Merge branch 'hm/paint-hits-in-log-grep' into maint

"git grep" looking in a blob that has non-UTF8 payload was
completely broken when linked with versions of PCREv2 library older
than 10.34 in the latest release.

* hm/paint-hits-in-log-grep:
  Revert "grep/pcre2: fix an edge case concerning ascii patterns and UTF-8 data"
This commit is contained in:
Junio C Hamano 2021-11-23 14:48:00 -08:00
Родитель cd3e606211 e7f3925bed
Коммит a650ff5aec
2 изменённых файлов: 2 добавлений и 52 удалений

6
grep.c
Просмотреть файл

@ -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

Просмотреть файл

@ -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 &&