grep/icase: avoid kwsset on literal non-ascii strings
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>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
diff --git a/grep.c b/grep.c
index f430d7e..451275d 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 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;
