Return bytes if object name can't be utf8-decoded

Signed-off-by: Tim Van Steenburgh <tvansteenburgh@gmail.com>

Author: tvansteenburgh

git/objects/fun.py

@@ -70,9 +70,13 @@ def tree_entries_from_data(data):
 		# default encoding for strings in git is utf8
 		# Only use the respective unicode object if the byte stream was encoded
 		name = data[ns:i]
-		name_enc = name.decode("utf-8")
-		if len(name) > len(name_enc):
-			name = name_enc
+                try:
+                        name_enc = name.decode("utf-8")
+                except UnicodeDecodeError:
+                        pass
+                else:
+                        if len(name) > len(name_enc):
+                                name = name_enc
 		# END handle encoding
 
 		# byte is NULL, get next 20

git/test/test_fun.py

@@ -249,3 +249,8 @@ def test_tree_traversal_single(self):
 			entries = traverse_tree_recursive(odb, commit.tree.binsha, '')
 			assert entries
 		# END for each commit
+
+def test_tree_entries_from_data():
+    from git.objects.fun import tree_entries_from_data
+    r = tree_entries_from_data(b'100644 \x9f\0aaa')
+    assert r == [('aaa', 33188, '\x9f')], r