fix(stats): preserve whitespace in filenames

Commit.stats strips leading and trailing whitespace from filenames after
splitting the diff output into records. This merges distinct paths such
as `name`, ` name`, and `name `, overwrites their per-file statistics, and
turns an all-space filename into an empty key.

Keep the filename field intact. Add an integration regression covering
root commits, later modifications, empty commits, and deletions. Store
blobs directly to avoid relying on trailing-space worktree filenames.

The regression fails before this change and passes afterward. On Linux
with Python 3.12, the full suite passes: 1690 passed, 89 skipped, 1 xfailed,
and 64 subtests passed. Pre-commit, mypy, and basedpyright also pass.

Prepared by OpenAI Codex (dot); human review is pending.

Author: v1shay

git/util.py

@@ -1107,7 +1107,7 @@ def _list_from_string(cls, repo: "Repo", text: str) -> "Stats":
                 "lines": insertions + deletions,
                 "change_type": change_type,
             }
-            hsh["files"][filename.strip()] = files_dict
+            hsh["files"][filename] = files_dict
         return Stats(hsh["total"], hsh["files"])
 
 

test/test_commit.py

@@ -17,6 +17,7 @@
 
 from git import Actor, Commit, Repo
 from git.exc import UnsafeOptionError
+from git.index.typ import BaseIndexEntry
 from git.objects.util import tzoffset, utc
 from git.repo.fun import touch
 
@@ -166,6 +167,36 @@ def check_entries(d, has_change_type=False):
         self.assertEqual(commit.committer_tz_offset, 14400, commit.committer_tz_offset)
         self.assertEqual(commit.message, "initial project\n")
 
+    @with_rw_directory
+    def test_stats_preserve_filename_spaces(self, rw_dir):
+        repo = Repo.init(rw_dir)
+        actor = Actor("Test", "test@example.com")
+        paths = ("name", " name", "name ", " name ", " ")
+        # Store blobs directly so trailing spaces work on Windows as well.
+        for multiplier, change_type in ((1, "A"), (2, "M")):
+            for count, path in enumerate(paths, 1):
+                data = b"line\n" * count * multiplier
+                blob = repo.odb.store(IStream("blob", len(data), BytesIO(data)))
+                repo.index.add([BaseIndexEntry((0o100644, blob.binsha, 0, path))])
+            commit = repo.index.commit("Update files", author=actor, committer=actor)
+            stats = commit.stats
+            assert stats.total == {"insertions": 15, "deletions": 0, "lines": 15, "files": 5}
+            assert stats.files == {
+                path: {"insertions": count, "deletions": 0, "lines": count, "change_type": change_type}
+                for count, path in enumerate(paths, 1)
+            }
+        empty_stats = repo.index.commit("No changes", author=actor, committer=actor).stats
+        assert empty_stats.files == {}
+        assert empty_stats.total == {"insertions": 0, "deletions": 0, "lines": 0, "files": 0}
+
+        repo.index.remove(list(paths))
+        removed_stats = repo.index.commit("Remove files", author=actor, committer=actor).stats
+        assert removed_stats.files == {
+            path: {"insertions": 0, "deletions": 2 * count, "lines": 2 * count, "change_type": "D"}
+            for count, path in enumerate(paths, 1)
+        }
+        assert removed_stats.total == {"insertions": 0, "deletions": 30, "lines": 30, "files": 5}
+
     def test_renames(self):
         commit = self.rorepo.commit("185d847ec7647fd2642a82d9205fb3d07ea71715")
         files = commit.stats.files