Initial frame for implementing read_tree using pure python. As git-read-tree can do much more than we can ( and faster assumably ), the .new method is used to create new index instances from up to 3 trees.

Implemented multi-tree traversal to facilitate building a stage list more efficiently ( although I am not sure whether it could be faster to use a dictionary together with some intensive lookup ), including test
Added performance to learn how fast certain operations are, and whether one should be preferred over another

1 files changed, 94 insertions, 0 deletions

diff --git a/test/git/performance/test_utils.py b/test/git/performance/test_utils.py
index 76adffec..16100f8b 100644
--- a/test/git/performance/test_utils.py
+++ b/test/git/performance/test_utils.py
@@ -57,3 +57,97 @@ class TestUtilPerformance(TestBigRepoR):
 			na = ni * 3
 			print >> sys.stderr, "Accessed %s[x] %i times in %s s ( %f acc / s)" % (cls.__name__, na, elapsed, na / elapsed)
 		# END for each sequence 
+		
+	def test_instantiation(self):
+		ni = 100000
+		max_num_items = 4
+		for mni in range(max_num_items+1):
+			for cls in (tuple, list):
+				st = time()
+				for i in xrange(ni):
+					if mni == 0:
+						cls()
+					elif mni == 1:
+						cls((1,))
+					elif mni == 2:
+						cls((1,2))
+					elif mni == 3:
+						cls((1,2,3))
+					elif mni == 4:
+						cls((1,2,3,4))
+					else:
+						cls(x for x in xrange(mni))
+					# END handle empty cls
+				# END for each item
+				elapsed = time() - st
+				print >> sys.stderr, "Created %i %ss of size %i in %f s ( %f inst / s)" % (ni, cls.__name__, mni, elapsed, ni / elapsed)
+			# END for each type
+		# END for each item count
+		
+		# tuple and tuple direct
+		st = time()
+		for i in xrange(ni):
+			t = (1,2,3,4)
+		# END for each item
+		elapsed = time() - st
+		print >> sys.stderr, "Created %i tuples (1,2,3,4) in %f s ( %f tuples / s)" % (ni, elapsed, ni / elapsed)
+		
+		st = time()
+		for i in xrange(ni):
+			t = tuple((1,2,3,4))
+		# END for each item
+		elapsed = time() - st
+		print >> sys.stderr, "Created %i tuples tuple((1,2,3,4)) in %f s ( %f tuples / s)" % (ni, elapsed, ni / elapsed)
+		
+	def test_unpacking_vs_indexing(self):
+		ni = 1000000
+		list_items = [1,2,3,4]
+		tuple_items = (1,2,3,4)
+		
+		for sequence in (list_items, tuple_items):
+			st = time()
+			for i in xrange(ni):
+				one, two, three, four = sequence
+			# END for eac iteration
+			elapsed = time() - st
+			print >> sys.stderr, "Unpacked %i %ss of size %i in %f s ( %f acc / s)" % (ni, type(sequence).__name__, len(sequence), elapsed, ni / elapsed)
+			
+			st = time()
+			for i in xrange(ni):
+				one, two, three, four = sequence[0], sequence[1], sequence[2], sequence[3]
+			# END for eac iteration
+			elapsed = time() - st
+			print >> sys.stderr, "Unpacked %i %ss of size %i individually in %f s ( %f acc / s)" % (ni, type(sequence).__name__, len(sequence), elapsed, ni / elapsed)
+			
+			st = time()
+			for i in xrange(ni):
+				one, two = sequence[0], sequence[1]
+			# END for eac iteration
+			elapsed = time() - st
+			print >> sys.stderr, "Unpacked %i %ss of size %i individually (2 of 4) in %f s ( %f acc / s)" % (ni, type(sequence).__name__, len(sequence), elapsed, ni / elapsed)
+		# END for each sequence
+		
+	def test_large_list_vs_iteration(self):
+		# what costs more: alloc/realloc of lists, or the cpu strain of iterators ?
+		def slow_iter(ni):
+			for i in xrange(ni):
+				yield i
+		# END slow iter - be closer to the real world
+		
+		# alloc doesn't play a role here it seems 
+		for ni in (500, 1000, 10000, 20000, 40000):
+			st = time()
+			for i in list(xrange(ni)):
+				i
+			# END for each item
+			elapsed = time() - st
+			print >> sys.stderr, "Iterated %i items from list in %f s ( %f acc / s)" % (ni, elapsed, ni / elapsed)
+			
+			st = time()
+			for i in slow_iter(ni):
+				i
+			# END for each item
+			elapsed = time() - st
+			print >> sys.stderr, "Iterated %i items from iterator in %f s ( %f acc / s)" % (ni, elapsed, ni / elapsed)
+		# END for each number of iterations
+