@@ -540,8 +540,19 @@ def test_partial(self):
540 540
)
541 541 542 542
def test_errors(self):
543 -
self.assertRaises(UnicodeDecodeError, codecs.utf_16_le_decode,
544 -
b"\xff", "strict", True)
543 +
tests = [
544 +
(b'\xff', '\ufffd'),
545 +
(b'A\x00Z', 'A\ufffd'),
546 +
(b'A\x00B\x00C\x00D\x00Z', 'ABCD\ufffd'),
547 +
(b'\x00\xd8', '\ufffd'),
548 +
(b'\x00\xd8A', '\ufffd'),
549 +
(b'\x00\xd8A\x00', '\ufffdA'),
550 +
(b'\x00\xdcA\x00', '\ufffdA'),
551 +
]
552 +
for raw, expected in tests:
553 +
self.assertRaises(UnicodeDecodeError, codecs.utf_16_le_decode,
554 +
raw, 'strict', True)
555 +
self.assertEqual(raw.decode('utf-16le', 'replace'), expected)
545 556 546 557
def test_nonbmp(self):
547 558
self.assertEqual("\U00010203".encode(self.encoding),
@@ -568,8 +579,19 @@ def test_partial(self):
568 579
)
569 580 570 581
def test_errors(self):
571 -
self.assertRaises(UnicodeDecodeError, codecs.utf_16_be_decode,
572 -
b"\xff", "strict", True)
582 +
tests = [
583 +
(b'\xff', '\ufffd'),
584 +
(b'\x00A\xff', 'A\ufffd'),
585 +
(b'\x00A\x00B\x00C\x00DZ', 'ABCD\ufffd'),
586 +
(b'\xd8\x00', '\ufffd'),
587 +
(b'\xd8\x00\xdc', '\ufffd'),
588 +
(b'\xd8\x00\x00A', '\ufffdA'),
589 +
(b'\xdc\x00\x00A', '\ufffdA'),
590 +
]
591 +
for raw, expected in tests:
592 +
self.assertRaises(UnicodeDecodeError, codecs.utf_16_be_decode,
593 +
raw, 'strict', True)
594 +
self.assertEqual(raw.decode('utf-16be', 'replace'), expected)
573 595 574 596
def test_nonbmp(self):
575 597
self.assertEqual("\U00010203".encode(self.encoding),
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4