Skip to content

Add an --only-unindexed flag to the indexer. #41

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
yilei merged 1 commit into from
Aug 5, 2026
Merged

Add an --only-unindexed flag to the indexer. #41

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions src/pyrefdev/indexer/crawl_docs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -133,6 +133,7 @@ def crawl_docs(
package: str | None = None,
force: bool = False,
upgrade: bool = False,
only_unindexed: bool = False,
retry_failed_urls: bool = True,
retry_http_404: bool = False,
index: Index = Index(),
Expand All @@ -158,6 +159,8 @@ def crawl_docs(
if pkg.do_not_update:
console.print(f"Skipping {pkg.pypi}: {pkg.do_not_update_reason}")
packages = [pkg for pkg in packages if not pkg.do_not_update]
if only_unindexed:
packages = [pkg for pkg in packages if not pkg.indexed]
if not force and not upgrade and not retry_failed_urls:
packages = [
pkg
Expand Down
5 changes: 4 additions & 1 deletion src/pyrefdev/indexer/update_docs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,19 +19,22 @@ def update_docs(
package: str | None = None,
force: bool = False,
upgrade: bool = True,
only_unindexed: bool = False,
retry_http_404: bool = False,
index: Index = Index(),
seconds_to_sleep_between_requests: float = 5.0,
num_parallel_packages: int = multiprocessing.cpu_count(),
num_threads_per_package: int = multiprocessing.cpu_count(),
) -> None:
"""Crawl and parse docs."""
should_update_last_updated_package = package is None
should_update_last_updated_package = package is None and not only_unindexed
packages = get_packages(package)
for pkg in packages:
if pkg.do_not_update:
console.print(f"Skipping {pkg.pypi}: {pkg.do_not_update_reason}")
packages = [pkg for pkg in packages if not pkg.do_not_update]
if only_unindexed:
packages = [pkg for pkg in packages if not pkg.indexed]
if (last_updated_package_name := index.load_last_updated_package()) is not None:
package_names = [pkg.pypi for pkg in packages]
try:
Expand Down
Loading