From c9b44d29d656e92bb08fa41bcc2c31b2a2a2607b Mon Sep 17 00:00:00 2001
From: Matteo Croce <teknoraver@meta.com>
Date: Wed, 11 Jan 2023 19:13:49 +0100
Subject: [PATCH] fix files list on file rename

GitPython parses the output of `git diff --numstat` to get the
files changed in a commit.
This breaks when a commit contains a file rename, because the output
of `git diff` is different than expected.
This is the output of a normal commit:

    $ git diff --numstat 8f41a390bf9a^ 8f41a390bf9a
    30      5       test/test_repo.py

And this a commit containing a rename:

    $ git diff --numstat 185d847ec764^ 185d847ec764
    3       1       .github/workflows/{test_pytest.yml => Future.yml}

This can be triggered by this code:

    for commit in repo.iter_commits():
        print(commit.hexsha)
            for file in commit.stats.files:
                print(file)

Which will print for the normal commit:

    8f41a390bf9a54db6f85032bc56b453307b95451
    'test/test_repo.py'

And when there is a rename:

    185d847ec7647fd2642a82d9205fb3d07ea71715
    '.github/workflows/{test_pytest.yml => Future.yml}'

Additionally, when a path member is removed, the file list become
a list of strings, breaking even more the caller. This is in the
Linux kernel tree:

    $ git diff --numstat db401875f438^ db401875f438
    1       1       tools/testing/selftests/drivers/net/mlxsw/{spectrum-2 => }/devlink_trap_tunnel_ipip6.sh

and GitPython parses it as:

    db401875f438168c5804b295b93a28c7730bb57a
    ('tools/testing/selftests/drivers/net/mlxsw/{spectrum-2 => '
    '}/devlink_trap_tunnel_ipip6.sh')

Fix this by pasing the --no-renames option to `git diff` which ignores
renames and print the same output as if the file was deleted from the
old path and created in the new one:

    $ git diff --numstat --no-renames 185d847ec764^ 185d847ec764
    57      0       .github/workflows/Future.yml
    0       55      .github/workflows/test_pytest.yml
---
 git/objects/commit.py |  4 ++--
 test/test_commit.py   | 31 +++++++++++++++++++++++++++++++
 2 files changed, 33 insertions(+), 2 deletions(-)

diff --git a/git/objects/commit.py b/git/objects/commit.py
index 82d2387b3..547e8fe82 100644
--- a/git/objects/commit.py
+++ b/git/objects/commit.py
@@ -324,14 +324,14 @@ def stats(self) -> Stats:
 
         :return: git.Stats"""
         if not self.parents:
-            text = self.repo.git.diff_tree(self.hexsha, "--", numstat=True, root=True)
+            text = self.repo.git.diff_tree(self.hexsha, "--", numstat=True, no_renames=True, root=True)
             text2 = ""
             for line in text.splitlines()[1:]:
                 (insertions, deletions, filename) = line.split("\t")
                 text2 += "%s\t%s\t%s\n" % (insertions, deletions, filename)
             text = text2
         else:
-            text = self.repo.git.diff(self.parents[0].hexsha, self.hexsha, "--", numstat=True)
+            text = self.repo.git.diff(self.parents[0].hexsha, self.hexsha, "--", numstat=True, no_renames=True)
         return Stats._list_from_string(self.repo, text)
 
     @property
diff --git a/test/test_commit.py b/test/test_commit.py
index c5a43c94a..1efc68897 100644
--- a/test/test_commit.py
+++ b/test/test_commit.py
@@ -159,6 +159,37 @@ def check_entries(d):
         self.assertEqual(commit.committer_tz_offset, 14400, commit.committer_tz_offset)
         self.assertEqual(commit.message, "initial project\n")
 
+    def test_renames(self):
+        commit = self.rorepo.commit("185d847ec7647fd2642a82d9205fb3d07ea71715")
+        files = commit.stats.files
+
+        # when a file is renamed, the output of git diff is like "dir/{old => new}"
+        # unless we disable rename with --no-renames, which produces two lines
+        # one with the old path deletes and another with the new added
+        self.assertEqual(len(files), 2)
+
+        def check_entries(path, changes):
+            expected = {
+                ".github/workflows/Future.yml" : {
+                    'insertions': 57,
+                    'deletions': 0,
+                    'lines': 57
+                },
+                ".github/workflows/test_pytest.yml" : {
+                    'insertions': 0,
+                    'deletions': 55,
+                    'lines': 55
+                },
+            }
+            assert path in expected
+            assert isinstance(changes, dict)
+            for key in ("insertions", "deletions", "lines"):
+                assert changes[key] == expected[path][key]
+
+        for path, changes in files.items():
+            check_entries(path, changes)
+        # END for each stated file
+
     def test_unicode_actor(self):
         # assure we can parse unicode actors correctly
         name = "Üäöß ÄußÉ"