From 661ecf3c48e16a9add216287eb969d7615e47968 Mon Sep 17 00:00:00 2001
From: Marc G. Fournier
Date: Sun, 15 Mar 1998 07:39:04 +0000
Subject: 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.)
---
 src/backend/regex/utftest.c | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)
 create mode 100644 src/backend/regex/utftest.c

(limited to 'src/backend/regex/utftest.c')

diff --git a/src/backend/regex/utftest.c b/src/backend/regex/utftest.c
new file mode 100644
index 00000000000..28baf7255ef
--- /dev/null
+++ b/src/backend/regex/utftest.c
@@ -0,0 +1,33 @@
+/*
+ * testing of utf2wchar()
+ * $Id: utftest.c,v 1.1 1998/03/15 07:38:37 scrappy Exp $
+ */
+#include <regex/regex.h>
+#include <regex/utils.h>
+#include <regex/regex2.h>
+
+#include <regex/pg_wchar.h>
+
+main()
+{
+  /* Example 1 from RFC2044 */
+  char utf1[] = {0x41,0xe2,0x89,0xa2,0xce,0x91,0x2e,0};
+  /* Example 2 from RFC2044 */
+  char utf2[] = {0x48,0x69,0x20,0x4d,0x6f,0x6d,0x20,0xe2,0x98,0xba,0x21,0};
+  /* Example 3 from RFC2044 */
+  char utf3[] = {0xe6,0x97,0xa5,0xe6,0x9c,0xac,0xe8,0xaa,0x9e,0};
+  char *utf[] = {utf1,utf2,utf3};
+  pg_wchar ucs[128];
+  pg_wchar *p;
+  int i;
+
+  for (i=0;i<sizeof(utf)/sizeof(char *);i++) {
+    pg_utf2wchar(utf[i],ucs);
+    p = ucs;
+    while(*p) {
+      printf("%04x ",*p);
+      p++;
+    }
+    printf("\n");
+  }
+}
-- 
cgit v1.2.3