Merge branch 'iteration_and_retrieval' into improvements

* iteration_and_retrieval:
  test_performance: module containing benchmarks to get an idea of the achieved throughput
  Removed plenty of mocked tree tests as they cannot work anymore with persistent commands that require stdin AND binary data - not even an adapter would help here. These tests will have to be replaced.
  tree: now reads tress directly by parsing the binary data, allowing it to safe possibly hundreds of command calls
  Refs are now truly dynamic - this costs a little bit of (persistent command) work, but assures refs behave as expected
  persistent command signature changed to also return the hexsha from a possible input ref - the objects pointed to by refs are now baked on demand - perhaps it should change to always be re-retrieved using a property as it is relatively fast - this way refs can always be cached
  test_blob: removed many redundant tests that would fail now as the mock cannot handle the complexity of the command backend
  Implemented git command facility to keep persistent commands for fast object information retrieval
  test: Added time-consuming test which could also be a benchmark in fact - currently it cause hundreds of command invocations which is slow
  cmd: added option to return the process directly, allowing to read the output directly from the output stream
  added Iterable interface to Ref type
  renamed find_all to list_all, changed commit to use iterable interface in preparation for command changes
  Added base for all iteratable objects
  unified name of utils module, recently it was named util and utils in different packages
  tree: renamed content_from_string to _from_string to make it private. Removed tests that were testing that method
  tree: now behaves like a list with string indexing functionality - using a dict as cache is a problem as the tree is ordered, added blobs, trees and traverse method
  test_base: Improved basic object creation as well as set hash tests
  repo.active_branch now returns a Head object, not a string
  IndexObjects are now checking their slots to raise a proper error message in case someone tries to access an unset path or mode - this information cannot be retrieved afterwards as IndexObject information is kept in the object that pointed at them. To find this information, one would have to search all objects which is not feasible
  refs now take repo as first argument and derive from LazyMixin to allow them to dynamically retrieve their objects

1 files changed, 16 insertions, 27 deletions

diff --git a/lib/git/objects/base.py b/lib/git/objects/base.py
index 43aa8dd1..07538ada 100644
--- a/lib/git/objects/base.py
+++ b/lib/git/objects/base.py
@@ -4,32 +4,10 @@
 # This module is part of GitPython and is released under
 # the BSD License: http://www.opensource.org/licenses/bsd-license.php
 import os
-
-class LazyMixin(object):
-	lazy_properties = []
-	__slots__ = tuple()
+from git.utils import LazyMixin
 	
-	def __getattr__(self, attr):
-		"""
-		Whenever an attribute is requested that we do not know, we allow it 
-		to be created and set. Next time the same attribute is reqeusted, it is simply
-		returned from our dict/slots.
-		"""
-		self._set_cache_(attr)
-		# will raise in case the cache was not created
-		return object.__getattribute__(self, attr)
+_assertion_msg_format = "Created object %r whose python type %r disagrees with the acutal git object type %r"
 
-	def _set_cache_(self, attr):
-		""" This method should be overridden in the derived class. 
-		It should check whether the attribute named by attr can be created
-		and cached. Do nothing if you do not know the attribute or call your subclass
-		
-		The derived class may create as many additional attributes as it deems 
-		necessary in case a git command returns more information than represented 
-		in the single attribute."""
-		pass
-	
-		
 class Object(LazyMixin):
 	"""
 	Implements an Object which may be Blobs, Trees, Commits and Tags
@@ -71,9 +49,13 @@ class Object(LazyMixin):
 		Retrieve object information
 		"""
 		if attr  == "size":
-			self.size = int(self.repo.git.cat_file(self.id, s=True).rstrip())
+			hexsha, typename, self.size = self.repo.git.get_object_header(self.id)
+			assert typename == self.type, _assertion_msg_format % (self.id, typename, self.type)
 		elif attr == "data":
-			self.data = self.repo.git.cat_file(self.id, p=True, with_raw_output=True)
+			hexsha, typename, self.size, self.data = self.repo.git.get_object_data(self.id)
+			assert typename == self.type, _assertion_msg_format % (self.id, typename, self.type)
+		else:
+			super(Object,self)._set_cache_(attr)
 		
 	def __eq__(self, other):
 		"""
@@ -143,8 +125,15 @@ class IndexObject(Object):
 		if isinstance(mode, basestring):
 			self.mode = self._mode_str_to_int(mode)
 	
+	def _set_cache_(self, attr):
+		if attr in IndexObject.__slots__:
+			# they cannot be retrieved lateron ( not without searching for them )
+			raise AttributeError( "path and mode attributes must have been set during %s object creation" % type(self).__name__ )
+		else:
+			super(IndexObject, self)._set_cache_(attr)
+	
 	@classmethod
-	def _mode_str_to_int( cls, modestr ):
+	def _mode_str_to_int(cls, modestr):
 		"""
 		``modestr``
 			string like 755 or 644 or 100644 - only the last 3 chars will be used