diff options
| -rw-r--r-- | Lib/test/test_codecs.py | 30 |
1 files changed, 26 insertions, 4 deletions
diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py index 5daaa19..59179c4 100644 --- a/Lib/test/test_codecs.py +++ b/Lib/test/test_codecs.py @@ -557,8 +557,19 @@ class UTF16LETest(ReadTest): ) 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 @@ class UTF16BETest(ReadTest): ) 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), |