undef/git-commit-vandalism
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'rs/pcre2-utf'

Browse Source 
"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
This commit is contained in:
Junio C Hamano 2022-01-05 14:01:31 -08:00
commit c91b0b7c72
2 changed files with 8 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
grep.c
View File

@ -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

6
t/t7812-grep-icase-non-ascii.sh
View File

@ -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