Added test to verify the actor type can handle and parse unicode if it is passed in

test_odb: added more information to the message output

Author: Byron

lib/git/ext/gitdb

@@ -49,17 +49,18 @@ def test_random_access(self):
 			st = time()
 			nb = 0
 			too_many = 15000
+			data_bytes = 0
 			for blob_list in blobs_per_commit:
 				for blob in blob_list:
-					blob.data_stream.read()
+					data_bytes += len(blob.data_stream.read())
 				# END for each blobsha
 				nb += len(blob_list)
 				if nb > too_many:
 					break
 			# END for each bloblist
 			elapsed = time() - st
 
-			print >> sys.stderr, "%s: Retrieved %i blob and their data in %g s ( %f blobs / s )" % (type(repo.odb), nb, elapsed, nb / elapsed)
+			print >> sys.stderr, "%s: Retrieved %i blob (%i KiB) and their data in %g s ( %f blobs / s, %f KiB / s )" % (type(repo.odb), nb, data_bytes/1000, elapsed, nb / elapsed, (data_bytes / 1000) / elapsed)
 			results[2].append(elapsed)
 		# END for each repo type
 

test/git/performance/test_odb.py

@@ -1,3 +1,4 @@
+# -*- coding: utf-8 -*-
 # test_commit.py
 # Copyright (C) 2008, 2009 Michael Trier ([email protected]) and contributors
 #
@@ -108,6 +109,14 @@ def check_entries(d):
 		assert commit.committer_tz_offset == 14400, commit.committer_tz_offset
 		assert commit.message == "initial project\n"
 
+	def test_unicode_actor(self):
+		# assure we can parse unicode actors correctly
+		name = "Üäöß ÄußÉ".decode("utf-8")
+		assert len(name) == 9
+		special = Actor._from_string(u"%s <[email protected]>" % name)
+		assert special.name == name
+		assert isinstance(special.name, unicode)
+		
 	def test_traversal(self):
 		start = self.rorepo.commit("a4d06724202afccd2b5c54f81bcf2bf26dea7fff")
 		first = self.rorepo.commit("33ebe7acec14b25c5f84f35a664803fcab2f7781")