[PATCH v6 00/11] Fix icase grep on non-ascii

From

Nguyễn Thái Ngọc Duy <pclouds@gmail.com>

Date

Feb 6, 2016, 02:02 UTC

Message-ID

<1454724190-14063-1-git-send-email-pclouds@gmail.com>

In-Reply-To

<1453982183-24124-1-git-send-email-pclouds@gmail.com>

diff --git a/grep.c b/grep.c
index 2e4f71d..aed4fe0 100644
--- a/grep.c
+++ b/grep.c
@@ -412,11 +412,11 @@ static void compile_fixed_regexp(struct grep_pat *p, struct grep_opt *opt)
 	basic_regex_quote_buf(&sb, p->pattern);
 	err = regcomp(&p->regexp, sb.buf, opt->regflags & ~REG_EXTENDED);
 	if (opt->debug)
-		fprintf(stderr, "fixed%s\n", sb.buf);
+		fprintf(stderr, "fixed %s\n", sb.buf);
 	strbuf_release(&sb);
 	if (err) {
 		char errbuf[1024];
-		regerror(err, &p->regexp, errbuf, 1024);
+		regerror(err, &p->regexp, errbuf, sizeof(errbuf));
 		regfree(&p->regexp);
 		compile_regexp_failed(p, errbuf);
 	}
@@ -424,19 +424,18 @@ static void compile_fixed_regexp(struct grep_pat *p, struct grep_opt *opt)
 
 static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
 {
-	int icase_non_ascii;
+	int icase, ascii_only;
 	int err;
 
 	p->word_regexp = opt->word_regexp;
 	p->ignore_case = opt->ignore_case;
-	icase_non_ascii =
-		(opt->regflags & REG_ICASE || p->ignore_case) &&
-		has_non_ascii(p->pattern);
+	icase	       = opt->regflags & REG_ICASE || p->ignore_case;
+	ascii_only     = !has_non_ascii(p->pattern);
 
-	if (!icase_non_ascii && is_fixed(p->pattern, p->patternlen))
+	if ((!icase || ascii_only) && is_fixed(p->pattern, p->patternlen))
 		p->fixed = 1;
 	else if (opt->fixed) {
-		p->fixed = !icase_non_ascii;
+		p->fixed = !icase || ascii_only;
 		if (!p->fixed) {
 			compile_fixed_regexp(p, opt);
 			return;
diff --git a/t/t0070-fundamental.sh b/t/t0070-fundamental.sh
index 5ed69a6..991ed2a 100755
--- a/t/t0070-fundamental.sh
+++ b/t/t0070-fundamental.sh
@@ -31,7 +31,7 @@ test_expect_success 'git_mkstemps_mode does not fail if fd 0 is not open' '
 
 test_expect_success 'check for a bug in the regex routines' '
 	# if this test fails, re-build git with NO_REGEX=1
-	test-regex
+	test-regex --bug
 '
 
 test_done
diff --git a/t/t7812-grep-icase-non-ascii.sh b/t/t7812-grep-icase-non-ascii.sh
index a5475bb..4176625 100755
--- a/t/t7812-grep-icase-non-ascii.sh
+++ b/t/t7812-grep-icase-non-ascii.sh
@@ -38,12 +38,12 @@ test_expect_success GETTEXT_LOCALE,LIBPCRE 'grep pcre utf-8 string with "+"' '
 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 &&
+	echo "fixed TILRAUN: Halló Heimur!" >expect1 &&
 	test_cmp expect1 debug1 &&
 
 	git grep --debug -i -F "TILRAUN: HALLÓ HEIMUR!"  2>&1 >/dev/null |
 		 grep fixed >debug2 &&
-	echo "fixedTILRAUN: HALLÓ HEIMUR!" >expect2 &&
+	echo "fixed TILRAUN: HALLÓ HEIMUR!" >expect2 &&
 	test_cmp expect2 debug2
 '
 
@@ -52,12 +52,12 @@ test_expect_success REGEX_LOCALE 'grep string with regex, with -F' '
 
 	git grep --debug -i -F "^*TILR^AUN:.* \\Halló \$He[]imur!\$" 2>&1 >/dev/null |
 		 grep fixed >debug1 &&
-	echo "fixed\\^*TILR^AUN:\\.\\* \\\\Halló \$He\\[]imur!\\\$" >expect1 &&
+	echo "fixed \\^*TILR^AUN:\\.\\* \\\\Halló \$He\\[]imur!\\\$" >expect1 &&
 	test_cmp expect1 debug1 &&
 
 	git grep --debug -i -F "^*TILR^AUN:.* \\HALLÓ \$HE[]IMUR!\$"  2>&1 >/dev/null |
 		 grep fixed >debug2 &&
-	echo "fixed\\^*TILR^AUN:\\.\\* \\\\HALLÓ \$HE\\[]IMUR!\\\$" >expect2 &&
+	echo "fixed \\^*TILR^AUN:\\.\\* \\\\HALLÓ \$HE\\[]IMUR!\\\$" >expect2 &&
 	test_cmp expect2 debug2
 '
 
diff --git a/test-regex.c b/test-regex.c
index 3b5641c..d1a952c 100644
--- a/test-regex.c
+++ b/test-regex.c
@@ -17,6 +17,25 @@ static struct reg_flag reg_flags[] = {
 	{ NULL, 0 }
 };
 
+static int test_regex_bug(void)
+{
+	char *pat = "[^={} \t]+";
+	char *str = "={}\nfred";
+	regex_t r;
+	regmatch_t m[1];
+
+	if (regcomp(&r, pat, REG_EXTENDED | REG_NEWLINE))
+		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);
+
+	/* http://sourceware.org/bugzilla/show_bug.cgi?id=3957  */
+	if (m[0].rm_so == 3) /* matches '\n' when it should not */
+		die("regex bug confirmed: re-build git with NO_REGEX=1");
+
+	return 0;
+}
+
 int main(int argc, char **argv)
 {
 	const char *pat;
@@ -25,40 +44,32 @@ int main(int argc, char **argv)
 	regex_t r;
 	regmatch_t m[1];
 
-	if (argc == 1) {
-		/* special case, bug check */
-		pat = "[^={} \t]+";
-		str = "={}\nfred";
-		flags = REG_EXTENDED | REG_NEWLINE;
-	} else {
+	if (argc == 2 && !strcmp(argv[1], "--bug"))
+		return test_regex_bug();
+	else if (argc < 3)
+		die("usage: test-regex --bug\n"
+		    "       test-regex <pattern> <string> [<options>]");
+
+	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++;
-		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();
 	}
+	git_setup_gettext();
 
 	if (regcomp(&r, pat, flags))
 		die("failed regcomp() for pattern '%s'", pat);
-	if (regexec(&r, str, 1, m, 0)) {
-		if (argc == 1)
-			die("no match of pattern '%s' to string '%s'", pat, str);
+	if (regexec(&r, str, 1, m, 0))
 		return 1;
-	}
-
-	/* http://sourceware.org/bugzilla/show_bug.cgi?id=3957  */
-	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);
+	return 0;
 }

-- 
2.7.0.377.g4cd97dd