[PATCH v5 06/10] grep/pcre: prepare locale-dependent tables for icase matching

[Nguyễn Thái Ngọc Duy]

The default tables are usually built with C locale and only suitable
for LANG=C or similar.  This should make case insensitive search work
correctly for all single-byte charsets.

Signed-off-by: Nguyễn Thái Ngọc Duy <pclo...@gmail.com>
---
 grep.c                             |  8 ++++++--
 grep.h                             |  1 +
 t/t7813-grep-icase-iso.sh (new +x) | 19 +++++++++++++++++++
 3 files changed, 26 insertions(+), 2 deletions(-)
 create mode 100755 t/t7813-grep-icase-iso.sh

diff --git a/grep.c b/grep.c
index fa96a29..921339a 100644
--- a/grep.c
+++ b/grep.c
@@ -324,11 +324,14 @@ static void compile_pcre_regexp(struct grep_pat *p, const 
struct grep_opt *opt)
        int erroffset;
        int options = PCRE_MULTILINE;
 
-       if (opt->ignore_case)
+       if (opt->ignore_case) {
+               if (has_non_ascii(p->pattern))
+                       p->pcre_tables = pcre_maketables();
                options |= PCRE_CASELESS;
+       }
 
        p->pcre_regexp = pcre_compile(p->pattern, options, &error, &erroffset,
-                       NULL);
+                                     p->pcre_tables);
        if (!p->pcre_regexp)
                compile_regexp_failed(p, error);
 
@@ -362,6 +365,7 @@ static void free_pcre_regexp(struct grep_pat *p)
 {
        pcre_free(p->pcre_regexp);
        pcre_free(p->pcre_extra_info);
+       pcre_free((void *)p->pcre_tables);
 }
 #else /* !USE_LIBPCRE */
 static void compile_pcre_regexp(struct grep_pat *p, const struct grep_opt *opt)
diff --git a/grep.h b/grep.h
index 95f197a..cee4357 100644
--- a/grep.h
+++ b/grep.h
@@ -48,6 +48,7 @@ struct grep_pat {
        regex_t regexp;
        pcre *pcre_regexp;
        pcre_extra *pcre_extra_info;
+       const unsigned char *pcre_tables;
        kwset_t kws;
        unsigned fixed:1;
        unsigned ignore_case:1;
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: Hall� 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.ll� Heimur!" &&
+       git grep --perl-regexp -i "TILRAUN: H.LL� HEIMUR!"
+'
+
+test_done
-- 
2.7.0.288.g1d8ad15

--
To unsubscribe from this list: send the line "unsubscribe git" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html