Skip to content

perf: skip impossible lexical field matches #8439

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
huangruiteng merged 1 commit into from
Nov 10, 2026
Merged

perf: skip impossible lexical field matches #8439

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
6 changes: 5 additions & 1 deletion loopx/semantics/field_use.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -263,7 +263,11 @@ def _token_pattern(field: str) -> re.Pattern[str]:
def lexical_module_count(field: str, suffix: str, sources: Iterable[SourceFile]) -> int:
"""The pre-B3 metric: modules whose text contains the standalone token."""
token = _token_pattern(field)
return sum(1 for source in sources if source.suffix == suffix and token.search(source.text))
# Literal containment is a prerequisite of the same boundary regex.
return sum(
1 for source in sources
if source.suffix == suffix and field in source.text and token.search(source.text)
)


def scan_field_uses(
Expand Down
15 changes: 15 additions & 0 deletions tests/architecture/test_semantic_field_use.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@
FACTS,
ROLES,
field_use_summary,
lexical_module_count,
python_module_scan,
scan_field_uses,
)
Expand All @@ -25,6 +26,20 @@
FIELDS = frozenset({FIELD})


@pytest.mark.parametrize("suffix, expected", [(".py", 3), (".ts", 1)])
def test_lexical_modules_preserve_boundaries_and_raw_source_text(suffix: str, expected: int) -> None:
sources = [
SourceFile("comment.py", ".py", "# goal_boundary goal_boundary"),
SourceFile("prefix.py", ".py", "goal_boundary_repair repair_goal_boundary"),
SourceFile("unicode.py", ".py", "汉goal_boundary字"),
SourceFile("escaped.py", ".py", r'"goal_\u0062oundary"'),
SourceFile("broken.py", ".py", "def broken(:\n# goal_boundary"),
SourceFile("other.ts", ".ts", "// goal_boundary"),
SourceFile("absent.py", ".py", "payload.get(dynamic_key)"),
]
assert lexical_module_count(FIELD, suffix, iter(sources)) == expected


def python(text: str) -> dict[str, set[str]]:
return python_module_scan(ast.parse(text), FIELDS)[0]

Expand Down
Loading