Merge pull request #349 from oraios/improve_search_for_nonignored_files

Improved performance of find_all_non_ignored_files

CHANGELOG.md

@@ -2,6 +2,9 @@
 
 Status of the `main` branch. Changes prior to the next official version change will appear here.
 
+Fixes:
+* Ignore `.git` in check for ignored paths and improve performance of `find_all_non_ignored_files`
+
 # 0.1.3
 
 ## Summary

src/serena/util/file_system.py

@@ -3,6 +3,7 @@ import logging
 import os
 from collections.abc import Callable
 from dataclasses import dataclass, field
+from pathlib import Path
 from typing import NamedTuple
 
 import pathspec
@@ -76,8 +77,10 @@ def find_all_non_ignored_files(repo_root: str) -> list[str]:
     :return: A list of all non-ignored files in the repository
     """
     gitignore_parser = GitignoreParser(repo_root)
-    _, files = scan_directory(repo_root, recursive=True)
-    return [file for file in files if not gitignore_parser.should_ignore(file)]
+    _, files = scan_directory(
+        repo_root, recursive=True, is_ignored_dir=gitignore_parser.should_ignore, is_ignored_file=gitignore_parser.should_ignore
+    )
+    return files
 
 
 @dataclass
@@ -256,6 +259,11 @@ class GitignoreParser:
         else:
             rel_path = path
 
+        # Ignore paths inside .git
+        rel_path_first_path = Path(rel_path).parts[0]
+        if rel_path_first_path == ".git":
+            return True
+
         abs_path = os.path.join(self.repo_root, rel_path)
 
         # Normalize path separators

src/serena/util/inspection.py

@@ -19,7 +19,7 @@ def iter_subclasses(cls: type[T], recursive: bool = True) -> Generator[type[T],
             yield from iter_subclasses(subclass, recursive)
 
 
-def determine_programming_language_composition(repo_path: str, rel_path_to_gitignore: str = ".gitignore") -> dict[str, float]:
+def determine_programming_language_composition(repo_path: str) -> dict[str, float]:
     """
     Determine the programming language composition of a repository.