diff options
| author | Antoine Pitrou <solipsis@pitrou.net> | 2012-07-20 22:45:14 (GMT) |
|---|---|---|
| committer | Antoine Pitrou <solipsis@pitrou.net> | 2012-07-20 22:45:14 (GMT) |
| commit | b4bbee25b1e3f4bccac222f806b3138fb72439d6 (patch) | |
| tree | 586129fbe8b38a553772635efa1ff753e5c7be70 /Lib | |
| parent | ca9652ea5d1d9ebddd1acf6abbbf3751bc366a44 (diff) | |
| download | cpython-b4bbee25b1e3f4bccac222f806b3138fb72439d6.zip cpython-b4bbee25b1e3f4bccac222f806b3138fb72439d6.tar.gz cpython-b4bbee25b1e3f4bccac222f806b3138fb72439d6.tar.bz2 | |
Issue #14579: Fix CVE-2012-2135: vulnerability in the utf-16 decoder after error handling.
Patch by Serhiy Storchaka.
Diffstat (limited to 'Lib')
| -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 4899a59..3426a4d 100644 --- a/Lib/test/test_codecs.py +++ b/Lib/test/test_codecs.py @@ -540,8 +540,19 @@ 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), @@ -568,8 +579,19 @@ 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), |