Merge branch 'nd/icase'

"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

1 files changed, 57 insertions, 7 deletions

diff --git a/grep.c b/grep.c
index 1e15b62..394c856 100644
--- a/grep.c
+++ b/grep.c
@@ -4,6 +4,8 @@
 #include "xdiff-interface.h"
 #include "diff.h"
 #include "diffcore.h"
+#include "commit.h"
+#include "quote.h"
 
 static int grep_source_load(struct grep_source *gs);
 static int grep_source_is_binary(struct grep_source *gs);
@@ -322,11 +324,16 @@ 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;
+	}
+	if (is_utf8_locale() && has_non_ascii(p->pattern))
+		options |= PCRE_UTF8;
 
 	p->pcre_regexp = pcre_compile(p->pattern, options, &error, &erroffset,
-			NULL);
+				      p->pcre_tables);
 	if (!p->pcre_regexp)
 		compile_regexp_failed(p, error);
 
@@ -360,6 +367,7 @@ 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)
@@ -396,26 +404,68 @@ static int is_fixed(const char *s, size_t len)
 	return 1;
 }
 
+static void compile_fixed_regexp(struct grep_pat *p, struct grep_opt *opt)
+{
+	struct strbuf sb = STRBUF_INIT;
+	int err;
+	int regflags;
+
+	basic_regex_quote_buf(&sb, p->pattern);
+	regflags = opt->regflags & ~REG_EXTENDED;
+	if (opt->ignore_case)
+		regflags |= REG_ICASE;
+	err = regcomp(&p->regexp, sb.buf, regflags);
+	if (opt->debug)
+		fprintf(stderr, "fixed %s\n", sb.buf);
+	strbuf_release(&sb);
+	if (err) {
+		char errbuf[1024];
+		regerror(err, &p->regexp, errbuf, sizeof(errbuf));
+		regfree(&p->regexp);
+		compile_regexp_failed(p, errbuf);
+	}
+}
+
 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);
 
+	/*
+	 * Even when -F (fixed) asks us to do a non-regexp search, we
+	 * may not be able to correctly case-fold when -i
+	 * (ignore-case) is asked (in which case, we'll synthesize a
+	 * regexp to match the pattern that matches regexp special
+	 * characters literally, while ignoring case differences).  On
+	 * the other hand, even without -F, if the pattern does not
+	 * have any regexp special characters and there is no need for
+	 * case-folding search, we can internally turn it into a
+	 * simple string match using kws.  p->fixed tells us if we
+	 * want to use kws.
+	 */
 	if (opt->fixed || is_fixed(p->pattern, p->patternlen))
-		p->fixed = 1;
+		p->fixed = !icase || ascii_only;
 	else
 		p->fixed = 0;
 
 	if (p->fixed) {
-		if (opt->regflags & REG_ICASE || p->ignore_case)
-			p->kws = kwsalloc(tolower_trans_tbl);
-		else
-			p->kws = kwsalloc(NULL);
+		p->kws = kwsalloc(icase ? tolower_trans_tbl : NULL);
 		kwsincr(p->kws, p->pattern, p->patternlen);
 		kwsprep(p->kws);
 		return;
+	} else if (opt->fixed) {
+		/*
+		 * We come here when the pattern has the non-ascii
+		 * characters we cannot case-fold, and asked to
+		 * ignore-case.
+		 */
+		compile_fixed_regexp(p, opt);
+		return;
 	}
 
 	if (opt->pcre) {