From: t-ishii@sra.co.jp

Included are patches intended for allowing PostgreSQL to handle
multi-byte charachter sets such as EUC(Extende Unix Code), Unicode and
Mule internal code. With the MB patch you can use multi-byte character
sets in regexp and LIKE. The encoding system chosen is determined at
the compile time.

To enable the MB extension, you need to define a variable "MB" in
Makefile.global or in Makefile.custom. For further information please
take a look at README.mb under doc directory.

(Note that unlike "jp patch" I do not use modified GNU regexp any
more. I changed Henry Spencer's regexp coming with PostgreSQL.)

1 files changed, 23 insertions, 2 deletions

diff --git a/src/backend/regex/regexec.c b/src/backend/regex/regexec.c
index e3ac5cd0644..8a51810a203 100644
--- a/src/backend/regex/regexec.c
+++ b/src/backend/regex/regexec.c
@@ -164,6 +164,11 @@ int			eflags;
 {
 	struct re_guts *g = preg->re_g;
 
+#ifdef MB
+	pg_wchar *str;
+	int sts;
+#endif
+
 #ifdef REDEBUG
 #define  GOODFLAGS(f)	 (f)
 #else
@@ -177,8 +182,24 @@ int			eflags;
 		return (REG_BADPAT);
 	eflags = GOODFLAGS(eflags);
 
+#ifdef MB
+	str = (pg_wchar *)malloc((strlen(string)+1) * sizeof(pg_wchar));
+	if (!str) {
+	  return(REG_ESPACE);
+	}
+	(void)pg_mb2wchar((unsigned char *)string,str);
 	if (g->nstates <= CHAR_BIT * sizeof(states1) && !(eflags & REG_LARGE))
-		return (smatcher(g, (char *) string, nmatch, pmatch, eflags));
+	  sts = smatcher(g, str, nmatch, pmatch, eflags);
 	else
-		return (lmatcher(g, (char *) string, nmatch, pmatch, eflags));
+	  sts = lmatcher(g, str, nmatch, pmatch, eflags);
+	free((char *)str);
+	return(sts);
+
+#  else
+
+	if (g->nstates <= CHAR_BIT * sizeof(states1) && !(eflags & REG_LARGE))
+		return (smatcher(g, (pg_wchar *) string, nmatch, pmatch, eflags));
+	else
+		return (lmatcher(g, (pg_wchar *) string, nmatch, pmatch, eflags));
+#endif
 }