mirrors/git
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'ab/grep-pcre-invalid-utf8'

Browse Source 
Update support for invalid UTF-8 in PCRE2.

* ab/grep-pcre-invalid-utf8:
  grep/pcre2: better support invalid UTF-8 haystacks
  grep/pcre2 tests: don't rely on invalid UTF-8 data test
This commit is contained in:
Junio C Hamano
2021-02-10 14:48:33 -08:00
parent 0199c68d01 95ca1f987e
commit 59ace284f3
7 changed files with 82 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
grep.c
View File

@ -391,7 +391,23 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt
}
if (!opt->ignore_locale && is_utf8_locale() && has_non_ascii(p->pattern) &&
!(!opt->ignore_case && (p->fixed || p->is_fixed)))
options |= PCRE2_UTF;
options |= (PCRE2_UTF | PCRE2_MATCH_INVALID_UTF);
/* Work around https://bugs.exim.org/show_bug.cgi?id=2642 fixed in 10.36 */
if (PCRE2_MATCH_INVALID_UTF && options & (PCRE2_UTF | PCRE2_CASELESS)) {
struct strbuf buf;
int len;
int err;
if ((len = pcre2_config(PCRE2_CONFIG_VERSION, NULL)) < 0)
BUG("pcre2_config(..., NULL) failed: %d", len);
strbuf_init(&buf, len + 1);
if ((err = pcre2_config(PCRE2_CONFIG_VERSION, buf.buf)) < 0)
BUG("pcre2_config(..., buf.buf) failed: %d", err);
if (versioncmp(buf.buf, "10.36") < 0)
options |= PCRE2_NO_START_OPTIMIZE;
strbuf_release(&buf);
}
p->pcre2_pattern = pcre2_compile((PCRE2_SPTR)p->pattern,
p->patternlen, options, &error, &erroffset,