[PATCH v4 00/10] icase match on non-ascii
- From
Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
- Date
- Aug 21, 2015, 12:47 UTC
- Message-ID
- <1440161240-28554-1-git-send-email-pclouds@gmail.com>
- In-Reply-To
- <1436880280-18194-1-git-send-email-pclouds@gmail.com>
Sorry it took more than a month for a simple reroll. Free time (with energy left) is rare these days. v4 adds system regex's icase support detection and only runs tests in these cases. This should fix test failures on Windows where compat regex does not support icase.
Diff from v3 below
diff --git a/t/t7812-grep-icase-non-ascii.sh b/t/t7812-grep-icase-non-ascii.sh index d07fa20..a5475bb 100755 --- a/t/t7812-grep-icase-non-ascii.sh +++ b/t/t7812-grep-icase-non-ascii.sh @@ -11,7 +11,11 @@ test_expect_success GETTEXT_LOCALE 'setup' ' export LC_ALL ' -test_expect_success GETTEXT_LOCALE 'grep literal string, no -F' ' +test_have_prereq GETTEXT_LOCALE && +test-regex "HALLÓ" "Halló" ICASE && +test_set_prereq REGEX_LOCALE + +test_expect_success REGEX_LOCALE 'grep literal string, no -F' ' git grep -i "TILRAUN: Halló Heimur!" && git grep -i "TILRAUN: HALLÓ HEIMUR!" ' @@ -31,7 +35,7 @@ test_expect_success GETTEXT_LOCALE,LIBPCRE 'grep pcre utf-8 string with "+"' ' test_cmp expected actual ' -test_expect_success GETTEXT_LOCALE 'grep literal string, with -F' ' +test_expect_success REGEX_LOCALE 'grep literal string, with -F' ' git grep --debug -i -F "TILRAUN: Halló Heimur!" 2>&1 >/dev/null | grep fixed >debug1 && echo "fixedTILRAUN: Halló Heimur!" >expect1 && @@ -43,7 +47,7 @@ test_expect_success GETTEXT_LOCALE 'grep literal string, with -F' ' test_cmp expect2 debug2 ' -test_expect_success GETTEXT_LOCALE 'grep string with regex, with -F' ' +test_expect_success REGEX_LOCALE 'grep string with regex, with -F' ' printf "^*TILR^AUN:.* \\Halló \$He[]imur!\$" >file && git grep --debug -i -F "^*TILR^AUN:.* \\Halló \$He[]imur!\$" 2>&1 >/dev/null | @@ -57,7 +61,7 @@ test_expect_success GETTEXT_LOCALE 'grep string with regex, with -F' ' test_cmp expect2 debug2 ' -test_expect_success GETTEXT_LOCALE 'pickaxe -i on non-ascii' ' +test_expect_success REGEX_LOCALE 'pickaxe -i on non-ascii' ' git commit -m first && git log --format=%f -i -S"TILRAUN: HALLÓ HEIMUR!" >actual && echo first >expected && diff --git a/test-regex.c b/test-regex.c index 0dc598e..3b5641c 100644 --- a/test-regex.c +++ b/test-regex.c @@ -1,19 +1,63 @@ #include "git-compat-util.h" +#include "gettext.h" + +struct reg_flag { + const char *name; + int flag; +}; + +static struct reg_flag reg_flags[] = { + { "EXTENDED", REG_EXTENDED }, + { "NEWLINE", REG_NEWLINE }, + { "ICASE", REG_ICASE }, + { "NOTBOL", REG_NOTBOL }, +#ifdef REG_STARTEND + { "STARTEND", REG_STARTEND }, +#endif + { NULL, 0 } +}; int main(int argc, char **argv) { - char *pat = "[^={} \t]+"; - char *str = "={}\nfred"; + const char *pat; + const char *str; + int flags = 0; regex_t r; regmatch_t m[1]; - if (regcomp(&r, pat, REG_EXTENDED | REG_NEWLINE)) + if (argc == 1) { + /* special case, bug check */ + pat = "[^={} \t]+"; + str = "={}\nfred"; + flags = REG_EXTENDED | REG_NEWLINE; + } else { + argv++; + pat = *argv++; + str = *argv++; + while (*argv) { + struct reg_flag *rf; + for (rf = reg_flags; rf->name; rf++) + if (!strcmp(*argv, rf->name)) { + flags |= rf->flag; + break; + } + if (!rf->name) + die("do not recognize %s", *argv); + argv++; + } + git_setup_gettext(); + } + + if (regcomp(&r, pat, flags)) die("failed regcomp() for pattern '%s'", pat); - if (regexec(&r, str, 1, m, 0)) - die("no match of pattern '%s' to string '%s'", pat, str); + if (regexec(&r, str, 1, m, 0)) { + if (argc == 1) + die("no match of pattern '%s' to string '%s'", pat, str); + return 1; + } /* http://sourceware.org/bugzilla/show_bug.cgi?id=3957 */ - if (m[0].rm_so == 3) /* matches '\n' when it should not */ + if (argc == 1 && m[0].rm_so == 3) /* matches '\n' when it should not */ die("regex bug confirmed: re-build git with NO_REGEX=1"); exit(0);
-- 2.3.0.rc1.137.g477eb31