Merge branch 'sf-master' of https://github.com/johnsca/GitPython into johnsca-sf-master

Conflicts:
	git/cmd.py
	git/objects/commit.py
	git/objects/fun.py
	git/objects/util.py
	git/remote.py
	git/repo/base.py
	git/test/lib/helper.py
	git/test/test_commit.py
	git/test/test_fun.py
	git/util.py

3 files changed, 29 insertions, 8 deletions

diff --git a/git/objects/commit.py b/git/objects/commit.py
index 4380f472..bc437e8b 100644
--- a/git/objects/commit.py
+++ b/git/objects/commit.py
@@ -8,6 +8,7 @@ from git.util import        (
                             Actor,
                             Iterable,
                             Stats,
+                            finalize_process
                         )
 from git.diff import Diffable
 from tree import Tree
@@ -65,7 +66,6 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable):
                  message=None,  parents=None, encoding=None, gpgsig=None):
         """Instantiate a new Commit. All keyword arguments taking None as default will
         be implicitly set on first query.
-
         :param binsha: 20 byte sha1
         :param parents: tuple( Commit, ... ) 
             is a tuple of commit ids or actual Commits
@@ -252,6 +252,10 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable):
             assert len(hexsha) == 40, "Invalid line: %s" % hexsha
             yield Commit(repo, hex_to_bin(hexsha))
         # END for each line in stream
+        # TODO: Review this - it seems process handling got a bit out of control
+        # due to many developers trying to fix the open file handles issue
+        if hasattr(proc_or_stream, 'wait'):
+            finalize_process(proc_or_stream)
         
         
     @classmethod
@@ -430,14 +434,21 @@ class Commit(base.Object, Iterable, Diffable, Traversable, Serializable):
         
         self.author, self.authored_date, self.author_tz_offset = parse_actor_and_date(next_line)
         self.committer, self.committed_date, self.committer_tz_offset = parse_actor_and_date(readline())
-        
+
+        # we might run into one or more mergetag blocks, skip those for now
+        next_line = readline()
+        while next_line.startswith('mergetag '):
+            next_line = readline()
+            while next_line.startswith(' '):
+                next_line = readline()
         
         # now we can have the encoding line, or an empty line followed by the optional
         # message.
         self.encoding = self.default_encoding
 
         # read headers
-        buf = readline().strip()
+        enc = next_line
+        buf = enc.strip()
         while buf != "":
             if buf[0:10] == "encoding ":
                 self.encoding = buf[buf.find(' ')+1:]
diff --git a/git/objects/fun.py b/git/objects/fun.py
index f73be542..66b7998e 100644
--- a/git/objects/fun.py
+++ b/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
@@ -84,6 +88,7 @@ def tree_entries_from_data(data):
     return out
     
     
+
 def _find_by_name(tree_data, name, is_dir, start_at):
     """return data entry matching the given name and tree mode
     or None.
diff --git a/git/objects/util.py b/git/objects/util.py
index 2e44c9c0..cdf72bed 100644
--- a/git/objects/util.py
+++ b/git/objects/util.py
@@ -167,6 +167,7 @@ def parse_date(string_date):
     
 # precompiled regex
 _re_actor_epoch = re.compile(r'^.+? (.*) (\d+) ([+-]\d+).*$')
+_re_only_actor = re.compile(r'^.+? (.*)$')
 
 def parse_actor_and_date(line):
     """Parse out the actor (author or committer) info from a line like::
@@ -174,10 +175,14 @@ def parse_actor_and_date(line):
         author Tom Preston-Werner <tom@mojombo.com> 1191999972 -0700
     
     :return: [Actor, int_seconds_since_epoch, int_timezone_offset]"""
+    actor, epoch, offset = '', 0, 0
     m = _re_actor_epoch.search(line)
-    actor, epoch, offset = m.groups()
+    if m:
+        actor, epoch, offset = m.groups()
+    else:
+        m = _re_only_actor.search(line)
+        actor = m.group(1) if m else line or ''
     return (Actor._from_string(actor), int(epoch), utctz_to_altz(offset))
-    
 
 #} END functions