Usually PCRE is compiled with JIT support, and therefore the code
path used includes calling pcre2_jit_match (for PCRE2), that ignores
invalid UTF-8 in the corpus.
Make that option explicit so it can be also used when JIT is not
enabled and pcre2_match is called instead, preventing `git grep`
to abort when hitting the first binary blob in a fixed match
after ed0479ce3d ("Merge branch 'ab/no-kwset' into next", 2019-07-15)
Signed-off-by: Carlo Marcelo Arenas Belón <carenas@xxxxxxxxx>
---
grep.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/grep.c b/grep.c
index fc0ed73ef3..146093f590 100644
--- a/grep.c
+++ b/grep.c
@@ -409,7 +409,7 @@ static void compile_pcre1_regexp(struct grep_pat *p, const struct grep_opt *opt)
static int pcre1match(struct grep_pat *p, const char *line, const char *eol,
regmatch_t *match, int eflags)
{
- int ovector[30], ret, flags = 0;
+ int ovector[30], ret, flags = PCRE_NO_UTF8_CHECK;
if (eflags & REG_NOTBOL)
flags |= PCRE_NOTBOL;
@@ -554,7 +554,7 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt
static int pcre2match(struct grep_pat *p, const char *line, const char *eol,
regmatch_t *match, int eflags)
{
- int ret, flags = 0;
+ int ret, flags = PCRE2_NO_UTF_CHECK;
PCRE2_SIZE *ovector;
PCRE2_UCHAR errbuf[256];
--
2.22.0
