[PATCH v2 11/12] diffcore-pickaxe: support case insensitive match on non-ascii

From: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
Date: Jun 25, 2016, 05:22 UTC
Message-ID: <20160625052238.13615-12-pclouds@gmail.com>
In-Reply-To: <20160625052238.13615-1-pclouds@gmail.com>

Similar to the "grep -F -i" case, we can't use kws on icase search outside ascii range, so we quote the string and pass it to regcomp as a basic regexp and let regex engine deal with case sensitivity.

The new test is put in t7812 instead of t4209-log-pickaxe because lib-gettext.sh might cause problems elsewhere, probably.

Noticed-by: Plamen Totev <plamen.totev@abv.bg>
Signed-off-by: Nguyễn Thái Ngọc Duy <pclouds@gmail.com>
---
 diffcore-pickaxe.c              | 11 +++++++++++
 t/t7812-grep-icase-non-ascii.sh |  7 +++++++
 2 files changed, 18 insertions(+)

diff --git a/diffcore-pickaxe.c b/diffcore-pickaxe.c
index 2093b6a..55067ca 100644
--- a/diffcore-pickaxe.c
+++ b/diffcore-pickaxe.c
@@ -7,6 +7,8 @@
 #include "diffcore.h"
 #include "xdiff-interface.h"
 #include "kwset.h"
+#include "commit.h"
+#include "quote.h"
 
 typedef int (*pickaxe_fn)(mmfile_t *one, mmfile_t *two,
 			  struct diff_options *o,
@@ -223,6 +225,15 @@ void diffcore_pickaxe(struct diff_options *o)
 			cflags |= REG_ICASE;
 		regcomp_or_die(&regex, needle, cflags);
 		regexp = &regex;
+	} else if (DIFF_OPT_TST(o, PICKAXE_IGNORE_CASE) &&
+		   has_non_ascii(needle)) {
+		struct strbuf sb = STRBUF_INIT;
+		int cflags = REG_NEWLINE | REG_ICASE;
+
+		basic_regex_quote_buf(&sb, needle);
+		regcomp_or_die(&regex, sb.buf, cflags);
+		strbuf_release(&sb);
+		regexp = &regex;
 	} else {
 		kws = kwsalloc(DIFF_OPT_TST(o, PICKAXE_IGNORE_CASE)
 			       ? tolower_trans_tbl : NULL);
diff --git a/t/t7812-grep-icase-non-ascii.sh b/t/t7812-grep-icase-non-ascii.sh
index 08ae4c9..169fd8d 100755
--- a/t/t7812-grep-icase-non-ascii.sh
+++ b/t/t7812-grep-icase-non-ascii.sh
@@ -61,4 +61,11 @@ test_expect_success REGEX_LOCALE 'grep string with regex, with -F' '
 	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

-- 
2.8.2.526.g02eed6d