[Python-checkins] cpython (merge 3.3 -> default): merge with 3.3

[philip.jenvey]

http://hg.python.org/cpython/rev/8e67d5dc069d
changeset:   79955:8e67d5dc069d
parent:      79952:a0337031a6b7
parent:      79954:fd41c6b4de57
user:        Philip Jenvey <pjenvey at underboss.org>
date:        Fri Oct 26 17:05:55 2012 -0700
summary:
  merge with 3.3

files:
  Lib/test/test_codecs.py |  2 ++
  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
--- a/Lib/test/test_codecs.py
+++ b/Lib/test/test_codecs.py
@@ -666,6 +666,8 @@
         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
--- a/Python/codecs.c
+++ b/Python/codecs.c
@@ -791,9 +791,10 @@
         /* 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)

-- 
Repository URL: http://hg.python.org/cpython