diff options
| author | Serhiy Storchaka <storchaka@gmail.com> | 2018-12-03 08:36:45 (GMT) |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2018-12-03 08:36:45 (GMT) |
| commit | 4013c179117754b039957db4730880bf3285919d (patch) | |
| tree | 7d7e8ed373d7469d8ddb5e6d5553337a3955f6b1 /Lib | |
| parent | 062cbb67726f26794b1b461853e40696b4a0b220 (diff) | |
| download | cpython-4013c179117754b039957db4730880bf3285919d.zip cpython-4013c179117754b039957db4730880bf3285919d.tar.gz cpython-4013c179117754b039957db4730880bf3285919d.tar.bz2 | |
bpo-35372: Fix the code page decoder for input > 2 GiB. (GH-10848)
Diffstat (limited to 'Lib')
| -rw-r--r-- | Lib/test/test_codecs.py | 18 |
1 files changed, 18 insertions, 0 deletions
diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py index 8c92556..79cddb8 100644 --- a/Lib/test/test_codecs.py +++ b/Lib/test/test_codecs.py @@ -3190,6 +3190,24 @@ class CodePageTest(unittest.TestCase): codec = codecs.lookup('cp123') self.assertEqual(codec.name, 'mbcs') + @support.bigmemtest(size=2**31, memuse=7, dry_run=False) + def test_large_input(self): + # Test input longer than INT_MAX. + # Input should contain undecodable bytes before and after + # the INT_MAX limit. + encoded = (b'01234567' * (2**28-1) + + b'\x85\x86\xea\xeb\xec\xef\xfc\xfd\xfe\xff') + self.assertEqual(len(encoded), 2**31+2) + decoded = codecs.code_page_decode(932, encoded, 'surrogateescape', True) + self.assertEqual(decoded[1], len(encoded)) + del encoded + self.assertEqual(len(decoded[0]), decoded[1]) + self.assertEqual(decoded[0][:10], '0123456701') + self.assertEqual(decoded[0][-20:], + '6701234567' + '\udc85\udc86\udcea\udceb\udcec' + '\udcef\udcfc\udcfd\udcfe\udcff') + class ASCIITest(unittest.TestCase): def test_encode(self): |