Author: martin.v.loewis Date: Fri Aug 31 13:01:23 2007 New Revision: 57837 Modified: python/branches/py3k/Objects/unicodeobject.c Log: Change %s argument for PyUnicode_FromFormat to be UTF-8. Fixes #1070.
Modified: python/branches/py3k/Objects/unicodeobject.c
==============================================================================
--- python/branches/py3k/Objects/unicodeobject.c (original)
+++ python/branches/py3k/Objects/unicodeobject.c Fri Aug 31 13:01:23 2007
@@ -621,8 +621,39 @@
abuffersize = width;
break;
case 's':
- n += strlen(va_arg(count, char*));
+ {
+ /* UTF-8 */
+ unsigned char*s;
+ s = va_arg(count, unsigned char*);
+ while (*s) {
+ if (*s < 128) {
+ n++; s++;
+ } else if (*s < 0xc0) {
+ /* invalid UTF-8 */
+ n++; s++;
+ } else if (*s < 0xc0) {
+ n++;
+ s++; if(!*s)break;
+ s++;
+ } else if (*s < 0xe0) {
+ n++;
+ s++; if(!*s)break;
+ s++; if(!*s)break;
+ s++;
+ } else {
+ #ifdef Py_UNICODE_WIDE
+ n++;
+ #else
+ n+=2;
+ #endif
+ s++; if(!*s)break;
+ s++; if(!*s)break;
+ s++; if(!*s)break;
+ s++;
+ }
+ }
break;
+ }
case 'U':
{
PyObject *obj = va_arg(count, PyObject *);
@@ -775,9 +806,22 @@
appendstring(realbuffer);
break;
case 's':
+ {
+ /* Parameter must be UTF-8 encoded.
+ In case of encoding errors, use
+ the replacement character. */
+ PyObject *u;
p = va_arg(vargs, char*);
- appendstring(p);
+ u = PyUnicode_DecodeUTF8(p, strlen(p),
+ "replace");
+ if (!u)
+ goto fail;
+ Py_UNICODE_COPY(s, PyUnicode_AS_UNICODE(u),
+ PyUnicode_GET_SIZE(u));
+ s += PyUnicode_GET_SIZE(u);
+ Py_DECREF(u);
break;
+ }
case 'U':
{
PyObject *obj = va_arg(vargs, PyObject *);
_______________________________________________
Python-3000-checkins mailing list
Python-3000-checkins@python.org
http://mail.python.org/mailman/listinfo/python-3000-checkins
