added Object.data_stream property allowing to stream object data directly.Considering the implementation of the git commnd which temporarily keeps it in a cache, it doesnt make a huge diffence as the data is kept in memory while streaming. Only good thing is that it is in a different process so python will never see it if done properly

2 files changed, 30 insertions, 0 deletions

diff --git a/lib/git/objects/base.py b/lib/git/objects/base.py
index ab1da7b0..dd67a3c7 100644
--- a/lib/git/objects/base.py
+++ b/lib/git/objects/base.py
@@ -16,6 +16,9 @@ class Object(LazyMixin):
 	This Object also serves as a constructor for instances of the correct type::
 	
 		inst = Object.new(repo,id)
+		inst.id		# objects sha in hex
+		inst.size	# objects uncompressed data size
+		inst.data	# byte string containing the whole data of the object
 	"""
 	TYPES = ("blob", "tree", "commit", "tag")
 	__slots__ = ("repo", "id", "size", "data" )
@@ -115,6 +118,15 @@ class Object(LazyMixin):
 		"""
 		return '<git.%s "%s">' % (self.__class__.__name__, self.id)
 
+	@property
+	def data_stream(self):
+		"""
+		Returns 
+			File Object compatible stream to the uncompressed raw data of the object
+		"""
+		proc = self.repo.git.cat_file(self.type, self.id, as_process=True)
+		return utils.ProcessStreamAdapter(proc, "stdout") 
+
 
 class IndexObject(Object):
 	"""
diff --git a/lib/git/objects/utils.py b/lib/git/objects/utils.py
index 367ed2b7..7bb4e8e2 100644
--- a/lib/git/objects/utils.py
+++ b/lib/git/objects/utils.py
@@ -52,3 +52,21 @@ def parse_actor_and_date(line):
 	m = _re_actor_epoch.search(line)
 	actor, epoch = m.groups()
 	return (Actor._from_string(actor), int(epoch))
+	
+	
+	
+class ProcessStreamAdapter(object):
+	"""
+	Class wireing all calls to the contained Process instance.
+	
+	Use this type to hide the underlying process to provide access only to a specified 
+	stream. The process is usually wrapped into an AutoInterrupt class to kill 
+	it if the instance goes out of scope.
+	"""
+	__slots__ = ("_proc", "_stream")
+	def __init__(self, process, stream_name):
+		self._proc = process
+		self._stream = getattr(process, stream_name)
+	
+	def __getattr__(self, attr):
+		return getattr(self._stream, attr)