Merge branch 'nd/icase' into maint

"git grep -i" has been taught to fold case in non-ascii locales
correctly.

* nd/icase:
  grep.c: reuse "icase" variable
  diffcore-pickaxe: support case insensitive match on non-ascii
  diffcore-pickaxe: Add regcomp_or_die()
  grep/pcre: support utf-8
  gettext: add is_utf8_locale()
  grep/pcre: prepare locale-dependent tables for icase matching
  grep: rewrite an if/else condition to avoid duplicate expression
  grep/icase: avoid kwsset when -F is specified
  grep/icase: avoid kwsset on literal non-ascii strings
  test-regex: expose full regcomp() to the command line
  test-regex: isolate the bug test code
  grep: break down an "if" stmt in preparation for next changes

4 files changed, 148 insertions, 3 deletions

diff --git a/t/helper/test-regex.c b/t/helper/test-regex.c
index 0dc598e..eff26f5 100644
--- a/t/helper/test-regex.c
+++ b/t/helper/test-regex.c
@@ -1,6 +1,23 @@
 #include "git-compat-util.h"
+#include "gettext.h"
 
-int main(int argc, char **argv)
+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 }
+};
+
+static int test_regex_bug(void)
 {
 	char *pat = "[^={} \t]+";
 	char *str = "={}\nfred";
@@ -16,5 +33,43 @@ int main(int argc, char **argv)
 	if (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;
+}
+
+int main(int argc, char **argv)
+{
+	const char *pat;
+	const char *str;
+	int flags = 0;
+	regex_t r;
+	regmatch_t m[1];
+
+	if (argc == 2 && !strcmp(argv[1], "--bug"))
+		return test_regex_bug();
+	else if (argc < 3)
+		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++;
+	}
+	git_setup_gettext();
+
+	if (regcomp(&r, pat, flags))
+		die("failed regcomp() for pattern '%s'", pat);
+	if (regexec(&r, str, 1, m, 0))
+		return 1;
+
+	return 0;
 }
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
new file mode 100755
index 0000000..169fd8d
--- /dev/null
+++ b/t/t7812-grep-icase-non-ascii.sh
@@ -0,0 +1,71 @@
+#!/bin/sh
+
+test_description='grep icase on non-English locales'
+
+. ./lib-gettext.sh
+
+test_expect_success GETTEXT_LOCALE 'setup' '
+	test_write_lines "TILRAUN: Halló Heimur!" >file &&
+	git add file &&
+	LC_ALL="$is_IS_locale" &&
+	export LC_ALL
+'
+
+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!"
+'
+
+test_expect_success GETTEXT_LOCALE,LIBPCRE 'grep pcre utf-8 icase' '
+	git grep --perl-regexp    "TILRAUN: H.lló Heimur!" &&
+	git grep --perl-regexp -i "TILRAUN: H.lló Heimur!" &&
+	git grep --perl-regexp -i "TILRAUN: H.LLÓ HEIMUR!"
+'
+
+test_expect_success GETTEXT_LOCALE,LIBPCRE 'grep pcre utf-8 string with "+"' '
+	test_write_lines "TILRAUN: Hallóó Heimur!" >file2 &&
+	git add file2 &&
+	git grep -l --perl-regexp "TILRAUN: H.lló+ Heimur!" >actual &&
+	echo file >expected &&
+	echo file2 >>expected &&
+	test_cmp expected actual
+'
+
+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 &&
+	test_write_lines "fixed TILRAUN: Halló Heimur!" >expect1 &&
+	test_cmp expect1 debug1 &&
+
+	git grep --debug -i -F "TILRAUN: HALLÓ HEIMUR!"  2>&1 >/dev/null |
+		 grep fixed >debug2 &&
+	test_write_lines "fixed TILRAUN: HALLÓ HEIMUR!" >expect2 &&
+	test_cmp expect2 debug2
+'
+
+test_expect_success REGEX_LOCALE 'grep string with regex, with -F' '
+	test_write_lines "^*TILR^AUN:.* \\Halló \$He[]imur!\$" >file &&
+
+	git grep --debug -i -F "^*TILR^AUN:.* \\Halló \$He[]imur!\$" 2>&1 >/dev/null |
+		 grep fixed >debug1 &&
+	test_write_lines "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 &&
+	test_write_lines "fixed \\^*TILR^AUN:\\.\\* \\\\HALLÓ \$HE\\[]IMUR!\\\$" >expect2 &&
+	test_cmp expect2 debug2
+'
+
+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 &&
+	test_cmp expected actual
+'
+
+test_done
diff --git a/t/t7813-grep-icase-iso.sh b/t/t7813-grep-icase-iso.sh
new file mode 100755
index 0000000..efef7fb
--- /dev/null
+++ b/t/t7813-grep-icase-iso.sh
@@ -0,0 +1,19 @@
+#!/bin/sh
+
+test_description='grep icase on non-English locales'
+
+. ./lib-gettext.sh
+
+test_expect_success GETTEXT_ISO_LOCALE 'setup' '
+	printf "TILRAUN: Halló Heimur!" >file &&
+	git add file &&
+	LC_ALL="$is_IS_iso_locale" &&
+	export LC_ALL
+'
+
+test_expect_success GETTEXT_ISO_LOCALE,LIBPCRE 'grep pcre string' '
+	git grep --perl-regexp -i "TILRAUN: H.lló Heimur!" &&
+	git grep --perl-regexp -i "TILRAUN: H.LLÓ HEIMUR!"
+'
+
+test_done