mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-07-24 11:44:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

#8271: the utf-8 decoder now outputs the correct number of U+FFFD characters when used with the "replace" error handler on invalid utf-8 sequences. Patch by Serhiy Storchaka, tests by Ezio Melotti.

Browse source
This commit is contained in:
Ezio Melotti 2012-11-04 23:21:38 +02:00
parent 55b5d5c919
commit f7ed5d111b
4 changed files with 292 additions and 38 deletions
Download patch file Download diff file Expand all files Collapse all files

10
Objects/unicodeobject.c
View file

@ -4759,9 +4759,7 @@ PyUnicode_DecodeUTF8Stateful(const char *s,
goto End;
errmsg = "unexpected end of data";
startinpos = s - starts;
endinpos = startinpos + 1;
while (endinpos < size && (starts[endinpos] & 0xC0) == 0x80)
endinpos++;
endinpos = end - starts;
break;
case 1:
errmsg = "invalid start byte";
@ -4769,11 +4767,11 @@ PyUnicode_DecodeUTF8Stateful(const char *s,
endinpos = startinpos + 1;
break;
case 2:
case 3:
case 4:
errmsg = "invalid continuation byte";
startinpos = s - starts;
endinpos = startinpos + 1;
while (endinpos < size && (starts[endinpos] & 0xC0) == 0x80)
endinpos++;
endinpos = startinpos + ch - 1;
break;
default:
if (unicode_putchar(&unicode, &outpos, ch) < 0)