mirror of
https://github.com/ruby/ruby.git
synced 2022-11-09 12:17:21 -05:00
Prevent potential buffer overrun in onigmo
A code pattern `p + enclen(enc, p, pend)` may lead to a buffer overrun if incomplete bytes of a UTF-8 character is placed at the end of a string. Because this pattern is used in several places in onigmo, this change fixes the issue in the side of `enclen`: the function should not return a number that is larger than `pend - p`. Co-Authored-By: Nobuyoshi Nakada <nobu@ruby-lang.org>
This commit is contained in:
parent
114e71d062
commit
1d2d25dcad
Notes:
git
2022-10-25 08:03:04 +00:00
3 changed files with 17 additions and 3 deletions
|
@ -356,9 +356,9 @@ int onigenc_ascii_only_case_map(OnigCaseFoldType* flagP, const OnigUChar** pp, c
|
|||
#define ONIGENC_PRECISE_MBC_ENC_LEN(enc,p,e) (enc)->precise_mbc_enc_len(p,e,enc)
|
||||
|
||||
ONIG_EXTERN
|
||||
int onigenc_mbclen_approximate(const OnigUChar* p,const OnigUChar* e, const struct OnigEncodingTypeST* enc);
|
||||
int onigenc_mbclen(const OnigUChar* p,const OnigUChar* e, const struct OnigEncodingTypeST* enc);
|
||||
|
||||
#define ONIGENC_MBC_ENC_LEN(enc,p,e) onigenc_mbclen_approximate(p,e,enc)
|
||||
#define ONIGENC_MBC_ENC_LEN(enc,p,e) onigenc_mbclen(p,e,enc)
|
||||
#define ONIGENC_MBC_MAXLEN(enc) ((enc)->max_enc_len)
|
||||
#define ONIGENC_MBC_MAXLEN_DIST(enc) ONIGENC_MBC_MAXLEN(enc)
|
||||
#define ONIGENC_MBC_MINLEN(enc) ((enc)->min_enc_len)
|
||||
|
|
15
regenc.c
15
regenc.c
|
@ -51,6 +51,21 @@ onigenc_set_default_encoding(OnigEncoding enc)
|
|||
return 0;
|
||||
}
|
||||
|
||||
extern int
|
||||
onigenc_mbclen(const OnigUChar* p,const OnigUChar* e, OnigEncoding enc)
|
||||
{
|
||||
int ret = ONIGENC_PRECISE_MBC_ENC_LEN(enc, p, e);
|
||||
if (ONIGENC_MBCLEN_CHARFOUND_P(ret)) {
|
||||
ret = ONIGENC_MBCLEN_CHARFOUND_LEN(ret);
|
||||
if (ret > (int)(e - p)) ret = (int)(e - p); // just for case
|
||||
return ret;
|
||||
}
|
||||
else if (ONIGENC_MBCLEN_NEEDMORE_P(ret)) {
|
||||
return (int)(e - p);
|
||||
}
|
||||
return p < e ? 1 : 0;
|
||||
}
|
||||
|
||||
extern int
|
||||
onigenc_mbclen_approximate(const OnigUChar* p,const OnigUChar* e, OnigEncoding enc)
|
||||
{
|
||||
|
|
|
@ -3799,7 +3799,6 @@ fetch_token(OnigToken* tok, UChar** src, UChar* end, ScanEnv* env)
|
|||
}
|
||||
else { /* string */
|
||||
p = tok->backp + enclen(enc, tok->backp, end);
|
||||
if (p > end) return ONIGERR_END_PATTERN_AT_ESCAPE;
|
||||
}
|
||||
}
|
||||
break;
|
||||
|
|
Loading…
Reference in a new issue