Merge remote-tracking branch 'upstream/master' into pr-cmd-raise-with-stderr-on-error

barry-scott · barry-scott · commit 35658887753d · 2016-06-06T09:27:20.000+01:00
diff --git a/README.md b/README.md
@@ -6,11 +6,13 @@ It provides abstractions of git objects for easy access of repository data, and
 
 The object database implementation is optimized for handling large quantities of objects and large datasets, which is achieved by using low-level structures and data streaming.
 
+
 ### REQUIREMENTS
 
 GitPython needs the `git` executable to be installed on the system and available in your `PATH` for most operations. If it is not in your `PATH`, you can help GitPython find it by setting the `GIT_PYTHON_GIT_EXECUTABLE=<path/to/git>` environment variable.
 
 * Git (1.7.x or newer)
+* Python 2.7 to 3.5, while python 2.6 is supported on a *best-effort basis*.
 
 The list of dependencies are listed in `./requirements.txt` and `./test-requirements.txt`. The installer takes care of installing them for you.
 
diff --git a/VERSION b/VERSION
@@ -1 +1 @@
-2.0.3
+2.0.6dev0
diff --git a/doc/source/changes.rst b/doc/source/changes.rst
@@ -2,9 +2,25 @@
 Changelog
 =========
 
+2.0.6 - Fixes
+=============
+
+* Fix: TypeError about passing keyword argument to string decode() on
+  Python 2.6.
+
+2.0.5 - Fixes
+=============
+
+* Fix: parser of fetch info lines choked on some legitimate lines
+
 2.0.4 - Fixes
 =============
 
+* Fix: parser of commit object data is now robust against cases where
+  commit object contains invalid bytes.  The invalid characters are now
+  replaced rather than choked on.
+* 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/cmd.py b/git/cmd.py
@@ -287,7 +287,7 @@ def __del__(self):
                 return
 
             # can be that nothing really exists anymore ...
-            if os is None:
+            if os is None or os.kill is None:
                 return
 
             # try to kill it
diff --git a/git/diff.py b/git/diff.py
@@ -15,12 +15,23 @@
     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 @@ def renamed(self):
         :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/objects/commit.py b/git/objects/commit.py
@@ -501,14 +501,14 @@ def _deserialize(self, stream):
 
         try:
             self.author, self.authored_date, self.author_tz_offset = \
-                parse_actor_and_date(author_line.decode(self.encoding))
+                parse_actor_and_date(author_line.decode(self.encoding, 'replace'))
         except UnicodeDecodeError:
             log.error("Failed to decode author line '%s' using encoding %s", author_line, self.encoding,
                       exc_info=True)
 
         try:
             self.committer, self.committed_date, self.committer_tz_offset = \
-                parse_actor_and_date(committer_line.decode(self.encoding))
+                parse_actor_and_date(committer_line.decode(self.encoding, 'replace'))
         except UnicodeDecodeError:
             log.error("Failed to decode committer line '%s' using encoding %s", committer_line, self.encoding,
                       exc_info=True)
@@ -518,7 +518,7 @@ def _deserialize(self, stream):
         # The end of our message stream is marked with a newline that we strip
         self.message = stream.read()
         try:
-            self.message = self.message.decode(self.encoding)
+            self.message = self.message.decode(self.encoding, 'replace')
         except UnicodeDecodeError:
             log.error("Failed to decode message '%s' using encoding %s", self.message, self.encoding, exc_info=True)
         # END exception handling
diff --git a/git/remote.py b/git/remote.py
@@ -204,7 +204,7 @@ class FetchInfo(object):
     NEW_TAG, NEW_HEAD, HEAD_UPTODATE, TAG_UPDATE, REJECTED, FORCED_UPDATE, \
         FAST_FORWARD, ERROR = [1 << x for x in range(8)]
 
-    re_fetch_result = re.compile("^\s*(.) (\[?[\w\s\.$@]+\]?)\s+(.+) -> ([/\w_\+\.\-$@#]+)(    \(.*\)?$)?")
+    re_fetch_result = re.compile("^\s*(.) (\[?[\w\s\.$@]+\]?)\s+(.+) -> ([/\w_\+\.\-$@#()]+)(    \(.*\)?$)?")
 
     _flag_map = {'!': ERROR,
                  '+': FORCED_UPDATE,
diff --git a/git/test/fixtures/commit_invalid_data b/git/test/fixtures/commit_invalid_data
@@ -0,0 +1,6 @@
+tree 9f1a495d7d9692d24f5caedaa89f5c2c32d59368
+parent 492ace2ffce0e426ebeb55e364e987bcf024dd3b
+author E.Azer Ko�o�o�oculu <azer@kodfabrik.com> 1306710073 +0300
+committer E.Azer Ko�o�o�oculu <azer@kodfabrik.com> 1306710073 +0300
+
+add environjs
diff --git 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_commit.py b/git/test/test_commit.py
@@ -306,6 +306,13 @@ def test_serialization_unicode_support(self):
         # it appears
         cmt.author.__repr__()
 
+    def test_invalid_commit(self):
+        cmt = self.rorepo.commit()
+        cmt._deserialize(open(fixture_path('commit_invalid_data'), 'rb'))
+
+        assert cmt.author.name == u'E.Azer Ko�o�o�oculu', cmt.author.name
+        assert cmt.author.email == 'azer@kodfabrik.com', cmt.author.email
+
     def test_gpgsig(self):
         cmt = self.rorepo.commit()
         cmt._deserialize(open(fixture_path('commit_with_gpgsig'), 'rb'))
diff --git a/git/test/test_diff.py b/git/test/test_diff.py
@@ -161,16 +161,17 @@ def test_diff_unsafe_paths(self):
         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
@@ -11,7 +11,6 @@
 
 
 class Tutorials(TestBase):
-
     @with_rw_directory
     def test_init_repo_object(self, rw_dir):
         # [1-test_init_repo_object]
@@ -165,7 +164,7 @@ def update(self, op_code, cur_count, max_count=None, message=''):
         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 +394,7 @@ def test_references_and_objects(self, rw_dir):
         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 +445,7 @@ def test_submodules(self):
         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 +457,7 @@ def test_submodules(self):
         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
diff --git a/setup.py b/setup.py
@@ -110,6 +110,7 @@ def _stamp_version(filename):
         "Operating System :: MacOS :: MacOS X",
         "Programming Language :: Python",
         "Programming Language :: Python :: 2",
+        "Programming Language :: Python :: 2.6",
         "Programming Language :: Python :: 2.7",
         "Programming Language :: Python :: 3",
         "Programming Language :: Python :: 3.3",
