diff options
-rw-r--r-- | doc/source/changes.rst | 2 | ||||
-rw-r--r-- | git/diff.py | 17 | ||||
-rw-r--r-- | git/test/fixtures/diff_patch_unsafe_paths | 7 | ||||
-rw-r--r-- | git/test/test_diff.py | 13 | ||||
-rw-r--r-- | git/test/test_docs.py | 11 |
5 files changed, 37 insertions, 13 deletions
diff --git a/doc/source/changes.rst b/doc/source/changes.rst index 928675d0..dd7a3815 100644 --- a/doc/source/changes.rst +++ b/doc/source/changes.rst @@ -5,6 +5,8 @@ Changelog 2.0.4 - Fixes ============= +* Fix: non-ASCII paths are now properly decoded and returned in + ``.diff()`` output * Fix: `RemoteProgress` will now strip the ', ' prefix or suffix from messages. * API: Remote.[fetch|push|pull](...) methods now allow the ``progress`` argument to be a callable. This saves you from creating a custom type with usually just one diff --git a/git/diff.py b/git/diff.py index 44a65017..9073767e 100644 --- a/git/diff.py +++ b/git/diff.py @@ -15,12 +15,23 @@ from git.compat import ( PY3 ) - __all__ = ('Diffable', 'DiffIndex', 'Diff', 'NULL_TREE') # Special object to compare against the empty tree in diffs NULL_TREE = object() +_octal_byte_re = re.compile(b'\\\\([0-9]{3})') + + +def _octal_repl(matchobj): + value = matchobj.group(1) + value = int(value, 8) + if PY3: + value = bytes(bytearray((value,))) + else: + value = chr(value) + return value + def decode_path(path, has_ab_prefix=True): if path == b'/dev/null': @@ -32,6 +43,8 @@ def decode_path(path, has_ab_prefix=True): .replace(b'\\"', b'"') .replace(b'\\\\', b'\\')) + path = _octal_byte_re.sub(_octal_repl, path) + if has_ab_prefix: assert path.startswith(b'a/') or path.startswith(b'b/') path = path[2:] @@ -337,7 +350,7 @@ class Diff(object): :note: This property is deprecated, please use ``renamed_file`` instead. """ return self.renamed_file - + @property def renamed_file(self): """:returns: True if the blob of our diff has been renamed diff --git a/git/test/fixtures/diff_patch_unsafe_paths b/git/test/fixtures/diff_patch_unsafe_paths index 14375f79..9ee6b834 100644 --- a/git/test/fixtures/diff_patch_unsafe_paths +++ b/git/test/fixtures/diff_patch_unsafe_paths @@ -61,6 +61,13 @@ index 0000000000000000000000000000000000000000..eaf5f7510320b6a327fb308379de2f94 +++ "b/path/¯\\_(ツ)_|¯" @@ -0,0 +1 @@ +dummy content +diff --git "a/path/\360\237\222\251.txt" "b/path/\360\237\222\251.txt" +new file mode 100644 +index 0000000000000000000000000000000000000000..eaf5f7510320b6a327fb308379de2f94d8859a54 +--- /dev/null ++++ "b/path/\360\237\222\251.txt" +@@ -0,0 +1 @@ ++dummy content diff --git a/a/with spaces b/b/with some spaces similarity index 100% rename from a/with spaces diff --git a/git/test/test_diff.py b/git/test/test_diff.py index 1d7a4fda..8966351a 100644 --- a/git/test/test_diff.py +++ b/git/test/test_diff.py @@ -161,16 +161,17 @@ class TestDiff(TestBase): self.assertEqual(res[6].b_path, u'path/with spaces') self.assertEqual(res[7].b_path, u'path/with-question-mark?') self.assertEqual(res[8].b_path, u'path/¯\\_(ツ)_|¯') + self.assertEqual(res[9].b_path, u'path/💩.txt') # The "Moves" # NOTE: The path prefixes a/ and b/ here are legit! We're actually # verifying that it's not "a/a/" that shows up, see the fixture data. - self.assertEqual(res[9].a_path, u'a/with spaces') # NOTE: path a/ here legit! - self.assertEqual(res[9].b_path, u'b/with some spaces') # NOTE: path b/ here legit! - self.assertEqual(res[10].a_path, u'a/ending in a space ') - self.assertEqual(res[10].b_path, u'b/ending with space ') - self.assertEqual(res[11].a_path, u'a/"with-quotes"') - self.assertEqual(res[11].b_path, u'b/"with even more quotes"') + self.assertEqual(res[10].a_path, u'a/with spaces') # NOTE: path a/ here legit! + self.assertEqual(res[10].b_path, u'b/with some spaces') # NOTE: path b/ here legit! + self.assertEqual(res[11].a_path, u'a/ending in a space ') + self.assertEqual(res[11].b_path, u'b/ending with space ') + self.assertEqual(res[12].a_path, u'a/"with-quotes"') + self.assertEqual(res[12].b_path, u'b/"with even more quotes"') def test_diff_patch_format(self): # test all of the 'old' format diffs for completness - it should at least diff --git a/git/test/test_docs.py b/git/test/test_docs.py index 7b3b7474..27470748 100644 --- a/git/test/test_docs.py +++ b/git/test/test_docs.py @@ -7,11 +7,12 @@ import os from git.test.lib import TestBase -from gitdb.test.lib import with_rw_directory +from gitdb.test.lib import skip_on_travis_ci, with_rw_directory class Tutorials(TestBase): + @skip_on_travis_ci @with_rw_directory def test_init_repo_object(self, rw_dir): # [1-test_init_repo_object] @@ -165,7 +166,7 @@ class Tutorials(TestBase): for sm in cloned_repo.submodules: assert not sm.remove().exists() # after removal, the sm doesn't exist anymore sm = cloned_repo.create_submodule('mysubrepo', 'path/to/subrepo', url=bare_repo.git_dir, branch='master') - + # .gitmodules was written and added to the index, which is now being committed cloned_repo.index.commit("Added submodule") assert sm.exists() and sm.module_exists() # this submodule is defintely available @@ -395,7 +396,7 @@ class Tutorials(TestBase): hcommit.diff() # diff tree against index hcommit.diff('HEAD~1') # diff tree against previous tree hcommit.diff(None) # diff tree against working tree - + index = repo.index index.diff() # diff index against itself yielding empty diff index.diff(None) # diff index against working copy @@ -446,7 +447,7 @@ class Tutorials(TestBase): sm = sms[0] assert sm.name == 'gitdb' # git-python has gitdb as single submodule ... assert sm.children()[0].name == 'smmap' # ... which has smmap as single submodule - + # The module is the repository referenced by the submodule assert sm.module_exists() # the module is available, which doesn't have to be the case. assert sm.module().working_tree_dir.endswith('gitdb') @@ -458,7 +459,7 @@ class Tutorials(TestBase): assert sm.config_reader().get_value('path') == sm.path assert len(sm.children()) == 1 # query the submodule hierarchy # ![1-test_submodules] - + @with_rw_directory def test_add_file_and_commit(self, rw_dir): import git |