diff options
author | Junio C Hamano <gitster@pobox.com> | 2022-01-06 01:01:31 +0300 |
---|---|---|
committer | Junio C Hamano <gitster@pobox.com> | 2022-01-06 01:01:31 +0300 |
commit | c91b0b7c7270dac8c539062d193749e654b7f002 (patch) | |
tree | 86df5729ee96b399c5f5b578708305670f6e5fbb | |
parent | 5d522cddfd910f6aa9383d121ac8dd17dfffff50 (diff) | |
parent | 32e3e8bc551e7b10bbda07110ae7cb15442d0392 (diff) |
Merge branch 'rs/pcre2-utf'
"git grep --perl-regexp" failed to match UTF-8 characters with
wildcard when the pattern consists only of ASCII letters, which has
been corrected.
* rs/pcre2-utf:
grep/pcre2: factor out literal variable
grep/pcre2: use PCRE2_UTF even with ASCII patterns
-rw-r--r-- | grep.c | 4 | ||||
-rwxr-xr-x | t/t7812-grep-icase-non-ascii.sh | 6 |
2 files changed, 8 insertions, 2 deletions
@@ -362,6 +362,7 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt int jitret; int patinforet; size_t jitsizearg; + int literal = !opt->ignore_case && (p->fixed || p->is_fixed); /* * Call pcre2_general_context_create() before calling any @@ -382,8 +383,7 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt } options |= PCRE2_CASELESS; } - if (!opt->ignore_locale && is_utf8_locale() && has_non_ascii(p->pattern) && - !(!opt->ignore_case && (p->fixed || p->is_fixed))) + if (!opt->ignore_locale && is_utf8_locale() && !literal) options |= (PCRE2_UTF | PCRE2_MATCH_INVALID_UTF); #ifdef GIT_PCRE2_VERSION_10_36_OR_HIGHER diff --git a/t/t7812-grep-icase-non-ascii.sh b/t/t7812-grep-icase-non-ascii.sh index e5d1e4ea68..ca3f24f807 100755 --- a/t/t7812-grep-icase-non-ascii.sh +++ b/t/t7812-grep-icase-non-ascii.sh @@ -123,4 +123,10 @@ test_expect_success GETTEXT_LOCALE,LIBPCRE2,PCRE2_MATCH_INVALID_UTF 'PCRE v2: gr test_cmp invalid-0xe5 actual ' +test_expect_success GETTEXT_LOCALE,LIBPCRE2 'PCRE v2: grep non-literal ASCII from UTF-8' ' + git grep --perl-regexp -h -o -e ll. file >actual && + echo "lló" >expected && + test_cmp expected actual +' + test_done |