1 files changed, 111 insertions, 0 deletions
diff --git a/src/backend/utils/mb/Unicode/UCS_to_UHC.pl b/src/backend/utils/mb/Unicode/UCS_to_UHC.pl
new file mode 100644
index 0000000000..626c7c50f0
--- /dev/null
+++ b/src/backend/utils/mb/Unicode/UCS_to_UHC.pl
@@ -0,0 +1,111 @@
+#! /usr/bin/perl
+#
+# Copyright 2001 by PostgreSQL Global Development Group
+#
+# $Id: UCS_to_UHC.pl,v 1.1 2002/03/06 06:12:55 momjian Exp $
+#
+# Generate UTF-8 <--> BIG5 code conversion tables from
+# map files provided by Unicode organization.
+# Unfortunately it is prohibited by the organization
+# to distribute the map files. So if you try to use this script,
+# you have to obtain OLD5601.TXT from 
+# the organization's ftp site.
+#
+# CP949.TXT format:
+#		 UHC code in hex
+#		 UCS-2 code in hex
+#		 # and Unicode name (not used in this script)
+
+require "ucs2utf.pl";
+
+# first generate UTF-8 --> WIN949 table
+
+$in_file = "CP949.TXT";
+
+open( FILE, $in_file ) || die( "cannot open $in_file" );
+
+while( <FILE> ){
+	chop;
+	if( /^#/ ){
+		next;
+	}
+	( $c, $u, $rest ) = split;
+	$ucs = hex($u);
+	$code = hex($c);
+	if( $code >= 0x80 && $ucs >= 0x0080 ){
+		$utf = &ucs2utf($ucs);
+		if( $array{ $utf } ne "" ){
+			printf STDERR "Warning: duplicate unicode: %04x\n",$ucs;
+			next;
+		}
+		$count++;
+
+		$array{ $utf } = $code;
+	}
+}
+close( FILE );
+
+#
+# first, generate UTF8 --> UHC table
+#
+
+$file = "utf8_to_uhc.map";
+open( FILE, "> $file" ) || die( "cannot open $file" );
+print FILE "static pg_utf_to_local ULmapUHC[ $count ] = {\n";
+
+for $index ( sort {$a <=> $b} keys( %array ) ){
+	$code = $array{ $index };
+	$count--;
+	if( $count == 0 ){
+		printf FILE "  {0x%04x, 0x%04x}\n", $index, $code;
+	} else {
+		printf FILE "  {0x%04x, 0x%04x},\n", $index, $code;
+	}
+}
+
+print FILE "};\n";
+close(FILE);
+
+#
+# then generate UHC --> UTF8 table
+#
+reset 'array';
+
+open( FILE, $in_file ) || die( "cannot open $in_file" );
+
+while( <FILE> ){
+	chop;
+	if( /^#/ ){
+		next;
+	}
+	( $c, $u, $rest ) = split;
+	$ucs = hex($u);
+	$code = hex($c);
+	if( $code >= 0x80 && $ucs >= 0x0080 ){
+		$utf = &ucs2utf($ucs);
+		if( $array{ $code } ne "" ){
+			printf STDERR "Warning: duplicate code: %04x\n",$ucs;
+			next;
+		}
+		$count++;
+
+		$array{ $code } = $utf;
+	}
+}
+close( FILE );
+
+$file = "uhc_to_utf8.map";
+open( FILE, "> $file" ) || die( "cannot open $file" );
+print FILE "static pg_local_to_utf LUmapUHC[ $count ] = {\n";
+for $index ( sort {$a <=> $b} keys( %array ) ){
+	$utf = $array{ $index };
+	$count--;
+	if( $count == 0 ){
+		printf FILE "  {0x%04x, 0x%04x}\n", $index, $utf;
+	} else {
+		printf FILE "  {0x%04x, 0x%04x},\n", $index, $utf;
+	}
+}
+
+print FILE "};\n";
+close(FILE);