Explicitly use UTF-8 as the encoding for the normalization file.

This commit is contained in:
Martin v. Löwis 2007-08-30 20:58:02 +00:00
parent 5495957b6c
commit 234a34a564
2 changed files with 4 additions and 4 deletions

View file

@ -33,7 +33,7 @@ def unistr(data):
class NormalizationTest(unittest.TestCase):
def test_main(self):
part1_data = {}
for line in open_urlresource(TESTDATAURL):
for line in open_urlresource(TESTDATAURL, encoding="utf-8"):
if '#' in line:
line = line.split('#')[0]
line = line.strip()