Skip to content

fix: Match file stems with leading or trailing underscores in the NL stem boost #304

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

Closed
flyinprogrammer wants to merge 1 commit into from
Closed

fix: Match file stems with leading or trailing underscores in the NL stem boost #304

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 src/semble/ranking/boosting.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -267,6 +267,11 @@ def stem_ok(stem: str) -> bool:
_boost_definitions(boosted, names, boost_unit, all_chunks, stem_ok)


def _split_path_part(name: str) -> list[str]:
"""Split a file stem or directory name, ignoring leading/trailing underscores (``__git`` -> ``git``)."""
return split_identifier(name.strip("_") or name)


def _count_keyword_matches(keywords: set[str], parts: set[str]) -> int:
"""Count query keywords that match path parts, allowing prefix overlap (min 3 chars)."""
exact = keywords & parts
Expand Down Expand Up @@ -303,9 +308,9 @@ def _boost_stem_matches(
for chunk in list(boosted):
if chunk.file_path not in path_cache:
path = Path(chunk.file_path)
parts: set[str] = set(split_identifier(path.stem))
parts: set[str] = set(_split_path_part(path.stem))
if path.parent.name and path.parent.name not in (".", "/", ".."):
parts.update(split_identifier(path.parent.name))
parts.update(_split_path_part(path.parent.name))
path_cache[chunk.file_path] = parts
n_matches = _count_keyword_matches(keywords, path_cache[chunk.file_path])
if n_matches > 0:
Expand Down
2 changes: 2 additions & 0 deletions tests/test_ranking.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,6 +109,8 @@ def test_apply_query_boost_skips_non_matching_stem(query: str) -> None:
[
("authenticate user session", "src/auth.py"), # prefix / morphological match
("auth service", "src/auth_service.py"), # every keyword exact-matches a stem part
("git status", "lua/telescope/__git.lua"), # leading underscores don't hide the stem
("git status", "lua/telescope/git__.lua"), # nor do trailing ones
],
)
def test_apply_query_boost_nl_stem_match_boosts(query: str, file_path: str) -> None:
Expand Down