mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-04 00:48:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

gh-70278: Fix PyUnicode_FromFormat() with precision for %s and %V (GH-120365)

Browse source 
PyUnicode_FromFormat() no longer produces the ending \ufffd
character for truncated C string when use precision with %s and %V.
It now truncates the string before the start of truncated multibyte sequences.
This commit is contained in:
Serhiy Storchaka 2024-06-24 18:07:07 +03:00 • committed by GitHub
parent 22b8a35d6e
commit 6eb23b1311
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 59 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

13
Objects/unicodeobject.c
View file

@ -2581,6 +2581,7 @@ unicode_fromformat_write_utf8(_PyUnicodeWriter *writer, const char *str,
Py_ssize_t width, Py_ssize_t precision, int flags)
{
/* UTF-8 */
Py_ssize_t *pconsumed = NULL;
Py_ssize_t length;
if (precision == -1) {
length = strlen(str);
@ -2590,15 +2591,23 @@ unicode_fromformat_write_utf8(_PyUnicodeWriter *writer, const char *str,
while (length < precision && str[length]) {
length++;
}
if (length == precision) {
/* The input string is not NUL-terminated. If it ends with an
* incomplete UTF-8 sequence, truncate the string just before it.
* Incomplete sequences in the middle and sequences which cannot
* be valid prefixes are still treated as errors and replaced
* with \xfffd. */
pconsumed = &length;
}
}
if (width < 0) {
return unicode_decode_utf8_writer(writer, str, length,
_Py_ERROR_REPLACE, "replace", NULL);
_Py_ERROR_REPLACE, "replace", pconsumed);
}
PyObject *unicode = PyUnicode_DecodeUTF8Stateful(str, length,
"replace", NULL);
"replace", pconsumed);
if (unicode == NULL)
return -1;