Objects: Constructor now manually checks and sets the input arguments…

… to the local cache - previously a procedural approach was used, which was less code, but slower too. Especially in case of CommitObjects unrolling the loop manually makes a difference.

Submodule: Implemented query methods and did a bit of testing. More is to come, but the test works for now. As special addition, the submodule implementation uses the section name as submodule ID even though it seems to be just the path. This allows to make renames easier

lib/git/objects/base.py

@@ -62,17 +62,6 @@ def new_from_sha(cls, repo, sha1):
 		inst.size = oinfo.size
 		return inst 
 
-	def _set_self_from_args_(self, args_dict):
-		"""Initialize attributes on self from the given dict that was retrieved
-		from locals() in the calling method.
-		
-		Will only set an attribute on self if the corresponding value in args_dict
-		is not None"""
-		for attr, val in args_dict.items():
-			if attr != "self" and val is not None:
-				setattr( self, attr, val )
-		# END set all non-None attributes
-
 	def _set_cache_(self, attr):
 		"""Retrieve object information"""
 		if attr	 == "size":
@@ -140,7 +129,10 @@ def __init__(self, repo, binsha, mode=None, path=None):
 			Path may not be set of the index object has been created directly as it cannot
 			be retrieved without knowing the parent tree."""
 		super(IndexObject, self).__init__(repo, binsha)
-		self._set_self_from_args_(locals())
+		if mode is not None:
+			self.mode = mode
+		if path is not None:
+			self.path = path
 
 	def __hash__(self):
 		""":return:

lib/git/objects/commit.py

@@ -108,7 +108,26 @@ def __init__(self, repo, binsha, tree=None, author=None, authored_date=None, aut
 		super(Commit,self).__init__(repo, binsha)
 		if tree is not None:
 			assert isinstance(tree, Tree), "Tree needs to be a Tree instance, was %s" % type(tree)
-		self._set_self_from_args_(locals())
+		if tree is not None:
+			self.tree = tree
+		if author is not None:
+			self.author = author
+		if authored_date is not None:
+			self.authored_date = authored_date
+		if author_tz_offset is not None:
+			self.author_tz_offset = author_tz_offset
+		if committer is not None:
+			self.committer = committer
+		if committed_date is not None:
+			self.committed_date = committed_date
+		if committer_tz_offset is not None:
+			self.committer_tz_offset = committer_tz_offset
+		if message is not None:
+			self.message = message
+		if parents is not None:
+			self.parents = parents
+		if encoding is not None:
+			self.encoding = encoding
 
 	@classmethod
 	def _get_intermediate_items(cls, commit):
@@ -434,7 +453,7 @@ def _deserialize(self, stream):
 		try:
 			self.author.name = self.author.name.decode(self.encoding) 
 		except UnicodeDecodeError:
-			print >> sys.stderr, "Failed to decode author name: %s" % self.author.name
+			print >> sys.stderr, "Failed to decode author name '%s' using encoding %s" % (self.author.name, self.encoding)
 		# END handle author's encoding
 
 		# a stream from our data simply gives us the plain message
@@ -443,7 +462,7 @@ def _deserialize(self, stream):
 		try:
 			self.message = self.message.decode(self.encoding)
 		except UnicodeDecodeError:
-			print >> sys.stderr, "Failed to decode message: %s" % self.message
+			print >> sys.stderr, "Failed to decode message '%s' using encoding %s" % (self.message, self.encoding)
 		# END exception handling 
 		return self