Skip to content

feat(extract): add regex-based R (.r/.R) extractor (#1689) #1759

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

Open
Sanjays2402 wants to merge 1 commit into
base: v8
Choose a base branch
from
+498 −11
Open

feat(extract): add regex-based R (.r/.R) extractor (#1689) #1759

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
9 changes: 7 additions & 2 deletions graphify/extract.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,6 +45,7 @@
from graphify.extractors.markdown import extract_markdown # noqa: F401
from graphify.extractors.pascal_forms import extract_delphi_form, extract_lazarus_form # noqa: F401
from graphify.extractors.powershell import extract_powershell, extract_powershell_manifest # noqa: F401
from graphify.extractors.r import extract_r # noqa: F401
from graphify.extractors.razor import extract_razor # noqa: F401
from graphify.extractors.rust import extract_rust # noqa: F401
from graphify.extractors.sln import extract_sln # noqa: F401
Expand Down Expand Up @@ -1786,6 +1787,7 @@ def _lang_is_case_insensitive(source_file: object) -> bool:
".zig": "zig",
".ex": "elixir", ".exs": "elixir",
".jl": "julia",
".r": "r",
".dart": "dart",
".sh": "shell", ".bash": "shell",
".ps1": "powershell", ".psm1": "powershell", ".psd1": "powershell",
Expand Down Expand Up @@ -3780,6 +3782,8 @@ def add_existing_edge(edge: dict) -> None:
".m": extract_objc,
".mm": extract_objc,
".jl": extract_julia,
".r": extract_r,
".R": extract_r,
".f": extract_fortran,
".F": extract_fortran,
".f90": extract_fortran,
Expand Down Expand Up @@ -3853,7 +3857,7 @@ def add_existing_edge(edge: dict) -> None:
# routes them to the CODE path via _shebang_interpreter; _get_extractor must
# honor the same signal or these files are classified as code and then silently
# dropped by extraction. Only interpreters with a real extractor are mapped —
# detect's wider set (perl, fish, tcsh, Rscript) stays unmapped and skipped.
# detect's wider set (perl, fish, tcsh) stays unmapped and skipped.
_SHEBANG_DISPATCH: dict[str, Any] = {
"python": extract_python,
"python2": extract_python,
Expand All @@ -3869,6 +3873,7 @@ def add_existing_edge(edge: dict) -> None:
"lua": extract_lua,
"php": extract_php,
"julia": extract_julia,
"Rscript": extract_r,
}


Expand Down Expand Up @@ -4285,7 +4290,7 @@ def extract(
)

# #1689: a file counted as code (extension in CODE_EXTENSIONS) but with no AST
# extractor wired up (e.g. .r/.R — there is no tree-sitter-r dispatch) silently
# extractor wired up (e.g. .ejs/.ets — there is no dispatch entry) silently
# contributes zero nodes. The #1666 warning above deliberately skips these (it
# only fires when an extractor exists), so surface them explicitly, grouped by
# extension, rather than reporting success as if the language were mapped.
Expand Down
Loading