changeset: 78207:118fe0ee6921 parent: 78205:f1f480650a0a parent: 78206:034ff986019d user: Antoine Pitrou date: Sat Jul 21 00:47:48 2012 +0200 files: Lib/test/test_codecs.py Misc/NEWS Objects/unicodeobject.c description: Port additional tests from #14579 (the issue is already fixed). diff -r f1f480650a0a -r 118fe0ee6921 Lib/test/test_codecs.py --- a/Lib/test/test_codecs.py Fri Jul 20 13:24:58 2012 -0700 +++ b/Lib/test/test_codecs.py Sat Jul 21 00:47:48 2012 +0200 @@ -557,8 +557,19 @@ ) def test_errors(self): - self.assertRaises(UnicodeDecodeError, codecs.utf_16_le_decode, - b"\xff", "strict", True) + tests = [ + (b'\xff', '\ufffd'), + (b'A\x00Z', 'A\ufffd'), + (b'A\x00B\x00C\x00D\x00Z', 'ABCD\ufffd'), + (b'\x00\xd8', '\ufffd'), + (b'\x00\xd8A', '\ufffd'), + (b'\x00\xd8A\x00', '\ufffdA'), + (b'\x00\xdcA\x00', '\ufffdA'), + ] + for raw, expected in tests: + self.assertRaises(UnicodeDecodeError, codecs.utf_16_le_decode, + raw, 'strict', True) + self.assertEqual(raw.decode('utf-16le', 'replace'), expected) def test_nonbmp(self): self.assertEqual("\U00010203".encode(self.encoding), @@ -585,8 +596,19 @@ ) def test_errors(self): - self.assertRaises(UnicodeDecodeError, codecs.utf_16_be_decode, - b"\xff", "strict", True) + tests = [ + (b'\xff', '\ufffd'), + (b'\x00A\xff', 'A\ufffd'), + (b'\x00A\x00B\x00C\x00DZ', 'ABCD\ufffd'), + (b'\xd8\x00', '\ufffd'), + (b'\xd8\x00\xdc', '\ufffd'), + (b'\xd8\x00\x00A', '\ufffdA'), + (b'\xdc\x00\x00A', '\ufffdA'), + ] + for raw, expected in tests: + self.assertRaises(UnicodeDecodeError, codecs.utf_16_be_decode, + raw, 'strict', True) + self.assertEqual(raw.decode('utf-16be', 'replace'), expected) def test_nonbmp(self): self.assertEqual("\U00010203".encode(self.encoding),