diff -r ae05d841bea1 Lib/test/test_zipfile.py --- a/Lib/test/test_zipfile.py Sun Apr 07 12:41:16 2013 -0500 +++ b/Lib/test/test_zipfile.py Mon Apr 08 12:54:31 2013 +0300 @@ -18,7 +18,7 @@ from random import randint, random from unittest import skipUnless -from test.test_support import TESTFN, run_unittest, findfile, unlink +from test.test_support import TESTFN, TESTFN_UNICODE, run_unittest, findfile, unlink TESTFN2 = TESTFN + "2" TESTFNDIR = TESTFN + "d" @@ -424,6 +424,25 @@ with open(filename, 'rb') as f: self.assertEqual(f.read(), content) + def test_extract_unicode_filenames(self): + fnames = [u'foo.txt', os.path.basename(TESTFN_UNICODE)] + content = 'Test for unicode filename' + with zipfile.ZipFile(TESTFN2, "w", zipfile.ZIP_STORED) as zipfp: + for fname in fnames: + zipfp.writestr(fname, content) + + with zipfile.ZipFile(TESTFN2, "r") as zipfp: + for fname in fnames: + writtenfile = zipfp.extract(fname) + + # make sure it was written to the right place + correctfile = os.path.join(os.getcwd(), fname) + correctfile = os.path.normpath(correctfile) + self.assertEqual(writtenfile, correctfile) + + self.check_file(writtenfile, content) + os.remove(writtenfile) + def test_extract_hackers_arcnames(self): hacknames = [ ('../foo/bar', 'foo/bar'), diff -r ae05d841bea1 Lib/zipfile.py --- a/Lib/zipfile.py Sun Apr 07 12:41:16 2013 -0500 +++ b/Lib/zipfile.py Mon Apr 08 12:54:31 2013 +0300 @@ -1053,7 +1053,10 @@ if os.path.sep == '\\': # filter illegal characters on Windows illegal = ':<>|"?*' - table = string.maketrans(illegal, '_' * len(illegal)) + if isinstance(arcname, unicode): + table = {ord(c): ord('_') for c in illegal} + else: + table = string.maketrans(illegal, '_' * len(illegal)) arcname = arcname.translate(table) # remove trailing dots arcname = (x.rstrip('.') for x in arcname.split(os.path.sep))