summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLibravatar Junio C Hamano <gitster@pobox.com>2021-11-19 09:06:36 -0800
committerLibravatar Junio C Hamano <gitster@pobox.com>2021-11-19 09:10:27 -0800
commite7f3925bed86edf1b79fd18e5600252e445019d1 (patch)
tree79a681ce03ce5028777414f382e36c99393e3093
parentgrep/pcre2: fix an edge case concerning ascii patterns and UTF-8 data (diff)
downloadtgif-e7f3925bed86edf1b79fd18e5600252e445019d1.tar.xz
Revert "grep/pcre2: fix an edge case concerning ascii patterns and UTF-8 data"
This reverts commit ae39ba431ab861548eb60b4bd2e1d8b8813db76f, as it breaks "grep" when looking for a string in non UTF-8 haystack, when linked with certain versions of PCREv2 library. Signed-off-by: Junio C Hamano <gitster@pobox.com>
-rw-r--r--grep.c6
-rwxr-xr-xt/t7812-grep-icase-non-ascii.sh48
2 files changed, 2 insertions, 52 deletions
diff --git a/grep.c b/grep.c
index f6e113e9f0..fe847a0111 100644
--- a/grep.c
+++ b/grep.c
@@ -382,10 +382,8 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt
}
options |= PCRE2_CASELESS;
}
- if ((!opt->ignore_locale && !has_non_ascii(p->pattern)) ||
- (!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() && has_non_ascii(p->pattern) &&
+ !(!opt->ignore_case && (p->fixed || p->is_fixed)))
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 22487d90fd..e5d1e4ea68 100755
--- a/t/t7812-grep-icase-non-ascii.sh
+++ b/t/t7812-grep-icase-non-ascii.sh
@@ -53,54 +53,6 @@ test_expect_success REGEX_LOCALE 'pickaxe -i on non-ascii' '
test_cmp expected actual
'
-test_expect_success GETTEXT_LOCALE,PCRE 'log --author with an ascii pattern on UTF-8 data' '
- cat >expected <<-\EOF &&
- Author: <BOLD;RED>À Ú Thor<RESET> <author@example.com>
- EOF
- test_write_lines "forth" >file4 &&
- git add file4 &&
- git commit --author="À Ú Thor <author@example.com>" -m sécond &&
- git log -1 --color=always --perl-regexp --author=".*Thor" >log &&
- grep Author log >actual.raw &&
- test_decode_color <actual.raw >actual &&
- test_cmp expected actual
-'
-
-test_expect_success GETTEXT_LOCALE,PCRE 'log --committer with an ascii pattern on ISO-8859-1 data' '
- cat >expected <<-\EOF &&
- Commit: Ç<BOLD;RED> O Mîtter <committer@example.com><RESET>
- EOF
- test_write_lines "fifth" >file5 &&
- git add file5 &&
- GIT_COMMITTER_NAME="Ç O Mîtter" &&
- GIT_COMMITTER_EMAIL="committer@example.com" &&
- git -c i18n.commitEncoding=latin1 commit -m thïrd &&
- git -c i18n.logOutputEncoding=latin1 log -1 --pretty=fuller --color=always --perl-regexp --committer=" O.*" >log &&
- grep Commit: log >actual.raw &&
- test_decode_color <actual.raw >actual &&
- test_cmp expected actual
-'
-
-test_expect_success GETTEXT_LOCALE,PCRE 'log --grep with an ascii pattern on UTF-8 data' '
- cat >expected <<-\EOF &&
- sé<BOLD;RED>con<RESET>d
- EOF
- git log -1 --color=always --perl-regexp --grep="con" >log &&
- grep con log >actual.raw &&
- test_decode_color <actual.raw >actual &&
- test_cmp expected actual
-'
-
-test_expect_success GETTEXT_LOCALE,PCRE 'log --grep with an ascii pattern on ISO-8859-1 data' '
- cat >expected <<-\EOF &&
- <BOLD;RED>thïrd<RESET>
- EOF
- git -c i18n.logOutputEncoding=latin1 log -1 --color=always --perl-regexp --grep="th.*rd" >log &&
- grep "th.*rd" log >actual.raw &&
- test_decode_color <actual.raw >actual &&
- test_cmp expected actual
-'
-
test_expect_success GETTEXT_LOCALE,LIBPCRE2 'PCRE v2: setup invalid UTF-8 data' '
printf "\\200\\n" >invalid-0x80 &&
echo "ævar" >expected &&