fix(stats): preserve Unicode line separators in filenames

git/objects/commit.py

@@ -405,6 +405,8 @@ def stats(self) -> Stats:
         def process_lines(lines: List[str]) -> str:
             text = ""
             for file_info, line in zip(lines, lines[len(lines) // 2 :]):
+                if not line:
+                    continue
                 change_type = file_info.split("\t")[0][-1]
                 (insertions, deletions, filename) = line.split("\t")
                 text += "%s\t%s\t%s\t%s\n" % (change_type, insertions, deletions, filename)
@@ -413,12 +415,12 @@ def process_lines(lines: List[str]) -> str:
         if not self.parents:
             lines = self.repo.git.diff_tree(
                 self.hexsha, "--", numstat=True, no_renames=True, root=True, raw=True
-            ).splitlines()[1:]
+            ).split("\n")[1:]
             text = process_lines(lines)
         else:
             lines = self.repo.git.diff(
                 self.parents[0].hexsha, self.hexsha, "--", numstat=True, no_renames=True, raw=True
-            ).splitlines()
+            ).split("\n")
             text = process_lines(lines)
         return Stats._list_from_string(self.repo, text)
 

git/util.py

@@ -1111,7 +1111,9 @@ def _list_from_string(cls, repo: "Repo", text: str) -> "Stats":
             "total": {"insertions": 0, "deletions": 0, "lines": 0, "files": 0},
             "files": {},
         }
-        for line in text.splitlines():
+        for line in text.split("\n"):
+            if not line:
+                continue
             (change_type, raw_insertions, raw_deletions, filename) = line.split("\t")
             insertions = raw_insertions != "-" and int(raw_insertions) or 0
             deletions = raw_deletions != "-" and int(raw_deletions) or 0

test/test_commit.py

@@ -200,6 +200,24 @@ def test_stats_preserve_filename_spaces(self, rw_dir):
         }
         assert removed_stats.total == {"insertions": 0, "deletions": 30, "lines": 30, "files": 5}
 
+    @with_rw_directory
+    def test_stats_preserve_unicode_line_separators(self, rw_dir):
+        with Repo.init(rw_dir) as repo:
+            repo.git.config("core.quotePath", "false")
+            actor = Actor("Test", "test@example.com")
+            paths = [f"before{separator}after.txt" for separator in ("\x85", "\u2028", "\u2029")]
+            for multiplier, change_type in ((1, "A"), (2, "M")):
+                for path in paths:
+                    data = b"line\n" * 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)
+                assert commit.stats.total == {"insertions": 3, "deletions": 0, "lines": 3, "files": 3}
+                assert commit.stats.files == {
+                    path: {"insertions": 1, "deletions": 0, "lines": 1, "change_type": change_type} for path in paths
+                }
+            assert repo.index.commit("No changes", author=actor, committer=actor).stats.files == {}
+
     def test_renames(self):
         commit = self.rorepo.commit("185d847ec7647fd2642a82d9205fb3d07ea71715")
         files = commit.stats.files