diff options
| author | Philip Jenvey <pjenvey@underboss.org> | 2012-10-27 00:05:55 (GMT) |
|---|---|---|
| committer | Philip Jenvey <pjenvey@underboss.org> | 2012-10-27 00:05:55 (GMT) |
| commit | 16bb5450d6b68514039e4c5fe835482aced38b73 (patch) | |
| tree | 23c248ac46963d2d17177a1bf68abb12ec452654 | |
| parent | a0e41a2e9bb107003db2446cb13a02d48570c956 (diff) | |
| parent | 5f9459fbedae091bff5b87189014a996f1352b1c (diff) | |
| download | cpython-16bb5450d6b68514039e4c5fe835482aced38b73.zip cpython-16bb5450d6b68514039e4c5fe835482aced38b73.tar.gz cpython-16bb5450d6b68514039e4c5fe835482aced38b73.tar.bz2 | |
merge with 3.3
| -rw-r--r-- | Lib/test/test_codecs.py | 2 | ||||
| -rw-r--r-- | Python/codecs.c | 7 |
2 files changed, 6 insertions, 3 deletions
diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py index 4e808ec..93660f7 100644 --- a/Lib/test/test_codecs.py +++ b/Lib/test/test_codecs.py @@ -666,6 +666,8 @@ class UTF8Test(ReadTest): self.assertEqual(b"\xf0\x90\xbf\xbf\xed\xa0\x80".decode("utf-8", "surrogatepass"), "\U00010fff\uD800") self.assertTrue(codecs.lookup_error("surrogatepass")) + with self.assertRaises(UnicodeDecodeError): + b"abc\xed\xa0".decode("utf-8", "surrogatepass") @unittest.skipUnless(sys.platform == 'win32', 'cp65001 is a Windows-only codec') diff --git a/Python/codecs.c b/Python/codecs.c index 797a45f..5470500 100644 --- a/Python/codecs.c +++ b/Python/codecs.c @@ -791,9 +791,10 @@ PyCodec_SurrogatePassErrors(PyObject *exc) /* Try decoding a single surrogate character. If there are more, let the codec call us again. */ p += start; - if ((p[0] & 0xf0) == 0xe0 || - (p[1] & 0xc0) == 0x80 || - (p[2] & 0xc0) == 0x80) { + if (strlen(p) > 2 && + ((p[0] & 0xf0) == 0xe0 || + (p[1] & 0xc0) == 0x80 || + (p[2] & 0xc0) == 0x80)) { /* it's a three-byte code */ ch = ((p[0] & 0x0f) << 12) + ((p[1] & 0x3f) << 6) + (p[2] & 0x3f); if (ch < 0xd800 || ch > 0xdfff) |