Branch merge

This commit is contained in:
Éric Araujo 2012-11-03 17:09:37 -04:00
commit 95b4ec8ee3
3 changed files with 9 additions and 4 deletions

View File

@ -668,6 +668,8 @@ class UTF8Test(ReadTest):
self.assertTrue(codecs.lookup_error("surrogatepass")) self.assertTrue(codecs.lookup_error("surrogatepass"))
with self.assertRaises(UnicodeDecodeError): with self.assertRaises(UnicodeDecodeError):
b"abc\xed\xa0".decode("utf-8", "surrogatepass") b"abc\xed\xa0".decode("utf-8", "surrogatepass")
with self.assertRaises(UnicodeDecodeError):
b"abc\xed\xa0z".decode("utf-8", "surrogatepass")
@unittest.skipUnless(sys.platform == 'win32', @unittest.skipUnless(sys.platform == 'win32',
'cp65001 is a Windows-only codec') 'cp65001 is a Windows-only codec')

View File

@ -10,6 +10,9 @@ What's New in Python 3.4.0 Alpha 1?
Core and Builtins Core and Builtins
----------------- -----------------
- Issue #16336: fix input checking in the surrogatepass error handler.
Patch by Serhiy Storchaka.
- Issue #8401: assigning an int to a bytearray slice (e.g. b[3:4] = 5) now - Issue #8401: assigning an int to a bytearray slice (e.g. b[3:4] = 5) now
raises an error. raises an error.

View File

@ -791,10 +791,10 @@ PyCodec_SurrogatePassErrors(PyObject *exc)
/* Try decoding a single surrogate character. If /* Try decoding a single surrogate character. If
there are more, let the codec call us again. */ there are more, let the codec call us again. */
p += start; p += start;
if (strlen(p) > 2 && if (PyBytes_GET_SIZE(object) - start >= 3 &&
((p[0] & 0xf0) == 0xe0 || (p[0] & 0xf0) == 0xe0 &&
(p[1] & 0xc0) == 0x80 || (p[1] & 0xc0) == 0x80 &&
(p[2] & 0xc0) == 0x80)) { (p[2] & 0xc0) == 0x80) {
/* it's a three-byte code */ /* it's a three-byte code */
ch = ((p[0] & 0x0f) << 12) + ((p[1] & 0x3f) << 6) + (p[2] & 0x3f); ch = ((p[0] & 0x0f) << 12) + ((p[1] & 0x3f) << 6) + (p[2] & 0x3f);
if (!Py_UNICODE_IS_SURROGATE(ch)) if (!Py_UNICODE_IS_SURROGATE(ch))