From 394ed7006ee5dc8bddfd132b64001d5dfc0ffdd3 Mon Sep 17 00:00:00 2001 From: Sebastian Thiel Date: Fri, 13 Aug 2010 14:04:11 +0200 Subject: unicode handling in messages and trees was improved. Messages are now written according to the encoding of the commit object, and decoded using that information as well. Trees will encode and decode their names with utf8 --- lib/git/objects/fun.py | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'lib/git/objects/fun.py') diff --git a/lib/git/objects/fun.py b/lib/git/objects/fun.py index e73e93b0..9b0a377c 100644 --- a/lib/git/objects/fun.py +++ b/lib/git/objects/fun.py @@ -66,7 +66,14 @@ def tree_entries_from_data(data): while data[i] != '\0': i += 1 # END while not reached NULL + + # default encoding for strings in git is utf8 + # Only use the respective unicode object if the byte stream was encoded name = data[ns:i] + name_enc = name.decode("utf-8") + if len(name) > len(name_enc): + name = name_enc + # END handle encoding # byte is NULL, get next 20 i += 1 -- cgit v1.2.1