[PATCH v7 05/12] grep/icase: avoid kwsset on literal non-ascii strings

From: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Date: Feb 14, 2016, 11:49 UTC
Message-ID: <1455450596-11904-6-git-send-email-pclouds@gmail.com>
In-Reply-To: <1455450596-11904-1-git-send-email-pclouds@gmail.com>

When we detect the pattern is just a literal string, we avoid heavy regex engine and use fast substring search implemented in kwsset.c. But kws uses git-ctype which is locale-independent so it does not know how to fold case properly outside ascii range. Let regcomp or pcre take care of this case instead. Slower, but accurate.

Noticed-by: Plamen Totev <plamen.totev@abv.bg>
Helped-by: René Scharfe <l.s.r@web.de>
Helped-by: Eric Sunshine <sunshine@sunshineco.com>
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 grep.c                                   |  7 ++++++-
 t/t7812-grep-icase-non-ascii.sh (new +x) | 23 +++++++++++++++++++++++
 2 files changed, 29 insertions(+), 1 deletion(-)
 create mode 100755 t/t7812-grep-icase-non-ascii.sh

diff --git a/grep.c b/grep.c
index 609f218..f192727 100644
--- a/grep.c
+++ b/grep.c
@@ -4,6 +4,7 @@
 #include "xdiff-interface.h"
 #include "diff.h"
 #include "diffcore.h"
+#include "commit.h"
 
 static int grep_source_load(struct grep_source *gs);
 static int grep_source_is_binary(struct grep_source *gs);
@@ -398,14 +399,18 @@ static int is_fixed(const char *s, size_t len)
 
 static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
 {
+	int icase, ascii_only;
 	int err;
 
 	p->word_regexp = opt->word_regexp;
 	p->ignore_case = opt->ignore_case;
+	icase	       = opt->regflags & REG_ICASE || p->ignore_case;
+	ascii_only     = !has_non_ascii(p->pattern);
 
 	if (opt->fixed) {
 		p->fixed = 1;
-	} else if (is_fixed(p->pattern, p->patternlen))
+	} else if ((!icase || ascii_only) &&
+		   is_fixed(p->pattern, p->patternlen))
 		p->fixed = 1;
 	else
 		p->fixed = 0;
diff --git a/t/t7812-grep-icase-non-ascii.sh b/t/t7812-grep-icase-non-ascii.sh
new file mode 100755
index 0000000..6eff490
--- /dev/null
+++ b/t/t7812-grep-icase-non-ascii.sh
@@ -0,0 +1,23 @@
+#!/bin/sh
+
+test_description='grep icase on non-English locales'
+
+. ./lib-gettext.sh
+
+test_expect_success GETTEXT_LOCALE 'setup' '
+	printf "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_done

-- 
2.7.0.377.g4cd97dd