Marc
/
server
forked from github/server
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Parser fallback to latin1 when detecting invalid utf-8

This commit is contained in:
Enno Rehling 2020-08-09 20:56:43 +02:00
parent 2fe4261c70
commit 55704cfce8
1 changed files with 9 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
src/util/parser.c
View File

@ -173,8 +173,15 @@ char *parse_token(const char **str, char *lbuf, size_t buflen)
else { else {
int ret = unicode_utf8_decode(&wc, ctoken, &len); int ret = unicode_utf8_decode(&wc, ctoken, &len);
if (ret != 0) { if (ret != 0) {
log_warning("illegal character sequence in UTF8 string: %s\n", ctoken); log_info("falling back to ISO-8859-1: %s\n", cstart);
break; if (cursor - buflen < lbuf - 2) {
size_t inlen = 1;
len = 2;
unicode_latin1_to_utf8(cursor, &len, ctoken, &inlen);
cursor += len;
ctoken += inlen;
continue;
}
} }
} }
if (escape) { if (escape) {