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.
........

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 81b62e4fd84caecdb4c28e21d907efbe4dcefd42..42e0c9fec695983af13e56c8a277ee41acdc7e58 100644 (file)
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -3067,7 +3067,7 @@ PyObject *unicodeescape_string(const Py_UNICODE *s,
 
             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 @@ PyObject *PyUnicode_EncodeRawUnicodeEscape(const Py_UNICODE *s,
 
                 ch2 = *s++;
                 size--;
-                if (ch2 >= 0xDC00 && ch2 <= 0xDFFF) {
+                if (ch2 >= 0xDC00 && ch2 <= 0xDFFF && size) {
                     ucs = (((ch & 0x03FF) << 10) | (ch2 & 0x03FF)) + 0x00010000;
                     *p++ = '\\';
                     *p++ = 'U';