merge with 3.3

This commit is contained in:
Philip Jenvey 2012-10-26 17:05:55 -07:00
commit 16bb5450d6
2 changed files with 6 additions and 3 deletions

View File

@ -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')

View File

@ -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)