations you - will need to use ``str(StrEnum.member)``. + will need to use ``str(MyStrEnum.MY_MEMBER)``. .. note:: @@ -555,7 +634,7 @@ Data Types >>> white in purple False - .. method:: __iter__(self): + .. method:: __iter__(self) Returns all contained non-alias members:: @@ -566,7 +645,7 @@ Data Types .. versionadded:: 3.11 - .. method:: __len__(self): + .. method:: __len__(self) Returns number of members in flag:: @@ -577,7 +656,7 @@ Data Types .. versionadded:: 3.11 - .. method:: __bool__(self): + .. method:: __bool__(self) Returns *True* if any members in flag, *False* otherwise:: @@ -614,7 +693,7 @@ Data Types >>> purple ^ Color.GREEN - .. method:: __invert__(self): + .. method:: __invert__(self) Returns all the flags in *type(self)* that are not in *self*:: @@ -850,6 +929,8 @@ Data Types --------------- +.. _enum-dunder-sunder: + Supported ``__dunder__`` names """""""""""""""""""""""""""""" @@ -857,17 +938,13 @@ Supported ``__dunder__`` names items. It is only available on the class. :meth:`~Enum.__new__`, if specified, must create and return the enum members; -it is also a very good idea to set the member's :attr:`!_value_` appropriately. +it is also a very good idea to set the member's :attr:`~Enum._value_` appropriately. Once all the members are created it is no longer used. Supported ``_sunder_`` names """""""""""""""""""""""""""" -- :meth:`~EnumType._add_alias_` -- adds a new name as an alias to an existing - member. -- :meth:`~EnumType._add_value_alias_` -- adds a new value as an alias to an - existing member. - :attr:`~Enum._name_` -- name of the member - :attr:`~Enum._value_` -- value of the member; can be set in ``__new__`` - :meth:`~Enum._missing_` -- a lookup function used when a value is not found; @@ -877,16 +954,14 @@ Supported ``_sunder_`` names from the final class - :attr:`~Enum._order_` -- no longer used, kept for backward compatibility (class attribute, removed during class creation) + - :meth:`~Enum._generate_next_value_` -- used to get an appropriate value for an enum member; may be overridden - .. note:: - - For standard :class:`Enum` classes the next value chosen is the highest - value seen incremented by one. - - For :class:`Flag` classes the next value chosen will be the next highest - power-of-two. +- :meth:`~Enum._add_alias_` -- adds a new name as an alias to an existing + member. +- :meth:`~Enum._add_value_alias_` -- adds a new value as an alias to an + existing member. - While ``_sunder_`` names are generally reserved for the further development of the :class:`Enum` class and can not be used, some are explicitly allowed: @@ -900,7 +975,7 @@ Supported ``_sunder_`` names --------------- -Utilities and Decorators +Utilities and decorators ------------------------ .. class:: auto @@ -913,12 +988,13 @@ Utilities and Decorators the member's name. Care must be taken if mixing *auto()* with manually specified values. - *auto* instances are only resolved when at the top level of an assignment: + *auto* instances are only resolved when at the top level of an assignment, either by + itself or as part of a tuple: * ``FIRST = auto()`` will work (auto() is replaced with ``1``); * ``SECOND = auto(), -2`` will work (auto is replaced with ``2``, so ``2, -2`` is used to create the ``SECOND`` enum member; - * ``THREE = [auto(), -3]`` will *not* work (``, -3`` is used to + * ``THREE = [auto(), -3]`` will *not* work (``[, -3]`` is used to create the ``THREE`` enum member) .. versionchanged:: 3.11.1 @@ -935,7 +1011,7 @@ Utilities and Decorators .. decorator:: property - A decorator similar to the built-in *property*, but specifically for + A decorator similar to the built-in :deco:`property`, but specifically for enumerations. It allows member attributes to have the same names as members themselves. @@ -1000,6 +1076,20 @@ Utilities and Decorators .. versionadded:: 3.11 +.. function:: bin(num, max_bits=None) + + Like built-in :func:`bin`, except negative values are represented in + two's complement, and the leading bit always indicates sign + (``0`` implies positive, ``1`` implies negative). + + >>> import enum + >>> enum.bin(10) + '0b0 1010' + >>> enum.bin(~10) # ~10 is -11 + '0b1 0101' + + .. versionadded:: 3.11 + --------------- Notes diff --git a/Doc/library/exceptions.rst b/Doc/library/exceptions.rst index bb72032891ea98..aae9bad1a9f3e8 100644 --- a/Doc/library/exceptions.rst +++ b/Doc/library/exceptions.rst @@ -204,10 +204,16 @@ The following exceptions are the exceptions that are usually raised. assignment fails. (When an object does not support attribute references or attribute assignments at all, :exc:`TypeError` is raised.) - The :attr:`name` and :attr:`obj` attributes can be set using keyword-only - arguments to the constructor. When set they represent the name of the attribute - that was attempted to be accessed and the object that was accessed for said - attribute, respectively. + The optional *name* and *obj* keyword-only arguments + set the corresponding attributes: + + .. attribute:: name + + The name of the attribute that was attempted to be accessed. + + .. attribute:: obj + + The object that was accessed for the named attribute. .. versionchanged:: 3.10 Added the :attr:`name` and :attr:`obj` attributes. @@ -215,7 +221,7 @@ The following exceptions are the exceptions that are usually raised. .. exception:: EOFError Raised when the :func:`input` function hits an end-of-file condition (EOF) - without reading any data. (N.B.: the :meth:`io.IOBase.read` and + without reading any data. (Note: the :meth:`io.TextIOBase.read` and :meth:`io.IOBase.readline` methods return an empty string when they hit EOF.) @@ -312,9 +318,11 @@ The following exceptions are the exceptions that are usually raised. unqualified names. The associated value is an error message that includes the name that could not be found. - The :attr:`name` attribute can be set using a keyword-only argument to the - constructor. When set it represent the name of the variable that was attempted - to be accessed. + The optional *name* keyword-only argument sets the attribute: + + .. attribute:: name + + The name of the variable that was attempted to be accessed. .. versionchanged:: 3.10 Added the :attr:`name` attribute. @@ -382,7 +390,7 @@ The following exceptions are the exceptions that are usually raised. The corresponding error message, as provided by the operating system. It is formatted by the C - functions :c:func:`perror` under POSIX, and :c:func:`FormatMessage` + functions :c:func:`!perror` under POSIX, and :c:func:`!FormatMessage` under Windows. .. attribute:: filename @@ -398,7 +406,7 @@ The following exceptions are the exceptions that are usually raised. .. versionchanged:: 3.3 :exc:`EnvironmentError`, :exc:`IOError`, :exc:`WindowsError`, :exc:`socket.error`, :exc:`select.error` and - :exc:`mmap.error` have been merged into :exc:`OSError`, and the + :exc:`!mmap.error` have been merged into :exc:`OSError`, and the constructor may return a subclass. .. versionchanged:: 3.4 @@ -590,7 +598,7 @@ The following exceptions are the exceptions that are usually raised. handled, the Python interpreter exits; no stack traceback is printed. The constructor accepts the same optional argument passed to :func:`sys.exit`. If the value is an integer, it specifies the system exit status (passed to - C's :c:func:`exit` function); if it is ``None``, the exit status is zero; if + C's :c:func:`!exit` function); if it is ``None``, the exit status is zero; if it has another type (such as a string), the object's value is printed and the exit status is one. @@ -727,8 +735,8 @@ depending on the system error code. .. attribute:: characters_written - An integer containing the number of characters written to the stream - before it blocked. This attribute is available when using the + An integer containing the number of **bytes** written to the stream + before it blocked. This attribute is available when using the buffered I/O classes from the :mod:`io` module. .. exception:: ChildProcessError @@ -882,6 +890,9 @@ The following exceptions are used as warning categories; see the Base class for warnings about dubious syntax. + This warning is typically emitted when compiling Python source code, and usually won't be reported + when running already compiled code. + .. exception:: RuntimeWarning @@ -960,6 +971,15 @@ their subgroups based on the types of the contained exceptions. raises a :exc:`TypeError` if any contained exception is not an :exc:`Exception` subclass. + Exception groups are :ref:`generic ` over the type of their + contained exceptions. + + .. impl-detail:: + + The ``excs`` parameter may be any sequence, but lists and tuples are + specifically processed more efficiently here. For optimal performance, + pass a tuple as ``excs``. + .. attribute:: message The ``msg`` argument to the constructor. This is a read-only attribute. @@ -1048,7 +1068,7 @@ their subgroups based on the types of the contained exceptions. subclasses that need a different constructor signature need to override that rather than :meth:`~object.__init__`. For example, the following defines an exception group subclass which accepts an exit_code and - and constructs the group's message from it. :: + constructs the group's message from it. :: class Errors(ExceptionGroup): def __new__(cls, errors, exit_code): diff --git a/Doc/library/faulthandler.rst b/Doc/library/faulthandler.rst index 5058b85bffb15c..f81e6bf5810f86 100644 --- a/Doc/library/faulthandler.rst +++ b/Doc/library/faulthandler.rst @@ -90,7 +90,7 @@ An error will be printed instead of the stack. Additionally, some compilers do not support :term:`CPython's ` implementation of C stack dumps. As a result, a different error may be printed -instead of the stack, even if the the operating system supports dumping stacks. +instead of the stack, even if the operating system supports dumping stacks. .. note:: @@ -228,6 +228,41 @@ handler: Fatal Python error: Segmentation fault Current thread 0x00007fb899f39700 (most recent call first): - File "/home/python/cpython/Lib/ctypes/__init__.py", line 486 in string_at + File "/opt/python/Lib/ctypes/__init__.py", line 486 in string_at File "", line 1 in + + Current thread's C stack trace (most recent call first): + Binary file "/opt/python/python", at _Py_DumpStack+0x42 [0x5b27f7d7147e] + Binary file "/opt/python/python", at +0x32dcbd [0x5b27f7d85cbd] + Binary file "/opt/python/python", at +0x32df8a [0x5b27f7d85f8a] + Binary file "/usr/lib/libc.so.6", at +0x3def0 [0x77b73226bef0] + Binary file "/usr/lib/libc.so.6", at +0x17ef9c [0x77b7323acf9c] + Binary file "/opt/python/build/lib.linux-x86_64-3.14/_ctypes.cpython-314d-x86_64-linux-gnu.so", at +0xcdf6 [0x77b7315dddf6] + Binary file "/usr/lib/libffi.so.8", at +0x7976 [0x77b73158f976] + Binary file "/usr/lib/libffi.so.8", at +0x413c [0x77b73158c13c] + Binary file "/usr/lib/libffi.so.8", at ffi_call+0x12e [0x77b73158ef0e] + Binary file "/opt/python/build/lib.linux-x86_64-3.14/_ctypes.cpython-314d-x86_64-linux-gnu.so", at +0x15a33 [0x77b7315e6a33] + Binary file "/opt/python/build/lib.linux-x86_64-3.14/_ctypes.cpython-314d-x86_64-linux-gnu.so", at +0x164fa [0x77b7315e74fa] + Binary file "/opt/python/build/lib.linux-x86_64-3.14/_ctypes.cpython-314d-x86_64-linux-gnu.so", at +0xc624 [0x77b7315dd624] + Binary file "/opt/python/python", at _PyObject_MakeTpCall+0xce [0x5b27f7b73883] + Binary file "/opt/python/python", at +0x11bab6 [0x5b27f7b73ab6] + Binary file "/opt/python/python", at PyObject_Vectorcall+0x23 [0x5b27f7b73b04] + Binary file "/opt/python/python", at _PyEval_EvalFrameDefault+0x490c [0x5b27f7cbb302] + Binary file "/opt/python/python", at +0x2818e6 [0x5b27f7cd98e6] + Binary file "/opt/python/python", at +0x281aab [0x5b27f7cd9aab] + Binary file "/opt/python/python", at PyEval_EvalCode+0xc5 [0x5b27f7cd9ba3] + Binary file "/opt/python/python", at +0x255957 [0x5b27f7cad957] + Binary file "/opt/python/python", at +0x255ab4 [0x5b27f7cadab4] + Binary file "/opt/python/python", at _PyEval_EvalFrameDefault+0x6c3e [0x5b27f7cbd634] + Binary file "/opt/python/python", at +0x2818e6 [0x5b27f7cd98e6] + Binary file "/opt/python/python", at +0x281aab [0x5b27f7cd9aab] + Binary file "/opt/python/python", at +0x11b6e1 [0x5b27f7b736e1] + Binary file "/opt/python/python", at +0x11d348 [0x5b27f7b75348] + Binary file "/opt/python/python", at +0x11d626 [0x5b27f7b75626] + Binary file "/opt/python/python", at PyObject_Call+0x20 [0x5b27f7b7565e] + Binary file "/opt/python/python", at +0x32a67a [0x5b27f7d8267a] + Binary file "/opt/python/python", at +0x32a7f8 [0x5b27f7d827f8] + Binary file "/opt/python/python", at +0x32ac1b [0x5b27f7d82c1b] + Binary file "/opt/python/python", at Py_RunMain+0x31 [0x5b27f7d82ebe] + Segmentation fault diff --git a/Doc/library/fcntl.rst b/Doc/library/fcntl.rst index c8ce86cc7af92c..4a08af4f90d419 100644 --- a/Doc/library/fcntl.rst +++ b/Doc/library/fcntl.rst @@ -2,7 +2,6 @@ ========================================================== .. module:: fcntl - :platform: Unix :synopsis: The fcntl() and ioctl() system calls. .. sectionauthor:: Jaap Vermeulen @@ -53,7 +52,7 @@ descriptor. the latter setting ``FD_CLOEXEC`` flag in addition. .. versionchanged:: 3.12 - On Linux >= 4.5, the :mod:`fcntl` module exposes the ``FICLONE`` and + On Linux >= 4.5, the :mod:`!fcntl` module exposes the ``FICLONE`` and ``FICLONERANGE`` constants, which allow to share some data of one file with another file by reflinking on some filesystems (e.g., btrfs, OCFS2, and XFS). This behavior is commonly referred to as "copy-on-write". @@ -91,7 +90,7 @@ The module defines the following functions: Perform the operation *cmd* on file descriptor *fd* (file objects providing a :meth:`~io.IOBase.fileno` method are accepted as well). The values used for *cmd* are operating system dependent, and are available as constants - in the :mod:`fcntl` module, using the same names as used in the relevant C + in the :mod:`!fcntl` module, using the same names as used in the relevant C header files. The argument *arg* can either be an integer value, a :term:`bytes-like object`, or a string. The type and size of *arg* must match the type and size of diff --git a/Doc/library/filecmp.rst b/Doc/library/filecmp.rst index abd1b8c826d170..105aaa23071806 100644 --- a/Doc/library/filecmp.rst +++ b/Doc/library/filecmp.rst @@ -10,11 +10,11 @@ -------------- -The :mod:`filecmp` module defines functions to compare files and directories, +The :mod:`!filecmp` module defines functions to compare files and directories, with various optional time/correctness trade-offs. For comparing files, see also the :mod:`difflib` module. -The :mod:`filecmp` module defines the following functions: +The :mod:`!filecmp` module defines the following functions: .. function:: cmp(f1, f2, shallow=True) @@ -36,9 +36,9 @@ The :mod:`filecmp` module defines the following functions: file changes. The entire cache may be cleared using :func:`clear_cache`. -.. function:: cmpfiles(dir1, dir2, common, shallow=True) +.. function:: cmpfiles(a, b, common, shallow=True) - Compare the files in the two directories *dir1* and *dir2* whose names are + Compare the files in the two directories *a* and *b* whose names are given by *common*. Returns three lists of file names: *match*, *mismatch*, diff --git a/Doc/library/fnmatch.rst b/Doc/library/fnmatch.rst index 12e61bc36f5db0..42539283c5ff2b 100644 --- a/Doc/library/fnmatch.rst +++ b/Doc/library/fnmatch.rst @@ -51,9 +51,9 @@ Unless stated otherwise, "filename string" and "pattern string" either refer to functions documented below do not allow to mix a :class:`!bytes` pattern with a :class:`!str` filename, and vice-versa. -Finally, note that :func:`functools.lru_cache` with a *maxsize* of 32768 +Finally, note that :deco:`functools.lru_cache` with a *maxsize* of 32768 is used to cache the (typed) compiled regex patterns in the following -functions: :func:`fnmatch`, :func:`fnmatchcase`, :func:`.filter`. +functions: :func:`fnmatch`, :func:`fnmatchcase`, :func:`.filter`, :func:`.filterfalse`. .. function:: fnmatch(name, pat) diff --git a/Doc/library/fractions.rst b/Doc/library/fractions.rst index fc7f9a6301a915..575e90942d48b0 100644 --- a/Doc/library/fractions.rst +++ b/Doc/library/fractions.rst @@ -11,11 +11,11 @@ -------------- -The :mod:`fractions` module provides support for rational number arithmetic. +The :mod:`!fractions` module provides support for rational number arithmetic. -A Fraction instance can be constructed from a pair of integers, from -another rational number, or from a string. +A Fraction instance can be constructed from a pair of rational numbers, from +a single number, or from a string. .. index:: single: as_integer_ratio() @@ -25,8 +25,8 @@ another rational number, or from a string. The first version requires that *numerator* and *denominator* are instances of :class:`numbers.Rational` and returns a new :class:`Fraction` instance - with value ``numerator/denominator``. If *denominator* is ``0``, it - raises a :exc:`ZeroDivisionError`. + with a value equal to ``numerator/denominator``. + If *denominator* is zero, it raises a :exc:`ZeroDivisionError`. The second version requires that *number* is an instance of :class:`numbers.Rational` or has the :meth:`!as_integer_ratio` method @@ -125,7 +125,8 @@ another rational number, or from a string. .. attribute:: denominator - Denominator of the Fraction in lowest term. + Denominator of the Fraction in lowest terms. + Guaranteed to be positive. .. method:: as_integer_ratio() @@ -142,7 +143,7 @@ another rational number, or from a string. .. versionadded:: 3.12 - .. classmethod:: from_float(flt) + .. classmethod:: from_float(f) Alternative constructor which only accepts instances of :class:`float` or :class:`numbers.Integral`. Beware that diff --git a/Doc/library/frameworks.rst b/Doc/library/frameworks.rst index 15ceeec9c255ed..f8e2f6bb18cb1c 100644 --- a/Doc/library/frameworks.rst +++ b/Doc/library/frameworks.rst @@ -1,18 +1,13 @@ +:orphan: + .. _frameworks: ****************** -Program Frameworks +Program frameworks ****************** -The modules described in this chapter are frameworks that will largely dictate -the structure of your program. Currently the modules described here are all -oriented toward writing command-line interfaces. - -The full list of modules described in this chapter is: - - -.. toctree:: +This chapter is no longer maintained, and the modules it contained have been moved to their respective topical documentation. - turtle.rst - cmd.rst - shlex.rst +* :mod:`cmd` — :doc:`Command Line Interface Libraries <./cmdlinelibs>` +* :mod:`shlex` — :doc:`Unix Specific Services <./unix>` +* :mod:`turtle` — :doc:`Graphical User Interfaces with Tk <./tk>` diff --git a/Doc/library/ftplib.rst b/Doc/library/ftplib.rst index bb15322067245e..9cbb387f40fb4c 100644 --- a/Doc/library/ftplib.rst +++ b/Doc/library/ftplib.rst @@ -23,7 +23,7 @@ The default encoding is UTF-8, following :rfc:`2640`. .. include:: ../includes/wasm-notavail.rst -Here's a sample session using the :mod:`ftplib` module:: +Here's a sample session using the :mod:`!ftplib` module:: >>> from ftplib import FTP >>> ftp = FTP('ftp.us.debian.org') # connect to host, default port diff --git a/Doc/library/functions.rst b/Doc/library/functions.rst index 7e367a0f2b6b25..16c420ddd1b5e6 100644 --- a/Doc/library/functions.rst +++ b/Doc/library/functions.rst @@ -54,7 +54,7 @@ are always available. They are listed here in alphabetical order. .. |func-bytearray| replace:: ``bytearray()`` .. |func-bytes| replace:: ``bytes()`` -.. function:: abs(x) +.. function:: abs(number, /) Return the absolute value of a number. The argument may be an integer, a floating-point number, or an object implementing @@ -62,7 +62,7 @@ are always available. They are listed here in alphabetical order. If the argument is a complex number, its magnitude is returned. -.. function:: aiter(async_iterable) +.. function:: aiter(async_iterable, /) Return an :term:`asynchronous iterator` for an :term:`asynchronous iterable`. Equivalent to calling ``x.__aiter__()``. @@ -71,7 +71,7 @@ are always available. They are listed here in alphabetical order. .. versionadded:: 3.10 -.. function:: all(iterable) +.. function:: all(iterable, /) Return ``True`` if all elements of the *iterable* are true (or if the iterable is empty). Equivalent to:: @@ -83,8 +83,8 @@ are always available. They are listed here in alphabetical order. return True -.. awaitablefunction:: anext(async_iterator) - anext(async_iterator, default) +.. awaitablefunction:: anext(async_iterator, /) + anext(async_iterator, default, /) When awaited, return the next item from the given :term:`asynchronous iterator`, or *default* if given and the iterator is exhausted. @@ -99,7 +99,7 @@ are always available. They are listed here in alphabetical order. .. versionadded:: 3.10 -.. function:: any(iterable) +.. function:: any(iterable, /) Return ``True`` if any element of the *iterable* is true. If the iterable is empty, return ``False``. Equivalent to:: @@ -111,7 +111,7 @@ are always available. They are listed here in alphabetical order. return False -.. function:: ascii(object) +.. function:: ascii(object, /) As :func:`repr`, return a string containing a printable representation of an object, but escape the non-ASCII characters in the string returned by @@ -119,10 +119,10 @@ are always available. They are listed here in alphabetical order. similar to that returned by :func:`repr` in Python 2. -.. function:: bin(x) +.. function:: bin(integer, /) Convert an integer number to a binary string prefixed with "0b". The result - is a valid Python expression. If *x* is not a Python :class:`int` object, it + is a valid Python expression. If *integer* is not a Python :class:`int` object, it has to define an :meth:`~object.__index__` method that returns an integer. Some examples: @@ -138,6 +138,8 @@ are always available. They are listed here in alphabetical order. >>> f'{14:#b}', f'{14:b}' ('0b1110', '1110') + See also :func:`enum.bin` to represent negative values as twos-complement. + See also :func:`format` for more information. @@ -183,8 +185,7 @@ are always available. They are listed here in alphabetical order. .. _func-bytearray: .. class:: bytearray(source=b'') - bytearray(source, encoding) - bytearray(source, encoding, errors) + bytearray(source, encoding, errors='strict') :noindex: Return a new array of bytes. The :class:`bytearray` class is a mutable @@ -215,8 +216,7 @@ are always available. They are listed here in alphabetical order. .. _func-bytes: .. class:: bytes(source=b'') - bytes(source, encoding) - bytes(source, encoding, errors) + bytes(source, encoding, errors='strict') :noindex: Return a new "bytes" object which is an immutable sequence of integers in @@ -231,7 +231,7 @@ are always available. They are listed here in alphabetical order. See also :ref:`binaryseq`, :ref:`typebytes`, and :ref:`bytes-methods`. -.. function:: callable(object) +.. function:: callable(object, /) Return :const:`True` if the *object* argument appears callable, :const:`False` if not. If this returns ``True``, it is still possible that a @@ -244,14 +244,14 @@ are always available. They are listed here in alphabetical order. in Python 3.2. -.. function:: chr(i) +.. function:: chr(codepoint, /) - Return the string representing a character whose Unicode code point is the - integer *i*. For example, ``chr(97)`` returns the string ``'a'``, while + Return the string representing a character with the specified Unicode code point. + For example, ``chr(97)`` returns the string ``'a'``, while ``chr(8364)`` returns the string ``'€'``. This is the inverse of :func:`ord`. The valid range for the argument is from 0 through 1,114,111 (0x10FFFF in - base 16). :exc:`ValueError` will be raised if *i* is outside that range. + base 16). :exc:`ValueError` will be raised if it is outside that range. .. decorator:: classmethod @@ -336,8 +336,8 @@ are always available. They are listed here in alphabetical order. ``__debug__`` is true), ``1`` (asserts are removed, ``__debug__`` is false) or ``2`` (docstrings are removed too). - This function raises :exc:`SyntaxError` if the compiled source is invalid, - and :exc:`ValueError` if the source contains null bytes. + This function raises :exc:`SyntaxError` or :exc:`ValueError` if the compiled + source is invalid. If you want to parse Python code into its AST representation, see :func:`ast.parse`. @@ -458,7 +458,7 @@ are always available. They are listed here in alphabetical order. deprecated; it should only be passed as a single positional argument. -.. function:: delattr(object, name) +.. function:: delattr(object, name, /) This is a relative of :func:`setattr`. The arguments are an object and a string. The string must be the name of one of the object's attributes. The @@ -468,20 +468,20 @@ are always available. They are listed here in alphabetical order. .. _func-dict: -.. class:: dict(**kwarg) - dict(mapping, **kwarg) - dict(iterable, **kwarg) +.. class:: dict(**kwargs) + dict(mapping, /, **kwargs) + dict(iterable, /, **kwargs) :noindex: Create a new dictionary. The :class:`dict` object is the dictionary class. - See :class:`dict` and :ref:`typesmapping` for documentation about this class. + See also :ref:`typesmapping` for documentation about this class. For other containers see the built-in :class:`list`, :class:`set`, and :class:`tuple` classes, as well as the :mod:`collections` module. .. function:: dir() - dir(object) + dir(object, /) Without arguments, return the list of names in the current local scope. With an argument, attempt to return a list of valid attributes for that object. @@ -541,7 +541,7 @@ are always available. They are listed here in alphabetical order. class. -.. function:: divmod(a, b) +.. function:: divmod(a, b, /) Take two (non-complex) numbers as arguments and return a pair of numbers consisting of their quotient and remainder when using integer division. With @@ -597,18 +597,20 @@ are always available. They are listed here in alphabetical order. .. warning:: This function executes arbitrary code. Calling it with - user-supplied input may lead to security vulnerabilities. + untrusted user-supplied input will lead to security vulnerabilities. - The *expression* argument is parsed and evaluated as a Python expression - (technically speaking, a condition list) using the *globals* and *locals* - mappings as global and local namespace. If the *globals* dictionary is - present and does not contain a value for the key ``__builtins__``, a + The *source* argument is parsed and evaluated as a Python expression + (technically speaking, an :ref:`expression list `) + using the *globals* and *locals* mappings as global and local namespace. + If the *globals* dictionary is present and does not contain a value for the + key ``__builtins__``, a reference to the dictionary of the built-in module :mod:`builtins` is - inserted under that key before *expression* is parsed. That way you can - control what builtins are available to the executed code by inserting your - own ``__builtins__`` dictionary into *globals* before passing it to - :func:`eval`. If the *locals* mapping is omitted it defaults to the - *globals* dictionary. If both mappings are omitted, the expression is + inserted under that key before *source* is parsed. + Overriding ``__builtins__`` can be used to restrict or change the available + names, but this is **not** a security mechanism: the executed code can + still access all builtins. + If the *locals* mapping is omitted it defaults to the + *globals* dictionary. If both mappings are omitted, the source is executed with the *globals* and *locals* in the environment where :func:`eval` is called. Note, *eval()* will only have access to the :term:`nested scopes ` (non-locals) in the enclosing @@ -621,6 +623,9 @@ are always available. They are listed here in alphabetical order. >>> eval('x+1') 2 + >>> eval("1, 2") + (1, 2) + This function can also be used to execute arbitrary code objects (such as those created by :func:`compile`). In this case, pass a code object instead of a string. If the code object has been compiled with ``'exec'`` as the @@ -634,7 +639,7 @@ are always available. They are listed here in alphabetical order. If the given source is a string, then leading and trailing spaces and tabs are stripped. - See :func:`ast.literal_eval` for a function that can safely evaluate strings + See :func:`ast.literal_eval` for a function to evaluate strings with expressions containing only literals. .. audit-event:: exec code_object eval @@ -658,7 +663,7 @@ are always available. They are listed here in alphabetical order. .. warning:: This function executes arbitrary code. Calling it with - user-supplied input may lead to security vulnerabilities. + untrusted user-supplied input will lead to security vulnerabilities. This function supports dynamic execution of Python code. *source* must be either a string or a code object. If it is a string, the string is parsed as @@ -689,9 +694,10 @@ are always available. They are listed here in alphabetical order. If the *globals* dictionary does not contain a value for the key ``__builtins__``, a reference to the dictionary of the built-in module - :mod:`builtins` is inserted under that key. That way you can control what - builtins are available to the executed code by inserting your own - ``__builtins__`` dictionary into *globals* before passing it to :func:`exec`. + :mod:`builtins` is inserted under that key. + Overriding ``__builtins__`` can be used to restrict or change the available + names, but this is **not** a security mechanism: the executed code can + still access all builtins. The *closure* argument specifies a closure--a tuple of cellvars. It's only valid when the *object* is a code object containing @@ -729,7 +735,7 @@ are always available. They are listed here in alphabetical order. described for the :func:`locals` builtin. -.. function:: filter(function, iterable) +.. function:: filter(function, iterable, /) Construct an iterator from those elements of *iterable* for which *function* is true. *iterable* may be either a sequence, a container which @@ -823,7 +829,7 @@ are always available. They are listed here in alphabetical order. single: __format__ single: string; format() (built-in function) -.. function:: format(value, format_spec="") +.. function:: format(value, format_spec="", /) Convert a *value* to a "formatted" representation, as controlled by *format_spec*. The interpretation of *format_spec* will depend on the type @@ -846,11 +852,11 @@ are always available. They are listed here in alphabetical order. .. _func-frozenset: -.. class:: frozenset(iterable=set()) +.. class:: frozenset(iterable=(), /) :noindex: Return a new :class:`frozenset` object, optionally with elements taken from - *iterable*. ``frozenset`` is a built-in class. See :class:`frozenset` and + *iterable*. :class:`frozenset` is a built-in class. See also :ref:`types-set` for documentation about this class. For other containers see the built-in :class:`set`, :class:`list`, @@ -858,8 +864,8 @@ are always available. They are listed here in alphabetical order. module. -.. function:: getattr(object, name) - getattr(object, name, default) +.. function:: getattr(object, name, /) + getattr(object, name, default, /) Return the value of the named attribute of *object*. *name* must be a string. If the string is the name of one of the object's attributes, the result is the @@ -883,7 +889,7 @@ are always available. They are listed here in alphabetical order. regardless of where the function is called. -.. function:: hasattr(object, name) +.. function:: hasattr(object, name, /) The arguments are an object and a string. The result is ``True`` if the string is the name of one of the object's attributes, ``False`` if not. (This @@ -891,7 +897,7 @@ are always available. They are listed here in alphabetical order. raises an :exc:`AttributeError` or not.) -.. function:: hash(object) +.. function:: hash(object, /) Return the hash value of the object (if it has one). Hash values are integers. They are used to quickly compare dictionary keys during a @@ -926,10 +932,10 @@ are always available. They are listed here in alphabetical order. signatures for callables are now more comprehensive and consistent. -.. function:: hex(x) +.. function:: hex(integer, /) Convert an integer number to a lowercase hexadecimal string prefixed with - "0x". If *x* is not a Python :class:`int` object, it has to define an + "0x". If *integer* is not a Python :class:`int` object, it has to define an :meth:`~object.__index__` method that returns an integer. Some examples: >>> hex(255) @@ -958,7 +964,7 @@ are always available. They are listed here in alphabetical order. :meth:`float.hex` method. -.. function:: id(object) +.. function:: id(object, /) Return the "identity" of an object. This is an integer which is guaranteed to be unique and constant for this object during its lifetime. @@ -971,7 +977,7 @@ are always available. They are listed here in alphabetical order. .. function:: input() - input(prompt) + input(prompt, /) If the *prompt* argument is present, it is written to standard output without a trailing newline. The function then reads a line from input, converts it @@ -1071,7 +1077,7 @@ are always available. They are listed here in alphabetical order. .. versionchanged:: 3.14 :func:`int` no longer delegates to the :meth:`~object.__trunc__` method. -.. function:: isinstance(object, classinfo) +.. function:: isinstance(object, classinfo, /) Return ``True`` if the *object* argument is an instance of the *classinfo* argument, or of a (direct, indirect, or :term:`virtual `) of *classinfo*. A @@ -1102,19 +1108,19 @@ are always available. They are listed here in alphabetical order. *classinfo* can be a :ref:`types-union`. -.. function:: iter(object) - iter(object, sentinel) +.. function:: iter(iterable, /) + iter(callable, sentinel, /) Return an :term:`iterator` object. The first argument is interpreted very differently depending on the presence of the second argument. Without a - second argument, *object* must be a collection object which supports the + second argument, the single argument must be a collection object which supports the :term:`iterable` protocol (the :meth:`~object.__iter__` method), or it must support the sequence protocol (the :meth:`~object.__getitem__` method with integer arguments starting at ``0``). If it does not support either of those protocols, :exc:`TypeError` is raised. If the second argument, *sentinel*, is given, - then *object* must be a callable object. The iterator created in this case - will call *object* with no arguments for each call to its + then the first argument must be a callable object. The iterator created in this case + will call *callable* with no arguments for each call to its :meth:`~iterator.__next__` method; if the value returned is equal to *sentinel*, :exc:`StopIteration` will be raised, otherwise the value will be returned. @@ -1131,7 +1137,7 @@ are always available. They are listed here in alphabetical order. process_block(block) -.. function:: len(s) +.. function:: len(object, /) Return the length (the number of items) of an object. The argument may be a sequence (such as a string, bytes, tuple, list, or range) or a collection @@ -1144,8 +1150,7 @@ are always available. They are listed here in alphabetical order. .. _func-list: -.. class:: list() - list(iterable) +.. class:: list(iterable=(), /) :noindex: Rather than being a function, :class:`list` is actually a mutable @@ -1154,44 +1159,44 @@ are always available. They are listed here in alphabetical order. .. function:: locals() - Return a mapping object representing the current local symbol table, with - variable names as the keys, and their currently bound references as the - values. - - At module scope, as well as when using :func:`exec` or :func:`eval` with - a single namespace, this function returns the same namespace as - :func:`globals`. - - At class scope, it returns the namespace that will be passed to the - metaclass constructor. - - When using ``exec()`` or ``eval()`` with separate local and global - arguments, it returns the local namespace passed in to the function call. - - In all of the above cases, each call to ``locals()`` in a given frame of - execution will return the *same* mapping object. Changes made through - the mapping object returned from ``locals()`` will be visible as assigned, - reassigned, or deleted local variables, and assigning, reassigning, or - deleting local variables will immediately affect the contents of the - returned mapping object. - - In an :term:`optimized scope` (including functions, generators, and - coroutines), each call to ``locals()`` instead returns a fresh dictionary - containing the current bindings of the function's local variables and any - nonlocal cell references. In this case, name binding changes made via the - returned dict are *not* written back to the corresponding local variables - or nonlocal cell references, and assigning, reassigning, or deleting local - variables and nonlocal cell references does *not* affect the contents - of previously returned dictionaries. - - Calling ``locals()`` as part of a comprehension in a function, generator, or - coroutine is equivalent to calling it in the containing scope, except that - the comprehension's initialised iteration variables will be included. In - other scopes, it behaves as if the comprehension were running as a nested - function. - - Calling ``locals()`` as part of a generator expression is equivalent to - calling it in a nested generator function. + Return a mapping object representing the current local symbol table, with + variable names as the keys, and their currently bound references as the + values. + + At module scope, as well as when using :func:`exec` or :func:`eval` with + a single namespace, this function returns the same namespace as + :func:`globals`. + + At class scope, it returns the namespace that will be passed to the + metaclass constructor. + + When using ``exec()`` or ``eval()`` with separate local and global + arguments, it returns the local namespace passed in to the function call. + + In all of the above cases, each call to ``locals()`` in a given frame of + execution will return the *same* mapping object. Changes made through + the mapping object returned from ``locals()`` will be visible as assigned, + reassigned, or deleted local variables, and assigning, reassigning, or + deleting local variables will immediately affect the contents of the + returned mapping object. + + In an :term:`optimized scope` (including functions, generators, and + coroutines), each call to ``locals()`` instead returns a fresh dictionary + containing the current bindings of the function's local variables and any + nonlocal cell references. In this case, name binding changes made via the + returned dict are *not* written back to the corresponding local variables + or nonlocal cell references, and assigning, reassigning, or deleting local + variables and nonlocal cell references does *not* affect the contents + of previously returned dictionaries. + + Calling ``locals()`` as part of a comprehension in a function, generator, or + coroutine is equivalent to calling it in the containing scope, except that + the comprehension's initialised iteration variables will be included. In + other scopes, it behaves as if the comprehension were running as a nested + function. + + Calling ``locals()`` as part of a generator expression is equivalent to + calling it in a nested generator function. .. versionchanged:: 3.12 The behaviour of ``locals()`` in a comprehension has been updated as @@ -1220,9 +1225,9 @@ are always available. They are listed here in alphabetical order. Added the *strict* parameter. -.. function:: max(iterable, *, key=None) - max(iterable, *, default, key=None) - max(arg1, arg2, *args, key=None) +.. function:: max(iterable, /, *, key=None) + max(iterable, /, *, default, key=None) + max(arg1, arg2, /, *args, key=None) Return the largest item in an iterable or the largest of two or more arguments. @@ -1258,9 +1263,9 @@ are always available. They are listed here in alphabetical order. :ref:`typememoryview` for more information. -.. function:: min(iterable, *, key=None) - min(iterable, *, default, key=None) - min(arg1, arg2, *args, key=None) +.. function:: min(iterable, /, *, key=None) + min(iterable, /, *, default, key=None) + min(arg1, arg2, /, *args, key=None) Return the smallest item in an iterable or the smallest of two or more arguments. @@ -1288,8 +1293,8 @@ are always available. They are listed here in alphabetical order. The *key* can be ``None``. -.. function:: next(iterator) - next(iterator, default) +.. function:: next(iterator, /) + next(iterator, default, /) Retrieve the next item from the :term:`iterator` by calling its :meth:`~iterator.__next__` method. If *default* is given, it is returned @@ -1310,10 +1315,10 @@ are always available. They are listed here in alphabetical order. :class:`object`. -.. function:: oct(x) +.. function:: oct(integer, /) Convert an integer number to an octal string prefixed with "0o". The result - is a valid Python expression. If *x* is not a Python :class:`int` object, it + is a valid Python expression. If *integer* is not a Python :class:`int` object, it has to define an :meth:`~object.__index__` method that returns an integer. For example: @@ -1562,13 +1567,19 @@ are always available. They are listed here in alphabetical order. .. versionchanged:: 3.11 The ``'U'`` mode has been removed. -.. function:: ord(c) +.. function:: ord(character, /) + + Return the ordinal value of a character. - Given a string representing one Unicode character, return an integer - representing the Unicode code point of that character. For example, + If the argument is a one-character string, return the Unicode code point + of that character. For example, ``ord('a')`` returns the integer ``97`` and ``ord('€')`` (Euro sign) returns ``8364``. This is the inverse of :func:`chr`. + If the argument is a :class:`bytes` or :class:`bytearray` object of + length 1, return its single byte value. + For example, ``ord(b'a')`` returns the integer ``97``. + .. function:: pow(base, exp, mod=None) @@ -1577,7 +1588,7 @@ are always available. They are listed here in alphabetical order. ``pow(base, exp) % mod``). The two-argument form ``pow(base, exp)`` is equivalent to using the power operator: ``base**exp``. - The arguments must have numeric types. With mixed operand types, the + When arguments are builtin numeric types with mixed operand types, the coercion rules for binary arithmetic operators apply. For :class:`int` operands, the result has the same type as the operands (after coercion) unless the second argument is negative; in that case, all arguments are @@ -1667,7 +1678,7 @@ are always available. They are listed here in alphabetical order. If given, *doc* will be the docstring of the property attribute. Otherwise, the property will copy *fget*'s docstring (if it exists). This makes it possible to - create read-only properties easily using :func:`property` as a :term:`decorator`:: + create read-only properties easily using :deco:`property` as a :term:`decorator`:: class Parrot: def __init__(self): @@ -1729,15 +1740,15 @@ are always available. They are listed here in alphabetical order. .. _func-range: -.. class:: range(stop) - range(start, stop, step=1) +.. class:: range(stop, /) + range(start, stop, step=1, /) :noindex: Rather than being a function, :class:`range` is actually an immutable sequence type, as documented in :ref:`typesseq-range` and :ref:`typesseq`. -.. function:: repr(object) +.. function:: repr(object, /) Return a string containing a printable representation of an object. For many types, this function makes an attempt to return a string that would yield an @@ -1761,9 +1772,9 @@ are always available. They are listed here in alphabetical order. return f"Person('{self.name}', {self.age})" -.. function:: reversed(seq) +.. function:: reversed(object, /) - Return a reverse :term:`iterator`. *seq* must be an object which has + Return a reverse :term:`iterator`. The argument must be an object which has a :meth:`~object.__reversed__` method or supports the sequence protocol (the :meth:`~object.__len__` method and the :meth:`~object.__getitem__` method with integer arguments starting at ``0``). @@ -1797,12 +1808,11 @@ are always available. They are listed here in alphabetical order. .. _func-set: -.. class:: set() - set(iterable) +.. class:: set(iterable=(), /) :noindex: Return a new :class:`set` object, optionally with elements taken from - *iterable*. ``set`` is a built-in class. See :class:`set` and + *iterable*. :class:`set` is a built-in class. See also :ref:`types-set` for documentation about this class. For other containers see the built-in :class:`frozenset`, :class:`list`, @@ -1810,7 +1820,7 @@ are always available. They are listed here in alphabetical order. module. -.. function:: setattr(object, name, value) +.. function:: setattr(object, name, value, /) This is the counterpart of :func:`getattr`. The arguments are an object, a string, and an arbitrary value. The string may name an existing attribute or a @@ -1832,27 +1842,27 @@ are always available. They are listed here in alphabetical order. :func:`setattr`. -.. class:: slice(stop) - slice(start, stop, step=None) +.. class:: slice(stop, /) + slice(start, stop, step=None, /) Return a :term:`slice` object representing the set of indices specified by ``range(start, stop, step)``. The *start* and *step* arguments default to ``None``. + Slice objects are also generated when :ref:`slicing syntax ` + is used. For example: ``a[start:stop:step]`` or ``a[start:stop, i]``. + + See :func:`itertools.islice` for an alternate version that returns an + :term:`iterator`. + .. attribute:: slice.start - .. attribute:: slice.stop - .. attribute:: slice.step + slice.stop + slice.step - Slice objects have read-only data attributes :attr:`!start`, - :attr:`!stop`, and :attr:`!step` which merely return the argument - values (or their default). They have no other explicit functionality; + These read-only attributes are set to the argument values + (or their default). They have no other explicit functionality; however, they are used by NumPy and other third-party packages. - Slice objects are also generated when extended indexing syntax is used. For - example: ``a[start:stop:step]`` or ``a[start:stop, i]``. See - :func:`itertools.islice` for an alternate version that returns an - :term:`iterator`. - .. versionchanged:: 3.12 Slice objects are now :term:`hashable` (provided :attr:`~slice.start`, :attr:`~slice.stop`, and :attr:`~slice.step` are hashable). @@ -1885,7 +1895,7 @@ are always available. They are listed here in alphabetical order. the same data with other ordering tools such as :func:`max` that rely on a different underlying method. Implementing all six comparisons also helps avoid confusion for mixed type comparisons which can call - reflected the :meth:`~object.__gt__` method. + the reflected :meth:`~object.__gt__` method. For sorting examples and a brief sorting tutorial, see :ref:`sortinghowto`. @@ -1909,7 +1919,7 @@ are always available. They are listed here in alphabetical order. be used in the class definition (such as ``f()``). Static methods in Python are similar to those found in Java or C++. Also, see - :func:`classmethod` for a variant that is useful for creating alternate class + :deco:`classmethod` for a variant that is useful for creating alternate class constructors. Like all decorators, it is also possible to call ``staticmethod`` as @@ -1938,8 +1948,10 @@ are always available. They are listed here in alphabetical order. single: string; str() (built-in function) .. _func-str: -.. class:: str(object='') - str(object=b'', encoding='utf-8', errors='strict') +.. class:: str(*, encoding='utf-8', errors='strict') + str(object) + str(object, encoding, errors='strict') + str(object, *, errors) :noindex: Return a :class:`str` version of *object*. See :func:`str` for details. @@ -1972,7 +1984,7 @@ are always available. They are listed here in alphabetical order. .. class:: super() - super(type, object_or_type=None) + super(type, object_or_type=None, /) Return a proxy object that delegates method calls to a parent or sibling class of *type*. This is useful for accessing inherited methods that have @@ -2054,16 +2066,15 @@ are always available. They are listed here in alphabetical order. .. _func-tuple: -.. class:: tuple() - tuple(iterable) +.. class:: tuple(iterable=(), /) :noindex: Rather than being a function, :class:`tuple` is actually an immutable sequence type, as documented in :ref:`typesseq-tuple` and :ref:`typesseq`. -.. class:: type(object) - type(name, bases, dict, **kwds) +.. class:: type(object, /) + type(name, bases, dict, /, **kwargs) .. index:: pair: object; type @@ -2099,6 +2110,11 @@ are always available. They are listed here in alphabetical order. in the same way that keywords in a class definition (besides *metaclass*) would. + Unlike a :keyword:`class` statement, the three argument form does not + call the metaclass ``__prepare__`` method (see :ref:`prepare`). Use + :func:`types.new_class` to dynamically create a class using the + appropriate metaclass. + See also :ref:`class-customization`. .. versionchanged:: 3.6 @@ -2106,7 +2122,7 @@ are always available. They are listed here in alphabetical order. longer use the one-argument form to get the type of an object. .. function:: vars() - vars(object) + vars(object, /) Return the :attr:`~object.__dict__` attribute for a module, class, instance, or any other object with a :attr:`!__dict__` attribute. diff --git a/Doc/library/functools.rst b/Doc/library/functools.rst index 3a933dff057bbb..417d8506c5bedd 100644 --- a/Doc/library/functools.rst +++ b/Doc/library/functools.rst @@ -20,11 +20,11 @@ -------------- -The :mod:`functools` module is for higher-order functions: functions that act on +The :mod:`!functools` module is for higher-order functions: functions that act on or return other functions. In general, any callable object can be treated as a function for the purposes of this module. -The :mod:`functools` module defines the following functions: +The :mod:`!functools` module defines the following functions: .. decorator:: cache(user_function) @@ -34,7 +34,7 @@ The :mod:`functools` module defines the following functions: Returns the same as ``lru_cache(maxsize=None)``, creating a thin wrapper around a dictionary lookup for the function arguments. Because it never needs to evict old values, this is smaller and faster than - :func:`lru_cache` with a size limit. + :deco:`lru_cache` with a size limit. For example:: @@ -42,11 +42,11 @@ The :mod:`functools` module defines the following functions: def factorial(n): return n * factorial(n-1) if n else 1 - >>> factorial(10) # no previously cached result, makes 11 recursive calls + >>> factorial(10) # no previously cached result, makes 11 recursive calls 3628800 - >>> factorial(5) # just looks up cached value result + >>> factorial(5) # no new calls, just returns the cached result 120 - >>> factorial(12) # makes two new recursive calls, the other 10 are cached + >>> factorial(12) # two new recursive calls, factorial(10) is cached 479001600 The cache is threadsafe so that the wrapped function can be used in @@ -64,7 +64,7 @@ The :mod:`functools` module defines the following functions: Transform a method of a class into a property whose value is computed once and then cached as a normal attribute for the life of the instance. Similar - to :func:`property`, with the addition of caching. Useful for expensive + to :deco:`property`, with the addition of caching. Useful for expensive computed properties of instances that are otherwise effectively immutable. Example:: @@ -78,8 +78,8 @@ The :mod:`functools` module defines the following functions: def stdev(self): return statistics.stdev(self._data) - The mechanics of :func:`cached_property` are somewhat different from - :func:`property`. A regular property blocks attribute writes unless a + The mechanics of :deco:`cached_property` are somewhat different from + :deco:`property`. A regular property blocks attribute writes unless a setter is defined. In contrast, a *cached_property* allows writes. The *cached_property* decorator only runs on lookups and only when an @@ -111,14 +111,14 @@ The :mod:`functools` module defines the following functions: (as such classes don't provide a ``__dict__`` attribute at all). If a mutable mapping is not available or if space-efficient key sharing is - desired, an effect similar to :func:`cached_property` can also be achieved by - stacking :func:`property` on top of :func:`lru_cache`. See - :ref:`faq-cache-method-calls` for more details on how this differs from :func:`cached_property`. + desired, an effect similar to :deco:`cached_property` can also be achieved by + stacking :deco:`property` on top of :deco:`lru_cache`. See + :ref:`faq-cache-method-calls` for more details on how this differs from :deco:`cached_property`. .. versionadded:: 3.8 .. versionchanged:: 3.12 - Prior to Python 3.12, ``cached_property`` included an undocumented lock to + Prior to Python 3.12, :deco:`!cached_property` included an undocumented lock to ensure that in multi-threaded usage the getter function was guaranteed to run only once per instance. However, the lock was per-property, not per-instance, which could result in unacceptably high lock contention. In @@ -190,7 +190,7 @@ The :mod:`functools` module defines the following functions: Note, type specificity applies only to the function's immediate arguments rather than their contents. The scalar arguments, ``Decimal(42)`` and - ``Fraction(42)`` are be treated as distinct calls with distinct results. + ``Fraction(42)`` are treated as distinct calls with distinct results. In contrast, the tuple arguments ``('answer', Decimal(42))`` and ``('answer', Fraction(42))`` are treated as equivalent. @@ -199,12 +199,18 @@ The :mod:`functools` module defines the following functions: and *typed*. This is for information purposes only. Mutating the values has no effect. + .. method:: lru_cache.cache_info() + :no-typesetting: + To help measure the effectiveness of the cache and tune the *maxsize* - parameter, the wrapped function is instrumented with a :func:`cache_info` + parameter, the wrapped function is instrumented with a :func:`!cache_info` function that returns a :term:`named tuple` showing *hits*, *misses*, *maxsize* and *currsize*. - The decorator also provides a :func:`cache_clear` function for clearing or + .. method:: lru_cache.cache_clear() + :no-typesetting: + + The decorator also provides a :func:`!cache_clear` function for clearing or invalidating the cache. The original underlying function is accessible through the @@ -284,9 +290,9 @@ The :mod:`functools` module defines the following functions: class decorator supplies the rest. This simplifies the effort involved in specifying all of the possible rich comparison operations: - The class must define one of :meth:`__lt__`, :meth:`__le__`, - :meth:`__gt__`, or :meth:`__ge__`. - In addition, the class should supply an :meth:`__eq__` method. + The class must define one of :meth:`~object.__lt__`, :meth:`~object.__le__`, + :meth:`~object.__gt__`, or :meth:`~object.__ge__`. + In addition, the class should supply an :meth:`~object.__eq__` method. For example:: @@ -383,9 +389,9 @@ The :mod:`functools` module defines the following functions: only one positional argument is provided, but there are two placeholders that must be filled in. - If :func:`!partial` is applied to an existing :func:`!partial` object, - :data:`!Placeholder` sentinels of the input object are filled in with - new positional arguments. + If :func:`!partial` is applied to an existing + :ref:`partial object `, :data:`!Placeholder` sentinels of the + input object are filled in with new positional arguments. A placeholder can be retained by inserting a new :data:`!Placeholder` sentinel to the place held by a previous :data:`!Placeholder`: @@ -403,8 +409,7 @@ The :mod:`functools` module defines the following functions: >>> remove_first_dear(message) 'Hello, dear world!' - :data:`!Placeholder` has no special treatment when used in a keyword - argument to :func:`!partial`. + :data:`!Placeholder` cannot be passed to :func:`!partial` as a keyword argument. .. versionchanged:: 3.14 Added support for :data:`Placeholder` in positional arguments. @@ -419,7 +424,7 @@ The :mod:`functools` module defines the following functions: like normal functions, are handled as descriptors). When *func* is a descriptor (such as a normal Python function, - :func:`classmethod`, :func:`staticmethod`, :func:`abstractmethod` or + :func:`classmethod`, :func:`staticmethod`, :func:`~abc.abstractmethod` or another instance of :class:`partialmethod`), calls to ``__get__`` are delegated to the underlying descriptor, and an appropriate :ref:`partial object` returned as the result. @@ -500,7 +505,10 @@ The :mod:`functools` module defines the following functions: ... print("Let me just say,", end=" ") ... print(arg) - To add overloaded implementations to the function, use the :func:`register` + .. method:: singledispatch.register() + :no-typesetting: + + To add overloaded implementations to the function, use the :func:`!register` attribute of the generic function, which can be used as a decorator. For functions annotated with types, the decorator will infer the type of the first argument automatically:: @@ -566,14 +574,14 @@ The :mod:`functools` module defines the following functions: runtime impact. To enable registering :term:`lambdas` and pre-existing functions, - the :func:`register` attribute can also be used in a functional form:: + the :func:`~singledispatch.register` attribute can also be used in a functional form:: >>> def nothing(arg, verbose=False): ... print("Nothing.") ... >>> fun.register(type(None), nothing) - The :func:`register` attribute returns the undecorated function. This + The :func:`~singledispatch.register` attribute returns the undecorated function. This enables decorator stacking, :mod:`pickling`, and the creation of unit tests for each variant independently:: @@ -651,10 +659,10 @@ The :mod:`functools` module defines the following functions: .. versionadded:: 3.4 .. versionchanged:: 3.7 - The :func:`register` attribute now supports using type annotations. + The :func:`~singledispatch.register` attribute now supports using type annotations. .. versionchanged:: 3.11 - The :func:`register` attribute now supports + The :func:`~singledispatch.register` attribute now supports :class:`typing.Union` as a type annotation. @@ -664,7 +672,7 @@ The :mod:`functools` module defines the following functions: dispatch>` :term:`generic function`. To define a generic method, decorate it with the ``@singledispatchmethod`` - decorator. When defining a function using ``@singledispatchmethod``, note + decorator. When defining a method using ``@singledispatchmethod``, note that the dispatch happens on the type of the first non-*self* or non-*cls* argument:: @@ -682,7 +690,7 @@ The :mod:`functools` module defines the following functions: return not arg ``@singledispatchmethod`` supports nesting with other decorators such as - :func:`@classmethod`. Note that to allow for + :deco:`classmethod`. Note that to allow for ``dispatcher.register``, ``singledispatchmethod`` must be the *outer most* decorator. Here is the ``Negator`` class with the ``neg`` methods bound to the class, rather than an instance of the class:: @@ -704,8 +712,7 @@ The :mod:`functools` module defines the following functions: return not arg The same pattern can be used for other similar decorators: - :func:`@staticmethod`, - :func:`@abstractmethod`, and others. + :deco:`staticmethod`, :deco:`~abc.abstractmethod`, and others. .. versionadded:: 3.8 @@ -725,7 +732,7 @@ The :mod:`functools` module defines the following functions: function's :attr:`~function.__dict__`, i.e. the instance dictionary). To allow access to the original function for introspection and other purposes - (e.g. bypassing a caching decorator such as :func:`lru_cache`), this function + (e.g. bypassing a caching decorator such as :deco:`lru_cache`), this function automatically adds a ``__wrapped__`` attribute to the wrapper that refers to the function being wrapped. @@ -784,7 +791,7 @@ The :mod:`functools` module defines the following functions: 'Docstring' Without the use of this decorator factory, the name of the example function - would have been ``'wrapper'``, and the docstring of the original :func:`example` + would have been ``'wrapper'``, and the docstring of the original :func:`!example` would have been lost. diff --git a/Doc/library/gc.rst b/Doc/library/gc.rst index 7ccb0e6bdf9406..3b28408b03a657 100644 --- a/Doc/library/gc.rst +++ b/Doc/library/gc.rst @@ -20,7 +20,7 @@ can be disabled by calling ``gc.disable()``. To debug a leaking program call ``gc.DEBUG_SAVEALL``, causing garbage-collected objects to be saved in gc.garbage for inspection. -The :mod:`gc` module provides the following functions: +The :mod:`!gc` module provides the following functions: .. function:: enable() @@ -40,18 +40,11 @@ The :mod:`gc` module provides the following functions: .. function:: collect(generation=2) - Perform a collection. The optional argument *generation* + With no arguments, run a full collection. The optional argument *generation* may be an integer specifying which generation to collect (from 0 to 2). A :exc:`ValueError` is raised if the generation number is invalid. The sum of collected objects and uncollectable objects is returned. - Calling ``gc.collect(0)`` will perform a GC collection on the young generation. - - Calling ``gc.collect(1)`` will perform a GC collection on the young generation - and an increment of the old generation. - - Calling ``gc.collect(2)`` or ``gc.collect()`` performs a full collection - The free lists maintained for a number of built-in types are cleared whenever a full collection or collection of the highest generation (2) is run. Not all items in some free lists may be freed due to the @@ -60,9 +53,12 @@ The :mod:`gc` module provides the following functions: The effect of calling ``gc.collect()`` while the interpreter is already performing a collection is undefined. - .. versionchanged:: 3.13 + .. versionchanged:: 3.14 ``generation=1`` performs an increment of collection. + .. versionchanged:: 3.14.5 + ``generation=1`` performs collection of the middle generation. + .. function:: set_debug(flags) @@ -78,20 +74,19 @@ The :mod:`gc` module provides the following functions: .. function:: get_objects(generation=None) - Returns a list of all objects tracked by the collector, excluding the list - returned. If *generation* is not ``None``, return only the objects as follows: - - * 0: All objects in the young generation - * 1: No objects, as there is no generation 1 (as of Python 3.13) - * 2: All objects in the old generation + returned. If *generation* is not ``None``, return only the objects tracked by + the collector that are in that generation. .. versionchanged:: 3.8 New *generation* parameter. - .. versionchanged:: 3.13 + .. versionchanged:: 3.14 Generation 1 is removed + .. versionchanged:: 3.14.5 + Generation 1 is reintroduced to maintain GC behavior from 3.13. + .. audit-event:: gc.get_objects generation gc.get_objects .. function:: get_stats() @@ -118,33 +113,33 @@ The :mod:`gc` module provides the following functions: Set the garbage collection thresholds (the collection frequency). Setting *threshold0* to zero disables collection. - The GC classifies objects into two generations depending on whether they have - survived a collection. New objects are placed in the young generation. If an - object survives a collection it is moved into the old generation. - - In order to decide when to run, the collector keeps track of the number of object + The GC classifies objects into three generations depending on how many + collection sweeps they have survived. New objects are placed in the youngest + generation (generation ``0``). If an object survives a collection it is moved + into the next older generation. Since generation ``2`` is the oldest + generation, objects in that generation remain there after a collection. In + order to decide when to run, the collector keeps track of the number object allocations and deallocations since the last collection. When the number of allocations minus the number of deallocations exceeds *threshold0*, collection - starts. For each collection, all the objects in the young generation and some - fraction of the old generation is collected. + starts. Initially only generation ``0`` is examined. If generation ``0`` has + been examined more than *threshold1* times since generation ``1`` has been + examined, then generation ``1`` is examined as well. + With the third generation, things are a bit more complicated, + see `Collecting the oldest generation `_ for more information. In the free-threaded build, the increase in process memory usage is also checked before running the collector. If the memory usage has not increased by 10% since the last collection and the net number of object allocations has not exceeded 40 times *threshold0*, the collection is not run. - The fraction of the old generation that is collected is **inversely** proportional - to *threshold1*. The larger *threshold1* is, the slower objects in the old generation - are collected. - For the default value of 10, 1% of the old generation is scanned during each collection. - - *threshold2* is ignored. + See `Garbage collector design `_ for more information. - See `Garbage collector design `_ for more information. - - .. versionchanged:: 3.13 + .. versionchanged:: 3.14 *threshold2* is ignored + .. versionchanged:: 3.14.5 + *threshold2* is restored to match Python 3.13 behavior. + .. function:: get_count() diff --git a/Doc/library/getopt.rst b/Doc/library/getopt.rst index 5c63009e22d58c..9995f114d063e8 100644 --- a/Doc/library/getopt.rst +++ b/Doc/library/getopt.rst @@ -62,6 +62,8 @@ exception: option ``--fo`` will match as ``--foo``, but ``--f`` will not match uniquely, so :exc:`GetoptError` will be raised. + If *longopts* is a string it gets treated as a list of a single element. + The return value consists of two elements: the first is a list of ``(option, value)`` pairs; the second is the list of program arguments left after the option list was stripped (this is a trailing slice of *args*). Each diff --git a/Doc/library/getpass.rst b/Doc/library/getpass.rst index 0fb0fc88683c03..37ffbe1be55a73 100644 --- a/Doc/library/getpass.rst +++ b/Doc/library/getpass.rst @@ -14,7 +14,7 @@ .. include:: ../includes/wasm-notavail.rst -The :mod:`getpass` module provides two functions: +The :mod:`!getpass` module provides two functions: .. function:: getpass(prompt='Password: ', stream=None, *, echo_char=None) @@ -27,9 +27,9 @@ The :mod:`getpass` module provides two functions: The *echo_char* argument controls how user input is displayed while typing. If *echo_char* is ``None`` (default), input remains hidden. Otherwise, - *echo_char* must be a printable ASCII string and each typed character - is replaced by it. For example, ``echo_char='*'`` will display - asterisks instead of the actual input. + *echo_char* must be a single printable ASCII character and each + typed character is replaced by it. For example, ``echo_char='*'`` will + display asterisks instead of the actual input. If echo free input is unavailable getpass() falls back to printing a warning message to *stream* and reading from ``sys.stdin`` and @@ -39,6 +39,14 @@ The :mod:`getpass` module provides two functions: If you call getpass from within IDLE, the input may be done in the terminal you launched IDLE from rather than the idle window itself. + .. note:: + On Unix systems, when *echo_char* is set, the terminal will be + configured to operate in + :manpage:`noncanonical mode `. + In particular, this means that line editing shortcuts such as + :kbd:`Ctrl+U` will not work and may insert unexpected characters into + the input. + .. versionchanged:: 3.14 Added the *echo_char* parameter for keyboard feedback. diff --git a/Doc/library/gettext.rst b/Doc/library/gettext.rst index d0de83907eb297..e6b3565173fe1c 100644 --- a/Doc/library/gettext.rst +++ b/Doc/library/gettext.rst @@ -11,7 +11,7 @@ -------------- -The :mod:`gettext` module provides internationalization (I18N) and localization +The :mod:`!gettext` module provides internationalization (I18N) and localization (L10N) services for your Python modules and applications. It supports both the GNU :program:`gettext` message catalog API and a higher level, class-based API that may be more appropriate for Python files. The interface described below allows you @@ -25,7 +25,7 @@ Some hints on localizing your Python modules and applications are also given. GNU :program:`gettext` API -------------------------- -The :mod:`gettext` module defines the following API, which is very similar to +The :mod:`!gettext` module defines the following API, which is very similar to the GNU :program:`gettext` API. If you use this API you will affect the translation of your entire application globally. Often this is what you want if your application is monolingual, with the choice of language dependent on the @@ -37,7 +37,7 @@ class-based API instead. .. function:: bindtextdomain(domain, localedir=None) Bind the *domain* to the locale directory *localedir*. More concretely, - :mod:`gettext` will look for binary :file:`.mo` files for the given domain using + :mod:`!gettext` will look for binary :file:`.mo` files for the given domain using the path (on Unix): :file:`{localedir}/{language}/LC_MESSAGES/{domain}.mo`, where *language* is searched for in the environment variables :envvar:`LANGUAGE`, :envvar:`LC_ALL`, :envvar:`LC_MESSAGES`, and :envvar:`LANG` respectively. @@ -54,19 +54,19 @@ class-based API instead. .. index:: single: _ (underscore); gettext -.. function:: gettext(message) +.. function:: gettext(message, /) Return the localized translation of *message*, based on the current global domain, language, and locale directory. This function is usually aliased as :func:`!_` in the local namespace (see examples below). -.. function:: dgettext(domain, message) +.. function:: dgettext(domain, message, /) Like :func:`.gettext`, but look the message up in the specified *domain*. -.. function:: ngettext(singular, plural, n) +.. function:: ngettext(singular, plural, n, /) Like :func:`.gettext`, but consider plural forms. If a translation is found, apply the plural formula to *n*, and return the resulting message (some @@ -81,15 +81,15 @@ class-based API instead. formulas for a variety of languages. -.. function:: dngettext(domain, singular, plural, n) +.. function:: dngettext(domain, singular, plural, n, /) Like :func:`ngettext`, but look the message up in the specified *domain*. -.. function:: pgettext(context, message) -.. function:: dpgettext(domain, context, message) -.. function:: npgettext(context, singular, plural, n) -.. function:: dnpgettext(domain, context, singular, plural, n) +.. function:: pgettext(context, message, /) +.. function:: dpgettext(domain, context, message, /) +.. function:: npgettext(context, singular, plural, n, /) +.. function:: dnpgettext(domain, context, singular, plural, n, /) Similar to the corresponding functions without the ``p`` in the prefix (that is, :func:`gettext`, :func:`dgettext`, :func:`ngettext`, :func:`dngettext`), @@ -114,7 +114,7 @@ Here's an example of typical usage for this API:: Class-based API --------------- -The class-based API of the :mod:`gettext` module gives you more flexibility and +The class-based API of the :mod:`!gettext` module gives you more flexibility and greater convenience than the GNU :program:`gettext` API. It is the recommended way of localizing your Python applications and modules. :mod:`!gettext` defines a :class:`GNUTranslations` class which implements the parsing of GNU :file:`.mo` format @@ -226,20 +226,20 @@ are the methods of :class:`!NullTranslations`: translation for a given message. - .. method:: gettext(message) + .. method:: gettext(message, /) If a fallback has been set, forward :meth:`!gettext` to the fallback. Otherwise, return *message*. Overridden in derived classes. - .. method:: ngettext(singular, plural, n) + .. method:: ngettext(singular, plural, n, /) If a fallback has been set, forward :meth:`!ngettext` to the fallback. Otherwise, return *singular* if *n* is 1; return *plural* otherwise. Overridden in derived classes. - .. method:: pgettext(context, message) + .. method:: pgettext(context, message, /) If a fallback has been set, forward :meth:`pgettext` to the fallback. Otherwise, return the translated message. Overridden in derived classes. @@ -247,7 +247,7 @@ are the methods of :class:`!NullTranslations`: .. versionadded:: 3.8 - .. method:: npgettext(context, singular, plural, n) + .. method:: npgettext(context, singular, plural, n, /) If a fallback has been set, forward :meth:`npgettext` to the fallback. Otherwise, return the translated message. Overridden in derived classes. @@ -325,7 +325,7 @@ unexpected, or if other problems occur while reading the file, instantiating a The following methods are overridden from the base class implementation: - .. method:: gettext(message) + .. method:: gettext(message, /) Look up the *message* id in the catalog and return the corresponding message string, as a Unicode string. If there is no entry in the catalog for the @@ -334,7 +334,7 @@ unexpected, or if other problems occur while reading the file, instantiating a *message* id is returned. - .. method:: ngettext(singular, plural, n) + .. method:: ngettext(singular, plural, n, /) Do a plural-forms lookup of a message id. *singular* is used as the message id for purposes of lookup in the catalog, while *n* is used to determine which @@ -355,7 +355,7 @@ unexpected, or if other problems occur while reading the file, instantiating a n) % {'num': n} - .. method:: pgettext(context, message) + .. method:: pgettext(context, message, /) Look up the *context* and *message* id in the catalog and return the corresponding message string, as a Unicode string. If there is no @@ -366,7 +366,7 @@ unexpected, or if other problems occur while reading the file, instantiating a .. versionadded:: 3.8 - .. method:: npgettext(context, singular, plural, n) + .. method:: npgettext(context, singular, plural, n, /) Do a plural-forms lookup of a message id. *singular* is used as the message id for purposes of lookup in the catalog, while *n* is used to @@ -393,7 +393,7 @@ The Catalog constructor .. index:: single: GNOME -GNOME uses a version of the :mod:`gettext` module by James Henstridge, but this +GNOME uses a version of the :mod:`!gettext` module by James Henstridge, but this version has a slightly different API. Its documented usage was:: import gettext @@ -425,7 +425,7 @@ take the following steps: #. create language-specific translations of the message catalogs -#. use the :mod:`gettext` module so that message strings are properly translated +#. use the :mod:`!gettext` module so that message strings are properly translated In order to prepare your code for I18N, you need to look at all the strings in your files. Any string that needs to be translated should be marked by wrapping @@ -473,10 +473,10 @@ supported natural language. They send back the completed language-specific versions as a :file:`.po` file that's compiled into a machine-readable :file:`.mo` binary catalog file using the :program:`msgfmt` program. The :file:`.mo` files are used by the -:mod:`gettext` module for the actual translation processing at +:mod:`!gettext` module for the actual translation processing at run-time. -How you use the :mod:`gettext` module in your code depends on whether you are +How you use the :mod:`!gettext` module in your code depends on whether you are internationalizing a single module or your entire application. The next two sections will discuss each case. diff --git a/Doc/library/glob.rst b/Doc/library/glob.rst index 59ad1b07f27338..49fb430e7ae709 100644 --- a/Doc/library/glob.rst +++ b/Doc/library/glob.rst @@ -18,23 +18,27 @@ single: - (minus); in glob-style wildcards single: . (dot); in glob-style wildcards -The :mod:`glob` module finds all the pathnames matching a specified pattern -according to the rules used by the Unix shell, although results are returned in -arbitrary order. No tilde expansion is done, but ``*``, ``?``, and character +The :mod:`!glob` module finds pathnames +using pattern matching rules similar to the Unix shell. +No tilde expansion is done, but ``*``, ``?``, and character ranges expressed with ``[]`` will be correctly matched. This is done by using the :func:`os.scandir` and :func:`fnmatch.fnmatch` functions in concert, and not by actually invoking a subshell. -Note that files beginning with a dot (``.``) can only be matched by +.. note:: + The pathnames are returned in no particular order. If you need a specific + order, sort the results. + +By default, files beginning with a dot (``.``) can only be matched by patterns that also start with a dot, unlike :func:`fnmatch.fnmatch` or :func:`pathlib.Path.glob`. -(For tilde and shell variable expansion, use :func:`os.path.expanduser` and -:func:`os.path.expandvars`.) +For tilde and shell variable expansion, use :func:`os.path.expanduser` and +:func:`os.path.expandvars`. For a literal match, wrap the meta-characters in brackets. For example, ``'[?]'`` matches the character ``'?'``. -The :mod:`glob` module defines the following functions: +The :mod:`!glob` module defines the following functions: .. function:: glob(pathname, *, root_dir=None, dir_fd=None, recursive=False, \ @@ -51,7 +55,7 @@ The :mod:`glob` module defines the following functions: If *root_dir* is not ``None``, it should be a :term:`path-like object` specifying the root directory for searching. It has the same effect on - :func:`glob` as changing the current directory before calling it. If + :func:`!glob` as changing the current directory before calling it. If *pathname* is relative, the result will contain paths relative to *root_dir*. @@ -66,7 +70,8 @@ The :mod:`glob` module defines the following functions: pattern is followed by an :data:`os.sep` or :data:`os.altsep` then files will not match. - If *include_hidden* is true, "``**``" pattern will match hidden directories. + If *include_hidden* is true, wildcards can match path segments that + begin with a dot (``.``). .. audit-event:: glob.glob pathname,recursive glob.glob .. audit-event:: glob.glob/2 pathname,recursive,root_dir,dir_fd glob.glob @@ -79,6 +84,11 @@ The :mod:`glob` module defines the following functions: This function may return duplicate path names if *pathname* contains multiple "``**``" patterns and *recursive* is true. + .. note:: + Any :exc:`OSError` exceptions raised from scanning the filesystem are + suppressed. This includes :exc:`PermissionError` when accessing + directories without read permission. + .. versionchanged:: 3.5 Support for recursive globs using "``**``". @@ -102,6 +112,11 @@ The :mod:`glob` module defines the following functions: This function may return duplicate path names if *pathname* contains multiple "``**``" patterns and *recursive* is true. + .. note:: + Any :exc:`OSError` exceptions raised from scanning the filesystem are + suppressed. This includes :exc:`PermissionError` when accessing + directories without read permission. + .. versionchanged:: 3.5 Support for recursive globs using "``**``". @@ -117,7 +132,7 @@ The :mod:`glob` module defines the following functions: Escape all special characters (``'?'``, ``'*'`` and ``'['``). This is useful if you want to match an arbitrary literal string that may have special characters in it. Special characters in drive/UNC - sharepoints are not escaped, e.g. on Windows + sharepoints are not escaped, for example on Windows ``escape('//?/c:/Quo vadis?.txt')`` returns ``'//?/c:/Quo vadis[?].txt'``. .. versionadded:: 3.4 diff --git a/Doc/library/graphlib.rst b/Doc/library/graphlib.rst index 053d5f8231ba0e..21f4d1fb938038 100644 --- a/Doc/library/graphlib.rst +++ b/Doc/library/graphlib.rst @@ -204,7 +204,7 @@ Exceptions ---------- -The :mod:`graphlib` module defines the following exception classes: +The :mod:`!graphlib` module defines the following exception classes: .. exception:: CycleError diff --git a/Doc/library/grp.rst b/Doc/library/grp.rst index d1c7f22a209780..f436970e791ace 100644 --- a/Doc/library/grp.rst +++ b/Doc/library/grp.rst @@ -2,7 +2,6 @@ ================================== .. module:: grp - :platform: Unix :synopsis: The group database (getgrnam() and friends). -------------- diff --git a/Doc/library/gzip.rst b/Doc/library/gzip.rst index c9d96085ef739d..a3c98d2f42b0b1 100644 --- a/Doc/library/gzip.rst +++ b/Doc/library/gzip.rst @@ -11,9 +11,11 @@ This module provides a simple interface to compress and decompress files just like the GNU programs :program:`gzip` and :program:`gunzip` would. +.. include:: ../includes/optional-module.rst + The data compression is provided by the :mod:`zlib` module. -The :mod:`gzip` module provides the :class:`GzipFile` class, as well as the +The :mod:`!gzip` module provides the :class:`GzipFile` class, as well as the :func:`.open`, :func:`compress` and :func:`decompress` convenience functions. The :class:`GzipFile` class reads and writes :program:`gzip`\ -format files, automatically compressing or decompressing the data so that it looks like an @@ -267,20 +269,20 @@ Example of how to GZIP compress a binary string:: .. _gzip-cli: -Command Line Interface +Command-line interface ---------------------- -The :mod:`gzip` module provides a simple command line interface to compress or +The :mod:`!gzip` module provides a simple command line interface to compress or decompress files. -Once executed the :mod:`gzip` module keeps the input file(s). +Once executed the :mod:`!gzip` module keeps the input file(s). .. versionchanged:: 3.8 Add a new command line interface with a usage. By default, when you will execute the CLI, the default compression level is 6. -Command line options +Command-line options ^^^^^^^^^^^^^^^^^^^^ .. option:: file diff --git a/Doc/library/hashlib.rst b/Doc/library/hashlib.rst index bb2d2fad23bdb8..84039ad28182d5 100644 --- a/Doc/library/hashlib.rst +++ b/Doc/library/hashlib.rst @@ -61,7 +61,7 @@ if you are using a rare "FIPS compliant" build of Python. These correspond to :data:`algorithms_guaranteed`. Additional algorithms may also be available if your Python distribution's -:mod:`hashlib` was linked against a build of OpenSSL that provides others. +:mod:`!hashlib` was linked against a build of OpenSSL that provides others. Others *are not guaranteed available* on all installations and will only be accessible by name via :func:`new`. See :data:`algorithms_available`. @@ -284,7 +284,7 @@ a file or file-like object. Example: >>> import io, hashlib, hmac - >>> with open(hashlib.__file__, "rb") as f: + >>> with open("library/hashlib.rst", "rb") as f: ... digest = hashlib.file_digest(f, "sha256") ... >>> digest.hexdigest() # doctest: +ELLIPSIS @@ -303,7 +303,7 @@ a file or file-like object. .. versionadded:: 3.11 .. versionchanged:: 3.14 - Now raises a :exc:`BlockingIOError` if the file is opened in blocking + Now raises a :exc:`BlockingIOError` if the file is opened in non-blocking mode. Previously, spurious null bytes were added to the digest. @@ -390,7 +390,7 @@ BLAKE2 supports **keyed mode** (a faster and simpler replacement for HMAC_), **salted hashing**, **personalization**, and **tree hashing**. Hash objects from this module follow the API of standard library's -:mod:`hashlib` objects. +:mod:`!hashlib` objects. Creating hash objects diff --git a/Doc/library/heapq.rst b/Doc/library/heapq.rst index 922ba0c8aa4214..a21dc4885e4744 100644 --- a/Doc/library/heapq.rst +++ b/Doc/library/heapq.rst @@ -58,6 +58,11 @@ functions, respectively. The following functions are provided for min-heaps: +.. function:: heapify(x) + + Transform list *x* into a min-heap, in-place, in linear time. + + .. function:: heappush(heap, item) Push the value *item* onto the *heap*, maintaining the min-heap invariant. @@ -77,11 +82,6 @@ The following functions are provided for min-heaps: followed by a separate call to :func:`heappop`. -.. function:: heapify(x) - - Transform list *x* into a min-heap, in-place, in linear time. - - .. function:: heapreplace(heap, item) Pop and return the smallest item from the *heap*, and also push the new *item*. @@ -231,6 +231,42 @@ Heap elements can be tuples. This is useful for assigning comparison values (1, 'write spec') +Other Applications +------------------ + +`Medians `_ are a measure of +central tendency for a set of numbers. In distributions skewed by +outliers, the median provides a more stable estimate than an average +(arithmetic mean). A running median is an `online algorithm +`_ that updates +continuously as new data arrives. + +A running median can be efficiently implemented by balancing two heaps, +a max-heap for values at or below the midpoint and a min-heap for values +above the midpoint. When the two heaps have the same size, the new +median is the average of the tops of the two heaps; otherwise, the +median is at the top of the larger heap:: + + def running_median(iterable): + "Yields the cumulative median of values seen so far." + + lo = [] # max-heap + hi = [] # min-heap (same size as or one smaller than lo) + + for x in iterable: + if len(lo) == len(hi): + heappush_max(lo, heappushpop(hi, x)) + yield lo[0] + else: + heappush(hi, heappushpop_max(lo, x)) + yield (lo[0] + hi[0]) / 2 + +For example:: + + >>> list(running_median([5.0, 9.0, 4.0, 12.0, 8.0, 9.0])) + [5.0, 7.0, 5.0, 7.0, 8.0, 8.5] + + Priority Queue Implementation Notes ----------------------------------- diff --git a/Doc/library/hmac.rst b/Doc/library/hmac.rst index d6692033b2d4c3..d5608bd7543eb1 100644 --- a/Doc/library/hmac.rst +++ b/Doc/library/hmac.rst @@ -12,6 +12,9 @@ -------------- This module implements the HMAC algorithm as described by :rfc:`2104`. +The interface allows to use any hash function with a *fixed* digest size. +In particular, extendable output functions such as SHAKE-128 or SHAKE-256 +cannot be used with HMAC. .. function:: new(key, msg=None, digestmod) @@ -47,7 +50,9 @@ This module implements the HMAC algorithm as described by :rfc:`2104`. .. versionadded:: 3.7 -An HMAC object has the following methods: +.. class:: HMAC + + An HMAC object has the following methods: .. method:: HMAC.update(msg) diff --git a/Doc/library/html.parser.rst b/Doc/library/html.parser.rst index 6d433b5a04fc4a..11f851d4f6c4b7 100644 --- a/Doc/library/html.parser.rst +++ b/Doc/library/html.parser.rst @@ -15,14 +15,18 @@ This module defines a class :class:`HTMLParser` which serves as the basis for parsing text files formatted in HTML (HyperText Mark-up Language) and XHTML. -.. class:: HTMLParser(*, convert_charrefs=True) +.. class:: HTMLParser(*, convert_charrefs=True, scripting=False) Create a parser instance able to parse invalid markup. - If *convert_charrefs* is ``True`` (the default), all character - references (except the ones in ``script``/``style`` elements) are + If *convert_charrefs* is true (the default), all character + references (except the ones in elements like ``script`` and ``style``) are automatically converted to the corresponding Unicode characters. + If *scripting* is false (the default), the content of the ``noscript`` + element is parsed normally; if it's true, it's returned as is without + being parsed. + An :class:`.HTMLParser` instance is fed HTML data and calls handler methods when start tags, end tags, text, comments, and other markup elements are encountered. The user should subclass :class:`.HTMLParser` and override its @@ -37,13 +41,18 @@ parsing text files formatted in HTML (HyperText Mark-up Language) and XHTML. .. versionchanged:: 3.5 The default value for argument *convert_charrefs* is now ``True``. + .. versionchanged:: 3.14.1 + Added the *scripting* parameter. + Example HTML Parser Application ------------------------------- As a basic example, below is a simple HTML parser that uses the :class:`HTMLParser` class to print out start tags, end tags, and data -as they are encountered:: +as they are encountered: + +.. testcode:: from html.parser import HTMLParser @@ -63,7 +72,7 @@ as they are encountered:: The output will then be: -.. code-block:: none +.. testoutput:: Encountered a start tag: html Encountered a start tag: head @@ -132,7 +141,7 @@ implementations do nothing (except for :meth:`~HTMLParser.handle_startendtag`): argument is a list of ``(name, value)`` pairs containing the attributes found inside the tag's ``<>`` brackets. The *name* will be translated to lower case, and quotes in the *value* have been removed, and character and entity references - have been replaced. + have been replaced. For empty attributes, *value* is ``None``. For instance, for the tag ````, this method would be called as ``handle_starttag('a', [('href', 'https://www.cwi.nl/')])``. @@ -159,15 +168,15 @@ implementations do nothing (except for :meth:`~HTMLParser.handle_startendtag`): .. method:: HTMLParser.handle_data(data) This method is called to process arbitrary data (e.g. text nodes and the - content of ```` and ````). + content of elements like ``script`` and ``style``). .. method:: HTMLParser.handle_entityref(name) This method is called to process a named character reference of the form ``&name;`` (e.g. ``>``), where *name* is a general entity reference - (e.g. ``'gt'``). This method is never called if *convert_charrefs* is - ``True``. + (e.g. ``'gt'``). + This method is only called if *convert_charrefs* is false. .. method:: HTMLParser.handle_charref(name) @@ -175,8 +184,8 @@ implementations do nothing (except for :meth:`~HTMLParser.handle_startendtag`): This method is called to process decimal and hexadecimal numeric character references of the form :samp:`&#{NNN};` and :samp:`&#x{NNN};`. For example, the decimal equivalent for ``>`` is ``>``, whereas the hexadecimal is ``>``; - in this case the method will receive ``'62'`` or ``'x3E'``. This method - is never called if *convert_charrefs* is ``True``. + in this case the method will receive ``'62'`` or ``'x3E'``. + This method is only called if *convert_charrefs* is false. .. method:: HTMLParser.handle_comment(data) @@ -230,7 +239,9 @@ Examples -------- The following class implements a parser that will be used to illustrate more -examples:: +examples: + +.. testcode:: from html.parser import HTMLParser from html.entities import name2codepoint @@ -266,13 +277,17 @@ examples:: parser = MyHTMLParser() -Parsing a doctype:: +Parsing a doctype: + +.. doctest:: >>> parser.feed('') Decl : DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd" -Parsing an element with a few attributes and a title:: +Parsing an element with a few attributes and a title: + +.. doctest:: >>> parser.feed('The Python logo') Start tag: img @@ -284,8 +299,10 @@ Parsing an element with a few attributes and a title:: Data : Python End tag : h1 -The content of ``script`` and ``style`` elements is returned as is, without -further parsing:: +The content of elements like ``script`` and ``style`` is returned as is, +without further parsing: + +.. doctest:: >>> parser.feed('') Start tag: style @@ -294,22 +311,43 @@ further parsing:: End tag : style >>> parser.feed('') + ... 'alert("hello! ☺");') Start tag: script attr: ('type', 'text/javascript') - Data : alert("hello!"); + Data : alert("hello! ☺"); End tag : script -Parsing comments:: +Attribute names are converted to lowercase, quotes from attribute values removed, +and ``None`` is returned as *value* for empty attributes (such as ``checked``): + +.. doctest:: - >>> parser.feed('' + >>> parser.feed("") + Start tag: input + attr: ('type', 'checkbox') + attr: ('checked', None) + attr: ('required', '') + attr: ('disabled', 'disabled') + +Parsing comments: + +.. doctest:: + + >>> parser.feed('' ... '') - Comment : a comment + Comment : a comment Comment : [if IE 9]>IE-specific content'``):: +correct char (note: these 3 references are all equivalent to ``'>'``): + +.. doctest:: + >>> parser = MyHTMLParser() + >>> parser.feed('>>>') + Data : >>> + + >>> parser = MyHTMLParser(convert_charrefs=False) >>> parser.feed('>>>') Named ent: > Num ent : > @@ -317,18 +355,22 @@ correct char (note: these 3 references are all equivalent to ``'>'``):: Feeding incomplete chunks to :meth:`~HTMLParser.feed` works, but :meth:`~HTMLParser.handle_data` might be called more than once -(unless *convert_charrefs* is set to ``True``):: +if *convert_charrefs* is false: - >>> for chunk in ['buff', 'ered ', 'text']: +.. doctest:: + + >>> for chunk in ['buff', 'ered', ' text']: ... parser.feed(chunk) ... Start tag: span Data : buff Data : ered - Data : text + Data : text End tag : span -Parsing invalid HTML (e.g. unquoted attributes) also works:: +Parsing invalid HTML (e.g. unquoted attributes) also works: + +.. doctest:: >>> parser.feed('

tag soup

') Start tag: p diff --git a/Doc/library/html.rst b/Doc/library/html.rst index 9aa39ba9a42b0f..65c49a4107a048 100644 --- a/Doc/library/html.rst +++ b/Doc/library/html.rst @@ -14,9 +14,12 @@ This module defines utilities to manipulate HTML. Convert the characters ``&``, ``<`` and ``>`` in string *s* to HTML-safe sequences. Use this if you need to display text that might contain such - characters in HTML. If the optional flag *quote* is true, the characters - (``"``) and (``'``) are also translated; this helps for inclusion in an HTML - attribute value delimited by quotes, as in ````. + characters in HTML. If the optional flag *quote* is true (the default), the + characters (``"``) and (``'``) are also translated; this helps for inclusion + in an HTML attribute value delimited by quotes, as in ````. + If *quote* is set to false, the characters (``"``) and (``'``) are not + translated. + .. versionadded:: 3.2 diff --git a/Doc/library/http.client.rst b/Doc/library/http.client.rst index 2835c8d0eb711e..14c67a0600f728 100644 --- a/Doc/library/http.client.rst +++ b/Doc/library/http.client.rst @@ -125,7 +125,7 @@ This module provides the following function: Parse the headers from a file pointer *fp* representing a HTTP request/response. The file has to be a :class:`~io.BufferedIOBase` reader - (i.e. not text) and must provide a valid :rfc:`2822` style header. + (i.e. not text) and must provide a valid :rfc:`5322` style header. This function returns an instance of :class:`http.client.HTTPMessage` that holds the header fields, but no payload @@ -311,6 +311,12 @@ HTTPConnection Objects :class:`str` or bytes-like object that is not also a file as the body representation. + .. note:: + + Note that you must have read the whole response or call :meth:`close` + if :meth:`getresponse` raised an non-:exc:`ConnectionError` exception + before you can send a new request to the server. + .. versionchanged:: 3.2 *body* can now be an iterable. @@ -326,16 +332,15 @@ HTTPConnection Objects Should be called after a request is sent to get the response from the server. Returns an :class:`HTTPResponse` instance. - .. note:: - - Note that you must have read the whole response before you can send a new - request to the server. - .. versionchanged:: 3.5 If a :exc:`ConnectionError` or subclass is raised, the :class:`HTTPConnection` object will be ready to reconnect when a new request is sent. + Note that this does not apply to :exc:`OSError`\s raised by the underlying + socket. Instead the caller is responsible to call :meth:`close` on the + existing connection. + .. method:: HTTPConnection.set_debuglevel(level) diff --git a/Doc/library/http.cookiejar.rst b/Doc/library/http.cookiejar.rst index 23ddecf873876d..644ddffa05052b 100644 --- a/Doc/library/http.cookiejar.rst +++ b/Doc/library/http.cookiejar.rst @@ -11,8 +11,8 @@ -------------- -The :mod:`http.cookiejar` module defines classes for automatic handling of HTTP -cookies. It is useful for accessing web sites that require small pieces of data +The :mod:`!http.cookiejar` module defines classes for automatic handling of HTTP +cookies. It is useful for accessing websites that require small pieces of data -- :dfn:`cookies` -- to be set on the client machine by an HTTP response from a web server, and then returned to the server in later HTTP requests. @@ -21,7 +21,7 @@ Both the regular Netscape cookie protocol and the protocol defined by :rfc:`2109` cookies are parsed as Netscape cookies and subsequently treated either as Netscape or RFC 2965 cookies according to the 'policy' in effect. Note that the great majority of cookies on the internet are Netscape cookies. -:mod:`http.cookiejar` attempts to follow the de-facto Netscape cookie protocol (which +:mod:`!http.cookiejar` attempts to follow the de-facto Netscape cookie protocol (which differs substantially from that set out in the original Netscape specification), including taking note of the ``max-age`` and ``port`` cookie-attributes introduced with RFC 2965. @@ -29,7 +29,7 @@ introduced with RFC 2965. .. note:: The various named parameters found in :mailheader:`Set-Cookie` and - :mailheader:`Set-Cookie2` headers (eg. ``domain`` and ``expires``) are + :mailheader:`Set-Cookie2` headers (for example, ``domain`` and ``expires``) are conventionally referred to as :dfn:`attributes`. To distinguish them from Python attributes, the documentation for this module uses the term :dfn:`cookie-attribute` instead. @@ -88,7 +88,7 @@ The following classes are provided: Constructor arguments should be passed as keyword arguments only. *blocked_domains* is a sequence of domain names that we never accept cookies - from, nor return cookies to. *allowed_domains* if not :const:`None`, this is a + from, nor return cookies to. *allowed_domains* if not ``None``, this is a sequence of the only domains for which we accept and return cookies. *secure_protocols* is a sequence of protocols for which secure cookies can be added to. By default *https* and *wss* (secure websocket) are considered @@ -96,12 +96,12 @@ The following classes are provided: :class:`CookiePolicy` and :class:`DefaultCookiePolicy` objects. :class:`DefaultCookiePolicy` implements the standard accept / reject rules for - Netscape and :rfc:`2965` cookies. By default, :rfc:`2109` cookies (ie. cookies + Netscape and :rfc:`2965` cookies. By default, :rfc:`2109` cookies (that is, cookies received in a :mailheader:`Set-Cookie` header with a version cookie-attribute of 1) are treated according to the RFC 2965 rules. However, if RFC 2965 handling is turned off or :attr:`rfc2109_as_netscape` is ``True``, RFC 2109 cookies are 'downgraded' by the :class:`CookieJar` instance to Netscape cookies, by - setting the :attr:`version` attribute of the :class:`Cookie` instance to 0. + setting the :attr:`~Cookie.version` attribute of the :class:`Cookie` instance to 0. :class:`DefaultCookiePolicy` also provides some parameters to allow some fine-tuning of policy. @@ -109,8 +109,8 @@ The following classes are provided: .. class:: Cookie() This class represents Netscape, :rfc:`2109` and :rfc:`2965` cookies. It is not - expected that users of :mod:`http.cookiejar` construct their own :class:`Cookie` - instances. Instead, if necessary, call :meth:`make_cookies` on a + expected that users of :mod:`!http.cookiejar` construct their own :class:`Cookie` + instances. Instead, if necessary, call :meth:`~CookieJar.make_cookies` on a :class:`CookieJar` instance. @@ -121,13 +121,13 @@ The following classes are provided: Module :mod:`http.cookies` HTTP cookie classes, principally useful for server-side code. The - :mod:`http.cookiejar` and :mod:`http.cookies` modules do not depend on each + :mod:`!http.cookiejar` and :mod:`http.cookies` modules do not depend on each other. https://curl.se/rfc/cookie_spec.html The specification of the original Netscape cookie protocol. Though this is still the dominant protocol, the 'Netscape cookie protocol' implemented by all - the major browsers (and :mod:`http.cookiejar`) only bears a passing resemblance to + the major browsers (and :mod:`!http.cookiejar`) only bears a passing resemblance to the one sketched out in ``cookie_spec.html``. :rfc:`2109` - HTTP State Management Mechanism @@ -144,7 +144,7 @@ The following classes are provided: .. _cookie-jar-objects: -CookieJar and FileCookieJar Objects +CookieJar and FileCookieJar objects ----------------------------------- :class:`CookieJar` objects support the :term:`iterator` protocol for iterating over @@ -157,20 +157,27 @@ contained :class:`Cookie` objects. Add correct :mailheader:`Cookie` header to *request*. - If policy allows (ie. the :attr:`rfc2965` and :attr:`hide_cookie2` attributes of + If policy allows (that is, the :attr:`~CookiePolicy.rfc2965` and + :attr:`~CookiePolicy.hide_cookie2` attributes of the :class:`CookieJar`'s :class:`CookiePolicy` instance are true and false respectively), the :mailheader:`Cookie2` header is also added when appropriate. The *request* object (usually a :class:`urllib.request.Request` instance) - must support the methods :meth:`get_full_url`, :meth:`has_header`, - :meth:`get_header`, :meth:`header_items`, :meth:`add_unredirected_header` - and the attributes :attr:`host`, :attr:`!type`, :attr:`unverifiable` - and :attr:`origin_req_host` as documented by :mod:`urllib.request`. + must support the methods :meth:`~urllib.request.Request.get_full_url`, + :meth:`~urllib.request.Request.has_header`, + :meth:`~urllib.request.Request.get_header`, + :meth:`~urllib.request.Request.header_items`, + :meth:`~urllib.request.Request.add_unredirected_header` + and the attributes :attr:`~urllib.request.Request.host`, + :attr:`~urllib.request.Request.type`, :attr:`~urllib.request.Request.unverifiable` + and :attr:`~urllib.request.Request.origin_req_host` as documented by + :mod:`urllib.request`. .. versionchanged:: 3.3 - *request* object needs :attr:`origin_req_host` attribute. Dependency on a - deprecated method :meth:`get_origin_req_host` has been removed. + *request* object needs :attr:`~urllib.request.Request.origin_req_host` + attribute. Dependency on a deprecated method + :meth:`!get_origin_req_host` has been removed. .. method:: CookieJar.extract_cookies(response, request) @@ -183,20 +190,24 @@ contained :class:`Cookie` objects. as appropriate (subject to the :meth:`CookiePolicy.set_ok` method's approval). The *response* object (usually the result of a call to - :meth:`urllib.request.urlopen`, or similar) should support an :meth:`info` - method, which returns an :class:`email.message.Message` instance. + :meth:`urllib.request.urlopen`, or similar) should support an + :meth:`~http.client.HTTPResponse.info` method, which returns an + :class:`email.message.Message` instance. The *request* object (usually a :class:`urllib.request.Request` instance) - must support the method :meth:`get_full_url` and the attributes - :attr:`host`, :attr:`unverifiable` and :attr:`origin_req_host`, + must support the method :meth:`~urllib.request.Request.get_full_url` and + the attributes :attr:`~urllib.request.Request.host`, + :attr:`~urllib.request.Request.unverifiable` + and :attr:`~urllib.request.Request.origin_req_host`, as documented by :mod:`urllib.request`. The request is used to set default values for cookie-attributes as well as for checking that the cookie is allowed to be set. .. versionchanged:: 3.3 - *request* object needs :attr:`origin_req_host` attribute. Dependency on a - deprecated method :meth:`get_origin_req_host` has been removed. + *request* object needs :attr:`~urllib.request.Request.origin_req_host` + attribute. Dependency on a deprecated method + :meth:`!get_origin_req_host` has been removed. .. method:: CookieJar.set_policy(policy) @@ -239,13 +250,13 @@ contained :class:`Cookie` objects. Discard all session cookies. - Discards all contained cookies that have a true :attr:`discard` attribute + Discards all contained cookies that have a true :attr:`~Cookie.discard` attribute (usually because they had either no ``max-age`` or ``expires`` cookie-attribute, or an explicit ``discard`` cookie-attribute). For interactive browsers, the end of a session usually corresponds to closing the browser window. - Note that the :meth:`save` method won't save session cookies anyway, unless you - ask otherwise by passing a true *ignore_discard* argument. + Note that the :meth:`~FileCookieJar.save` method won't save session cookies + anyway, unless you ask otherwise by passing a true *ignore_discard* argument. :class:`FileCookieJar` implements the following additional methods: @@ -258,8 +269,9 @@ contained :class:`Cookie` objects. method unimplemented. *filename* is the name of file in which to save cookies. If *filename* is not - specified, :attr:`self.filename` is used (whose default is the value passed to - the constructor, if any); if :attr:`self.filename` is :const:`None`, + specified, :attr:`self.filename ` is used (whose + default is the value passed to the constructor, if any); if + :attr:`self.filename ` is ``None``, :exc:`ValueError` is raised. *ignore_discard*: save even cookies set to be discarded. *ignore_expires*: save @@ -352,7 +364,7 @@ writing. .. _cookie-policy-objects: -CookiePolicy Objects +CookiePolicy objects -------------------- Objects implementing the :class:`CookiePolicy` interface have the following @@ -436,7 +448,7 @@ setting and receiving any and all cookies (this is unlikely to be useful). .. _default-cookie-policy-objects: -DefaultCookiePolicy Objects +DefaultCookiePolicy objects --------------------------- Implements the standard rules for accepting and returning cookies. @@ -466,10 +478,10 @@ blocking some benign cookies). A domain blocklist and allowlist is provided (both off by default). Only domains not in the blocklist and present in the allowlist (if the allowlist is active) participate in cookie setting and returning. Use the *blocked_domains* -constructor argument, and :meth:`blocked_domains` and -:meth:`set_blocked_domains` methods (and the corresponding argument and methods -for *allowed_domains*). If you set an allowlist, you can turn it off again by -setting it to :const:`None`. +constructor argument, and :meth:`~DefaultCookiePolicy.blocked_domains` and +:meth:`~DefaultCookiePolicy.set_blocked_domains` methods (and the corresponding +argument and methods for *allowed_domains*). If you set an allowlist, you can +turn it off again by setting it to ``None``. Domains in block or allow lists that do not start with a dot must equal the cookie domain to be matched. For example, ``"example.com"`` matches a blocklist @@ -501,12 +513,12 @@ and ``".168.1.2"``, 192.168.1.2 is blocked, but 193.168.1.2 is not. .. method:: DefaultCookiePolicy.allowed_domains() - Return :const:`None`, or the sequence of allowed domains (as a tuple). + Return ``None``, or the sequence of allowed domains (as a tuple). .. method:: DefaultCookiePolicy.set_allowed_domains(allowed_domains) - Set the sequence of allowed domains, or :const:`None`. + Set the sequence of allowed domains, or ``None``. .. method:: DefaultCookiePolicy.is_not_allowed(domain) @@ -522,9 +534,9 @@ all be assigned to. .. attribute:: DefaultCookiePolicy.rfc2109_as_netscape If true, request that the :class:`CookieJar` instance downgrade :rfc:`2109` cookies - (ie. cookies received in a :mailheader:`Set-Cookie` header with a version + (that is, cookies received in a :mailheader:`Set-Cookie` header with a version cookie-attribute of 1) to Netscape cookies by setting the version attribute of - the :class:`Cookie` instance to 0. The default value is :const:`None`, in which + the :class:`Cookie` instance to 0. The default value is ``None``, in which case RFC 2109 cookies are downgraded if and only if :rfc:`2965` handling is turned off. Therefore, RFC 2109 cookies are downgraded by default. @@ -570,14 +582,14 @@ Netscape protocol strictness switches: Don't allow setting cookies whose path doesn't path-match request URI. -:attr:`strict_ns_domain` is a collection of flags. Its value is constructed by +:attr:`~DefaultCookiePolicy.strict_ns_domain` is a collection of flags. Its value is constructed by or-ing together (for example, ``DomainStrictNoDots|DomainStrictNonDomain`` means both flags are set). .. attribute:: DefaultCookiePolicy.DomainStrictNoDots - When setting cookies, the 'host prefix' must not contain a dot (eg. + When setting cookies, the 'host prefix' must not contain a dot (for example, ``www.foo.bar.com`` can't set a cookie for ``.bar.com``, because ``www.foo`` contains a dot). @@ -585,7 +597,7 @@ both flags are set). .. attribute:: DefaultCookiePolicy.DomainStrictNonDomain Cookies that did not explicitly specify a ``domain`` cookie-attribute can only - be returned to a domain equal to the domain that set the cookie (eg. + be returned to a domain equal to the domain that set the cookie (for example, ``spam.example.com`` won't be returned cookies from ``example.com`` that had no ``domain`` cookie-attribute). @@ -600,7 +612,7 @@ combinations of the above flags: .. attribute:: DefaultCookiePolicy.DomainLiberal - Equivalent to 0 (ie. all of the above Netscape domain strictness flags switched + Equivalent to 0 (that is, all of the above Netscape domain strictness flags switched off). @@ -609,7 +621,7 @@ combinations of the above flags: Equivalent to ``DomainStrictNoDots|DomainStrictNonDomain``. -Cookie Objects +Cookie objects -------------- :class:`Cookie` instances have Python attributes roughly corresponding to the @@ -617,7 +629,7 @@ standard cookie-attributes specified in the various cookie standards. The correspondence is not one-to-one, because there are complicated rules for assigning default values, because the ``max-age`` and ``expires`` cookie-attributes contain equivalent information, and because :rfc:`2109` cookies -may be 'downgraded' by :mod:`http.cookiejar` from version 1 to version 0 (Netscape) +may be 'downgraded' by :mod:`!http.cookiejar` from version 1 to version 0 (Netscape) cookies. Assignment to these attributes should not be necessary other than in rare @@ -627,9 +639,9 @@ internal consistency, so you should know what you're doing if you do that. .. attribute:: Cookie.version - Integer or :const:`None`. Netscape cookies have :attr:`version` 0. :rfc:`2965` and + Integer or ``None``. Netscape cookies have :attr:`version` 0. :rfc:`2965` and :rfc:`2109` cookies have a ``version`` cookie-attribute of 1. However, note that - :mod:`http.cookiejar` may 'downgrade' RFC 2109 cookies to Netscape cookies, in which + :mod:`!http.cookiejar` may 'downgrade' RFC 2109 cookies to Netscape cookies, in which case :attr:`version` is 0. @@ -640,13 +652,13 @@ internal consistency, so you should know what you're doing if you do that. .. attribute:: Cookie.value - Cookie value (a string), or :const:`None`. + Cookie value (a string), or ``None``. .. attribute:: Cookie.port - String representing a port or a set of ports (eg. '80', or '80,8080'), or - :const:`None`. + String representing a port or a set of ports (for example, '80', or '80,8080'), or + ``None``. .. attribute:: Cookie.domain @@ -656,7 +668,7 @@ internal consistency, so you should know what you're doing if you do that. .. attribute:: Cookie.path - Cookie path (a string, eg. ``'/acme/rocket_launchers'``). + Cookie path (a string, for example, ``'/acme/rocket_launchers'``). .. attribute:: Cookie.secure @@ -666,7 +678,7 @@ internal consistency, so you should know what you're doing if you do that. .. attribute:: Cookie.expires - Integer expiry date in seconds since epoch, or :const:`None`. See also the + Integer expiry date in seconds since epoch, or ``None``. See also the :meth:`is_expired` method. @@ -678,21 +690,21 @@ internal consistency, so you should know what you're doing if you do that. .. attribute:: Cookie.comment String comment from the server explaining the function of this cookie, or - :const:`None`. + ``None``. .. attribute:: Cookie.comment_url URL linking to a comment from the server explaining the function of this cookie, - or :const:`None`. + or ``None``. .. attribute:: Cookie.rfc2109 - ``True`` if this cookie was received as an :rfc:`2109` cookie (ie. the cookie + ``True`` if this cookie was received as an :rfc:`2109` cookie (that is, the cookie arrived in a :mailheader:`Set-Cookie` header, and the value of the Version cookie-attribute in that header was 1). This attribute is provided because - :mod:`http.cookiejar` may 'downgrade' RFC 2109 cookies to Netscape cookies, in + :mod:`!http.cookiejar` may 'downgrade' RFC 2109 cookies to Netscape cookies, in which case :attr:`version` is 0. @@ -744,7 +756,7 @@ The :class:`Cookie` class also defines the following method: Examples -------- -The first example shows the most common usage of :mod:`http.cookiejar`:: +The first example shows the most common usage of :mod:`!http.cookiejar`:: import http.cookiejar, urllib.request cj = http.cookiejar.CookieJar() diff --git a/Doc/library/http.cookies.rst b/Doc/library/http.cookies.rst index eb196320721194..1b2d17975a5edb 100644 --- a/Doc/library/http.cookies.rst +++ b/Doc/library/http.cookies.rst @@ -11,7 +11,7 @@ -------------- -The :mod:`http.cookies` module defines classes for abstracting the concept of +The :mod:`!http.cookies` module defines classes for abstracting the concept of cookies, an HTTP state management mechanism. It supports both simple string-only cookies, and provides an abstraction for having any serializable data-type as cookie value. @@ -65,7 +65,7 @@ in a cookie name (as :attr:`~Morsel.key`). Module :mod:`http.cookiejar` HTTP cookie handling for web *clients*. The :mod:`http.cookiejar` and - :mod:`http.cookies` modules do not depend on each other. + :mod:`!http.cookies` modules do not depend on each other. :rfc:`2109` - HTTP State Management Mechanism This is the state management specification implemented by this module. @@ -148,9 +148,12 @@ Morsel Objects in HTTP requests, and is not accessible through JavaScript. This is intended to mitigate some forms of cross-site scripting. - The attribute :attr:`samesite` specifies that the browser is not allowed to - send the cookie along with cross-site requests. This helps to mitigate CSRF - attacks. Valid values for this attribute are "Strict" and "Lax". + The attribute :attr:`samesite` controls when the browser sends the cookie with + cross-site requests. This helps to mitigate CSRF attacks. Valid values are + "Strict" (only sent with same-site requests), "Lax" (sent with same-site + requests and top-level navigations), and "None" (sent with same-site and + cross-site requests). When using "None", the "secure" attribute must also + be set, as required by modern browsers. The attribute :attr:`partitioned` indicates to user agents that these cross-site cookies *should* only be available in the same top-level context @@ -261,7 +264,7 @@ Morsel Objects Example ------- -The following example demonstrates how to use the :mod:`http.cookies` module. +The following example demonstrates how to use the :mod:`!http.cookies` module. .. doctest:: :options: +NORMALIZE_WHITESPACE @@ -289,9 +292,9 @@ The following example demonstrates how to use the :mod:`http.cookies` module. Set-Cookie: chips=ahoy Set-Cookie: vienna=finger >>> C = cookies.SimpleCookie() - >>> C.load('keebler="E=everybody; L=\\"Loves\\"; fudge=\\012;";') + >>> C.load('keebler="E=everybody; L=\\"Loves\\"; fudge=;";') >>> print(C) - Set-Cookie: keebler="E=everybody; L=\"Loves\"; fudge=\012;" + Set-Cookie: keebler="E=everybody; L=\"Loves\"; fudge=;" >>> C = cookies.SimpleCookie() >>> C["oreo"] = "doublestuff" >>> C["oreo"]["path"] = "/" diff --git a/Doc/library/http.rst b/Doc/library/http.rst index ce3fb9f8120502..43a801416e24f9 100644 --- a/Doc/library/http.rst +++ b/Doc/library/http.rst @@ -12,7 +12,7 @@ -------------- -:mod:`http` is a package that collects several modules for working with the +:mod:`!http` is a package that collects several modules for working with the HyperText Transfer Protocol: * :mod:`http.client` is a low-level HTTP protocol client; for high-level URL @@ -22,7 +22,7 @@ HyperText Transfer Protocol: * :mod:`http.cookiejar` provides persistence of cookies -The :mod:`http` module also defines the following enums that help you work with http related code: +The :mod:`!http` module also defines the following enums that help you work with http related code: .. class:: HTTPStatus @@ -139,7 +139,8 @@ equal to the constant name (i.e. ``http.HTTPStatus.OK`` is also available as .. versionchanged:: 3.13 Implemented RFC9110 naming for status constants. Old constant names are preserved for - backwards compatibility. + backwards compatibility: ``413 REQUEST_ENTITY_TOO_LARGE``, ``414 REQUEST_URI_TOO_LONG``, + ``416 REQUESTED_RANGE_NOT_SATISFIABLE`` and ``422 UNPROCESSABLE_ENTITY``. HTTP status category -------------------- diff --git a/Doc/library/http.server.rst b/Doc/library/http.server.rst index 54df4a7e804d50..a9242558c494af 100644 --- a/Doc/library/http.server.rst +++ b/Doc/library/http.server.rst @@ -19,7 +19,7 @@ This module defines classes for implementing HTTP servers. .. warning:: - :mod:`http.server` is not recommended for production. It only implements + :mod:`!http.server` is not recommended for production. It only implements :ref:`basic security checks `. .. include:: ../includes/wasm-notavail.rst @@ -39,7 +39,17 @@ handler. Code to create and run the server looks like this:: This class builds on the :class:`~socketserver.TCPServer` class by storing the server address as instance variables named :attr:`server_name` and :attr:`server_port`. The server is accessible by the handler, typically - through the handler's :attr:`server` instance variable. + through the handler's :attr:`~socketserver.BaseRequestHandler.server` + instance variable. + + .. attribute:: server_name + + The HTTP server's fully qualified domain name. + + .. attribute:: server_port + + The HTTP server's port number obtained from *server_address*. + .. class:: ThreadingHTTPServer(server_address, RequestHandlerClass) @@ -60,7 +70,7 @@ handler. Code to create and run the server looks like this:: object fails with a :exc:`RuntimeError`. The *certfile* argument is the path to the SSL certificate chain file, - and the *keyfile* is the path to file containing the private key. + and the *keyfile* is the path to the file containing the private key. A *password* can be specified for files protected and wrapped with PKCS#8, but beware that this could possibly expose hardcoded passwords in clear. @@ -99,7 +109,7 @@ instantiation, of which this module provides three different variants: This class is used to handle the HTTP requests that arrive at the server. By itself, it cannot respond to any actual HTTP requests; it must be subclassed - to handle each request method (e.g. GET or POST). + to handle each request method (for example, ``'GET'`` or ``'POST'``). :class:`BaseHTTPRequestHandler` provides a number of class and instance variables, and methods for use by subclasses. @@ -140,7 +150,7 @@ instantiation, of which this module provides three different variants: .. attribute:: path - Contains the request path. If query component of the URL is present, + Contains the request path. If the query component of the URL is present, then ``path`` includes the query. Using the terminology of :rfc:`3986`, ``path`` here includes ``hier-part`` and the ``query``. @@ -154,7 +164,7 @@ instantiation, of which this module provides three different variants: variable. This instance parses and manages the headers in the HTTP request. The :func:`~http.client.parse_headers` function from :mod:`http.client` is used to parse the headers and it requires that the - HTTP request provide a valid :rfc:`2822` style header. + HTTP request provide a valid :rfc:`5322` style header. .. attribute:: rfile @@ -190,7 +200,7 @@ instantiation, of which this module provides three different variants: Specifies a format string that should be used by :meth:`send_error` method for building an error response to the client. The string is filled by default with variables from :attr:`responses` based on the status code - that passed to :meth:`send_error`. + passed to :meth:`send_error`. .. attribute:: error_content_type @@ -238,10 +248,10 @@ instantiation, of which this module provides three different variants: .. method:: handle_expect_100() When an HTTP/1.1 conformant server receives an ``Expect: 100-continue`` - request header it responds back with a ``100 Continue`` followed by ``200 - OK`` headers. + request header it responds with a ``100 Continue`` followed by ``200 OK`` + headers. This method can be overridden to raise an error if the server does not - want the client to continue. For e.g. server can choose to send ``417 + want the client to continue. For example, the server can choose to send ``417 Expectation Failed`` as a response header and ``return False``. .. versionadded:: 3.2 @@ -287,16 +297,20 @@ instantiation, of which this module provides three different variants: specifying its value. Note that, after the send_header calls are done, :meth:`end_headers` MUST BE called in order to complete the operation. + This method does not reject input containing CRLF sequences. + .. versionchanged:: 3.2 Headers are stored in an internal buffer. .. method:: send_response_only(code, message=None) Sends the response header only, used for the purposes when ``100 - Continue`` response is sent by the server to the client. The headers not - buffered and sent directly the output stream.If the *message* is not + Continue`` response is sent by the server to the client. The headers are + not buffered and sent directly the output stream. If the *message* is not specified, the HTTP message corresponding the response *code* is sent. + This method does not reject *message* containing CRLF sequences. + .. versionadded:: 3.2 .. method:: end_headers() @@ -334,7 +348,7 @@ instantiation, of which this module provides three different variants: to create custom error logging mechanisms. The *format* argument is a standard printf-style format string, where the additional arguments to :meth:`log_message` are applied as inputs to the formatting. The client - ip address and current date and time are prefixed to every message logged. + IP address and current date and time are prefixed to every message logged. .. method:: version_string() @@ -386,6 +400,14 @@ instantiation, of which this module provides three different variants: This will be ``"SimpleHTTP/" + __version__``, where ``__version__`` is defined at the module level. + .. attribute:: index_pages + + Specifies the filenames that are treated as directory index pages. + + Defaults to ``("index.html", "index.htm")``. + + .. versionadded:: 3.12 + .. attribute:: extensions_map A dictionary mapping suffixes into MIME types, contains custom overrides @@ -409,8 +431,8 @@ instantiation, of which this module provides three different variants: The request is mapped to a local file by interpreting the request as a path relative to the current working directory. - If the request was mapped to a directory, the directory is checked for a - file named ``index.html`` or ``index.htm`` (in that order). If found, the + If the request was mapped to a directory, the directory is checked for + an index page as specified by :attr:`index_pages`. If found, the file's contents are returned; otherwise a directory listing is generated by calling the :meth:`list_directory` method. This method uses :func:`os.listdir` to scan the directory, and returns a ``404`` error @@ -429,8 +451,7 @@ instantiation, of which this module provides three different variants: ``'Last-Modified:'`` header with the file's modification time. Then follows a blank line signifying the end of the headers, and then the - contents of the file are output. If the file's MIME type starts with - ``text/`` the file is opened in text mode; otherwise binary mode is used. + contents of the file are output. For example usage, see the implementation of the ``test`` function in :source:`Lib/http/server.py`. @@ -438,9 +459,32 @@ instantiation, of which this module provides three different variants: .. versionchanged:: 3.7 Support of the ``'If-Modified-Since'`` header. -The :class:`SimpleHTTPRequestHandler` class can be used in the following -manner in order to create a very basic webserver serving files relative to -the current directory:: + .. method:: list_directory(path) + + Helper to list the contents of *path* when no index page is present. + + This returns either a :term:`file-like object` (which must be closed + by the caller) or ``None`` to indicate an error, in which case the + caller has nothing further to do. In either case, the headers are sent. + + .. method:: guess_type(path) + + Guess the type of the file at the given *path*. + + This returns a string of the form ``type/subtype``, usable for + a MIME Content-type header. + + The default implementation looks the file's extension up in + :attr:`extensions_map`, falling back to + :func:`mimetypes.guess_file_type` and then to + ``'application/octet-stream'``. + + .. versionchanged:: 3.13 + Add :func:`mimetypes.guess_file_type` as a fallback. + + +The :class:`SimpleHTTPRequestHandler` class can be used to create a very basic +webserver serving files relative to the current directory as follows:: import http.server import socketserver @@ -456,7 +500,7 @@ the current directory:: :class:`SimpleHTTPRequestHandler` can also be subclassed to enhance behavior, such as using different index file names by overriding the class attribute -:attr:`index_pages`. +:attr:`~SimpleHTTPRequestHandler.index_pages`. .. class:: CGIHTTPRequestHandler(request, client_address, server) @@ -477,7 +521,9 @@ such as using different index file names by overriding the class attribute the other common server configuration is to treat special extensions as denoting CGI scripts. - The :func:`do_GET` and :func:`do_HEAD` functions are modified to run CGI scripts + The :func:`~SimpleHTTPRequestHandler.do_GET` and + :func:`~SimpleHTTPRequestHandler.do_HEAD` functions + are modified to run CGI scripts and serve the output, instead of serving files, if the request leads to somewhere below the ``cgi_directories`` path. @@ -513,9 +559,11 @@ such as using different index file names by overriding the class attribute Command-line interface ---------------------- -:mod:`http.server` can also be invoked directly using the :option:`-m` +:mod:`!http.server` can also be invoked directly using the :option:`-m` switch of the interpreter. The following example illustrates how to serve -files relative to the current directory:: +files relative to the current directory: + +.. code-block:: bash python -m http.server [OPTIONS] [port] @@ -526,7 +574,9 @@ The following options are accepted: .. option:: port The server listens to port 8000 by default. The default can be overridden - by passing the desired port number as an argument:: + by passing the desired port number as an argument: + + .. code-block:: bash python -m http.server 9000 @@ -535,7 +585,9 @@ The following options are accepted: Specifies a specific address to which it should bind. Both IPv4 and IPv6 addresses are supported. By default, the server binds itself to all interfaces. For example, the following command causes the server to bind - to localhost only:: + to localhost only: + + .. code-block:: bash python -m http.server --bind 127.0.0.1 @@ -548,7 +600,9 @@ The following options are accepted: Specifies a directory to which it should serve the files. By default, the server uses the current directory. For example, the following command - uses a specific directory:: + uses a specific directory: + + .. code-block:: bash python -m http.server --directory /tmp/ @@ -558,7 +612,9 @@ The following options are accepted: Specifies the HTTP version to which the server is conformant. By default, the server is conformant to HTTP/1.0. For example, the following command - runs an HTTP/1.1 conformant server:: + runs an HTTP/1.1 conformant server: + + .. code-block:: bash python -m http.server --protocol HTTP/1.1 @@ -573,7 +629,7 @@ The following options are accepted: .. deprecated-removed:: 3.13 3.15 - :mod:`http.server` command line ``--cgi`` support is being removed + :mod:`!http.server` command line ``--cgi`` support is being removed because :class:`CGIHTTPRequestHandler` is being removed. .. warning:: @@ -584,7 +640,9 @@ The following options are accepted: .. option:: --tls-cert - Specifies a TLS certificate chain for HTTPS connections:: + Specifies a TLS certificate chain for HTTPS connections: + + .. code-block:: bash python -m http.server --tls-cert fullchain.pem @@ -600,14 +658,16 @@ The following options are accepted: .. option:: --tls-password-file - Specifies the password file for password-protected private keys:: + Specifies the password file for password-protected private keys: + + .. code-block:: bash python -m http.server \ --tls-cert cert.pem \ --tls-key key.pem \ --tls-password-file password.txt - This option requires `--tls-cert`` to be specified. + This option requires ``--tls-cert`` to be specified. .. versionadded:: 3.14 @@ -620,9 +680,14 @@ Security considerations .. index:: pair: http.server; security :class:`SimpleHTTPRequestHandler` will follow symbolic links when handling -requests, this makes it possible for files outside of the specified directory +requests which makes it possible for files outside of the specified directory to be served. +Methods :meth:`BaseHTTPRequestHandler.send_header` and +:meth:`BaseHTTPRequestHandler.send_response_only` assume sanitized input +and do not perform input validation such as checking for the presence of CRLF +sequences. Untrusted input may result in HTTP header injection attacks. + Earlier versions of Python did not scrub control characters from the log messages emitted to stderr from ``python -m http.server`` or the default :class:`BaseHTTPRequestHandler` ``.log_message`` diff --git a/Doc/library/idle.rst b/Doc/library/idle.rst index fabea611e0ebcd..89be225b6baae4 100644 --- a/Doc/library/idle.rst +++ b/Doc/library/idle.rst @@ -13,7 +13,7 @@ IDLE --- Python editor and shell single: Integrated Development Environment .. - Remember to update Lib/idlelib/help.html with idlelib.help.copy_source() when modifying this file. + Remember to update Lib/idlelib/help.html with idlelib.help.copy_strip() when modifying this file. -------------- @@ -37,6 +37,10 @@ IDLE has the following features: * configuration, browsers, and other dialogs +The IDLE application is implemented in the :mod:`idlelib` package. + +.. include:: ../includes/optional-module.rst + Menus ----- @@ -88,7 +92,7 @@ Save Save As... Save the current window with a Save As dialog. The file saved becomes the - new associated file for the window. (If your file namager is set to hide + new associated file for the window. (If your file manager is set to hide extensions, the current extension will be omitted in the file name box. If the new filename has no '.', '.py' and '.txt' will be added for Python and text files, except that on macOS Aqua,'.py' is added for all files.) @@ -154,7 +158,7 @@ Go to Line Show Completions Open a scrollable list allowing selection of existing names. See - :ref:`Completions ` in the Editing and navigation section below. + :ref:`Completions ` in the Editing and Navigation section below. Expand Word Expand a prefix you have typed to match a full word in the same window; @@ -163,7 +167,7 @@ Expand Word Show Call Tip After an unclosed parenthesis for a function, open a small window with function parameter hints. See :ref:`Calltips ` in the - Editing and navigation section below. + Editing and Navigation section below. Show Surrounding Parens Highlight the surrounding parenthesis. @@ -174,9 +178,9 @@ Format menu (Editor window only) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Format Paragraph - Reformat the current blank-line-delimited paragraph in comment block or - multiline string or selected line in a string. All lines in the - paragraph will be formatted to less than N columns, where N defaults to 72. + Rewrap the text block containing the text insert cursor. + Avoid code lines. See :ref:`Format block` in the + Editing and Navigation section below. Indent Region Shift selected lines right by the indent width (default 4 spaces). @@ -204,9 +208,9 @@ New Indent Width Open a dialog to change indent width. The accepted default by the Python community is 4 spaces. -Strip Trailing Chitespace +Strip Trailing Whitespace Remove trailing space and other whitespace characters after the last - non-whitespace character of a line by applying str.rstrip to each line, + non-whitespace character of a line by applying :meth:`str.rstrip` to each line, including lines within multiline strings. Except for Shell windows, remove extra newlines at the end of the file. @@ -562,6 +566,20 @@ In an editor, import statements have no effect until one runs the file. One might want to run a file after writing import statements, after adding function definitions, or after opening an existing file. +.. _format-block: + +Format block +^^^^^^^^^^^^ + +Reformat Paragraph rewraps a block ('paragraph') of contiguous equally +indented non-blank comments, a similar block of text within a multiline +string, or a selected subset of either. +If needed, add a blank line to separate string from code. +Partial lines in a selection expand to complete lines. +The resulting lines have the same indent as before +but have maximum total length of N columns (characters). +Change the default N of 72 on the Window tab of IDLE Settings. + .. _code-context: Code Context @@ -657,7 +675,9 @@ looked for in the user's home directory. Statements in this file will be executed in the Tk namespace, so this file is not useful for importing functions to be used from IDLE's Python shell. -Command line usage +.. _idlelib-cli: + +Command-line usage ^^^^^^^^^^^^^^^^^^ .. program:: idle diff --git a/Doc/library/imaplib.rst b/Doc/library/imaplib.rst index 9f198aebcb66b0..131bc0101fb5a5 100644 --- a/Doc/library/imaplib.rst +++ b/Doc/library/imaplib.rst @@ -24,12 +24,12 @@ This module defines three classes, :class:`IMAP4`, :class:`IMAP4_SSL` and :class:`IMAP4_stream`, which encapsulate a connection to an IMAP4 server and implement a large subset of the IMAP4rev1 client protocol as defined in -:rfc:`2060`. It is backward compatible with IMAP4 (:rfc:`1730`) servers, but +:rfc:`3501`. It is backward compatible with IMAP4 (:rfc:`1730`) servers, but note that the ``STATUS`` command is not supported in IMAP4. .. include:: ../includes/wasm-notavail.rst -Three classes are provided by the :mod:`imaplib` module, :class:`IMAP4` is the +Three classes are provided by the :mod:`!imaplib` module, :class:`IMAP4` is the base class: @@ -97,6 +97,13 @@ There's also a subclass for secure connections: (potentially long-lived) structure. Please read :ref:`ssl-security` for best practices. + .. note:: + + With the default *ssl_context*, the connection is encrypted but the + server certificate and hostname are not verified. + To verify them, pass a context created by + :func:`ssl.create_default_context`. + The optional *timeout* parameter specifies a timeout in seconds for the connection attempt. If timeout is not given or is ``None``, the global default socket timeout is used. @@ -128,11 +135,11 @@ The second subclass allows for connections created by a child process: The following utility functions are defined: -.. function:: Internaldate2tuple(datestr) +.. function:: Internaldate2tuple(resp) - Parse an IMAP4 ``INTERNALDATE`` string and return corresponding local - time. The return value is a :class:`time.struct_time` tuple or - ``None`` if the string has wrong format. + Parse a :term:`bytes-like object` containing an IMAP4 ``INTERNALDATE`` + response and return the corresponding local time. The return value is a + :class:`time.struct_time` tuple or ``None`` if the input has wrong format. .. function:: Int2AP(num) @@ -140,9 +147,11 @@ The following utility functions are defined: [``A`` .. ``P``]. -.. function:: ParseFlags(flagstr) +.. function:: ParseFlags(resp) - Converts an IMAP4 ``FLAGS`` response to a tuple of individual flags. + Converts a :term:`bytes-like object` containing an IMAP4 ``FLAGS`` response + to a tuple of individual flags as :class:`bytes`. The return value is an + empty tuple if the input has wrong format. .. function:: Time2Internaldate(date_time) @@ -187,6 +196,9 @@ enclosed with either parentheses or double quotes) each string is quoted. However, the *password* argument to the ``LOGIN`` command is always quoted. If you want to avoid having an argument string quoted (eg: the *flags* argument to ``STORE``) then enclose the string in parentheses (eg: ``r'(\Deleted)'``). +In general, pass arguments unquoted and let the module quote them as needed. +An argument that is already enclosed in double quotes is left unchanged, +so that code which quotes arguments itself keeps working. Most commands return a tuple: ``(type, [data, ...])`` where *type* is usually ``'OK'`` or ``'NO'``, and *data* is either the text from the command response, @@ -207,6 +219,11 @@ An :class:`IMAP4` instance has the following methods: Append *message* to named mailbox. + *flags* may be ``None`` or a string of IMAP flag tokens. Multiple + flags are separated by spaces, for example ``r'\Seen \Answered'``. + If *flags* is not already enclosed in parentheses, parentheses are + added automatically. + .. method:: IMAP4.authenticate(mechanism, authobject) @@ -395,7 +412,7 @@ An :class:`IMAP4` instance has the following methods: .. versionadded:: 3.14 -.. method:: IMAP4.list([directory[, pattern]]) +.. method:: IMAP4.list(directory='', pattern='*') List mailbox names in *directory* matching *pattern*. *directory* defaults to the top-level mail folder, and *pattern* defaults to match anything. Returned @@ -413,6 +430,9 @@ An :class:`IMAP4` instance has the following methods: the password. Will only work if the server ``CAPABILITY`` response includes the phrase ``AUTH=CRAM-MD5``. + .. versionchanged:: 3.14 + An :exc:`IMAP4.error` is raised if MD5 support is not available. + .. method:: IMAP4.logout() @@ -422,7 +442,7 @@ An :class:`IMAP4` instance has the following methods: The method no longer ignores silently arbitrary exceptions. -.. method:: IMAP4.lsub(directory='""', pattern='*') +.. method:: IMAP4.lsub(directory='', pattern='*') List subscribed mailbox names in directory matching pattern. *directory* defaults to the top level directory and *pattern* defaults to match any mailbox. @@ -586,6 +606,13 @@ An :class:`IMAP4` instance has the following methods: encryption on the IMAP connection. Please read :ref:`ssl-security` for best practices. + .. note:: + + With the default *ssl_context*, the connection is encrypted but the + server certificate and hostname are not verified. + To verify them, pass a context created by + :func:`ssl.create_default_context`. + .. versionadded:: 3.2 .. versionchanged:: 3.4 @@ -602,7 +629,7 @@ An :class:`IMAP4` instance has the following methods: .. method:: IMAP4.store(message_set, command, flag_list) Alters flag dispositions for messages in mailbox. *command* is specified by - section 6.4.6 of :rfc:`2060` as being one of "FLAGS", "+FLAGS", or "-FLAGS", + section 6.4.6 of :rfc:`3501` as being one of "FLAGS", "+FLAGS", or "-FLAGS", optionally with a suffix of ".SILENT". For example, to set the delete flag on all messages:: @@ -616,11 +643,11 @@ An :class:`IMAP4` instance has the following methods: Creating flags containing ']' (for example: "[test]") violates :rfc:`3501` (the IMAP protocol). However, imaplib has historically - allowed creation of such tags, and popular IMAP servers, such as Gmail, + allowed creation of such flags, and popular IMAP servers, such as Gmail, accept and produce such flags. There are non-Python programs which also - create such tags. Although it is an RFC violation and IMAP clients and + create such flags. Although it is an RFC violation and IMAP clients and servers are supposed to be strict, imaplib still continues to allow - such tags to be created for backward compatibility reasons, and as of + such flags to be created for backward compatibility reasons, and as of Python 3.6, handles them if they are sent from the server, since this improves real-world compatibility. @@ -720,3 +747,10 @@ retrieves and prints all messages:: M.close() M.logout() +.. note:: + + A ``FETCH`` response may contain additional or unsolicited data + (see :rfc:`3501`, section 7.4.2), + so production code should inspect the whole response + rather than rely on ``data[0][1]``. + diff --git a/Doc/library/importlib.metadata.rst b/Doc/library/importlib.metadata.rst index 12014309e26ec9..3d5f4420a4f382 100644 --- a/Doc/library/importlib.metadata.rst +++ b/Doc/library/importlib.metadata.rst @@ -18,11 +18,9 @@ the metadata of an installed `Distribution Package `_\s, modules, if any). Built in part on Python's import system, this library -intends to replace similar functionality in the `entry point -API`_ and `metadata API`_ of ``pkg_resources``. Along with -:mod:`importlib.resources`, -this package can eliminate the need to use the older and less efficient -``pkg_resources`` package. +provides the entry point and metadata APIs that were previously +exposed by the now-removed ``pkg_resources`` package. Along with +:mod:`importlib.resources`, it supersedes ``pkg_resources``. ``importlib.metadata`` operates on third-party *distribution packages* installed into Python's ``site-packages`` directory via tools such as @@ -588,7 +586,3 @@ packages served by the ``DatabaseImporter``, assuming that the The ``DatabaseDistribution`` may also provide other metadata files, like ``RECORD`` (required for ``Distribution.files``) or override the implementation of ``Distribution.files``. See the source for more inspiration. - - -.. _`entry point API`: https://setuptools.readthedocs.io/en/latest/pkg_resources.html#entry-points -.. _`metadata API`: https://setuptools.readthedocs.io/en/latest/pkg_resources.html#metadata-api diff --git a/Doc/library/importlib.resources.abc.rst b/Doc/library/importlib.resources.abc.rst index 7a77466bcbaf27..45979c5691270a 100644 --- a/Doc/library/importlib.resources.abc.rst +++ b/Doc/library/importlib.resources.abc.rst @@ -49,44 +49,47 @@ .. method:: open_resource(resource) :abstractmethod: - Returns an opened, :term:`file-like object` for binary reading - of the *resource*. + Returns an opened, :term:`file-like object` for binary reading + of the *resource*. - If the resource cannot be found, :exc:`FileNotFoundError` is - raised. + If the resource cannot be found, :exc:`FileNotFoundError` is + raised. .. method:: resource_path(resource) :abstractmethod: - Returns the file system path to the *resource*. + Returns the file system path to the *resource*. - If the resource does not concretely exist on the file system, - raise :exc:`FileNotFoundError`. + If the resource does not concretely exist on the file system, + raise :exc:`FileNotFoundError`. - .. method:: is_resource(name) + .. method:: is_resource(path) :abstractmethod: - Returns ``True`` if the named *name* is considered a resource. - :exc:`FileNotFoundError` is raised if *name* does not exist. + Returns ``True`` if the named *path* is considered a resource. + :exc:`FileNotFoundError` is raised if *path* does not exist. + + .. versionchanged:: 3.10 + The argument *name* was renamed to *path*. .. method:: contents() :abstractmethod: - Returns an :term:`iterable` of strings over the contents of - the package. Do note that it is not required that all names - returned by the iterator be actual resources, e.g. it is - acceptable to return names for which :meth:`is_resource` would - be false. - - Allowing non-resource names to be returned is to allow for - situations where how a package and its resources are stored - are known a priori and the non-resource names would be useful. - For instance, returning subdirectory names is allowed so that - when it is known that the package and resources are stored on - the file system then those subdirectory names can be used - directly. - - The abstract method returns an iterable of no items. + Returns an :term:`iterable` of strings over the contents of + the package. Do note that it is not required that all names + returned by the iterator be actual resources, e.g. it is + acceptable to return names for which :meth:`is_resource` would + be false. + + Allowing non-resource names to be returned is to allow for + situations where how a package and its resources are stored + are known a priori and the non-resource names would be useful. + For instance, returning subdirectory names is allowed so that + when it is known that the package and resources are stored on + the file system then those subdirectory names can be used + directly. + + The abstract method returns an iterable of no items. .. class:: Traversable diff --git a/Doc/library/importlib.resources.rst b/Doc/library/importlib.resources.rst index e002198899c8b8..0bebd974d3ad30 100644 --- a/Doc/library/importlib.resources.rst +++ b/Doc/library/importlib.resources.rst @@ -16,11 +16,12 @@ within *packages*. "Resources" are file-like resources associated with a module or package in Python. The resources may be contained directly in a package, within a subdirectory contained in that package, or adjacent to modules outside a -package. Resources may be text or binary. As a result, Python module sources -(.py) of a package and compilation artifacts (pycache) are technically -de-facto resources of that package. In practice, however, resources are -primarily those non-Python artifacts exposed specifically by the package -author. +package. Resources may be text or binary. As a result, a package's Python +module sources (.py), compilation artifacts (pycache), and installation +artifacts (like :func:`reserved filenames ` +in directories) are technically de-facto resources of that package. +In practice, however, resources are primarily those non-Python artifacts +exposed specifically by the package author. Resources can be opened or read in either binary or text mode. @@ -30,15 +31,13 @@ not** have to exist as physical files and directories on the file system: for example, a package and its resources can be imported from a zip file using :py:mod:`zipimport`. -.. note:: +.. warning:: + + :mod:`importlib.resources` follows the same security model as the built-in + :func:`open` function. Passing untrusted inputs to the functions + in this module is unsafe. - This module provides functionality similar to `pkg_resources - `_ `Basic - Resource Access - `_ - without the performance overhead of that package. This makes reading - resources included in packages easier, with more stable and consistent - semantics. +.. note:: The standalone backport of this module provides more information on `using importlib.resources @@ -238,7 +237,6 @@ For all the following functions: .. versionchanged:: 3.13 Multiple *path_names* are accepted. - *encoding* and *errors* must be given as keyword arguments. .. function:: is_resource(anchor, *path_names) diff --git a/Doc/library/importlib.rst b/Doc/library/importlib.rst index ea5a77028683b3..2e65eff83f51a4 100644 --- a/Doc/library/importlib.rst +++ b/Doc/library/importlib.rst @@ -17,7 +17,7 @@ Introduction ------------ -The purpose of the :mod:`importlib` package is three-fold. +The purpose of the :mod:`!importlib` package is three-fold. One is to provide the implementation of the :keyword:`import` statement (and thus, by extension, the @@ -206,9 +206,13 @@ Functions :exc:`ModuleNotFoundError` is raised when the module being reloaded lacks a :class:`~importlib.machinery.ModuleSpec`. + .. warning:: + This function is not thread-safe. Calling it from multiple threads can result + in unexpected behavior. It's recommended to use the :class:`threading.Lock` + or other synchronization primitives for thread-safe module reloading. -:mod:`importlib.abc` -- Abstract base classes related to import ---------------------------------------------------------------- +:mod:`!importlib.abc` -- Abstract base classes related to import +---------------------------------------------------------------- .. module:: importlib.abc :synopsis: Abstract base classes related to import @@ -218,7 +222,7 @@ Functions -------------- -The :mod:`importlib.abc` module contains all of the core abstract base classes +The :mod:`!importlib.abc` module contains all of the core abstract base classes used by :keyword:`import`. Some subclasses of the core abstract base classes are also provided to help in implementing the core ABCs. @@ -389,6 +393,8 @@ ABC hierarchy:: .. deprecated:: 3.7 This ABC is deprecated in favour of supporting resource loading through :class:`importlib.resources.abc.TraversableResources`. + This class exists for backwards compatibility only with other ABCs in + this module. .. method:: get_data(path) :abstractmethod: @@ -631,174 +637,8 @@ ABC hierarchy:: itself does not end in ``__init__``. -.. class:: ResourceReader - - *Superseded by TraversableResources* - - An :term:`abstract base class` to provide the ability to read - *resources*. - - From the perspective of this ABC, a *resource* is a binary - artifact that is shipped within a package. Typically this is - something like a data file that lives next to the ``__init__.py`` - file of the package. The purpose of this class is to help abstract - out the accessing of such data files so that it does not matter if - the package and its data file(s) are stored e.g. in a zip file - versus on the file system. - - For any of methods of this class, a *resource* argument is - expected to be a :term:`path-like object` which represents - conceptually just a file name. This means that no subdirectory - paths should be included in the *resource* argument. This is - because the location of the package the reader is for, acts as the - "directory". Hence the metaphor for directories and file - names is packages and resources, respectively. This is also why - instances of this class are expected to directly correlate to - a specific package (instead of potentially representing multiple - packages or a module). - - Loaders that wish to support resource reading are expected to - provide a method called ``get_resource_reader(fullname)`` which - returns an object implementing this ABC's interface. If the module - specified by fullname is not a package, this method should return - :const:`None`. An object compatible with this ABC should only be - returned when the specified module is a package. - - .. versionadded:: 3.7 - - .. deprecated-removed:: 3.12 3.14 - Use :class:`importlib.resources.abc.TraversableResources` instead. - - .. method:: open_resource(resource) - :abstractmethod: - - Returns an opened, :term:`file-like object` for binary reading - of the *resource*. - - If the resource cannot be found, :exc:`FileNotFoundError` is - raised. - - .. method:: resource_path(resource) - :abstractmethod: - - Returns the file system path to the *resource*. - - If the resource does not concretely exist on the file system, - raise :exc:`FileNotFoundError`. - - .. method:: is_resource(name) - :abstractmethod: - - Returns ``True`` if the named *name* is considered a resource. - :exc:`FileNotFoundError` is raised if *name* does not exist. - - .. method:: contents() - :abstractmethod: - - Returns an :term:`iterable` of strings over the contents of - the package. Do note that it is not required that all names - returned by the iterator be actual resources, e.g. it is - acceptable to return names for which :meth:`is_resource` would - be false. - - Allowing non-resource names to be returned is to allow for - situations where how a package and its resources are stored - are known a priori and the non-resource names would be useful. - For instance, returning subdirectory names is allowed so that - when it is known that the package and resources are stored on - the file system then those subdirectory names can be used - directly. - - The abstract method returns an iterable of no items. - - -.. class:: Traversable - - An object with a subset of :class:`pathlib.Path` methods suitable for - traversing directories and opening files. - - For a representation of the object on the file-system, use - :meth:`importlib.resources.as_file`. - - .. versionadded:: 3.9 - - .. deprecated-removed:: 3.12 3.14 - Use :class:`importlib.resources.abc.Traversable` instead. - - .. attribute:: name - - Abstract. The base name of this object without any parent references. - - .. method:: iterdir() - :abstractmethod: - - Yield ``Traversable`` objects in ``self``. - - .. method:: is_dir() - :abstractmethod: - - Return ``True`` if ``self`` is a directory. - - .. method:: is_file() - :abstractmethod: - - Return ``True`` if ``self`` is a file. - - .. method:: joinpath(child) - :abstractmethod: - - Return Traversable child in ``self``. - - .. method:: __truediv__(child) - :abstractmethod: - - Return ``Traversable`` child in ``self``. - - .. method:: open(mode='r', *args, **kwargs) - :abstractmethod: - - *mode* may be 'r' or 'rb' to open as text or binary. Return a handle - suitable for reading (same as :attr:`pathlib.Path.open`). - - When opening as text, accepts encoding parameters such as those - accepted by :class:`io.TextIOWrapper`. - - .. method:: read_bytes() - - Read contents of ``self`` as bytes. - - .. method:: read_text(encoding=None) - - Read contents of ``self`` as text. - - -.. class:: TraversableResources - - An abstract base class for resource readers capable of serving - the :meth:`importlib.resources.files` interface. Subclasses - :class:`importlib.resources.abc.ResourceReader` and provides - concrete implementations of the :class:`importlib.resources.abc.ResourceReader`'s - abstract methods. Therefore, any loader supplying - :class:`importlib.abc.TraversableResources` also supplies ResourceReader. - - Loaders that wish to support resource reading are expected to - implement this interface. - - .. versionadded:: 3.9 - - .. deprecated-removed:: 3.12 3.14 - Use :class:`importlib.resources.abc.TraversableResources` instead. - - .. method:: files() - :abstractmethod: - - Returns a :class:`importlib.resources.abc.Traversable` object for the loaded - package. - - - -:mod:`importlib.machinery` -- Importers and path hooks ------------------------------------------------------- +:mod:`!importlib.machinery` -- Importers and path hooks +------------------------------------------------------- .. module:: importlib.machinery :synopsis: Importers and path hooks @@ -1247,7 +1087,7 @@ find and load modules. To accommodate this requirement, when running on iOS, extension module binaries are *not* packaged as ``.so`` files on ``sys.path``, but as individual standalone frameworks. To discover those frameworks, this loader - is be registered against the ``.fwork`` file extension, with a ``.fwork`` + is registered against the ``.fwork`` file extension, with a ``.fwork`` file acting as a placeholder in the original location of the binary on ``sys.path``. The ``.fwork`` file contains the path of the actual binary in the ``Frameworks`` folder, relative to the app bundle. To allow for @@ -1296,8 +1136,8 @@ find and load modules. Path to the ``.fwork`` file for the extension module. -:mod:`importlib.util` -- Utility code for importers ---------------------------------------------------- +:mod:`!importlib.util` -- Utility code for importers +---------------------------------------------------- .. module:: importlib.util :synopsis: Utility code for importers diff --git a/Doc/library/index.rst b/Doc/library/index.rst index 44b218948d07e1..8fc77be520d426 100644 --- a/Doc/library/index.rst +++ b/Doc/library/index.rst @@ -43,6 +43,7 @@ the `Python Package Index `_. constants.rst stdtypes.rst exceptions.rst + threadsafety.rst text.rst binary.rst @@ -63,7 +64,6 @@ the `Python Package Index `_. internet.rst mm.rst i18n.rst - frameworks.rst tk.rst development.rst debug.rst diff --git a/Doc/library/inspect.rst b/Doc/library/inspect.rst index e8d1176f477866..411b376277b8e0 100644 --- a/Doc/library/inspect.rst +++ b/Doc/library/inspect.rst @@ -16,7 +16,7 @@ -------------- -The :mod:`inspect` module provides several useful functions to help get +The :mod:`!inspect` module provides several useful functions to help get information about live objects such as modules, classes, methods, functions, tracebacks, frame objects, and code objects. For example, it can help you examine the contents of a class, retrieve the source code of a method, extract @@ -253,6 +253,9 @@ attributes (see :ref:`import-mod-attrs` for module attributes): +-----------------+-------------------+---------------------------+ | | gi_running | is the generator running? | +-----------------+-------------------+---------------------------+ +| | gi_suspended | is the generator | +| | | suspended? | ++-----------------+-------------------+---------------------------+ | | gi_code | code | +-----------------+-------------------+---------------------------+ | | gi_yieldfrom | object being iterated by | @@ -270,6 +273,9 @@ attributes (see :ref:`import-mod-attrs` for module attributes): +-----------------+-------------------+---------------------------+ | | ag_running | is the generator running? | +-----------------+-------------------+---------------------------+ +| | ag_suspended | is the generator | +| | | suspended? | ++-----------------+-------------------+---------------------------+ | | ag_code | code | +-----------------+-------------------+---------------------------+ | coroutine | __name__ | name | @@ -283,6 +289,9 @@ attributes (see :ref:`import-mod-attrs` for module attributes): +-----------------+-------------------+---------------------------+ | | cr_running | is the coroutine running? | +-----------------+-------------------+---------------------------+ +| | cr_suspended | is the coroutine | +| | | suspended? | ++-----------------+-------------------+---------------------------+ | | cr_code | code | +-----------------+-------------------+---------------------------+ | | cr_origin | where coroutine was | @@ -316,6 +325,18 @@ attributes (see :ref:`import-mod-attrs` for module attributes): Add ``__builtins__`` attribute to functions. +.. versionchanged:: 3.11 + + Add ``gi_suspended`` attribute to generators. + +.. versionchanged:: 3.11 + + Add ``cr_suspended`` attribute to coroutines. + +.. versionchanged:: 3.12 + + Add ``ag_suspended`` attribute to async generators. + .. versionchanged:: 3.14 Add ``f_generator`` attribute to frames. @@ -378,17 +399,47 @@ attributes (see :ref:`import-mod-attrs` for module attributes): Return ``True`` if the object is a class, whether built-in or created in Python code. + This function returns ``False`` for :ref:`generic aliases ` of classes, + such as ``list[int]``. + .. function:: ismethod(object) Return ``True`` if the object is a bound method written in Python. + .. note:: -.. function:: ispackage(object) + For example, given this class:: - Return ``True`` if the object is a :term:`package`. + >>> class Greeter: + ... def say_hello(self): + ... print('hello!') - .. versionadded:: 3.14 + A bound method (also known as an *instance method*) is created when + accessing ``say_hello`` (a :term:`function` defined in the + ``Greeter`` namespace) through an instance of the ``Greeter`` class:: + + >>> instance = Greeter() + + >>> instance.say_hello + > + >>> ismethod(instance.say_hello) + True + >>> isfunction(instance.say_hello) + False + + Accessing ``say_hello`` through the ``Greeter`` class will return the + function itself. For this function, :func:`ismethod` will return + ``False``, but :func:`isfunction` will return ``True``:: + + >>> Greeter.say_hello + + >>> ismethod(Greeter.say_hello) + False + >>> isfunction(Greeter.say_hello) + True + + See :ref:`typesmethods` for details. .. function:: isfunction(object) @@ -396,11 +447,23 @@ attributes (see :ref:`import-mod-attrs` for module attributes): Return ``True`` if the object is a Python function, which includes functions created by a :term:`lambda` expression. + See the note for :func:`~inspect.ismethod` for an example. + + +.. function:: ispackage(object) + + Return ``True`` if the object is a :term:`package`. + + .. versionadded:: 3.14 + .. function:: isgeneratorfunction(object) Return ``True`` if the object is a Python generator function. + It also returns ``True`` for bound methods created from Python generator functions + (see :ref:`typesmethods` for more information). + .. versionchanged:: 3.8 Functions wrapped in :func:`functools.partial` now return ``True`` if the wrapped function is a Python generator function. @@ -503,7 +566,7 @@ attributes (see :ref:`import-mod-attrs` for module attributes): .. versionchanged:: 3.13 Functions wrapped in :func:`functools.partialmethod` now return ``True`` - if the wrapped function is a :term:`coroutine function`. + if the wrapped function is a :term:`asynchronous generator` function. .. function:: isasyncgen(object) @@ -555,8 +618,7 @@ attributes (see :ref:`import-mod-attrs` for module attributes): .. function:: ismethoddescriptor(object) Return ``True`` if the object is a method descriptor, but not if - :func:`ismethod`, :func:`isclass`, :func:`isfunction` or :func:`isbuiltin` - are true. + :func:`isclass`, :func:`ismethod` or :func:`isfunction` is true. This, for example, is true of ``int.__add__``. An object passing this test has a :meth:`~object.__get__` method, but not a :meth:`~object.__set__` @@ -564,10 +626,10 @@ attributes (see :ref:`import-mod-attrs` for module attributes): attributes varies. A :attr:`~definition.__name__` attribute is usually sensible, and :attr:`~definition.__doc__` often is. - Methods implemented via descriptors that also pass one of the other tests - return ``False`` from the :func:`ismethoddescriptor` test, simply because the - other tests promise more -- you can, e.g., count on having the - :attr:`~method.__func__` attribute (etc) when an object passes + Method descriptors that also pass any of the other tests (:func:`!isclass`, + :func:`!ismethod` or :func:`!isfunction`) make this function return ``False``, + simply because those other tests promise more -- you can, for example, count + on having the :attr:`~method.__func__` attribute when an object passes :func:`ismethod`. .. versionchanged:: 3.13 @@ -578,16 +640,28 @@ attributes (see :ref:`import-mod-attrs` for module attributes): .. function:: isdatadescriptor(object) - Return ``True`` if the object is a data descriptor. + Return ``True`` if the object is a data descriptor, but not if + :func:`isclass`, :func:`ismethod` or :func:`isfunction` is true. + + Data descriptors always have a :meth:`~object.__set__` method and/or + a :meth:`~object.__delete__` method. Optionally, they may also have a + :meth:`~object.__get__` method. - Data descriptors have a :attr:`~object.__set__` or a :attr:`~object.__delete__` method. - Examples are properties (defined in Python), getsets, and members. The - latter two are defined in C and there are more specific tests available for - those types, which is robust across Python implementations. Typically, data - descriptors will also have :attr:`~definition.__name__` and :attr:`!__doc__` attributes - (properties, getsets, and members have both of these attributes), but this is - not guaranteed. + Examples of data descriptors are :func:`properties `, getsets and + member descriptors. Note that for the latter two (defined only in C extension + modules), more specific tests are available: :func:`isgetsetdescriptor` and + :func:`ismemberdescriptor`, respectively. + While data descriptors may also have :attr:`~definition.__name__` and + :attr:`!__doc__` attributes (as properties, getsets and member descriptors + do), this is not necessarily the case in general. + + .. versionchanged:: 3.8 + This function now reports objects with only a :meth:`~object.__set__` method + as being data descriptors (the presence of :meth:`~object.__get__` is no + longer required for that). Moreover, objects with :meth:`~object.__delete__`, + but not :meth:`~object.__set__`, are now properly recognized as data + descriptors as well, which was not the case previously. .. function:: isgetsetdescriptor(object) @@ -640,6 +714,7 @@ Retrieving source code .. function:: getfile(object) Return the name of the (text or binary) file in which an object was defined. + An :exc:`OSError` is raised if the source code cannot be retrieved. This will fail with a :exc:`TypeError` if the object is a built-in module, class, or function. @@ -653,9 +728,10 @@ Retrieving source code .. function:: getsourcefile(object) Return the name of the Python source file in which an object was defined - or ``None`` if no way can be identified to get the source. This - will fail with a :exc:`TypeError` if the object is a built-in module, class, or - function. + or ``None`` if no way can be identified to get the source. An :exc:`OSError` is + raised if the source code cannot be retrieved. + This will fail with a :exc:`TypeError` if the object is a built-in module, + class, or function. .. function:: getsourcelines(object) @@ -1179,7 +1255,7 @@ Classes and functions :func:`signature` in Python 3.5, but that decision has been reversed in order to restore a clearly supported standard interface for single-source Python 2/3 code migrating away from the legacy - :func:`getargspec` API. + :func:`!getargspec` API. .. versionchanged:: 3.7 Python only explicitly guaranteed that it preserved the declaration @@ -1289,6 +1365,11 @@ Classes and functions This is an alias for :func:`annotationlib.get_annotations`; see the documentation of that function for more information. + .. caution:: + + This function may execute arbitrary code contained in annotations. + See :ref:`annotationlib-security` for more information. + .. versionadded:: 3.10 .. versionchanged:: 3.14 @@ -1506,10 +1587,11 @@ properties, will be invoked and :meth:`~object.__getattr__` and may be called. For cases where you want passive introspection, like documentation tools, this -can be inconvenient. :func:`getattr_static` has the same signature as :func:`getattr` +can be inconvenient. :func:`getattr_static` has a similar signature as :func:`getattr` but avoids executing code when it fetches attributes. -.. function:: getattr_static(obj, attr, default=None) +.. function:: getattr_static(obj, attr) + getattr_static(obj, attr, default) Retrieve attributes without triggering dynamic lookup via the descriptor protocol, :meth:`~object.__getattr__` @@ -1729,7 +1811,7 @@ which is a bitmap of the following flags: The flags are specific to CPython, and may not be defined in other Python implementations. Furthermore, the flags are an implementation detail, and can be removed or deprecated in future Python releases. - It's recommended to use public APIs from the :mod:`inspect` module + It's recommended to use public APIs from the :mod:`!inspect` module for any introspection needs. @@ -1768,10 +1850,10 @@ Buffer flags .. _inspect-module-cli: -Command Line Interface +Command-line interface ---------------------- -The :mod:`inspect` module also provides a basic introspection capability +The :mod:`!inspect` module also provides a basic introspection capability from the command line. .. program:: inspect diff --git a/Doc/library/io.rst b/Doc/library/io.rst index 3aa2f35f05eba0..7f72e72b3c86f9 100644 --- a/Doc/library/io.rst +++ b/Doc/library/io.rst @@ -24,7 +24,7 @@ Overview .. index:: single: file object; io module -The :mod:`io` module provides Python's main facilities for dealing with various +The :mod:`!io` module provides Python's main facilities for dealing with various types of I/O. There are three main types of I/O: *text I/O*, *binary I/O* and *raw I/O*. These are generic categories, and various backing stores can be used for each of them. A concrete object belonging to any of these @@ -46,6 +46,7 @@ will raise a :exc:`TypeError`. So will giving a :class:`bytes` object to the Operations that used to raise :exc:`IOError` now raise :exc:`OSError`, since :exc:`IOError` is now an alias of :exc:`OSError`. +.. _text-io: Text I/O ^^^^^^^^ @@ -73,6 +74,7 @@ In-memory text streams are also available as :class:`StringIO` objects:: The text stream API is described in detail in the documentation of :class:`TextIOBase`. +.. _binary-io: Binary I/O ^^^^^^^^^^ @@ -111,6 +113,13 @@ stream by opening a file in binary mode with buffering disabled:: The raw stream API is described in detail in the docs of :class:`RawIOBase`. +.. warning:: + Raw I/O is a low-level interface and methods generally must have their return + values checked and be explicitly retried to ensure an operation completes. + For instance :meth:`~RawIOBase.write` returns the number of bytes written + which may be less than the number of bytes provided (a partial write). + High-level I/O objects like :ref:`binary-io` and :ref:`text-io` implement + retry behavior. .. _io-text-encoding: @@ -292,7 +301,7 @@ interface to a buffered raw stream (:class:`BufferedIOBase`). Finally, Argument names are not part of the specification, and only the arguments of :func:`open` are intended to be used as keyword arguments. -The following table summarizes the ABCs provided by the :mod:`io` module: +The following table summarizes the ABCs provided by the :mod:`!io` module: .. tabularcolumns:: |l|l|L|L| @@ -486,8 +495,11 @@ I/O Base Classes Read up to *size* bytes from the object and return them. As a convenience, if *size* is unspecified or -1, all bytes until EOF are returned. - Otherwise, only one system call is ever made. Fewer than *size* bytes may - be returned if the operating system call returns fewer than *size* bytes. + + Attempts to make only one system call but will retry if interrupted and + the signal handler does not raise an exception (see :pep:`475` for the + rationale). This means fewer than *size* bytes may be returned if the + operating system call returns fewer than *size* bytes. If 0 bytes are returned, and *size* was not 0, this indicates end of file. If the object is in non-blocking mode and no bytes are available, @@ -501,13 +513,19 @@ I/O Base Classes Read and return all the bytes from the stream until EOF, using multiple calls to the stream if necessary. + If ``0`` bytes are returned this indicates end of file. If the object is in + non-blocking mode and the underlying :meth:`read` returns ``None`` + indicating no bytes are available, ``None`` is returned. + .. method:: readinto(b, /) Read bytes into a pre-allocated, writable :term:`bytes-like object` *b*, and return the number of bytes read. For example, *b* might be a :class:`bytearray`. - If the object is in non-blocking mode and no bytes - are available, ``None`` is returned. + + If ``0`` is returned and ``len(b)`` is not ``0``, this indicates end of file. If + the object is in non-blocking mode and no bytes are available, ``None`` is + returned. .. method:: write(b, /) @@ -521,6 +539,13 @@ I/O Base Classes this method returns, so the implementation should only access *b* during the method call. + .. warning:: + + This function does not ensure all bytes are written or an exception is + thrown. Callers may implement that behavior by checking the return + value and, if it is less than the length of *b*, looping with additional + write calls until all unwritten bytes are written. High-level I/O + objects like :ref:`binary-io` and :ref:`text-io` implement retry behavior. .. class:: BufferedIOBase @@ -528,14 +553,13 @@ I/O Base Classes It inherits from :class:`IOBase`. The main difference with :class:`RawIOBase` is that methods :meth:`read`, - :meth:`readinto` and :meth:`write` will try (respectively) to read as much - input as requested or to consume all given output, at the expense of - making perhaps more than one system call. + :meth:`readinto` and :meth:`write` will try (respectively) to read + as much input as requested or to emit all provided data. - In addition, those methods can raise :exc:`BlockingIOError` if the - underlying raw stream is in non-blocking mode and cannot take or give - enough data; unlike their :class:`RawIOBase` counterparts, they will - never return ``None``. + In addition, if the underlying raw stream is in non-blocking mode, when the + system returns would block :meth:`write` will raise :exc:`BlockingIOError` + with :attr:`BlockingIOError.characters_written` and :meth:`read` will return + data read so far or ``None`` if no data is available. Besides, the :meth:`read` method does not have a default implementation that defers to :meth:`readinto`. @@ -568,29 +592,40 @@ I/O Base Classes .. method:: read(size=-1, /) - Read and return up to *size* bytes. If the argument is omitted, ``None``, - or negative, data is read and returned until EOF is reached. An empty - :class:`bytes` object is returned if the stream is already at EOF. + Read and return up to *size* bytes. If the argument is omitted, ``None``, + or negative read as much as possible. - If the argument is positive, and the underlying raw stream is not - interactive, multiple raw reads may be issued to satisfy the byte count - (unless EOF is reached first). But for interactive raw streams, at most - one raw read will be issued, and a short result does not imply that EOF is - imminent. + Fewer bytes may be returned than requested. An empty :class:`bytes` object + is returned if the stream is already at EOF. More than one read may be + made and calls may be retried if specific errors are encountered, see + :meth:`os.read` and :pep:`475` for more details. Less than size bytes + being returned does not imply that EOF is imminent. - A :exc:`BlockingIOError` is raised if the underlying raw stream is in - non blocking-mode, and has no data available at the moment. + When reading as much as possible the default implementation will use + ``raw.readall`` if available (which should implement + :meth:`RawIOBase.readall`), otherwise will read in a loop until read + returns ``None``, an empty :class:`bytes`, or a non-retryable error. For + most streams this is to EOF, but for non-blocking streams more data may + become available. + + .. note:: + + When the underlying raw stream is non-blocking, implementations may + either raise :exc:`BlockingIOError` or return ``None`` if no data is + available. :mod:`!io` implementations return ``None``. .. method:: read1(size=-1, /) - Read and return up to *size* bytes, with at most one call to the - underlying raw stream's :meth:`~RawIOBase.read` (or - :meth:`~RawIOBase.readinto`) method. This can be useful if you are - implementing your own buffering on top of a :class:`BufferedIOBase` - object. + Read and return up to *size* bytes, calling :meth:`~RawIOBase.readinto` + which may retry if :py:const:`~errno.EINTR` is encountered per + :pep:`475`. If *size* is ``-1`` or not provided, the implementation will + choose an arbitrary value for *size*. + + .. note:: - If *size* is ``-1`` (the default), an arbitrary number of bytes are - returned (more than zero unless EOF is reached). + When the underlying raw stream is non-blocking, implementations may + either raise :exc:`BlockingIOError` or return ``None`` if no data is + available. :mod:`!io` implementations return ``None``. .. method:: readinto(b, /) @@ -639,7 +674,11 @@ Raw File I/O .. class:: FileIO(name, mode='r', closefd=True, opener=None) A raw binary stream representing an OS-level file containing bytes data. It - inherits from :class:`RawIOBase`. + inherits from :class:`RawIOBase` and implements its low-level access design. + This means :meth:`~RawIOBase.write` does not guarantee all bytes are written + and :meth:`~RawIOBase.read` may read less bytes than requested even when more + bytes may be present in the underlying file. To get "write all" and + "read at least" behavior, use :ref:`binary-io`. The *name* can be one of two things: @@ -659,10 +698,6 @@ Raw File I/O implies writing, so this mode behaves in a similar way to ``'w'``. Add a ``'+'`` to the mode to allow simultaneous reading and writing. - The :meth:`~RawIOBase.read` (when called with a positive argument), - :meth:`~RawIOBase.readinto` and :meth:`~RawIOBase.write` methods on this - class will only make one system call. - A custom opener can be used by passing a callable as *opener*. The underlying file descriptor for the file object is then obtained by calling *opener* with (*name*, *flags*). *opener* must return an open file descriptor (passing @@ -674,6 +709,13 @@ Raw File I/O See the :func:`open` built-in function for examples on using the *opener* parameter. + .. warning:: + :class:`FileIO` is a low-level I/O object and members, such as + :meth:`~RawIOBase.read` and :meth:`~RawIOBase.write`, need to have their + return values checked explicitly in a retry loop to implement "write all" + and "read at least" behavior. High-level I/O objects :ref:`binary-io` and + :ref:`text-io` implement retry behavior. + .. versionchanged:: 3.3 The *opener* parameter was added. The ``'x'`` mode was added. @@ -767,34 +809,21 @@ than raw I/O does. .. method:: peek(size=0, /) - Return bytes from the stream without advancing the position. At most one - single read on the raw stream is done to satisfy the call. The number of - bytes returned may be less or more than requested. + Return bytes from the stream without advancing the position. The number of + bytes returned may be less or more than requested. If the underlying raw + stream is non-blocking and the operation would block, returns empty bytes. .. method:: read(size=-1, /) - Read and return *size* bytes, or if *size* is not given or negative, until - EOF or if the read call would block in non-blocking mode. - - .. note:: - - When the underlying raw stream is non-blocking, a :exc:`BlockingIOError` - may be raised if a read operation cannot be completed immediately. + In :class:`BufferedReader` this is the same as :meth:`io.BufferedIOBase.read` .. method:: read1(size=-1, /) - Read and return up to *size* bytes with only one call on the raw stream. - If at least one byte is buffered, only buffered bytes are returned. - Otherwise, one raw stream read call is made. + In :class:`BufferedReader` this is the same as :meth:`io.BufferedIOBase.read1` .. versionchanged:: 3.7 The *size* argument is now optional. - .. note:: - - When the underlying raw stream is non-blocking, a :exc:`BlockingIOError` - may be raised if a read operation cannot be completed immediately. - .. class:: BufferedWriter(raw, buffer_size=DEFAULT_BUFFER_SIZE) A buffered binary stream providing higher-level access to a writeable, non @@ -826,15 +855,15 @@ than raw I/O does. Write the :term:`bytes-like object`, *b*, and return the number of bytes written. When in non-blocking mode, a - :exc:`BlockingIOError` is raised if the buffer needs to be written out but - the raw stream blocks. + :exc:`BlockingIOError` with :attr:`BlockingIOError.characters_written` set + is raised if the buffer needs to be written out but the raw stream blocks. .. class:: BufferedRandom(raw, buffer_size=DEFAULT_BUFFER_SIZE) - A buffered binary stream providing higher-level access to a seekable - :class:`RawIOBase` raw binary stream. It inherits from :class:`BufferedReader` - and :class:`BufferedWriter`. + A buffered binary stream implementing :class:`BufferedIOBase` interfaces + providing higher-level access to a seekable :class:`RawIOBase` raw binary + stream. The constructor creates a reader and writer for a seekable raw stream, given in the first argument. If the *buffer_size* is omitted it defaults to @@ -894,9 +923,10 @@ Text I/O .. attribute:: buffer - The underlying binary buffer (a :class:`BufferedIOBase` instance) that - :class:`TextIOBase` deals with. This is not part of the - :class:`TextIOBase` API and may not exist in some implementations. + The underlying binary buffer (a :class:`BufferedIOBase` + or :class:`RawIOBase` instance) that :class:`TextIOBase` deals with. + This is not part of the :class:`TextIOBase` API and may not exist + in some implementations. .. method:: detach() diff --git a/Doc/library/ipaddress.rst b/Doc/library/ipaddress.rst index e5bdfbb144b65a..45256d29e854d0 100644 --- a/Doc/library/ipaddress.rst +++ b/Doc/library/ipaddress.rst @@ -10,7 +10,7 @@ -------------- -:mod:`ipaddress` provides the capabilities to create, manipulate and +:mod:`!ipaddress` provides the capabilities to create, manipulate and operate on IPv4 and IPv6 addresses and networks. The functions and classes in this module make it straightforward to handle @@ -34,7 +34,7 @@ This is the full module API reference—for an overview and introduction, see Convenience factory functions ----------------------------- -The :mod:`ipaddress` module provides factory functions to conveniently create +The :mod:`!ipaddress` module provides factory functions to conveniently create IP addresses, networks and interfaces: .. function:: ip_address(address) @@ -240,7 +240,16 @@ write code that handles both IP versions correctly. Address objects are .. attribute:: is_reserved - ``True`` if the address is otherwise IETF reserved. + ``True`` if the address is noted as reserved by the IETF. + For IPv4, this is only ``240.0.0.0/4``, the ``Reserved`` address block. + For IPv6, this is all addresses `allocated `__ as + ``Reserved by IETF`` for future use. + + .. note:: For IPv4, ``is_reserved`` is not related to the address block value of the + ``Reserved-by-Protocol`` column in iana-ipv4-special-registry_. + + .. caution:: For IPv6, ``fec0::/10`` a former Site-Local scoped address prefix is + currently excluded from that list (see :attr:`~IPv6Address.is_site_local` & :rfc:`3879`). .. attribute:: is_loopback @@ -261,6 +270,7 @@ write code that handles both IP versions correctly. Address objects are .. _iana-ipv4-special-registry: https://www.iana.org/assignments/iana-ipv4-special-registry/iana-ipv4-special-registry.xhtml .. _iana-ipv6-special-registry: https://www.iana.org/assignments/iana-ipv6-special-registry/iana-ipv6-special-registry.xhtml +.. _iana-ipv6-address-space: https://www.iana.org/assignments/ipv6-address-space/ipv6-address-space.xhtml .. method:: IPv4Address.__format__(fmt) @@ -359,9 +369,9 @@ write code that handles both IP versions correctly. Address objects are .. attribute:: ipv4_mapped - For addresses that appear to be IPv4 mapped addresses (starting with - ``::FFFF/96``), this property will report the embedded IPv4 address. - For any other address, this property will be ``None``. + For addresses that appear to be IPv4 mapped addresses in the range + ``::FFFF:0:0/96`` as defined by :RFC:`4291`, this property reports the + embedded IPv4 address. For any other address, this property will be ``None``. .. attribute:: scope_id @@ -1017,7 +1027,7 @@ The module also provides the following module level functions: IPv4Address('192.0.2.0') <= IPv4Network('192.0.2.0/24') doesn't make sense. There are some times however, where you may wish to - have :mod:`ipaddress` sort these anyway. If you need to do this, you can use + have :mod:`!ipaddress` sort these anyway. If you need to do this, you can use this function as the *key* argument to :func:`sorted`. *obj* is either a network or address object. diff --git a/Doc/library/itertools.rst b/Doc/library/itertools.rst index 00925ae920aad9..8bfe5ac31e8990 100644 --- a/Doc/library/itertools.rst +++ b/Doc/library/itertools.rst @@ -30,18 +30,7 @@ For instance, SML provides a tabulation tool: ``tabulate(f)`` which produces a sequence ``f(0), f(1), ...``. The same effect can be achieved in Python by combining :func:`map` and :func:`count` to form ``map(f, count())``. - -**Infinite iterators:** - -================== ================= ================================================= ========================================= -Iterator Arguments Results Example -================== ================= ================================================= ========================================= -:func:`count` [start[, step]] start, start+step, start+2*step, ... ``count(10) → 10 11 12 13 14 ...`` -:func:`cycle` p p0, p1, ... plast, p0, p1, ... ``cycle('ABCD') → A B C D A B C D ...`` -:func:`repeat` elem [,n] elem, elem, elem, ... endlessly or up to n times ``repeat(10, 3) → 10 10 10`` -================== ================= ================================================= ========================================= - -**Iterators terminating on the shortest input sequence:** +**General iterators:** ============================ ============================ ================================================= ============================================================= Iterator Arguments Results Example @@ -51,11 +40,14 @@ Iterator Arguments Results :func:`chain` p, q, ... p0, p1, ... plast, q0, q1, ... ``chain('ABC', 'DEF') → A B C D E F`` :func:`chain.from_iterable` iterable p0, p1, ... plast, q0, q1, ... ``chain.from_iterable(['ABC', 'DEF']) → A B C D E F`` :func:`compress` data, selectors (d[0] if s[0]), (d[1] if s[1]), ... ``compress('ABCDEF', [1,0,1,0,1,1]) → A C E F`` +:func:`count` [start[, step]] start, start+step, start+2*step, ... ``count(10) → 10 11 12 13 14 ...`` +:func:`cycle` p p0, p1, ... plast, p0, p1, ... ``cycle('ABCD') → A B C D A B C D ...`` :func:`dropwhile` predicate, seq seq[n], seq[n+1], starting when predicate fails ``dropwhile(lambda x: x<5, [1,4,6,3,8]) → 6 3 8`` :func:`filterfalse` predicate, seq elements of seq where predicate(elem) fails ``filterfalse(lambda x: x<5, [1,4,6,3,8]) → 6 8`` :func:`groupby` iterable[, key] sub-iterators grouped by value of key(v) ``groupby(['A','B','DEF'], len) → (1, A B) (3, DEF)`` :func:`islice` seq, [start,] stop [, step] elements from seq[start:stop:step] ``islice('ABCDEFG', 2, None) → C D E F G`` :func:`pairwise` iterable (p[0], p[1]), (p[1], p[2]) ``pairwise('ABCDEFG') → AB BC CD DE EF FG`` +:func:`repeat` elem [,n] elem, elem, elem, ... endlessly or up to n times ``repeat(10, 3) → 10 10 10`` :func:`starmap` func, seq func(\*seq[0]), func(\*seq[1]), ... ``starmap(pow, [(2,5), (3,2), (10,3)]) → 32 9 1000`` :func:`takewhile` predicate, seq seq[0], seq[1], until predicate fails ``takewhile(lambda x: x<5, [1,4,6,3,8]) → 1 4`` :func:`tee` it, n it1, it2, ... itn splits one iterator into n ``tee('ABC', 2) → A B C, A B C`` @@ -819,7 +811,7 @@ well as with the built-in itertools such as ``map()``, ``filter()``, A secondary purpose of the recipes is to serve as an incubator. The ``accumulate()``, ``compress()``, and ``pairwise()`` itertools started out as -recipes. Currently, the ``sliding_window()``, ``iter_index()``, and ``sieve()`` +recipes. Currently, the ``sliding_window()``, ``derangements()``, and ``sieve()`` recipes are being tested to see whether they prove their worth. Substantially all of these recipes and many, many others can be installed from @@ -838,11 +830,18 @@ and :term:`generators ` which incur interpreter overhead. .. testcode:: + from itertools import (accumulate, batched, chain, combinations, compress, + count, cycle, filterfalse, groupby, islice, permutations, product, + repeat, starmap, tee, zip_longest) from collections import Counter, deque from contextlib import suppress from functools import reduce - from math import comb, prod, sumprod, isqrt - from operator import itemgetter, getitem, mul, neg + from heapq import heappush, heappushpop, heappush_max, heappushpop_max + from math import comb, isqrt, prod, sumprod + from operator import getitem, is_not, itemgetter, mul, neg, truediv + + + # ==== Basic one liners ==== def take(n, iterable): "Return first n items of the iterable as a list." @@ -853,10 +852,6 @@ and :term:`generators ` which incur interpreter overhead. # prepend(1, [2, 3, 4]) → 1 2 3 4 return chain([value], iterable) - def tabulate(function, start=0): - "Return function(0), function(1), ..." - return map(function, count(start)) - def repeatfunc(function, times=None, *args): "Repeat calls to a function with specified arguments." if times is None: @@ -899,8 +894,8 @@ and :term:`generators ` which incur interpreter overhead. def first_true(iterable, default=False, predicate=None): "Returns the first true value or the *default* if there is no true value." - # first_true([a,b,c], x) → a or b or c or x - # first_true([a,b], x, f) → a if f(a) else b if f(b) else x + # first_true([a, b, c], x) → a or b or c or x + # first_true([a, b], x, f) → a if f(a) else b if f(b) else x return next(filter(predicate, iterable), default) def all_equal(iterable, key=None): @@ -908,6 +903,9 @@ and :term:`generators ` which incur interpreter overhead. # all_equal('4٤௪౪໔', key=int) → True return len(take(2, groupby(iterable, key))) <= 1 + + # ==== Data pipelines ==== + def unique_justseen(iterable, key=None): "Yield unique elements, preserving order. Remember only the element just seen." # unique_justseen('AAAABBBCCDAABBB') → A B C D A B @@ -933,14 +931,14 @@ and :term:`generators ` which incur interpreter overhead. yield element def unique(iterable, key=None, reverse=False): - "Yield unique elements in sorted order. Supports unhashable inputs." - # unique([[1, 2], [3, 4], [1, 2]]) → [1, 2] [3, 4] - sequenced = sorted(iterable, key=key, reverse=reverse) - return unique_justseen(sequenced, key=key) + "Yield unique elements in sorted order. Supports unhashable inputs." + # unique([[1, 2], [3, 4], [1, 2]]) → [1, 2] [3, 4] + sequenced = sorted(iterable, key=key, reverse=reverse) + return unique_justseen(sequenced, key=key) def sliding_window(iterable, n): "Collect data into overlapping fixed-length chunks or blocks." - # sliding_window('ABCDEFG', 4) → ABCD BCDE CDEF DEFG + # sliding_window('ABCDEFG', 3) → ABC BCD CDE DEF EFG iterator = iter(iterable) window = deque(islice(iterator, n - 1), maxlen=n) for x in iterator: @@ -949,7 +947,7 @@ and :term:`generators ` which incur interpreter overhead. def grouper(iterable, n, *, incomplete='fill', fillvalue=None): "Collect data into non-overlapping fixed-length chunks or blocks." - # grouper('ABCDEFG', 3, fillvalue='x') → ABC DEF Gxx + # grouper('ABCDEFG', 3, fillvalue='x') → ABC DEF Gxx # grouper('ABCDEFG', 3, incomplete='strict') → ABC DEF ValueError # grouper('ABCDEFG', 3, incomplete='ignore') → ABC DEF iterators = [iter(iterable)] * n @@ -978,6 +976,16 @@ and :term:`generators ` which incur interpreter overhead. slices = starmap(slice, combinations(range(len(seq) + 1), 2)) return map(getitem, repeat(seq), slices) + def derangements(iterable, r=None): + "Produce r length permutations without fixed points." + # derangements('ABCD') → BADC BCDA BDAC CADB CDAB CDBA DABC DCAB DCBA + # Algorithm credited to Stefan Pochmann + seq = tuple(iterable) + pos = tuple(range(len(seq))) + have_moved = map(map, repeat(is_not), repeat(pos), permutations(pos, r=r)) + valid_derangements = map(all, have_moved) + return compress(permutations(seq, r=r), valid_derangements) + def iter_index(iterable, value, start=0, stop=None): "Return indices where a value occurs in a sequence or iterable." # iter_index('AABCADEAF', 'A') → 0 1 4 7 @@ -1005,9 +1013,7 @@ and :term:`generators ` which incur interpreter overhead. yield function() -The following recipes have a more mathematical flavor: - -.. testcode:: + # ==== Mathematical operations ==== def multinomial(*counts): "Number of distinct arrangements of a multiset." @@ -1026,9 +1032,12 @@ The following recipes have a more mathematical flavor: # sum_of_squares([10, 20, 30]) → 1400 return sumprod(*tee(iterable)) + + # ==== Matrix operations ==== + def reshape(matrix, columns): "Reshape a 2-D matrix to have a given number of columns." - # reshape([(0, 1), (2, 3), (4, 5)], 3) → (0, 1, 2), (3, 4, 5) + # reshape([(0, 1), (2, 3), (4, 5)], 3) → (0, 1, 2) (3, 4, 5) return batched(chain.from_iterable(matrix), columns, strict=True) def transpose(matrix): @@ -1038,10 +1047,13 @@ The following recipes have a more mathematical flavor: def matmul(m1, m2): "Multiply two matrices." - # matmul([(7, 5), (3, 5)], [(2, 5), (7, 9)]) → (49, 80), (41, 60) + # matmul([(7, 5), (3, 5)], [(2, 5), (7, 9)]) → (49, 80) (41, 60) n = len(m2[0]) return batched(starmap(sumprod, product(m1, transpose(m2))), n) + + # ==== Polynomial arithmetic ==== + def convolve(signal, kernel): """Discrete linear convolution of two iterables. Equivalent to polynomial multiplication. @@ -1096,6 +1108,9 @@ The following recipes have a more mathematical flavor: powers = reversed(range(1, n)) return list(map(mul, coefficients, powers)) + + # ==== Number theory ==== + def sieve(n): "Primes less than n." # sieve(30) → 2 3 5 7 11 13 17 19 23 29 @@ -1134,6 +1149,49 @@ The following recipes have a more mathematical flavor: return n + # ==== Running statistics ==== + + def running_mean(iterable): + "Average of values seen so far." + # running_mean([37, 33, 38, 28]) → 37 35 36 34 + return map(truediv, accumulate(iterable), count(1)) + + def running_min(iterable): + "Smallest of values seen so far." + # running_min([37, 33, 38, 28]) → 37 33 33 28 + return accumulate(iterable, func=min) + + def running_max(iterable): + "Largest of values seen so far." + # running_max([37, 33, 38, 28]) → 37 37 38 38 + return accumulate(iterable, func=max) + + def running_median(iterable): + "Median of values seen so far." + # running_median([37, 33, 38, 28]) → 37 35 37 35 + read = iter(iterable).__next__ + lo = [] # max-heap + hi = [] # min-heap the same size as or one smaller than lo + with suppress(StopIteration): + while True: + heappush_max(lo, heappushpop(hi, read())) + yield lo[0] + heappush(hi, heappushpop_max(lo, read())) + yield (lo[0] + hi[0]) / 2 + + def running_statistics(iterable): + "Aggregate statistics for values seen so far." + # Generate tuples: (size, minimum, median, maximum, mean) + t0, t1, t2, t3 = tee(iterable, 4) + return zip( + count(1), + running_min(t0), + running_median(t1), + running_max(t2), + running_mean(t3), + ) + + .. doctest:: :hide: @@ -1210,10 +1268,6 @@ The following recipes have a more mathematical flavor: [(0, 'a'), (1, 'b'), (2, 'c')] - >>> list(islice(tabulate(lambda x: 2*x), 4)) - [0, 2, 4, 6] - - >>> for _ in loops(5): ... print('hi') ... @@ -1663,6 +1717,36 @@ The following recipes have a more mathematical flavor: ['A', 'AB', 'ABC', 'ABCD', 'B', 'BC', 'BCD', 'C', 'CD', 'D'] + >>> ' '.join(map(''.join, derangements('ABCD'))) + 'BADC BCDA BDAC CADB CDAB CDBA DABC DCAB DCBA' + >>> ' '.join(map(''.join, derangements('ABCD', 3))) + 'BAD BCA BCD BDA CAB CAD CDA CDB DAB DCA DCB' + >>> ' '.join(map(''.join, derangements('ABCD', 2))) + 'BA BC BD CA CD DA DC' + >>> ' '.join(map(''.join, derangements('ABCD', 1))) + 'B C D' + >>> ' '.join(map(''.join, derangements('ABCD', 0))) + '' + >>> # Compare number of derangements to https://oeis.org/A000166 + >>> [len(list(derangements(range(n)))) for n in range(10)] + [1, 0, 1, 2, 9, 44, 265, 1854, 14833, 133496] + >>> # Verify that identical objects are treated as unique by position + >>> identical = 'X' + >>> distinct = 'x' + >>> seq1 = ('A', identical, 'B', identical) + >>> result1 = ' '.join(map(''.join, derangements(seq1))) + >>> result1 + 'XAXB XBXA XXAB BAXX BXAX BXXA XAXB XBAX XBXA' + >>> seq2 = ('A', identical, 'B', distinct) + >>> result2 = ' '.join(map(''.join, derangements(seq2))) + >>> result2 + 'XAxB XBxA XxAB BAxX BxAX BxXA xAXB xBAX xBXA' + >>> result1 == result2 + False + >>> result1.casefold() == result2.casefold() + True + + >>> list(powerset([1,2,3])) [(), (1,), (2,), (3,), (1, 2), (1, 3), (2, 3), (1, 2, 3)] >>> all(len(list(powerset(range(n)))) == 2**n for n in range(18)) @@ -1743,11 +1827,37 @@ The following recipes have a more mathematical flavor: True + >>> list(running_mean([8.5, 9.5, 7.5, 6.5])) + [8.5, 9.0, 8.5, 8.0] + >>> list(running_mean([37, 33, 38, 28])) + [37.0, 35.0, 36.0, 34.0] + + + >>> list(running_min([37, 33, 38, 28])) + [37, 33, 33, 28] + + + >>> list(running_max([37, 33, 38, 28])) + [37, 37, 38, 38] + + + >>> list(running_median([37, 33, 38, 28])) + [37, 35.0, 37, 35.0] + + + >>> list(running_statistics([37, 33, 38, 28])) + [(1, 37, 37, 37, 37.0), (2, 33, 35.0, 37, 35.0), (3, 33, 37, 38, 36.0), (4, 28, 35.0, 38, 34.0)] + + .. testcode:: :hide: # Old recipes and their tests which are guaranteed to continue to work. + def tabulate(function, start=0): + "Return function(0), function(1), ..." + return map(function, count(start)) + def old_sumprod_recipe(vec1, vec2): "Compute a sum of products." return sum(starmap(operator.mul, zip(vec1, vec2, strict=True))) @@ -1827,6 +1937,10 @@ The following recipes have a more mathematical flavor: .. doctest:: :hide: + >>> list(islice(tabulate(lambda x: 2*x), 4)) + [0, 2, 4, 6] + + >>> dotproduct([1,2,3], [4,5,6]) 32 diff --git a/Doc/library/json.rst b/Doc/library/json.rst index 26579ec6328860..231654a3a9315f 100644 --- a/Doc/library/json.rst +++ b/Doc/library/json.rst @@ -18,12 +18,17 @@ is a lightweight data interchange format inspired by `JavaScript `_ object literal syntax (although it is not a strict subset of JavaScript [#rfc-errata]_ ). +.. note:: + The term "object" in the context of JSON processing in Python can be + ambiguous. All values in Python are objects. In JSON, an object refers to + any data wrapped in curly braces, similar to a Python dictionary. + .. warning:: Be cautious when parsing JSON data from untrusted sources. A malicious JSON string may cause the decoder to consume considerable CPU and memory resources. Limiting the size of data to be parsed is recommended. -:mod:`json` exposes an API familiar to users of the standard library +This module exposes an API familiar to users of the standard library :mod:`marshal` and :mod:`pickle` modules. Encoding basic Python object hierarchies:: @@ -60,7 +65,7 @@ Pretty printing:: "6": 7 } -Specializing JSON object encoding:: +Customizing JSON object encoding:: >>> import json >>> def custom_json(obj): @@ -83,7 +88,7 @@ Decoding JSON:: >>> json.load(io) ['streaming API'] -Specializing JSON object decoding:: +Customizing JSON object decoding:: >>> import json >>> def as_complex(dct): @@ -116,7 +121,7 @@ Extending :class:`JSONEncoder`:: ['[2.0', ', 1.0', ']'] -Using :mod:`json` from the shell to validate and pretty-print: +Using :mod:`!json` from the shell to validate and pretty-print: .. code-block:: shell-session @@ -178,8 +183,10 @@ Basic Usage :param bool ensure_ascii: If ``True`` (the default), the output is guaranteed to - have all incoming non-ASCII characters escaped. - If ``False``, these characters will be outputted as-is. + have all incoming non-ASCII and non-printable characters escaped. + If ``False``, all characters will be outputted as-is, except for + the characters that must be escaped: quotation mark, reverse solidus, + and the control characters U+0000 through U+001F. :param bool check_circular: If ``False``, the circular reference check for container types is skipped @@ -207,7 +214,7 @@ Basic Usage a string (such as ``"\t"``) is used to indent each level. If zero, negative, or ``""`` (the empty string), only newlines are inserted. - If ``None`` (the default), the most compact representation is used. + If ``None`` (the default), no newlines are inserted. :type indent: int | str | None :param separators: @@ -279,7 +286,7 @@ Basic Usage :param object_hook: If set, a function that is called with the result of - any object literal decoded (a :class:`dict`). + any JSON object literal decoded (a :class:`dict`). The return value of this function will be used instead of the :class:`dict`. This feature can be used to implement custom decoders, @@ -289,7 +296,7 @@ Basic Usage :param object_pairs_hook: If set, a function that is called with the result of - any object literal decoded with an ordered list of pairs. + any JSON object literal decoded with an ordered list of pairs. The return value of this function will be used instead of the :class:`dict`. This feature can be used to implement custom decoders. @@ -490,8 +497,10 @@ Encoders and Decoders :class:`bool` or ``None``. If *skipkeys* is true, such items are simply skipped. If *ensure_ascii* is true (the default), the output is guaranteed to - have all incoming non-ASCII characters escaped. If *ensure_ascii* is - false, these characters will be output as-is. + have all incoming non-ASCII and non-printable characters escaped. + If *ensure_ascii* is false, all characters will be output as-is, except for + the characters that must be escaped: quotation mark, reverse solidus, + and the control characters U+0000 through U+001F. If *check_circular* is true (the default), then lists, dicts, and custom encoded objects will be checked for circular references during encoding to @@ -631,7 +640,7 @@ UTF-32, with UTF-8 being the recommended default for maximum interoperability. As permitted, though not required, by the RFC, this module's serializer sets *ensure_ascii=True* by default, thus escaping the output so that the resulting -strings only contain ASCII characters. +strings only contain printable ASCII characters. Other than the *ensure_ascii* parameter, this module is defined strictly in terms of conversion between Python objects and @@ -738,8 +747,8 @@ Command-line interface -------------- -The :mod:`json` module can be invoked as a script via ``python -m json`` -to validate and pretty-print JSON objects. The :mod:`json.tool` submodule +The :mod:`!json` module can be invoked as a script via ``python -m json`` +to validate and pretty-print JSON objects. The :mod:`!json.tool` submodule implements this interface. If the optional ``infile`` and ``outfile`` arguments are not @@ -760,7 +769,7 @@ specified, :data:`sys.stdin` and :data:`sys.stdout` will be used respectively: alphabetically by key. .. versionchanged:: 3.14 - The :mod:`json` module may now be directly executed as + The :mod:`!json` module may now be directly executed as ``python -m json``. For backwards compatibility, invoking the CLI as ``python -m json.tool`` remains supported. diff --git a/Doc/library/linecache.rst b/Doc/library/linecache.rst index e766a9280946d3..0a5373ec976371 100644 --- a/Doc/library/linecache.rst +++ b/Doc/library/linecache.rst @@ -10,7 +10,7 @@ -------------- -The :mod:`linecache` module allows one to get any line from a Python source file, while +The :mod:`!linecache` module allows one to get any line from a Python source file, while attempting to optimize internally, using a cache, the common case where many lines are read from a single file. This is used by the :mod:`traceback` module to retrieve source lines for inclusion in the formatted traceback. @@ -19,7 +19,7 @@ The :func:`tokenize.open` function is used to open files. This function uses :func:`tokenize.detect_encoding` to get the encoding of the file; in the absence of an encoding token, the file encoding defaults to UTF-8. -The :mod:`linecache` module defines the following functions: +The :mod:`!linecache` module defines the following functions: .. function:: getline(filename, lineno, module_globals=None) @@ -31,7 +31,7 @@ The :mod:`linecache` module defines the following functions: .. index:: triple: module; search; path If *filename* indicates a frozen module (starting with ``'`, or a pair, + language code and encoding. An empty string specifies the user's default settings. If the modification of the locale fails, the exception :exc:`Error` is raised. If successful, the new locale setting is returned. + If *locale* is a pair, it is converted to a locale name using + the locale aliasing engine. + The language code has the same format as a :ref:`locale name `, + but without encoding and ``@``-modifier. + The language code and encoding can be ``None``. + If *locale* is omitted or ``None``, the current setting for *category* is returned. + Example:: + + >>> import locale + >>> loc = locale.setlocale(locale.LC_ALL) # get current locale + # use German locale; name and availability varies with platform + >>> locale.setlocale(locale.LC_ALL, 'de_DE.UTF-8') + >>> locale.strcoll('f\xe4n', 'foo') # compare a string containing an umlaut + >>> locale.setlocale(locale.LC_ALL, '') # use user's preferred locale + >>> locale.setlocale(locale.LC_ALL, 'C') # use default (C) locale + >>> locale.setlocale(locale.LC_ALL, loc) # restore saved locale + :func:`setlocale` is not thread-safe on most systems. Applications typically - start with a call of :: + start with a call of:: import locale locale.setlocale(locale.LC_ALL, '') @@ -345,22 +361,24 @@ The :mod:`locale` module defines the following exception and functions: ``'LANG'``. The GNU gettext search path contains ``'LC_ALL'``, ``'LC_CTYPE'``, ``'LANG'`` and ``'LANGUAGE'``, in that order. - Except for the code ``'C'``, the language code corresponds to :rfc:`1766`. - *language code* and *encoding* may be ``None`` if their values cannot be + The language code has the same format as a :ref:`locale name `, + but without encoding and ``@``-modifier. + The language code and encoding may be ``None`` if their values cannot be determined. - - .. deprecated-removed:: 3.11 3.15 + The "C" locale is represented as ``(None, None)``. .. function:: getlocale(category=LC_CTYPE) - Returns the current setting for the given locale category as sequence containing - *language code*, *encoding*. *category* may be one of the :const:`!LC_\*` values - except :const:`LC_ALL`. It defaults to :const:`LC_CTYPE`. + Returns the current setting for the given locale category as a tuple containing + the language code and encoding. *category* may be one of the :const:`!LC_\*` + values except :const:`LC_ALL`. It defaults to :const:`LC_CTYPE`. - Except for the code ``'C'``, the language code corresponds to :rfc:`1766`. - *language code* and *encoding* may be ``None`` if their values cannot be + The language code has the same format as a :ref:`locale name `, + but without encoding and ``@``-modifier. + The language code and encoding may be ``None`` if their values cannot be determined. + The "C" locale is represented as ``(None, None)``. .. function:: getpreferredencoding(do_setlocale=True) @@ -508,14 +526,14 @@ The :mod:`locale` module defines the following exception and functions: SSH connections. Python doesn't internally use locale-dependent character transformation functions - from ``ctype.h``. Instead, an internal ``pyctype.h`` provides locale-independent - equivalents like :c:macro:`!Py_TOLOWER`. + from ``ctype.h``. Instead, ``pyctype.h`` provides locale-independent + equivalents like :c:macro:`Py_TOLOWER`. .. data:: LC_COLLATE Locale category for sorting strings. The functions :func:`strcoll` and - :func:`strxfrm` of the :mod:`locale` module are affected. + :func:`strxfrm` of the :mod:`!locale` module are affected. .. data:: LC_TIME @@ -544,7 +562,7 @@ The :mod:`locale` module defines the following exception and functions: .. data:: LC_NUMERIC Locale category for formatting numbers. The functions :func:`format_string`, - :func:`atoi`, :func:`atof` and :func:`.str` of the :mod:`locale` module are + :func:`atoi`, :func:`atof` and :func:`.str` of the :mod:`!locale` module are affected by that category. All other numeric formatting operations are not affected. @@ -564,18 +582,6 @@ The :mod:`locale` module defines the following exception and functions: :func:`localeconv`. -Example:: - - >>> import locale - >>> loc = locale.getlocale() # get current locale - # use German locale; name might vary with platform - >>> locale.setlocale(locale.LC_ALL, 'de_DE') - >>> locale.strcoll('f\xe4n', 'foo') # compare a string containing an umlaut - >>> locale.setlocale(locale.LC_ALL, '') # use user's preferred locale - >>> locale.setlocale(locale.LC_ALL, 'C') # use default (C) locale - >>> locale.setlocale(locale.LC_ALL, loc) # restore saved locale - - Background, details, hints, tips and caveats -------------------------------------------- @@ -615,6 +621,61 @@ whose high bit is set (i.e., non-ASCII bytes) are never converted or considered part of a character class such as letter or whitespace. +.. _locale_name: + +Locale names +------------ + +The format of the locale name is platform dependent, and the set of supported +locales can depend on the system configuration. + +On Posix platforms, it usually has the format [1]_: + +.. productionlist:: locale_name + : language ["_" territory] ["." charset] ["@" modifier] + +where *language* is a two- or three-letter language code from `ISO 639`_, +*territory* is a two-letter country or region code from `ISO 3166`_, +*charset* is a locale encoding, and *modifier* is a script name, +a language subtag, a sort order identifier, or other locale modifier +(for example, "latin", "valencia", "stroke" and "euro"). + +On Windows, several formats are supported. [2]_ [3]_ +A subset of `IETF BCP 47`_ tags: + +.. productionlist:: locale_name + : language ["-" script] ["-" territory] ["." charset] + : language ["-" script] "-" territory "-" modifier + +where *language* and *territory* have the same meaning as in Posix, +*script* is a four-letter script code from `ISO 15924`_, +and *modifier* is a language subtag, a sort order identifier +or custom modifier (for example, "valencia", "stroke" or "x-python"). +Both hyphen (``'-'``) and underscore (``'_'``) separators are supported. +Only UTF-8 encoding is allowed for BCP 47 tags. + +Windows also supports locale names in the format: + +.. productionlist:: locale_name + : language ["_" territory] ["." charset] + +where *language* and *territory* are full names, such as "English" and +"United States", and *charset* is either a code page number (for example, "1252") +or UTF-8. +Only the underscore separator is supported in this format. + +The "C" locale is supported on all platforms. + +.. _ISO 639: https://www.iso.org/iso-639-language-code +.. _ISO 3166: https://www.iso.org/iso-3166-country-codes.html +.. _IETF BCP 47: https://www.rfc-editor.org/info/bcp47 +.. _ISO 15924: https://www.unicode.org/iso15924/ + +.. [1] `IEEE Std 1003.1-2024; 8.2 Internationalization Variables `_ +.. [2] `UCRT Locale names, Languages, and Country/Region strings `_ +.. [3] `Locale Names `_ + + .. _embedding-locale: For extension writers and programs that embed Python @@ -625,7 +686,7 @@ the current locale is. But since the return value can only be used portably to restore it, that is not very useful (except perhaps to find out whether or not the locale is ``C``). -When Python code uses the :mod:`locale` module to change the locale, this also +When Python code uses the :mod:`!locale` module to change the locale, this also affects the embedding application. If the embedding application doesn't want this to happen, it should remove the :mod:`!_locale` extension module (which does all the work) from the table of built-in modules in the :file:`config.c` file, diff --git a/Doc/library/logging.config.rst b/Doc/library/logging.config.rst index 0e9dc33ae2123a..6709062dfca72b 100644 --- a/Doc/library/logging.config.rst +++ b/Doc/library/logging.config.rst @@ -28,7 +28,7 @@ Configuration functions ^^^^^^^^^^^^^^^^^^^^^^^ The following functions configure the logging module. They are located in the -:mod:`logging.config` module. Their use is optional --- you can configure the +:mod:`!logging.config` module. Their use is optional --- you can configure the logging module using these functions or by making calls to the main API (defined in :mod:`logging` itself) and defining handlers which are declared either in :mod:`logging` or :mod:`logging.handlers`. @@ -55,7 +55,7 @@ in :mod:`logging` itself) and defining handlers which are declared either in Parsing is performed by the :class:`DictConfigurator` class, whose constructor is passed the dictionary used for configuration, and - has a :meth:`configure` method. The :mod:`logging.config` module + has a :meth:`configure` method. The :mod:`!logging.config` module has a callable attribute :attr:`dictConfigClass` which is initially set to :class:`DictConfigurator`. You can replace the value of :attr:`dictConfigClass` with a @@ -548,7 +548,7 @@ mnemonic that the corresponding value is a callable. The ``filters`` member of ``handlers`` and ``loggers`` can take filter instances in addition to ids. -You can also specify a special key ``'.'`` whose value is a dictionary is a +You can also specify a special key ``'.'`` whose value is a mapping of attribute names to values. If found, the specified attributes will be set on the user-defined object before it is returned. Thus, with the following configuration:: @@ -586,7 +586,7 @@ configuration dictionary for the handler named ``foo``, and later (once that handler has been configured) it points to the configured handler instance. Thus, ``cfg://handlers.foo`` could resolve to either a dictionary or a handler instance. In general, it is wise to name handlers in a way such that dependent -handlers are configured _after_ any handlers they depend on; that allows +handlers are configured *after* any handlers they depend on; that allows something like ``cfg://handlers.foo`` to be used in configuring a handler that depends on handler ``foo``. If that dependent handler were named ``bar``, problems would result, because the configuration of ``bar`` would be attempted diff --git a/Doc/library/logging.handlers.rst b/Doc/library/logging.handlers.rst index 63ef533e82c658..d128f64aae7236 100644 --- a/Doc/library/logging.handlers.rst +++ b/Doc/library/logging.handlers.rst @@ -160,7 +160,7 @@ WatchedFileHandler .. currentmodule:: logging.handlers -The :class:`WatchedFileHandler` class, located in the :mod:`logging.handlers` +The :class:`WatchedFileHandler` class, located in the :mod:`!logging.handlers` module, is a :class:`FileHandler` which watches the file it is logging to. If the file changes, it is closed and reopened using the file name. @@ -213,7 +213,7 @@ for this value. BaseRotatingHandler ^^^^^^^^^^^^^^^^^^^ -The :class:`BaseRotatingHandler` class, located in the :mod:`logging.handlers` +The :class:`BaseRotatingHandler` class, located in the :mod:`!logging.handlers` module, is the base class for the rotating file handlers, :class:`RotatingFileHandler` and :class:`TimedRotatingFileHandler`. You should not need to instantiate this class, but it has attributes and methods you may @@ -307,7 +307,7 @@ For an example, see :ref:`cookbook-rotator-namer`. RotatingFileHandler ^^^^^^^^^^^^^^^^^^^ -The :class:`RotatingFileHandler` class, located in the :mod:`logging.handlers` +The :class:`RotatingFileHandler` class, located in the :mod:`!logging.handlers` module, supports rotation of disk log files. @@ -352,13 +352,17 @@ module, supports rotation of disk log files. Outputs the record to the file, catering for rollover as described previously. + .. method:: shouldRollover(record) + + See if the supplied record would cause the file to exceed the configured size limit. + .. _timed-rotating-file-handler: TimedRotatingFileHandler ^^^^^^^^^^^^^^^^^^^^^^^^ The :class:`TimedRotatingFileHandler` class, located in the -:mod:`logging.handlers` module, supports rotation of disk log files at certain +:mod:`!logging.handlers` module, supports rotation of disk log files at certain timed intervals. @@ -461,12 +465,17 @@ timed intervals. Returns a list of filenames which should be deleted as part of rollover. These are the absolute paths of the oldest backup log files written by the handler. + .. method:: shouldRollover(record) + + See if enough time has passed for a rollover to occur and if it has, compute + the next rollover time. + .. _socket-handler: SocketHandler ^^^^^^^^^^^^^ -The :class:`SocketHandler` class, located in the :mod:`logging.handlers` module, +The :class:`SocketHandler` class, located in the :mod:`!logging.handlers` module, sends logging output to a network socket. The base class uses a TCP socket. @@ -562,7 +571,7 @@ sends logging output to a network socket. The base class uses a TCP socket. DatagramHandler ^^^^^^^^^^^^^^^ -The :class:`DatagramHandler` class, located in the :mod:`logging.handlers` +The :class:`DatagramHandler` class, located in the :mod:`!logging.handlers` module, inherits from :class:`SocketHandler` to support sending logging messages over UDP sockets. @@ -609,7 +618,7 @@ over UDP sockets. SysLogHandler ^^^^^^^^^^^^^ -The :class:`SysLogHandler` class, located in the :mod:`logging.handlers` module, +The :class:`SysLogHandler` class, located in the :mod:`!logging.handlers` module, supports sending logging messages to a remote or local Unix syslog. @@ -788,7 +797,7 @@ supports sending logging messages to a remote or local Unix syslog. NTEventLogHandler ^^^^^^^^^^^^^^^^^ -The :class:`NTEventLogHandler` class, located in the :mod:`logging.handlers` +The :class:`NTEventLogHandler` class, located in the :mod:`!logging.handlers` module, supports sending logging messages to a local Windows NT, Windows 2000 or Windows XP event log. Before you can use it, you need Mark Hammond's Win32 extensions for Python installed. @@ -855,7 +864,7 @@ extensions for Python installed. SMTPHandler ^^^^^^^^^^^ -The :class:`SMTPHandler` class, located in the :mod:`logging.handlers` module, +The :class:`SMTPHandler` class, located in the :mod:`!logging.handlers` module, supports sending logging messages to an email address via SMTP. @@ -896,7 +905,7 @@ supports sending logging messages to an email address via SMTP. MemoryHandler ^^^^^^^^^^^^^ -The :class:`MemoryHandler` class, located in the :mod:`logging.handlers` module, +The :class:`MemoryHandler` class, located in the :mod:`!logging.handlers` module, supports buffering of logging records in memory, periodically flushing them to a :dfn:`target` handler. Flushing occurs whenever the buffer is full, or when an event of a certain severity or greater is seen. @@ -976,7 +985,7 @@ should, then :meth:`flush` is expected to do the flushing. HTTPHandler ^^^^^^^^^^^ -The :class:`HTTPHandler` class, located in the :mod:`logging.handlers` module, +The :class:`HTTPHandler` class, located in the :mod:`!logging.handlers` module, supports sending logging messages to a web server, using either ``GET`` or ``POST`` semantics. @@ -1028,7 +1037,7 @@ QueueHandler .. versionadded:: 3.2 -The :class:`QueueHandler` class, located in the :mod:`logging.handlers` module, +The :class:`QueueHandler` class, located in the :mod:`!logging.handlers` module, supports sending logging messages to a queue, such as those implemented in the :mod:`queue` or :mod:`multiprocessing` modules. @@ -1051,6 +1060,15 @@ possible, while any potentially slow operations (such as sending an email via .. note:: If you are using :mod:`multiprocessing`, you should avoid using :class:`~queue.SimpleQueue` and instead use :class:`multiprocessing.Queue`. + .. warning:: + + The :mod:`multiprocessing` module uses an internal logger created and + accessed via :meth:`~multiprocessing.get_logger`. + :class:`multiprocessing.Queue` will log ``DEBUG`` level messages upon + items being queued. If those log messages are processed by a + :class:`QueueHandler` using the same :class:`multiprocessing.Queue` instance, + it will cause a deadlock or infinite recursion. + .. method:: emit(record) Enqueues the result of preparing the LogRecord. Should an exception @@ -1112,7 +1130,7 @@ QueueListener .. versionadded:: 3.2 -The :class:`QueueListener` class, located in the :mod:`logging.handlers` +The :class:`QueueListener` class, located in the :mod:`!logging.handlers` module, supports receiving logging messages from a queue, such as those implemented in the :mod:`queue` or :mod:`multiprocessing` modules. The messages are received from a queue in an internal thread and passed, on diff --git a/Doc/library/logging.rst b/Doc/library/logging.rst index 72190e97240514..6e38d45504c4db 100644 --- a/Doc/library/logging.rst +++ b/Doc/library/logging.rst @@ -671,8 +671,7 @@ Formatter Objects which is just the logged message. :type fmt: str - :param datefmt: A format string in the given *style* for - the date/time portion of the logged output. + :param datefmt: A format string for the date/time portion of the logged output. If not specified, the default described in :meth:`formatTime` is used. :type datefmt: str @@ -680,7 +679,7 @@ Formatter Objects how the format string will be merged with its data: using one of :ref:`old-string-formatting` (``%``), :meth:`str.format` (``{``) or :class:`string.Template` (``$``). This only applies to - *fmt* and *datefmt* (e.g. ``'%(message)s'`` versus ``'{message}'``), + *fmt* (e.g. ``'%(message)s'`` versus ``'{message}'``), not to the actual log messages passed to the logging methods. However, there are :ref:`other ways ` to use ``{``- and ``$``-formatting for log messages. @@ -1012,6 +1011,11 @@ the options available to you. | exc_info | You shouldn't need to | Exception tuple (à la ``sys.exc_info``) or, | | | format this yourself. | if no exception has occurred, ``None``. | +----------------+-------------------------+-----------------------------------------------+ +| exc_text | You shouldn't need to | Exception information formatted as a string. | +| | format this yourself. | This is set when :meth:`Formatter.format` is | +| | | invoked, or ``None`` if no exception has | +| | | occurred. | ++----------------+-------------------------+-----------------------------------------------+ | filename | ``%(filename)s`` | Filename portion of ``pathname``. | +----------------+-------------------------+-----------------------------------------------+ | funcName | ``%(funcName)s`` | Name of function containing the logging call. | @@ -1083,12 +1087,13 @@ LoggerAdapter Objects information into logging calls. For a usage example, see the section on :ref:`adding contextual information to your logging output `. -.. class:: LoggerAdapter(logger, extra, merge_extra=False) +.. class:: LoggerAdapter(logger, extra=None, merge_extra=False) Returns an instance of :class:`LoggerAdapter` initialized with an - underlying :class:`Logger` instance, a dict-like object (*extra*), and a - boolean (*merge_extra*) indicating whether or not the *extra* argument of - individual log calls should be merged with the :class:`LoggerAdapter` extra. + underlying :class:`Logger` instance, an optional dict-like object (*extra*), + and an optional boolean (*merge_extra*) indicating whether or not + the *extra* argument of individual log calls should be merged with + the :class:`LoggerAdapter` extra. The default behavior is to ignore the *extra* argument of individual log calls and only use the one of the :class:`LoggerAdapter` instance @@ -1128,16 +1133,20 @@ information into logging calls. For a usage example, see the section on Attribute :attr:`!manager` and method :meth:`!_log` were added, which delegate to the underlying logger and allow adapters to be nested. + .. versionchanged:: 3.10 + + The *extra* argument is now optional. + .. versionchanged:: 3.13 - The *merge_extra* argument was added. + The *merge_extra* parameter was added. Thread Safety ------------- The logging module is intended to be thread-safe without any special work -needing to be done by its clients. It achieves this though using threading +needing to be done by its clients. It achieves this through using threading locks; there is one lock to serialize access to the module's shared data, and each handler also creates a lock to serialize access to its underlying I/O. @@ -1525,7 +1534,7 @@ Module-Level Attributes Integration with the warnings module ------------------------------------ -The :func:`captureWarnings` function can be used to integrate :mod:`logging` +The :func:`captureWarnings` function can be used to integrate :mod:`!logging` with the :mod:`warnings` module. .. function:: captureWarnings(capture) @@ -1556,7 +1565,7 @@ with the :mod:`warnings` module. library. `Original Python logging package `_ - This is the original source for the :mod:`logging` package. The version of the + This is the original source for the :mod:`!logging` package. The version of the package available from this site is suitable for use with Python 1.5.2, 2.1.x - and 2.2.x, which do not include the :mod:`logging` package in the standard + and 2.2.x, which do not include the :mod:`!logging` package in the standard library. diff --git a/Doc/library/lzma.rst b/Doc/library/lzma.rst index 69f7cb8d48d7ae..6742cbf701b67a 100644 --- a/Doc/library/lzma.rst +++ b/Doc/library/lzma.rst @@ -23,6 +23,8 @@ module. Note that :class:`LZMAFile` and :class:`bz2.BZ2File` are *not* thread-safe, so if you need to use a single :class:`LZMAFile` instance from multiple threads, it is necessary to protect it with a lock. +.. include:: ../includes/optional-module.rst + .. exception:: LZMAError @@ -153,35 +155,14 @@ Compressing and decompressing data in memory :func:`compress`. The *format* argument specifies what container format should be used. - Possible values are: - - * :const:`FORMAT_XZ`: The ``.xz`` container format. - This is the default format. - - * :const:`FORMAT_ALONE`: The legacy ``.lzma`` container format. - This format is more limited than ``.xz`` -- it does not support integrity - checks or multiple filters. - - * :const:`FORMAT_RAW`: A raw data stream, not using any container format. - This format specifier does not support integrity checks, and requires that - you always specify a custom filter chain (for both compression and - decompression). Additionally, data compressed in this manner cannot be - decompressed using :const:`FORMAT_AUTO` (see :class:`LZMADecompressor`). + Possible values are :const:`FORMAT_XZ` (the default), + :const:`FORMAT_ALONE` and :const:`FORMAT_RAW`. The *check* argument specifies the type of integrity check to include in the compressed data. This check is used when decompressing, to ensure that the - data has not been corrupted. Possible values are: - - * :const:`CHECK_NONE`: No integrity check. - This is the default (and the only acceptable value) for - :const:`FORMAT_ALONE` and :const:`FORMAT_RAW`. - - * :const:`CHECK_CRC32`: 32-bit Cyclic Redundancy Check. - - * :const:`CHECK_CRC64`: 64-bit Cyclic Redundancy Check. - This is the default for :const:`FORMAT_XZ`. - - * :const:`CHECK_SHA256`: 256-bit Secure Hash Algorithm. + data has not been corrupted. Possible values are :const:`CHECK_NONE`, + :const:`CHECK_CRC32`, :const:`CHECK_CRC64` (the default for + :const:`FORMAT_XZ`) and :const:`CHECK_SHA256`. If the specified check is not supported, an :class:`LZMAError` is raised. @@ -357,12 +338,12 @@ options. Valid filter IDs are as follows: * Branch-Call-Jump (BCJ) filters: - * :const:`FILTER_X86` - * :const:`FILTER_IA64` - * :const:`FILTER_ARM` - * :const:`FILTER_ARMTHUMB` - * :const:`FILTER_POWERPC` - * :const:`FILTER_SPARC` + * :const:`!FILTER_X86` + * :const:`!FILTER_IA64` + * :const:`!FILTER_ARM` + * :const:`!FILTER_ARMTHUMB` + * :const:`!FILTER_POWERPC` + * :const:`!FILTER_SPARC` A filter chain can consist of up to 4 filters, and cannot be empty. The last filter in the chain must be a compression filter, and any other filters must be @@ -399,6 +380,106 @@ These filters support one option, ``start_offset``. This specifies the address that should be mapped to the beginning of the input data. The default is 0. +Constants +--------- + +The following module-level constants are provided for use as the *format*, +*check*, *preset* and *filters* arguments of the classes and functions above. + +Container formats: + +.. data:: FORMAT_XZ + + The ``.xz`` container format. + +.. data:: FORMAT_ALONE + + The legacy ``.lzma`` container format. This format is more limited than + ``.xz`` -- it does not support integrity checks or multiple filters. + +.. data:: FORMAT_RAW + + A raw data stream, not using any container format. This format specifier + does not support integrity checks, and requires that you always specify a + custom filter chain (for both compression and decompression). Additionally, + data compressed in this manner cannot be decompressed using + :const:`FORMAT_AUTO`. + +.. data:: FORMAT_AUTO + + Used for decompression only. The container format is detected + automatically, so that both ``.xz`` and ``.lzma`` files can be decompressed. + +Integrity checks: + +.. data:: CHECK_NONE + + No integrity check. This is the default (and the only acceptable value) for + :const:`FORMAT_ALONE` and :const:`FORMAT_RAW`. + +.. data:: CHECK_CRC32 + + A 32-bit Cyclic Redundancy Check. + +.. data:: CHECK_CRC64 + + A 64-bit Cyclic Redundancy Check. This is the default for + :const:`FORMAT_XZ`. + +.. data:: CHECK_SHA256 + + A 256-bit Secure Hash Algorithm. + +.. data:: CHECK_UNKNOWN + + The integrity check used by a stream could not yet be determined. This may + be the value of the :attr:`LZMADecompressor.check` attribute until enough of + the input has been decoded. + +.. data:: CHECK_ID_MAX + + The largest supported integrity-check ID. + +Compression presets: + +.. data:: PRESET_DEFAULT + + The default compression preset, equivalent to preset level ``6``. + +.. data:: PRESET_EXTREME + + A flag that may be bitwise OR-ed with a preset level (``0`` to ``9``) to + select a slower but more thorough variant of that preset. + +Filter IDs and options: + +.. data:: FILTER_LZMA1 + FILTER_LZMA2 + + The LZMA1 and LZMA2 compression filters. :const:`FILTER_LZMA1` is for use + with :const:`FORMAT_ALONE`, while :const:`FILTER_LZMA2` is for use with + :const:`FORMAT_XZ` and :const:`FORMAT_RAW`. + +.. data:: FILTER_DELTA + + The delta filter. + +.. data:: MODE_FAST + MODE_NORMAL + + Compression modes that may be used as the ``mode`` option of a filter + specifier (see :ref:`filter-chain-specs`). + +.. data:: MF_HC3 + MF_HC4 + MF_BT2 + MF_BT3 + MF_BT4 + + Match finders that may be used as the ``mf`` option of a filter specifier + (see :ref:`filter-chain-specs`). + + Examples -------- diff --git a/Doc/library/mailbox.rst b/Doc/library/mailbox.rst index e8a96f29ea185e..ed135bf02cb968 100644 --- a/Doc/library/mailbox.rst +++ b/Doc/library/mailbox.rst @@ -917,7 +917,7 @@ Supported mailbox formats are Maildir, mbox, MH, Babyl, and MMDF. copied; furthermore, any format-specific information is converted insofar as possible if *message* is a :class:`!Message` instance. If *message* is a string, a byte string, - or a file, it should contain an :rfc:`2822`\ -compliant message, which is read + or a file, it should contain an :rfc:`5322`\ -compliant message, which is read and parsed. Files should be open in binary mode, but text mode files are accepted for backward compatibility. @@ -1025,7 +1025,7 @@ Supported mailbox formats are Maildir, mbox, MH, Babyl, and MMDF. .. method:: remove_flag(flag) Unset the flag(s) specified by *flag* without changing other flags. To - remove more than one flag at a time, *flag* maybe a string of more than + remove more than one flag at a time, *flag* may be a string of more than one character. If "info" contains experimental information rather than flags, the current "info" is not modified. @@ -1190,7 +1190,7 @@ When a :class:`!MaildirMessage` instance is created based upon a .. method:: remove_flag(flag) Unset the flag(s) specified by *flag* without changing other flags. To - remove more than one flag at a time, *flag* maybe a string of more than + remove more than one flag at a time, *flag* may be a string of more than one character. When an :class:`!mboxMessage` instance is created based upon a @@ -1562,7 +1562,7 @@ When a :class:`!BabylMessage` instance is created based upon an .. method:: remove_flag(flag) Unset the flag(s) specified by *flag* without changing other flags. To - remove more than one flag at a time, *flag* maybe a string of more than + remove more than one flag at a time, *flag* may be a string of more than one character. When an :class:`!MMDFMessage` instance is created based upon a @@ -1641,7 +1641,7 @@ The following exception classes are defined in the :mod:`!mailbox` module: .. exception:: Error() - The based class for all other module-specific exceptions. + The base class for all other module-specific exceptions. .. exception:: NoSuchMailboxError() @@ -1661,7 +1661,7 @@ The following exception classes are defined in the :mod:`!mailbox` module: Raised when some mailbox-related condition beyond the control of the program causes it to be unable to proceed, such as when failing to acquire a lock that - another program already holds a lock, or when a uniquely generated file name + another program already holds, or when a uniquely generated file name already exists. diff --git a/Doc/library/marshal.rst b/Doc/library/marshal.rst index e8e9071a5c9ef4..ed182ea24e8f3c 100644 --- a/Doc/library/marshal.rst +++ b/Doc/library/marshal.rst @@ -20,7 +20,7 @@ rarely does). [#]_ This is not a general "persistence" module. For general persistence and transfer of Python objects through RPC calls, see the modules :mod:`pickle` and -:mod:`shelve`. The :mod:`marshal` module exists mainly to support reading and +:mod:`shelve`. The :mod:`!marshal` module exists mainly to support reading and writing the "pseudo-compiled" code for Python modules of :file:`.pyc` files. Therefore, the Python maintainers reserve the right to modify the marshal format in backward incompatible ways should the need arise. @@ -34,7 +34,7 @@ supports a substantially wider range of objects than marshal. .. warning:: - The :mod:`marshal` module is not intended to be secure against erroneous or + The :mod:`!marshal` module is not intended to be secure against erroneous or maliciously constructed data. Never unmarshal data received from an untrusted or unauthenticated source. diff --git a/Doc/library/math.rst b/Doc/library/math.rst index 0749367045dfa9..241f043ede7a9f 100644 --- a/Doc/library/math.rst +++ b/Doc/library/math.rst @@ -10,8 +10,8 @@ -------------- -This module provides access to the mathematical functions defined by the C -standard. +This module provides access to common mathematical functions and constants, +including those defined by the C standard. These functions cannot be used with complex numbers; use the functions of the same name from the :mod:`cmath` module if you require support for complex @@ -144,8 +144,7 @@ Number-theoretic functions .. function:: factorial(n) - Return *n* factorial as an integer. Raises :exc:`ValueError` if *n* is not integral or - is negative. + Return factorial of the nonnegative integer *n*. .. versionchanged:: 3.10 Floats with integral values (like ``5.0``) are no longer accepted. @@ -322,10 +321,12 @@ Floating point manipulation functions .. function:: frexp(x) - Return the mantissa and exponent of *x* as the pair ``(m, e)``. *m* is a float - and *e* is an integer such that ``x == m * 2**e`` exactly. If *x* is zero, - returns ``(0.0, 0)``, otherwise ``0.5 <= abs(m) < 1``. This is used to "pick - apart" the internal representation of a float in a portable way. + Return the mantissa and exponent of *x* as the pair ``(m, e)``. + If *x* is a finite nonzero number, then *m* is a float with + ``0.5 <= abs(m) < 1.0`` and an integer *e* is such that + ``x == m * 2**e`` exactly. Else, return ``(x, 0)``. + This is used to "pick apart" the internal representation of + a float in a portable way. Note that :func:`frexp` has a different call/return pattern than its C equivalents: it takes a single argument and return a pair of @@ -775,7 +776,7 @@ Constants The mathematical constant *τ* = 6.283185..., to available precision. Tau is a circle constant equal to 2\ *π*, the ratio of a circle's circumference to its radius. To learn more about Tau, check out Vi Hart's video `Pi is (still) - Wrong `_, and start celebrating + Wrong `_, and start celebrating `Tau day `_ by eating twice as much pie! .. versionadded:: 3.6 @@ -817,7 +818,7 @@ Constants .. impl-detail:: - The :mod:`math` module consists mostly of thin wrappers around the platform C + The :mod:`!math` module consists mostly of thin wrappers around the platform C math library functions. Behavior in exceptional cases follows Annex F of the C99 standard where appropriate. The current implementation will raise :exc:`ValueError` for invalid operations like ``sqrt(-1.0)`` or ``log(0.0)`` diff --git a/Doc/library/mimetypes.rst b/Doc/library/mimetypes.rst index 13511b16a0ed8c..647f9d05c4db23 100644 --- a/Doc/library/mimetypes.rst +++ b/Doc/library/mimetypes.rst @@ -12,7 +12,7 @@ -------------- -The :mod:`mimetypes` module converts between a filename or URL and the MIME type +The :mod:`!mimetypes` module converts between a filename or URL and the MIME type associated with the filename extension. Conversions are provided from filename to MIME type and from MIME type to filename extension; encodings are not supported for the latter conversion. @@ -56,8 +56,8 @@ the information :func:`init` sets up. .. versionchanged:: 3.8 Added support for *url* being a :term:`path-like object`. - .. deprecated:: 3.13 - Passing a file path instead of URL is :term:`soft deprecated`. + .. soft-deprecated:: 3.13 + Passing a file path instead of URL. Use :func:`guess_file_type` for this. @@ -118,12 +118,13 @@ behavior of the module. Previously, Windows registry settings were ignored. -.. function:: read_mime_types(filename) +.. function:: read_mime_types(file) - Load the type map given in the file *filename*, if it exists. The type map is - returned as a dictionary mapping filename extensions, including the leading dot - (``'.'``), to strings of the form ``'type/subtype'``. If the file *filename* - does not exist or cannot be read, ``None`` is returned. + Load the type map given in the file named by *file*, if it exists. *file* + must be a string specifying the name of the file to read. The type map is + returned as a dictionary mapping file extensions, including the leading dot + (``'.'``), to strings of the form ``'type/subtype'``. If the file does not + exist or cannot be read, ``None`` is returned. .. function:: add_type(type, ext, strict=True) @@ -196,7 +197,7 @@ MimeTypes objects The :class:`MimeTypes` class may be useful for applications which may want more than one MIME-type database; it provides an interface similar to the one of the -:mod:`mimetypes` module. +:mod:`!mimetypes` module. .. class:: MimeTypes(filenames=(), strict=True) @@ -350,7 +351,7 @@ it converts file extensions to MIME types. For each ``type`` entry, the script writes a line into the standard output stream. If an unknown type occurs, it writes an error message into the -standard error stream and exits with the return code ``1``. +standard output stream and exits with the return code ``1``. .. mimetypes-cli-example: @@ -377,7 +378,7 @@ interface: $ # get a MIME type for a rare file extension $ python -m mimetypes filename.pict - error: unknown extension of filename.pict + error: media type unknown for filename.pict $ # now look in the extended database built into Python $ python -m mimetypes --lenient filename.pict @@ -399,7 +400,8 @@ interface: $ python -m mimetypes filename.sh filename.nc filename.xxx filename.txt type: application/x-sh encoding: None type: application/x-netcdf encoding: None - error: unknown extension of filename.xxx + error: media type unknown for filename.xxx + type: text/plain encoding: None $ # try to feed an unknown MIME type $ python -m mimetypes --extension audio/aac audio/opus audio/future audio/x-wav diff --git a/Doc/library/mmap.rst b/Doc/library/mmap.rst index 4e20c07331a220..f78518ac2232a0 100644 --- a/Doc/library/mmap.rst +++ b/Doc/library/mmap.rst @@ -200,7 +200,8 @@ To map anonymous memory, -1 should be passed as the fileno along with the length Writable :term:`bytes-like object` is now accepted. - .. method:: flush([offset[, size]]) + .. method:: flush() + flush(offset, size, /) Flushes changes made to the in-memory copy of a file back to disk. Without use of this call there is no guarantee that changes are written back before @@ -269,7 +270,7 @@ To map anonymous memory, -1 should be passed as the fileno along with the length Resizing a map created with *access* of :const:`ACCESS_READ` or :const:`ACCESS_COPY`, will raise a :exc:`TypeError` exception. - Resizing a map created with with *trackfd* set to ``False``, + Resizing a map created with *trackfd* set to ``False``, will raise a :exc:`ValueError` exception. **On Windows**: Resizing the map will raise an :exc:`OSError` if there are other diff --git a/Doc/library/msvcrt.rst b/Doc/library/msvcrt.rst index 327cc3602b1a77..79069c136c2841 100644 --- a/Doc/library/msvcrt.rst +++ b/Doc/library/msvcrt.rst @@ -2,7 +2,6 @@ =========================================================== .. module:: msvcrt - :platform: Windows :synopsis: Miscellaneous useful routines from the MS VC++ runtime. .. sectionauthor:: Fred L. Drake, Jr. @@ -22,6 +21,8 @@ api. The normal API deals only with ASCII characters and is of limited use for internationalized applications. The wide char API should be used where ever possible. +.. availability:: Windows. + .. versionchanged:: 3.3 Operations in this module now raise :exc:`OSError` where :exc:`IOError` was raised. diff --git a/Doc/library/multiprocessing.rst b/Doc/library/multiprocessing.rst index 6c43d5fe166e2f..b4d5eca4e91a8e 100644 --- a/Doc/library/multiprocessing.rst +++ b/Doc/library/multiprocessing.rst @@ -13,17 +13,16 @@ Introduction ------------ -:mod:`multiprocessing` is a package that supports spawning processes using an -API similar to the :mod:`threading` module. The :mod:`multiprocessing` package +:mod:`!multiprocessing` is a package that supports spawning processes using an +API similar to the :mod:`threading` module. The :mod:`!multiprocessing` package offers both local and remote concurrency, effectively side-stepping the :term:`Global Interpreter Lock ` by using subprocesses instead of threads. Due -to this, the :mod:`multiprocessing` module allows the programmer to fully +to this, the :mod:`!multiprocessing` module allows the programmer to fully leverage multiple processors on a given machine. It runs on both POSIX and Windows. -The :mod:`multiprocessing` module also introduces APIs which do not have -analogs in the :mod:`threading` module. A prime example of this is the +The :mod:`!multiprocessing` module also introduces the :class:`~multiprocessing.pool.Pool` object which offers a convenient means of parallelizing the execution of a function across multiple input values, distributing the input data across processes (data parallelism). The following @@ -44,6 +43,10 @@ will print to standard output :: [1, 4, 9] +The :mod:`!multiprocessing` module also introduces APIs which do not have +analogs in the :mod:`threading` module, like the ability to :meth:`terminate +`, :meth:`interrupt ` or :meth:`kill +` a running process. .. seealso:: @@ -58,7 +61,7 @@ will print to standard output :: The :class:`Process` class ^^^^^^^^^^^^^^^^^^^^^^^^^^ -In :mod:`multiprocessing`, processes are spawned by creating a :class:`Process` +In :mod:`!multiprocessing`, processes are spawned by creating a :class:`Process` object and then calling its :meth:`~Process.start` method. :class:`Process` follows the API of :class:`threading.Thread`. A trivial example of a multiprocess program is :: @@ -97,6 +100,10 @@ To show the individual process IDs involved, here is an expanded example:: For an explanation of why the ``if __name__ == '__main__'`` part is necessary, see :ref:`multiprocessing-programming`. +The arguments to :class:`Process` usually need to be picklable so they can be +passed to the child process. If you tried typing the above example directly +into a REPL it could lead to an :exc:`AttributeError` in the child process +trying to locate the *f* function in the ``__main__`` module. .. _multiprocessing-start-methods: @@ -104,7 +111,7 @@ necessary, see :ref:`multiprocessing-programming`. Contexts and start methods ^^^^^^^^^^^^^^^^^^^^^^^^^^ -Depending on the platform, :mod:`multiprocessing` supports three ways +Depending on the platform, :mod:`!multiprocessing` supports three ways to start a process. These *start methods* are .. _multiprocessing-start-method-spawn: @@ -233,9 +240,12 @@ processes for a different context. In particular, locks created using the *fork* context cannot be passed to processes started using the *spawn* or *forkserver* start methods. -A library which wants to use a particular start method should probably -use :func:`get_context` to avoid interfering with the choice of the -library user. +Libraries using :mod:`!multiprocessing` or +:class:`~concurrent.futures.ProcessPoolExecutor` should be designed to allow +their users to provide their own multiprocessing context. Using a specific +context of your own within a library can lead to incompatibilities with the +rest of the library user's application. Always document if your library +requires a specific start method. .. warning:: @@ -248,7 +258,7 @@ library user. Exchanging objects between processes ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -:mod:`multiprocessing` supports two types of communication channel between +:mod:`!multiprocessing` supports two types of communication channel between processes: **Queues** @@ -269,7 +279,7 @@ processes: p.join() Queues are thread and process safe. - Any object put into a :mod:`~multiprocessing` queue will be serialized. + Any object put into a :mod:`!multiprocessing` queue will be serialized. **Pipes** @@ -303,7 +313,7 @@ processes: Synchronization between processes ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -:mod:`multiprocessing` contains equivalents of all the synchronization +:mod:`!multiprocessing` contains equivalents of all the synchronization primitives from :mod:`threading`. For instance one can use a lock to ensure that only one process prints to standard output at a time:: @@ -334,7 +344,7 @@ avoid using shared state as far as possible. This is particularly true when using multiple processes. However, if you really do need to use some shared data then -:mod:`multiprocessing` provides a couple of ways of doing so. +:mod:`!multiprocessing` provides a couple of ways of doing so. **Shared memory** @@ -508,9 +518,24 @@ process which created it. Reference --------- -The :mod:`multiprocessing` package mostly replicates the API of the +The :mod:`!multiprocessing` package mostly replicates the API of the :mod:`threading` module. +.. _global-start-method: + +Global start method +^^^^^^^^^^^^^^^^^^^ + +Python supports several ways to create and initialize a process. +The global start method sets the default mechanism for creating a process. + +Several multiprocessing functions and methods that may also instantiate +certain objects will implicitly set the global start method to the system's default, +if it hasn’t been set already. The global start method can only be set once. +If you need to change the start method from the system default, you must +proactively set the global start method before calling functions or methods, +or creating these objects. + :class:`Process` and exceptions ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ @@ -538,9 +563,42 @@ The :mod:`multiprocessing` package mostly replicates the API of the to pass to *target*. If a subclass overrides the constructor, it must make sure it invokes the - base class constructor (:meth:`Process.__init__`) before doing anything else + base class constructor (``super().__init__()``) before doing anything else to the process. + .. note:: + + In general, all arguments to :class:`Process` must be picklable. This is + frequently observed when trying to create a :class:`Process` or use a + :class:`concurrent.futures.ProcessPoolExecutor` from a REPL with a + locally defined *target* function. + + Passing a callable object defined in the current REPL session causes the + child process to die via an uncaught :exc:`AttributeError` exception when + starting as *target* must have been defined within an importable module + in order to be loaded during unpickling. + + Example of this uncatchable error from the child:: + + >>> import multiprocessing as mp + >>> def knigit(): + ... print("Ni!") + ... + >>> process = mp.Process(target=knigit) + >>> process.start() + >>> Traceback (most recent call last): + File ".../multiprocessing/spawn.py", line ..., in spawn_main + File ".../multiprocessing/spawn.py", line ..., in _main + AttributeError: module '__main__' has no attribute 'knigit' + >>> process + + + See :ref:`multiprocessing-programming-spawn`. While this restriction is + not true if using the ``"fork"`` start method, as of Python ``3.14`` that + is no longer the default on any platform. See + :ref:`multiprocessing-start-methods`. + See also :gh:`132898`. + .. versionchanged:: 3.3 Added the *daemon* parameter. @@ -646,7 +704,7 @@ The :mod:`multiprocessing` package mostly replicates the API of the The process's authentication key (a byte string). - When :mod:`multiprocessing` is initialized the main process is assigned a + When :mod:`!multiprocessing` is initialized the main process is assigned a random string using :func:`os.urandom`. When a :class:`Process` object is created, it will inherit the @@ -747,7 +805,7 @@ The :mod:`multiprocessing` package mostly replicates the API of the .. exception:: ProcessError - The base class of all :mod:`multiprocessing` exceptions. + The base class of all :mod:`!multiprocessing` exceptions. .. exception:: BufferTooShort @@ -787,19 +845,19 @@ If you use :class:`JoinableQueue` then you **must** call semaphore used to count the number of unfinished tasks may eventually overflow, raising an exception. -One difference from other Python queue implementations, is that :mod:`multiprocessing` +One difference from other Python queue implementations, is that :mod:`!multiprocessing` queues serializes all objects that are put into them using :mod:`pickle`. -The object return by the get method is a re-created object that does not share memory -with the original object. +The object returned by the get method is a re-created object that does not share +memory with the original object. Note that one can also create a shared queue by using a manager object -- see :ref:`multiprocessing-managers`. .. note:: - :mod:`multiprocessing` uses the usual :exc:`queue.Empty` and + :mod:`!multiprocessing` uses the usual :exc:`queue.Empty` and :exc:`queue.Full` exceptions to signal a timeout. They are not available in - the :mod:`multiprocessing` namespace so you need to import them from + the :mod:`!multiprocessing` namespace so you need to import them from :mod:`queue`. .. note:: @@ -847,7 +905,7 @@ For an example of the usage of queues for interprocess communication see :ref:`multiprocessing-examples`. -.. function:: Pipe([duplex]) +.. function:: Pipe(duplex=True) Returns a pair ``(conn1, conn2)`` of :class:`~multiprocessing.connection.Connection` objects representing the @@ -867,11 +925,15 @@ For an example of the usage of queues for interprocess communication see locks/semaphores. When a process first puts an item on the queue a feeder thread is started which transfers objects from a buffer into the pipe. + Instantiating this class may set the global start method. See + :ref:`global-start-method` for more details. + The usual :exc:`queue.Empty` and :exc:`queue.Full` exceptions from the standard library's :mod:`queue` module are raised to signal timeouts. :class:`Queue` implements all the methods of :class:`queue.Queue` except for - :meth:`~queue.Queue.task_done` and :meth:`~queue.Queue.join`. + :meth:`~queue.Queue.task_done`, :meth:`~queue.Queue.join`, and + :meth:`~queue.Queue.shutdown`. .. method:: qsize() @@ -936,8 +998,13 @@ For an example of the usage of queues for interprocess communication see .. method:: close() - Indicate that no more data will be put on this queue by the current - process. The background thread will quit once it has flushed all buffered + Close the queue: release internal resources. + + A queue must not be used anymore after it is closed. For example, + :meth:`~Queue.get`, :meth:`~Queue.put` and :meth:`~Queue.empty` + methods must no longer be called. + + The background thread will quit once it has flushed all buffered data to the pipe. This is called automatically when the queue is garbage collected. @@ -977,6 +1044,9 @@ For an example of the usage of queues for interprocess communication see It is a simplified :class:`Queue` type, very close to a locked :class:`Pipe`. + Instantiating this class may set the global start method. See + :ref:`global-start-method` for more details. + .. method:: close() Close the queue: release internal resources. @@ -1007,6 +1077,9 @@ For an example of the usage of queues for interprocess communication see :class:`JoinableQueue`, a :class:`Queue` subclass, is a queue which additionally has :meth:`task_done` and :meth:`join` methods. + Instantiating this class may set the global start method. See + :ref:`global-start-method` for more details. + .. method:: task_done() Indicate that a formerly enqueued task is complete. Used by queue @@ -1080,8 +1153,8 @@ Miscellaneous .. function:: freeze_support() - Add support for when a program which uses :mod:`multiprocessing` has been - frozen to produce a Windows executable. (Has been tested with **py2exe**, + Add support for when a program which uses :mod:`!multiprocessing` has been + frozen to produce an executable. (Has been tested with **py2exe**, **PyInstaller** and **cx_Freeze**.) One needs to call this function straight after the ``if __name__ == @@ -1099,10 +1172,10 @@ Miscellaneous If the ``freeze_support()`` line is omitted then trying to run the frozen executable will raise :exc:`RuntimeError`. - Calling ``freeze_support()`` has no effect when invoked on any operating - system other than Windows. In addition, if the module is being run - normally by the Python interpreter on Windows (the program has not been - frozen), then ``freeze_support()`` has no effect. + Calling ``freeze_support()`` has no effect when the start method is not + *spawn*. In addition, if the module is being run normally by the Python + interpreter (the program has not been frozen), then ``freeze_support()`` + has no effect. .. function:: get_all_start_methods() @@ -1116,9 +1189,11 @@ Miscellaneous .. function:: get_context(method=None) Return a context object which has the same attributes as the - :mod:`multiprocessing` module. + :mod:`!multiprocessing` module. - If *method* is ``None`` then the default context is returned. + If *method* is ``None`` then the default context is returned. Note that if + the global start method has not been set, this will set it to the system default + See :ref:`global-start-method` for more details. Otherwise *method* should be ``'fork'``, ``'spawn'``, ``'forkserver'``. :exc:`ValueError` is raised if the specified start method is not available. See :ref:`multiprocessing-start-methods`. @@ -1129,10 +1204,9 @@ Miscellaneous Return the name of start method used for starting processes. - If the start method has not been fixed and *allow_none* is false, - then the start method is fixed to the default and the name is - returned. If the start method has not been fixed and *allow_none* - is true then ``None`` is returned. + If the global start method is not set and *allow_none* is ``False``, the global start + method is set to the default, and its name is returned. See + :ref:`global-start-method` for more details. The return value can be ``'fork'``, ``'spawn'``, ``'forkserver'`` or ``None``. See :ref:`multiprocessing-start-methods`. @@ -1149,7 +1223,7 @@ Miscellaneous Set the path of the Python interpreter to use when starting a child process. (By default :data:`sys.executable` is used). Embedders will probably need to - do some thing like :: + do something like :: set_executable(os.path.join(sys.exec_prefix, 'pythonw.exe')) @@ -1196,7 +1270,7 @@ Miscellaneous .. note:: - :mod:`multiprocessing` contains no analogues of + :mod:`!multiprocessing` contains no analogues of :func:`threading.active_count`, :func:`threading.enumerate`, :func:`threading.settrace`, :func:`threading.setprofile`, :class:`threading.Timer`, or :class:`threading.local`. @@ -1252,12 +1326,12 @@ Connection objects are usually created using Note that multiple connection objects may be polled at once by using :func:`multiprocessing.connection.wait`. - .. method:: send_bytes(buffer[, offset[, size]]) + .. method:: send_bytes(buf[, offset[, size]]) Send byte data from a :term:`bytes-like object` as a complete message. - If *offset* is given then data is read from that position in *buffer*. If - *size* is given then that many bytes will be read from buffer. Very large + If *offset* is given then data is read from that position in *buf*. If + *size* is given then that many bytes will be read from *buf*. Very large buffers (approximately 32 MiB+, though it depends on the OS) may raise a :exc:`ValueError` exception @@ -1277,18 +1351,18 @@ Connection objects are usually created using alias of :exc:`OSError`. - .. method:: recv_bytes_into(buffer[, offset]) + .. method:: recv_bytes_into(buf[, offset]) - Read into *buffer* a complete message of byte data sent from the other end + Read into *buf* a complete message of byte data sent from the other end of the connection and return the number of bytes in the message. Blocks until there is something to receive. Raises :exc:`EOFError` if there is nothing left to receive and the other end was closed. - *buffer* must be a writable :term:`bytes-like object`. If + *buf* must be a writable :term:`bytes-like object`. If *offset* is given then the message will be written into the buffer from that position. Offset must be a non-negative integer less than the - length of *buffer* (in bytes). + length of *buf* (in bytes). If the buffer is too short then a :exc:`BufferTooShort` exception is raised and the complete message is available as ``e.args[0]`` where ``e`` @@ -1359,6 +1433,9 @@ object -- see :ref:`multiprocessing-managers`. A barrier object: a clone of :class:`threading.Barrier`. + Instantiating this class may set the global start method. See + :ref:`global-start-method` for more details. + .. versionadded:: 3.3 .. class:: BoundedSemaphore([value]) @@ -1366,9 +1443,18 @@ object -- see :ref:`multiprocessing-managers`. A bounded semaphore object: a close analog of :class:`threading.BoundedSemaphore`. + Instantiating this class may set the global start method. See + :ref:`global-start-method` for more details. + A solitary difference from its close analog exists: its ``acquire`` method's first argument is named *block*, as is consistent with :meth:`Lock.acquire`. + .. method:: locked() + + Return a boolean indicating whether this object is locked right now. + + .. versionadded:: 3.14 + .. note:: On macOS, this is indistinguishable from :class:`Semaphore` because ``sem_getvalue()`` is not implemented on that platform. @@ -1378,7 +1464,10 @@ object -- see :ref:`multiprocessing-managers`. A condition variable: an alias for :class:`threading.Condition`. If *lock* is specified then it should be a :class:`Lock` or :class:`RLock` - object from :mod:`multiprocessing`. + object from :mod:`!multiprocessing`. + + Instantiating this class may set the global start method. See + :ref:`global-start-method` for more details. .. versionchanged:: 3.3 The :meth:`~threading.Condition.wait_for` method was added. @@ -1387,6 +1476,8 @@ object -- see :ref:`multiprocessing-managers`. A clone of :class:`threading.Event`. + Instantiating this class may set the global start method. See + :ref:`global-start-method` for more details. .. class:: Lock() @@ -1402,6 +1493,9 @@ object -- see :ref:`multiprocessing-managers`. instance of ``multiprocessing.synchronize.Lock`` initialized with a default context. + Instantiating this class may set the global start method. See + :ref:`global-start-method` for more details. + :class:`Lock` supports the :term:`context manager` protocol and thus may be used in :keyword:`with` statements. @@ -1459,6 +1553,9 @@ object -- see :ref:`multiprocessing-managers`. instance of ``multiprocessing.synchronize.RLock`` initialized with a default context. + Instantiating this class may set the global start method. See + :ref:`global-start-method` for more details. + :class:`RLock` supports the :term:`context manager` protocol and thus may be used in :keyword:`with` statements. @@ -1518,9 +1615,28 @@ object -- see :ref:`multiprocessing-managers`. A semaphore object: a close analog of :class:`threading.Semaphore`. + Instantiating this class may set the global start method. See + :ref:`global-start-method` for more details. + A solitary difference from its close analog exists: its ``acquire`` method's first argument is named *block*, as is consistent with :meth:`Lock.acquire`. + + .. method:: get_value() + + Return the current value of semaphore. + + Note that this may raise :exc:`NotImplementedError` on platforms like + macOS where ``sem_getvalue()`` is not implemented. + + + .. method:: locked() + + Return a boolean indicating whether this object is locked right now. + + .. versionadded:: 3.14 + + .. note:: On macOS, ``sem_timedwait`` is unsupported, so calling ``acquire()`` with @@ -1578,11 +1694,14 @@ inherited by child processes. value is actually a synchronized wrapper for the array. *typecode_or_type* determines the type of the elements of the returned array: - it is either a ctypes type or a one character typecode of the kind used by - the :mod:`array` module. If *size_or_initializer* is an integer, then it - determines the length of the array, and the array will be initially zeroed. - Otherwise, *size_or_initializer* is a sequence which is used to initialize - the array and whose length determines the length of the array. + it is either a :ref:`ctypes type ` or a one + character typecode of the kind used by the :mod:`array` module with the + exception of ``'w'``, which is not supported. In addition, the ``'c'`` + typecode is an alias for :class:`ctypes.c_char`. If *size_or_initializer* + is an integer, then it determines the length of the array, and the array + will be initially zeroed. Otherwise, *size_or_initializer* is a sequence + which is used to initialize the array and whose length determines the length + of the array. If *lock* is ``True`` (the default) then a new lock object is created to synchronize access to the value. If *lock* is a :class:`Lock` or @@ -1594,16 +1713,19 @@ inherited by child processes. Note that *lock* is a keyword only argument. Note that an array of :data:`ctypes.c_char` has *value* and *raw* - attributes which allow one to use it to store and retrieve strings. + attributes which can both be used to store and retrieve byte strings. + While *raw* allows interaction with a :class:`bytes` object the full size of + the array, reading *value* will terminate after a null byte, like most + programming languages handle strings. -The :mod:`multiprocessing.sharedctypes` module -"""""""""""""""""""""""""""""""""""""""""""""" +The :mod:`!multiprocessing.sharedctypes` module +""""""""""""""""""""""""""""""""""""""""""""""" .. module:: multiprocessing.sharedctypes :synopsis: Allocate ctypes objects from shared memory. -The :mod:`multiprocessing.sharedctypes` module provides functions for allocating +The :mod:`!multiprocessing.sharedctypes` module provides functions for allocating :mod:`ctypes` objects from shared memory which can be inherited by child processes. @@ -1646,7 +1768,7 @@ processes. attributes which allow one to use it to store and retrieve strings -- see documentation for :mod:`ctypes`. -.. function:: Array(typecode_or_type, size_or_initializer, *, lock=True) +.. function:: Array(typecode_or_type, size_or_initializer, *, lock=True, ctx=None) The same as :func:`RawArray` except that depending on the value of *lock* a process-safe synchronization wrapper may be returned instead of a raw ctypes @@ -1660,9 +1782,13 @@ processes. automatically protected by a lock, so it will not necessarily be "process-safe". - Note that *lock* is a keyword-only argument. + *ctx* is a context object, or ``None`` (use the current context). If ``None``, + calling this may set the global start method. See + :ref:`global-start-method` for more details. -.. function:: Value(typecode_or_type, *args, lock=True) + Note that *lock* and *ctx* are keyword-only parameters. + +.. function:: Value(typecode_or_type, *args, lock=True, ctx=None) The same as :func:`RawValue` except that depending on the value of *lock* a process-safe synchronization wrapper may be returned instead of a raw ctypes @@ -1675,19 +1801,27 @@ processes. automatically protected by a lock, so it will not necessarily be "process-safe". - Note that *lock* is a keyword-only argument. + *ctx* is a context object, or ``None`` (use the current context). If ``None``, + calling this may set the global start method. See + :ref:`global-start-method` for more details. + + Note that *lock* and *ctx* are keyword-only parameters. .. function:: copy(obj) Return a ctypes object allocated from shared memory which is a copy of the ctypes object *obj*. -.. function:: synchronized(obj[, lock]) +.. function:: synchronized(obj, lock=None, ctx=None) Return a process-safe wrapper object for a ctypes object which uses *lock* to synchronize access. If *lock* is ``None`` (the default) then a :class:`multiprocessing.RLock` object is created automatically. + *ctx* is a context object, or ``None`` (use the current context). If ``None``, + calling this may set the global start method. See + :ref:`global-start-method` for more details. + A synchronized wrapper will have two methods in addition to those of the object it wraps: :meth:`get_obj` returns the wrapped object and :meth:`get_lock` returns the lock object used for synchronization. @@ -1805,8 +1939,9 @@ their parent process exits. The manager classes are defined in the *serializer* must be ``'pickle'`` (use :mod:`pickle` serialization) or ``'xmlrpclib'`` (use :mod:`xmlrpc.client` serialization). - *ctx* is a context object, or ``None`` (use the current context). See the - :func:`get_context` function. + *ctx* is a context object, or ``None`` (use the current context). If ``None``, + calling this may set the global start method. See + :ref:`global-start-method` for more details. *shutdown_timeout* is a timeout in seconds used to wait until the process used by the manager completes in the :meth:`shutdown` method. If the @@ -2190,7 +2325,7 @@ demonstrates a level of control over the synchronization. .. note:: - The proxy types in :mod:`multiprocessing` do nothing to support comparisons + The proxy types in :mod:`!multiprocessing` do nothing to support comparisons by value. So, for instance, we have: .. doctest:: @@ -2299,7 +2434,9 @@ with the :class:`Pool` class. the worker processes. Usually a pool is created using the function :func:`multiprocessing.Pool` or the :meth:`Pool` method of a context object. In both cases *context* is set - appropriately. + appropriately. If ``None``, calling this function will have the side effect + of setting the current global start method if it has not been set already. + See the :func:`get_context` function. Note that the methods of the pool object should only be called by the process which created the pool. @@ -2330,7 +2467,7 @@ with the :class:`Pool` class. duration of the Pool's work queue. A frequent pattern found in other systems (such as Apache, mod_wsgi, etc) to free resources held by workers is to allow a worker within a pool to complete only a set - amount of work before being exiting, being cleaned up and a new + amount of work before exiting, being cleaned up and a new process spawned to replace the old one. The *maxtasksperchild* argument to the :class:`Pool` exposes this ability to the end user. @@ -2515,7 +2652,7 @@ Usually message passing between processes is done using queues or by using :class:`~Connection` objects returned by :func:`~multiprocessing.Pipe`. -However, the :mod:`multiprocessing.connection` module allows some extra +However, the :mod:`!multiprocessing.connection` module allows some extra flexibility. It basically gives a high level message oriented API for dealing with sockets or Windows named pipes. It also has support for *digest authentication* using the :mod:`hmac` module, and for polling @@ -2773,6 +2910,16 @@ between themselves. Suitable authentication keys can also be generated by using :func:`os.urandom`. +This authentication protects :class:`Listener` and :func:`Client` connections, +which are reachable by address. It is not applied to the anonymous pipes +created by :func:`~multiprocessing.Pipe` or used internally by +:class:`~multiprocessing.Queue`. +:mod:`multiprocessing` treats all local processes running as the same user as +trusted; on most operating systems such processes can access each other's pipe +file descriptors regardless. Applications that require isolation between +processes of the same user must arrange it at the operating-system level -- +for example, by running workers under a different user account or in a sandbox. + Logging ^^^^^^^ @@ -2784,7 +2931,7 @@ handler type) for messages from different processes to get mixed up. .. currentmodule:: multiprocessing .. function:: get_logger() - Returns the logger used by :mod:`multiprocessing`. If necessary, a new one + Returns the logger used by :mod:`!multiprocessing`. If necessary, a new one will be created. When first created the logger has level :const:`logging.NOTSET` and no @@ -2822,18 +2969,18 @@ Below is an example session with logging turned on:: For a full table of logging levels, see the :mod:`logging` module. -The :mod:`multiprocessing.dummy` module -^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +The :mod:`!multiprocessing.dummy` module +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ .. module:: multiprocessing.dummy :synopsis: Dumb wrapper around threading. -:mod:`multiprocessing.dummy` replicates the API of :mod:`multiprocessing` but is +:mod:`!multiprocessing.dummy` replicates the API of :mod:`!multiprocessing` but is no more than a wrapper around the :mod:`threading` module. .. currentmodule:: multiprocessing.pool -In particular, the ``Pool`` function provided by :mod:`multiprocessing.dummy` +In particular, the ``Pool`` function provided by :mod:`!multiprocessing.dummy` returns an instance of :class:`ThreadPool`, which is a subclass of :class:`Pool` that supports all the same method calls but uses a pool of worker threads rather than worker processes. @@ -2878,7 +3025,7 @@ Programming guidelines ---------------------- There are certain guidelines and idioms which should be adhered to when using -:mod:`multiprocessing`. +:mod:`!multiprocessing`. All start methods @@ -2919,7 +3066,7 @@ Joining zombie processes Better to inherit than pickle/unpickle When using the *spawn* or *forkserver* start methods many types - from :mod:`multiprocessing` need to be picklable so that child + from :mod:`!multiprocessing` need to be picklable so that child processes can use them. However, one should generally avoid sending shared objects to other processes using pipes or queues. Instead you should arrange the program so that a process which @@ -3009,7 +3156,7 @@ Explicitly pass resources to child processes Beware of replacing :data:`sys.stdin` with a "file like object" - :mod:`multiprocessing` originally unconditionally called:: + :mod:`!multiprocessing` originally unconditionally called:: os.close(sys.stdin.fileno()) @@ -3051,10 +3198,10 @@ start method. More picklability - Ensure that all arguments to :meth:`Process.__init__` are picklable. - Also, if you subclass :class:`~multiprocessing.Process` then make sure that - instances will be picklable when the :meth:`Process.start - ` method is called. + Ensure that all arguments to :class:`~multiprocessing.Process` are + picklable. Also, if you subclass ``Process.__init__``, you must make sure + that instances will be picklable when the + :meth:`Process.start ` method is called. Global variables diff --git a/Doc/library/netrc.rst b/Doc/library/netrc.rst index f6260383b2b057..74c97e8c9a9759 100644 --- a/Doc/library/netrc.rst +++ b/Doc/library/netrc.rst @@ -24,12 +24,14 @@ the Unix :program:`ftp` program and other FTP clients. a :exc:`FileNotFoundError` exception will be raised. Parse errors will raise :exc:`NetrcParseError` with diagnostic information including the file name, line number, and terminating token. + If no argument is specified on a POSIX system, the presence of passwords in the :file:`.netrc` file will raise a :exc:`NetrcParseError` if the file ownership or permissions are insecure (owned by a user other than the user running the process, or accessible for read or write by any other user). This implements security behavior equivalent to that of ftp and other - programs that use :file:`.netrc`. + programs that use :file:`.netrc`. Such security checks are not available + on platforms that do not support :func:`os.getuid`. .. versionchanged:: 3.4 Added the POSIX permission check. diff --git a/Doc/library/numbers.rst b/Doc/library/numbers.rst index 681d0b76f2a14b..0ed24b4e6c5225 100644 --- a/Doc/library/numbers.rst +++ b/Doc/library/numbers.rst @@ -69,11 +69,11 @@ The numeric tower .. attribute:: numerator - Abstract. + Abstract. The numerator of this rational number. .. attribute:: denominator - Abstract. + Abstract. The denominator of this rational number. .. class:: Integral @@ -90,20 +90,7 @@ Notes for type implementers Implementers should be careful to make equal numbers equal and hash them to the same values. This may be subtle if there are two different -extensions of the real numbers. For example, :class:`fractions.Fraction` -implements :func:`hash` as follows:: - - def __hash__(self): - if self.denominator == 1: - # Get integers right. - return hash(self.numerator) - # Expensive check, but definitely correct. - if self == float(self): - return hash(float(self)) - else: - # Use tuple's hash to avoid a high collision rate on - # simple fractions. - return hash((self.numerator, self.denominator)) +extensions of the real numbers. See also :ref:`numeric-hash`. Adding More Numeric ABCs diff --git a/Doc/library/operator.rst b/Doc/library/operator.rst index e8e71068dd99eb..d88e008fa926f1 100644 --- a/Doc/library/operator.rst +++ b/Doc/library/operator.rst @@ -15,7 +15,7 @@ -------------- -The :mod:`operator` module exports a set of efficient functions corresponding to +The :mod:`!operator` module exports a set of efficient functions corresponding to the intrinsic operators of Python. For example, ``operator.add(x, y)`` is equivalent to the expression ``x+y``. Many function names are those used for special methods, without the double underscores. For backward compatibility, @@ -112,7 +112,7 @@ The mathematical and bitwise operations are the most numerous: .. function:: and_(a, b) __and__(a, b) - Return the bitwise and of *a* and *b*. + Return ``a & b``. .. function:: floordiv(a, b) @@ -136,13 +136,13 @@ The mathematical and bitwise operations are the most numerous: __inv__(obj) __invert__(obj) - Return the bitwise inverse of the number *obj*. This is equivalent to ``~obj``. + Return ``~obj``. .. function:: lshift(a, b) __lshift__(a, b) - Return *a* shifted left by *b*. + Return ``a << b``. .. function:: mod(a, b) @@ -154,7 +154,7 @@ The mathematical and bitwise operations are the most numerous: .. function:: mul(a, b) __mul__(a, b) - Return ``a * b``, for *a* and *b* numbers. + Return ``a * b``. .. function:: matmul(a, b) @@ -174,25 +174,25 @@ The mathematical and bitwise operations are the most numerous: .. function:: or_(a, b) __or__(a, b) - Return the bitwise or of *a* and *b*. + Return ``a | b``. .. function:: pos(obj) __pos__(obj) - Return *obj* positive (``+obj``). + Return ``+obj``. .. function:: pow(a, b) __pow__(a, b) - Return ``a ** b``, for *a* and *b* numbers. + Return ``a ** b``. .. function:: rshift(a, b) __rshift__(a, b) - Return *a* shifted right by *b*. + Return ``a >> b``. .. function:: sub(a, b) @@ -211,7 +211,7 @@ The mathematical and bitwise operations are the most numerous: .. function:: xor(a, b) __xor__(a, b) - Return the bitwise exclusive or of *a* and *b*. + Return ``a ^ b``. Operations which work with sequences (some of them with mappings too) include: @@ -275,7 +275,7 @@ The following operation works with callables: .. versionadded:: 3.11 -The :mod:`operator` module also defines tools for generalized attribute and item +The :mod:`!operator` module also defines tools for generalized attribute and item lookups. These are useful for making fast field extractors as arguments for :func:`map`, :func:`sorted`, :meth:`itertools.groupby`, or other functions that expect a function argument. @@ -390,7 +390,7 @@ Mapping Operators to Functions ------------------------------ This table shows how abstract operations correspond to operator symbols in the -Python syntax and the functions in the :mod:`operator` module. +Python syntax and the functions in the :mod:`!operator` module. +-----------------------+-------------------------+---------------------------------------+ | Operation | Syntax | Function | @@ -405,13 +405,18 @@ Python syntax and the functions in the :mod:`operator` module. +-----------------------+-------------------------+---------------------------------------+ | Division | ``a // b`` | ``floordiv(a, b)`` | +-----------------------+-------------------------+---------------------------------------+ -| Bitwise And | ``a & b`` | ``and_(a, b)`` | +| Bitwise And, or | ``a & b`` | ``and_(a, b)`` | +| Intersection | | | +-----------------------+-------------------------+---------------------------------------+ -| Bitwise Exclusive Or | ``a ^ b`` | ``xor(a, b)`` | +| Bitwise Exclusive Or, | ``a ^ b`` | ``xor(a, b)`` | +| or Symmetric | | | +| Difference | | | +-----------------------+-------------------------+---------------------------------------+ -| Bitwise Inversion | ``~ a`` | ``invert(a)`` | +| Bitwise Inversion, or | ``~ a`` | ``invert(a)`` | +| Complement | | | +-----------------------+-------------------------+---------------------------------------+ -| Bitwise Or | ``a | b`` | ``or_(a, b)`` | +| Bitwise Or, or | ``a | b`` | ``or_(a, b)`` | +| Union | | | +-----------------------+-------------------------+---------------------------------------+ | Exponentiation | ``a ** b`` | ``pow(a, b)`` | +-----------------------+-------------------------+---------------------------------------+ diff --git a/Doc/library/optparse.rst b/Doc/library/optparse.rst index ff327cf9162a8c..51827e1f8da534 100644 --- a/Doc/library/optparse.rst +++ b/Doc/library/optparse.rst @@ -20,7 +20,7 @@ The standard library includes three argument parsing libraries: * :mod:`getopt`: a module that closely mirrors the procedural C ``getopt`` API. Included in the standard library since before the initial Python 1.0 release. -* :mod:`optparse`: a declarative replacement for ``getopt`` that +* :mod:`!optparse`: a declarative replacement for ``getopt`` that provides equivalent functionality without requiring each application to implement its own procedural option parsing logic. Included in the standard library since the Python 2.3 release. @@ -37,10 +37,10 @@ the highest level of baseline functionality with the least application level cod However, it also serves a niche use case as a tool for prototyping and testing command line argument handling in ``getopt``-based C applications. -:mod:`optparse` should be considered as an alternative to :mod:`argparse` in the +:mod:`!optparse` should be considered as an alternative to :mod:`argparse` in the following cases: -* an application is already using :mod:`optparse` and doesn't want to risk the +* an application is already using :mod:`!optparse` and doesn't want to risk the subtle behavioural changes that may arise when migrating to :mod:`argparse` * the application requires additional control over the way options and positional parameters are interleaved on the command line (including @@ -55,7 +55,7 @@ following cases: behavior which ``argparse`` does not support, but which can be implemented in terms of the lower level interface offered by ``optparse`` -These considerations also mean that :mod:`optparse` is likely to provide a +These considerations also mean that :mod:`!optparse` is likely to provide a better foundation for library authors writing third party command line argument processing libraries. @@ -126,15 +126,15 @@ application use case. Introduction ------------ -:mod:`optparse` is a more convenient, flexible, and powerful library for parsing +:mod:`!optparse` is a more convenient, flexible, and powerful library for parsing command-line options than the minimalist :mod:`getopt` module. -:mod:`optparse` uses a more declarative style of command-line parsing: +:mod:`!optparse` uses a more declarative style of command-line parsing: you create an instance of :class:`OptionParser`, populate it with options, and parse the command line. -:mod:`optparse` allows users to specify options in the conventional +:mod:`!optparse` allows users to specify options in the conventional GNU/POSIX syntax, and additionally generates usage and help messages for you. -Here's an example of using :mod:`optparse` in a simple script:: +Here's an example of using :mod:`!optparse` in a simple script:: from optparse import OptionParser ... @@ -152,11 +152,11 @@ on the command-line, for example:: --file=outfile -q -As it parses the command line, :mod:`optparse` sets attributes of the +As it parses the command line, :mod:`!optparse` sets attributes of the ``options`` object returned by :meth:`~OptionParser.parse_args` based on user-supplied command-line values. When :meth:`~OptionParser.parse_args` returns from parsing this command line, ``options.filename`` will be ``"outfile"`` and ``options.verbose`` will be -``False``. :mod:`optparse` supports both long and short options, allows short +``False``. :mod:`!optparse` supports both long and short options, allows short options to be merged together, and allows options to be associated with their arguments in a variety of ways. Thus, the following command lines are all equivalent to the above example:: @@ -171,7 +171,7 @@ Additionally, users can run one of the following :: -h --help -and :mod:`optparse` will print out a brief summary of your script's options: +and :mod:`!optparse` will print out a brief summary of your script's options: .. code-block:: text @@ -191,7 +191,7 @@ where the value of *yourscript* is determined at runtime (normally from Background ---------- -:mod:`optparse` was explicitly designed to encourage the creation of programs +:mod:`!optparse` was explicitly designed to encourage the creation of programs with straightforward command-line interfaces that follow the conventions established by the :c:func:`!getopt` family of functions available to C developers. To that end, it supports only the most common command-line syntax and semantics @@ -223,7 +223,7 @@ option options to be merged into a single argument, e.g. ``-x -F`` is equivalent to ``-xF``. The GNU project introduced ``--`` followed by a series of hyphen-separated words, e.g. ``--file`` or ``--dry-run``. These are the - only two option syntaxes provided by :mod:`optparse`. + only two option syntaxes provided by :mod:`!optparse`. Some other option syntaxes that the world has seen include: @@ -240,7 +240,7 @@ option * a slash followed by a letter, or a few letters, or a word, e.g. ``/f``, ``/file`` - These option syntaxes are not supported by :mod:`optparse`, and they never + These option syntaxes are not supported by :mod:`!optparse`, and they never will be. This is deliberate: the first three are non-standard on any environment, and the last only makes sense if you're exclusively targeting Windows or certain legacy platforms (e.g. VMS, MS-DOS). @@ -248,7 +248,7 @@ option option argument an argument that follows an option, is closely associated with that option, and is consumed from the argument list when that option is. With - :mod:`optparse`, option arguments may either be in a separate argument from + :mod:`!optparse`, option arguments may either be in a separate argument from their option: .. code-block:: text @@ -268,7 +268,7 @@ option argument will take an argument if they see it, and won't if they don't. This is somewhat controversial, because it makes parsing ambiguous: if ``-a`` takes an optional argument and ``-b`` is another option entirely, how do we - interpret ``-ab``? Because of this ambiguity, :mod:`optparse` does not + interpret ``-ab``? Because of this ambiguity, :mod:`!optparse` does not support this feature. positional argument @@ -278,7 +278,7 @@ positional argument required option an option that must be supplied on the command-line; note that the phrase - "required option" is self-contradictory in English. :mod:`optparse` doesn't + "required option" is self-contradictory in English. :mod:`!optparse` doesn't prevent you from implementing required options, but doesn't give you much help at it either. @@ -357,9 +357,9 @@ too many options can overwhelm users and make your code much harder to maintain. Tutorial -------- -While :mod:`optparse` is quite flexible and powerful, it's also straightforward +While :mod:`!optparse` is quite flexible and powerful, it's also straightforward to use in most cases. This section covers the code patterns that are common to -any :mod:`optparse`\ -based program. +any :mod:`!optparse`\ -based program. First, you need to import the OptionParser class; then, early in the main program, create an OptionParser instance:: @@ -374,7 +374,7 @@ Then you can start defining options. The basic syntax is:: attr=value, ...) Each option has one or more option strings, such as ``-f`` or ``--file``, -and several option attributes that tell :mod:`optparse` what to expect and what +and several option attributes that tell :mod:`!optparse` what to expect and what to do when it encounters that option on the command line. Typically, each option will have one short option string and one long option @@ -389,10 +389,10 @@ string overall. The option strings passed to :meth:`OptionParser.add_option` are effectively labels for the option defined by that call. For brevity, we will frequently refer to -*encountering an option* on the command line; in reality, :mod:`optparse` +*encountering an option* on the command line; in reality, :mod:`!optparse` encounters *option strings* and looks up options from them. -Once all of your options are defined, instruct :mod:`optparse` to parse your +Once all of your options are defined, instruct :mod:`!optparse` to parse your program's command line:: (options, args) = parser.parse_args() @@ -420,14 +420,14 @@ most fundamental. Understanding option actions ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -Actions tell :mod:`optparse` what to do when it encounters an option on the -command line. There is a fixed set of actions hard-coded into :mod:`optparse`; +Actions tell :mod:`!optparse` what to do when it encounters an option on the +command line. There is a fixed set of actions hard-coded into :mod:`!optparse`; adding new actions is an advanced topic covered in section -:ref:`optparse-extending-optparse`. Most actions tell :mod:`optparse` to store +:ref:`optparse-extending-optparse`. Most actions tell :mod:`!optparse` to store a value in some variable---for example, take a string from the command line and store it in an attribute of ``options``. -If you don't specify an option action, :mod:`optparse` defaults to ``store``. +If you don't specify an option action, :mod:`!optparse` defaults to ``store``. .. _optparse-store-action: @@ -435,7 +435,7 @@ If you don't specify an option action, :mod:`optparse` defaults to ``store``. The store action ^^^^^^^^^^^^^^^^ -The most common option action is ``store``, which tells :mod:`optparse` to take +The most common option action is ``store``, which tells :mod:`!optparse` to take the next argument (or the remainder of the current argument), ensure that it is of the correct type, and store it to your chosen destination. @@ -444,16 +444,16 @@ For example:: parser.add_option("-f", "--file", action="store", type="string", dest="filename") -Now let's make up a fake command line and ask :mod:`optparse` to parse it:: +Now let's make up a fake command line and ask :mod:`!optparse` to parse it:: args = ["-f", "foo.txt"] (options, args) = parser.parse_args(args) -When :mod:`optparse` sees the option string ``-f``, it consumes the next +When :mod:`!optparse` sees the option string ``-f``, it consumes the next argument, ``foo.txt``, and stores it in ``options.filename``. So, after this call to :meth:`~OptionParser.parse_args`, ``options.filename`` is ``"foo.txt"``. -Some other option types supported by :mod:`optparse` are ``int`` and ``float``. +Some other option types supported by :mod:`!optparse` are ``int`` and ``float``. Here's an option that expects an integer argument:: parser.add_option("-n", type="int", dest="num") @@ -470,19 +470,19 @@ right up against the option: since ``-n42`` (one argument) is equivalent to will print ``42``. -If you don't specify a type, :mod:`optparse` assumes ``string``. Combined with +If you don't specify a type, :mod:`!optparse` assumes ``string``. Combined with the fact that the default action is ``store``, that means our first example can be a lot shorter:: parser.add_option("-f", "--file", dest="filename") -If you don't supply a destination, :mod:`optparse` figures out a sensible +If you don't supply a destination, :mod:`!optparse` figures out a sensible default from the option strings: if the first long option string is ``--foo-bar``, then the default destination is ``foo_bar``. If there are no -long option strings, :mod:`optparse` looks at the first short option string: the +long option strings, :mod:`!optparse` looks at the first short option string: the default destination for ``-f`` is ``f``. -:mod:`optparse` also includes the built-in ``complex`` type. Adding +:mod:`!optparse` also includes the built-in ``complex`` type. Adding types is covered in section :ref:`optparse-extending-optparse`. @@ -492,7 +492,7 @@ Handling boolean (flag) options ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Flag options---set a variable to true or false when a particular option is -seen---are quite common. :mod:`optparse` supports them with two separate actions, +seen---are quite common. :mod:`!optparse` supports them with two separate actions, ``store_true`` and ``store_false``. For example, you might have a ``verbose`` flag that is turned on with ``-v`` and off with ``-q``:: @@ -503,7 +503,7 @@ Here we have two different options with the same destination, which is perfectly OK. (It just means you have to be a bit careful when setting default values---see below.) -When :mod:`optparse` encounters ``-v`` on the command line, it sets +When :mod:`!optparse` encounters ``-v`` on the command line, it sets ``options.verbose`` to ``True``; when it encounters ``-q``, ``options.verbose`` is set to ``False``. @@ -513,7 +513,7 @@ When :mod:`optparse` encounters ``-v`` on the command line, it sets Other actions ^^^^^^^^^^^^^ -Some other actions supported by :mod:`optparse` are: +Some other actions supported by :mod:`!optparse` are: ``"store_const"`` store a constant value, pre-set via :attr:`Option.const` @@ -539,11 +539,11 @@ Default values All of the above examples involve setting some variable (the "destination") when certain command-line options are seen. What happens if those options are never seen? Since we didn't supply any defaults, they are all set to ``None``. This -is usually fine, but sometimes you want more control. :mod:`optparse` lets you +is usually fine, but sometimes you want more control. :mod:`!optparse` lets you supply a default value for each destination, which is assigned before the command line is parsed. -First, consider the verbose/quiet example. If we want :mod:`optparse` to set +First, consider the verbose/quiet example. If we want :mod:`!optparse` to set ``verbose`` to ``True`` unless ``-q`` is seen, then we can do this:: parser.add_option("-v", action="store_true", dest="verbose", default=True) @@ -582,7 +582,7 @@ values, not both. Generating help ^^^^^^^^^^^^^^^ -:mod:`optparse`'s ability to generate help and usage text automatically is +:mod:`!optparse`'s ability to generate help and usage text automatically is useful for creating user-friendly command-line interfaces. All you have to do is supply a :attr:`~Option.help` value for each option, and optionally a short usage message for your whole program. Here's an OptionParser populated with @@ -603,7 +603,7 @@ user-friendly (documented) options:: help="interaction mode: novice, intermediate, " "or expert [default: %default]") -If :mod:`optparse` encounters either ``-h`` or ``--help`` on the +If :mod:`!optparse` encounters either ``-h`` or ``--help`` on the command-line, or if you just call :meth:`parser.print_help`, it prints the following to standard output: @@ -620,26 +620,26 @@ following to standard output: -m MODE, --mode=MODE interaction mode: novice, intermediate, or expert [default: intermediate] -(If the help output is triggered by a help option, :mod:`optparse` exits after +(If the help output is triggered by a help option, :mod:`!optparse` exits after printing the help text.) -There's a lot going on here to help :mod:`optparse` generate the best possible +There's a lot going on here to help :mod:`!optparse` generate the best possible help message: * the script defines its own usage message:: usage = "usage: %prog [options] arg1 arg2" - :mod:`optparse` expands ``%prog`` in the usage string to the name of the + :mod:`!optparse` expands ``%prog`` in the usage string to the name of the current program, i.e. ``os.path.basename(sys.argv[0])``. The expanded string is then printed before the detailed option help. - If you don't supply a usage string, :mod:`optparse` uses a bland but sensible + If you don't supply a usage string, :mod:`!optparse` uses a bland but sensible default: ``"Usage: %prog [options]"``, which is fine if your script doesn't take any positional arguments. * every option defines a help string, and doesn't worry about - line-wrapping---\ :mod:`optparse` takes care of wrapping lines and making + line-wrapping---\ :mod:`!optparse` takes care of wrapping lines and making the help output look good. * options that take a value indicate this fact in their automatically generated @@ -649,7 +649,7 @@ help message: Here, "MODE" is called the meta-variable: it stands for the argument that the user is expected to supply to ``-m``/``--mode``. By default, - :mod:`optparse` converts the destination variable name to uppercase and uses + :mod:`!optparse` converts the destination variable name to uppercase and uses that for the meta-variable. Sometimes, that's not what you want---for example, the ``--filename`` option explicitly sets ``metavar="FILE"``, resulting in this automatically generated option description:: @@ -663,7 +663,7 @@ help message: way to make your help text a lot clearer and more useful for end users. * options that have a default value can include ``%default`` in the help - string---\ :mod:`optparse` will replace it with :func:`str` of the option's + string---\ :mod:`!optparse` will replace it with :func:`str` of the option's default value. If an option has no default value (or the default value is ``None``), ``%default`` expands to ``none``. @@ -779,14 +779,14 @@ option groups is: Printing a version string ^^^^^^^^^^^^^^^^^^^^^^^^^ -Similar to the brief usage string, :mod:`optparse` can also print a version +Similar to the brief usage string, :mod:`!optparse` can also print a version string for your program. You have to supply the string as the ``version`` argument to OptionParser:: parser = OptionParser(usage="%prog [-f] [-q]", version="%prog 1.0") ``%prog`` is expanded just like it is in ``usage``. Apart from that, -``version`` can contain anything you like. When you supply it, :mod:`optparse` +``version`` can contain anything you like. When you supply it, :mod:`!optparse` automatically adds a ``--version`` option to your parser. If it encounters this option on the command line, it expands your ``version`` string (by replacing ``%prog``), prints it to stdout, and exits. @@ -815,10 +815,10 @@ The following two methods can be used to print and get the ``version`` string: .. _optparse-how-optparse-handles-errors: -How :mod:`optparse` handles errors -^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ +How :mod:`!optparse` handles errors +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -There are two broad classes of errors that :mod:`optparse` has to worry about: +There are two broad classes of errors that :mod:`!optparse` has to worry about: programmer errors and user errors. Programmer errors are usually erroneous calls to :func:`OptionParser.add_option`, e.g. invalid option strings, unknown option attributes, missing option attributes, etc. These are dealt with in the @@ -826,7 +826,7 @@ usual way: raise an exception (either :exc:`optparse.OptionError` or :exc:`TypeError`) and let the program crash. Handling user errors is much more important, since they are guaranteed to happen -no matter how stable your code is. :mod:`optparse` can automatically detect +no matter how stable your code is. :mod:`!optparse` can automatically detect some user errors, such as bad option arguments (passing ``-n 4x`` where ``-n`` takes an integer argument), missing arguments (``-n`` at the end of the command line, where ``-n`` takes an argument of any type). Also, @@ -838,7 +838,7 @@ condition:: if options.a and options.b: parser.error("options -a and -b are mutually exclusive") -In either case, :mod:`optparse` handles the error the same way: it prints the +In either case, :mod:`!optparse` handles the error the same way: it prints the program's usage message and an error message to standard error and exits with error status 2. @@ -861,11 +861,11 @@ Or, where the user fails to pass a value at all: foo: error: -n option requires an argument -:mod:`optparse`\ -generated error messages take care always to mention the +:mod:`!optparse`\ -generated error messages take care always to mention the option involved in the error; be sure to do the same when calling :func:`OptionParser.error` from your application code. -If :mod:`optparse`'s default error-handling behaviour does not suit your needs, +If :mod:`!optparse`'s default error-handling behaviour does not suit your needs, you'll need to subclass OptionParser and override its :meth:`~OptionParser.exit` and/or :meth:`~OptionParser.error` methods. @@ -875,7 +875,7 @@ and/or :meth:`~OptionParser.error` methods. Putting it all together ^^^^^^^^^^^^^^^^^^^^^^^ -Here's what :mod:`optparse`\ -based scripts usually look like:: +Here's what :mod:`!optparse`\ -based scripts usually look like:: from optparse import OptionParser ... @@ -911,7 +911,7 @@ Reference Guide Creating the parser ^^^^^^^^^^^^^^^^^^^ -The first step in using :mod:`optparse` is to create an OptionParser instance. +The first step in using :mod:`!optparse` is to create an OptionParser instance. .. class:: OptionParser(...) @@ -921,7 +921,7 @@ The first step in using :mod:`optparse` is to create an OptionParser instance. ``usage`` (default: ``"%prog [options]"``) The usage summary to print when your program is run incorrectly or with a - help option. When :mod:`optparse` prints the usage string, it expands + help option. When :mod:`!optparse` prints the usage string, it expands ``%prog`` to ``os.path.basename(sys.argv[0])`` (or to ``prog`` if you passed that keyword argument). To suppress a usage message, pass the special value :const:`optparse.SUPPRESS_USAGE`. @@ -938,7 +938,7 @@ The first step in using :mod:`optparse` is to create an OptionParser instance. ``version`` (default: ``None``) A version string to print when the user supplies a version option. If you - supply a true value for ``version``, :mod:`optparse` automatically adds a + supply a true value for ``version``, :mod:`!optparse` automatically adds a version option with the single option string ``--version``. The substring ``%prog`` is expanded the same as for ``usage``. @@ -949,17 +949,17 @@ The first step in using :mod:`optparse` is to create an OptionParser instance. ``description`` (default: ``None``) A paragraph of text giving a brief overview of your program. - :mod:`optparse` reformats this paragraph to fit the current terminal width + :mod:`!optparse` reformats this paragraph to fit the current terminal width and prints it when the user requests help (after ``usage``, but before the list of options). ``formatter`` (default: a new :class:`IndentedHelpFormatter`) An instance of optparse.HelpFormatter that will be used for printing help - text. :mod:`optparse` provides two concrete classes for this purpose: + text. :mod:`!optparse` provides two concrete classes for this purpose: IndentedHelpFormatter and TitledHelpFormatter. ``add_help_option`` (default: ``True``) - If true, :mod:`optparse` will add a help option (with option strings ``-h`` + If true, :mod:`!optparse` will add a help option (with option strings ``-h`` and ``--help``) to the parser. ``prog`` @@ -997,7 +997,7 @@ the OptionParser constructor, as in:: (:func:`make_option` is a factory function for creating Option instances; currently it is an alias for the Option constructor. A future version of -:mod:`optparse` may split Option into several classes, and :func:`make_option` +:mod:`!optparse` may split Option into several classes, and :func:`make_option` will pick the right class to instantiate. Do not instantiate Option directly.) @@ -1027,12 +1027,12 @@ The canonical way to create an :class:`Option` instance is with the The keyword arguments define attributes of the new Option object. The most important option attribute is :attr:`~Option.action`, and it largely determines which other attributes are relevant or required. If you pass - irrelevant option attributes, or fail to pass required ones, :mod:`optparse` + irrelevant option attributes, or fail to pass required ones, :mod:`!optparse` raises an :exc:`OptionError` exception explaining your mistake. - An option's *action* determines what :mod:`optparse` does when it encounters + An option's *action* determines what :mod:`!optparse` does when it encounters this option on the command-line. The standard option actions hard-coded into - :mod:`optparse` are: + :mod:`!optparse` are: ``"store"`` store this option's argument (default) @@ -1066,7 +1066,7 @@ The canonical way to create an :class:`Option` instance is with the attributes; see :ref:`optparse-standard-option-actions`.) As you can see, most actions involve storing or updating a value somewhere. -:mod:`optparse` always creates a special object for this, conventionally called +:mod:`!optparse` always creates a special object for this, conventionally called ``options``, which is an instance of :class:`optparse.Values`. .. class:: Values @@ -1084,7 +1084,7 @@ For example, when you call :: parser.parse_args() -one of the first things :mod:`optparse` does is create the ``options`` object:: +one of the first things :mod:`!optparse` does is create the ``options`` object:: options = Values() @@ -1099,7 +1099,7 @@ and the command-line being parsed includes any of the following:: --file=foo --file foo -then :mod:`optparse`, on seeing this option, will do the equivalent of :: +then :mod:`!optparse`, on seeing this option, will do the equivalent of :: options.filename = "foo" @@ -1124,13 +1124,13 @@ Option attributes The following option attributes may be passed as keyword arguments to :meth:`OptionParser.add_option`. If you pass an option attribute that is not relevant to a particular option, or fail to pass a required option attribute, -:mod:`optparse` raises :exc:`OptionError`. +:mod:`!optparse` raises :exc:`OptionError`. .. attribute:: Option.action (default: ``"store"``) - Determines :mod:`optparse`'s behaviour when this option is seen on the + Determines :mod:`!optparse`'s behaviour when this option is seen on the command line; the available options are documented :ref:`here `. @@ -1147,8 +1147,8 @@ relevant to a particular option, or fail to pass a required option attribute, (default: derived from option strings) If the option's action implies writing or modifying a value somewhere, this - tells :mod:`optparse` where to write it: :attr:`~Option.dest` names an - attribute of the ``options`` object that :mod:`optparse` builds as it parses + tells :mod:`!optparse` where to write it: :attr:`~Option.dest` names an + attribute of the ``options`` object that :mod:`!optparse` builds as it parses the command line. .. attribute:: Option.default @@ -1161,7 +1161,7 @@ relevant to a particular option, or fail to pass a required option attribute, (default: 1) How many arguments of type :attr:`~Option.type` should be consumed when this - option is seen. If > 1, :mod:`optparse` will store a tuple of values to + option is seen. If > 1, :mod:`!optparse` will store a tuple of values to :attr:`~Option.dest`. .. attribute:: Option.const @@ -1207,7 +1207,7 @@ Standard option actions The various option actions all have slightly different requirements and effects. Most actions have several relevant option attributes which you may specify to -guide :mod:`optparse`'s behaviour; a few have required attributes, which you +guide :mod:`!optparse`'s behaviour; a few have required attributes, which you must specify for any option using that action. * ``"store"`` [relevant: :attr:`~Option.type`, :attr:`~Option.dest`, @@ -1225,9 +1225,9 @@ must specify for any option using that action. If :attr:`~Option.type` is not supplied, it defaults to ``"string"``. - If :attr:`~Option.dest` is not supplied, :mod:`optparse` derives a destination + If :attr:`~Option.dest` is not supplied, :mod:`!optparse` derives a destination from the first long option string (e.g., ``--foo-bar`` implies - ``foo_bar``). If there are no long option strings, :mod:`optparse` derives a + ``foo_bar``). If there are no long option strings, :mod:`!optparse` derives a destination from the first short option string (e.g., ``-f`` implies ``f``). Example:: @@ -1239,7 +1239,7 @@ must specify for any option using that action. -f foo.txt -p 1 -3.5 4 -fbar.txt - :mod:`optparse` will set :: + :mod:`!optparse` will set :: options.f = "foo.txt" options.point = (1.0, -3.5, 4.0) @@ -1259,7 +1259,7 @@ must specify for any option using that action. parser.add_option("--noisy", action="store_const", const=2, dest="verbose") - If ``--noisy`` is seen, :mod:`optparse` will set :: + If ``--noisy`` is seen, :mod:`!optparse` will set :: options.verbose = 2 @@ -1282,7 +1282,7 @@ must specify for any option using that action. The option must be followed by an argument, which is appended to the list in :attr:`~Option.dest`. If no default value for :attr:`~Option.dest` is - supplied, an empty list is automatically created when :mod:`optparse` first + supplied, an empty list is automatically created when :mod:`!optparse` first encounters this option on the command-line. If :attr:`~Option.nargs` > 1, multiple arguments are consumed, and a tuple of length :attr:`~Option.nargs` is appended to :attr:`~Option.dest`. @@ -1294,7 +1294,7 @@ must specify for any option using that action. parser.add_option("-t", "--tracks", action="append", type="int") - If ``-t3`` is seen on the command-line, :mod:`optparse` does the equivalent + If ``-t3`` is seen on the command-line, :mod:`!optparse` does the equivalent of:: options.tracks = [] @@ -1333,7 +1333,7 @@ must specify for any option using that action. parser.add_option("-v", action="count", dest="verbosity") - The first time ``-v`` is seen on the command line, :mod:`optparse` does the + The first time ``-v`` is seen on the command line, :mod:`!optparse` does the equivalent of:: options.verbosity = 0 @@ -1364,7 +1364,7 @@ must specify for any option using that action. listed in the help message. To omit an option entirely, use the special value :const:`optparse.SUPPRESS_HELP`. - :mod:`optparse` automatically adds a :attr:`~Option.help` option to all + :mod:`!optparse` automatically adds a :attr:`~Option.help` option to all OptionParsers, so you do not normally need to create one. Example:: @@ -1382,7 +1382,7 @@ must specify for any option using that action. help="Input file to read data from") parser.add_option("--secret", help=SUPPRESS_HELP) - If :mod:`optparse` sees either ``-h`` or ``--help`` on the command line, + If :mod:`!optparse` sees either ``-h`` or ``--help`` on the command line, it will print something like the following help message to stdout (assuming ``sys.argv[0]`` is ``"foo.py"``): @@ -1395,7 +1395,7 @@ must specify for any option using that action. -v Be moderately verbose --file=FILENAME Input file to read data from - After printing the help message, :mod:`optparse` terminates your process with + After printing the help message, :mod:`!optparse` terminates your process with ``sys.exit(0)``. * ``"version"`` @@ -1405,7 +1405,7 @@ must specify for any option using that action. ``print_version()`` method of OptionParser. Generally only relevant if the ``version`` argument is supplied to the OptionParser constructor. As with :attr:`~Option.help` options, you will rarely create ``version`` options, - since :mod:`optparse` automatically adds them when needed. + since :mod:`!optparse` automatically adds them when needed. .. _optparse-standard-option-types: @@ -1413,7 +1413,7 @@ must specify for any option using that action. Standard option types ^^^^^^^^^^^^^^^^^^^^^ -:mod:`optparse` has five built-in option types: ``"string"``, ``"int"``, +:mod:`!optparse` has five built-in option types: ``"string"``, ``"int"``, ``"choice"``, ``"float"`` and ``"complex"``. If you need to add new option types, see section :ref:`optparse-extending-optparse`. @@ -1432,7 +1432,7 @@ Integer arguments (type ``"int"``) are parsed as follows: The conversion is done by calling :func:`int` with the appropriate base (2, 8, -10, or 16). If this fails, so will :mod:`optparse`, although with a more useful +10, or 16). If this fails, so will :mod:`!optparse`, although with a more useful error message. ``"float"`` and ``"complex"`` option arguments are converted directly with @@ -1471,7 +1471,7 @@ The whole point of creating and populating an OptionParser is to call its ``options`` the same object that was passed in as *values*, or the ``optparse.Values`` - instance created by :mod:`optparse` + instance created by :mod:`!optparse` ``args`` the leftover positional arguments after all options have been processed @@ -1499,7 +1499,7 @@ provides several methods to help you out: .. method:: OptionParser.disable_interspersed_args() Set parsing to stop on the first non-option. For example, if ``-a`` and - ``-b`` are both simple options that take no arguments, :mod:`optparse` + ``-b`` are both simple options that take no arguments, :mod:`!optparse` normally accepts this syntax:: prog -a arg1 -b arg2 @@ -1554,7 +1554,7 @@ strings:: (This is particularly true if you've defined your own OptionParser subclass with some standard options.) -Every time you add an option, :mod:`optparse` checks for conflicts with existing +Every time you add an option, :mod:`!optparse` checks for conflicts with existing options. If it finds any, it invokes the current conflict-handling mechanism. You can set the conflict-handling mechanism either in the constructor:: @@ -1581,7 +1581,7 @@ intelligently and add conflicting options to it:: parser.add_option("-n", "--dry-run", ..., help="do no harm") parser.add_option("-n", "--noisy", ..., help="be noisy") -At this point, :mod:`optparse` detects that a previously added option is already +At this point, :mod:`!optparse` detects that a previously added option is already using the ``-n`` option string. Since ``conflict_handler`` is ``"resolve"``, it resolves the situation by removing ``-n`` from the earlier option's list of option strings. Now ``--dry-run`` is the only way for the user to activate @@ -1594,14 +1594,14 @@ that option. If the user asks for help, the help message will reflect that:: It's possible to whittle away the option strings for a previously added option until there are none left, and the user has no way of invoking that option from -the command-line. In that case, :mod:`optparse` removes that option completely, +the command-line. In that case, :mod:`!optparse` removes that option completely, so it doesn't show up in help text or anywhere else. Carrying on with our existing OptionParser:: parser.add_option("--dry-run", ..., help="new dry-run option") At this point, the original ``-n``/``--dry-run`` option is no longer -accessible, so :mod:`optparse` removes it, leaving this help text:: +accessible, so :mod:`!optparse` removes it, leaving this help text:: Options: ... @@ -1676,9 +1676,9 @@ OptionParser supports several other public methods: Option Callbacks ---------------- -When :mod:`optparse`'s built-in actions and types aren't quite enough for your -needs, you have two choices: extend :mod:`optparse` or define a callback option. -Extending :mod:`optparse` is more general, but overkill for a lot of simple +When :mod:`!optparse`'s built-in actions and types aren't quite enough for your +needs, you have two choices: extend :mod:`!optparse` or define a callback option. +Extending :mod:`!optparse` is more general, but overkill for a lot of simple cases. Quite often a simple callback is all you need. There are two steps to defining a callback option: @@ -1702,14 +1702,14 @@ only option attribute you must specify is ``callback``, the function to call:: ``callback`` is a function (or other callable object), so you must have already defined ``my_callback()`` when you create this callback option. In this simple -case, :mod:`optparse` doesn't even know if ``-c`` takes any arguments, +case, :mod:`!optparse` doesn't even know if ``-c`` takes any arguments, which usually means that the option takes no arguments---the mere presence of ``-c`` on the command-line is all it needs to know. In some circumstances, though, you might want your callback to consume an arbitrary number of command-line arguments. This is where writing callbacks gets tricky; it's covered later in this section. -:mod:`optparse` always passes four particular arguments to your callback, and it +:mod:`!optparse` always passes four particular arguments to your callback, and it will only pass additional arguments if you specify them via :attr:`~Option.callback_args` and :attr:`~Option.callback_kwargs`. Thus, the minimal callback function signature is:: @@ -1723,12 +1723,12 @@ callback option: :attr:`~Option.type` has its usual meaning: as with the ``"store"`` or ``"append"`` actions, it - instructs :mod:`optparse` to consume one argument and convert it to + instructs :mod:`!optparse` to consume one argument and convert it to :attr:`~Option.type`. Rather than storing the converted value(s) anywhere, - though, :mod:`optparse` passes it to your callback function. + though, :mod:`!optparse` passes it to your callback function. :attr:`~Option.nargs` - also has its usual meaning: if it is supplied and > 1, :mod:`optparse` will + also has its usual meaning: if it is supplied and > 1, :mod:`!optparse` will consume :attr:`~Option.nargs` arguments, each of which must be convertible to :attr:`~Option.type`. It then passes a tuple of converted values to your callback. @@ -1762,7 +1762,7 @@ where ``"--foobar"``.) ``value`` - is the argument to this option seen on the command-line. :mod:`optparse` will + is the argument to this option seen on the command-line. :mod:`!optparse` will only expect an argument if :attr:`~Option.type` is set; the type of ``value`` will be the type implied by the option's type. If :attr:`~Option.type` for this option is ``None`` (no argument expected), then ``value`` will be ``None``. If :attr:`~Option.nargs` @@ -1787,7 +1787,7 @@ where ``parser.values`` the object where option values are by default stored (an instance of optparse.OptionValues). This lets callbacks use the same mechanism as the - rest of :mod:`optparse` for storing option values; you don't need to mess + rest of :mod:`!optparse` for storing option values; you don't need to mess around with globals or closures. You can also access or modify the value(s) of any options already encountered on the command-line. @@ -1806,7 +1806,7 @@ Raising errors in a callback ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ The callback function should raise :exc:`OptionValueError` if there are any -problems with the option or its argument(s). :mod:`optparse` catches this and +problems with the option or its argument(s). :mod:`!optparse` catches this and terminates the program, printing the error message you supply to stderr. Your message should be clear, concise, accurate, and mention the option at fault. Otherwise, the user will have a hard time figuring out what they did wrong. @@ -1906,7 +1906,7 @@ Here's an example that just emulates the standard ``"store"`` action:: action="callback", callback=store_value, type="int", nargs=3, dest="foo") -Note that :mod:`optparse` takes care of consuming 3 arguments and converting +Note that :mod:`!optparse` takes care of consuming 3 arguments and converting them to integers for you; all you have to do is store them. (Or whatever; obviously you don't need a callback for this example.) @@ -1917,9 +1917,9 @@ Callback example 6: variable arguments ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ Things get hairy when you want an option to take a variable number of arguments. -For this case, you must write a callback, as :mod:`optparse` doesn't provide any +For this case, you must write a callback, as :mod:`!optparse` doesn't provide any built-in capabilities for it. And you have to deal with certain intricacies of -conventional Unix command-line parsing that :mod:`optparse` normally handles for +conventional Unix command-line parsing that :mod:`!optparse` normally handles for you. In particular, callbacks should implement the conventional rules for bare ``--`` and ``-`` arguments: @@ -1934,7 +1934,7 @@ you. In particular, callbacks should implement the conventional rules for bare If you want an option that takes a variable number of arguments, there are several subtle, tricky issues to worry about. The exact implementation you choose will be based on which trade-offs you're willing to make for your -application (which is why :mod:`optparse` doesn't support this sort of thing +application (which is why :mod:`!optparse` doesn't support this sort of thing directly). Nevertheless, here's a stab at a callback for an option with variable @@ -1970,10 +1970,10 @@ arguments:: .. _optparse-extending-optparse: -Extending :mod:`optparse` -------------------------- +Extending :mod:`!optparse` +-------------------------- -Since the two major controlling factors in how :mod:`optparse` interprets +Since the two major controlling factors in how :mod:`!optparse` interprets command-line options are the action and type of each option, the most likely direction of extension is to add new actions and new types. @@ -1983,9 +1983,9 @@ direction of extension is to add new actions and new types. Adding new types ^^^^^^^^^^^^^^^^ -To add new types, you need to define your own subclass of :mod:`optparse`'s +To add new types, you need to define your own subclass of :mod:`!optparse`'s :class:`Option` class. This class has a couple of attributes that define -:mod:`optparse`'s types: :attr:`~Option.TYPES` and :attr:`~Option.TYPE_CHECKER`. +:mod:`!optparse`'s types: :attr:`~Option.TYPES` and :attr:`~Option.TYPE_CHECKER`. .. attribute:: Option.TYPES @@ -2015,7 +2015,7 @@ To add new types, you need to define your own subclass of :mod:`optparse`'s Here's a silly example that demonstrates adding a ``"complex"`` option type to parse Python-style complex numbers on the command line. (This is even sillier -than it used to be, because :mod:`optparse` 1.3 added built-in support for +than it used to be, because :mod:`!optparse` 1.3 added built-in support for complex numbers, but never mind.) First, the necessary imports:: @@ -2041,12 +2041,12 @@ Finally, the Option subclass:: TYPE_CHECKER["complex"] = check_complex (If we didn't make a :func:`copy` of :attr:`Option.TYPE_CHECKER`, we would end -up modifying the :attr:`~Option.TYPE_CHECKER` attribute of :mod:`optparse`'s +up modifying the :attr:`~Option.TYPE_CHECKER` attribute of :mod:`!optparse`'s Option class. This being Python, nothing stops you from doing that except good manners and common sense.) That's it! Now you can write a script that uses the new option type just like -any other :mod:`optparse`\ -based script, except you have to instruct your +any other :mod:`!optparse`\ -based script, except you have to instruct your OptionParser to use MyOption instead of Option:: parser = OptionParser(option_class=MyOption) @@ -2066,10 +2066,10 @@ Adding new actions ^^^^^^^^^^^^^^^^^^ Adding new actions is a bit trickier, because you have to understand that -:mod:`optparse` has a couple of classifications for actions: +:mod:`!optparse` has a couple of classifications for actions: "store" actions - actions that result in :mod:`optparse` storing a value to an attribute of the + actions that result in :mod:`!optparse` storing a value to an attribute of the current OptionValues instance; these options require a :attr:`~Option.dest` attribute to be supplied to the Option constructor. @@ -2101,7 +2101,7 @@ of the following class attributes of Option (all are lists of strings): .. attribute:: Option.ALWAYS_TYPED_ACTIONS Actions that always take a type (i.e. whose options always take a value) are - additionally listed here. The only effect of this is that :mod:`optparse` + additionally listed here. The only effect of this is that :mod:`!optparse` assigns the default type, ``"string"``, to options with no explicit type whose action is listed in :attr:`ALWAYS_TYPED_ACTIONS`. @@ -2144,12 +2144,12 @@ Features of note: somewhere, so it goes in both :attr:`~Option.STORE_ACTIONS` and :attr:`~Option.TYPED_ACTIONS`. -* to ensure that :mod:`optparse` assigns the default type of ``"string"`` to +* to ensure that :mod:`!optparse` assigns the default type of ``"string"`` to ``"extend"`` actions, we put the ``"extend"`` action in :attr:`~Option.ALWAYS_TYPED_ACTIONS` as well. * :meth:`MyOption.take_action` implements just this one new action, and passes - control back to :meth:`Option.take_action` for the standard :mod:`optparse` + control back to :meth:`Option.take_action` for the standard :mod:`!optparse` actions. * ``values`` is an instance of the optparse_parser.Values class, which provides diff --git a/Doc/library/os.path.rst b/Doc/library/os.path.rst index ecbbc1d7605f9f..b0607f066a7213 100644 --- a/Doc/library/os.path.rst +++ b/Doc/library/os.path.rst @@ -36,14 +36,14 @@ the :mod:`glob` module.) Since different operating systems have different path name conventions, there are several versions of this module in the standard library. The - :mod:`os.path` module is always the path module suitable for the operating + :mod:`!os.path` module is always the path module suitable for the operating system Python is running on, and therefore usable for local paths. However, you can also import and use the individual modules if you want to manipulate a path that is *always* in one of the different formats. They all have the same interface: - * :mod:`posixpath` for UNIX-style paths - * :mod:`ntpath` for Windows paths + * :mod:`!posixpath` for UNIX-style paths + * :mod:`!ntpath` for Windows paths .. versionchanged:: 3.8 @@ -57,14 +57,27 @@ the :mod:`glob` module.) .. function:: abspath(path) Return a normalized absolutized version of the pathname *path*. On most - platforms, this is equivalent to calling the function :func:`normpath` as - follows: ``normpath(join(os.getcwd(), path))``. + platforms, this is equivalent to calling ``normpath(join(os.getcwd(), path))``. + + On Windows the path is normalized by the operating system, + therefore the result can differ from ``normpath(join(os.getcwd(), path))``. + A drive-relative path is resolved against the current directory + of the specified drive, and the drive letter is capitalized. + Trailing dots and spaces are stripped. + For example:: + + >>> os.path.abspath('c:spam') + 'C:\\Temp\\spam' + >>> os.path.abspath('c:/temp/spam. . .') + 'c:\\temp\\spam' + + .. seealso:: :func:`os.path.join` and :func:`os.path.normpath`. .. versionchanged:: 3.6 Accepts a :term:`path-like object`. -.. function:: basename(path) +.. function:: basename(path, /) Return the base name of pathname *path*. This is the second element of the pair returned by passing *path* to the function :func:`split`. Note that @@ -94,17 +107,19 @@ the :mod:`glob` module.) Any iterable can now be passed, rather than just sequences. -.. function:: commonprefix(list) +.. function:: commonprefix(list, /) - Return the longest path prefix (taken character-by-character) that is a - prefix of all paths in *list*. If *list* is empty, return the empty string + Return the longest string prefix (taken character-by-character) that is a + prefix of all strings in *list*. If *list* is empty, return the empty string (``''``). - .. note:: + .. warning:: This function may return invalid paths because it works a - character at a time. To obtain a valid path, see - :func:`commonpath`. + character at a time. + If you need a **common path prefix**, then the algorithm + implemented in this function is not secure. Use + :func:`commonpath` for finding a common path prefix. :: @@ -118,7 +133,7 @@ the :mod:`glob` module.) Accepts a :term:`path-like object`. -.. function:: dirname(path) +.. function:: dirname(path, /) Return the directory name of pathname *path*. This is the first element of the pair returned by passing *path* to the function :func:`split`. @@ -199,14 +214,14 @@ the :mod:`glob` module.) Accepts a :term:`path-like object`. -.. function:: getatime(path) +.. function:: getatime(path, /) Return the time of last access of *path*. The return value is a floating-point number giving the number of seconds since the epoch (see the :mod:`time` module). Raise :exc:`OSError` if the file does not exist or is inaccessible. -.. function:: getmtime(path) +.. function:: getmtime(path, /) Return the time of last modification of *path*. The return value is a floating-point number giving the number of seconds since the epoch (see the :mod:`time` module). @@ -216,7 +231,7 @@ the :mod:`glob` module.) Accepts a :term:`path-like object`. -.. function:: getctime(path) +.. function:: getctime(path, /) Return the system's ctime which, on some systems (like Unix) is the time of the last metadata change, and, on others (like Windows), is the creation time for *path*. @@ -228,7 +243,7 @@ the :mod:`glob` module.) Accepts a :term:`path-like object`. -.. function:: getsize(path) +.. function:: getsize(path, /) Return the size, in bytes, of *path*. Raise :exc:`OSError` if the file does not exist or is inaccessible. @@ -237,12 +252,14 @@ the :mod:`glob` module.) Accepts a :term:`path-like object`. -.. function:: isabs(path) +.. function:: isabs(path, /) Return ``True`` if *path* is an absolute pathname. On Unix, that means it begins with a slash, on Windows that it begins with two (back)slashes, or a drive letter, colon, and (back)slash together. + .. seealso:: :func:`abspath` + .. versionchanged:: 3.6 Accepts a :term:`path-like object`. @@ -261,7 +278,7 @@ the :mod:`glob` module.) Accepts a :term:`path-like object`. -.. function:: isdir(path) +.. function:: isdir(path, /) Return ``True`` if *path* is an :func:`existing ` directory. This follows symbolic links, so both :func:`islink` and :func:`isdir` can be true @@ -298,9 +315,10 @@ the :mod:`glob` module.) device than *path*, or whether :file:`{path}/..` and *path* point to the same i-node on the same device --- this should detect mount points for all Unix and POSIX variants. It is not able to reliably detect bind mounts on the - same filesystem. On Windows, a drive letter root and a share UNC are - always mount points, and for any other path ``GetVolumePathName`` is called - to see if it is different from the input path. + same filesystem. On Linux systems, it will always return ``True`` for btrfs + subvolumes, even if they aren't mount points. On Windows, a drive letter root + and a share UNC are always mount points, and for any other path + ``GetVolumePathName`` is called to see if it is different from the input path. .. versionchanged:: 3.4 Added support for detecting non-root mount points on Windows. @@ -350,20 +368,34 @@ the :mod:`glob` module.) .. versionadded:: 3.13 -.. function:: join(path, *paths) +.. function:: join(path, /, *paths) Join one or more path segments intelligently. The return value is the concatenation of *path* and all members of *\*paths*, with exactly one directory separator following each non-empty part, except the last. That is, the result will only end in a separator if the last part is either empty or - ends in a separator. If a segment is an absolute path (which on Windows - requires both a drive and a root), then all previous segments are ignored and - joining continues from the absolute path segment. + ends in a separator. + + If a segment is an absolute path (which on Windows requires both a drive and + a root), then all previous segments are ignored and joining continues from the + absolute path segment. On Linux, for example:: + + >>> os.path.join('/home/foo', 'bar') + '/home/foo/bar' + >>> os.path.join('/home/foo', '/home/bar') + '/home/bar' On Windows, the drive is not reset when a rooted path segment (e.g., ``r'\foo'``) is encountered. If a segment is on a different drive or is an - absolute path, all previous segments are ignored and the drive is reset. Note - that since there is a current directory for each drive, + absolute path, all previous segments are ignored and the drive is reset. For + example:: + + >>> os.path.join('c:\\', 'foo') + 'c:\\foo' + >>> os.path.join('c:\\foo', 'd:\\bar') + 'd:\\bar' + + Note that since there is a current directory for each drive, ``os.path.join("c:", "foo")`` represents a path relative to the current directory on drive :file:`C:` (:file:`c:foo`), not :file:`c:\\foo`. @@ -371,7 +403,7 @@ the :mod:`glob` module.) Accepts a :term:`path-like object` for *path* and *paths*. -.. function:: normcase(path) +.. function:: normcase(path, /) Normalize the case of a pathname. On Windows, convert all characters in the pathname to lowercase, and also convert forward slashes to backward slashes. @@ -401,16 +433,36 @@ the :mod:`glob` module.) Accepts a :term:`path-like object`. -.. function:: realpath(path, *, strict=False) +.. function:: realpath(path, /, *, strict=False) Return the canonical path of the specified filename, eliminating any symbolic links encountered in the path (if they are supported by the operating system). On Windows, this function will also resolve MS-DOS (also called 8.3) style names such as ``C:\\PROGRA~1`` to ``C:\\Program Files``. + The returned path uses the case reported by the operating system, + which can differ from the case of *path*, + in particular the drive letter is capitalized. - If a path doesn't exist or a symlink loop is encountered, and *strict* is - ``True``, :exc:`OSError` is raised. If *strict* is ``False`` these errors - are ignored, and so the result might be missing or otherwise inaccessible. + By default, the path is evaluated up to the first component that does not + exist, is a symlink loop, or whose evaluation raises :exc:`OSError`. + All such components are appended unchanged to the existing part of the path. + + Some errors that are handled this way include "access denied", "not a + directory", or "bad argument to internal function". Thus, the + resulting path may be missing or inaccessible, may still contain + links or loops, and may traverse non-directories. + + This behavior can be modified by keyword arguments: + + If *strict* is ``True``, the first error encountered when evaluating the path is + re-raised. + In particular, :exc:`FileNotFoundError` is raised if *path* does not exist, + or another :exc:`OSError` if it is otherwise inaccessible. + + If *strict* is :py:data:`os.path.ALLOW_MISSING`, errors other than + :exc:`FileNotFoundError` are re-raised (as with ``strict=True``). + Thus, the returned path will not contain any symbolic links, but the named + file and some of its parent directories may be missing. .. note:: This function emulates the operating system's procedure for making a path @@ -429,6 +481,15 @@ the :mod:`glob` module.) .. versionchanged:: 3.10 The *strict* parameter was added. + .. versionchanged:: 3.14 + The :py:data:`~os.path.ALLOW_MISSING` value for the *strict* parameter + was added. + +.. data:: ALLOW_MISSING + + Special value used for the *strict* argument in :func:`realpath`. + + .. versionadded:: 3.14 .. function:: relpath(path, start=os.curdir) @@ -444,7 +505,7 @@ the :mod:`glob` module.) Accepts a :term:`path-like object`. -.. function:: samefile(path1, path2) +.. function:: samefile(path1, path2, /) Return ``True`` if both pathname arguments refer to the same file or directory. This is determined by the device number and i-node number and raises an @@ -471,7 +532,7 @@ the :mod:`glob` module.) Accepts a :term:`path-like object`. -.. function:: samestat(stat1, stat2) +.. function:: samestat(stat1, stat2, /) Return ``True`` if the stat tuples *stat1* and *stat2* refer to the same file. These structures may have been returned by :func:`os.fstat`, @@ -481,11 +542,8 @@ the :mod:`glob` module.) .. versionchanged:: 3.4 Added Windows support. - .. versionchanged:: 3.6 - Accepts a :term:`path-like object`. - -.. function:: split(path) +.. function:: split(path, /) Split the pathname *path* into a pair, ``(head, tail)`` where *tail* is the last pathname component and *head* is everything leading up to that. The @@ -494,14 +552,14 @@ the :mod:`glob` module.) *path* is empty, both *head* and *tail* are empty. Trailing slashes are stripped from *head* unless it is the root (one or more slashes only). In all cases, ``join(head, tail)`` returns a path to the same location as *path* - (but the strings may differ). Also see the functions :func:`dirname` and - :func:`basename`. + (but the strings may differ). Also see the functions :func:`join`, + :func:`dirname` and :func:`basename`. .. versionchanged:: 3.6 Accepts a :term:`path-like object`. -.. function:: splitdrive(path) +.. function:: splitdrive(path, /) Split the pathname *path* into a pair ``(drive, tail)`` where *drive* is either a mount point or the empty string. On systems which do not use drive @@ -526,7 +584,7 @@ the :mod:`glob` module.) Accepts a :term:`path-like object`. -.. function:: splitroot(path) +.. function:: splitroot(path, /) Split the pathname *path* into a 3-item tuple ``(drive, root, tail)`` where *drive* is a device name or mount point, *root* is a string of separators @@ -559,7 +617,7 @@ the :mod:`glob` module.) .. versionadded:: 3.12 -.. function:: splitext(path) +.. function:: splitext(path, /) Split the pathname *path* into a pair ``(root, ext)`` such that ``root + ext == path``, and the extension, *ext*, is empty or begins with a period and contains at diff --git a/Doc/library/os.rst b/Doc/library/os.rst index 1e54cfec609bd2..df7d84a3531093 100644 --- a/Doc/library/os.rst +++ b/Doc/library/os.rst @@ -25,7 +25,7 @@ Notes on the availability of these functions: with the POSIX interface). * Extensions peculiar to a particular operating system are also available - through the :mod:`os` module, but using them is of course a threat to + through the :mod:`!os` module, but using them is of course a threat to portability. * All functions accepting path or file names accept both bytes and string @@ -34,7 +34,7 @@ Notes on the availability of these functions: * On VxWorks, os.popen, os.fork, os.execv and os.spawn*p* are not supported. -* On WebAssembly platforms, Android and iOS, large parts of the :mod:`os` module are +* On WebAssembly platforms, Android and iOS, large parts of the :mod:`!os` module are not available or behave differently. APIs related to processes (e.g. :func:`~os.fork`, :func:`~os.execve`) and resources (e.g. :func:`~os.nice`) are not available. Others like :func:`~os.getuid` and :func:`~os.getpid` are @@ -188,7 +188,7 @@ process and user. of your home directory (on some platforms), and is equivalent to ``getenv("HOME")`` in C. - This mapping is captured the first time the :mod:`os` module is imported, + This mapping is captured the first time the :mod:`!os` module is imported, typically during Python startup as part of processing :file:`site.py`. Changes to the environment made after this time are not reflected in :data:`os.environ`, except for changes made by modifying :data:`os.environ` directly. @@ -257,7 +257,7 @@ process and user. .. warning:: This function is not thread-safe. Calling it while the environment is - being modified in an other thread is an undefined behavior. Reading from + being modified in another thread is an undefined behavior. Reading from :data:`os.environ` or :data:`os.environb`, or calling :func:`os.getenv` while reloading, may return an empty result. @@ -532,7 +532,7 @@ process and user. Return a tuple (ruid, euid, suid) denoting the current process's real, effective, and saved user ids. - .. availability:: Unix, not WASI. + .. availability:: Unix, not WASI, not macOS, not iOS. .. versionadded:: 3.2 @@ -542,7 +542,7 @@ process and user. Return a tuple (rgid, egid, sgid) denoting the current process's real, effective, and saved group ids. - .. availability:: Unix, not WASI. + .. availability:: Unix, not WASI, not macOS, not iOS. .. versionadded:: 3.2 @@ -561,7 +561,7 @@ process and user. .. function:: initgroups(username, gid, /) - Call the system initgroups() to initialize the group access list with all of + Call the system ``initgroups()`` to initialize the group access list with all of the groups of which the specified username is a member, plus the specified group id. @@ -716,7 +716,7 @@ process and user. Set the current process's real, effective, and saved group ids. - .. availability:: Unix, not WASI, not Android. + .. availability:: Unix, not WASI, not Android, not macOS, not iOS. .. versionadded:: 3.2 @@ -725,7 +725,7 @@ process and user. Set the current process's real, effective, and saved user ids. - .. availability:: Unix, not WASI, not Android. + .. availability:: Unix, not WASI, not Android, not macOS, not iOS. .. versionadded:: 3.2 @@ -791,29 +791,19 @@ process and user. single: gethostbyaddr() (in module socket) Returns information identifying the current operating system. - The return value is an object with five attributes: - - * :attr:`sysname` - operating system name - * :attr:`nodename` - name of machine on network (implementation-defined) - * :attr:`release` - operating system release - * :attr:`version` - operating system version - * :attr:`machine` - hardware identifier - - For backwards compatibility, this object is also iterable, behaving - like a five-tuple containing :attr:`sysname`, :attr:`nodename`, - :attr:`release`, :attr:`version`, and :attr:`machine` - in that order. + The return value is a :class:`uname_result`. - Some systems truncate :attr:`nodename` to 8 characters or to the - leading component; a better way to get the hostname is - :func:`socket.gethostname` or even - ``socket.gethostbyaddr(socket.gethostname())``. - - On macOS, iOS and Android, this returns the *kernel* name and version (i.e., + On macOS, iOS and Android, this returns the *kernel* name and release (i.e., ``'Darwin'`` on macOS and iOS; ``'Linux'`` on Android). :func:`platform.uname` - can be used to get the user-facing operating system name and version on iOS and + can be used to get the user-facing operating system name and release on iOS and Android. + .. seealso:: + :data:`sys.platform` which has finer granularity. + + The :mod:`platform` module provides detailed checks for the + system's identity. + .. availability:: Unix. .. versionchanged:: 3.3 @@ -821,6 +811,41 @@ process and user. with named attributes. +.. class:: uname_result + + Name and information about the system returned by :func:`os.uname`. + These attributes correspond to the members described in :manpage:`uname(2)`. + + For backwards compatibility, this object is also iterable, behaving + like a five-tuple containing :attr:`~uname_result.sysname`, + :attr:`~uname_result.nodename`, :attr:`~uname_result.release`, + :attr:`~uname_result.version`, and :attr:`~uname_result.machine` + in that order. + + .. attribute:: sysname + + Operating system name. + + .. attribute:: nodename + + Name of machine on network. Some systems truncate + :attr:`~uname_result.nodename` to 8 characters or to the leading + component; a better way to get the hostname is :func:`socket.gethostname` + or even ``socket.gethostbyaddr(socket.gethostname())``. + + .. attribute:: release + + Operating system release. + + .. attribute:: version + + Operating system version. + + .. attribute:: machine + + Hardware identifier. + + .. function:: unsetenv(key, /) .. index:: single: environment variables; deleting @@ -1062,10 +1087,7 @@ as internal buffering of data. Force write of file with filedescriptor *fd* to disk. Does not force update of metadata. - .. availability:: Unix. - - .. note:: - This function is not available on MacOS. + .. availability:: Unix, not macOS, not iOS. .. function:: fpathconf(fd, name, /) @@ -1103,8 +1125,8 @@ as internal buffering of data. .. function:: fstatvfs(fd, /) Return information about the filesystem containing the file associated with - file descriptor *fd*, like :func:`statvfs`. As of Python 3.3, this is - equivalent to ``os.statvfs(fd)``. + file descriptor *fd* in a :class:`statvfs_result`, like :func:`statvfs`. + As of Python 3.3, this is equivalent to ``os.statvfs(fd)``. .. availability:: Unix. @@ -1282,7 +1304,7 @@ as internal buffering of data. For a description of the flag and mode values, see the C run-time documentation; flag constants (like :const:`O_RDONLY` and :const:`O_WRONLY`) are defined in - the :mod:`os` module. In particular, on Windows adding + the :mod:`!os` module. In particular, on Windows adding :const:`O_BINARY` is needed to open files in binary mode. This function can support :ref:`paths relative to directory descriptors @@ -1297,8 +1319,8 @@ as internal buffering of data. This function is intended for low-level I/O. For normal usage, use the built-in function :func:`open`, which returns a :term:`file object` with - :meth:`~file.read` and :meth:`~file.write` methods (and many more). To - wrap a file descriptor in a file object, use :func:`fdopen`. + :meth:`~io.BufferedIOBase.read` and :meth:`~io.BufferedIOBase.write` methods. + To wrap a file descriptor in a file object, use :func:`fdopen`. .. versionchanged:: 3.3 Added the *dir_fd* parameter. @@ -1417,7 +1439,7 @@ or `the MSDN `_ on Windo Return a pair of file descriptors ``(r, w)`` usable for reading and writing, respectively. - .. availability:: Unix, not WASI. + .. availability:: Unix, not WASI, not macOS, not iOS. .. versionadded:: 3.3 @@ -1427,7 +1449,7 @@ or `the MSDN `_ on Windo Ensures that enough disk space is allocated for the file specified by *fd* starting from *offset* and continuing for *len* bytes. - .. availability:: Unix. + .. availability:: Unix, not macOS, not iOS. .. versionadded:: 3.3 @@ -1442,7 +1464,7 @@ or `the MSDN `_ on Windo :data:`POSIX_FADV_RANDOM`, :data:`POSIX_FADV_NOREUSE`, :data:`POSIX_FADV_WILLNEED` or :data:`POSIX_FADV_DONTNEED`. - .. availability:: Unix. + .. availability:: Unix, not macOS, not iOS. .. versionadded:: 3.3 @@ -1652,7 +1674,7 @@ or `the MSDN `_ on Windo descriptor as returned by :func:`os.open` or :func:`pipe`. To read a "file object" returned by the built-in function :func:`open` or by :func:`popen` or :func:`fdopen`, or :data:`sys.stdin`, use its - :meth:`~file.read` or :meth:`~file.readline` methods. + :meth:`~io.TextIOBase.read` or :meth:`~io.IOBase.readline` methods. .. versionchanged:: 3.5 If the system call is interrupted and the signal handler does not raise an @@ -1887,7 +1909,7 @@ or `the MSDN `_ on Windo descriptor as returned by :func:`os.open` or :func:`pipe`. To write a "file object" returned by the built-in function :func:`open` or by :func:`popen` or :func:`fdopen`, or :data:`sys.stdout` or :data:`sys.stderr`, use its - :meth:`~file.write` method. + :meth:`~io.TextIOBase.write` method. .. versionchanged:: 3.5 If the system call is interrupted and the signal handler does not raise an @@ -1961,7 +1983,8 @@ can be inherited by child processes. Since Python 3.4, file descriptors created by Python are non-inheritable by default. On UNIX, non-inheritable file descriptors are closed in child processes at the -execution of a new program, other file descriptors are inherited. +execution of a new program, other file descriptors are inherited. Note that +non-inheritable file descriptors are still *inherited* by child processes on :func:`os.fork`. On Windows, non-inheritable handles and file descriptors are closed in child processes, except for standard streams (file descriptors 0, 1 and 2: stdin, stdout @@ -2005,12 +2028,12 @@ features: .. _path_fd: * **specifying a file descriptor:** - Normally the *path* argument provided to functions in the :mod:`os` module + Normally the *path* argument provided to functions in the :mod:`!os` module must be a string specifying a file path. However, some functions now alternatively accept an open file descriptor for their *path* argument. The function will then operate on the file referred to by the descriptor. - (For POSIX systems, Python will call the variant of the function prefixed - with ``f`` (e.g. call ``fchdir`` instead of ``chdir``).) + For POSIX systems, Python will call the variant of the function prefixed + with ``f`` (e.g. call ``fchdir`` instead of ``chdir``). You can check whether or not *path* can be specified as a file descriptor for a particular function on your platform using :data:`os.supports_fd`. @@ -2025,7 +2048,7 @@ features: * **paths relative to directory descriptors:** If *dir_fd* is not ``None``, it should be a file descriptor referring to a directory, and the path to operate on should be relative; path will then be relative to that directory. If the - path is absolute, *dir_fd* is ignored. (For POSIX systems, Python will call + path is absolute, *dir_fd* is ignored. For POSIX systems, Python will call the variant of the function with an ``at`` suffix and possibly prefixed with ``f`` (e.g. call ``faccessat`` instead of ``access``). @@ -2038,8 +2061,8 @@ features: * **not following symlinks:** If *follow_symlinks* is ``False``, and the last element of the path to operate on is a symbolic link, the function will operate on the symbolic link itself rather than the file - pointed to by the link. (For POSIX systems, Python will call the ``l...`` - variant of the function.) + pointed to by the link. For POSIX systems, Python will call the ``l...`` + variant of the function. You can check whether or not *follow_symlinks* is supported for a particular function on your platform using :data:`os.supports_follow_symlinks`. @@ -2127,6 +2150,11 @@ features: .. audit-event:: os.chdir path os.chdir + .. seealso:: + + The :func:`contextlib.chdir` context manager, which changes the current + working directory on entering and restores the previous one on exit. + .. versionchanged:: 3.3 Added support for specifying *path* as a file descriptor on some platforms. @@ -2936,6 +2964,9 @@ features: To be directly usable as a :term:`path-like object`, ``os.DirEntry`` implements the :class:`PathLike` interface. + :class:`!DirEntry` objects are :ref:`generic ` over the type of the + path (:class:`str` or :class:`bytes`). + Attributes and methods on a ``os.DirEntry`` instance are as follows: .. attribute:: name @@ -2949,10 +2980,16 @@ features: .. attribute:: path - The entry's full path name: equivalent to ``os.path.join(scandir_path, - entry.name)`` where *scandir_path* is the :func:`scandir` *path* - argument. The path is only absolute if the :func:`scandir` *path* - argument was absolute. If the :func:`scandir` *path* + The entry's path name: equivalent to ``os.path.join(scandir_path, + entry.name)`` where *scandir_path* is the original :func:`scandir` + *path* argument. Apart from the filename, the path preserves the + original :func:`scandir` argument. If the :func:`scandir` *path* + argument was relative, the :attr:`path` attribute is also relative. + Changing the current working directory after creating the + :func:`scandir` iterator may cause later uses of :attr:`path` to resolve + differently. On some platforms, the constructed path may not be valid + if the original :func:`scandir` argument was usable for enumeration but + not for joining with the entry name. If the :func:`scandir` *path* argument was a :ref:`file descriptor `, the :attr:`path` attribute is the same as the :attr:`name` attribute. @@ -3370,53 +3407,179 @@ features: .. function:: statvfs(path) - Perform a :c:func:`!statvfs` system call on the given path. The return value is - an object whose attributes describe the filesystem on the given path, and - correspond to the members of the :c:struct:`statvfs` structure, namely: - :attr:`f_bsize`, :attr:`f_frsize`, :attr:`f_blocks`, :attr:`f_bfree`, - :attr:`f_bavail`, :attr:`f_files`, :attr:`f_ffree`, :attr:`f_favail`, - :attr:`f_flag`, :attr:`f_namemax`, :attr:`f_fsid`. - - Two module-level constants are defined for the :attr:`f_flag` attribute's - bit-flags: if :const:`ST_RDONLY` is set, the filesystem is mounted - read-only, and if :const:`ST_NOSUID` is set, the semantics of - setuid/setgid bits are disabled or not supported. - - Additional module-level constants are defined for GNU/glibc based systems. - These are :const:`ST_NODEV` (disallow access to device special files), - :const:`ST_NOEXEC` (disallow program execution), :const:`ST_SYNCHRONOUS` - (writes are synced at once), :const:`ST_MANDLOCK` (allow mandatory locks on an FS), - :const:`ST_WRITE` (write on file/directory/symlink), :const:`ST_APPEND` - (append-only file), :const:`ST_IMMUTABLE` (immutable file), :const:`ST_NOATIME` - (do not update access times), :const:`ST_NODIRATIME` (do not update directory access - times), :const:`ST_RELATIME` (update atime relative to mtime/ctime). + Perform a :manpage:`statvfs(3)` system call on the given path. The return value + is a :class:`statvfs_result` whose attributes describe the filesystem + on the given path and correspond to the members of the :c:struct:`statvfs` + structure. This function can support :ref:`specifying a file descriptor `. .. availability:: Unix. - .. versionchanged:: 3.2 - The :const:`ST_RDONLY` and :const:`ST_NOSUID` constants were added. - .. versionchanged:: 3.3 Added support for specifying *path* as an open file descriptor. - .. versionchanged:: 3.4 - The :const:`ST_NODEV`, :const:`ST_NOEXEC`, :const:`ST_SYNCHRONOUS`, - :const:`ST_MANDLOCK`, :const:`ST_WRITE`, :const:`ST_APPEND`, - :const:`ST_IMMUTABLE`, :const:`ST_NOATIME`, :const:`ST_NODIRATIME`, - and :const:`ST_RELATIME` constants were added. - .. versionchanged:: 3.6 Accepts a :term:`path-like object`. - .. versionchanged:: 3.7 - Added the :attr:`f_fsid` attribute. + +.. class:: statvfs_result + + Filesystem statistics returned by :func:`os.statvfs` and :func:`os.fstatvfs`. + See :manpage:`statvfs(3)` for more details. + + .. attribute:: f_bsize + + Block size. + + .. attribute:: f_frsize + + Fragment size. + + .. attribute:: f_blocks + + Number of :attr:`~statvfs_result.f_frsize` sized blocks the filesystem + can contain. + + .. attribute:: f_bfree + + Number of free blocks. + + .. attribute:: f_bavail + + Number of free blocks for unprivileged users. + + .. attribute:: f_files + + Number of file entries, inodes, the filesystem can contain. + + .. attribute:: f_ffree + + Number of free files entries. + + .. attribute:: f_favail + + Number of free file entries for unprivileged users. + + .. attribute:: f_flag + + Bit-mask of mount flags. The following flags are defined: + :data:`ST_RDONLY`, :data:`ST_NOSUID`, :data:`ST_NODEV`, + :data:`ST_NOEXEC`, :data:`ST_SYNCHRONOUS`, :data:`ST_MANDLOCK`, + :data:`ST_WRITE`, :data:`ST_APPEND`, :data:`ST_IMMUTABLE`, + :data:`ST_NOATIME`, :data:`ST_NODIRATIME`, and :data:`ST_RELATIME`. + + .. attribute:: f_namemax + + Filesystem max filename length. OS specific limitations such as + :ref:`Windows MAX_PATH ` and those described in Linux + :manpage:`pathname(7)` may exist. + + .. attribute:: f_fsid + + Filesystem ID. + + .. versionadded:: 3.7 + + +The following flags are used in :attr:`statvfs_result.f_flag`. + +.. data:: ST_RDONLY + + Read-only filesystem. + + .. versionadded:: 3.2 + +.. data:: ST_NOSUID + + Setuid/setgid bits are disabled or not supported. + + .. versionadded:: 3.2 + +.. data:: ST_NODEV + + Disallow access to device special files. + + .. availability:: Linux. + + .. versionadded:: 3.4 + +.. data:: ST_NOEXEC + + Disallow program execution. + + .. availability:: Linux. + + .. versionadded:: 3.4 + +.. data:: ST_SYNCHRONOUS + + Writes are synced at once. + + .. availability:: Linux. + + .. versionadded:: 3.4 + +.. data:: ST_MANDLOCK + + Allow mandatory locks on an FS. + + .. availability:: Linux. + + .. versionadded:: 3.4 + +.. data:: ST_WRITE + + Write on file/directory/symlink. + + .. availability:: Linux. + + .. versionadded:: 3.4 + +.. data:: ST_APPEND + + Append-only file. + + .. availability:: Linux. + + .. versionadded:: 3.4 + +.. data:: ST_IMMUTABLE + + Immutable file. + + .. availability:: Linux. + + .. versionadded:: 3.4 + +.. data:: ST_NOATIME + + Do not update access times. + + .. availability:: Linux. + + .. versionadded:: 3.4 + +.. data:: ST_NODIRATIME + + Do not update directory access times. + + .. availability:: Linux. + + .. versionadded:: 3.4 + +.. data:: ST_RELATIME + + Update atime relative to mtime/ctime. + + .. availability:: Linux. + + .. versionadded:: 3.4 .. data:: supports_dir_fd - A :class:`set` object indicating which functions in the :mod:`os` + A :class:`set` object indicating which functions in the :mod:`!os` module accept an open file descriptor for their *dir_fd* parameter. Different platforms provide different features, and the underlying functionality Python uses to implement the *dir_fd* parameter is not @@ -3461,7 +3624,7 @@ features: .. data:: supports_fd A :class:`set` object indicating which functions in the - :mod:`os` module permit specifying their *path* parameter as an open file + :mod:`!os` module permit specifying their *path* parameter as an open file descriptor on the local platform. Different platforms provide different features, and the underlying functionality Python uses to accept open file descriptors as *path* arguments is not available on all platforms Python @@ -3480,7 +3643,7 @@ features: .. data:: supports_follow_symlinks - A :class:`set` object indicating which functions in the :mod:`os` module + A :class:`set` object indicating which functions in the :mod:`!os` module accept ``False`` for their *follow_symlinks* parameter on the local platform. Different platforms provide different features, and the underlying functionality Python uses to implement *follow_symlinks* is not available @@ -3505,6 +3668,9 @@ features: Create a symbolic link pointing to *src* named *dst*. + The *src* parameter refers to the target of the link (the file or directory being linked to), + and *dst* is the name of the link being created. + On Windows, a symlink represents either a file or a directory, and does not morph to the target dynamically. If the target is present, the type of the symlink will be created to match. Otherwise, the symlink will be created @@ -3760,9 +3926,9 @@ features: import os for root, dirs, files, rootfd in os.fwalk('python/Lib/xml'): - print(root, "consumes", end="") + print(root, "consumes", end=" ") print(sum([os.stat(name, dir_fd=rootfd).st_size for name in files]), - end="") + end=" ") print("bytes in", len(files), "non-directory files") if '__pycache__' in dirs: dirs.remove('__pycache__') # don't visit __pycache__ directories @@ -3876,7 +4042,7 @@ features: import os # semaphore with start value '1' - fd = os.eventfd(1, os.EFD_SEMAPHORE | os.EFC_CLOEXEC) + fd = os.eventfd(1, os.EFD_SEMAPHORE | os.EFD_CLOEXEC) try: # acquire semaphore v = os.eventfd_read(fd) @@ -3985,7 +4151,7 @@ Naturally, they are all only available on Linux. except it includes any time that the system is suspended. The file descriptor's behaviour can be modified by specifying a *flags* value. - Any of the following variables may used, combined using bitwise OR + Any of the following variables may be used, combined using bitwise OR (the ``|`` operator): - :const:`TFD_NONBLOCK` @@ -4017,7 +4183,7 @@ Naturally, they are all only available on Linux. *fd* must be a valid timer file descriptor. The timer's behaviour can be modified by specifying a *flags* value. - Any of the following variables may used, combined using bitwise OR + Any of the following variables may be used, combined using bitwise OR (the ``|`` operator): - :const:`TFD_TIMER_ABSTIME` @@ -4086,7 +4252,7 @@ Naturally, they are all only available on Linux. Return a two-item tuple of floats (``next_expiration``, ``interval``). - ``next_expiration`` denotes the relative time until next the timer next fires, + ``next_expiration`` denotes the relative time until the timer next fires, regardless of if the :const:`TFD_TIMER_ABSTIME` flag is set. ``interval`` denotes the timer's interval. @@ -4322,7 +4488,7 @@ to be ignored. The current process is replaced immediately. Open file objects and descriptors are not flushed, so if there may be data buffered on these open files, you should flush them using - :func:`sys.stdout.flush` or :func:`os.fsync` before calling an + :func:`~io.IOBase.flush` or :func:`os.fsync` before calling an :func:`exec\* ` function. The "l" and "v" variants of the :func:`exec\* ` functions differ in how @@ -4665,7 +4831,7 @@ written in Python, such as a mail server's external command delivery program. Lock program segments into memory. The value of *op* (defined in ````) determines which segments are locked. - .. availability:: Unix, not WASI, not iOS. + .. availability:: Unix, not WASI, not macOS, not iOS. .. function:: popen(cmd, mode='r', buffering=-1) @@ -4707,9 +4873,8 @@ written in Python, such as a mail server's external command delivery program. Use :class:`subprocess.Popen` or :func:`subprocess.run` to control options like encodings. - .. deprecated:: 3.14 - The function is :term:`soft deprecated` and should no longer be used to - write new code. The :mod:`subprocess` module is recommended instead. + .. soft-deprecated:: 3.14 + The :mod:`subprocess` module is recommended instead. .. function:: posix_spawn(path, argv, env, *, file_actions=None, \ @@ -4937,9 +5102,8 @@ written in Python, such as a mail server's external command delivery program. .. versionchanged:: 3.6 Accepts a :term:`path-like object`. - .. deprecated:: 3.14 - These functions are :term:`soft deprecated` and should no longer be used - to write new code. The :mod:`subprocess` module is recommended instead. + .. soft-deprecated:: 3.14 + The :mod:`subprocess` module is recommended instead. .. data:: P_NOWAIT @@ -5613,7 +5777,7 @@ Miscellaneous System Information .. versionchanged:: 3.13 If :option:`-X cpu_count <-X>` is given or :envvar:`PYTHON_CPU_COUNT` is set, - :func:`cpu_count` returns the overridden value *n*. + :func:`cpu_count` returns the override value *n*. .. function:: getloadavg() @@ -5635,7 +5799,7 @@ Miscellaneous System Information in the **system**. If :option:`-X cpu_count <-X>` is given or :envvar:`PYTHON_CPU_COUNT` is set, - :func:`process_cpu_count` returns the overridden value *n*. + :func:`process_cpu_count` returns the override value *n*. See also the :func:`sched_getaffinity` function. diff --git a/Doc/library/pathlib.rst b/Doc/library/pathlib.rst index 7d7692dea5c38c..792cd255753c5b 100644 --- a/Doc/library/pathlib.rst +++ b/Doc/library/pathlib.rst @@ -311,7 +311,7 @@ Pure paths provide the following methods and properties: .. attribute:: PurePath.parser The implementation of the :mod:`os.path` module used for low-level path - parsing and joining: either :mod:`posixpath` or :mod:`ntpath`. + parsing and joining: either :mod:`!posixpath` or :mod:`!ntpath`. .. versionadded:: 3.13 @@ -486,6 +486,10 @@ Pure paths provide the following methods and properties: >>> PurePosixPath('my/library').stem 'library' + .. versionchanged:: 3.14 + + A single dot ("``.``") is considered a valid suffix. + .. method:: PurePath.as_posix() @@ -1345,6 +1349,10 @@ Reading directories PosixPath('setup.py'), PosixPath('test_pathlib.py')] + .. note:: + The paths are returned in no particular order. + If you need a specific order, sort the results. + .. seealso:: :ref:`pathlib-pattern-language` documentation. @@ -1357,6 +1365,11 @@ Reading directories ``False``, this method follows symlinks except when expanding "``**``" wildcards. Set *recurse_symlinks* to ``True`` to always follow symlinks. + .. note:: + Any :exc:`OSError` exceptions raised from scanning the filesystem are + suppressed. This includes :exc:`PermissionError` when accessing + directories without read permission. + .. audit-event:: pathlib.Path.glob self,pattern pathlib.Path.glob .. versionchanged:: 3.12 @@ -1379,6 +1392,15 @@ Reading directories Glob the given relative *pattern* recursively. This is like calling :func:`Path.glob` with "``**/``" added in front of the *pattern*. + .. note:: + The paths are returned in no particular order. + If you need a specific order, sort the results. + + .. note:: + Any :exc:`OSError` exceptions raised from scanning the filesystem are + suppressed. This includes :exc:`PermissionError` when accessing + directories without read permission. + .. seealso:: :ref:`pathlib-pattern-language` and :meth:`Path.glob` documentation. @@ -1781,9 +1803,12 @@ The following wildcards are supported in patterns for ``?`` Matches one non-separator character. ``[seq]`` - Matches one character in *seq*. + Matches one character in *seq*, where *seq* is a sequence of characters. + Range expressions are supported; for example, ``[a-z]`` matches any lowercase ASCII letter. + Multiple ranges can be combined: ``[a-zA-Z0-9_]`` matches any ASCII letter, digit, or underscore. + ``[!seq]`` - Matches one character not in *seq*. + Matches one character not in *seq*, where *seq* follows the same rules as above. For a literal match, wrap the meta-characters in brackets. For example, ``"[?]"`` matches the character ``"?"``. @@ -1886,7 +1911,7 @@ Below is a table mapping various :mod:`os` functions to their corresponding :class:`PurePath`/:class:`Path` equivalent. ===================================== ============================================== -:mod:`os` and :mod:`os.path` :mod:`pathlib` +:mod:`os` and :mod:`os.path` :mod:`!pathlib` ===================================== ============================================== :func:`os.path.dirname` :attr:`PurePath.parent` :func:`os.path.basename` :attr:`PurePath.name` @@ -1945,7 +1970,7 @@ Protocols :synopsis: pathlib types for static type checking -The :mod:`pathlib.types` module provides types for static type checking. +The :mod:`!pathlib.types` module provides types for static type checking. .. versionadded:: 3.14 @@ -1982,7 +2007,7 @@ The :mod:`pathlib.types` module provides types for static type checking. If *follow_symlinks* is ``False``, return ``True`` only if the path is a file (without following symlinks); return ``False`` if the path - is a directory or other other non-file, or if it doesn't exist. + is a directory or other non-file, or if it doesn't exist. .. method:: is_symlink() diff --git a/Doc/library/pdb.rst b/Doc/library/pdb.rst index a0304edddf6478..e7dd2e5524abca 100644 --- a/Doc/library/pdb.rst +++ b/Doc/library/pdb.rst @@ -1,7 +1,7 @@ .. _debugger: -:mod:`pdb` --- The Python Debugger -================================== +:mod:`!pdb` --- The Python Debugger +=================================== .. module:: pdb :synopsis: The Python debugger for interactive interpreters. @@ -12,7 +12,7 @@ -------------- -The module :mod:`pdb` defines an interactive source code debugger for Python +The module :mod:`!pdb` defines an interactive source code debugger for Python programs. It supports setting (conditional) breakpoints and single stepping at the source line level, inspection of stack frames, source code listing, and evaluation of arbitrary Python code in the context of any stack frame. It also @@ -75,12 +75,17 @@ The debugger's prompt is ``(Pdb)``, which is the indicator that you are in debug arguments of the ``p`` command. +.. _pdb-cli: + +Command-line interface +---------------------- + .. program:: pdb -You can also invoke :mod:`pdb` from the command line to debug other scripts. For +You can also invoke :mod:`!pdb` from the command line to debug other scripts. For example:: - python -m pdb [-c command] (-m module | pyfile) [args ...] + python -m pdb [-c command] (-m module | -p pid | pyfile) [args ...] When invoked as a module, pdb will automatically enter post-mortem debugging if the program being debugged exits abnormally. After post-mortem debugging (or @@ -104,6 +109,24 @@ useful than quitting the debugger upon program's exit. .. versionchanged:: 3.7 Added the ``-m`` option. +.. option:: -p, --pid + + Attach to the process with the specified PID. + + .. versionadded:: 3.14 + + +To attach to a running Python process for remote debugging, use the ``-p`` or +``--pid`` option with the target process's PID:: + + python -m pdb -p 1234 + +.. note:: + + Attaching to a process that is blocked in a system call or waiting for I/O + will only work once the next bytecode instruction is executed or when the + process receives a signal. + Typical usage to execute a statement under control of the debugger is:: >>> import pdb @@ -315,7 +338,7 @@ access further features, you have to do this yourself: .. _debugger-commands: -Debugger Commands +Debugger commands ----------------- The commands recognized by the debugger are listed below. Most commands can be diff --git a/Doc/library/pickle.rst b/Doc/library/pickle.rst index 007c9fe1b950cf..efae4910ca4358 100644 --- a/Doc/library/pickle.rst +++ b/Doc/library/pickle.rst @@ -19,7 +19,7 @@ -------------- -The :mod:`pickle` module implements binary protocols for serializing and +The :mod:`!pickle` module implements binary protocols for serializing and de-serializing a Python object structure. *"Pickling"* is the process whereby a Python object hierarchy is converted into a byte stream, and *"unpickling"* is the inverse operation, whereby a byte stream @@ -50,35 +50,22 @@ Comparison with ``marshal`` ^^^^^^^^^^^^^^^^^^^^^^^^^^^ Python has a more primitive serialization module called :mod:`marshal`, but in -general :mod:`pickle` should always be the preferred way to serialize Python +general :mod:`!pickle` should always be the preferred way to serialize Python objects. :mod:`marshal` exists primarily to support Python's :file:`.pyc` files. -The :mod:`pickle` module differs from :mod:`marshal` in several significant ways: - -* The :mod:`pickle` module keeps track of the objects it has already serialized, - so that later references to the same object won't be serialized again. - :mod:`marshal` doesn't do this. - - This has implications both for recursive objects and object sharing. Recursive - objects are objects that contain references to themselves. These are not - handled by marshal, and in fact, attempting to marshal recursive objects will - crash your Python interpreter. Object sharing happens when there are multiple - references to the same object in different places in the object hierarchy being - serialized. :mod:`pickle` stores such objects only once, and ensures that all - other references point to the master copy. Shared objects remain shared, which - can be very important for mutable objects. +The :mod:`!pickle` module differs from :mod:`marshal` in several significant ways: * :mod:`marshal` cannot be used to serialize user-defined classes and their - instances. :mod:`pickle` can save and restore class instances transparently, + instances. :mod:`!pickle` can save and restore class instances transparently, however the class definition must be importable and live in the same module as - when the object was stored. + when the object was pickled. * The :mod:`marshal` serialization format is not guaranteed to be portable across Python versions. Because its primary job in life is to support :file:`.pyc` files, the Python implementers reserve the right to change the serialization format in non-backwards compatible ways should the need arise. - The :mod:`pickle` serialization format is guaranteed to be backwards compatible + The :mod:`!pickle` serialization format is guaranteed to be backwards compatible across Python releases provided a compatible pickle protocol is chosen and pickling and unpickling code deals with Python 2 to Python 3 type differences if your data is crossing that unique breaking change language boundary. @@ -123,17 +110,17 @@ Data stream format .. index:: single: External Data Representation -The data format used by :mod:`pickle` is Python-specific. This has the +The data format used by :mod:`!pickle` is Python-specific. This has the advantage that there are no restrictions imposed by external standards such as JSON (which can't represent pointer sharing); however it means that non-Python programs may not be able to reconstruct pickled Python objects. -By default, the :mod:`pickle` data format uses a relatively compact binary +By default, the :mod:`!pickle` data format uses a relatively compact binary representation. If you need optimal size characteristics, you can efficiently :doc:`compress ` pickled data. The module :mod:`pickletools` contains tools for analyzing data streams -generated by :mod:`pickle`. :mod:`pickletools` source code has extensive +generated by :mod:`!pickle`. :mod:`pickletools` source code has extensive comments about opcodes used by pickle protocols. There are currently 6 different protocols which can be used for pickling. @@ -167,9 +154,9 @@ to read the pickle produced. .. note:: Serialization is a more primitive notion than persistence; although - :mod:`pickle` reads and writes file objects, it does not handle the issue of + :mod:`!pickle` reads and writes file objects, it does not handle the issue of naming persistent objects, nor the (even more complicated) issue of concurrent - access to persistent objects. The :mod:`pickle` module can transform a complex + access to persistent objects. The :mod:`!pickle` module can transform a complex object into a byte stream and it can transform the byte stream into an object with the same internal structure. Perhaps the most obvious thing to do with these byte streams is to write them onto a file, but it is also conceivable to @@ -186,7 +173,7 @@ Similarly, to de-serialize a data stream, you call the :func:`loads` function. However, if you want more control over serialization and de-serialization, you can create a :class:`Pickler` or an :class:`Unpickler` object, respectively. -The :mod:`pickle` module provides the following constants: +The :mod:`!pickle` module provides the following constants: .. data:: HIGHEST_PROTOCOL @@ -217,7 +204,7 @@ The :mod:`pickle` module provides the following constants: The default protocol is 5. -The :mod:`pickle` module provides the following functions to make the pickling +The :mod:`!pickle` module provides the following functions to make the pickling process more convenient: .. function:: dump(obj, file, protocol=None, *, fix_imports=True, buffer_callback=None) @@ -275,7 +262,7 @@ process more convenient: The *buffers* argument was added. -The :mod:`pickle` module defines three exceptions: +The :mod:`!pickle` module defines three exceptions: .. exception:: PickleError @@ -300,7 +287,7 @@ The :mod:`pickle` module defines three exceptions: IndexError. -The :mod:`pickle` module exports three classes, :class:`Pickler`, +The :mod:`!pickle` module exports three classes, :class:`Pickler`, :class:`Unpickler` and :class:`PickleBuffer`: .. class:: Pickler(file, protocol=None, *, fix_imports=True, buffer_callback=None) @@ -532,7 +519,7 @@ The following types can be pickled: * classes accessible from the top level of a module; -* instances of such classes whose the result of calling :meth:`~object.__getstate__` +* instances of such classes for which the result of calling :meth:`~object.__getstate__` is picklable (see section :ref:`pickle-inst` for details). Attempts to pickle unpicklable objects will raise the :exc:`PicklingError` @@ -601,7 +588,7 @@ methods: .. method:: object.__getnewargs_ex__() - In protocols 2 and newer, classes that implements the + In protocols 2 and newer, classes that implement the :meth:`__getnewargs_ex__` method can dictate the values passed to the :meth:`__new__` method upon unpickling. The method must return a pair ``(args, kwargs)`` where *args* is a tuple of positional arguments @@ -709,7 +696,10 @@ or both. If a string is returned, the string should be interpreted as the name of a global variable. It should be the object's local name relative to its module; the pickle module searches the module namespace to determine the - object's module. This behaviour is typically useful for singletons. + object's module: for a given ``obj`` to be pickled, the ``__module__`` + attribute is looked up on ``obj`` directly, which falls back to a lookup + on the type of ``obj`` if no ``__module__`` instance attribute is set. + This behaviour is typically useful for singletons. When a tuple is returned, it must be between two and six items long. Optional items can either be omitted, or ``None`` can be provided as their @@ -732,8 +722,8 @@ or both. These items will be appended to the object either using ``obj.append(item)`` or, in batch, using ``obj.extend(list_of_items)``. This is primarily used for list subclasses, but may be used by other - classes as long as they have - :ref:`append and extend methods ` with + classes as long as they have :meth:`~sequence.append` + and :meth:`~sequence.extend` methods with the appropriate signature. (Whether :meth:`!append` or :meth:`!extend` is used depends on which pickle protocol version is used as well as the number of items to append, so both must be supported.) @@ -773,13 +763,13 @@ Persistence of External Objects single: persistent_id (pickle protocol) single: persistent_load (pickle protocol) -For the benefit of object persistence, the :mod:`pickle` module supports the +For the benefit of object persistence, the :mod:`!pickle` module supports the notion of a reference to an object outside the pickled data stream. Such objects are referenced by a persistent ID, which should be either a string of alphanumeric characters (for protocol 0) [#]_ or just an arbitrary object (for any newer protocol). -The resolution of such persistent IDs is not defined by the :mod:`pickle` +The resolution of such persistent IDs is not defined by the :mod:`!pickle` module; it will delegate this resolution to the user-defined methods on the pickler and unpickler, :meth:`~Pickler.persistent_id` and :meth:`~Unpickler.persistent_load` respectively. @@ -973,10 +963,10 @@ Out-of-band Buffers .. versionadded:: 3.8 -In some contexts, the :mod:`pickle` module is used to transfer massive amounts +In some contexts, the :mod:`!pickle` module is used to transfer massive amounts of data. Therefore, it can be important to minimize the number of memory copies, to preserve performance and resource consumption. However, normal -operation of the :mod:`pickle` module, as it transforms a graph-like structure +operation of the :mod:`!pickle` module, as it transforms a graph-like structure of objects into a sequential stream of bytes, intrinsically involves copying data to and from the pickle stream. @@ -995,8 +985,8 @@ for any large data. A :class:`PickleBuffer` object *signals* that the underlying buffer is eligible for out-of-band data transfer. Those objects remain compatible -with normal usage of the :mod:`pickle` module. However, consumers can also -opt-in to tell :mod:`pickle` that they will handle those buffers by +with normal usage of the :mod:`!pickle` module. However, consumers can also +opt-in to tell :mod:`!pickle` that they will handle those buffers by themselves. Consumer API @@ -1172,7 +1162,7 @@ Performance Recent versions of the pickle protocol (from protocol 2 and upwards) feature efficient binary encodings for several common features and built-in types. -Also, the :mod:`pickle` module has a transparent optimizer written in C. +Also, the :mod:`!pickle` module has a transparent optimizer written in C. .. _pickle-example: @@ -1215,7 +1205,7 @@ The following example reads the resulting pickled data. :: Command-line interface ---------------------- -The :mod:`pickle` module can be invoked as a script from the command line, +The :mod:`!pickle` module can be invoked as a script from the command line, it will display contents of the pickle files. However, when the pickle file that you want to examine comes from an untrusted source, ``-m pickletools`` is a safer option because it does not execute pickle bytecode, see @@ -1243,7 +1233,7 @@ The following option is accepted: Tools for working with and analyzing pickled data. Module :mod:`shelve` - Indexed databases of objects; uses :mod:`pickle`. + Indexed databases of objects; uses :mod:`!pickle`. Module :mod:`copy` Shallow and deep object copying. diff --git a/Doc/library/pickletools.rst b/Doc/library/pickletools.rst index 30fc2962e0bf78..7a771ea3ab93d4 100644 --- a/Doc/library/pickletools.rst +++ b/Doc/library/pickletools.rst @@ -15,7 +15,7 @@ This module contains various constants relating to the intimate details of the few useful functions for analyzing pickled data. The contents of this module are useful for Python core developers who are working on the :mod:`pickle`; ordinary users of the :mod:`pickle` module probably won't find the -:mod:`pickletools` module relevant. +:mod:`!pickletools` module relevant. .. _pickletools-cli: diff --git a/Doc/library/pkgutil.rst b/Doc/library/pkgutil.rst index 20b8f6bcf19117..aa7dd71c1329df 100644 --- a/Doc/library/pkgutil.rst +++ b/Doc/library/pkgutil.rst @@ -69,8 +69,8 @@ support. Yield :term:`finder` objects for the given module name. - If fullname contains a ``'.'``, the finders will be for the package - containing fullname, otherwise they will be all registered top level + If *fullname* contains a ``'.'``, the finders will be for the package + containing *fullname*, otherwise they will be all registered top level finders (i.e. those on both :data:`sys.meta_path` and :data:`sys.path_hooks`). If the named module is in a package, that package is imported as a side @@ -151,24 +151,48 @@ support. :meth:`get_data ` API. The *package* argument should be the name of a package, in standard module format (``foo.bar``). The *resource* argument should be in the form of a relative - filename, using ``/`` as the path separator. The parent directory name - ``..`` is not allowed, and nor is a rooted name (starting with a ``/``). + filename, using ``/`` as the path separator. The function returns a binary string that is the contents of the specified resource. + This function uses the :term:`loader` method + :func:`~importlib.abc.FileLoader.get_data` + to support modules installed in the filesystem, but also in zip files, + databases, or elsewhere. + For packages located in the filesystem, which have already been imported, this is the rough equivalent of:: d = os.path.dirname(sys.modules[package].__file__) data = open(os.path.join(d, resource), 'rb').read() + Like the :func:`open` function, :func:`!get_data` can follow parent + directories (``../``) and absolute paths (starting with ``/`` or ``C:/``, + for example). + It can open compilation/installation artifacts like ``.py`` and ``.pyc`` + files or files with :func:`reserved filenames `. + To be compatible with non-filesystem loaders, avoid using these features. + + .. warning:: + + This function is intended for trusted input. + It does not verify that *resource* "belongs" to *package*. + + If you use a user-provided *resource* path, consider verifying it. + For example, require an alphanumeric filename with a known extension, or + install and check a list of known resources. + If the package cannot be located or loaded, or it uses a :term:`loader` which does not support :meth:`get_data `, then ``None`` is returned. In particular, the :term:`loader` for :term:`namespace packages ` does not support :meth:`get_data `. + .. seealso:: + + The :mod:`importlib.resources` module provides structured access to + module resources. .. function:: resolve_name(name) diff --git a/Doc/library/platform.rst b/Doc/library/platform.rst index 5c999054323be5..37c7cb44664ea8 100644 --- a/Doc/library/platform.rst +++ b/Doc/library/platform.rst @@ -56,6 +56,8 @@ Cross platform Returns the machine type, e.g. ``'AMD64'``. An empty string is returned if the value cannot be determined. + The output is platform-dependent and may differ in casing and naming conventions. + .. function:: node() @@ -142,6 +144,8 @@ Cross platform Returns the system's release, e.g. ``'2.2.0'`` or ``'NT'``. An empty string is returned if the value cannot be determined. + On iOS and Android, this is the user-facing OS release. To obtain the + Darwin or Linux kernel release, use :func:`os.uname`. .. function:: system() @@ -164,9 +168,6 @@ Cross platform Returns the system's release version, e.g. ``'#3 on degas'``. An empty string is returned if the value cannot be determined. - On iOS and Android, this is the user-facing OS version. To obtain the - Darwin or Linux kernel version, use :func:`os.uname`. - .. function:: uname() Fairly portable uname interface. Returns a :func:`~collections.namedtuple` @@ -176,8 +177,8 @@ Cross platform :attr:`processor` is resolved late, on demand. Note: the first two attribute names differ from the names presented by - :func:`os.uname`, where they are named :attr:`sysname` and - :attr:`nodename`. + :func:`os.uname`, where they are named :attr:`!sysname` and + :attr:`!nodename`. Entries which cannot be determined are set to ``''``. @@ -187,6 +188,14 @@ Cross platform .. versionchanged:: 3.9 :attr:`processor` is resolved late instead of immediately. +.. function:: invalidate_caches() + + Clear out the internal cache of information, such as the :func:`uname`. + This is typically useful when the platform's :func:`node` is changed + by an external process and one needs to retrieve the updated value. + + .. versionadded:: 3.14 + Java platform ------------- @@ -365,7 +374,7 @@ Android platform Command-line usage ------------------ -:mod:`platform` can also be invoked directly using the :option:`-m` +:mod:`!platform` can also be invoked directly using the :option:`-m` switch of the interpreter:: python -m platform [--terse] [--nonaliased] [{nonaliased,terse} ...] @@ -388,14 +397,3 @@ The following options are accepted: You can also pass one or more positional arguments (``terse``, ``nonaliased``) to explicitly control the output format. These behave similarly to their corresponding options. - -Miscellaneous -------------- - -.. function:: invalidate_caches() - - Clear out the internal cache of information, such as the :func:`uname`. - This is typically useful when the platform's :func:`node` is changed - by an external process and one needs to retrieve the updated value. - - .. versionadded:: 3.14 diff --git a/Doc/library/plistlib.rst b/Doc/library/plistlib.rst index 415c4b45c4f100..41802ada7e1dbb 100644 --- a/Doc/library/plistlib.rst +++ b/Doc/library/plistlib.rst @@ -184,7 +184,7 @@ Examples Generating a plist:: - import datetime + import datetime as dt import plistlib pl = dict( @@ -200,7 +200,7 @@ Generating a plist:: ), someData = b"", someMoreData = b"" * 10, - aDate = datetime.datetime.now() + aDate = dt.datetime.now() ) print(plistlib.dumps(pl).decode()) diff --git a/Doc/library/poplib.rst b/Doc/library/poplib.rst index 23f20b00e6dc6d..51ae480338ddb7 100644 --- a/Doc/library/poplib.rst +++ b/Doc/library/poplib.rst @@ -30,7 +30,7 @@ mailserver supports IMAP, you would be better off using the .. include:: ../includes/wasm-notavail.rst -The :mod:`poplib` module provides two classes: +The :mod:`!poplib` module provides two classes: .. class:: POP3(host, port=POP3_PORT[, timeout]) @@ -86,7 +86,7 @@ The :mod:`poplib` module provides two classes: .. versionchanged:: 3.12 The deprecated *keyfile* and *certfile* parameters have been removed. -One exception is defined as an attribute of the :mod:`poplib` module: +One exception is defined as an attribute of the :mod:`!poplib` module: .. exception:: error_proto diff --git a/Doc/library/posix.rst b/Doc/library/posix.rst index 14ab3e91e8a8e4..1f1ca03dfd6222 100644 --- a/Doc/library/posix.rst +++ b/Doc/library/posix.rst @@ -2,7 +2,6 @@ ==================================================== .. module:: posix - :platform: Unix :synopsis: The most common POSIX system calls (normally used via module os). -------------- @@ -17,10 +16,10 @@ interface). **Do not import this module directly.** Instead, import the module :mod:`os`, which provides a *portable* version of this interface. On Unix, the :mod:`os` -module provides a superset of the :mod:`posix` interface. On non-Unix operating -systems the :mod:`posix` module is not available, but a subset is always +module provides a superset of the :mod:`!posix` interface. On non-Unix operating +systems the :mod:`!posix` module is not available, but a subset is always available through the :mod:`os` interface. Once :mod:`os` is imported, there is -*no* performance penalty in using it instead of :mod:`posix`. In addition, +*no* performance penalty in using it instead of :mod:`!posix`. In addition, :mod:`os` provides some additional functionality, such as automatically calling :func:`~os.putenv` when an entry in ``os.environ`` is changed. @@ -67,7 +66,7 @@ Notable Module Contents ----------------------- In addition to many functions described in the :mod:`os` module documentation, -:mod:`posix` defines the following data item: +:mod:`!posix` defines the following data item: .. data:: environ @@ -91,4 +90,4 @@ In addition to many functions described in the :mod:`os` module documentation, which updates the environment on modification. Note also that updating :data:`os.environ` will render this dictionary obsolete. Use of the :mod:`os` module version of this is recommended over direct access to the - :mod:`posix` module. + :mod:`!posix` module. diff --git a/Doc/library/pprint.rst b/Doc/library/pprint.rst index 2985f31bacb47a..be942949d3ebfe 100644 --- a/Doc/library/pprint.rst +++ b/Doc/library/pprint.rst @@ -11,7 +11,7 @@ -------------- -The :mod:`pprint` module provides a capability to "pretty-print" arbitrary +The :mod:`!pprint` module provides a capability to "pretty-print" arbitrary Python data structures in a form which can be used as input to the interpreter. If the formatted structures include objects which are not fundamental Python types, the representation may not be loadable. This may be the case if objects @@ -22,8 +22,6 @@ The formatted representation keeps objects on a single line if it can, and breaks them onto multiple lines if they don't fit within the allowed width, adjustable by the *width* parameter defaulting to 80 characters. -Dictionaries are sorted by key before the display is computed. - .. versionchanged:: 3.9 Added support for pretty-printing :class:`types.SimpleNamespace`. diff --git a/Doc/library/profile.rst b/Doc/library/profile.rst index b6e51dffc40157..57f997792b85b1 100644 --- a/Doc/library/profile.rst +++ b/Doc/library/profile.rst @@ -217,14 +217,14 @@ Invoked as a script, the :mod:`pstats` module is a statistics browser for reading and examining profile dumps. It has a simple line-oriented interface (implemented using :mod:`cmd`) and interactive help. -:mod:`profile` and :mod:`cProfile` Module Reference -======================================================= +:mod:`profile` and :mod:`!cProfile` Module Reference +==================================================== .. module:: cProfile .. module:: profile :synopsis: Python source profiler. -Both the :mod:`profile` and :mod:`cProfile` modules provide the following +Both the :mod:`profile` and :mod:`!cProfile` modules provide the following functions: .. function:: run(command, filename=None, sort=-1) @@ -278,7 +278,7 @@ functions: print(s.getvalue()) The :class:`Profile` class can also be used as a context manager (supported - only in :mod:`cProfile` module. see :ref:`typecontextmanager`):: + only in :mod:`!cProfile` module. see :ref:`typecontextmanager`):: import cProfile @@ -292,11 +292,11 @@ functions: .. method:: enable() - Start collecting profiling data. Only in :mod:`cProfile`. + Start collecting profiling data. Only in :mod:`!cProfile`. .. method:: disable() - Stop collecting profiling data. Only in :mod:`cProfile`. + Stop collecting profiling data. Only in :mod:`!cProfile`. .. method:: create_stats() @@ -499,7 +499,7 @@ Analysis of the profiler data is done using the :class:`~pstats.Stats` class. significant entries. Initially, the list is taken to be the complete set of profiled functions. Each restriction is either an integer (to select a count of lines), or a decimal fraction between 0.0 and 1.0 inclusive (to - select a percentage of lines), or a string that will interpreted as a + select a percentage of lines), or a string that will be interpreted as a regular expression (to pattern match the standard name that is printed). If several restrictions are provided, then they are applied sequentially. For example:: diff --git a/Doc/library/pty.rst b/Doc/library/pty.rst index 1a44bb13a841de..9d6036d92c4cc8 100644 --- a/Doc/library/pty.rst +++ b/Doc/library/pty.rst @@ -2,7 +2,6 @@ ========================================= .. module:: pty - :platform: Unix :synopsis: Pseudo-Terminal Handling for Unix. .. moduleauthor:: Steen Lumholt @@ -12,7 +11,7 @@ -------------- -The :mod:`pty` module defines operations for handling the pseudo-terminal +The :mod:`!pty` module defines operations for handling the pseudo-terminal concept: starting another process and being able to write to and read from its controlling terminal programmatically. @@ -22,7 +21,7 @@ Pseudo-terminal handling is highly platform dependent. This code is mainly tested on Linux, FreeBSD, and macOS (it is supposed to work on other POSIX platforms but it's not been thoroughly tested). -The :mod:`pty` module defines the following functions: +The :mod:`!pty` module defines the following functions: .. function:: fork() diff --git a/Doc/library/pwd.rst b/Doc/library/pwd.rst index e1ff32912132f7..7691fed2c7cb83 100644 --- a/Doc/library/pwd.rst +++ b/Doc/library/pwd.rst @@ -2,7 +2,6 @@ ===================================== .. module:: pwd - :platform: Unix :synopsis: The password database (getpwnam() and friends). -------------- diff --git a/Doc/library/py_compile.rst b/Doc/library/py_compile.rst index 75aa739d1003b8..1cff16b6c1bf97 100644 --- a/Doc/library/py_compile.rst +++ b/Doc/library/py_compile.rst @@ -13,7 +13,7 @@ -------------- -The :mod:`py_compile` module provides a function to generate a byte-code file +The :mod:`!py_compile` module provides a function to generate a byte-code file from a source file, and another function used when the module source file is invoked as a script. diff --git a/Doc/library/pyclbr.rst b/Doc/library/pyclbr.rst index 5efb11d89dd143..40f93646af2ceb 100644 --- a/Doc/library/pyclbr.rst +++ b/Doc/library/pyclbr.rst @@ -10,7 +10,7 @@ -------------- -The :mod:`pyclbr` module provides limited information about the +The :mod:`!pyclbr` module provides limited information about the functions, classes, and methods defined in a Python-coded module. The information is sufficient to implement a module browser. The information is extracted from the Python source code rather than by diff --git a/Doc/library/pydoc.rst b/Doc/library/pydoc.rst index e8f153ee1b35ce..a59793c25159df 100644 --- a/Doc/library/pydoc.rst +++ b/Doc/library/pydoc.rst @@ -71,6 +71,11 @@ will start a HTTP server on port 1234, allowing you to browse the documentation at ``http://localhost:1234/`` in your preferred web browser. Specifying ``0`` as the port number will select an arbitrary unused port. +.. warning:: + + The :mod:`!pydoc` HTTP server is intended for local use during + development and is not suitable for production use. + :program:`python -m pydoc -n ` will start the server listening at the given hostname. By default the hostname is 'localhost' but if you want the server to be reached from other machines, you may want to change the host name that the diff --git a/Doc/library/pyexpat.rst b/Doc/library/pyexpat.rst index 2d57cff10a9278..de9130bf1560d9 100644 --- a/Doc/library/pyexpat.rst +++ b/Doc/library/pyexpat.rst @@ -16,16 +16,15 @@ references to these attributes should be marked using the :member: role. -.. warning:: +.. note:: - The :mod:`pyexpat` module is not secure against maliciously - constructed data. If you need to parse untrusted or unauthenticated data see - :ref:`xml-vulnerabilities`. + If you need to parse untrusted or unauthenticated data, see + :ref:`xml-security`. .. index:: single: Expat -The :mod:`xml.parsers.expat` module is a Python interface to the Expat +The :mod:`!xml.parsers.expat` module is a Python interface to the Expat non-validating XML parser. The module provides a single extension type, :class:`xmlparser`, that represents the current state of an XML parser. After an :class:`xmlparser` object has been created, various attributes of the object @@ -56,7 +55,7 @@ This module provides one exception and one type object: The type of the return values from the :func:`ParserCreate` function. -The :mod:`xml.parsers.expat` module contains two functions: +The :mod:`!xml.parsers.expat` module contains two functions: .. function:: ErrorString(errno) @@ -73,6 +72,13 @@ The :mod:`xml.parsers.expat` module contains two functions: *encoding* [1]_ is given it will override the implicit or explicit encoding of the document. + .. _xmlparser-non-root: + + Parsers created through :func:`!ParserCreate` are called "root" parsers, + in the sense that they do not have any parent parser attached. Non-root + parsers are created by :meth:`parser.ExternalEntityParserCreate + `. + Expat can optionally do XML namespace processing for you, enabled by providing a value for *namespace_separator*. The value must be a one-character string; a :exc:`ValueError` will be raised if the string has an illegal length (``None`` @@ -232,6 +238,111 @@ XMLParser Objects .. versionadded:: 3.13 +:class:`!xmlparser` objects have the following methods to tune protections +against some common XML vulnerabilities. + +.. method:: xmlparser.SetBillionLaughsAttackProtectionActivationThreshold(threshold, /) + + Sets the number of output bytes needed to activate protection against + `billion laughs`_ attacks. + + The number of output bytes includes amplification from entity expansion + and reading DTD files. + + Parser objects usually have a protection activation threshold of 8 MiB, + but the actual default value depends on the underlying Expat library. + + An :exc:`ExpatError` is raised if this method is called on a + |xml-non-root-parser| parser. + The corresponding :attr:`~ExpatError.lineno` and :attr:`~ExpatError.offset` + should not be used as they may have no special meaning. + + .. note:: + + Activation thresholds below 4 MiB are known to break support for DITA 1.3 + payload and are hence not recommended. + + .. versionadded:: 3.14.6 + +.. method:: xmlparser.SetBillionLaughsAttackProtectionMaximumAmplification(max_factor, /) + + Sets the maximum tolerated amplification factor for protection against + `billion laughs`_ attacks. + + The amplification factor is calculated as ``(direct + indirect) / direct`` + while parsing, where ``direct`` is the number of bytes read from + the primary document in parsing and ``indirect`` is the number of + bytes added by expanding entities and reading of external DTD files. + + The *max_factor* value must be a non-NaN :class:`float` value greater than + or equal to 1.0. Peak amplifications of factor 15,000 for the entire payload + and of factor 30,000 in the middle of parsing have been observed with small + benign files in practice. In particular, the activation threshold should be + carefully chosen to avoid false positives. + + Parser objects usually have a maximum amplification factor of 100, + but the actual default value depends on the underlying Expat library. + + An :exc:`ExpatError` is raised if this method is called on a + |xml-non-root-parser| parser or if *max_factor* is outside the valid range. + The corresponding :attr:`~ExpatError.lineno` and :attr:`~ExpatError.offset` + should not be used as they may have no special meaning. + + .. note:: + + The maximum amplification factor is only considered if the threshold + that can be adjusted by :meth:`.SetBillionLaughsAttackProtectionActivationThreshold` + is exceeded. + + .. versionadded:: 3.14.6 + +.. method:: xmlparser.SetAllocTrackerActivationThreshold(threshold, /) + + Sets the number of allocated bytes of dynamic memory needed to activate + protection against disproportionate use of RAM. + + Parser objects usually have an allocation activation threshold of 64 MiB, + but the actual default value depends on the underlying Expat library. + + An :exc:`ExpatError` is raised if this method is called on a + |xml-non-root-parser| parser. + The corresponding :attr:`~ExpatError.lineno` and :attr:`~ExpatError.offset` + should not be used as they may have no special meaning. + + .. versionadded:: 3.14.1 + +.. method:: xmlparser.SetAllocTrackerMaximumAmplification(max_factor, /) + + Sets the maximum amplification factor between direct input and bytes + of dynamic memory allocated. + + The amplification factor is calculated as ``allocated / direct`` + while parsing, where ``direct`` is the number of bytes read from + the primary document in parsing and ``allocated`` is the number + of bytes of dynamic memory allocated in the parser hierarchy. + + The *max_factor* value must be a non-NaN :class:`float` value greater than + or equal to 1.0. Amplification factors greater than 100.0 can be observed + near the start of parsing even with benign files in practice. In particular, + the activation threshold should be carefully chosen to avoid false positives. + + Parser objects usually have a maximum amplification factor of 100, + but the actual default value depends on the underlying Expat library. + + An :exc:`ExpatError` is raised if this method is called on a + |xml-non-root-parser| parser or if *max_factor* is outside the valid range. + The corresponding :attr:`~ExpatError.lineno` and :attr:`~ExpatError.offset` + should not be used as they may have no special meaning. + + .. note:: + + The maximum amplification factor is only considered if the threshold + that can be adjusted by :meth:`.SetAllocTrackerActivationThreshold` + is exceeded. + + .. versionadded:: 3.14.1 + + :class:`xmlparser` objects have the following attributes: @@ -354,7 +465,7 @@ otherwise stated. ...``). The *doctypeName* is provided exactly as presented. The *systemId* and *publicId* parameters give the system and public identifiers if specified, or ``None`` if omitted. *has_internal_subset* will be true if the document - contains and internal document declaration subset. This requires Expat version + contains an internal document declaration subset. This requires Expat version 1.2 or newer. @@ -503,6 +614,15 @@ otherwise stated. .. method:: xmlparser.ExternalEntityRefHandler(context, base, systemId, publicId) + .. warning:: + + Implementing a handler that accesses local files and/or the network + may create a vulnerability to + `external entity attacks `_ + if :class:`xmlparser` is used with user-provided XML content. + Please reflect on your `threat model `_ + before implementing this handler. + Called for references to external entities. *base* is the current base, as set by a previous call to :meth:`SetBase`. The public and system identifiers, *systemId* and *publicId*, are strings if given; if the public identifier is not @@ -619,7 +739,7 @@ values: the type, the quantifier, the name, and a tuple of children. Children are simply additional content model descriptions. The values of the first two fields are constants defined in the -:mod:`xml.parsers.expat.model` module. These constants can be collected in two +:mod:`!xml.parsers.expat.model` module. These constants can be collected in two groups: the model type group and the quantifier group. The constants in the model type group are: @@ -693,7 +813,7 @@ Expat error constants .. module:: xml.parsers.expat.errors -The following constants are provided in the :mod:`xml.parsers.expat.errors` +The following constants are provided in the :mod:`!xml.parsers.expat.errors` module. These constants are useful in interpreting some of the attributes of the :exc:`ExpatError` exception objects raised when an error has occurred. Since for backwards compatibility reasons, the constants' value is the error @@ -840,7 +960,7 @@ The ``errors`` module has the following attributes: An operation was requested that requires DTD support to be compiled in, but Expat was configured without DTD support. This should never be reported by a - standard build of the :mod:`xml.parsers.expat` module. + standard build of the :mod:`!xml.parsers.expat` module. .. data:: XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING @@ -955,3 +1075,6 @@ The ``errors`` module has the following attributes: not. See https://www.w3.org/TR/2006/REC-xml11-20060816/#NT-EncodingDecl and https://www.iana.org/assignments/character-sets/character-sets.xhtml. + +.. _billion laughs: https://en.wikipedia.org/wiki/Billion_laughs_attack +.. |xml-non-root-parser| replace:: :ref:`non-root ` diff --git a/Doc/library/python.rst b/Doc/library/python.rst index c2c231af7c3033..c5c762e11b99e5 100644 --- a/Doc/library/python.rst +++ b/Doc/library/python.rst @@ -27,3 +27,8 @@ overview: inspect.rst annotationlib.rst site.rst + +.. seealso:: + + * See the :mod:`concurrent.interpreters` module, which similarly + exposes core runtime functionality. diff --git a/Doc/library/queue.rst b/Doc/library/queue.rst index fbbebcf4ed8f92..f5326aff7236bd 100644 --- a/Doc/library/queue.rst +++ b/Doc/library/queue.rst @@ -8,7 +8,7 @@ -------------- -The :mod:`queue` module implements multi-producer, multi-consumer queues. +The :mod:`!queue` module implements multi-producer, multi-consumer queues. It is especially useful in threaded programming when information must be exchanged safely between multiple threads. The :class:`Queue` class in this module implements all the required locking semantics. @@ -30,7 +30,7 @@ In addition, the module implements a "simple" specific implementation provides additional guarantees in exchange for the smaller functionality. -The :mod:`queue` module defines the following classes and exceptions: +The :mod:`!queue` module defines the following classes and exceptions: .. class:: Queue(maxsize=0) @@ -76,6 +76,8 @@ The :mod:`queue` module defines the following classes and exceptions: Constructor for an unbounded :abbr:`FIFO (first-in, first-out)` queue. Simple queues lack advanced functionality such as task tracking. + Simple queues are :ref:`generic ` over the type of their items. + .. versionadded:: 3.7 @@ -187,9 +189,6 @@ fully processed by daemon consumer threads. processed (meaning that a :meth:`task_done` call was received for every item that had been :meth:`put` into the queue). - ``shutdown(immediate=True)`` calls :meth:`task_done` for each remaining item - in the queue. - Raises a :exc:`ValueError` if called more times than there were items placed in the queue. @@ -204,6 +203,9 @@ fully processed by daemon consumer threads. count of unfinished tasks drops to zero, :meth:`join` unblocks. +Waiting for task completion +^^^^^^^^^^^^^^^^^^^^^^^^^^^ + Example of how to wait for enqueued tasks to be completed:: import threading @@ -233,22 +235,39 @@ Example of how to wait for enqueued tasks to be completed:: Terminating queues ^^^^^^^^^^^^^^^^^^ -:class:`Queue` objects can be made to prevent further interaction by shutting -them down. +When no longer needed, :class:`Queue` objects can be wound down +until empty or terminated immediately with a hard shutdown. .. method:: Queue.shutdown(immediate=False) - Shut down the queue, making :meth:`~Queue.get` and :meth:`~Queue.put` raise - :exc:`ShutDown`. + Put a :class:`Queue` instance into a shutdown mode. + + The queue can no longer grow. + Future calls to :meth:`~Queue.put` raise :exc:`ShutDown`. + Currently blocked callers of :meth:`~Queue.put` will be unblocked + and will raise :exc:`ShutDown` in the formerly blocked thread. + + If *immediate* is false (the default), the queue can be wound + down normally with :meth:`~Queue.get` calls to extract tasks + that have already been loaded. + + And if :meth:`~Queue.task_done` is called for each remaining task, a + pending :meth:`~Queue.join` will be unblocked normally. + + Once the queue is empty, future calls to :meth:`~Queue.get` will + raise :exc:`ShutDown`. - By default, :meth:`~Queue.get` on a shut down queue will only raise once the - queue is empty. Set *immediate* to true to make :meth:`~Queue.get` raise - immediately instead. + If *immediate* is true, the queue is terminated immediately. + The queue is drained to be completely empty and the count + of unfinished tasks is reduced by the number of tasks drained. + If unfinished tasks is zero, callers of :meth:`~Queue.join` + are unblocked. Also, blocked callers of :meth:`~Queue.get` + are unblocked and will raise :exc:`ShutDown` because the + queue is empty. - All blocked callers of :meth:`~Queue.put` and :meth:`~Queue.get` will be - unblocked. If *immediate* is true, a task will be marked as done for each - remaining item in the queue, which may unblock callers of - :meth:`~Queue.join`. + Use caution when using :meth:`~Queue.join` with *immediate* set + to true. This unblocks the join even when no work has been done + on the tasks, violating the usual invariant for joining a queue. .. versionadded:: 3.13 diff --git a/Doc/library/random.rst b/Doc/library/random.rst index ef0cfb0e76cef6..9327e5a23d621a 100644 --- a/Doc/library/random.rst +++ b/Doc/library/random.rst @@ -37,7 +37,7 @@ Class :class:`Random` can also be subclassed if you want to use a different basic generator of your own devising: see the documentation on that class for more details. -The :mod:`random` module also provides the :class:`SystemRandom` class which +The :mod:`!random` module also provides the :class:`SystemRandom` class which uses the system function :func:`os.urandom` to generate random numbers from sources provided by the operating system. @@ -78,7 +78,7 @@ Bookkeeping functions instead of the system time (see the :func:`os.urandom` function for details on availability). - If *a* is an int, it is used directly. + If *a* is an int, its absolute value is used directly. With version 2 (the default), a :class:`str`, :class:`bytes`, or :class:`bytearray` object gets converted to an :class:`int` and all of its bits are used. @@ -410,7 +410,7 @@ Alternative Generator .. class:: Random([seed]) Class that implements the default pseudo-random number generator used by the - :mod:`random` module. + :mod:`!random` module. .. versionchanged:: 3.11 Formerly the *seed* could be any hashable object. Now it is limited to: @@ -447,6 +447,11 @@ Alternative Generator Override this method in subclasses to customise the :meth:`~random.getrandbits` behaviour of :class:`!Random` instances. + .. method:: Random.randbytes(n) + + Override this method in subclasses to customise the + :meth:`~random.randbytes` behaviour of :class:`!Random` instances. + .. class:: SystemRandom([seed]) @@ -628,11 +633,12 @@ These recipes show how to efficiently make random selections from the combinatoric iterators in the :mod:`itertools` module: .. testcode:: + import random - def random_product(*args, repeat=1): - "Random selection from itertools.product(*args, **kwds)" - pools = [tuple(pool) for pool in args] * repeat + def random_product(*iterables, repeat=1): + "Random selection from itertools.product(*iterables, repeat=repeat)" + pools = tuple(map(tuple, iterables)) * repeat return tuple(map(random.choice, pools)) def random_permutation(iterable, r=None): @@ -656,6 +662,91 @@ from the combinatoric iterators in the :mod:`itertools` module: indices = sorted(random.choices(range(n), k=r)) return tuple(pool[i] for i in indices) + def random_derangement(iterable): + "Choose a permutation where no element stays in its original position." + seq = tuple(iterable) + if len(seq) < 2: + if not seq: + return () + raise IndexError('No derangments to choose from') + perm = list(range(len(seq))) + start = tuple(perm) + while True: + random.shuffle(perm) + if all(p != q for p, q in zip(start, perm)): + return tuple([seq[i] for i in perm]) + +.. doctest:: + :hide: + + >>> import random + + + >>> random.seed(8675309) + >>> random_product('ABCDEFG', repeat=5) + ('D', 'B', 'E', 'F', 'E') + + + >>> random.seed(8675309) + >>> random_permutation('ABCDEFG') + ('D', 'B', 'E', 'C', 'G', 'A', 'F') + >>> random_permutation('ABCDEFG', 5) + ('A', 'G', 'D', 'C', 'B') + + + >>> random.seed(8675309) + >>> random_combination('ABCDEFG', 7) + ('A', 'B', 'C', 'D', 'E', 'F', 'G') + >>> random_combination('ABCDEFG', 6) + ('A', 'B', 'C', 'D', 'F', 'G') + >>> random_combination('ABCDEFG', 5) + ('A', 'B', 'C', 'E', 'F') + >>> random_combination('ABCDEFG', 4) + ('B', 'C', 'D', 'G') + >>> random_combination('ABCDEFG', 3) + ('B', 'E', 'G') + >>> random_combination('ABCDEFG', 2) + ('E', 'G') + >>> random_combination('ABCDEFG', 1) + ('C',) + >>> random_combination('ABCDEFG', 0) + () + + + >>> random.seed(8675309) + >>> random_combination_with_replacement('ABCDEFG', 7) + ('B', 'C', 'D', 'E', 'E', 'E', 'G') + >>> random_combination_with_replacement('ABCDEFG', 3) + ('A', 'B', 'E') + >>> random_combination_with_replacement('ABCDEFG', 2) + ('A', 'G') + >>> random_combination_with_replacement('ABCDEFG', 1) + ('E',) + >>> random_combination_with_replacement('ABCDEFG', 0) + () + + + >>> random.seed(8675309) + >>> random_derangement('') + () + >>> random_derangement('A') + Traceback (most recent call last): + ... + IndexError: No derangments to choose from + >>> random_derangement('AB') + ('B', 'A') + >>> random_derangement('ABC') + ('C', 'A', 'B') + >>> random_derangement('ABCD') + ('B', 'A', 'D', 'C') + >>> random_derangement('ABCDE') + ('B', 'C', 'A', 'E', 'D') + >>> # Identical inputs treated as distinct + >>> identical = 20 + >>> random_derangement((10, identical, 30, identical)) + (20, 30, 10, 20) + + The default :func:`.random` returns multiples of 2⁻⁵³ in the range *0.0 ≤ x < 1.0*. All such numbers are evenly spaced and are exactly representable as Python floats. However, many other representable diff --git a/Doc/library/re.rst b/Doc/library/re.rst index eb3b1e5549cc98..456d74292ef4a7 100644 --- a/Doc/library/re.rst +++ b/Doc/library/re.rst @@ -49,7 +49,7 @@ fine-tuning parameters. .. seealso:: The third-party :pypi:`regex` module, - which has an API compatible with the standard library :mod:`re` module, + which has an API compatible with the standard library :mod:`!re` module, but offers additional functionality and a more thorough Unicode support. @@ -512,8 +512,9 @@ The special characters are: *name* exists, and with ``no-pattern`` if it doesn't. ``no-pattern`` is optional and can be omitted. For example, ``(<)?(\w+@\w+(?:\.\w+)+)(?(1)>|$)`` is a poor email matching pattern, which - will match with ``''`` as well as ``'user@host.com'``, but - not with ``''``. + matches ``''`` as well as ``'user@host.com'``, but does not + match ``''`` in their entirety + (:func:`re.search` finds only ``'user@host.com'`` in the former). .. versionchanged:: 3.12 Group *id* can only contain ASCII digits. @@ -991,8 +992,8 @@ Functions That way, separator components are always found at the same relative indices within the result list. - Empty matches for the pattern split the string only when not adjacent - to a previous empty match. + Adjacent empty matches are not possible, but an empty match can occur + immediately after a non-empty match. .. code:: pycon @@ -1095,9 +1096,12 @@ Functions The optional argument *count* is the maximum number of pattern occurrences to be replaced; *count* must be a non-negative integer. If omitted or zero, all - occurrences will be replaced. Empty matches for the pattern are replaced only - when not adjacent to a previous empty match, so ``sub('x*', '-', 'abxd')`` returns - ``'-a-b--d-'``. + occurrences will be replaced. + + Adjacent empty matches are not possible, but an empty match can occur + immediately after a non-empty match. + As a result, ``sub('x*', '-', 'abxd')`` returns ``'-a-b--d-'`` + instead of ``'-a-b-d-'``. .. index:: single: \g; in regular expressions @@ -1128,8 +1132,7 @@ Functions .. versionchanged:: 3.7 Unknown escapes in *repl* consisting of ``'\'`` and an ASCII letter now are errors. - Empty matches for the pattern are replaced when adjacent to a previous - non-empty match. + An empty match can occur immediately after a non-empty match. .. versionchanged:: 3.12 Group *id* can only contain ASCII digits. @@ -1239,6 +1242,9 @@ Regular Expression Objects Compiled regular expression object returned by :func:`re.compile`. + Patterns are :ref:`generic ` over the type of string they handle + (:class:`str` or :class:`bytes`). + .. versionchanged:: 3.9 :py:class:`re.Pattern` supports ``[]`` to indicate a Unicode (str) or bytes pattern. See :ref:`types-genericalias`. @@ -1382,6 +1388,9 @@ when there is no match, you can test whether there was a match with a simple Match object returned by successful ``match``\ es and ``search``\ es. + Matches are :ref:`generic ` over the type of string which was + matched (:class:`str` or :class:`bytes`). + .. versionchanged:: 3.9 :py:class:`re.Match` supports ``[]`` to indicate a Unicode (str) or bytes match. See :ref:`types-genericalias`. @@ -1405,10 +1414,10 @@ when there is no match, you can test whether there was a match with a simple result is a single string; if there are multiple arguments, the result is a tuple with one item per argument. Without arguments, *group1* defaults to zero (the whole match is returned). If a *groupN* argument is zero, the corresponding - return value is the entire matching string; if it is in the inclusive range - [1..99], it is the string matching the corresponding parenthesized group. If a - group number is negative or larger than the number of groups defined in the - pattern, an :exc:`IndexError` exception is raised. If a group is contained in a + return value is the entire matching string; if it is a positive integer, it is + the string matching the corresponding parenthesized group. If a group number is + negative or larger than the number of groups defined in the pattern, an + :exc:`IndexError` exception is raised. If a group is contained in a part of the pattern that did not match, the corresponding result is ``None``. If a group is contained in a part of the pattern that matched multiple times, the last match is returned. :: @@ -1881,7 +1890,7 @@ successive matches:: class Token(NamedTuple): type: str - value: str + value: int | float | str line: int column: int diff --git a/Doc/library/readline.rst b/Doc/library/readline.rst index f649fce5efc377..be36f7b1b6a2ea 100644 --- a/Doc/library/readline.rst +++ b/Doc/library/readline.rst @@ -2,14 +2,13 @@ =========================================== .. module:: readline - :platform: Unix :synopsis: GNU readline support for Python. .. sectionauthor:: Skip Montanaro -------------- -The :mod:`readline` module defines a number of functions to facilitate +The :mod:`!readline` module defines a number of functions to facilitate completion and reading/writing of history files from the Python interpreter. This module can be used directly, or via the :mod:`rlcompleter` module, which supports completion of Python identifiers at the interactive prompt. Settings @@ -26,11 +25,15 @@ Readline library in general. .. include:: ../includes/wasm-mobile-notavail.rst +.. include:: ../includes/optional-module.rst + +.. availability:: Unix. + .. note:: The underlying Readline library API may be implemented by the ``editline`` (``libedit``) library instead of GNU readline. - On macOS the :mod:`readline` module detects which library is being used + On macOS the :mod:`!readline` module detects which library is being used at run time. The configuration file for ``editline`` is different from that @@ -253,7 +256,7 @@ The following functions relate to implementing a custom word completion function. This is typically operated by the Tab key, and can suggest and automatically complete a word being typed. By default, Readline is set up to be used by :mod:`rlcompleter` to complete Python identifiers for -the interactive interpreter. If the :mod:`readline` module is to be used +the interactive interpreter. If the :mod:`!readline` module is to be used with a custom completer, a different set of word delimiters should be set. @@ -322,7 +325,7 @@ with a custom completer, a different set of word delimiters should be set. Example ------- -The following example demonstrates how to use the :mod:`readline` module's +The following example demonstrates how to use the :mod:`!readline` module's history reading and writing functions to automatically load and save a history file named :file:`.python_history` from the user's home directory. The code below would normally be executed automatically during interactive sessions @@ -392,3 +395,9 @@ support history save/restore. :: def save_history(self, histfile): readline.set_history_length(1000) readline.write_history_file(histfile) + +.. note:: + + The new :term:`REPL` introduced in version 3.13 doesn't support readline. + However, readline can still be used by setting the :envvar:`PYTHON_BASIC_REPL` + environment variable. diff --git a/Doc/library/resource.rst b/Doc/library/resource.rst index 0515d205bbca0b..357686da00ca4e 100644 --- a/Doc/library/resource.rst +++ b/Doc/library/resource.rst @@ -2,7 +2,6 @@ =============================================== .. module:: resource - :platform: Unix :synopsis: An interface to provide resource usage information on the current process. .. moduleauthor:: Jeremy Hylton @@ -63,12 +62,12 @@ this module for those platforms. Sets new limits of consumption of *resource*. The *limits* argument must be a tuple ``(soft, hard)`` of two integers describing the new limits. A value of - :data:`~resource.RLIM_INFINITY` can be used to request a limit that is + :const:`~resource.RLIM_INFINITY` can be used to request a limit that is unlimited. Raises :exc:`ValueError` if an invalid resource is specified, if the new soft limit exceeds the hard limit, or if a process tries to raise its hard limit. - Specifying a limit of :data:`~resource.RLIM_INFINITY` when the hard or + Specifying a limit of :const:`~resource.RLIM_INFINITY` when the hard or system limit for that resource is not unlimited will result in a :exc:`ValueError`. A process with the effective UID of super-user can request any valid limit value, including unlimited, but :exc:`ValueError` @@ -78,7 +77,7 @@ this module for those platforms. ``setrlimit`` may also raise :exc:`error` if the underlying system call fails. - VxWorks only supports setting :data:`RLIMIT_NOFILE`. + VxWorks only supports setting :const:`RLIMIT_NOFILE`. .. audit-event:: resource.setrlimit resource,limits resource.setrlimit @@ -127,7 +126,7 @@ platform. .. data:: RLIMIT_CPU The maximum amount of processor time (in seconds) that a process can use. If - this limit is exceeded, a :const:`SIGXCPU` signal is sent to the process. (See + this limit is exceeded, a :const:`~signal.SIGXCPU` signal is sent to the process. (See the :mod:`signal` module documentation for information about how to catch this signal and do something useful, e.g. flush open files to disk.) @@ -176,8 +175,9 @@ platform. .. data:: RLIMIT_VMEM The largest area of mapped memory which the process may occupy. + Usually an alias of :const:`RLIMIT_AS`. - .. availability:: FreeBSD >= 11. + .. availability:: Solaris, FreeBSD, NetBSD. .. data:: RLIMIT_AS @@ -230,16 +230,18 @@ platform. .. versionadded:: 3.4 + .. data:: RLIMIT_SBSIZE The maximum size (in bytes) of socket buffer usage for this user. This limits the amount of network memory, and hence the amount of mbufs, that this user may hold at any time. - .. availability:: FreeBSD. + .. availability:: FreeBSD, NetBSD. .. versionadded:: 3.4 + .. data:: RLIMIT_SWAP The maximum size (in bytes) of the swap space that may be reserved or @@ -249,18 +251,20 @@ platform. `tuning(7) `__ for a complete description of this sysctl. - .. availability:: FreeBSD. + .. availability:: FreeBSD >= 8. .. versionadded:: 3.4 + .. data:: RLIMIT_NPTS The maximum number of pseudo-terminals created by this user id. - .. availability:: FreeBSD. + .. availability:: FreeBSD >= 8. .. versionadded:: 3.4 + .. data:: RLIMIT_KQUEUES The maximum number of kqueues this user id is allowed to create. @@ -269,6 +273,7 @@ platform. .. versionadded:: 3.10 + Resource Usage -------------- @@ -297,54 +302,54 @@ These functions are used to retrieve resource usage information: print(getrusage(RUSAGE_SELF)) The fields of the return value each describe how a particular system resource - has been used, e.g. amount of time spent running is user mode or number of times + has been used, e.g. amount of time spent running in user mode or number of times the process was swapped out of main memory. Some values are dependent on the - clock tick internal, e.g. the amount of memory the process is using. + clock tick interval, e.g. the amount of memory the process is using. For backward compatibility, the return value is also accessible as a tuple of 16 elements. - The fields :attr:`ru_utime` and :attr:`ru_stime` of the return value are + The fields :attr:`!ru_utime` and :attr:`!ru_stime` of the return value are floating-point values representing the amount of time spent executing in user mode and the amount of time spent executing in system mode, respectively. The remaining values are integers. Consult the :manpage:`getrusage(2)` man page for detailed information about these values. A brief summary is presented here: - +--------+---------------------+---------------------------------------+ - | Index | Field | Resource | - +========+=====================+=======================================+ - | ``0`` | :attr:`ru_utime` | time in user mode (float seconds) | - +--------+---------------------+---------------------------------------+ - | ``1`` | :attr:`ru_stime` | time in system mode (float seconds) | - +--------+---------------------+---------------------------------------+ - | ``2`` | :attr:`ru_maxrss` | maximum resident set size | - +--------+---------------------+---------------------------------------+ - | ``3`` | :attr:`ru_ixrss` | shared memory size | - +--------+---------------------+---------------------------------------+ - | ``4`` | :attr:`ru_idrss` | unshared memory size | - +--------+---------------------+---------------------------------------+ - | ``5`` | :attr:`ru_isrss` | unshared stack size | - +--------+---------------------+---------------------------------------+ - | ``6`` | :attr:`ru_minflt` | page faults not requiring I/O | - +--------+---------------------+---------------------------------------+ - | ``7`` | :attr:`ru_majflt` | page faults requiring I/O | - +--------+---------------------+---------------------------------------+ - | ``8`` | :attr:`ru_nswap` | number of swap outs | - +--------+---------------------+---------------------------------------+ - | ``9`` | :attr:`ru_inblock` | block input operations | - +--------+---------------------+---------------------------------------+ - | ``10`` | :attr:`ru_oublock` | block output operations | - +--------+---------------------+---------------------------------------+ - | ``11`` | :attr:`ru_msgsnd` | messages sent | - +--------+---------------------+---------------------------------------+ - | ``12`` | :attr:`ru_msgrcv` | messages received | - +--------+---------------------+---------------------------------------+ - | ``13`` | :attr:`ru_nsignals` | signals received | - +--------+---------------------+---------------------------------------+ - | ``14`` | :attr:`ru_nvcsw` | voluntary context switches | - +--------+---------------------+---------------------------------------+ - | ``15`` | :attr:`ru_nivcsw` | involuntary context switches | - +--------+---------------------+---------------------------------------+ + +--------+----------------------+---------------------------------------+ + | Index | Field | Resource | + +========+======================+=======================================+ + | ``0`` | :attr:`!ru_utime` | time in user mode (float seconds) | + +--------+----------------------+---------------------------------------+ + | ``1`` | :attr:`!ru_stime` | time in system mode (float seconds) | + +--------+----------------------+---------------------------------------+ + | ``2`` | :attr:`!ru_maxrss` | maximum resident set size | + +--------+----------------------+---------------------------------------+ + | ``3`` | :attr:`!ru_ixrss` | shared memory size | + +--------+----------------------+---------------------------------------+ + | ``4`` | :attr:`!ru_idrss` | unshared memory size | + +--------+----------------------+---------------------------------------+ + | ``5`` | :attr:`!ru_isrss` | unshared stack size | + +--------+----------------------+---------------------------------------+ + | ``6`` | :attr:`!ru_minflt` | page faults not requiring I/O | + +--------+----------------------+---------------------------------------+ + | ``7`` | :attr:`!ru_majflt` | page faults requiring I/O | + +--------+----------------------+---------------------------------------+ + | ``8`` | :attr:`!ru_nswap` | number of swap outs | + +--------+----------------------+---------------------------------------+ + | ``9`` | :attr:`!ru_inblock` | block input operations | + +--------+----------------------+---------------------------------------+ + | ``10`` | :attr:`!ru_oublock` | block output operations | + +--------+----------------------+---------------------------------------+ + | ``11`` | :attr:`!ru_msgsnd` | messages sent | + +--------+----------------------+---------------------------------------+ + | ``12`` | :attr:`!ru_msgrcv` | messages received | + +--------+----------------------+---------------------------------------+ + | ``13`` | :attr:`!ru_nsignals` | signals received | + +--------+----------------------+---------------------------------------+ + | ``14`` | :attr:`!ru_nvcsw` | voluntary context switches | + +--------+----------------------+---------------------------------------+ + | ``15`` | :attr:`!ru_nivcsw` | involuntary context switches | + +--------+----------------------+---------------------------------------+ This function will raise a :exc:`ValueError` if an invalid *who* parameter is specified. It may also raise :exc:`error` exception in unusual circumstances. diff --git a/Doc/library/runpy.rst b/Doc/library/runpy.rst index b07ec6e93f80ab..2e8081f3bf0d61 100644 --- a/Doc/library/runpy.rst +++ b/Doc/library/runpy.rst @@ -10,7 +10,7 @@ -------------- -The :mod:`runpy` module is used to locate and run Python modules without +The :mod:`!runpy` module is used to locate and run Python modules without importing them first. Its main use is to implement the :option:`-m` command line switch that allows scripts to be located using the Python module namespace rather than the filesystem. @@ -20,11 +20,11 @@ current process, and any side effects (such as cached imports of other modules) will remain in place after the functions have returned. Furthermore, any functions and classes defined by the executed code are not -guaranteed to work correctly after a :mod:`runpy` function has returned. +guaranteed to work correctly after a :mod:`!runpy` function has returned. If that limitation is not acceptable for a given use case, :mod:`importlib` is likely to be a more suitable choice than this module. -The :mod:`runpy` module provides two functions: +The :mod:`!runpy` module provides two functions: .. function:: run_module(mod_name, init_globals=None, run_name=None, alter_sys=False) diff --git a/Doc/library/sched.rst b/Doc/library/sched.rst index 517dbe8c321898..302231d95f8979 100644 --- a/Doc/library/sched.rst +++ b/Doc/library/sched.rst @@ -12,7 +12,7 @@ -------------- -The :mod:`sched` module defines a class which implements a general purpose event +The :mod:`!sched` module defines a class which implements a general purpose event scheduler: .. class:: scheduler(timefunc=time.monotonic, delayfunc=time.sleep) @@ -119,9 +119,11 @@ Scheduler Objects function passed to the constructor) for the next event, then execute it and so on until there are no more scheduled events. - If *blocking* is false executes the scheduled events due to expire soonest - (if any) and then return the deadline of the next scheduled call in the - scheduler (if any). + If *blocking* is false, immediately executes all events in the queue which have + a time value less than or equal to the current *timefunc* value (if any) and + returns the difference between the current *timefunc* value and the time value + of the next scheduled event in the scheduler's event queue. If the queue is + empty, returns ``None``. Either *action* or *delayfunc* can raise an exception. In either case, the scheduler will maintain a consistent state and propagate the exception. If an diff --git a/Doc/library/secrets.rst b/Doc/library/secrets.rst index 75dafc54d40ca5..6d708d1f713f9d 100644 --- a/Doc/library/secrets.rst +++ b/Doc/library/secrets.rst @@ -17,11 +17,11 @@ ------------- -The :mod:`secrets` module is used for generating cryptographically strong +The :mod:`!secrets` module is used for generating cryptographically strong random numbers suitable for managing data such as passwords, account authentication, security tokens, and related secrets. -In particular, :mod:`secrets` should be used in preference to the +In particular, :mod:`!secrets` should be used in preference to the default pseudo-random number generator in the :mod:`random` module, which is designed for modelling and simulation, not security or cryptography. @@ -33,7 +33,7 @@ is designed for modelling and simulation, not security or cryptography. Random numbers -------------- -The :mod:`secrets` module provides access to the most secure source of +The :mod:`!secrets` module provides access to the most secure source of randomness that your operating system provides. .. class:: SystemRandom @@ -58,43 +58,48 @@ randomness that your operating system provides. Generating tokens ----------------- -The :mod:`secrets` module provides functions for generating secure +The :mod:`!secrets` module provides functions for generating secure tokens, suitable for applications such as password resets, hard-to-guess URLs, and similar. -.. function:: token_bytes([nbytes=None]) +.. function:: token_bytes(nbytes=None) Return a random byte string containing *nbytes* number of bytes. - If *nbytes* is ``None`` or not supplied, a reasonable default is - used. + + If *nbytes* is not specified or ``None``, :const:`DEFAULT_ENTROPY` + is used instead. .. doctest:: - >>> token_bytes(16) #doctest:+SKIP + >>> token_bytes(16) # doctest: +SKIP b'\xebr\x17D*t\xae\xd4\xe3S\xb6\xe2\xebP1\x8b' -.. function:: token_hex([nbytes=None]) +.. function:: token_hex(nbytes=None) Return a random text string, in hexadecimal. The string has *nbytes* - random bytes, each byte converted to two hex digits. If *nbytes* is - ``None`` or not supplied, a reasonable default is used. + random bytes, each byte converted to two hex digits. + + If *nbytes* is not specified or ``None``, :const:`DEFAULT_ENTROPY` + is used instead. .. doctest:: - >>> token_hex(16) #doctest:+SKIP + >>> token_hex(16) # doctest: +SKIP 'f9bf78b9a18ce6d46a0cd2b0b86df9da' -.. function:: token_urlsafe([nbytes=None]) +.. function:: token_urlsafe(nbytes=None) Return a random URL-safe text string, containing *nbytes* random bytes. The text is Base64 encoded, so on average each byte results - in approximately 1.3 characters. If *nbytes* is ``None`` or not - supplied, a reasonable default is used. + in approximately 1.3 characters. + + If *nbytes* is not specified or ``None``, :const:`DEFAULT_ENTROPY` + is used instead. .. doctest:: - >>> token_urlsafe(16) #doctest:+SKIP + >>> token_urlsafe(16) # doctest: +SKIP 'Drmhze6EPcv0fN_81Bj-nA' @@ -107,7 +112,7 @@ tokens need to have sufficient randomness. Unfortunately, what is considered sufficient will necessarily increase as computers get more powerful and able to make more guesses in a shorter period. As of 2015, it is believed that 32 bytes (256 bits) of randomness is sufficient for -the typical use-case expected for the :mod:`secrets` module. +the typical use-case expected for the :mod:`!secrets` module. For those who want to manage their own token length, you can explicitly specify how much randomness is used for tokens by giving an :class:`int` @@ -115,11 +120,13 @@ argument to the various ``token_*`` functions. That argument is taken as the number of bytes of randomness to use. Otherwise, if no argument is provided, or if the argument is ``None``, -the ``token_*`` functions will use a reasonable default instead. +the ``token_*`` functions use :const:`DEFAULT_ENTROPY` instead. -.. note:: +.. data:: DEFAULT_ENTROPY + + Default number of bytes of randomness used by the ``token_*`` functions. - That default is subject to change at any time, including during + The exact value is subject to change at any time, including during maintenance releases. @@ -132,14 +139,14 @@ Other functions :term:`bytes-like objects ` *a* and *b* are equal, otherwise ``False``, using a "constant-time compare" to reduce the risk of - `timing attacks `_. + `timing attacks `__. See :func:`hmac.compare_digest` for additional details. Recipes and best practices -------------------------- -This section shows recipes and best practices for using :mod:`secrets` +This section shows recipes and best practices for using :mod:`!secrets` to manage a basic level of security. Generate an eight-character alphanumeric password: diff --git a/Doc/library/security_warnings.rst b/Doc/library/security_warnings.rst index a573c98f73eb0a..70c359cc1c0fc3 100644 --- a/Doc/library/security_warnings.rst +++ b/Doc/library/security_warnings.rst @@ -28,7 +28,7 @@ The following modules have specific security considerations: ` * :mod:`tempfile`: :ref:`mktemp is deprecated due to vulnerability to race conditions ` -* :mod:`xml`: :ref:`XML vulnerabilities ` +* :mod:`xml`: :ref:`XML security ` * :mod:`zipfile`: :ref:`maliciously prepared .zip files can cause disk volume exhaustion ` diff --git a/Doc/library/select.rst b/Doc/library/select.rst index d2094283d54736..3c72c2d59150c9 100644 --- a/Doc/library/select.rst +++ b/Doc/library/select.rst @@ -18,7 +18,7 @@ it was last read. .. note:: The :mod:`selectors` module allows high-level and efficient I/O - multiplexing, built upon the :mod:`select` module primitives. Users are + multiplexing, built upon the :mod:`!select` module primitives. Users are encouraged to use the :mod:`selectors` module instead, unless they want precise control over the OS-level primitives used. @@ -37,7 +37,7 @@ The module defines the following: .. function:: devpoll() - (Only supported on Solaris and derivatives.) Returns a ``/dev/poll`` + Returns a ``/dev/poll`` polling object; see section :ref:`devpoll-objects` below for the methods supported by devpoll objects. @@ -54,9 +54,11 @@ The module defines the following: .. versionchanged:: 3.4 The new file descriptor is now non-inheritable. + .. availability:: Solaris. + .. function:: epoll(sizehint=-1, flags=0) - (Only supported on Linux 2.5.44 and newer.) Return an edge polling object, + Return an edge polling object, which can be used as Edge or Level Triggered interface for I/O events. @@ -89,18 +91,22 @@ The module defines the following: The *flags* parameter. ``select.EPOLL_CLOEXEC`` is used by default now. Use :func:`os.set_inheritable` to make the file descriptor inheritable. + .. availability:: Linux >= 2.5.44. + .. function:: poll() - (Not supported by all operating systems.) Returns a polling object, which + Returns a polling object, which supports registering and unregistering file descriptors, and then polling them for I/O events; see section :ref:`poll-objects` below for the methods supported by polling objects. + .. availability:: Unix. + .. function:: kqueue() - (Only supported on BSD.) Returns a kernel queue object; see section + Returns a kernel queue object; see section :ref:`kqueue-objects` below for the methods supported by kqueue objects. The new file descriptor is :ref:`non-inheritable `. @@ -108,14 +114,18 @@ The module defines the following: .. versionchanged:: 3.4 The new file descriptor is now non-inheritable. + .. availability:: BSD, macOS. + .. function:: kevent(ident, filter=KQ_FILTER_READ, flags=KQ_EV_ADD, fflags=0, data=0, udata=0) - (Only supported on BSD.) Returns a kernel event object; see section + Returns a kernel event object; see section :ref:`kevent-objects` below for the methods supported by kevent objects. + .. availability:: BSD, macOS. + -.. function:: select(rlist, wlist, xlist[, timeout]) +.. function:: select(rlist, wlist, xlist, timeout=None) This is a straightforward interface to the Unix :c:func:`!select` system call. The first three arguments are iterables of 'waitable objects': either @@ -130,7 +140,8 @@ The module defines the following: Empty iterables are allowed, but acceptance of three empty iterables is platform-dependent. (It is known to work on Unix but not on Windows.) The optional *timeout* argument specifies a time-out as a floating-point number - in seconds. When the *timeout* argument is omitted the function blocks until + in seconds. + When the *timeout* argument is omitted or ``None``, the function blocks until at least one file descriptor is ready. A time-out value of zero specifies a poll and never blocks. @@ -170,7 +181,7 @@ The module defines the following: The minimum number of bytes which can be written without blocking to a pipe when the pipe has been reported as ready for writing by :func:`~select.select`, :func:`!poll` or another interface in this module. This doesn't apply - to other kind of file-like objects such as sockets. + to other kinds of file-like objects such as sockets. This value is guaranteed by POSIX to be at least 512. @@ -181,7 +192,7 @@ The module defines the following: .. _devpoll-objects: -``/dev/poll`` Polling Objects +``/dev/poll`` polling objects ----------------------------- Solaris and derivatives have ``/dev/poll``. While :c:func:`!select` is @@ -222,7 +233,7 @@ object. implement :meth:`!fileno`, so they can also be used as the argument. *eventmask* is an optional bitmask describing the type of events you want to - check for. The constants are the same that with :c:func:`!poll` + check for. The constants are the same as with :c:func:`!poll` object. The default value is a combination of the constants :const:`POLLIN`, :const:`POLLPRI`, and :const:`POLLOUT`. @@ -237,7 +248,7 @@ object. .. method:: devpoll.modify(fd[, eventmask]) This method does an :meth:`unregister` followed by a - :meth:`register`. It is (a bit) more efficient that doing the same + :meth:`register`. It is (a bit) more efficient than doing the same explicitly. @@ -273,52 +284,52 @@ object. .. _epoll-objects: -Edge and Level Trigger Polling (epoll) Objects +Edge and level trigger polling (epoll) objects ---------------------------------------------- https://linux.die.net/man/4/epoll - *eventmask* - - +-------------------------+-----------------------------------------------+ - | Constant | Meaning | - +=========================+===============================================+ - | :const:`EPOLLIN` | Available for read | - +-------------------------+-----------------------------------------------+ - | :const:`EPOLLOUT` | Available for write | - +-------------------------+-----------------------------------------------+ - | :const:`EPOLLPRI` | Urgent data for read | - +-------------------------+-----------------------------------------------+ - | :const:`EPOLLERR` | Error condition happened on the assoc. fd | - +-------------------------+-----------------------------------------------+ - | :const:`EPOLLHUP` | Hang up happened on the assoc. fd | - +-------------------------+-----------------------------------------------+ - | :const:`EPOLLET` | Set Edge Trigger behavior, the default is | - | | Level Trigger behavior | - +-------------------------+-----------------------------------------------+ - | :const:`EPOLLONESHOT` | Set one-shot behavior. After one event is | - | | pulled out, the fd is internally disabled | - +-------------------------+-----------------------------------------------+ - | :const:`EPOLLEXCLUSIVE` | Wake only one epoll object when the | - | | associated fd has an event. The default (if | - | | this flag is not set) is to wake all epoll | - | | objects polling on a fd. | - +-------------------------+-----------------------------------------------+ - | :const:`EPOLLRDHUP` | Stream socket peer closed connection or shut | - | | down writing half of connection. | - +-------------------------+-----------------------------------------------+ - | :const:`EPOLLRDNORM` | Equivalent to :const:`EPOLLIN` | - +-------------------------+-----------------------------------------------+ - | :const:`EPOLLRDBAND` | Priority data band can be read. | - +-------------------------+-----------------------------------------------+ - | :const:`EPOLLWRNORM` | Equivalent to :const:`EPOLLOUT` | - +-------------------------+-----------------------------------------------+ - | :const:`EPOLLWRBAND` | Priority data may be written. | - +-------------------------+-----------------------------------------------+ - | :const:`EPOLLMSG` | Ignored. | - +-------------------------+-----------------------------------------------+ - | :const:`EPOLLWAKEUP` | Prevents sleep during event waiting. | - +-------------------------+-----------------------------------------------+ + The *eventmask* is a bit mask using the following constants: + + +-------------------------+------------------------------------------------+ + | Constant | Meaning | + +=========================+================================================+ + | :const:`EPOLLIN` | Available for read. | + +-------------------------+------------------------------------------------+ + | :const:`EPOLLOUT` | Available for write. | + +-------------------------+------------------------------------------------+ + | :const:`EPOLLPRI` | Urgent data for read. | + +-------------------------+------------------------------------------------+ + | :const:`EPOLLERR` | Error condition happened on the associated fd. | + +-------------------------+------------------------------------------------+ + | :const:`EPOLLHUP` | Hang up happened on the associated fd. | + +-------------------------+------------------------------------------------+ + | :const:`EPOLLET` | Set Edge Trigger behavior, the default is | + | | Level Trigger behavior. | + +-------------------------+------------------------------------------------+ + | :const:`EPOLLONESHOT` | Set one-shot behavior. After one event is | + | | pulled out, the fd is internally disabled. | + +-------------------------+------------------------------------------------+ + | :const:`EPOLLEXCLUSIVE` | Wake only one epoll object when the | + | | associated fd has an event. The default (if | + | | this flag is not set) is to wake all epoll | + | | objects polling on an fd. | + +-------------------------+------------------------------------------------+ + | :const:`EPOLLRDHUP` | Stream socket peer closed connection or shut | + | | down writing half of connection. | + +-------------------------+------------------------------------------------+ + | :const:`EPOLLRDNORM` | Equivalent to :const:`EPOLLIN` | + +-------------------------+------------------------------------------------+ + | :const:`EPOLLRDBAND` | Priority data band can be read. | + +-------------------------+------------------------------------------------+ + | :const:`EPOLLWRNORM` | Equivalent to :const:`EPOLLOUT`. | + +-------------------------+------------------------------------------------+ + | :const:`EPOLLWRBAND` | Priority data may be written. | + +-------------------------+------------------------------------------------+ + | :const:`EPOLLMSG` | Ignored. | + +-------------------------+------------------------------------------------+ + | :const:`EPOLLWAKEUP` | Prevents sleep during event waiting. | + +-------------------------+------------------------------------------------+ .. versionadded:: 3.6 :const:`EPOLLEXCLUSIVE` was added. It's only supported by Linux Kernel 4.5 @@ -350,12 +361,12 @@ Edge and Level Trigger Polling (epoll) Objects .. method:: epoll.register(fd[, eventmask]) - Register a fd descriptor with the epoll object. + Register a file descriptor *fd* with the epoll object. .. method:: epoll.modify(fd, eventmask) - Modify a registered file descriptor. + Modify a registered file descriptor *fd*. .. method:: epoll.unregister(fd) @@ -379,7 +390,7 @@ Edge and Level Trigger Polling (epoll) Objects .. _poll-objects: -Polling Objects +Polling objects --------------- The :c:func:`!poll` system call, supported on most Unix systems, provides better @@ -404,24 +415,24 @@ linearly scanned again. :c:func:`!select` is *O*\ (*highest file descriptor*), w :const:`POLLPRI`, and :const:`POLLOUT`, described in the table below. If not specified, the default value used will check for all 3 types of events. - +-------------------+------------------------------------------+ - | Constant | Meaning | - +===================+==========================================+ - | :const:`POLLIN` | There is data to read | - +-------------------+------------------------------------------+ - | :const:`POLLPRI` | There is urgent data to read | - +-------------------+------------------------------------------+ - | :const:`POLLOUT` | Ready for output: writing will not block | - +-------------------+------------------------------------------+ - | :const:`POLLERR` | Error condition of some sort | - +-------------------+------------------------------------------+ - | :const:`POLLHUP` | Hung up | - +-------------------+------------------------------------------+ - | :const:`POLLRDHUP`| Stream socket peer closed connection, or | - | | shut down writing half of connection | - +-------------------+------------------------------------------+ - | :const:`POLLNVAL` | Invalid request: descriptor not open | - +-------------------+------------------------------------------+ + +-------------------+-------------------------------------------+ + | Constant | Meaning | + +===================+===========================================+ + | :const:`POLLIN` | There is data to read. | + +-------------------+-------------------------------------------+ + | :const:`POLLPRI` | There is urgent data to read. | + +-------------------+-------------------------------------------+ + | :const:`POLLOUT` | Ready for output: writing will not block. | + +-------------------+-------------------------------------------+ + | :const:`POLLERR` | Error condition of some sort. | + +-------------------+-------------------------------------------+ + | :const:`POLLHUP` | Hung up. | + +-------------------+-------------------------------------------+ + | :const:`POLLRDHUP`| Stream socket peer closed connection, or | + | | shut down writing half of connection. | + +-------------------+-------------------------------------------+ + | :const:`POLLNVAL` | Invalid request: descriptor not open. | + +-------------------+-------------------------------------------+ Registering a file descriptor that's already registered is not an error, and has the same effect as registering the descriptor exactly once. @@ -467,7 +478,7 @@ linearly scanned again. :c:func:`!select` is *O*\ (*highest file descriptor*), w .. _kqueue-objects: -Kqueue Objects +Kqueue objects -------------- .. method:: kqueue.close() @@ -508,7 +519,7 @@ Kqueue Objects .. _kevent-objects: -Kevent Objects +Kevent objects -------------- https://man.freebsd.org/cgi/man.cgi?query=kqueue&sektion=2 @@ -528,66 +539,66 @@ https://man.freebsd.org/cgi/man.cgi?query=kqueue&sektion=2 | Constant | Meaning | +===========================+=============================================+ | :const:`KQ_FILTER_READ` | Takes a descriptor and returns whenever | - | | there is data available to read | + | | there is data available to read. | +---------------------------+---------------------------------------------+ | :const:`KQ_FILTER_WRITE` | Takes a descriptor and returns whenever | - | | there is data available to write | + | | there is data available to write. | +---------------------------+---------------------------------------------+ - | :const:`KQ_FILTER_AIO` | AIO requests | + | :const:`KQ_FILTER_AIO` | AIO requests. | +---------------------------+---------------------------------------------+ | :const:`KQ_FILTER_VNODE` | Returns when one or more of the requested | - | | events watched in *fflag* occurs | + | | events watched in *fflag* occurs. | +---------------------------+---------------------------------------------+ - | :const:`KQ_FILTER_PROC` | Watch for events on a process id | + | :const:`KQ_FILTER_PROC` | Watch for events on a process ID. | +---------------------------+---------------------------------------------+ | :const:`KQ_FILTER_NETDEV` | Watch for events on a network device | - | | [not available on macOS] | + | | (not available on macOS). | +---------------------------+---------------------------------------------+ | :const:`KQ_FILTER_SIGNAL` | Returns whenever the watched signal is | - | | delivered to the process | + | | delivered to the process. | +---------------------------+---------------------------------------------+ - | :const:`KQ_FILTER_TIMER` | Establishes an arbitrary timer | + | :const:`KQ_FILTER_TIMER` | Establishes an arbitrary timer. | +---------------------------+---------------------------------------------+ .. attribute:: kevent.flags Filter action. - +---------------------------+---------------------------------------------+ - | Constant | Meaning | - +===========================+=============================================+ - | :const:`KQ_EV_ADD` | Adds or modifies an event | - +---------------------------+---------------------------------------------+ - | :const:`KQ_EV_DELETE` | Removes an event from the queue | - +---------------------------+---------------------------------------------+ - | :const:`KQ_EV_ENABLE` | Permitscontrol() to returns the event | - +---------------------------+---------------------------------------------+ - | :const:`KQ_EV_DISABLE` | Disablesevent | - +---------------------------+---------------------------------------------+ - | :const:`KQ_EV_ONESHOT` | Removes event after first occurrence | - +---------------------------+---------------------------------------------+ - | :const:`KQ_EV_CLEAR` | Reset the state after an event is retrieved | - +---------------------------+---------------------------------------------+ - | :const:`KQ_EV_SYSFLAGS` | internal event | - +---------------------------+---------------------------------------------+ - | :const:`KQ_EV_FLAG1` | internal event | - +---------------------------+---------------------------------------------+ - | :const:`KQ_EV_EOF` | Filter specific EOF condition | - +---------------------------+---------------------------------------------+ - | :const:`KQ_EV_ERROR` | See return values | - +---------------------------+---------------------------------------------+ + +---------------------------+----------------------------------------------+ + | Constant | Meaning | + +===========================+==============================================+ + | :const:`KQ_EV_ADD` | Adds or modifies an event. | + +---------------------------+----------------------------------------------+ + | :const:`KQ_EV_DELETE` | Removes an event from the queue. | + +---------------------------+----------------------------------------------+ + | :const:`KQ_EV_ENABLE` | Permits control() to return the event. | + +---------------------------+----------------------------------------------+ + | :const:`KQ_EV_DISABLE` | Disables event. | + +---------------------------+----------------------------------------------+ + | :const:`KQ_EV_ONESHOT` | Removes event after first occurrence. | + +---------------------------+----------------------------------------------+ + | :const:`KQ_EV_CLEAR` | Reset the state after an event is retrieved. | + +---------------------------+----------------------------------------------+ + | :const:`KQ_EV_SYSFLAGS` | Internal event. | + +---------------------------+----------------------------------------------+ + | :const:`KQ_EV_FLAG1` | Internal event. | + +---------------------------+----------------------------------------------+ + | :const:`KQ_EV_EOF` | Filter-specific EOF condition. | + +---------------------------+----------------------------------------------+ + | :const:`KQ_EV_ERROR` | See return values. | + +---------------------------+----------------------------------------------+ .. attribute:: kevent.fflags - Filter specific flags. + Filter-specific flags. :const:`KQ_FILTER_READ` and :const:`KQ_FILTER_WRITE` filter flags: +----------------------------+--------------------------------------------+ | Constant | Meaning | +============================+============================================+ - | :const:`KQ_NOTE_LOWAT` | low water mark of a socket buffer | + | :const:`KQ_NOTE_LOWAT` | Low water mark of a socket buffer. | +----------------------------+--------------------------------------------+ :const:`KQ_FILTER_VNODE` filter flags: @@ -595,19 +606,19 @@ https://man.freebsd.org/cgi/man.cgi?query=kqueue&sektion=2 +----------------------------+--------------------------------------------+ | Constant | Meaning | +============================+============================================+ - | :const:`KQ_NOTE_DELETE` | *unlink()* was called | + | :const:`KQ_NOTE_DELETE` | *unlink()* was called. | +----------------------------+--------------------------------------------+ - | :const:`KQ_NOTE_WRITE` | a write occurred | + | :const:`KQ_NOTE_WRITE` | A write occurred. | +----------------------------+--------------------------------------------+ - | :const:`KQ_NOTE_EXTEND` | the file was extended | + | :const:`KQ_NOTE_EXTEND` | The file was extended. | +----------------------------+--------------------------------------------+ - | :const:`KQ_NOTE_ATTRIB` | an attribute was changed | + | :const:`KQ_NOTE_ATTRIB` | An attribute was changed. | +----------------------------+--------------------------------------------+ - | :const:`KQ_NOTE_LINK` | the link count has changed | + | :const:`KQ_NOTE_LINK` | The link count has changed. | +----------------------------+--------------------------------------------+ - | :const:`KQ_NOTE_RENAME` | the file was renamed | + | :const:`KQ_NOTE_RENAME` | The file was renamed. | +----------------------------+--------------------------------------------+ - | :const:`KQ_NOTE_REVOKE` | access to the file was revoked | + | :const:`KQ_NOTE_REVOKE` | Access to the file was revoked. | +----------------------------+--------------------------------------------+ :const:`KQ_FILTER_PROC` filter flags: @@ -615,22 +626,22 @@ https://man.freebsd.org/cgi/man.cgi?query=kqueue&sektion=2 +----------------------------+--------------------------------------------+ | Constant | Meaning | +============================+============================================+ - | :const:`KQ_NOTE_EXIT` | the process has exited | + | :const:`KQ_NOTE_EXIT` | The process has exited. | +----------------------------+--------------------------------------------+ - | :const:`KQ_NOTE_FORK` | the process has called *fork()* | + | :const:`KQ_NOTE_FORK` | The process has called *fork()*. | +----------------------------+--------------------------------------------+ - | :const:`KQ_NOTE_EXEC` | the process has executed a new process | + | :const:`KQ_NOTE_EXEC` | The process has executed a new process. | +----------------------------+--------------------------------------------+ - | :const:`KQ_NOTE_PCTRLMASK` | internal filter flag | + | :const:`KQ_NOTE_PCTRLMASK` | Internal filter flag. | +----------------------------+--------------------------------------------+ - | :const:`KQ_NOTE_PDATAMASK` | internal filter flag | + | :const:`KQ_NOTE_PDATAMASK` | Internal filter flag. | +----------------------------+--------------------------------------------+ - | :const:`KQ_NOTE_TRACK` | follow a process across *fork()* | + | :const:`KQ_NOTE_TRACK` | Follow a process across *fork()*. | +----------------------------+--------------------------------------------+ - | :const:`KQ_NOTE_CHILD` | returned on the child process for | - | | *NOTE_TRACK* | + | :const:`KQ_NOTE_CHILD` | Returned on the child process for | + | | *NOTE_TRACK*. | +----------------------------+--------------------------------------------+ - | :const:`KQ_NOTE_TRACKERR` | unable to attach to a child | + | :const:`KQ_NOTE_TRACKERR` | Unable to attach to a child. | +----------------------------+--------------------------------------------+ :const:`KQ_FILTER_NETDEV` filter flags (not available on macOS): @@ -638,19 +649,19 @@ https://man.freebsd.org/cgi/man.cgi?query=kqueue&sektion=2 +----------------------------+--------------------------------------------+ | Constant | Meaning | +============================+============================================+ - | :const:`KQ_NOTE_LINKUP` | link is up | + | :const:`KQ_NOTE_LINKUP` | Link is up. | +----------------------------+--------------------------------------------+ - | :const:`KQ_NOTE_LINKDOWN` | link is down | + | :const:`KQ_NOTE_LINKDOWN` | Link is down. | +----------------------------+--------------------------------------------+ - | :const:`KQ_NOTE_LINKINV` | link state is invalid | + | :const:`KQ_NOTE_LINKINV` | Link state is invalid. | +----------------------------+--------------------------------------------+ .. attribute:: kevent.data - Filter specific data. + Filter-specific data. .. attribute:: kevent.udata - User defined value. + User-defined value. diff --git a/Doc/library/selectors.rst b/Doc/library/selectors.rst index ee556f1f3cecae..2d523a9d2ea440 100644 --- a/Doc/library/selectors.rst +++ b/Doc/library/selectors.rst @@ -54,7 +54,7 @@ Classes hierarchy:: In the following, *events* is a bitwise mask indicating which I/O events should -be waited for on a given file object. It can be a combination of the modules +be waited for on a given file object. It can be a combination of the module's constants below: +-----------------------+-----------------------------------------------+ diff --git a/Doc/library/shelve.rst b/Doc/library/shelve.rst index 6e74a59b82b8ec..a2c9065ae788a3 100644 --- a/Doc/library/shelve.rst +++ b/Doc/library/shelve.rst @@ -61,11 +61,11 @@ lots of shared sub-objects. The keys are ordinary strings. .. warning:: - Because the :mod:`shelve` module is backed by :mod:`pickle`, it is insecure + Because the :mod:`!shelve` module is backed by :mod:`pickle`, it is insecure to load a shelf from an untrusted source. Like with pickle, loading a shelf can execute arbitrary code. -Shelf objects support most of methods and operations supported by dictionaries +Shelf objects support most of the methods and operations supported by dictionaries (except copying, constructors and operators ``|`` and ``|=``). This eases the transition from dictionary based scripts to those requiring persistent storage. @@ -106,7 +106,7 @@ Restrictions database should be fairly small, and in rare cases key collisions may cause the database to refuse updates. -* The :mod:`shelve` module does not support *concurrent* read/write access to +* The :mod:`!shelve` module does not support *concurrent* read/write access to shelved objects. (Multiple simultaneous read accesses are safe.) When a program has a shelf open for writing, no other program should have it open for reading or writing. Unix file locking can be used to solve this, but this @@ -219,5 +219,5 @@ object):: Generic interface to ``dbm``-style databases. Module :mod:`pickle` - Object serialization used by :mod:`shelve`. + Object serialization used by :mod:`!shelve`. diff --git a/Doc/library/shlex.rst b/Doc/library/shlex.rst index a96f0864dc1260..0653bf2f4189c2 100644 --- a/Doc/library/shlex.rst +++ b/Doc/library/shlex.rst @@ -18,7 +18,7 @@ simple syntaxes resembling that of the Unix shell. This will often be useful for writing minilanguages, (for example, in run control files for Python applications) or for parsing quoted strings. -The :mod:`shlex` module defines the following functions: +The :mod:`!shlex` module defines the following functions: .. function:: split(s, comments=False, posix=True) @@ -98,7 +98,7 @@ The :mod:`shlex` module defines the following functions: .. versionadded:: 3.3 -The :mod:`shlex` module defines the following class: +The :mod:`!shlex` module defines the following class: .. class:: shlex(instream=None, infile=None, posix=False, punctuation_chars=False) @@ -214,7 +214,7 @@ A :class:`~shlex.shlex` instance has the following methods: with the name of the current source file and the ``%d`` with the current input line number (the optional arguments can be used to override these). - This convenience is provided to encourage :mod:`shlex` users to generate error + This convenience is provided to encourage :mod:`!shlex` users to generate error messages in the standard, parseable format understood by Emacs and other Unix tools. @@ -343,7 +343,7 @@ variables which either control lexical analysis or can be used for debugging: Parsing Rules ------------- -When operating in non-POSIX mode, :class:`~shlex.shlex` will try to obey to the +When operating in non-POSIX mode, :class:`~shlex.shlex` will try to obey the following rules. * Quote characters are not recognized within words (``Do"Not"Separate`` is @@ -366,7 +366,7 @@ following rules. * It's not possible to parse empty strings, even if quoted. -When operating in POSIX mode, :class:`~shlex.shlex` will try to obey to the +When operating in POSIX mode, :class:`~shlex.shlex` will try to obey the following parsing rules. * Quotes are stripped out, and do not separate words (``"Do"Not"Separate"`` is @@ -382,7 +382,7 @@ following parsing rules. * Enclosing characters in quotes which are part of :attr:`~shlex.escapedquotes` (e.g. ``'"'``) preserves the literal value of all characters within the quotes, with the exception of the characters - mentioned in :attr:`~shlex.escape`. The escape characters retain its + mentioned in :attr:`~shlex.escape`. The escape characters retain their special meaning only when followed by the quote in use, or the escape character itself. Otherwise the escape character will be considered a normal character. diff --git a/Doc/library/shutil.rst b/Doc/library/shutil.rst index 2cbf95bcf535e4..d802a2572871ea 100644 --- a/Doc/library/shutil.rst +++ b/Doc/library/shutil.rst @@ -15,7 +15,7 @@ -------------- -The :mod:`shutil` module offers a number of high-level operations on files and +The :mod:`!shutil` module offers a number of high-level operations on files and collections of files. In particular, functions are provided which support file copying and removal. For operations on individual files, see also the :mod:`os` module. @@ -47,6 +47,13 @@ Directory and files operations 0, only the contents from the current file position to the end of the file will be copied. + :func:`copyfileobj` will *not* guarantee that the destination stream has + been flushed on completion of the copy. If you want to read from the + destination at the completion of the copy operation (for example, reading + the contents of a temporary file that has been copied from a HTTP stream), + you must ensure that you have called :func:`~io.IOBase.flush` or + :func:`~io.IOBase.close` on the file-like object before attempting to read + the destination file. .. function:: copyfile(src, dst, *, follow_symlinks=True) @@ -83,6 +90,13 @@ Directory and files operations copy the file more efficiently. See :ref:`shutil-platform-dependent-efficient-copy-operations` section. +.. exception:: SpecialFileError + + This exception is raised when :func:`copyfile` or :func:`copytree` attempt + to copy a named pipe. + + .. versionadded:: 2.7 + .. exception:: SameFileError This exception is raised if source and destination in :func:`copyfile` @@ -327,6 +341,10 @@ Directory and files operations The deprecated *onerror* is similar to *onexc*, except that the third parameter it receives is the tuple returned from :func:`sys.exc_info`. + .. seealso:: + :ref:`shutil-rmtree-example` for an example of handling the removal + of a directory tree that contains read-only files. + .. audit-event:: shutil.rmtree path,dir_fd shutil.rmtree .. versionchanged:: 3.3 @@ -370,10 +388,14 @@ Directory and files operations If *dst* already exists but is not a directory, it may be overwritten depending on :func:`os.rename` semantics. - If the destination is on the current filesystem, then :func:`os.rename` is - used. Otherwise, *src* is copied to the destination using *copy_function* - and then removed. In case of symlinks, a new symlink pointing to the target - of *src* will be created as the destination and *src* will be removed. + :func:`os.rename` is preferably used internally when *src* and the destination are on + the same filesystem. In case :func:`os.rename` fails due to :exc:`OSError` + (e.g. the user has write permission to the destination file but not to its parent + directory), this method falls back to using *copy_function*, in which case + *src* is copied to the destination using *copy_function* and then removed. + + In case of symlinks, a new symlink pointing to the target of *src* will be + created in or as the destination, and *src* will be removed. If *copy_function* is given, it must be a callable that takes two arguments, *src* and the destination, and will be used to copy *src* to the destination @@ -454,6 +476,10 @@ Directory and files operations :envvar:`PATH` environment variable is read from :data:`os.environ`, falling back to :data:`os.defpath` if it is not set. + If *cmd* contains a directory component, :func:`!which` only checks the + specified path directly and does not search the directories listed in + *path* or in the system's :envvar:`PATH` environment variable. + On Windows, the current directory is prepended to the *path* if *mode* does not include ``os.X_OK``. When the *mode* does include ``os.X_OK``, the Windows API ``NeedCurrentDirectoryForExePathW`` will be consulted to @@ -521,7 +547,7 @@ instead of 64 KiB) and a :func:`memoryview`-based variant of :func:`shutil.copyfileobj` is used. If the fast-copy operation fails and no data was written in the destination -file then shutil will silently fallback on using less efficient +file then shutil will silently fall back to less efficient :func:`copyfileobj` function internally. .. versionchanged:: 3.8 @@ -603,7 +629,8 @@ provided. They rely on the :mod:`zipfile` and :mod:`tarfile` modules. *format* is the archive format: one of "zip" (if the :mod:`zlib` module is available), "tar", "gztar" (if the :mod:`zlib` module is available), "bztar" (if the :mod:`bz2` module is - available), or "xztar" (if the :mod:`lzma` module is available). + available), "xztar" (if the :mod:`lzma` module is available), or "zstdtar" + (if the :mod:`compression.zstd` module is available). *root_dir* is a directory that will be the root directory of the archive, all paths in the archive will be relative to it; for example, @@ -651,13 +678,15 @@ provided. They rely on the :mod:`zipfile` and :mod:`tarfile` modules. Return a list of supported formats for archiving. Each element of the returned sequence is a tuple ``(name, description)``. - By default :mod:`shutil` provides these formats: + By default :mod:`!shutil` provides these formats: - *zip*: ZIP file (if the :mod:`zlib` module is available). - *tar*: Uncompressed tar file. Uses POSIX.1-2001 pax format for new archives. - *gztar*: gzip'ed tar-file (if the :mod:`zlib` module is available). - *bztar*: bzip2'ed tar-file (if the :mod:`bz2` module is available). - *xztar*: xz'ed tar-file (if the :mod:`lzma` module is available). + - *zstdtar*: Zstandard compressed tar-file (if the :mod:`compression.zstd` + module is available). You can register new formats or provide your own archiver for any existing formats, by using :func:`register_archive_format`. @@ -667,7 +696,7 @@ provided. They rely on the :mod:`zipfile` and :mod:`tarfile` modules. Register an archiver for the format *name*. - *function* is the callable that will be used to unpack archives. The callable + *function* is the callable that will be used to create archives. The callable will receive the *base_name* of the file to create, followed by the *base_dir* (which defaults to :data:`os.curdir`) to start archiving from. Further arguments are passed as keyword arguments: *owner*, *group*, @@ -701,8 +730,8 @@ provided. They rely on the :mod:`zipfile` and :mod:`tarfile` modules. *extract_dir* is the name of the target directory where the archive is unpacked. If not provided, the current working directory is used. - *format* is the archive format: one of "zip", "tar", "gztar", "bztar", or - "xztar". Or any other format registered with + *format* is the archive format: one of "zip", "tar", "gztar", "bztar", + "xztar", or "zstdtar". Or any other format registered with :func:`register_unpack_format`. If not provided, :func:`unpack_archive` will use the archive file name extension and see if an unpacker was registered for that extension. In case none is found, @@ -720,8 +749,8 @@ provided. They rely on the :mod:`zipfile` and :mod:`tarfile` modules. Never extract archives from untrusted sources without prior inspection. It is possible that files are created outside of the path specified in - the *extract_dir* argument, e.g. members that have absolute filenames - starting with "/" or filenames with two dots "..". + the *extract_dir* argument, for example, members that have absolute filenames + or filenames with ".." components. Since Python 3.14, the defaults for both built-in formats (zip and tar files) will prevent the most dangerous of such security issues, @@ -766,7 +795,7 @@ provided. They rely on the :mod:`zipfile` and :mod:`tarfile` modules. Each element of the returned sequence is a tuple ``(name, extensions, description)``. - By default :mod:`shutil` provides these formats: + By default :mod:`!shutil` provides these formats: - *zip*: ZIP file (unpacking compressed files works only if the corresponding module is available). @@ -774,6 +803,8 @@ provided. They rely on the :mod:`zipfile` and :mod:`tarfile` modules. - *gztar*: gzip'ed tar-file (if the :mod:`zlib` module is available). - *bztar*: bzip2'ed tar-file (if the :mod:`bz2` module is available). - *xztar*: xz'ed tar-file (if the :mod:`lzma` module is available). + - *zstdtar*: Zstandard compressed tar-file (if the :mod:`compression.zstd` + module is available). You can register new formats or provide your own unpacker for any existing formats, by using :func:`register_unpack_format`. @@ -840,7 +871,7 @@ In the final archive, :file:`please_add.txt` should be included, but ... root_dir='tmp/root', ... base_dir='structure/content', ... ) - '/Users/tarek/my_archive.tar' + '/Users/tarek/myarchive.tar' Listing the files in the resulting archive gives us: diff --git a/Doc/library/signal.rst b/Doc/library/signal.rst index c28841dbb8cfc8..8e543d9205ec6a 100644 --- a/Doc/library/signal.rst +++ b/Doc/library/signal.rst @@ -36,7 +36,7 @@ Execution of Python signal handlers A Python signal handler does not get executed inside the low-level (C) signal handler. Instead, the low-level signal handler sets a flag which tells the :term:`virtual machine` to execute the corresponding Python signal handler -at a later point(for example at the next :term:`bytecode` instruction). +at a later point (for example, at the next :term:`bytecode` instruction). This has consequences: * It makes little sense to catch synchronous errors like :const:`SIGFPE` or @@ -68,6 +68,11 @@ the synchronization primitives from the :mod:`threading` module instead. Besides, only the main thread of the main interpreter is allowed to set a new signal handler. +.. warning:: + + Synchronization primitives such as :class:`threading.Lock` should not be used + within signal handlers. Doing so can lead to unexpected deadlocks. + Module contents --------------- @@ -92,13 +97,13 @@ The signal module defines three enums: .. class:: Handlers - :class:`enum.IntEnum` collection the constants :const:`SIG_DFL` and :const:`SIG_IGN`. + :class:`enum.IntEnum` collection of the constants :const:`SIG_DFL` and :const:`SIG_IGN`. .. versionadded:: 3.5 .. class:: Sigmasks - :class:`enum.IntEnum` collection the constants :const:`SIG_BLOCK`, :const:`SIG_UNBLOCK` and :const:`SIG_SETMASK`. + :class:`enum.IntEnum` collection of the constants :const:`SIG_BLOCK`, :const:`SIG_UNBLOCK` and :const:`SIG_SETMASK`. .. availability:: Unix. @@ -108,7 +113,7 @@ The signal module defines three enums: .. versionadded:: 3.5 -The variables defined in the :mod:`signal` module are: +The variables defined in the :mod:`!signal` module are: .. data:: SIG_DFL @@ -205,14 +210,32 @@ The variables defined in the :mod:`signal` module are: .. availability:: Unix. +.. data:: SIGPROF + + Profiling timer expired. + + .. availability:: Unix. + +.. data:: SIGQUIT + + Terminal quit signal. + + .. availability:: Unix. + .. data:: SIGSEGV Segmentation fault: invalid memory reference. +.. data:: SIGSTOP + + Stop executing (cannot be caught or ignored). + + .. availability:: Unix. + .. data:: SIGSTKFLT - Stack fault on coprocessor. The Linux kernel does not raise this signal: it - can only be raised in user space. + Stack fault on coprocessor. The Linux kernel does not raise this signal: it + can only be raised in user space. .. availability:: Linux. @@ -237,18 +260,30 @@ The variables defined in the :mod:`signal` module are: .. availability:: Unix. +.. data:: SIGVTALRM + + Virtual timer expired. + + .. availability:: Unix. + .. data:: SIGWINCH Window resize signal. .. availability:: Unix. +.. data:: SIGXCPU + + CPU time limit exceeded. + + .. availability:: Unix. + .. data:: SIG* All the signal numbers are defined symbolically. For example, the hangup signal is defined as :const:`signal.SIGHUP`; the variable names are identical to the names used in C programs, as found in ````. The Unix man page for - ':c:func:`signal`' lists the existing signals (on some systems this is + '``signal``' lists the existing signals (on some systems this is :manpage:`signal(2)`, on others the list is in :manpage:`signal(7)`). Note that not all systems define the same set of signal names; only those names defined by the system are defined by this module. @@ -322,7 +357,7 @@ The variables defined in the :mod:`signal` module are: .. versionadded:: 3.3 -The :mod:`signal` module defines one exception: +The :mod:`!signal` module defines one exception: .. exception:: ItimerError @@ -336,7 +371,7 @@ The :mod:`signal` module defines one exception: alias of :exc:`OSError`. -The :mod:`signal` module defines the following functions: +The :mod:`!signal` module defines the following functions: .. function:: alarm(time) @@ -639,9 +674,8 @@ The :mod:`signal` module defines the following functions: *sigset*. The return value is an object representing the data contained in the - :c:type:`siginfo_t` structure, namely: :attr:`si_signo`, :attr:`si_code`, - :attr:`si_errno`, :attr:`si_pid`, :attr:`si_uid`, :attr:`si_status`, - :attr:`si_band`. + ``siginfo_t`` structure, namely: ``si_signo``, ``si_code``, + ``si_errno``, ``si_pid``, ``si_uid``, ``si_status``, ``si_band``. .. availability:: Unix. diff --git a/Doc/library/site.rst b/Doc/library/site.rst index e98dd83b60eb60..19c2257031a6ee 100644 --- a/Doc/library/site.rst +++ b/Doc/library/site.rst @@ -34,7 +34,7 @@ For the head part, it uses ``sys.prefix`` and ``sys.exec_prefix``; empty heads are skipped. For the tail part, it uses the empty string and then :file:`lib/site-packages` (on Windows) or :file:`lib/python{X.Y[t]}/site-packages` (on Unix and macOS). (The -optional suffix "t" indicates the :term:`free threading` build, and is +optional suffix "t" indicates the :term:`free-threaded build`, and is appended if ``"t"`` is present in the :data:`sys.abiflags` constant.) For each of the distinct head-tail combinations, it sees if it refers to an existing @@ -51,11 +51,11 @@ added path for configuration files. .. versionchanged:: 3.14 - :mod:`site` is no longer responsible for updating :data:`sys.prefix` and + :mod:`!site` is no longer responsible for updating :data:`sys.prefix` and :data:`sys.exec_prefix` on :ref:`sys-path-init-virtual-environments`. This is now done during the :ref:`path initialization `. As a result, under :ref:`sys-path-init-virtual-environments`, :data:`sys.prefix` and - :data:`sys.exec_prefix` no longer depend on the :mod:`site` initialization, + :data:`sys.exec_prefix` no longer depend on the :mod:`!site` initialization, and are therefore unaffected by :option:`-S`. .. _site-virtual-environments-configuration: @@ -130,38 +130,38 @@ directory precedes the :file:`foo` directory because :file:`bar.pth` comes alphabetically before :file:`foo.pth`; and :file:`spam` is omitted because it is not mentioned in either path configuration file. -:mod:`sitecustomize` --------------------- +:mod:`!sitecustomize` +--------------------- .. module:: sitecustomize After these path manipulations, an attempt is made to import a module named -:mod:`sitecustomize`, which can perform arbitrary site-specific customizations. +:mod:`!sitecustomize`, which can perform arbitrary site-specific customizations. It is typically created by a system administrator in the site-packages directory. If this import fails with an :exc:`ImportError` or its subclass exception, and the exception's :attr:`~ImportError.name` -attribute equals to ``'sitecustomize'``, +attribute equals ``'sitecustomize'``, it is silently ignored. If Python is started without output streams available, as with :file:`pythonw.exe` on Windows (which is used by default to start IDLE), -attempted output from :mod:`sitecustomize` is ignored. Any other exception +attempted output from :mod:`!sitecustomize` is ignored. Any other exception causes a silent and perhaps mysterious failure of the process. -:mod:`usercustomize` --------------------- +:mod:`!usercustomize` +--------------------- .. module:: usercustomize -After this, an attempt is made to import a module named :mod:`usercustomize`, +After this, an attempt is made to import a module named :mod:`!usercustomize`, which can perform arbitrary user-specific customizations, if :data:`~site.ENABLE_USER_SITE` is true. This file is intended to be created in the user site-packages directory (see below), which is part of ``sys.path`` unless disabled by :option:`-s`. If this import fails with an :exc:`ImportError` or its subclass exception, and the exception's :attr:`~ImportError.name` -attribute equals to ``'usercustomize'``, it is silently ignored. +attribute equals ``'usercustomize'``, it is silently ignored. Note that for some non-Unix systems, ``sys.prefix`` and ``sys.exec_prefix`` are empty, and the path manipulations are skipped; however the import of -:mod:`sitecustomize` and :mod:`usercustomize` is still attempted. +:mod:`sitecustomize` and :mod:`!usercustomize` is still attempted. .. currentmodule:: site @@ -173,7 +173,7 @@ Readline configuration On systems that support :mod:`readline`, this module will also import and configure the :mod:`rlcompleter` module, if Python is started in :ref:`interactive mode ` and without the :option:`-S` option. -The default behavior is enable tab-completion and to use +The default behavior is to enable tab completion and to use :file:`~/.python_history` as the history save file. To disable it, delete (or override) the :data:`sys.__interactivehook__` attribute in your :mod:`sitecustomize` or :mod:`usercustomize` module or your @@ -241,12 +241,19 @@ Module contents used in :mod:`sitecustomize` or :mod:`usercustomize` (see above). -.. function:: getsitepackages() +.. function:: getsitepackages(prefixes=None) Return a list containing all global site-packages directories. + For each directory present in *prefixes* (or :data:`PREFIXES` if *prefixes* + is ``None``), this function will find its site-packages subdirectory + depending on the system environment, and will return a list of full paths. + .. versionadded:: 3.2 + .. versionchanged:: 3.3 + Added the optional *prefixes* parameter. + .. function:: getuserbase() @@ -270,12 +277,12 @@ Module contents .. _site-commandline: -Command Line Interface +Command-line interface ---------------------- .. program:: site -The :mod:`site` module also provides a way to get the user directories from the +The :mod:`!site` module also provides a way to get the user directories from the command line: .. code-block:: shell-session diff --git a/Doc/library/smtplib.rst b/Doc/library/smtplib.rst index c5f8516f768a68..583bc3afcad040 100644 --- a/Doc/library/smtplib.rst +++ b/Doc/library/smtplib.rst @@ -14,7 +14,7 @@ -------------- -The :mod:`smtplib` module defines an SMTP client session object that can be used +The :mod:`!smtplib` module defines an SMTP client session object that can be used to send mail to any internet machine with an SMTP or ESMTP listener daemon. For details of SMTP and ESMTP operation, consult :rfc:`821` (Simple Mail Transfer Protocol) and :rfc:`1869` (SMTP Service Extensions). @@ -80,8 +80,8 @@ Protocol) and :rfc:`1869` (SMTP Service Extensions). An :class:`SMTP_SSL` instance behaves exactly the same as instances of :class:`SMTP`. :class:`SMTP_SSL` should be used for situations where SSL is - required from the beginning of the connection and using :meth:`starttls` is - not appropriate. If *host* is not specified, the local host is used. If + required from the beginning of the connection and using :meth:`~SMTP.starttls` + is not appropriate. If *host* is not specified, the local host is used. If *port* is zero, the standard SMTP-over-SSL port (465) is used. The optional arguments *local_hostname*, *timeout* and *source_address* have the same meaning as they do in the :class:`SMTP` class. *context*, also optional, @@ -112,7 +112,7 @@ Protocol) and :rfc:`1869` (SMTP Service Extensions). The LMTP protocol, which is very similar to ESMTP, is heavily based on the standard SMTP client. It's common to use Unix sockets for LMTP, so our - :meth:`connect` method must support that as well as a regular host:port + :meth:`~SMTP.connect` method must support that as well as a regular host:port server. The optional arguments *local_hostname* and *source_address* have the same meaning as they do in the :class:`SMTP` class. To specify a Unix socket, you must use an absolute path for *host*, starting with a '/'. @@ -147,9 +147,15 @@ A nice selection of exceptions is defined as well: .. exception:: SMTPResponseException Base class for all exceptions that include an SMTP error code. These exceptions - are generated in some instances when the SMTP server returns an error code. The - error code is stored in the :attr:`smtp_code` attribute of the error, and the - :attr:`smtp_error` attribute is set to the error message. + are generated in some instances when the SMTP server returns an error code. + + .. attribute:: smtp_code + + The error code. + + .. attribute:: smtp_error + + The error message. .. exception:: SMTPSenderRefused @@ -161,9 +167,13 @@ A nice selection of exceptions is defined as well: .. exception:: SMTPRecipientsRefused - All recipient addresses refused. The errors for each recipient are accessible - through the attribute :attr:`recipients`, which is a dictionary of exactly the - same sort as :meth:`SMTP.sendmail` returns. + All recipient addresses refused. + + .. attribute:: recipients + + A dictionary of exactly the same sort as returned + by :meth:`SMTP.sendmail` containing the errors for + each recipient. .. exception:: SMTPDataError @@ -213,7 +223,6 @@ SMTP Objects An :class:`SMTP` instance has the following methods: - .. method:: SMTP.set_debuglevel(level) Set the debug output level. A value of 1 or ``True`` for *level* results in @@ -327,7 +336,7 @@ An :class:`SMTP` instance has the following methods: :exc:`SMTPException` No suitable authentication method was found. - Each of the authentication methods supported by :mod:`smtplib` are tried in + Each of the authentication methods supported by :mod:`!smtplib` are tried in turn if they are advertised as supported by the server. See :meth:`auth` for a list of supported authentication methods. *initial_response_ok* is passed through to :meth:`auth`. @@ -379,7 +388,7 @@ An :class:`SMTP` instance has the following methods: call the :meth:`login` method, which will try each of the above mechanisms in turn, in the order listed. ``auth`` is exposed to facilitate the implementation of authentication methods not (or not yet) supported - directly by :mod:`smtplib`. + directly by :mod:`!smtplib`. .. versionadded:: 3.5 @@ -417,7 +426,7 @@ An :class:`SMTP` instance has the following methods: .. versionchanged:: 3.4 The method now supports hostname check with - :attr:`SSLContext.check_hostname` and *Server Name Indicator* (see + :attr:`ssl.SSLContext.check_hostname` and *Server Name Indicator* (see :const:`~ssl.HAS_SNI`). .. versionchanged:: 3.5 @@ -431,11 +440,13 @@ An :class:`SMTP` instance has the following methods: Send mail. The required arguments are an :rfc:`822` from-address string, a list of :rfc:`822` to-address strings (a bare string will be treated as a list with 1 address), and a message string. The caller may pass a list of ESMTP options - (such as ``8bitmime``) to be used in ``MAIL FROM`` commands as *mail_options*. + (such as ``"8bitmime"``) to be used in ``MAIL FROM`` commands as *mail_options*. ESMTP options (such as ``DSN`` commands) that should be used with all ``RCPT`` - commands can be passed as *rcpt_options*. (If you need to use different ESMTP + commands can be passed as *rcpt_options*. Each option should be passed as a string + containing the full text of the option, including any potential key + (for instance, ``"NOTIFY=SUCCESS,FAILURE"``). (If you need to use different ESMTP options to different recipients you have to use the low-level methods such as - :meth:`mail`, :meth:`rcpt` and :meth:`data` to send the message.) + :meth:`!mail`, :meth:`!rcpt` and :meth:`!data` to send the message.) .. note:: @@ -467,10 +478,7 @@ An :class:`SMTP` instance has the following methods: This method may raise the following exceptions: :exc:`SMTPRecipientsRefused` - All recipients were refused. Nobody got the mail. The :attr:`recipients` - attribute of the exception object is a dictionary with information about the - refused recipients (like the one returned when at least one recipient was - accepted). + All recipients were refused. Nobody got the mail. :exc:`SMTPHeloError` The server didn't reply properly to the ``HELO`` greeting. @@ -546,6 +554,30 @@ Low-level methods corresponding to the standard SMTP/ESMTP commands ``HELP``, Normally these do not need to be called directly, so they are not documented here. For details, consult the module code. +Additionally, an SMTP instance has the following attributes: + + +.. attribute:: SMTP.helo_resp + + The response to the ``HELO`` command, see :meth:`helo`. + + +.. attribute:: SMTP.ehlo_resp + + The response to the ``EHLO`` command, see :meth:`ehlo`. + + +.. attribute:: SMTP.does_esmtp + + A boolean value indicating whether the server supports ESMTP, see + :meth:`ehlo`. + + +.. attribute:: SMTP.esmtp_features + + A dictionary of the names of SMTP service extensions supported by the server, + see :meth:`ehlo`. + .. _smtp-example: diff --git a/Doc/library/socket.rst b/Doc/library/socket.rst index 8fd5187e3a4a36..71f5fb6ab0cc75 100644 --- a/Doc/library/socket.rst +++ b/Doc/library/socket.rst @@ -39,6 +39,8 @@ is implicit on send operations. A TLS/SSL wrapper for socket objects. +.. _socket-addresses: + Socket families --------------- @@ -83,7 +85,7 @@ created. Socket addresses are represented as follows: - For :const:`AF_INET6` address family, a four-tuple ``(host, port, flowinfo, scope_id)`` is used, where *flowinfo* and *scope_id* represent the ``sin6_flowinfo`` and ``sin6_scope_id`` members in :const:`struct sockaddr_in6` in C. For - :mod:`socket` module methods, *flowinfo* and *scope_id* can be omitted just for + :mod:`!socket` module methods, *flowinfo* and *scope_id* can be omitted just for backward compatibility. Note, however, omission of *scope_id* can cause problems in manipulating scoped IPv6 addresses. @@ -118,10 +120,10 @@ created. Socket addresses are represented as follows: ``'can0'``. The network interface name ``''`` can be used to receive packets from all network interfaces of this family. - - :const:`CAN_ISOTP` protocol require a tuple ``(interface, rx_addr, tx_addr)`` + - :const:`CAN_ISOTP` protocol requires a tuple ``(interface, rx_addr, tx_addr)`` where both additional parameters are unsigned long integer that represent a CAN identifier (standard or extended). - - :const:`CAN_J1939` protocol require a tuple ``(interface, name, pgn, addr)`` + - :const:`CAN_J1939` protocol requires a tuple ``(interface, name, pgn, addr)`` where additional parameters are 64-bit unsigned integer representing the ECU name, a 32-bit unsigned integer representing the Parameter Group Number (PGN), and an 8-bit integer representing the address. @@ -302,7 +304,7 @@ generalization of this based on timeouts is supported through Module contents --------------- -The module :mod:`socket` exports the following elements. +The module :mod:`!socket` exports the following elements. Exceptions @@ -362,10 +364,10 @@ Exceptions Constants ^^^^^^^^^ - The AF_* and SOCK_* constants are now :class:`AddressFamily` and - :class:`SocketKind` :class:`.IntEnum` collections. +The AF_* and SOCK_* constants are now :class:`AddressFamily` and +:class:`SocketKind` :class:`.IntEnum` collections. - .. versionadded:: 3.4 +.. versionadded:: 3.4 .. data:: AF_UNIX AF_INET @@ -773,9 +775,9 @@ Constants Constant to optimize CPU locality, to be used in conjunction with :data:`SO_REUSEPORT`. - .. versionadded:: 3.11 + .. versionadded:: 3.11 - .. availability:: Linux >= 3.9 + .. availability:: Linux >= 3.9 .. data:: SO_REUSEPORT_LB @@ -836,71 +838,14 @@ Creating sockets The following functions all create :ref:`socket objects `. -.. class:: socket(family=AF_INET, type=SOCK_STREAM, proto=0, fileno=None) - - Create a new socket using the given address family, socket type and protocol - number. The address family should be :const:`AF_INET` (the default), - :const:`AF_INET6`, :const:`AF_UNIX`, :const:`AF_CAN`, :const:`AF_PACKET`, - or :const:`AF_RDS`. The socket type should be :const:`SOCK_STREAM` (the - default), :const:`SOCK_DGRAM`, :const:`SOCK_RAW` or perhaps one of the other - ``SOCK_`` constants. The protocol number is usually zero and may be omitted - or in the case where the address family is :const:`AF_CAN` the protocol - should be one of :const:`CAN_RAW`, :const:`CAN_BCM`, :const:`CAN_ISOTP` or - :const:`CAN_J1939`. - - If *fileno* is specified, the values for *family*, *type*, and *proto* are - auto-detected from the specified file descriptor. Auto-detection can be - overruled by calling the function with explicit *family*, *type*, or *proto* - arguments. This only affects how Python represents e.g. the return value - of :meth:`socket.getpeername` but not the actual OS resource. Unlike - :func:`socket.fromfd`, *fileno* will return the same socket and not a - duplicate. This may help close a detached socket using - :meth:`socket.close`. - - The newly created socket is :ref:`non-inheritable `. - - .. audit-event:: socket.__new__ self,family,type,protocol socket.socket - - .. versionchanged:: 3.3 - The AF_CAN family was added. - The AF_RDS family was added. - - .. versionchanged:: 3.4 - The CAN_BCM protocol was added. - - .. versionchanged:: 3.4 - The returned socket is now non-inheritable. - - .. versionchanged:: 3.7 - The CAN_ISOTP protocol was added. - - .. versionchanged:: 3.7 - When :const:`SOCK_NONBLOCK` or :const:`SOCK_CLOEXEC` - bit flags are applied to *type* they are cleared, and - :attr:`socket.type` will not reflect them. They are still passed - to the underlying system ``socket()`` call. Therefore, - - :: - - sock = socket.socket( - socket.AF_INET, - socket.SOCK_STREAM | socket.SOCK_NONBLOCK) - - will still create a non-blocking socket on OSes that support - ``SOCK_NONBLOCK``, but ``sock.type`` will be set to - ``socket.SOCK_STREAM``. - - .. versionchanged:: 3.9 - The CAN_J1939 protocol was added. - - .. versionchanged:: 3.10 - The IPPROTO_MPTCP protocol was added. +The :class:`socket ` class constructor creates a new socket +directly; see :ref:`socket-objects` for its parameters and full description. .. function:: socketpair([family[, type[, proto]]]) Build a pair of connected socket objects using the given address family, socket type, and protocol number. Address family, socket type, and protocol number are - as for the :func:`~socket.socket` function above. The default family is :const:`AF_UNIX` + as for the :func:`~socket.socket` function. The default family is :const:`AF_UNIX` if defined on the platform; otherwise, the default is :const:`AF_INET`. The newly created sockets are :ref:`non-inheritable `. @@ -996,8 +941,8 @@ The following functions all create :ref:`socket objects `. Duplicate the file descriptor *fd* (an integer as returned by a file object's :meth:`~io.IOBase.fileno` method) and build a socket object from the result. Address - family, socket type and protocol number are as for the :func:`~socket.socket` function - above. The file descriptor should refer to a socket, but this is not checked --- + family, socket type and protocol number are as for the :func:`~socket.socket` function. + The file descriptor should refer to a socket, but this is not checked --- subsequent operations on the object may fail if the file descriptor is invalid. This function is rarely needed, but can be used to get or set socket options on a socket passed to a program as standard input or output (such as a server @@ -1019,22 +964,16 @@ The following functions all create :ref:`socket objects `. .. versionadded:: 3.3 -.. data:: SocketType - - This is a Python type object that represents the socket object type. It is the - same as ``type(socket(...))``. - - Other functions ''''''''''''''' -The :mod:`socket` module also offers various network-related services: +The :mod:`!socket` module also offers various network-related services: .. function:: close(fd) Close a socket file descriptor. This is like :func:`os.close`, but for - sockets. On some platforms (most noticeable Windows) :func:`os.close` + sockets. On some platforms (most notably Windows) :func:`os.close` does not work for socket file descriptors. .. versionadded:: 3.7 @@ -1492,7 +1431,7 @@ The :mod:`socket` module also offers various network-related services: The *fds* parameter is a sequence of file descriptors. Consult :meth:`~socket.sendmsg` for the documentation of these parameters. - .. availability:: Unix, Windows, not WASI. + .. availability:: Unix, not WASI. Unix platforms supporting :meth:`~socket.sendmsg` and :const:`SCM_RIGHTS` mechanism. @@ -1506,9 +1445,9 @@ The :mod:`socket` module also offers various network-related services: Return ``(msg, list(fds), flags, addr)``. Consult :meth:`~socket.recvmsg` for the documentation of these parameters. - .. availability:: Unix, Windows, not WASI. + .. availability:: Unix, not WASI. - Unix platforms supporting :meth:`~socket.sendmsg` + Unix platforms supporting :meth:`~socket.recvmsg` and :const:`SCM_RIGHTS` mechanism. .. versionadded:: 3.9 @@ -1523,641 +1462,706 @@ The :mod:`socket` module also offers various network-related services: Socket Objects -------------- -Socket objects have the following methods. Except for -:meth:`~socket.makefile`, these correspond to Unix system calls applicable -to sockets. +.. class:: socket(family=AF_INET, type=SOCK_STREAM, proto=0, fileno=None) + + Create a new socket using the given address family, socket type and protocol + number. The address family should be :const:`AF_INET` (the default), + :const:`AF_INET6`, :const:`AF_UNIX`, :const:`AF_CAN`, :const:`AF_PACKET`, + or :const:`AF_RDS`. The socket type should be :const:`SOCK_STREAM` (the + default), :const:`SOCK_DGRAM`, :const:`SOCK_RAW` or perhaps one of the other + ``SOCK_`` constants. The protocol number is usually zero and may be omitted + or in the case where the address family is :const:`AF_CAN` the protocol + should be one of :const:`CAN_RAW`, :const:`CAN_BCM`, :const:`CAN_ISOTP` or + :const:`CAN_J1939`. -.. versionchanged:: 3.2 - Support for the :term:`context manager` protocol was added. Exiting the - context manager is equivalent to calling :meth:`~socket.close`. + If *fileno* is specified, the values for *family*, *type*, and *proto* are + auto-detected from the specified file descriptor. Auto-detection can be + overruled by calling the function with explicit *family*, *type*, or *proto* + arguments. This only affects how Python represents e.g. the return value + of :meth:`socket.getpeername` but not the actual OS resource. Unlike + :func:`socket.fromfd`, *fileno* will return the same socket and not a + duplicate. This may help close a detached socket using + :meth:`socket.close`. + The newly created socket is :ref:`non-inheritable `. -.. method:: socket.accept() + .. audit-event:: socket.__new__ self,family,type,protocol socket.socket - Accept a connection. The socket must be bound to an address and listening for - connections. The return value is a pair ``(conn, address)`` where *conn* is a - *new* socket object usable to send and receive data on the connection, and - *address* is the address bound to the socket on the other end of the connection. + .. versionchanged:: 3.3 + The AF_CAN family was added. + The AF_RDS family was added. - The newly created socket is :ref:`non-inheritable `. + .. versionchanged:: 3.4 + The CAN_BCM protocol was added. .. versionchanged:: 3.4 - The socket is now non-inheritable. + The returned socket is now non-inheritable. - .. versionchanged:: 3.5 - If the system call is interrupted and the signal handler does not raise - an exception, the method now retries the system call instead of raising - an :exc:`InterruptedError` exception (see :pep:`475` for the rationale). + .. versionchanged:: 3.7 + The CAN_ISOTP protocol was added. + .. versionchanged:: 3.7 + When :const:`SOCK_NONBLOCK` or :const:`SOCK_CLOEXEC` + bit flags are applied to *type* they are cleared, and + :attr:`socket.type` will not reflect them. They are still passed + to the underlying system ``socket()`` call. Therefore, -.. method:: socket.bind(address) + :: - Bind the socket to *address*. The socket must not already be bound. (The format - of *address* depends on the address family --- see above.) + sock = socket.socket( + socket.AF_INET, + socket.SOCK_STREAM | socket.SOCK_NONBLOCK) - .. audit-event:: socket.bind self,address socket.socket.bind + will still create a non-blocking socket on OSes that support + ``SOCK_NONBLOCK``, but ``sock.type`` will be set to + ``socket.SOCK_STREAM``. - .. availability:: not WASI. + .. versionchanged:: 3.9 + The CAN_J1939 protocol was added. + .. versionchanged:: 3.10 + The IPPROTO_MPTCP protocol was added. -.. method:: socket.close() + Socket objects have the following methods. Except for + :meth:`~socket.makefile`, these correspond to Unix system calls applicable + to sockets. - Mark the socket closed. The underlying system resource (e.g. a file - descriptor) is also closed when all file objects from :meth:`makefile` - are closed. Once that happens, all future operations on the socket - object will fail. The remote end will receive no more data (after - queued data is flushed). + .. versionchanged:: 3.2 + Support for the :term:`context manager` protocol was added. Exiting the + context manager is equivalent to calling :meth:`~socket.close`. - Sockets are automatically closed when they are garbage-collected, but - it is recommended to :meth:`close` them explicitly, or to use a - :keyword:`with` statement around them. - .. versionchanged:: 3.6 - :exc:`OSError` is now raised if an error occurs when the underlying - :c:func:`close` call is made. + .. method:: accept() - .. note:: + Accept a connection. The socket must be bound to an address and listening for + connections. The return value is a pair ``(conn, address)`` where *conn* is a + *new* socket object usable to send and receive data on the connection, and + *address* is the address bound to the socket on the other end of the connection. - :meth:`close` releases the resource associated with a connection but - does not necessarily close the connection immediately. If you want - to close the connection in a timely fashion, call :meth:`shutdown` - before :meth:`close`. + The newly created socket is :ref:`non-inheritable `. + .. versionchanged:: 3.4 + The socket is now non-inheritable. -.. method:: socket.connect(address) + .. versionchanged:: 3.5 + If the system call is interrupted and the signal handler does not raise + an exception, the method now retries the system call instead of raising + an :exc:`InterruptedError` exception (see :pep:`475` for the rationale). - Connect to a remote socket at *address*. (The format of *address* depends on the - address family --- see above.) - If the connection is interrupted by a signal, the method waits until the - connection completes, or raise a :exc:`TimeoutError` on timeout, if the - signal handler doesn't raise an exception and the socket is blocking or has - a timeout. For non-blocking sockets, the method raises an - :exc:`InterruptedError` exception if the connection is interrupted by a - signal (or the exception raised by the signal handler). + .. method:: bind(address) - .. audit-event:: socket.connect self,address socket.socket.connect + Bind the socket to *address*. The socket must not already be bound. The format + of *address* depends on the address family --- see :ref:`socket-addresses`. - .. versionchanged:: 3.5 - The method now waits until the connection completes instead of raising an + .. audit-event:: socket.bind self,address socket.socket.bind + + .. availability:: not WASI. + + + .. method:: close() + + Mark the socket closed. The underlying system resource (e.g. a file + descriptor) is also closed when all file objects from :meth:`makefile` + are closed. Once that happens, all future operations on the socket + object will fail. The remote end will receive no more data (after + queued data is flushed). + + Sockets are automatically closed when they are garbage-collected, but + it is recommended to :meth:`close` them explicitly, or to use a + :keyword:`with` statement around them. + + .. versionchanged:: 3.6 + :exc:`OSError` is now raised if an error occurs when the underlying + :c:func:`!close` call is made. + + .. note:: + + :meth:`close` releases the resource associated with a connection but + does not necessarily close the connection immediately. If you want + to close the connection in a timely fashion, call :meth:`shutdown` + before :meth:`close`. + + + .. method:: connect(address) + + Connect to a remote socket at *address*. The format of *address* depends on the + address family --- see :ref:`socket-addresses`. + + If the connection is interrupted by a signal, the method waits until the + connection completes, or raises a :exc:`TimeoutError` on timeout, if the + signal handler doesn't raise an exception and the socket is blocking or has + a timeout. For non-blocking sockets, the method raises an :exc:`InterruptedError` exception if the connection is interrupted by a - signal, the signal handler doesn't raise an exception and the socket is - blocking or has a timeout (see the :pep:`475` for the rationale). + signal (or the exception raised by the signal handler). - .. availability:: not WASI. + .. audit-event:: socket.connect self,address socket.socket.connect + .. versionchanged:: 3.5 + The method now waits until the connection completes instead of raising an + :exc:`InterruptedError` exception if the connection is interrupted by a + signal, the signal handler doesn't raise an exception and the socket is + blocking or has a timeout (see the :pep:`475` for the rationale). -.. method:: socket.connect_ex(address) + .. availability:: not WASI. - Like ``connect(address)``, but return an error indicator instead of raising an - exception for errors returned by the C-level :c:func:`connect` call (other - problems, such as "host not found," can still raise exceptions). The error - indicator is ``0`` if the operation succeeded, otherwise the value of the - :c:data:`errno` variable. This is useful to support, for example, asynchronous - connects. - .. audit-event:: socket.connect self,address socket.socket.connect_ex + .. method:: connect_ex(address) - .. availability:: not WASI. + Like ``connect(address)``, but return an error indicator instead of raising an + exception for errors returned by the C-level :c:func:`!connect` call (other + problems, such as "host not found," can still raise exceptions). The error + indicator is ``0`` if the operation succeeded, otherwise the value of the + :c:data:`errno` variable. This is useful to support, for example, asynchronous + connects. -.. method:: socket.detach() + .. audit-event:: socket.connect self,address socket.socket.connect_ex - Put the socket object into closed state without actually closing the - underlying file descriptor. The file descriptor is returned, and can - be reused for other purposes. + .. availability:: not WASI. - .. versionadded:: 3.2 + .. method:: detach() + Put the socket object into closed state without actually closing the + underlying file descriptor. The file descriptor is returned, and can + be reused for other purposes. -.. method:: socket.dup() + .. versionadded:: 3.2 - Duplicate the socket. - The newly created socket is :ref:`non-inheritable `. + .. method:: dup() - .. versionchanged:: 3.4 - The socket is now non-inheritable. + Duplicate the socket. - .. availability:: not WASI. + The newly created socket is :ref:`non-inheritable `. + .. versionchanged:: 3.4 + The socket is now non-inheritable. -.. method:: socket.fileno() + .. availability:: not WASI. - Return the socket's file descriptor (a small integer), or -1 on failure. This - is useful with :func:`select.select`. - Under Windows the small integer returned by this method cannot be used where a - file descriptor can be used (such as :func:`os.fdopen`). Unix does not have - this limitation. + .. method:: fileno() -.. method:: socket.get_inheritable() + Return the socket's file descriptor (a small integer), or -1 on failure. This + is useful with :func:`select.select`. - Get the :ref:`inheritable flag ` of the socket's file - descriptor or socket's handle: ``True`` if the socket can be inherited in - child processes, ``False`` if it cannot. + Under Windows the small integer returned by this method cannot be used where a + file descriptor can be used (such as :func:`os.fdopen`). Unix does not have + this limitation. - .. versionadded:: 3.4 + .. method:: get_inheritable() + Get the :ref:`inheritable flag ` of the socket's file + descriptor or socket's handle: ``True`` if the socket can be inherited in + child processes, ``False`` if it cannot. -.. method:: socket.getpeername() + .. versionadded:: 3.4 - Return the remote address to which the socket is connected. This is useful to - find out the port number of a remote IPv4/v6 socket, for instance. (The format - of the address returned depends on the address family --- see above.) On some - systems this function is not supported. + .. method:: getpeername() -.. method:: socket.getsockname() + Return the remote address to which the socket is connected. This is useful to + find out the port number of a remote IPv4/v6 socket, for instance. The format + of the address returned depends on the address family --- see :ref:`socket-addresses`. + On some systems this function is not supported. - Return the socket's own address. This is useful to find out the port number of - an IPv4/v6 socket, for instance. (The format of the address returned depends on - the address family --- see above.) + .. method:: getsockname() -.. method:: socket.getsockopt(level, optname[, buflen]) + Return the socket's own address. This is useful to find out the port number of + an IPv4/v6 socket, for instance. The format of the address returned depends on + the address family --- see :ref:`socket-addresses`. - Return the value of the given socket option (see the Unix man page - :manpage:`getsockopt(2)`). The needed symbolic constants (:ref:`SO_\* etc. `) - are defined in this module. If *buflen* is absent, an integer option is assumed - and its integer value is returned by the function. If *buflen* is present, it - specifies the maximum length of the buffer used to receive the option in, and - this buffer is returned as a bytes object. It is up to the caller to decode the - contents of the buffer (see the optional built-in module :mod:`struct` for a way - to decode C structures encoded as byte strings). - .. availability:: not WASI. + .. method:: getsockopt(level, optname[, buflen]) + Return the value of the given socket option (see the Unix man page + :manpage:`getsockopt(2)`). The needed symbolic constants (:ref:`SO_\* etc. `) + are defined in this module. If *buflen* is absent, an integer option is assumed + and its integer value is returned by the function. If *buflen* is present, it + specifies the maximum length of the buffer used to receive the option in, and + this buffer is returned as a bytes object. It is up to the caller to decode the + contents of the buffer (see the optional built-in module :mod:`struct` for a way + to decode C structures encoded as byte strings). -.. method:: socket.getblocking() + .. availability:: not WASI. - Return ``True`` if socket is in blocking mode, ``False`` if in - non-blocking. - This is equivalent to checking ``socket.gettimeout() != 0``. + .. method:: getblocking() - .. versionadded:: 3.7 + Return ``True`` if socket is in blocking mode, ``False`` if in + non-blocking. + This is equivalent to checking ``socket.gettimeout() != 0``. -.. method:: socket.gettimeout() + .. versionadded:: 3.7 - Return the timeout in seconds (float) associated with socket operations, - or ``None`` if no timeout is set. This reflects the last call to - :meth:`setblocking` or :meth:`settimeout`. + .. method:: gettimeout() -.. method:: socket.ioctl(control, option) + Return the timeout in seconds (float) associated with socket operations, + or ``None`` if no timeout is set. This reflects the last call to + :meth:`setblocking` or :meth:`settimeout`. - The :meth:`ioctl` method is a limited interface to the WSAIoctl system - interface. Please refer to the `Win32 documentation - `_ for more - information. - On other platforms, the generic :func:`fcntl.fcntl` and :func:`fcntl.ioctl` - functions may be used; they accept a socket object as their first argument. + .. method:: ioctl(control, option) - Currently only the following control codes are supported: - ``SIO_RCVALL``, ``SIO_KEEPALIVE_VALS``, and ``SIO_LOOPBACK_FAST_PATH``. + The :meth:`ioctl` method is a limited interface to the WSAIoctl system + interface. Please refer to the `Win32 documentation + `_ for more + information. - .. availability:: Windows + On other platforms, the generic :func:`fcntl.fcntl` and :func:`fcntl.ioctl` + functions may be used; they accept a socket object as their first argument. - .. versionchanged:: 3.6 - ``SIO_LOOPBACK_FAST_PATH`` was added. + Currently only the following control codes are supported: + ``SIO_RCVALL``, ``SIO_KEEPALIVE_VALS``, and ``SIO_LOOPBACK_FAST_PATH``. + .. availability:: Windows -.. method:: socket.listen([backlog]) + .. versionchanged:: 3.6 + ``SIO_LOOPBACK_FAST_PATH`` was added. - Enable a server to accept connections. If *backlog* is specified, it must - be at least 0 (if it is lower, it is set to 0); it specifies the number of - unaccepted connections that the system will allow before refusing new - connections. If not specified, a default reasonable value is chosen. - .. availability:: not WASI. + .. method:: listen([backlog]) - .. versionchanged:: 3.5 - The *backlog* parameter is now optional. + Enable a server to accept connections. If *backlog* is specified, it must + be at least 0 (if it is lower, it is set to 0); it specifies the number of + unaccepted connections that the system will allow before refusing new + connections. If not specified, a default reasonable value is chosen. + .. availability:: not WASI. -.. method:: socket.makefile(mode='r', buffering=None, *, encoding=None, \ - errors=None, newline=None) + .. versionchanged:: 3.5 + The *backlog* parameter is now optional. - .. index:: single: I/O control; buffering - Return a :term:`file object` associated with the socket. The exact returned - type depends on the arguments given to :meth:`makefile`. These arguments are - interpreted the same way as by the built-in :func:`open` function, except - the only supported *mode* values are ``'r'`` (default), ``'w'``, ``'b'``, or - a combination of those. + .. method:: makefile(mode='r', buffering=None, *, encoding=None, \ + errors=None, newline=None) - The socket must be in blocking mode; it can have a timeout, but the file - object's internal buffer may end up in an inconsistent state if a timeout - occurs. + .. index:: single: I/O control; buffering - Closing the file object returned by :meth:`makefile` won't close the - original socket unless all other file objects have been closed and - :meth:`socket.close` has been called on the socket object. + Return a :term:`file object` associated with the socket. The exact returned + type depends on the arguments given to :meth:`makefile`. These arguments are + interpreted the same way as by the built-in :func:`open` function, except + the only supported *mode* values are ``'r'`` (default), ``'w'``, ``'b'``, or + a combination of those. - .. note:: + The socket must be in blocking mode; it can have a timeout, but the file + object's internal buffer may end up in an inconsistent state if a timeout + occurs. - On Windows, the file-like object created by :meth:`makefile` cannot be - used where a file object with a file descriptor is expected, such as the - stream arguments of :meth:`subprocess.Popen`. + Closing the file object returned by :meth:`makefile` won't close the + original socket unless all other file objects have been closed and + :meth:`socket.close` has been called on the socket object. + .. note:: -.. method:: socket.recv(bufsize[, flags]) + On Windows, the file-like object created by :meth:`makefile` cannot be + used where a file object with a file descriptor is expected, such as the + stream arguments of :meth:`subprocess.Popen`. - Receive data from the socket. The return value is a bytes object representing the - data received. The maximum amount of data to be received at once is specified - by *bufsize*. A returned empty bytes object indicates that the client has disconnected. - See the Unix manual page :manpage:`recv(2)` for the meaning of the optional argument - *flags*; it defaults to zero. - .. versionchanged:: 3.5 - If the system call is interrupted and the signal handler does not raise - an exception, the method now retries the system call instead of raising - an :exc:`InterruptedError` exception (see :pep:`475` for the rationale). + .. method:: recv(bufsize[, flags]) + Receive data from the socket. The return value is a bytes object representing the + data received. The maximum amount of data to be received at once is specified + by *bufsize*. A returned empty bytes object indicates that the client has disconnected. + See the Unix manual page :manpage:`recv(2)` for the meaning of the optional argument + *flags*; it defaults to zero. -.. method:: socket.recvfrom(bufsize[, flags]) + .. versionchanged:: 3.5 + If the system call is interrupted and the signal handler does not raise + an exception, the method now retries the system call instead of raising + an :exc:`InterruptedError` exception (see :pep:`475` for the rationale). - Receive data from the socket. The return value is a pair ``(bytes, address)`` - where *bytes* is a bytes object representing the data received and *address* is the - address of the socket sending the data. See the Unix manual page - :manpage:`recv(2)` for the meaning of the optional argument *flags*; it defaults - to zero. (The format of *address* depends on the address family --- see above.) - .. versionchanged:: 3.5 - If the system call is interrupted and the signal handler does not raise - an exception, the method now retries the system call instead of raising - an :exc:`InterruptedError` exception (see :pep:`475` for the rationale). + .. method:: recvfrom(bufsize[, flags]) - .. versionchanged:: 3.7 - For multicast IPv6 address, first item of *address* does not contain - ``%scope_id`` part anymore. In order to get full IPv6 address use - :func:`getnameinfo`. - -.. method:: socket.recvmsg(bufsize[, ancbufsize[, flags]]) - - Receive normal data (up to *bufsize* bytes) and ancillary data from - the socket. The *ancbufsize* argument sets the size in bytes of - the internal buffer used to receive the ancillary data; it defaults - to 0, meaning that no ancillary data will be received. Appropriate - buffer sizes for ancillary data can be calculated using - :func:`CMSG_SPACE` or :func:`CMSG_LEN`, and items which do not fit - into the buffer might be truncated or discarded. The *flags* - argument defaults to 0 and has the same meaning as for - :meth:`recv`. - - The return value is a 4-tuple: ``(data, ancdata, msg_flags, - address)``. The *data* item is a :class:`bytes` object holding the - non-ancillary data received. The *ancdata* item is a list of zero - or more tuples ``(cmsg_level, cmsg_type, cmsg_data)`` representing - the ancillary data (control messages) received: *cmsg_level* and - *cmsg_type* are integers specifying the protocol level and - protocol-specific type respectively, and *cmsg_data* is a - :class:`bytes` object holding the associated data. The *msg_flags* - item is the bitwise OR of various flags indicating conditions on - the received message; see your system documentation for details. - If the receiving socket is unconnected, *address* is the address of - the sending socket, if available; otherwise, its value is - unspecified. - - On some systems, :meth:`sendmsg` and :meth:`recvmsg` can be used to - pass file descriptors between processes over an :const:`AF_UNIX` - socket. When this facility is used (it is often restricted to - :const:`SOCK_STREAM` sockets), :meth:`recvmsg` will return, in its - ancillary data, items of the form ``(socket.SOL_SOCKET, - socket.SCM_RIGHTS, fds)``, where *fds* is a :class:`bytes` object - representing the new file descriptors as a binary array of the - native C :c:expr:`int` type. If :meth:`recvmsg` raises an - exception after the system call returns, it will first attempt to - close any file descriptors received via this mechanism. - - Some systems do not indicate the truncated length of ancillary data - items which have been only partially received. If an item appears - to extend beyond the end of the buffer, :meth:`recvmsg` will issue - a :exc:`RuntimeWarning`, and will return the part of it which is - inside the buffer provided it has not been truncated before the - start of its associated data. - - On systems which support the :const:`SCM_RIGHTS` mechanism, the - following function will receive up to *maxfds* file descriptors, - returning the message data and a list containing the descriptors - (while ignoring unexpected conditions such as unrelated control - messages being received). See also :meth:`sendmsg`. :: - - import socket, array - - def recv_fds(sock, msglen, maxfds): - fds = array.array("i") # Array of ints - msg, ancdata, flags, addr = sock.recvmsg(msglen, socket.CMSG_LEN(maxfds * fds.itemsize)) - for cmsg_level, cmsg_type, cmsg_data in ancdata: - if cmsg_level == socket.SOL_SOCKET and cmsg_type == socket.SCM_RIGHTS: - # Append data, ignoring any truncated integers at the end. - fds.frombytes(cmsg_data[:len(cmsg_data) - (len(cmsg_data) % fds.itemsize)]) - return msg, list(fds) - - .. availability:: Unix. + Receive data from the socket. The return value is a pair ``(bytes, address)`` + where *bytes* is a bytes object representing the data received and *address* is the + address of the socket sending the data. See the Unix manual page + :manpage:`recv(2)` for the meaning of the optional argument *flags*; it defaults + to zero. The format of *address* depends on the address family --- see + :ref:`socket-addresses`. - Most Unix platforms. + .. versionchanged:: 3.5 + If the system call is interrupted and the signal handler does not raise + an exception, the method now retries the system call instead of raising + an :exc:`InterruptedError` exception (see :pep:`475` for the rationale). - .. versionadded:: 3.3 + .. versionchanged:: 3.7 + For multicast IPv6 address, first item of *address* does not contain + ``%scope_id`` part anymore. In order to get full IPv6 address use + :func:`getnameinfo`. - .. versionchanged:: 3.5 - If the system call is interrupted and the signal handler does not raise - an exception, the method now retries the system call instead of raising - an :exc:`InterruptedError` exception (see :pep:`475` for the rationale). - - -.. method:: socket.recvmsg_into(buffers[, ancbufsize[, flags]]) - - Receive normal data and ancillary data from the socket, behaving as - :meth:`recvmsg` would, but scatter the non-ancillary data into a - series of buffers instead of returning a new bytes object. The - *buffers* argument must be an iterable of objects that export - writable buffers (e.g. :class:`bytearray` objects); these will be - filled with successive chunks of the non-ancillary data until it - has all been written or there are no more buffers. The operating - system may set a limit (:func:`~os.sysconf` value ``SC_IOV_MAX``) - on the number of buffers that can be used. The *ancbufsize* and - *flags* arguments have the same meaning as for :meth:`recvmsg`. - - The return value is a 4-tuple: ``(nbytes, ancdata, msg_flags, - address)``, where *nbytes* is the total number of bytes of - non-ancillary data written into the buffers, and *ancdata*, - *msg_flags* and *address* are the same as for :meth:`recvmsg`. - - Example:: - - >>> import socket - >>> s1, s2 = socket.socketpair() - >>> b1 = bytearray(b'----') - >>> b2 = bytearray(b'0123456789') - >>> b3 = bytearray(b'--------------') - >>> s1.send(b'Mary had a little lamb') - 22 - >>> s2.recvmsg_into([b1, memoryview(b2)[2:9], b3]) - (22, [], 0, None) - >>> [b1, b2, b3] - [bytearray(b'Mary'), bytearray(b'01 had a 9'), bytearray(b'little lamb---')] - - .. availability:: Unix. + .. method:: recvmsg(bufsize[, ancbufsize[, flags]]) + + Receive normal data (up to *bufsize* bytes) and ancillary data from + the socket. The *ancbufsize* argument sets the size in bytes of + the internal buffer used to receive the ancillary data; it defaults + to 0, meaning that no ancillary data will be received. Appropriate + buffer sizes for ancillary data can be calculated using + :func:`CMSG_SPACE` or :func:`CMSG_LEN`, and items which do not fit + into the buffer might be truncated or discarded. The *flags* + argument defaults to 0 and has the same meaning as for + :meth:`recv`. + + The return value is a 4-tuple: ``(data, ancdata, msg_flags, + address)``. The *data* item is a :class:`bytes` object holding the + non-ancillary data received. The *ancdata* item is a list of zero + or more tuples ``(cmsg_level, cmsg_type, cmsg_data)`` representing + the ancillary data (control messages) received: *cmsg_level* and + *cmsg_type* are integers specifying the protocol level and + protocol-specific type respectively, and *cmsg_data* is a + :class:`bytes` object holding the associated data. The *msg_flags* + item is the bitwise OR of various flags indicating conditions on + the received message; see your system documentation for details. + If the receiving socket is unconnected, *address* is the address of + the sending socket, if available; otherwise, its value is + unspecified. + + On some systems, :meth:`sendmsg` and :meth:`recvmsg` can be used to + pass file descriptors between processes over an :const:`AF_UNIX` + socket. When this facility is used (it is often restricted to + :const:`SOCK_STREAM` sockets), :meth:`recvmsg` will return, in its + ancillary data, items of the form ``(socket.SOL_SOCKET, + socket.SCM_RIGHTS, fds)``, where *fds* is a :class:`bytes` object + representing the new file descriptors as a binary array of the + native C :c:expr:`int` type. If :meth:`recvmsg` raises an + exception after the system call returns, it will first attempt to + close any file descriptors received via this mechanism. + + Some systems do not indicate the truncated length of ancillary data + items which have been only partially received. If an item appears + to extend beyond the end of the buffer, :meth:`recvmsg` will issue + a :exc:`RuntimeWarning`, and will return the part of it which is + inside the buffer provided it has not been truncated before the + start of its associated data. + + On systems which support the :const:`!SCM_RIGHTS` mechanism, the + following function will receive up to *maxfds* file descriptors, + returning the message data and a list containing the descriptors + (while ignoring unexpected conditions such as unrelated control + messages being received). See also :meth:`sendmsg`. :: + + import socket, array + + def recv_fds(sock, msglen, maxfds): + fds = array.array("i") # Array of ints + msg, ancdata, flags, addr = sock.recvmsg(msglen, socket.CMSG_LEN(maxfds * fds.itemsize)) + for cmsg_level, cmsg_type, cmsg_data in ancdata: + if cmsg_level == socket.SOL_SOCKET and cmsg_type == socket.SCM_RIGHTS: + # Append data, ignoring any truncated integers at the end. + fds.frombytes(cmsg_data[:len(cmsg_data) - (len(cmsg_data) % fds.itemsize)]) + return msg, list(fds) + + .. availability:: Unix. + + Most Unix platforms. + + .. versionadded:: 3.3 + + .. versionchanged:: 3.5 + If the system call is interrupted and the signal handler does not raise + an exception, the method now retries the system call instead of raising + an :exc:`InterruptedError` exception (see :pep:`475` for the rationale). + + + .. method:: recvmsg_into(buffers[, ancbufsize[, flags]]) + + Receive normal data and ancillary data from the socket, behaving as + :meth:`recvmsg` would, but scatter the non-ancillary data into a + series of buffers instead of returning a new bytes object. The + *buffers* argument must be an iterable of objects that export + writable buffers (e.g. :class:`bytearray` objects); these will be + filled with successive chunks of the non-ancillary data until it + has all been written or there are no more buffers. The operating + system may set a limit (:func:`~os.sysconf` value ``SC_IOV_MAX``) + on the number of buffers that can be used. The *ancbufsize* and + *flags* arguments have the same meaning as for :meth:`recvmsg`. + + The return value is a 4-tuple: ``(nbytes, ancdata, msg_flags, + address)``, where *nbytes* is the total number of bytes of + non-ancillary data written into the buffers, and *ancdata*, + *msg_flags* and *address* are the same as for :meth:`recvmsg`. + + Example:: + + >>> import socket + >>> s1, s2 = socket.socketpair() + >>> b1 = bytearray(b'----') + >>> b2 = bytearray(b'0123456789') + >>> b3 = bytearray(b'--------------') + >>> s1.send(b'Mary had a little lamb') + 22 + >>> s2.recvmsg_into([b1, memoryview(b2)[2:9], b3]) + (22, [], 0, None) + >>> [b1, b2, b3] + [bytearray(b'Mary'), bytearray(b'01 had a 9'), bytearray(b'little lamb---')] + + .. availability:: Unix. + + Most Unix platforms. + + .. versionadded:: 3.3 + + + .. method:: recvfrom_into(buffer[, nbytes[, flags]]) + + Receive data from the socket, writing it into *buffer* instead of creating a + new bytestring. The return value is a pair ``(nbytes, address)`` where *nbytes* is + the number of bytes received and *address* is the address of the socket sending + the data. See the Unix manual page :manpage:`recv(2)` for the meaning of the + optional argument *flags*; it defaults to zero. The format of *address* + depends on the address family --- see :ref:`socket-addresses`. + + + .. method:: recv_into(buffer[, nbytes[, flags]]) + + Receive up to *nbytes* bytes from the socket, storing the data into a buffer + rather than creating a new bytestring. If *nbytes* is not specified (or 0), + receive up to the size available in the given buffer. Returns the number of + bytes received. See the Unix manual page :manpage:`recv(2)` for the meaning + of the optional argument *flags*; it defaults to zero. - Most Unix platforms. - .. versionadded:: 3.3 + .. method:: send(bytes[, flags]) + Send data to the socket. The socket must be connected to a remote socket. The + optional *flags* argument has the same meaning as for :meth:`recv`. + Returns the number of bytes sent. Applications are responsible for checking that + all data has been sent; if only some of the data was transmitted, the + application needs to attempt delivery of the remaining data. For further + information on this topic, consult the :ref:`socket-howto`. -.. method:: socket.recvfrom_into(buffer[, nbytes[, flags]]) + .. versionchanged:: 3.5 + If the system call is interrupted and the signal handler does not raise + an exception, the method now retries the system call instead of raising + an :exc:`InterruptedError` exception (see :pep:`475` for the rationale). - Receive data from the socket, writing it into *buffer* instead of creating a - new bytestring. The return value is a pair ``(nbytes, address)`` where *nbytes* is - the number of bytes received and *address* is the address of the socket sending - the data. See the Unix manual page :manpage:`recv(2)` for the meaning of the - optional argument *flags*; it defaults to zero. (The format of *address* - depends on the address family --- see above.) + .. method:: sendall(bytes[, flags]) -.. method:: socket.recv_into(buffer[, nbytes[, flags]]) + Send data to the socket. The socket must be connected to a remote socket. The + optional *flags* argument has the same meaning as for :meth:`recv`. + Unlike :meth:`send`, this method continues to send data from *bytes* until + either all data has been sent or an error occurs. ``None`` is returned on + success. On error, an exception is raised, and there is no way to determine how + much data, if any, was successfully sent. - Receive up to *nbytes* bytes from the socket, storing the data into a buffer - rather than creating a new bytestring. If *nbytes* is not specified (or 0), - receive up to the size available in the given buffer. Returns the number of - bytes received. See the Unix manual page :manpage:`recv(2)` for the meaning - of the optional argument *flags*; it defaults to zero. + .. versionchanged:: 3.5 + The socket timeout is no longer reset each time data is sent successfully. + The socket timeout is now the maximum total duration to send all data. + .. versionchanged:: 3.5 + If the system call is interrupted and the signal handler does not raise + an exception, the method now retries the system call instead of raising + an :exc:`InterruptedError` exception (see :pep:`475` for the rationale). -.. method:: socket.send(bytes[, flags]) - Send data to the socket. The socket must be connected to a remote socket. The - optional *flags* argument has the same meaning as for :meth:`recv` above. - Returns the number of bytes sent. Applications are responsible for checking that - all data has been sent; if only some of the data was transmitted, the - application needs to attempt delivery of the remaining data. For further - information on this topic, consult the :ref:`socket-howto`. + .. method:: sendto(bytes, address) + sendto(bytes, flags, address) - .. versionchanged:: 3.5 - If the system call is interrupted and the signal handler does not raise - an exception, the method now retries the system call instead of raising - an :exc:`InterruptedError` exception (see :pep:`475` for the rationale). + Send data to the socket. The socket should not be connected to a remote socket, + since the destination socket is specified by *address*. The optional *flags* + argument has the same meaning as for :meth:`recv`. Return the number of + bytes sent. The format of *address* depends on the address family --- see + :ref:`socket-addresses`. + .. audit-event:: socket.sendto self,address socket.socket.sendto -.. method:: socket.sendall(bytes[, flags]) + .. versionchanged:: 3.5 + If the system call is interrupted and the signal handler does not raise + an exception, the method now retries the system call instead of raising + an :exc:`InterruptedError` exception (see :pep:`475` for the rationale). - Send data to the socket. The socket must be connected to a remote socket. The - optional *flags* argument has the same meaning as for :meth:`recv` above. - Unlike :meth:`send`, this method continues to send data from *bytes* until - either all data has been sent or an error occurs. ``None`` is returned on - success. On error, an exception is raised, and there is no way to determine how - much data, if any, was successfully sent. - .. versionchanged:: 3.5 - The socket timeout is no longer reset each time data is sent successfully. - The socket timeout is now the maximum total duration to send all data. + .. method:: sendmsg(buffers[, ancdata[, flags[, address]]]) - .. versionchanged:: 3.5 - If the system call is interrupted and the signal handler does not raise - an exception, the method now retries the system call instead of raising - an :exc:`InterruptedError` exception (see :pep:`475` for the rationale). + Send normal and ancillary data to the socket, gathering the + non-ancillary data from a series of buffers and concatenating it + into a single message. The *buffers* argument specifies the + non-ancillary data as an iterable of + :term:`bytes-like objects ` + (e.g. :class:`bytes` objects); the operating system may set a limit + (:func:`~os.sysconf` value ``SC_IOV_MAX``) on the number of buffers + that can be used. The *ancdata* argument specifies the ancillary + data (control messages) as an iterable of zero or more tuples + ``(cmsg_level, cmsg_type, cmsg_data)``, where *cmsg_level* and + *cmsg_type* are integers specifying the protocol level and + protocol-specific type respectively, and *cmsg_data* is a + bytes-like object holding the associated data. Note that + some systems (in particular, systems without :func:`CMSG_SPACE`) + might support sending only one control message per call. The + *flags* argument defaults to 0 and has the same meaning as for + :meth:`send`. If *address* is supplied and not ``None``, it sets a + destination address for the message. The return value is the + number of bytes of non-ancillary data sent. + The following function sends the list of file descriptors *fds* + over an :const:`AF_UNIX` socket, on systems which support the + :const:`!SCM_RIGHTS` mechanism. See also :meth:`recvmsg`. :: -.. method:: socket.sendto(bytes, address) - socket.sendto(bytes, flags, address) + import socket, array - Send data to the socket. The socket should not be connected to a remote socket, - since the destination socket is specified by *address*. The optional *flags* - argument has the same meaning as for :meth:`recv` above. Return the number of - bytes sent. (The format of *address* depends on the address family --- see - above.) + def send_fds(sock, msg, fds): + return sock.sendmsg([msg], [(socket.SOL_SOCKET, socket.SCM_RIGHTS, array.array("i", fds))]) - .. audit-event:: socket.sendto self,address socket.socket.sendto + .. availability:: Unix, not WASI. - .. versionchanged:: 3.5 - If the system call is interrupted and the signal handler does not raise - an exception, the method now retries the system call instead of raising - an :exc:`InterruptedError` exception (see :pep:`475` for the rationale). - - -.. method:: socket.sendmsg(buffers[, ancdata[, flags[, address]]]) - - Send normal and ancillary data to the socket, gathering the - non-ancillary data from a series of buffers and concatenating it - into a single message. The *buffers* argument specifies the - non-ancillary data as an iterable of - :term:`bytes-like objects ` - (e.g. :class:`bytes` objects); the operating system may set a limit - (:func:`~os.sysconf` value ``SC_IOV_MAX``) on the number of buffers - that can be used. The *ancdata* argument specifies the ancillary - data (control messages) as an iterable of zero or more tuples - ``(cmsg_level, cmsg_type, cmsg_data)``, where *cmsg_level* and - *cmsg_type* are integers specifying the protocol level and - protocol-specific type respectively, and *cmsg_data* is a - bytes-like object holding the associated data. Note that - some systems (in particular, systems without :func:`CMSG_SPACE`) - might support sending only one control message per call. The - *flags* argument defaults to 0 and has the same meaning as for - :meth:`send`. If *address* is supplied and not ``None``, it sets a - destination address for the message. The return value is the - number of bytes of non-ancillary data sent. - - The following function sends the list of file descriptors *fds* - over an :const:`AF_UNIX` socket, on systems which support the - :const:`SCM_RIGHTS` mechanism. See also :meth:`recvmsg`. :: - - import socket, array - - def send_fds(sock, msg, fds): - return sock.sendmsg([msg], [(socket.SOL_SOCKET, socket.SCM_RIGHTS, array.array("i", fds))]) + Most Unix platforms. - .. availability:: Unix, not WASI. + .. audit-event:: socket.sendmsg self,address socket.socket.sendmsg - Most Unix platforms. + .. versionadded:: 3.3 - .. audit-event:: socket.sendmsg self,address socket.socket.sendmsg + .. versionchanged:: 3.5 + If the system call is interrupted and the signal handler does not raise + an exception, the method now retries the system call instead of raising + an :exc:`InterruptedError` exception (see :pep:`475` for the rationale). - .. versionadded:: 3.3 + .. method:: sendmsg_afalg([msg], *, op[, iv[, assoclen[, flags]]]) - .. versionchanged:: 3.5 - If the system call is interrupted and the signal handler does not raise - an exception, the method now retries the system call instead of raising - an :exc:`InterruptedError` exception (see :pep:`475` for the rationale). + Specialized version of :meth:`~socket.sendmsg` for :const:`AF_ALG` socket. + Set mode, IV, AEAD associated data length and flags for :const:`AF_ALG` socket. -.. method:: socket.sendmsg_afalg([msg], *, op[, iv[, assoclen[, flags]]]) + .. availability:: Linux >= 2.6.38. - Specialized version of :meth:`~socket.sendmsg` for :const:`AF_ALG` socket. - Set mode, IV, AEAD associated data length and flags for :const:`AF_ALG` socket. + .. versionadded:: 3.6 - .. availability:: Linux >= 2.6.38. + .. method:: sendfile(file, offset=0, count=None) - .. versionadded:: 3.6 + Send a file until EOF is reached by using high-performance + :mod:`os.sendfile` and return the total number of bytes which were sent. + *file* must be a regular file object opened in binary mode. If + :mod:`os.sendfile` is not available (e.g. Windows) or *file* is not a + regular file :meth:`send` will be used instead. *offset* tells from where to + start reading the file. If specified, *count* is the total number of bytes + to transmit as opposed to sending the file until EOF is reached. File + position is updated on return or also in case of error in which case + :meth:`file.tell() ` can be used to figure out the number of + bytes which were sent. The socket must be of :const:`SOCK_STREAM` type. + Non-blocking sockets are not supported. -.. method:: socket.sendfile(file, offset=0, count=None) + .. versionadded:: 3.5 - Send a file until EOF is reached by using high-performance - :mod:`os.sendfile` and return the total number of bytes which were sent. - *file* must be a regular file object opened in binary mode. If - :mod:`os.sendfile` is not available (e.g. Windows) or *file* is not a - regular file :meth:`send` will be used instead. *offset* tells from where to - start reading the file. If specified, *count* is the total number of bytes - to transmit as opposed to sending the file until EOF is reached. File - position is updated on return or also in case of error in which case - :meth:`file.tell() ` can be used to figure out the number of - bytes which were sent. The socket must be of :const:`SOCK_STREAM` type. - Non-blocking sockets are not supported. + .. method:: set_inheritable(inheritable) - .. versionadded:: 3.5 + Set the :ref:`inheritable flag ` of the socket's file + descriptor or socket's handle. -.. method:: socket.set_inheritable(inheritable) + .. versionadded:: 3.4 - Set the :ref:`inheritable flag ` of the socket's file - descriptor or socket's handle. - .. versionadded:: 3.4 + .. method:: setblocking(flag) + Set blocking or non-blocking mode of the socket: if *flag* is false, the + socket is set to non-blocking, else to blocking mode. -.. method:: socket.setblocking(flag) + This method is a shorthand for certain :meth:`~socket.settimeout` calls: - Set blocking or non-blocking mode of the socket: if *flag* is false, the - socket is set to non-blocking, else to blocking mode. + * ``sock.setblocking(True)`` is equivalent to ``sock.settimeout(None)`` - This method is a shorthand for certain :meth:`~socket.settimeout` calls: + * ``sock.setblocking(False)`` is equivalent to ``sock.settimeout(0.0)`` - * ``sock.setblocking(True)`` is equivalent to ``sock.settimeout(None)`` + .. versionchanged:: 3.7 + The method no longer applies :const:`SOCK_NONBLOCK` flag on + :attr:`socket.type`. - * ``sock.setblocking(False)`` is equivalent to ``sock.settimeout(0.0)`` - .. versionchanged:: 3.7 - The method no longer applies :const:`SOCK_NONBLOCK` flag on - :attr:`socket.type`. + .. method:: settimeout(value) + Set a timeout on blocking socket operations. The *value* argument can be a + nonnegative real number expressing seconds, or ``None``. + If a non-zero value is given, subsequent socket operations will raise a + :exc:`timeout` exception if the timeout period *value* has elapsed before + the operation has completed. If zero is given, the socket is put in + non-blocking mode. If ``None`` is given, the socket is put in blocking mode. -.. method:: socket.settimeout(value) + For further information, please consult the :ref:`notes on socket timeouts `. - Set a timeout on blocking socket operations. The *value* argument can be a - nonnegative floating-point number expressing seconds, or ``None``. - If a non-zero value is given, subsequent socket operations will raise a - :exc:`timeout` exception if the timeout period *value* has elapsed before - the operation has completed. If zero is given, the socket is put in - non-blocking mode. If ``None`` is given, the socket is put in blocking mode. + .. versionchanged:: 3.7 + The method no longer toggles :const:`SOCK_NONBLOCK` flag on + :attr:`socket.type`. - For further information, please consult the :ref:`notes on socket timeouts `. - .. versionchanged:: 3.7 - The method no longer toggles :const:`SOCK_NONBLOCK` flag on - :attr:`socket.type`. + .. method:: setsockopt(level, optname, value: int | Buffer) + setsockopt(level, optname, None, optlen: int) + .. index:: pair: module; struct -.. method:: socket.setsockopt(level, optname, value: int) -.. method:: socket.setsockopt(level, optname, value: buffer) - :noindex: -.. method:: socket.setsockopt(level, optname, None, optlen: int) - :noindex: + Set the value of the given socket option (see the Unix manual page + :manpage:`setsockopt(2)`). The needed symbolic constants are defined in this + module (:ref:`!SO_\* etc. `). The value can be an integer, + ``None`` or a :term:`bytes-like object` representing a buffer. In the latter + case it is up to the caller to ensure that the bytestring contains the + proper bits (see the optional built-in module :mod:`struct` for a way to + encode C structures as bytestrings). When *value* is set to ``None``, + *optlen* argument is required. It's equivalent to calling :c:func:`!setsockopt` C + function with ``optval=NULL`` and ``optlen=optlen``. - .. index:: pair: module; struct + .. versionchanged:: 3.5 + Writable :term:`bytes-like object` is now accepted. - Set the value of the given socket option (see the Unix manual page - :manpage:`setsockopt(2)`). The needed symbolic constants are defined in this - module (:ref:`!SO_\* etc. `). The value can be an integer, - ``None`` or a :term:`bytes-like object` representing a buffer. In the later - case it is up to the caller to ensure that the bytestring contains the - proper bits (see the optional built-in module :mod:`struct` for a way to - encode C structures as bytestrings). When *value* is set to ``None``, - *optlen* argument is required. It's equivalent to call :c:func:`setsockopt` C - function with ``optval=NULL`` and ``optlen=optlen``. + .. versionchanged:: 3.6 + setsockopt(level, optname, None, optlen: int) form added. - .. versionchanged:: 3.5 - Writable :term:`bytes-like object` is now accepted. + .. availability:: not WASI. - .. versionchanged:: 3.6 - setsockopt(level, optname, None, optlen: int) form added. - .. availability:: not WASI. + .. method:: shutdown(how) + Shut down one or both halves of the connection. If *how* is :const:`SHUT_RD`, + further receives are disallowed. If *how* is :const:`SHUT_WR`, further sends + are disallowed. If *how* is :const:`SHUT_RDWR`, further sends and receives are + disallowed. -.. method:: socket.shutdown(how) + .. availability:: not WASI. - Shut down one or both halves of the connection. If *how* is :const:`SHUT_RD`, - further receives are disallowed. If *how* is :const:`SHUT_WR`, further sends - are disallowed. If *how* is :const:`SHUT_RDWR`, further sends and receives are - disallowed. - .. availability:: not WASI. + .. method:: share(process_id) + Duplicate a socket and prepare it for sharing with a target process. The + target process must be provided with *process_id*. The resulting bytes object + can then be passed to the target process using some form of interprocess + communication and the socket can be recreated there using :func:`fromshare`. + Once this method has been called, it is safe to close the socket since + the operating system has already duplicated it for the target process. -.. method:: socket.share(process_id) + .. availability:: Windows. - Duplicate a socket and prepare it for sharing with a target process. The - target process must be provided with *process_id*. The resulting bytes object - can then be passed to the target process using some form of interprocess - communication and the socket can be recreated there using :func:`fromshare`. - Once this method has been called, it is safe to close the socket since - the operating system has already duplicated it for the target process. + .. versionadded:: 3.3 - .. availability:: Windows. - .. versionadded:: 3.3 + Note that there are no methods :meth:`!read` or :meth:`!write`; use + :meth:`~socket.recv` and :meth:`~socket.send` without *flags* argument instead. + Socket objects also have these (read-only) attributes that correspond to the + values given to the :class:`~socket.socket` constructor. -Note that there are no methods :meth:`read` or :meth:`write`; use -:meth:`~socket.recv` and :meth:`~socket.send` without *flags* argument instead. -Socket objects also have these (read-only) attributes that correspond to the -values given to the :class:`~socket.socket` constructor. + .. attribute:: family + The socket family. -.. attribute:: socket.family - The socket family. + .. attribute:: type + The socket type. -.. attribute:: socket.type - The socket type. + .. attribute:: proto + The socket protocol. -.. attribute:: socket.proto - The socket protocol. +.. class:: SocketType + The base class of the :class:`~socket.socket` type, re-exported from + :mod:`!_socket`. An instance check such as + ``isinstance(socket(...), SocketType)`` is true, but ``SocketType`` is not + the same as ``type(socket(...))``, which is :class:`~socket.socket` itself. .. _socket-timeouts: @@ -2415,7 +2419,7 @@ lead to this error:: This is because the previous execution has left the socket in a ``TIME_WAIT`` state, and can't be immediately reused. -There is a :mod:`socket` flag to set, in order to prevent this, +There is a :mod:`!socket` flag to set, in order to prevent this, :const:`socket.SO_REUSEADDR`:: s = socket.socket(socket.AF_INET, socket.SOCK_STREAM) diff --git a/Doc/library/socketserver.rst b/Doc/library/socketserver.rst index 59cfa136a3b7da..e1d47b69b7578a 100644 --- a/Doc/library/socketserver.rst +++ b/Doc/library/socketserver.rst @@ -8,7 +8,7 @@ -------------- -The :mod:`socketserver` module simplifies the task of writing network servers. +The :mod:`!socketserver` module simplifies the task of writing network servers. .. include:: ../includes/wasm-notavail.rst @@ -541,10 +541,10 @@ objects that simplify communication by providing the standard file interface):: The difference is that the ``readline()`` call in the second handler will call ``recv()`` multiple times until it encounters a newline character, while the -the first handler had to use a ``recv()`` loop to accumulate data until a +first handler had to use a ``recv()`` loop to accumulate data until a newline itself. If it had just used a single ``recv()`` without the loop it would just have returned what has been received so far from the client. -TCP is stream based: data arrives in the order it was sent, but there no +TCP is stream based: data arrives in the order it was sent, but there is no correlation between client ``send()`` or ``sendall()`` calls and the number of ``recv()`` calls on the server required to receive it. diff --git a/Doc/library/sqlite3.rst b/Doc/library/sqlite3.rst index c615650b622f7f..8e022e1b31d0f3 100644 --- a/Doc/library/sqlite3.rst +++ b/Doc/library/sqlite3.rst @@ -31,7 +31,9 @@ PostgreSQL or Oracle. The :mod:`!sqlite3` module was written by Gerhard Häring. It provides an SQL interface compliant with the DB-API 2.0 specification described by :pep:`249`, and -requires SQLite 3.15.2 or newer. +requires the third-party `SQLite `_ library. + +.. include:: ../includes/optional-module.rst This document includes four main sections: @@ -55,7 +57,7 @@ This document includes four main sections: PEP written by Marc-André Lemburg. -.. We use the following practises for SQL code: +.. We use the following practices for SQL code: - UPPERCASE for keywords - snake_case for schema - single quotes for string literals @@ -289,7 +291,7 @@ Module functions Set it to any combination (using ``|``, bitwise or) of :const:`PARSE_DECLTYPES` and :const:`PARSE_COLNAMES` to enable this. - Column names takes precedence over declared types if both flags are set. + Column names take precedence over declared types if both flags are set. By default (``0``), type detection is disabled. :param isolation_level: @@ -614,7 +616,7 @@ Connection objects supplied, this must be a :term:`callable` returning an instance of :class:`Cursor` or its subclasses. - .. method:: blobopen(table, column, row, /, *, readonly=False, name="main") + .. method:: blobopen(table, column, rowid, /, *, readonly=False, name="main") Open a :class:`Blob` handle to an existing :abbr:`BLOB (Binary Large OBject)`. @@ -625,8 +627,8 @@ Connection objects :param str column: The name of the column where the blob is located. - :param str row: - The name of the row where the blob is located. + :param int rowid: + The row id where the blob is located. :param bool readonly: Set to ``True`` if the blob should be opened without write @@ -1418,6 +1420,9 @@ Connection objects See :ref:`sqlite3-howto-row-factory` for more details. + .. versionchanged:: 3.14.6 + Deleting the ``row_factory`` attribute is no longer allowed. + .. attribute:: text_factory A :term:`callable` that accepts a :class:`bytes` parameter @@ -1427,6 +1432,9 @@ Connection objects See :ref:`sqlite3-howto-encoding` for more details. + .. versionchanged:: 3.14.6 + Deleting the ``text_factory`` attribute is no longer allowed. + .. attribute:: total_changes Return the total number of database rows that have been modified, inserted, or @@ -1492,7 +1500,9 @@ Cursor objects :type parameters: :class:`dict` | :term:`sequence` :raises ProgrammingError: - If *sql* contains more than one SQL statement. + When *sql* contains more than one SQL statement. + When :ref:`named placeholders ` are used + and *parameters* is a sequence instead of a :class:`dict`. If :attr:`~Connection.autocommit` is :data:`LEGACY_TRANSACTION_CONTROL`, @@ -1501,13 +1511,11 @@ Cursor objects and there is no open transaction, a transaction is implicitly opened before executing *sql*. - .. deprecated-removed:: 3.12 3.14 + .. versionchanged:: 3.14 - :exc:`DeprecationWarning` is emitted if + :exc:`ProgrammingError` is emitted if :ref:`named placeholders ` are used and *parameters* is a sequence instead of a :class:`dict`. - Starting with Python 3.14, :exc:`ProgrammingError` will - be raised instead. Use :meth:`executescript` to execute multiple SQL statements. @@ -1529,8 +1537,10 @@ Cursor objects :type parameters: :term:`iterable` :raises ProgrammingError: - If *sql* contains more than one SQL statement, - or is not a DML statement. + When *sql* contains more than one SQL statement + or is not a DML statement, + When :ref:`named placeholders ` are used + and the items in *parameters* are sequences instead of :class:`dict`\s. Example: @@ -1554,14 +1564,12 @@ Cursor objects .. _RETURNING clauses: https://www.sqlite.org/lang_returning.html - .. deprecated-removed:: 3.12 3.14 + .. versionchanged:: 3.14 - :exc:`DeprecationWarning` is emitted if + :exc:`ProgrammingError` is emitted if :ref:`named placeholders ` are used and the items in *parameters* are sequences instead of :class:`dict`\s. - Starting with Python 3.14, :exc:`ProgrammingError` will - be raised instead. .. method:: executescript(sql_script, /) @@ -1612,6 +1620,9 @@ Cursor objects If the *size* parameter is used, then it is best for it to retain the same value from one :meth:`fetchmany` call to the next. + .. versionchanged:: 3.14.1 + Negative *size* values are rejected by raising :exc:`ValueError`. + .. method:: fetchall() Return all (remaining) rows of a query result as a :class:`list`. @@ -1639,6 +1650,9 @@ Cursor objects Read/write attribute that controls the number of rows returned by :meth:`fetchmany`. The default value is 1 which means a single row would be fetched per call. + .. versionchanged:: 3.14.1 + Negative values are rejected by raising :exc:`ValueError`. + .. attribute:: connection Read-only attribute that provides the SQLite database :class:`Connection` @@ -1704,6 +1718,9 @@ Cursor objects See :ref:`sqlite3-howto-row-factory` for more details. + .. versionchanged:: 3.14.6 + Deleting the ``row_factory`` attribute is no longer allowed. + .. The sqlite3.Row example used to be a how-to. It has now been incorporated into the Row reference. We keep the anchor here in order not to break @@ -2280,7 +2297,7 @@ This section shows recipes for common adapters and converters. .. testcode:: - import datetime + import datetime as dt import sqlite3 def adapt_date_iso(val): @@ -2289,27 +2306,27 @@ This section shows recipes for common adapters and converters. def adapt_datetime_iso(val): """Adapt datetime.datetime to timezone-naive ISO 8601 date.""" - return val.isoformat() + return val.replace(tzinfo=None).isoformat() def adapt_datetime_epoch(val): """Adapt datetime.datetime to Unix timestamp.""" return int(val.timestamp()) - sqlite3.register_adapter(datetime.date, adapt_date_iso) - sqlite3.register_adapter(datetime.datetime, adapt_datetime_iso) - sqlite3.register_adapter(datetime.datetime, adapt_datetime_epoch) + sqlite3.register_adapter(dt.date, adapt_date_iso) + sqlite3.register_adapter(dt.datetime, adapt_datetime_iso) + sqlite3.register_adapter(dt.datetime, adapt_datetime_epoch) def convert_date(val): """Convert ISO 8601 date to datetime.date object.""" - return datetime.date.fromisoformat(val.decode()) + return dt.date.fromisoformat(val.decode()) def convert_datetime(val): """Convert ISO 8601 datetime to datetime.datetime object.""" - return datetime.datetime.fromisoformat(val.decode()) + return dt.datetime.fromisoformat(val.decode()) def convert_timestamp(val): """Convert Unix epoch timestamp to datetime.datetime object.""" - return datetime.datetime.fromtimestamp(int(val)) + return dt.datetime.fromtimestamp(int(val)) sqlite3.register_converter("date", convert_date) sqlite3.register_converter("datetime", convert_datetime) @@ -2318,17 +2335,17 @@ This section shows recipes for common adapters and converters. .. testcode:: :hide: - dt = datetime.datetime(2019, 5, 18, 15, 17, 8, 123456) + when = dt.datetime(2019, 5, 18, 15, 17, 8, 123456) - assert adapt_date_iso(dt.date()) == "2019-05-18" - assert convert_date(b"2019-05-18") == dt.date() + assert adapt_date_iso(when.date()) == "2019-05-18" + assert convert_date(b"2019-05-18") == when.date() - assert adapt_datetime_iso(dt) == "2019-05-18T15:17:08.123456" - assert convert_datetime(b"2019-05-18T15:17:08.123456") == dt + assert adapt_datetime_iso(when) == "2019-05-18T15:17:08.123456" + assert convert_datetime(b"2019-05-18T15:17:08.123456") == when # Using current time as fromtimestamp() returns local date/time. # Dropping microseconds as adapt_datetime_epoch truncates fractional second part. - now = datetime.datetime.now().replace(microsecond=0) + now = dt.datetime.now().replace(microsecond=0) current_timestamp = int(now.timestamp()) assert adapt_datetime_epoch(now) == current_timestamp diff --git a/Doc/library/ssl.rst b/Doc/library/ssl.rst index c0dcecf737ef76..92282bf624fe62 100644 --- a/Doc/library/ssl.rst +++ b/Doc/library/ssl.rst @@ -18,8 +18,9 @@ This module provides access to Transport Layer Security (often known as "Secure Sockets Layer") encryption and peer authentication facilities for network sockets, both client-side and server-side. This module uses the OpenSSL -library. It is available on all modern Unix systems, Windows, macOS, and -probably additional platforms, as long as OpenSSL is installed on that platform. +library. + +.. include:: ../includes/optional-module.rst .. note:: @@ -69,7 +70,7 @@ by SSL sockets created through the :meth:`SSLContext.wrap_socket` method. Use of deprecated constants and functions result in deprecation warnings. -Functions, Constants, and Exceptions +Functions, constants, and exceptions ------------------------------------ @@ -125,10 +126,11 @@ Context creation A convenience function helps create :class:`SSLContext` objects for common purposes. -.. function:: create_default_context(purpose=Purpose.SERVER_AUTH, cafile=None, capath=None, cadata=None) +.. function:: create_default_context(purpose=Purpose.SERVER_AUTH, *,\ + cafile=None, capath=None, cadata=None) Return a new :class:`SSLContext` object with default settings for - the given *purpose*. The settings are chosen by the :mod:`ssl` module, + the given *purpose*. The settings are chosen by the :mod:`!ssl` module, and usually represent a higher security level than when calling the :class:`SSLContext` constructor directly. @@ -314,7 +316,7 @@ Exceptions Random generation ^^^^^^^^^^^^^^^^^ -.. function:: RAND_bytes(num) +.. function:: RAND_bytes(num, /) Return *num* cryptographically strong pseudo-random bytes. Raises an :class:`SSLError` if the PRNG has not been seeded with enough data or if the @@ -338,7 +340,7 @@ Random generation :func:`ssl.RAND_egd` and :func:`ssl.RAND_add` to increase the randomness of the pseudo-random number generator. -.. function:: RAND_add(bytes, entropy) +.. function:: RAND_add(bytes, entropy, /) Mix the given *bytes* into the SSL pseudo-random number generator. The parameter *entropy* (a float) is a lower bound on the entropy contained in @@ -357,7 +359,7 @@ Certificate handling .. function:: cert_time_to_seconds(cert_time) - Return the time in seconds since the Epoch, given the ``cert_time`` + Return the time in seconds since the epoch, given the ``cert_time`` string representing the "notBefore" or "notAfter" date from a certificate in ``"%b %d %H:%M:%S %Y %Z"`` strptime format (C locale). @@ -367,12 +369,12 @@ Certificate handling .. doctest:: newcontext >>> import ssl + >>> import datetime as dt >>> timestamp = ssl.cert_time_to_seconds("Jan 5 09:34:43 2018 GMT") >>> timestamp # doctest: +SKIP 1515144883 - >>> from datetime import datetime - >>> print(datetime.utcfromtimestamp(timestamp)) # doctest: +SKIP - 2018-01-05 09:34:43 + >>> print(dt.datetime.fromtimestamp(timestamp, dt.UTC)) # doctest: +SKIP + 2018-01-05 09:34:43+00:00 "notBefore" or "notAfter" dates must use GMT (:rfc:`5280`). @@ -406,12 +408,12 @@ Certificate handling .. versionchanged:: 3.10 The *timeout* parameter was added. -.. function:: DER_cert_to_PEM_cert(DER_cert_bytes) +.. function:: DER_cert_to_PEM_cert(der_cert_bytes) Given a certificate as a DER-encoded blob of bytes, returns a PEM-encoded string version of the same certificate. -.. function:: PEM_cert_to_DER_cert(PEM_cert_string) +.. function:: PEM_cert_to_DER_cert(pem_cert_string) Given a certificate as an ASCII PEM string, returns a DER-encoded sequence of bytes for that same certificate. @@ -1048,7 +1050,7 @@ Constants :attr:`TLSVersion.TLSv1_3` are deprecated. -SSL Sockets +SSL sockets ----------- .. class:: SSLSocket(socket.socket) @@ -1096,7 +1098,7 @@ SSL Sockets :meth:`SSLContext.wrap_socket` to wrap a socket. .. versionchanged:: 3.7 - :class:`SSLSocket` instances must to created with + :class:`SSLSocket` instances must be created with :meth:`~SSLContext.wrap_socket`. In earlier versions, it was possible to create instances directly. This was never documented or officially supported. @@ -1128,10 +1130,10 @@ SSL sockets also have the following additional methods and attributes: .. deprecated:: 3.6 Use :meth:`~SSLSocket.recv` instead of :meth:`~SSLSocket.read`. -.. method:: SSLSocket.write(buf) +.. method:: SSLSocket.write(data) - Write *buf* to the SSL socket and return the number of bytes written. The - *buf* argument must be an object supporting the buffer interface. + Write *data* to the SSL socket and return the number of bytes written. The + *data* argument must be an object supporting the buffer interface. Raise :exc:`SSLWantReadError` or :exc:`SSLWantWriteError` if the socket is :ref:`non-blocking ` and the write would block. @@ -1141,7 +1143,7 @@ SSL sockets also have the following additional methods and attributes: .. versionchanged:: 3.5 The socket timeout is no longer reset each time bytes are received or sent. - The socket timeout is now the maximum total duration to write *buf*. + The socket timeout is now the maximum total duration to write *data*. .. deprecated:: 3.6 Use :meth:`~SSLSocket.send` instead of :meth:`~SSLSocket.write`. @@ -1158,12 +1160,15 @@ SSL sockets also have the following additional methods and attributes: :meth:`~socket.socket.recv` and :meth:`~socket.socket.send` instead of these methods. -.. method:: SSLSocket.do_handshake() +.. method:: SSLSocket.do_handshake(block=False) Perform the SSL setup handshake. + If *block* is true and the timeout obtained by :meth:`~socket.socket.gettimeout` + is zero, the socket is set in blocking mode until the handshake is performed. + .. versionchanged:: 3.4 - The handshake method also performs :func:`match_hostname` when the + The handshake method also performs :func:`!match_hostname` when the :attr:`~SSLContext.check_hostname` attribute of the socket's :attr:`~SSLSocket.context` is true. @@ -1173,7 +1178,7 @@ SSL sockets also have the following additional methods and attributes: .. versionchanged:: 3.7 Hostname or IP address is matched by OpenSSL during handshake. The - function :func:`match_hostname` is no longer used. In case OpenSSL + function :func:`!match_hostname` is no longer used. In case OpenSSL refuses a hostname or IP address, the handshake is aborted early and a TLS alert message is sent to the peer. @@ -1406,7 +1411,7 @@ SSL sockets also have the following additional methods and attributes: .. versionadded:: 3.6 -SSL Contexts +SSL contexts ------------ .. versionadded:: 3.2 @@ -1451,7 +1456,7 @@ to speed up repeated connections from the same clients. TLS 1.3. .. seealso:: - :func:`create_default_context` lets the :mod:`ssl` module choose + :func:`create_default_context` lets the :mod:`!ssl` module choose security settings for a given purpose. .. versionchanged:: 3.6 @@ -1643,7 +1648,7 @@ to speed up repeated connections from the same clients. provided as part of the operating system, though, it is likely to be configured properly. -.. method:: SSLContext.set_ciphers(ciphers) +.. method:: SSLContext.set_ciphers(ciphers, /) Set the available ciphers for sockets created with this context. It should be a string in the `OpenSSL cipher list format @@ -1659,7 +1664,7 @@ to speed up repeated connections from the same clients. TLS 1.3 cipher suites cannot be disabled with :meth:`~SSLContext.set_ciphers`. -.. method:: SSLContext.set_alpn_protocols(protocols) +.. method:: SSLContext.set_alpn_protocols(alpn_protocols) Specify which protocols the socket should advertise during the SSL/TLS handshake. It should be a list of ASCII strings, like ``['http/1.1', @@ -1673,7 +1678,7 @@ to speed up repeated connections from the same clients. .. versionadded:: 3.5 -.. method:: SSLContext.set_npn_protocols(protocols) +.. method:: SSLContext.set_npn_protocols(npn_protocols) Specify which protocols the socket should advertise during the SSL/TLS handshake. It should be a list of strings, like ``['http/1.1', 'spdy/2']``, @@ -1740,7 +1745,7 @@ to speed up repeated connections from the same clients. .. versionadded:: 3.7 -.. attribute:: SSLContext.set_servername_callback(server_name_callback) +.. method:: SSLContext.set_servername_callback(server_name_callback) This is a legacy API retained for backwards compatibility. When possible, you should use :attr:`sni_callback` instead. The given *server_name_callback* @@ -1754,7 +1759,7 @@ to speed up repeated connections from the same clients. .. versionadded:: 3.4 -.. method:: SSLContext.load_dh_params(dhfile) +.. method:: SSLContext.load_dh_params(dhfile, /) Load the key generation parameters for Diffie-Hellman (DH) key exchange. Using DH key exchange improves forward secrecy at the expense of @@ -1767,7 +1772,7 @@ to speed up repeated connections from the same clients. .. versionadded:: 3.3 -.. method:: SSLContext.set_ecdh_curve(curve_name) +.. method:: SSLContext.set_ecdh_curve(curve_name, /) Set the curve name for Elliptic Curve-based Diffie-Hellman (ECDH) key exchange. ECDH is significantly faster than regular DH while arguably @@ -1846,8 +1851,9 @@ to speed up repeated connections from the same clients. .. attribute:: SSLContext.sslsocket_class The return type of :meth:`SSLContext.wrap_socket`, defaults to - :class:`SSLSocket`. The attribute can be overridden on instance of class - in order to return a custom subclass of :class:`SSLSocket`. + :class:`SSLSocket`. The attribute can be assigned to on instances of + :class:`SSLContext` in order to return a custom subclass of + :class:`SSLSocket`. .. versionadded:: 3.7 @@ -1944,7 +1950,7 @@ to speed up repeated connections from the same clients. :attr:`~SSLContext.minimum_version` and :attr:`SSLContext.options` all affect the supported SSL and TLS versions of the context. The implementation does not prevent - invalid combination. For example a context with + invalid combinations. For example a context with :attr:`OP_NO_TLSv1_2` in :attr:`~SSLContext.options` and :attr:`~SSLContext.maximum_version` set to :attr:`TLSVersion.TLSv1_2` will not be able to establish a TLS 1.2 connection. @@ -2521,7 +2527,7 @@ thus several things you need to be aware of: as well. -Memory BIO Support +Memory BIO support ------------------ .. versionadded:: 3.5 @@ -2640,12 +2646,12 @@ purpose. It wraps an OpenSSL memory BIO (Basic IO) object: A boolean indicating whether the memory BIO is current at the end-of-file position. - .. method:: MemoryBIO.read(n=-1) + .. method:: MemoryBIO.read(n=-1, /) Read up to *n* bytes from the memory buffer. If *n* is not specified or negative, all bytes are returned. - .. method:: MemoryBIO.write(buf) + .. method:: MemoryBIO.write(buf, /) Write the bytes from *buf* to the memory BIO. The *buf* argument must be an object supporting the buffer protocol. @@ -2728,7 +2734,7 @@ This common check is automatically performed when .. versionchanged:: 3.7 Hostname matchings is now performed by OpenSSL. Python no longer uses - :func:`match_hostname`. + :func:`!match_hostname`. In server mode, if you want to authenticate your clients using the SSL layer (rather than using a higher-level authentication mechanism), you'll also have @@ -2747,11 +2753,11 @@ disabled by default. :: >>> client_context = ssl.SSLContext(ssl.PROTOCOL_TLS_CLIENT) - >>> client_context.minimum_version = ssl.TLSVersion.TLSv1_3 + >>> client_context.minimum_version = ssl.TLSVersion.TLSv1_2 >>> client_context.maximum_version = ssl.TLSVersion.TLSv1_3 -The SSL context created above will only allow TLSv1.3 and later (if +The SSL client context created above will only allow TLSv1.2 and TLSv1.3 (if supported by your system) connections to a server. :const:`PROTOCOL_TLS_CLIENT` implies certificate validation and hostname checks by default. You have to load certificates into the context. @@ -2819,16 +2825,16 @@ of TLS/SSL. Some new TLS 1.3 features are not yet available. Steve Kent :rfc:`RFC 4086: Randomness Requirements for Security <4086>` - Donald E., Jeffrey I. Schiller + Donald E. Eastlake, Jeffrey I. Schiller, Steve Crocker :rfc:`RFC 5280: Internet X.509 Public Key Infrastructure Certificate and Certificate Revocation List (CRL) Profile <5280>` - D. Cooper + David Cooper et al. :rfc:`RFC 5246: The Transport Layer Security (TLS) Protocol Version 1.2 <5246>` - T. Dierks et. al. + Tim Dierks and Eric Rescorla. :rfc:`RFC 6066: Transport Layer Security (TLS) Extensions <6066>` - D. Eastlake + Donald E. Eastlake `IANA TLS: Transport Layer Security (TLS) Parameters `_ IANA diff --git a/Doc/library/stat.rst b/Doc/library/stat.rst index 8434b2e8c75cf4..bcb1dc269b6107 100644 --- a/Doc/library/stat.rst +++ b/Doc/library/stat.rst @@ -11,7 +11,7 @@ -------------- -The :mod:`stat` module defines constants and functions for interpreting the +The :mod:`!stat` module defines constants and functions for interpreting the results of :func:`os.stat`, :func:`os.fstat` and :func:`os.lstat` (if they exist). For complete details about the :c:func:`stat`, :c:func:`!fstat` and :c:func:`!lstat` calls, consult the documentation for your system. @@ -19,7 +19,7 @@ exist). For complete details about the :c:func:`stat`, :c:func:`!fstat` and .. versionchanged:: 3.4 The stat module is backed by a C implementation. -The :mod:`stat` module defines the following functions to test for specific file +The :mod:`!stat` module defines the following functions to test for specific file types: diff --git a/Doc/library/stdtypes.rst b/Doc/library/stdtypes.rst index 39aaa5da0786f8..d58382eaea794b 100644 --- a/Doc/library/stdtypes.rst +++ b/Doc/library/stdtypes.rst @@ -46,8 +46,10 @@ Any object can be tested for truth value, for use in an :keyword:`if` or By default, an object is considered true unless its class defines either a :meth:`~object.__bool__` method that returns ``False`` or a :meth:`~object.__len__` method that -returns zero, when called with the object. [1]_ Here are most of the built-in -objects considered false: +returns zero, when called with the object. [1]_ If one of the methods raises an +exception when called, the exception is propagated and the object does +not have a truth value (for example, :data:`NotImplemented`). +Here are most of the built-in objects considered false: .. index:: single: None (Built-in object) @@ -164,7 +166,7 @@ This table summarizes the comparison operations: pair: object; numeric pair: objects; comparing -Objects of different types, except different numeric types, never compare equal. +Unless stated otherwise, objects of different types never compare equal. The ``==`` operator is always defined but for some object types (for example, class objects) is equivalent to :keyword:`is`. The ``<``, ``<=``, ``>`` and ``>=`` operators are only defined where they make sense; for example, they raise a @@ -263,9 +265,17 @@ The constructors :func:`int`, :func:`float`, and pair: operator; % (percent) pair: operator; ** +.. _stdtypes-mixed-arithmetic: + Python fully supports mixed arithmetic: when a binary arithmetic operator has -operands of different numeric types, the operand with the "narrower" type is -widened to that of the other, where integer is narrower than floating point. +operands of different built-in numeric types, the operand with the "narrower" +type is widened to that of the other: + +* If both arguments are complex numbers, no conversion is performed; +* if either argument is a complex or a floating-point number, the other is + converted to a floating-point number; +* otherwise, both must be integers and no conversion is necessary. + Arithmetic with complex and real operands is defined by the usual mathematical formula, for example:: @@ -1000,8 +1010,6 @@ operations have the same priority as the corresponding numeric operations. [3]_ pair: slice; operation pair: operator; in pair: operator; not in - single: count() (sequence method) - single: index() (sequence method) +--------------------------+--------------------------------+----------+ | Operation | Result | Notes | @@ -1018,7 +1026,7 @@ operations have the same priority as the corresponding numeric operations. [3]_ | ``s * n`` or | equivalent to adding *s* to | (2)(7) | | ``n * s`` | itself *n* times | | +--------------------------+--------------------------------+----------+ -| ``s[i]`` | *i*\ th item of *s*, origin 0 | \(3) | +| ``s[i]`` | *i*\ th item of *s*, origin 0 | (3)(8) | +--------------------------+--------------------------------+----------+ | ``s[i:j]`` | slice of *s* from *i* to *j* | (3)(4) | +--------------------------+--------------------------------+----------+ @@ -1031,13 +1039,6 @@ operations have the same priority as the corresponding numeric operations. [3]_ +--------------------------+--------------------------------+----------+ | ``max(s)`` | largest item of *s* | | +--------------------------+--------------------------------+----------+ -| ``s.index(x[, i[, j]])`` | index of the first occurrence | \(8) | -| | of *x* in *s* (at or after | | -| | index *i* and before index *j*)| | -+--------------------------+--------------------------------+----------+ -| ``s.count(x)`` | total number of occurrences of | | -| | *x* in *s* | | -+--------------------------+--------------------------------+----------+ Sequences of the same type also support comparisons. In particular, tuples and lists are compared lexicographically by comparing corresponding elements. @@ -1100,11 +1101,14 @@ Notes: still ``0``. (4) - The slice of *s* from *i* to *j* is defined as the sequence of items with index - *k* such that ``i <= k < j``. If *i* or *j* is greater than ``len(s)``, use - ``len(s)``. If *i* is omitted or ``None``, use ``0``. If *j* is omitted or - ``None``, use ``len(s)``. If *i* is greater than or equal to *j*, the slice is - empty. + The slice of *s* from *i* to *j* is defined as the sequence of items with + index *k* such that ``i <= k < j``. + + * If *i* is omitted or ``None``, use ``0``. + * If *j* is omitted or ``None``, use ``len(s)``. + * If *i* or *j* is less than ``-len(s)``, use ``0``. + * If *i* or *j* is greater than ``len(s)``, use ``len(s)``. + * If *i* is greater than or equal to *j*, the slice is empty. (5) The slice of *s* from *i* to *j* with step *k* is defined as the sequence of @@ -1143,12 +1147,41 @@ Notes: concatenation or repetition. (8) - ``index`` raises :exc:`ValueError` when *x* is not found in *s*. - Not all implementations support passing the additional arguments *i* and *j*. - These arguments allow efficient searching of subsections of the sequence. Passing - the extra arguments is roughly equivalent to using ``s[i:j].index(x)``, only - without copying any data and with the returned index being relative to - the start of the sequence rather than the start of the slice. + An :exc:`IndexError` is raised if *i* is outside the sequence range. + +.. rubric:: Sequence Methods + +Sequence types also support the following methods: + +.. method:: list.count(value, /) + range.count(value, /) + tuple.count(value, /) + :no-contents-entry: + :no-index-entry: + :no-typesetting: +.. method:: sequence.count(value, /) + + Return the total number of occurrences of *value* in *sequence*. + +.. method:: list.index(value[, start[, stop]]) + range.index(value[, start[, stop]]) + tuple.index(value[, start[, stop]]) + :no-contents-entry: + :no-index-entry: + :no-typesetting: +.. method:: sequence.index(value[, start[, stop]]) + + Return the index of the first occurrence of *value* in *sequence*. + + Raises :exc:`ValueError` if *value* is not found in *sequence*. + + The *start* or *stop* arguments allow for efficient searching + of subsections of the sequence, beginning at *start* and ending at *stop*. + This is roughly equivalent to ``start + sequence[start:stop].index(value)``, + only without copying any data. + + .. caution:: + Not all sequence types support passing the *start* and *stop* arguments. .. _typesseq-immutable: @@ -1199,14 +1232,6 @@ accepts integers that meet the value restriction ``0 <= x <= 255``). pair: subscript; assignment pair: slice; assignment pair: statement; del - single: append() (sequence method) - single: clear() (sequence method) - single: copy() (sequence method) - single: extend() (sequence method) - single: insert() (sequence method) - single: pop() (sequence method) - single: remove() (sequence method) - single: reverse() (sequence method) +------------------------------+--------------------------------+---------------------+ | Operation | Result | Notes | @@ -1214,11 +1239,15 @@ accepts integers that meet the value restriction ``0 <= x <= 255``). | ``s[i] = x`` | item *i* of *s* is replaced by | | | | *x* | | +------------------------------+--------------------------------+---------------------+ +| ``del s[i]`` | removes item *i* of *s* | | ++------------------------------+--------------------------------+---------------------+ | ``s[i:j] = t`` | slice of *s* from *i* to *j* | | | | is replaced by the contents of | | | | the iterable *t* | | +------------------------------+--------------------------------+---------------------+ -| ``del s[i:j]`` | same as ``s[i:j] = []`` | | +| ``del s[i:j]`` | removes the elements of | | +| | ``s[i:j]`` from the list | | +| | (same as ``s[i:j] = []``) | | +------------------------------+--------------------------------+---------------------+ | ``s[i:j:k] = t`` | the elements of ``s[i:j:k]`` | \(1) | | | are replaced by those of *t* | | @@ -1226,39 +1255,14 @@ accepts integers that meet the value restriction ``0 <= x <= 255``). | ``del s[i:j:k]`` | removes the elements of | | | | ``s[i:j:k]`` from the list | | +------------------------------+--------------------------------+---------------------+ -| ``s.append(x)`` | appends *x* to the end of the | | -| | sequence (same as | | -| | ``s[len(s):len(s)] = [x]``) | | -+------------------------------+--------------------------------+---------------------+ -| ``s.clear()`` | removes all items from *s* | \(5) | -| | (same as ``del s[:]``) | | -+------------------------------+--------------------------------+---------------------+ -| ``s.copy()`` | creates a shallow copy of *s* | \(5) | -| | (same as ``s[:]``) | | -+------------------------------+--------------------------------+---------------------+ -| ``s.extend(t)`` or | extends *s* with the | | -| ``s += t`` | contents of *t* (for the | | +| ``s += t`` | extends *s* with the | | +| | contents of *t* (for the | | | | most part the same as | | | | ``s[len(s):len(s)] = t``) | | +------------------------------+--------------------------------+---------------------+ -| ``s *= n`` | updates *s* with its contents | \(6) | +| ``s *= n`` | updates *s* with its contents | \(2) | | | repeated *n* times | | +------------------------------+--------------------------------+---------------------+ -| ``s.insert(i, x)`` | inserts *x* into *s* at the | | -| | index given by *i* | | -| | (same as ``s[i:i] = [x]``) | | -+------------------------------+--------------------------------+---------------------+ -| ``s.pop()`` or ``s.pop(i)`` | retrieves the item at *i* and | \(2) | -| | also removes it from *s* | | -+------------------------------+--------------------------------+---------------------+ -| ``s.remove(x)`` | removes the first item from | \(3) | -| | *s* where ``s[i]`` is equal to | | -| | *x* | | -+------------------------------+--------------------------------+---------------------+ -| ``s.reverse()`` | reverses the items of *s* in | \(4) | -| | place | | -+------------------------------+--------------------------------+---------------------+ - Notes: @@ -1266,32 +1270,105 @@ Notes: If *k* is not equal to ``1``, *t* must have the same length as the slice it is replacing. (2) - The optional argument *i* defaults to ``-1``, so that by default the last - item is removed and returned. + The value *n* is an integer, or an object implementing + :meth:`~object.__index__`. Zero and negative values of *n* clear + the sequence. Items in the sequence are not copied; they are referenced + multiple times, as explained for ``s * n`` under :ref:`typesseq-common`. -(3) - :meth:`remove` raises :exc:`ValueError` when *x* is not found in *s*. +.. rubric:: Mutable Sequence Methods -(4) - The :meth:`reverse` method modifies the sequence in place for economy of - space when reversing a large sequence. To remind users that it operates by - side effect, it does not return the reversed sequence. +Mutable sequence types also support the following methods: -(5) - :meth:`clear` and :meth:`!copy` are included for consistency with the - interfaces of mutable containers that don't support slicing operations - (such as :class:`dict` and :class:`set`). :meth:`!copy` is not part of the - :class:`collections.abc.MutableSequence` ABC, but most concrete - mutable sequence classes provide it. +.. method:: bytearray.append(value, /) + list.append(value, /) + :no-contents-entry: + :no-index-entry: + :no-typesetting: +.. method:: sequence.append(value, /) + + Append *value* to the end of the sequence. + This is equivalent to writing ``seq[len(seq):len(seq)] = [value]``. + +.. method:: bytearray.clear() + list.clear() + :no-contents-entry: + :no-index-entry: + :no-typesetting: +.. method:: sequence.clear() .. versionadded:: 3.3 - :meth:`clear` and :meth:`!copy` methods. -(6) - The value *n* is an integer, or an object implementing - :meth:`~object.__index__`. Zero and negative values of *n* clear - the sequence. Items in the sequence are not copied; they are referenced - multiple times, as explained for ``s * n`` under :ref:`typesseq-common`. + Remove all items from *sequence*. + This is equivalent to writing ``del sequence[:]``. + +.. method:: bytearray.copy() + list.copy() + :no-contents-entry: + :no-index-entry: + :no-typesetting: +.. method:: sequence.copy() + + .. versionadded:: 3.3 + + Create a shallow copy of *sequence*. + This is equivalent to writing ``sequence[:]``. + + .. hint:: The :meth:`!copy` method is not part of the + :class:`~collections.abc.MutableSequence` :class:`~abc.ABC`, + but most concrete mutable sequence types provide it. + +.. method:: bytearray.extend(iterable, /) + list.extend(iterable, /) + :no-contents-entry: + :no-index-entry: + :no-typesetting: +.. method:: sequence.extend(iterable, /) + + Extend *sequence* with the contents of *iterable*. + For the most part, this is the same as writing + ``seq[len(seq):len(seq)] = iterable``. + +.. method:: bytearray.insert(index, value, /) + list.insert(index, value, /) + :no-contents-entry: + :no-index-entry: + :no-typesetting: +.. method:: sequence.insert(index, value, /) + + Insert *value* into *sequence* at the given *index*. + This is equivalent to writing ``sequence[index:index] = [value]``. + +.. method:: bytearray.pop(index=-1, /) + list.pop(index=-1, /) + :no-contents-entry: + :no-index-entry: + :no-typesetting: +.. method:: sequence.pop(index=-1, /) + + Retrieve the item at *index* and also removes it from *sequence*. + By default, the last item in *sequence* is removed and returned. + +.. method:: bytearray.remove(value, /) + list.remove(value, /) + :no-contents-entry: + :no-index-entry: + :no-typesetting: +.. method:: sequence.remove(value, /) + + Remove the first item from *sequence* where ``sequence[i] == value``. + + Raises :exc:`ValueError` if *value* is not found in *sequence*. + +.. method:: bytearray.reverse() + list.reverse() + :no-contents-entry: + :no-index-entry: + :no-typesetting: +.. method:: sequence.reverse() + + Reverse the items of *sequence* in place. + This method maintains economy of space when reversing a large sequence. + To remind users that it operates by side-effect, it returns ``None``. .. _typesseq-list: @@ -1305,7 +1382,7 @@ Lists are mutable sequences, typically used to store collections of homogeneous items (where the precise degree of similarity will vary by application). -.. class:: list([iterable]) +.. class:: list(iterable=(), /) Lists may be constructed in several ways: @@ -1326,6 +1403,8 @@ application). Many other operations also produce lists, including the :func:`sorted` built-in. + Lists are :ref:`generic ` over the types of their items. + Lists implement all of the :ref:`common ` and :ref:`mutable ` sequence operations. Lists also provide the following additional method: @@ -1372,6 +1451,11 @@ application). list appear empty for the duration, and raises :exc:`ValueError` if it can detect that the list has been mutated during a sort. +.. seealso:: + + For detailed information on thread-safety guarantees for :class:`list` + objects, see :ref:`thread-safety-list`. + .. _typesseq-tuple: @@ -1386,7 +1470,7 @@ built-in). Tuples are also used for cases where an immutable sequence of homogeneous data is needed (such as allowing storage in a :class:`set` or :class:`dict` instance). -.. class:: tuple([iterable]) +.. class:: tuple(iterable=(), /) Tuples may be constructed in a number of ways: @@ -1412,6 +1496,10 @@ homogeneous data is needed (such as allowing storage in a :class:`set` or Tuples implement all of the :ref:`common ` sequence operations. + Tuples are :ref:`generic ` over the types of their contents. + For more information, refer to + :ref:`the typing documentation on annotating tuples `. + For heterogeneous collections of data where access by name is clearer than access by index, :func:`collections.namedtuple` may be a more appropriate choice than a simple tuple object. @@ -1428,8 +1516,8 @@ The :class:`range` type represents an immutable sequence of numbers and is commonly used for looping a specific number of times in :keyword:`for` loops. -.. class:: range(stop) - range(start, stop[, step]) +.. class:: range(stop, /) + range(start, stop, step=1, /) The arguments to the range constructor must be integers (either built-in :class:`int` or any object that implements the :meth:`~object.__index__` special @@ -1632,7 +1720,11 @@ category. | | :meth:`str.strip` | :meth:`bytes.strip` | | +--------------------+----------------------+----------------------+----------------------------+ | | :meth:`str.lstrip` | :meth:`str.rstrip` | :meth:`bytes.lstrip` | :meth:`bytes.rstrip` | -+--------------------------+--------------------+----------------------+----------------------+----------------------------+ +| +--------------------+----------------------+----------------------+----------------------------+ +| | :meth:`str.removeprefix` | :meth:`bytes.removeprefix` | +| +-------------------------------------------+---------------------------------------------------+ +| | :meth:`str.removesuffix` | :meth:`bytes.removesuffix` | ++--------------------------+-------------------------------------------+---------------------------------------------------+ | Translation and Encoding | :meth:`str.translate` | :meth:`bytes.translate` | | +-------------------------------------------+---------------------------------------------------+ | | :meth:`str.maketrans` | :meth:`bytes.maketrans` | @@ -1689,8 +1781,10 @@ multiple fragments. .. index:: single: string; str (built-in class) -.. class:: str(object='') - str(object=b'', encoding='utf-8', errors='strict') +.. class:: str(*, encoding='utf-8', errors='strict') + str(object) + str(object, encoding, errors='strict') + str(object, *, errors) Return a :ref:`string ` version of *object*. If *object* is not provided, returns the empty string. Otherwise, the behavior of ``str()`` @@ -1776,6 +1870,14 @@ expression support in the :mod:`re` module). lowercase letter ``'ß'`` is equivalent to ``"ss"``. Since it is already lowercase, :meth:`lower` would do nothing to ``'ß'``; :meth:`casefold` converts it to ``"ss"``. + For example: + + .. doctest:: + + >>> 'straße'.lower() + 'straße' + >>> 'straße'.casefold() + 'strasse' The casefolding algorithm is `described in section 3.13 'Default Case Folding' of the Unicode Standard @@ -1784,12 +1886,18 @@ expression support in the :mod:`re` module). .. versionadded:: 3.3 -.. method:: str.center(width[, fillchar]) +.. method:: str.center(width, fillchar=' ', /) Return centered in a string of length *width*. Padding is done using the specified *fillchar* (default is an ASCII space). The original string is - returned if *width* is less than or equal to ``len(s)``. + returned if *width* is less than or equal to ``len(s)``. For example:: + >>> 'Python'.center(10) + ' Python ' + >>> 'Python'.center(10, '-') + '--Python--' + >>> 'Python'.center(4) + 'Python' .. method:: str.count(sub[, start[, end]]) @@ -1799,8 +1907,18 @@ expression support in the :mod:`re` module). interpreted as in slice notation. If *sub* is empty, returns the number of empty strings between characters - which is the length of the string plus one. - + which is the length of the string plus one. For example:: + + >>> 'spam, spam, spam'.count('spam') + 3 + >>> 'spam, spam, spam'.count('spam', 5) + 2 + >>> 'spam, spam, spam'.count('spam', 5, 10) + 1 + >>> 'spam, spam, spam'.count('eggs') + 0 + >>> 'spam, spam, spam'.count('') + 17 .. method:: str.encode(encoding="utf-8", errors="strict") @@ -1820,6 +1938,14 @@ expression support in the :mod:`re` module). unless an encoding error actually occurs, :ref:`devmode` is enabled or a :ref:`debug build ` is used. + For example:: + + >>> encoded_str_to_bytes = 'Python'.encode() + >>> type(encoded_str_to_bytes) + + >>> encoded_str_to_bytes + b'Python' + .. versionchanged:: 3.1 Added support for keyword arguments. @@ -1834,7 +1960,19 @@ expression support in the :mod:`re` module). Return ``True`` if the string ends with the specified *suffix*, otherwise return ``False``. *suffix* can also be a tuple of suffixes to look for. With optional *start*, test beginning at that position. With optional *end*, stop comparing - at that position. + at that position. Using *start* and *end* is equivalent to + ``str[start:end].endswith(suffix)``. For example:: + + >>> 'Python'.endswith('on') + True + >>> 'a tuple of suffixes'.endswith(('at', 'in')) + False + >>> 'a tuple of suffixes'.endswith(('at', 'es')) + True + >>> 'Python is amazing'.endswith('is', 0, 9) + True + + See also :meth:`startswith` and :meth:`removesuffix`. .. method:: str.expandtabs(tabsize=8) @@ -1850,12 +1988,15 @@ expression support in the :mod:`re` module). (``\n``) or return (``\r``), it is copied and the current column is reset to zero. Any other character is copied unchanged and the current column is incremented by one regardless of how the character is represented when - printed. + printed. For example:: >>> '01\t012\t0123\t01234'.expandtabs() '01 012 0123 01234' >>> '01\t012\t0123\t01234'.expandtabs(4) '01 012 0123 01234' + >>> print('01\t012\n0123\t01234'.expandtabs(4)) + 01 012 + 0123 01234 .. method:: str.find(sub[, start[, end]]) @@ -1863,6 +2004,14 @@ expression support in the :mod:`re` module). Return the lowest index in the string where substring *sub* is found within the slice ``s[start:end]``. Optional arguments *start* and *end* are interpreted as in slice notation. Return ``-1`` if *sub* is not found. + For example:: + + >>> 'spam, spam, spam'.find('sp') + 0 + >>> 'spam, spam, spam'.find('sp', 5) + 6 + + See also :meth:`rfind` and :meth:`index`. .. note:: @@ -1881,10 +2030,16 @@ expression support in the :mod:`re` module). ``{}``. Each replacement field contains either the numeric index of a positional argument, or the name of a keyword argument. Returns a copy of the string where each replacement field is replaced with the string value of - the corresponding argument. + the corresponding argument. For example: + + .. doctest:: >>> "The sum of 1 + 2 is {0}".format(1+2) 'The sum of 1 + 2 is 3' + >>> "The sum of {a} + {b} is {answer}".format(answer=1+2, a=1, b=2) + 'The sum of 1 + 2 is 3' + >>> "{1} expects the {0} Inquisition!".format("Spanish", "Nobody") + 'Nobody expects the Spanish Inquisition!' See :ref:`formatstrings` for a description of the various formatting options that can be specified in format strings. @@ -1924,7 +2079,20 @@ expression support in the :mod:`re` module). .. method:: str.index(sub[, start[, end]]) Like :meth:`~str.find`, but raise :exc:`ValueError` when the substring is - not found. + not found. For example: + + .. doctest:: + + >>> 'spam, spam, spam'.index('spam') + 0 + >>> 'spam, spam, spam'.index('eggs') + Traceback (most recent call last): + File "", line 1, in + 'spam, spam, spam'.index('eggs') + ~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^ + ValueError: substring not found + + See also :meth:`rindex`. .. method:: str.isalnum() @@ -1932,7 +2100,18 @@ expression support in the :mod:`re` module). Return ``True`` if all characters in the string are alphanumeric and there is at least one character, ``False`` otherwise. A character ``c`` is alphanumeric if one of the following returns ``True``: ``c.isalpha()``, ``c.isdecimal()``, - ``c.isdigit()``, or ``c.isnumeric()``. + ``c.isdigit()``, or ``c.isnumeric()``. For example: + + .. doctest:: + + >>> 'abc123'.isalnum() + True + >>> 'abc123!@#'.isalnum() + False + >>> ''.isalnum() + False + >>> ' '.isalnum() + False .. method:: str.isalpha() @@ -1944,13 +2123,32 @@ expression support in the :mod:`re` module). from the `Alphabetic property defined in the section 4.10 'Letters, Alphabetic, and Ideographic' of the Unicode Standard `_. + For example: + + .. doctest:: + + >>> 'Letters and spaces'.isalpha() + False + >>> 'LettersOnly'.isalpha() + True + >>> 'µ'.isalpha() # non-ASCII characters can be considered alphabetical too + True + + See :ref:`unicode-properties`. .. method:: str.isascii() Return ``True`` if the string is empty or all characters in the string are ASCII, ``False`` otherwise. - ASCII characters have code points in the range U+0000-U+007F. + ASCII characters have code points in the range U+0000-U+007F. For example: + + .. doctest:: + + >>> 'ASCII characters'.isascii() + True + >>> 'µ'.isascii() + False .. versionadded:: 3.7 @@ -1960,9 +2158,18 @@ expression support in the :mod:`re` module). Return ``True`` if all characters in the string are decimal characters and there is at least one character, ``False`` otherwise. Decimal characters are those that can be used to form - numbers in base 10, e.g. U+0660, ARABIC-INDIC DIGIT + numbers in base 10, such as U+0660, ARABIC-INDIC DIGIT ZERO. Formally a decimal character is a character in the Unicode - General Category "Nd". + General Category "Nd". For example: + + .. doctest:: + + >>> '0123456789'.isdecimal() + True + >>> '٠١٢٣٤٥٦٧٨٩'.isdecimal() # Arabic-Indic digits zero to nine + True + >>> 'alphabetic'.isdecimal() + False .. method:: str.isdigit() @@ -1971,9 +2178,25 @@ expression support in the :mod:`re` module). character, ``False`` otherwise. Digits include decimal characters and digits that need special handling, such as the compatibility superscript digits. This covers digits which cannot be used to form numbers in base 10, - like the Kharosthi numbers. Formally, a digit is a character that has the + like the `Kharosthi numbers `__. + Formally, a digit is a character that has the property value Numeric_Type=Digit or Numeric_Type=Decimal. + For example: + + .. doctest:: + + >>> '0123456789'.isdigit() + True + >>> '٠١٢٣٤٥٦٧٨٩'.isdigit() # Arabic-Indic digits zero to nine + True + >>> '⅕'.isdigit() # Vulgar fraction one fifth + False + >>> '²'.isdecimal(), '²'.isdigit(), '²'.isnumeric() + (False, True, True) + + See also :meth:`isdecimal` and :meth:`isnumeric`. + .. method:: str.isidentifier() @@ -2008,11 +2231,25 @@ expression support in the :mod:`re` module). that have the Unicode numeric value property, e.g. U+2155, VULGAR FRACTION ONE FIFTH. Formally, numeric characters are those with the property value Numeric_Type=Digit, Numeric_Type=Decimal or Numeric_Type=Numeric. + For example: + + .. doctest:: + + >>> '0123456789'.isnumeric() + True + >>> '٠١٢٣٤٥٦٧٨٩'.isnumeric() # Arabic-Indic digits zero to nine + True + >>> '⅕'.isnumeric() # Vulgar fraction one fifth + True + >>> '²'.isdecimal(), '²'.isdigit(), '²'.isnumeric() + (False, True, True) + + See also :meth:`isdecimal` and :meth:`isdigit`. .. method:: str.isprintable() - Return true if all characters in the string are printable, false if it + Return ``True`` if all characters in the string are printable, ``False`` if it contains at least one non-printable character. Here "printable" means the character is suitable for :func:`repr` to use in @@ -2026,17 +2263,43 @@ expression support in the :mod:`re` module). Nonprintable characters are those in group Separator or Other (Z or C), except the ASCII space. + For example: + + .. doctest:: + + >>> ''.isprintable(), ' '.isprintable() + (True, True) + >>> '\t'.isprintable(), '\n'.isprintable() + (False, False) + + See also :meth:`isspace`. + .. method:: str.isspace() Return ``True`` if there are only whitespace characters in the string and there is at least one character, ``False`` otherwise. + For example: + + .. doctest:: + + >>> ''.isspace() + False + >>> ' '.isspace() + True + >>> '\t\n'.isspace() # TAB and BREAK LINE + True + >>> '\u3000'.isspace() # IDEOGRAPHIC SPACE + True + A character is *whitespace* if in the Unicode character database (see :mod:`unicodedata`), either its general category is ``Zs`` ("Separator, space"), or its bidirectional class is one of ``WS``, ``B``, or ``S``. + See also :meth:`isprintable`. + .. method:: str.istitle() @@ -2044,6 +2307,19 @@ expression support in the :mod:`re` module). character, for example uppercase characters may only follow uncased characters and lowercase characters only cased ones. Return ``False`` otherwise. + For example: + + .. doctest:: + + >>> 'Spam, Spam, Spam'.istitle() + True + >>> 'spam, spam, spam'.istitle() + False + >>> 'SPAM, SPAM, SPAM'.istitle() + False + + See also :meth:`title`. + .. method:: str.isupper() @@ -2063,32 +2339,59 @@ expression support in the :mod:`re` module). .. _meth-str-join: -.. method:: str.join(iterable) +.. method:: str.join(iterable, /) Return a string which is the concatenation of the strings in *iterable*. A :exc:`TypeError` will be raised if there are any non-string values in *iterable*, including :class:`bytes` objects. The separator between - elements is the string providing this method. + elements is the string providing this method. For example: + + .. doctest:: + + >>> ', '.join(['spam', 'spam', 'spam']) + 'spam, spam, spam' + >>> '-'.join('Python') + 'P-y-t-h-o-n' + See also :meth:`split`. -.. method:: str.ljust(width[, fillchar]) + +.. method:: str.ljust(width, fillchar=' ', /) Return the string left justified in a string of length *width*. Padding is done using the specified *fillchar* (default is an ASCII space). The original string is returned if *width* is less than or equal to ``len(s)``. + For example: + + .. doctest:: + + >>> 'Python'.ljust(10) + 'Python ' + >>> 'Python'.ljust(10, '.') + 'Python....' + >>> 'Monty Python'.ljust(10, '.') + 'Monty Python' + + See also :meth:`rjust`. + .. method:: str.lower() Return a copy of the string with all the cased characters [4]_ converted to - lowercase. + lowercase. For example: + + .. doctest:: + + >>> 'Lower Method Example'.lower() + 'lower method example' The lowercasing algorithm used is `described in section 3.13 'Default Case Folding' of the Unicode Standard `__. -.. method:: str.lstrip([chars]) +.. method:: str.lstrip(chars=None, /) Return a copy of the string with leading characters removed. The *chars* argument is a string specifying the set of characters to be removed. If omitted @@ -2109,7 +2412,8 @@ expression support in the :mod:`re` module). 'three!' -.. staticmethod:: str.maketrans(x[, y[, z]]) +.. staticmethod:: str.maketrans(dict, /) + str.maketrans(from, to, remove='', /) This static method returns a translation table usable for :meth:`str.translate`. @@ -2119,24 +2423,39 @@ expression support in the :mod:`re` module). converted to ordinals. If there are two arguments, they must be strings of equal length, and in the - resulting dictionary, each character in x will be mapped to the character at - the same position in y. If there is a third argument, it must be a string, + resulting dictionary, each character in *from* will be mapped to the character at + the same position in *to*. If there is a third argument, it must be a string, whose characters will be mapped to ``None`` in the result. -.. method:: str.partition(sep) +.. method:: str.partition(sep, /) Split the string at the first occurrence of *sep*, and return a 3-tuple containing the part before the separator, the separator itself, and the part after the separator. If the separator is not found, return a 3-tuple containing the string itself, followed by two empty strings. + For example: + + .. doctest:: + + >>> 'Monty Python'.partition(' ') + ('Monty', ' ', 'Python') + >>> "Monty Python's Flying Circus".partition(' ') + ('Monty', ' ', "Python's Flying Circus") + >>> 'Monty Python'.partition('-') + ('Monty Python', '', '') + + See also :meth:`rpartition`. + .. method:: str.removeprefix(prefix, /) If the string starts with the *prefix* string, return ``string[len(prefix):]``. Otherwise, return a copy of the original - string:: + string: + + .. doctest:: >>> 'TestHook'.removeprefix('Test') 'Hook' @@ -2145,12 +2464,16 @@ expression support in the :mod:`re` module). .. versionadded:: 3.9 + See also :meth:`removesuffix` and :meth:`startswith`. + .. method:: str.removesuffix(suffix, /) If the string ends with the *suffix* string and that *suffix* is not empty, return ``string[:-len(suffix)]``. Otherwise, return a copy of the - original string:: + original string: + + .. doctest:: >>> 'MiscTests'.removesuffix('Tests') 'Misc' @@ -2159,12 +2482,22 @@ expression support in the :mod:`re` module). .. versionadded:: 3.9 + See also :meth:`removeprefix` and :meth:`endswith`. -.. method:: str.replace(old, new, count=-1) + +.. method:: str.replace(old, new, /, count=-1) Return a copy of the string with all occurrences of substring *old* replaced by *new*. If *count* is given, only the first *count* occurrences are replaced. If *count* is not specified or ``-1``, then all occurrences are replaced. + For example: + + .. doctest:: + + >>> 'spam, spam, spam'.replace('spam', 'eggs') + 'eggs, eggs, eggs' + >>> 'spam, spam, spam'.replace('spam', 'eggs', 1) + 'eggs, spam, spam' .. versionchanged:: 3.13 *count* is now supported as a keyword argument. @@ -2175,51 +2508,105 @@ expression support in the :mod:`re` module). Return the highest index in the string where substring *sub* is found, such that *sub* is contained within ``s[start:end]``. Optional arguments *start* and *end* are interpreted as in slice notation. Return ``-1`` on failure. + For example: + + .. doctest:: + + >>> 'spam, spam, spam'.rfind('sp') + 12 + >>> 'spam, spam, spam'.rfind('sp', 0, 10) + 6 + + See also :meth:`find` and :meth:`rindex`. .. method:: str.rindex(sub[, start[, end]]) Like :meth:`rfind` but raises :exc:`ValueError` when the substring *sub* is not found. + For example: + + .. doctest:: + + >>> 'spam, spam, spam'.rindex('spam') + 12 + >>> 'spam, spam, spam'.rindex('eggs') + Traceback (most recent call last): + File "", line 1, in + 'spam, spam, spam'.rindex('eggs') + ~~~~~~~~~~~~~~~~~~~~~~~~~^^^^^^^^ + ValueError: substring not found + + See also :meth:`index` and :meth:`find`. -.. method:: str.rjust(width[, fillchar]) +.. method:: str.rjust(width, fillchar=' ', /) Return the string right justified in a string of length *width*. Padding is done using the specified *fillchar* (default is an ASCII space). The original string is returned if *width* is less than or equal to ``len(s)``. + For example: -.. method:: str.rpartition(sep) + .. doctest:: + + >>> 'Python'.rjust(10) + ' Python' + >>> 'Python'.rjust(10, '.') + '....Python' + >>> 'Monty Python'.rjust(10, '.') + 'Monty Python' + + See also :meth:`ljust` and :meth:`zfill`. + + +.. method:: str.rpartition(sep, /) Split the string at the last occurrence of *sep*, and return a 3-tuple containing the part before the separator, the separator itself, and the part after the separator. If the separator is not found, return a 3-tuple containing two empty strings, followed by the string itself. + For example: + + .. doctest:: + + >>> 'Monty Python'.rpartition(' ') + ('Monty', ' ', 'Python') + >>> "Monty Python's Flying Circus".rpartition(' ') + ("Monty Python's Flying", ' ', 'Circus') + >>> 'Monty Python'.rpartition('-') + ('', '', 'Monty Python') + + See also :meth:`partition`. + .. method:: str.rsplit(sep=None, maxsplit=-1) Return a list of the words in the string, using *sep* as the delimiter string. If *maxsplit* is given, at most *maxsplit* splits are done, the *rightmost* - ones. If *sep* is not specified or ``None``, any whitespace string is a + ones. If *sep* is not specified or ``None``, any + :meth:`whitespace ` string is a separator. Except for splitting from the right, :meth:`rsplit` behaves like :meth:`split` which is described in detail below. -.. method:: str.rstrip([chars]) +.. method:: str.rstrip(chars=None, /) Return a copy of the string with trailing characters removed. The *chars* argument is a string specifying the set of characters to be removed. If omitted or ``None``, the *chars* argument defaults to removing whitespace. The *chars* - argument is not a suffix; rather, all combinations of its values are stripped:: + argument is not a suffix; rather, all combinations of its values are stripped. + For example: + + .. doctest:: >>> ' spacious '.rstrip() ' spacious' >>> 'mississippi'.rstrip('ipz') 'mississ' - See :meth:`str.removesuffix` for a method that will remove a single suffix + See :meth:`removesuffix` for a method that will remove a single suffix string rather than all of a set of characters. For example:: >>> 'Monty Python'.rstrip(' Python') @@ -2227,6 +2614,9 @@ expression support in the :mod:`re` module). >>> 'Monty Python'.removesuffix(' Python') 'Monty' + See also :meth:`strip`. + + .. method:: str.split(sep=None, maxsplit=-1) Return a list of the words in the string, using *sep* as the delimiter @@ -2242,7 +2632,9 @@ expression support in the :mod:`re` module). :func:`re.split`). Splitting an empty string with a specified separator returns ``['']``. - For example:: + For example: + + .. doctest:: >>> '1,2,3'.split(',') ['1', '2', '3'] @@ -2254,13 +2646,16 @@ expression support in the :mod:`re` module). ['1', '2', '3<4'] If *sep* is not specified or is ``None``, a different splitting algorithm is - applied: runs of consecutive whitespace are regarded as a single separator, + applied: runs of consecutive :meth:`whitespace ` are regarded + as a single separator, and the result will contain no empty strings at the start or end if the string has leading or trailing whitespace. Consequently, splitting an empty string or a string consisting of just whitespace with a ``None`` separator returns ``[]``. - For example:: + For example: + + .. doctest:: >>> '1 2 3'.split() ['1', '2', '3'] @@ -2269,6 +2664,22 @@ expression support in the :mod:`re` module). >>> ' 1 2 3 '.split() ['1', '2', '3'] + If *sep* is not specified or is ``None`` and *maxsplit* is ``0``, only + leading runs of consecutive whitespace are considered. + + For example: + + .. doctest:: + + >>> "".split(None, 0) + [] + >>> " ".split(None, 0) + [] + >>> " foo ".split(maxsplit=0) + ['foo '] + + See also :meth:`join` and :meth:`rsplit`. + .. index:: single: universal newlines; str.splitlines method @@ -2343,14 +2754,33 @@ expression support in the :mod:`re` module). test string beginning at that position. With optional *end*, stop comparing string at that position. + For example: -.. method:: str.strip([chars]) + .. doctest:: + + >>> 'Python'.startswith('Py') + True + >>> 'a tuple of prefixes'.startswith(('at', 'a')) + True + >>> 'Python is amazing'.startswith('is', 7) + True + + See also :meth:`endswith` and :meth:`removeprefix`. + + +.. method:: str.strip(chars=None, /) Return a copy of the string with the leading and trailing characters removed. The *chars* argument is a string specifying the set of characters to be removed. If omitted or ``None``, the *chars* argument defaults to removing whitespace. The *chars* argument is not a prefix or suffix; rather, all combinations of its - values are stripped:: + values are stripped. + + Whitespace characters are defined by :meth:`str.isspace`. + + For example: + + .. doctest:: >>> ' spacious '.strip() 'spacious' @@ -2361,18 +2791,37 @@ expression support in the :mod:`re` module). from the string. Characters are removed from the leading end until reaching a string character that is not contained in the set of characters in *chars*. A similar action takes place on the trailing end. - For example:: + + For example: + + .. doctest:: >>> comment_string = '#....... Section 3.2.1 Issue #32 .......' >>> comment_string.strip('.#! ') 'Section 3.2.1 Issue #32' + See also :meth:`rstrip`. + .. method:: str.swapcase() Return a copy of the string with uppercase characters converted to lowercase and - vice versa. Note that it is not necessarily true that - ``s.swapcase().swapcase() == s``. + vice versa. For example: + + .. doctest:: + + >>> 'Hello World'.swapcase() + 'hELLO wORLD' + + Note that it is not necessarily true that ``s.swapcase().swapcase() == s``. + For example: + + .. doctest:: + + >>> 'straße'.swapcase().swapcase() + 'strasse' + + See also :meth:`str.lower` and :meth:`str.upper`. .. method:: str.title() @@ -2408,8 +2857,10 @@ expression support in the :mod:`re` module). >>> titlecase("they're bill's friends.") "They're Bill's Friends." + See also :meth:`istitle`. -.. method:: str.translate(table) + +.. method:: str.translate(table, /) Return a copy of the string in which each character has been mapped through the given translation table. The table must be an object that implements @@ -2440,7 +2891,7 @@ expression support in the :mod:`re` module). `__. -.. method:: str.zfill(width) +.. method:: str.zfill(width, /) Return a copy of the string left filled with ASCII ``'0'`` digits to make a string of length *width*. A leading sign prefix (``'+'``/``'-'``) @@ -2448,13 +2899,17 @@ expression support in the :mod:`re` module). than before. The original string is returned if *width* is less than or equal to ``len(s)``. - For example:: + For example: + + .. doctest:: >>> "42".zfill(5) '00042' >>> "-42".zfill(5) '-0042' + See also :meth:`rjust`. + .. index:: single: ! formatted string literal @@ -2470,6 +2925,8 @@ expression support in the :mod:`re` module). single: : (colon); in formatted string literal single: = (equals); for help in debugging using string literals +.. _stdtypes-fstrings: + Formatted String Literals (f-strings) ------------------------------------- @@ -2478,123 +2935,147 @@ Formatted String Literals (f-strings) The :keyword:`await` and :keyword:`async for` can be used in expressions within f-strings. .. versionchanged:: 3.8 - Added the debugging operator (``=``) + Added the debug specifier (``=``) .. versionchanged:: 3.12 Many restrictions on expressions within f-strings have been removed. Notably, nested strings, comments, and backslashes are now permitted. An :dfn:`f-string` (formally a :dfn:`formatted string literal`) is a string literal that is prefixed with ``f`` or ``F``. -This type of string literal allows embedding arbitrary Python expressions -within *replacement fields*, which are delimited by curly brackets (``{}``). -These expressions are evaluated at runtime, similarly to :meth:`str.format`, -and are converted into regular :class:`str` objects. -For example: +This type of string literal allows embedding the results of arbitrary Python +expressions within *replacement fields*, which are delimited by curly +brackets (``{}``). +Each replacement field must contain an expression, optionally followed by: -.. doctest:: +* a *debug specifier* -- an equal sign (``=``); +* a *conversion specifier* -- ``!s``, ``!r`` or ``!a``; and/or +* a *format specifier* prefixed with a colon (``:``). - >>> who = 'nobody' - >>> nationality = 'Spanish' - >>> f'{who.title()} expects the {nationality} Inquisition!' - 'Nobody expects the Spanish Inquisition!' +See the :ref:`Lexical Analysis section on f-strings ` for details +on the syntax of these fields. -It is also possible to use a multi line f-string: +Debug specifier +^^^^^^^^^^^^^^^ -.. doctest:: +.. versionadded:: 3.8 - >>> f'''This is a string - ... on two lines''' - 'This is a string\non two lines' +If a debug specifier -- an equal sign (``=``) -- appears after the replacement +field expression, the resulting f-string will contain the expression's source, +the equal sign, and the value of the expression. +This is often useful for debugging:: -A single opening curly bracket, ``'{'``, marks a *replacement field* that -can contain any Python expression: + >>> number = 14.3 + >>> f'{number=}' + 'number=14.3' -.. doctest:: +Whitespace before, inside and after the expression, as well as whitespace +after the equal sign, is significant --- it is retained in the result:: - >>> nationality = 'Spanish' - >>> f'The {nationality} Inquisition!' - 'The Spanish Inquisition!' + >>> f'{ number - 4 = }' + ' number - 4 = 10.3' -To include a literal ``{`` or ``}``, use a double bracket: -.. doctest:: +Conversion specifier +^^^^^^^^^^^^^^^^^^^^ - >>> x = 42 - >>> f'{{x}} is {x}' - '{x} is 42' - -Functions can also be used, and :ref:`format specifiers `: - -.. doctest:: - - >>> from math import sqrt - >>> f'√2 \N{ALMOST EQUAL TO} {sqrt(2):.5f}' - '√2 ≈ 1.41421' - -Any non-string expression is converted using :func:`str`, by default: - -.. doctest:: +By default, the value of a replacement field expression is converted to +a string using :func:`str`:: >>> from fractions import Fraction - >>> f'{Fraction(1, 3)}' + >>> one_third = Fraction(1, 3) + >>> f'{one_third}' '1/3' -To use an explicit conversion, use the ``!`` (exclamation mark) operator, -followed by any of the valid formats, which are: +When a debug specifier but no format specifier is used, the default conversion +instead uses :func:`repr`:: -========== ============== -Conversion Meaning -========== ============== -``!a`` :func:`ascii` -``!r`` :func:`repr` -``!s`` :func:`str` -========== ============== + >>> f'{one_third = }' + 'one_third = Fraction(1, 3)' -For example: +The conversion can be specified explicitly using one of these specifiers: -.. doctest:: +* ``!s`` for :func:`str` +* ``!r`` for :func:`repr` +* ``!a`` for :func:`ascii` - >>> from fractions import Fraction - >>> f'{Fraction(1, 3)!s}' +For example:: + + >>> str(one_third) '1/3' - >>> f'{Fraction(1, 3)!r}' + >>> repr(one_third) 'Fraction(1, 3)' - >>> question = '¿Dónde está el Presidente?' - >>> print(f'{question!a}') - '\xbfD\xf3nde est\xe1 el Presidente?' - -While debugging it may be helpful to see both the expression and its value, -by using the equals sign (``=``) after the expression. -This preserves spaces within the brackets, and can be used with a converter. -By default, the debugging operator uses the :func:`repr` (``!r``) conversion. -For example: -.. doctest:: + >>> f'{one_third!s} is {one_third!r}' + '1/3 is Fraction(1, 3)' - >>> from fractions import Fraction - >>> calculation = Fraction(1, 3) - >>> f'{calculation=}' - 'calculation=Fraction(1, 3)' - >>> f'{calculation = }' - 'calculation = Fraction(1, 3)' - >>> f'{calculation = !s}' - 'calculation = 1/3' - -Once the output has been evaluated, it can be formatted using a -:ref:`format specifier ` following a colon (``':'``). -After the expression has been evaluated, and possibly converted to a string, -the :meth:`!__format__` method of the result is called with the format specifier, -or the empty string if no format specifier is given. -The formatted result is then used as the final value for the replacement field. -For example: + >>> string = "¡kočka 😸!" + >>> ascii(string) + "'\\xa1ko\\u010dka \\U0001f638!'" -.. doctest:: + >>> f'{string = !a}' + "string = '\\xa1ko\\u010dka \\U0001f638!'" + + +Format specifier +^^^^^^^^^^^^^^^^ + +After the expression has been evaluated, and possibly converted using an +explicit conversion specifier, it is formatted using the :func:`format` function. +If the replacement field includes a *format specifier* introduced by a colon +(``:``), the specifier is passed to :func:`!format` as the second argument. +The result of :func:`!format` is then used as the final value for the +replacement field. For example:: >>> from fractions import Fraction - >>> f'{Fraction(1, 7):.6f}' - '0.142857' - >>> f'{Fraction(1, 7):_^+10}' - '___+1/7___' + >>> one_third = Fraction(1, 3) + >>> f'{one_third:.6f}' + '0.333333' + >>> f'{one_third:_^+10}' + '___+1/3___' + >>> >>> f'{one_third!r:_^20}' + '___Fraction(1, 3)___' + >>> f'{one_third = :~>10}~' + 'one_third = ~~~~~~~1/3~' + +.. _stdtypes-tstrings: + +Template String Literals (t-strings) +------------------------------------ + +An :dfn:`t-string` (formally a :dfn:`template string literal`) is +a string literal that is prefixed with ``t`` or ``T``. + +These strings follow the same syntax and evaluation rules as +:ref:`formatted string literals `, +with for the following differences: + +* Rather than evaluating to a ``str`` object, template string literals evaluate + to a :class:`string.templatelib.Template` object. + +* The :func:`format` protocol is not used. + Instead, the format specifier and conversions (if any) are passed to + a new :class:`~string.templatelib.Interpolation` object that is created + for each evaluated expression. + It is up to code that processes the resulting :class:`~string.templatelib.Template` + object to decide how to handle format specifiers and conversions. + +* Format specifiers containing nested replacement fields are evaluated eagerly, + prior to being passed to the :class:`~string.templatelib.Interpolation` object. + For instance, an interpolation of the form ``{amount:.{precision}f}`` will + evaluate the inner expression ``{precision}`` to determine the value of the + ``format_spec`` attribute. + If ``precision`` were to be ``2``, the resulting format specifier + would be ``'.2f'``. + +* When the equals sign ``'='`` is provided in an interpolation expression, + the text of the expression is appended to the literal string that precedes + the relevant interpolation. + This includes the equals sign and any surrounding whitespace. + The :class:`!Interpolation` instance for the expression will be created as + normal, except that :attr:`~string.templatelib.Interpolation.conversion` will + be set to '``r``' (:func:`repr`) by default. + If an explicit conversion or format specifier are provided, + this will override the default behaviour. .. _old-string-formatting: @@ -2615,11 +3096,12 @@ For example: The formatting operations described here exhibit a variety of quirks that lead to a number of common errors (such as failing to display tuples and - dictionaries correctly). Using the newer :ref:`formatted string literals - `, the :meth:`str.format` interface, or :ref:`template strings - ` may help avoid these errors. Each of these - alternatives provides their own trade-offs and benefits of simplicity, - flexibility, and/or extensibility. + dictionaries correctly). + + Using :ref:`formatted string literals `, the :meth:`str.format` + interface, or :class:`string.Template` may help avoid these errors. + Each of these alternatives provides their own trade-offs and benefits of + simplicity, flexibility, and/or extensibility. String objects have one unique built-in operation: the ``%`` operator (modulo). This is also known as the string *formatting* or *interpolation* operator. @@ -2757,6 +3239,10 @@ The conversion types are: | | character in the result. | | +------------+-----------------------------------------------------+-------+ +For floating-point formats, the result should be correctly rounded to a given +precision ``p`` of digits after the decimal point. The rounding mode matches +that of the :func:`round` builtin. + Notes: (1) @@ -2831,7 +3317,8 @@ binary protocols are based on the ASCII text encoding, bytes objects offer several methods that are only valid when working with ASCII compatible data and are closely related to string objects in a variety of other ways. -.. class:: bytes([source[, encoding[, errors]]]) +.. class:: bytes(source=b'') + bytes(source, encoding, errors='strict') Firstly, the syntax for bytes literals is largely the same as that for string literals, except that a ``b`` prefix is added: @@ -2871,7 +3358,7 @@ data and are closely related to string objects in a variety of other ways. numbers are a commonly used format for describing binary data. Accordingly, the bytes type has an additional class method to read data in that format: - .. classmethod:: fromhex(string) + .. classmethod:: fromhex(string, /) This :class:`bytes` class method returns a bytes object, decoding the given string object. The string must contain two hexadecimal digits per @@ -2891,7 +3378,8 @@ data and are closely related to string objects in a variety of other ways. A reverse conversion function exists to transform a bytes object into its hexadecimal representation. - .. method:: hex([sep[, bytes_per_sep]]) + .. method:: hex(*, bytes_per_sep=1) + hex(sep, bytes_per_sep=1) Return a string object containing two hexadecimal digits for each byte in the instance. @@ -2940,7 +3428,8 @@ Bytearray Objects :class:`bytearray` objects are a mutable counterpart to :class:`bytes` objects. -.. class:: bytearray([source[, encoding[, errors]]]) +.. class:: bytearray(source=b'') + bytearray(source, encoding, errors='strict') There is no dedicated literal syntax for bytearray objects, instead they are always created by calling the constructor: @@ -2960,7 +3449,7 @@ objects. numbers are a commonly used format for describing binary data. Accordingly, the bytearray type has an additional class method to read data in that format: - .. classmethod:: fromhex(string) + .. classmethod:: fromhex(string, /) This :class:`bytearray` class method returns bytearray object, decoding the given string object. The string must contain two hexadecimal digits @@ -2980,7 +3469,8 @@ objects. A reverse conversion function exists to transform a bytearray object into its hexadecimal representation. - .. method:: hex([sep[, bytes_per_sep]]) + .. method:: hex(*, bytes_per_sep=1) + hex(sep, bytes_per_sep=1) Return a string object containing two hexadecimal digits for each byte in the instance. @@ -2995,7 +3485,7 @@ objects. optional *sep* and *bytes_per_sep* parameters to insert separators between bytes in the hex output. - .. method:: resize(size) + .. method:: resize(size, /) Resize the :class:`bytearray` to contain *size* bytes. *size* must be greater than or equal to 0. @@ -3037,6 +3527,11 @@ The representation of bytearray objects uses the bytes literal format ``bytearray([46, 46, 46])``. You can always convert a bytearray object into a list of integers using ``list(b)``. +.. seealso:: + + For detailed information on thread-safety guarantees for :class:`bytearray` + objects, see :ref:`thread-safety-bytearray`. + .. _bytes-methods: @@ -3218,8 +3713,8 @@ arbitrary binary data. Also accept an integer in the range 0 to 255 as the subsequence. -.. method:: bytes.join(iterable) - bytearray.join(iterable) +.. method:: bytes.join(iterable, /) + bytearray.join(iterable, /) Return a bytes or bytearray object which is the concatenation of the binary data sequences in *iterable*. A :exc:`TypeError` will be raised @@ -3229,8 +3724,8 @@ arbitrary binary data. bytearray object providing this method. -.. staticmethod:: bytes.maketrans(from, to) - bytearray.maketrans(from, to) +.. staticmethod:: bytes.maketrans(from, to, /) + bytearray.maketrans(from, to, /) This static method returns a translation table usable for :meth:`bytes.translate` that will map each character in *from* into the @@ -3240,8 +3735,8 @@ arbitrary binary data. .. versionadded:: 3.1 -.. method:: bytes.partition(sep) - bytearray.partition(sep) +.. method:: bytes.partition(sep, /) + bytearray.partition(sep, /) Split the sequence at the first occurrence of *sep*, and return a 3-tuple containing the part before the separator, the separator itself or its @@ -3253,8 +3748,8 @@ arbitrary binary data. The separator to search for may be any :term:`bytes-like object`. -.. method:: bytes.replace(old, new[, count]) - bytearray.replace(old, new[, count]) +.. method:: bytes.replace(old, new, count=-1, /) + bytearray.replace(old, new, count=-1, /) Return a copy of the sequence with all occurrences of subsequence *old* replaced by *new*. If the optional argument *count* is given, only the @@ -3297,8 +3792,8 @@ arbitrary binary data. Also accept an integer in the range 0 to 255 as the subsequence. -.. method:: bytes.rpartition(sep) - bytearray.rpartition(sep) +.. method:: bytes.rpartition(sep, /) + bytearray.rpartition(sep, /) Split the sequence at the last occurrence of *sep*, and return a 3-tuple containing the part before the separator, the separator itself or its @@ -3348,8 +3843,8 @@ with arbitrary binary data by passing appropriate arguments. Note that all of the bytearray methods in this section do *not* operate in place, and instead produce new objects. -.. method:: bytes.center(width[, fillbyte]) - bytearray.center(width[, fillbyte]) +.. method:: bytes.center(width, fillbyte=b' ', /) + bytearray.center(width, fillbyte=b' ', /) Return a copy of the object centered in a sequence of length *width*. Padding is done using the specified *fillbyte* (default is an ASCII @@ -3362,8 +3857,8 @@ produce new objects. it always produces a new object, even if no changes were made. -.. method:: bytes.ljust(width[, fillbyte]) - bytearray.ljust(width[, fillbyte]) +.. method:: bytes.ljust(width, fillbyte=b' ', /) + bytearray.ljust(width, fillbyte=b' ', /) Return a copy of the object left justified in a sequence of length *width*. Padding is done using the specified *fillbyte* (default is an ASCII @@ -3376,14 +3871,14 @@ produce new objects. it always produces a new object, even if no changes were made. -.. method:: bytes.lstrip([chars]) - bytearray.lstrip([chars]) +.. method:: bytes.lstrip(bytes=None, /) + bytearray.lstrip(bytes=None, /) Return a copy of the sequence with specified leading bytes removed. The - *chars* argument is a binary sequence specifying the set of byte values to - be removed - the name refers to the fact this method is usually used with - ASCII characters. If omitted or ``None``, the *chars* argument defaults - to removing ASCII whitespace. The *chars* argument is not a prefix; + *bytes* argument is a binary sequence specifying the set of byte values to + be removed. If omitted or ``None``, the *bytes* argument defaults + to removing :meth:`ASCII whitespace `. + The *bytes* argument is not a prefix; rather, all combinations of its values are stripped:: >>> b' spacious '.lstrip() @@ -3407,8 +3902,8 @@ produce new objects. it always produces a new object, even if no changes were made. -.. method:: bytes.rjust(width[, fillbyte]) - bytearray.rjust(width[, fillbyte]) +.. method:: bytes.rjust(width, fillbyte=b' ', /) + bytearray.rjust(width, fillbyte=b' ', /) Return a copy of the object right justified in a sequence of length *width*. Padding is done using the specified *fillbyte* (default is an ASCII @@ -3427,19 +3922,20 @@ produce new objects. Split the binary sequence into subsequences of the same type, using *sep* as the delimiter string. If *maxsplit* is given, at most *maxsplit* splits are done, the *rightmost* ones. If *sep* is not specified or ``None``, - any subsequence consisting solely of ASCII whitespace is a separator. + any subsequence consisting solely of + :meth:`ASCII whitespace ` is a separator. Except for splitting from the right, :meth:`rsplit` behaves like :meth:`split` which is described in detail below. -.. method:: bytes.rstrip([chars]) - bytearray.rstrip([chars]) +.. method:: bytes.rstrip(bytes=None, /) + bytearray.rstrip(bytes=None, /) Return a copy of the sequence with specified trailing bytes removed. The - *chars* argument is a binary sequence specifying the set of byte values to - be removed - the name refers to the fact this method is usually used with - ASCII characters. If omitted or ``None``, the *chars* argument defaults to - removing ASCII whitespace. The *chars* argument is not a suffix; rather, + *bytes* argument is a binary sequence specifying the set of byte values to + be removed. If omitted or ``None``, the *bytes* argument defaults to + removing :meth:`ASCII whitespace `. + The *bytes* argument is not a suffix; rather, all combinations of its values are stripped:: >>> b' spacious '.rstrip() @@ -3492,7 +3988,8 @@ produce new objects. [b'1', b'2', b'3<4'] If *sep* is not specified or is ``None``, a different splitting algorithm - is applied: runs of consecutive ASCII whitespace are regarded as a single + is applied: runs of consecutive :meth:`ASCII whitespace ` + are regarded as a single separator, and the result will contain no empty strings at the start or end if the sequence has leading or trailing whitespace. Consequently, splitting an empty sequence or a sequence consisting solely of ASCII @@ -3509,14 +4006,14 @@ produce new objects. [b'1', b'2', b'3'] -.. method:: bytes.strip([chars]) - bytearray.strip([chars]) +.. method:: bytes.strip(bytes=None, /) + bytearray.strip(bytes=None, /) Return a copy of the sequence with specified leading and trailing bytes - removed. The *chars* argument is a binary sequence specifying the set of - byte values to be removed - the name refers to the fact this method is - usually used with ASCII characters. If omitted or ``None``, the *chars* - argument defaults to removing ASCII whitespace. The *chars* argument is + removed. The *bytes* argument is a binary sequence specifying the set of + byte values to be removed. If omitted or ``None``, the *bytes* + argument defaults to removing :meth:`ASCII whitespace `. + The *bytes* argument is not a prefix or suffix; rather, all combinations of its values are stripped:: @@ -3838,8 +4335,8 @@ place, and instead produce new objects. always produces a new object, even if no changes were made. -.. method:: bytes.zfill(width) - bytearray.zfill(width) +.. method:: bytes.zfill(width, /) + bytearray.zfill(width, /) Return a copy of the sequence left filled with ASCII ``b'0'`` digits to make a sequence of length *width*. A leading sign prefix (``b'+'``/ @@ -4087,6 +4584,9 @@ copying. types such as :class:`bytes` and :class:`bytearray`, an element is a single byte, but other types such as :class:`array.array` may have bigger elements. + :class:`!memoryview`\s are :ref:`generic ` over the type of their + underlying data. + ``len(view)`` is equal to the length of :class:`~memoryview.tolist`, which is the nested list representation of the view. If ``view.ndim = 1``, this is equal to the number of elements in the view. @@ -4251,7 +4751,8 @@ copying. in-memory Fortran order is preserved. For non-contiguous views, the data is converted to C first. *order=None* is the same as *order='C'*. - .. method:: hex([sep[, bytes_per_sep]]) + .. method:: hex(*, bytes_per_sep=1) + hex(sep, bytes_per_sep=1) Return a string object containing two hexadecimal digits for each byte in the buffer. :: @@ -4336,7 +4837,8 @@ copying. .. versionadded:: 3.2 - .. method:: cast(format[, shape]) + .. method:: cast(format, /) + cast(format, shape, /) Cast a memoryview to a new format or shape. *shape* defaults to ``[byte_length//new_itemsize]``, which means that the result view @@ -4564,6 +5066,9 @@ copying. .. versionadded:: 3.3 +For information on the thread safety of :class:`memoryview` objects in +the :term:`free-threaded build`, see :ref:`thread-safety-memoryview`. + .. _types-set: @@ -4586,11 +5091,12 @@ other sequence-like behavior. There are currently two built-in set types, :class:`set` and :class:`frozenset`. The :class:`set` type is mutable --- the contents can be changed using methods -like :meth:`~set.add` and :meth:`~set.remove`. Since it is mutable, it has no -hash value and cannot be used as either a dictionary key or as an element of -another set. The :class:`frozenset` type is immutable and :term:`hashable` --- -its contents cannot be altered after it is created; it can therefore be used as -a dictionary key or as an element of another set. +like :meth:`~set.add` and :meth:`~set.remove`. +Since it is mutable, it has no hash value and cannot be used as +either a dictionary key or as an element of another set. +The :class:`frozenset` type is immutable and :term:`hashable` --- +its contents cannot be altered after it is created; +it can therefore be used as a dictionary key or as an element of another set. Non-empty sets (not frozensets) can be created by placing a comma-separated list of elements within braces, for example: ``{'jack', 'sjoerd'}``, in addition to the @@ -4598,8 +5104,8 @@ of elements within braces, for example: ``{'jack', 'sjoerd'}``, in addition to t The constructors for both classes work the same: -.. class:: set([iterable]) - frozenset([iterable]) +.. class:: set(iterable=(), /) + frozenset(iterable=(), /) Return a new set or frozenset object whose elements are taken from *iterable*. The elements of a set must be :term:`hashable`. To @@ -4607,164 +5113,179 @@ The constructors for both classes work the same: objects. If *iterable* is not specified, a new empty set is returned. - Sets can be created by several means: +Sets can be created by several means: - * Use a comma-separated list of elements within braces: ``{'jack', 'sjoerd'}`` - * Use a set comprehension: ``{c for c in 'abracadabra' if c not in 'abc'}`` - * Use the type constructor: ``set()``, ``set('foobar')``, ``set(['a', 'b', 'foo'])`` +* Use a comma-separated list of elements within braces: ``{'jack', 'sjoerd'}`` +* Use a set comprehension: ``{c for c in 'abracadabra' if c not in 'abc'}`` +* Use the type constructor: ``set()``, ``set('foobar')``, ``set(['a', 'b', 'foo'])`` - Instances of :class:`set` and :class:`frozenset` provide the following - operations: +Instances of :class:`set` and :class:`frozenset` provide the following +operations: - .. describe:: len(s) +.. describe:: len(s) - Return the number of elements in set *s* (cardinality of *s*). + Return the number of elements in set *s* (cardinality of *s*). - .. describe:: x in s +.. describe:: x in s - Test *x* for membership in *s*. + Test *x* for membership in *s*. - .. describe:: x not in s +.. describe:: x not in s - Test *x* for non-membership in *s*. + Test *x* for non-membership in *s*. - .. method:: isdisjoint(other) +.. method:: frozenset.isdisjoint(other, /) + set.isdisjoint(other, /) - Return ``True`` if the set has no elements in common with *other*. Sets are - disjoint if and only if their intersection is the empty set. + Return ``True`` if the set has no elements in common with *other*. Sets are + disjoint if and only if their intersection is the empty set. - .. method:: issubset(other) - set <= other +.. method:: frozenset.issubset(other, /) + set.issubset(other, /) +.. describe:: set <= other - Test whether every element in the set is in *other*. + Test whether every element in the set is in *other*. - .. method:: set < other +.. describe:: set < other - Test whether the set is a proper subset of *other*, that is, - ``set <= other and set != other``. + Test whether the set is a proper subset of *other*, that is, + ``set <= other and set != other``. - .. method:: issuperset(other) - set >= other +.. method:: frozenset.issuperset(other, /) + set.issuperset(other, /) +.. describe:: set >= other - Test whether every element in *other* is in the set. + Test whether every element in *other* is in the set. - .. method:: set > other +.. describe:: set > other - Test whether the set is a proper superset of *other*, that is, ``set >= - other and set != other``. + Test whether the set is a proper superset of *other*, that is, ``set >= + other and set != other``. - .. method:: union(*others) - set | other | ... +.. method:: frozenset.union(*others) + set.union(*others) +.. describe:: set | other | ... - Return a new set with elements from the set and all others. + Return a new set with elements from the set and all others. - .. method:: intersection(*others) - set & other & ... +.. method:: frozenset.intersection(*others) + set.intersection(*others) +.. describe:: set & other & ... - Return a new set with elements common to the set and all others. + Return a new set with elements common to the set and all others. - .. method:: difference(*others) - set - other - ... +.. method:: frozenset.difference(*others) + set.difference(*others) +.. describe:: set - other - ... - Return a new set with elements in the set that are not in the others. + Return a new set with elements in the set that are not in the others. - .. method:: symmetric_difference(other) - set ^ other +.. method:: frozenset.symmetric_difference(other, /) + set.symmetric_difference(other, /) +.. describe:: set ^ other - Return a new set with elements in either the set or *other* but not both. + Return a new set with elements in either the set or *other* but not both. - .. method:: copy() +.. method:: frozenset.copy() + set.copy() - Return a shallow copy of the set. + Return a shallow copy of the set. - Note, the non-operator versions of :meth:`union`, :meth:`intersection`, - :meth:`difference`, :meth:`symmetric_difference`, :meth:`issubset`, and - :meth:`issuperset` methods will accept any iterable as an argument. In - contrast, their operator based counterparts require their arguments to be - sets. This precludes error-prone constructions like ``set('abc') & 'cbs'`` - in favor of the more readable ``set('abc').intersection('cbs')``. +Note, the non-operator versions of :meth:`~frozenset.union`, +:meth:`~frozenset.intersection`, :meth:`~frozenset.difference`, :meth:`~frozenset.symmetric_difference`, :meth:`~frozenset.issubset`, and +:meth:`~frozenset.issuperset` methods will accept any iterable as an argument. In +contrast, their operator based counterparts require their arguments to be +sets. This precludes error-prone constructions like ``set('abc') & 'cbs'`` +in favor of the more readable ``set('abc').intersection('cbs')``. - Both :class:`set` and :class:`frozenset` support set to set comparisons. Two - sets are equal if and only if every element of each set is contained in the - other (each is a subset of the other). A set is less than another set if and - only if the first set is a proper subset of the second set (is a subset, but - is not equal). A set is greater than another set if and only if the first set - is a proper superset of the second set (is a superset, but is not equal). +Both :class:`set` and :class:`frozenset` support set to set comparisons. Two +sets are equal if and only if every element of each set is contained in the +other (each is a subset of the other). A set is less than another set if and +only if the first set is a proper subset of the second set (is a subset, but +is not equal). A set is greater than another set if and only if the first set +is a proper superset of the second set (is a superset, but is not equal). - Instances of :class:`set` are compared to instances of :class:`frozenset` - based on their members. For example, ``set('abc') == frozenset('abc')`` - returns ``True`` and so does ``set('abc') in set([frozenset('abc')])``. +Instances of :class:`set` are compared to instances of :class:`frozenset` +based on their members. For example, ``set('abc') == frozenset('abc')`` +returns ``True`` and so does ``set('abc') in set([frozenset('abc')])``. - The subset and equality comparisons do not generalize to a total ordering - function. For example, any two nonempty disjoint sets are not equal and are not - subsets of each other, so *all* of the following return ``False``: ``ab``. +The subset and equality comparisons do not generalize to a total ordering +function. For example, any two nonempty disjoint sets are not equal and are not +subsets of each other, so *all* of the following return ``False``: ``ab``. - Since sets only define partial ordering (subset relationships), the output of - the :meth:`list.sort` method is undefined for lists of sets. +Since sets only define partial ordering (subset relationships), the output of +the :meth:`list.sort` method is undefined for lists of sets. - Set elements, like dictionary keys, must be :term:`hashable`. +Set elements, like dictionary keys, must be :term:`hashable`. - Binary operations that mix :class:`set` instances with :class:`frozenset` - return the type of the first operand. For example: ``frozenset('ab') | - set('bc')`` returns an instance of :class:`frozenset`. +Binary operations that mix :class:`set` instances with :class:`frozenset` +return the type of the first operand. For example: ``frozenset('ab') | +set('bc')`` returns an instance of :class:`frozenset`. - The following table lists operations available for :class:`set` that do not - apply to immutable instances of :class:`frozenset`: +The following table lists operations available for :class:`set` that do not +apply to immutable instances of :class:`frozenset`: - .. method:: update(*others) - set |= other | ... +.. method:: set.update(*others) +.. describe:: set |= other | ... - Update the set, adding elements from all others. + Update the set, adding elements from all others. - .. method:: intersection_update(*others) - set &= other & ... +.. method:: set.intersection_update(*others) +.. describe:: set &= other & ... - Update the set, keeping only elements found in it and all others. + Update the set, keeping only elements found in it and all others. - .. method:: difference_update(*others) - set -= other | ... +.. method:: set.difference_update(*others) +.. describe:: set -= other | ... - Update the set, removing elements found in others. + Update the set, removing elements found in others. - .. method:: symmetric_difference_update(other) - set ^= other +.. method:: set.symmetric_difference_update(other, /) +.. describe:: set ^= other - Update the set, keeping only elements found in either set, but not in both. + Update the set, keeping only elements found in either set, but not in both. - .. method:: add(elem) +.. method:: set.add(elem, /) - Add element *elem* to the set. + Add element *elem* to the set. - .. method:: remove(elem) +.. method:: set.remove(elem, /) - Remove element *elem* from the set. Raises :exc:`KeyError` if *elem* is - not contained in the set. + Remove element *elem* from the set. Raises :exc:`KeyError` if *elem* is + not contained in the set. - .. method:: discard(elem) +.. method:: set.discard(elem, /) - Remove element *elem* from the set if it is present. + Remove element *elem* from the set if it is present. - .. method:: pop() +.. method:: set.pop() - Remove and return an arbitrary element from the set. Raises - :exc:`KeyError` if the set is empty. + Remove and return an arbitrary element from the set. Raises + :exc:`KeyError` if the set is empty. - .. method:: clear() +.. method:: set.clear() - Remove all elements from the set. + Remove all elements from the set. - Note, the non-operator versions of the :meth:`update`, - :meth:`intersection_update`, :meth:`difference_update`, and - :meth:`symmetric_difference_update` methods will accept any iterable as an - argument. +Note, the non-operator versions of the :meth:`~set.update`, +:meth:`~set.intersection_update`, :meth:`~set.difference_update`, and +:meth:`~set.symmetric_difference_update` methods will accept any iterable as an +argument. - Note, the *elem* argument to the :meth:`~object.__contains__`, - :meth:`remove`, and - :meth:`discard` methods may be a set. To support searching for an equivalent - frozenset, a temporary one is created from *elem*. +Note, the *elem* argument to the :meth:`~object.__contains__`, +:meth:`~set.remove`, and +:meth:`~set.discard` methods may be a set. To support searching for an equivalent +frozenset, a temporary one is created from *elem*. + +.. seealso:: + + For detailed information on thread-safety guarantees for :class:`set` + objects, see :ref:`thread-safety-set`. + + Sets and frozensets are :ref:`generic ` over the type of their elements. .. _typesmapping: @@ -4794,8 +5315,8 @@ Values that compare equal (such as ``1``, ``1.0``, and ``True``) can be used interchangeably to index the same dictionary entry. .. class:: dict(**kwargs) - dict(mapping, **kwargs) - dict(iterable, **kwargs) + dict(mapping, /, **kwargs) + dict(iterable, /, **kwargs) Return a new dictionary initialized from an optional positional argument and a possibly empty set of keyword arguments. @@ -4823,7 +5344,10 @@ can be used interchangeably to index the same dictionary entry. being added is already present, the value from the keyword argument replaces the value from the positional argument. - To illustrate, the following examples all return a dictionary equal to + Dictionaries compare equal if and only if they have the same ``(key, + value)`` pairs (regardless of ordering). Order comparisons ('<', '<=', '>=', '>') raise + :exc:`TypeError`. To illustrate dictionary creation and equality, + the following examples all return a dictionary equal to ``{"one": 1, "two": 2, "three": 3}``:: >>> a = dict(one=1, two=2, three=3) @@ -4838,6 +5362,30 @@ can be used interchangeably to index the same dictionary entry. Providing keyword arguments as in the first example only works for keys that are valid Python identifiers. Otherwise, any valid keys can be used. + Dictionaries preserve insertion order. Note that updating a key does not + affect the order. Keys added after deletion are inserted at the end. :: + + >>> d = {"one": 1, "two": 2, "three": 3, "four": 4} + >>> d + {'one': 1, 'two': 2, 'three': 3, 'four': 4} + >>> list(d) + ['one', 'two', 'three', 'four'] + >>> list(d.values()) + [1, 2, 3, 4] + >>> d["one"] = 42 + >>> d + {'one': 42, 'two': 2, 'three': 3, 'four': 4} + >>> del d["two"] + >>> d["two"] = None + >>> d + {'one': 42, 'three': 3, 'four': 4, 'two': None} + + .. versionchanged:: 3.7 + Dictionary order is guaranteed to be insertion order. This behavior was + an implementation detail of CPython from 3.6. + + Dictionaries are :ref:`generic ` over two types, signifying + (respectively) the types of the dictionary's keys and values. These are the operations that dictionaries support (and therefore, custom mapping types should support too): @@ -4857,13 +5405,13 @@ can be used interchangeably to index the same dictionary entry. .. index:: __missing__() - If a subclass of dict defines a method :meth:`__missing__` and *key* + If a subclass of dict defines a method :meth:`~object.__missing__` and *key* is not present, the ``d[key]`` operation calls that method with the key *key* as argument. The ``d[key]`` operation then returns or raises whatever is returned or raised by the ``__missing__(key)`` call. - No other operations or methods invoke :meth:`__missing__`. If - :meth:`__missing__` is not defined, :exc:`KeyError` is raised. - :meth:`__missing__` must be a method; it cannot be an instance variable:: + No other operations or methods invoke :meth:`~object.__missing__`. If + :meth:`~object.__missing__` is not defined, :exc:`KeyError` is raised. + :meth:`~object.__missing__` must be a method; it cannot be an instance variable:: >>> class Counter(dict): ... def __missing__(self, key): @@ -4877,7 +5425,8 @@ can be used interchangeably to index the same dictionary entry. 1 The example above shows part of the implementation of - :class:`collections.Counter`. A different ``__missing__`` method is used + :class:`collections.Counter`. + A different :meth:`!__missing__` method is used by :class:`collections.defaultdict`. .. describe:: d[key] = value @@ -4936,7 +5485,8 @@ can be used interchangeably to index the same dictionary entry. Return a new view of the dictionary's keys. See the :ref:`documentation of view objects `. - .. method:: pop(key[, default]) + .. method:: pop(key, /) + pop(key, default, /) If *key* is in the dictionary, remove it and return its value, else return *default*. If *default* is not given and *key* is not in the dictionary, @@ -4968,9 +5518,11 @@ can be used interchangeably to index the same dictionary entry. with a value of *default* and return *default*. *default* defaults to ``None``. - .. method:: update([other]) + .. method:: update(**kwargs) + update(mapping, /, **kwargs) + update(iterable, /, **kwargs) - Update the dictionary with the key/value pairs from *other*, overwriting + Update the dictionary with the key/value pairs from *mapping* or *iterable* and *kwargs*, overwriting existing keys. Return ``None``. :meth:`update` accepts either another object with a ``keys()`` method (in @@ -5008,32 +5560,6 @@ can be used interchangeably to index the same dictionary entry. .. versionadded:: 3.9 - Dictionaries compare equal if and only if they have the same ``(key, - value)`` pairs (regardless of ordering). Order comparisons ('<', '<=', '>=', '>') raise - :exc:`TypeError`. - - Dictionaries preserve insertion order. Note that updating a key does not - affect the order. Keys added after deletion are inserted at the end. :: - - >>> d = {"one": 1, "two": 2, "three": 3, "four": 4} - >>> d - {'one': 1, 'two': 2, 'three': 3, 'four': 4} - >>> list(d) - ['one', 'two', 'three', 'four'] - >>> list(d.values()) - [1, 2, 3, 4] - >>> d["one"] = 42 - >>> d - {'one': 42, 'two': 2, 'three': 3, 'four': 4} - >>> del d["two"] - >>> d["two"] = None - >>> d - {'one': 42, 'three': 3, 'four': 4, 'two': None} - - .. versionchanged:: 3.7 - Dictionary order is guaranteed to be insertion order. This behavior was - an implementation detail of CPython from 3.6. - Dictionaries and dictionary views are reversible. :: >>> d = {"one": 1, "two": 2, "three": 3, "four": 4} @@ -5055,6 +5581,12 @@ can be used interchangeably to index the same dictionary entry. of a :class:`dict`. +.. seealso:: + + For detailed information on thread-safety guarantees for :class:`dict` + objects, see :ref:`thread-safety-dict`. + + .. _dict-views: Dictionary view objects @@ -5206,9 +5738,11 @@ before the statement body is executed and exited when the statement ends: Returning a true value from this method will cause the :keyword:`with` statement to suppress the exception and continue execution with the statement immediately following the :keyword:`!with` statement. Otherwise the exception continues - propagating after this method has finished executing. Exceptions that occur - during execution of this method will replace any exception that occurred in the - body of the :keyword:`!with` statement. + propagating after this method has finished executing. + + If this method raises an exception while handling an earlier exception from the + :keyword:`with` block, the new exception is raised, and the original exception + is stored in its :attr:`~BaseException.__context__` attribute. The exception passed in should never be reraised explicitly - instead, this method should return a false value to indicate that the method completed @@ -5297,7 +5831,8 @@ type and the :class:`bytes` data type: ``GenericAlias`` objects are instances of the class :class:`types.GenericAlias`, which can also be used to create ``GenericAlias`` -objects directly. +objects directly. Specializations of user-defined :ref:`generic classes ` +may not be instances of :class:`types.GenericAlias`, but they provide similar functionality. .. describe:: T[X, Y, ...] @@ -5346,6 +5881,15 @@ creation:: >>> type(l) + +Instances of ``GenericAlias`` are not classes at runtime, even though they behave like classes (they can be instantiated and subclassed):: + + >>> import inspect + >>> inspect.isclass(list[int]) + False + +This is true for :ref:`user-defined generics ` also. + Calling :func:`repr` or :func:`str` on a generic shows the parameterized type:: >>> repr(list[int]) @@ -5409,6 +5953,7 @@ list is non-exhaustive. * :class:`collections.abc.MutableMapping` * :class:`collections.abc.Sequence` * :class:`collections.abc.MutableSequence` +* :class:`collections.abc.ByteString` * :class:`collections.abc.MappingView` * :class:`collections.abc.KeysView` * :class:`collections.abc.ItemsView` @@ -5684,9 +6229,10 @@ Methods .. index:: pair: object; method -Methods are functions that are called using the attribute notation. There are -two flavors: :ref:`built-in methods ` (such as :meth:`append` -on lists) and :ref:`class instance method `. +Methods are functions that are called using the attribute notation. +There are two flavors: :ref:`built-in methods ` +(such as :meth:`~list.append` on lists) +and :ref:`class instance method `. Built-in methods are described with the types that support them. If you access a method (a function defined in a class namespace) through an @@ -5792,13 +6338,34 @@ It is written as ``None``. The Ellipsis Object ------------------- -This object is commonly used by slicing (see :ref:`slicings`). It supports no -special operations. There is exactly one ellipsis object, named +This object is commonly used to indicate that something is omitted. +It supports no special operations. There is exactly one ellipsis object, named :const:`Ellipsis` (a built-in name). ``type(Ellipsis)()`` produces the :const:`Ellipsis` singleton. It is written as ``Ellipsis`` or ``...``. +In typical use, ``...`` as the ``Ellipsis`` object appears in a few different +places, for instance: + +- In type annotations, such as :ref:`callable arguments ` + or :ref:`tuple elements `. + +- As the body of a function instead of a :ref:`pass statement `. + +- In third-party libraries, such as `Numpy's slicing and striding + `_. + +Python also uses three dots in ways that are not ``Ellipsis`` objects, for instance: + +- Doctest's :const:`ELLIPSIS `, as a pattern for missing content. + +- The default Python prompt of the :term:`interactive` shell when partial input is incomplete. + +Lastly, the Python documentation often uses three dots in conventional English +usage to mean omitted content, even in code examples that also use them as the +``Ellipsis``. + .. _bltin-notimplemented-object: diff --git a/Doc/library/string.rst b/Doc/library/string.rst index b44d98819b6998..f1abed91d20ed5 100644 --- a/Doc/library/string.rst +++ b/Doc/library/string.rst @@ -4,7 +4,7 @@ .. module:: string :synopsis: Common string operations. -**Source code:** :source:`Lib/string.py` +**Source code:** :source:`Lib/string/__init__.py` -------------- @@ -82,12 +82,12 @@ The constants defined in this module are: .. _string-formatting: -Custom String Formatting +Custom string formatting ------------------------ The built-in string class provides the ability to do complex variable substitutions and value formatting via the :meth:`~str.format` method described in -:pep:`3101`. The :class:`Formatter` class in the :mod:`string` module allows +:pep:`3101`. The :class:`Formatter` class in the :mod:`!string` module allows you to create and customize your own string formatting behaviors using the same implementation as the built-in :meth:`~str.format` method. @@ -192,14 +192,15 @@ implementation as the built-in :meth:`~str.format` method. .. _formatstrings: -Format String Syntax +Format string syntax -------------------- The :meth:`str.format` method and the :class:`Formatter` class share the same syntax for format strings (although in the case of :class:`Formatter`, subclasses can define their own format string syntax). The syntax is -related to that of :ref:`formatted string literals `, but it is -less sophisticated and, in particular, does not support arbitrary expressions. +related to that of :ref:`formatted string literals ` and +:ref:`template string literals `, but it is less sophisticated +and, in particular, does not support arbitrary expressions in interpolations. .. index:: single: {} (curly brackets); in string formatting @@ -264,6 +265,8 @@ Some simple format string examples:: "Weight in tons {0.weight}" # 'weight' attribute of first positional arg "Units destroyed: {players[0]}" # First element of keyword argument 'players'. +.. _formatstrings-conversion: + The *conversion* field causes a type coercion before formatting. Normally, the job of formatting a value is done by the :meth:`~object.__format__` method of the value itself. However, in some cases it is desirable to force a type to be formatted @@ -301,12 +304,12 @@ See the :ref:`formatexamples` section for some examples. .. _formatspec: -Format Specification Mini-Language +Format specification mini-language ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ "Format specifications" are used within replacement fields contained within a format string to define how individual values are presented (see -:ref:`formatstrings` and :ref:`f-strings`). +:ref:`formatstrings`, :ref:`f-strings`, and :ref:`t-strings`). They can also be passed directly to the built-in :func:`format` function. Each formattable type may define how the format specification is to be interpreted. @@ -328,7 +331,7 @@ The general form of a *standard format specifier* is: sign: "+" | "-" | " " width_and_precision: [`width_with_grouping`][`precision_with_grouping`] width_with_grouping: [`width`][`grouping`] - precision_with_grouping: "." [`precision`][`grouping`] + precision_with_grouping: "." [`precision`][`grouping`] | "." `grouping` width: `~python-grammar:digit`+ precision: `~python-grammar:digit`+ grouping: "," | "_" @@ -469,7 +472,9 @@ of a number respectively. It can be one of the following: | | this option is not supported. | +---------+----------------------------------------------------------+ -For a locale aware separator, use the ``'n'`` presentation type instead. +For a locale-aware separator, use the ``'n'`` +:ref:`float presentation type ` or +:ref:`integer presentation type ` instead. .. versionchanged:: 3.1 Added the ``','`` option (see also :pep:`378`). @@ -515,9 +520,14 @@ The available integer presentation types are: | | In case ``'#'`` is specified, the prefix ``'0x'`` will | | | be upper-cased to ``'0X'`` as well. | +---------+----------------------------------------------------------+ - | ``'n'`` | Number. This is the same as ``'d'``, except that it uses | + | ``'n'`` | .. _n-format-integer: | + | | | + | | Number. This is the same as ``'d'``, except that it uses | | | the current locale setting to insert the appropriate | - | | digit group separators. | + | | digit group separators. Note that the default locale is | + | | not the system locale. Depending on your use case, you | + | | may wish to set :const:`~locale.LC_NUMERIC` with | + | | :func:`locale.setlocale` before using ``'n'``. | +---------+----------------------------------------------------------+ | None | The same as ``'d'``. | +---------+----------------------------------------------------------+ @@ -543,6 +553,9 @@ The available presentation types for :class:`float` and | | :class:`float`, and shows all coefficient digits | | | for :class:`~decimal.Decimal`. If ``p=0``, the decimal | | | point is omitted unless the ``#`` option is used. | + | | | + | | For :class:`float`, the exponent always contains at | + | | least two digits, and is zero if the value is zero. | +---------+----------------------------------------------------------+ | ``'E'`` | Scientific notation. Same as ``'e'`` except it uses | | | an upper case 'E' as the separator character. | @@ -597,10 +610,15 @@ The available presentation types for :class:`float` and | | ``'E'`` if the number gets too large. The | | | representations of infinity and NaN are uppercased, too. | +---------+----------------------------------------------------------+ - | ``'n'`` | Number. This is the same as ``'g'``, except that it uses | + | ``'n'`` | .. _n-format-float: | + | | | + | | Number. This is the same as ``'g'``, except that it uses | | | the current locale setting to insert the appropriate | - | | digit group separators | - | | for the integral part of a number. | + | | digit group separators for the integral part of a | + | | number. Note that the default locale is not the system | + | | locale. Depending on your use case, you may wish to set | + | | :const:`~locale.LC_NUMERIC` with | + | | :func:`locale.setlocale` before using ``'n'``. | +---------+----------------------------------------------------------+ | ``'%'`` | Percentage. Multiplies the number by 100 and displays | | | in fixed (``'f'``) format, followed by a percent sign. | @@ -753,8 +771,8 @@ Expressing a percentage:: Using type-specific formatting:: - >>> import datetime - >>> d = datetime.datetime(2010, 7, 4, 12, 15, 58) + >>> import datetime as dt + >>> d = dt.datetime(2010, 7, 4, 12, 15, 58) >>> '{:%Y-%m-%d %H:%M:%S}'.format(d) '2010-07-04 12:15:58' @@ -789,10 +807,22 @@ Nesting arguments and more complex examples:: -.. _template-strings: +.. _template-strings-pep292: -Template strings ----------------- +Template strings ($-strings) +---------------------------- + +.. note:: + + The feature described here was introduced in Python 2.4; + a simple templating method based upon regular expressions. + It predates :meth:`str.format`, :ref:`formatted string literals `, + and :ref:`template string literals `. + + It is unrelated to template string literals (t-strings), + which were introduced in Python 3.14. + These evaluate to :class:`string.templatelib.Template` objects, + found in the :mod:`string.templatelib` module. Template strings provide simpler string substitutions as described in :pep:`292`. A primary use case for template strings is for @@ -822,7 +852,7 @@ Template strings support ``$``-based substitutions, using the following rules: Any other appearance of ``$`` in the string will result in a :exc:`ValueError` being raised. -The :mod:`string` module provides a :class:`Template` class that implements +The :mod:`!string` module provides a :class:`Template` class that implements these rules. The methods of :class:`Template` are: @@ -858,7 +888,7 @@ these rules. The methods of :class:`Template` are: .. method:: is_valid() - Returns false if the template has invalid placeholders that will cause + Returns ``False`` if the template has invalid placeholders that will cause :meth:`substitute` to raise :exc:`ValueError`. .. versionadded:: 3.11 @@ -941,7 +971,8 @@ attributes: Alternatively, you can provide the entire regular expression pattern by overriding the class attribute *pattern*. If you do this, the value must be a -regular expression object with four named capturing groups. The capturing +regular expression pattern string, or a compiled regular expression +object, with four named capturing groups. The capturing groups correspond to the rules given above, along with the invalid placeholder rule: diff --git a/Doc/library/string.templatelib.rst b/Doc/library/string.templatelib.rst new file mode 100644 index 00000000000000..6e91850fdf59ca --- /dev/null +++ b/Doc/library/string.templatelib.rst @@ -0,0 +1,351 @@ +:mod:`!string.templatelib` --- Support for template string literals +=================================================================== + +.. module:: string.templatelib + :synopsis: Support for template string literals. + +**Source code:** :source:`Lib/string/templatelib.py` + +-------------- + +.. seealso:: + + * :ref:`Format strings ` + * :ref:`Template string literal (t-string) syntax ` + * :pep:`750` + +.. _template-strings: + +Template strings +---------------- + +.. versionadded:: 3.14 + +Template strings are a mechanism for custom string processing. +They have the full flexibility of Python's :ref:`f-strings`, +but return a :class:`Template` instance that gives access +to the static and interpolated (in curly brackets) parts of a string +*before* they are combined. + +To write a t-string, use a ``'t'`` prefix instead of an ``'f'``, like so: + +.. code-block:: pycon + + >>> pi = 3.14 + >>> t't-strings are new in Python {pi!s}!' + Template( + strings=('t-strings are new in Python ', '!'), + interpolations=(Interpolation(3.14, 'pi', 's', ''),) + ) + +Types +----- + +.. class:: Template + + The :class:`!Template` class describes the contents of a template string. + It is immutable, meaning that attributes of a template cannot be reassigned. + + The most common way to create a :class:`!Template` instance is to use the + :ref:`template string literal syntax `. + This syntax is identical to that of :ref:`f-strings `, + except that it uses a ``t`` prefix in place of an ``f``: + + >>> cheese = 'Red Leicester' + >>> template = t"We're fresh out of {cheese}, sir." + >>> type(template) + + + Templates are stored as sequences of literal :attr:`~Template.strings` + and dynamic :attr:`~Template.interpolations`. + A :attr:`~Template.values` attribute holds the values of the interpolations: + + >>> cheese = 'Camembert' + >>> template = t'Ah! We do have {cheese}.' + >>> template.strings + ('Ah! We do have ', '.') + >>> template.interpolations + (Interpolation('Camembert', ...),) + >>> template.values + ('Camembert',) + + The :attr:`!strings` tuple has one more element than :attr:`!interpolations` + and :attr:`!values`; the interpolations “belong” between the strings. + This may be easier to understand when tuples are aligned + + .. code-block:: python + + template.strings: ('Ah! We do have ', '.') + template.values: ( 'Camembert', ) + + .. rubric:: Attributes + + .. attribute:: strings + :type: tuple[str, ...] + + A :class:`tuple` of the static strings in the template. + + >>> cheese = 'Camembert' + >>> template = t'Ah! We do have {cheese}.' + >>> template.strings + ('Ah! We do have ', '.') + + Empty strings *are* included in the tuple: + + >>> response = 'We do have ' + >>> cheese = 'Camembert' + >>> template = t'Ah! {response}{cheese}.' + >>> template.strings + ('Ah! ', '', '.') + + The ``strings`` tuple is never empty, and always contains one more + string than the ``interpolations`` and ``values`` tuples: + + >>> t''.strings + ('',) + >>> t''.values + () + >>> t'{'cheese'}'.strings + ('', '') + >>> t'{'cheese'}'.values + ('cheese',) + + .. attribute:: interpolations + :type: tuple[Interpolation, ...] + + A :class:`tuple` of the interpolations in the template. + + >>> cheese = 'Camembert' + >>> template = t'Ah! We do have {cheese}.' + >>> template.interpolations + (Interpolation('Camembert', 'cheese', None, ''),) + + The ``interpolations`` tuple may be empty and always contains one fewer + values than the ``strings`` tuple: + + >>> t'Red Leicester'.interpolations + () + + .. attribute:: values + :type: tuple[object, ...] + + A tuple of all interpolated values in the template. + + >>> cheese = 'Camembert' + >>> template = t'Ah! We do have {cheese}.' + >>> template.values + ('Camembert',) + + The ``values`` tuple always has the same length as the + ``interpolations`` tuple. It is always equivalent to + ``tuple(i.value for i in template.interpolations)``. + + .. rubric:: Methods + + .. method:: __new__(*args: str | Interpolation) + + While literal syntax is the most common way to create a :class:`!Template`, + it is also possible to create them directly using the constructor: + + >>> from string.templatelib import Interpolation, Template + >>> cheese = 'Camembert' + >>> template = Template( + ... 'Ah! We do have ', Interpolation(cheese, 'cheese'), '.' + ... ) + >>> list(template) + ['Ah! We do have ', Interpolation('Camembert', 'cheese', None, ''), '.'] + + If multiple strings are passed consecutively, they will be concatenated + into a single value in the :attr:`~Template.strings` attribute. For example, + the following code creates a :class:`Template` with a single final string: + + >>> from string.templatelib import Template + >>> template = Template('Ah! We do have ', 'Camembert', '.') + >>> template.strings + ('Ah! We do have Camembert.',) + + If multiple interpolations are passed consecutively, they will be treated + as separate interpolations and an empty string will be inserted between them. + For example, the following code creates a template with empty placeholders + in the :attr:`~Template.strings` attribute: + + >>> from string.templatelib import Interpolation, Template + >>> template = Template( + ... Interpolation('Camembert', 'cheese'), + ... Interpolation('.', 'punctuation'), + ... ) + >>> template.strings + ('', '', '') + + .. describe:: iter(template) + + Iterate over the template, yielding each non-empty string and + :class:`Interpolation` in the correct order: + + >>> cheese = 'Camembert' + >>> list(t'Ah! We do have {cheese}.') + ['Ah! We do have ', Interpolation('Camembert', 'cheese', None, ''), '.'] + + .. caution:: + + Empty strings are **not** included in the iteration: + + >>> response = 'We do have ' + >>> cheese = 'Camembert' + >>> list(t'Ah! {response}{cheese}.') # doctest: +NORMALIZE_WHITESPACE + ['Ah! ', + Interpolation('We do have ', 'response', None, ''), + Interpolation('Camembert', 'cheese', None, ''), + '.'] + + .. describe:: template + other + template += other + + Concatenate this template with another, returning a new + :class:`!Template` instance: + + >>> cheese = 'Camembert' + >>> list(t'Ah! ' + t'We do have {cheese}.') + ['Ah! We do have ', Interpolation('Camembert', 'cheese', None, ''), '.'] + + Concatenating a :class:`!Template` and a ``str`` is **not** supported. + This is because it is unclear whether the string should be treated as + a static string or an interpolation. + If you want to concatenate a :class:`!Template` with a string, + you should either wrap the string directly in a :class:`!Template` + (to treat it as a static string) + or use an :class:`!Interpolation` (to treat it as dynamic): + + >>> from string.templatelib import Interpolation, Template + >>> template = t'Ah! ' + >>> # Treat 'We do have ' as a static string + >>> template += Template('We do have ') + >>> # Treat cheese as an interpolation + >>> cheese = 'Camembert' + >>> template += Template(Interpolation(cheese, 'cheese')) + >>> list(template) + ['Ah! We do have ', Interpolation('Camembert', 'cheese', None, '')] + + +.. class:: Interpolation + + The :class:`!Interpolation` type represents an expression inside a template string. + It is immutable, meaning that attributes of an interpolation cannot be reassigned. + + Interpolations support pattern matching, allowing you to match against + their attributes with the :ref:`match statement `: + + >>> from string.templatelib import Interpolation + >>> interpolation = t'{1. + 2.:.2f}'.interpolations[0] + >>> interpolation + Interpolation(3.0, '1. + 2.', None, '.2f') + >>> match interpolation: + ... case Interpolation(value, expression, conversion, format_spec): + ... print(value, expression, conversion, format_spec, sep=' | ') + ... + 3.0 | 1. + 2. | None | .2f + + Interpolations are :ref:`generic ` over the types of their values. + + .. rubric:: Attributes + + .. attribute:: value + :type: object + + The evaluated value of the interpolation. + + >>> t'{1 + 2}'.interpolations[0].value + 3 + + .. attribute:: expression + :type: str + + For interpolations created by t-string literals, :attr:`!expression` + is the expression text found inside the curly brackets (``{`` & ``}``), + including any whitespace, excluding the curly brackets themselves, + and ending before the first ``!``, ``:``, or ``=`` if any is present. + For manually created interpolations, :attr:`!expression` is the arbitrary + string provided when constructing the interpolation instance. + + We recommend using valid Python expressions or the empty string for the + ``expression`` field of manually created :class:`!Interpolation` + instances, although this is not enforced at runtime. + + >>> t'{1 + 2}'.interpolations[0].expression + '1 + 2' + + .. attribute:: conversion + :type: typing.Literal['a', 'r', 's'] | None + + The conversion to apply to the value, or ``None``. + + The :attr:`!conversion` is the optional conversion to apply + to the value: + + >>> t'{1 + 2!a}'.interpolations[0].conversion + 'a' + + .. note:: + + Unlike f-strings, where conversions are applied automatically, + the expected behavior with t-strings is that code that *processes* the + :class:`!Template` will decide how to interpret and whether to apply + the :attr:`!conversion`. + For convenience, the :func:`convert` function can be used to mimic + f-string conversion semantics. + + .. attribute:: format_spec + :type: str + + The format specification to apply to the value. + + The :attr:`!format_spec` is an optional, arbitrary string + used as the format specification to present the value: + + >>> t'{1 + 2:.2f}'.interpolations[0].format_spec + '.2f' + + .. note:: + + Unlike f-strings, where format specifications are applied automatically + via the :func:`format` protocol, the expected behavior with + t-strings is that code that *processes* the interpolation will + decide how to interpret and whether to apply the format specification. + As a result, :attr:`!format_spec` values in interpolations + can be arbitrary strings, + including those that do not conform to the :func:`format` protocol. + + .. rubric:: Methods + + .. method:: __new__(value: object, \ + expression: str, \ + conversion: typing.Literal['a', 'r', 's'] | None = None, \ + format_spec: str = '') + + Create a new :class:`!Interpolation` object from component parts. + + :param value: The evaluated, in-scope result of the interpolation. + :param expression: The text of a valid Python expression, + or an empty string. + :param conversion: The :ref:`conversion ` to be used, + one of ``None``, ``'a'``, ``'r'``, or ``'s'``. + :param format_spec: An optional, arbitrary string used as the + :ref:`format specification ` to present the value. + + +Helper functions +---------------- + +.. function:: convert(obj, /, conversion) + + Applies formatted string literal :ref:`conversion ` + semantics to the given object *obj*. + This is frequently useful for custom template string processing logic. + + Three conversion flags are currently supported: + + * ``'s'`` which calls :func:`str` on the value (like ``!s``), + * ``'r'`` which calls :func:`repr` (like ``!r``), and + * ``'a'`` which calls :func:`ascii` (like ``!a``). + + If the conversion flag is ``None``, *obj* is returned unchanged. diff --git a/Doc/library/stringprep.rst b/Doc/library/stringprep.rst index 37d5adf0fa9541..b9caa2aa830e94 100644 --- a/Doc/library/stringprep.rst +++ b/Doc/library/stringprep.rst @@ -26,14 +26,14 @@ define which tables it uses, and what other optional parts of the ``stringprep`` procedure are part of the profile. One example of a ``stringprep`` profile is ``nameprep``, which is used for internationalized domain names. -The module :mod:`stringprep` only exposes the tables from :rfc:`3454`. As these +The module :mod:`!stringprep` only exposes the tables from :rfc:`3454`. As these tables would be very large to represent as dictionaries or lists, the module uses the Unicode character database internally. The module source code itself was generated using the ``mkstringprep.py`` utility. As a result, these tables are exposed as functions, not as data structures. There are two kinds of tables in the RFC: sets and mappings. For a set, -:mod:`stringprep` provides the "characteristic function", i.e. a function that +:mod:`!stringprep` provides the "characteristic function", i.e. a function that returns ``True`` if the parameter is part of the set. For mappings, it provides the mapping function: given the key, it returns the associated value. Below is a list of all functions available in the module. diff --git a/Doc/library/struct.rst b/Doc/library/struct.rst index 17fc479fd0c8c9..f4fdff951661b6 100644 --- a/Doc/library/struct.rst +++ b/Doc/library/struct.rst @@ -36,7 +36,7 @@ and the C layer. responsible for defining byte ordering and padding between elements. See :ref:`struct-alignment` for details. -Several :mod:`struct` functions (and methods of :class:`Struct`) take a *buffer* +Several :mod:`!struct` functions (and methods of :class:`Struct`) take a *buffer* argument. This refers to objects that implement the :ref:`bufferobjects` and provide either a readable or read-writable buffer. The most common types used for that purpose are :class:`bytes` and :class:`bytearray`, but many other types @@ -68,6 +68,7 @@ The module defines the following exception and functions: Pack the values *v1*, *v2*, ... according to the format string *format* and write the packed bytes into the writable buffer *buffer* starting at position *offset*. Note that *offset* is a required argument. + A negative *offset* counts from the end of *buffer*. .. function:: unpack(format, buffer) @@ -84,6 +85,7 @@ The module defines the following exception and functions: string *format*. The result is a tuple even if it contains exactly one item. The buffer's size in bytes, starting at position *offset*, must be at least the size required by the format, as reflected by :func:`calcsize`. + A negative *offset* counts from the end of *buffer*. .. function:: iter_unpack(format, buffer) @@ -227,34 +229,34 @@ platform-dependent. +--------+--------------------------+--------------------+----------------+------------+ | ``c`` | :c:expr:`char` | bytes of length 1 | 1 | | +--------+--------------------------+--------------------+----------------+------------+ -| ``b`` | :c:expr:`signed char` | integer | 1 | \(1), \(2) | +| ``b`` | :c:expr:`signed char` | int | 1 | \(2) | +--------+--------------------------+--------------------+----------------+------------+ -| ``B`` | :c:expr:`unsigned char` | integer | 1 | \(2) | +| ``B`` | :c:expr:`unsigned char` | int | 1 | \(2) | +--------+--------------------------+--------------------+----------------+------------+ | ``?`` | :c:expr:`_Bool` | bool | 1 | \(1) | +--------+--------------------------+--------------------+----------------+------------+ -| ``h`` | :c:expr:`short` | integer | 2 | \(2) | +| ``h`` | :c:expr:`short` | int | 2 | \(2) | +--------+--------------------------+--------------------+----------------+------------+ -| ``H`` | :c:expr:`unsigned short` | integer | 2 | \(2) | +| ``H`` | :c:expr:`unsigned short` | int | 2 | \(2) | +--------+--------------------------+--------------------+----------------+------------+ -| ``i`` | :c:expr:`int` | integer | 4 | \(2) | +| ``i`` | :c:expr:`int` | int | 4 | \(2) | +--------+--------------------------+--------------------+----------------+------------+ -| ``I`` | :c:expr:`unsigned int` | integer | 4 | \(2) | +| ``I`` | :c:expr:`unsigned int` | int | 4 | \(2) | +--------+--------------------------+--------------------+----------------+------------+ -| ``l`` | :c:expr:`long` | integer | 4 | \(2) | +| ``l`` | :c:expr:`long` | int | 4 | \(2) | +--------+--------------------------+--------------------+----------------+------------+ -| ``L`` | :c:expr:`unsigned long` | integer | 4 | \(2) | +| ``L`` | :c:expr:`unsigned long` | int | 4 | \(2) | +--------+--------------------------+--------------------+----------------+------------+ -| ``q`` | :c:expr:`long long` | integer | 8 | \(2) | +| ``q`` | :c:expr:`long long` | int | 8 | \(2) | +--------+--------------------------+--------------------+----------------+------------+ -| ``Q`` | :c:expr:`unsigned long | integer | 8 | \(2) | +| ``Q`` | :c:expr:`unsigned long | int | 8 | \(2) | | | long` | | | | +--------+--------------------------+--------------------+----------------+------------+ -| ``n`` | :c:type:`ssize_t` | integer | | \(3) | +| ``n`` | :c:type:`ssize_t` | int | | \(2), \(3) | +--------+--------------------------+--------------------+----------------+------------+ -| ``N`` | :c:type:`size_t` | integer | | \(3) | +| ``N`` | :c:type:`size_t` | int | | \(2), \(3) | +--------+--------------------------+--------------------+----------------+------------+ -| ``e`` | \(6) | float | 2 | \(4) | +| ``e`` | :c:expr:`_Float16` | float | 2 | \(4), \(6) | +--------+--------------------------+--------------------+----------------+------------+ | ``f`` | :c:expr:`float` | float | 4 | \(4) | +--------+--------------------------+--------------------+----------------+------------+ @@ -268,7 +270,7 @@ platform-dependent. +--------+--------------------------+--------------------+----------------+------------+ | ``p`` | :c:expr:`char[]` | bytes | | \(8) | +--------+--------------------------+--------------------+----------------+------------+ -| ``P`` | :c:expr:`void \*` | integer | | \(5) | +| ``P`` | :c:expr:`void \*` | int | | \(2), \(5) | +--------+--------------------------+--------------------+----------------+------------+ .. versionchanged:: 3.3 @@ -280,6 +282,12 @@ platform-dependent. .. versionchanged:: 3.14 Added support for the ``'F'`` and ``'D'`` formats. +.. seealso:: + + The :mod:`array` and :ref:`ctypes ` modules, + as well as third-party modules like `numpy `__, + use similar -- but slightly different -- type codes. + Notes: @@ -322,7 +330,9 @@ Notes: revision of the `IEEE 754 standard `_. It has a sign bit, a 5-bit exponent and 11-bit precision (with 10 bits explicitly stored), and can represent numbers between approximately ``6.1e-05`` and ``6.5e+04`` - at full precision. This type is not widely supported by C compilers: on a + at full precision. This type is not widely supported by C compilers: + it's available as :c:expr:`_Float16` type, if the compiler supports the Annex H + of the C23 standard. On a typical machine, an unsigned short can be used for storage, but not for math operations. See the Wikipedia page on the `half-precision floating-point format `_ for more information. @@ -334,27 +344,31 @@ Notes: The ``'p'`` format character encodes a "Pascal string", meaning a short variable-length string stored in a *fixed number of bytes*, given by the count. The first byte stored is the length of the string, or 255, whichever is - smaller. The bytes of the string follow. If the string passed in to + smaller. The bytes of the string follow. If the byte string passed in to :func:`pack` is too long (longer than the count minus 1), only the leading - ``count-1`` bytes of the string are stored. If the string is shorter than + ``count-1`` bytes of the string are stored. If the byte string is shorter than ``count-1``, it is padded with null bytes so that exactly count bytes in all are used. Note that for :func:`unpack`, the ``'p'`` format character consumes - ``count`` bytes, but that the string returned can never contain more than 255 + ``count`` bytes, but that the :class:`!bytes` object returned can never contain more than 255 bytes. + When packing, arguments of types :class:`bytes` and :class:`bytearray` + are accepted. (9) For the ``'s'`` format character, the count is interpreted as the length of the - bytes, not a repeat count like for the other format characters; for example, + byte string, not a repeat count like for the other format characters; for example, ``'10s'`` means a single 10-byte string mapping to or from a single Python byte string, while ``'10c'`` means 10 separate one byte character elements (e.g., ``cccccccccc``) mapping to or from ten different Python byte objects. (See :ref:`struct-examples` for a concrete demonstration of the difference.) - If a count is not given, it defaults to 1. For packing, the string is + If a count is not given, it defaults to 1. For packing, the byte string is truncated or padded with null bytes as appropriate to make it fit. For - unpacking, the resulting bytes object always has exactly the specified number - of bytes. As a special case, ``'0s'`` means a single, empty string (while + unpacking, the resulting :class:`!bytes` object always has exactly the specified number + of bytes. As a special case, ``'0s'`` means a single, empty byte string (while ``'0c'`` means 0 characters). + When packing, arguments of types :class:`bytes` and :class:`bytearray` + are accepted. (10) For the ``'F'`` and ``'D'`` format characters, the packed representation uses @@ -479,7 +493,7 @@ at the end, assuming the platform's longs are aligned on 4-byte boundaries:: Applications ------------ -Two main applications for the :mod:`struct` module exist, data +Two main applications for the :mod:`!struct` module exist, data interchange between Python and C code within an application or another application compiled using the same compiler (:ref:`native formats`), and data interchange between applications using agreed upon data layout @@ -571,7 +585,7 @@ below were executed on a 32-bit machine:: Classes ------- -The :mod:`struct` module also defines the following type: +The :mod:`!struct` module also defines the following type: .. class:: Struct(format) diff --git a/Doc/library/subprocess.rst b/Doc/library/subprocess.rst index 028a7861f36798..66a3d6a484a8a8 100644 --- a/Doc/library/subprocess.rst +++ b/Doc/library/subprocess.rst @@ -11,14 +11,14 @@ -------------- -The :mod:`subprocess` module allows you to spawn new processes, connect to their +The :mod:`!subprocess` module allows you to spawn new processes, connect to their input/output/error pipes, and obtain their return codes. This module intends to replace several older modules and functions:: os.system os.spawn* -Information about how the :mod:`subprocess` module can be used to replace these +Information about how the :mod:`!subprocess` module can be used to replace these modules and functions can be found in the following sections. .. seealso:: @@ -27,8 +27,8 @@ modules and functions can be found in the following sections. .. include:: ../includes/wasm-mobile-notavail.rst -Using the :mod:`subprocess` Module ----------------------------------- +Using the :mod:`!subprocess` Module +----------------------------------- The recommended approach to invoking subprocesses is to use the :func:`run` function for all use cases it can handle. For more advanced use cases, the @@ -630,6 +630,12 @@ functions. the value in ``pw_uid`` will be used. If the value is an integer, it will be passed verbatim. (POSIX only) + .. note:: + + Specifying *user* will not drop existing supplementary group memberships! + The caller must also pass ``extra_groups=()`` to reduce the group membership + of the child process for security purposes. + .. availability:: POSIX .. versionadded:: 3.9 @@ -649,7 +655,7 @@ functions. If specified, *env* must provide any variables required for the program to execute. On Windows, in order to run a `side-by-side assembly`_ the - specified *env* **must** include a valid :envvar:`SystemRoot`. + specified *env* **must** include a valid ``%SystemRoot%``. .. _side-by-side assembly: https://en.wikipedia.org/wiki/Side-by-Side_Assembly @@ -831,7 +837,9 @@ Instances of the :class:`Popen` class have the following methods: If the process does not terminate after *timeout* seconds, a :exc:`TimeoutExpired` exception will be raised. Catching this exception and - retrying communication will not lose any output. + retrying communication will not lose any output. Supplying *input* to a + subsequent post-timeout :meth:`communicate` call is in undefined behavior + and may become an error in the future. The child process is not killed if the timeout expires, so in order to cleanup properly a well-behaved application should kill the child process and @@ -844,6 +852,11 @@ Instances of the :class:`Popen` class have the following methods: proc.kill() outs, errs = proc.communicate() + After a call to :meth:`~Popen.communicate` raises :exc:`TimeoutExpired`, do + not call :meth:`~Popen.wait`. Use an additional :meth:`~Popen.communicate` + call to finish handling pipes and populate the :attr:`~Popen.returncode` + attribute. + .. note:: The data read is buffered in memory, so do not use this method if the data @@ -945,6 +958,11 @@ Reassigning them to new values is unsupported: A negative value ``-N`` indicates that the child was terminated by signal ``N`` (POSIX only). + When ``shell=True``, the return code reflects the exit status of the shell + itself (e.g. ``/bin/sh``), which may map signals to codes such as + ``128+N``. See the documentation of the shell (for example, the Bash + manual's Exit Status) for details. + Windows Popen Helpers --------------------- @@ -1034,7 +1052,7 @@ on Windows. Windows Constants ^^^^^^^^^^^^^^^^^ -The :mod:`subprocess` module exposes the following constants. +The :mod:`!subprocess` module exposes the following constants. .. data:: STD_INPUT_HANDLE @@ -1323,8 +1341,8 @@ calls these functions. .. _subprocess-replacements: -Replacing Older Functions with the :mod:`subprocess` Module ------------------------------------------------------------ +Replacing Older Functions with the :mod:`!subprocess` Module +------------------------------------------------------------ In this section, "a becomes b" means that b can be used as a replacement for a. @@ -1340,7 +1358,7 @@ In this section, "a becomes b" means that b can be used as a replacement for a. :attr:`~CalledProcessError.output` attribute of the raised exception. In the following examples, we assume that the relevant functions have already -been imported from the :mod:`subprocess` module. +been imported from the :mod:`!subprocess` module. Replacing :program:`/bin/sh` shell command substitution @@ -1400,7 +1418,7 @@ Notes: * The :func:`os.system` function ignores SIGINT and SIGQUIT signals while the command is running, but the caller must do this separately when - using the :mod:`subprocess` module. + using the :mod:`!subprocess` module. A more realistic example would look like this:: @@ -1473,7 +1491,7 @@ handling consistency are valid for these functions. Return ``(exitcode, output)`` of executing *cmd* in a shell. - Execute the string *cmd* in a shell with :meth:`Popen.check_output` and + Execute the string *cmd* in a shell with :func:`check_output` and return a 2-tuple ``(exitcode, output)``. *encoding* and *errors* are used to decode output; see the notes on :ref:`frequently-used-arguments` for more details. @@ -1584,7 +1602,7 @@ runtime): Disable use of ``posix_spawn()`` ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -On Linux, :mod:`subprocess` defaults to using the ``vfork()`` system call +On Linux, :mod:`!subprocess` defaults to using the ``vfork()`` system call internally when it is safe to do so rather than ``fork()``. This greatly improves performance. diff --git a/Doc/library/symtable.rst b/Doc/library/symtable.rst index 54e19af4bd69a6..2f7bba2537dc5f 100644 --- a/Doc/library/symtable.rst +++ b/Doc/library/symtable.rst @@ -14,7 +14,7 @@ Symbol tables are generated by the compiler from AST just before bytecode is generated. The symbol table is responsible for calculating the scope of every -identifier in the code. :mod:`symtable` provides an interface to examine these +identifier in the code. :mod:`!symtable` provides an interface to examine these tables. @@ -355,7 +355,7 @@ Command-Line Usage .. versionadded:: 3.13 -The :mod:`symtable` module can be executed as a script from the command line. +The :mod:`!symtable` module can be executed as a script from the command line. .. code-block:: sh diff --git a/Doc/library/sys.monitoring.rst b/Doc/library/sys.monitoring.rst index 0674074b8c0df6..16e6b1d6dc786b 100644 --- a/Doc/library/sys.monitoring.rst +++ b/Doc/library/sys.monitoring.rst @@ -10,17 +10,17 @@ .. note:: - :mod:`sys.monitoring` is a namespace within the :mod:`sys` module, - not an independent module, so there is no need to - ``import sys.monitoring``, simply ``import sys`` and then use - ``sys.monitoring``. + :mod:`!sys.monitoring` is a namespace within the :mod:`sys` module, + not an independent module, and ``import sys.monitoring`` would fail + with a :exc:`ModuleNotFoundError`. Instead, simply ``import sys`` + and then use ``sys.monitoring``. This namespace provides access to the functions and constants necessary to activate and control event monitoring. As programs execute, events occur that might be of interest to tools that -monitor execution. The :mod:`sys.monitoring` namespace provides means to +monitor execution. The :mod:`!sys.monitoring` namespace provides means to receive callbacks when events of interest occur. The monitoring API consists of three components: @@ -137,7 +137,8 @@ The following events are supported: .. monitoring-event:: PY_UNWIND - Exit from a Python function during exception unwinding. + Exit from a Python function during exception unwinding. This includes exceptions raised directly within the + function and that are allowed to continue to propagate. .. monitoring-event:: PY_YIELD @@ -171,7 +172,7 @@ events, use the expression ``PY_RETURN | PY_START``. if get_events(DEBUGGER_ID) == NO_EVENTS: ... -Events are divided into three groups: + Setting this event deactivates all events. .. _monitoring-event-local: @@ -215,14 +216,17 @@ by another event: The :monitoring-event:`C_RETURN` and :monitoring-event:`C_RAISE` events are controlled by the :monitoring-event:`CALL` event. -:monitoring-event:`C_RETURN` and :monitoring-event:`C_RAISE` events will only be seen if the -corresponding :monitoring-event:`CALL` event is being monitored. +:monitoring-event:`C_RETURN` and :monitoring-event:`C_RAISE` events will only be +seen if the corresponding :monitoring-event:`CALL` event is being monitored. + + +.. _monitoring-event-global: Other events '''''''''''' Other events are not necessarily tied to a specific location in the -program and cannot be individually disabled. +program and cannot be individually disabled via :data:`DISABLE`. The other events that can be monitored are: @@ -243,20 +247,23 @@ raise an exception unless it would be visible to other code. To allow tools to monitor for real exceptions without slowing down generators and coroutines, the :monitoring-event:`STOP_ITERATION` event is provided. -:monitoring-event:`STOP_ITERATION` can be locally disabled, unlike :monitoring-event:`RAISE`. +:monitoring-event:`STOP_ITERATION` can be locally disabled, unlike +:monitoring-event:`RAISE`. -Note that the :monitoring-event:`STOP_ITERATION` event and the :monitoring-event:`RAISE` -event for a :exc:`StopIteration` exception are equivalent, and are treated as interchangeable -when generating events. Implementations will favor :monitoring-event:`STOP_ITERATION` for -performance reasons, but may generate a :monitoring-event:`RAISE` event with a :exc:`StopIteration`. +Note that the :monitoring-event:`STOP_ITERATION` event and the +:monitoring-event:`RAISE` event for a :exc:`StopIteration` exception are +equivalent, and are treated as interchangeable when generating events. +Implementations will favor :monitoring-event:`STOP_ITERATION` for performance +reasons, but may generate a :monitoring-event:`RAISE` event with a +:exc:`StopIteration`. Turning events on and off ------------------------- In order to monitor an event, it must be turned on and a corresponding callback -must be registered. -Events can be turned on or off by setting the events either globally or -for a particular code object. +must be registered. Events can be turned on or off by setting the events either +globally and/or for a particular code object. An event will trigger only once, +even if it is turned on both globally and locally. Setting events globally @@ -285,16 +292,13 @@ in Python (see :ref:`c-api-monitoring`). .. function:: get_local_events(tool_id: int, code: CodeType, /) -> int - Returns all the local events for *code* + Returns all the :ref:`local events ` for *code* .. function:: set_local_events(tool_id: int, code: CodeType, event_set: int, /) -> None - Activates all the local events for *code* which are set in *event_set*. - Raises a :exc:`ValueError` if *tool_id* is not in use. - -Local events add to global events, but do not mask them. -In other words, all global events will trigger for a code object, -regardless of the local events. + Activates all the :ref:`local events ` for *code* + which are set in *event_set*. Raises a :exc:`ValueError` if *tool_id* is not + in use. Disabling events @@ -305,15 +309,21 @@ Disabling events A special value that can be returned from a callback function to disable events for the current code location. -Local events can be disabled for a specific code location by returning -:data:`sys.monitoring.DISABLE` from a callback function. This does not change -which events are set, or any other code locations for the same event. +:ref:`Local events ` can be disabled for a specific code +location by returning :data:`sys.monitoring.DISABLE` from a callback function. +This does not change which events are set, or any other code locations for the +same event. Disabling events for specific locations is very important for high performance monitoring. For example, a program can be run under a debugger with no overhead if the debugger disables all monitoring except for a few breakpoints. +If :data:`DISABLE` is returned by a callback for a +:ref:`global event `, :exc:`ValueError` will be raised +by the interpreter in a non-specific location (that is, no traceback will be +provided). + .. function:: restart_events() -> None Enable all the events that were disabled by :data:`sys.monitoring.DISABLE` @@ -325,8 +335,6 @@ except for a few breakpoints. Registering callback functions ------------------------------ -To register a callable for events call - .. function:: register_callback(tool_id: int, event: int, func: Callable | None, /) -> Callable | None Registers the callable *func* for the *event* with the given *tool_id* @@ -335,13 +343,17 @@ To register a callable for events call it is unregistered and returned. Otherwise :func:`register_callback` returns ``None``. + .. audit-event:: sys.monitoring.register_callback func sys.monitoring.register_callback Functions can be unregistered by calling ``sys.monitoring.register_callback(tool_id, event, None)``. Callback functions can be registered and unregistered at any time. -Registering or unregistering a callback function will generate a :func:`sys.audit` event. +Callbacks are called only once regardless if the event is turned on both +globally and locally. As such, if an event could be turned on for both global +and local events by your code then the callback needs to be written to handle +either trigger. Callback function arguments @@ -353,37 +365,46 @@ Callback function arguments that there are no arguments to the call. When an active event occurs, the registered callback function is called. +Callback functions returning an object other than :data:`DISABLE` will have no effect. Different events will provide the callback function with different arguments, as follows: * :monitoring-event:`PY_START` and :monitoring-event:`PY_RESUME`:: - func(code: CodeType, instruction_offset: int) -> DISABLE | Any + func(code: CodeType, instruction_offset: int) -> object * :monitoring-event:`PY_RETURN` and :monitoring-event:`PY_YIELD`:: - func(code: CodeType, instruction_offset: int, retval: object) -> DISABLE | Any + func(code: CodeType, instruction_offset: int, retval: object) -> object -* :monitoring-event:`CALL`, :monitoring-event:`C_RAISE` and :monitoring-event:`C_RETURN`:: +* :monitoring-event:`CALL`, :monitoring-event:`C_RAISE` and :monitoring-event:`C_RETURN` + (*arg0* can be :data:`MISSING` specifically):: - func(code: CodeType, instruction_offset: int, callable: object, arg0: object | MISSING) -> DISABLE | Any + func(code: CodeType, instruction_offset: int, callable: object, arg0: object) -> object + *code* represents the code object where the call is being made, while + *callable* is the object that is about to be called (and thus + triggered the event). If there are no arguments, *arg0* is set to :data:`sys.monitoring.MISSING`. + For instance methods, *callable* will be the function object as found on the + class with *arg0* set to the instance (i.e. the ``self`` argument to the + method). + * :monitoring-event:`RAISE`, :monitoring-event:`RERAISE`, :monitoring-event:`EXCEPTION_HANDLED`, :monitoring-event:`PY_UNWIND`, :monitoring-event:`PY_THROW` and :monitoring-event:`STOP_ITERATION`:: - func(code: CodeType, instruction_offset: int, exception: BaseException) -> DISABLE | Any + func(code: CodeType, instruction_offset: int, exception: BaseException) -> object * :monitoring-event:`LINE`:: - func(code: CodeType, line_number: int) -> DISABLE | Any + func(code: CodeType, line_number: int) -> object * :monitoring-event:`BRANCH_LEFT`, :monitoring-event:`BRANCH_RIGHT` and :monitoring-event:`JUMP`:: - func(code: CodeType, instruction_offset: int, destination_offset: int) -> DISABLE | Any + func(code: CodeType, instruction_offset: int, destination_offset: int) -> object Note that the *destination_offset* is where the code will next execute. * :monitoring-event:`INSTRUCTION`:: - func(code: CodeType, instruction_offset: int) -> DISABLE | Any + func(code: CodeType, instruction_offset: int) -> object diff --git a/Doc/library/sys.rst b/Doc/library/sys.rst index 55e442b20ff877..6fe097407445e4 100644 --- a/Doc/library/sys.rst +++ b/Doc/library/sys.rst @@ -515,7 +515,7 @@ always available. Unless explicitly noted otherwise, all variables are read-only in the range 0--127, and produce undefined results otherwise. Some systems have a convention for assigning specific meanings to specific exit codes, but these are generally underdeveloped; Unix programs generally use 2 for command - line syntax errors and 1 for all other kind of errors. If another type of + line syntax errors and 1 for all other kinds of errors. If another type of object is passed, ``None`` is equivalent to passing zero, and any other object is printed to :data:`stderr` and results in an exit code of 1. In particular, ``sys.exit("some error message")`` is a quick way to exit a @@ -953,6 +953,8 @@ always available. Unless explicitly noted otherwise, all variables are read-only This function should be used for internal and specialized purposes only. It is not guaranteed to exist in all implementations of Python. + .. versionadded:: 3.12 + .. function:: getobjects(limit[, type]) @@ -1128,10 +1130,14 @@ always available. Unless explicitly noted otherwise, all variables are read-only The size of the seed key of the hash algorithm + .. attribute:: hash_info.cutoff + + Cutoff for small string DJBX33A optimization in range ``[1, cutoff)``. + .. versionadded:: 3.2 .. versionchanged:: 3.4 - Added *algorithm*, *hash_bits* and *seed_bits* + Added *algorithm*, *hash_bits*, *seed_bits*, and *cutoff*. .. data:: hexversion @@ -1185,6 +1191,15 @@ always available. Unless explicitly noted otherwise, all variables are read-only ``cache_tag`` is set to ``None``, it indicates that module caching should be disabled. + *supports_isolated_interpreters* is a boolean value, whether + this implementation supports multiple isolated interpreters. + It is ``True`` for CPython on most platforms. Platforms with + this support implement the low-level :mod:`!_interpreters` module. + + .. seealso:: + + :pep:`684`, :pep:`734`, and :mod:`concurrent.interpreters`. + :data:`sys.implementation` may contain additional attributes specific to the Python implementation. These non-standard attributes must start with an underscore, and are not described here. Regardless of its contents, @@ -1194,6 +1209,9 @@ always available. Unless explicitly noted otherwise, all variables are read-only .. versionadded:: 3.3 + .. versionchanged:: 3.14 + Added ``supports_isolated_interpreters`` field. + .. note:: The addition of new required attributes must go through the normal PEP @@ -1750,7 +1768,7 @@ always available. Unless explicitly noted otherwise, all variables are read-only :func:`settrace` for each thread being debugged or use :func:`threading.settrace`. Trace functions should have three arguments: *frame*, *event*, and - *arg*. *frame* is the current stack frame. *event* is a string: ``'call'``, + *arg*. *frame* is the :ref:`current stack frame `. *event* is a string: ``'call'``, ``'line'``, ``'return'``, ``'exception'`` or ``'opcode'``. *arg* depends on the event type. @@ -1780,7 +1798,7 @@ always available. Unless explicitly noted otherwise, all variables are read-only The interpreter is about to execute a new line of code or re-execute the condition of a loop. The local trace function is called; *arg* is ``None``; the return value specifies the new local trace function. See - :file:`Objects/lnotab_notes.txt` for a detailed explanation of how this + :source:`InternalDocs/code_objects.md` for a detailed explanation of how this works. Per-line events may be disabled for a frame by setting :attr:`~frame.f_trace_lines` to :const:`False` on that @@ -1933,8 +1951,28 @@ always available. Unless explicitly noted otherwise, all variables are read-only interpreter is pre-release (alpha, beta, or release candidate) then the local and remote interpreters must be the same exact version. + See :ref:`remote-debugging` for more information about the remote debugging + mechanism. + + .. audit-event:: sys.remote_exec pid script_path + + When the code is executed in the remote process, an + :ref:`auditing event ` ``sys.remote_exec`` is raised with + the *pid* and the path to the script file. + This event is raised in the process that called :func:`sys.remote_exec`. + + .. audit-event:: cpython.remote_debugger_script script_path + + When the script is executed in the remote process, an + :ref:`auditing event ` + ``cpython.remote_debugger_script`` is raised + with the path in the remote process. + This event is raised in the remote process, not the one + that called :func:`sys.remote_exec`. + .. availability:: Unix, Windows. .. versionadded:: 3.14 + See :pep:`768` for more details. .. function:: _enablelegacywindowsfsencoding() @@ -1979,7 +2017,7 @@ always available. Unless explicitly noted otherwise, all variables are read-only returned by the :func:`open` function. Their parameters are chosen as follows: - * The encoding and error handling are is initialized from + * The encoding and error handling are initialized from :c:member:`PyConfig.stdio_encoding` and :c:member:`PyConfig.stdio_errors`. On Windows, UTF-8 is used for the console device. Non-character @@ -2161,8 +2199,11 @@ always available. Unless explicitly noted otherwise, all variables are read-only .. data:: api_version - The C API version for this interpreter. Programmers may find this useful when - debugging version conflicts between Python and extension modules. + The C API version, equivalent to the C macro :c:macro:`PYTHON_API_VERSION`. + Defined for backwards compatibility. + + Currently, this constant is not updated in new Python versions, and is not + useful for versioning. This may change in the future. .. data:: version_info @@ -2189,7 +2230,7 @@ always available. Unless explicitly noted otherwise, all variables are read-only The version number used to form registry keys on Windows platforms. This is stored as string resource 1000 in the Python DLL. The value is normally the - major and minor versions of the running Python interpreter. It is provided in the :mod:`sys` + major and minor versions of the running Python interpreter. It is provided in the :mod:`!sys` module for informational purposes; modifying this value has no effect on the registry keys used by Python. diff --git a/Doc/library/sysconfig.rst b/Doc/library/sysconfig.rst index 684d14a74c48ab..138af76a66f6b8 100644 --- a/Doc/library/sysconfig.rst +++ b/Doc/library/sysconfig.rst @@ -16,7 +16,7 @@ -------------- -The :mod:`sysconfig` module provides access to Python's configuration +The :mod:`!sysconfig` module provides access to Python's configuration information like the list of installation paths and the configuration variables relevant for the current platform. @@ -28,7 +28,7 @@ A Python distribution contains a :file:`Makefile` and a :file:`pyconfig.h` header file that are necessary to build both the Python binary itself and third-party C extensions compiled using ``setuptools``. -:mod:`sysconfig` puts all variables found in these files in a dictionary that +:mod:`!sysconfig` puts all variables found in these files in a dictionary that can be accessed using :func:`get_config_vars` or :func:`get_config_var`. Notice that on Windows, it's a much smaller set. @@ -68,7 +68,7 @@ Installation paths ------------------ Python uses an installation scheme that differs depending on the platform and on -the installation options. These schemes are stored in :mod:`sysconfig` under +the installation options. These schemes are stored in :mod:`!sysconfig` under unique identifiers based on the value returned by :const:`os.name`. The schemes are used by package installers to determine where to copy files to. @@ -258,12 +258,12 @@ Path Installation directory Installation path functions --------------------------- -:mod:`sysconfig` provides some functions to determine these installation paths. +:mod:`!sysconfig` provides some functions to determine these installation paths. .. function:: get_scheme_names() Return a tuple containing all schemes currently supported in - :mod:`sysconfig`. + :mod:`!sysconfig`. .. function:: get_default_scheme() @@ -285,7 +285,7 @@ Installation path functions *key* must be either ``"prefix"``, ``"home"``, or ``"user"``. The return value is a scheme name listed in :func:`get_scheme_names`. It - can be passed to :mod:`sysconfig` functions that take a *scheme* argument, + can be passed to :mod:`!sysconfig` functions that take a *scheme* argument, such as :func:`get_paths`. .. versionadded:: 3.10 @@ -313,7 +313,7 @@ Installation path functions .. function:: get_path_names() Return a tuple containing all path names currently supported in - :mod:`sysconfig`. + :mod:`!sysconfig`. .. function:: get_path(name, [scheme, [vars, [expand]]]) @@ -323,7 +323,7 @@ Installation path functions *name* has to be a value from the list returned by :func:`get_path_names`. - :mod:`sysconfig` stores installation paths corresponding to each path name, + :mod:`!sysconfig` stores installation paths corresponding to each path name, for each platform, with variables to be expanded. For instance the *stdlib* path for the *nt* scheme is: ``{base}/Lib``. @@ -382,22 +382,19 @@ Other functions Examples of returned values: - - linux-i586 - - linux-alpha (?) - - solaris-2.6-sun4u - Windows will return one of: + Windows: - win-amd64 (64-bit Windows on AMD64, aka x86_64, Intel64, and EM64T) - win-arm64 (64-bit Windows on ARM64, aka AArch64) - win32 (all others - specifically, sys.platform is returned) - macOS can return: + POSIX based OS: - - macosx-10.6-ppc - - macosx-10.4-ppc64 - - macosx-10.3-i386 - - macosx-10.4-fat + - linux-x86_64 + - macosx-15.5-arm64 + - macosx-26.0-universal2 (macOS on Apple Silicon or Intel) + - android-24-arm64_v8a For other non-POSIX platforms, currently just returns :data:`sys.platform`. @@ -434,7 +431,7 @@ Other functions Command-line usage ------------------ -You can use :mod:`sysconfig` as a script with Python's *-m* option: +You can use :mod:`!sysconfig` as a script with Python's *-m* option: .. code-block:: shell-session diff --git a/Doc/library/syslog.rst b/Doc/library/syslog.rst index 548898a37bc6ea..b6bf01240951eb 100644 --- a/Doc/library/syslog.rst +++ b/Doc/library/syslog.rst @@ -2,7 +2,6 @@ =============================================== .. module:: syslog - :platform: Unix :synopsis: An interface to the Unix syslog library routines. -------------- diff --git a/Doc/library/tarfile.rst b/Doc/library/tarfile.rst index f9cb5495e60cd2..28e950e8f728e2 100644 --- a/Doc/library/tarfile.rst +++ b/Doc/library/tarfile.rst @@ -11,15 +11,23 @@ -------------- -The :mod:`tarfile` module makes it possible to read and write tar +The :mod:`!tarfile` module makes it possible to read and write tar archives, including those using gzip, bz2 and lzma compression. Use the :mod:`zipfile` module to read or write :file:`.zip` files, or the higher-level functions in :ref:`shutil `. Some facts and figures: -* reads and writes :mod:`gzip`, :mod:`bz2` and :mod:`lzma` compressed archives - if the respective modules are available. +* reads and writes :mod:`gzip`, :mod:`bz2`, :mod:`compression.zstd`, and + :mod:`lzma` compressed archives if the respective modules are available. + + .. + The following paragraph should be similar to ../includes/optional-module.rst + + If any of these :term:`optional modules ` are missing from + your copy of CPython, look for documentation from your distributor (that is, + whoever provided Python to you). + If you are the distributor, see :ref:`optional-module-requirements`. * read/write support for the POSIX.1-1988 (ustar) format. @@ -47,6 +55,10 @@ Some facts and figures: or paths outside of the destination. Previously, the filter strategy was equivalent to :func:`fully_trusted `. +.. versionchanged:: 3.14 + + Added support for Zstandard compression using :mod:`compression.zstd`. + .. function:: open(name=None, mode='r', fileobj=None, bufsize=10240, **kwargs) Return a :class:`TarFile` object for the pathname *name*. For detailed @@ -59,8 +71,8 @@ Some facts and figures: +------------------+---------------------------------------------+ | mode | action | +==================+=============================================+ - | ``'r' or 'r:*'`` | Open for reading with transparent | - | | compression (recommended). | + | ``'r'`` or | Open for reading with transparent | + | ``'r:*'`` | compression (recommended). | +------------------+---------------------------------------------+ | ``'r:'`` | Open for reading exclusively without | | | compression. | @@ -71,6 +83,8 @@ Some facts and figures: +------------------+---------------------------------------------+ | ``'r:xz'`` | Open for reading with lzma compression. | +------------------+---------------------------------------------+ + | ``'r:zst'`` | Open for reading with Zstandard compression.| + +------------------+---------------------------------------------+ | ``'x'`` or | Create a tarfile exclusively without | | ``'x:'`` | compression. | | | Raise a :exc:`FileExistsError` exception | @@ -88,10 +102,15 @@ Some facts and figures: | | Raise a :exc:`FileExistsError` exception | | | if it already exists. | +------------------+---------------------------------------------+ - | ``'a' or 'a:'`` | Open for appending with no compression. The | - | | file is created if it does not exist. | + | ``'x:zst'`` | Create a tarfile with Zstandard compression.| + | | Raise a :exc:`FileExistsError` exception | + | | if it already exists. | + +------------------+---------------------------------------------+ + | ``'a'`` or | Open for appending with no compression. The | + | ``'a:'`` | file is created if it does not exist. | +------------------+---------------------------------------------+ - | ``'w' or 'w:'`` | Open for uncompressed writing. | + | ``'w'`` or | Open for uncompressed writing. | + | ``'w:'`` | | +------------------+---------------------------------------------+ | ``'w:gz'`` | Open for gzip compressed writing. | +------------------+---------------------------------------------+ @@ -99,6 +118,8 @@ Some facts and figures: +------------------+---------------------------------------------+ | ``'w:xz'`` | Open for lzma compressed writing. | +------------------+---------------------------------------------+ + | ``'w:zst'`` | Open for Zstandard compressed writing. | + +------------------+---------------------------------------------+ Note that ``'a:gz'``, ``'a:bz2'`` or ``'a:xz'`` is not possible. If *mode* is not suitable to open a certain (compressed) file for reading, @@ -115,6 +136,15 @@ Some facts and figures: For modes ``'w:xz'``, ``'x:xz'`` and ``'w|xz'``, :func:`tarfile.open` accepts the keyword argument *preset* to specify the compression level of the file. + For modes ``'w:zst'``, ``'x:zst'`` and ``'w|zst'``, :func:`tarfile.open` + accepts the keyword argument *level* to specify the compression level of + the file. The keyword argument *options* may also be passed, providing + advanced Zstandard compression parameters described by + :class:`~compression.zstd.CompressionParameter`. The keyword argument + *zstd_dict* can be passed to provide a :class:`~compression.zstd.ZstdDict`, + a Zstandard dictionary used to improve compression of smaller amounts of + data. + For special purposes, there is a second format for *mode*: ``'filemode|[compression]'``. :func:`tarfile.open` will return a :class:`TarFile` object that processes its data as a stream of blocks. No random seeking will @@ -146,6 +176,9 @@ Some facts and figures: | ``'r|xz'`` | Open an lzma compressed *stream* for | | | reading. | +-------------+--------------------------------------------+ + | ``'r|zst'`` | Open a Zstandard compressed *stream* for | + | | reading. | + +-------------+--------------------------------------------+ | ``'w|'`` | Open an uncompressed *stream* for writing. | +-------------+--------------------------------------------+ | ``'w|gz'`` | Open a gzip compressed *stream* for | @@ -157,6 +190,9 @@ Some facts and figures: | ``'w|xz'`` | Open an lzma compressed *stream* for | | | writing. | +-------------+--------------------------------------------+ + | ``'w|zst'`` | Open a Zstandard compressed *stream* for | + | | writing. | + +-------------+--------------------------------------------+ .. versionchanged:: 3.5 The ``'x'`` (exclusive creation) mode was added. @@ -180,25 +216,25 @@ Some facts and figures: .. function:: is_tarfile(name) - Return :const:`True` if *name* is a tar archive file, that the :mod:`tarfile` + Return :const:`True` if *name* is a tar archive file, that the :mod:`!tarfile` module can read. *name* may be a :class:`str`, file, or file-like object. .. versionchanged:: 3.9 Support for file and file-like objects. -The :mod:`tarfile` module defines the following exceptions: +The :mod:`!tarfile` module defines the following exceptions: .. exception:: TarError - Base class for all :mod:`tarfile` exceptions. + Base class for all :mod:`!tarfile` exceptions. .. exception:: ReadError Is raised when a tar archive is opened, that either cannot be handled by the - :mod:`tarfile` module or is somehow invalid. + :mod:`!tarfile` module or is somehow invalid. .. exception:: CompressionError @@ -255,6 +291,15 @@ The :mod:`tarfile` module defines the following exceptions: Raised to refuse extracting a symbolic link pointing outside the destination directory. +.. exception:: LinkFallbackError + + Raised to refuse emulating a link (hard or symbolic) by extracting another + archive member, when that member would be rejected by the filter location. + The exception that was raised to reject the replacement member is available + as :attr:`!BaseException.__context__`. + + .. versionadded:: 3.14 + The following constants are available at the module level: @@ -310,7 +355,7 @@ The following constants are available at the module level: Each of the following constants defines a tar archive format that the -:mod:`tarfile` module is able to create. See section :ref:`tar-formats` for +:mod:`!tarfile` module is able to create. See section :ref:`tar-formats` for details. @@ -618,7 +663,7 @@ be finalized; only the internally used file object will be closed. See the it is best practice to only do so in top-level applications or :mod:`site configuration `. To set a global default this way, a filter function needs to be wrapped in - :func:`staticmethod` to prevent injection of a ``self`` argument. + :deco:`staticmethod` to prevent injection of a ``self`` argument. .. versionchanged:: 3.14 @@ -1068,6 +1113,12 @@ reused in custom filters: Implements the ``'data'`` filter. In addition to what ``tar_filter`` does: + - Normalize link targets (:attr:`TarInfo.linkname`) using + :func:`os.path.normpath`. + Note that this removes internal ``..`` components, which may change the + meaning of the link if the path in :attr:`!TarInfo.linkname` traverses + symbolic links. + - :ref:`Refuse ` to extract links (hard or soft) that link to absolute paths, or ones that link outside the destination. @@ -1099,6 +1150,10 @@ reused in custom filters: Note that this filter does not block *all* dangerous archive features. See :ref:`tarfile-further-verification` for details. + .. versionchanged:: 3.14 + + Link targets are now normalized. + .. _tarfile-extraction-refuse: @@ -1127,6 +1182,7 @@ Here is an incomplete list of things to consider: * Extract to a :func:`new temporary directory ` to prevent e.g. exploiting pre-existing links, and to make it easier to clean up after a failed extraction. +* Disallow symbolic links if you do not need the functionality. * When working with untrusted data, use external (e.g. OS-level) limits on disk, memory and CPU usage. * Check filenames against an allow-list of characters @@ -1229,7 +1285,7 @@ Command-Line Interface .. versionadded:: 3.4 -The :mod:`tarfile` module provides a simple command-line interface to interact +The :mod:`!tarfile` module provides a simple command-line interface to interact with tar archives. If you want to create a new tar archive, specify its name after the :option:`-c` @@ -1305,6 +1361,9 @@ Command-line options Examples -------- +Reading examples +~~~~~~~~~~~~~~~~~~~ + How to extract an entire tar archive to the current working directory:: import tarfile @@ -1327,6 +1386,23 @@ a generator function instead of a list:: tar.extractall(members=py_files(tar)) tar.close() +How to read a gzip compressed tar archive and display some member information:: + + import tarfile + tar = tarfile.open("sample.tar.gz", "r:gz") + for tarinfo in tar: + print(tarinfo.name, "is", tarinfo.size, "bytes in size and is ", end="") + if tarinfo.isreg(): + print("a regular file.") + elif tarinfo.isdir(): + print("a directory.") + else: + print("something else.") + tar.close() + +Writing examples +~~~~~~~~~~~~~~~~ + How to create an uncompressed tar archive from a list of filenames:: import tarfile @@ -1342,19 +1418,15 @@ The same example using the :keyword:`with` statement:: for name in ["foo", "bar", "quux"]: tar.add(name) -How to read a gzip compressed tar archive and display some member information:: +How to create and write an archive to stdout using +:data:`sys.stdout.buffer ` in the *fileobj* parameter +in :meth:`TarFile.add`:: - import tarfile - tar = tarfile.open("sample.tar.gz", "r:gz") - for tarinfo in tar: - print(tarinfo.name, "is", tarinfo.size, "bytes in size and is ", end="") - if tarinfo.isreg(): - print("a regular file.") - elif tarinfo.isdir(): - print("a directory.") - else: - print("something else.") - tar.close() + import sys + import tarfile + with tarfile.open("sample.tar.gz", "w|gz", fileobj=sys.stdout.buffer) as tar: + for name in ["foo", "bar", "quux"]: + tar.add(name) How to create an archive and reset the user information using the *filter* parameter in :meth:`TarFile.add`:: @@ -1374,7 +1446,7 @@ parameter in :meth:`TarFile.add`:: Supported tar formats --------------------- -There are three tar formats that can be created with the :mod:`tarfile` module: +There are three tar formats that can be created with the :mod:`!tarfile` module: * The POSIX.1-1988 ustar format (:const:`USTAR_FORMAT`). It supports filenames up to a length of at best 256 characters and linknames up to 100 characters. @@ -1383,7 +1455,7 @@ There are three tar formats that can be created with the :mod:`tarfile` module: * The GNU tar format (:const:`GNU_FORMAT`). It supports long filenames and linknames, files bigger than 8 GiB and sparse files. It is the de facto - standard on GNU/Linux systems. :mod:`tarfile` fully supports the GNU tar + standard on GNU/Linux systems. :mod:`!tarfile` fully supports the GNU tar extensions for long names, sparse file support is read-only. * The POSIX.1-2001 pax format (:const:`PAX_FORMAT`). It is the most flexible @@ -1428,7 +1500,7 @@ Unfortunately, there is no way to autodetect the encoding of an archive. The pax format was designed to solve this problem. It stores non-ASCII metadata using the universal character encoding *UTF-8*. -The details of character conversion in :mod:`tarfile` are controlled by the +The details of character conversion in :mod:`!tarfile` are controlled by the *encoding* and *errors* keyword arguments of the :class:`TarFile` class. *encoding* defines the character encoding to use for the metadata in the diff --git a/Doc/library/tempfile.rst b/Doc/library/tempfile.rst index f0a81a093b435b..bd8df44618ad79 100644 --- a/Doc/library/tempfile.rst +++ b/Doc/library/tempfile.rst @@ -225,11 +225,13 @@ The module defines the following user-callable items: properly implements the :const:`os.O_EXCL` flag for :func:`os.open`. The file is readable and writable only by the creating user ID. If the platform uses permission bits to indicate whether a file is executable, - the file is executable by no one. The file descriptor is not inherited - by child processes. + the file is executable by no one. + + The file descriptor is :ref:`not inherited by child processes `. Unlike :func:`TemporaryFile`, the user of :func:`mkstemp` is responsible - for deleting the temporary file when done with it. + for closing the file descriptor (for example, using :func:`os.close`) and + deleting the temporary file (for example, using :func:`os.remove`). If *suffix* is not ``None``, the file name will end with that suffix, otherwise there will be no suffix. :func:`mkstemp` does not put a dot @@ -385,7 +387,7 @@ not surprise other unsuspecting code by changing global API behavior. Examples -------- -Here are some examples of typical usage of the :mod:`tempfile` module:: +Here are some examples of typical usage of the :mod:`!tempfile` module:: >>> import tempfile diff --git a/Doc/library/termios.rst b/Doc/library/termios.rst index 0c6f3059fe71d1..537dfcedd8cf5a 100644 --- a/Doc/library/termios.rst +++ b/Doc/library/termios.rst @@ -2,7 +2,6 @@ =========================================== .. module:: termios - :platform: Unix :synopsis: POSIX style tty control. .. index:: @@ -38,7 +37,7 @@ The module defines the following functions: items with indices :const:`VMIN` and :const:`VTIME`, which are integers when these fields are defined). The interpretation of the flags and the speeds as well as the indexing in the *cc* array must be done using the symbolic - constants defined in the :mod:`termios` module. + constants defined in the :mod:`!termios` module. .. function:: tcsetattr(fd, when, attributes) diff --git a/Doc/library/test.rst b/Doc/library/test.rst index 0aae14c15a6104..e5671159baf738 100644 --- a/Doc/library/test.rst +++ b/Doc/library/test.rst @@ -7,7 +7,7 @@ .. sectionauthor:: Brett Cannon .. note:: - The :mod:`test` package is meant for internal use by Python only. It is + The :mod:`!test` package is meant for internal use by Python only. It is documented for the benefit of the core developers of Python. Any use of this package outside of Python's standard library is discouraged as code mentioned here can change or be removed without notice between releases of @@ -15,12 +15,12 @@ -------------- -The :mod:`test` package contains all regression tests for Python as well as the +The :mod:`!test` package contains all regression tests for Python as well as the modules :mod:`test.support` and :mod:`test.regrtest`. :mod:`test.support` is used to enhance your tests while :mod:`test.regrtest` drives the testing suite. -Each module in the :mod:`test` package whose name starts with ``test_`` is a +Each module in the :mod:`!test` package whose name starts with ``test_`` is a testing suite for a specific module or feature. All new tests should be written using the :mod:`unittest` or :mod:`doctest` module. Some older tests are written using a "traditional" testing style that compares output printed to @@ -38,8 +38,8 @@ written using a "traditional" testing style that compares output printed to .. _writing-tests: -Writing Unit Tests for the :mod:`test` package ----------------------------------------------- +Writing Unit Tests for the :mod:`!test` package +----------------------------------------------- It is preferred that tests that use the :mod:`unittest` module follow a few guidelines. One is to name the test module by starting it with ``test_`` and end @@ -162,12 +162,12 @@ Running tests using the command-line interface .. module:: test.regrtest :synopsis: Drives the regression test suite. -The :mod:`test` package can be run as a script to drive Python's regression +The :mod:`!test` package can be run as a script to drive Python's regression test suite, thanks to the :option:`-m` option: :program:`python -m test`. Under -the hood, it uses :mod:`test.regrtest`; the call :program:`python -m +the hood, it uses :mod:`!test.regrtest`; the call :program:`python -m test.regrtest` used in previous Python versions still works. Running the script by itself automatically starts running all regression tests in the -:mod:`test` package. It does this by finding all modules in the package whose +:mod:`!test` package. It does this by finding all modules in the package whose name starts with ``test_``, importing them, and executing the function :func:`test_main` if present or loading the tests via unittest.TestLoader.loadTestsFromModule if ``test_main`` does not exist. The @@ -175,14 +175,14 @@ names of tests to execute may also be passed to the script. Specifying a single regression test (:program:`python -m test test_spam`) will minimize output and only print whether the test passed or failed. -Running :mod:`test` directly allows what resources are available for +Running :mod:`!test` directly allows what resources are available for tests to use to be set. You do this by using the ``-u`` command-line option. Specifying ``all`` as the value for the ``-u`` option enables all possible resources: :program:`python -m test -uall`. If all but one resource is desired (a more common case), a comma-separated list of resources that are not desired may be listed after ``all``. The command :program:`python -m test -uall,-audio,-largefile` -will run :mod:`test` with all resources except the ``audio`` and +will run :mod:`!test` with all resources except the ``audio`` and ``largefile`` resources. For a list of all resources and more command-line options, run :program:`python -m test -h`. @@ -197,19 +197,19 @@ regression tests. :ref:`controlled using environment variables `. -:mod:`test.support` --- Utilities for the Python test suite -=========================================================== +:mod:`!test.support` --- Utilities for the Python test suite +============================================================ .. module:: test.support :synopsis: Support for Python's regression test suite. -The :mod:`test.support` module provides support for Python's regression +The :mod:`!test.support` module provides support for Python's regression test suite. .. note:: - :mod:`test.support` is not a public module. It is documented here to help + :mod:`!test.support` is not a public module. It is documented here to help Python developers write tests. The API of this module is subject to change without backwards compatibility concerns between releases. @@ -230,7 +230,7 @@ This module defines the following exceptions: function. -The :mod:`test.support` module defines the following constants: +The :mod:`!test.support` module defines the following constants: .. data:: verbose @@ -287,7 +287,7 @@ The :mod:`test.support` module defines the following constants: :meth:`~socket.socket.recv` and :meth:`~socket.socket.send` methods of :class:`socket.socket`. - Its default value is 5 seconds. + Its default value is 10 seconds. See also :data:`INTERNET_TIMEOUT`. @@ -363,7 +363,7 @@ The :mod:`test.support` module defines the following constants: .. data:: TEST_SUPPORT_DIR - Set to the top level directory that contains :mod:`test.support`. + Set to the top level directory that contains :mod:`!test.support`. .. data:: TEST_HOME_DIR @@ -438,7 +438,7 @@ The :mod:`test.support` module defines the following constants: Used to test mixed type comparison. -The :mod:`test.support` module defines the following functions: +The :mod:`!test.support` module defines the following functions: .. function:: busy_retry(timeout, err_msg=None, /, *, error=True) @@ -492,6 +492,12 @@ The :mod:`test.support` module defines the following functions: tests. +.. function:: get_resource_value(resource) + + Return the value specified for *resource* (as :samp:`-u {resource}={value}`). + Return ``None`` if *resource* is disabled or no value is specified. + + .. function:: python_is_optimized() Return ``True`` if Python was not built with ``-O0`` or ``-Og``. @@ -714,7 +720,7 @@ The :mod:`test.support` module defines the following functions: .. decorator:: anticipate_failure(condition) A decorator to conditionally mark tests with - :func:`unittest.expectedFailure`. Any use of this decorator should + :deco:`unittest.expectedFailure`. Any use of this decorator should have an associated comment identifying the relevant tracker issue. @@ -851,7 +857,7 @@ The :mod:`test.support` module defines the following functions: Decorator for tests that fill the address space. -.. function:: linked_with_musl() +.. function:: linked_to_musl() Return ``False`` if there is no evidence the interpreter was compiled with ``musl``, otherwise return a version triple, either ``(0, 0, 0)`` if the @@ -957,6 +963,72 @@ The :mod:`test.support` module defines the following functions: :mod:`tracemalloc` is enabled. +.. currentmodule:: test.support.isolation + +.. decorator:: runInSubprocess(*, options=(), env=None, timeout=None) + + Decorator that runs the decorated test in a fresh interpreter subprocess, in + isolation, so that it does not share global or interpreter state with the + rest of the test run. It can decorate a test method or a whole + :class:`~unittest.TestCase` subclass. Decorated methods must take no extra + arguments. A failure, error or skip in the subprocess is reported for the + corresponding test, and individual :meth:`subtests + ` that fail or are skipped are reported + individually. A reported failure or error shows the original subprocess + traceback as the cause of the exception. + + When a **method** is decorated, only that method runs in a subprocess; all + fixtures (:meth:`~unittest.TestCase.setUp` / :meth:`~unittest.TestCase.tearDown`, + :meth:`~unittest.TestCase.setUpClass` / :meth:`~unittest.TestCase.tearDownClass` + and ``setUpModule()`` / ``tearDownModule()``) run both in the parent process + (as usual) and in the subprocess around the method. + + When a **class** is decorated, the whole class runs in a single subprocess, + and :meth:`~unittest.TestCase.setUpClass`, + :meth:`~unittest.TestCase.tearDownClass`, :meth:`~unittest.TestCase.setUp` + and :meth:`~unittest.TestCase.tearDown` run once each in the subprocess and + are skipped in the parent process. A failure or skip of + :meth:`~unittest.TestCase.setUpClass` in the subprocess is reported for the + whole class. ``setUpModule()`` cannot be controlled by a class decorator, + so it still runs in the parent process too; test it with + :data:`runningInSubprocess` if needed. + + The subprocess inherits the enabled resources (``-u``), memory limit + (``-M``) and verbosity (``-v``) of the parent test run, so that + :func:`~test.support.requires_resource`, :func:`~test.support.requires`, + :func:`~test.support.bigmemtest` and the like behave consistently in both + processes. + + *options* is a sequence of interpreter command line options + to run the subprocess with, + and *env* is a mapping of environment variables to set in it, + on top of the inherited environment. + A value of ``None`` in *env* unsets the variable. + Note that :option:`-E` and :option:`-I` make the subprocess ignore + the ``PYTHON*`` environment variables, including :envvar:`PYTHONPATH`. + + *timeout* is the number of seconds to wait for the subprocess; + the test is reported as an error if it does not complete in time. + By default there is no timeout, + and a hung test is left to the timeout of the test runner. + + The test is skipped on platforms without subprocess support. + + +.. data:: runningInSubprocess + + ``True`` while the code runs in the isolated subprocess spawned by + :func:`runInSubprocess`, and ``False`` otherwise (including in the parent + process and in a normal, non-isolated test run). Fixtures such as + :meth:`~unittest.TestCase.setUp`, :meth:`~unittest.TestCase.tearDown`, + :meth:`~unittest.TestCase.setUpClass`, :meth:`~unittest.TestCase.tearDownClass`, + ``setUpModule()`` and ``tearDownModule()`` can test it to choose which code + to run in the subprocess. + + +.. currentmodule:: test.support + + .. function:: check_free_after_iterating(test, iter, cls, args=()) Assert instances of *cls* are deallocated after iterating. @@ -1037,7 +1109,7 @@ The :mod:`test.support` module defines the following functions: .. versionadded:: 3.11 -The :mod:`test.support` module defines the following classes: +The :mod:`!test.support` module defines the following classes: .. class:: SuppressCrashReport() @@ -1083,14 +1155,14 @@ The :mod:`test.support` module defines the following classes: Try to match a single stored value (*dv*) with a supplied value (*v*). -:mod:`test.support.socket_helper` --- Utilities for socket tests -================================================================ +:mod:`!test.support.socket_helper` --- Utilities for socket tests +================================================================= .. module:: test.support.socket_helper :synopsis: Support for socket tests. -The :mod:`test.support.socket_helper` module provides support for socket tests. +The :mod:`!test.support.socket_helper` module provides support for socket tests. .. versionadded:: 3.9 @@ -1161,14 +1233,14 @@ The :mod:`test.support.socket_helper` module provides support for socket tests. exceptions. -:mod:`test.support.script_helper` --- Utilities for the Python execution tests -============================================================================== +:mod:`!test.support.script_helper` --- Utilities for the Python execution tests +=============================================================================== .. module:: test.support.script_helper :synopsis: Support for Python's script execution tests. -The :mod:`test.support.script_helper` module provides support for Python's +The :mod:`!test.support.script_helper` module provides support for Python's script execution tests. .. function:: interpreter_requires_environment() @@ -1272,13 +1344,13 @@ script execution tests. path and the archive name for the zip file. -:mod:`test.support.bytecode_helper` --- Support tools for testing correct bytecode generation -============================================================================================= +:mod:`!test.support.bytecode_helper` --- Support tools for testing correct bytecode generation +============================================================================================== .. module:: test.support.bytecode_helper :synopsis: Support tools for testing correct bytecode generation. -The :mod:`test.support.bytecode_helper` module provides support for testing +The :mod:`!test.support.bytecode_helper` module provides support for testing and inspecting bytecode generation. .. versionadded:: 3.9 @@ -1304,13 +1376,13 @@ The module defines the following class: Throws :exc:`AssertionError` if *opname* is found. -:mod:`test.support.threading_helper` --- Utilities for threading tests -====================================================================== +:mod:`!test.support.threading_helper` --- Utilities for threading tests +======================================================================= .. module:: test.support.threading_helper :synopsis: Support for threading tests. -The :mod:`test.support.threading_helper` module provides support for threading tests. +The :mod:`!test.support.threading_helper` module provides support for threading tests. .. versionadded:: 3.10 @@ -1384,13 +1456,20 @@ The :mod:`test.support.threading_helper` module provides support for threading t .. versionadded:: 3.8 -:mod:`test.support.os_helper` --- Utilities for os tests -======================================================================== +.. function:: run_concurrently(worker_func, nthreads, args=(), kwargs={}) + + Run the worker function concurrently in multiple threads. + Re-raises an exception if any thread raises one, after all threads have + finished. + + +:mod:`!test.support.os_helper` --- Utilities for os tests +========================================================= .. module:: test.support.os_helper :synopsis: Support for os tests. -The :mod:`test.support.os_helper` module provides support for os tests. +The :mod:`!test.support.os_helper` module provides support for os tests. .. versionadded:: 3.10 @@ -1579,13 +1658,13 @@ The :mod:`test.support.os_helper` module provides support for os tests. wrapped with a wait loop that checks for the existence of the file. -:mod:`test.support.import_helper` --- Utilities for import tests -================================================================ +:mod:`!test.support.import_helper` --- Utilities for import tests +================================================================= .. module:: test.support.import_helper :synopsis: Support for import tests. -The :mod:`test.support.import_helper` module provides support for import tests. +The :mod:`!test.support.import_helper` module provides support for import tests. .. versionadded:: 3.10 @@ -1693,13 +1772,13 @@ The :mod:`test.support.import_helper` module provides support for import tests. will be reverted at the end of the block. -:mod:`test.support.warnings_helper` --- Utilities for warnings tests -==================================================================== +:mod:`!test.support.warnings_helper` --- Utilities for warnings tests +===================================================================== .. module:: test.support.warnings_helper :synopsis: Support for warnings tests. -The :mod:`test.support.warnings_helper` module provides support for warnings tests. +The :mod:`!test.support.warnings_helper` module provides support for warnings tests. .. versionadded:: 3.10 diff --git a/Doc/library/text.rst b/Doc/library/text.rst index 47b678434fc899..92e7dd9a53b80d 100644 --- a/Doc/library/text.rst +++ b/Doc/library/text.rst @@ -16,6 +16,7 @@ Python's built-in string type in :ref:`textseq`. .. toctree:: string.rst + string.templatelib.rst re.rst difflib.rst textwrap.rst diff --git a/Doc/library/textwrap.rst b/Doc/library/textwrap.rst index a58b460fef409c..c9230f7d82705f 100644 --- a/Doc/library/textwrap.rst +++ b/Doc/library/textwrap.rst @@ -11,7 +11,7 @@ -------------- -The :mod:`textwrap` module provides some convenience functions, +The :mod:`!textwrap` module provides some convenience functions, as well as :class:`TextWrapper`, the class that does all the work. If you're just wrapping or filling one or two text strings, the convenience functions should be good enough; otherwise, you should use an instance of @@ -102,6 +102,10 @@ functions should be good enough; otherwise, you should use an instance of print(repr(s)) # prints ' hello\n world\n ' print(repr(dedent(s))) # prints 'hello\n world\n' + .. versionchanged:: 3.14 + The :func:`!dedent` function now correctly normalizes blank lines containing + only whitespace characters. Previously, the implementation only normalized + blank lines containing tabs and spaces. .. function:: indent(text, prefix, predicate=None) diff --git a/Doc/library/threading.rst b/Doc/library/threading.rst index 249c0a5cb035c3..69539fa1fd4bb5 100644 --- a/Doc/library/threading.rst +++ b/Doc/library/threading.rst @@ -11,6 +11,52 @@ This module constructs higher-level threading interfaces on top of the lower level :mod:`_thread` module. +.. include:: ../includes/wasm-notavail.rst + +Introduction +------------ + +The :mod:`!threading` module provides a way to run multiple `threads +`_ (smaller +units of a process) concurrently within a single process. It allows for the +creation and management of threads, making it possible to execute tasks in +parallel, sharing memory space. Threads are particularly useful when tasks are +I/O bound, such as file operations or making network requests, +where much of the time is spent waiting for external resources. + +A typical use case for :mod:`!threading` includes managing a pool of worker +threads that can process multiple tasks concurrently. Here's a basic example of +creating and starting threads using :class:`~threading.Thread`:: + + import threading + import time + + def crawl(link, delay=3): + print(f"crawl started for {link}") + time.sleep(delay) # Blocking I/O (simulating a network request) + print(f"crawl ended for {link}") + + links = [ + "https://python.org", + "https://docs.python.org", + "https://peps.python.org", + ] + + # Start threads for each link + threads = [] + for link in links: + # Using `args` to pass positional arguments and `kwargs` for keyword arguments + t = threading.Thread(target=crawl, args=(link,), kwargs={"delay": 2}) + threads.append(t) + + # Start each thread + for t in threads: + t.start() + + # Wait for all threads to finish + for t in threads: + t.join() + .. versionchanged:: 3.7 This module used to be optional, it is now always available. @@ -45,7 +91,25 @@ level :mod:`_thread` module. However, threading is still an appropriate model if you want to run multiple I/O-bound tasks simultaneously. -.. include:: ../includes/wasm-notavail.rst +GIL and performance considerations +---------------------------------- + +Unlike the :mod:`multiprocessing` module, which uses separate processes to +bypass the :term:`global interpreter lock` (GIL), the threading module operates +within a single process, meaning that all threads share the same memory space. +However, the GIL limits the performance gains of threading when it comes to +CPU-bound tasks, as only one thread can execute Python bytecode at a time. +Despite this, threads remain a useful tool for achieving concurrency in many +scenarios. + +As of Python 3.13, :term:`free-threaded ` builds +can disable the GIL, enabling true parallel execution of threads, but this +feature is not available by default (see :pep:`703`). + +.. TODO: At some point this feature will become available by default. + +Reference +--------- This module defines the following functions: @@ -62,7 +126,7 @@ This module defines the following functions: Return the current :class:`Thread` object, corresponding to the caller's thread of control. If the caller's thread of control was not created through the - :mod:`threading` module, a dummy thread object with limited functionality is + :mod:`!threading` module, a dummy thread object with limited functionality is returned. The function ``currentThread`` is a deprecated alias for this function. @@ -157,13 +221,13 @@ This module defines the following functions: .. index:: single: trace function - Set a trace function for all threads started from the :mod:`threading` module. + Set a trace function for all threads started from the :mod:`!threading` module. The *func* will be passed to :func:`sys.settrace` for each thread, before its :meth:`~Thread.run` method is called. .. function:: settrace_all_threads(func) - Set a trace function for all threads started from the :mod:`threading` module + Set a trace function for all threads started from the :mod:`!threading` module and all Python threads that are currently executing. The *func* will be passed to :func:`sys.settrace` for each thread, before its @@ -186,13 +250,13 @@ This module defines the following functions: .. index:: single: profile function - Set a profile function for all threads started from the :mod:`threading` module. + Set a profile function for all threads started from the :mod:`!threading` module. The *func* will be passed to :func:`sys.setprofile` for each thread, before its :meth:`~Thread.run` method is called. .. function:: setprofile_all_threads(func) - Set a profile function for all threads started from the :mod:`threading` module + Set a profile function for all threads started from the :mod:`!threading` module and all Python threads that are currently executing. The *func* will be passed to :func:`sys.setprofile` for each thread, before its @@ -257,8 +321,8 @@ when implemented, are mapped to module-level functions. All of the methods described below are executed atomically. -Thread-Local Data ------------------ +Thread-local data +^^^^^^^^^^^^^^^^^ Thread-local data is data whose values are thread specific. If you have data that you want to be local to a thread, create a @@ -389,8 +453,8 @@ affects what we see:: .. _thread-objects: -Thread Objects --------------- +Thread objects +^^^^^^^^^^^^^^ The :class:`Thread` class represents an activity that is run in a separate thread of control. There are two ways to specify the activity: by passing a @@ -448,7 +512,7 @@ since it is impossible to detect the termination of alien threads. This constructor should always be called with keyword arguments. Arguments are: - *group* should be ``None``; reserved for future extension when a + *group* must be ``None`` as it is reserved for future extension when a :class:`!ThreadGroup` class is implemented. *target* is the callable object to be invoked by the :meth:`run` method. @@ -557,7 +621,7 @@ since it is impossible to detect the termination of alien threads. an error to :meth:`~Thread.join` a thread before it has been started and attempts to do so raise the same exception. - If an attempt is made to join a running daemonic thread in in late stages + If an attempt is made to join a running daemonic thread in late stages of :term:`Python finalization ` :meth:`!join` raises a :exc:`PythonFinalizationError`. @@ -645,8 +709,8 @@ since it is impossible to detect the termination of alien threads. .. _lock-objects: -Lock Objects ------------- +Lock objects +^^^^^^^^^^^^ A primitive lock is a synchronization primitive that is not owned by a particular thread when locked. In Python, it is currently the lowest level @@ -738,8 +802,8 @@ All methods are executed atomically. .. _rlock-objects: -RLock Objects -------------- +RLock objects +^^^^^^^^^^^^^ A reentrant lock is a synchronization primitive that may be acquired multiple times by the same thread. Internally, it uses the concepts of "owning thread" @@ -848,8 +912,8 @@ call release as many times the lock has been acquired can lead to deadlock. .. _condition-objects: -Condition Objects ------------------ +Condition objects +^^^^^^^^^^^^^^^^^ A condition variable is always associated with some kind of lock; this can be passed in or one will be created by default. Passing one in is useful when @@ -1026,8 +1090,8 @@ item to the buffer only needs to wake up one consumer thread. .. _semaphore-objects: -Semaphore Objects ------------------ +Semaphore objects +^^^^^^^^^^^^^^^^^ This is one of the oldest synchronization primitives in the history of computer science, invented by the early Dutch computer scientist Edsger W. Dijkstra (he @@ -1107,7 +1171,7 @@ Semaphores also support the :ref:`context management protocol `. .. _semaphore-examples: -:class:`Semaphore` Example +:class:`Semaphore` example ^^^^^^^^^^^^^^^^^^^^^^^^^^ Semaphores are often used to guard resources with limited capacity, for example, @@ -1135,8 +1199,8 @@ causes the semaphore to be released more than it's acquired will go undetected. .. _event-objects: -Event Objects -------------- +Event objects +^^^^^^^^^^^^^ This is one of the simplest mechanisms for communication between threads: one thread signals an event and other threads wait for it. @@ -1192,8 +1256,8 @@ method. The :meth:`~Event.wait` method blocks until the flag is true. .. _timer-objects: -Timer Objects -------------- +Timer objects +^^^^^^^^^^^^^ This class represents an action that should be run only after a certain amount of time has passed --- a timer. :class:`Timer` is a subclass of :class:`Thread` @@ -1230,8 +1294,8 @@ For example:: only work if the timer is still in its waiting stage. -Barrier Objects ---------------- +Barrier objects +^^^^^^^^^^^^^^^ .. versionadded:: 3.2 diff --git a/Doc/library/threadsafety.rst b/Doc/library/threadsafety.rst new file mode 100644 index 00000000000000..a529f7803affbc --- /dev/null +++ b/Doc/library/threadsafety.rst @@ -0,0 +1,606 @@ +.. _threadsafety: + +************************ +Thread Safety Guarantees +************************ + +This page documents thread-safety guarantees for built-in types in Python's +free-threaded build. The guarantees described here apply when using Python with +the :term:`GIL` disabled (free-threaded mode). When the GIL is enabled, most +operations are implicitly serialized. + +For general guidance on writing thread-safe code in free-threaded Python, see +:ref:`freethreading-python-howto`. + + +.. _threadsafety-levels: + +Thread safety levels +==================== + +The C API documentation uses the following levels to describe the thread +safety guarantees of each function. The levels are listed from least to +most safe. + +.. _threadsafety-level-incompatible: + +Incompatible +------------ + +A function or operation that cannot be made safe for concurrent use even +with external synchronization. Incompatible code typically accesses +global state in an unsynchronized way and must only be called from a single +thread throughout the program's lifetime. + +Example: a function that modifies process-wide state such as signal handlers +or environment variables, where concurrent calls from any threads, even with +external locking, can conflict with the runtime or other libraries. + +.. _threadsafety-level-compatible: + +Compatible +---------- + +A function or operation that is safe to call from multiple threads +*provided* the caller supplies appropriate external synchronization, for +example by holding a :term:`lock` for the duration of each call. Without +such synchronization, concurrent calls may produce :term:`race conditions +` or :term:`data races `. + +Example: a function that reads from or writes to an object whose internal +state is not protected by a lock. Callers must ensure that no two threads +access the same object at the same time. + +.. _threadsafety-level-distinct: + +Safe on distinct objects +------------------------ + +A function or operation that is safe to call from multiple threads without +external synchronization, as long as each thread operates on a **different** +object. Two threads may call the function at the same time, but they must +not pass the same object (or objects that share underlying state) as +arguments. + +Example: a function that modifies fields of a struct using non-atomic +writes. Two threads can each call the function on their own struct +instance safely, but concurrent calls on the *same* instance require +external synchronization. + +.. _threadsafety-level-shared: + +Safe on shared objects +---------------------- + +A function or operation that is safe for concurrent use on the **same** +object. The implementation uses internal synchronization (such as +:term:`per-object locks ` or +:ref:`critical sections `) to protect shared +mutable state, so callers do not need to supply their own locking. + +Example: :c:func:`PyList_GetItemRef` can be called from multiple threads on the +same :c:type:`PyListObject` - it uses internal synchronization to serialize +access. + +.. _threadsafety-level-atomic: + +Atomic +------ + +A function or operation that appears :term:`atomic ` with +respect to other threads - it executes instantaneously from the perspective +of other threads. This is the strongest form of thread safety. + +Example: :c:func:`PyMutex_IsLocked` performs an atomic read of the mutex +state and can be called from any thread at any time. + + +.. _thread-safety-list: + +Thread safety for list objects +============================== + +Reading a single element from a :class:`list` is +:term:`atomic `: + +.. code-block:: + :class: good + + lst[i] # list.__getitem__ + +The following methods traverse the list and use :term:`atomic ` +reads of each item to perform their function. That means that they may +return results affected by concurrent modifications: + +.. code-block:: + :class: maybe + + item in lst + lst.index(item) + lst.count(item) + +All of the above operations avoid acquiring :term:`per-object locks +`. They do not block concurrent modifications. Other +operations that hold a lock will not block these from observing intermediate +states. + +All other operations from here on block using the :term:`per-object lock`. + +Writing a single item via ``lst[i] = x`` is safe to call from multiple +threads and will not corrupt the list. + +The following operations return new objects and appear +:term:`atomic ` to other threads: + +.. code-block:: + :class: good + + lst1 + lst2 # concatenates two lists into a new list + x * lst # repeats lst x times into a new list + lst.copy() # returns a shallow copy of the list + +The following methods that only operate on a single element with no shifting +required are :term:`atomic `: + +.. code-block:: + :class: good + + lst.append(x) # append to the end of the list, no shifting required + lst.pop() # pop element from the end of the list, no shifting required + +The :meth:`~list.clear` method is also :term:`atomic `. +Other threads cannot observe elements being removed. + +The :meth:`~list.sort` method is not :term:`atomic `. +Other threads cannot observe intermediate states during sorting, but the +list appears empty for the duration of the sort. + +The following operations may allow :term:`lock-free` operations to observe +intermediate states since they modify multiple elements in place: + +.. code-block:: + :class: maybe + + lst.insert(idx, item) # shifts elements + lst.pop(idx) # idx not at the end of the list, shifts elements + lst *= x # copies elements in place + +The :meth:`~list.remove` method may allow concurrent modifications since +element comparison may execute arbitrary Python code (via +:meth:`~object.__eq__`). + +:meth:`~list.extend` is safe to call from multiple threads. However, its +guarantees depend on the iterable passed to it. If it is a :class:`list`, a +:class:`tuple`, a :class:`set`, a :class:`frozenset`, a :class:`dict` or a +:ref:`dictionary view object ` (but not their subclasses), the +``extend`` operation is safe from concurrent modifications to the iterable. +Otherwise, an iterator is created which can be concurrently modified by +another thread. The same applies to inplace concatenation of a list with +other iterables when using ``lst += iterable``. + +Similarly, assigning to a list slice with ``lst[i:j] = iterable`` is safe +to call from multiple threads, but ``iterable`` is only locked when it is +also a :class:`list` (but not its subclasses). + +Operations that involve multiple accesses, as well as iteration, are never +atomic. For example: + +.. code-block:: + :class: bad + + # NOT atomic: read-modify-write + lst[i] = lst[i] + 1 + + # NOT atomic: check-then-act + if lst: + item = lst.pop() + + # NOT thread-safe: iteration while modifying + for item in lst: + process(item) # another thread may modify lst + +Consider external synchronization when sharing :class:`list` instances +across threads. + + +.. _thread-safety-dict: + +Thread safety for dict objects +============================== + +Creating a dictionary with the :class:`dict` constructor is atomic when the +argument to it is a :class:`dict` or a :class:`tuple`. When using the +:meth:`dict.fromkeys` method, dictionary creation is atomic when the +argument is a :class:`dict`, :class:`tuple`, :class:`set` or +:class:`frozenset`. + +The following operations and functions are :term:`lock-free` and +:term:`atomic `. + +.. code-block:: + :class: good + + d[key] # dict.__getitem__ + d.get(key) # dict.get + key in d # dict.__contains__ + len(d) # dict.__len__ + +All other operations from here on hold the :term:`per-object lock`. + +Writing or removing a single item is safe to call from multiple threads +and will not corrupt the dictionary: + +.. code-block:: + :class: good + + d[key] = value # write + del d[key] # delete + d.pop(key) # remove and return + d.popitem() # remove and return last item + d.setdefault(key, v) # insert if missing + +These operations may compare keys using :meth:`~object.__eq__`, which can +execute arbitrary Python code. During such comparisons, the dictionary may +be modified by another thread. For built-in types like :class:`str`, +:class:`int`, and :class:`float`, that implement :meth:`~object.__eq__` in C, +the underlying lock is not released during comparisons and this is not a +concern. + +The following operations return new objects and hold the :term:`per-object lock` +for the duration of the operation: + +.. code-block:: + :class: good + + d.copy() # returns a shallow copy of the dictionary + d | other # merges two dicts into a new dict + d.keys() # returns a new dict_keys view object + d.values() # returns a new dict_values view object + d.items() # returns a new dict_items view object + +The :meth:`~dict.clear` method holds the lock for its duration. Other +threads cannot observe elements being removed. + +The following operations lock both dictionaries. For :meth:`~dict.update` +and ``|=``, this applies only when the other operand is a :class:`dict` +that uses the standard dict iterator (but not subclasses that override +iteration). For equality comparison, this applies to :class:`dict` and +its subclasses: + +.. code-block:: + :class: good + + d.update(other_dict) # both locked when other_dict is a dict + d |= other_dict # both locked when other_dict is a dict + d == other_dict # both locked for dict and subclasses + +All comparison operations also compare values using :meth:`~object.__eq__`, +so for non-built-in types the lock may be released during comparison. + +:meth:`~dict.fromkeys` locks both the new dictionary and the iterable +when the iterable is exactly a :class:`dict`, :class:`set`, or +:class:`frozenset` (not subclasses): + +.. code-block:: + :class: good + + dict.fromkeys(a_dict) # locks both + dict.fromkeys(a_set) # locks both + dict.fromkeys(a_frozenset) # locks both + +When updating from a non-dict iterable, only the target dictionary is +locked. The iterable may be concurrently modified by another thread: + +.. code-block:: + :class: maybe + + d.update(iterable) # iterable is not a dict: only d locked + d |= iterable # iterable is not a dict: only d locked + dict.fromkeys(iterable) # iterable is not a dict/set/frozenset: only result locked + +Operations that involve multiple accesses, as well as iteration, are never +atomic: + +.. code-block:: + :class: bad + + # NOT atomic: read-modify-write + d[key] = d[key] + 1 + + # NOT atomic: check-then-act (TOCTOU) + if key in d: + del d[key] + + # NOT thread-safe: iteration while modifying + for key, value in d.items(): + process(key) # another thread may modify d + +To avoid time-of-check to time-of-use (TOCTOU) issues, use atomic +operations or handle exceptions: + +.. code-block:: + :class: good + + # Use pop() with default instead of check-then-delete + d.pop(key, None) + + # Or handle the exception + try: + del d[key] + except KeyError: + pass + +To safely iterate over a dictionary that may be modified by another +thread, iterate over a copy: + +.. code-block:: + :class: good + + # Make a copy to iterate safely + for key, value in d.copy().items(): + process(key) + +Consider external synchronization when sharing :class:`dict` instances +across threads. + + +.. _thread-safety-set: + +Thread safety for set objects +============================== + +The :func:`len` function is lock-free and :term:`atomic `. + +The following read operation is lock-free. It does not block concurrent +modifications and may observe intermediate states from operations that +hold the per-object lock: + +.. code-block:: + :class: good + + elem in s # set.__contains__ + +This operation may compare elements using :meth:`~object.__eq__`, which can +execute arbitrary Python code. During such comparisons, the set may be +modified by another thread. For built-in types like :class:`str`, +:class:`int`, and :class:`float`, :meth:`!__eq__` does not release the +underlying lock during comparisons and this is not a concern. + +All other operations from here on hold the per-object lock. + +Adding or removing a single element is safe to call from multiple threads +and will not corrupt the set: + +.. code-block:: + :class: good + + s.add(elem) # add element + s.remove(elem) # remove element, raise if missing + s.discard(elem) # remove element if present + s.pop() # remove and return arbitrary element + +These operations also compare elements, so the same :meth:`~object.__eq__` +considerations as above apply. + +The :meth:`~set.copy` method returns a new object and holds the per-object lock +for the duration so that it is always atomic. + +The :meth:`~set.clear` method holds the lock for its duration. Other +threads cannot observe elements being removed. + +The following operations only accept :class:`set` or :class:`frozenset` +as operands and always lock both objects: + +.. code-block:: + :class: good + + s |= other # other must be set/frozenset + s &= other # other must be set/frozenset + s -= other # other must be set/frozenset + s ^= other # other must be set/frozenset + s & other # other must be set/frozenset + s | other # other must be set/frozenset + s - other # other must be set/frozenset + s ^ other # other must be set/frozenset + +:meth:`set.update`, :meth:`set.union`, :meth:`set.intersection` and +:meth:`set.difference` can take multiple iterables as arguments. They all +iterate through all the passed iterables and do the following: + + * :meth:`set.update` and :meth:`set.union` lock both objects only when + the other operand is a :class:`set`, :class:`frozenset`, or :class:`dict`. + * :meth:`set.intersection` and :meth:`set.difference` always try to lock + all objects. + +:meth:`set.symmetric_difference` tries to lock both objects. + +The update variants of the above methods also have some differences between +them: + + * :meth:`set.difference_update` and :meth:`set.intersection_update` try + to lock all objects one-by-one. + * :meth:`set.symmetric_difference_update` only locks the arguments if it is + of type :class:`set`, :class:`frozenset`, or :class:`dict`. + +The following methods always try to lock both objects: + +.. code-block:: + :class: good + + s.isdisjoint(other) # both locked + s.issubset(other) # both locked + s.issuperset(other) # both locked + +Operations that involve multiple accesses, as well as iteration, are never +atomic: + +.. code-block:: + :class: bad + + # NOT atomic: check-then-act + if elem in s: + s.remove(elem) + + # NOT thread-safe: iteration while modifying + for elem in s: + process(elem) # another thread may modify s + +Consider external synchronization when sharing :class:`set` instances +across threads. See :ref:`freethreading-python-howto` for more information. + + +.. _thread-safety-bytearray: + +Thread safety for bytearray objects +=================================== + + The :func:`len` function is lock-free and :term:`atomic `. + + Concatenation and comparisons use the buffer protocol, which prevents + resizing but does not hold the per-object lock. These operations may + observe intermediate states from concurrent modifications: + + .. code-block:: + :class: maybe + + ba + other # may observe concurrent writes + ba == other # may observe concurrent writes + ba < other # may observe concurrent writes + + All other operations from here on hold the per-object lock. + + Reading a single element or slice is safe to call from multiple threads: + + .. code-block:: + :class: good + + ba[i] # bytearray.__getitem__ + ba[i:j] # slice + + The following operations are safe to call from multiple threads and will + not corrupt the bytearray: + + .. code-block:: + :class: good + + ba[i] = x # write single byte + ba[i:j] = values # write slice + ba.append(x) # append single byte + ba.extend(other) # extend with iterable + ba.insert(i, x) # insert single byte + ba.pop() # remove and return last byte + ba.pop(i) # remove and return byte at index + ba.remove(x) # remove first occurrence + ba.reverse() # reverse in place + ba.clear() # remove all bytes + + Slice assignment locks both objects when *values* is a :class:`bytearray`: + + .. code-block:: + :class: good + + ba[i:j] = other_bytearray # both locked + + The following operations return new objects and hold the per-object lock + for the duration: + + .. code-block:: + :class: good + + ba.copy() # returns a shallow copy + ba * n # repeat into new bytearray + + The membership test holds the lock for its duration: + + .. code-block:: + :class: good + + x in ba # bytearray.__contains__ + + All other bytearray methods (such as :meth:`~bytearray.find`, + :meth:`~bytearray.replace`, :meth:`~bytearray.split`, + :meth:`~bytearray.decode`, etc.) hold the per-object lock for their + duration. + + Operations that involve multiple accesses, as well as iteration, are never + atomic: + + .. code-block:: + :class: bad + + # NOT atomic: check-then-act + if x in ba: + ba.remove(x) + + # NOT thread-safe: iteration while modifying + for byte in ba: + process(byte) # another thread may modify ba + + To safely iterate over a bytearray that may be modified by another + thread, iterate over a copy: + + .. code-block:: + :class: good + + # Make a copy to iterate safely + for byte in ba.copy(): + process(byte) + + Consider external synchronization when sharing :class:`bytearray` instances + across threads. See :ref:`freethreading-python-howto` for more information. + + +.. _thread-safety-memoryview: + +Thread safety for memoryview objects +==================================== + +:class:`memoryview` objects provide access to the internal data of an +underlying object without copying. Thread safety depends on both the +memoryview itself and the underlying buffer exporter. + +The memoryview implementation uses atomic operations to track its own +exports in the :term:`free-threaded build`. Creating and +releasing a memoryview are thread-safe. Attribute access (e.g., +:attr:`~memoryview.shape`, :attr:`~memoryview.format`) reads fields that +are immutable for the lifetime of the memoryview, so concurrent reads +are safe as long as the memoryview has not been released. + +However, the actual data accessed through the memoryview is owned by the +underlying object. Concurrent access to this data is only safe if the +underlying object supports it: + +* For immutable objects like :class:`bytes`, concurrent reads through + multiple memoryviews are safe. + +* For mutable objects like :class:`bytearray`, reading and writing the + same memory region from multiple threads without external + synchronization is not safe and may result in data corruption. + Note that even read-only memoryviews of mutable objects do not + prevent data races if the underlying object is modified from + another thread. + +.. code-block:: + :class: bad + + # NOT safe: concurrent writes to the same buffer + data = bytearray(1000) + view = memoryview(data) + # Thread 1: view[0:500] = b'x' * 500 + # Thread 2: view[0:500] = b'y' * 500 + +.. code-block:: + :class: good + + # Safe: use a lock for concurrent access + import threading + lock = threading.Lock() + data = bytearray(1000) + view = memoryview(data) + + with lock: + view[0:500] = b'x' * 500 + +Resizing or reallocating the underlying object (such as calling +:meth:`bytearray.resize`) while a memoryview is exported raises +:exc:`BufferError`. This is enforced regardless of threading. diff --git a/Doc/library/time.rst b/Doc/library/time.rst index 542493a82af94d..a8b721b59df348 100644 --- a/Doc/library/time.rst +++ b/Doc/library/time.rst @@ -238,8 +238,8 @@ Functions The result has the following attributes: - - *adjustable*: ``True`` if the clock can be changed automatically (e.g. by - a NTP daemon) or manually by the system administrator, ``False`` otherwise + - *adjustable*: ``True`` if the clock can be set to jump forward or backward + in time, ``False`` otherwise. Does not refer to gradual NTP rate adjustments. - *implementation*: The name of the underlying C function used to get the clock value. Refer to :ref:`time-clock-id-constants` for possible values. - *monotonic*: ``True`` if the clock cannot go backward, @@ -306,10 +306,11 @@ Functions .. versionadded:: 3.3 .. versionchanged:: 3.5 - The function is now always available and always system-wide. + The function is now always available and the clock is now the same for + all processes. .. versionchanged:: 3.10 - On macOS, the function is now system-wide. + On macOS, the clock is now the same for all processes. .. function:: monotonic_ns() -> int @@ -325,7 +326,8 @@ Functions Return the value (in fractional seconds) of a performance counter, i.e. a clock with the highest available resolution to measure a short duration. It - does include time elapsed during sleep and is system-wide. The reference + does include time elapsed during sleep. The clock is the same for all + processes. The reference point of the returned value is undefined, so that only the difference between the results of two calls is valid. @@ -340,7 +342,7 @@ Functions .. versionadded:: 3.3 .. versionchanged:: 3.10 - On Windows, the function is now system-wide. + On Windows, the clock is now the same for all processes. .. versionchanged:: 3.13 Use the same clock as :func:`time.monotonic`. @@ -394,9 +396,9 @@ Functions On Windows, if *secs* is zero, the thread relinquishes the remainder of its time slice to any other thread that is ready to run. If there are no other threads ready to run, the function returns immediately, and the thread - continues execution. On Windows 8.1 and newer the implementation uses + continues execution. On Windows 10 and newer the implementation uses a `high-resolution timer - `_ + `_ which provides resolution of 100 nanoseconds. If *secs* is zero, ``Sleep(0)`` is used. .. rubric:: Unix implementation @@ -568,7 +570,7 @@ Functions calculations when the day of the week and the year are specified. Here is an example, a format for dates compatible with that specified in the - :rfc:`2822` Internet email standard. [1]_ :: + :rfc:`5322` Internet email standard. [1]_ :: >>> from time import gmtime, strftime >>> strftime("%a, %d %b %Y %H:%M:%S +0000", gmtime()) @@ -712,13 +714,18 @@ Functions Clock: - * On Windows, call ``GetSystemTimeAsFileTime()``. + * On Windows, call ``GetSystemTimePreciseAsFileTime()``. * Call ``clock_gettime(CLOCK_REALTIME)`` if available. * Otherwise, call ``gettimeofday()``. Use :func:`time_ns` to avoid the precision loss caused by the :class:`float` type. +.. versionchanged:: 3.13 + + On Windows, calls ``GetSystemTimePreciseAsFileTime()`` instead of + ``GetSystemTimeAsFileTime()``. + .. function:: time_ns() -> int @@ -928,7 +935,7 @@ These constants are used as parameters for :func:`clock_getres` and .. data:: CLOCK_TAI - `International Atomic Time `_ + `International Atomic Time `_ The system must have a current leap second table in order for this to give the correct answer. PTP or NTP software can maintain a leap second table. @@ -982,8 +989,8 @@ The following constant is the only parameter that can be sent to .. data:: CLOCK_REALTIME - System-wide real-time clock. Setting this clock requires appropriate - privileges. + Real-time clock. Setting this clock requires appropriate privileges. + The clock is the same for all processes. .. availability:: Unix. @@ -1045,4 +1052,5 @@ Timezone Constants strict reading of the original 1982 :rfc:`822` standard calls for a two-digit year (``%y`` rather than ``%Y``), but practice moved to 4-digit years long before the year 2000. After that, :rfc:`822` became obsolete and the 4-digit year has - been first recommended by :rfc:`1123` and then mandated by :rfc:`2822`. + been first recommended by :rfc:`1123` and then mandated by :rfc:`2822`, + with :rfc:`5322` continuing this requirement. diff --git a/Doc/library/timeit.rst b/Doc/library/timeit.rst index 548a3ee0540506..bc12061a2aeb2d 100644 --- a/Doc/library/timeit.rst +++ b/Doc/library/timeit.rst @@ -355,7 +355,7 @@ to test for missing and present object attributes: 0.08588060699912603 -To give the :mod:`timeit` module access to functions you define, you can pass a +To give the :mod:`!timeit` module access to functions you define, you can pass a *setup* parameter which contains an import statement:: def test(): diff --git a/Doc/library/tk.rst b/Doc/library/tk.rst index 0593f8b73ea545..fa3c7e910ce21f 100644 --- a/Doc/library/tk.rst +++ b/Doc/library/tk.rst @@ -1,7 +1,7 @@ .. _tkinter: ********************************* -Graphical User Interfaces with Tk +Graphical user interfaces with Tk ********************************* .. index:: @@ -39,6 +39,7 @@ alternative `GUI frameworks and tools .dnd_leave(source, event)* -#. Call to *.dnd_enter(source, event)* -#. Call to *.dnd_commit(source, event)* to notify of drop -#. Call to *.dnd_end(target, event)* to signal end of drag-and-drop +#. Call to ``.dnd_leave(source, event)``. +#. Call to ``.dnd_enter(source, event)``. +#. Call to ``.dnd_commit(source, event)`` to notify of the drop. +#. Call to ``.dnd_end(target, event)`` to signal the end of drag-and-drop. .. class:: DndHandler(source, event) @@ -49,7 +49,8 @@ Selection of a target object occurs as follows: .. method:: on_motion(event) - Inspect area below mouse for target objects while drag is performed. + Inspect area below mouse for target objects while a drag + is performed. .. method:: on_release(event) @@ -57,7 +58,9 @@ Selection of a target object occurs as follows: .. function:: dnd_start(source, event) - Factory function for drag-and-drop process. + Factory function for the drag-and-drop process. + Return the :class:`DndHandler` instance managing the drag, or ``None`` if a + drag could not be started. .. seealso:: diff --git a/Doc/library/tkinter.font.rst b/Doc/library/tkinter.font.rst index ed01bd5f483943..947207724ab040 100644 --- a/Doc/library/tkinter.font.rst +++ b/Doc/library/tkinter.font.rst @@ -2,14 +2,13 @@ ============================================= .. module:: tkinter.font - :platform: Tk :synopsis: Tkinter font-wrapping class **Source code:** :source:`Lib/tkinter/font.py` -------------- -The :mod:`tkinter.font` module provides the :class:`Font` class for creating +The :mod:`!tkinter.font` module provides the :class:`Font` class for creating and using named fonts. The different font weights and slants are: @@ -27,6 +26,10 @@ The different font weights and slants are: fonts as a single object, rather than specifying a font by its attributes with each occurrence. + .. versionchanged:: 3.10 + Two fonts now compare equal (``==``) only when both are :class:`Font` + instances with the same name belonging to the same Tcl interpreter. + arguments: | *font* - font specifier tuple (family, size, options) @@ -35,7 +38,7 @@ The different font weights and slants are: additional keyword options (ignored if *font* is specified): - | *family* - font family i.e. Courier, Times + | *family* - font family, for example, Courier, Times | *size* - font size | If *size* is positive it is interpreted as size in points. | If *size* is a negative number its absolute value is treated @@ -47,29 +50,47 @@ The different font weights and slants are: .. method:: actual(option=None, displayof=None) - Return the attributes of the font. + Return the actual attributes of the font, which may differ from the + requested ones because of platform limitations. + With no *option*, return a dictionary of all the attributes; if *option* + is given, return the value of that single attribute. + The attributes are resolved on the display of the *displayof* widget, + or the main application window if it is not specified. .. method:: cget(option) Retrieve an attribute of the font. .. method:: config(**options) + :no-typesetting: + + .. method:: configure(**options) + + Modify one or more attributes of the font. + With no arguments, return a dictionary of the current attributes. - Modify attributes of the font. + :meth:`config` is an alias of :meth:`!configure`. .. method:: copy() - Return new instance of the current font. + Return a distinct copy of the current font: + a new named font with the same attributes but a different name, + which can be reconfigured independently of the original. + If the current font wraps a font description, + the copy is instead a named font with its resolved attributes. .. method:: measure(text, displayof=None) Return amount of space the text would occupy on the specified display - when formatted in the current font. If no display is specified then the - main application window is assumed. + when formatted in the current font, as an integer number of pixels. + If no display is specified then the main application window is assumed. .. method:: metrics(*options, **kw) Return font-specific data. + With no options, return a dictionary mapping each metric name to its + integer value; if one option name is given, return that metric's value as + an integer. Options include: *ascent* - distance between baseline and highest point that a @@ -85,15 +106,17 @@ The different font weights and slants are: .. function:: families(root=None, displayof=None) - Return the different font families. + Return a tuple of the names of the available font families. .. function:: names(root=None) - Return the names of defined fonts. + Return a tuple of the names of all the defined fonts. .. function:: nametofont(name, root=None) - Return a :class:`Font` representation of a tk named font. + Return a :class:`Font` representation of the existing named font *name*. + *root* is the widget whose Tcl interpreter owns the font; if omitted, the + default root window is used. .. versionchanged:: 3.10 The *root* parameter was added. diff --git a/Doc/library/tkinter.messagebox.rst b/Doc/library/tkinter.messagebox.rst index 0dc9632ca73304..47fe680bac9107 100644 --- a/Doc/library/tkinter.messagebox.rst +++ b/Doc/library/tkinter.messagebox.rst @@ -2,19 +2,19 @@ ====================================================== .. module:: tkinter.messagebox - :platform: Tk :synopsis: Various types of alert dialogs **Source code:** :source:`Lib/tkinter/messagebox.py` -------------- -The :mod:`tkinter.messagebox` module provides a template base class as well as -a variety of convenience methods for commonly used configurations. The message -boxes are modal and will return a subset of (``True``, ``False``, ``None``, -:data:`OK`, :data:`CANCEL`, :data:`YES`, :data:`NO`) based on -the user's selection. Common message box styles and layouts include but are not -limited to: +The :mod:`!tkinter.messagebox` module provides a template base class as well as +a variety of convenience methods for commonly used configurations. +The message boxes are modal: each blocks until the user responds, then returns +a value that depends on the function. +The ``show*`` functions and :meth:`Message.show` return the symbolic name of +the button the user pressed, as a string (such as :data:`OK` or :data:`YES`). +Common message box styles and layouts include but are not limited to: .. figure:: tk_msg.png @@ -67,6 +67,10 @@ limited to: Arranges for a :ref:`predefined set of buttons ` to be displayed. + .. note:: + + Tk 8.6 added the *command* option. + .. method:: show(**options) Display a message window and wait for the user to select one of the buttons. Then return the symbolic name of the selected button. @@ -107,7 +111,7 @@ limited to: .. function:: askretrycancel(title=None, message=None, **options) Ask if operation should be retried. Shows buttons :data:`RETRY` and :data:`CANCEL`. - Return ``True`` if the answer is yes and ``False`` otherwise. + Return ``True`` if the answer is retry and ``False`` otherwise. .. function:: askyesno(title=None, message=None, **options) diff --git a/Doc/library/tkinter.rst b/Doc/library/tkinter.rst index f284988daf2d4e..542f0484ac9aed 100644 --- a/Doc/library/tkinter.rst +++ b/Doc/library/tkinter.rst @@ -10,19 +10,24 @@ -------------- -The :mod:`tkinter` package ("Tk interface") is the standard Python interface to -the Tcl/Tk GUI toolkit. Both Tk and :mod:`tkinter` are available on most Unix +The :mod:`!tkinter` package ("Tk interface") is the standard Python interface to +the Tcl/Tk GUI toolkit. Both Tk and :mod:`!tkinter` are available on most Unix platforms, including macOS, as well as on Windows systems. Running ``python -m tkinter`` from the command line should open a window -demonstrating a simple Tk interface, letting you know that :mod:`tkinter` is +demonstrating a simple Tk interface, letting you know that :mod:`!tkinter` is properly installed on your system, and also showing what version of Tcl/Tk is installed, so you can read the Tcl/Tk documentation specific to that version. -Tkinter supports a range of Tcl/Tk versions, built either with or -without thread support. The official Python binary release bundles Tcl/Tk 8.6 -threaded. See the source code for the :mod:`_tkinter` module -for more information about supported versions. +Tkinter supports a range of Tcl/Tk versions, built either with or without +thread support. +Tcl/Tk 8.5.12 is the minimum supported version; the official Python binary +release bundles Tcl/Tk 8.6. +See the source code for the :mod:`_tkinter` module for more information about +supported versions. + +.. versionchanged:: 3.11 + Support for Tcl/Tk versions older than 8.5.12 was removed. Tkinter is not a thin wrapper, but adds a fair amount of its own logic to make the experience more pythonic. This documentation will concentrate on these @@ -32,10 +37,13 @@ details that are unchanged. .. note:: Tcl/Tk 8.5 (2007) introduced a modern set of themed user interface components - along with a new API to use them. Both old and new APIs are still available. + along with a new API to use them (see :mod:`tkinter.ttk`). + Both old and new APIs are still available. Most documentation you will find online still uses the old API and can be woefully outdated. +.. include:: ../includes/optional-module.rst + .. seealso:: * `TkDocs `_ @@ -47,7 +55,7 @@ details that are unchanged. Tcl/Tk Resources: - * `Tk commands `_ + * `Tk commands `_ Comprehensive reference to each of the underlying Tcl/Tk commands used by Tkinter. * `Tcl/Tk Home Page `_ @@ -103,20 +111,20 @@ Ttk bindings are provided in a separate module, :mod:`tkinter.ttk`. Internally, Tk and Ttk use facilities of the underlying operating system, -i.e., Xlib on Unix/X11, Cocoa on macOS, GDI on Windows. +that is, Xlib on Unix/X11, Cocoa on macOS, GDI on Windows. -When your Python application uses a class in Tkinter, e.g., to create a widget, -the :mod:`tkinter` module first assembles a Tcl/Tk command string. It passes that +When your Python application uses a class in Tkinter, for example, to create a widget, +the :mod:`!tkinter` module first assembles a Tcl/Tk command string. It passes that Tcl command string to an internal :mod:`_tkinter` binary module, which then calls the Tcl interpreter to evaluate it. The Tcl interpreter will then call into the Tk and/or Ttk packages, which will in turn make calls to Xlib, Cocoa, or GDI. -Tkinter Modules +Tkinter modules --------------- Support for Tkinter is spread across several modules. Most applications will need the -main :mod:`tkinter` module, as well as the :mod:`tkinter.ttk` module, which provides +main :mod:`!tkinter` module, as well as the :mod:`tkinter.ttk` module, which provides the modern themed widget set and API:: @@ -124,85 +132,9 @@ the modern themed widget set and API:: from tkinter import ttk -.. class:: Tk(screenName=None, baseName=None, className='Tk', useTk=True, sync=False, use=None) - - Construct a toplevel Tk widget, which is usually the main window of an - application, and initialize a Tcl interpreter for this widget. Each - instance has its own associated Tcl interpreter. - - The :class:`Tk` class is typically instantiated using all default values. - However, the following keyword arguments are currently recognized: - - *screenName* - When given (as a string), sets the :envvar:`DISPLAY` environment - variable. (X11 only) - *baseName* - Name of the profile file. By default, *baseName* is derived from the - program name (``sys.argv[0]``). - *className* - Name of the widget class. Used as a profile file and also as the name - with which Tcl is invoked (*argv0* in *interp*). - *useTk* - If ``True``, initialize the Tk subsystem. The :func:`tkinter.Tcl() ` - function sets this to ``False``. - *sync* - If ``True``, execute all X server commands synchronously, so that errors - are reported immediately. Can be used for debugging. (X11 only) - *use* - Specifies the *id* of the window in which to embed the application, - instead of it being created as an independent toplevel window. *id* must - be specified in the same way as the value for the -use option for - toplevel widgets (that is, it has a form like that returned by - :meth:`winfo_id`). - - Note that on some platforms this will only work correctly if *id* refers - to a Tk frame or toplevel that has its -container option enabled. - - :class:`Tk` reads and interprets profile files, named - :file:`.{className}.tcl` and :file:`.{baseName}.tcl`, into the Tcl - interpreter and calls :func:`exec` on the contents of - :file:`.{className}.py` and :file:`.{baseName}.py`. The path for the - profile files is the :envvar:`HOME` environment variable or, if that - isn't defined, then :data:`os.curdir`. - - .. attribute:: tk - - The Tk application object created by instantiating :class:`Tk`. This - provides access to the Tcl interpreter. Each widget that is attached - the same instance of :class:`Tk` has the same value for its :attr:`tk` - attribute. - - .. attribute:: master - - The widget object that contains this widget. For :class:`Tk`, the - *master* is :const:`None` because it is the main window. The terms - *master* and *parent* are similar and sometimes used interchangeably - as argument names; however, calling :meth:`winfo_parent` returns a - string of the widget name whereas :attr:`master` returns the object. - *parent*/*child* reflects the tree-like relationship while - *master*/*slave* reflects the container structure. - - .. attribute:: children - - The immediate descendants of this widget as a :class:`dict` with the - child widget names as the keys and the child instance objects as the - values. - - -.. function:: Tcl(screenName=None, baseName=None, className='Tk', useTk=False) - - The :func:`Tcl` function is a factory function which creates an object much like - that created by the :class:`Tk` class, except that it does not initialize the Tk - subsystem. This is most often useful when driving the Tcl interpreter in an - environment where one doesn't want to create extraneous toplevel windows, or - where one cannot (such as Unix/Linux systems without an X server). An object - created by the :func:`Tcl` object can have a Toplevel window created (and the Tk - subsystem initialized) by calling its :meth:`loadtk` method. - - The modules that provide Tk support include: -:mod:`tkinter` +:mod:`!tkinter` Main Tkinter module. :mod:`tkinter.colorchooser` @@ -228,7 +160,7 @@ The modules that provide Tk support include: :mod:`tkinter.ttk` Themed widget set introduced in Tk 8.5, providing modern alternatives - for many of the classic widgets in the main :mod:`tkinter` module. + for many of the classic widgets in the main :mod:`!tkinter` module. Additional modules: @@ -237,29 +169,31 @@ Additional modules: :mod:`_tkinter` A binary module that contains the low-level interface to Tcl/Tk. - It is automatically imported by the main :mod:`tkinter` module, + It is automatically imported by the main :mod:`!tkinter` module, and should never be used directly by application programmers. It is usually a shared library (or DLL), but might in some cases be statically linked with the Python interpreter. :mod:`idlelib` Python's Integrated Development and Learning Environment (IDLE). Based - on :mod:`tkinter`. + on :mod:`!tkinter`. -:mod:`tkinter.constants` +:mod:`!tkinter.constants` Symbolic constants that can be used in place of strings when passing various parameters to Tkinter calls. Automatically imported by the - main :mod:`tkinter` module. + main :mod:`!tkinter` module. :mod:`tkinter.dnd` - (experimental) Drag-and-drop support for :mod:`tkinter`. This will + (experimental) Drag-and-drop support for :mod:`!tkinter`. This will become deprecated when it is replaced with the Tk DND. :mod:`turtle` Turtle graphics in a Tk window. +.. currentmodule:: tkinter + -Tkinter Life Preserver +Tkinter life preserver ---------------------- This section is not designed to be an exhaustive tutorial on either Tk or @@ -274,7 +208,7 @@ find more detailed documentation on them, including in the official Tcl/Tk reference manual. -A Hello World Program +A Hello World program ^^^^^^^^^^^^^^^^^^^^^ We'll start by walking through a "Hello World" application in Tkinter. This @@ -302,19 +236,20 @@ The following line creates a frame widget, which in this case will contain a label and a button we'll create next. The frame is fit inside the root window. -The next line creates a label widget holding a static text string. The -:meth:`grid` method is used to specify the relative layout (position) of the -label within its containing frame widget, similar to how tables in HTML work. +The next line creates a label widget holding a static text string. +The :meth:`~Grid.grid` method is used to specify the relative layout (position) +of the label within its containing frame widget, similar to how tables in HTML +work. -A button widget is then created, and placed to the right of the label. When -pressed, it will call the :meth:`destroy` method of the root window. +A button widget is then created, and placed to the right of the label. +When pressed, it will call the :meth:`~Misc.destroy` method of the root window. Finally, the :meth:`mainloop` method puts everything on the display, and responds to user input until the program terminates. -Important Tk Concepts +Important Tk concepts ^^^^^^^^^^^^^^^^^^^^^ Even this simple program illustrates the following key Tk concepts: @@ -346,7 +281,7 @@ event loop isn't running the event loop, your user interface won't update. -Understanding How Tkinter Wraps Tcl/Tk +Understanding how Tkinter wraps Tcl/Tk ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ When your application uses Tkinter's classes and methods, internally Tkinter @@ -392,7 +327,7 @@ by spaces. Without getting into too many details, notice the following: * Operations which are implemented as separate *commands* in Tcl (like ``grid`` or ``destroy``) are represented as *methods* on Tkinter widget objects. As you'll see shortly, at other times Tcl uses what appear to be - method calls on widget objects, which more closely mirror what would is + method calls on widget objects, which more closely mirror what is used in Tkinter. @@ -414,9 +349,9 @@ interactive Python shell or with :func:`print`, can help you identify what you need. To find out what configuration options are available on any widget, call its -:meth:`configure` method, which returns a dictionary containing a variety of -information about each object, including its default and current values. Use -:meth:`keys` to get just the names of each option. +:meth:`~Misc.configure` method, which returns a dictionary containing a variety +of information about each object, including its default and current values. +Use :meth:`~Misc.keys` to get just the names of each option. :: @@ -443,18 +378,20 @@ is helpful. print(set(dir(btn)) - set(dir(frm))) -Navigating the Tcl/Tk Reference Manual +Navigating the Tcl/Tk reference manual ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ -As noted, the official `Tk commands `_ -reference manual (man pages) is often the most accurate description of what -specific operations on widgets do. Even when you know the name of the option -or method that you need, you may still have a few places to look. +As noted, the official +`Tk commands `_ reference +manual (man pages) is often the most accurate description of what specific +operations on widgets do. +Even when you know the name of the option or method that you need, you may +still have a few places to look. While all operations in Tkinter are implemented as method calls on widget objects, you've seen that many Tcl/Tk operations appear as commands that take a widget pathname as its first parameter, followed by optional -parameters, e.g. +parameters, for example :: @@ -473,22 +410,23 @@ name of a method to call). In the official Tcl/Tk reference documentation, you'll find most operations -that look like method calls on the man page for a specific widget (e.g., -you'll find the :meth:`invoke` method on the -`ttk::button `_ +that look like method calls on the man page for a specific widget (for example, +you'll find the :meth:`~tkinter.ttk.Button.invoke` method on the +`ttk::button `_ man page), while functions that take a widget as a parameter often have -their own man page (e.g., -`grid `_). +their own man page (for example, +`grid `_). You'll find many common options and methods in the -`options `_ or -`ttk::widget `_ man +`options `_ or +`ttk::widget `_ man pages, while others are found in the man page for a specific widget class. -You'll also find that many Tkinter methods have compound names, e.g., -:func:`winfo_x`, :func:`winfo_height`, :func:`winfo_viewable`. You'd find -documentation for all of these in the -`winfo `_ man page. +You'll also find that many Tkinter methods have compound names, for example, +:meth:`~Misc.winfo_x`, :meth:`~Misc.winfo_height`, +:meth:`~Misc.winfo_viewable`. +You'd find documentation for all of these in the +`winfo `_ man page. .. note:: Somewhat confusingly, there are also methods on all Tkinter widgets @@ -502,7 +440,7 @@ documentation for all of these in the Threading model --------------- -Python and Tcl/Tk have very different threading models, which :mod:`tkinter` +Python and Tcl/Tk have very different threading models, which :mod:`!tkinter` tries to bridge. If you use threads, you may need to be aware of this. A Python interpreter may have many threads associated with it. In Tcl, multiple @@ -510,34 +448,38 @@ threads can be created, but each thread has a separate Tcl interpreter instance associated with it. Threads can also create more than one interpreter instance, though each interpreter instance can be used only by the one thread that created it. -Each :class:`Tk` object created by :mod:`tkinter` contains a Tcl interpreter. +Each :class:`Tk` object created by :mod:`!tkinter` contains a Tcl interpreter. It also keeps track of which thread created that interpreter. Calls to -:mod:`tkinter` can be made from any Python thread. Internally, if a call comes +:mod:`!tkinter` can be made from any Python thread. Internally, if a call comes from a thread other than the one that created the :class:`Tk` object, an event is posted to the interpreter's event queue, and when executed, the result is returned to the calling Python thread. -Tcl/Tk applications are normally event-driven, meaning that after initialization, -the interpreter runs an event loop (i.e. :func:`Tk.mainloop`) and responds to events. -Because it is single-threaded, event handlers must respond quickly, otherwise they -will block other events from being processed. To avoid this, any long-running -computations should not run in an event handler, but are either broken into smaller -pieces using timers, or run in another thread. This is different from many GUI -toolkits where the GUI runs in a completely separate thread from all application -code including event handlers. +Tcl/Tk applications are normally event-driven, meaning that after +initialization, the interpreter runs an event loop (that is, +:meth:`Tk.mainloop `) and responds to events. +Because it is single-threaded, event handlers must respond quickly, otherwise +they will block other events from being processed. +To avoid this, any long-running computations should not run in an event +handler, but are either broken into smaller pieces using timers, or run in +another thread. +This is different from many GUI toolkits where the GUI runs in a completely +separate thread from all application code including event handlers. If the Tcl interpreter is not running the event loop and processing events, any -:mod:`tkinter` calls made from threads other than the one running the Tcl +:mod:`!tkinter` calls made from threads other than the one running the Tcl interpreter will fail. A number of special cases exist: -* Tcl/Tk libraries can be built so they are not thread-aware. In this case, - :mod:`tkinter` calls the library from the originating Python thread, even +* Tcl/Tk libraries built without thread support are now rare: the bundled + Tcl/Tk 8.6 is built with thread support, so this case only arises with some + older non-threaded builds. When the library is not thread-aware, + :mod:`!tkinter` calls the library from the originating Python thread, even if this is different than the thread that created the Tcl interpreter. A global lock ensures only one call occurs at a time. -* While :mod:`tkinter` allows you to create more than one instance of a :class:`Tk` +* While :mod:`!tkinter` allows you to create more than one instance of a :class:`Tk` object (with its own interpreter), all interpreters that are part of the same thread share a common event queue, which gets ugly fast. In practice, don't create more than one instance of :class:`Tk` at a time. Otherwise, it's best to create @@ -548,17 +490,17 @@ A number of special cases exist: or abandon the event loop entirely. If you're doing anything tricky when it comes to events or threads, be aware of these possibilities. -* There are a few select :mod:`tkinter` functions that presently work only when +* There are a few select :mod:`!tkinter` functions that presently work only when called from the thread that created the Tcl interpreter. -Handy Reference +Handy reference --------------- .. _tkinter-setting-options: -Setting Options +Setting options ^^^^^^^^^^^^^^^ Options control things like the color and border width of a widget. Options can @@ -580,6 +522,17 @@ Use the config() method to update multiple attrs subsequent to object creation fred.config(fg="red", bg="blue") +.. note:: + + The ``fg`` and ``bg`` options used here, + and other options that control a widget's appearance, + belong to the classic :mod:`!tkinter` widgets. + The themed :mod:`tkinter.ttk` widgets recommended in the introduction + do not accept them; + style a themed widget through the :class:`ttk.Style ` + class instead. + The three ways of setting an option shown above apply to both widget sets. + For a complete explanation of a given option and its behavior, see the Tk man pages for the widget in question. @@ -594,17 +547,14 @@ document. Some options don't apply to some kinds of widgets. Whether a given widget responds to a particular option depends on the class of the widget; buttons have a ``command`` option, labels do not. -The options supported by a given widget are listed in that widget's man page, or -can be queried at runtime by calling the :meth:`config` method without -arguments, or by calling the :meth:`keys` method on that widget. The return -value of these calls is a dictionary whose key is the name of the option as a -string (for example, ``'relief'``) and whose values are 5-tuples. +The options supported by a given widget are listed in that widget's man page, +or can be queried at runtime by calling the :meth:`~Misc.config` method without +arguments, or by calling the :meth:`~Misc.keys` method on that widget. +The return value of these calls is a dictionary whose key is the name of the +option as a string (for example, ``'relief'``) and whose values are 5-tuples. -Some options, like ``bg`` are synonyms for common options with long names -(``bg`` is shorthand for "background"). Passing the ``config()`` method the name -of a shorthand option will return a 2-tuple, not 5-tuple. The 2-tuple passed -back will contain the name of the synonym and the "real" option (such as -``('bg', 'background')``). +Some options, like ``bg``, are synonyms for common options with long names +(``bg`` is shorthand for "background"). +-------+---------------------------------+--------------+ | Index | Meaning | Example | @@ -630,174 +580,206 @@ Of course, the dictionary printed will include all the options available and their values. This is meant only as an example. -The Packer -^^^^^^^^^^ +.. _pack-the-packer: +.. _tkinter-geometry-management: +.. _the-packer: +.. _packer-options: -.. index:: single: packing (widgets) +Geometry management +^^^^^^^^^^^^^^^^^^^ -The packer is one of Tk's geometry-management mechanisms. Geometry managers -are used to specify the relative positioning of widgets within their container - -their mutual *master*. In contrast to the more cumbersome *placer* (which is -used less commonly, and we do not cover here), the packer takes qualitative -relationship specification - *above*, *to the left of*, *filling*, etc - and -works everything out to determine the exact placement coordinates for you. +.. index:: + single: geometry management (widgets) + single: packing (widgets) + +Creating a widget does not display it. +A widget appears only after it has been handed to a *geometry manager*, +which works out its size and position inside its container +and keeps the layout up to date as the container is resized or its content changes. +Forgetting to call a geometry manager is a common early mistake: +the widget is created, but nothing shows up. + +Tk provides three geometry managers. +Each is inherited by every widget, so any widget can be managed by any of them +(but see the warning below about the incompatibility of grid and pack). +The choice depends on the kind of layout you want. + +:meth:`grid ` + Arranges widgets in a two-dimensional table of rows and columns. + It is the most flexible manager and the one to reach for by default: + layouts that would otherwise need several nested frames can often be + expressed as a single grid, + and rows and columns can be told how to absorb extra space. -The size of any *master* widget is determined by the size of the "slave widgets" -inside. The packer is used to control where slave widgets appear inside the -master into which they are packed. You can pack widgets into frames, and frames -into other frames, in order to achieve the kind of layout you desire. -Additionally, the arrangement is dynamically adjusted to accommodate incremental -changes to the configuration, once it is packed. + :: -Note that widgets do not appear until they have had their geometry specified -with a geometry manager. It's a common early mistake to leave out the geometry -specification, and then be surprised when the widget is created but nothing -appears. A widget will appear only after it has had, for example, the packer's -:meth:`pack` method applied to it. + ttk.Label(frm, text="Name:").grid(column=0, row=0, sticky="w") + ttk.Entry(frm).grid(column=1, row=0) + ttk.Button(frm, text="OK").grid(column=1, row=1, sticky="e") -The pack() method can be called with keyword-option/value pairs that control -where the widget is to appear within its container, and how it is to behave when -the main application window is resized. Here are some examples:: +:meth:`pack ` + Stacks widgets against one side of their container + -- ``"top"`` (the default), ``"bottom"``, ``"left"`` or ``"right"`` -- + and can make them fill or expand into the space that is left. + It is convenient for simple arrangements, + such as a single row or column of widgets + or a content area framed by a toolbar and a status bar. - fred.pack() # defaults to side = "top" - fred.pack(side="left") - fred.pack(expand=1) + :: + toolbar.pack(side="top", fill="x") + status.pack(side="bottom", fill="x") + body.pack(side="left", expand=True, fill="both") -Packer Options -^^^^^^^^^^^^^^ +:meth:`place ` + Positions each widget at an explicit spot, + given either as absolute screen distances or as a fraction of the container's size. + It offers the most control but the least automatic behavior, and is used the least; + it suits special cases such as overlapping widgets or precise custom layouts. -For more extensive information on the packer and the options that it can take, -see the man pages and page 183 of John Ousterhout's book. + :: -anchor - Anchor type. Denotes where the packer is to place each slave in its parcel. + background.place(x=0, y=0, relwidth=1.0, relheight=1.0) + badge.place(relx=1.0, rely=0.0, anchor="ne") -expand - Boolean, ``0`` or ``1``. +Layouts are built up by nesting: +grid or pack widgets, including frames, inside a frame or toplevel. +Toplevels are managed by the OS window manager. +Classic and themed :mod:`tkinter.ttk` widgets can be managed interchangeably. -fill - Legal values: ``'x'``, ``'y'``, ``'both'``, ``'none'``. +.. warning:: -ipadx and ipady - A distance - designating internal padding on each side of the slave widget. + Do not apply :meth:`!pack` and :meth:`!grid` to two widgets that share the same container. + The two managers negotiate sizes in incompatible ways, + and the application can hang as they repeatedly resize the container against each other. + To combine them, keep each manager's widgets in a separate frame. -padx and pady - A distance - designating external padding on each side of the slave widget. +The full set of options accepted by each manager, with their values and defaults, +is documented under :meth:`Grid.grid_configure`, :meth:`Pack.pack_configure` +and :meth:`Place.place_configure`; +see also the :manpage:`grid(3tk)`, :manpage:`pack(3tk)` and :manpage:`place(3tk)` +man pages. -side - Legal values are: ``'left'``, ``'right'``, ``'top'``, ``'bottom'``. +.. _coupling-widget-variables: -Coupling Widget Variables +Coupling widget variables ^^^^^^^^^^^^^^^^^^^^^^^^^ -The current-value setting of some widgets (like text entry widgets) can be -connected directly to application variables by using special options. These -options are ``variable``, ``textvariable``, ``onvalue``, ``offvalue``, and -``value``. This connection works both ways: if the variable changes for any -reason, the widget it's connected to will be updated to reflect the new value. - -Unfortunately, in the current implementation of :mod:`tkinter` it is not -possible to hand over an arbitrary Python variable to a widget through a -``variable`` or ``textvariable`` option. The only kinds of variables for which -this works are variables that are subclassed from a class called Variable, -defined in :mod:`tkinter`. - -There are many useful subclasses of Variable already defined: -:class:`StringVar`, :class:`IntVar`, :class:`DoubleVar`, and -:class:`BooleanVar`. To read the current value of such a variable, call the -:meth:`get` method on it, and to change its value you call the :meth:`!set` -method. If you follow this protocol, the widget will always track the value of -the variable, with no further intervention on your part. +Some widgets can tie their current value directly to a program variable, +so that the two stay in sync. +Options such as ``variable``, ``textvariable``, ``value``, ``onvalue`` and +``offvalue`` set up this connection: +when the user changes the widget the variable is updated, +and when the variable is set the widget redraws to match. + +A widget can be linked only to a :class:`Variable` object, +not to an ordinary Python variable. +This is not a limitation of :mod:`!tkinter` +but a consequence of how the two languages differ: +the link relies on Tcl being notified every time the value changes, +and Python offers no way to react when a plain variable is reassigned. +A :class:`Variable` sidesteps this by keeping its value inside the Tcl interpreter +and exposing it through explicit :meth:`~Variable.get` and :meth:`~Variable.set` methods. + +Ready-made subclasses cover the common types: +:class:`StringVar`, :class:`IntVar`, :class:`DoubleVar` and :class:`BooleanVar`. +Pass one as a widget's ``textvariable`` (or ``variable``) option, +then read and update it with :meth:`~Variable.get` and :meth:`~Variable.set`; +the widget tracks it with no further work on your part. + +Keep a reference to the variable for as long as the widget uses it +-- for example by storing it as an attribute. +A :class:`Variable` that is garbage collected removes its underlying Tcl variable, +breaking the connection to the widget (see :class:`Variable`). For example:: import tkinter as tk + from tkinter import ttk + + root = tk.Tk() - class App(tk.Frame): - def __init__(self, master): - super().__init__(master) - self.pack() + # Create the application variable and give it an initial value. + contents = tk.StringVar(value="this is a variable") - self.entrythingy = tk.Entry() - self.entrythingy.pack() + # Tell the entry widget to track the variable. + entry = ttk.Entry(root, textvariable=contents) + entry.pack() - # Create the application variable. - self.contents = tk.StringVar() - # Set it to some value. - self.contents.set("this is a variable") - # Tell the entry widget to watch this variable. - self.entrythingy["textvariable"] = self.contents + # Print the current value whenever the user presses Return. + def print_contents(event): + print("The current entry content is:", contents.get()) - # Define a callback for when the user hits return. - # It prints the current value of the variable. - self.entrythingy.bind('', - self.print_contents) + entry.bind("", print_contents) - def print_contents(self, event): - print("Hi. The current entry content is:", - self.contents.get()) + # Setting the variable from the program updates the entry through the + # same link. + def clear(): + contents.set("") - root = tk.Tk() - myapp = App(root) - myapp.mainloop() + ttk.Button(root, text="Clear", command=clear).pack() + + root.mainloop() + +.. _tkinter-window-manager: -The Window Manager +The window manager ^^^^^^^^^^^^^^^^^^ .. index:: single: window manager (widgets) -In Tk, there is a utility command, ``wm``, for interacting with the window -manager. Options to the ``wm`` command allow you to control things like titles, -placement, icon bitmaps, and the like. In :mod:`tkinter`, these commands have -been implemented as methods on the :class:`Wm` class. Toplevel widgets are -subclassed from the :class:`Wm` class, and so can call the :class:`Wm` methods -directly. +The *window manager* is the part of the desktop responsible for the title bar, +border and controls drawn around each top-level window, +and for such things as its title, position, size and icon. +Tk gives access to these through the :class:`Wm` mixin, +which is inherited by the :class:`Tk` root window and by every :class:`Toplevel`. +You therefore call the window-manager methods directly on a top-level window. +Each has a short name and an equivalent ``wm_``-prefixed name, +for example :meth:`~Wm.title` and :meth:`~Wm.wm_title`. -To get at the toplevel window that contains a given widget, you can often just -refer to the widget's master. Of course if the widget has been packed inside of -a frame, the master won't represent a toplevel window. To get at the toplevel -window that contains an arbitrary widget, you can call the :meth:`_root` method. -This method begins with an underscore to denote the fact that this function is -part of the implementation, and not an interface to Tk functionality. +These methods act on the top-level window +whether its content is built from the classic widgets or the themed :mod:`tkinter.ttk` widgets. +To reach the top-level window containing an arbitrary widget, +call its :meth:`~Misc.winfo_toplevel` method. -Here are some examples of typical usage:: +For example:: import tkinter as tk + from tkinter import ttk + + root = tk.Tk() + root.title("My Application") + root.geometry("640x480") + root.minsize(320, 240) - class App(tk.Frame): - def __init__(self, master=None): - super().__init__(master) - self.pack() + ttk.Label(root, text="Hello").pack(padx=20, pady=20) - # create the application - myapp = App() + root.mainloop() - # - # here are method calls to the window manager class - # - myapp.master.title("My Do-Nothing Application") - myapp.master.maxsize(1000, 400) +See :class:`Wm` for the full set of window-manager methods. - # start the program - myapp.mainloop() +.. _Tk-option-data-types: -Tk Option Data Types +Tk option data types ^^^^^^^^^^^^^^^^^^^^ .. index:: single: Tk Option Data Types +Many widget options documented in the reference +accept values of a small number of common types, described here. + anchor Legal values are points of the compass: ``"n"``, ``"ne"``, ``"e"``, ``"se"``, ``"s"``, ``"sw"``, ``"w"``, ``"nw"``, and also ``"center"``. bitmap - There are eight built-in, named bitmaps: ``'error'``, ``'gray25'``, - ``'gray50'``, ``'hourglass'``, ``'info'``, ``'questhead'``, ``'question'``, - ``'warning'``. To specify an X bitmap filename, give the full path to the file, - preceded with an ``@``, as in ``"@/usr/contrib/bitmap/gumby.bit"``. + There are ten built-in, named bitmaps: ``'error'``, ``'gray12'``, + ``'gray25'``, ``'gray50'``, ``'gray75'``, ``'hourglass'``, ``'info'``, + ``'questhead'``, ``'question'``, ``'warning'``. To specify an X bitmap + filename, give the full path to the file, preceded with an ``@``, as in + ``"@/usr/contrib/bitmap/gumby.bit"``. boolean You can pass integers 0 or 1 or the strings ``"yes"`` or ``"no"``. @@ -813,13 +795,20 @@ color Colors can be given as the names of X colors in the rgb.txt file, or as strings representing RGB values in 4 bit: ``"#RGB"``, 8 bit: ``"#RRGGBB"``, 12 bit: ``"#RRRGGGBBB"``, or 16 bit: ``"#RRRRGGGGBBBB"`` ranges, where R,G,B here - represent any legal hex digit. See page 160 of Ousterhout's book for details. + represent any legal hex digit. See the :manpage:`colors(3tk)` man page for + the list of named colors. cursor - The standard X cursor names from :file:`cursorfont.h` can be used, without the - ``XC_`` prefix. For example to get a hand cursor (:const:`XC_hand2`), use the - string ``"hand2"``. You can also specify a bitmap and mask file of your own. - See page 179 of Ousterhout's book. + The name of the mouse cursor to display while the pointer is over the widget. + Tk provides a portable set of cursor names available on all platforms + (for example ``"arrow"``, ``"watch"``, ``"cross"``, or ``"hand2"``); + the standard X cursor names from :file:`cursorfont.h` may also be used, + without the ``XC_`` prefix (so ``XC_hand2`` becomes ``"hand2"``). + The full list of names, including the platform-specific ones, + is given in the :manpage:`cursors(3tk)` manual page. + You can also specify a bitmap and mask file of your own. + On Windows a cursor file (:file:`.cur` or :file:`.ani`) may be used directly, + giving its path preceded with an ``@``, as in ``"@C:/cursors/bart.ani"``. distance Screen distances can be specified in either pixels or absolute distances. @@ -829,9 +818,11 @@ distance as ``"3.5i"``. font - Tk uses a list font name format, such as ``{courier 10 bold}``. Font sizes with - positive numbers are measured in points; sizes with negative numbers are - measured in pixels. + Tk uses a font description such as ``{courier 10 bold}``; in + :mod:`!tkinter` this is most naturally passed as a tuple of + ``(family, size, *styles)`` (or as the equivalent string + ``"Courier 10 bold"``). Font sizes with positive numbers are measured in + points; sizes with negative numbers are measured in pixels. geometry This is a string of the form ``widthxheight``, where width and height are @@ -839,8 +830,7 @@ geometry For example: ``fred["geometry"] = "200x100"``. justify - Legal values are the strings: ``"left"``, ``"center"``, ``"right"``, and - ``"fill"``. + Legal values are the strings: ``"left"``, ``"center"``, and ``"right"``. region This is a string with four space-delimited elements, each of which is a legal @@ -849,7 +839,8 @@ region relief Determines what the border style of a widget will be. Legal values are: - ``"raised"``, ``"sunken"``, ``"flat"``, ``"groove"``, and ``"ridge"``. + ``"raised"``, ``"sunken"``, ``"flat"``, ``"groove"``, ``"ridge"``, and + ``"solid"``. scrollcommand This is almost always the :meth:`!set` method of some scrollbar widget, but can @@ -860,7 +851,7 @@ wrap .. _Bindings-and-Events: -Bindings and Events +Bindings and events ^^^^^^^^^^^^^^^^^^^ .. index:: @@ -876,9 +867,11 @@ of the bind method is:: where: sequence - is a string that denotes the target kind of event. (See the - :manpage:`bind(3tk)` man page, and page 201 of John Ousterhout's book, - :title-reference:`Tcl and the Tk Toolkit (2nd edition)`, for details). + is a string that denotes the target kind of event. Physical events use the + ```` form (for example ``""`` or + ``""``); application-defined virtual events use double angle + brackets, as in ``"<>"``. (See the + :manpage:`bind(3tk)` man page for details.) func is a Python function, taking one argument, to be invoked when the event occurs. @@ -922,9 +915,27 @@ they are denoted in Tk, which can be useful when referring to the Tk man pages. +----+---------------------+----+---------------------+ | %y | y | %Y | y_root | +----+---------------------+----+---------------------+ +| %# | serial | %b | num | ++----+---------------------+----+---------------------+ +| %d | detail | %D | delta | ++----+---------------------+----+---------------------+ + +The ``add`` parameter above only affects the bindings you make yourself. +Every widget also inherits *class bindings* +that implement its standard behavior -- +for example a :class:`Text` widget binds :kbd:`Control-t` +to transpose two characters. +These are described in the bindings section of the widget's Tk man page +(such as :manpage:`text(3tk)` or :manpage:`entry(3tk)`). +Class bindings are processed separately from your own, +so binding an event yourself does not replace the default; both run. +To suppress an unwanted default binding, +bind the event on the widget +and return the string ``"break"`` from your callback. -The index Parameter + +The index parameter ^^^^^^^^^^^^^^^^^^^ A number of widgets require "index" parameters to be passed. These are used to @@ -932,9 +943,32 @@ point at a specific place in a Text widget, or to particular characters in an Entry widget, or to particular menu items in a Menu widget. Entry widget indexes (index, view index, etc.) - Entry widgets have options that refer to character positions in the text being - displayed. You can use these :mod:`tkinter` functions to access these special - points in text widgets: + Entry widgets have methods and options that refer to character positions + in the text being displayed. + Anytime an index is needed, you may pass in: + + * an integer which refers to the numeric position of a character, + counted from the beginning of the text, starting with 0; + + * the string ``"anchor"``, + which refers to the anchor point of the selection, + set with the widget's selection methods; + + * the string ``"end"``, + which refers to the position just after the last character; + + * the string ``"insert"``, + which refers to the character just after the insertion cursor; + + * the strings ``"sel.first"`` and ``"sel.last"``, + which refer to the first character in the selection + and the position just after the last + (it is an error to use these if there is no selection); + + * a string consisting of ``@`` followed by an integer, as in ``"@6"``, + where the integer is interpreted as an x pixel coordinate + in the entry's coordinate system, + selecting the character spanning that point. Text widget indexes The index notation for Text widgets is very rich and is best described in the Tk @@ -952,8 +986,9 @@ Menu indexes (menu.invoke(), menu.entryconfig(), etc.) * the string ``"last"`` which refers to the last menu item; - * An integer preceded by ``@``, as in ``@6``, where the integer is interpreted - as a y pixel coordinate in the menu's coordinate system; + * a string consisting of ``@`` followed by an integer, as in ``"@6"``, where + the integer is interpreted as a y pixel coordinate in the menu's coordinate + system; * the string ``"none"``, which indicates no menu entry at all, most often used with menu.activate() to deactivate all entries, and finally, @@ -989,7 +1024,7 @@ option (other options are available as well). :meth:`!copy`. The image object can then be used wherever an ``image`` option is supported by -some widget (e.g. labels, buttons, menus). In these cases, Tk will not keep a +some widget (for example, labels, buttons, menus). In these cases, Tk will not keep a reference to the image. When the last Python reference to the image object is deleted, the image data is deleted as well, and Tk will display an empty box wherever the image was used. @@ -999,51 +1034,5520 @@ wherever the image was used. The `Pillow `_ package adds support for formats such as BMP, JPEG, TIFF, and WebP, among others. -.. _tkinter-file-handlers: -File Handlers -------------- +Reference +--------- -Tk allows you to register and unregister a callback function which will be -called from the Tk mainloop when I/O is possible on a file descriptor. -Only one handler may be registered per file descriptor. Example code:: +.. currentmodule:: tkinter - import tkinter - widget = tkinter.Tk() - mask = tkinter.READABLE | tkinter.WRITABLE - widget.tk.createfilehandler(file, mask, callback) - ... - widget.tk.deletefilehandler(file) +This section documents the classes, methods, functions and constants of the +:mod:`!tkinter` module. +Most of them wrap Tcl/Tk commands; consult the official Tcl/Tk manual pages for +the full list of widget options and further details. -This feature is not available on Windows. +.. exception:: TclError -Since you don't know how many bytes are available for reading, you may not -want to use the :class:`~io.BufferedIOBase` or :class:`~io.TextIOBase` -:meth:`~io.BufferedIOBase.read` or :meth:`~io.IOBase.readline` methods, -since these will insist on reading a predefined number of bytes. -For sockets, the :meth:`~socket.socket.recv` or -:meth:`~socket.socket.recvfrom` methods will work fine; for other files, -use raw reads or ``os.read(file.fileno(), maxbytecount)``. + The exception raised when a call into the Tcl interpreter fails, for example + when a widget is given an unknown option or an invalid value. +Base and mixin classes +^^^^^^^^^^^^^^^^^^^^^^ -.. method:: Widget.tk.createfilehandler(file, mask, func) +.. class:: Misc() - Registers the file handler callback function *func*. The *file* argument - may either be an object with a :meth:`~io.IOBase.fileno` method (such as - a file or socket object), or an integer file descriptor. The *mask* - argument is an ORed combination of any of the three constants below. - The callback is called as follows:: + The :class:`!Misc` class is a mix-in inherited by :class:`Tk` and, through + :class:`BaseWidget`, by every widget. + It provides the large set of methods common to all Tk objects: querying + window information, managing event bindings and the event loop, controlling + the keyboard focus and pointer grabs, accessing the selection, clipboard and + option database, and assorted utility and introspection services. + Because they are inherited, these methods are available on every widget and + on the :class:`Tk` application object, and are documented here once rather + than repeated for each widget. - callback(file, mask) + .. method:: cget(key) + Return the current value of the configuration option named *key* for this + widget, as a string. + The expression ``widget[key]`` is equivalent and may be used instead. -.. method:: Widget.tk.deletefilehandler(file) + .. method:: config(cnf=None, **kw) + :no-typesetting: - Unregisters a file handler. + .. method:: configure(cnf=None, **kw) + Query or modify the configuration options of the widget. + With no arguments, return a dictionary mapping every available option + name to a tuple describing it (its name, X resource name, X resource + class, default value and current value). + If a single option name is given as a string, return the tuple for just + that option. + If one or more keyword arguments are given, or a dictionary is passed as + *cnf*, set each named option to the corresponding value; the expression + ``widget[key] = value`` sets a single option in the same way. -.. data:: READABLE - WRITABLE - EXCEPTION + :meth:`config` is an alias of :meth:`!configure`. - Constants used in the *mask* arguments. + .. method:: keys() + + Return a list of the names of all configuration options of this widget. + + .. method:: getboolean(s) + + Interpret the string *s* as a Tcl boolean and return the corresponding + :class:`bool`. + Tcl accepts values such as ``'1'``, ``'0'``, ``'yes'``, ``'no'``, + ``'true'`` and ``'false'``. + Raise :exc:`ValueError` if *s* is not a valid boolean. + + .. method:: getdouble(s) + + Interpret the string *s* as a Tcl floating-point number and return it as + a :class:`float`. + Raise :exc:`ValueError` if *s* is not a valid number. + + .. versionadded:: 3.5 + + + .. method:: getint(s) + + Interpret the string *s* as a Tcl integer and return it as an + :class:`int`. + Raise :exc:`ValueError` if *s* is not a valid integer. + + .. method:: getvar(name) + + Return the value of the Tcl global variable named *name*. + + .. method:: setvar(name, value) + + Set the Tcl global variable named *name* to *value*. + + The :meth:`!getvar` and :meth:`!setvar` methods give direct access to Tcl + variables. + In most code you will instead use a :class:`Variable` subclass such as + :class:`StringVar` or :class:`IntVar`, which wraps a Tcl variable and + converts its value to and from a Python type. + + .. method:: register(func, subst=None, needcleanup=1) + + Register the Python callable *func* as a Tcl command and return the name + of the new command as a string. + Whenever Tcl invokes that command, *func* is called; if *subst* is given, + it is applied to the command's arguments first. + This is the mechanism used internally to turn Python callbacks into the + command names passed to Tk options such as *command*. + Unless *needcleanup* is false, the command is deleted automatically when + the widget is destroyed. + + .. versionchanged:: 3.13 + The arguments passed to *func* are no longer converted to strings. + + .. method:: deletecommand(name) + + Delete the Tcl command named *name*, such as one previously returned by + :meth:`register`. + + .. method:: nametowidget(name) + + Return the widget instance corresponding to the Tk pathname *name*. + + .. method:: send(interp, cmd, *args) + + Send the Tcl command *cmd*, with the given *args*, to the Tcl interpreter + registered under the name *interp*, and return its result. + This is not available on all platforms. + + .. method:: destroy() + + Destroy this widget and all of its descendant widgets, and delete the Tcl + commands associated with them. + + .. method:: lift(aboveThis=None) + :no-typesetting: + + .. method:: tkraise(aboveThis=None) + + Raise this widget in the stacking order so that it is drawn on top of its + siblings. + If *aboveThis* is given, the widget is moved to be just above it in the + stacking order instead. + + :meth:`lift` is an alias of :meth:`!tkraise`. + + .. method:: lower(belowThis=None) + + Lower this widget in the stacking order so that it is drawn beneath its + siblings. + If *belowThis* is given, the widget is moved to be just below it in the + stacking order instead. + + :meth:`tkraise`/:meth:`lift` and :meth:`lower` are overridden by the + :class:`Canvas` widget, + where they restack canvas items instead. + + .. method:: image_names() + + Return the names of all images that currently exist in the Tcl + interpreter. + + This is overridden by the :class:`Text` widget, + where :meth:`!image_names` returns the names of its embedded images + instead. + + .. method:: image_types() + + Return the available image types, such as ``'photo'`` and ``'bitmap'``. + + .. method:: anchor(anchor=None) + :no-typesetting: + + .. method:: grid_anchor(anchor=None) + + Set the anchor that controls where the grid is placed inside this + container when the container is larger than the grid and no row or column + has a non-zero weight. + *anchor* is one of the usual anchor strings, such as ``'nw'`` (the + default) or ``'center'``. + Called with no argument, this method has no effect. + + :meth:`anchor` is an alias of :meth:`!grid_anchor`. + + .. versionadded:: 3.3 + + .. method:: bbox(column=None, row=None, col2=None, row2=None) + :no-typesetting: + + .. method:: grid_bbox(column=None, row=None, col2=None, row2=None) + + Return the bounding box, in pixels, of a region of the grid laid out in + this container, as a 4-tuple ``(xoffset, yoffset, width, height)``. + With no arguments the bounding box of the whole grid is returned. + If *column* and *row* are given, the box spans from the cell at row and + column 0 to that cell; if *col2* and *row2* are also given, it spans from + the cell (*column*, *row*) to the cell (*col2*, *row2*). + + :meth:`bbox` is an alias of :meth:`!grid_bbox`, + except on :class:`Canvas`, :class:`Listbox`, :class:`Spinbox`, + :class:`Text`, :class:`ttk.Entry ` and + :class:`ttk.Treeview `, + which provide their own :meth:`!bbox` method. + + .. method:: columnconfigure(index, cnf={}, **kw) + :no-typesetting: + + .. method:: grid_columnconfigure(index, cnf={}, **kw) + + Query or set the properties of the column (or columns) *index* of the + grid managed by this container. + *index* may be a column number; when setting options it may also be a + list of column numbers, the string ``'all'`` to affect every column, or + a child widget whose occupied columns are affected. + The supported options are: + + *minsize* + The column's minimum size, in pixels. + + *weight* + An integer setting how much of any extra space is apportioned to the + column. + A weight of ``0`` keeps the column at its requested size, and a column + of weight two grows twice as fast as a column of weight one. + + *uniform* + The name of a uniform group. + Columns sharing a non-empty group name are kept in sizes that are + strictly proportional to their weights. + + *pad* + Extra space, in pixels, added to the largest widget in the column when + computing the column's size. + + With a single option name, return that option's value; with no options, + return a dictionary of all of them. + + :meth:`columnconfigure` is an alias of :meth:`!grid_columnconfigure`. + + .. method:: rowconfigure(index, cnf={}, **kw) + :no-typesetting: + + .. method:: grid_rowconfigure(index, cnf={}, **kw) + + Query or set the properties of the row (or rows) *index* of the grid + managed by this container. + *index* is interpreted as for :meth:`grid_columnconfigure`, and the + supported options (*minsize*, *weight*, *uniform* and *pad*) are the + same, applied to a row instead of a column. + + :meth:`rowconfigure` is an alias of :meth:`!grid_rowconfigure`. + + .. method:: grid_location(x, y) + + Return the ``(column, row)`` of the grid cell that contains the pixel at + position (*x*, *y*), given in pixels relative to this container. + For locations above or to the left of the grid, ``-1`` is returned for + the corresponding coordinate. + + .. method:: grid_propagate() + grid_propagate(flag) + + Enable or disable geometry propagation for this container when it manages + its children with the grid geometry manager. + When *flag* is true, the container resizes itself to fit the requested + sizes of its children; when it is false, its size is left under your + control. + Called with no argument, return the current setting as a boolean. + + .. method:: size() + :no-typesetting: + + .. method:: grid_size() + + Return the size of the grid managed by this container as a + ``(columns, rows)`` tuple. + + :meth:`size` is an alias of :meth:`!grid_size`, + except on the :class:`Listbox` widget, + which provides its own :meth:`!size` method. + + .. method:: grid_slaves(row=None, column=None) + + Return a list of the child widgets managed in this container's grid, most + recently managed first. + If *row* or *column* is given, only the children in that row or column + are returned. + + .. method:: propagate() + propagate(flag) + :no-typesetting: + + .. method:: pack_propagate() + pack_propagate(flag) + + Enable or disable geometry propagation for this container when it manages + its children with the pack geometry manager. + When *flag* is true, the container resizes itself to fit the requested + sizes of its children; when it is false, its size is left under your + control. + Called with no argument, return the current setting as a boolean. + + :meth:`propagate` is an alias of :meth:`!pack_propagate`. + + .. method:: slaves() + :no-typesetting: + + .. method:: pack_slaves() + + Return a list of the child widgets managed by this container with the + pack geometry manager, in packing order. + + :meth:`slaves` is an alias of :meth:`!pack_slaves`. + + .. method:: place_slaves() + + Return a list of the child widgets managed by this container with the + place geometry manager. + + .. method:: bind(sequence=None, func=None, add=None) + + Bind the event pattern *sequence* on this widget to the callable *func*. + + *sequence* is an event pattern, such as ``''`` (a mouse click) + or ``''``, optionally a concatenation of several such + patterns that must occur shortly after one another. + When the event occurs, *func* is called with an :class:`Event` instance + describing it as its only argument; if *func* returns the string + ``'break'``, no further bindings for the event are invoked. + + If *add* is true, *func* is added to any functions already bound to + *sequence*; otherwise it replaces them. + The binding applies only to this widget. + + :meth:`!bind` returns a string identifier (a *funcid*) that can later be + passed to :meth:`unbind` to remove the binding without leaking the + associated Tcl command. + + If *func* is omitted, return the binding currently associated with + *sequence*; if *sequence* is also omitted, return a list of all the + sequences for which bindings exist on this widget. + + .. method:: bind_class(className, sequence=None, func=None, add=None) + + Like :meth:`bind`, but bind *func* to the binding tag *className* rather + than to a single widget, so that the binding applies to every widget + having that tag. + *className* is usually the name of a widget class, such as ``'Button'``, + in which case the binding affects all widgets of that class. + The set of binding tags for a widget can be inspected and changed with + :meth:`bindtags`. + + The remaining arguments and the return value are as for :meth:`bind`. + + .. method:: bind_all(sequence=None, func=None, add=None) + + Like :meth:`bind`, but bind *func* to the special binding tag ``'all'``, + so that the binding applies to every widget in the application. + + The remaining arguments and the return value are as for :meth:`bind`. + + .. method:: unbind(sequence, funcid=None) + + Remove bindings for the event pattern *sequence* on this widget. + + If *funcid* is given, only the function identified by it (a value + returned from a previous call to :meth:`bind`) is removed, and its + associated Tcl command is deleted. + Otherwise all bindings for *sequence* are destroyed, leaving it unbound. + + .. versionchanged:: 3.13 + If *funcid* is given, only that callback is unbound; other callbacks + bound to *sequence* are kept. + + + .. method:: unbind_class(className, sequence) + + Remove all bindings for the event pattern *sequence* from the binding tag + *className*. + See :meth:`bind_class`. + + .. method:: unbind_all(sequence) + + Remove all bindings for the event pattern *sequence* from the special + binding tag ``'all'``. + See :meth:`bind_all`. + + .. method:: bindtags(tagList=None) + + If *tagList* is omitted, return a tuple of the binding tags associated + with this widget. + When an event occurs in a widget, it is applied to each of the widget's + binding tags in order, and for each tag the most specific matching + binding is executed. + By default a widget has four binding tags: its own pathname, its widget + class, the pathname of its nearest toplevel ancestor, and ``'all'``, in + that order. + + If *tagList* is given, it must be a sequence of strings; the widget's + binding tags are set to its elements, which determines the order in which + bindings are evaluated. + + The methods with the ``event_`` prefix define virtual events and generate + events programmatically. + + .. method:: event_add(virtual, *sequences) + + Associate the virtual event *virtual*, whose name has the form + ``'<>'``, with each of the physical event patterns given by + *sequences*, so that the virtual event triggers whenever any of them + occurs. + If *virtual* is already defined, the new sequences are added to its + existing ones. + + .. method:: event_delete(virtual, *sequences) + + Remove each of *sequences* from those associated with the virtual event + *virtual*. + Sequences that are not currently associated with *virtual* are ignored. + If no *sequences* are given, all physical event sequences are removed, so + that *virtual* no longer triggers. + + .. method:: event_generate(sequence, **kw) + + Generate the event *sequence* on this widget and arrange for it to be + processed just as if it had come from the window system. + *sequence* must be a single event pattern, such as ``''`` or + ``'<>'``, not a concatenation of several. + Keyword arguments specify additional fields of the event, for example *x* + and *y* for the pointer position, or *when* to control when the event is + processed; refer to the Tk ``event`` manual page for the full list. + + .. method:: event_info(virtual=None) + + If *virtual* is omitted, return a tuple of all the virtual events that + are currently defined. + If *virtual* is given, return a tuple of the physical event sequences + currently associated with it, or an empty tuple if it is not defined. + + The methods with the ``after`` prefix schedule callbacks to run after a + delay or when the application is idle. + + .. method:: after(ms, func=None, *args, **kw) + + Schedule the callable *func* to be called after *ms* milliseconds, with + *args* and *kw* passed to it as positional and keyword arguments. + Return an identifier that can be passed to :meth:`after_cancel` to cancel + the call. + + If *func* is omitted, sleep for *ms* milliseconds instead, processing no + events during that time, and return ``None``. + + .. versionchanged:: 3.10 + *func* can now be any callable object, not only a function. + + .. versionchanged:: 3.14 + Keyword arguments are now passed to *func*. + + + .. method:: after_cancel(id) + + Cancel a callback previously scheduled with :meth:`after` or + :meth:`after_idle`. + *id* must be an identifier returned by one of those methods; passing a + value that is not such an identifier raises :exc:`ValueError`. + If the callback has already run or been cancelled, this has no effect. + + .. versionchanged:: 3.7 + Passing ``None`` (or any false value) as *id* now raises + :exc:`ValueError`. + + + .. method:: after_idle(func, *args, **kw) + + Schedule the callable *func* to be called, with *args* and *kw* passed to + it, when the Tk main loop next becomes idle, that is, when it has no + other events to process. + Return an identifier that can be passed to :meth:`after_cancel` to cancel + the call. + + .. versionchanged:: 3.14 + Keyword arguments are now passed to *func*. + + + .. method:: after_info(id=None) + + If *id* is omitted, return a tuple of the identifiers of all callbacks + currently scheduled with :meth:`after` and :meth:`after_idle` for this + interpreter. + + If *id* is given, it must identify a callback that has not yet run or + been cancelled, and the return value is a tuple ``(script, type)``, where + *script* refers to the function to be called and *type* is either + ``'idle'`` or ``'timer'``. + A :exc:`TclError` is raised if *id* does not exist. + + .. versionadded:: 3.13 + + + .. method:: mainloop(n=0) + + Enter the Tk event loop, which processes events until all windows are + destroyed. + This is normally called once, on the root window, to run the application. + + .. method:: quit() + + Quit the Tcl interpreter, causing :meth:`mainloop` to return. + + .. method:: update() + + Enter the event loop until all pending events, including idle callbacks, + have been processed. + This brings the display up to date and handles any events that are + already queued, then returns. + + .. method:: update_idletasks() + + Enter the event loop until all pending idle callbacks have been called. + This updates the display of windows, for example after geometry changes, + but does not process events caused by the user. + + .. method:: waitvar(name) + :no-typesetting: + + .. method:: wait_variable(name) + + Wait until the Tcl variable *name* is modified, continuing to process + events in the meantime so that the application stays responsive. + *name* is usually a :class:`Variable` instance, such as an + :class:`IntVar` or :class:`StringVar`. + + :meth:`waitvar` is an alias of :meth:`!wait_variable`. + + .. method:: wait_window(window=None) + + Wait until *window* is destroyed, continuing to process events in the + meantime. + If *window* is omitted, this widget is used. + This is typically used to wait for the user to finish interacting with a + dialog box. + + .. method:: wait_visibility(window=None) + + Wait until the visibility state of *window* changes, for example when it + first appears on the screen, continuing to process events in the + meantime. + If *window* is omitted, this widget is used. + This is typically used to wait for a newly created window to become + visible before acting on it. + + The methods with the ``focus_`` prefix manage the keyboard focus. + + .. method:: focus_set() + :no-typesetting: + + .. method:: focus() + + Direct the keyboard input focus for this widget's display to this widget. + If the application does not currently have the input focus on this + widget's display, the widget is remembered as the focus window for its + top level, and the focus will be redirected to it the next time the + window manager gives the focus to the top level. + :meth:`focus` is an alias of :meth:`!focus_set`, + except on the :class:`Canvas` and + :class:`ttk.Treeview ` widgets, + which provide their own :meth:`!focus` method. + + .. method:: focus_force() + + Direct the keyboard input focus to this widget even if the application + does not currently have the input focus for the widget's display. + This method should be used sparingly, if at all; normally an application + should wait for the window manager to give it the focus rather than + claiming it. + + .. method:: focus_get() + + Return the widget that currently has the keyboard focus in the + application, or ``None`` if no widget in the application has the focus. + Use :meth:`focus_displayof` to work correctly with several displays. + + .. method:: focus_displayof() + + Return the widget that currently has the keyboard focus on the display + where this widget is located, or ``None`` if no widget in the application + has the focus on that display. + + .. method:: focus_lastfor() + + Return the most recent widget to have had the keyboard focus among all + the widgets in the same top level as this widget; this is the widget that + will receive the focus the next time the window manager gives the focus + to the top level. + If no widget in that top level has ever had the focus, or if the most + recent focus widget has been deleted, the top level itself is returned. + + .. method:: tk_focusFollowsMouse() + + Reconfigure Tk to use an implicit focus model in which the focus is set + to a widget whenever the mouse pointer enters it. + This cannot easily be disabled once enabled. + + .. method:: tk_focusNext() + + Return the next widget after this one in the keyboard traversal order, or + ``None`` if there is none. + The traversal order goes first to the next child, then recursively to the + children of that child, and then to the next sibling higher in the + stacking order. + A widget is skipped if its ``takefocus`` option is set to ``0``. + This method is used in the default bindings for the :kbd:`Tab` key. + + .. method:: tk_focusPrev() + + Return the previous widget before this one in the keyboard traversal + order, or ``None`` if there is none. + See :meth:`tk_focusNext` for how the order is defined. + This method is used in the default bindings for the :kbd:`Shift-Tab` key. + + The methods with the ``grab_`` prefix set and query the input grab, which + directs all input events to a single widget. + + .. method:: grab_set() + + Set a local grab on this widget. + A grab confines pointer events to this widget and its descendants: while + the pointer is outside the widget's subtree, button presses and releases + and pointer motion are reported to the grab widget, and windows outside + the subtree become insensitive until the grab is released. + A local grab affects only the grabbing application. + Any grab previously set by this application on the widget's display is + automatically released. + Setting a grab is the usual way to make a dialog modal: while the grab is + in effect the user cannot interact with the other windows of the + application. + + .. method:: grab_set_global() + + Set a global grab on this widget. + A global grab is like the local grab set by :meth:`grab_set`, but it + locks out all other applications on the screen, so that only this + widget's subtree is sensitive to pointer events, and it also grabs the + keyboard. + Use with caution: it is easy to render a display unusable with a global + grab, since other applications stop receiving events until it is + released. + + .. method:: grab_release() + + Release the grab on this widget if there is one; otherwise do nothing. + + .. method:: grab_current() + + Return the widget that currently holds the grab in this application for + this widget's display, or ``None`` if there is no such widget. + + .. method:: grab_status() + + Return ``None`` if no grab is currently set on this widget, ``"local"`` + if a local grab is set, or ``"global"`` if a global grab is set. + + The methods with the ``selection_`` prefix retrieve and manage the X + selection. + + .. method:: selection_clear(**kw) + + Clear the X selection, so that no window owns it anymore. + The selection to clear is given by the keyword argument *selection*, an + atom name such as ``'PRIMARY'`` or ``'CLIPBOARD'``; it defaults to + ``PRIMARY``. + The *displayof* keyword argument names a widget that determines the + display on which to operate, and defaults to this widget. + + This is overridden by the :class:`Entry`, :class:`Listbox` and + :class:`Spinbox` widgets, + where :meth:`!selection_clear` clears the widget's own selection instead. + + .. method:: selection_get(**kw) + + Return the contents of the current X selection. + The keyword argument *selection* names the selection and defaults to + ``PRIMARY``. + The keyword argument *type* specifies the form in which the data is to be + returned (the desired conversion target), an atom name such as + ``'STRING'`` or ``'FILE_NAME'``; it defaults to ``STRING``, except on + X11, where ``UTF8_STRING`` is tried first and ``STRING`` is used as a + fallback. + The *displayof* keyword argument names a widget that determines the + display from which to retrieve the selection, and defaults to this + widget. + + .. method:: selection_handle(command, **kw) + + Register *command* as a handler to supply the X selection owned by this + widget when another application requests it. + When the selection is retrieved, *command* is called with two arguments, + the starting character offset and the maximum number of characters to + return, and must return at most that many characters of the selection + starting at that offset; for very long selections it is called repeatedly + with increasing offsets. + The keyword argument *selection* names the selection (default + ``PRIMARY``) and the keyword argument *type* gives the form of the + selection that the handler supplies (such as ``'STRING'`` or + ``'FILE_NAME'``, default ``STRING``). + + .. method:: selection_own(**kw) + + Make this widget the owner of the X selection on its display. + The previous owner, if any, is notified that it has lost the selection. + The keyword argument *selection* names the selection and defaults to + ``PRIMARY``. + + .. method:: selection_own_get(**kw) + + Return the widget in this application that owns the X selection on the + display containing this widget, or ``None`` if no widget in this + application owns the selection. + The keyword argument *selection* names the selection and defaults to + ``PRIMARY``. + The *displayof* keyword argument names a widget that determines the + display to query, and defaults to this widget. + + The methods with the ``clipboard_`` prefix manage the clipboard. + + .. method:: clipboard_append(string, **kw) + + Append *string* to the Tk clipboard and claim ownership of the clipboard + on this widget's display. + Before appending, the clipboard should be emptied with + :meth:`clipboard_clear`; all appends should be completed before returning + to the event loop so that the clipboard is updated atomically. + The keyword argument *type* specifies the form of the data, an atom name + such as ``'STRING'`` or ``'FILE_NAME'`` (default ``STRING``), and the + keyword argument *format* specifies the representation used to transmit + it (default ``STRING``). + The *displayof* keyword argument names a widget that determines the + target display, and defaults to this widget. + The contents can be retrieved with :meth:`clipboard_get` or + :meth:`selection_get`. + + .. method:: clipboard_clear(**kw) + + Claim ownership of the clipboard on this widget's display and remove any + previous contents. + The *displayof* keyword argument names a widget that determines the + target display, and defaults to this widget. + + .. method:: clipboard_get(**kw) + + Retrieve data from the clipboard on this widget's display. + The keyword argument *type* specifies the form in which the data is to be + returned, an atom name such as ``'STRING'`` or ``'FILE_NAME'``; it + defaults to ``STRING``, except on X11, where ``UTF8_STRING`` is tried + first and ``STRING`` is used as a fallback. + The *displayof* keyword argument names a widget that determines the + display, and defaults to the root window of the application. + This is equivalent to ``selection_get(selection='CLIPBOARD')``. + + The methods with the ``option_`` prefix query and modify the Tk option + database. + + .. method:: option_add(pattern, value, priority=None) + + Add an option to the Tk option database that associates *value* with + *pattern*. + *pattern* consists of names and/or classes separated by asterisks or + dots, in the usual X format. + *priority* is an integer between 0 and 100, or one of the symbolic names + ``'widgetDefault'`` (20), ``'startupFile'`` (40), ``'userDefault'`` (60), + or ``'interactive'`` (80); it defaults to ``interactive``. + + .. method:: option_clear() + + Clear the Tk option database. + Default options from the :envvar:`!RESOURCE_MANAGER` property or the + :file:`.Xdefaults` file are reloaded automatically the next time an + option is added to or removed from the database. + + .. method:: option_get(name, className) + + Return the value of the option matching this widget under *name* and + *className* from the Tk option database, or an empty string if there is + no matching entry. + When several entries match, the one with the highest priority is + returned, and among entries of equal priority the most recently added + one. + + .. method:: option_readfile(fileName, priority=None) + + Read the file named *fileName*, which should have the standard format for + an X resource database such as :file:`.Xdefaults`, and add all the + options it specifies to the Tk option database. + *priority* is interpreted as for :meth:`option_add` and defaults to + ``interactive``. + + .. method:: bell(displayof=0) + + Ring the bell on the display for this widget, using the display's current + bell-related settings, and reset the screen saver for the screen. + If *displayof* is given as a widget, the bell is rung on that widget's + display instead. + + .. method:: tk_setPalette(background, /) + tk_setPalette(*args, **kw) + + Set a new color scheme for all Tk widget elements. + Existing widgets are updated and the option database is changed so that + future widgets use the new colors. + A single color argument is taken as the normal background color, from + which a complete palette is computed. + Alternatively, the arguments may be given as keyword *name*/*value* pairs + naming individual options in the option database. + The recognized option names are ``activeBackground``, + ``activeForeground``, ``background``, ``disabledForeground``, + ``foreground``, ``highlightBackground``, ``highlightColor``, + ``insertBackground``, ``selectColor``, ``selectBackground``, + ``selectForeground``, and ``troughColor``; reasonable defaults are + computed for any that are not specified. + + .. method:: tk_bisque() + + Restore the application's colors to the light brown (bisque) color scheme + used in Tk 3.6 and earlier versions. + Provided for backward compatibility. + + .. method:: tk_strictMotif(boolean=None) + + Query or set whether Tk's look and feel should strictly adhere to Motif. + A true *boolean* value enables strict Motif compliance (for example, no + color change when the mouse passes over a slider). + Return the resulting setting. + + The methods with the ``busy_`` prefix manage the busy state of a window, + which shows a busy cursor and ignores user input. + + .. method:: busy(**kw) + :no-typesetting: + + .. method:: busy_hold(**kw) + :no-typesetting: + + .. method:: tk_busy(**kw) + :no-typesetting: + + .. method:: tk_busy_hold(**kw) + + Make this widget appear busy. + A transparent window is placed in front of the widget, so that it and all + of its descendants in the widget hierarchy are blocked from pointer + events and display a busy cursor. + Normally :meth:`update` should be called immediately afterwards to ensure + that the hold operation is in effect before the application starts its + processing. + + The only supported configuration option is *cursor*, the cursor to be + displayed while the widget is busy; it may have any of the values + accepted by :meth:`!configure`. + + :meth:`busy_hold`, :meth:`busy` and :meth:`tk_busy` are aliases of + :meth:`!tk_busy_hold`. + + .. versionadded:: 3.13 + + + .. method:: busy_configure(cnf=None, **kw) + :no-typesetting: + + .. method:: busy_config(cnf=None, **kw) + :no-typesetting: + + .. method:: tk_busy_config(cnf=None, **kw) + :no-typesetting: + + .. method:: tk_busy_configure(cnf=None, **kw) + + Query or modify the configuration options of the busy window. + The widget must have been previously made busy by :meth:`tk_busy_hold`. + With no arguments, return a dictionary describing all of the available + options; if *cnf* is the name of an option, return a tuple describing + that one option. + Otherwise set the given options to the given values. + Options may have any of the values accepted by :meth:`tk_busy_hold`. + + The option database is referenced through the widget name or class. + For example, if a :class:`Frame` widget named ``frame`` is to be made + busy, the busy cursor can be specified for it by either of the calls:: + + w.option_add('*frame.busyCursor', 'gumby') + w.option_add('*Frame.BusyCursor', 'gumby') + + :meth:`busy_configure`, :meth:`busy_config` and :meth:`tk_busy_config` + are aliases of :meth:`!tk_busy_configure`. + + .. versionadded:: 3.13 + + + .. method:: busy_cget(option) + :no-typesetting: + + .. method:: tk_busy_cget(option) + + Return the current value of the busy configuration *option*. + The widget must have been previously made busy by :meth:`tk_busy_hold`, + and *option* may have any of the values accepted by that method. + + :meth:`busy_cget` is an alias of :meth:`!tk_busy_cget`. + + .. versionadded:: 3.13 + + + .. method:: busy_forget() + :no-typesetting: + + .. method:: tk_busy_forget() + + Make this widget no longer busy, releasing the resources (including the + transparent window) allocated when it was made busy. + User events will again be received by the widget. + These resources are also released when the widget is destroyed. + + :meth:`busy_forget` is an alias of :meth:`!tk_busy_forget`. + + .. versionadded:: 3.13 + + + .. method:: busy_status() + :no-typesetting: + + .. method:: tk_busy_status() + + Return ``True`` if the widget is currently busy, ``False`` otherwise. + + :meth:`busy_status` is an alias of :meth:`!tk_busy_status`. + + .. versionadded:: 3.13 + + + .. method:: busy_current(pattern=None) + :no-typesetting: + + .. method:: tk_busy_current(pattern=None) + + Return a list of widgets that are currently busy. + If *pattern* is given, only busy widgets whose path names match the + pattern are returned. + + :meth:`busy_current` is an alias of :meth:`!tk_busy_current`. + + .. versionadded:: 3.13 + + The methods with the ``winfo_`` prefix retrieve information about windows + managed by Tk. + + .. method:: winfo_atom(name, displayof=0) + + Return the integer identifier for the atom whose name is *name*, creating + a new atom if none exists. + If *displayof* is given, the atom is looked up on the display of that + window; otherwise it is looked up on the display of the application's + main window. + + .. method:: winfo_atomname(id, displayof=0) + + Return the textual name for the atom whose integer identifier is *id*. + This is the inverse of :meth:`winfo_atom`. + If *displayof* is given, the identifier is looked up on the display of + that window; otherwise it is looked up on the display of the + application's main window. + + .. method:: winfo_cells() + + Return the number of cells in the colormap for the widget. + + .. method:: winfo_children() + + Return a list containing the widgets that are children of the widget, in + stacking order from lowest to highest. + Toplevel windows are returned as children of their logical parents. + + .. method:: winfo_class() + + Return the class name of the widget. + + .. method:: winfo_colormapfull() + + Return ``True`` if the colormap for the widget is known to be full, + ``False`` otherwise. + + .. method:: winfo_containing(rootX, rootY, displayof=0) + + Return the widget containing the point given by *rootX* and *rootY*, or + ``None`` if no window in this application contains the point. + The coordinates are in screen units in the coordinate system of the root + window. + If *displayof* is given, the coordinates refer to the screen containing + that window; otherwise they refer to the screen of the application's main + window. + + .. method:: winfo_depth() + + Return the depth of the widget, that is, the number of bits per pixel. + + .. method:: winfo_exists() + + Return true if the widget exists, false otherwise. + + .. method:: winfo_fpixels(number) + + Return a floating-point value giving the number of pixels in the widget + corresponding to the screen distance *number* (for example, + ``"2.0c"`` or ``"1i"``). + The result may be fractional; for a rounded integer value use + :meth:`winfo_pixels`. + + .. method:: winfo_geometry() + + Return the geometry of the widget, in the form ``widthxheight+x+y``. + All dimensions are in pixels. + An offset can be negative; see :meth:`~Wm.geometry`. + + .. method:: winfo_height() + + Return the height of the widget in pixels. + When a window is first created its height is 1 pixel; it is eventually + changed by a geometry manager. + See also :meth:`winfo_reqheight`. + + .. method:: winfo_id() + + Return a low-level platform-specific identifier for the widget. + On Unix this is the X window identifier, and on Windows it is the window + handle. + + .. method:: winfo_interps(displayof=0) + + Return a tuple of the names of all Tcl interpreters currently registered + for a particular display. + If *displayof* is given, the return value refers to the display of that + window; otherwise it refers to the display of the application's main + window. + + .. method:: winfo_ismapped() + + Return true if the widget is currently mapped, false otherwise. + + .. method:: winfo_manager() + + Return the name of the geometry manager currently responsible for the + widget, or an empty string if it is not managed by any geometry manager. + + .. method:: winfo_name() + + Return the widget's name within its parent, as opposed to its full path + name. + + .. method:: winfo_parent() + + Return the path name of the widget's parent, or an empty string if the + widget is the main window of the application. + + .. method:: winfo_pathname(id, displayof=0) + + Return the path name of the window whose identifier is *id*. + If *displayof* is given, the identifier is looked up on the display of + that window; otherwise it is looked up on the display of the + application's main window. + + .. method:: winfo_pixels(number) + + Return the number of pixels in the widget corresponding to the screen + distance *number* (for example, ``"2.0c"`` or ``"1i"``). + The result is rounded to the nearest integer; for a fractional result use + :meth:`winfo_fpixels`. + + .. method:: winfo_pointerx() + + Return the pointer's *x* coordinate, in pixels, relative to the screen's + root window (or virtual root, if one is in use). + Return ``-1`` if the pointer is not on the same screen as the widget. + + .. method:: winfo_pointerxy() + + Return the pointer's coordinates as an ``(x, y)`` tuple, in pixels, + relative to the screen's root window (or virtual root, if one is in use). + Both coordinates are ``-1`` if the pointer is not on the same screen as + the widget. + + .. method:: winfo_pointery() + + Return the pointer's *y* coordinate, in pixels, relative to the screen's + root window (or virtual root, if one is in use). + Return ``-1`` if the pointer is not on the same screen as the widget. + + .. method:: winfo_reqheight() + + Return the widget's requested height in pixels. + This is the value used by the widget's geometry manager to compute its + geometry. + + .. method:: winfo_reqwidth() + + Return the widget's requested width in pixels. + This is the value used by the widget's geometry manager to compute its + geometry. + + .. method:: winfo_rgb(color) + + Return an ``(r, g, b)`` tuple of the red, green, and blue intensities, in + the range 0 to 65535, that correspond to *color* in the widget. + *color* may be specified in any of the forms acceptable for a color + option. + + .. method:: winfo_rootx() + + Return the *x* coordinate, in the root window of the screen, of the + upper-left corner of the widget's border (or of the widget itself if it + has no border). + + .. method:: winfo_rooty() + + Return the *y* coordinate, in the root window of the screen, of the + upper-left corner of the widget's border (or of the widget itself if it + has no border). + + .. method:: winfo_screen() + + Return the name of the screen associated with the widget, in the form + ``displayName.screenIndex``. + + .. method:: winfo_screencells() + + Return the number of cells in the default colormap for the widget's + screen. + + .. method:: winfo_screendepth() + + Return the depth of the root window of the widget's screen, that is, the + number of bits per pixel. + + .. method:: winfo_screenheight() + + Return the height of the widget's screen in pixels. + + .. method:: winfo_screenmmheight() + + Return the height of the widget's screen in millimeters. + + .. method:: winfo_screenmmwidth() + + Return the width of the widget's screen in millimeters. + + .. method:: winfo_screenvisual() + + Return the default visual class for the widget's screen, one of + ``"directcolor"``, ``"grayscale"``, ``"pseudocolor"``, ``"staticcolor"``, + ``"staticgray"``, or ``"truecolor"``. + + .. method:: winfo_screenwidth() + + Return the width of the widget's screen in pixels. + + .. method:: winfo_server() + + Return a string containing information about the server for the widget's + display. + The exact format of this string may vary from platform to platform. + + .. method:: winfo_toplevel() + + Return the top-of-hierarchy window containing the widget. + In standard Tk this is always a :class:`Toplevel` widget. + + .. method:: winfo_viewable() + + Return true if the widget and all of its ancestors up through the + nearest toplevel window are mapped, false otherwise. + + .. method:: winfo_visual() + + Return the visual class for the widget, one of ``"directcolor"``, + ``"grayscale"``, ``"pseudocolor"``, ``"staticcolor"``, ``"staticgray"``, + or ``"truecolor"``. + + .. method:: winfo_visualid() + + Return the X identifier for the visual for the widget. + + .. method:: winfo_visualsavailable(includeids=False) + + Return a list describing the visuals available for the widget's screen. + Each item consists of a visual class (see :meth:`winfo_visual`) followed + by an integer depth. + If *includeids* is true, the X identifier for the visual is also + included. + + .. method:: winfo_vrootheight() + + Return the height of the virtual root window associated with the widget + if there is one; otherwise return the height of the widget's screen. + + .. method:: winfo_vrootwidth() + + Return the width of the virtual root window associated with the widget if + there is one; otherwise return the width of the widget's screen. + + .. method:: winfo_vrootx() + + Return the *x* offset of the virtual root window associated with the + widget, relative to the root window of its screen. + This is normally zero or negative, and is ``0`` if there is no virtual + root window. + + .. method:: winfo_vrooty() + + Return the *y* offset of the virtual root window associated with the + widget, relative to the root window of its screen. + This is normally zero or negative, and is ``0`` if there is no virtual + root window. + + .. method:: winfo_width() + + Return the width of the widget in pixels. + When a window is first created its width is 1 pixel; it is eventually + changed by a geometry manager. + See also :meth:`winfo_reqwidth`. + + .. method:: winfo_x() + + Return the *x* coordinate, in the widget's parent, of the upper-left + corner of the widget's border (or of the widget itself if it has no + border). + + .. method:: winfo_y() + + Return the *y* coordinate, in the widget's parent, of the upper-left + corner of the widget's border (or of the widget itself if it has no + border). + + .. method:: info_patchlevel() + + Return the Tcl/Tk patch level as a named tuple with the same five fields + as :data:`sys.version_info`: *major*, *minor*, *micro*, *releaselevel* + and *serial*. + *releaselevel* is ``'alpha'``, ``'beta'`` or ``'final'``. + Converting it to a string gives the version in the usual Tcl/Tk notation, + for example ``'9.0.3'`` for a final release or ``'9.1b2'`` for a + pre-release. + + .. versionadded:: 3.11 + + + +.. class:: Wm() + + The :class:`!Wm` mixin provides access to the window manager, allowing an + application to control such things as the title, geometry and icon of a + top-level window, the way it is resized, and how it responds to window + manager protocols. + It is mixed into :class:`Tk` and :class:`Toplevel`, so its methods are + available on every top-level window. + Each method has two equivalent spellings: a short name and a + ``wm_``-prefixed name (for example, :meth:`title` and :meth:`wm_title`). + See also :ref:`tkinter-window-manager`. + + .. method:: wm_aspect(minNumer=None, minDenom=None, maxNumer=None, maxDenom=None) + :no-typesetting: + + .. method:: aspect(minNumer=None, minDenom=None, maxNumer=None, maxDenom=None) + + Constrain the aspect ratio (the ratio of width to height) of the window. + If all four arguments are given, the window manager keeps the ratio + between ``minNumer/minDenom`` and ``maxNumer/maxDenom``; passing empty + strings removes any existing restriction. + With no arguments, return a tuple of the four current values, or ``None`` + if no aspect restriction is in effect. + :meth:`wm_aspect` is an alias of :meth:`!aspect`. + + .. method:: wm_attributes(*args, return_python_dict=False, **kwargs) + :no-typesetting: + + .. method:: attributes(*args, return_python_dict=False, **kwargs) + + Query or set platform-specific attributes of the window. + With no arguments, return the platform-specific flags and their values; + pass *return_python_dict* as true to get them as a dictionary. + A single option name such as ``'alpha'`` returns the value of that + option, and options are set using keyword arguments (``alpha=0.5``). + + The available attributes differ by platform. + All platforms support: + + *alpha* + The window's opacity, from ``0.0`` (fully transparent) to ``1.0`` + (opaque). + Where transparency is unsupported the value stays at ``1.0``. + + *appearance* + Whether the window is rendered in dark mode on Windows and macOS: + ``'auto'``, ``'light'`` or ``'dark'`` (this has no effect on X11). + + *fullscreen* + Whether the window takes up the entire screen and has no borders. + + *topmost* + Whether the window is displayed above all other windows. + + Windows additionally supports: + + *disabled* + Whether the window is in a disabled state. + + *toolwindow* + Whether the window uses the tool window style. + + *transparentcolor* + The color that is made fully transparent, or an empty string for none. + + macOS additionally supports: + + *class* + Whether the underlying Aqua window is an ``nswindow`` or an + ``nspanel``; this can only be set before the window is created. + + *modified* + The modification state shown by the window's close button and proxy + icon. + + *notify* + Whether the application's dock icon bounces to request attention. + + *stylemask* + The style mask of the underlying Aqua window, given as a list of bit + names such as ``titled`` or ``resizable``. + + *tabbingid* + The identifier of the tab group that the window belongs to. + + *tabbingmode* + Whether the window may be opened as a tab: ``'auto'``, ``'preferred'`` + or ``'disallowed'``. + + *titlepath* + The path of the file represented by the window's proxy icon. + + *transparent* + Whether the content area is transparent and the window shadow is + turned off. + + X11 additionally supports: + + *type* + The window type, or a list of types in order of preference, that the + window manager should use to interpret the window, such as + ``'dialog'`` or ``'splash'``. + + *zoomed* + Whether the window is maximized. + + .. note:: + + Tk 8.6 added the *type* attribute, and Tk 9.0 added the *appearance*, + *class*, *stylemask*, *tabbingid* and *tabbingmode* attributes. + + On X11 changes are applied asynchronously, so a queried value may not yet + reflect the most recent request. + :meth:`wm_attributes` is an alias of :meth:`!attributes`. + + .. versionchanged:: 3.13 + A single attribute may now be queried by name without the leading + ``-``, and attributes may be set using keyword arguments. + The *return_python_dict* parameter was added. + + .. deprecated:: 3.13 + Setting an attribute by passing the option name (with a leading + ``-``) and its value as two positional arguments, as in + ``w.attributes('-alpha', 0.5)``, is deprecated; use keyword arguments + instead. + + + .. method:: wm_client(name=None) + :no-typesetting: + + .. method:: client(name=None) + + Store *name*, which should be the name of the host on which the + application is running, in the window's ``WM_CLIENT_MACHINE`` property + for use by the window or session manager. + An empty string deletes the property. + With no argument, return the last name set, or an empty string. + :meth:`wm_client` is an alias of :meth:`!client`. + + .. method:: wm_colormapwindows(*wlist) + :no-typesetting: + + .. method:: colormapwindows(*wlist) + + Manipulate the ``WM_COLORMAP_WINDOWS`` property, which tells the window + manager about windows that have private colormaps. + If *wlist* is given, overwrite the property with those windows (their + order is a priority order for installing colormaps). + With no arguments, return the list of windows currently named in the + property. + :meth:`wm_colormapwindows` is an alias of :meth:`!colormapwindows`. + + .. method:: wm_command(value=None) + :no-typesetting: + + .. method:: command(value=None) + + Store *value* in the window's ``WM_COMMAND`` property for use by the + window or session manager; it should be a list giving the words of the + command used to invoke the application. + An empty string deletes the property. + With no argument, return the last value set, or an empty string. + :meth:`wm_command` is an alias of :meth:`!command`. + + .. method:: wm_deiconify() + :no-typesetting: + + .. method:: deiconify() + + Display the window in normal (non-iconified) form by mapping it. + If the window has never been mapped, this ensures it appears de-iconified + when it is first mapped. + On Windows the window is also raised and given the focus. + :meth:`wm_deiconify` is an alias of :meth:`!deiconify`. + + .. method:: wm_focusmodel(model=None) + :no-typesetting: + + .. method:: focusmodel(model=None) + + Set or query the focus model for the window. + *model* is either ``'active'`` (the window claims the input focus for + itself or its descendants, even when the focus is in another application) + or ``'passive'`` (the window relies on the window manager to give it the + focus). + With no argument, return the current model. + The default is ``'passive'``, which is what the :meth:`!focus` command + assumes. + :meth:`wm_focusmodel` is an alias of :meth:`!focusmodel`. + + .. method:: wm_forget(window) + :no-typesetting: + + .. method:: forget(window) + + Unmap *window* from the screen so that it is no longer managed by the + window manager. + A :class:`Toplevel` is then treated like a :class:`Frame`, although its + ``-menu`` configuration is remembered and the menu reappears if the + widget is managed again. + :meth:`wm_forget` is an alias of :meth:`!forget`. + + Not to be confused with :meth:`Pack.forget`. + + .. versionadded:: 3.3 + + .. method:: wm_frame() + :no-typesetting: + + .. method:: frame() + + Return the platform-specific window identifier for the outermost + decorative frame containing the window, if the window manager has + reparented it into such a frame; otherwise return the identifier of the + window itself. + :meth:`wm_frame` is an alias of :meth:`!frame`. + + .. method:: wm_geometry(newGeometry=None) + :no-typesetting: + + .. method:: geometry(newGeometry=None) + + Set or query the geometry of the window. + *newGeometry* has the form ``=widthxheight+x+y``, where any of ``=``, + ``widthxheight`` and the ``+x+y`` position may be omitted. + *width* and *height* are in pixels (or grid units for a gridded window); + a position preceded by ``+`` is measured from the left or top edge of the + screen and one preceded by ``-`` from the right or bottom edge. + An offset can be negative, as in ``'200x100+-9+-8'``, when the window + edge is positioned beyond the corresponding screen edge. + An empty string cancels any user-specified geometry, letting the window + revert to its natural size. + With no argument, return the current geometry as a string of the form + ``'200x200+10+10'``. + :meth:`wm_geometry` is an alias of :meth:`!geometry`. + + .. method:: wm_grid(baseWidth=None, baseHeight=None, widthInc=None, heightInc=None) + :no-typesetting: + + .. method:: grid(baseWidth=None, baseHeight=None, widthInc=None, heightInc=None) + + Manage the window as a gridded window and define the relationship between + grid units and pixels. + *baseWidth* and *baseHeight* are the numbers of grid units for the + window's internally requested size, and *widthInc* and *heightInc* are + the pixel sizes of a horizontal and vertical grid unit. + Empty strings turn off gridded management. + With no arguments, return a tuple of the four current values, or ``None`` + if the window is not gridded. + :meth:`wm_grid` is an alias of :meth:`!grid`. + + Not to be confused with the grid geometry manager :meth:`Grid.grid`. + + .. method:: wm_group(pathName=None) + :no-typesetting: + + .. method:: group(pathName=None) + + Set or query the leader of a group of related windows. + *pathName* gives the path name of the group leader; the window manager + may, for example, unmap all windows in the group when the leader is + iconified. + An empty string removes the window from any group. + With no argument, return the path name of the current group leader, or an + empty string. + :meth:`wm_group` is an alias of :meth:`!group`. + + .. method:: wm_iconbitmap(bitmap=None, default=None) + :no-typesetting: + + .. method:: iconbitmap(bitmap=None, default=None) + + Set or query the bitmap used by the window manager for the window's icon. + *bitmap* names a bitmap in one of the standard forms accepted by Tk; an + empty string cancels the current icon bitmap. + With no argument, return the name of the current icon bitmap, or an empty + string. + On Windows the *default* argument names an icon (for example an ``.ico`` + file) applied to all top-level windows that have no icon of their own. + :meth:`wm_iconbitmap` is an alias of :meth:`!iconbitmap`. + + .. method:: wm_iconify() + :no-typesetting: + + .. method:: iconify() + + Iconify the window. + If the window has not yet been mapped for the first time, arrange for it + to appear in the iconified state when it is eventually mapped. + :meth:`wm_iconify` is an alias of :meth:`!iconify`. + + .. method:: wm_iconmask(bitmap=None) + :no-typesetting: + + .. method:: iconmask(bitmap=None) + + Set or query the bitmap used as a mask for the icon (see + :meth:`iconbitmap`). + Where the mask is zero no icon is displayed; where it is one, the + corresponding bits of the icon bitmap are shown. + An empty string cancels the current mask. + With no argument, return the name of the current icon mask, or an empty + string. + :meth:`wm_iconmask` is an alias of :meth:`!iconmask`. + + .. method:: wm_iconname(newName=None) + :no-typesetting: + + .. method:: iconname(newName=None) + + Set or query the name displayed by the window manager inside the window's + icon. + With no argument, return the current icon name, or an empty string if + none has been set (in which case the window manager normally displays the + window's title). + :meth:`wm_iconname` is an alias of :meth:`!iconname`. + + .. method:: wm_iconphoto(default=False, *images) + :no-typesetting: + + .. method:: iconphoto(default=False, *images) + + Set the titlebar icon for the window from one or more :class:`PhotoImage` + objects given in *images*. + Several images of different sizes (for example 16x16 and 32x32) may be + supplied so that the window manager can choose an appropriate one. + The image data is taken as a snapshot at the time of the call; later + changes to the images are not reflected. + If *default* is true, the icon is also applied to all top-level windows + created in the future. + On macOS only the first image is used. + :meth:`wm_iconphoto` is an alias of :meth:`!iconphoto`. + + .. versionadded:: 3.3 + + .. method:: wm_iconposition(x=None, y=None) + :no-typesetting: + + .. method:: iconposition(x=None, y=None) + + Set or query a hint to the window manager about where the window's icon + should be positioned. + Empty strings cancel an existing hint. + With no arguments, return a tuple of the two current values, or ``None`` + if no hint is in effect. + :meth:`wm_iconposition` is an alias of :meth:`!iconposition`. + + .. method:: wm_iconwindow(pathName=None) + :no-typesetting: + + .. method:: iconwindow(pathName=None) + + Set or query the window used as the icon for the window. + When the window is iconified, *pathName* is mapped to serve as its icon + and unmapped again when it is de-iconified. + An empty string cancels the association. + With no argument, return the path name of the current icon window, or an + empty string. + Not all window managers support icon windows, and the concept is + meaningless on non-X11 platforms. + :meth:`wm_iconwindow` is an alias of :meth:`!iconwindow`. + + .. method:: wm_manage(widget) + :no-typesetting: + + .. method:: manage(widget) + + Make *widget* a stand-alone top-level window, decorated by the window + manager with a title bar and so on. + Only :class:`Frame`, :class:`LabelFrame` and :class:`Toplevel` widgets + may be used (the :mod:`tkinter.ttk` versions are **not** accepted); + passing any other widget type raises an error. + :meth:`wm_manage` is an alias of :meth:`!manage`. + + .. versionadded:: 3.3 + + .. method:: wm_maxsize(width=None, height=None) + :no-typesetting: + + .. method:: maxsize(width=None, height=None) + + Set or query the maximum permissible dimensions of the window, in pixels + (or grid units for a gridded window). + The window manager restricts the window to be no larger than *width* and + *height*. + With no arguments, return a tuple of the current maximum width and + height. + The maximum size defaults to the size of the screen. + :meth:`wm_maxsize` is an alias of :meth:`!maxsize`. + + .. method:: wm_minsize(width=None, height=None) + :no-typesetting: + + .. method:: minsize(width=None, height=None) + + Set or query the minimum permissible dimensions of the window, in pixels + (or grid units for a gridded window). + The window manager restricts the window to be no smaller than *width* and + *height*. + With no arguments, return a tuple of the current minimum width and + height. + The minimum size defaults to one pixel in each dimension. + :meth:`wm_minsize` is an alias of :meth:`!minsize`. + + .. method:: wm_overrideredirect(boolean=None) + :no-typesetting: + + .. method:: overrideredirect(boolean=None) + + Set or query the override-redirect flag for the window. + When this flag is set, the window is ignored by the window manager: it is + not reparented into a decorative frame and the user cannot manipulate it + through the usual window manager controls. + With no argument, return a boolean indicating whether the flag is set, + or ``None`` if it has not been set. + The flag is reliably honored only when the window is first mapped or + remapped from the withdrawn state. + :meth:`wm_overrideredirect` is an alias of :meth:`!overrideredirect`. + + .. method:: wm_positionfrom(who=None) + :no-typesetting: + + .. method:: positionfrom(who=None) + + Set or query the source of the window's current position. + *who* is either ``'program'`` or ``'user'`` and indicates whether the + position was requested by the program or by the user; an empty string + cancels the current source. + With no argument, return the current source, or an empty string if none + has been set. + Tk automatically sets the source to ``'user'`` when :meth:`geometry` is + called, unless it has been set explicitly to ``'program'``. + :meth:`wm_positionfrom` is an alias of :meth:`!positionfrom`. + + .. method:: wm_protocol(name=None, func=None) + :no-typesetting: + + .. method:: protocol(name=None, func=None) + + Register *func* as the handler for the window manager protocol *name*, an + atom such as ``'WM_DELETE_WINDOW'``, ``'WM_SAVE_YOURSELF'`` or + ``'WM_TAKE_FOCUS'``; *func* is then called whenever the window manager + sends a message of that protocol. + Tk installs a default ``WM_DELETE_WINDOW`` handler that destroys the + window, which this method can replace. + If *func* is an empty string, the handler is removed. + With only *name*, return the name of its registered handler command, or + an empty string if none is set (the default ``WM_DELETE_WINDOW`` handler + is not reported); with no arguments, return a tuple of the protocols that + currently have handlers. + :meth:`wm_protocol` is an alias of :meth:`!protocol`. + + .. method:: wm_resizable(width=None, height=None) + :no-typesetting: + + .. method:: resizable(width=None, height=None) + + Control whether the user may interactively resize the window. + *width* and *height* are boolean values that determine whether the + window's width and height may be changed. + With no arguments, return a tuple of two ``0``/``1`` values indicating + whether each dimension is currently resizable. + By default a window is resizable in both dimensions. + :meth:`wm_resizable` is an alias of :meth:`!resizable`. + + .. method:: wm_sizefrom(who=None) + :no-typesetting: + + .. method:: sizefrom(who=None) + + Set or query the source of the window's current size. + *who* is either ``'program'`` or ``'user'`` and indicates whether the + size was requested by the program or by the user; an empty string cancels + the current source. + With no argument, return the current source, or an empty string if none + has been set. + :meth:`wm_sizefrom` is an alias of :meth:`!sizefrom`. + + .. method:: wm_state(newstate=None) + :no-typesetting: + + .. method:: state(newstate=None) + + Set or query the state of the window. + With no argument, return the current state: one of ``'normal'``, + ``'iconic'``, ``'withdrawn'``, ``'icon'`` or, on Windows and macOS only, + ``'zoomed'``. + ``'iconic'`` refers to a window that has been iconified, while ``'icon'`` + refers to a window serving as the icon for another window (see + :meth:`iconwindow`); the ``'icon'`` state cannot be set. + :meth:`wm_state` is an alias of :meth:`!state`. + + Not to be confused with :meth:`ttk.Widget.state + `. + + .. method:: wm_title(string=None) + :no-typesetting: + + .. method:: title(string=None) + + Set or query the title for the window, which the window manager should + display in the window's title bar. + With no argument, return the current title. + The title defaults to the window's name. + :meth:`wm_title` is an alias of :meth:`!title`. + + .. method:: wm_transient(master=None) + :no-typesetting: + + .. method:: transient(master=None) + + Mark the window as a transient window (such as a pull-down menu or + dialog) working on behalf of *master*, the path name of another top-level + window. + An empty string clears the transient status. + With no argument, return the path name of the current master, or an empty + string. + A transient window mirrors state changes in its master and may be + decorated differently by the window manager; it is an error to make a + window a transient of itself. + :meth:`wm_transient` is an alias of :meth:`!transient`. + + .. method:: wm_withdraw() + :no-typesetting: + + .. method:: withdraw() + + Withdraw the window from the screen, unmapping it and causing the window + manager to forget about it. + If the window has never been mapped, it is instead mapped in the + withdrawn state. + It is sometimes necessary to withdraw a window and then re-map it (for + example with :meth:`deiconify`) to make some window managers notice + changes to window attributes. + :meth:`wm_withdraw` is an alias of :meth:`!withdraw`. + + +.. class:: Pack() + + Geometry manager that arranges widgets by packing them against the sides of + their container. + The :class:`!Pack` mix-in is inherited by all widgets (through + :class:`Widget`) and provides the methods for managing a widget with the + *pack* geometry manager. + See also :ref:`tkinter-geometry-management`. + + .. note:: + + :class:`Pack`, :class:`Place` and :class:`Grid` all define the short + method names :meth:`!forget`, :meth:`!info`, :meth:`!slaves`, + :meth:`!content` and :meth:`!propagate`. + On a widget the bare names resolve to the *pack* manager's versions, + since :class:`Pack` and :class:`Misc` precede :class:`Place` and + :class:`Grid` in the method resolution order, + whatever manager actually manages the widget; + and :meth:`!configure`/:meth:`!config` configure the widget's options, + not its geometry. + Use the explicit ``pack_*``, ``grid_*`` and ``place_*`` methods + (and ``pack``, ``grid``, ``place`` for geometry configuration) + to act on a specific geometry manager. + + .. method:: configure(cnf={}, **kw) + :no-typesetting: + + .. method:: config(cnf={}, **kw) + :no-typesetting: + + .. method:: pack_configure(cnf={}, **kw) + pack(cnf={}, **kw) + + Pack the widget inside its container, positioning it relative to the + siblings already packed there. + The supported options are: + + *side* + Which side of the container to pack the widget against: ``'top'`` (the + default), ``'bottom'``, ``'left'`` or ``'right'``. + + *fill* + Whether to stretch the widget to fill its parcel: ``'none'`` (the + default), ``'x'``, ``'y'`` or ``'both'``. + + *expand* + Whether the widget should expand to consume any extra space in its + container (a boolean, default false). + + *anchor* + Where to position the widget in its parcel when the parcel is larger + than the widget: an anchor such as ``'n'`` or ``'sw'`` (default + ``'center'``). + + *ipadx*, *ipady* + Internal padding added on the left and right (*ipadx*) or top and + bottom (*ipady*) of the widget, as a screen distance (default ``0``). + + *padx*, *pady* + External padding left on the left and right (*padx*) or top and bottom + (*pady*) of the widget, as a screen distance or a pair of two + distances for the two sides (default ``0``). + + *after* + Pack the widget after the given widget in the packing order, using the + same container. + + *before* + Pack the widget before the given widget in the packing order, using + the same container. + + *in_* + The container in which to pack the widget; it defaults to the parent + widget. + + :meth:`pack`, :meth:`configure` and :meth:`config` are aliases of + :meth:`!pack_configure`. + + .. method:: forget() + :no-typesetting: + + .. method:: pack_forget() + + Unmap the widget and remove it from the packing order, forgetting its + packing options. + It can be packed again later with :meth:`pack_configure`. + :meth:`forget` is an alias of :meth:`!pack_forget`, + except on :class:`PanedWindow`, + :class:`ttk.Notebook ` and + :class:`ttk.PanedWindow `, + which provide their own :meth:`!forget` method. + + Not to be confused with :meth:`Wm.forget`. + + .. method:: info() + :no-typesetting: + + .. method:: pack_info() + + Return a dictionary of the widget's current packing options. + :meth:`info` is an alias of :meth:`!pack_info`. + + .. method:: propagate() + propagate(flag) + :no-typesetting: + + .. method:: pack_propagate() + pack_propagate(flag) + + Same as :meth:`Misc.pack_propagate`, treating this widget as a container: + enable or disable geometry propagation. + :meth:`propagate` is an alias of :meth:`!pack_propagate`. + + .. method:: slaves() + :no-typesetting: + + .. method:: pack_slaves() + + Same as :meth:`Misc.pack_slaves`: return the list of widgets packed in + this widget. + :meth:`slaves` is an alias of :meth:`!pack_slaves`. + + +.. class:: Place() + + Geometry manager that places widgets at explicit positions and sizes within + their container. + The :class:`!Place` mix-in is inherited by all widgets (through + :class:`Widget`). + See also :ref:`tkinter-geometry-management`. + + .. method:: configure(cnf={}, **kw) + :no-typesetting: + + .. method:: config(cnf={}, **kw) + :no-typesetting: + + .. method:: place_configure(cnf={}, **kw) + place(cnf={}, **kw) + + Place the widget inside its container at an absolute or relative + position. + The supported options are: + + *x*, *y* + The absolute horizontal and vertical position of the widget's anchor + point, as a screen distance (default ``0``). + + *relx*, *rely* + The horizontal and vertical position of the widget's anchor point as a + fraction of the container's width and height, where ``0.0`` is the + left or top edge and ``1.0`` is the right or bottom edge. + If both the absolute and the relative option are given, their values + are summed. + + *anchor* + Which point of the widget is placed at the given position: an anchor + such as ``'n'`` or ``'se'`` (default ``'nw'``). + + *width*, *height* + The absolute width and height of the widget, as a screen distance. + By default the widget's requested size is used. + + *relwidth*, *relheight* + The width and height of the widget as a fraction of the container's + width and height. + If both the absolute and the relative option are given, their values + are summed. + + *bordermode* + How the container's border affects placement: ``'inside'`` (the + default) measures the area inside the border, ``'outside'`` measures + the area including the border, and ``'ignore'`` uses the official X + area. + + *in_* + The container relative to which the widget is placed; it must be the + widget's parent or a descendant of the parent, and defaults to the + parent. + + :meth:`place`, :meth:`configure` and :meth:`config` are aliases of + :meth:`!place_configure`. + + .. method:: forget() + :no-typesetting: + + .. method:: place_forget() + + Unmap the widget and remove it from the placement, forgetting its place + options. + + .. method:: info() + :no-typesetting: + + .. method:: place_info() + + Return a dictionary of the widget's current place options. + + .. method:: slaves() + :no-typesetting: + + .. method:: place_slaves() + + Same as :meth:`Misc.place_slaves`: return the list of widgets placed in + this widget. + + +.. class:: Grid() + + Geometry manager that arranges widgets in a two-dimensional grid of rows and + columns within their container. + The :class:`!Grid` mix-in is inherited by all widgets (through + :class:`Widget`). + See also :ref:`tkinter-geometry-management`. + + .. method:: configure(cnf={}, **kw) + :no-typesetting: + + .. method:: config(cnf={}, **kw) + :no-typesetting: + + .. method:: grid_configure(cnf={}, **kw) + grid(cnf={}, **kw) + + Position the widget in a cell of its container's grid. + + Not to be confused with :meth:`Wm.grid`. + + The supported options are: + + *row*, *column* + The row and column of the cell to place the widget in, counting from + ``0``. + *column* defaults to the column after the previous widget placed in + the same :meth:`!grid_configure` call (or ``0``), and *row* defaults + to the next empty row. + + *rowspan*, *columnspan* + The number of rows and columns the widget should span (default ``1``). + + *sticky* + How to position or stretch the widget when its cell is larger than the + widget: a string containing zero or more of the characters ``'n'``, + ``'s'``, ``'e'`` and ``'w'``, naming the cell sides the widget sticks + to. + Specifying both ``'n'`` and ``'s'`` (or ``'e'`` and ``'w'``) stretches + the widget to fill the height (or width) of the cell. + The default is ``''``, which centers the widget at its requested size. + + *ipadx*, *ipady* + Internal padding added on the left and right (*ipadx*) or top and + bottom (*ipady*) of the widget, as a screen distance (default ``0``). + + *padx*, *pady* + External padding left on the left and right (*padx*) or top and bottom + (*pady*) of the widget, as a screen distance or a pair of two + distances for the two sides (default ``0``). + + *in_* + The container in whose grid to place the widget; it defaults to the + parent widget. + + :meth:`grid`, :meth:`configure` and :meth:`config` are aliases of + :meth:`!grid_configure`. + + .. method:: forget() + :no-typesetting: + + .. method:: grid_forget() + + Unmap the widget and remove it from the grid, forgetting its grid + options. + + .. method:: grid_remove() + + Unmap the widget and remove it from the grid, but remember its grid + options so that it is restored to the same cell if it is gridded again. + + .. method:: info() + :no-typesetting: + + .. method:: grid_info() + + Return a dictionary of the widget's current grid options. + + .. method:: bbox(column=None, row=None, col2=None, row2=None) + :no-typesetting: + + .. method:: grid_bbox(column=None, row=None, col2=None, row2=None) + + Same as :meth:`Misc.grid_bbox`. + :meth:`bbox` is an alias of :meth:`!grid_bbox`, + except on :class:`Canvas`, :class:`Listbox`, :class:`Spinbox`, + :class:`Text`, :class:`ttk.Entry ` and + :class:`ttk.Treeview `, + which provide their own :meth:`!bbox` method. + + .. method:: columnconfigure(index, cnf={}, **kw) + :no-typesetting: + + .. method:: grid_columnconfigure(index, cnf={}, **kw) + + Same as :meth:`Misc.grid_columnconfigure`: query or set the options (such + as *weight*, *minsize*, *pad* and *uniform*) of a grid column. + :meth:`columnconfigure` is an alias of :meth:`!grid_columnconfigure`. + + .. method:: rowconfigure(index, cnf={}, **kw) + :no-typesetting: + + .. method:: grid_rowconfigure(index, cnf={}, **kw) + + Same as :meth:`Misc.grid_rowconfigure`: query or set the options of a + grid row. + :meth:`rowconfigure` is an alias of :meth:`!grid_rowconfigure`. + + .. method:: location(x, y) + :no-typesetting: + + .. method:: grid_location(x, y) + + Same as :meth:`Misc.grid_location`: return the ``(column, row)`` of the + cell that covers the pixel at *x*, *y*. + :meth:`location` is an alias of :meth:`!grid_location`. + + .. method:: size() + :no-typesetting: + + .. method:: grid_size() + + Same as :meth:`Misc.grid_size`: return a ``(columns, rows)`` tuple giving + the size of the grid. + :meth:`size` is an alias of :meth:`!grid_size`, + except on the :class:`Listbox` widget, + which provides its own :meth:`!size` method. + + .. method:: propagate() + propagate(flag) + :no-typesetting: + + .. method:: grid_propagate() + grid_propagate(flag) + + Same as :meth:`Misc.grid_propagate`. + + .. method:: slaves(row=None, column=None) + :no-typesetting: + + .. method:: grid_slaves(row=None, column=None) + + Same as :meth:`Misc.grid_slaves`: return the widgets managed in the grid, + optionally restricted to a *row* and/or *column*. + + +.. class:: XView() + + Mix-in providing the horizontal-scrolling interface shared by widgets such + as :class:`Entry`, :class:`Canvas`, :class:`Listbox`, :class:`Text` and + :class:`Spinbox`. + A widget's :meth:`xview` method is registered as the *command* of a + horizontal :class:`Scrollbar`. + + .. method:: xview(*args) + + Query or change the horizontal position of the view. + With no arguments, return a tuple ``(first, last)`` of two fractions + between 0 and 1 giving the portion of the document that is currently + visible. + Otherwise the arguments are passed to the Tk ``xview`` widget command and + are usually generated by a scrollbar; :meth:`xview_moveto` and + :meth:`xview_scroll` provide a more convenient interface. + + .. method:: xview_moveto(fraction) + + Adjust the view so that *fraction* of the total width of the document is + off-screen to the left. + *fraction* is a number between 0 and 1. + + .. method:: xview_scroll(number, what) + + Shift the view left or right by *number* units. + *what* is either ``'units'`` or ``'pages'``; a negative *number* scrolls + left and a positive one scrolls right. + + +.. class:: YView() + + Mix-in providing the vertical-scrolling interface shared by widgets such as + :class:`Canvas`, :class:`Listbox` and :class:`Text`. + A widget's :meth:`yview` method is registered as the *command* of a vertical + :class:`Scrollbar`. + + .. method:: yview(*args) + + Query or change the vertical position of the view. + With no arguments, return a tuple ``(first, last)`` of two fractions + between 0 and 1 giving the portion of the document that is currently + visible. + Otherwise the arguments are passed to the Tk ``yview`` widget command, + usually generated by a scrollbar; :meth:`yview_moveto` and + :meth:`yview_scroll` provide a more convenient interface. + + .. method:: yview_moveto(fraction) + + Adjust the view so that *fraction* of the total height of the document is + off-screen above the top. + *fraction* is a number between 0 and 1. + + .. method:: yview_scroll(number, what) + + Shift the view up or down by *number* units. + *what* is either ``'units'`` or ``'pages'``; a negative *number* scrolls + up and a positive one scrolls down. + + +.. class:: BaseWidget(master, widgetName, cnf={}, kw={}, extra=()) + + Internal base class for all widgets. + It inherits from :class:`Misc` and adds the machinery that creates the + underlying Tk widget; application code normally uses :class:`Widget` or a + concrete widget class rather than instantiating :class:`!BaseWidget` + directly. + + .. method:: destroy() + + Destroy this widget and all of its children, removing the corresponding + Tk widgets and deleting the associated Tcl commands. + + +.. class:: Widget(master, widgetName, cnf={}, kw={}, extra=()) + + Internal base class for the standard widgets. + It combines :class:`BaseWidget` with the geometry-manager mix-ins + :class:`Pack`, :class:`Place` and :class:`Grid`, so that every widget can be + managed by any of the three geometry managers. + The concrete widget classes (:class:`Button`, :class:`Label`, and so on) + derive from :class:`!Widget`. + + +Toplevel widgets +^^^^^^^^^^^^^^^^ + +.. class:: Tk(screenName=None, baseName=None, className='Tk', useTk=True, sync=False, use=None) + + Construct a toplevel Tk widget, which is usually the main window of an + application, and initialize a Tcl interpreter for this widget. Each + instance has its own associated Tcl interpreter. + Inherits from :class:`Misc` and :class:`Wm`. + + To create a Tcl interpreter without initializing the Tk subsystem, use the + :func:`Tcl` factory function instead. + + The :class:`Tk` class is typically instantiated using all default values. + However, the following keyword arguments are currently recognized: + + *screenName* + When given (as a string), sets the :envvar:`DISPLAY` environment + variable. (X11 only) + *baseName* + Name of the profile file. By default, *baseName* is derived from the + program name (``sys.argv[0]``). + *className* + Name of the widget class. Used as a profile file and also as the name + with which Tcl is invoked (*argv0* in *interp*). + *useTk* + If ``True``, initialize the Tk subsystem. The :func:`tkinter.Tcl() ` + function sets this to ``False``. + *sync* + If ``True``, execute all X server commands synchronously, so that errors + are reported immediately. Can be used for debugging. (X11 only) + *use* + Specifies the *id* of the window in which to embed the application, + instead of it being created as an independent toplevel window. *id* must + be specified in the same way as the value for the -use option for + toplevel widgets (that is, it has a form like that returned by + :meth:`~Misc.winfo_id`). + + Note that on some platforms this will only work correctly if *id* refers + to a Tk frame or toplevel that has its -container option enabled. + + :class:`Tk` reads and interprets profile files, named + :file:`.{className}.tcl` and :file:`.{baseName}.tcl`, into the Tcl + interpreter and calls :func:`exec` on the contents of + :file:`.{className}.py` and :file:`.{baseName}.py`. The path for the + profile files is the :envvar:`HOME` environment variable or, if that + isn't defined, then :data:`os.curdir`. + + .. note:: + + On Windows, creating a Tcl interpreter (by instantiating :class:`Tk` or + calling :func:`Tcl`) sets the :envvar:`HOME` environment variable for + the process, if it is not already set, to ``%HOMEDRIVE%%HOMEPATH%`` (or + :envvar:`USERPROFILE`, or ``c:\``). This is done by Tcl and can affect + other code that reads :envvar:`HOME`. + + .. attribute:: tk + + The Tk application object created by instantiating :class:`Tk`. This + provides access to the Tcl interpreter. Each widget that is attached + the same instance of :class:`Tk` has the same value for its :attr:`tk` + attribute. + + .. attribute:: master + + The widget object that contains this widget. + For :class:`Tk`, the :attr:`!master` is :const:`None` because it is the + main window. + The terms *master* and *parent* are similar and sometimes used + interchangeably as argument names; however, calling + :meth:`~Misc.winfo_parent` returns a string of the widget name whereas + :attr:`!master` returns the object. + *parent*/*child* reflects the tree-like relationship while *master* (or + *container*)/*content* reflects the container structure. + + .. attribute:: children + + The immediate descendants of this widget as a :class:`dict` with the + child widget names as the keys and the child instance objects as the + values. + + .. method:: destroy() + + Destroy this and all descendant widgets and, for the main window, end the + connection to the underlying Tcl interpreter. + + .. method:: loadtk() + + Finish loading and initializing the Tk subsystem. + This is needed only when the interpreter was created without Tk (for + example through :func:`Tcl`); it is called automatically when *useTk* is + true. + + .. method:: readprofile(baseName, className) + + Read and source the user's profile files :file:`.{className}.tcl` and + :file:`.{baseName}.tcl` into the Tcl interpreter, and execute the + corresponding :file:`.{className}.py` and :file:`.{baseName}.py` files. + This is called during initialization; see the description of the + constructor above. + + .. method:: report_callback_exception(exc, val, tb) + + Report a callback exception. + This is called when an exception propagates out of a Tkinter callback; + *exc*, *val* and *tb* are the exception type, value and traceback as + returned by :func:`sys.exc_info`. + The default implementation prints a traceback to :data:`sys.stderr`. + It can be overridden to customize error handling, for example to display + the traceback in a dialog. + + +.. class:: Toplevel(master=None, cnf={}, **kw) + + A :class:`!Toplevel` widget is a top-level window, similar to a + :class:`Frame` except that its X parent is the root window of a screen + rather than its logical parent. + Its primary purpose is to serve as a container for dialog boxes and other + collections of widgets; its only visible features are its background and an + optional 3-D border. + Notable options include *menu*, which installs a :class:`Menu` as the + window's menubar. + Inherits from :class:`BaseWidget` and :class:`Wm`, so a toplevel is managed + by the window manager. + Refer to the Tk ``toplevel`` manual page for the full list of options. + + +Widget classes +^^^^^^^^^^^^^^ + +.. class:: Button(master=None, cnf={}, **kw) + + A :class:`!Button` widget displays a textual string, bitmap or image and + invokes a command when the user presses it (by clicking mouse button 1 over + the button or, when the button has focus, by pressing the space key). + Inherits from :class:`Widget`. + In addition to the standard widget options, a button accepts the options + documented in the Tk ``button`` manual page, such as *command* (the callback + invoked when the button is pressed), *textvariable*, *state* and *default*. + + .. method:: invoke() + + Invoke the command associated with the button, if there is one, and + return its result, or an empty string if no command is associated with + the button. + This is ignored if the button's state is ``disabled``. + + .. method:: flash() + + Flash the button by redisplaying it several times, alternating between + the active and normal colors. + At the end of the flash the button is left in the same normal or active + state as when the method was called. + This is ignored if the button's state is ``disabled``. + + +.. class:: Canvas(master=None, cnf={}, **kw) + + A :class:`!Canvas` widget implements structured graphics. + It displays any number of *items*, such as arcs, lines, ovals, polygons, + rectangles, text, bitmaps, images and embedded windows, which may be drawn, + moved, re-colored and bound to events. + Inherits from :class:`Widget`, :class:`XView` and :class:`YView`, so the + view can be scrolled horizontally and vertically with :meth:`~XView.xview` + and :meth:`~YView.yview`. + Refer to the Tk ``canvas`` manual page for the full list of widget and item + options. + + Each item has a unique integer *id*, assigned when it is created, and zero + or more string *tags*. + A tag is an arbitrary string that does not have the form of an integer; the + same tag may be shared by many items, which makes tags convenient for + grouping items. + The special tag ``'all'`` matches every item in the canvas, and + ``'current'`` matches the topmost item under the mouse pointer. + Most methods take a *tagOrId* argument that may be an integer id naming a + single item, or a tag naming zero or more items; as described in the Tk + ``canvas`` manual page, a tag may also be a logical expression of tags + combined with the operators ``&&``, ``||``, ``^``, ``!`` and parentheses. + When a method that operates on a single item is given a *tagOrId* matching + several items, it normally uses the lowest matching item in the display + list. + + The items are kept in a *display list* that determines drawing order: items + later in the list are drawn on top of earlier ones. + A newly created item is placed at the top of the list; the order can be + changed with :meth:`tag_raise` and :meth:`tag_lower`. + + .. method:: create_arc(*args, **kw) + create_bitmap(*args, **kw) + create_image(*args, **kw) + create_line(*args, **kw) + create_oval(*args, **kw) + create_polygon(*args, **kw) + create_rectangle(*args, **kw) + create_text(*args, **kw) + create_window(*args, **kw) + + Create a new item of the corresponding type and return its integer id. + Each method is called as ``create_TYPE(coord..., **options)``: the + leading positional arguments give the coordinates that define the item + (as separate numbers, as a single sequence of numbers, or as coordinate + pairs), and the keyword arguments set item-specific options. + Coordinates and screen distances may be given as numbers (interpreted as + pixels) or as strings with a unit suffix (``'m'``, ``'c'``, ``'i'`` or + ``'p'`` for millimetres, centimetres, inches or printer's points), but + are always stored and returned in pixels. + + The item types are: ``arc`` (an arc-shaped region that is a section of an + oval, defined by two diagonally opposite corners ``x1, y1, x2, y2`` of + the enclosing rectangle); ``bitmap`` (a two-color bitmap positioned at a + point ``x, y``); ``image`` (a Tk image positioned at a point ``x, y``); + ``line`` (a line or curve through the points ``x1, y1, ..., xn, yn``); + ``oval`` (a circle or ellipse inscribed in the rectangle + ``x1, y1, x2, y2``); ``polygon`` (a closed polygon through the points + ``x1, y1, ..., xn, yn``); ``rectangle`` (a rectangle with corners + ``x1, y1, x2, y2``); ``text`` (a string of text positioned at a point + ``x, y``); and ``window`` (a child widget embedded in the canvas at a + point ``x, y``, specified with the *window* option). + + Most item types accept a common set of *standard item options*, plus a + few options specific to each type. + Option names are passed as keyword arguments, without the leading + hyphen. + + The standard item options are: + + *fill* + The color used to fill the item's interior, or to draw a *line* + item or the characters of a *text* item. + An empty string (the default for all types except *line* and *text*) + leaves the item unfilled. + + *outline* + The color used to draw the item's outline. + An empty string draws no outline. + + *width* + The width of the outline, defaulting to ``1.0``. + Has no effect if *outline* is empty. + + *dash* + A dash pattern for the outline, given either as a sequence of + segment lengths in pixels or as a string of the characters + ``'.'``, ``','``, ``'-'``, ``'_'`` and space. + An empty pattern (the default) draws a solid outline. + + *dashoffset* + The starting offset in pixels into the *dash* pattern. + Ignored if there is no *dash* pattern. + + *stipple* + A bitmap used as a stipple pattern when filling the item. + Only well supported on X11. + + *outlinestipple* + A bitmap used as a stipple pattern when drawing the outline. + Has no effect if *outline* is empty. + + *offset*, *outlineoffset* + The offset of the fill and outline stipple patterns, given as + ``'x,y'`` or as a side such as ``'n'``, ``'se'`` or ``'center'``. + Stipple offsets are only supported on X11. + + *state* + Overrides the canvas state for this item; one of ``'normal'``, + ``'disabled'`` or ``'hidden'``. + + *tags* + A single tag or a sequence of tags to associate with the item, + replacing any existing tags. + + Many of these options have *active...* and *disabled...* variants + (such as *activefill*, *disabledfill*, *activewidth*, *disableddash*, + *activeoutline*, *disabledstipple*) that override the base option when + the item is the active item (under the mouse pointer) or is in the + disabled state. + + The following item types support additional options. + + For ``arc`` items: + + *start* + The start of the arc's angular range, in degrees measured + counter-clockwise from the 3-o'clock position. + + *extent* + The size of the angular range, in degrees counter-clockwise from + *start*. + + *style* + How the arc is drawn: ``'pieslice'`` (the default), ``'chord'`` or + ``'arc'``. + + For ``line`` items: + + *arrow* + Where to draw arrowheads: ``'none'`` (the default), ``'first'``, + ``'last'`` or ``'both'``. + + *arrowshape* + A sequence of three distances describing the shape of the + arrowheads. + + *capstyle* + How line ends are drawn: ``'butt'`` (the default), ``'projecting'`` + or ``'round'``. + + *joinstyle* + How line vertices are drawn: ``'round'`` (the default), ``'bevel'`` + or ``'miter'``. + + *smooth* + The smoothing method: a false value (the default) for no smoothing, + or ``'true'``/``'bezier'`` or ``'raw'`` to draw the line as a curve. + + *splinesteps* + The number of line segments approximating each spline when + *smooth* is enabled. + + For ``polygon`` items: + + *joinstyle*, *smooth*, *splinesteps* + As for ``line`` items, applied to the polygon's outline. + + For ``text`` items: + + *text* + The string to display; newline characters start new lines. + + *font* + The font used for the text. + + *justify* + How lines are justified: ``'left'`` (the default), ``'right'`` or + ``'center'``. + + *anchor* + How the text is positioned relative to its point, defaulting to + ``'center'``. + + *width* + The maximum line length; if non-zero, lines are wrapped at spaces. + + *angle* + How many degrees to rotate the text counter-clockwise about its + positioning point, from ``0.0`` to ``360.0`` (default ``0.0``). + + *underline* + The index of a character to underline, or ``-1`` for none. + + For ``bitmap`` items: + + *bitmap* + The bitmap to display. + + *anchor* + How the bitmap is positioned relative to its point. + + *background*, *foreground* + The colors used for the bitmap's ``0`` and ``1`` pixels; an empty + *background* makes the ``0`` pixels transparent. + Both have *active...* and *disabled...* variants, and *bitmap* has + *activebitmap* and *disabledbitmap* variants. + + For ``image`` items: + + *image* + The Tk image to display, previously created with the image + protocols. + + *anchor* + How the image is positioned relative to its point. + + Both options have *active...* and *disabled...* variants + (*activeimage*, *disabledimage*) used in the active and disabled + states. + + For ``window`` items: + + *window* + The widget to embed; it must be a child of the canvas or of one of + its ancestors, and may not be a top-level window. + + *anchor* + How the window is positioned relative to its point. + + *width*, *height* + The size to assign to the window; if zero (the default), the window + is given its requested size. + + ``oval`` and ``rectangle`` items have no type-specific options; they + use only the standard item options. + + .. note:: + + Tk 8.6 added the *angle* option and Tk 9.0 added the *underline* + option for ``text`` items. + + .. method:: coords(tagOrId) + coords(tagOrId, coordList, /) + coords(tagOrId, /, *coordList) + + Query or modify the coordinates of an item. + With only *tagOrId*, return a list of the floating-point coordinates of + the item given by *tagOrId* (the first matching item if it matches + several). + Given new coordinates, replace the coordinates of that item with them; + like the ``create_*`` methods, the coordinates may be given as separate + numbers, as a single sequence, or as coordinate pairs. + The returned coordinates are always in pixels, regardless of the units + used to specify them; for rectangles, ovals and arcs they are ordered + left, top, right, bottom. + + .. versionchanged:: 3.12 + The arguments are now flattened: the coordinates may be given as + separate arguments, as a single sequence, or grouped in pairs, like + the ``create_*`` methods. + + + .. method:: move(tagOrId, xAmount, yAmount, /) + + Move each of the items given by *tagOrId* in the canvas coordinate space + by adding *xAmount* to every x-coordinate and *yAmount* to every + y-coordinate of the item. + + .. method:: moveto(tagOrId, x='', y='') + + Move the items given by *tagOrId* so that the first coordinate pair (the + upper-left corner of the bounding box) of the lowest matching item is at + position (*x*, *y*). + *x* or *y* may be an empty string, in which case the corresponding + coordinate is unchanged. + All matching items keep their positions relative to each other. + + .. versionadded:: 3.8 + + + .. method:: scale(tagOrId, xOrigin, yOrigin, xScale, yScale, /) + + Rescale the coordinates of all items given by *tagOrId* in canvas + coordinate space. + Each x-coordinate is adjusted so that its distance from *xOrigin* changes + by a factor of *xScale*, and each y-coordinate so that its distance from + *yOrigin* changes by a factor of *yScale* (a factor of ``1.0`` leaves the + coordinate unchanged). + + .. method:: delete(*tagOrIds) + + Delete each of the items given by the *tagOrIds* arguments. + + .. method:: dchars(tagOrId, first, /) + dchars(tagOrId, first, last, /) + + Delete from each of the items given by *tagOrId* the characters (for text + items) or coordinates (for line and polygon items) in the range from + *first* to *last* inclusive; *last* defaults to *first*. + Items that do not support indexing ignore this operation. + + .. method:: insert(tagOrId, beforeThis, string, /) + + Insert *string* into each of the items given by *tagOrId* just before the + character or coordinate whose index is *beforeThis*. + For line and polygon items *string* must be a valid sequence of + coordinates. + + .. method:: itemcget(tagOrId, option) + + Return the current value of the configuration option *option* for the + item given by *tagOrId* (the lowest matching item if it matches several). + This is like :meth:`~Misc.cget` but applies to an individual item. + + .. method:: itemconfig(tagOrId, cnf=None, **kw) + :no-typesetting: + + .. method:: itemconfigure(tagOrId, cnf=None, **kw) + + Query or modify the configuration options of the items given by + *tagOrId*. + This mirrors :meth:`~Misc.configure`, except that it applies to + individual items rather than to the canvas as a whole. + With no options, it returns a dictionary describing the current options + of the first matching item; otherwise it sets the given options on every + matching item. + The legal options are those accepted by the corresponding ``create_*`` + method. + :meth:`itemconfig` is an alias of :meth:`!itemconfigure`. + + .. method:: type(tagOrId) + + Return the type of the item given by *tagOrId* (the first matching item + if it matches several), such as ``'rectangle'`` or ``'text'``, or + ``None`` if *tagOrId* does not match any item. + + .. method:: gettags(tagOrId, /) + + Return a tuple of the tags associated with the item given by *tagOrId* + (the first matching item in display-list order if it matches several). + Return an empty tuple if no item matches or the item has no tags. + + .. method:: dtag(tagOrId, /) + dtag(tagOrId, tagToDelete, /) + + Remove the tag *tagToDelete* (which defaults to *tagOrId*) from each of + the items given by *tagOrId*. + Items that do not have that tag are unaffected. + + .. method:: addtag(newtag, searchSpec, /, *args) + + Add the tag *newtag* to each item selected by the search specification + *searchSpec* (and any further *args*). + *searchSpec* is one of ``'above'``, ``'all'``, ``'below'``, + ``'closest'``, ``'enclosed'``, ``'overlapping'`` or ``'withtag'``; the + ``addtag_*`` methods below are convenient wrappers that supply each of + these forms. + + .. method:: addtag_above(newtag, tagOrId) + + Add the tag *newtag* to the item just above (after) *tagOrId* in the + display list. + + .. method:: addtag_all(newtag) + + Add the tag *newtag* to all items in the canvas. + + .. method:: addtag_below(newtag, tagOrId) + + Add the tag *newtag* to the item just below (before) *tagOrId* in the + display list. + + .. method:: addtag_closest(newtag, x, y, halo=None, start=None) + + Add the tag *newtag* to the item closest to the point (*x*, *y*). + If *halo* is given, any item within that distance of the point is treated + as overlapping it. + If *start* is given (a tag or id), select the topmost closest item that + lies below *start* in the display list, which can be used to step through + all the closest items. + + .. method:: addtag_enclosed(newtag, x1, y1, x2, y2) + + Add the tag *newtag* to every item completely enclosed within the + rectangle (*x1*, *y1*, *x2*, *y2*), where *x1* <= *x2* and *y1* <= *y2*. + + .. method:: addtag_overlapping(newtag, x1, y1, x2, y2) + + Add the tag *newtag* to every item that overlaps or is enclosed within + the rectangle (*x1*, *y1*, *x2*, *y2*), where *x1* <= *x2* and *y1* <= + *y2*. + + .. method:: addtag_withtag(newtag, tagOrId) + + Add the tag *newtag* to every item given by *tagOrId*. + + .. method:: find(searchSpec, /, *args) + + Return a tuple of the ids of all items selected by the search + specification *searchSpec* (and any further *args*), in stacking order + with the lowest item first. + The search specification has any of the forms accepted by :meth:`addtag`. + The ``find_*`` methods below are more convenient wrappers around it. + + .. method:: find_above(tagOrId) + + Return a tuple containing the id of the item just above *tagOrId* in the + display list. + + .. method:: find_all() + + Return a tuple of the ids of all items in the canvas, in stacking order. + + .. method:: find_below(tagOrId) + + Return a tuple containing the id of the item just below *tagOrId* in the + display list. + + .. method:: find_closest(x, y, halo=None, start=None) + + Return a tuple containing the id of the item closest to the point (*x*, + *y*). + *halo* and *start* are interpreted as for :meth:`addtag_closest`. + + .. method:: find_enclosed(x1, y1, x2, y2) + + Return a tuple of the ids of all items completely enclosed within the + rectangle (*x1*, *y1*, *x2*, *y2*). + + .. method:: find_overlapping(x1, y1, x2, y2) + + Return a tuple of the ids of all items that overlap or are enclosed + within the rectangle (*x1*, *y1*, *x2*, *y2*). + + .. method:: find_withtag(tagOrId) + + Return a tuple of the ids of all items given by *tagOrId*. + + .. method:: lift(tagOrId, aboveThis=None, /) + :no-typesetting: + + .. method:: tkraise(tagOrId, aboveThis=None, /) + :no-typesetting: + + .. method:: tag_raise(tagOrId, aboveThis=None, /) + + Move all items given by *tagOrId* to a new position in the display list + just above the item given by *aboveThis*, or to the top of the display + list if *aboveThis* is omitted. + When several items are moved their relative order is preserved. + This has no effect on embedded window items, whose stacking order is + controlled by :meth:`Misc.tkraise` and :meth:`Misc.lower` instead. + :meth:`lift` and :meth:`tkraise` are aliases of :meth:`!tag_raise`. + + .. method:: lower(tagOrId, belowThis=None, /) + :no-typesetting: + + .. method:: tag_lower(tagOrId, belowThis=None, /) + + Move all items given by *tagOrId* to a new position in the display list + just below the item given by *belowThis*, or to the bottom of the display + list if *belowThis* is omitted. + When several items are moved their relative order is preserved. + This has no effect on embedded window items. + :meth:`lower` is an alias of :meth:`!tag_lower`. + + .. note:: + + On a :class:`Canvas`, :meth:`tkraise`/:meth:`lift` and :meth:`lower` + restack canvas items, + shadowing the inherited :meth:`Misc.tkraise`/:meth:`Misc.lift` and + :meth:`Misc.lower` methods that restack the widget itself, + which are therefore not available. + + .. method:: tag_bind(tagOrId, sequence=None, func=None, add=None) + + Bind the callback *func* to the event *sequence* for all items given by + *tagOrId*, so that *func* is invoked whenever that event occurs for one + of the items. + This is like :meth:`Widget.bind ` but operates on canvas items + rather than on whole widgets; only mouse, keyboard and virtual events may + be bound. + Mouse events are directed to the current item and keyboard events to the + focus item (see :meth:`focus`). + If *add* is true the new binding is added to any existing bindings for + the same sequence, rather than replacing them. + Return the identifier of the bound function, which can be passed to + :meth:`tag_unbind`. + + .. method:: tag_unbind(tagOrId, sequence, funcid=None) + + Remove for all items given by *tagOrId* the binding for the event + *sequence*. + If *funcid* is given, only that callback (as returned by + :meth:`tag_bind`) is unbound and deregistered. + + .. versionchanged:: 3.13 + If *funcid* is given, only that callback is unbound. + + + .. method:: bbox(tagOrId, /, *tagOrIds) + + Return a 4-tuple ``(x1, y1, x2, y2)`` giving an approximate bounding box, + in pixels, that encloses all the items given by *tagOrId* and any further + *tagOrIds*. + The result may overestimate the true bounding box by a few pixels. + Return ``None`` if no item matches or the matching items have nothing to + display. + + This shadows the inherited :meth:`!Misc.bbox`; + use :meth:`~Misc.grid_bbox` for the grid bounding box. + + .. method:: canvasx(screenx, gridspacing=None) + + Given a window x-coordinate *screenx*, return the canvas x-coordinate + displayed at that location. + If *gridspacing* is given, the result is rounded to the nearest multiple + of *gridspacing* units. + + .. method:: canvasy(screeny, gridspacing=None) + + Given a window y-coordinate *screeny*, return the canvas y-coordinate + displayed at that location. + If *gridspacing* is given, the result is rounded to the nearest multiple + of *gridspacing* units. + + .. method:: focus() + focus(tagOrId, /) + + With *tagOrId*, set the keyboard focus for the canvas to the first item + given by *tagOrId* that supports the insertion cursor; the focus is left + unchanged if no such item exists. + If *tagOrId* is an empty string, reset the focus so that no item has it. + With no argument, return the id of the item that currently has the focus, + or an empty string if none does. + An item only displays the insertion cursor when both it is the focus item + and its canvas has the input focus. + + This shadows the inherited :meth:`!Misc.focus`; + use :meth:`~Misc.focus_set` to focus the widget itself. + + .. method:: icursor(tagOrId, index, /) + + Set the insertion cursor of the items given by *tagOrId* to just before + the character given by *index*. + Items that do not support an insertion cursor are unaffected. + The cursor is only displayed when the item has the focus, but its + position may be set at any time. + + .. method:: index(tagOrId, index, /) + + Return as an integer the numerical index within *tagOrId* corresponding + to *index*, which is a textual description of a position (for text items + an index into the characters, for line and polygon items an index into + the coordinates). + If *tagOrId* matches several items, the first one that supports indexing + is used. + + .. method:: select_adjust(tagOrId, index) + + Adjust the end of the selection in *tagOrId* nearest to *index* so that + it is at *index*, and make the other end the anchor point for future + :meth:`select_to` calls. + If the selection is not currently in *tagOrId*, this behaves like + :meth:`select_to`. + + .. method:: select_clear() + + Clear the selection if it is in this canvas; otherwise do nothing. + + .. method:: select_from(tagOrId, index) + + Set the selection anchor point to just before the character given by + *index* in the item given by *tagOrId*. + This does not change the selection itself; it sets the fixed end for + future :meth:`select_to` calls. + + .. method:: select_item() + + Return the id of the item that holds the selection, or ``None`` if the + selection is not in this canvas. + Unlike :meth:`find` and the ``find_*`` methods, this returns the id as a + string rather than an integer. + + .. method:: select_to(tagOrId, index) + + Set the selection to the characters of *tagOrId* between the selection + anchor point and *index*, inclusive of *index*. + The anchor point is the one set by the most recent :meth:`select_adjust` + or :meth:`select_from` call. + + .. method:: scan_mark(x, y) + + Record *x*, *y* and the current view, for use with later + :meth:`scan_dragto` calls. + This is typically bound to a mouse button press in the widget. + + .. method:: scan_dragto(x, y, gain=10) + + Scroll the canvas by *gain* times the difference between *x*, *y* and the + coordinates passed to the last :meth:`scan_mark` call. + This is typically bound to mouse motion events in the widget, producing + the effect of dragging the canvas at high speed through its window. + + .. method:: postscript(cnf={}, **kw) + + Generate a PostScript (Encapsulated PostScript, version 3.0) + representation of part or all of the canvas. + If the *file* or *channel* option is given, the PostScript is written + there and an empty string is returned; otherwise it is returned as a + string. + By default only the area currently visible in the window is generated, so + it is usually necessary either to call :meth:`~Misc.update` first or to + use the *width* and *height* options. + Supported options include *colormap*, *colormode*, *file*, *fontmap*, + *height*, *pageanchor*, *pageheight*, *pagewidth*, *pagex*, *pagey*, + *rotate*, *width*, *x* and *y*. + + +.. class:: Checkbutton(master=None, cnf={}, **kw) + + A :class:`!Checkbutton` widget displays a textual string, bitmap or image + together with a square indicator, and toggles a boolean selection when + pressed. + It has all the behavior of a simple button and, in addition, can be + selected: when selected the indicator is drawn with a check mark and the + associated variable is set to the ``onvalue``, and when deselected the + indicator is drawn empty and the variable is set to the ``offvalue``. + Inherits from :class:`Widget`. + In addition to the standard widget options, a checkbutton accepts the + options documented in the Tk ``checkbutton`` manual page, such as + *variable*, *onvalue*, *offvalue* and *command*. + + .. method:: invoke() + + Do just what would happen if the user pressed the checkbutton with the + mouse: toggle the selection state of the button and invoke the associated + command, if there is one. + Return the result of the command, or an empty string if no command is + associated with the checkbutton. + This is ignored if the checkbutton's state is ``disabled``. + + .. method:: select() + + Select the checkbutton and set the associated variable to its + ``onvalue``. + + .. method:: deselect() + + Deselect the checkbutton and set the associated variable to its + ``offvalue``. + + .. method:: toggle() + + Toggle the selection state of the button, redisplaying it and modifying + its associated variable to reflect the new state. + + .. method:: flash() + + Flash the checkbutton by redisplaying it several times, alternating + between the active and normal colors. + At the end of the flash the checkbutton is left in the same normal or + active state as when the method was called. + This is ignored if the checkbutton's state is ``disabled``. + + +.. class:: Entry(master=None, cnf={}, **kw) + + An :class:`!Entry` widget displays a single line of text and lets the user + edit it. + Inherits from :class:`Widget` and :class:`XView`; since entries can hold + strings too long to fit in the window, they support horizontal scrolling + through :meth:`~XView.xview`. + + In addition to the standard widget options, an entry accepts the options + documented in the Tk ``entry`` manual page. + Notable ones are *textvariable* (the name of a variable kept in sync with + the entry's contents), *show* (if set, each character is displayed as the + given character rather than its true value, useful for password entry), + *validate* and *validatecommand* (which together let a callback accept or + reject edits), and *state* (one of ``'normal'``, ``'disabled'`` or + ``'readonly'``). + + Many of the methods below take an *index* argument that selects a character + in the entry's string. + As described in the Tk ``entry`` manual page, *index* may be a number + (counting from 0), ``'insert'`` (the character just after the insertion + cursor), ``'end'`` (just after the last character), ``'anchor'`` (the + selection anchor point), ``'sel.first'`` and ``'sel.last'`` (the ends of the + selection), or ``@x`` (the character covering pixel x-coordinate *x* in the + window). + Out-of-range indices are rounded to the nearest legal value. + + .. method:: delete(first, last=None) + + Delete the characters from index *first* up to but not including index + *last*. + If *last* is omitted, only the single character at *first* is deleted. + + .. method:: get() + + Return the entry's current string. + + .. method:: insert(index, string) + + Insert *string* just before the character given by *index*. + + .. method:: icursor(index) + + Arrange for the insertion cursor to be displayed just before the + character given by *index*. + + .. method:: index(index) + + Return the numerical index corresponding to *index*. + + .. method:: select_adjust(index) + :no-typesetting: + + .. method:: selection_adjust(index) + + Locate the end of the selection nearest to the character given by + *index*, and adjust that end to be at *index* (including but not going + beyond it); the other end becomes the anchor point for future + :meth:`selection_to` calls. + If there is no selection in the entry, a new one is created between + *index* and the most recent anchor point, inclusive. + :meth:`select_adjust` is an alias of :meth:`!selection_adjust`. + + .. method:: select_clear() + :no-typesetting: + + .. method:: selection_clear() + + Clear the selection if it is currently in this widget. + If the selection is not in this widget the method has no effect. + :meth:`select_clear` is an alias of :meth:`!selection_clear`. + + .. note:: + + This shadows the inherited :meth:`Misc.selection_clear`, + which clears the X selection; + that method is not available on an :class:`Entry`. + + .. method:: select_from(index) + :no-typesetting: + + .. method:: selection_from(index) + + Set the selection anchor point to just before the character given by + *index*, without changing the selection. + :meth:`select_from` is an alias of :meth:`!selection_from`. + + .. method:: select_present() + :no-typesetting: + + .. method:: selection_present() + + Return ``True`` if there are characters selected in the entry, ``False`` + otherwise. + :meth:`select_present` is an alias of :meth:`!selection_present`. + + .. method:: select_range(start, end) + :no-typesetting: + + .. method:: selection_range(start, end) + + Set the selection to include the characters starting with the one indexed + by *start* and ending with the one just before *end*. + If *end* refers to the same character as *start* or an earlier one, the + selection is cleared. + :meth:`select_range` is an alias of :meth:`!selection_range`. + + .. method:: select_to(index) + :no-typesetting: + + .. method:: selection_to(index) + + Set the selection between the anchor point and *index*: if *index* is + before the anchor point, the selection runs from *index* up to but not + including the anchor; if *index* is after it, from the anchor up to but + not including *index*; if they coincide, nothing happens. + The anchor point is the one set by the most recent :meth:`selection_from` + or :meth:`selection_adjust` call. + If there is no selection in the entry, a new one is created using the + most recent anchor point. + :meth:`select_to` is an alias of :meth:`!selection_to`. + + .. method:: scan_mark(x) + + Record *x* and the current view in the entry window, for use with later + :meth:`scan_dragto` calls. + Typically associated with a mouse button press in the widget. + + .. method:: scan_dragto(x) + + Compute the difference between *x* and the *x* given to the last + :meth:`scan_mark` call, and adjust the view left or right by 10 times + that difference. + Typically associated with mouse motion events, to produce the effect of + dragging the entry at high speed through the window. + + +.. class:: Frame(master=None, cnf={}, **kw) + + A :class:`!Frame` widget is a simple container. + Its primary purpose is to act as a spacer or container for complex window + layouts; its only features are its background and an optional 3-D border to + make the frame appear raised or sunken. + Inherits from :class:`Widget`. + Refer to the Tk ``frame`` manual page for the full list of options. + + +.. class:: Label(master=None, cnf={}, **kw) + + A :class:`!Label` widget displays a non-interactive textual string, bitmap + or image. + The displayed text is set with the *text* option or linked to a variable + through *textvariable*, and an image can be shown using the *image* option. + Text must all be in a single font but may occupy multiple lines, and one + character may be underlined with the *underline* option. + Inherits from :class:`Widget`. + Refer to the Tk ``label`` manual page for the full list of options. + + +.. class:: LabelFrame(master=None, cnf={}, **kw) + + A :class:`!LabelFrame` widget is a container that has the features of a + :class:`Frame` plus the ability to display a label. + The label text is set with the *text* option and positioned with + *labelanchor*, or an arbitrary widget may be used as the label by giving it + as the *labelwidget* option. + Inherits from :class:`Widget`. + Refer to the Tk ``labelframe`` manual page for the full list of options. + + +.. class:: Listbox(master=None, cnf={}, **kw) + + A :class:`!Listbox` widget displays a list of single-line text items, one + per line, of which the user can select one or more. + The way the selection behaves is governed by the *selectmode* option, which + is one of ``browse`` (the default; at most one item, which may be dragged + with the mouse), ``single`` (at most one item), ``multiple`` (any number of + items, toggled individually), or ``extended`` (any number of items, + including discontiguous ranges, selected by clicking and dragging). + Inherits from :class:`Widget`, :class:`XView` and :class:`YView`, so the + view can be scrolled horizontally and vertically with :meth:`~XView.xview` + and :meth:`~YView.yview`. + Refer to the Tk ``listbox`` manual page for the full list of options. + + Many of the methods take an *index* argument identifying a particular item. + As described in the Tk ``listbox`` manual page, *index* may be a numeric + index (counting from 0 at the top), ``'active'`` (the item with the location + cursor, set with :meth:`activate`), ``'anchor'`` (the selection anchor, set + with :meth:`selection_anchor`), ``'end'`` (the last item, or for + :meth:`index` and :meth:`insert` the position just after it), or ``@x,y`` + (the item covering pixel coordinates *x*, *y* in the listbox window). + Arguments named *first* and *last* are indices of the same forms. + + .. method:: insert(index, *elements) + + Insert the given *elements* as new items just before the item given by + *index*. + If *index* is ``'end'``, the new items are appended to the end of the + list. + + .. method:: delete(first, last=None) + + Delete the items in the range from *first* to *last* inclusive. + If *last* is omitted, it defaults to *first*, so that a single item is + deleted. + + .. method:: get(first, last=None) + + If *last* is omitted, return the contents of the item given by *first*, + or an empty string if *first* refers to a non-existent item. + If *last* is given, return a tuple of all the items in the range from + *first* to *last* inclusive. + + .. method:: size() + + Return the total number of items in the listbox. + + This shadows the inherited :meth:`!Misc.size`; + use :meth:`~Misc.grid_size` for the grid size. + + .. method:: index(index) + + Return the integer index value corresponding to *index*, or ``None`` if + *index* is out of range. + If *index* is ``'end'``, the result is a count of the number of items in + the listbox (not the index of the last item). + + .. method:: bbox(index) + + Return a tuple ``(x, y, width, height)`` describing the bounding box, in + pixels relative to the widget, of the text of the item given by *index*. + Return ``None`` if no part of that item is visible on the screen, or if + *index* refers to a non-existent item; if the item is only partly + visible, the result still gives the full area of the item, including the + parts that are not visible. + + This shadows the inherited :meth:`!Misc.bbox`; + use :meth:`~Misc.grid_bbox` for the grid bounding box. + + .. method:: nearest(y) + + Given a y-coordinate within the listbox window, return the index of the + visible item nearest to that y-coordinate. + + .. method:: see(index) + + Adjust the view so that the item given by *index* is visible. + If the item is already visible the method has no effect; if it is near an + edge of the window the listbox scrolls just enough to bring it into view + at that edge, otherwise the listbox scrolls to center the item. + + .. method:: activate(index) + + Set the active item to the one given by *index*. + If *index* is outside the range of items, the closest item is activated + instead. + The active item is drawn as specified by the *activestyle* option when + the widget has the input focus, and its index may be retrieved with the + ``'active'`` index. + + .. method:: curselection() + + Return a tuple containing the numerical indices of all of the items that + are currently selected, or an empty tuple if no items are selected. + + .. method:: select_anchor(index) + :no-typesetting: + + .. method:: selection_anchor(index) + + Set the selection anchor to the item given by *index*. + If *index* refers to a non-existent item, the closest item is used. + The selection anchor is the end of the selection that is fixed while + dragging out a selection with the mouse, and may afterwards be referred + to with the ``'anchor'`` index. + :meth:`select_anchor` is an alias of :meth:`!selection_anchor`. + + .. method:: select_clear(first, last=None) + :no-typesetting: + + .. method:: selection_clear(first, last=None) + + Deselect any of the items in the range from *first* to *last* inclusive + that are selected. + The selection state of items outside this range is not changed. + :meth:`select_clear` is an alias of :meth:`!selection_clear`. + + .. note:: + + This shadows the inherited :meth:`Misc.selection_clear`, + which clears the X selection; + that method is not available on a :class:`Listbox`. + + .. method:: select_includes(index) + :no-typesetting: + + .. method:: selection_includes(index) + + Return ``True`` if the item given by *index* is currently selected, + ``False`` otherwise. + :meth:`select_includes` is an alias of :meth:`!selection_includes`. + + .. method:: select_set(first, last=None) + :no-typesetting: + + .. method:: selection_set(first, last=None) + + Select all of the items in the range from *first* to *last* inclusive, + without affecting the selection state of items outside that range. + :meth:`select_set` is an alias of :meth:`!selection_set`. + + .. method:: itemcget(index, option) + + Return the current value of the configuration option *option* for the + item given by *index*. + + .. method:: itemconfig(index, cnf=None, **kw) + :no-typesetting: + + .. method:: itemconfigure(index, cnf=None, **kw) + + Query or modify the configuration options of the item given by *index*. + This mirrors :meth:`~Misc.configure`, except that it applies to an + individual item rather than to the listbox as a whole. + With no options, it returns a dictionary describing the current options + of the item; otherwise it sets the given options. + The supported item options are *background*, *foreground*, + *selectbackground* and *selectforeground*. + :meth:`itemconfig` is an alias of :meth:`!itemconfigure`. + + .. method:: scan_mark(x, y) + + Record *x*, *y* and the current view, for use with later + :meth:`scan_dragto` calls. + This is typically bound to a mouse button press in the widget. + + .. method:: scan_dragto(x, y) + + Scroll the listbox by 10 times the difference between *x*, *y* and the + coordinates passed to the last :meth:`scan_mark` call. + This is typically bound to mouse motion events in the widget, producing + the effect of dragging the list at high speed through the window. + + +.. class:: Menu(master=None, cnf={}, **kw) + + A :class:`!Menu` widget displays a column of entries, each of which may be a + command, a checkbutton, a radiobutton, a cascade (which posts an associated + submenu) or a separator. + Menus are used as the menubar of a toplevel window, as pulldown menus posted + from a cascade entry or menubutton, and as popup menus. + Inherits from :class:`Widget`. + + Many of the entry methods take an *index* argument that selects which entry + to operate on. + As described in the Tk ``menu`` manual page, *index* may be a numeric index + (counting from 0 at the top), ``'active'`` (the currently active entry), + ``'end'`` or ``'last'`` (the bottommost entry), ``'none'`` (no entry at all, + written ``{}`` in Tcl), ``@y`` (the entry covering pixel y-coordinate *y* in + the menu window), or a pattern matched against the labels of the entries + from the top down. + + .. method:: add(itemType, cnf={}, **kw) + + Add a new entry to the bottom of the menu. + *itemType* is one of ``'command'``, ``'cascade'``, ``'checkbutton'``, + ``'radiobutton'`` or ``'separator'`` and determines the type of the new + entry; the remaining options configure it. + The :meth:`!add_command`, :meth:`!add_cascade`, :meth:`!add_checkbutton`, + :meth:`!add_radiobutton` and :meth:`!add_separator` convenience methods + call this method with the corresponding *itemType*. + + The entry is configured by the following options, although not every + option applies to every entry type (a separator accepts none of them): + + *label* + The text to display in the entry. + + *command* + The function to call when the entry is invoked (command, checkbutton + and radiobutton entries). + + *accelerator* + A string displayed at the right of the entry to advertise an + accelerator keystroke; it does not itself create the binding. + + *underline* + The index of a character in the label to underline for keyboard + traversal. + + *state* + One of ``'normal'``, ``'active'`` or ``'disabled'``. + + *image* + An image to display instead of, or together with, the text label. + + *compound* + Where to show the image relative to the text: ``'none'`` (the + default), ``'text'``, ``'image'``, ``'top'``, ``'bottom'``, ``'left'`` + or ``'right'``. + + *bitmap* + A bitmap to display instead of the text label. + + *font* + The font to use for the text. + + *background*, *foreground* + The entry's background and foreground colors in its normal state + (ignored on macOS). + + *activebackground*, *activeforeground* + The background and foreground colors used when the entry is active + (ignored on macOS). + + *columnbreak* + If true, the entry starts a new column instead of being placed below + the previous entry. + + *hidemargin* + If true, the standard margin around the entry is omitted, which is + useful when a menu is used as a palette. + + *menu* + The submenu posted by a cascade entry; it must be a child of this + menu. + + *variable* + The variable associated with a checkbutton or radiobutton entry. + + *onvalue*, *offvalue* + The values stored in *variable* when a checkbutton entry is selected + or cleared. + + *value* + The value stored in *variable* when a radiobutton entry is selected. + + *indicatoron* + Whether to display the indicator of a checkbutton or radiobutton + entry. + + *selectcolor* + The color of the indicator of a checkbutton or radiobutton entry when + it is selected. + + *selectimage* + The image displayed when a checkbutton or radiobutton entry is + selected and *image* is also given. + + .. method:: add_cascade(cnf={}, **kw) + + Add a new cascade entry to the bottom of the menu. + A cascade entry has an associated submenu, given by its *menu* option, + which must be a child of this menu; posting the entry posts the submenu + next to it. + + .. method:: add_checkbutton(cnf={}, **kw) + + Add a new checkbutton entry to the bottom of the menu. + When invoked, a checkbutton entry toggles between its *onvalue* and + *offvalue*, storing the result in its associated *variable*, and displays + an indicator showing whether it is selected. + + .. method:: add_command(cnf={}, **kw) + + Add a new command entry to the bottom of the menu. + A command entry behaves much like a button: when it is invoked, the + callback given by its *command* option is called. + + .. method:: add_radiobutton(cnf={}, **kw) + + Add a new radiobutton entry to the bottom of the menu. + Radiobutton entries sharing the same *variable* form a group of which + only one may be selected at a time; selecting an entry stores its *value* + in the variable. + + .. method:: add_separator(cnf={}, **kw) + + Add a separator to the bottom of the menu. + A separator is displayed as a horizontal dividing line and cannot be + activated or invoked. + + .. method:: insert(index, itemType, cnf={}, **kw) + + Same as :meth:`add`, except that the new entry is inserted just before + the entry given by *index* instead of being appended to the end of the + menu. + *itemType* is one of ``'command'``, ``'cascade'``, ``'checkbutton'``, + ``'radiobutton'`` or ``'separator'``. + The :meth:`!insert_command`, :meth:`!insert_cascade`, + :meth:`!insert_checkbutton`, :meth:`!insert_radiobutton` and + :meth:`!insert_separator` convenience methods call this method with the + corresponding *itemType*. + + .. method:: insert_cascade(index, cnf={}, **kw) + + Insert a new cascade entry before the entry given by *index* (see + :meth:`add_cascade`). + + .. method:: insert_checkbutton(index, cnf={}, **kw) + + Insert a new checkbutton entry before the entry given by *index* (see + :meth:`add_checkbutton`). + + .. method:: insert_command(index, cnf={}, **kw) + + Insert a new command entry before the entry given by *index* (see + :meth:`add_command`). + + .. method:: insert_radiobutton(index, cnf={}, **kw) + + Insert a new radiobutton entry before the entry given by *index* (see + :meth:`add_radiobutton`). + + .. method:: insert_separator(index, cnf={}, **kw) + + Insert a separator before the entry given by *index* (see + :meth:`add_separator`). + + .. method:: delete(index1, index2=None) + + Delete all of the menu entries between *index1* and *index2* inclusive. + If *index2* is omitted, it defaults to *index1*, so that a single entry + is deleted. + Attempts to delete a tear-off entry are ignored; remove it by changing + the *tearoff* option instead. + + .. method:: entrycget(index, option) + + Return the current value of the configuration option *option* for the + entry given by *index*. + + .. method:: entryconfig(index, cnf=None, **kw) + :no-typesetting: + + .. method:: entryconfigure(index, cnf=None, **kw) + + Query or modify the configuration options of the entry given by *index*. + This mirrors :meth:`~Misc.configure`, except that it applies to an + individual entry rather than to the menu as a whole. + With no options, it returns a dictionary describing the current options + of the entry; otherwise it sets the given options. + The supported options are those accepted by :meth:`add` for the entry's + type. + :meth:`entryconfig` is an alias of :meth:`!entryconfigure`. + + .. method:: index(index) + + Return the numerical index corresponding to *index*, or ``None`` if + *index* selects no entry. + + .. method:: type(index) + + Return the type of the entry given by *index*: one of ``'command'``, + ``'cascade'``, ``'checkbutton'``, ``'radiobutton'``, ``'separator'`` or + ``'tearoff'`` (for the tear-off entry). + + .. method:: activate(index) + + Make the entry given by *index* the active entry, redisplaying it with + its active colors, and deactivate any previously active entry. + If *index* selects no entry, or the selected entry is disabled, the menu + ends up with no active entry. + + .. method:: invoke(index) + + Invoke the action of the entry given by *index*, as if it had been + clicked. + Nothing happens if the entry is disabled. + If the entry has a *command* associated with it, the result of that + command is returned; otherwise the result is an empty string. + + .. method:: post(x, y) + + Display the menu on the screen at the root-window coordinates *x* and + *y*, adjusting them if necessary so that the whole menu is visible. + If the *postcommand* option has been specified, it is evaluated before + the menu is posted. + + .. method:: tk_popup(x, y, entry='') + + Post the menu as a popup at the root-window coordinates *x* and *y*. + If *entry* is given, the menu is positioned so that this entry is + displayed under the pointer. + + .. method:: unpost() + + Unmap the menu so that it is no longer displayed, also unposting any + posted lower-level cascaded submenu. + This has no effect on Windows and macOS, which manage the unposting of + menus themselves. + + .. method:: xposition(index) + + Return the x-coordinate, within the menu window, of the leftmost pixel of + the entry given by *index*. + + .. versionadded:: 3.3 + + .. method:: yposition(index) + + Return the y-coordinate, within the menu window, of the topmost pixel of + the entry given by *index*. + + +.. class:: Menubutton(master=None, cnf={}, **kw) + + A :class:`!Menubutton` widget displays a textual string, bitmap or image and + posts an associated :class:`Menu`, given by its *menu* option, when the user + presses it. + Like a :class:`Label` it can show *text*, a *textvariable*, or an *image*, + and the *direction* option controls where the menu appears relative to the + button. + Inherits from :class:`Widget`. + Refer to the Tk ``menubutton`` manual page for the full list of options. + + +.. class:: Message(master=None, cnf={}, **kw) + + A :class:`!Message` widget displays a non-interactive textual string, given + by the *text* option or linked to a variable through *textvariable*. + Unlike a :class:`Label`, it breaks the string into multiple lines in order + to produce a given aspect ratio, choosing line breaks at word boundaries, + and it can justify the text left, centered or right. + Inherits from :class:`Widget`. + Refer to the Tk ``message`` manual page for the full list of options. + + +.. class:: OptionMenu(master, variable, value, *values, **kwargs) + + A helper subclass of :class:`Menubutton` that displays a pop-up menu of + mutually exclusive choices. + *variable* is a :class:`Variable` kept in sync with the selection, *value* + is the initial choice, and *values* are the remaining menu entries. + The keyword argument *command* may be given a callback that is invoked with + the selected value, and the keyword argument *name* sets the Tk widget name. + + .. method:: destroy() + + Destroy the widget, also cleaning up the associated pop-up menu. + + .. versionchanged:: 3.14 + Added support for the *name* keyword argument. + + + +.. class:: PanedWindow(master=None, cnf={}, **kw) + + A :class:`!PanedWindow` is a geometry-manager widget that arranges any + number of child *panes* in a row (when *orient* is ``'horizontal'``) or a + column (when *orient* is ``'vertical'``). + Each pane holds one widget, and each pair of adjacent panes is separated by + a movable *sash* that the user can drag with the mouse to resize the widgets + on either side of it. + Inherits from :class:`Widget`. + + The *orient* option selects the layout direction, *sashwidth* sets the width + of each sash and *sashrelief* its relief. + When *showhandle* is true a small handle is drawn on each sash that the user + can grab to drag it. + Refer to the Tk ``panedwindow`` manual page for the full list of options. + + .. method:: add(child, **kw) + + Add *child* to the panedwindow as a new pane, placed after any existing + panes. + The keyword arguments specify per-pane management options for *child*; + they may be any of the options accepted by :meth:`paneconfigure`. + + .. method:: forget(child) + :no-typesetting: + + .. method:: remove(child) + + Remove the pane containing *child* from the panedwindow. + All geometry management options for *child* are forgotten. + :meth:`forget` is an alias of :meth:`!remove`. + This shadows the inherited geometry-manager :meth:`!forget`; + use :meth:`~Pack.pack_forget`, :meth:`~Grid.grid_forget` or + :meth:`~Place.place_forget` to remove the widget itself from its manager. + + .. method:: panes() + + Return a tuple of the widgets managed by the panedwindow, one per pane, + in order. + + .. method:: panecget(child, option) + + Return the current value of the management option *option* for the pane + containing *child*. + *option* may be any value allowed by :meth:`paneconfigure`. + + .. method:: paneconfig(tagOrId, cnf=None, **kw) + :no-typesetting: + + .. method:: paneconfigure(tagOrId, cnf=None, **kw) + + Query or modify the management options of the pane containing the widget + *tagOrId*. + With no options, it returns a dictionary describing all of the available + options for the pane; given a single option name as a string, it returns + a description of that one option; otherwise it sets the given options. + The supported options include *after* and *before* (insert the pane after + or before another managed window), *height* and *width* (the outer + dimensions of the window, including any border), *minsize* (the minimum + size in the paned dimension), *padx* and *pady* (extra space to leave on + each side of the window), *sticky* (position or stretch the window within + an oversized pane, using a string of the characters ``n``, ``s``, ``e`` + and ``w``), *hide* (hide the pane while keeping it in the list of panes) + and *stretch* (how extra space is allocated to the pane: one of + ``'always'``, ``'first'``, ``'last'``, ``'middle'`` or ``'never'``). + :meth:`paneconfig` is an alias of :meth:`!paneconfigure`. + + .. method:: identify(x, y) + + Identify the panedwindow component underneath the point given by *x* and + *y*, in window coordinates. + If the point is over a sash or a sash handle, the result is a two-element + tuple containing the index of the sash or handle and a word indicating + whether it is over a sash or a handle, such as ``(0, 'sash')`` or + ``(2, 'handle')``. + If the point is over any other part of the panedwindow, the result is an + empty string. + + .. method:: sash(*args) + + Query or change the position of the sashes in the panedwindow. + This is a thin wrapper around the Tk ``sash`` subcommand; the convenience + methods :meth:`sash_coord`, :meth:`sash_mark` and :meth:`sash_place` + should normally be used instead. + + .. method:: sash_coord(index) + + Return the current x and y coordinate pair for the sash given by *index*, + which must be an integer between 0 and one less than the number of panes + in the panedwindow. + The coordinates returned are those of the top left corner of the region + containing the sash. + + .. method:: sash_mark(index) + + Record the current mouse position for the sash given by *index*, for use + together with later sash-drag operations to move the sash. + + .. method:: sash_place(index, x, y) + + Place the sash given by *index* at the coordinates *x* and *y*. + + .. method:: proxy(*args) + + Query or change the position of the sash proxy, the "ghost" sash shown + while a sash is being dragged with non-opaque resizing. + This is a thin wrapper around the Tk ``proxy`` subcommand; the + convenience methods :meth:`proxy_coord`, :meth:`proxy_forget` and + :meth:`proxy_place` should normally be used instead. + + .. method:: proxy_coord() + + Return a tuple containing the x and y coordinates of the most recent + proxy location. + + .. method:: proxy_forget() + + Remove the proxy from the display. + + .. method:: proxy_place(x, y) + + Place the proxy at the coordinates *x* and *y*. + + +.. class:: Radiobutton(master=None, cnf={}, **kw) + + A :class:`!Radiobutton` widget displays a textual string, bitmap or image + together with a diamond or circular indicator, and selects one choice out of + several. + It has all the behavior of a simple button and, in addition, can be + selected: typically several radiobuttons share a single *variable*, and + selecting one sets that variable to the radiobutton's *value*; each + radiobutton also monitors the variable and automatically selects or + deselects itself when the variable changes. + Inherits from :class:`Widget`. + In addition to the standard widget options, a radiobutton accepts the + options documented in the Tk ``radiobutton`` manual page, such as + *variable*, *value* and *command*. + + .. method:: invoke() + + Do just what would happen if the user pressed the radiobutton with the + mouse: select the button and invoke the associated command, if there is + one. + Return the result of the command, or an empty string if no command is + associated with the radiobutton. + This is ignored if the radiobutton's state is ``disabled``. + + .. method:: select() + + Select the radiobutton and set the associated variable to the value + corresponding to this widget. + + .. method:: deselect() + + Deselect the radiobutton and set the associated variable to an empty + string. + If this radiobutton was not currently selected, this has no effect. + + .. method:: flash() + + Flash the radiobutton by redisplaying it several times, alternating + between the active and normal colors. + At the end of the flash the radiobutton is left in the same normal or + active state as when the method was called. + This is ignored if the radiobutton's state is ``disabled``. + + +.. class:: Scale(master=None, cnf={}, **kw) + + A :class:`!Scale` widget lets the user select a numerical value by moving a + slider along a trough. + It can be oriented vertically or horizontally and can optionally display a + label and the current value. + Inherits from :class:`Widget`. + + In addition to the standard widget options, a scale accepts the options + documented in the Tk ``scale`` manual page, such as *from_*, *to*, + *resolution*, *orient*, *tickinterval*, *variable* and *command*. + As elsewhere in :mod:`!tkinter`, the leading ``-`` of the Tk option name is + dropped; *from* is spelled ``from_`` because :keyword:`from` is a Python + keyword. + + With a non-integer *resolution*, see :ref:`numeric values and the locale + `. + + .. method:: get() + + Return the current value of the scale. + The result is an integer if the scale's *resolution* yields whole + numbers, and a float otherwise. + + .. method:: set(value) + + Set the scale to *value*, moving the slider accordingly. + This has no effect if the scale is disabled. + + .. method:: coords(value=None) + + Return a tuple ``(x, y)`` giving the pixel coordinates, relative to the + widget, of the point on the centerline of the trough that corresponds to + *value*. + If *value* is omitted, the scale's current value is used. + + .. method:: identify(x, y) + + Return a string describing the part of the scale at the pixel coordinates + *x*, *y*: ``'slider'``, ``'trough1'`` (the part of the trough above or to + the left of the slider), ``'trough2'`` (below or to the right of the + slider), or an empty string if the point is not over any of these + elements. + + +.. class:: Scrollbar(master=None, cnf={}, **kw) + + A :class:`!Scrollbar` widget displays a slider and two arrows that let the + user scroll an associated widget, such as a :class:`Listbox`, :class:`Text`, + :class:`Canvas` or :class:`Entry`. + It is connected to the scrolled widget by setting that widget's + *xscrollcommand* or *yscrollcommand* option to the scrollbar's :meth:`set` + method, and the scrollbar's *command* option to the scrolled widget's + :meth:`~XView.xview` or :meth:`~YView.yview` method. + Inherits from :class:`Widget`. + + .. method:: get() + + Return the current scrollbar settings as a tuple ``(first, last)`` of two + fractions between 0 and 1, describing the portion of the document that is + currently visible, as last passed to :meth:`set`. + + .. method:: set(first, last) + + Set the scrollbar. + *first* and *last* are fractions between 0 and 1 giving the positions of + the start and end of the visible portion of the associated document. + This method is normally registered as the scrolled widget's + *xscrollcommand* or *yscrollcommand* and called by that widget. + + .. method:: activate(index=None) + + Mark the element *index* (one of ``'arrow1'``, ``'slider'`` or + ``'arrow2'``) as active, displaying it according to the + *activebackground* and *activerelief* options. + If *index* is omitted, return the name of the currently active element, + or ``None`` if no element is active. + + .. versionchanged:: 3.5 + The *index* argument is now optional. + + .. method:: delta(deltax, deltay) + + Return a float indicating the fractional change in the scrollbar setting + that corresponds to moving the slider by *deltax* pixels horizontally + (for horizontal scrollbars) or *deltay* pixels vertically (for vertical + scrollbars). + + .. method:: fraction(x, y) + + Return a float between 0 and 1 indicating where the point at pixel + coordinates *x*, *y* lies in the trough: 0 corresponds to the top or left + of the trough and 1 to the bottom or right. + + .. method:: identify(x, y) + + Return the name of the element under the pixel coordinates *x*, *y* (such + as ``'arrow1'``), or an empty string if the point does not lie in any + element of the scrollbar. + + +.. class:: Spinbox(master=None, cnf={}, **kw) + + A :class:`!Spinbox` widget is an :class:`Entry`-like widget with a pair of + up/down arrow buttons that let the user step through a range of values in + addition to editing the value directly. + The set of values may be a numeric range given by the *from_*, *to* and + *increment* options, or an explicit list of strings given by the *values* + option (which takes precedence over the range). + Each time an arrow is invoked the *command* callback, if any, is called; the + *wrap* option controls whether stepping past either end of the range wraps + around to the other end; the *format* option specifies how numeric values + are formatted; and the *validate* option enables validation of the entered + text. + Inherits from :class:`Widget` and :class:`XView`. + + With a non-integer *increment*, see :ref:`numeric values and the locale + `. + + Many of the methods take an *index* argument identifying a character in the + spinbox's string. + As described in the Tk ``spinbox`` manual page, *index* may be a numeric + index (counting from 0), ``'anchor'`` (the selection anchor point), + ``'end'`` (just after the last character), ``'insert'`` (the character just + after the insertion cursor), ``'sel.first'`` or ``'sel.last'`` (the ends of + the selection), or ``@x`` (the character covering pixel x-coordinate *x* in + the window). + + .. method:: get() + + Return the spinbox's string. + + .. method:: insert(index, s) + + Insert the characters of the string *s* just before the character given + by *index*. + + .. method:: delete(first, last=None) + + Delete one or more characters of the spinbox. + *first* is the index of the first character to delete, and *last* is the + index of the character just after the last one to delete. + If *last* is omitted, a single character at *first* is deleted. + + .. method:: icursor(index) + + Arrange for the insertion cursor to be displayed just before the + character given by *index*. + + .. method:: index(index) + + Return the numerical index corresponding to *index*, as a string. + + .. method:: bbox(index) + + Return a tuple of four integers ``(x, y, width, height)`` describing the + bounding box of the character given by *index*. + *x* and *y* are the pixel coordinates of the upper-left corner of the + character relative to the widget, and *width* and *height* are its size + in pixels. + The bounding box may refer to a region outside the visible area of the + window. + + This shadows the inherited :meth:`!Misc.bbox`; + use :meth:`~Misc.grid_bbox` for the grid bounding box. + + .. method:: identify(x, y) + + Return the name of the window element at the pixel coordinates *x*, *y*: + one of ``'buttondown'``, ``'buttonup'``, ``'entry'`` or ``'none'``. + + .. method:: invoke(element) + + Invoke the spin button given by *element*, either ``'buttonup'`` or + ``'buttondown'``, triggering the action associated with it. + + .. method:: scan(*args) + + A thin wrapper around the Tk ``scan`` widget subcommand, used to + implement fast dragging of the view: ``scan('mark', x)`` records *x* and + the current view, and ``scan('dragto', x)`` adjusts the view relative to + that mark. + The :meth:`scan_mark` and :meth:`scan_dragto` methods wrap the two forms. + + .. method:: scan_mark(x) + + Record *x* and the current view in the spinbox window, for use with a + later :meth:`scan_dragto` call. + This is typically associated with a mouse button press in the widget. + + .. method:: scan_dragto(x) + + Adjust the view by 10 times the difference between *x* and the *x* passed + to the last :meth:`scan_mark` call. + This is typically associated with mouse motion events, producing the + effect of dragging the spinbox at high speed through the window. + + .. method:: selection(*args) + + A thin wrapper around the Tk ``selection`` widget subcommand, used to + adjust the selection within the spinbox. + It has several forms depending on the first argument, such as + ``selection('adjust', index)``, ``selection('clear')``, + ``selection('element', ?elem?)``, ``selection('from', index)``, + ``selection('present')``, ``selection('range', start, end)`` and + ``selection('to', index)``. + The :meth:`selection_adjust`, :meth:`selection_clear`, + :meth:`selection_element`, :meth:`selection_from`, + :meth:`selection_present`, :meth:`selection_range` and + :meth:`selection_to` methods wrap these forms. + + .. method:: selection_adjust(index) + + Locate the end of the selection nearest to the character given by *index* + and adjust that end of the selection to be at *index* (including but not + going beyond *index*). + The other end becomes the anchor point for future :meth:`selection_to` + calls. + If the selection is not currently in the spinbox, a new selection is + created to include the characters between *index* and the most recent + anchor point, inclusive. + + .. method:: selection_clear() + + Clear the selection if it is currently in this widget. + If the selection is not in this widget, the method has no effect. + + .. note:: + + This shadows the inherited :meth:`Misc.selection_clear`, + which clears the X selection; + that method is not available on a :class:`Spinbox`. + + .. method:: selection_element(element=None) + + Set or get the currently selected element. + If *element* (one of ``'buttonup'``, ``'buttondown'`` or ``'none'``) is + given, that spin button is selected and displayed depressed; otherwise + the name of the currently selected element is returned. + + .. method:: selection_from(index) + + Set the selection anchor point to just before the character given by + *index*, without changing the selection itself. + + .. versionadded:: 3.8 + + + .. method:: selection_present() + + Return ``True`` if there are characters selected in the spinbox, + ``False`` otherwise. + + .. versionadded:: 3.8 + + + .. method:: selection_range(start, end) + + Set the selection to include the characters starting with the one indexed + by *start* and ending with the one just before *end*. + If *end* refers to the same character as *start* or an earlier one, the + selection is cleared. + + .. versionadded:: 3.8 + + + .. method:: selection_to(index) + + Set the selection between *index* and the anchor point. + If *index* is before the anchor point, the selection runs from *index* up + to but not including the anchor point; if it is after, the selection runs + from the anchor point up to but not including *index*; if it is the same, + nothing happens. + The anchor point is the one set by the most recent :meth:`selection_from` + or :meth:`selection_adjust` call. + If the selection is not in this widget, a new selection is created using + the most recent anchor point. + + .. versionadded:: 3.8 + + + +.. class:: Text(master=None, cnf={}, **kw) + + A :class:`!Text` widget displays and edits multi-line text. + Portions of the text may be styled with **tags**, particular positions may + be annotated with floating **marks**, and arbitrary images and other widgets + may be embedded in the text. + The widget also provides an unlimited undo/redo mechanism and supports peer + widgets that share the same underlying data. + Inherits from :class:`Widget`, :class:`XView` and :class:`YView`, so the + view can be scrolled horizontally and vertically with :meth:`~XView.xview` + and :meth:`~YView.yview`. + Refer to the Tk ``text`` manual page for the full list of options. + + Most of the methods take one or more *index* arguments that identify a + position within the text. + As described in the Tk ``text`` manual page, an index is a string consisting + of a base, optionally followed by one or more modifiers. + The base may be ``'line.char'`` (line *line*, character *char*, where lines + are counted from 1 and characters within a line from 0; ``'line.end'`` + refers to the newline ending the line), ``'end'`` (the position just after + the last newline), the name of a mark, ``'tag.first'`` or ``'tag.last'`` + (the first character tagged with *tag*, or the position just after the last + such character), the name of an embedded image or window, or ``@x,y`` (the + character covering pixel coordinates *x*, *y* in the widget). + A modifier such as ``'+5 chars'``, ``'-3 lines'``, ``'linestart'``, + ``'lineend'``, ``'wordstart'`` or ``'wordend'`` adjusts the index relative + to its base; several modifiers may be combined and are applied from left to + right, for example ``'insert wordstart - 1 c'``. + + .. method:: insert(index, chars, *args) + + Insert the string *chars* just before the character at *index* (if + *index* is ``'end'``, just before the final newline). + By default the new text inherits any tags present on both sides of the + insertion point. + If *args* is given, it consists of alternating *tagList*, *chars* values: + the preceding *chars* receives exactly the tags listed (a tag list may be + a single tag name or a sequence of names), overriding the surrounding + tags. + + .. method:: delete(index1, index2=None) + + Delete the range of characters from *index1* up to but not including + *index2*. + If *index2* is omitted, the single character at *index1* is deleted. + The widget always keeps a newline as its last character, so a deletion + that would remove it is adjusted accordingly. + + .. method:: replace(index1, index2, chars, *args) + + Replace the range of characters from *index1* up to but not including + *index2* with *chars*. + This is equivalent to a :meth:`delete` followed by an :meth:`insert` at + *index1*; *args* is interpreted as for :meth:`insert`. + + .. versionadded:: 3.3 + + .. method:: get(index1, index2=None) + + Return the text from *index1* up to but not including *index2* as a + string. + If *index2* is omitted, return the single character at *index1*. + Embedded images and windows are omitted from the result. + + .. method:: index(index) + + Return the position corresponding to *index* in the canonical + ``'line.char'`` form. + + .. method:: compare(index1, op, index2) + + Compare the positions of *index1* and *index2* using the relational + operator *op*, which must be one of ``'<'``, ``'<='``, ``'=='``, + ``'>='``, ``'>'`` or ``'!='``, and return the boolean result. + + .. method:: count(index1, index2, *options, return_ints=False) + + Count the number of items of the requested kinds between *index1* and + *index2*; the count is negative if *index1* is after *index2*. + Each of *options* names a kind of item to count: ``'chars'``, + ``'displaychars'``, ``'displayindices'``, ``'displaylines'``, + ``'indices'``, ``'lines'``, ``'xpixels'`` or ``'ypixels'`` (the default, + used when no option is given, is ``'indices'``). + The pseudo-option ``'update'`` forces any out-of-date layout information + to be recalculated before the following options are evaluated. + When *return_ints* is true and a single counting option is given, return + a plain integer; otherwise return a tuple with one integer per counting + option (or ``None`` if the result is empty). + + .. versionadded:: 3.3 + + .. versionchanged:: 3.13 + Added the *return_ints* parameter. + + + .. method:: see(index) + + Adjust the view so that the character given by *index* is visible. + If it is already visible the method has no effect; if it is a short + distance out of view the widget scrolls just enough to bring it to the + nearest edge, otherwise it scrolls to center *index* in the window. + + .. method:: bbox(index) + + Return a tuple ``(x, y, width, height)`` giving the bounding box, in + pixels, of the visible part of the character at *index*, or ``None`` if + that character is not visible on the screen. + + This shadows the inherited :meth:`!Misc.bbox`; + use :meth:`~Misc.grid_bbox` for the grid bounding box. + + .. method:: dlineinfo(index) + + Return a tuple ``(x, y, width, height, baseline)`` describing the display + line that contains *index*: the first four values give the bounding box + of the line in pixels and *baseline* gives the offset of the baseline + measured down from the top of the area. + Return ``None`` if that display line is not visible on the screen. + + .. method:: mark_set(markName, index) + + Set the mark named *markName* to the position just before the character + at *index*, creating the mark if it does not already exist. + A mark created this way has right gravity by default. + + .. method:: mark_unset(*markNames) + + Remove each of the marks named in *markNames*. + The special ``insert`` and ``current`` marks may not be removed. + + .. method:: mark_names() + + Return a tuple of the names of all marks currently set in the widget. + + .. method:: mark_gravity(markName, direction=None) + + If *direction* is omitted, return the gravity of mark *markName*, either + ``'left'`` or ``'right'``. + Otherwise set its gravity to *direction*. + The gravity determines on which side of the mark text inserted at the + mark's position appears: a mark with right gravity (the default) stays to + the right of such text. + + .. method:: mark_next(index) + + Return the name of the first mark at or after *index*, or ``None`` if + there is none. + When *index* is the name of a mark, the search starts just after that + mark. + + .. method:: mark_previous(index) + + Return the name of the last mark at or before *index*, or ``None`` if + there is none. + When *index* is the name of a mark, the search starts just before that + mark. + + .. method:: tag_add(tagName, index1, *args) + + Add the tag *tagName* to the range of characters from *index1* up to but + not including the next index in *args*. + Further pairs of indices may follow in *args* to tag additional ranges; a + trailing single index tags just the character at that index. + + .. method:: tag_remove(tagName, index1, index2=None) + + Remove the tag *tagName* from the characters from *index1* up to but not + including *index2* (or from the single character at *index1* if *index2* + is omitted). + The tag itself continues to exist even if no characters carry it. + + .. method:: tag_delete(*tagNames) + + Delete each of the tags named in *tagNames*, removing them from all + characters and discarding their options and bindings. + + .. method:: tag_config(tagName, cnf=None, **kw) + :no-typesetting: + + .. method:: tag_configure(tagName, cnf=None, **kw) + + Query or modify the configuration options of the tag *tagName*. + This mirrors :meth:`~Misc.configure`, except that it applies to a tag + rather than to the widget as a whole: with no options it returns a + dictionary describing the current options, otherwise it sets the given + options. + Defining a tag this way also gives it a priority higher than any existing + tag. + + The supported tag options, all controlling the appearance of the tagged + text, are: + + *font* + The font to use for the text. + + *foreground* + The color to use for the text. + + *background* + The color to use for the area behind the text. + + *fgstipple*, *bgstipple* + Bitmaps used to stipple the foreground (text) and the background; + only well supported on X11. + + *borderwidth* + The width of the border drawn around the text according to *relief* + (default ``0``). + + *relief* + The 3-D appearance of the text's border: ``'flat'`` (the default), + ``'raised'``, ``'sunken'``, ``'ridge'``, ``'groove'`` or ``'solid'``. + + *offset* + How far the text is raised above (or, if negative, lowered below) the + baseline, for superscripts and subscripts. + + *underline* + Whether to underline the text. + + *underlinefg* + The color of the underline; it defaults to the text color. + + *overstrike* + Whether to draw a line through the middle of the text. + + *overstrikefg* + The color of the overstrike line; it defaults to the text color. + + *elide* + Whether the text is elided (hidden). + + *justify* + How to justify the first character of a display line: ``'left'`` (the + default), ``'right'`` or ``'center'``. + + *wrap* + How to wrap lines that are too long: ``'char'``, ``'word'`` or + ``'none'``. + + *lmargin1*, *lmargin2* + The indentation, in pixels, of the first display line of a logical + line and of the remaining display lines. + + *lmargincolor* + The color of the left margin area. + + *rmargin* + The right-hand margin, in pixels. + + *rmargincolor* + The color of the right margin area. + + *spacing1*, *spacing2*, *spacing3* + Extra space, in pixels, above the first display line of a logical + line, between its display lines, and below its last display line. + + *tabs* + The set of tab stops, in the same form as the widget's *tabs* option. + + *tabstyle* + How tab stops are interpreted: ``'tabular'`` or ``'wordprocessor'``. + + *selectbackground*, *selectforeground* + The background and foreground colors used for the text while it is + selected. + + .. note:: + + Tk 8.6 added the *lmargincolor*, *overstrikefg*, *rmargincolor*, + *selectbackground*, *selectforeground* and *underlinefg* options. + + :meth:`tag_config` is an alias of :meth:`!tag_configure`. + + .. method:: tag_cget(tagName, option) + + Return the current value of the configuration option *option* for the tag + *tagName*. + + .. method:: tag_names(index=None) + + If *index* is omitted, return a tuple of the names of all tags defined in + the widget; otherwise return only the names of the tags applied to the + character at *index*. + The names are ordered from lowest to highest priority. + + .. method:: tag_ranges(tagName) + + Return a tuple of indices describing all ranges of text tagged with + *tagName*. + The result alternates start and end indices, so that elements ``2*i`` and + ``2*i+1`` bound the *i*-th range. + + .. method:: tag_nextrange(tagName, index1, index2=None) + + Search forward from *index1* (up to *index2* if given) for the first + range of characters tagged with *tagName*, and return a two-element tuple + of its start and end indices, or an empty tuple if there is no such + range. + + .. method:: tag_prevrange(tagName, index1, index2=None) + + Search backward from *index1* (down to *index2* if given) for the nearest + preceding range of characters tagged with *tagName*, and return a + two-element tuple of its start and end indices, or an empty tuple if + there is no such range. + + .. method:: tag_raise(tagName, aboveThis=None) + + Raise the priority of tag *tagName* so that it is just above the priority + of *aboveThis*, or to the highest priority of all tags if *aboveThis* is + omitted. + When the display options of overlapping tags conflict, the + higher-priority tag wins. + + .. method:: tag_lower(tagName, belowThis=None) + + Lower the priority of tag *tagName* so that it is just below the priority + of *belowThis*, or to the lowest priority of all tags if *belowThis* is + omitted. + + .. method:: tag_bind(tagName, sequence, func, add=None) + + Bind the event *sequence* on characters tagged with *tagName* to the + callback *func*, so that *func* is invoked when that event occurs over + such a character. + If *add* is true the binding is added alongside any existing bindings for + *sequence*, otherwise it replaces them. + Works like :meth:`~Misc.bind` and returns the identifier of the new + binding. + + .. method:: tag_unbind(tagName, sequence, funcid=None) + + Remove the bindings of the event *sequence* on characters tagged with + *tagName*. + If *funcid* is given, only that binding (as returned by :meth:`tag_bind`) + is removed and its callback is unregistered. + + .. versionchanged:: 3.13 + If *funcid* is given, only that callback is unbound. + + + .. method:: image_create(index, cnf={}, **kw) + + Embed an image at *index* and return the name assigned to this image + instance, which may then be used as an index or passed to the other + ``image_*`` methods. + The options, given in *cnf* and *kw*, include *image* (the Tk image to + display), *name* (a base name for the instance), *align*, *padx* and + *pady*. + + .. method:: image_cget(index, option) + + Return the current value of the configuration option *option* for the + embedded image at *index*. + + .. method:: image_configure(index, cnf=None, **kw) + + Query or modify the configuration options of the embedded image at + *index*, like :meth:`~Misc.configure` but applied to that image. + + .. method:: image_names() + + Return a tuple of the names of all images embedded in the widget. + + .. note:: + + This shadows the inherited :meth:`Misc.image_names`, + which returns the names of all images in the Tcl interpreter; + that method is not available on a :class:`Text`. + + .. method:: window_create(index, cnf={}, **kw) + + Embed a window (any widget) at *index*. + The options, given in *cnf* and *kw*, include *window* (the widget to + embed), *create* (a callback that creates the widget on demand), *align*, + *stretch*, *padx* and *pady*. + The embedded widget must be a descendant of the text widget's parent. + + .. method:: window_cget(index, option) + + Return the current value of the configuration option *option* for the + embedded window at *index*. + + .. method:: window_config(index, cnf=None, **kw) + :no-typesetting: + + .. method:: window_configure(index, cnf=None, **kw) + + Query or modify the configuration options of the embedded window at + *index*, like :meth:`~Misc.configure` but applied to that window. + + :meth:`window_config` is an alias of :meth:`!window_configure`. + + .. method:: window_names() + + Return a tuple of the names of all windows embedded in the widget. + + .. method:: edit(*args) + + Low-level wrapper around the Tk ``edit`` widget command that controls the + undo/redo mechanism and the modified flag; *args* is the ``edit`` + subcommand and its arguments. + The :meth:`!edit_\*` methods below are thin wrappers around it and are + usually more convenient. + + .. method:: edit_modified(arg=None) + + If *arg* is omitted, return the current state of the modified flag as + true or false; the flag is set automatically whenever the text is + inserted or deleted. + Otherwise set the flag to the boolean *arg*. + + .. method:: edit_undo() + + Undo the most recent edit action, that is, all the inserts and deletes + recorded on the undo stack since the previous separator, and move it to + the redo stack. + Raises :exc:`TclError` if the undo stack is empty. + Has no effect unless the *undo* option is true. + Since Tk 9.0, returns a tuple of indices delimiting the ranges of text + that were changed. + + .. method:: edit_redo() + + Reapply the most recently undone edit action, provided no further edits + have been made since, and move it back to the undo stack. + Raises :exc:`TclError` if the redo stack is empty. + Has no effect unless the *undo* option is true. + Since Tk 9.0, returns a tuple of indices delimiting the ranges of text + that were changed. + + .. method:: edit_reset() + + Clear the undo and redo stacks. + + .. method:: edit_separator() + + Push a separator onto the undo stack, marking a boundary between edit + actions for undo and redo. + Has no effect unless the *undo* option is true. + Separators are inserted automatically when the *autoseparators* option is + true. + + .. method:: search(pattern, index, stopindex=None, forwards=None, backwards=None, exact=None, regexp=None, nocase=None, count=None, elide=None) + + Search for *pattern* starting at *index* and return the index of the + first character of the first match, or an empty string if there is no + match. + Searching stops at *stopindex* if given; otherwise it wraps around the + ends of the text until the starting position is reached again. + The following boolean keyword flags control the search: *forwards* or + *backwards* select the direction (forward is the default); *exact* (the + default) or *regexp* select literal or regular-expression matching; + *nocase* makes the match case-insensitive; and *elide* causes hidden text + to be searched as well. + If *count* is a :class:`Variable`, the number of index positions in the + match is stored in it. + + + .. method:: scan_mark(x, y) + + Record *x*, *y* and the current view, for use with later + :meth:`scan_dragto` calls. + This is typically bound to a mouse button press in the widget. + + .. method:: scan_dragto(x, y) + + Scroll the widget by 10 times the difference between *x*, *y* and the + coordinates passed to the last :meth:`scan_mark` call. + This is typically bound to mouse motion events, producing the effect of + dragging the text at high speed through the window. + + .. method:: debug(boolean=None) + + If *boolean* is omitted, return whether internal consistency checks of + the B-tree data structure are enabled. + Otherwise enable or disable them. + The setting is shared by all text widgets and may noticeably slow down + widgets holding large amounts of text. + + .. method:: dump(index1, index2=None, command=None, **kw) + + Return the contents of the widget from *index1* up to but not including + *index2* (or just the segment at *index1* if *index2* is omitted), + including text and information about marks, tags, images and windows. + The result is a list of ``(key, value, index)`` triples, where *key* is + one of ``'text'``, ``'mark'``, ``'tagon'``, ``'tagoff'``, ``'image'`` or + ``'window'``. + By default all kinds are reported; passing any of the keyword arguments + *all*, *text*, *mark*, *tag*, *image* or *window* as true restricts the + dump to the selected kinds. + If *command* is given, it is called once per triple with the three values + as arguments and nothing is returned. + + .. method:: peer_create(newPathName, cnf={}, **kw) + + Create a peer text widget with the path name *newPathName* that shares + this widget's underlying data (text, marks, tags, images and the undo + stack). + Changes made through any peer are reflected in all of them. + By default the peer covers the same lines as this widget; standard text + options, including *startline* and *endline*, may be given to override + this. + + .. versionadded:: 3.3 + + .. method:: peer_names() + + Return a tuple of the path names of this widget's peers, not including + the widget itself. + + .. versionadded:: 3.3 + + .. method:: yview_pickplace(*what) + + Adjust the view so that the location given by *what* is visible. + This is an obsolete equivalent of :meth:`see`, which should be used + instead. + + +Variable classes +^^^^^^^^^^^^^^^^ + +.. class:: Variable(master=None, value=None, name=None) + + The base class for the Tk variable wrappers. + A Tk variable is a value stored in the Tcl interpreter that can be linked to + widgets through their *variable* or *textvariable* options (see + :ref:`coupling-widget-variables`), so that changes propagate both ways: + updating the variable updates every widget bound to it, and a user editing + such a widget updates the variable. + + *master* is the widget whose Tcl interpreter owns the variable; if omitted, + the default root window is used. + *value* is the initial value; if omitted, a type-specific default is used. + *name* is the name of the variable in the Tcl interpreter; if omitted, a + unique name of the form ``'PY_VARnum'`` is generated. + If *name* matches an existing variable and *value* is omitted, the existing + value is retained. + + In most cases you should use one of the typed subclasses below -- + :class:`StringVar`, :class:`IntVar`, :class:`DoubleVar` or + :class:`BooleanVar` -- rather than :class:`!Variable` directly. + + .. note:: + + When a :class:`!Variable` is garbage collected, its Tcl variable is unset. + Keep a reference to it for as long as a widget is linked to it, for example + by storing it as an attribute rather than in a local variable. + Otherwise Tk recreates the Tcl variable to keep the widget working, but it + is never unset again, leaking one Tcl variable per dropped wrapper. + + .. versionchanged:: 3.10 + Two variables now compare equal (``==``) only when they have the same + name, are of the same class, and belong to the same Tcl interpreter. + + .. method:: get() + + Return the current value of the variable. + For the base class the value is returned as a string; the typed + subclasses convert it to the appropriate Python type. + + .. method:: initialize(value) + :no-typesetting: + + .. method:: set(value) + + Set the variable to *value*. + :meth:`initialize` is an alias of :meth:`!set`. + + .. versionadded:: 3.3 + The *initialize* spelling. + + .. method:: trace_add(mode, callback) + + Register *callback* to be called when the variable is accessed according + to *mode*. + *mode* is one of the strings ``'array'``, ``'read'``, ``'write'`` or + ``'unset'``, or a list or tuple of such strings. + + When triggered, *callback* is called with three arguments: the name of + the Tcl variable, an index (or an empty string if the variable is not an + element of an array), and the *mode* that triggered the call. + + Return the internal name of the registered callback, which can be passed + to :meth:`trace_remove`. + + .. versionadded:: 3.6 + + .. method:: trace_remove(mode, cbname) + + Remove a trace callback from the variable. + *mode* must match the *mode* that was passed to :meth:`trace_add`, and + *cbname* is the callback name returned by :meth:`trace_add`. + + .. versionadded:: 3.6 + + .. method:: trace_info() + + Return a list of ``(modes, cbname)`` pairs describing all traces + currently set on the variable, where *modes* is a tuple of mode strings + and *cbname* is the internal callback name. + + .. versionadded:: 3.6 + + .. method:: trace(mode, callback) + :no-typesetting: + + .. method:: trace_variable(mode, callback) + + Register *callback* to be called when the variable is accessed according + to *mode*. + *mode* is one of the strings ``'r'``, ``'w'`` or ``'u'``, for read, write + or unset. + Return the internal name of the registered callback. + :meth:`trace` is an alias of :meth:`!trace_variable`. + + .. deprecated:: 3.6 + Use :meth:`trace_add` instead. This method wraps a Tcl feature that + was removed in Tcl 9.0. + + .. method:: trace_vdelete(mode, cbname) + + Remove the trace callback named *cbname* registered for *mode* with + :meth:`trace_variable`. + + .. deprecated:: 3.6 + Use :meth:`trace_remove` instead. This method wraps a Tcl feature + that was removed in Tcl 9.0. + + .. method:: trace_vinfo() + + Return a list of ``(mode, cbname)`` pairs for all traces set on the + variable with :meth:`trace_variable`. + + .. deprecated:: 3.6 + Use :meth:`trace_info` instead. This method wraps a Tcl feature that + was removed in Tcl 9.0. + + +.. class:: StringVar(master=None, value=None, name=None) + + A :class:`Variable` subclass that holds a string. + The default value is ``''``. + + .. method:: get() + + Return the value of the variable as a :class:`str`. + + +.. class:: IntVar(master=None, value=None, name=None) + + A :class:`Variable` subclass that holds an integer. + The default value is ``0``. + + .. method:: get() + + Return the value of the variable as an :class:`int`. + + +.. class:: DoubleVar(master=None, value=None, name=None) + + A :class:`Variable` subclass that holds a float. + The default value is ``0.0``. + + .. method:: get() + + Return the value of the variable as a :class:`float`. + + .. _tkinter-numeric-locale: + + .. note:: + + A floating-point value is always parsed with a period (``.``) as the + decimal separator, but :class:`Spinbox`, :class:`Scale` and + :class:`ttk.Spinbox ` format it according to the + ``LC_NUMERIC`` locale. Under a locale that uses a comma they produce a + value that :meth:`get` cannot read, raising :exc:`TclError`. Set + ``LC_NUMERIC`` to a locale that uses a period (such as ``'C'``) to avoid + this. + + +.. class:: BooleanVar(master=None, value=None, name=None) + + A :class:`Variable` subclass that holds a boolean. + The default value is ``False``. + + .. method:: get() + + Return the value of the variable as a :class:`bool`. + Raise a :exc:`ValueError` if the value cannot be interpreted as a + boolean. + + .. method:: initialize(value) + :no-typesetting: + + .. method:: set(value) + + Set the variable to *value*, converting it to a boolean. + :meth:`initialize` is an alias of :meth:`!set`. + + .. versionadded:: 3.3 + The *initialize* spelling. + + +Image classes +^^^^^^^^^^^^^ + +.. class:: Image(imgtype, name=None, cnf={}, master=None, **kw) + + Base class for Tk images. + *imgtype* is the Tk image type, one of ``'photo'`` or ``'bitmap'``. + An image is a named object that can be displayed by widgets through their + *image* option; deleting all references to the :class:`!Image` object + deletes the underlying Tk image. + Usually you create a :class:`PhotoImage` or :class:`BitmapImage` rather than + an :class:`!Image` directly. + + The image's configuration options are given by *cnf* and *kw* and may be + queried and changed later with the mapping protocol (using ``image[key]``) + or with the :meth:`configure` method. + + .. method:: config(**kw) + :no-typesetting: + + .. method:: configure(**kw) + + Modify one or more configuration options of the image. + The valid options depend on the image type; see :class:`PhotoImage` and + :class:`BitmapImage`. + :meth:`config` is an alias of :meth:`!configure`. + + .. method:: height() + + Return the height of the image, in pixels. + + .. method:: width() + + Return the width of the image, in pixels. + + .. method:: type() + + Return the type of the image, that is the value of *imgtype* with which + it was created (for example ``'photo'`` or ``'bitmap'``). + + +.. class:: PhotoImage(name=None, cnf={}, master=None, **kw) + + A full-color image (the Tk ``photo`` image type), stored internally with a + varying degree of transparency per pixel. + It can read and write GIF, PPM/PGM and (in Tk 8.6 and later) PNG files, read + SVG files (in Tk 9.0 and later), and be drawn in widgets. + Inherits from :class:`Image`. + + The configuration options include *data* (the image contents as a string), + *file* (the name of a file to read the contents from), *format* (the name of + the file format handler), *width* and *height* (the size of the image, used + when building it up piece by piece), *gamma* and *palette*. + + .. method:: blank() + + Blank the image; that is, set the entire image to have no data, so that + it is displayed as transparent and the background of whatever window it + is displayed in shows through. + + .. method:: cget(option) + + Return the current value of the configuration option *option*. + + .. method:: copy(*, from_coords=None, zoom=None, subsample=None) + + Return a new :class:`PhotoImage` with a copy of this image. + + *from_coords* specifies a rectangular sub-region of the source image to + be copied. + It must be a tuple or a list of 1 to 4 integers ``(x1, y1, x2, y2)``. + ``(x1, y1)`` and ``(x2, y2)`` specify diagonally opposite corners of the + rectangle. + If *x2* and *y2* are not specified, they default to the bottom-right + corner of the source image. + The pixels copied include the left and top edges of the rectangle but not + the bottom or right edges. + If *from_coords* is not given, the whole source image is copied. + + If *zoom* or *subsample* are specified, the image is transformed as in + the :meth:`zoom` or :meth:`subsample` methods. + The value must be a single integer or a pair of integers. + + .. versionchanged:: 3.13 + Added the *from_coords*, *zoom* and *subsample* parameters. + + + .. method:: copy_replace(sourceImage, *, from_coords=None, to=None, \ + shrink=False, zoom=None, subsample=None, \ + compositingrule=None) + + Copy a region from *sourceImage* (which must be a :class:`PhotoImage`) + into this image, possibly with pixel zooming and/or subsampling. + If no options are specified, the whole of *sourceImage* is copied into + this image, starting at coordinates ``(0, 0)``. + + *from_coords* specifies a rectangular sub-region of the source image to + be copied, as in the :meth:`copy` method. + + *to* specifies a rectangular sub-region of the destination image to be + affected. + It must be a tuple or a list of 1 to 4 integers ``(x1, y1, x2, y2)``. + If *x2* and *y2* are not specified, they default to ``(x1, y1)`` plus the + size of the source region (after subsampling and zooming, if specified). + If *x2* and *y2* are specified, the source region is replicated if + necessary to fill the destination region in a tiled fashion. + + If *shrink* is true, the size of the destination image is reduced, if + necessary, so that the region being copied into is at the bottom-right + corner of the image. + + If *zoom* or *subsample* are specified, the image is transformed as in + the :meth:`zoom` or :meth:`subsample` methods. + The value must be a single integer or a pair of integers. + + *compositingrule* specifies how transparent pixels in the source image + are combined with the destination image. + With ``'overlay'`` (the default), the old contents of the destination + image remain visible, as if the source image were printed on a piece of + transparent film and placed over the top of the destination. + With ``'set'``, the old contents of the destination image are discarded + and the source image is used as-is. + + .. versionadded:: 3.13 + + + .. method:: data(format=None, *, from_coords=None, background=None, \ + grayscale=False) + + Return the image data. + + *format* specifies the name of the image file format handler to use. + If it is not given, the data is returned as a tuple (one element per row) + of strings containing space-separated (one element per pixel/column) + colors in ``#RRGGBB`` format. + + *from_coords* specifies a rectangular region of the image to be returned. + It must be a tuple or a list of 1 to 4 integers ``(x1, y1, x2, y2)``. + If only *x1* and *y1* are specified, the region extends from ``(x1, y1)`` + to the bottom-right corner of the image. + If all four coordinates are given, they specify diagonally opposite + corners of the region, including ``(x1, y1)`` and excluding ``(x2, y2)``. + If *from_coords* is not given, the whole image is returned. + + If *background* is specified, the data does not contain any transparency + information; in all transparent pixels the color is replaced by the + specified color. + + If *grayscale* is true, the data does not contain color information; all + pixel data is transformed into grayscale. + + .. versionadded:: 3.13 + + + .. method:: get(x, y) + + Return the color of the pixel at coordinates (*x*, *y*) as an + ``(r, g, b)`` tuple of three integers between 0 and 255, representing the + red, green and blue components respectively. + + .. method:: put(data, to=None) + + Set pixels of the image to the colors given in *data*, which must be a + string or a nested sequence of horizontal rows of pixel colors (for + example ``"{red green} {blue yellow}"``). + + *to* specifies the coordinates of the region of the image into which the + data are copied. + It must be a tuple or a list of 2 or 4 integers ``(x1, y1)`` or + ``(x1, y1, x2, y2)`` giving the top-left corner, and optionally the + bottom-right corner, of the region. + The default position is ``(0, 0)``. + + .. method:: read(filename, format=None, *, from_coords=None, to=None, \ + shrink=False) + + Read image data from the file named *filename* into the image. + + *format* specifies the format of the image data in the file. + + *from_coords* specifies a rectangular sub-region of the image file data + to be copied to the destination image. + It must be a tuple or a list of 1 to 4 integers ``(x1, y1, x2, y2)``. + If only *x1* and *y1* are specified, the region extends from ``(x1, y1)`` + to the bottom-right corner of the image in the file. + If all four coordinates are given, they specify diagonally opposite + corners of the region. + If *from_coords* is not given, the whole of the image in the file is + read. + + *to* specifies the coordinates of the top-left corner of the region of + the image into which the data are read. + The default is ``(0, 0)``. + + If *shrink* is true, the size of the image is reduced, if necessary, so + that the region into which the file data are read is at the bottom-right + corner of the image. + + .. versionadded:: 3.13 + + + .. method:: subsample(x, y='', *, from_coords=None) + + Return a new :class:`PhotoImage` based on this image but using only every + *x*-th pixel in the X direction and every *y*-th pixel in the Y + direction. + If *y* is not given, it defaults to the same value as *x*. + + *from_coords* specifies a rectangular sub-region of the source image to + be copied, as in the :meth:`copy` method. + + .. versionchanged:: 3.13 + Added the *from_coords* parameter. + + + .. method:: transparency_get(x, y) + + Return ``True`` if the pixel at coordinates (*x*, *y*) is fully + transparent, ``False`` otherwise. + + .. versionadded:: 3.8 + + + .. method:: transparency_set(x, y, boolean) + + Make the pixel at coordinates (*x*, *y*) fully transparent if *boolean* + is true, fully opaque otherwise. + + .. versionadded:: 3.8 + + + .. method:: write(filename, format=None, from_coords=None, *, \ + background=None, grayscale=False) + + Write image data from the image to the file named *filename*. + + *format* specifies the name of the image file format handler to use. + If it is not given, the format is guessed from the file extension. + + *from_coords* specifies a rectangular region of the image to be written. + It must be a tuple or a list of 1 to 4 integers ``(x1, y1, x2, y2)``. + If only *x1* and *y1* are specified, the region extends from ``(x1, y1)`` + to the bottom-right corner of the image. + If all four coordinates are given, they specify diagonally opposite + corners of the region. + If *from_coords* is not given, the whole image is written. + + If *background* is specified, the data does not contain any transparency + information; in all transparent pixels the color is replaced by the + specified color. + + If *grayscale* is true, the data does not contain color information; all + pixel data is transformed into grayscale. + + .. versionchanged:: 3.13 + Added the *background* and *grayscale* parameters. + + + .. method:: zoom(x, y='', *, from_coords=None) + + Return a new :class:`PhotoImage` with this image magnified by a factor of + *x* in the X direction and *y* in the Y direction. + If *y* is not given, it defaults to the same value as *x*. + + *from_coords* specifies a rectangular sub-region of the source image to + be copied, as in the :meth:`copy` method. + + .. versionchanged:: 3.13 + Added the *from_coords* parameter. + + + +.. class:: BitmapImage(name=None, cnf={}, master=None, **kw) + + A two-color image (the Tk ``bitmap`` image type) created from an X11 bitmap. + Each pixel displays a foreground color, a background color, or nothing + (producing a transparent effect). + Inherits from :class:`Image`. + + The configuration options are *data* or *file* (the source bitmap, given as + a string in X11 bitmap format or as the name of a file in that format), + *maskdata* or *maskfile* (the mask bitmap, in the same forms), and + *foreground* and *background* (the two colors). + For pixels where the mask is zero the image displays nothing; for other + pixels it displays the foreground color where the source is one and the + background color where the source is zero. + If *background* is set to an empty string, the background pixels are + transparent. + + :class:`!BitmapImage` has no methods of its own beyond those inherited from + :class:`Image`. + + +Other classes +^^^^^^^^^^^^^ + +.. class:: Event() + + A container for the attributes of an event passed to a callback bound with + :meth:`Misc.bind`. + An :class:`!Event` instance has the following attributes, each corresponding + to a field of the underlying Tk event; depending on the event type, some + attributes may be set to the string ``'??'`` to indicate that they are not + meaningful. + See :ref:`bindings-and-events`. + + .. attribute:: serial + + The serial number of the event. + + .. attribute:: num + + The mouse button that was pressed or released (for button events). + + .. attribute:: focus + + Whether the window has the focus (for ``Enter`` and ``Leave`` events). + + .. attribute:: height + width + + The new height and width of the window (for ``Configure`` and ``Expose`` + events). + + .. attribute:: keycode + + The keycode of the key that was pressed or released. + + .. attribute:: state + + The state of the event, as a number (for most events) or a string (for + ``Visibility`` events). + + .. attribute:: time + + The timestamp of the event, in milliseconds. + + .. attribute:: x + y + + The pointer position relative to the widget, in pixels. + + .. attribute:: x_root + y_root + + The pointer position relative to the top-left corner of the screen, in + pixels. + + .. attribute:: char + + The character typed, as a string (for key events). + + .. attribute:: send_event + + ``True`` if the event was sent by another application. + + .. attribute:: keysym + + The symbolic name of the key that was pressed or released. + + .. attribute:: keysym_num + + The numeric value of :attr:`keysym`. + + .. attribute:: type + + The :class:`EventType` of the event. + + .. attribute:: widget + + The widget on which the event occurred. + + .. attribute:: delta + + The amount the mouse wheel was rotated (for ``MouseWheel`` events). + + +.. class:: EventType(*values) + + An :class:`enum.StrEnum` enumerating the Tk event types, used as the value + of :attr:`Event.type`. + Its members include, among others, ``KeyPress``, ``KeyRelease``, + ``ButtonPress``, ``ButtonRelease``, ``Motion``, ``Enter``, ``Leave``, + ``FocusIn``, ``FocusOut``, ``Configure``, ``Map``, ``Unmap``, ``Expose``, + ``Destroy`` and ``MouseWheel``. + + .. versionadded:: 3.6 + + + +.. class:: CallWrapper(func, subst, widget) + + Internal helper that wraps a Python callback so that it can be invoked from + Tcl. + *func* is the Python function, *subst* is an optional function that + pre-processes the Tcl arguments, and *widget* is the widget used for error + reporting. + Instances are created automatically by :meth:`Misc.register`; this class is + not normally used directly. + + +Module-level functions +^^^^^^^^^^^^^^^^^^^^^^ + +.. function:: Tcl(screenName=None, baseName=None, className='Tk', useTk=False) + + The :func:`Tcl` function is a factory function which creates an object much + like that created by the :class:`Tk` class, except that it does not + initialize the Tk subsystem. + This is most often useful when driving the Tcl interpreter in an environment + where one doesn't want to create extraneous toplevel windows, or where one + cannot (such as Unix/Linux systems without an X server). + An object created by the :func:`Tcl` object can have a Toplevel window + created (and the Tk subsystem initialized) by calling its :meth:`~Tk.loadtk` + method. + +.. function:: NoDefaultRoot() + + Inhibit the creation of an implicit default root window. + Afterwards :mod:`!tkinter` no longer creates a shared default root + automatically, and operations that rely on one --- such as constructing a + widget without an explicit *master* --- raise a :exc:`RuntimeError`. + Call this early in larger applications to make the root window explicit. + +.. function:: mainloop(n=0) + + Run the Tk main event loop on the default root window until all windows are + destroyed. + Equivalent to calling :meth:`Misc.mainloop` on the default root. + +.. function:: getboolean(s) + + Convert the Tcl boolean string *s* (one of ``'1'``, ``'true'``, ``'yes'``, + ``'on'`` and similar, or their false counterparts) to a Python + :class:`bool`. + Raise :exc:`TclError` for an invalid value. + +.. function:: getdouble(s) + + Convert *s* to a floating-point number. + This is the built-in :class:`float`. + +.. function:: getint(s) + + Convert *s* to an integer. + This is the built-in :class:`int`. + +.. function:: image_names() + + Return the names of all existing images in the default root's interpreter. + +.. function:: image_types() + + Return the available image types (such as ``'photo'`` and ``'bitmap'``) in + the default root's interpreter. + + +.. _tkinter-file-handlers: + +File handlers +^^^^^^^^^^^^^ + +Tk allows you to register and unregister a callback function which will be +called from the Tk mainloop when I/O is possible on a file descriptor. +Only one handler may be registered per file descriptor. Example code:: + + import tkinter + widget = tkinter.Tk() + mask = tkinter.READABLE | tkinter.WRITABLE + widget.tk.createfilehandler(file, mask, callback) + ... + widget.tk.deletefilehandler(file) + +This feature is not available on Windows. + +Since you don't know how many bytes are available for reading, you may not +want to use the :class:`~io.BufferedIOBase` or :class:`~io.TextIOBase` +:meth:`~io.BufferedIOBase.read` or :meth:`~io.IOBase.readline` methods, +since these will insist on reading a predefined number of bytes. +For sockets, the :meth:`~socket.socket.recv` or +:meth:`~socket.socket.recvfrom` methods will work fine; for other files, +use raw reads or ``os.read(file.fileno(), maxbytecount)``. + + +.. method:: Widget.tk.createfilehandler(file, mask, func) + + Registers the file handler callback function *func*. The *file* argument + may either be an object with a :meth:`~io.IOBase.fileno` method (such as + a file or socket object), or an integer file descriptor. The *mask* + argument is an ORed combination of any of the three constants below. + The callback is called as follows:: + + callback(file, mask) + + +.. method:: Widget.tk.deletefilehandler(file) + + Unregisters a file handler. + + +.. data:: READABLE + WRITABLE + EXCEPTION + + Constants used in the *mask* arguments. + + +Constants +^^^^^^^^^ + +The following symbolic constants are available in both the :mod:`!tkinter` +and :mod:`!tkinter.constants` namespaces. + +.. data:: TRUE + YES + ON + + Truthy values, all equal to the integer ``1``. + +.. data:: FALSE + NO + OFF + + Falsy values, all equal to the integer ``0``. + +.. data:: N + S + E + W + NE + NW + SE + SW + NS + EW + NSEW + CENTER + + Compass directions (``'n'``, ``'s'``, ``'e'``, ``'w'`` and the diagonals and + edges) plus ``CENTER`` (``'center'``), used as values for the *anchor* and + *sticky* options and by methods such as :meth:`Misc.grid_anchor`. + +.. data:: LEFT + RIGHT + TOP + BOTTOM + + Sides for the *side* option of the packer (see :meth:`Pack.pack_configure`). + +.. data:: X + Y + BOTH + NONE + + Values for the *fill* option of the packer: ``'x'``, ``'y'``, ``'both'`` or + ``'none'``. + +.. data:: RAISED + SUNKEN + FLAT + RIDGE + GROOVE + SOLID + + Values for the *relief* option, which controls a widget's 3-D border. + +.. data:: HORIZONTAL + VERTICAL + + Values for the *orient* option of widgets such as :class:`Scale`, + :class:`Scrollbar` and :class:`PanedWindow`. + +.. data:: CHAR + WORD + + Values for the *wrap* option of the :class:`Text` widget, selecting line + wrapping on character or word boundaries. + +.. data:: BASELINE + + The text-alignment value ``'baseline'``. + +.. data:: INSIDE + OUTSIDE + + Values for the *bordermode* option of the placer (see + :meth:`Place.place_configure`). + +.. data:: INSERT + CURRENT + END + ANCHOR + SEL + SEL_FIRST + SEL_LAST + + Symbolic indices used by the :class:`Text`, :class:`Entry`, :class:`Listbox` + and :class:`Canvas` widgets, such as ``'insert'`` (the insertion cursor), + ``'current'``, ``'end'``, ``'anchor'`` and the bounds of the selection + (``'sel.first'`` and ``'sel.last'``). + +.. data:: ALL + + The special tag ``'all'``, which matches every item of a :class:`Canvas` or + every character of a :class:`Text` (for example ``canvas.delete(ALL)``). + +.. data:: NORMAL + DISABLED + ACTIVE + HIDDEN + + Values for the *state* option of various widgets and items. + +.. data:: CASCADE + CHECKBUTTON + COMMAND + RADIOBUTTON + SEPARATOR + + Menu entry types, used as the *itemType* argument of :meth:`Menu.add` and + :meth:`Menu.insert`. + +.. data:: SINGLE + BROWSE + MULTIPLE + EXTENDED + + Values for the *selectmode* option of the :class:`Listbox` widget. + +.. data:: PIESLICE + CHORD + ARC + + Values for the *style* option of :class:`Canvas` arc items. + +.. data:: BUTT + PROJECTING + ROUND + BEVEL + MITER + + Values for the *capstyle* (``'butt'``, ``'projecting'``, ``'round'``) and + *joinstyle* (``'round'``, ``'bevel'``, ``'miter'``) options of + :class:`Canvas` line items. + +.. data:: FIRST + LAST + + Values for the *arrow* option of :class:`Canvas` line items, indicating + which ends have arrowheads. + +.. data:: MOVETO + SCROLL + + The first argument passed by a :class:`Scrollbar` to the :meth:`XView.xview` + or :meth:`YView.yview` method of the scrolled widget. + +.. data:: UNITS + PAGES + + Values for the *what* argument of :meth:`XView.xview_scroll` and + :meth:`YView.yview_scroll`. + +.. data:: UNDERLINE + NUMERIC + DOTBOX + + Other option values: ``'underline'``, ``'numeric'`` and ``'dotbox'``. diff --git a/Doc/library/tkinter.scrolledtext.rst b/Doc/library/tkinter.scrolledtext.rst index 763e24929d74b5..37e26a486d10c0 100644 --- a/Doc/library/tkinter.scrolledtext.rst +++ b/Doc/library/tkinter.scrolledtext.rst @@ -1,8 +1,7 @@ -:mod:`!tkinter.scrolledtext` --- Scrolled Text Widget +:mod:`!tkinter.scrolledtext` --- Scrolled text widget ===================================================== .. module:: tkinter.scrolledtext - :platform: Tk :synopsis: Text widget with a vertical scroll bar. .. sectionauthor:: Fred L. Drake, Jr. @@ -11,15 +10,17 @@ -------------- -The :mod:`tkinter.scrolledtext` module provides a class of the same name which +The :mod:`!tkinter.scrolledtext` module provides a class of the same name which implements a basic text widget which has a vertical scroll bar configured to do the "right thing." Using the :class:`ScrolledText` class is a lot easier than setting up a text widget and scroll bar directly. -The text widget and scrollbar are packed together in a :class:`Frame`, and the -methods of the :class:`Grid` and :class:`Pack` geometry managers are acquired -from the :class:`Frame` object. This allows the :class:`ScrolledText` widget to -be used directly to achieve most normal geometry management behavior. +The text widget and scrollbar are packed together in a :class:`~tkinter.Frame`, +and the methods of the :class:`~tkinter.Pack`, :class:`~tkinter.Grid` and +:class:`~tkinter.Place` geometry managers are acquired from the +:class:`~tkinter.Frame` object. +This allows the :class:`ScrolledText` widget to be used directly to achieve +most normal geometry management behavior. Should more specific control be necessary, the following attributes are available: diff --git a/Doc/library/tkinter.ttk.rst b/Doc/library/tkinter.ttk.rst index 628e9f945ac365..68ea834747ebfe 100644 --- a/Doc/library/tkinter.ttk.rst +++ b/Doc/library/tkinter.ttk.rst @@ -12,20 +12,29 @@ -------------- -The :mod:`tkinter.ttk` module provides access to the Tk themed widget set, -introduced in Tk 8.5. It provides additional benefits including anti-aliased font -rendering under X11 and window transparency (requiring a composition -window manager on X11). +The :mod:`!tkinter.ttk` module provides access to the Tk themed widget set, +introduced in Tk 8.5. +Its widgets adapt their appearance to the platform's native theme, +giving an application a better and more consistent look and feel +than the classic :mod:`tkinter` widgets, whose appearance is fixed. -The basic idea for :mod:`tkinter.ttk` is to separate, to the extent possible, +The basic idea for :mod:`!tkinter.ttk` is to separate, to the extent possible, the code implementing a widget's behavior from the code implementing its appearance. +Ttk widgets are used just like the classic :mod:`tkinter` widgets +and share the same machinery: +the widget hierarchy, the geometry managers, variable coupling and event binding. +Those foundational concepts are covered in the :mod:`tkinter` documentation +and are not repeated here. + +.. versionadded:: 3.1 + .. seealso:: - `Tk Widget Styling Support `_ - A document introducing theming support for Tk + `Tk Widget Styling Support (TIP #48) `_ + The Tcl Improvement Proposal that introduced the themed widget styling engine. Using Ttk @@ -40,28 +49,30 @@ To override the basic Tk widgets, the import should follow the Tk import:: from tkinter import * from tkinter.ttk import * -That code causes several :mod:`tkinter.ttk` widgets (:class:`Button`, +That code causes several :mod:`!tkinter.ttk` widgets (:class:`Button`, :class:`Checkbutton`, :class:`Entry`, :class:`Frame`, :class:`Label`, -:class:`LabelFrame`, :class:`Menubutton`, :class:`PanedWindow`, -:class:`Radiobutton`, :class:`Scale` and :class:`Scrollbar`) to +:class:`LabelFrame`, :class:`Menubutton`, :class:`OptionMenu`, +:class:`PanedWindow`, :class:`Radiobutton`, :class:`Scale`, +:class:`Scrollbar` and :class:`Spinbox`) to automatically replace the Tk widgets. -This has the direct benefit of using the new widgets which gives a better -look and feel across platforms; however, the replacement widgets are not -completely compatible. The main difference is that widget options such as -"fg", "bg" and others related to widget styling are no -longer present in Ttk widgets. Instead, use the :class:`ttk.Style` class -for improved styling effects. +.. note:: + Overriding the classic widgets with ``from tkinter.ttk import *`` + is convenient for adapting existing code, + but new code is usually clearer if it imports the module + as ``from tkinter import ttk`` and refers to the themed widgets explicitly, + such as ``ttk.Button``. -.. seealso:: - - `Converting existing applications to use Tile widgets `_ - A monograph (using Tcl terminology) about differences typically - encountered when moving applications to use the new widgets. +This has the direct benefit of using the new widgets which gives a better look +and feel across platforms; however, the replacement widgets are not completely +compatible. +The main difference is that widget options such as ``fg``, ``bg`` and others +related to widget styling are no longer present in Ttk widgets. +Instead, use the :class:`ttk.Style {%- endblock -%} {% block body %}

{{ docstitle|e }}

@@ -21,63 +50,82 @@

{{ docstitle|e }}

{% trans %}Welcome! This is the official documentation for Python {{ release }}.{% endtrans %}

{% trans %}Documentation sections:{% endtrans %}

- - -
- - - - - - - - - - - - - -
+
+ + +
+ +

{% trans %}Other resources:{% endtrans %}

+
+ + +

{% trans %}Indices, glossary, and search:{% endtrans %}

- - -
- - - - - - -
+
+ + +

{% trans %}Project information:{% endtrans %}

- - -
- - - - - - - -
+ {% endblock %} diff --git a/Doc/tools/templates/indexsidebar.html b/Doc/tools/templates/indexsidebar.html index eea29e2449a9cf..5e7f03cd024ef7 100644 --- a/Doc/tools/templates/indexsidebar.html +++ b/Doc/tools/templates/indexsidebar.html @@ -6,12 +6,3 @@

{% trans %}Docs by version{% endtrans %}

{% include "_docs_by_version.html" without context %}
  • {% trans %}All versions{% endtrans %}
  • -

    {% trans %}Other resources{% endtrans %}

    - diff --git a/Doc/tools/templates/layout.html b/Doc/tools/templates/layout.html index 56023ebf962703..54c6eb9b5ef7e4 100644 --- a/Doc/tools/templates/layout.html +++ b/Doc/tools/templates/layout.html @@ -26,11 +26,11 @@ {% endblock %} {% block extrahead %} - {% if builder == "html" and enable_analytics %} - - {% endif %} - - {% if builder != "htmlhelp" %} + {% if builder == "html" %} + {% if enable_analytics %} + + {% endif %} + {% if pagename == 'whatsnew/changelog' and not embedded %} {% endif %} {% endif %} diff --git a/Doc/tutorial/appendix.rst b/Doc/tutorial/appendix.rst index 6a1611afadb57c..2539edb51ba3a0 100644 --- a/Doc/tutorial/appendix.rst +++ b/Doc/tutorial/appendix.rst @@ -14,8 +14,7 @@ There are two variants of the interactive :term:`REPL`. The classic basic interpreter is supported on all platforms with minimal line control capabilities. -On Windows, or Unix-like systems with :mod:`curses` support, -a new interactive shell is used by default. +Since Python 3.13, a new interactive shell is used by default. This one supports color, multiline editing, history browsing, and paste mode. To disable color, see :ref:`using-on-controlling-color` for details. Function keys provide some additional functionality. diff --git a/Doc/tutorial/classes.rst b/Doc/tutorial/classes.rst index 9d0fab8861d2a9..3c690343022618 100644 --- a/Doc/tutorial/classes.rst +++ b/Doc/tutorial/classes.rst @@ -359,7 +359,7 @@ Usually, a method is called right after it is bound:: x.f() -In the :class:`!MyClass` example, this will return the string ``'hello world'``. +If ``x = MyClass()``, as above, this will return the string ``'hello world'``. However, it is not necessary to call a method right away: ``x.f`` is a method object, and can be stored away and called at a later time. For example:: @@ -420,7 +420,7 @@ of the class:: 'Buddy' As discussed in :ref:`tut-object`, shared data can have possibly surprising -effects with involving :term:`mutable` objects such as lists and dictionaries. +effects involving :term:`mutable` objects such as lists and dictionaries. For example, the *tricks* list in the following code should not be used as a class variable because just a single list would be shared by all *Dog* instances:: diff --git a/Doc/tutorial/controlflow.rst b/Doc/tutorial/controlflow.rst index 95939242fb7d44..bee6cc39fafcdb 100644 --- a/Doc/tutorial/controlflow.rst +++ b/Doc/tutorial/controlflow.rst @@ -155,8 +155,8 @@ that takes an iterable is :func:`sum`:: 6 Later we will see more functions that return iterables and take iterables as -arguments. In chapter :ref:`tut-structures`, we will discuss in more detail about -:func:`list`. +arguments. In chapter :ref:`tut-structures`, we will discuss :func:`list` in more +detail. .. _tut-break: @@ -251,6 +251,7 @@ statements: a ``try`` statement's ``else`` clause runs when no exception occurs, and a loop's ``else`` clause runs when no ``break`` occurs. For more on the ``try`` statement and exceptions, see :ref:`tut-handling`. +.. index:: single: ...; ellipsis literal .. _tut-pass: :keyword:`!pass` Statements @@ -277,6 +278,12 @@ at a more abstract level. The :keyword:`!pass` is silently ignored:: ... pass # Remember to implement this! ... +For this last case, many people use the ellipsis literal :code:`...` instead of +:code:`pass`. This use has no special meaning to Python, and is not part of +the language definition (you could use any constant expression here), but +:code:`...` is used conventionally as a placeholder body as well. +See :ref:`bltin-ellipsis-object`. + .. _tut-match: @@ -434,7 +441,7 @@ Several other key features of this statement: ``False`` and ``None`` are compared by identity. - Patterns may use named constants. These must be dotted names - to prevent them from being interpreted as capture variable:: + to prevent them from being interpreted as capture variables:: from enum import Enum class Color(Enum): @@ -561,7 +568,7 @@ This example, as usual, demonstrates some new Python features: Different types define different methods. Methods of different types may have the same name without causing ambiguity. (It is possible to define your own object types and methods, using *classes*, see :ref:`tut-classes`) - The method :meth:`!append` shown in the example is defined for list objects; it + The method :meth:`~list.append` shown in the example is defined for list objects; it adds a new element at the end of the list. In this example it is equivalent to ``result = result + [a]``, but more efficient. @@ -999,7 +1006,8 @@ scope:: 43 The above example uses a lambda expression to return a function. Another use -is to pass a small function as an argument:: +is to pass a small function as an argument. For instance, :meth:`list.sort` +takes a sorting key function *key* which can be a lambda function:: >>> pairs = [(1, 'one'), (2, 'two'), (3, 'three'), (4, 'four')] >>> pairs.sort(key=lambda pair: pair[1]) @@ -1031,31 +1039,28 @@ blank, visually separating the summary from the rest of the description. The following lines should be one or more paragraphs describing the object's calling conventions, its side effects, etc. -The Python parser does not strip indentation from multi-line string literals in -Python, so tools that process documentation have to strip indentation if -desired. This is done using the following convention. The first non-blank line -*after* the first line of the string determines the amount of indentation for -the entire documentation string. (We can't use the first line since it is -generally adjacent to the string's opening quotes so its indentation is not -apparent in the string literal.) Whitespace "equivalent" to this indentation is -then stripped from the start of all lines of the string. Lines that are -indented less should not occur, but if they occur all their leading whitespace -should be stripped. Equivalence of whitespace should be tested after expansion -of tabs (to 8 spaces, normally). +The Python parser strips indentation from multi-line string literals when they +serve as module, class, or function docstrings. Here is an example of a multi-line docstring:: >>> def my_function(): ... """Do nothing, but document it. ... - ... No, really, it doesn't do anything. + ... No, really, it doesn't do anything: + ... + ... >>> my_function() + ... >>> ... """ ... pass ... >>> print(my_function.__doc__) Do nothing, but document it. - No, really, it doesn't do anything. + No, really, it doesn't do anything: + + >>> my_function() + >>> .. _tut-annotations: @@ -1073,7 +1078,7 @@ Function Annotations information about the types used by user-defined functions (see :pep:`3107` and :pep:`484` for more information). -:term:`Annotations ` are stored in the :attr:`!__annotations__` +:term:`Annotations ` are stored in the :attr:`~object.__annotations__` attribute of the function as a dictionary and have no effect on any other part of the function. Parameter annotations are defined by a colon after the parameter name, followed by an expression evaluating to the value of the annotation. Return annotations are @@ -1102,7 +1107,7 @@ Intermezzo: Coding Style Now that you are about to write longer, more complex pieces of Python, it is a good time to talk about *coding style*. Most languages can be written (or more -concise, *formatted*) in different styles; some are more readable than others. +concisely, *formatted*) in different styles; some are more readable than others. Making it easy for others to read your code is always a good idea, and adopting a nice coding style helps tremendously for that. diff --git a/Doc/tutorial/datastructures.rst b/Doc/tutorial/datastructures.rst index cbe780e075baf5..db9b4cae1d489d 100644 --- a/Doc/tutorial/datastructures.rst +++ b/Doc/tutorial/datastructures.rst @@ -12,24 +12,23 @@ and adds some new things as well. More on Lists ============= -The list data type has some more methods. Here are all of the methods of list -objects: +The :ref:`list ` data type has some more methods. Here are all +of the methods of list objects: - -.. method:: list.append(x) +.. method:: list.append(value, /) :noindex: Add an item to the end of the list. Similar to ``a[len(a):] = [x]``. -.. method:: list.extend(iterable) +.. method:: list.extend(iterable, /) :noindex: Extend the list by appending all the items from the iterable. Similar to ``a[len(a):] = iterable``. -.. method:: list.insert(i, x) +.. method:: list.insert(index, value, /) :noindex: Insert an item at a given position. The first argument is the index of the @@ -37,14 +36,14 @@ objects: the list, and ``a.insert(len(a), x)`` is equivalent to ``a.append(x)``. -.. method:: list.remove(x) +.. method:: list.remove(value, /) :noindex: - Remove the first item from the list whose value is equal to *x*. It raises a + Remove the first item from the list whose value is equal to *value*. It raises a :exc:`ValueError` if there is no such item. -.. method:: list.pop([i]) +.. method:: list.pop(index=-1, /) :noindex: Remove the item at the given position in the list, and return it. If no index @@ -59,10 +58,10 @@ objects: Remove all items from the list. Similar to ``del a[:]``. -.. method:: list.index(x[, start[, end]]) +.. method:: list.index(value[, start[, stop]]) :noindex: - Return zero-based index in the list of the first item whose value is equal to *x*. + Return zero-based index of the first occurrence of *value* in the list. Raises a :exc:`ValueError` if there is no such item. The optional arguments *start* and *end* are interpreted as in the slice @@ -71,10 +70,10 @@ objects: sequence rather than the *start* argument. -.. method:: list.count(x) +.. method:: list.count(value, /) :noindex: - Return the number of times *x* appears in the list. + Return the number of times *value* appears in the list. .. method:: list.sort(*, key=None, reverse=False) @@ -142,8 +141,8 @@ Using Lists as Stacks The list methods make it very easy to use a list as a stack, where the last element added is the first element retrieved ("last-in, first-out"). To add an -item to the top of the stack, use :meth:`!append`. To retrieve an item from the -top of the stack, use :meth:`!pop` without an explicit index. For example:: +item to the top of the stack, use :meth:`~list.append`. To retrieve an item from the +top of the stack, use :meth:`~list.pop` without an explicit index. For example:: >>> stack = [3, 4, 5] >>> stack.append(6) @@ -340,7 +339,7 @@ The :keyword:`!del` statement ============================= There is a way to remove an item from a list given its index instead of its -value: the :keyword:`del` statement. This differs from the :meth:`!pop` method +value: the :keyword:`del` statement. This differs from the :meth:`~list.pop` method which returns a value. The :keyword:`!del` statement can also be used to remove slices from a list or clear the entire list (which we did earlier by assignment of an empty list to the slice). For example:: @@ -445,15 +444,19 @@ packing and sequence unpacking. Sets ==== -Python also includes a data type for *sets*. A set is an unordered collection -with no duplicate elements. Basic uses include membership testing and -eliminating duplicate entries. Set objects also support mathematical operations -like union, intersection, difference, and symmetric difference. +Python also includes a data type for :ref:`sets `. A set is +an unordered collection with no duplicate elements. Basic uses include +membership testing and eliminating duplicate entries. Set objects also +support mathematical operations like union, intersection, difference, and +symmetric difference. Curly braces or the :func:`set` function can be used to create sets. Note: to create an empty set you have to use ``set()``, not ``{}``; the latter creates an empty dictionary, a data structure that we discuss in the next section. +Because sets are unordered, iterating over them or printing them can +produce the elements in a different order than you expect. + Here is a brief demonstration:: >>> basket = {'apple', 'orange', 'apple', 'pear', 'orange', 'banana'} @@ -500,8 +503,8 @@ any immutable type; strings and numbers can always be keys. Tuples can be used as keys if they contain only strings, numbers, or tuples; if a tuple contains any mutable object either directly or indirectly, it cannot be used as a key. You can't use lists as keys, since lists can be modified in place using index -assignments, slice assignments, or methods like :meth:`!append` and -:meth:`!extend`. +assignments, slice assignments, or methods like :meth:`~list.append` and +:meth:`~list.extend`. It is best to think of a dictionary as a set of *key: value* pairs, with the requirement that the keys are unique (within one dictionary). A pair of @@ -512,8 +515,12 @@ dictionary; this is also the way dictionaries are written on output. The main operations on a dictionary are storing a value with some key and extracting the value given the key. It is also possible to delete a key:value pair with ``del``. If you store using a key that is already in use, the old -value associated with that key is forgotten. It is an error to extract a value -using a non-existent key. +value associated with that key is forgotten. + +Extracting a value for a non-existent key by subscripting (``d[key]``) raises a +:exc:`KeyError`. To avoid getting this error when trying to access a possibly +non-existent key, use the :meth:`~dict.get` method instead, which returns +``None`` (or a specified default value) if the key is not in the dictionary. Performing ``list(d)`` on a dictionary returns a list of all the keys used in the dictionary, in insertion order (if you want it sorted, just use @@ -528,6 +535,12 @@ Here is a small example using a dictionary:: {'jack': 4098, 'sape': 4139, 'guido': 4127} >>> tel['jack'] 4098 + >>> tel['irv'] + Traceback (most recent call last): + File "", line 1, in + KeyError: 'irv' + >>> print(tel.get('irv')) + None >>> del tel['sape'] >>> tel['irv'] = 4127 >>> tel diff --git a/Doc/tutorial/errors.rst b/Doc/tutorial/errors.rst index 1c20fa2f0b6ae5..3c6edf2c4793ab 100644 --- a/Doc/tutorial/errors.rst +++ b/Doc/tutorial/errors.rst @@ -121,9 +121,9 @@ A :keyword:`try` statement may have more than one *except clause*, to specify handlers for different exceptions. At most one handler will be executed. Handlers only handle exceptions that occur in the corresponding *try clause*, not in other handlers of the same :keyword:`!try` statement. An *except clause* -may name multiple exceptions as a parenthesized tuple, for example:: +may name multiple exceptions, for example:: - ... except (RuntimeError, TypeError, NameError): + ... except RuntimeError, TypeError, NameError: ... pass A class in an :keyword:`except` clause matches exceptions which are instances of the @@ -549,9 +549,9 @@ caught like any other exception. :: >>> try: ... f() ... except Exception as e: - ... print(f'caught {type(e)}: e') + ... print(f'caught {type(e)}: {e}') ... - caught : e + caught : there were problems (2 sub-exceptions) >>> By using ``except*`` instead of ``except``, we can selectively diff --git a/Doc/tutorial/index.rst b/Doc/tutorial/index.rst index 96791f88c867ab..20fe161be4acc2 100644 --- a/Doc/tutorial/index.rst +++ b/Doc/tutorial/index.rst @@ -4,6 +4,10 @@ The Python Tutorial ###################### +.. Tip:: This tutorial is designed for + *programmers* that are new to the Python language, + **not** *beginners* who are new to programming. + Python is an easy to learn, powerful programming language. It has efficient high-level data structures and a simple but effective approach to object-oriented programming. Python's elegant syntax and dynamic typing, @@ -11,7 +15,7 @@ together with its interpreted nature, make it an ideal language for scripting and rapid application development in many areas on most platforms. The Python interpreter and the extensive standard library are freely available -in source or binary form for all major platforms from the Python web site, +in source or binary form for all major platforms from the Python website, https://www.python.org/, and may be freely distributed. The same site also contains distributions of and pointers to many free third party Python modules, programs and tools, and additional documentation. @@ -21,7 +25,8 @@ implemented in C or C++ (or other languages callable from C). Python is also suitable as an extension language for customizable applications. This tutorial introduces the reader informally to the basic concepts and -features of the Python language and system. It helps to have a Python +features of the Python language and system. Be aware that it expects you to +have a basic understanding of programming in general. It helps to have a Python interpreter handy for hands-on experience, but all examples are self-contained, so the tutorial can be read off-line as well. diff --git a/Doc/tutorial/inputoutput.rst b/Doc/tutorial/inputoutput.rst index 35b8c7cd8eb049..a00f06cf46c41a 100644 --- a/Doc/tutorial/inputoutput.rst +++ b/Doc/tutorial/inputoutput.rst @@ -95,10 +95,11 @@ Some examples:: >>> repr((x, y, ('spam', 'eggs'))) "(32.5, 40000, ('spam', 'eggs'))" -The :mod:`string` module contains a :class:`~string.Template` class that offers -yet another way to substitute values into strings, using placeholders like -``$x`` and replacing them with values from a dictionary, but offers much less -control of the formatting. +The :mod:`string` module contains support for a simple templating approach +based upon regular expressions, via :class:`string.Template`. +This offers yet another way to substitute values into strings, +using placeholders like ``$x`` and replacing them with values from a dictionary. +This syntax is easy to use, although it offers much less control for formatting. .. index:: single: formatted string literal diff --git a/Doc/tutorial/interpreter.rst b/Doc/tutorial/interpreter.rst index 02e7de77322e99..af01a4a96be244 100644 --- a/Doc/tutorial/interpreter.rst +++ b/Doc/tutorial/interpreter.rst @@ -34,13 +34,13 @@ status. If that doesn't work, you can exit the interpreter by typing the following command: ``quit()``. The interpreter's line-editing features include interactive editing, history -substitution and code completion on systems that support the `GNU Readline -`_ library. +substitution and code completion on most systems. Perhaps the quickest check to see whether command line editing is supported is -typing :kbd:`Control-P` to the first Python prompt you get. If it beeps, you -have command line editing; see Appendix :ref:`tut-interacting` for an -introduction to the keys. If nothing appears to happen, or if ``^P`` is -echoed, command line editing isn't available; you'll only be able to use +typing a word in on the Python prompt, then pressing Left arrow (or :kbd:`Control-b`). +If the cursor moves, you have command line editing; see Appendix +:ref:`tut-interacting` for an introduction to the keys. +If nothing appears to happen, or if a sequence like ``^[[D`` or ``^B`` appears, +command line editing isn't available; you'll only be able to use backspace to remove characters from the current line. The interpreter operates somewhat like the Unix shell: when called with standard diff --git a/Doc/tutorial/introduction.rst b/Doc/tutorial/introduction.rst index bec5da8fd759ac..7778e37a9adaa9 100644 --- a/Doc/tutorial/introduction.rst +++ b/Doc/tutorial/introduction.rst @@ -13,10 +13,9 @@ end a multi-line command. .. only:: html - You can toggle the display of prompts and output by clicking on ``>>>`` - in the upper-right corner of an example box. If you hide the prompts - and output for an example, then you can easily copy and paste the input - lines into your interpreter. + You can use the "Copy" button (it appears in the upper-right corner + when hovering over or tapping a code example), which strips prompts + and omits output, to copy and paste the input lines into your interpreter. .. index:: single: # (hash); comment @@ -50,7 +49,7 @@ primary prompt, ``>>>``. (It shouldn't take long.) Numbers ------- -The interpreter acts as a simple calculator: you can type an expression at it +The interpreter acts as a simple calculator: you can type an expression into it and it will write the value. Expression syntax is straightforward: the operators ``+``, ``-``, ``*`` and ``/`` can be used to perform arithmetic; parentheses (``()``) can be used for grouping. @@ -147,6 +146,8 @@ Python can manipulate text (represented by type :class:`str`, so-called "``Yay! :)``". They can be enclosed in single quotes (``'...'``) or double quotes (``"..."``) with the same result [#]_. +.. code-block:: pycon + >>> 'spam eggs' # single quotes 'spam eggs' >>> "Paris rabbit got your back :)! Yay!" # double quotes @@ -183,11 +184,11 @@ If you don't want characters prefaced by ``\`` to be interpreted as special characters, you can use *raw strings* by adding an ``r`` before the first quote:: - >>> print('C:\some\name') # here \n means newline! - C:\some + >>> print('C:\this\name') # here \t means tab, \n means newline + C: his ame - >>> print(r'C:\some\name') # note the r before the quote - C:\some\name + >>> print(r'C:\this\name') # note the r before the quote + C:\this\name There is one subtle aspect to raw strings: a raw string may not end in an odd number of ``\`` characters; see @@ -419,7 +420,7 @@ type, i.e. it is possible to change their content:: [1, 8, 27, 64, 125] You can also add new items at the end of the list, by using -the :meth:`!list.append` *method* (we will see more about methods later):: +the :meth:`list.append` *method* (we will see more about methods later):: >>> cubes.append(216) # add the cube of 6 >>> cubes.append(7 ** 3) # and the cube of 7 diff --git a/Doc/tutorial/modules.rst b/Doc/tutorial/modules.rst index de7aa0e2342946..f8105cd5441fec 100644 --- a/Doc/tutorial/modules.rst +++ b/Doc/tutorial/modules.rst @@ -27,14 +27,16 @@ called :file:`fibo.py` in the current directory with the following contents:: # Fibonacci numbers module - def fib(n): # write Fibonacci series up to n + def fib(n): + """Write Fibonacci series up to n.""" a, b = 0, 1 while a < n: print(a, end=' ') a, b = b, a+b print() - def fib2(n): # return Fibonacci series up to n + def fib2(n): + """Return Fibonacci series up to n.""" result = [] a, b = 0, 1 while a < n: @@ -577,8 +579,8 @@ module for example, you might use:: from .. import formats from ..filters import equalizer -Note that relative imports are based on the name of the current module. Since -the name of the main module is always ``"__main__"``, modules intended for use +Note that relative imports are based on the name of the current module's package. +Since the main module does not have a package, modules intended for use as the main module of a Python application must always use absolute imports. diff --git a/Doc/tutorial/stdlib.rst b/Doc/tutorial/stdlib.rst index 4b3eef313e76d7..320d365313225c 100644 --- a/Doc/tutorial/stdlib.rst +++ b/Doc/tutorial/stdlib.rst @@ -1,13 +1,13 @@ .. _tut-brieftour: ********************************** -Brief Tour of the Standard Library +Brief tour of the standard library ********************************** .. _tut-os-interface: -Operating System Interface +Operating system interface ========================== The :mod:`os` module provides dozens of functions for interacting with the @@ -47,7 +47,7 @@ a higher level interface that is easier to use:: .. _tut-file-wildcards: -File Wildcards +File wildcards ============== The :mod:`glob` module provides a function for making file lists from directory @@ -60,7 +60,7 @@ wildcard searches:: .. _tut-command-line-arguments: -Command Line Arguments +Command-line arguments ====================== Common utility scripts often need to process command line arguments. These @@ -97,7 +97,7 @@ to ``['alpha.txt', 'beta.txt']``. .. _tut-stderr: -Error Output Redirection and Program Termination +Error output redirection and program termination ================================================ The :mod:`sys` module also has attributes for *stdin*, *stdout*, and *stderr*. @@ -112,7 +112,7 @@ The most direct way to terminate a script is to use ``sys.exit()``. .. _tut-string-pattern-matching: -String Pattern Matching +String pattern matching ======================= The :mod:`re` module provides regular expression tools for advanced string @@ -175,7 +175,7 @@ computations. .. _tut-internet-access: -Internet Access +Internet access =============== There are a number of modules for accessing the internet and processing internet @@ -183,13 +183,13 @@ protocols. Two of the simplest are :mod:`urllib.request` for retrieving data from URLs and :mod:`smtplib` for sending mail:: >>> from urllib.request import urlopen - >>> with urlopen('http://worldtimeapi.org/api/timezone/etc/UTC.txt') as response: + >>> with urlopen('https://docs.python.org/3/') as response: ... for line in response: ... line = line.decode() # Convert bytes to a str - ... if line.startswith('datetime'): + ... if 'updated' in line: ... print(line.rstrip()) # Remove trailing newline ... - datetime: 2022-01-01T01:36:47.689215+00:00 + Last updated on Nov 11, 2025 (20:11 UTC). >>> import smtplib >>> server = smtplib.SMTP('localhost') @@ -206,7 +206,7 @@ from URLs and :mod:`smtplib` for sending mail:: .. _tut-dates-and-times: -Dates and Times +Dates and times =============== The :mod:`datetime` module supplies classes for manipulating dates and times in @@ -216,15 +216,15 @@ formatting and manipulation. The module also supports objects that are timezone aware. :: >>> # dates are easily constructed and formatted - >>> from datetime import date - >>> now = date.today() + >>> import datetime as dt + >>> now = dt.date.today() >>> now datetime.date(2003, 12, 2) >>> now.strftime("%m-%d-%y. %d %b %Y is a %A on the %d day of %B.") '12-02-03. 02 Dec 2003 is a Tuesday on the 02 day of December.' >>> # dates support calendar arithmetic - >>> birthday = date(1964, 7, 31) + >>> birthday = dt.date(1964, 7, 31) >>> age = now - birthday >>> age.days 14368 @@ -232,7 +232,7 @@ aware. :: .. _tut-data-compression: -Data Compression +Data compression ================ Common data archiving and compression formats are directly supported by modules @@ -254,7 +254,7 @@ including: :mod:`zlib`, :mod:`gzip`, :mod:`bz2`, :mod:`lzma`, :mod:`zipfile` and .. _tut-performance-measurement: -Performance Measurement +Performance measurement ======================= Some Python users develop a deep interest in knowing the relative performance of @@ -278,7 +278,7 @@ larger blocks of code. .. _tut-quality-control: -Quality Control +Quality control =============== One approach for developing high quality software is to write tests for each @@ -324,7 +324,7 @@ file:: .. _tut-batteries-included: -Batteries Included +Batteries included ================== Python has a "batteries included" philosophy. This is best seen through the @@ -335,7 +335,7 @@ sophisticated and robust capabilities of its larger packages. For example: names, no direct knowledge or handling of XML is needed. * The :mod:`email` package is a library for managing email messages, including - MIME and other :rfc:`2822`-based message documents. Unlike :mod:`smtplib` and + MIME and other :rfc:`5322`-based message documents. Unlike :mod:`smtplib` and :mod:`poplib` which actually send and receive messages, the email package has a complete toolset for building or decoding complex message structures (including attachments) and for implementing internet encoding and header diff --git a/Doc/tutorial/stdlib2.rst b/Doc/tutorial/stdlib2.rst index a2f96b34b2dead..cc28f6ef6c5fdc 100644 --- a/Doc/tutorial/stdlib2.rst +++ b/Doc/tutorial/stdlib2.rst @@ -1,7 +1,7 @@ .. _tut-brieftourtwo: ********************************************** -Brief Tour of the Standard Library --- Part II +Brief tour of the standard library --- part II ********************************************** This second tour covers more advanced modules that support professional @@ -10,7 +10,7 @@ programming needs. These modules rarely occur in small scripts. .. _tut-output-formatting: -Output Formatting +Output formatting ================= The :mod:`reprlib` module provides a version of :func:`repr` customized for @@ -130,7 +130,7 @@ templates for XML files, plain text reports, and HTML web reports. .. _tut-binary-formats: -Working with Binary Data Record Layouts +Working with binary data record layouts ======================================= The :mod:`struct` module provides :func:`~struct.pack` and @@ -178,14 +178,13 @@ tasks in background while the main program continues to run:: class AsyncZip(threading.Thread): def __init__(self, infile, outfile): - threading.Thread.__init__(self) + super().__init__() self.infile = infile self.outfile = outfile def run(self): - f = zipfile.ZipFile(self.outfile, 'w', zipfile.ZIP_DEFLATED) - f.write(self.infile) - f.close() + with zipfile.ZipFile(self.outfile, 'w', zipfile.ZIP_DEFLATED) as f: + f.write(self.infile) print('Finished background zip of:', self.infile) background = AsyncZip('mydata.txt', 'myarchive.zip') @@ -245,7 +244,7 @@ application. .. _tut-weak-references: -Weak References +Weak references =============== Python does automatic memory management (reference counting for most objects and @@ -286,7 +285,7 @@ applications include caching objects that are expensive to create:: .. _tut-list-tools: -Tools for Working with Lists +Tools for working with lists ============================ Many data structure needs can be met with the built-in list type. However, @@ -352,7 +351,7 @@ not want to run a full list sort:: .. _tut-decimal-fp: -Decimal Floating-Point Arithmetic +Decimal floating-point arithmetic ================================= The :mod:`decimal` module offers a :class:`~decimal.Decimal` datatype for diff --git a/Doc/tutorial/venv.rst b/Doc/tutorial/venv.rst index f362e1943b666f..6b6b8a768e3f58 100644 --- a/Doc/tutorial/venv.rst +++ b/Doc/tutorial/venv.rst @@ -88,6 +88,11 @@ For example: '~/envs/tutorial-env/lib/python3.5/site-packages'] >>> +Note that the activated virtual environment does not alter the ``PYTHONPATH`` variable in any way. +This may lead to unexpected results if the path includes references to code which is incompatible with +the Python version the virtual environment is using. The best practice is to ``unset PYTHONPATH`` +in bash or the equivalent for the shell you are using. + To deactivate a virtual environment, type:: deactivate diff --git a/Doc/tutorial/whatnow.rst b/Doc/tutorial/whatnow.rst index dbe2d7fc09927e..aae8f29b007762 100644 --- a/Doc/tutorial/whatnow.rst +++ b/Doc/tutorial/whatnow.rst @@ -30,7 +30,7 @@ the set are: More Python resources: -* https://www.python.org: The major Python web site. It contains code, +* https://www.python.org: The major Python website. It contains code, documentation, and pointers to Python-related pages around the web. * https://docs.python.org: Fast access to Python's documentation. @@ -68,6 +68,6 @@ already contain the solution for your problem. .. rubric:: Footnotes -.. [#] "Cheese Shop" is a Monty Python's sketch: a customer enters a cheese shop, +.. [#] "Cheese Shop" is a Monty Python sketch: a customer enters a cheese shop, but whatever cheese he asks for, the clerk says it's missing. diff --git a/Doc/using/android.rst b/Doc/using/android.rst index 65bf23dc994856..60a13569318141 100644 --- a/Doc/using/android.rst +++ b/Doc/using/android.rst @@ -30,7 +30,7 @@ Adding Python to an Android app Most app developers should use one of the following tools, which will provide a much easier experience: -* `Briefcase `__, from the BeeWare project +* `Briefcase `__, from the BeeWare project * `Buildozer `__, from the Kivy project * `Chaquopy `__ * `pyqtdeploy `__ @@ -40,8 +40,15 @@ If you're sure you want to do all of this manually, read on. You can use the :source:`testbed app ` as a guide; each step below contains a link to the relevant file. -* Build Python by following the instructions in :source:`Android/README.md`. - This will create the directory ``cross-build/HOST/prefix``. +* First, acquire a build of Python for Android: + + * The easiest way is to download an Android release from `python.org + `__. The ``prefix`` directory + mentioned below is at the top level of the package. + + * Or if you want to build it yourself, follow the instructions in + :source:`Android/README.md`. The ``prefix`` directory will be created under + :samp:`cross-build/{HOST}`. * Add code to your :source:`build.gradle ` file to copy the following items into your project. All except your own Python @@ -63,3 +70,12 @@ link to the relevant file. * Add code to your app to :source:`start Python in embedded mode `. This will need to be C code called via JNI. + +Building a Python package for Android +------------------------------------- + +Python packages can be built for Android as wheels and released on PyPI. The +recommended tool for doing this is `cibuildwheel +`__, which automates +all the details of setting up a cross-compilation environment, building the +wheel, and testing it on an emulator. diff --git a/Doc/using/cmdline.rst b/Doc/using/cmdline.rst index 40a46a62031ef7..a33747830f893c 100644 --- a/Doc/using/cmdline.rst +++ b/Doc/using/cmdline.rst @@ -50,8 +50,8 @@ additional methods of invocation: * When called with ``-c command``, it executes the Python statement(s) given as *command*. Here *command* may contain multiple statements separated by newlines. Leading whitespace is significant in Python statements! -* When called with ``-m module-name``, the given module is located on the - Python module path and executed as a script. +* When called with ``-m module-name``, the given module is located using the standard + import mechanism and executed as a script. In non-interactive mode, the entire input is parsed before it is executed. @@ -78,8 +78,8 @@ source. .. option:: -m - Search :data:`sys.path` for the named module and execute its contents as - the :mod:`__main__` module. + Locate the module using the standard import mechanism and execute its contents + as the :mod:`__main__` module. Since the argument is a *module* name, you must not give a file extension (``.py``). The module name should be a valid absolute Python module name, but @@ -369,8 +369,8 @@ Miscellaneous options .. option:: -R Turn on hash randomization. This option only has an effect if the - :envvar:`PYTHONHASHSEED` environment variable is set to ``0``, since hash - randomization is enabled by default. + :envvar:`PYTHONHASHSEED` environment variable is set to anything other + than ``random``, since hash randomization is enabled by default. On previous versions of Python, this option turns on hash randomization, so that the :meth:`~object.__hash__` values of str and bytes objects @@ -381,7 +381,7 @@ Miscellaneous options Hash randomization is intended to provide protection against a denial-of-service caused by carefully chosen inputs that exploit the worst case performance of a dict construction, *O*\ (*n*\ :sup:`2`) complexity. See - http://ocert.org/advisories/ocert-2011-003.html for details. + https://ocert.org/advisories/ocert-2011-003.html for details. :envvar:`PYTHONHASHSEED` allows you to set a fixed value for the hash seed secret. @@ -501,7 +501,25 @@ Miscellaneous options .. option:: -x Skip the first line of the source, allowing use of non-Unix forms of - ``#!cmd``. This is intended for a DOS specific hack only. + ``#!cmd``. + + This can be used to turn a Python script into a Windows batch file. + Similarly to adding a shebang line and setting the executable bit on Unix, + the extension of the Python script can be changed to ``.bat`` and the + following line can be added at the start of the script: + + .. code-block:: batch + + @py -x "%~f0" %* & exit /b + + Or, to specify the path to the Python interpreter explicitly: + + .. code-block:: batch + + @"C:\Path\to\python.exe" -x "%~f0" %* & exit /b + + Unlike a shebang line which is a Python comment, this line is not valid + Python syntax, and the :option:`-x` option is needed to skip it. .. option:: -X @@ -653,7 +671,7 @@ Miscellaneous options .. versionadded:: 3.13 * :samp:`-X thread_inherit_context={0,1}` causes :class:`~threading.Thread` - to, by default, use a copy of context of of the caller of + to, by default, use a copy of context of the caller of ``Thread.start()`` when starting. Otherwise, threads will start with an empty context. If unset, the value of this option defaults to ``1`` on free-threaded builds and to ``0`` otherwise. See also @@ -669,6 +687,13 @@ Miscellaneous options .. versionadded:: 3.14 + * :samp:`-X tlbc={0,1}` enables (1, the default) or disables (0) thread-local + bytecode in builds configured with :option:`--disable-gil`. When disabled, + this also disables the specializing interpreter. See also + :envvar:`PYTHON_TLBC`. + + .. versionadded:: 3.14 + It also allows passing arbitrary values and retrieving them through the :data:`sys._xoptions` dictionary. @@ -1038,6 +1063,13 @@ conflict. * ``pymalloc_debug``: same as ``pymalloc`` but also install debug hooks. * ``mimalloc_debug``: same as ``mimalloc`` but also install debug hooks. + .. note:: + + In the :term:`free-threaded ` build, the ``malloc``, + ``malloc_debug``, ``pymalloc``, and ``pymalloc_debug`` values are not + supported. Only ``default``, ``debug``, ``mimalloc``, and + ``mimalloc_debug`` are accepted. + .. versionadded:: 3.6 .. versionchanged:: 3.7 @@ -1047,12 +1079,13 @@ conflict. .. envvar:: PYTHONMALLOCSTATS If set to a non-empty string, Python will print statistics of the - :ref:`pymalloc memory allocator ` every time a new pymalloc object - arena is created, and on shutdown. + :ref:`pymalloc memory allocator ` or the + :ref:`mimalloc memory allocator ` (whichever is in use) + every time a new object arena is created, and on shutdown. This variable is ignored if the :envvar:`PYTHONMALLOC` environment variable is used to force the :c:func:`malloc` allocator of the C library, or if - Python is configured without ``pymalloc`` support. + Python is configured without both ``pymalloc`` and ``mimalloc`` support. .. versionchanged:: 3.6 This variable can now also be used on Python compiled in release mode. @@ -1249,9 +1282,8 @@ conflict. .. envvar:: PYTHON_BASIC_REPL If this variable is set to any value, the interpreter will not attempt to - load the Python-based :term:`REPL` that requires :mod:`curses` and - :mod:`readline`, and will instead use the traditional parser-based - :term:`REPL`. + load the Python-based :term:`REPL` that requires :mod:`readline`, and will + instead use the traditional parser-based :term:`REPL`. .. versionadded:: 3.13 @@ -1277,7 +1309,7 @@ conflict. .. envvar:: PYTHON_THREAD_INHERIT_CONTEXT If this variable is set to ``1`` then :class:`~threading.Thread` will, - by default, use a copy of context of of the caller of ``Thread.start()`` + by default, use a copy of context of the caller of ``Thread.start()`` when starting. Otherwise, new threads will start with an empty context. If unset, this variable defaults to ``1`` on free-threaded builds and to ``0`` otherwise. See also :option:`-X thread_inherit_context<-X>`. @@ -1302,6 +1334,16 @@ conflict. .. versionadded:: 3.13 +.. envvar:: PYTHON_TLBC + + If set to ``1`` enables thread-local bytecode. If set to ``0`` thread-local + bytecode and the specializing interpreter are disabled. Only applies to + builds configured with :option:`--disable-gil`. + + See also the :option:`-X tlbc <-X>` command-line option. + + .. versionadded:: 3.14 + Debug-mode variables ~~~~~~~~~~~~~~~~~~~~ diff --git a/Doc/using/configure.rst b/Doc/using/configure.rst index b914d3397b6dda..2c0d81d4800701 100644 --- a/Doc/using/configure.rst +++ b/Doc/using/configure.rst @@ -4,10 +4,13 @@ Configure Python .. highlight:: sh + +.. _build-requirements: + Build Requirements ================== -Features and minimum versions required to build CPython: +To build CPython, you will need: * A `C11 `_ compiler. `Optional C11 features @@ -22,47 +25,136 @@ Features and minimum versions required to build CPython: * Support for threads. -* OpenSSL 1.1.1 is the minimum version and OpenSSL 3.0.16 is the recommended - minimum version for the :mod:`ssl` and :mod:`hashlib` extension modules. +.. versionchanged:: 3.5 + On Windows, Visual Studio 2015 or later is now required. + +.. versionchanged:: 3.6 + Selected C99 features, like ```` and ``static inline`` functions, + are now required. + +.. versionchanged:: 3.7 + Thread support is now required. + +.. versionchanged:: 3.11 + C11 compiler, IEEE 754 and NaN support are now required. + On Windows, Visual Studio 2017 or later is required. -* SQLite 3.15.2 for the :mod:`sqlite3` extension module. +See also :pep:`7` "Style Guide for C Code" and :pep:`11` "CPython platform +support". -* Tcl/Tk 8.5.12 for the :mod:`tkinter` module. -* Autoconf 2.72 and aclocal 1.16.5 are required to regenerate the - :file:`configure` script. +.. _optional-module-requirements: + +Requirements for optional modules +--------------------------------- + +Some :term:`optional modules ` of the standard library +require third-party libraries installed for development +(for example, header files must be available). + +Missing requirements are reported in the ``configure`` output. +Modules that are missing due to missing dependencies are listed near the end +of the ``make`` output, +sometimes using an internal name, for example, ``_ctypes`` for :mod:`ctypes` +module. + +If you distribute a CPython interpreter without optional modules, +it's best practice to advise users, who generally expect that +standard library modules are available. + +Dependencies to build optional modules are: + +.. list-table:: + :header-rows: 1 + :align: left + + * - Dependency + - Minimum version + - Python module + * - `libbz2 `_ + - + - :mod:`bz2` + * - `libffi `_ + - 3.3.0 recommended + - :mod:`ctypes` + * - `liblzma `_ + - + - :mod:`lzma` + * - `libmpdec `_ + - 2.5.0 + - :mod:`decimal` [1]_ + * - `libreadline `_ or + `libedit `_ [2]_ + - + - :mod:`readline` + * - `libuuid `_ + - + - ``_uuid`` [3]_ + * - `ncurses `_ [4]_ + - + - :mod:`curses` + * - `OpenSSL `_ + - | 3.0.18 recommended + | (1.1.1 minimum) + - :mod:`ssl`, :mod:`hashlib` [5]_ + * - `SQLite `_ + - 3.15.2 + - :mod:`sqlite3` + * - `Tcl/Tk `_ + - 8.5.12 + - :mod:`tkinter`, :ref:`IDLE `, :mod:`turtle` + * - `zlib `_ + - 1.2.2.1 + - :mod:`zlib`, :mod:`gzip`, :mod:`ensurepip` + * - `zstd `_ + - 1.4.5 + - :mod:`compression.zstd` + +.. [1] If *libmpdec* is not available, the :mod:`decimal` module will use + a pure-Python implementation. + See :option:`--with-system-libmpdec` for details. +.. [2] See :option:`--with-readline` for choosing the backend for the + :mod:`readline` module. +.. [3] The :mod:`uuid` module uses ``_uuid`` to generate "safe" UUIDs. + See the module documentation for details. +.. [4] The :mod:`curses` module requires the ``libncurses`` or ``libncursesw`` + library. + The :mod:`curses.panel` module additionally requires the ``libpanel`` or + ``libpanelw`` library. +.. [5] If OpenSSL is not available, the :mod:`hashlib` module will use + bundled implementations of several hash functions. + See :option:`--with-builtin-hashlib-hashes` for *forcing* usage of OpenSSL. + +Note that the table does not include all optional modules; in particular, +platform-specific modules like :mod:`winreg` are not listed here. + +.. seealso:: + + * The `devguide `_ + includes a full list of dependencies required to build all modules and + instructions on how to install them on common platforms. + * :option:`--with-system-expat` allows building with an external + `libexpat `_ library. + * :ref:`configure-options-for-dependencies` .. versionchanged:: 3.1 - Tcl/Tk version 8.3.1 is now required. + Tcl/Tk version 8.3.1 is now required for :mod:`tkinter`. .. versionchanged:: 3.5 - On Windows, Visual Studio 2015 or later is now required. - Tcl/Tk version 8.4 is now required. - -.. versionchanged:: 3.6 - Selected C99 features are now required, like ```` and ``static - inline`` functions. + Tcl/Tk version 8.4 is now required for :mod:`tkinter`. .. versionchanged:: 3.7 - Thread support and OpenSSL 1.0.2 are now required. + OpenSSL 1.0.2 is now required for :mod:`hashlib` and :mod:`ssl`. .. versionchanged:: 3.10 - OpenSSL 1.1.1 is now required. - Require SQLite 3.7.15. + OpenSSL 1.1.1 is now required for :mod:`hashlib` and :mod:`ssl`. + SQLite 3.7.15 is now required for :mod:`sqlite3`. .. versionchanged:: 3.11 - C11 compiler, IEEE 754 and NaN support are now required. - On Windows, Visual Studio 2017 or later is required. - Tcl/Tk version 8.5.12 is now required for the :mod:`tkinter` module. + Tcl/Tk version 8.5.12 is now required for :mod:`tkinter`. .. versionchanged:: 3.13 - Autoconf 2.71, aclocal 1.16.5 and SQLite 3.15.2 are now required. - -.. versionchanged:: 3.14 - Autoconf 2.72 is now required. - -See also :pep:`7` "Style Guide for C Code" and :pep:`11` "CPython platform -support". + SQLite 3.15.2 is now required for :mod:`sqlite3`. Generated files @@ -91,8 +183,19 @@ The container is optional, the following command can be run locally:: autoreconf -ivf -Werror -The generated files can change depending on the exact ``autoconf-archive``, -``aclocal`` and ``pkg-config`` versions. +The generated files can change depending on the exact versions of the +tools used. +The container that CPython uses has +`Autoconf `_ 2.72, +``aclocal`` from `Automake `_ 1.16.5, +and `pkg-config `_ 1.8.1. + +.. versionchanged:: 3.13 + Autoconf 2.71 and aclocal 1.16.5 and are now used to regenerate + :file:`configure`. + +.. versionchanged:: 3.14 + Autoconf 2.72 is now used to regenerate :file:`configure`. .. _configure-options: @@ -290,8 +393,8 @@ General Options .. option:: --disable-gil - Enables **experimental** support for running Python without the - :term:`global interpreter lock` (GIL): free threading build. + Enables support for running Python without the :term:`global interpreter + lock` (GIL): :term:`free-threaded build`. Defines the ``Py_GIL_DISABLED`` macro and adds ``"t"`` to :data:`sys.abiflags`. @@ -370,6 +473,8 @@ Linker options Name for machine-dependent library files. +.. _configure-options-for-dependencies: + Options for third-party dependencies ------------------------------------ @@ -392,12 +497,6 @@ Options for third-party dependencies C compiler and linker flags for ``gdbm``. -.. option:: LIBB2_CFLAGS -.. option:: LIBB2_LIBS - - C compiler and linker flags for ``libb2`` (:ref:`BLAKE2 `), - used by :mod:`hashlib` module, overriding ``pkg-config``. - .. option:: LIBEDIT_CFLAGS .. option:: LIBEDIT_LIBS @@ -445,6 +544,14 @@ Options for third-party dependencies C compiler and linker flags for ``libuuid``, used by :mod:`uuid` module, overriding ``pkg-config``. +.. option:: LIBZSTD_CFLAGS +.. option:: LIBZSTD_LIBS + + C compiler and linker flags for ``libzstd``, used by :mod:`compression.zstd` module, + overriding ``pkg-config``. + + .. versionadded:: 3.14 + .. option:: PANEL_CFLAGS .. option:: PANEL_LIBS @@ -640,6 +747,9 @@ also be used to improve performance. Disable the fast :ref:`mimalloc ` allocator (enabled by default). + This option cannot be used together with :option:`--disable-gil` + because the :term:`free-threaded ` build requires mimalloc. + See also :envvar:`PYTHONMALLOC` environment variable. .. option:: --without-pymalloc @@ -675,6 +785,13 @@ also be used to improve performance. not compiled. This includes both the functionality to schedule code to be executed and the functionality to receive code to be executed. + .. c:macro:: Py_REMOTE_DEBUG + + This macro is defined by default, unless Python is configured with + :option:`--without-remote-debug`. + + Note that even if the macro is defined, remote debugging may not be + available (for example, on an incompatible platform). .. versionadded:: 3.14 @@ -721,9 +838,11 @@ See also the :ref:`Python Development Mode ` and the :option:`--with-trace-refs` configure option. .. versionchanged:: 3.8 - Release builds and debug builds are now ABI compatible: defining the + Release builds are now ABI compatible with debug builds: defining the ``Py_DEBUG`` macro no longer implies the ``Py_TRACE_REFS`` macro (see the - :option:`--with-trace-refs` option). + :option:`--with-trace-refs` option). However, debug builds still expose + more symbols than release builds and code built against a debug build is not + necessarily compatible with a release build. Debug options @@ -784,6 +903,9 @@ Debug options .. option:: --with-address-sanitizer Enable AddressSanitizer memory error detector, ``asan`` (default is no). + To improve ASan detection capabilities you may also want to combine this + with :option:`--without-pymalloc` to disable the specialized small-object + allocator whose allocations are not tracked by ASan. .. versionadded:: 3.6 @@ -845,9 +967,16 @@ Libraries options .. versionchanged:: 3.13 Default to using the installed ``mpdecimal`` library. - .. deprecated-removed:: 3.13 3.15 + .. versionchanged:: 3.15 + + A bundled copy of the library will no longer be selected + implicitly if an installed ``mpdecimal`` library is not found. + In Python 3.15 only, it can still be selected explicitly using + ``--with-system-libmpdec=no`` or ``--without-system-libmpdec``. + + .. deprecated-removed:: 3.13 3.16 A copy of the ``mpdecimal`` library sources will no longer be distributed - with Python 3.15. + with Python 3.16. .. seealso:: :option:`LIBMPDEC_CFLAGS` and :option:`LIBMPDEC_LIBS`. @@ -1377,6 +1506,12 @@ Compiler flags .. versionadded:: 3.7 +.. envvar:: CFLAGS_CEVAL + + Flags used to compile ``Python/ceval.c``. + + .. versionadded:: 3.14.5 + .. envvar:: CCSHARED Compiler flags used to build a shared library. diff --git a/Doc/using/ios.rst b/Doc/using/ios.rst index 7d5c6331bef5ce..5e4033fb6cec7a 100644 --- a/Doc/using/ios.rst +++ b/Doc/using/ios.rst @@ -170,7 +170,7 @@ helpful. To add Python to an iOS Xcode project: 1. Build or obtain a Python ``XCFramework``. See the instructions in - :source:`iOS/README.rst` (in the CPython source distribution) for details on + :source:`Apple/iOS/README.md` (in the CPython source distribution) for details on how to build a Python ``XCFramework``. At a minimum, you will need a build that supports ``arm64-apple-ios``, plus one of either ``arm64-apple-ios-simulator`` or ``x86_64-apple-ios-simulator``. @@ -180,22 +180,19 @@ To add Python to an iOS Xcode project: of your project; however, you can use any other location that you want by adjusting paths as needed. -3. Drag the ``iOS/Resources/dylib-Info-template.plist`` file into your project, - and ensure it is associated with the app target. - -4. Add your application code as a folder in your Xcode project. In the +3. Add your application code as a folder in your Xcode project. In the following instructions, we'll assume that your user code is in a folder named ``app`` in the root of your project; you can use any other location by adjusting paths as needed. Ensure that this folder is associated with your app target. -5. Select the app target by selecting the root node of your Xcode project, then +4. Select the app target by selecting the root node of your Xcode project, then the target name in the sidebar that appears. -6. In the "General" settings, under "Frameworks, Libraries and Embedded +5. In the "General" settings, under "Frameworks, Libraries and Embedded Content", add ``Python.xcframework``, with "Embed & Sign" selected. -7. In the "Build Settings" tab, modify the following: +6. In the "Build Settings" tab, modify the following: - Build Options @@ -211,86 +208,24 @@ To add Python to an iOS Xcode project: * Quoted Include In Framework Header: No -8. Add a build step that copies the Python standard library into your app. In - the "Build Phases" tab, add a new "Run Script" build step *before* the - "Embed Frameworks" step, but *after* the "Copy Bundle Resources" step. Name - the step "Install Target Specific Python Standard Library", disable the - "Based on dependency analysis" checkbox, and set the script content to: +7. Add a build step that processes the Python standard library, and your own + Python binary dependencies. In the "Build Phases" tab, add a new "Run + Script" build step *before* the "Embed Frameworks" step, but *after* the + "Copy Bundle Resources" step. Name the step "Process Python libraries", + disable the "Based on dependency analysis" checkbox, and set the script + content to: .. code-block:: bash - set -e - - mkdir -p "$CODESIGNING_FOLDER_PATH/python/lib" - if [ "$EFFECTIVE_PLATFORM_NAME" = "-iphonesimulator" ]; then - echo "Installing Python modules for iOS Simulator" - rsync -au --delete "$PROJECT_DIR/Python.xcframework/ios-arm64_x86_64-simulator/lib/" "$CODESIGNING_FOLDER_PATH/python/lib/" - else - echo "Installing Python modules for iOS Device" - rsync -au --delete "$PROJECT_DIR/Python.xcframework/ios-arm64/lib/" "$CODESIGNING_FOLDER_PATH/python/lib/" - fi - - Note that the name of the simulator "slice" in the XCframework may be - different, depending the CPU architectures your ``XCFramework`` supports. - -9. Add a second build step that processes the binary extension modules in the - standard library into "Framework" format. Add a "Run Script" build step - *directly after* the one you added in step 8, named "Prepare Python Binary - Modules". It should also have "Based on dependency analysis" unchecked, with - the following script content: + set -e + source $PROJECT_DIR/Python.xcframework/build/build_utils.sh + install_python Python.xcframework app - .. code-block:: bash + If you have placed your XCframework somewhere other than the root of your + project, modify the path to the first argument. - set -e - - install_dylib () { - INSTALL_BASE=$1 - FULL_EXT=$2 - - # The name of the extension file - EXT=$(basename "$FULL_EXT") - # The location of the extension file, relative to the bundle - RELATIVE_EXT=${FULL_EXT#$CODESIGNING_FOLDER_PATH/} - # The path to the extension file, relative to the install base - PYTHON_EXT=${RELATIVE_EXT/$INSTALL_BASE/} - # The full dotted name of the extension module, constructed from the file path. - FULL_MODULE_NAME=$(echo $PYTHON_EXT | cut -d "." -f 1 | tr "/" "."); - # A bundle identifier; not actually used, but required by Xcode framework packaging - FRAMEWORK_BUNDLE_ID=$(echo $PRODUCT_BUNDLE_IDENTIFIER.$FULL_MODULE_NAME | tr "_" "-") - # The name of the framework folder. - FRAMEWORK_FOLDER="Frameworks/$FULL_MODULE_NAME.framework" - - # If the framework folder doesn't exist, create it. - if [ ! -d "$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER" ]; then - echo "Creating framework for $RELATIVE_EXT" - mkdir -p "$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER" - cp "$CODESIGNING_FOLDER_PATH/dylib-Info-template.plist" "$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER/Info.plist" - plutil -replace CFBundleExecutable -string "$FULL_MODULE_NAME" "$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER/Info.plist" - plutil -replace CFBundleIdentifier -string "$FRAMEWORK_BUNDLE_ID" "$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER/Info.plist" - fi - - echo "Installing binary for $FRAMEWORK_FOLDER/$FULL_MODULE_NAME" - mv "$FULL_EXT" "$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER/$FULL_MODULE_NAME" - # Create a placeholder .fwork file where the .so was - echo "$FRAMEWORK_FOLDER/$FULL_MODULE_NAME" > ${FULL_EXT%.so}.fwork - # Create a back reference to the .so file location in the framework - echo "${RELATIVE_EXT%.so}.fwork" > "$CODESIGNING_FOLDER_PATH/$FRAMEWORK_FOLDER/$FULL_MODULE_NAME.origin" - } - - PYTHON_VER=$(ls -1 "$CODESIGNING_FOLDER_PATH/python/lib") - echo "Install Python $PYTHON_VER standard library extension modules..." - find "$CODESIGNING_FOLDER_PATH/python/lib/$PYTHON_VER/lib-dynload" -name "*.so" | while read FULL_EXT; do - install_dylib python/lib/$PYTHON_VER/lib-dynload/ "$FULL_EXT" - done - - # Clean up dylib template - rm -f "$CODESIGNING_FOLDER_PATH/dylib-Info-template.plist" - - echo "Signing frameworks as $EXPANDED_CODE_SIGN_IDENTITY_NAME ($EXPANDED_CODE_SIGN_IDENTITY)..." - find "$CODESIGNING_FOLDER_PATH/Frameworks" -name "*.framework" -exec /usr/bin/codesign --force --sign "$EXPANDED_CODE_SIGN_IDENTITY" ${OTHER_CODE_SIGN_FLAGS:-} -o runtime --timestamp=none --preserve-metadata=identifier,entitlements,flags --generate-entitlement-der "{}" \; - -10. Add Objective C code to initialize and use a Python interpreter in embedded - mode. You should ensure that: +8. Add Objective C code to initialize and use a Python interpreter in embedded + mode. You should ensure that: * UTF-8 mode (:c:member:`PyPreConfig.utf8_mode`) is *enabled*; * Buffered stdio (:c:member:`PyConfig.buffered_stdio`) is *disabled*; @@ -298,9 +233,9 @@ To add Python to an iOS Xcode project: * Signal handlers (:c:member:`PyConfig.install_signal_handlers`) are *enabled*; * System logging (:c:member:`PyConfig.use_system_logger`) is *enabled* (optional, but strongly recommended; this is enabled by default); - * ``PYTHONHOME`` for the interpreter is configured to point at the + * :envvar:`PYTHONHOME` for the interpreter is configured to point at the ``python`` subfolder of your app's bundle; and - * The ``PYTHONPATH`` for the interpreter includes: + * The :envvar:`PYTHONPATH` for the interpreter includes: - the ``python/lib/python3.X`` subfolder of your app's bundle, - the ``python/lib/python3.X/lib-dynload`` subfolder of your app's bundle, and @@ -309,45 +244,52 @@ To add Python to an iOS Xcode project: Your app's bundle location can be determined using ``[[NSBundle mainBundle] resourcePath]``. -Steps 8, 9 and 10 of these instructions assume that you have a single folder of +Steps 7 and 8 of these instructions assume that you have a single folder of pure Python application code, named ``app``. If you have third-party binary modules in your app, some additional steps will be required: * You need to ensure that any folders containing third-party binaries are - either associated with the app target, or copied in as part of step 8. Step 8 - should also purge any binaries that are not appropriate for the platform a - specific build is targeting (i.e., delete any device binaries if you're - building an app targeting the simulator). + either associated with the app target, or are explicitly copied as part of + step 7. Step 7 should also purge any binaries that are not appropriate for + the platform a specific build is targeting (i.e., delete any device binaries + if you're building an app targeting the simulator). -* Any folders that contain third-party binaries must be processed into - framework form by step 9. The invocation of ``install_dylib`` that processes - the ``lib-dynload`` folder can be copied and adapted for this purpose. +* If you're using a separate folder for third-party packages, ensure that + folder is added to the end of the call to ``install_python`` in step 7, and + as part of the :envvar:`PYTHONPATH` configuration in step 8. -* If you're using a separate folder for third-party packages, ensure that folder - is included as part of the ``PYTHONPATH`` configuration in step 10. +* If any of the folders that contain third-party packages will contain ``.pth`` + files, you should add that folder as a *site directory* (using + :meth:`site.addsitedir`), rather than adding to :envvar:`PYTHONPATH` or + :attr:`sys.path` directly. Testing a Python package ------------------------ -The CPython source tree contains :source:`a testbed project ` that +The CPython source tree contains :source:`a testbed project ` that is used to run the CPython test suite on the iOS simulator. This testbed can also be used as a testbed project for running your Python library's test suite on iOS. -After building or obtaining an iOS XCFramework (See :source:`iOS/README.rst` -for details), create a clone of the Python iOS testbed project by running: +After building or obtaining an iOS XCFramework (see :source:`Apple/iOS/README.md` +for details), create a clone of the Python iOS testbed project. If you used the +``Apple`` build script to build the XCframework, you can run: .. code-block:: bash - $ python iOS/testbed clone --framework --app --app app-testbed + $ python cross-build/iOS/testbed clone --app --app app-testbed + +Or, if you've sourced your own XCframework, by running: + +.. code-block:: bash -You will need to modify the ``iOS/testbed`` reference to point to that -directory in the CPython source tree; any folders specified with the ``--app`` -flag will be copied into the cloned testbed project. The resulting testbed will -be created in the ``app-testbed`` folder. In this example, the ``module1`` and -``module2`` would be importable modules at runtime. If your project has -additional dependencies, they can be installed into the -``app-testbed/iOSTestbed/app_packages`` folder (using ``pip install --target -app-testbed/iOSTestbed/app_packages`` or similar). + $ python Apple/testbed clone --platform iOS --framework --app --app app-testbed + +Any folders specified with the ``--app`` flag will be copied into the cloned +testbed project. The resulting testbed will be created in the ``app-testbed`` +folder. In this example, the ``module1`` and ``module2`` would be importable +modules at runtime. If your project has additional dependencies, they can be +installed into the ``app-testbed/Testbed/app_packages`` folder (using ``pip +install --target app-testbed/Testbed/app_packages`` or similar). You can then use the ``app-testbed`` folder to run the test suite for your app, For example, if ``module1.tests`` was the entry point to your test suite, you @@ -369,13 +311,29 @@ You can also open the testbed project in Xcode by running: This will allow you to use the full Xcode suite of tools for debugging. +The arguments used to run the test suite are defined as part of the test plan. +To modify the test plan, select the test plan node of the project tree (it +should be the first child of the root node), and select the "Configurations" +tab. Modify the "Arguments Passed On Launch" value to change the testing +arguments. + +The test plan also disables parallel testing, and specifies the use of the +``Testbed.lldbinit`` file for providing configuration of the debugger. The +default debugger configuration disables automatic breakpoints on the +``SIGINT``, ``SIGUSR1``, ``SIGUSR2``, and ``SIGXFSZ`` signals. + App Store Compliance ==================== The only mechanism for distributing apps to third-party iOS devices is to submit the app to the iOS App Store; apps submitted for distribution must pass Apple's app review process. This process includes a set of automated validation -rules that inspect the submitted application bundle for problematic code. +rules that inspect the submitted application bundle for problematic code. There +are some steps that must be taken to ensure that your app will be able to pass +these validation steps. + +Incompatible code in the standard library +----------------------------------------- The Python standard library contains some code that is known to violate these automated rules. While these violations appear to be false positives, Apple's @@ -386,3 +344,18 @@ The Python source tree contains :source:`a patch file ` that will remove all code that is known to cause issues with the App Store review process. This patch is applied automatically when building for iOS. + +Privacy manifests +----------------- + +In April 2025, Apple introduced a requirement for `certain third-party +libraries to provide a Privacy Manifest +`__. +As a result, if you have a binary module that uses one of the affected +libraries, you must provide an ``.xcprivacy`` file for that library. +OpenSSL is one library affected by this requirement, but there are others. + +If you produce a binary module named ``mymodule.so``, and use you the Xcode +build script described in step 7 above, you can place a ``mymodule.xcprivacy`` +file next to ``mymodule.so``, and the privacy manifest will be installed into +the required location when the binary module is converted into a framework. diff --git a/Doc/using/mac.rst b/Doc/using/mac.rst index 4b6c884f3d4f25..6490cec91bf4aa 100644 --- a/Doc/using/mac.rst +++ b/Doc/using/mac.rst @@ -1,3 +1,4 @@ +.. highlight:: none .. _using-on-mac: @@ -20,13 +21,6 @@ the Pythons provided by the CPython release team for download from the `python.org website `_. See :ref:`alternative_bundles` for some other options. -.. |usemac_x_dot_y| replace:: 3.13 -.. |usemac_python_x_dot_y_literal| replace:: ``python3.13`` -.. |usemac_python_x_dot_y_t_literal| replace:: ``python3.13t`` -.. |usemac_python_x_dot_y_t_literal_config| replace:: ``python3.13t-config`` -.. |usemac_applications_folder_name| replace:: ``Python 3.13`` -.. |usemac_applications_folder_version| replace:: ``/Applications/Python 3.13/`` - .. _getting-osx: .. _getting-and-installing-macpython: @@ -46,7 +40,7 @@ Current installers provide a `universal2 binary `_ build of Python which runs natively on all Macs (Apple Silicon and Intel) that are supported by a wide range of macOS versions, -currently typically from at least **macOS 10.13 High Sierra** on. +currently typically from at least **macOS 10.15 Catalina** on. The downloaded file is a standard macOS installer package file (``.pkg``). File integrity information (checksum, size, sigstore signature, etc) for each file is included @@ -64,7 +58,7 @@ Clicking on the **Continue** button brings up the **Read Me** for this installer Besides other important information, the **Read Me** documents which Python version is going to be installed and on what versions of macOS it is supported. You may need to scroll through to read the whole file. By default, this **Read Me** will also be -installed in |usemac_applications_folder_version| and available to read anytime. +installed in |applications_python_version_literal| and available to read anytime. .. image:: mac_installer_02_readme.png @@ -83,7 +77,7 @@ display. For most uses, the standard set of installation operations is appropria By pressing the **Customize** button, you can choose to omit or select certain package components of the installer. Click on each package name to see a description of what it installs. -To also install support for the optional experimental free-threaded feature, +To also install support for the optional free-threaded feature, see :ref:`install-freethreaded-macos`. .. image:: mac_installer_05_custom_install.png @@ -97,7 +91,7 @@ When the installation is complete, the **Summary** window will appear. .. image:: mac_installer_06_summary.png Double-click on the :command:`Install Certificates.command` -icon or file in the |usemac_applications_folder_version| window to complete the +icon or file in the |applications_python_version_literal| window to complete the installation. .. image:: mac_installer_07_applications.png @@ -114,7 +108,7 @@ Close this terminal window and the installer window. A default install will include: -* A |usemac_applications_folder_name| folder in your :file:`Applications` folder. In here +* A |python_version_literal| folder in your :file:`Applications` folder. In here you find :program:`IDLE`, the development environment that is a standard part of official Python distributions; and :program:`Python Launcher`, which handles double-clicking Python scripts from the macOS `Finder `_. @@ -141,7 +135,7 @@ How to run a Python script There are two ways to invoke the Python interpreter. If you are familiar with using a Unix shell in a terminal -window, you can invoke |usemac_python_x_dot_y_literal| or ``python3`` optionally +window, you can invoke |python_x_dot_y_literal| or ``python3`` optionally followed by one or more command line options (described in :ref:`using-on-general`). The Python tutorial also has a useful section on :ref:`using Python interactively from a shell `. @@ -160,7 +154,7 @@ for more information. To run a Python script file from the terminal window, you can invoke the interpreter with the name of the script file: - |usemac_python_x_dot_y_literal| ``myscript.py`` + |python_x_dot_y_literal| ``myscript.py`` To run your script from the Finder, you can either: @@ -259,20 +253,20 @@ Advanced Topics Installing Free-threaded Binaries --------------------------------- -.. versionadded:: 3.13 (Experimental) - -.. note:: - - Everything described in this section is considered experimental, - and should be expected to change in future releases. +.. versionadded:: 3.13 The ``python.org`` :ref:`Python for macOS ` installer package can optionally install an additional build of -Python |usemac_x_dot_y| that supports :pep:`703`, the experimental free-threading feature +Python |version| that supports :pep:`703`, the free-threading feature (running with the :term:`global interpreter lock` disabled). Check the release page on ``python.org`` for possible updated information. -Because this feature is still considered experimental, the support for it +The free-threaded mode is working and continues to be improved, but +there is some additional overhead in single-threaded workloads compared +to the regular build. Additionally, third-party packages, in particular ones +with an :term:`extension module`, may not be ready for use in a +free-threaded build, and will re-enable the :term:`GIL`. +Therefore, the support for free-threading is not installed by default. It is packaged as a separate install option, available by clicking the **Customize** button on the **Installation Type** step of the installer as described above. @@ -282,46 +276,54 @@ step of the installer as described above. If the box next to the **Free-threaded Python** package name is checked, a separate :file:`PythonT.framework` will also be installed alongside the normal :file:`Python.framework` in :file:`/Library/Frameworks`. -This configuration allows a free-threaded Python |usemac_x_dot_y| build to co-exist -on your system with a traditional (GIL only) Python |usemac_x_dot_y| build with -minimal risk while installing or testing. This installation layout is itself -experimental and is subject to change in future releases. +This configuration allows a free-threaded Python |version| build to co-exist +on your system with a traditional (GIL only) Python |version| build with +minimal risk while installing or testing. This installation layout may +change in future releases. Known cautions and limitations: - The **UNIX command-line tools** package, which is selected by default, - will install links in :file:`/usr/local/bin` for |usemac_python_x_dot_y_t_literal|, - the free-threaded interpreter, and |usemac_python_x_dot_y_t_literal_config|, + will install links in :file:`/usr/local/bin` for |python_x_dot_y_t_literal|, + the free-threaded interpreter, and |python_x_dot_y_t_literal_config|, a configuration utility which may be useful for package builders. Since :file:`/usr/local/bin` is typically included in your shell ``PATH``, in most cases no changes to your ``PATH`` environment variables should - be needed to use |usemac_python_x_dot_y_t_literal|. + be needed to use |python_x_dot_y_t_literal|. - For this release, the **Shell profile updater** package and the - :file:`Update Shell Profile.command` in |usemac_applications_folder_version| + :file:`Update Shell Profile.command` in |applications_python_version_literal| do not support the free-threaded package. - The free-threaded build and the traditional build have separate search paths and separate :file:`site-packages` directories so, by default, if you need a package available in both builds, it may need to be installed in both. The free-threaded package will install a separate instance of :program:`pip` for use - with |usemac_python_x_dot_y_t_literal|. + with |python_x_dot_y_t_literal|. - To install a package using :command:`pip` without a :command:`venv`: - |usemac_python_x_dot_y_t_literal| ``-m pip install `` + .. parsed-literal:: + + python\ |version|\ t -m pip install - When working with multiple Python environments, it is usually safest and easiest to :ref:`create and use virtual environments `. This can avoid possible command name conflicts and confusion about which Python is in use: - |usemac_python_x_dot_y_t_literal| ``-m venv `` + .. parsed-literal:: + + python\ |version|\ t -m venv + then :command:`activate`. - To run a free-threaded version of IDLE: - |usemac_python_x_dot_y_t_literal| ``-m idlelib`` + .. parsed-literal:: + + python\ |version|\ t -m idlelib + - The interpreters in both builds respond to the same :ref:`PYTHON environment variables ` @@ -337,28 +339,28 @@ Known cautions and limitations: thus it only needs to be run once. - If you cannot depend on the link in ``/usr/local/bin`` pointing to the - ``python.org`` free-threaded |usemac_python_x_dot_y_t_literal| (for example, if you want + ``python.org`` free-threaded |python_x_dot_y_t_literal| (for example, if you want to install your own version there or some other distribution does), you can explicitly set your shell ``PATH`` environment variable to include the ``PythonT`` framework ``bin`` directory: - .. code-block:: sh + .. parsed-literal:: - export PATH="/Library/Frameworks/PythonT.framework/Versions/3.13/bin":"$PATH" + export PATH="/Library/Frameworks/PythonT.framework/Versions/\ |version|\ /bin":"$PATH" The traditional framework installation by default does something similar, except for :file:`Python.framework`. Be aware that having both framework ``bin`` directories in ``PATH`` can lead to confusion if there are duplicate names - like ``python3.13`` in both; which one is actually used depends on the order + like |python_x_dot_y_literal| in both; which one is actually used depends on the order they appear in ``PATH``. The ``which python3.x`` or ``which python3.xt`` commands can show which path is being used. Using virtual environments can help avoid such ambiguities. Another option might be to create a shell :command:`alias` to the desired interpreter, like: - .. code-block:: sh + .. parsed-literal:: - alias py3.13="/Library/Frameworks/Python.framework/Versions/3.13/bin/python3.13" - alias py3.13t="/Library/Frameworks/PythonT.framework/Versions/3.13/bin/python3.13t" + alias py\ |version|\ ="/Library/Frameworks/Python.framework/Versions/\ |version|\ /bin/python\ |version|\ " + alias py\ |version|\ t="/Library/Frameworks/PythonT.framework/Versions/\ |version|\ /bin/python\ |version|\ t" Installing using the command line --------------------------------- @@ -369,22 +371,22 @@ the macOS command line :command:`installer` utility lets you select non-default options, too. If you are not familiar with :command:`installer`, it can be somewhat cryptic (see :command:`man installer` for more information). As an example, the following shell snippet shows one way to do it, -using the ``3.13.0b2`` release and selecting the free-threaded interpreter +using the |x_dot_y_b2_literal| release and selecting the free-threaded interpreter option: -.. code-block:: sh +.. parsed-literal:: - RELEASE="python-3.13.0b2-macos11.pkg" + RELEASE="python-\ |version|\ 0b2-macos11.pkg" # download installer pkg - curl -O https://www.python.org/ftp/python/3.13.0/${RELEASE} + curl -O \https://www.python.org/ftp/python/\ |version|\ .0/${RELEASE} # create installer choicechanges to customize the install: - # enable the PythonTFramework-3.13 package + # enable the PythonTFramework-\ |version|\ package # while accepting the other defaults (install all other packages) cat > ./choicechanges.plist < - + @@ -393,7 +395,7 @@ option: choiceAttribute selected choiceIdentifier - org.python.Python.PythonTFramework-3.13 + org.python.Python.PythonTFramework-\ |version|\ @@ -404,19 +406,19 @@ option: You can then test that both installer builds are now available with something like: -.. code-block:: console +.. parsed-literal:: $ # test that the free-threaded interpreter was installed if the Unix Command Tools package was enabled - $ /usr/local/bin/python3.13t -VV - Python 3.13.0b2 experimental free-threading build (v3.13.0b2:3a83b172af, Jun 5 2024, 12:57:31) [Clang 15.0.0 (clang-1500.3.9.4)] + $ /usr/local/bin/python\ |version|\ t -VV + Python \ |version|\ .0b2 free-threading build (v\ |version|\ .0b2:3a83b172af, Jun 5 2024, 12:57:31) [Clang 15.0.0 (clang-1500.3.9.4)] $ # and the traditional interpreter - $ /usr/local/bin/python3.13 -VV - Python 3.13.0b2 (v3.13.0b2:3a83b172af, Jun 5 2024, 12:50:24) [Clang 15.0.0 (clang-1500.3.9.4)] + $ /usr/local/bin/python\ |version|\ -VV + Python \ |version|\ .0b2 (v\ |version|\ .0b2:3a83b172af, Jun 5 2024, 12:50:24) [Clang 15.0.0 (clang-1500.3.9.4)] $ # test that they are also available without the prefix if /usr/local/bin is on $PATH - $ python3.13t -VV - Python 3.13.0b2 experimental free-threading build (v3.13.0b2:3a83b172af, Jun 5 2024, 12:57:31) [Clang 15.0.0 (clang-1500.3.9.4)] - $ python3.13 -VV - Python 3.13.0b2 (v3.13.0b2:3a83b172af, Jun 5 2024, 12:50:24) [Clang 15.0.0 (clang-1500.3.9.4)] + $ python\ |version|\ t -VV + Python \ |version|\ .0b2 free-threading build (v\ |version|\ .0b2:3a83b172af, Jun 5 2024, 12:57:31) [Clang 15.0.0 (clang-1500.3.9.4)] + $ python\ |version|\ -VV + Python \ |version|\ .0b2 (v\ |version|\ .0b2:3a83b172af, Jun 5 2024, 12:50:24) [Clang 15.0.0 (clang-1500.3.9.4)] .. note:: diff --git a/Doc/using/mac_installer_07_applications.png b/Doc/using/mac_installer_07_applications.png index 940219cad6f61c..c8b3aa1099adfc 100644 Binary files a/Doc/using/mac_installer_07_applications.png and b/Doc/using/mac_installer_07_applications.png differ diff --git a/Doc/using/unix.rst b/Doc/using/unix.rst index 9ec4e3419321a4..a9950ef7525497 100644 --- a/Doc/using/unix.rst +++ b/Doc/using/unix.rst @@ -84,11 +84,17 @@ On FreeBSD and OpenBSD Building Python =============== +.. seealso:: + + If you want to contribute to CPython, refer to the + `devguide `_, + which includes build instructions and other tips on setting up environment. + If you want to compile CPython yourself, first thing you should do is get the `source `_. You can download either the -latest release's source or just grab a fresh `clone -`_. (If you want -to contribute patches, you will need a clone.) +latest release's source or grab a fresh `clone +`_. +You will also need to install the :ref:`build requirements `. The build process consists of the usual commands:: diff --git a/Doc/using/win_install_freethreaded.png b/Doc/using/win_install_freethreaded.png index 0aa01c1df6e051..12b89c0165d994 100644 Binary files a/Doc/using/win_install_freethreaded.png and b/Doc/using/win_install_freethreaded.png differ diff --git a/Doc/using/win_installer.png b/Doc/using/win_installer.png index 03bf2d7b16c599..fc9605a79cfcc5 100644 Binary files a/Doc/using/win_installer.png and b/Doc/using/win_installer.png differ diff --git a/Doc/using/windows.rst b/Doc/using/windows.rst index 74d6db5d7d1a98..46eebaebd5d7f3 100644 --- a/Doc/using/windows.rst +++ b/Doc/using/windows.rst @@ -4,6 +4,8 @@ .. _Microsoft Store app: https://apps.microsoft.com/detail/9NQ7512CXL7T +.. _legacy launcher: https://www.python.org/ftp/python/3.14.0/win32/launcher.msi + .. _using-on-windows: ************************* @@ -60,7 +62,7 @@ packages. .. _windows-path-mod: .. _launcher: -Python Install Manager +Python install manager ====================== Installation @@ -77,34 +79,33 @@ To install the file downloaded from python.org, either double-click and select "Install", or run ``Add-AppxPackage `` in Windows Powershell. After installation, the ``python``, ``py``, and ``pymanager`` commands should be -available. If they are not, click Start and search for "Manage app execution -aliases". This settings page will let you enable the relevant commands. They -will be labelled "Python (default)", "Python (default windowed)", and "Python -install manager". - -If you have existing installations of Python, or you have modified your -:envvar:`PATH` variable, you may need to remove them or undo the modifications -in order for the commands to work. Old versions of Python can be reinstalled -using the Python install manager. +available. If you have existing installations of Python, or you have modified +your :envvar:`PATH` variable, you may need to remove them or undo the +modifications. See :ref:`pymanager-troubleshoot` for more help with fixing +non-working commands. When you first install a runtime, you will likely be prompted to add a directory to your :envvar:`PATH`. This is optional, if you prefer to use the ``py`` command, but is offered for those who prefer the full range of aliases (such as ``python3.14.exe``) to be available. The directory will be -:file:`%LocalAppData%\Python\bin` by default, but may be customized by an +:file:`%LocalAppData%\\Python\\bin` by default, but may be customized by an administrator. Click Start and search for "Edit environment variables for your account" for the system settings page to add the path. +Each Python runtime you install will have its own directory for scripts. These +also need to be added to :envvar:`PATH` if you want to use them. + The Python install manager will be automatically updated to new releases. This does not affect any installs of Python runtimes. Uninstalling the Python install manager does not uninstall any Python runtimes. If you are not able to install an MSIX in your context, for example, you are -using automated deployment software that does not support it, please see -:ref:`pymanager-advancedinstall` below for more information. +using automated deployment software that does not support it, or are targeting +Windows Server 2019, please see :ref:`pymanager-advancedinstall` below for more +information. -Basic Use +Basic use --------- The recommended command for launching Python is ``python``, which will either @@ -125,12 +126,11 @@ is also an unambiguous ``pymanager`` command. Scripted installs that are intending to use Python install manager should consider using ``pymanager``, due to the lower chance of encountering a conflict with existing installs. The only difference between the two commands is when running without any arguments: -``py`` will install and launch your default interpreter, while ``pymanager`` -will display help (``pymanager exec ...`` provides equivalent behaviour to -``py ...``). +``py`` will launch your default interpreter, while ``pymanager`` will display +help (``pymanager exec ...`` provides equivalent behaviour to ``py ...``). Each of these commands also has a windowed version that avoids creating a -console window. These are ``pyw``, ``pythonw`` and ``pymanagerw``. A ``python3`` +console window. These are ``pyw``, ``pythonw`` and ``pywmanager``. A ``python3`` command is also included that mimics the ``python`` command. It is intended to catch accidental uses of the typical POSIX command on Windows, but is not meant to be widely used or recommended. @@ -147,6 +147,10 @@ want to be passed to the runtime (such as script files or the module to launch): $> py -m this ... +The default runtime can be overridden with the :envvar:`PYTHON_MANAGER_DEFAULT` +environment variable, or a configuration file. See :ref:`pymanager-config` for +information about configuration settings. + To launch a specific runtime, the ``py`` command accepts a ``-V:`` option. This option must be specified before any others. The tag is part or all of the identifier for the runtime; for those from the CPython team, it looks like the @@ -160,7 +164,9 @@ omitted in cases where the tag refers to an official release and starts with $> py -V:3-arm64 ... Runtimes from other distributors may require the *company* to be included as -well. This should be separated from the tag by a slash, and may be a prefix. +well. +It should be separated from the tag by a slash (either ``/`` or ``\``), +and may be shortened to any prefix of its full value. Specifying the company is optional when it is ``PythonCore``, and specifying the tag is optional (but not the slash) when you want the latest release from a specific company. @@ -182,15 +188,14 @@ that virtual environment. In this scenario, the ``python`` command was likely already overridden and none of these checks occurred. However, this behaviour ensures that the ``py`` command can be used interchangeably. -When you launch either ``python`` or ``py`` but do not have any runtimes -installed, and the requested version is the default, it will be installed -automatically and then launched. Otherwise, the requested version will be -installed if automatic installation is configured (most likely by setting -``PYTHON_MANAGER_AUTOMATIC_INSTALL`` to ``true``), or if the ``py exec`` or -``pymanager exec`` forms of the command were used. +When no runtimes are installed, any launch command will try to install the +requested version and launch it. However, after any version is installed, only +the ``py exec ...`` and ``pymanager exec ...`` commands will install if the +requested version is absent. Other forms of commands will display an error and +direct you to use ``py install`` first. -Command Help +Command help ------------ The ``py help`` command will display the full list of supported commands, along @@ -215,7 +220,7 @@ override multiple settings at once. See :ref:`pymanager-config` below for more information about these files. -Listing Runtimes +Listing runtimes ---------------- .. code:: @@ -256,7 +261,7 @@ For compatibility with the old launcher, the ``--list``, ``--list-paths``, additional options, and will produce legacy formatted output. -Installing Runtimes +Installing runtimes ------------------- .. code:: @@ -284,18 +289,36 @@ work. Passing ``--dry-run`` will generate output and logs, but will not modify any installs. +Passing ``--refresh`` will update all registrations for installed runtimes. This +will recreate Start menu shortcuts, registry keys, and global aliases (such as +``python3.14.exe`` or for any installed scripts). These are automatically +refreshed on installation of any runtime, but may need to be manually refreshed +after installing packages. + In addition to the above options, the ``--target`` option will extract the -runtime to the specified directory instead of doing a normal install. This is -useful for embedding runtimes into larger applications. +runtime to the specified directory instead of doing a normal install. +This is useful for embedding runtimes into larger applications. +Unlike a normal install, ``py`` will not be aware of the extracted runtime, +and no Start menu or other shortcuts will be created. +To launch the runtime, directly execute the main executable (typically +``python.exe``) in the target directory. .. code:: $> py install ... [-t=|--target=] +The ``py exec`` command will install the requested runtime if it is not already +present. This is controlled by the ``automatic_install`` configuration +(:envvar:`PYTHON_MANAGER_AUTOMATIC_INSTALL`), and is enabled by default. +If no runtimes are available at all, all launch commands will do an automatic +install if the configuration setting allows. This is to ensure a good experience +for new users, but should not generally be relied on rather than using the +``py exec`` command or explicit install commands. + .. _pymanager-offline: -Offline Installs +Offline installs ---------------- To perform offline installs of Python, you will need to first create an offline @@ -327,7 +350,7 @@ In this way, Python runtimes can be installed and managed on a machine without access to the internet. -Uninstalling Runtimes +Uninstalling runtimes --------------------- .. code:: @@ -373,59 +396,125 @@ overridden installs may resolve settings differently. A global configuration file may be configured by an administrator, and would be read first. The user configuration file is stored at -:file:`%AppData%\\Python\\pymanager.json` (by default) and is read next, +:file:`%AppData%\\Python\\pymanager.json` +(note that this location is under ``Roaming``, not ``Local``) and is read next, overwriting any settings from earlier files. An additional configuration file may be specified as the ``PYTHON_MANAGER_CONFIG`` environment variable or the ``--config`` command line option (but not both). +These locations may be modified by administrative customization options listed +later. The following settings are those that are considered likely to be modified in normal use. Later sections list those that are intended for administrative customization. -.. csv-table:: Standard configuration options - :header: "Config Key", "Environment Variable", "Description" - :widths: 2, 2, 4 - - ``default_tag``,``PYTHON_MANAGER_DEFAULT``,"The preferred default - version to launch or install. By default, this is interpreted as the most - recent non-prerelease version from the CPython team. - " - ``default_platform``,``PYTHON_MANAGER_DEFAULT_PLATFORM``,"The preferred - default platform to launch or install. This is treated as a suffix to the - specified tag, such that ``py -V:3.14`` would prefer an install for - ``3.14-64`` if it exists (and ``default_platform`` is ``-64``), but will use - ``3.14`` if no tagged install exists. - " - ``logs_dir``,``PYTHON_MANAGER_LOGS``,"The location where log files are - written. By default, :file:`%TEMP%`. - " - ``automatic_install``,``PYTHON_MANAGER_AUTOMATIC_INSTALL``,"True to - allow automatic installs when specifying a particular runtime to launch. - By default, true. - " - ``include_unmanaged``,``PYTHON_MANAGER_INCLUDE_UNMANAGED``,"True to - allow listing and launching runtimes that were not installed by the Python - install manager, or false to exclude them. By default, true. - " - ``shebang_can_run_anything``,"``PYTHON_MANAGER_SHEBANG_CAN_RUN_ANYTHING`` - ","True to allow shebangs in ``.py`` files to launch applications other than - Python runtimes, or false to prevent it. By default, true. - " - ``log_level``,"``PYMANAGER_VERBOSE``, ``PYMANAGER_DEBUG``","Set - the default level of output (0-50) By default, 20. Lower values produce more - output. The environment variables are boolean, and may produce additional - output during startup that is later suppressed by other configuration. - " - ``confirm``,``PYTHON_MANAGER_CONFIRM``,"True to confirm certain actions - before taking them (such as uninstall), or false to skip the confirmation. By - default, true. - " - ``install.source``,``PYTHON_MANAGER_SOURCE_URL``,"Override the index - feed to obtain new installs from. - " - ``list.format``,``PYTHON_MANAGER_LIST_FORMAT``,"Specify the default - format used by the ``py list`` command. By default, ``table``. - " +.. Sphinx bug with text writer; remove widths & caption temporarily +.. :widths: 2, 2, 4 + +.. rubric:: Standard configuration options + +.. list-table:: + :header-rows: 1 + + * - Config Key + - Environment Variable + - Description + + * - ``default_tag`` + - .. envvar:: PYTHON_MANAGER_DEFAULT + - The preferred default version to launch or install. + By default, this is interpreted as the most recent non-prerelease version + from the CPython team. + + * - ``default_platform`` + - ``PYTHON_MANAGER_DEFAULT_PLATFORM`` + - The preferred default platform to launch or install. + This is treated as a suffix to the specified tag, such that ``py -V:3.14`` + would prefer an install for ``3.14-64`` if it exists + (and ``default_platform`` is ``-64``), + but will use ``3.14`` if no tagged install exists. + + * - ``logs_dir`` + - ``PYTHON_MANAGER_LOGS`` + - The location where log files are written. + By default, :file:`%TEMP%`. + + * - ``automatic_install`` + - .. envvar:: PYTHON_MANAGER_AUTOMATIC_INSTALL + - True to allow automatic installs when using ``py exec`` to launch (or + ``py`` when no runtimes are installed yet). + Other commands will not automatically install, regardless of this + setting. + By default, true. + + * - ``include_unmanaged`` + - ``PYTHON_MANAGER_INCLUDE_UNMANAGED`` + - True to allow listing and launching runtimes that were not installed + by the Python install manager, or false to exclude them. + By default, true. + + * - ``shebang_can_run_anything`` + - ``PYTHON_MANAGER_SHEBANG_CAN_RUN_ANYTHING`` + - True to allow shebangs in ``.py`` files to launch applications other than + Python runtimes, or false to prevent it. + By default, true. + + * - ``shebang_templates`` + - (none) + - Mapping from shebang line template to alternative command, such as + ``py -V:`` or a substitute string. + See :ref:`pymanager-shebang` for more details. + + * - ``log_level`` + - ``PYMANAGER_VERBOSE``, ``PYMANAGER_DEBUG`` + - Set the default level of output (0-50). + By default, 20. + Lower values produce more output. + The environment variables are boolean, and may produce additional + output during startup that is later suppressed by other configuration. + + * - ``confirm`` + - ``PYTHON_MANAGER_CONFIRM`` + - True to confirm certain actions before taking them (such as uninstall), + or false to skip the confirmation. + By default, true. + + * - ``install.source`` + - ``PYTHON_MANAGER_SOURCE_URL`` + - Override the index feed to obtain new installs from. + + * - ``install.enable_entrypoints`` + - (none) + - True to generate global commands for installed packages (such as + ``pip.exe``). These are defined by the packages themselves. + If set to false, only the Python interpreter has global commands created. + By default, true. You should run ``py install --refresh`` after changing + this setting. + + * - ``list.format`` + - ``PYTHON_MANAGER_LIST_FORMAT`` + - Specify the default format used by the ``py list`` command. + By default, ``table``. + + * - ``install_dir`` + - (none) + - Specify the root directory that runtimes will be installed into. + If you change this setting, previously installed runtimes will not be + usable unless you move them to the new location. + + * - ``global_dir`` + - (none) + - Specify the directory where global commands (such as ``python3.14.exe`` + and ``pip.exe``) are stored. + This directory should be added to your :envvar:`PATH` to make the + commands available from your terminal. + + * - ``download_dir`` + - (none) + - Specify the directory where downloaded files are stored. + This directory is a temporary cache, and can be cleaned up from time to + time. + Dotted names should be nested inside JSON objects, for example, ``list.format`` would be specified as ``{"list": {"format": "table"}}``. @@ -469,6 +558,10 @@ directory (which you may have added to your :envvar:`PATH` environment variable) can be used in a shebang, even if it is not on your :envvar:`PATH`. This allows the use of shebangs like ``/usr/bin/python3.12`` to select a particular runtime. +If no runtimes are installed, or if automatic installation is enabled, the +requested runtime will be installed if necessary. See :ref:`pymanager-config` +for information about configuration settings. + The ``/usr/bin/env`` form of shebang line will also search the :envvar:`PATH` environment variable for unrecognized commands. This corresponds to the behaviour of the Unix ``env`` program, which performs the same search, but @@ -485,21 +578,50 @@ which the path to the script and any additional arguments will be appended. This functionality may be disabled by the ``shebang_can_run_anything`` configuration option. -.. note: +Since version 26.3 of the Python install manager, custom shebang templates may +be added to your configuration file. Add the ``shebang_templates`` object with +one member for each template (the string to match) and the command to use when +the template is matched. Most commands should be ``py -V:`` (or ``pyw``) to +launch one of your installed runtimes. The ``py -3.`` form is also +allowed, as is a plain ``py`` to launch the default. No other arguments are +supported. + +.. code:: json5 + + { + "shebang_templates": { + "/usr/bin/python": "py", + "/usr/bin/my_custom_python": "py -V:MyCustomPython/3" + } + } + +If the substitute command is not ``py`` or ``pyw``, it will be written back into +the shebang and regular handling continues. If launching arbitrary executables +is permitted, then providing a full path will allow you to redirect from Python +to any executable. The template should match either the entire line (ignoring +leading and trailing whitespace), or up to the first space in the shebang line. + + +.. note:: The behaviour of shebangs in the Python install manager is subtly different from the previous ``py.exe`` launcher, and the old configuration options no longer apply. If you are specifically reliant on the old behaviour or - configuration, we recommend keeping the legacy launcher. It may be - `downloaded independently `_ - and installed on its own. The legacy launcher's ``py`` command will override - PyManager's one, and you will need to use ``pymanager`` commands for - installing and uninstalling. + configuration, we recommend installing the `legacy launcher`_. The legacy + launcher's ``py`` command will override PyManager's one by default, and you + will need to use ``pymanager`` commands for installing and uninstalling. +.. _Add-AppxPackage: https://learn.microsoft.com/powershell/module/appx/add-appxpackage + +.. _Remove-AppxPackage: https://learn.microsoft.com/powershell/module/appx/remove-appxpackage + +.. _Add-AppxProvisionedPackage: https://learn.microsoft.com/powershell/module/dism/add-appxprovisionedpackage + +.. _PackageManager: https://learn.microsoft.com/uwp/api/windows.management.deployment.packagemanager .. _pymanager-advancedinstall: -Advanced Installation +Advanced installation --------------------- For situations where an MSIX cannot be installed, such as some older @@ -509,6 +631,11 @@ per-machine installs to its default location in Program Files. It will attempt to modify the system :envvar:`PATH` environment variable to include this install location, but be sure to validate this on your configuration. +.. note:: + + Windows Server 2019 is the only version of Windows that CPython supports that + does not support MSIX. For Windows Server 2019, you should use the MSI. + Be aware that the MSI package does not bundle any runtimes, and so is not suitable for installs into offline environments without also creating an offline install index. See :ref:`pymanager-offline` and :ref:`pymanager-admin-config` @@ -529,29 +656,66 @@ depending on whether it was installed from python.org or through the Windows Store. Attempting to run the executable directly from Program Files is not recommended. -To programmatically install or uninstall the MSIX without using your -distribution platform's native support, the `Add-AppxPackage -`_ and -`Remove-AppxPackage `_ -PowerShell cmdlets are simplest to use: +To programmatically install the Python install manager, it is easiest to use +WinGet, which is included with all supported versions of Windows: -.. code:: +.. code-block:: powershell + + $> winget install 9NQ7512CXL7T -e --accept-package-agreements --disable-interactivity + + # Optionally run the configuration checker and accept all changes + $> py install --configure -y + +To download the Python install manager and install on another machine, the +following WinGet command will download the required files from the Store to your +Downloads directory (add ``-d `` to customize the output location). +This also generates a YAML file that appears to be unnecessary, as the +downloaded MSIX can be installed by launching or using the commands below. + +.. code-block:: powershell + + $> winget download 9NQ7512CXL7T -e --skip-license --accept-package-agreements --accept-source-agreements + +To programmatically install or uninstall an MSIX using only PowerShell, the +`Add-AppxPackage`_ and `Remove-AppxPackage`_ PowerShell cmdlets are recommended: + +.. code-block:: powershell $> Add-AppxPackage C:\Downloads\python-manager-25.0.msix ... $> Get-AppxPackage PythonSoftwareFoundation.PythonManager | Remove-AppxPackage -The native APIs for package management may be found on the Windows -`PackageManager `_ -class. The :func:`!AddPackageAsync` method installs for the current user, or use -:func:`!StagePackageAsync` followed by :func:`!ProvisionPackageForAllUsersAsync` -to install the Python install manager for all users from the MSIX package. Users -will still need to install their own copies of Python itself, as there is no way -to trigger those installs without being a logged in user. +The latest release can be downloaded and installed by Windows by passing the +AppInstaller file to the Add-AppxPackage command. This installs using the MSIX +on python.org, and is only recommended for cases where installing via the Store +(interactively or using WinGet) is not possible. + +.. code-block:: powershell + + $> Add-AppxPackage -AppInstallerFile https://www.python.org/ftp/python/pymanager/pymanager.appinstaller + +Other tools and APIs may also be used to provision an MSIX package for all users +on a machine, but Python does not consider this a supported scenario. We suggest +looking into the PowerShell `Add-AppxProvisionedPackage`_ cmdlet, the native +Windows `PackageManager`_ class, or the documentation and support for your +deployment tool. + +Regardless of the install method, users will still need to install their own +copies of Python itself, as there is no way to trigger those installs without +being a logged in user. When using the MSIX, the latest version of Python will +be available for all users to install without network access. + +Note that the MSIX downloadable from the Store and from the Python website are +subtly different and cannot be installed at the same time. Wherever possible, +we suggest using the above WinGet commands to download the package from the +Store to reduce the risk of setting up conflicting installs. There are no +licensing restrictions on the Python install manager that would prevent using +the Store package in this way. + .. _pymanager-admin-config: -Administrative Configuration +Administrative configuration ---------------------------- There are a number of options that may be useful for administrators to override @@ -581,60 +745,89 @@ variable will be used instead. Configuration settings that are paths are interpreted as relative to the directory containing the configuration file that specified them. -.. csv-table:: Administrative configuration options - :header: "Config Key", "Description" - :widths: 1, 4 - - ``base_config``,"The highest priority configuration file to read. Note that - only the built-in configuration file and the registry can modify this - setting. - " - ``user_config``,"The second configuration file to read. - " - ``additional_config``,"The third configuration file to read. - " - ``registry_override_key``,"Registry location to check for overrides. Note - that only the built-in configuration file can modify this setting. - " - ``bundled_dir``,"Read-only directory containing locally cached files. - " - ``install.fallback_source``,"Path or URL to an index to consult when the - main index cannot be accessed. - " - ``install.enable_shortcut_kinds``,"Comma-separated list of shortcut kinds - to allow (e.g. ``""pep514,start""``). Enabled shortcuts may still be disabled - by ``disable_shortcut_kinds``. - " - ``install.disable_shortcut_kinds``,"Comma-separated list of shortcut kinds - to exclude (e.g. ``""pep514,start""``). Disabled shortcuts are not - reactivated by ``enable_shortcut_kinds``. - " - ``pep514_root``,"Registry location to read and write PEP 514 entries into. - By default, :file:`HKEY_CURRENT_USER\\Software\\Python`. - " - ``start_folder``,"Start menu folder to write shortcuts into. By default, - ``Python``. This path is relative to the user's Programs folder. - " - ``virtual_env``,"Path to the active virtual environment. By default, this - is ``%VIRTUAL_ENV%``, but may be set empty to disable venv detection. - " - ``shebang_can_run_anything_silently``,"True to suppress visible warnings - when a shebang launches an application other than a Python runtime. - " +.. Sphinx bug with text writer; remove widths & caption temporarily +.. :widths: 1, 4 -.. _install-freethreaded-windows: +.. rubric:: Administrative configuration options -Installing Free-threaded Binaries ---------------------------------- +.. list-table:: + :header-rows: 1 -.. versionadded:: 3.13 (Experimental) + * - Config Key + - Description -.. note:: + * - ``base_config`` + - The highest priority configuration file to read. + Note that only the built-in configuration file and the registry can + modify this setting. + + * - ``user_config`` + - The second configuration file to read. + + * - ``additional_config`` + - The third configuration file to read. + + * - ``registry_override_key`` + - Registry location to check for overrides. + Note that only the built-in configuration file can modify this setting. + + * - ``bundled_dir`` + - Read-only directory containing locally cached files. + + * - ``install.fallback_source`` + - Path or URL to an index to consult when the main index cannot be accessed. + + * - ``install.enable_shortcut_kinds`` + - Comma-separated list of shortcut kinds to allow (e.g. ``"pep514,start"``). + Enabled shortcuts may still be disabled by ``disable_shortcut_kinds``. + + * - ``install.disable_shortcut_kinds`` + - Comma-separated list of shortcut kinds to exclude + (e.g. ``"pep514,start"``). + Disabled shortcuts are not reactivated by ``enable_shortcut_kinds``. + + * - ``install.hard_link_entrypoints`` + - True to use hard links for global shortcuts to save disk space. If false, + each shortcut executable is copied instead. After changing this setting, + you must run ``py install --refresh --force`` to update existing + commands. + By default, true. Disabling this may be necessary for troubleshooting or + systems that have issues with file links. + + * - ``pep514_root`` + - Registry location to read and write PEP 514 entries into. + By default, :file:`HKEY_CURRENT_USER\\Software\\Python`. + + * - ``start_folder`` + - Start menu folder to write shortcuts into. + By default, ``Python``. + This path is relative to the user's Programs folder. + + * - ``virtual_env`` + - Path to the active virtual environment. + By default, this is ``%VIRTUAL_ENV%``, but may be set empty + to disable venv detection. + + * - ``shebang_can_run_anything_silently`` + - True to suppress visible warnings when a shebang launches an application + other than a Python runtime. + + * - ``source_settings`` + - A mapping from source URL to settings specific to that index. + When multiple configuration files include this section, URL settings are + added or overwritten, but individual settings are not merged. + These settings are currently only for :ref:`index signatures + `. + + +.. _install-freethreaded-windows: + +Installing free-threaded binaries +--------------------------------- - Everything described in this section is considered experimental, - and should be expected to change in future releases. +.. versionadded:: 3.13 -Pre-built distributions of the experimental free-threaded build are available +Pre-built distributions of the free-threaded build are available by installing tags with the ``t`` suffix. .. code:: @@ -648,6 +841,101 @@ installed, then ``python`` will launch this one. Otherwise, you will need to use ``py -V:3.14t ...`` or, if you have added the global aliases directory to your :envvar:`PATH` environment variable, the ``python3.14t.exe`` commands. + +.. _pymanager-index-signatures: + +Index signatures +---------------- + +.. versionadded:: 26.2 + +Index files may be signed to detect tampering. A signature is a catalog file +at the same URL as the index with ``.cat`` added to the filename. The catalog +file should contain the hash of its matching index file, and should be signed +with a valid Authenticode signature. This allows standard tooling (on Windows) +to generate a signature, and any certificate may be used as long as the client +operating system already trusts its certification authority (root CA). + +Index signatures are only downloaded and checked when the local configuration's +``source_settings`` section includes the index URL and ``requires_signature`` is +true, or the index JSON contains ``requires_signature`` set to true. When the +setting exists in local configuration, even when false, settings in the index +are ignored. + +As well as requiring a valid signature, the ``required_root_subject`` and +``required_publisher_subject`` settings can further restrict acceptable +signatures based on the certificate Subject fields. Any attribute specified in +the configuration must match the attribute in the certificate (additional +attributes in the certificate are ignored). Typical attributes are ``CN=`` for +the common name, ``O=`` for the organizational unit, and ``C=`` for the +publisher's country. + +Finally, the ``required_publisher_eku`` setting allows requiring that a specific +Enhanced Key Usage (EKU) has been assigned to the publisher certificate. For +example, the EKU ``1.3.6.1.5.5.7.3.3`` indicates that the certificate was +intended for code signing (as opposed to server or client authentication). +In combination with a specific root CA, this provides another mechanism to +verify a legitimate signature. + +This is an example ``source_settings`` section from a configuration file. In +this case, the publisher of the feed is uniquely identified by the combination +of the Microsoft Identity Verification root and the EKU assigned by that root. +The signature for this case would be found at +``https://www.python.org/ftp/python/index-windows.json.cat``. + +.. code:: json5 + + { + "source_settings": { + "https://www.python.org/ftp/python/index-windows.json": { + "requires_signature": true, + "required_root_subject": "CN=Microsoft Identity Verification Root Certificate Authority 2020", + "required_publisher_subject": "CN=Python Software Foundation", + "required_publisher_eku": "1.3.6.1.4.1.311.97.608394634.79987812.305991749.578777327" + } + } + } + +The same settings could be specified in the ``index.json`` file instead. In this +case, the root and EKU are omitted, meaning that the signature must be valid and +have a specific common name in the publisher's certificate, but no other checks +are used. + +.. code:: json5 + + { + "requires_signature": true, + "required_publisher_subject": "CN=Python Software Foundation", + "versions": [ + // ... + ] + } + +When settings from inside a feed are used, the user is notified and the settings +are shown in the log file or verbose output. It is recommended to copy these +settings into a local configuration file for feeds that will be used frequently, +so that unauthorised modifications to the feed cannot disable verification. + +It is not possible to override the location of the signature file in the feed or +through a configuration file. Administrators can provide their own +``source_settings`` in a mandatory configuration file (see +:ref:`pymanager-admin-config`). + +If signature validation fails, you will be notified and prompted to continue. +When interactive confirmation is not allowed (for example, because ``--yes`` was +specified), it will always abort. To use a feed with invalid configuration in +this scenario, you must provide a configuration file that disables signature +checking for that feed. + +.. code:: json5 + + "source_settings": { + "https://www.example.com/feed-with-invalid-signature.json": { + "requires_signature": false + } + } + + .. _pymanager-troubleshoot: Troubleshooting @@ -655,65 +943,141 @@ Troubleshooting If your Python install manager does not seem to be working correctly, please work through these tests and fixes to see if it helps. If not, please report an -issue at `our bug tracker `_, +issue at `our bug tracker `_, including any relevant log files (written to your :file:`%TEMP%` directory by default). -.. csv-table:: Troubleshooting - :header: "Symptom", "Things to try" - :widths: 1, 1 - - "``python`` gives me a ""command not found"" error or opens the Store app - when I type it in my terminal.", "Did you :ref:`install the Python install - manager `? - " - "", "Click Start, open ""Manage app execution aliases"", and check that the - aliases for ""Python (default)"" are enabled. If they already are, try - disabling and re-enabling to refresh the command. The ""Python (default - windowed)"" and ""Python install manager"" commands may also need refreshing. - " - "", "Check that the ``py`` and ``pymanager`` commands work. - " - "``py`` gives me a ""command not found"" error when I type it in my - terminal.","Did you :ref:`install the Python install manager `? - " - "", "Click Start, open ""Manage app execution aliases"", and check that the - aliases for ""Python install manager"" are enabled. If they already are, try - disabling and re-enabling to refresh the command. The ""Python (default - windowed)"" and ""Python install manager"" commands may also need refreshing. - " - "``py`` gives me a ""can't open file"" error when I type commands in my - terminal.", "This usually means you have the legacy launcher installed and it - has priority over the Python install manager. To remove, click Start, open - ""Installed apps"", search for ""Python launcher"" and uninstall it. - " - "``python`` doesn't launch the same runtime as ``py``", "Click Start, open - ""Installed apps"", look for any existing Python runtimes, and either remove - them or Modify and disable the :envvar:`PATH` options. - " - "", "Click Start, open ""Manage app execution aliases"", and check that your - ``python.exe`` alias is set to ""Python (default)"" - " - "``python`` and ``py`` don't launch the runtime I expect", "Check your - ``PYTHON_MANAGER_DEFAULT`` environment variable or ``default_tag`` - configuration. The ``py list`` command will show your default based on these - settings. - " - "", "Installs that are managed by the Python install manager will be chosen - ahead of unmanaged installs. Use ``py install`` to install the runtime you - expect, or configure your default tag. - " - "", "Prerelease and experimental installs that are not managed by the Python - install manager may be chosen ahead of stable releases. Configure your - default tag or uninstall the prerelease runtime and reinstall using ``py - install``. - " - "``pythonw`` or ``pyw`` don't launch the same runtime as ``python`` or - ``py``","Click Start, open ""Manage app execution aliases"", and check that - your ``pythonw.exe`` and ``pyw.exe`` aliases are consistent with your - others. - " - +.. Sphinx bug with text writer; remove widths & caption temporarily +.. :widths: 1, 1 + +.. rubric:: Troubleshooting + +.. list-table:: + :header-rows: 1 + + * - Symptom + - Things to try + + * - ``python`` gives me a "command not found" error or opens the Store app + when I type it in my terminal. + - Did you :ref:`install the Python install manager `? + + * - + - Click Start, open "Manage app execution aliases", and check that the + aliases for "Python (default)" are enabled. + If they already are, try disabling and re-enabling to refresh the command. + The "Python (default windowed)" and "Python install manager" commands + may also need refreshing. + + * - + - Check that the ``py`` and ``pymanager`` commands work. + + * - + - Ensure your :envvar:`PATH` variable contains the entry for + ``%UserProfile%\AppData\Local\Microsoft\WindowsApps``. + The operating system includes this entry once by default, after other + user paths. If removed, shortcuts will not be found. + + * - ``py`` gives me a "command not found" error when I type it in my terminal. + - Did you :ref:`install the Python install manager `? + + * - + - Click Start, open "Manage app execution aliases", and check that the + aliases for "Python (default)" are enabled. + If they already are, try disabling and re-enabling to refresh the command. + The "Python (default windowed)" and "Python install manager" commands + may also need refreshing. + + * - + - Ensure your :envvar:`PATH` variable contains the entry for + ``%UserProfile%\AppData\Local\Microsoft\WindowsApps``. + The operating system includes this entry once by default, after other + user paths. If removed, shortcuts will not be found. + + * - ``py`` gives me a "can't open file" error when I type commands in my + terminal. + - This usually means you have the legacy launcher installed and + it has priority over the Python install manager. + To remove, click Start, open "Installed apps", + search for "Python launcher" and uninstall it. + + * - ``python`` doesn't launch the same runtime as ``py`` + - Click Start, open "Installed apps", look for any existing Python runtimes, + and either remove them or Modify and disable the :envvar:`PATH` options. + + * - + - Click Start, open "Manage app execution aliases", and check that your + ``python.exe`` alias is set to "Python (default)" + + * - ``python`` and ``py`` don't launch the runtime I expect + - Check your :envvar:`PYTHON_MANAGER_DEFAULT` environment variable + or ``default_tag`` configuration. + The ``py list`` command will show your default based on these settings. + + * - + - Installs that are managed by the Python install manager will be chosen + ahead of unmanaged installs. + Use ``py install`` to install the runtime you expect, + or configure your default tag. + + * - + - Prerelease and experimental installs that are not managed by the Python + install manager may be chosen ahead of stable releases. + Configure your default tag or uninstall the prerelease runtime + and reinstall it using ``py install``. + + * - ``pythonw`` or ``pyw`` don't launch the same runtime as ``python`` or ``py`` + - Click Start, open "Manage app execution aliases", and check that your + ``pythonw.exe`` and ``pyw.exe`` aliases are consistent with your others. + + * - ``pip`` gives me a "command not found" error when I type it in my terminal. + - Have you activated a virtual environment? + Run the ``.venv\Scripts\activate`` script in your terminal to activate. + + * - + - The package may be available but missing the generated executable. + We recommend using the ``python -m pip`` command instead. + Running ``py install --refresh`` and ensuring that the global shortcuts + directory is on :envvar:`PATH` (it will be shown in the command output if + it is not) should make commands such as ``pip`` (and other installed + packages) available. + + * - I installed a package with ``pip`` but its command is not found. + - Have you activated a virtual environment? + Run the ``.venv\Scripts\activate`` script in your terminal to activate. + + * - + - New packages do not automatically have global shortcuts created by the + Python install manager. Similarly, uninstalled packages do not have their + shortcuts removed. + Run ``py install --refresh`` to update the global shortcuts for newly + installed packages. + + * - Typing ``script-name.py`` in the terminal opens in a new window. + - This is a known limitation of the operating system. Either specify ``py`` + before the script name, create a batch file containing ``@py "%~dpn0.py" %*`` + with the same name as the script, or install the `legacy launcher`_ + and select it as the association for scripts. + + * - Drag-dropping files onto a script doesn't work + - This is a known limitation of the operating system. It is supported with + the `legacy launcher`_, or with the Python install manager when installed + from the MSI. + + * - I have installed the Python install manager multiple times. + - It is possible to install from the Store or WinGet, from the MSIX on + the Python website, and from the MSI, all at once. + They are all compatible and will share configuration and runtimes. + + * - + - See the earlier :ref:`pymanager-advancedinstall` section for ways to + uninstall the install manager other than the typical Installed Apps + (Add and Remove Programs) settings page. + + * - My old ``py.ini`` settings no longer work. + - The new Python install manager no longer supports this configuration file + or its settings, and so it will be ignored. + See :ref:`pymanager-config` for information about configuration settings. .. _windows-embeddable: @@ -731,7 +1095,7 @@ To install an embedded distribution, we recommend using ``py install`` with the .. code:: - $> py install 3.14-embed --target=runtime + $> py install 3.14-embed --target= When extracted, the embedded distribution is (almost) fully isolated from the user's system, including environment variables, system registry settings, and @@ -754,7 +1118,7 @@ versions before providing updates to users. The two recommended use cases for this distribution are described below. -Python Application +Python application ------------------ An application written in Python does not necessarily require users to be aware @@ -814,9 +1178,9 @@ on using nuget. What follows is a summary that is sufficient for Python developers. The ``nuget.exe`` command line tool may be downloaded directly from -``https://aka.ms/nugetclidl``, for example, using curl or PowerShell. With the -tool, the latest version of Python for 64-bit or 32-bit machines is installed -using:: +``https://dist.nuget.org/win-x86-commandline/latest/nuget.exe``, for example, +using curl or PowerShell. With the tool, the latest version of Python for +64-bit or 32-bit machines is installed using:: nuget.exe install python -ExcludeVersion -OutputDirectory . nuget.exe install pythonx86 -ExcludeVersion -OutputDirectory . @@ -858,12 +1222,7 @@ for the 64-bit version, `www.nuget.org/packages/pythonx86 Free-threaded packages ---------------------- -.. versionadded:: 3.13 (Experimental) - -.. note:: - - Everything described in this section is considered experimental, - and should be expected to change in future releases. +.. versionadded:: 3.13 Packages containing free-threaded binaries are named `python-freethreaded `_ @@ -915,7 +1274,7 @@ please install Python 3.12. .. _max-path: -Removing the MAX_PATH Limitation +Removing the MAX_PATH limitation ================================ Windows historically has limited path lengths to 260 characters. This meant that @@ -1196,7 +1555,7 @@ installation". In this case: * Shortcuts are available for all users -Removing the MAX_PATH Limitation +Removing the MAX_PATH limitation -------------------------------- Windows historically has limited path lengths to 260 characters. This meant that @@ -1219,7 +1578,7 @@ After changing the above option, no further configuration is required. .. _install-quiet-option: -Installing Without UI +Installing without UI --------------------- All of the options available in the installer UI can also be specified from the @@ -1368,7 +1727,7 @@ example file sets the same options as the previous example: .. _install-layout-option: -Installing Without Downloading +Installing without downloading ------------------------------ As some features of Python are not included in the initial installer download, @@ -1409,15 +1768,10 @@ settings and replace any that have been removed or modified. :ref:`launcher`, which has its own entry in Programs and Features. -Installing Free-threaded Binaries +Installing free-threaded binaries --------------------------------- -.. versionadded:: 3.13 (Experimental) - -.. note:: - - Everything described in this section is considered experimental, - and should be expected to change in future releases. +.. versionadded:: 3.13 To install pre-built binaries with free-threading enabled (see :pep:`703`), you should select "Customize installation". The second page of options includes the @@ -1449,7 +1803,7 @@ builds. Free-threaded binaries are also available :ref:`on nuget.org `. -Python Launcher for Windows (Deprecated) +Python launcher for Windows (deprecated) ======================================== .. deprecated:: 3.14 @@ -1601,7 +1955,7 @@ have the script specify the version which should be used. The key benefit of this is that a single launcher can support multiple Python versions at the same time depending on the contents of the first line. -Shebang Lines +Shebang lines ------------- If the first line of a script file starts with ``#!``, it is known as a @@ -1666,7 +2020,7 @@ program, which performs a :envvar:`PATH` search. If an executable matching the first argument after the ``env`` command cannot be found, but the argument starts with ``python``, it will be handled as described for the other virtual commands. -The environment variable :envvar:`PYLAUNCHER_NO_SEARCH_PATH` may be set +The environment variable :envvar:`!PYLAUNCHER_NO_SEARCH_PATH` may be set (to any value) to skip this search of :envvar:`PATH`. Shebang lines that do not match any of these patterns are looked up in the @@ -1733,7 +2087,7 @@ For example, a shebang line of ``#!python`` has no version qualifier, while ``#!python3`` has a version qualifier which specifies only a major version. If no version qualifiers are found in a command, the environment -variable :envvar:`PY_PYTHON` can be set to specify the default version +variable :envvar:`!PY_PYTHON` can be set to specify the default version qualifier. If it is not set, the default is "3". The variable can specify any value that may be passed on the command line, such as "3", "3.7", "3.7-32" or "3.7-64". (Note that the "-64" option is only @@ -1806,17 +2160,17 @@ For example: Diagnostics ----------- -If an environment variable :envvar:`PYLAUNCHER_DEBUG` is set (to any value), the +If an environment variable :envvar:`!PYLAUNCHER_DEBUG` is set (to any value), the launcher will print diagnostic information to stderr (i.e. to the console). While this information manages to be simultaneously verbose *and* terse, it should allow you to see what versions of Python were located, why a particular version was chosen and the exact command-line used to execute the target Python. It is primarily intended for testing and debugging. -Dry Run +Dry run ------- -If an environment variable :envvar:`PYLAUNCHER_DRYRUN` is set (to any value), +If an environment variable :envvar:`!PYLAUNCHER_DRYRUN` is set (to any value), the launcher will output the command it would have run, but will not actually launch Python. This may be useful for tools that want to use the launcher to detect and then launch Python directly. Note that the command written to @@ -1826,14 +2180,14 @@ the console. Install on demand ----------------- -If an environment variable :envvar:`PYLAUNCHER_ALLOW_INSTALL` is set (to any +If an environment variable :envvar:`!PYLAUNCHER_ALLOW_INSTALL` is set (to any value), and the requested Python version is not installed but is available on the Microsoft Store, the launcher will attempt to install it. This may require user interaction to complete, and you may need to run the command again. -An additional :envvar:`PYLAUNCHER_ALWAYS_INSTALL` variable causes the launcher +An additional :envvar:`!PYLAUNCHER_ALWAYS_INSTALL` variable causes the launcher to always try to install Python, even if it is detected. This is mainly intended -for testing (and should be used with :envvar:`PYLAUNCHER_DRYRUN`). +for testing (and should be used with :envvar:`!PYLAUNCHER_DRYRUN`). Return codes ------------ diff --git a/Doc/whatsnew/2.0.rst b/Doc/whatsnew/2.0.rst index 1a949ec4035807..c157c0337a1342 100644 --- a/Doc/whatsnew/2.0.rst +++ b/Doc/whatsnew/2.0.rst @@ -656,7 +656,8 @@ break. The change which will probably break the most code is tightening up the arguments accepted by some methods. Some methods would take multiple arguments and treat them as a tuple, particularly various list methods such as -:meth:`!append` and :meth:`!insert`. In earlier versions of Python, if ``L`` is +:meth:`~list.append` and :meth:`~list.insert`. +In earlier versions of Python, if ``L`` is a list, ``L.append( 1,2 )`` appends the tuple ``(1,2)`` to the list. In Python 2.0 this causes a :exc:`TypeError` exception to be raised, with the message: 'append requires exactly 1 argument; 2 given'. The fix is to simply add an diff --git a/Doc/whatsnew/2.3.rst b/Doc/whatsnew/2.3.rst index b7e4e73f4ce4aa..43ab19037d2627 100644 --- a/Doc/whatsnew/2.3.rst +++ b/Doc/whatsnew/2.3.rst @@ -66,7 +66,7 @@ Here's a simple example:: The union and intersection of sets can be computed with the :meth:`~frozenset.union` and :meth:`~frozenset.intersection` methods; an alternative notation uses the bitwise operators ``&`` and ``|``. Mutable sets also have in-place versions of these methods, -:meth:`!union_update` and :meth:`~frozenset.intersection_update`. :: +:meth:`!union_update` and :meth:`~set.intersection_update`. :: >>> S1 = sets.Set([1,2,3]) >>> S2 = sets.Set([4,5,6]) @@ -87,7 +87,7 @@ It's also possible to take the symmetric difference of two sets. This is the set of all elements in the union that aren't in the intersection. Another way of putting it is that the symmetric difference contains all elements that are in exactly one set. Again, there's an alternative notation (``^``), and an -in-place version with the ungainly name :meth:`~frozenset.symmetric_difference_update`. :: +in-place version with the ungainly name :meth:`~set.symmetric_difference_update`. :: >>> S1 = sets.Set([1,2,3,4]) >>> S2 = sets.Set([3,4,5,6]) @@ -1698,8 +1698,8 @@ current local date. Once created, instances of the date/time classes are all immutable. There are a number of methods for producing formatted strings from objects:: - >>> import datetime - >>> now = datetime.datetime.now() + >>> import datetime as dt + >>> now = dt.datetime.now() >>> now.isoformat() '2002-12-30T21:27:03.994956' >>> now.ctime() # Only available on date, datetime @@ -1710,10 +1710,10 @@ number of methods for producing formatted strings from objects:: The :meth:`~datetime.datetime.replace` method allows modifying one or more fields of a :class:`~datetime.date` or :class:`~datetime.datetime` instance, returning a new instance:: - >>> d = datetime.datetime.now() + >>> d = dt.datetime.now() >>> d datetime.datetime(2002, 12, 30, 22, 15, 38, 827738) - >>> d.replace(year=2001, hour = 12) + >>> d.replace(year=2001, hour=12) datetime.datetime(2001, 12, 30, 12, 15, 38, 827738) >>> diff --git a/Doc/whatsnew/2.4.rst b/Doc/whatsnew/2.4.rst index 7628cfefe0ec96..87c7b6b17477b5 100644 --- a/Doc/whatsnew/2.4.rst +++ b/Doc/whatsnew/2.4.rst @@ -35,7 +35,7 @@ implementation and design rationale. PEP 218: Built-In Set Objects ============================= -Python 2.3 introduced the :mod:`sets` module. C implementations of set data +Python 2.3 introduced the :mod:`!sets` module. C implementations of set data types have now been added to the Python core as two new built-in types, ``set(iterable)`` and ``frozenset(iterable)``. They provide high speed operations for membership testing, for eliminating duplicates from sequences, @@ -72,8 +72,8 @@ The :func:`frozenset` type is an immutable version of :func:`set`. Since it is immutable and hashable, it may be used as a dictionary key or as a member of another set. -The :mod:`sets` module remains in the standard library, and may be useful if you -wish to subclass the :class:`Set` or :class:`ImmutableSet` classes. There are +The :mod:`!sets` module remains in the standard library, and may be useful if you +wish to subclass the :class:`!Set` or :class:`!ImmutableSet` classes. There are currently no plans to deprecate the module. @@ -189,7 +189,7 @@ aren't aware of the Python language. The format string's syntax is complicated to explain to such users, and if they make a mistake, it's difficult to provide helpful feedback to them. -PEP 292 adds a :class:`Template` class to the :mod:`string` module that uses +PEP 292 adds a :class:`~string.Template` class to the :mod:`string` module that uses ``$`` to indicate a substitution:: >>> import string @@ -197,9 +197,9 @@ PEP 292 adds a :class:`Template` class to the :mod:`string` module that uses >>> t.substitute({'page':2, 'title': 'The Best of Times'}) '2: The Best of Times' -If a key is missing from the dictionary, the :meth:`substitute` method will -raise a :exc:`KeyError`. There's also a :meth:`safe_substitute` method that -ignores missing keys:: +If a key is missing from the dictionary, the :meth:`~string.Template.substitute` +method will raise a :exc:`KeyError`. There's also a +:meth:`~string.Template.safe_substitute` method that ignores missing keys:: >>> t = string.Template('$page: $title') >>> t.safe_substitute({'page':3}) @@ -430,14 +430,14 @@ The constructor has a number of handy options: * *universal_newlines* opens the child's input and output using Python's :term:`universal newlines` feature. -Once you've created the :class:`Popen` instance, you can call its :meth:`wait` -method to pause until the subprocess has exited, :meth:`poll` to check if it's +Once you've created the :class:`~subprocess.Popen` instance, you can call its :meth:`~subprocess.Popen.wait` +method to pause until the subprocess has exited, :meth:`~subprocess.Popen.poll` to check if it's exited without pausing, or ``communicate(data)`` to send the string *data* to the subprocess's standard input. ``communicate(data)`` then reads any data that the subprocess has sent to its standard output or standard error, returning a tuple ``(stdout_data, stderr_data)``. -:func:`call` is a shortcut that passes its arguments along to the :class:`Popen` +:func:`~subprocess.call` is a shortcut that passes its arguments along to the :class:`~subprocess.Popen` constructor, waits for the command to complete, and returns the status code of the subprocess. It can serve as a safer analog to :func:`os.system`:: @@ -476,7 +476,7 @@ Python has always supported floating-point (FP) numbers, based on the underlying C :c:expr:`double` type, as a data type. However, while most programming languages provide a floating-point type, many people (even programmers) are unaware that floating-point numbers don't represent certain decimal fractions -accurately. The new :class:`Decimal` type can represent these fractions +accurately. The new :class:`~decimal.Decimal` type can represent these fractions accurately, up to a user-specified precision limit. @@ -531,20 +531,20 @@ decimal places, the error is never apparent. However, for applications where it does matter, it's a lot of work to implement your own custom arithmetic routines. -Hence, the :class:`Decimal` type was created. +Hence, the :class:`~decimal.Decimal` type was created. -The :class:`Decimal` type -------------------------- +The :class:`~decimal.Decimal` type +---------------------------------- A new module, :mod:`decimal`, was added to Python's standard library. It -contains two classes, :class:`Decimal` and :class:`Context`. :class:`Decimal` -instances represent numbers, and :class:`Context` instances are used to wrap up +contains two classes, :class:`~decimal.Decimal` and :class:`~decimal.Context`. :class:`~decimal.Decimal` +instances represent numbers, and :class:`~decimal.Context` instances are used to wrap up various settings such as the precision and default rounding mode. -:class:`Decimal` instances are immutable, like regular Python integers and FP +:class:`~decimal.Decimal` instances are immutable, like regular Python integers and FP numbers; once it's been created, you can't change the value an instance -represents. :class:`Decimal` instances can be created from integers or +represents. :class:`~decimal.Decimal` instances can be created from integers or strings:: >>> import decimal @@ -567,7 +567,7 @@ number representing 1.1 turn into the decimal number for exactly 1.1, or for 1.1 plus whatever inaccuracies are introduced? The decision was to dodge the issue and leave such a conversion out of the API. Instead, you should convert the floating-point number into a string using the desired precision and pass the -string to the :class:`Decimal` constructor:: +string to the :class:`~decimal.Decimal` constructor:: >>> f = 1.1 >>> decimal.Decimal(str(f)) @@ -575,7 +575,7 @@ string to the :class:`Decimal` constructor:: >>> decimal.Decimal('%.12f' % f) Decimal("1.100000000000") -Once you have :class:`Decimal` instances, you can perform the usual mathematical +Once you have :class:`~decimal.Decimal` instances, you can perform the usual mathematical operations on them. One limitation: exponentiation requires an integer exponent:: @@ -596,7 +596,7 @@ exponent:: ... decimal.InvalidOperation: x ** (non-integer) -You can combine :class:`Decimal` instances with integers, but not with +You can combine :class:`~decimal.Decimal` instances with integers, but not with floating-point numbers:: >>> a + 4 @@ -607,11 +607,11 @@ floating-point numbers:: TypeError: You can interact Decimal only with int, long or Decimal data types. >>> -:class:`Decimal` numbers can be used with the :mod:`math` and :mod:`cmath` +:class:`~decimal.Decimal` numbers can be used with the :mod:`math` and :mod:`cmath` modules, but note that they'll be immediately converted to floating-point numbers before the operation is performed, resulting in a possible loss of precision and accuracy. You'll also get back a regular floating-point number -and not a :class:`Decimal`. :: +and not a :class:`~decimal.Decimal`. :: >>> import math, cmath >>> d = decimal.Decimal('123456789012.345') @@ -620,32 +620,33 @@ and not a :class:`Decimal`. :: >>> cmath.sqrt(-d) 351364.18288201344j -:class:`Decimal` instances have a :meth:`sqrt` method that returns a -:class:`Decimal`, but if you need other things such as trigonometric functions +:class:`~decimal.Decimal` instances have a :meth:`~decimal.Decimal.sqrt` method that returns a +:class:`~decimal.Decimal`, but if you need other things such as trigonometric functions you'll have to implement them. :: >>> d.sqrt() Decimal("351364.1828820134592177245001") -The :class:`Context` type -------------------------- +The :class:`~decimal.Context` type +---------------------------------- -Instances of the :class:`Context` class encapsulate several settings for +Instances of the :class:`~decimal.Context` class encapsulate several settings for decimal operations: -* :attr:`prec` is the precision, the number of decimal places. +* :attr:`~decimal.Context.prec` is the precision, the number of decimal places. -* :attr:`rounding` specifies the rounding mode. The :mod:`decimal` module has - constants for the various possibilities: :const:`ROUND_DOWN`, - :const:`ROUND_CEILING`, :const:`ROUND_HALF_EVEN`, and various others. +* :attr:`~decimal.Context.rounding` specifies the rounding mode. The + :mod:`decimal` module has constants for the various possibilities: + :const:`~decimal.ROUND_DOWN`, :const:`~decimal.ROUND_CEILING`, + :const:`~decimal.ROUND_HALF_EVEN`, and various others. -* :attr:`traps` is a dictionary specifying what happens on encountering certain +* :attr:`~decimal.Context.traps` is a dictionary specifying what happens on encountering certain error conditions: either an exception is raised or a value is returned. Some examples of error conditions are division by zero, loss of precision, and overflow. -There's a thread-local default context available by calling :func:`getcontext`; +There's a thread-local default context available by calling :func:`~decimal.getcontext`; you can change the properties of this context to alter the default precision, rounding, or trap handling. The following example shows the effect of changing the precision of the default context:: @@ -671,8 +672,8 @@ raised:: Decimal("Infinity") >>> -The :class:`Context` instance also has various methods for formatting numbers -such as :meth:`to_eng_string` and :meth:`to_sci_string`. +The :class:`~decimal.Context` instance also has various methods for formatting numbers +such as :meth:`~decimal.Context.to_eng_string` and :meth:`~decimal.Context.to_sci_string`. For more information, see the documentation for the :mod:`decimal` module, which includes a quick-start tutorial and a reference. @@ -740,7 +741,7 @@ display conventions that are localized to a particular country or language. However, the module was careful to not change the numeric locale because various functions in Python's implementation required that the numeric locale remain set to the ``'C'`` locale. Often this was because the code was using the C -library's :c:func:`atof` function. +library's :c:func:`!atof` function. Not setting the numeric locale caused trouble for extensions that used third-party C libraries, however, because they wouldn't have the correct locale set. @@ -793,11 +794,11 @@ Here are all of the changes that Python 2.4 makes to the core Python language. :class:`dict` constructor. This includes any mapping, any iterable of key/value pairs, and keyword arguments. (Contributed by Raymond Hettinger.) -* The string methods :meth:`ljust`, :meth:`rjust`, and :meth:`center` now take +* The string methods :meth:`~str.ljust`, :meth:`~str.rjust`, and :meth:`~str.center` now take an optional argument for specifying a fill character other than a space. (Contributed by Raymond Hettinger.) -* Strings also gained an :meth:`rsplit` method that works like the :meth:`split` +* Strings also gained an :meth:`~str.rsplit` method that works like the :meth:`~str.split` method but splits from the end of the string. (Contributed by Sean Reifschneider.) :: @@ -807,13 +808,13 @@ Here are all of the changes that Python 2.4 makes to the core Python language. ['www.python', 'org'] * Three keyword parameters, *cmp*, *key*, and *reverse*, were added to the - :meth:`sort` method of lists. These parameters make some common usages of - :meth:`sort` simpler. All of these parameters are optional. + :meth:`~list.sort` method of lists. These parameters make some common usages of + :meth:`~list.sort` simpler. All of these parameters are optional. For the *cmp* parameter, the value should be a comparison function that takes two parameters and returns -1, 0, or +1 depending on how the parameters compare. This function will then be used to sort the list. Previously this was the only - parameter that could be provided to :meth:`sort`. + parameter that could be provided to :meth:`~list.sort`. *key* should be a single-parameter function that takes a list element and returns a comparison key for the element. The list is then sorted using the @@ -834,9 +835,9 @@ Here are all of the changes that Python 2.4 makes to the core Python language. The last example, which uses the *cmp* parameter, is the old way to perform a case-insensitive sort. It works but is slower than using a *key* parameter. - Using *key* calls :meth:`lower` method once for each element in the list while + Using *key* calls :meth:`~str.lower` method once for each element in the list while using *cmp* will call it twice for each comparison, so using *key* saves on - invocations of the :meth:`lower` method. + invocations of the :meth:`~str.lower` method. For simple key functions and comparison functions, it is often possible to avoid a :keyword:`lambda` expression by using an unbound method instead. For example, @@ -856,7 +857,7 @@ Here are all of the changes that Python 2.4 makes to the core Python language. age, resulting in a list sorted by age where people with the same age are in name-sorted order. - (All changes to :meth:`sort` contributed by Raymond Hettinger.) + (All changes to :meth:`~list.sort` contributed by Raymond Hettinger.) * There is a new built-in function ``sorted(iterable)`` that works like the in-place :meth:`list.sort` method but can be used in expressions. The @@ -891,8 +892,8 @@ Here are all of the changes that Python 2.4 makes to the core Python language. (Contributed by Raymond Hettinger.) -* Integer operations will no longer trigger an :exc:`OverflowWarning`. The - :exc:`OverflowWarning` warning will disappear in Python 2.5. +* Integer operations will no longer trigger an :exc:`!OverflowWarning`. The + :exc:`!OverflowWarning` warning will disappear in Python 2.5. * The interpreter gained a new switch, :option:`-m`, that takes a name, searches for the corresponding module on ``sys.path``, and runs the module as a script. @@ -904,7 +905,7 @@ Here are all of the changes that Python 2.4 makes to the core Python language. for the *locals* parameter. Previously this had to be a regular Python dictionary. (Contributed by Raymond Hettinger.) -* The :func:`zip` built-in function and :func:`itertools.izip` now return an +* The :func:`zip` built-in function and :func:`!itertools.izip` now return an empty list if called with no arguments. Previously they raised a :exc:`TypeError` exception. This makes them more suitable for use with variable length argument lists:: @@ -935,8 +936,8 @@ Optimizations * The inner loops for list and tuple slicing were optimized and now run about one-third faster. The inner loops for dictionaries were also optimized, - resulting in performance boosts for :meth:`keys`, :meth:`values`, :meth:`items`, - :meth:`iterkeys`, :meth:`itervalues`, and :meth:`iteritems`. (Contributed by + resulting in performance boosts for :meth:`~dict.keys`, :meth:`~dict.values`, :meth:`~dict.items`, + :meth:`!iterkeys`, :meth:`!itervalues`, and :meth:`!iteritems`. (Contributed by Raymond Hettinger.) * The machinery for growing and shrinking lists was optimized for speed and for @@ -948,11 +949,11 @@ Optimizations * :func:`list`, :func:`tuple`, :func:`map`, :func:`filter`, and :func:`zip` now run several times faster with non-sequence arguments that supply a - :meth:`__len__` method. (Contributed by Raymond Hettinger.) + :meth:`~object.__len__` method. (Contributed by Raymond Hettinger.) -* The methods :meth:`list.__getitem__`, :meth:`dict.__getitem__`, and - :meth:`dict.__contains__` are now implemented as :class:`method_descriptor` - objects rather than :class:`wrapper_descriptor` objects. This form of access +* The methods :meth:`!list.__getitem__`, :meth:`!dict.__getitem__`, and + :meth:`!dict.__contains__` are now implemented as :class:`!method_descriptor` + objects rather than :class:`!wrapper_descriptor` objects. This form of access doubles their performance and makes them more suitable for use as arguments to functionals: ``map(mydict.__getitem__, keylist)``. (Contributed by Raymond Hettinger.) @@ -968,7 +969,7 @@ Optimizations * String concatenations in statements of the form ``s = s + "abc"`` and ``s += "abc"`` are now performed more efficiently in certain circumstances. This optimization won't be present in other Python implementations such as Jython, so - you shouldn't rely on it; using the :meth:`join` method of strings is still + you shouldn't rely on it; using the :meth:`~str.join` method of strings is still recommended when you want to efficiently glue a large number of strings together. (Contributed by Armin Rigo.) @@ -1023,13 +1024,13 @@ complete list of changes, or look through the CVS logs for all the details. PCTP-154, and TIS-620. * The UTF-8 and UTF-16 codecs now cope better with receiving partial input. - Previously the :class:`StreamReader` class would try to read more data, making - it impossible to resume decoding from the stream. The :meth:`read` method will + Previously the :class:`~codecs.StreamReader` class would try to read more data, making + it impossible to resume decoding from the stream. The :meth:`~codecs.StreamReader.read` method will now return as much data as it can and future calls will resume decoding where previous ones left off. (Implemented by Walter Dörwald.) * There is a new :mod:`collections` module for various specialized collection - datatypes. Currently it contains just one type, :class:`deque`, a double-ended + datatypes. Currently it contains just one type, :class:`~collections.deque`, a double-ended queue that supports efficiently adding and removing elements from either end:: @@ -1048,7 +1049,7 @@ complete list of changes, or look through the CVS logs for all the details. >>> 'h' in d # search the deque True - Several modules, such as the :mod:`Queue` and :mod:`threading` modules, now take + Several modules, such as the :mod:`queue` and :mod:`threading` modules, now take advantage of :class:`collections.deque` for improved performance. (Contributed by Raymond Hettinger.) @@ -1058,49 +1059,49 @@ complete list of changes, or look through the CVS logs for all the details. isn't a string. (Contributed by John Belmonte and David Goodger.) * The :mod:`curses` module now supports the ncurses extension - :func:`use_default_colors`. On platforms where the terminal supports + :func:`~curses.use_default_colors`. On platforms where the terminal supports transparency, this makes it possible to use a transparent background. (Contributed by Jörg Lehmann.) -* The :mod:`difflib` module now includes an :class:`HtmlDiff` class that creates +* The :mod:`difflib` module now includes an :class:`~difflib.HtmlDiff` class that creates an HTML table showing a side by side comparison of two versions of a text. (Contributed by Dan Gass.) * The :mod:`email` package was updated to version 3.0, which dropped various deprecated APIs and removes support for Python versions earlier than 2.3. The 3.0 version of the package uses a new incremental parser for MIME messages, - available in the :mod:`email.FeedParser` module. The new parser doesn't require + available in the :mod:`!email.FeedParser` module. The new parser doesn't require reading the entire message into memory, and doesn't raise exceptions if a - message is malformed; instead it records any problems in the :attr:`defect` + message is malformed; instead it records any problems in the :attr:`!defect` attribute of the message. (Developed by Anthony Baxter, Barry Warsaw, Thomas Wouters, and others.) * The :mod:`heapq` module has been converted to C. The resulting tenfold improvement in speed makes the module suitable for handling high volumes of - data. In addition, the module has two new functions :func:`nlargest` and - :func:`nsmallest` that use heaps to find the N largest or smallest values in a + data. In addition, the module has two new functions :func:`~heapq.nlargest` and + :func:`~heapq.nsmallest` that use heaps to find the N largest or smallest values in a dataset without the expense of a full sort. (Contributed by Raymond Hettinger.) * The :mod:`httplib ` module now contains constants for HTTP status codes defined in various HTTP-related RFC documents. Constants have names such as - :const:`OK`, :const:`CREATED`, :const:`CONTINUE`, and - :const:`MOVED_PERMANENTLY`; use pydoc to get a full list. (Contributed by + :const:`!OK`, :const:`!CREATED`, :const:`!CONTINUE`, and + :const:`!MOVED_PERMANENTLY`; use pydoc to get a full list. (Contributed by Andrew Eland.) * The :mod:`imaplib` module now supports IMAP's THREAD command (contributed by - Yves Dionne) and new :meth:`deleteacl` and :meth:`myrights` methods (contributed - by Arnaud Mazin). + Yves Dionne) and new :meth:`~imaplib.IMAP4.deleteacl` and + :meth:`~imaplib.IMAP4.myrights` methods (contributed by Arnaud Mazin). * The :mod:`itertools` module gained a ``groupby(iterable[, *func*])`` function. *iterable* is something that can be iterated over to return a stream of elements, and the optional *func* parameter is a function that takes an element and returns a key value; if omitted, the key is simply the element - itself. :func:`groupby` then groups the elements into subsequences which have + itself. :func:`~itertools.groupby` then groups the elements into subsequences which have matching values of the key, and returns a series of 2-tuples containing the key value and an iterator over the subsequence. Here's an example to make this clearer. The *key* function simply returns - whether a number is even or odd, so the result of :func:`groupby` is to return + whether a number is even or odd, so the result of :func:`~itertools.groupby` is to return consecutive runs of odd or even numbers. :: >>> import itertools @@ -1115,8 +1116,8 @@ complete list of changes, or look through the CVS logs for all the details. 0 [12, 14] >>> - :func:`groupby` is typically used with sorted input. The logic for - :func:`groupby` is similar to the Unix ``uniq`` filter which makes it handy for + :func:`~itertools.groupby` is typically used with sorted input. The logic for + :func:`~itertools.groupby` is similar to the Unix ``uniq`` filter which makes it handy for eliminating, counting, or identifying duplicate elements:: >>> word = 'abracadabra' @@ -1153,22 +1154,22 @@ complete list of changes, or look through the CVS logs for all the details. >>> list(i2) # Run the second iterator to exhaustion [1, 2, 3] - Note that :func:`tee` has to keep copies of the values returned by the + Note that :func:`~itertools.tee` has to keep copies of the values returned by the iterator; in the worst case, it may need to keep all of them. This should therefore be used carefully if the leading iterator can run far ahead of the trailing iterator in a long stream of inputs. If the separation is large, then you might as well use :func:`list` instead. When the iterators track closely - with one another, :func:`tee` is ideal. Possible applications include + with one another, :func:`~itertools.tee` is ideal. Possible applications include bookmarking, windowing, or lookahead iterators. (Contributed by Raymond Hettinger.) * A number of functions were added to the :mod:`locale` module, such as - :func:`bind_textdomain_codeset` to specify a particular encoding and a family of + :func:`~locale.bind_textdomain_codeset` to specify a particular encoding and a family of :func:`!l\*gettext` functions that return messages in the chosen encoding. (Contributed by Gustavo Niemeyer.) * Some keyword arguments were added to the :mod:`logging` package's - :func:`basicConfig` function to simplify log configuration. The default + :func:`~logging.basicConfig` function to simplify log configuration. The default behavior is to log messages to standard error, but various keyword arguments can be specified to log to a particular file, change the logging format, or set the logging level. For example:: @@ -1179,10 +1180,10 @@ complete list of changes, or look through the CVS logs for all the details. format='%(levelname):%(process):%(thread):%(message)') Other additions to the :mod:`logging` package include a ``log(level, msg)`` - convenience method, as well as a :class:`TimedRotatingFileHandler` class that + convenience method, as well as a :class:`~logging.handlers.TimedRotatingFileHandler` class that rotates its log files at a timed interval. The module already had - :class:`RotatingFileHandler`, which rotated logs once the file exceeded a - certain size. Both classes derive from a new :class:`BaseRotatingHandler` class + :class:`~logging.handlers.RotatingFileHandler`, which rotated logs once the file exceeded a + certain size. Both classes derive from a new :class:`~logging.handlers.BaseRotatingHandler` class that can be used to implement other rotating handlers. (Changes implemented by Vinay Sajip.) @@ -1192,8 +1193,8 @@ complete list of changes, or look through the CVS logs for all the details. effect is to make :file:`.pyc` files significantly smaller. (Contributed by Martin von Löwis.) -* The :mod:`!nntplib` module's :class:`NNTP` class gained :meth:`description` and - :meth:`descriptions` methods to retrieve newsgroup descriptions for a single +* The :mod:`!nntplib` module's :class:`!NNTP` class gained :meth:`!description` and + :meth:`!descriptions` methods to retrieve newsgroup descriptions for a single group or for a range of groups. (Contributed by Jürgen A. Erhard.) * Two new functions were added to the :mod:`operator` module, @@ -1235,7 +1236,7 @@ complete list of changes, or look through the CVS logs for all the details. *path* is a symlink that points to a destination that doesn't exist. (Contributed by Beni Cherniavsky.) -* A new :func:`getsid` function was added to the :mod:`posix` module that +* A new :func:`~os.getsid` function was added to the :mod:`posix` module that underlies the :mod:`os` module. (Contributed by J. Raynor.) * The :mod:`poplib` module now supports POP over SSL. (Contributed by Hector @@ -1245,8 +1246,8 @@ complete list of changes, or look through the CVS logs for all the details. by Nick Bastin.) * The :mod:`random` module has a new method called ``getrandbits(N)`` that - returns a long integer *N* bits in length. The existing :meth:`randrange` - method now uses :meth:`getrandbits` where appropriate, making generation of + returns a long integer *N* bits in length. The existing :meth:`~random.randrange` + method now uses :meth:`~random.getrandbits` where appropriate, making generation of arbitrarily large random numbers more efficient. (Contributed by Raymond Hettinger.) @@ -1269,24 +1270,24 @@ complete list of changes, or look through the CVS logs for all the details. * The :mod:`signal` module now performs tighter error-checking on the parameters to the :func:`signal.signal` function. For example, you can't set a handler on - the :const:`SIGKILL` signal; previous versions of Python would quietly accept + the :const:`~signal.SIGKILL` signal; previous versions of Python would quietly accept this, but 2.4 will raise a :exc:`RuntimeError` exception. -* Two new functions were added to the :mod:`socket` module. :func:`socketpair` +* Two new functions were added to the :mod:`socket` module. :func:`~socket.socketpair` returns a pair of connected sockets and ``getservbyport(port)`` looks up the service name for a given port number. (Contributed by Dave Cole and Barry Warsaw.) -* The :func:`sys.exitfunc` function has been deprecated. Code should be using +* The :func:`!sys.exitfunc` function has been deprecated. Code should be using the existing :mod:`atexit` module, which correctly handles calling multiple exit - functions. Eventually :func:`sys.exitfunc` will become a purely internal + functions. Eventually :func:`!sys.exitfunc` will become a purely internal interface, accessed only by :mod:`atexit`. * The :mod:`tarfile` module now generates GNU-format tar files by default. (Contributed by Lars Gustäbel.) * The :mod:`threading` module now has an elegantly simple way to support - thread-local data. The module contains a :class:`local` class whose attribute + thread-local data. The module contains a :class:`~threading.local` class whose attribute values are local to different threads. :: import threading @@ -1295,8 +1296,8 @@ complete list of changes, or look through the CVS logs for all the details. data.number = 42 data.url = ('www.python.org', 80) - Other threads can assign and retrieve their own values for the :attr:`number` - and :attr:`url` attributes. You can subclass :class:`local` to initialize + Other threads can assign and retrieve their own values for the :attr:`!number` + and :attr:`!url` attributes. You can subclass :class:`~threading.local` to initialize attributes or to add methods. (Contributed by Jim Fulton.) * The :mod:`timeit` module now automatically disables periodic garbage @@ -1312,7 +1313,7 @@ complete list of changes, or look through the CVS logs for all the details. transmitting multiple XML-RPC calls in a single HTTP operation. (Contributed by Brian Quinlan.) -* The :mod:`mpz`, :mod:`rotor`, and :mod:`xreadlines` modules have been +* The :mod:`!mpz`, :mod:`!rotor`, and :mod:`!xreadlines` modules have been removed. .. ====================================================================== @@ -1336,7 +1337,7 @@ use the Mozilla or Lynx cookie files, and one that stores cookies in the same format as the Perl libwww library. :mod:`urllib2 ` has been changed to interact with :mod:`cookielib `: -:class:`HTTPCookieProcessor` manages a cookie jar that is used when accessing +:class:`~urllib.request.HTTPCookieProcessor` manages a cookie jar that is used when accessing URLs. This module was contributed by John J. Lee. @@ -1352,7 +1353,7 @@ Loper and Tim Peters. Testing can still be as simple as running :func:`doctest.testmod`, but the refactorings allow customizing the module's operation in various ways -The new :class:`DocTestFinder` class extracts the tests from a given object's +The new :class:`~doctest.DocTestFinder` class extracts the tests from a given object's docstrings:: def f (x, y): @@ -1368,7 +1369,7 @@ docstrings:: # Get list of DocTest instances tests = finder.find(f) -The new :class:`DocTestRunner` class then runs individual tests and can produce +The new :class:`~doctest.DocTestRunner` class then runs individual tests and can produce a summary of the results:: runner = doctest.DocTestRunner() @@ -1385,10 +1386,10 @@ The above example produces the following output:: 2 passed and 0 failed. Test passed. -:class:`DocTestRunner` uses an instance of the :class:`OutputChecker` class to +:class:`~doctest.DocTestRunner` uses an instance of the :class:`~doctest.OutputChecker` class to compare the expected output with the actual output. This class takes a number of different flags that customize its behaviour; ambitious users can also write -a completely new subclass of :class:`OutputChecker`. +a completely new subclass of :class:`~doctest.OutputChecker`. The default output checker provides a number of handy features. For example, with the :const:`doctest.ELLIPSIS` option flag, an ellipsis (``...``) in the @@ -1465,7 +1466,7 @@ Some of the changes to Python's build process and to the C API are: lookups without masking exceptions raised during the look-up process. (Contributed by Raymond Hettinger.) -* The :c:expr:`Py_IS_NAN(X)` macro returns 1 if its float or double argument +* The :c:macro:`Py_IS_NAN` macro returns 1 if its float or double argument *X* is a NaN. (Contributed by Tim Peters.) * C code can avoid unnecessary locking by using the new @@ -1479,7 +1480,7 @@ Some of the changes to Python's build process and to the C API are: * A new method flag, :c:macro:`METH_COEXIST`, allows a function defined in slots to co-exist with a :c:type:`PyCFunction` having the same name. This can halve - the access time for a method such as :meth:`set.__contains__`. (Contributed by + the access time for a method such as :meth:`!set.__contains__`. (Contributed by Raymond Hettinger.) * Python can now be built with additional profiling for the interpreter itself, @@ -1493,7 +1494,7 @@ Some of the changes to Python's build process and to the C API are: register". (Contributed by Jeremy Hylton.) * The :c:type:`!tracebackobject` type has been renamed to - :c:type:`PyTracebackObject`. + :c:type:`!PyTracebackObject`. .. ====================================================================== @@ -1517,14 +1518,14 @@ code: trigger a :exc:`FutureWarning` and return a value limited to 32 or 64 bits; instead they return a long integer. -* Integer operations will no longer trigger an :exc:`OverflowWarning`. The - :exc:`OverflowWarning` warning will disappear in Python 2.5. +* Integer operations will no longer trigger an :exc:`!OverflowWarning`. The + :exc:`!OverflowWarning` warning will disappear in Python 2.5. -* The :func:`zip` built-in function and :func:`itertools.izip` now return an +* The :func:`zip` built-in function and :func:`!itertools.izip` now return an empty list instead of raising a :exc:`TypeError` exception if called with no arguments. -* You can no longer compare the :class:`date` and :class:`~datetime.datetime` instances +* You can no longer compare the :class:`~datetime.date` and :class:`~datetime.datetime` instances provided by the :mod:`datetime` module. Two instances of different classes will now always be unequal, and relative comparisons (``<``, ``>``) will raise a :exc:`TypeError`. @@ -1532,7 +1533,8 @@ code: * :func:`!dircache.listdir` now passes exceptions to the caller instead of returning empty lists. -* :func:`LexicalHandler.startDTD` used to receive the public and system IDs in +* :meth:`LexicalHandler.startDTD ` + used to receive the public and system IDs in the wrong order. This has been corrected; applications relying on the wrong order need to be fixed. @@ -1547,9 +1549,9 @@ code: * :const:`None` is now a constant; code that binds a new value to the name ``None`` is now a syntax error. -* The :func:`signals.signal` function now raises a :exc:`RuntimeError` exception +* The :func:`signal.signal` function now raises a :exc:`RuntimeError` exception for certain illegal values; previously these errors would pass silently. For - example, you can no longer set a handler on the :const:`SIGKILL` signal. + example, you can no longer set a handler on the :const:`~signal.SIGKILL` signal. .. ====================================================================== diff --git a/Doc/whatsnew/2.5.rst b/Doc/whatsnew/2.5.rst index 3430ac8668e280..0449644833b7e9 100644 --- a/Doc/whatsnew/2.5.rst +++ b/Doc/whatsnew/2.5.rst @@ -16,8 +16,8 @@ release schedule. Python 2.5 was released on September 19, 2006. The changes in Python 2.5 are an interesting mix of language and library improvements. The library enhancements will be more important to Python's user community, I think, because several widely useful packages were added. New -modules include ElementTree for XML processing (:mod:`xml.etree`), -the SQLite database module (:mod:`sqlite`), and the :mod:`ctypes` +modules include ElementTree for XML processing (:mod:`xml.etree.ElementTree`), +the SQLite database module (:mod:`sqlite3`), and the :mod:`ctypes` module for calling C functions. The language changes are of middling significance. Some pleasant new features @@ -134,14 +134,14 @@ PEP 309: Partial Function Application The :mod:`functools` module is intended to contain tools for functional-style programming. -One useful tool in this module is the :func:`partial` function. For programs +One useful tool in this module is the :func:`~functools.partial` function. For programs written in a functional style, you'll sometimes want to construct variants of existing functions that have some of the parameters filled in. Consider a Python function ``f(a, b, c)``; you could create a new function ``g(b, c)`` that was equivalent to ``f(1, b, c)``. This is called "partial function application". -:func:`partial` takes the arguments ``(function, arg1, arg2, ... kwarg1=value1, +:func:`~functools.partial` takes the arguments ``(function, arg1, arg2, ... kwarg1=value1, kwarg2=value2)``. The resulting object is callable, so you can just call it to invoke *function* with the filled-in arguments. @@ -159,7 +159,7 @@ Here's a small but realistic example:: Here's another example, from a program that uses PyGTK. Here a context-sensitive pop-up menu is being constructed dynamically. The callback provided -for the menu option is a partially applied version of the :meth:`open_item` +for the menu option is a partially applied version of the ``open_item()`` method, where the first argument has been provided. :: ... @@ -172,7 +172,7 @@ method, where the first argument has been provided. :: Another function in the :mod:`functools` module is the ``update_wrapper(wrapper, wrapped)`` function that helps you write -well-behaved decorators. :func:`update_wrapper` copies the name, module, and +well-behaved decorators. :func:`~functools.update_wrapper` copies the name, module, and docstring attribute to a wrapper function so that tracebacks inside the wrapped function are easier to understand. For example, you might write:: @@ -183,7 +183,7 @@ function are easier to understand. For example, you might write:: functools.update_wrapper(wrapper, f) return wrapper -:func:`wraps` is a decorator that can be used inside your own decorators to copy +:func:`~functools.wraps` is a decorator that can be used inside your own decorators to copy the wrapped function's information. An alternate version of the previous example would be:: @@ -209,7 +209,7 @@ example would be:: PEP 314: Metadata for Python Software Packages v1.1 =================================================== -Some simple dependency support was added to Distutils. The :func:`setup` +Some simple dependency support was added to Distutils. The :func:`!setup` function now has ``requires``, ``provides``, and ``obsoletes`` keyword parameters. When you build a source distribution using the ``sdist`` command, the dependency information will be recorded in the :file:`PKG-INFO` file. @@ -271,26 +271,26 @@ Let's say you have a package directory like this:: pkg/main.py pkg/string.py -This defines a package named :mod:`pkg` containing the :mod:`pkg.main` and -:mod:`pkg.string` submodules. +This defines a package named ``pkg`` containing the ``pkg.main`` and +``pkg.string`` submodules. Consider the code in the :file:`main.py` module. What happens if it executes the statement ``import string``? In Python 2.4 and earlier, it will first look in the package's directory to perform a relative import, finds :file:`pkg/string.py`, imports the contents of that file as the -:mod:`pkg.string` module, and that module is bound to the name ``string`` in the -:mod:`pkg.main` module's namespace. +``pkg.string`` module, and that module is bound to the name ``string`` in the +``pkg.main`` module's namespace. -That's fine if :mod:`pkg.string` was what you wanted. But what if you wanted +That's fine if ``pkg.string`` was what you wanted. But what if you wanted Python's standard :mod:`string` module? There's no clean way to ignore -:mod:`pkg.string` and look for the standard module; generally you had to look at +``pkg.string`` and look for the standard module; generally you had to look at the contents of ``sys.modules``, which is slightly unclean. Holger Krekel's -:mod:`py.std` package provides a tidier way to perform imports from the standard +:mod:`!py.std` package provides a tidier way to perform imports from the standard library, ``import py; py.std.string.join()``, but that package isn't available on all Python installations. Reading code which relies on relative imports is also less clear, because a -reader may be confused about which module, :mod:`string` or :mod:`pkg.string`, +reader may be confused about which module, :mod:`string` or ``pkg.string``, is intended to be used. Python users soon learned not to duplicate the names of standard library modules in the names of their packages' submodules, but you can't protect against having your submodule's name being used for a new module @@ -313,9 +313,9 @@ name when using the ``from ... import`` form:: from . import string This imports the :mod:`string` module relative to the current package, so in -:mod:`pkg.main` this will import *name1* and *name2* from :mod:`pkg.string`. +``pkg.main`` this will import *name1* and *name2* from ``pkg.string``. Additional leading periods perform the relative import starting from the parent -of the current package. For example, code in the :mod:`A.B.C` module can do:: +of the current package. For example, code in the ``A.B.C`` module can do:: from . import D # Imports A.B.D from .. import E # Imports A.E @@ -331,7 +331,7 @@ statement, only the ``from ... import`` form. PEP written by Aahz; implemented by Thomas Wouters. https://pylib.readthedocs.io/ - The py library by Holger Krekel, which contains the :mod:`py.std` package. + The py library by Holger Krekel, which contains the :mod:`!py.std` package. .. ====================================================================== @@ -347,7 +347,7 @@ Python interpreter, the switch now uses an implementation in a new module, :mod:`runpy`. The :mod:`runpy` module implements a more sophisticated import mechanism so that -it's now possible to run modules in a package such as :mod:`pychecker.checker`. +it's now possible to run modules in a package such as :mod:`!pychecker.checker`. The module also supports alternative import mechanisms such as the :mod:`zipimport` module. This means you can add a .zip archive's path to ``sys.path`` and then use the :option:`-m` switch to execute code from the @@ -392,8 +392,8 @@ write:: The code in *block-1* is executed. If the code raises an exception, the various :keyword:`except` blocks are tested: if the exception is of class -:class:`Exception1`, *handler-1* is executed; otherwise if it's of class -:class:`Exception2`, *handler-2* is executed, and so forth. If no exception is +``Exception1``, *handler-1* is executed; otherwise if it's of class +``Exception2``, *handler-2* is executed, and so forth. If no exception is raised, the *else-block* is executed. No matter what happened previously, the *final-block* is executed once the code @@ -492,21 +492,21 @@ And here's an example of changing the counter:: :keyword:`yield` will usually return :const:`None`, so you should always check for this case. Don't just use its value in expressions unless you're sure that -the :meth:`send` method will be the only method used to resume your generator +the :meth:`~generator.send` method will be the only method used to resume your generator function. -In addition to :meth:`send`, there are two other new methods on generators: +In addition to :meth:`~generator.send`, there are two other new methods on generators: * ``throw(type, value=None, traceback=None)`` is used to raise an exception inside the generator; the exception is raised by the :keyword:`yield` expression where the generator's execution is paused. -* :meth:`close` raises a new :exc:`GeneratorExit` exception inside the generator +* :meth:`~generator.close` raises a new :exc:`GeneratorExit` exception inside the generator to terminate the iteration. On receiving this exception, the generator's code must either raise :exc:`GeneratorExit` or :exc:`StopIteration`. Catching the :exc:`GeneratorExit` exception and returning a value is illegal and will trigger a :exc:`RuntimeError`; if the function raises some other exception, that - exception is propagated to the caller. :meth:`close` will also be called by + exception is propagated to the caller. :meth:`~generator.close` will also be called by Python's garbage collector when the generator is garbage-collected. If you need to run cleanup code when a :exc:`GeneratorExit` occurs, I suggest @@ -521,8 +521,8 @@ function, and a :keyword:`return` statement), but coroutines can be entered, exited, and resumed at many different points (the :keyword:`yield` statements). We'll have to figure out patterns for using coroutines effectively in Python. -The addition of the :meth:`close` method has one side effect that isn't obvious. -:meth:`close` is called when a generator is garbage-collected, so this means the +The addition of the :meth:`~generator.close` method has one side effect that isn't obvious. +:meth:`~generator.close` is called when a generator is garbage-collected, so this means the generator's code gets one last chance to run before the generator is destroyed. This last chance means that ``try...finally`` statements in generators can now be guaranteed to work; the :keyword:`finally` clause will now always get a @@ -534,8 +534,8 @@ seems like a minor bit of language trivia, but using generators and in the following section. Another even more esoteric effect of this change: previously, the -:attr:`gi_frame` attribute of a generator was always a frame object. It's now -possible for :attr:`gi_frame` to be ``None`` once the generator has been +:attr:`!gi_frame` attribute of a generator was always a frame object. It's now +possible for :attr:`!gi_frame` to be ``None`` once the generator has been exhausted. @@ -622,7 +622,7 @@ The :mod:`threading` module's locks and condition variables also support the The lock is acquired before the block is executed and always released once the block is complete. -The new :func:`localcontext` function in the :mod:`decimal` module makes it easy +The new :func:`~decimal.localcontext` function in the :mod:`decimal` module makes it easy to save and restore the current decimal context, which encapsulates the desired precision and rounding characteristics for computations:: @@ -692,7 +692,7 @@ be to let the user write code like this:: The transaction should be committed if the code in the block runs flawlessly or rolled back if there's an exception. Here's the basic interface for -:class:`DatabaseConnection` that I'll assume:: +``DatabaseConnection`` that I'll assume:: class DatabaseConnection: # Database interface @@ -745,7 +745,7 @@ The contextlib module The new :mod:`contextlib` module provides some functions and a decorator that are useful for writing objects for use with the ':keyword:`with`' statement. -The decorator is called :func:`contextmanager`, and lets you write a single +The decorator is called :deco:`~contextlib.contextmanager`, and lets you write a single generator function instead of defining a new class. The generator should yield exactly one value. The code up to the :keyword:`yield` will be executed as the :meth:`~object.__enter__` method, and the value yielded will be the method's return @@ -910,7 +910,7 @@ may therefore need to have some variables changed to :c:type:`Py_ssize_t`. The :c:func:`PyArg_ParseTuple` and :c:func:`Py_BuildValue` functions have a new conversion code, ``n``, for :c:type:`Py_ssize_t`. :c:func:`PyArg_ParseTuple`'s ``s#`` and ``t#`` still output :c:expr:`int` by default, but you can define the -macro :c:macro:`PY_SSIZE_T_CLEAN` before including :file:`Python.h` to make +macro :c:macro:`!PY_SSIZE_T_CLEAN` before including :file:`Python.h` to make them return :c:type:`Py_ssize_t`. :pep:`353` has a section on conversion guidelines that extension authors should @@ -931,19 +931,19 @@ PEP 357: The '__index__' method =============================== The NumPy developers had a problem that could only be solved by adding a new -special method, :meth:`__index__`. When using slice notation, as in +special method, :meth:`~object.__index__`. When using slice notation, as in ``[start:stop:step]``, the values of the *start*, *stop*, and *step* indexes must all be either integers or long integers. NumPy defines a variety of specialized integer types corresponding to unsigned and signed integers of 8, 16, 32, and 64 bits, but there was no way to signal that these types could be used as slice indexes. -Slicing can't just use the existing :meth:`__int__` method because that method +Slicing can't just use the existing :meth:`~object.__int__` method because that method is also used to implement coercion to integers. If slicing used -:meth:`__int__`, floating-point numbers would also become legal slice indexes +:meth:`~object.__int__`, floating-point numbers would also become legal slice indexes and that's clearly an undesirable behaviour. -Instead, a new special method called :meth:`__index__` was added. It takes no +Instead, a new special method called :meth:`~object.__index__` was added. It takes no arguments and returns an integer giving the slice index to use. For example:: class C: @@ -957,7 +957,7 @@ interpreter will check that the type returned is correct, and raises a A corresponding :c:member:`~PyNumberMethods.nb_index` slot was added to the C-level :c:type:`PyNumberMethods` structure to let C extensions implement this protocol. ``PyNumber_Index(obj)`` can be used in extension code to call the -:meth:`__index__` function and retrieve its result. +:meth:`~object.__index__` function and retrieve its result. .. seealso:: @@ -978,7 +978,7 @@ Here are all of the changes that Python 2.5 makes to the core Python language. * The :class:`dict` type has a new hook for letting subclasses provide a default value when a key isn't contained in the dictionary. When a key isn't found, the dictionary's ``__missing__(key)`` method will be called. This hook is used - to implement the new :class:`defaultdict` class in the :mod:`collections` + to implement the new :class:`~collections.defaultdict` class in the :mod:`collections` module. The following example defines a dictionary that returns zero for any missing key:: @@ -1017,7 +1017,7 @@ Here are all of the changes that Python 2.5 makes to the core Python language. (Implemented by Fredrik Lundh following a suggestion by Raymond Hettinger.) -* The :meth:`startswith` and :meth:`endswith` methods of string types now accept +* The :meth:`~str.startswith` and :meth:`~str.endswith` methods of string types now accept tuples of strings to check for. :: def is_image_file (filename): @@ -1028,7 +1028,7 @@ Here are all of the changes that Python 2.5 makes to the core Python language. .. RFE #1491485 * The :func:`min` and :func:`max` built-in functions gained a ``key`` keyword - parameter analogous to the ``key`` argument for :meth:`sort`. This parameter + parameter analogous to the ``key`` argument for :meth:`~list.sort`. This parameter supplies a function that takes a single argument and is called for every value in the list; :func:`min`/:func:`max` will return the element with the smallest/largest return value from this function. For example, to find the @@ -1049,12 +1049,12 @@ Here are all of the changes that Python 2.5 makes to the core Python language. returned by the iterator evaluate as true. (Suggested by Guido van Rossum, and implemented by Raymond Hettinger.) -* The result of a class's :meth:`__hash__` method can now be either a long +* The result of a class's :meth:`~object.__hash__` method can now be either a long integer or a regular integer. If a long integer is returned, the hash of that value is taken. In earlier versions the hash value was required to be a regular integer, but in 2.5 the :func:`id` built-in was changed to always return non-negative numbers, and users often seem to use ``id(self)`` in - :meth:`__hash__` methods (though this is discouraged). + :meth:`~object.__hash__` methods (though this is discouraged). .. Bug #1536021 @@ -1166,7 +1166,7 @@ marked in the following list. .. Patch 1442927 * It's now illegal to mix iterating over a file with ``for line in file`` and - calling the file object's :meth:`read`/:meth:`readline`/:meth:`readlines` + calling the file object's :meth:`!read`/:meth:`!readline`/:meth:`!readlines` methods. Iteration uses an internal buffer and the :meth:`!read\*` methods don't use that buffer. Instead they would return the data following the buffer, causing the data to appear out of order. Mixing iteration and these @@ -1204,7 +1204,7 @@ marked in the following list. Sean Reifschneider at the NeedForSpeed sprint.) * Importing now caches the paths tried, recording whether they exist or not so - that the interpreter makes fewer :c:func:`open` and :c:func:`stat` calls on + that the interpreter makes fewer :c:func:`!open` and :c:func:`!stat` calls on startup. (Contributed by Martin von Löwis and Georg Brandl.) .. Patch 921466 @@ -1226,23 +1226,24 @@ complete list of changes, or look through the SVN logs for all the details. u-LAW encoding has been improved. (Contributed by Lars Immisch.) * The :mod:`codecs` module gained support for incremental codecs. The - :func:`codec.lookup` function now returns a :class:`CodecInfo` instance instead - of a tuple. :class:`CodecInfo` instances behave like a 4-tuple to preserve - backward compatibility but also have the attributes :attr:`encode`, - :attr:`decode`, :attr:`incrementalencoder`, :attr:`incrementaldecoder`, - :attr:`streamwriter`, and :attr:`streamreader`. Incremental codecs can receive + :func:`codecs.lookup` function now returns a :class:`~codecs.CodecInfo` instance instead + of a tuple. :class:`~codecs.CodecInfo` instances behave like a 4-tuple to preserve + backward compatibility but also have the attributes :attr:`~codecs.CodecInfo.encode`, + :attr:`~codecs.CodecInfo.decode`, :attr:`~codecs.CodecInfo.incrementalencoder`, + :attr:`~codecs.CodecInfo.incrementaldecoder`, :attr:`~codecs.CodecInfo.streamwriter`, + and :attr:`~codecs.CodecInfo.streamreader`. Incremental codecs can receive input and produce output in multiple chunks; the output is the same as if the entire input was fed to the non-incremental codec. See the :mod:`codecs` module documentation for details. (Designed and implemented by Walter Dörwald.) .. Patch 1436130 -* The :mod:`collections` module gained a new type, :class:`defaultdict`, that +* The :mod:`collections` module gained a new type, :class:`~collections.defaultdict`, that subclasses the standard :class:`dict` type. The new type mostly behaves like a dictionary but constructs a default value when a key isn't present, automatically adding it to the dictionary for the requested key value. - The first argument to :class:`defaultdict`'s constructor is a factory function + The first argument to :class:`~collections.defaultdict`'s constructor is a factory function that gets called whenever a key is requested but not found. This factory function receives no arguments, so you can use built-in type constructors such as :func:`list` or :func:`int`. For example, you can make an index of words @@ -1268,7 +1269,7 @@ complete list of changes, or look through the SVN logs for all the details. (Contributed by Guido van Rossum.) -* The :class:`deque` double-ended queue type supplied by the :mod:`collections` +* The :class:`~collections.deque` double-ended queue type supplied by the :mod:`collections` module now has a ``remove(value)`` method that removes the first occurrence of *value* in the queue, raising :exc:`ValueError` if the value isn't found. (Contributed by Raymond Hettinger.) @@ -1287,15 +1288,15 @@ complete list of changes, or look through the SVN logs for all the details. Also, the :mod:`pstats` module for analyzing the data measured by the profiler now supports directing the output to any file object by supplying a *stream* - argument to the :class:`Stats` constructor. (Contributed by Skip Montanaro.) + argument to the :class:`~pstats.Stats` constructor. (Contributed by Skip Montanaro.) * The :mod:`csv` module, which parses files in comma-separated value format, received several enhancements and a number of bugfixes. You can now set the maximum size in bytes of a field by calling the ``csv.field_size_limit(new_limit)`` function; omitting the *new_limit* - argument will return the currently set limit. The :class:`reader` class now has - a :attr:`line_num` attribute that counts the number of physical lines read from - the source; records can span multiple physical lines, so :attr:`line_num` is not + argument will return the currently set limit. The :class:`~csv.reader` class now has + a :attr:`~csv.csvreader.line_num` attribute that counts the number of physical lines read from + the source; records can span multiple physical lines, so :attr:`~csv.csvreader.line_num` is not the same as the number of records read. The CSV parser is now stricter about multi-line quoted fields. Previously, if a @@ -1313,12 +1314,12 @@ complete list of changes, or look through the SVN logs for all the details. by Josh Spoerri. It uses the same format characters as :func:`time.strptime` and :func:`time.strftime`:: - from datetime import datetime + import datetime as dt - ts = datetime.strptime('10:13:15 2006-03-07', - '%H:%M:%S %Y-%m-%d') + ts = dt.datetime.strptime('10:13:15 2006-03-07', + '%H:%M:%S %Y-%m-%d') -* The :meth:`SequenceMatcher.get_matching_blocks` method in the :mod:`difflib` +* The :meth:`difflib.SequenceMatcher.get_matching_blocks` method in the :mod:`difflib` module now guarantees to return a minimal list of blocks describing matching subsequences. Previously, the algorithm would occasionally break a block of matching elements into two list entries. (Enhancement by Tim Peters.) @@ -1327,8 +1328,8 @@ complete list of changes, or look through the SVN logs for all the details. being executed at all. This is intended for code snippets that are usage examples intended for the reader and aren't actually test cases. - An *encoding* parameter was added to the :func:`testfile` function and the - :class:`DocFileSuite` class to specify the file's encoding. This makes it + An *encoding* parameter was added to the :func:`~doctest.testfile` function and the + :class:`~doctest.DocFileSuite` class to specify the file's encoding. This makes it easier to use non-ASCII characters in tests contained within a docstring. (Contributed by Bjorn Tillenius.) @@ -1347,20 +1348,20 @@ complete list of changes, or look through the SVN logs for all the details. :func:`input` function to allow opening files in binary or :term:`universal newlines` mode. Another new parameter, *openhook*, lets you use a function other than :func:`open` to open the input files. Once you're iterating over - the set of files, the :class:`FileInput` object's new :meth:`~fileinput.fileno` returns + the set of files, the :class:`~fileinput.FileInput` object's new :meth:`~fileinput.fileno` returns the file descriptor for the currently opened file. (Contributed by Georg Brandl.) -* In the :mod:`gc` module, the new :func:`get_count` function returns a 3-tuple +* In the :mod:`gc` module, the new :func:`~gc.get_count` function returns a 3-tuple containing the current collection counts for the three GC generations. This is accounting information for the garbage collector; when these counts reach a specified threshold, a garbage collection sweep will be made. The existing :func:`gc.collect` function now takes an optional *generation* argument of 0, 1, or 2 to specify which generation to collect. (Contributed by Barry Warsaw.) -* The :func:`nsmallest` and :func:`nlargest` functions in the :mod:`heapq` +* The :func:`~heapq.nsmallest` and :func:`~heapq.nlargest` functions in the :mod:`heapq` module now support a ``key`` keyword parameter similar to the one provided by - the :func:`min`/:func:`max` functions and the :meth:`sort` methods. For + the :func:`min`/:func:`max` functions and the :meth:`~list.sort` methods. For example:: >>> import heapq @@ -1382,7 +1383,7 @@ complete list of changes, or look through the SVN logs for all the details. (Contributed by Raymond Hettinger.) * The :func:`format` function in the :mod:`locale` module has been modified and - two new functions were added, :func:`format_string` and :func:`currency`. + two new functions were added, :func:`~locale.format_string` and :func:`~locale.currency`. The :func:`format` function's *val* parameter could previously be a string as long as no more than one %char specifier appeared; now the parameter must be @@ -1391,10 +1392,10 @@ complete list of changes, or look through the SVN logs for all the details. formatting currency in placing a separator between groups of three digits. To format strings with multiple %char specifiers, use the new - :func:`format_string` function that works like :func:`format` but also supports + :func:`~locale.format_string` function that works like :func:`format` but also supports mixing %char specifiers with arbitrary text. - A new :func:`currency` function was also added that formats a number according + A new :func:`~locale.currency` function was also added that formats a number according to the current locale's settings. (Contributed by Georg Brandl.) @@ -1403,9 +1404,11 @@ complete list of changes, or look through the SVN logs for all the details. * The :mod:`mailbox` module underwent a massive rewrite to add the capability to modify mailboxes in addition to reading them. A new set of classes that include - :class:`mbox`, :class:`MH`, and :class:`Maildir` are used to read mailboxes, and + :class:`~mailbox.mbox`, :class:`~mailbox.MH`, and :class:`~mailbox.Maildir` + are used to read mailboxes, and have an ``add(message)`` method to add messages, ``remove(key)`` to - remove messages, and :meth:`lock`/:meth:`unlock` to lock/unlock the mailbox. + remove messages, and :meth:`~mailbox.Mailbox.lock`/:meth:`~mailbox.Mailbox.unlock` + to lock/unlock the mailbox. The following example converts a maildir-format mailbox into an mbox-format one:: @@ -1430,19 +1433,19 @@ complete list of changes, or look through the SVN logs for all the details. default domain by supplying a *domain* argument to the :func:`!nis.match` and :func:`!nis.maps` functions. (Contributed by Ben Bell.) -* The :mod:`operator` module's :func:`itemgetter` and :func:`attrgetter` +* The :mod:`operator` module's :func:`~operator.itemgetter` and :func:`~operator.attrgetter` functions now support multiple fields. A call such as ``operator.attrgetter('a', 'b')`` will return a function that retrieves the - :attr:`a` and :attr:`b` attributes. Combining this new feature with the - :meth:`sort` method's ``key`` parameter lets you easily sort lists using + ``a`` and ``b`` attributes. Combining this new feature with the + :meth:`~list.sort` method's ``key`` parameter lets you easily sort lists using multiple fields. (Contributed by Raymond Hettinger.) * The :mod:`optparse` module was updated to version 1.5.1 of the Optik library. - The :class:`OptionParser` class gained an :attr:`epilog` attribute, a string - that will be printed after the help message, and a :meth:`destroy` method to + The :class:`~optparse.OptionParser` class gained an :attr:`!epilog` attribute, a string + that will be printed after the help message, and a :meth:`!destroy` method to break reference cycles created by the object. (Contributed by Greg Ward.) -* The :mod:`os` module underwent several changes. The :attr:`stat_float_times` +* The :mod:`os` module underwent several changes. The :attr:`!stat_float_times` variable now defaults to true, meaning that :func:`os.stat` will now return time values as floats. (This doesn't necessarily mean that :func:`os.stat` will return times that are precise to fractions of a second; not all systems support @@ -1453,19 +1456,20 @@ complete list of changes, or look through the SVN logs for all the details. :func:`os.lseek` function. Two new constants for locking are :const:`os.O_SHLOCK` and :const:`os.O_EXLOCK`. - Two new functions, :func:`wait3` and :func:`wait4`, were added. They're similar - the :func:`waitpid` function which waits for a child process to exit and returns - a tuple of the process ID and its exit status, but :func:`wait3` and - :func:`wait4` return additional information. :func:`wait3` doesn't take a + Two new functions, :func:`~os.wait3` and :func:`~os.wait4`, were added. They're similar + the :func:`~os.waitpid` function which waits for a child process to exit and returns + a tuple of the process ID and its exit status, but :func:`~os.wait3` and + :func:`~os.wait4` return additional information. :func:`~os.wait3` doesn't take a process ID as input, so it waits for any child process to exit and returns a 3-tuple of *process-id*, *exit-status*, *resource-usage* as returned from the :func:`resource.getrusage` function. ``wait4(pid)`` does take a process ID. (Contributed by Chad J. Schroeder.) On FreeBSD, the :func:`os.stat` function now returns times with nanosecond - resolution, and the returned object now has :attr:`st_gen` and - :attr:`st_birthtime`. The :attr:`st_flags` attribute is also available, if the - platform supports it. (Contributed by Antti Louko and Diego Pettenò.) + resolution, and the returned object now has :attr:`~os.stat_result.st_gen` and + :attr:`~os.stat_result.st_birthtime`. The :attr:`~os.stat_result.st_flags` + attribute is also available, if the platform supports it. + (Contributed by Antti Louko and Diego Pettenò.) .. (Patch 1180695, 1212117) @@ -1495,21 +1499,21 @@ complete list of changes, or look through the SVN logs for all the details. instead of performing many different operations and reducing the result to a single number as :file:`pystone.py` does. -* The :mod:`pyexpat` module now uses version 2.0 of the Expat parser. +* The :mod:`!pyexpat` module now uses version 2.0 of the Expat parser. (Contributed by Trent Mick.) -* The :class:`~queue.Queue` class provided by the :mod:`Queue` module gained two new - methods. :meth:`join` blocks until all items in the queue have been retrieved +* The :class:`~queue.Queue` class provided by the :mod:`queue` module gained two new + methods. :meth:`~queue.Queue.join` blocks until all items in the queue have been retrieved and all processing work on the items have been completed. Worker threads call - the other new method, :meth:`task_done`, to signal that processing for an item + the other new method, :meth:`~queue.Queue.task_done`, to signal that processing for an item has been completed. (Contributed by Raymond Hettinger.) -* The old :mod:`regex` and :mod:`regsub` modules, which have been deprecated +* The old :mod:`!regex` and :mod:`!regsub` modules, which have been deprecated ever since Python 2.0, have finally been deleted. Other deleted modules: - :mod:`statcache`, :mod:`tzparse`, :mod:`whrandom`. + :mod:`!statcache`, :mod:`!tzparse`, :mod:`!whrandom`. * Also deleted: the :file:`lib-old` directory, which includes ancient modules - such as :mod:`dircmp` and :mod:`ni`, was removed. :file:`lib-old` wasn't on the + such as :mod:`!dircmp` and :mod:`!ni`, was removed. :file:`lib-old` wasn't on the default ``sys.path``, so unless your programs explicitly added the directory to ``sys.path``, this removal shouldn't affect your code. @@ -1519,14 +1523,16 @@ complete list of changes, or look through the SVN logs for all the details. .. Patch #1472854 -* The :mod:`SimpleXMLRPCServer ` and :mod:`DocXMLRPCServer ` classes now have a - :attr:`rpc_paths` attribute that constrains XML-RPC operations to a limited set +* The :mod:`SimpleXMLRPCServer ` and :mod:`DocXMLRPCServer + ` classes now have a :attr:`~xmlrpc.server.SimpleXMLRPCRequestHandler.rpc_paths` + attribute that constrains XML-RPC operations to a limited set of URL paths; the default is to allow only ``'/'`` and ``'/RPC2'``. Setting - :attr:`rpc_paths` to ``None`` or an empty tuple disables this path checking. + :attr:`~xmlrpc.server.SimpleXMLRPCRequestHandler.rpc_paths` to ``None`` or an + empty tuple disables this path checking. .. Bug #1473048 -* The :mod:`socket` module now supports :const:`AF_NETLINK` sockets on Linux, +* The :mod:`socket` module now supports :const:`!AF_NETLINK` sockets on Linux, thanks to a patch from Philippe Biondi. Netlink sockets are a Linux-specific mechanism for communications between a user-space process and kernel code; an introductory article about them is at https://www.linuxjournal.com/article/7356. @@ -1538,19 +1544,19 @@ complete list of changes, or look through the SVN logs for all the details. supports the buffer protocol instead of returning the data as a string. This means you can put the data directly into an array or a memory-mapped file. - Socket objects also gained :meth:`getfamily`, :meth:`gettype`, and - :meth:`getproto` accessor methods to retrieve the family, type, and protocol + Socket objects also gained :meth:`!getfamily`, :meth:`!gettype`, and + :meth:`!getproto` accessor methods to retrieve the family, type, and protocol values for the socket. * New module: the :mod:`!spwd` module provides functions for accessing the shadow password database on systems that support shadow passwords. * The :mod:`struct` is now faster because it compiles format strings into - :class:`Struct` objects with :meth:`pack` and :meth:`unpack` methods. This is + :class:`~struct.Struct` objects with :meth:`~struct.Struct.pack` and :meth:`~struct.Struct.unpack` methods. This is similar to how the :mod:`re` module lets you create compiled regular expression - objects. You can still use the module-level :func:`pack` and :func:`unpack` - functions; they'll create :class:`Struct` objects and cache them. Or you can - use :class:`Struct` instances directly:: + objects. You can still use the module-level :func:`~struct.pack` and :func:`~struct.unpack` + functions; they'll create :class:`~struct.Struct` objects and cache them. Or you can + use :class:`~struct.Struct` instances directly:: s = struct.Struct('ih3s') @@ -1562,7 +1568,7 @@ complete list of changes, or look through the SVN logs for all the details. offset)`` methods. This lets you store data directly into an array or a memory-mapped file. - (:class:`Struct` objects were implemented by Bob Ippolito at the NeedForSpeed + (:class:`~struct.Struct` objects were implemented by Bob Ippolito at the NeedForSpeed sprint. Support for buffer objects was added by Martin Blais, also at the NeedForSpeed sprint.) @@ -1582,8 +1588,8 @@ complete list of changes, or look through the SVN logs for all the details. topmost stack frame currently active in that thread at the time the function is called. (Contributed by Tim Peters.) -* The :class:`TarFile` class in the :mod:`tarfile` module now has an - :meth:`extractall` method that extracts all members from the archive into the +* The :class:`~tarfile.TarFile` class in the :mod:`tarfile` module now has an + :meth:`~tarfile.TarFile.extractall` method that extracts all members from the archive into the current working directory. It's also possible to set a different directory as the extraction target, and to unpack only a subset of the archive's members. @@ -1607,8 +1613,8 @@ complete list of changes, or look through the SVN logs for all the details. * New module: the :mod:`uuid` module generates universally unique identifiers (UUIDs) according to :rfc:`4122`. The RFC defines several different UUID versions that are generated from a starting string, from system properties, or - purely randomly. This module contains a :class:`UUID` class and functions - named :func:`uuid1`, :func:`uuid3`, :func:`uuid4`, and :func:`uuid5` to + purely randomly. This module contains a :class:`~uuid.UUID` class and functions + named :func:`~uuid.uuid1`, :func:`~uuid.uuid3`, :func:`~uuid.uuid4`, and :func:`~uuid.uuid5` to generate different versions of UUID. (Version 2 UUIDs are not specified in :rfc:`4122` and are not supported by this module.) :: @@ -1631,18 +1637,18 @@ complete list of changes, or look through the SVN logs for all the details. (Contributed by Ka-Ping Yee.) -* The :mod:`weakref` module's :class:`WeakKeyDictionary` and - :class:`WeakValueDictionary` types gained new methods for iterating over the - weak references contained in the dictionary. :meth:`iterkeyrefs` and - :meth:`keyrefs` methods were added to :class:`WeakKeyDictionary`, and - :meth:`itervaluerefs` and :meth:`valuerefs` were added to - :class:`WeakValueDictionary`. (Contributed by Fred L. Drake, Jr.) +* The :mod:`weakref` module's :class:`~weakref.WeakKeyDictionary` and + :class:`~weakref.WeakValueDictionary` types gained new methods for iterating over the + weak references contained in the dictionary. :meth:`!iterkeyrefs` and + :meth:`~weakref.WeakKeyDictionary.keyrefs` methods were added to :class:`~weakref.WeakKeyDictionary`, and + :meth:`!itervaluerefs` and :meth:`~weakref.WeakValueDictionary.valuerefs` were added to + :class:`~weakref.WeakValueDictionary`. (Contributed by Fred L. Drake, Jr.) * The :mod:`webbrowser` module received a number of enhancements. It's now usable as a script with ``python -m webbrowser``, taking a URL as the argument; there are a number of switches to control the behaviour (:option:`!-n` for a new browser window, :option:`!-t` for a new tab). New module-level functions, - :func:`open_new` and :func:`open_new_tab`, were added to support this. The + :func:`~webbrowser.open_new` and :func:`~webbrowser.open_new_tab`, were added to support this. The module's :func:`open` function supports an additional feature, an *autoraise* parameter that signals whether to raise the open window when possible. A number of additional browsers were added to the supported list such as Firefox, Opera, @@ -1663,9 +1669,9 @@ complete list of changes, or look through the SVN logs for all the details. .. Patch 1446489 -* The :mod:`zlib` module's :class:`Compress` and :class:`Decompress` objects now +* The :mod:`zlib` module's :class:`!Compress` and :class:`!Decompress` objects now support a :meth:`copy` method that makes a copy of the object's internal state - and returns a new :class:`Compress` or :class:`Decompress` object. + and returns a new :class:`!Compress` or :class:`!Decompress` object. (Contributed by Chris AtLee.) .. Patch 1435422 @@ -1685,34 +1691,34 @@ provides functions for loading shared libraries and calling functions in them. The :mod:`ctypes` package is much fancier. To load a shared library or DLL, you must create an instance of the -:class:`CDLL` class and provide the name or path of the shared library or DLL. +:class:`~ctypes.CDLL` class and provide the name or path of the shared library or DLL. Once that's done, you can call arbitrary functions by accessing them as -attributes of the :class:`CDLL` object. :: +attributes of the :class:`~ctypes.CDLL` object. :: import ctypes libc = ctypes.CDLL('libc.so.6') result = libc.printf("Line of output\n") -Type constructors for the various C types are provided: :func:`c_int`, -:func:`c_float`, :func:`c_double`, :func:`c_char_p` (equivalent to :c:expr:`char +Type constructors for the various C types are provided: :func:`~ctypes.c_int`, +:func:`~ctypes.c_float`, :func:`~ctypes.c_double`, :func:`~ctypes.c_char_p` (equivalent to :c:expr:`char \*`), and so forth. Unlike Python's types, the C versions are all mutable; you -can assign to their :attr:`value` attribute to change the wrapped value. Python +can assign to their :attr:`~ctypes._SimpleCData.value` attribute to change the wrapped value. Python integers and strings will be automatically converted to the corresponding C types, but for other types you must call the correct type constructor. (And I mean *must*; getting it wrong will often result in the interpreter crashing with a segmentation fault.) -You shouldn't use :func:`c_char_p` with a Python string when the C function will +You shouldn't use :func:`~ctypes.c_char_p` with a Python string when the C function will be modifying the memory area, because Python strings are supposed to be immutable; breaking this rule will cause puzzling bugs. When you need a -modifiable memory area, use :func:`create_string_buffer`:: +modifiable memory area, use :func:`~ctypes.create_string_buffer`:: s = "this is a string" buf = ctypes.create_string_buffer(s) libc.strfry(buf) -C functions are assumed to return integers, but you can set the :attr:`restype` +C functions are assumed to return integers, but you can set the :attr:`~ctypes._CFuncPtr.restype` attribute of the function object to change this:: >>> libc.atof('2.71828') @@ -1760,9 +1766,9 @@ The ElementTree package ----------------------- A subset of Fredrik Lundh's ElementTree library for processing XML has been -added to the standard library as :mod:`xml.etree`. The available modules are -:mod:`ElementTree`, :mod:`ElementPath`, and :mod:`ElementInclude` from -ElementTree 1.2.6. The :mod:`cElementTree` accelerator module is also +added to the standard library as :mod:`!xml.etree`. The available modules are +:mod:`!ElementTree`, :mod:`!ElementPath`, and :mod:`!ElementInclude` from +ElementTree 1.2.6. The :mod:`!cElementTree` accelerator module is also included. The rest of this section will provide a brief overview of using ElementTree. @@ -1770,14 +1776,15 @@ Full documentation for ElementTree is available at https://web.archive.org/web/20201124024954/http://effbot.org/zone/element-index.htm. ElementTree represents an XML document as a tree of element nodes. The text -content of the document is stored as the :attr:`text` and :attr:`tail` +content of the document is stored as the :attr:`~xml.etree.ElementTree.Element.text` +and :attr:`~xml.etree.ElementTree.Element.tail` attributes of (This is one of the major differences between ElementTree and the Document Object Model; in the DOM there are many different types of node, -including :class:`TextNode`.) +including :class:`!TextNode`.) -The most commonly used parsing function is :func:`parse`, that takes either a +The most commonly used parsing function is :func:`~xml.etree.ElementTree.parse`, that takes either a string (assumed to contain a filename) or a file-like object and returns an -:class:`ElementTree` instance:: +:class:`~xml.etree.ElementTree.ElementTree` instance:: from xml.etree import ElementTree as ET @@ -1787,11 +1794,13 @@ string (assumed to contain a filename) or a file-like object and returns an 'http://planet.python.org/rss10.xml') tree = ET.parse(feed) -Once you have an :class:`ElementTree` instance, you can call its :meth:`getroot` -method to get the root :class:`Element` node. +Once you have an :class:`~xml.etree.ElementTree.ElementTree` instance, you can +call its :meth:`~xml.etree.ElementTree.ElementTree.getroot` +method to get the root :class:`~xml.etree.ElementTree.Element` node. -There's also an :func:`XML` function that takes a string literal and returns an -:class:`Element` node (not an :class:`ElementTree`). This function provides a +There's also an :func:`~xml.etree.ElementTree.XML` function that takes a string +literal and returns an :class:`~xml.etree.ElementTree.Element` node (not an +:class:`~xml.etree.ElementTree.ElementTree`). This function provides a tidy way to incorporate XML fragments, approaching the convenience of an XML literal:: @@ -1834,7 +1843,7 @@ list-like operations are used to access child nodes. | ``del elem.attrib[name]`` | Deletes attribute *name*. | +-------------------------------+--------------------------------------------+ -Comments and processing instructions are also represented as :class:`Element` +Comments and processing instructions are also represented as :class:`~xml.etree.ElementTree.Element` nodes. To check if a node is a comment or processing instructions:: if elem.tag is ET.Comment: @@ -1842,8 +1851,8 @@ nodes. To check if a node is a comment or processing instructions:: elif elem.tag is ET.ProcessingInstruction: ... -To generate XML output, you should call the :meth:`ElementTree.write` method. -Like :func:`parse`, it can take either a string or a file-like object:: +To generate XML output, you should call the :meth:`xml.etree.ElementTree.ElementTree.write` method. +Like :func:`~xml.etree.ElementTree.parse`, it can take either a string or a file-like object:: # Encoding is US-ASCII tree.write('output.xml') @@ -1913,7 +1922,7 @@ differently. :: Once a hash object has been created, its methods are the same as before: ``update(string)`` hashes the specified string into the current digest -state, :meth:`digest` and :meth:`hexdigest` return the digest value as a binary +state, :meth:`~hashlib.hash.digest` and :meth:`~hashlib.hash.hexdigest` return the digest value as a binary string or a string of hex digits, and :meth:`copy` returns a new hashing object with the same digest state. @@ -1949,7 +1958,7 @@ doesn't include the SQLite code, only the wrapper module. You'll need to have the SQLite libraries and headers installed before compiling Python, and the build process will compile the module when the necessary headers are available. -To use the module, you must first create a :class:`Connection` object that +To use the module, you must first create a :class:`~sqlite3.Connection` object that represents the database. Here the data will be stored in the :file:`/tmp/example` file:: @@ -1957,8 +1966,8 @@ represents the database. Here the data will be stored in the You can also supply the special name ``:memory:`` to create a database in RAM. -Once you have a :class:`Connection`, you can create a :class:`Cursor` object -and call its :meth:`execute` method to perform SQL commands:: +Once you have a :class:`~sqlite3.Connection`, you can create a :class:`~sqlite3.Cursor` object +and call its :meth:`~sqlite3.Cursor.execute` method to perform SQL commands:: c = conn.cursor() @@ -1977,7 +1986,7 @@ is insecure; it makes your program vulnerable to an SQL injection attack. Instead, use the DB-API's parameter substitution. Put ``?`` as a placeholder wherever you want to use a value, and then provide a tuple of values as the -second argument to the cursor's :meth:`execute` method. (Other database modules +second argument to the cursor's :meth:`~sqlite3.Cursor.execute` method. (Other database modules may use a different placeholder, such as ``%s`` or ``:1``.) For example:: # Never do this -- insecure! @@ -1996,8 +2005,8 @@ may use a different placeholder, such as ``%s`` or ``:1``.) For example:: c.execute('insert into stocks values (?,?,?,?,?)', t) To retrieve data after executing a SELECT statement, you can either treat the -cursor as an iterator, call the cursor's :meth:`fetchone` method to retrieve a -single matching row, or call :meth:`fetchall` to get a list of the matching +cursor as an iterator, call the cursor's :meth:`~sqlite3.Cursor.fetchone` method to retrieve a +single matching row, or call :meth:`~sqlite3.Cursor.fetchall` to get a list of the matching rows. This example uses the iterator form:: @@ -2118,7 +2127,7 @@ Changes to Python's build process and to the C API include: discusses the design. To start learning about the code, read the definition of the various AST nodes in :file:`Parser/Python.asdl`. A Python script reads this file and generates a set of C structure definitions in - :file:`Include/Python-ast.h`. The :c:func:`PyParser_ASTFromString` and + :file:`Include/Python-ast.h`. The :c:func:`!PyParser_ASTFromString` and :c:func:`!PyParser_ASTFromFile`, defined in :file:`Include/pythonrun.h`, take Python source as input and return the root of an AST representing the contents. This AST can then be turned into a code object by :c:func:`!PyAST_Compile`. For @@ -2169,9 +2178,9 @@ Changes to Python's build process and to the C API include: * Two new macros can be used to indicate C functions that are local to the current file so that a faster calling convention can be used. - ``Py_LOCAL(type)`` declares the function as returning a value of the + :c:macro:`Py_LOCAL` declares the function as returning a value of the specified *type* and uses a fast-calling qualifier. - ``Py_LOCAL_INLINE(type)`` does the same thing and also requests the + :c:macro:`Py_LOCAL_INLINE` does the same thing and also requests the function be inlined. If macro :c:macro:`!PY_LOCAL_AGGRESSIVE` is defined before :file:`python.h` is included, a set of more aggressive optimizations are enabled for the module; you should benchmark the results to find out if these @@ -2235,9 +2244,9 @@ code: encoding declaration. In Python 2.4 this triggered a warning, not a syntax error. -* Previously, the :attr:`gi_frame` attribute of a generator was always a frame +* Previously, the :attr:`!gi_frame` attribute of a generator was always a frame object. Because of the :pep:`342` changes described in section :ref:`pep-342`, - it's now possible for :attr:`gi_frame` to be ``None``. + it's now possible for :attr:`!gi_frame` to be ``None``. * A new warning, :class:`UnicodeWarning`, is triggered when you attempt to compare a Unicode string and an 8-bit string that can't be converted to Unicode @@ -2258,11 +2267,12 @@ code: return a tuple of arguments instead. The modules also no longer accept the deprecated *bin* keyword parameter. -* Library: The :mod:`SimpleXMLRPCServer ` and :mod:`DocXMLRPCServer ` classes now - have a :attr:`rpc_paths` attribute that constrains XML-RPC operations to a +* Library: The :mod:`SimpleXMLRPCServer ` and :mod:`DocXMLRPCServer + ` classes now have a :attr:`~xmlrpc.server.SimpleXMLRPCRequestHandler.rpc_paths` + attribute that constrains XML-RPC operations to a limited set of URL paths; the default is to allow only ``'/'`` and ``'/RPC2'``. - Setting :attr:`rpc_paths` to ``None`` or an empty tuple disables this path - checking. + Setting :attr:`~xmlrpc.server.SimpleXMLRPCRequestHandler.rpc_paths` to ``None`` + or an empty tuple disables this path checking. * C API: Many functions now use :c:type:`Py_ssize_t` instead of :c:expr:`int` to allow processing more data on 64-bit machines. Extension code may need to make diff --git a/Doc/whatsnew/2.6.rst b/Doc/whatsnew/2.6.rst index 9dbc07a34e20a1..db5b41b40fecab 100644 --- a/Doc/whatsnew/2.6.rst +++ b/Doc/whatsnew/2.6.rst @@ -56,7 +56,7 @@ Python 2.6 incorporates new features and syntax from 3.0 while remaining compatible with existing code by not removing older features or syntax. When it's not possible to do that, Python 2.6 tries to do what it can, adding compatibility functions in a -:mod:`future_builtins` module and a :option:`!-3` switch to warn about +:mod:`!future_builtins` module and a :option:`!-3` switch to warn about usages that will become unsupported in 3.0. Some significant new packages have been added to the standard library, @@ -101,15 +101,15 @@ to break, they've been backported to 2.6 and are described in this document in the appropriate place. Some of the 3.0-derived features are: -* A :meth:`__complex__` method for converting objects to a complex number. +* A :meth:`~object.__complex__` method for converting objects to a complex number. * Alternate syntax for catching exceptions: ``except TypeError as exc``. * The addition of :func:`functools.reduce` as a synonym for the built-in - :func:`reduce` function. + :func:`!reduce` function. Python 3.0 adds several new built-in functions and changes the semantics of some existing builtins. Functions that are new in 3.0 such as :func:`bin` have simply been added to Python 2.6, but existing -builtins haven't been changed; instead, the :mod:`future_builtins` +builtins haven't been changed; instead, the :mod:`!future_builtins` module has versions with the new 3.0 semantics. Code written to be compatible with 3.0 can do ``from future_builtins import hex, map`` as necessary. @@ -118,7 +118,7 @@ A new command-line switch, :option:`!-3`, enables warnings about features that will be removed in Python 3.0. You can run code with this switch to see how much work will be necessary to port code to 3.0. The value of this switch is available -to Python code as the boolean variable :data:`sys.py3kwarning`, +to Python code as the boolean variable :data:`!sys.py3kwarning`, and to C extension code as :c:data:`!Py_Py3kWarningFlag`. .. seealso:: @@ -307,9 +307,9 @@ The :mod:`threading` module's locks and condition variables also support the The lock is acquired before the block is executed and always released once the block is complete. -The :func:`localcontext` function in the :mod:`decimal` module makes it easy -to save and restore the current decimal context, which encapsulates the desired -precision and rounding characteristics for computations:: +The :func:`~decimal.localcontext` function in the :mod:`decimal` module makes +it easy to save and restore the current decimal context, which encapsulates +the desired precision and rounding characteristics for computations:: from decimal import Decimal, Context, localcontext @@ -337,12 +337,12 @@ underlying implementation and should keep reading. A high-level explanation of the context management protocol is: * The expression is evaluated and should result in an object called a "context - manager". The context manager must have :meth:`~object.__enter__` and :meth:`~object.__exit__` - methods. + manager". The context manager must have :meth:`~object.__enter__` and + :meth:`~object.__exit__` methods. -* The context manager's :meth:`~object.__enter__` method is called. The value returned - is assigned to *VAR*. If no ``as VAR`` clause is present, the value is simply - discarded. +* The context manager's :meth:`~object.__enter__` method is called. The value + returned is assigned to *VAR*. If no ``as VAR`` clause is present, the + value is simply discarded. * The code in *BLOCK* is executed. @@ -378,7 +378,7 @@ be to let the user write code like this:: The transaction should be committed if the code in the block runs flawlessly or rolled back if there's an exception. Here's the basic interface for -:class:`DatabaseConnection` that I'll assume:: +:class:`!DatabaseConnection` that I'll assume:: class DatabaseConnection: # Database interface @@ -431,14 +431,15 @@ The contextlib module The :mod:`contextlib` module provides some functions and a decorator that are useful when writing objects for use with the ':keyword:`with`' statement. -The decorator is called :func:`contextmanager`, and lets you write a single -generator function instead of defining a new class. The generator should yield -exactly one value. The code up to the :keyword:`yield` will be executed as the -:meth:`~object.__enter__` method, and the value yielded will be the method's return -value that will get bound to the variable in the ':keyword:`with`' statement's -:keyword:`!as` clause, if any. The code after the :keyword:`!yield` will be -executed in the :meth:`~object.__exit__` method. Any exception raised in the block will -be raised by the :keyword:`!yield` statement. +The decorator is called :deco:`~contextlib.contextmanager`, and lets you write +a single generator function instead of defining a new class. The generator +should yield exactly one value. The code up to the :keyword:`yield` will be +executed as the :meth:`~object.__enter__` method, and the value yielded will +be the method's return value that will get bound to the variable in the +':keyword:`with`' statement's :keyword:`!as` clause, if any. The code after +the :keyword:`!yield` will be executed in the :meth:`~object.__exit__` method. +Any exception raised in the block will be raised by the :keyword:`!yield` +statement. Using this decorator, our database example from the previous section could be written as:: @@ -469,7 +470,7 @@ statement both starts a database transaction and acquires a thread lock:: with nested (db_transaction(db), lock) as (cursor, locked): ... -Finally, the :func:`closing` function returns its argument so that it can be +Finally, the :func:`~contextlib.closing` function returns its argument so that it can be bound to a variable, and calls the argument's ``.close()`` method at the end of the block. :: @@ -538,7 +539,7 @@ If you don't like the default directory, it can be overridden by an environment variable. :envvar:`PYTHONUSERBASE` sets the root directory used for all Python versions supporting this feature. On Windows, the directory for application-specific data can be changed by -setting the :envvar:`APPDATA` environment variable. You can also +setting the :envvar:`!APPDATA` environment variable. You can also modify the :file:`site.py` file for your Python installation. The feature can be disabled entirely by running Python with the @@ -568,11 +569,12 @@ The :mod:`multiprocessing` module started out as an exact emulation of the :mod:`threading` module using processes instead of threads. That goal was discarded along the path to Python 2.6, but the general approach of the module is still similar. The fundamental class -is the :class:`Process`, which is passed a callable object and -a collection of arguments. The :meth:`start` method +is the :class:`~multiprocessing.Process`, which is passed a callable object and +a collection of arguments. The :meth:`~multiprocessing.Process.start` method sets the callable running in a subprocess, after which you can call -the :meth:`is_alive` method to check whether the subprocess is still running -and the :meth:`join` method to wait for the process to exit. +the :meth:`~multiprocessing.Process.is_alive` method to check whether the +subprocess is still running and the :meth:`~multiprocessing.Process.join` +method to wait for the process to exit. Here's a simple example where the subprocess will calculate a factorial. The function doing the calculation is written strangely so @@ -619,13 +621,16 @@ the object to communicate. (If the parent were to change the value of the global variable, the child's value would be unaffected, and vice versa.) -Two other classes, :class:`Pool` and :class:`Manager`, provide -higher-level interfaces. :class:`Pool` will create a fixed number of -worker processes, and requests can then be distributed to the workers -by calling :meth:`apply` or :meth:`apply_async` to add a single request, -and :meth:`map` or :meth:`map_async` to add a number of -requests. The following code uses a :class:`Pool` to spread requests -across 5 worker processes and retrieve a list of results:: +Two other classes, :class:`~multiprocessing.pool.Pool` and +:class:`~multiprocessing.Manager`, provide higher-level interfaces. +:class:`~multiprocessing.pool.Pool` will create a fixed number of worker +processes, and requests can then be distributed to the workers by calling +:meth:`~multiprocessing.pool.Pool.apply` or +:meth:`~multiprocessing.pool.Pool.apply_async` to add a single request, and +:meth:`~multiprocessing.pool.Pool.map` or +:meth:`~multiprocessing.pool.Pool.map_async` to add a number of +requests. The following code uses a :class:`~multiprocessing.pool.Pool` to +spread requests across 5 worker processes and retrieve a list of results:: from multiprocessing import Pool @@ -646,15 +651,18 @@ This produces the following output:: 33452526613163807108170062053440751665152000000000 ... -The other high-level interface, the :class:`Manager` class, creates a -separate server process that can hold master copies of Python data +The other high-level interface, the :class:`~multiprocessing.Manager` class, +creates a separate server process that can hold master copies of Python data structures. Other processes can then access and modify these data structures using proxy objects. The following example creates a shared dictionary by calling the :meth:`dict` method; the worker processes then insert values into the dictionary. (Locking is not done for you automatically, which doesn't matter in this example. -:class:`Manager`'s methods also include :meth:`Lock`, :meth:`RLock`, -and :meth:`Semaphore` to create shared locks.) +:class:`~multiprocessing.Manager`'s methods also include +:meth:`~multiprocessing.managers.SyncManager.Lock`, +:meth:`~multiprocessing.managers.SyncManager.RLock`, +and :meth:`~multiprocessing.managers.SyncManager.Semaphore` to create +shared locks.) :: @@ -824,7 +832,7 @@ documentation for a :ref:`complete list `; here's a sample: format, followed by a percent sign. ===== ======================================================================== -Classes and types can define a :meth:`__format__` method to control how they're +Classes and types can define a :meth:`~object.__format__` method to control how they're formatted. It receives a single argument, the format specifier:: def __format__(self, format_spec): @@ -834,7 +842,7 @@ formatted. It receives a single argument, the format specifier:: return str(self) There's also a :func:`format` builtin that will format a single -value. It calls the type's :meth:`__format__` method with the +value. It calls the type's :meth:`~object.__format__` method with the provided specifier:: >>> format(75.6564, '.2f') @@ -997,9 +1005,10 @@ sequence of bytes:: u'\u31ef \u3244' Byte arrays support most of the methods of string types, such as -:meth:`startswith`/:meth:`endswith`, :meth:`find`/:meth:`rfind`, -and some of the methods of lists, such as :meth:`append`, -:meth:`pop`, and :meth:`reverse`. +:meth:`~bytearray.startswith`/:meth:`~bytearray.endswith`, +:meth:`~bytearray.find`/:meth:`~bytearray.rfind`, +and some of the methods of lists, such as :meth:`~bytearray.append`, +:meth:`~bytearray.pop`, and :meth:`~bytearray.reverse`. :: @@ -1028,56 +1037,58 @@ PEP 3116: New I/O Library Python's built-in file objects support a number of methods, but file-like objects don't necessarily support all of them. Objects that -imitate files usually support :meth:`read` and :meth:`write`, but they -may not support :meth:`readline`, for example. Python 3.0 introduces -a layered I/O library in the :mod:`io` module that separates buffering -and text-handling features from the fundamental read and write -operations. +imitate files usually support :meth:`!read` and +:meth:`!write`, but they may not support :meth:`!readline`, +for example. Python 3.0 introduces a layered I/O library in the :mod:`io` +module that separates buffering and text-handling features from the +fundamental read and write operations. There are three levels of abstract base classes provided by the :mod:`io` module: -* :class:`RawIOBase` defines raw I/O operations: :meth:`read`, - :meth:`readinto`, - :meth:`write`, :meth:`seek`, :meth:`tell`, :meth:`truncate`, - and :meth:`close`. +* :class:`~io.RawIOBase` defines raw I/O operations: :meth:`~io.RawIOBase.read`, + :meth:`~io.RawIOBase.readinto`, :meth:`~io.RawIOBase.write`, + :meth:`~io.IOBase.seek`, :meth:`~io.IOBase.tell`, :meth:`~io.IOBase.truncate`, + and :meth:`~io.IOBase.close`. Most of the methods of this class will often map to a single system call. - There are also :meth:`readable`, :meth:`writable`, and :meth:`seekable` - methods for determining what operations a given object will allow. + There are also :meth:`~io.IOBase.readable`, :meth:`~io.IOBase.writable`, + and :meth:`~io.IOBase.seekable` methods for determining what operations a + given object will allow. Python 3.0 has concrete implementations of this class for files and sockets, but Python 2.6 hasn't restructured its file and socket objects in this way. -* :class:`BufferedIOBase` is an abstract base class that +* :class:`~io.BufferedIOBase` is