Mercurial > cpython-lru_cache-weakref

diff Python/codecs.c @ 79953:74d65c746f63 3.2

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
bounds check for bad data (thanks amaury)
author Philip Jenvey <pjenvey@underboss.org>
date Fri, 26 Oct 2012 17:01:53 -0700
parents 46b245f03f54
children 18ed608ee594 fd41c6b4de57
line wrap: on
line diff
--- a/Python/codecs.c	Fri Oct 26 19:14:16 2012 +0300
+++ b/Python/codecs.c	Fri Oct 26 17:01:53 2012 -0700
@@ -821,9 +821,10 @@
         /* 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)