git.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>
To: git@vger.kernel.org
Cc: "Junio C Hamano" <gitster@pobox.com>,
	plamen.totev@abv.bg, l.s.r@web.de,
	"Eric Sunshine" <sunshine@sunshineco.com>,
	tboegi@web.de, "Nguyễn Thái Ngọc Duy" <pclouds@gmail.com>
Subject: [PATCH v4 00/10] icase match on non-ascii
Date: Fri, 21 Aug 2015 19:47:10 +0700	[thread overview]
Message-ID: <1440161240-28554-1-git-send-email-pclouds@gmail.com> (raw)
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

  parent reply	other threads:[~2015-08-21 12:58 UTC|newest]

Thread overview: 53+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-07-06 11:28 Git grep does not support multi-byte characters (like UTF-8) Plamen Totev
2015-07-06 12:23 ` Duy Nguyen
2015-07-07  8:58   ` Plamen Totev
2015-07-07 12:22     ` Duy Nguyen
2015-07-07 16:07     ` Junio C Hamano
2015-07-07 18:08       ` Plamen Totev
2015-07-08  2:19         ` Duy Nguyen
2015-07-08  4:52           ` Junio C Hamano
2015-07-06 12:42 ` [PATCH] grep: use regcomp() for icase search with non-ascii patterns Nguyễn Thái Ngọc Duy
2015-07-06 20:10   ` René Scharfe
2015-07-06 23:02     ` Duy Nguyen
2015-07-07 14:25       ` Plamen Totev
2015-07-08 10:38   ` [PATCH v2 0/9] icase match on non-ascii Nguyễn Thái Ngọc Duy
2015-07-08 10:38     ` [PATCH v2 1/9] grep: allow -F -i combination Nguyễn Thái Ngọc Duy
2015-07-08 10:38     ` [PATCH v2 2/9] grep: break down an "if" stmt in preparation for next changes Nguyễn Thái Ngọc Duy
2015-07-08 10:38     ` [PATCH v2 3/9] grep/icase: avoid kwsset on literal non-ascii strings Nguyễn Thái Ngọc Duy
2015-07-08 10:38     ` [PATCH v2 4/9] grep/icase: avoid kwsset when -F is specified Nguyễn Thái Ngọc Duy
2015-07-08 10:38     ` [PATCH v2 5/9] grep/pcre: prepare locale-dependent tables for icase matching Nguyễn Thái Ngọc Duy
2015-07-08 11:00       ` Duy Nguyen
2015-07-08 10:38     ` [PATCH v2 6/9] gettext: add is_utf8_locale() Nguyễn Thái Ngọc Duy
2015-07-08 10:38     ` [PATCH v2 7/9] grep/pcre: support utf-8 Nguyễn Thái Ngọc Duy
2015-07-11  8:07       ` Plamen Totev
2015-07-08 10:38     ` [PATCH v2 8/9] diffcore-pickaxe: "share" regex error handling code Nguyễn Thái Ngọc Duy
2015-07-08 10:38     ` [PATCH v2 9/9] diffcore-pickaxe: support case insensitive match on non-ascii Nguyễn Thái Ngọc Duy
2015-07-09 22:55       ` Eric Sunshine
2015-07-08 11:32     ` [PATCH v2 0/9] icase " Torsten Bögershausen
2015-07-08 12:13       ` Duy Nguyen
2015-07-08 15:36     ` Junio C Hamano
2015-07-08 23:28       ` Duy Nguyen
2015-07-14 13:24     ` [PATCH v3 " Nguyễn Thái Ngọc Duy
2015-07-14 13:24       ` [PATCH v3 1/9] grep: allow -F -i combination Nguyễn Thái Ngọc Duy
2015-07-14 13:24       ` [PATCH v3 2/9] grep: break down an "if" stmt in preparation for next changes Nguyễn Thái Ngọc Duy
2015-07-14 13:24       ` [PATCH v3 3/9] grep/icase: avoid kwsset on literal non-ascii strings Nguyễn Thái Ngọc Duy
2015-07-14 13:24       ` [PATCH v3 4/9] grep/icase: avoid kwsset when -F is specified Nguyễn Thái Ngọc Duy
2015-07-14 13:24       ` [PATCH v3 5/9] grep/pcre: prepare locale-dependent tables for icase matching Nguyễn Thái Ngọc Duy
2015-07-14 13:24       ` [PATCH v3 6/9] gettext: add is_utf8_locale() Nguyễn Thái Ngọc Duy
2015-07-14 13:24       ` [PATCH v3 7/9] grep/pcre: support utf-8 Nguyễn Thái Ngọc Duy
2015-07-14 13:24       ` [PATCH v3 8/9] diffcore-pickaxe: "share" regex error handling code Nguyễn Thái Ngọc Duy
2015-07-14 13:24       ` [PATCH v3 9/9] diffcore-pickaxe: support case insensitive match on non-ascii Nguyễn Thái Ngọc Duy
2015-07-14 16:42       ` [PATCH v3 0/9] icase " Torsten Bögershausen
2015-07-15  9:39         ` Duy Nguyen
2015-07-15 19:51           ` Torsten Bögershausen
2015-08-21 12:47       ` Nguyễn Thái Ngọc Duy [this message]
2015-08-21 12:47         ` [PATCH v4 01/10] grep: allow -F -i combination Nguyễn Thái Ngọc Duy
2015-08-21 12:47         ` [PATCH v4 02/10] grep: break down an "if" stmt in preparation for next changes Nguyễn Thái Ngọc Duy
2015-08-21 12:47         ` [PATCH v4 03/10] test-regex: expose full regcomp() to the command line Nguyễn Thái Ngọc Duy
2015-08-21 12:47         ` [PATCH v4 04/10] grep/icase: avoid kwsset on literal non-ascii strings Nguyễn Thái Ngọc Duy
2015-08-21 12:47         ` [PATCH v4 05/10] grep/icase: avoid kwsset when -F is specified Nguyễn Thái Ngọc Duy
2015-08-21 12:47         ` [PATCH v4 06/10] grep/pcre: prepare locale-dependent tables for icase matching Nguyễn Thái Ngọc Duy
2015-08-21 12:47         ` [PATCH v4 07/10] gettext: add is_utf8_locale() Nguyễn Thái Ngọc Duy
2015-08-21 12:47         ` [PATCH v4 08/10] grep/pcre: support utf-8 Nguyễn Thái Ngọc Duy
2015-08-21 12:47         ` [PATCH v4 09/10] diffcore-pickaxe: "share" regex error handling code Nguyễn Thái Ngọc Duy
2015-08-21 12:47         ` [PATCH v4 10/10] diffcore-pickaxe: support case insensitive match on non-ascii Nguyễn Thái Ngọc Duy

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1440161240-28554-1-git-send-email-pclouds@gmail.com \
    --to=pclouds@gmail.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=l.s.r@web.de \
    --cc=plamen.totev@abv.bg \
    --cc=sunshine@sunshineco.com \
    --cc=tboegi@web.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).