commit 09f0d60f7cc08746511bb957c518885ee0421363
author Georg Brandl <georg@python.org> Sun Aug 01 18:41:59 2010 +0000
committer Georg Brandl <georg@python.org> Sun Aug 01 18:41:59 2010 +0000
tree ccb0712b1de5cc9ed03ce1459060a4a0bfc0dad2
parent 607951d405d7afd8a17408aa9c0e10f44f505c8c

Merged revisions 83395 via svnmerge from
svn+ssh://pythondev@svn.python.org/python/branches/py3k

........
  r83395 | georg.brandl | 2010-08-01 10:49:18 +0200 (So, 01 Aug 2010) | 1 line

  #8821: do not rely on Unicode strings being terminated with a \u0000, rather explicitly check range before looking for a second surrogate character.
........

Objects/unicodeobject.c

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 81b62e4..42e0c9f 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -3067,7 +3067,7 @@
 
             ch2 = *s++;
             size--;
-            if (ch2 >= 0xDC00 && ch2 <= 0xDFFF) {
+            if (ch2 >= 0xDC00 && ch2 <= 0xDFFF && size) {
                 ucs = (((ch & 0x03FF) << 10) | (ch2 & 0x03FF)) + 0x00010000;
                 *p++ = '\\';
                 *p++ = 'U';
@@ -3316,7 +3316,7 @@
 
                 ch2 = *s++;
                 size--;
-                if (ch2 >= 0xDC00 && ch2 <= 0xDFFF) {
+                if (ch2 >= 0xDC00 && ch2 <= 0xDFFF && size) {
                     ucs = (((ch & 0x03FF) << 10) | (ch2 & 0x03FF)) + 0x00010000;
                     *p++ = '\\';
                     *p++ = 'U';