Add new encoding EUC_JIS_2004 and SHIFT_JIS_2004,

along with new conversions among EUC_JIS_2004, SHIFT_JIS_2004 and UTF-8.
catalog version has been bump up.

doc/src/sgml/charset.sgml

-<!-- $PostgreSQL: pgsql/doc/src/sgml/charset.sgml,v 2.81 2007/01/31 20:56:16 momjian Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/charset.sgml,v 2.82 2007/03/25 11:56:01 ishii Exp $ -->
 
 <chapter id="charset">
  <title>Localization</>
@@ -364,6 +364,14 @@ initdb --locale=sv_SE
          <entry>1-3</entry>
          <entry></entry>
         </row>
+        <row>
+         <entry><literal>EUC_JIS_2004</literal></entry>
+         <entry>Extended UNIX Code-JP, JIS X 0213</entry>
+         <entry>Japanese</entry>
+         <entry>Yes</entry>
+         <entry>1-3</entry>
+         <entry></entry>
+        </row>
         <row>
          <entry><literal>EUC_KR</literal></entry>
          <entry>Extended UNIX Code-KR</entry>
@@ -540,6 +548,14 @@ initdb --locale=sv_SE
          <entry>1-2</entry>
          <entry><literal>Mskanji</>, <literal>ShiftJIS</>, <literal>WIN932</>, <literal>Windows932</></entry>
         </row>
+        <row>
+         <entry><literal>SHIFT_JIS_2004</literal></entry>
+         <entry>Shift JIS, JIS X 0213</entry>
+         <entry>Japanese</entry>
+         <entry>No</entry>
+         <entry>1-2</entry>
+         <entry></entry>
+        </row>
         <row>
          <entry><literal>SQL_ASCII</literal></entry>
          <entry>unspecified (see text)</entry>

doc/src/sgml/func.sgml

-<!-- $PostgreSQL: pgsql/doc/src/sgml/func.sgml,v 1.370 2007/03/20 05:44:59 neilc Exp $ -->
+<!-- $PostgreSQL: pgsql/doc/src/sgml/func.sgml,v 1.371 2007/03/25 11:56:01 ishii Exp $ -->
 
  <chapter id="functions">
   <title>Functions and Operators</title>
@@ -2394,6 +2394,42 @@
        <entry><literal>UTF8</literal></entry>
       </row>
 
+      <row>
+       <entry><literal>euc_jis_2004_to_utf8</literal></entry>
+       <entry><literal>EUC_JIS_2004</literal></entry>
+       <entry><literal>UTF8</literal></entry>
+      </row>
+
+      <row>
+       <entry><literal>ut8_to_euc_jis_2004</literal></entry>
+       <entry><literal>UTF8</literal></entry>
+       <entry><literal>EUC_JIS_2004</literal></entry>
+      </row>
+
+      <row>
+       <entry><literal>shift_jis_2004_to_utf8</literal></entry>
+       <entry><literal>SHIFT_JIS_2004</literal></entry>
+       <entry><literal>UTF8</literal></entry>
+      </row>
+
+      <row>
+       <entry><literal>ut8_to_shift_jis_2004</literal></entry>
+       <entry><literal>UTF8</literal></entry>
+       <entry><literal>SHIFT_JIS_2004</literal></entry>
+      </row>
+
+      <row>
+       <entry><literal>euc_jis_2004_to_shift_jis_2004</literal></entry>
+       <entry><literal>EUC_JIS_2004</literal></entry>
+       <entry><literal>SHIFT_JIS_2004</literal></entry>
+      </row>
+
+      <row>
+       <entry><literal>shift_jis_2004_to_euc_jis_2004</literal></entry>
+       <entry><literal>SHIFT_JIS_2004</literal></entry>
+       <entry><literal>EUC_JIS_2004</literal></entry>
+      </row>
+
      </tbody>
     </tgroup>
    </table>

src/backend/utils/mb/Unicode/UCS_to_EUC_JIS_2004.pl

+#! /usr/bin/perl
+#
+# Copyright (c) 2007, PostgreSQL Global Development Group
+#
+# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_EUC_JIS_2004.pl,v 1.1 2007/03/25 11:56:02 ishii Exp $
+#
+# Generate UTF-8 <--> EUC_JIS_2004 code conversion tables from
+# "euc-jis-2004-std.txt" (http://x0213.org)
+
+require "ucs2utf.pl";
+
+$TEST = 1;
+
+# first generate UTF-8 --> EUC_JIS_2004 table
+
+$in_file = "euc-jis-2004-std.txt";
+
+open( FILE, $in_file ) || die( "cannot open $in_file" );
+
+reset 'array';
+reset 'array1';
+reset 'comment';
+reset 'comment1';
+
+while($line = <FILE> ){
+	if ($line =~ /^0x(.*)[ \t]*U\+(.*)\+(.*)[ \t]*#(.*)$/) {
+		$c = $1;
+		$u1 = $2;
+		$u2 = $3;
+		$rest = "U+" . $u1 . "+" . $u2 . $4;
+		$code = hex($c);
+		$ucs = hex($u1);
+		$utf1 = &ucs2utf($ucs);
+		$ucs = hex($u2);
+		$utf2 = &ucs2utf($ucs);
+		$str = sprintf "%08x%08x", $utf1, $utf2;
+		$array1{ $str } = $code;
+		$comment1{ $str } = $rest;
+		$count1++;
+		next;
+	} elsif ($line =~ /^0x(.*)[ \t]*U\+(.*)[ \t]*#(.*)$/) {
+		$c = $1;
+		$u = $2;
+		$rest = "U+" . $u . $3;
+	} else {
+		next;
+	}
+	
+	$ucs = hex($u);
+	$code = hex($c);
+	$utf = &ucs2utf($ucs);
+	if( $array{ $utf } ne "" ){
+		printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs;
+		next;
+	}
+	$count++;
+
+	$array{ $utf } = $code;
+	$comment{ $code } = $rest;
+}
+close( FILE );
+
+$file = "utf8_to_euc_jis_2004.map";
+open( FILE, "> $file" ) || die( "cannot open $file" );
+print FILE "/*\n";
+print FILE " * This file was generated by UCS_to_EUC_JIS_2004.pl\n";
+print FILE " */\n";
+print FILE "static pg_utf_to_local ULmapEUC_JIS_2004[] = {\n";
+
+for $index ( sort {$a <=> $b} keys( %array ) ){
+	$code = $array{ $index };
+	$count--;
+	if( $count == 0 ){
+		printf FILE "  {0x%08x, 0x%06x}	/* %s */\n", $index, $code, $comment{ $code };
+	} else {
+		printf FILE "  {0x%08x, 0x%06x},	/* %s */\n", $index, $code, $comment{ $code }; 
+	}
+}
+
+print FILE "};\n";
+close(FILE);
+
+if ($TEST == 1) {
+	$file1 = "utf8.data";
+	$file2 = "euc_jis_2004.data";
+	open( FILE1, "> $file1" ) || die( "cannot open $file1" );
+	open( FILE2, "> $file2" ) || die( "cannot open $file2" );
+
+	for $index ( sort {$a <=> $b} keys( %array ) ){
+		$code = $array{ $index };
+		if ($code > 0x00 && $code != 0x09 && $code != 0x0a && $code != 0x0d &&
+			$code != 0x5c &&
+			($code < 0x80 ||
+			 ($code >= 0x8ea1 && $code <= 0x8efe) ||
+			 ($code >= 0x8fa1a1 && $code <= 0x8ffefe) ||
+			 ($code >= 0xa1a1 && $code <= 0x8fefe))) {
+			for ($i = 3; $i >= 0; $i--) {
+				$s = $i * 8;
+				$mask = 0xff << $s;
+				print FILE1 pack("C", ($index & $mask) >> $s) if $index & $mask;
+				print FILE2 pack("C", ($code & $mask) >> $s) if $code & $mask;
+			}
+			print FILE1 "\n";
+			print FILE2 "\n";
+		}
+	}
+}
+
+$file = "utf8_to_euc_jis_2004_combined.map";
+open( FILE, "> $file" ) || die( "cannot open $file" );
+print FILE "/*\n";
+print FILE " * This file was generated by UCS_to_EUC_JIS_2004.pl\n";
+print FILE " */\n";
+print FILE "static pg_utf_to_local_combined ULmapEUC_JIS_2004_combined[] = {\n";
+
+for $index ( sort {$a cmp $b} keys( %array1 ) ){
+	$code = $array1{ $index };
+	$count1--;
+	if( $count1 == 0 ){
+		printf FILE "  {0x%s, 0x%s, 0x%06x}	/* %s */\n", substr($index, 0, 8), substr($index, 8, 8), $code, $comment1{ $index };
+	} else {
+		printf FILE "  {0x%s, 0x%s, 0x%06x},	/* %s */\n", substr($index, 0, 8), substr($index, 8, 8), $code, $comment1{ $index };
+	}
+}
+
+print FILE "};\n";
+close(FILE);
+
+if ($TEST == 1) {
+	for $index ( sort {$a cmp $b} keys( %array1 ) ){
+		$code = $array1{ $index };
+		if ($code > 0x00 && $code != 0x09 && $code != 0x0a && $code != 0x0d &&
+			$code != 0x5c &&
+			($code < 0x80 ||
+			 ($code >= 0x8ea1 && $code <= 0x8efe) ||
+			 ($code >= 0x8fa1a1 && $code <= 0x8ffefe) ||
+			 ($code >= 0xa1a1 && $code <= 0x8fefe))) {
+			
+			$v1 = hex(substr($index, 0, 8));
+			$v2 = hex(substr($index, 8, 8));
+
+			for ($i = 3; $i >= 0; $i--) {
+				$s = $i * 8;
+				$mask = 0xff << $s;
+				print FILE1 pack("C", ($v1 & $mask) >> $s) if $v1 & $mask;
+				print FILE2 pack("C", ($code & $mask) >> $s) if $code & $mask;
+			}
+			for ($i = 3; $i >= 0; $i--) {
+				$s = $i * 8;
+				$mask = 0xff << $s;
+				print FILE1 pack("C", ($v2 & $mask) >> $s) if $v2 & $mask;
+			}
+			print FILE1 "\n";
+			print FILE2 "\n";
+		}
+	}
+	close(FILE1);
+	close(FILE2);
+}
+
+# then generate EUC_JIS_2004 --> UTF-8 table
+
+$in_file = "euc-jis-2004-std.txt";
+
+open( FILE, $in_file ) || die( "cannot open $in_file" );
+
+reset 'array';
+reset 'array1';
+reset 'comment';
+reset 'comment1';
+
+while($line = <FILE> ){
+	if ($line =~ /^0x(.*)[ \t]*U\+(.*)\+(.*)[ \t]*#(.*)$/) {
+		$c = $1;
+		$u1 = $2;
+		$u2 = $3;
+		$rest = "U+" . $u1 . "+" . $u2 . $4;
+		$code = hex($c);
+		$ucs = hex($u1);
+		$utf1 = &ucs2utf($ucs);
+		$ucs = hex($u2);
+		$utf2 = &ucs2utf($ucs);
+		$str = sprintf "%08x%08x", $utf1, $utf2;
+		$array1{ $code } = $str;
+		$comment1{ $code } = $rest;
+		$count1++;
+		next;
+	} elsif ($line =~ /^0x(.*)[ \t]*U\+(.*)[ \t]*#(.*)$/) {
+		$c = $1;
+		$u = $2;
+		$rest = "U+" . $u . $3;
+	} else {
+		next;
+	}
+	
+	$ucs = hex($u);
+	$code = hex($c);
+	$utf = &ucs2utf($ucs);
+	if( $array{ $code } ne "" ){
+		printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs;
+		next;
+	}
+	$count++;
+
+	$array{ $code } = $utf;
+	$comment{ $utf } = $rest;
+}
+close( FILE );
+
+$file = "euc_jis_2004_to_utf8.map";
+open( FILE, "> $file" ) || die( "cannot open $file" );
+print FILE "/*\n";
+print FILE " * This file was generated by UCS_to_EUC_JIS_2004.pl\n";
+print FILE " */\n";
+print FILE "static pg_local_to_utf LUmapEUC_JIS_2004[] = {\n";
+
+for $index ( sort {$a <=> $b} keys( %array ) ){
+	$code = $array{ $index };
+	$count--;
+	if( $count == 0 ){
+		printf FILE "  {0x%06x, 0x%08x}	/* %s */\n", $index, $code, $comment{ $code };
+	} else {
+		printf FILE "  {0x%06x, 0x%08x},	/* %s */\n", $index, $code, $comment{ $code }; 
+	}
+}
+
+print FILE "};\n";
+close(FILE);
+
+$file = "euc_jis_2004_to_utf8_combined.map";
+open( FILE, "> $file" ) || die( "cannot open $file" );
+print FILE "/*\n";
+print FILE " * This file was generated by UCS_to_EUC_JIS_2004.pl\n";
+print FILE " */\n";
+print FILE "static pg_local_to_utf_combined LUmapEUC_JIS_2004_combined[] = {\n";
+
+for $index ( sort {$a <=> $b} keys( %array1 ) ){
+	$code = $array1{ $index };
+	$count1--;
+	if( $count1 == 0 ){
+		printf FILE "  {0x%06x, 0x%s, 0x%s}	/* %s */\n", $index, substr($code, 0, 8), substr($code, 8, 8), $comment1{ $index };
+	} else {
+		printf FILE "  {0x%06x, 0x%s, 0x%s},	/* %s */\n", $index, substr($code, 0, 8), substr($code, 8, 8), $comment1{ $index };
+	}
+}
+
+print FILE "};\n";
+close(FILE);

src/backend/utils/mb/Unicode/UCS_to_SHIFT_JIS_2004.pl

+#! /usr/bin/perl
+#
+# Copyright (c) 2007, PostgreSQL Global Development Group
+#
+# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_SHIFT_JIS_2004.pl,v 1.1 2007/03/25 11:56:02 ishii Exp $
+#
+# Generate UTF-8 <--> SHIFT_JIS_2004 code conversion tables from
+# "sjis-0213-2004-std.txt" (http://x0213.org)
+
+require "ucs2utf.pl";
+
+# first generate UTF-8 --> SHIFT_JIS_2004 table
+
+$in_file = "sjis-0213-2004-std.txt";
+
+open( FILE, $in_file ) || die( "cannot open $in_file" );
+
+reset 'array';
+reset 'array1';
+reset 'comment';
+reset 'comment1';
+
+while($line = <FILE> ){
+	if ($line =~ /^0x(.*)[ \t]*U\+(.*)\+(.*)[ \t]*#(.*)$/) {
+		$c = $1;
+		$u1 = $2;
+		$u2 = $3;
+		$rest = "U+" . $u1 . "+" . $u2 . $4;
+		$code = hex($c);
+		$ucs = hex($u1);
+		$utf1 = &ucs2utf($ucs);
+		$ucs = hex($u2);
+		$utf2 = &ucs2utf($ucs);
+		$str = sprintf "%08x%08x", $utf1, $utf2;
+		$array1{ $str } = $code;
+		$comment1{ $str } = $rest;
+		$count1++;
+		next;
+	} elsif ($line =~ /^0x(.*)[ \t]*U\+(.*)[ \t]*#(.*)$/) {
+		$c = $1;
+		$u = $2;
+		$rest = "U+" . $u . $3;
+	} else {
+		next;
+	}
+	
+	$ucs = hex($u);
+	$code = hex($c);
+	$utf = &ucs2utf($ucs);
+	if( $array{ $utf } ne "" ){
+		printf STDERR "Warning: duplicate UTF8: %08x UCS: %04x Shift JIS: %04x\n",$utf, $ucs, $code;
+		next;
+	}
+	$count++;
+
+	$array{ $utf } = $code;
+	$comment{ $code } = $rest;
+}
+close( FILE );
+
+$file = "utf8_to_shift_jis_2004.map";
+open( FILE, "> $file" ) || die( "cannot open $file" );
+print FILE "/*\n";
+print FILE " * This file was generated by UCS_to_SHIFT_JIS_2004.pl\n";
+print FILE " */\n";
+print FILE "static pg_utf_to_local ULmapSHIFT_JIS_2004[] = {\n";
+
+for $index ( sort {$a <=> $b} keys( %array ) ){
+	$code = $array{ $index };
+	$count--;
+	if( $count == 0 ){
+		printf FILE "  {0x%08x, 0x%06x}	/* %s */\n", $index, $code, $comment{ $code };
+	} else {
+		printf FILE "  {0x%08x, 0x%06x},	/* %s */\n", $index, $code, $comment{ $code }; 
+	}
+}
+
+print FILE "};\n";
+close(FILE);
+
+$file = "utf8_to_shift_jis_2004_combined.map";
+open( FILE, "> $file" ) || die( "cannot open $file" );
+print FILE "/*\n";
+print FILE " * This file was generated by UCS_to_SHIFT_JIS_2004.pl\n";
+print FILE " */\n";
+print FILE "static pg_utf_to_local_combined ULmapSHIFT_JIS_2004_combined[] = {\n";
+
+for $index ( sort {$a cmp $b} keys( %array1 ) ){
+	$code = $array1{ $index };
+	$count1--;
+	if( $count1 == 0 ){
+		printf FILE "  {0x%s, 0x%s, 0x%04x}	/* %s */\n", substr($index, 0, 8), substr($index, 8, 8), $code, $comment1{ $index };
+	} else {
+		printf FILE "  {0x%s, 0x%s, 0x%04x},	/* %s */\n", substr($index, 0, 8), substr($index, 8, 8), $code, $comment1{ $index };
+	}
+}
+
+print FILE "};\n";
+close(FILE);
+
+# then generate SHIFT_JIS_2004 --> UTF-8 table
+
+$in_file = "sjis-0213-2004-std.txt";
+
+open( FILE, $in_file ) || die( "cannot open $in_file" );
+
+reset 'array';
+reset 'array1';
+reset 'comment';
+reset 'comment1';
+
+while($line = <FILE> ){
+	if ($line =~ /^0x(.*)[ \t]*U\+(.*)\+(.*)[ \t]*#(.*)$/) {
+		$c = $1;
+		$u1 = $2;
+		$u2 = $3;
+		$rest = "U+" . $u1 . "+" . $u2 . $4;
+		$code = hex($c);
+		$ucs = hex($u1);
+		$utf1 = &ucs2utf($ucs);
+		$ucs = hex($u2);
+		$utf2 = &ucs2utf($ucs);
+		$str = sprintf "%08x%08x", $utf1, $utf2;
+		$array1{ $code } = $str;
+		$comment1{ $code } = $rest;
+		$count1++;
+		next;
+	} elsif ($line =~ /^0x(.*)[ \t]*U\+(.*)[ \t]*#(.*)$/) {
+		$c = $1;
+		$u = $2;
+		$rest = "U+" . $u . $3;
+	} else {
+		next;
+	}
+	
+	$ucs = hex($u);
+	$code = hex($c);
+	$utf = &ucs2utf($ucs);
+	if( $array{ $code } ne "" ){
+		printf STDERR "Warning: duplicate UTF-8: %08x UCS: %04x Shift JIS: %04x\n",$utf, $ucs, $code;
+		printf STDERR "Previous value: UTF-8: %08x\n", $array{ $utf };
+		next;
+	}
+	$count++;
+
+	$array{ $code } = $utf;
+	$comment{ $utf } = $rest;
+}
+close( FILE );
+
+$file = "shift_jis_2004_to_utf8.map";
+open( FILE, "> $file" ) || die( "cannot open $file" );
+print FILE "/*\n";
+print FILE " * This file was generated by UCS_to_SHIFTJIS_2004.pl\n";
+print FILE " */\n";
+print FILE "static pg_local_to_utf LUmapSHIFT_JIS_2004[] = {\n";
+
+for $index ( sort {$a <=> $b} keys( %array ) ){
+	$code = $array{ $index };
+	$count--;
+	if( $count == 0 ){
+		printf FILE "  {0x%04x, 0x%08x}	/* %s */\n", $index, $code, $comment{ $code };
+	} else {
+		printf FILE "  {0x%04x, 0x%08x},	/* %s */\n", $index, $code, $comment{ $code }; 
+	}
+}
+
+print FILE "};\n";
+close(FILE);
+
+$file = "shift_jis_2004_to_utf8_combined.map";
+open( FILE, "> $file" ) || die( "cannot open $file" );
+print FILE "/*\n";
+print FILE " * This file was generated by UCS_to_SHIFT_JIS_2004.pl\n";
+print FILE " */\n";
+print FILE "static pg_local_to_utf_combined LUmapSHIFT_JIS_2004_combined[] = {\n";
+
+for $index ( sort {$a <=> $b} keys( %array1 ) ){
+	$code = $array1{ $index };
+	$count1--;
+	if( $count1 == 0 ){
+		printf FILE "  {0x%04x, 0x%s, 0x%s}	/* %s */\n", $index, substr($code, 0, 8), substr($code, 8, 8), $comment1{ $index };
+	} else {
+		printf FILE "  {0x%04x, 0x%s, 0x%s},	/* %s */\n", $index, substr($code, 0, 8), substr($code, 8, 8), $comment1{ $index };
+	}
+}
+
+print FILE "};\n";
+close(FILE);

src/backend/utils/mb/Unicode/euc_jis_2004_to_utf8_combined.map

+/*
+ * This file was generated by UCS_to_EUC_JIS_2004.pl
+ */
+static pg_local_to_utf_combined LUmapEUC_JIS_2004_combined[] = {
+  {0x00a4f7, 0x00e3818b, 0x00e3829a},	/* U+304B+309A	 	[2000] */
+  {0x00a4f8, 0x00e3818d, 0x00e3829a},	/* U+304D+309A	 	[2000] */
+  {0x00a4f9, 0x00e3818f, 0x00e3829a},	/* U+304F+309A	 	[2000] */
+  {0x00a4fa, 0x00e38191, 0x00e3829a},	/* U+3051+309A	 	[2000] */
+  {0x00a4fb, 0x00e38193, 0x00e3829a},	/* U+3053+309A	 	[2000] */
+  {0x00a5f7, 0x00e382ab, 0x00e3829a},	/* U+30AB+309A	 	[2000] */
+  {0x00a5f8, 0x00e382ad, 0x00e3829a},	/* U+30AD+309A	 	[2000] */
+  {0x00a5f9, 0x00e382af, 0x00e3829a},	/* U+30AF+309A	 	[2000] */
+  {0x00a5fa, 0x00e382b1, 0x00e3829a},	/* U+30B1+309A	 	[2000] */
+  {0x00a5fb, 0x00e382b3, 0x00e3829a},	/* U+30B3+309A	 	[2000] */
+  {0x00a5fc, 0x00e382bb, 0x00e3829a},	/* U+30BB+309A	 	[2000] */
+  {0x00a5fd, 0x00e38384, 0x00e3829a},	/* U+30C4+309A	 	[2000] */
+  {0x00a5fe, 0x00e38388, 0x00e3829a},	/* U+30C8+309A	 	[2000] */
+  {0x00a6f8, 0x00e387b7, 0x00e3829a},	/* U+31F7+309A	 	[2000] */
+  {0x00abc4, 0x0000c3a6, 0x0000cc80},	/* U+00E6+0300	 	[2000] */
+  {0x00abc8, 0x0000c994, 0x0000cc80},	/* U+0254+0300	 	[2000] */
+  {0x00abc9, 0x0000c994, 0x0000cc81},	/* U+0254+0301	 	[2000] */
+  {0x00abca, 0x0000ca8c, 0x0000cc80},	/* U+028C+0300	 	[2000] */
+  {0x00abcb, 0x0000ca8c, 0x0000cc81},	/* U+028C+0301	 	[2000] */
+  {0x00abcc, 0x0000c999, 0x0000cc80},	/* U+0259+0300	 	[2000] */
+  {0x00abcd, 0x0000c999, 0x0000cc81},	/* U+0259+0301	 	[2000] */
+  {0x00abce, 0x0000c99a, 0x0000cc80},	/* U+025A+0300	 	[2000] */
+  {0x00abcf, 0x0000c99a, 0x0000cc81},	/* U+025A+0301	 	[2000] */
+  {0x00abe5, 0x0000cba9, 0x0000cba5},	/* U+02E9+02E5	 	[2000] */
+  {0x00abe6, 0x0000cba5, 0x0000cba9}	/* U+02E5+02E9	 	[2000] */
+};

src/backend/utils/mb/Unicode/shift_jis_2004_to_utf8_combined.map

+/*
+ * This file was generated by UCS_to_SHIFT_JIS_2004.pl
+ */
+static pg_local_to_utf_combined LUmapSHIFT_JIS_2004_combined[] = {
+  {0x82f5, 0x00e3818b, 0x00e3829a},	/* U+304B+309A	 	[2000] */
+  {0x82f6, 0x00e3818d, 0x00e3829a},	/* U+304D+309A	 	[2000] */
+  {0x82f7, 0x00e3818f, 0x00e3829a},	/* U+304F+309A	 	[2000] */
+  {0x82f8, 0x00e38191, 0x00e3829a},	/* U+3051+309A	 	[2000] */
+  {0x82f9, 0x00e38193, 0x00e3829a},	/* U+3053+309A	 	[2000] */
+  {0x8397, 0x00e382ab, 0x00e3829a},	/* U+30AB+309A	 	[2000] */
+  {0x8398, 0x00e382ad, 0x00e3829a},	/* U+30AD+309A	 	[2000] */
+  {0x8399, 0x00e382af, 0x00e3829a},	/* U+30AF+309A	 	[2000] */
+  {0x839a, 0x00e382b1, 0x00e3829a},	/* U+30B1+309A	 	[2000] */
+  {0x839b, 0x00e382b3, 0x00e3829a},	/* U+30B3+309A	 	[2000] */
+  {0x839c, 0x00e382bb, 0x00e3829a},	/* U+30BB+309A	 	[2000] */
+  {0x839d, 0x00e38384, 0x00e3829a},	/* U+30C4+309A	 	[2000] */
+  {0x839e, 0x00e38388, 0x00e3829a},	/* U+30C8+309A	 	[2000] */
+  {0x83f6, 0x00e387b7, 0x00e3829a},	/* U+31F7+309A	 	[2000] */
+  {0x8663, 0x0000c3a6, 0x0000cc80},	/* U+00E6+0300	 	[2000] */
+  {0x8667, 0x0000c994, 0x0000cc80},	/* U+0254+0300	 	[2000] */
+  {0x8668, 0x0000c994, 0x0000cc81},	/* U+0254+0301	 	[2000] */
+  {0x8669, 0x0000ca8c, 0x0000cc80},	/* U+028C+0300	 	[2000] */
+  {0x866a, 0x0000ca8c, 0x0000cc81},	/* U+028C+0301	 	[2000] */
+  {0x866b, 0x0000c999, 0x0000cc80},	/* U+0259+0300	 	[2000] */
+  {0x866c, 0x0000c999, 0x0000cc81},	/* U+0259+0301	 	[2000] */
+  {0x866d, 0x0000c99a, 0x0000cc80},	/* U+025A+0300	 	[2000] */
+  {0x866e, 0x0000c99a, 0x0000cc81},	/* U+025A+0301	 	[2000] */
+  {0x8685, 0x0000cba9, 0x0000cba5},	/* U+02E9+02E5	 	[2000] */
+  {0x8686, 0x0000cba5, 0x0000cba9}	/* U+02E5+02E9	 	[2000] */
+};

src/backend/utils/mb/Unicode/utf8_to_euc_jis_2004_combined.map

+/*
+ * This file was generated by UCS_to_EUC_JIS_2004.pl
+ */
+static pg_utf_to_local_combined ULmapEUC_JIS_2004_combined[] = {
+  {0x0000c3a6, 0x0000cc80, 0x00abc4},	/* U+00E6+0300	 	[2000] */
+  {0x0000c994, 0x0000cc80, 0x00abc8},	/* U+0254+0300	 	[2000] */
+  {0x0000c994, 0x0000cc81, 0x00abc9},	/* U+0254+0301	 	[2000] */
+  {0x0000c999, 0x0000cc80, 0x00abcc},	/* U+0259+0300	 	[2000] */
+  {0x0000c999, 0x0000cc81, 0x00abcd},	/* U+0259+0301	 	[2000] */
+  {0x0000c99a, 0x0000cc80, 0x00abce},	/* U+025A+0300	 	[2000] */
+  {0x0000c99a, 0x0000cc81, 0x00abcf},	/* U+025A+0301	 	[2000] */
+  {0x0000ca8c, 0x0000cc80, 0x00abca},	/* U+028C+0300	 	[2000] */
+  {0x0000ca8c, 0x0000cc81, 0x00abcb},	/* U+028C+0301	 	[2000] */
+  {0x0000cba5, 0x0000cba9, 0x00abe6},	/* U+02E5+02E9	 	[2000] */
+  {0x0000cba9, 0x0000cba5, 0x00abe5},	/* U+02E9+02E5	 	[2000] */
+  {0x00e3818b, 0x00e3829a, 0x00a4f7},	/* U+304B+309A	 	[2000] */
+  {0x00e3818d, 0x00e3829a, 0x00a4f8},	/* U+304D+309A	 	[2000] */
+  {0x00e3818f, 0x00e3829a, 0x00a4f9},	/* U+304F+309A	 	[2000] */
+  {0x00e38191, 0x00e3829a, 0x00a4fa},	/* U+3051+309A	 	[2000] */
+  {0x00e38193, 0x00e3829a, 0x00a4fb},	/* U+3053+309A	 	[2000] */
+  {0x00e382ab, 0x00e3829a, 0x00a5f7},	/* U+30AB+309A	 	[2000] */
+  {0x00e382ad, 0x00e3829a, 0x00a5f8},	/* U+30AD+309A	 	[2000] */
+  {0x00e382af, 0x00e3829a, 0x00a5f9},	/* U+30AF+309A	 	[2000] */
+  {0x00e382b1, 0x00e3829a, 0x00a5fa},	/* U+30B1+309A	 	[2000] */
+  {0x00e382b3, 0x00e3829a, 0x00a5fb},	/* U+30B3+309A	 	[2000] */
+  {0x00e382bb, 0x00e3829a, 0x00a5fc},	/* U+30BB+309A	 	[2000] */
+  {0x00e38384, 0x00e3829a, 0x00a5fd},	/* U+30C4+309A	 	[2000] */
+  {0x00e38388, 0x00e3829a, 0x00a5fe},	/* U+30C8+309A	 	[2000] */
+  {0x00e387b7, 0x00e3829a, 0x00a6f8}	/* U+31F7+309A	 	[2000] */
+};

src/backend/utils/mb/Unicode/utf8_to_shift_jis_2004_combined.map

+/*
+ * This file was generated by UCS_to_SHIFT_JIS_2004.pl
+ */
+static pg_utf_to_local_combined ULmapSHIFT_JIS_2004_combined[] = {
+  {0x0000c3a6, 0x0000cc80, 0x8663},	/* U+00E6+0300	 	[2000] */
+  {0x0000c994, 0x0000cc80, 0x8667},	/* U+0254+0300	 	[2000] */
+  {0x0000c994, 0x0000cc81, 0x8668},	/* U+0254+0301	 	[2000] */
+  {0x0000c999, 0x0000cc80, 0x866b},	/* U+0259+0300	 	[2000] */
+  {0x0000c999, 0x0000cc81, 0x866c},	/* U+0259+0301	 	[2000] */
+  {0x0000c99a, 0x0000cc80, 0x866d},	/* U+025A+0300	 	[2000] */
+  {0x0000c99a, 0x0000cc81, 0x866e},	/* U+025A+0301	 	[2000] */
+  {0x0000ca8c, 0x0000cc80, 0x8669},	/* U+028C+0300	 	[2000] */
+  {0x0000ca8c, 0x0000cc81, 0x866a},	/* U+028C+0301	 	[2000] */
+  {0x0000cba5, 0x0000cba9, 0x8686},	/* U+02E5+02E9	 	[2000] */
+  {0x0000cba9, 0x0000cba5, 0x8685},	/* U+02E9+02E5	 	[2000] */
+  {0x00e3818b, 0x00e3829a, 0x82f5},	/* U+304B+309A	 	[2000] */
+  {0x00e3818d, 0x00e3829a, 0x82f6},	/* U+304D+309A	 	[2000] */
+  {0x00e3818f, 0x00e3829a, 0x82f7},	/* U+304F+309A	 	[2000] */
+  {0x00e38191, 0x00e3829a, 0x82f8},	/* U+3051+309A	 	[2000] */
+  {0x00e38193, 0x00e3829a, 0x82f9},	/* U+3053+309A	 	[2000] */
+  {0x00e382ab, 0x00e3829a, 0x8397},	/* U+30AB+309A	 	[2000] */
+  {0x00e382ad, 0x00e3829a, 0x8398},	/* U+30AD+309A	 	[2000] */
+  {0x00e382af, 0x00e3829a, 0x8399},	/* U+30AF+309A	 	[2000] */
+  {0x00e382b1, 0x00e3829a, 0x839a},	/* U+30B1+309A	 	[2000] */
+  {0x00e382b3, 0x00e3829a, 0x839b},	/* U+30B3+309A	 	[2000] */
+  {0x00e382bb, 0x00e3829a, 0x839c},	/* U+30BB+309A	 	[2000] */
+  {0x00e38384, 0x00e3829a, 0x839d},	/* U+30C4+309A	 	[2000] */
+  {0x00e38388, 0x00e3829a, 0x839e},	/* U+30C8+309A	 	[2000] */
+  {0x00e387b7, 0x00e3829a, 0x83f6}	/* U+31F7+309A	 	[2000] */
+};

src/backend/utils/mb/conv.c

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/mb/conv.c,v 1.62 2007/01/05 22:19:44 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/mb/conv.c,v 1.63 2007/03/25 11:56:02 ishii Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -244,10 +244,10 @@ mic2latin_with_table(const unsigned char *mic,
 static int
 compare1(const void *p1, const void *p2)
 {
-	unsigned int v1,
+	uint32 v1,
 				v2;
 
-	v1 = *(unsigned int *) p1;
+	v1 = *(uint32 *) p1;
 	v2 = ((pg_utf_to_local *) p2)->utf;
 	return (v1 > v2) ? 1 : ((v1 == v2) ? 0 : -1);
 }
@@ -259,31 +259,86 @@ compare1(const void *p1, const void *p2)
 static int
 compare2(const void *p1, const void *p2)
 {
-	unsigned int v1,
+	uint32 v1,
 				v2;
 
-	v1 = *(unsigned int *) p1;
+	v1 = *(uint32 *) p1;
 	v2 = ((pg_local_to_utf *) p2)->code;
 	return (v1 > v2) ? 1 : ((v1 == v2) ? 0 : -1);
 }
 
+/*
+ * comparison routine for bsearch()
+ * this routine is intended for combined UTF8 -> local code
+ */
+static int
+compare3(const void *p1, const void *p2)
+{
+	uint32 s1, s2, d1, d2;
+
+	s1 = *(uint32 *)p1;
+	s2 = *((uint32 *)p1 + 1);
+	d1 = ((pg_utf_to_local_combined *) p2)->utf1;
+	d2 = ((pg_utf_to_local_combined *) p2)->utf2;
+	return (s1 > d1 || (s1 == d1 && s2 > d2)) ? 1 : ((s1 == d1 && s2 == d2) ? 0 : -1);
+}
+
+/*
+ * comparison routine for bsearch()
+ * this routine is intended for local code -> combined UTF8
+ */
+static int
+compare4(const void *p1, const void *p2)
+{
+	uint32 v1,
+				v2;
+
+	v1 = *(uint32 *) p1;
+	v2 = ((pg_local_to_utf_combined *) p2)->code;
+	return (v1 > v2) ? 1 : ((v1 == v2) ? 0 : -1);
+}
+
+/*
+ * convert 32bit wide character to mutibye stream pointed to by iso
+ */
+static unsigned char *set_iso_code(unsigned char *iso,  uint32 code)
+{
+	if (code & 0xff000000)
+		*iso++ = code >> 24;
+	if (code & 0x00ff0000)
+		*iso++ = (code & 0x00ff0000) >> 16;
+	if (code & 0x0000ff00)
+		*iso++ = (code & 0x0000ff00) >> 8;
+	if (code & 0x000000ff)
+		*iso++ = code & 0x000000ff;
+	return iso;
+}
+
 /*
  * UTF8 ---> local code
  *
  * utf: input UTF8 string (need not be null-terminated).
  * iso: pointer to the output area (must be large enough!)
  * map: the conversion map.
- * size: the size of the conversion map.
+ * cmap: the conversion map for combined characters.
+ *		  (optional)
+ * size1: the size of the conversion map.
+ * size2: the size of the conversion map for combined characters
+ *		  (optional)
  * encoding: the PG identifier for the local encoding.
  * len: length of input string.
  */
 void
 UtfToLocal(const unsigned char *utf, unsigned char *iso,
-		   const pg_utf_to_local *map, int size, int encoding, int len)
+		   const pg_utf_to_local *map, const pg_utf_to_local_combined *cmap, 
+		   int size1, int size2, int encoding, int len)
 {
-	unsigned int iutf;
-	int			l;
+	uint32 iutf;
+	uint32 cutf[2];
+	uint32 code;
 	pg_utf_to_local *p;
+	pg_utf_to_local_combined *cp;
+	int			l;
 
 	for (; len > 0; len -= l)
 	{
@@ -324,21 +379,94 @@ UtfToLocal(const unsigned char *utf, unsigned char *iso,
 			iutf |= *utf++;
 		}
 
-		p = bsearch(&iutf, map, size,
-					sizeof(pg_utf_to_local), compare1);
+		/*
+		 * first, try with combined map if possible
+		 */
+		if (cmap && len > l)
+		{
+			const unsigned char *utf_save  = utf;
+			int len_save = len;
+			int l_save = l;
+			
+			len -= l;
 
-		if (p == NULL)
-			report_untranslatable_char(PG_UTF8, encoding,
-									   (const char *) (utf - l), len);
-
-		if (p->code & 0xff000000)
-			*iso++ = p->code >> 24;
-		if (p->code & 0x00ff0000)
-			*iso++ = (p->code & 0x00ff0000) >> 16;
-		if (p->code & 0x0000ff00)
-			*iso++ = (p->code & 0x0000ff00) >> 8;
-		if (p->code & 0x000000ff)
-			*iso++ = p->code & 0x000000ff;
+			l = pg_utf_mblen(utf);
+			if (len < l)
+				break;
+
+			if (!pg_utf8_islegal(utf, l))
+				break;
+
+			cutf[0] = iutf;
+
+			if (l == 1)
+			{
+				if (len_save > 1)
+				{
+					p = bsearch(&cutf[0], map, size1,
+								sizeof(pg_utf_to_local), compare1);
+					if (p == NULL)
+						report_untranslatable_char(PG_UTF8, encoding,
+											   (const char *) (utf_save - l_save), len_save);
+					iso = set_iso_code(iso, p->code);
+				}
+
+				/* ASCII case is easy */
+				*iso++ = *utf++;
+				continue;
+			}
+			else if (l == 2)
+			{
+				iutf = *utf++ << 8;
+				iutf |= *utf++;
+			}
+			else if (l == 3)
+			{
+				iutf = *utf++ << 16;
+				iutf |= *utf++ << 8;
+				iutf |= *utf++;
+			}
+			else if (l == 4)
+			{
+				iutf = *utf++ << 24;
+				iutf |= *utf++ << 16;
+				iutf |= *utf++ << 8;
+				iutf |= *utf++;
+			}
+
+			cutf[1] = iutf;
+			cp = bsearch(cutf, cmap, size2,
+						 sizeof(pg_utf_to_local_combined), compare3);
+			if (cp)
+				code = cp->code;
+			else
+			{
+				/* not found in combined map. try with ordinary map */
+				p = bsearch(&cutf[0], map, size1,
+							sizeof(pg_utf_to_local), compare1);
+				if (p == NULL)
+					report_untranslatable_char(PG_UTF8, encoding,
+											   (const char *) (utf_save - l_save), len_save);
+				iso = set_iso_code(iso, p->code);
+
+				p = bsearch(&cutf[1], map, size1,
+							sizeof(pg_utf_to_local), compare1);
+				if (p == NULL)
+					report_untranslatable_char(PG_UTF8, encoding,
+											   (const char *) (utf - l), len);
+				code = p->code;
+			}
+		}
+		else	/* no cmap or no remaining data */
+		{
+			p = bsearch(&iutf, map, size1,
+						sizeof(pg_utf_to_local), compare1);
+			if (p == NULL)
+				report_untranslatable_char(PG_UTF8, encoding,
+											   (const char *) (utf - l), len);
+			code = p->code;
+		}
+		iso = set_iso_code(iso, code);
 	}
 
 	if (len > 0)
@@ -353,17 +481,23 @@ UtfToLocal(const unsigned char *utf, unsigned char *iso,
  * iso: input local string (need not be null-terminated).
  * utf: pointer to the output area (must be large enough!)
  * map: the conversion map.
- * size: the size of the conversion map.
+ * cmap: the conversion map for combined characters.
+ *		  (optional)
+ * size1: the size of the conversion map.
+ * size2: the size of the conversion map for combined characters
+ *		  (optional)
  * encoding: the PG identifier for the local encoding.
  * len: length of input string.
  */
 void
 LocalToUtf(const unsigned char *iso, unsigned char *utf,
-		   const pg_local_to_utf *map, int size, int encoding, int len)
+		   const pg_local_to_utf *map, const pg_local_to_utf_combined *cmap, 
+		   int size1, int size2, int encoding, int len)
 {
 	unsigned int iiso;
 	int			l;
 	pg_local_to_utf *p;
+	pg_local_to_utf_combined *cp;
 
 	if (!PG_VALID_ENCODING(encoding))
 		ereport(ERROR,
@@ -409,20 +543,59 @@ LocalToUtf(const unsigned char *iso, unsigned char *utf,
 			iiso |= *iso++;
 		}
 
-		p = bsearch(&iiso, map, size,
+		p = bsearch(&iiso, map, size1,
 					sizeof(pg_local_to_utf), compare2);
+
 		if (p == NULL)
+		{
+			/*
+			 * not found in the ordinary map. if there's a combined
+			 * character map, try with it
+			 */
+			if (cmap)
+			{
+				cp = bsearch(&iiso, cmap, size2,
+							sizeof(pg_local_to_utf_combined), compare4);
+
+				if (cp)
+				{
+					if (cp->utf1 & 0xff000000)
+						*utf++ = cp->utf1 >> 24;
+					if (cp->utf1 & 0x00ff0000)
+						*utf++ = (cp->utf1 & 0x00ff0000) >> 16;
+					if (cp->utf1 & 0x0000ff00)
+						*utf++ = (cp->utf1 & 0x0000ff00) >> 8;
+					if (cp->utf1 & 0x000000ff)
+						*utf++ = cp->utf1 & 0x000000ff;
+
+					if (cp->utf2 & 0xff000000)
+						*utf++ = cp->utf2 >> 24;
+					if (cp->utf2 & 0x00ff0000)
+						*utf++ = (cp->utf2 & 0x00ff0000) >> 16;
+					if (cp->utf2 & 0x0000ff00)
+						*utf++ = (cp->utf2 & 0x0000ff00) >> 8;
+					if (cp->utf2 & 0x000000ff)
+						*utf++ = cp->utf2 & 0x000000ff;
+
+					continue;
+				}
+			}
+
 			report_untranslatable_char(encoding, PG_UTF8,
 									   (const char *) (iso - l), len);
 
-		if (p->utf & 0xff000000)
-			*utf++ = p->utf >> 24;
-		if (p->utf & 0x00ff0000)
-			*utf++ = (p->utf & 0x00ff0000) >> 16;
-		if (p->utf & 0x0000ff00)
-			*utf++ = (p->utf & 0x0000ff00) >> 8;
-		if (p->utf & 0x000000ff)
-			*utf++ = p->utf & 0x000000ff;
+		}
+		else
+		{
+			if (p->utf & 0xff000000)
+				*utf++ = p->utf >> 24;
+			if (p->utf & 0x00ff0000)
+				*utf++ = (p->utf & 0x00ff0000) >> 16;
+			if (p->utf & 0x0000ff00)
+				*utf++ = (p->utf & 0x0000ff00) >> 8;
+			if (p->utf & 0x000000ff)
+				*utf++ = p->utf & 0x000000ff;
+		}
 	}
 
 	if (len > 0)

src/backend/utils/mb/conversion_procs/Makefile

@@ -4,7 +4,7 @@
 #    Makefile for utils/mb/conversion_procs
 #
 # IDENTIFICATION
-#    $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/Makefile,v 1.17 2006/02/27 16:09:49 petere Exp $
+#    $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/Makefile,v 1.18 2007/03/25 11:56:02 ishii Exp $
 #
 #-------------------------------------------------------------------------
 
@@ -23,7 +23,8 @@ DIRS = \
 	utf8_and_ascii utf8_and_big5 utf8_and_cyrillic utf8_and_euc_cn \
 	utf8_and_euc_jp utf8_and_euc_kr utf8_and_euc_tw utf8_and_gb18030 \
 	utf8_and_gbk utf8_and_iso8859 utf8_and_iso8859_1 utf8_and_johab \
-	utf8_and_sjis utf8_and_win utf8_and_uhc
+	utf8_and_sjis utf8_and_win utf8_and_uhc \
+	utf8_and_euc_jis_2004 utf8_and_shift_jis_2004 euc_jis_2004_and_shift_jis_2004
 
 # conversion_name source_encoding destination_encoding function object
 CONVERSIONS = \
@@ -150,8 +151,13 @@ CONVERSIONS = \
 		sjis_to_utf8 SJIS UTF8 sjis_to_utf8 utf8_and_sjis \
 		utf8_to_sjis UTF8 SJIS utf8_to_sjis utf8_and_sjis \
 		uhc_to_utf8 UHC UTF8 uhc_to_utf8 utf8_and_uhc \
-		utf8_to_uhc UTF8 UHC utf8_to_uhc utf8_and_uhc
-
+		utf8_to_uhc UTF8 UHC utf8_to_uhc utf8_and_uhc \
+		euc_jis_2004_to_utf8 EUC_JIS_2004 UTF8 euc_jis_2004_to_utf8 utf8_and_euc_jis_2004 \
+		utf8_to_euc_jis_2004 UTF8 EUC_JIS_2004 utf8_to_euc_jis_2004 utf8_and_euc_jis_2004 \
+		shift_jis_2004_to_utf8 SHIFT_JIS_2004 UTF8 shift_jis_2004_to_utf8 utf8_and_shift_jis_2004 \
+		utf8_to_shift_jis_2004 UTF8 SHIFT_JIS_2004 utf8_to_shift_jis_2004 utf8_and_shift_jis_2004 \
+		euc_jis_2004_to_shift_jis_2004 EUC_JIS_2004 SHIFT_JIS_2004 euc_jis_2004_to_shift_jis_2004 euc_jis_2004_and_shift_jis_2004 \
+		shift_jis_2004_to_euc_jis_2004 SHIFT_JIS_2004 EUC_JIS_2004 shift_jis_2004_to_euc_jis_2004 euc_jis_2004_and_shift_jis_2004
 
 all: $(SQLSCRIPT)
 	@for dir in $(DIRS); do $(MAKE) -C $$dir $@ || exit; done

src/backend/utils/mb/conversion_procs/euc_jis_2004_and_shift_jis_2004/Makefile

+#-------------------------------------------------------------------------
+#
+# $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/euc_jis_2004_and_shift_jis_2004/Makefile,v 1.1 2007/03/25 11:56:02 ishii Exp $
+#
+#-------------------------------------------------------------------------
+subdir = src/backend/utils/mb/conversion_procs/euc_jis_2004_and_shit_jis_2004
+top_builddir = ../../../../../..
+include $(top_builddir)/src/Makefile.global
+
+NAME		= euc_jis_2004_and_shift_jis_2004
+
+include $(srcdir)/../proc.mk

src/backend/utils/mb/conversion_procs/euc_jis_2004_and_shift_jis_2004/euc_jis_2004_and_shift_jis_2004.c

+/*-------------------------------------------------------------------------
+ *
+ *	  EUC_JIS_2004, SHIFT_JIS_2004
+ *
+ * Copyright (c) 2007, PostgreSQL Global Development Group
+ *
+ * IDENTIFICATION
+ *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/euc_jis_2004_and_shift_jis_2004/euc_jis_2004_and_shift_jis_2004.c,v 1.1 2007/03/25 11:56:02 ishii Exp $
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#include "postgres.h"
+#include "fmgr.h"
+#include "mb/pg_wchar.h"
+
+PG_MODULE_MAGIC;
+
+PG_FUNCTION_INFO_V1(euc_jis_2004_to_shift_jis_2004);
+PG_FUNCTION_INFO_V1(shift_jis_2004_to_euc_jis_2004);
+
+extern Datum euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS);
+extern Datum shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS);
+
+static void euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len);
+static void shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len);
+
+/* ----------
+ * conv_proc(
+ *		INTEGER,	-- source encoding id
+ *		INTEGER,	-- destination encoding id
+ *		CSTRING,	-- source string (null terminated C string)
+ *		CSTRING,	-- destination string (null terminated C string)
+ *		INTEGER		-- source string length
+ * ) returns VOID;
+ * ----------
+ */
+
+Datum
+euc_jis_2004_to_shift_jis_2004(PG_FUNCTION_ARGS)
+{
+	unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2);
+	unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3);
+	int			len = PG_GETARG_INT32(4);
+
+	Assert(PG_GETARG_INT32(0) == PG_EUC_JIS_2004);
+	Assert(PG_GETARG_INT32(1) == PG_SHIFT_JIS_2004);
+	Assert(len >= 0);
+
+	euc_jis_20042shift_jis_2004(src, dest, len);
+
+	PG_RETURN_VOID();
+}
+
+Datum
+shift_jis_2004_to_euc_jis_2004(PG_FUNCTION_ARGS)
+{
+	unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2);
+	unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3);
+	int			len = PG_GETARG_INT32(4);
+
+	Assert(PG_GETARG_INT32(0) == PG_SHIFT_JIS_2004);
+	Assert(PG_GETARG_INT32(1) == PG_EUC_JIS_2004);
+	Assert(len >= 0);
+
+	shift_jis_20042euc_jis_2004(src, dest, len);
+
+	PG_RETURN_VOID();
+}
+
+/*
+ * EUC_JIS_2004 -> SHIFT_JIS_2004
+ */
+static void
+euc_jis_20042shift_jis_2004(const unsigned char *euc, unsigned char *p, int len)
+{
+	int			c1,
+				ku,
+		ten;
+	int			l;
+
+	while (len > 0)
+	{
+		c1 = *euc;
+		if (!IS_HIGHBIT_SET(c1))
+		{
+			/* ASCII */
+			if (c1 == 0)
+				report_invalid_encoding(PG_EUC_JIS_2004,
+										(const char *) euc, len);
+			*p++ = c1;
+			euc++;
+			len--;
+			continue;
+		}
+
+		l = pg_encoding_verifymb(PG_EUC_JIS_2004, (const char *) euc, len);
+
+		if (l < 0)
+			report_invalid_encoding(PG_EUC_JIS_2004,
+									(const char *) euc, len);
+
+		if (c1 == SS2 && l == 2)	/* JIS X 0201 kana? */
+		{
+			*p++ = euc[1];
+		}
+		else if (c1 == SS3 && l == 3)		/* JIS X 0213 plane 2? */
+		{
+			ku = euc[1] - 0xa0;
+			ten = euc[2] - 0xa0;
+
+			switch (ku)
+			{
+				case 1:
+				case 3:
+				case 4:
+				case 5:
+				case 8:
+				case 12:
+				case 13:
+				case 14:
+				case 15:
+					*p++ = ((ku + 0x1df) >> 1) - (ku >> 3) * 3;
+					break;
+				default:
+					if (ku >= 78 && ku <= 94)
+					{
+						*p++ = (ku + 0x19b) >> 1;
+					}
+					else
+						report_invalid_encoding(PG_EUC_JIS_2004,
+												(const char *) euc, len);
+			}
+
+			if (ku % 2)
+			{
+				if (ten >= 1 && ten <= 63)
+					*p++ = ten + 0x3f;
+				else if (ten >= 64 && ten <= 94)
+					*p++ = ten + 0x40;
+				else
+					report_invalid_encoding(PG_EUC_JIS_2004,
+											(const char *) euc, len);
+			}
+			else
+				*p++ = ten + 0x9e;
+		}
+
+		else if (l == 2)	/* JIS X 0213 plane 1? */
+		{
+			ku = c1 - 0xa0;
+			ten = euc[1] - 0xa0;
+
+			if (ku >= 1 && ku <= 62)
+				*p++ = (ku + 0x101) >> 1;
+			else if (ku >= 63 && ku <= 94)
+				*p++ = (ku + 0x181) >> 1;
+			else
+				report_invalid_encoding(PG_EUC_JIS_2004,
+										(const char *) euc, len);
+
+			if (ku % 2)
+			{
+				if (ten >= 1 && ten <= 63)
+					*p++ = ten + 0x3f;
+				else if (ten >= 64 && ten <= 94)
+					*p++ = ten + 0x40;
+				else
+					report_invalid_encoding(PG_EUC_JIS_2004,
+											(const char *) euc, len);
+			}
+			else
+				*p++ = ten + 0x9e;
+		}
+		else
+			report_invalid_encoding(PG_EUC_JIS_2004,
+									(const char *) euc, len);
+
+		euc += l;
+		len -= l;
+	}
+	*p = '\0';
+}
+
+/*
+ * returns SHIFT_JIS_2004 "ku" code indicated by second byte
+ * *ku = 0: "ku" = even
+ * *ku = 1: "ku" = odd
+ */
+static int get_ten(int b, int *ku)
+{
+	int ten;
+
+	if (b >= 0x40 && b <= 0x7e)
+	{
+		ten = b - 0x3f;
+		*ku = 1;
+	} else if (b >= 0x80 && b <= 0x9e)
+	{
+		ten = b - 0x40;
+		*ku = 1;
+	} else if (b >= 0x9f && b <= 0xfc)
+	{
+		ten = b - 0x9e;
+		*ku = 0;
+	}
+	else
+	{
+		ten = -1;		/* error */
+	}
+	return ten;
+}
+
+/*
+ * SHIFT_JIS_2004 ---> EUC_JIS_2004
+ */
+
+static void
+shift_jis_20042euc_jis_2004(const unsigned char *sjis, unsigned char *p, int len)
+{
+	int			c1,
+		c2;
+	int			ku, ten, kubun;
+	int			plane;
+	int			l;
+
+	while (len > 0)
+	{
+		c1 = *sjis;
+		c2 = sjis[1];
+
+		if (!IS_HIGHBIT_SET(c1))
+		{
+			/* ASCII */
+			if (c1 == 0)
+				report_invalid_encoding(PG_SHIFT_JIS_2004,
+										(const char *) sjis, len);
+			*p++ = c1;
+			sjis++;
+			len--;
+			continue;
+		}
+
+		l = pg_encoding_verifymb(PG_SHIFT_JIS_2004, (const char *) sjis, len);
+
+		if (l < 0)
+			report_invalid_encoding(PG_SHIFT_JIS_2004,
+									(const char *) sjis, len);
+
+		if (c1 >= 0xa1 && c1 <= 0xdf && l == 1)
+		{
+			/* JIS X0201 (1 byte kana) */
+			*p++ = SS2;
+			*p++ = c1;
+		}
+		else if (l == 2)
+		{
+			plane = 1;
+			ku = 1;
+			ten = 1;
+
+			/*
+			 * JIS X 0213
+			 */
+			if (c1 >= 0x81 && c1 <= 0x9f)		/* plane 1 1ku-62ku */
+			{
+				ku = (c1 << 1) - 0x100;
+				ten = get_ten(c2, &kubun);
+				if (ten < 0)
+					report_invalid_encoding(PG_SHIFT_JIS_2004,
+											(const char *) sjis, len);
+				ku -= kubun;
+			}
+			else if (c1 >= 0xe0 && c1 <= 0xef)	/* plane 1 62ku-94ku */
+			{
+				ku = (c1 << 1) - 0x180;
+				ten = get_ten(c2, &kubun);
+				if (ten < 0)
+					report_invalid_encoding(PG_SHIFT_JIS_2004,
+
+											(const char *) sjis, len);
+				ku -= kubun;
+			}
+			else if (c1 >= 0xf0 && c1 <= 0xf3)	/* plane 2 1,3,4,5,8,12,13,14,15 ku */
+			{
+				plane = 2;
+				ten = get_ten(c2, &kubun);
+				if (ten < 0)
+					report_invalid_encoding(PG_SHIFT_JIS_2004,
+											(const char *) sjis, len);
+				switch (c1)
+				{
+					case 0xf0:
+						ku = kubun == 0? 8: 1;						
+						break;
+					case 0xf1:
+						ku = kubun == 0? 4: 3;
+						break;
+					case 0xf2:
+						ku = kubun == 0? 12: 5;
+						break;
+					default:
+						ku = kubun == 0? 14: 13;
+						break;
+				}
+			}
+			else if (c1 >= 0xf4 && c1 <= 0xfc)	/* plane 2 78-94ku */
+			{
+				plane = 2;
+				ten = get_ten(c2, &kubun);
+				if (ten < 0)
+					report_invalid_encoding(PG_SHIFT_JIS_2004,
+											(const char *) sjis, len);
+				if (c1 == 0xf4 && kubun == 1)
+					ku = 15;
+				else
+					ku = (c1 << 1) - 0x19a - kubun;
+			}
+			else
+				report_invalid_encoding(PG_SHIFT_JIS_2004,
+										(const char *) sjis, len);
+
+			if (plane == 2)
+				*p++ = SS3;
+
+			*p++ = ku + 0xa0;
+			*p++ = ten + 0xa0;
+		}
+		sjis += l;
+		len -= l;
+	}
+	*p = '\0';
+}

src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c,v 1.15 2007/01/05 22:19:45 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c,v 1.16 2007/03/25 11:56:02 ishii Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -46,8 +46,8 @@ big5_to_utf8(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_UTF8);
 	Assert(len >= 0);
 
-	LocalToUtf(src, dest, LUmapBIG5,
-			   sizeof(LUmapBIG5) / sizeof(pg_local_to_utf), PG_BIG5, len);
+	LocalToUtf(src, dest, LUmapBIG5, NULL, 
+			   sizeof(LUmapBIG5) / sizeof(pg_local_to_utf), 0, PG_BIG5, len);
 
 	PG_RETURN_VOID();
 }
@@ -63,8 +63,8 @@ utf8_to_big5(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_BIG5);
 	Assert(len >= 0);
 
-	UtfToLocal(src, dest, ULmapBIG5,
-			   sizeof(ULmapBIG5) / sizeof(pg_utf_to_local), PG_BIG5, len);
+	UtfToLocal(src, dest, ULmapBIG5, NULL, 
+			   sizeof(ULmapBIG5) / sizeof(pg_utf_to_local), 0, PG_BIG5, len);
 
 	PG_RETURN_VOID();
 }

src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c,v 1.18 2007/01/05 22:19:45 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c,v 1.19 2007/03/25 11:56:02 ishii Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -47,8 +47,8 @@ utf8_to_koi8r(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_KOI8R);
 	Assert(len >= 0);
 
-	UtfToLocal(src, dest, ULmapKOI8R,
-			   sizeof(ULmapKOI8R) / sizeof(pg_utf_to_local), PG_KOI8R, len);
+	UtfToLocal(src, dest, ULmapKOI8R, NULL, 
+			   sizeof(ULmapKOI8R) / sizeof(pg_utf_to_local), 0, PG_KOI8R, len);
 
 	PG_RETURN_VOID();
 }
@@ -64,8 +64,8 @@ koi8r_to_utf8(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_UTF8);
 	Assert(len >= 0);
 
-	LocalToUtf(src, dest, LUmapKOI8R,
-			   sizeof(LUmapKOI8R) / sizeof(pg_local_to_utf), PG_KOI8R, len);
+	LocalToUtf(src, dest, LUmapKOI8R, NULL,
+			   sizeof(LUmapKOI8R) / sizeof(pg_local_to_utf), 0, PG_KOI8R, len);
 
 	PG_RETURN_VOID();
 }

src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c,v 1.16 2007/01/05 22:19:45 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c,v 1.17 2007/03/25 11:56:02 ishii Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -46,8 +46,8 @@ euc_cn_to_utf8(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_UTF8);
 	Assert(len >= 0);
 
-	LocalToUtf(src, dest, LUmapEUC_CN,
-			   sizeof(LUmapEUC_CN) / sizeof(pg_local_to_utf), PG_EUC_CN, len);
+	LocalToUtf(src, dest, LUmapEUC_CN, NULL,
+			   sizeof(LUmapEUC_CN) / sizeof(pg_local_to_utf), 0, PG_EUC_CN, len);
 
 	PG_RETURN_VOID();
 }
@@ -63,8 +63,8 @@ utf8_to_euc_cn(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_EUC_CN);
 	Assert(len >= 0);
 
-	UtfToLocal(src, dest, ULmapEUC_CN,
-			   sizeof(ULmapEUC_CN) / sizeof(pg_utf_to_local), PG_EUC_CN, len);
+	UtfToLocal(src, dest, ULmapEUC_CN, NULL,
+			   sizeof(ULmapEUC_CN) / sizeof(pg_utf_to_local), 0, PG_EUC_CN, len);
 
 	PG_RETURN_VOID();
 }

src/backend/utils/mb/conversion_procs/utf8_and_euc_jis_2004/Makefile

+#-------------------------------------------------------------------------
+#
+# $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_jis_2004/Makefile,v 1.1 2007/03/25 11:56:02 ishii Exp $
+#
+#-------------------------------------------------------------------------
+subdir = src/backend/utils/mb/conversion_procs/utf8_and_euc_jis_2004
+top_builddir = ../../../../../..
+include $(top_builddir)/src/Makefile.global
+
+NAME		= utf8_and_euc_jis_2004
+
+include $(srcdir)/../proc.mk

src/backend/utils/mb/conversion_procs/utf8_and_euc_jis_2004/utf8_and_euc_jis_2004.c

+/*-------------------------------------------------------------------------
+ *
+ *	  EUC_JIS_2004 <--> UTF8
+ *
+ * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * IDENTIFICATION
+ *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_jis_2004/utf8_and_euc_jis_2004.c,v 1.1 2007/03/25 11:56:03 ishii Exp $
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#include "postgres.h"
+#include "fmgr.h"
+#include "mb/pg_wchar.h"
+#include "../../Unicode/euc_jis_2004_to_utf8.map"
+#include "../../Unicode/utf8_to_euc_jis_2004.map"
+#include "../../Unicode/euc_jis_2004_to_utf8_combined.map"
+#include "../../Unicode/utf8_to_euc_jis_2004_combined.map"
+
+PG_MODULE_MAGIC;
+
+PG_FUNCTION_INFO_V1(euc_jis_2004_to_utf8);
+PG_FUNCTION_INFO_V1(utf8_to_euc_jis_2004);
+
+extern Datum euc_jis_2004_to_utf8(PG_FUNCTION_ARGS);
+extern Datum utf8_to_euc_jis_2004(PG_FUNCTION_ARGS);
+
+/* ----------
+ * conv_proc(
+ *		INTEGER,	-- source encoding id
+ *		INTEGER,	-- destination encoding id
+ *		CSTRING,	-- source string (null terminated C string)
+ *		CSTRING,	-- destination string (null terminated C string)
+ *		INTEGER		-- source string length
+ * ) returns VOID;
+ * ----------
+ */
+Datum
+euc_jis_2004_to_utf8(PG_FUNCTION_ARGS)
+{
+	unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2);
+	unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3);
+	int			len = PG_GETARG_INT32(4);
+
+	Assert(PG_GETARG_INT32(0) == PG_EUC_JIS_2004);
+	Assert(PG_GETARG_INT32(1) == PG_UTF8);
+	Assert(len >= 0);
+
+	LocalToUtf(src, dest, LUmapEUC_JIS_2004, LUmapEUC_JIS_2004_combined,
+			   sizeof(LUmapEUC_JIS_2004) / sizeof(pg_local_to_utf),
+			   sizeof(LUmapEUC_JIS_2004_combined) / sizeof(pg_local_to_utf_combined),
+			   PG_EUC_JIS_2004, len);
+
+	PG_RETURN_VOID();
+}
+
+Datum
+utf8_to_euc_jis_2004(PG_FUNCTION_ARGS)
+{
+	unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2);
+	unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3);
+	int			len = PG_GETARG_INT32(4);
+
+	Assert(PG_GETARG_INT32(0) == PG_UTF8);
+	Assert(PG_GETARG_INT32(1) == PG_EUC_JIS_2004);
+	Assert(len >= 0);
+
+	UtfToLocal(src, dest, ULmapEUC_JIS_2004, ULmapEUC_JIS_2004_combined,
+			   sizeof(ULmapEUC_JIS_2004) / sizeof(pg_utf_to_local),
+			   sizeof(ULmapEUC_JIS_2004_combined) / sizeof(pg_utf_to_local_combined),
+			   PG_EUC_JIS_2004, len);
+
+	PG_RETURN_VOID();
+}

src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c,v 1.16 2007/01/05 22:19:45 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c,v 1.17 2007/03/25 11:56:03 ishii Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -46,8 +46,8 @@ euc_jp_to_utf8(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_UTF8);
 	Assert(len >= 0);
 
-	LocalToUtf(src, dest, LUmapEUC_JP,
-			   sizeof(LUmapEUC_JP) / sizeof(pg_local_to_utf), PG_EUC_JP, len);
+	LocalToUtf(src, dest, LUmapEUC_JP, NULL,
+			   sizeof(LUmapEUC_JP) / sizeof(pg_local_to_utf), 0, PG_EUC_JP, len);
 
 	PG_RETURN_VOID();
 }
@@ -63,8 +63,8 @@ utf8_to_euc_jp(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_EUC_JP);
 	Assert(len >= 0);
 
-	UtfToLocal(src, dest, ULmapEUC_JP,
-			   sizeof(ULmapEUC_JP) / sizeof(pg_utf_to_local), PG_EUC_JP, len);
+	UtfToLocal(src, dest, ULmapEUC_JP, NULL,
+			   sizeof(ULmapEUC_JP) / sizeof(pg_utf_to_local), 0, PG_EUC_JP, len);
 
 	PG_RETURN_VOID();
 }

src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c,v 1.16 2007/01/05 22:19:45 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c,v 1.17 2007/03/25 11:56:03 ishii Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -46,8 +46,8 @@ euc_kr_to_utf8(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_UTF8);
 	Assert(len >= 0);
 
-	LocalToUtf(src, dest, LUmapEUC_KR,
-			   sizeof(LUmapEUC_KR) / sizeof(pg_local_to_utf), PG_EUC_KR, len);
+	LocalToUtf(src, dest, LUmapEUC_KR, NULL,
+			   sizeof(LUmapEUC_KR) / sizeof(pg_local_to_utf), 0, PG_EUC_KR, len);
 
 	PG_RETURN_VOID();
 }
@@ -63,8 +63,8 @@ utf8_to_euc_kr(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_EUC_KR);
 	Assert(len >= 0);
 
-	UtfToLocal(src, dest, ULmapEUC_KR,
-			   sizeof(ULmapEUC_KR) / sizeof(pg_utf_to_local), PG_EUC_KR, len);
+	UtfToLocal(src, dest, ULmapEUC_KR, NULL,
+			   sizeof(ULmapEUC_KR) / sizeof(pg_utf_to_local), 0, PG_EUC_KR, len);
 
 	PG_RETURN_VOID();
 }

src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c,v 1.16 2007/01/05 22:19:45 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c,v 1.17 2007/03/25 11:56:03 ishii Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -46,8 +46,8 @@ euc_tw_to_utf8(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_UTF8);
 	Assert(len >= 0);
 
-	LocalToUtf(src, dest, LUmapEUC_TW,
-			   sizeof(LUmapEUC_TW) / sizeof(pg_local_to_utf), PG_EUC_TW, len);
+	LocalToUtf(src, dest, LUmapEUC_TW, NULL,
+			   sizeof(LUmapEUC_TW) / sizeof(pg_local_to_utf), 0, PG_EUC_TW, len);
 
 	PG_RETURN_VOID();
 }
@@ -63,8 +63,8 @@ utf8_to_euc_tw(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_EUC_TW);
 	Assert(len >= 0);
 
-	UtfToLocal(src, dest, ULmapEUC_TW,
-			   sizeof(ULmapEUC_TW) / sizeof(pg_utf_to_local), PG_EUC_TW, len);
+	UtfToLocal(src, dest, ULmapEUC_TW, NULL,
+			   sizeof(ULmapEUC_TW) / sizeof(pg_utf_to_local), 0, PG_EUC_TW, len);
 
 	PG_RETURN_VOID();
 }

src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c,v 1.17 2007/01/05 22:19:46 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c,v 1.18 2007/03/25 11:56:03 ishii Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -46,8 +46,8 @@ gb18030_to_utf8(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_UTF8);
 	Assert(len >= 0);
 
-	LocalToUtf(src, dest, LUmapGB18030,
-			sizeof(LUmapGB18030) / sizeof(pg_local_to_utf), PG_GB18030, len);
+	LocalToUtf(src, dest, LUmapGB18030, NULL,
+			sizeof(LUmapGB18030) / sizeof(pg_local_to_utf), 0, PG_GB18030, len);
 
 	PG_RETURN_VOID();
 }
@@ -63,8 +63,8 @@ utf8_to_gb18030(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_GB18030);
 	Assert(len >= 0);
 
-	UtfToLocal(src, dest, ULmapGB18030,
-			sizeof(ULmapGB18030) / sizeof(pg_utf_to_local), PG_GB18030, len);
+	UtfToLocal(src, dest, ULmapGB18030, NULL,
+			sizeof(ULmapGB18030) / sizeof(pg_utf_to_local), 0, PG_GB18030, len);
 
 	PG_RETURN_VOID();
 }

src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c,v 1.15 2007/01/05 22:19:46 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c,v 1.16 2007/03/25 11:56:03 ishii Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -46,8 +46,8 @@ gbk_to_utf8(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_UTF8);
 	Assert(len >= 0);
 
-	LocalToUtf(src, dest, LUmapGBK,
-			   sizeof(LUmapGBK) / sizeof(pg_local_to_utf), PG_GBK, len);
+	LocalToUtf(src, dest, LUmapGBK, NULL,
+			   sizeof(LUmapGBK) / sizeof(pg_local_to_utf), 0, PG_GBK, len);
 
 	PG_RETURN_VOID();
 }
@@ -63,8 +63,8 @@ utf8_to_gbk(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_GBK);
 	Assert(len >= 0);
 
-	UtfToLocal(src, dest, ULmapGBK,
-			   sizeof(ULmapGBK) / sizeof(pg_utf_to_local), PG_GBK, len);
+	UtfToLocal(src, dest, ULmapGBK, NULL,
+			   sizeof(ULmapGBK) / sizeof(pg_utf_to_local), 0, PG_GBK, len);
 
 	PG_RETURN_VOID();
 }

src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c,v 1.25 2007/01/05 22:19:46 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c,v 1.26 2007/03/25 11:56:03 ishii Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -127,7 +127,7 @@ iso8859_to_utf8(PG_FUNCTION_ARGS)
 	{
 		if (encoding == maps[i].encoding)
 		{
-			LocalToUtf(src, dest, maps[i].map1, maps[i].size1, encoding, len);
+			LocalToUtf(src, dest, maps[i].map1, NULL, maps[i].size1, 0, encoding, len);
 			PG_RETURN_VOID();
 		}
 	}
@@ -155,7 +155,7 @@ utf8_to_iso8859(PG_FUNCTION_ARGS)
 	{
 		if (encoding == maps[i].encoding)
 		{
-			UtfToLocal(src, dest, maps[i].map2, maps[i].size2, encoding, len);
+			UtfToLocal(src, dest, maps[i].map2, NULL, maps[i].size2, 0, encoding, len);
 			PG_RETURN_VOID();
 		}
 	}

src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c,v 1.16 2007/01/05 22:19:46 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c,v 1.17 2007/03/25 11:56:03 ishii Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -46,8 +46,8 @@ johab_to_utf8(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_UTF8);
 	Assert(len >= 0);
 
-	LocalToUtf(src, dest, LUmapJOHAB,
-			   sizeof(LUmapJOHAB) / sizeof(pg_local_to_utf), PG_JOHAB, len);
+	LocalToUtf(src, dest, LUmapJOHAB, NULL,
+			   sizeof(LUmapJOHAB) / sizeof(pg_local_to_utf), 0, PG_JOHAB, len);
 
 	PG_RETURN_VOID();
 }
@@ -63,8 +63,8 @@ utf8_to_johab(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_JOHAB);
 	Assert(len >= 0);
 
-	UtfToLocal(src, dest, ULmapJOHAB,
-			   sizeof(ULmapJOHAB) / sizeof(pg_utf_to_local), PG_JOHAB, len);
+	UtfToLocal(src, dest, ULmapJOHAB, NULL,
+			   sizeof(ULmapJOHAB) / sizeof(pg_utf_to_local), 0, PG_JOHAB, len);
 
 	PG_RETURN_VOID();
 }

src/backend/utils/mb/conversion_procs/utf8_and_shift_jis_2004/Makefile

+#-------------------------------------------------------------------------
+#
+# $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_shift_jis_2004/Makefile,v 1.1 2007/03/25 11:56:03 ishii Exp $
+#
+#-------------------------------------------------------------------------
+subdir = src/backend/utils/mb/conversion_procs/utf8_and_shift_jis_2004
+top_builddir = ../../../../../..
+include $(top_builddir)/src/Makefile.global
+
+NAME		= utf8_and_shift_jis_2004
+
+include $(srcdir)/../proc.mk

src/backend/utils/mb/conversion_procs/utf8_and_shift_jis_2004/utf8_and_shift_jis_2004.c

+/*-------------------------------------------------------------------------
+ *
+ *	  SHIFT_JIS_2004 <--> UTF8
+ *
+ * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * IDENTIFICATION
+ *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_shift_jis_2004/utf8_and_shift_jis_2004.c,v 1.1 2007/03/25 11:56:03 ishii Exp $
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#include "postgres.h"
+#include "fmgr.h"
+#include "mb/pg_wchar.h"
+#include "../../Unicode/shift_jis_2004_to_utf8.map"
+#include "../../Unicode/utf8_to_shift_jis_2004.map"
+#include "../../Unicode/shift_jis_2004_to_utf8_combined.map"
+#include "../../Unicode/utf8_to_shift_jis_2004_combined.map"
+
+PG_MODULE_MAGIC;
+
+PG_FUNCTION_INFO_V1(shift_jis_2004_to_utf8);
+PG_FUNCTION_INFO_V1(utf8_to_shift_jis_2004);
+
+extern Datum shift_jis_2004_to_utf8(PG_FUNCTION_ARGS);
+extern Datum utf8_to_shift_jis_2004(PG_FUNCTION_ARGS);
+
+/* ----------
+ * conv_proc(
+ *		INTEGER,	-- source encoding id
+ *		INTEGER,	-- destination encoding id
+ *		CSTRING,	-- source string (null terminated C string)
+ *		CSTRING,	-- destination string (null terminated C string)
+ *		INTEGER		-- source string length
+ * ) returns VOID;
+ * ----------
+ */
+Datum
+shift_jis_2004_to_utf8(PG_FUNCTION_ARGS)
+{
+	unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2);
+	unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3);
+	int			len = PG_GETARG_INT32(4);
+
+	Assert(PG_GETARG_INT32(0) == PG_SHIFT_JIS_2004);
+	Assert(PG_GETARG_INT32(1) == PG_UTF8);
+	Assert(len >= 0);
+
+	LocalToUtf(src, dest, LUmapSHIFT_JIS_2004, LUmapSHIFT_JIS_2004_combined,
+			   sizeof(LUmapSHIFT_JIS_2004) / sizeof(pg_local_to_utf),
+			   sizeof(LUmapSHIFT_JIS_2004_combined) / sizeof(pg_local_to_utf_combined),
+			   PG_SHIFT_JIS_2004, len);
+
+	PG_RETURN_VOID();
+}
+
+Datum
+utf8_to_shift_jis_2004(PG_FUNCTION_ARGS)
+{
+	unsigned char *src = (unsigned char *) PG_GETARG_CSTRING(2);
+	unsigned char *dest = (unsigned char *) PG_GETARG_CSTRING(3);
+	int			len = PG_GETARG_INT32(4);
+
+	Assert(PG_GETARG_INT32(0) == PG_UTF8);
+	Assert(PG_GETARG_INT32(1) == PG_SHIFT_JIS_2004);
+	Assert(len >= 0);
+
+	UtfToLocal(src, dest, ULmapSHIFT_JIS_2004, ULmapSHIFT_JIS_2004_combined,
+			   sizeof(ULmapSHIFT_JIS_2004) / sizeof(pg_utf_to_local),
+			   sizeof(ULmapSHIFT_JIS_2004_combined) / sizeof(pg_utf_to_local_combined),
+			   PG_SHIFT_JIS_2004, len);
+
+	PG_RETURN_VOID();
+}

src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c,v 1.15 2007/01/05 22:19:46 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c,v 1.16 2007/03/25 11:56:03 ishii Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -46,8 +46,8 @@ sjis_to_utf8(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_UTF8);
 	Assert(len >= 0);
 
-	LocalToUtf(src, dest, LUmapSJIS,
-			   sizeof(LUmapSJIS) / sizeof(pg_local_to_utf), PG_SJIS, len);
+	LocalToUtf(src, dest, LUmapSJIS, NULL,
+			   sizeof(LUmapSJIS) / sizeof(pg_local_to_utf), 0, PG_SJIS, len);
 
 	PG_RETURN_VOID();
 }
@@ -63,8 +63,8 @@ utf8_to_sjis(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_SJIS);
 	Assert(len >= 0);
 
-	UtfToLocal(src, dest, ULmapSJIS,
-			   sizeof(ULmapSJIS) / sizeof(pg_utf_to_local), PG_SJIS, len);
+	UtfToLocal(src, dest, ULmapSJIS, NULL,
+			   sizeof(ULmapSJIS) / sizeof(pg_utf_to_local), 0, PG_SJIS, len);
 
 	PG_RETURN_VOID();
 }

src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c,v 1.15 2007/01/05 22:19:46 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c,v 1.16 2007/03/25 11:56:03 ishii Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -46,8 +46,8 @@ uhc_to_utf8(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_UTF8);
 	Assert(len >= 0);
 
-	LocalToUtf(src, dest, LUmapUHC,
-			   sizeof(LUmapUHC) / sizeof(pg_local_to_utf), PG_UHC, len);
+	LocalToUtf(src, dest, LUmapUHC, NULL,
+			   sizeof(LUmapUHC) / sizeof(pg_local_to_utf), 0, PG_UHC, len);
 
 	PG_RETURN_VOID();
 }
@@ -63,8 +63,8 @@ utf8_to_uhc(PG_FUNCTION_ARGS)
 	Assert(PG_GETARG_INT32(1) == PG_UHC);
 	Assert(len >= 0);
 
-	UtfToLocal(src, dest, ULmapUHC,
-			   sizeof(ULmapUHC) / sizeof(pg_utf_to_local), PG_UHC, len);
+	UtfToLocal(src, dest, ULmapUHC, NULL,
+			   sizeof(ULmapUHC) / sizeof(pg_utf_to_local), 0, PG_UHC, len);
 
 	PG_RETURN_VOID();
 }

src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c

@@ -6,7 +6,7 @@
  * Portions Copyright (c) 1994, Regents of the University of California
  *
  * IDENTIFICATION
- *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c,v 1.9 2007/01/05 22:19:46 momjian Exp $
+ *	  $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_win/utf8_and_win.c,v 1.10 2007/03/25 11:56:04 ishii Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -117,7 +117,7 @@ win_to_utf8(PG_FUNCTION_ARGS)
 	{
 		if (encoding == maps[i].encoding)
 		{
-			LocalToUtf(src, dest, maps[i].map1, maps[i].size1, encoding, len);
+			LocalToUtf(src, dest, maps[i].map1, NULL, maps[i].size1, 0, encoding, len);
 			PG_RETURN_VOID();
 		}
 	}
@@ -145,7 +145,7 @@ utf8_to_win(PG_FUNCTION_ARGS)
 	{
 		if (encoding == maps[i].encoding)
 		{
-			UtfToLocal(src, dest, maps[i].map2, maps[i].size2, encoding, len);
+			UtfToLocal(src, dest, maps[i].map2, NULL, maps[i].size2, 0, encoding, len);
 			PG_RETURN_VOID();
 		}
 	}

src/backend/utils/mb/encnames.c

@@ -2,7 +2,7 @@
  * Encoding names and routines for work with it. All
  * in this file is shared bedween FE and BE.
  *
- * $PostgreSQL: pgsql/src/backend/utils/mb/encnames.c,v 1.31 2006/07/14 14:52:25 momjian Exp $
+ * $PostgreSQL: pgsql/src/backend/utils/mb/encnames.c,v 1.32 2007/03/25 11:56:02 ishii Exp $
  */
 #ifdef FRONTEND
 #include "postgres_fe.h"
@@ -44,6 +44,10 @@ pg_encname	pg_encname_tbl[] =
 		"euccn", PG_EUC_CN
 	},							/* EUC-CN; Extended Unix Code for simplified
 								 * Chinese */
+	{
+		"eucjis2004", PG_EUC_JIS_2004
+	},							/* EUC-JIS-2004; Extended UNIX Code fixed Width for
+								 * Japanese, standard JIS X 0213 */
 	{
 		"eucjp", PG_EUC_JP
 	},							/* EUC-JP; Extended UNIX Code fixed Width for
@@ -156,6 +160,11 @@ pg_encname	pg_encname_tbl[] =
 	{
 		"shiftjis", PG_SJIS
 	},							/* Shift_JIS; JIS X 0202-1991 */
+
+	{
+		"shiftjis2004", PG_SHIFT_JIS_2004
+	},							/* SHIFT-JIS-2004; Shift JIS for
+								 * Japanese, standard JIS X 0213 */
 	{
 		"sjis", PG_SJIS
 	},							/* alias for Shift_JIS */
@@ -391,6 +400,9 @@ pg_enc2name pg_enc2name_tbl[] =
 	{
 		"WIN1257", PG_WIN1257
 	},
+	{
+		"EUC_JIS_2004", PG_EUC_JIS_2004
+	},
 	{
 		"SJIS", PG_SJIS
 	},
@@ -405,6 +417,9 @@ pg_enc2name pg_enc2name_tbl[] =
 	},
 	{
 		"GB18030", PG_GB18030
+	},
+	{
+		"SHIFT_JIS_2004", PG_SHIFT_JIS_2004
 	}
 };
 

src/backend/utils/mb/wchar.c

 /*
  * conversion functions between pg_wchar and multibyte streams.
  * Tatsuo Ishii
- * $PostgreSQL: pgsql/src/backend/utils/mb/wchar.c,v 1.59 2007/01/24 17:12:17 tgl Exp $
+ * $PostgreSQL: pgsql/src/backend/utils/mb/wchar.c,v 1.60 2007/03/25 11:56:02 ishii Exp $
  *
  * WIN1250 client encoding updated by Pavel Behal
  *
@@ -1346,11 +1346,13 @@ pg_wchar_tbl pg_wchar_table[] = {
 	{pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1},		/* 30; PG_WIN1254 */
 	{pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1},		/* 31; PG_WIN1255 */
 	{pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, pg_latin1_verifier, 1},		/* 32; PG_WIN1257 */
-	{0, pg_sjis_mblen, pg_sjis_dsplen, pg_sjis_verifier, 2},	/* 33; PG_SJIS */
-	{0, pg_big5_mblen, pg_big5_dsplen, pg_big5_verifier, 2},	/* 34; PG_BIG5 */
-	{0, pg_gbk_mblen, pg_gbk_dsplen, pg_gbk_verifier, 2},		/* 35; PG_GBK */
-	{0, pg_uhc_mblen, pg_uhc_dsplen, pg_uhc_verifier, 2},		/* 36; PG_UHC */
-	{0, pg_gb18030_mblen, pg_gb18030_dsplen, pg_gb18030_verifier, 2}	/* 37; PG_GB18030 */
+	{pg_eucjp2wchar_with_len, pg_eucjp_mblen, pg_eucjp_dsplen, pg_eucjp_verifier, 3},	/* 33; PG_EUC_JIS_2004 */
+	{0, pg_sjis_mblen, pg_sjis_dsplen, pg_sjis_verifier, 2},	/* 34; PG_SJIS */
+	{0, pg_big5_mblen, pg_big5_dsplen, pg_big5_verifier, 2},	/* 35; PG_BIG5 */
+	{0, pg_gbk_mblen, pg_gbk_dsplen, pg_gbk_verifier, 2},		/* 36; PG_GBK */
+	{0, pg_uhc_mblen, pg_uhc_dsplen, pg_uhc_verifier, 2},		/* 37; PG_UHC */
+	{0, pg_gb18030_mblen, pg_gb18030_dsplen, pg_gb18030_verifier, 2},	/* 38; PG_GB18030 */
+	{0, pg_sjis_mblen, pg_sjis_dsplen, pg_sjis_verifier, 2}		/* 39; PG_SHIFT_JIS_2004 */
 };
 
 /* returns the byte length of a word for mule internal code */

src/include/catalog/catversion.h

@@ -37,7 +37,7 @@
  * Portions Copyright (c) 1996-2007, PostgreSQL Global Development Group
  * Portions Copyright (c) 1994, Regents of the University of California
  *
- * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.393 2007/03/20 05:45:00 neilc Exp $
+ * $PostgreSQL: pgsql/src/include/catalog/catversion.h,v 1.394 2007/03/25 11:56:04 ishii Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -53,6 +53,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	200703201
+#define CATALOG_VERSION_NO	200703251
 
 #endif

src/include/mb/pg_wchar.h

-/* $PostgreSQL: pgsql/src/include/mb/pg_wchar.h,v 1.70 2006/12/24 00:57:48 tgl Exp $ */
+/* $PostgreSQL: pgsql/src/include/mb/pg_wchar.h,v 1.71 2007/03/25 11:56:04 ishii Exp $ */
 
 #ifndef PG_WCHAR_H
 #define PG_WCHAR_H
@@ -187,6 +187,7 @@ typedef enum pg_enc
 	PG_WIN1254,					/* windows-1254 */
 	PG_WIN1255,					/* windows-1255 */
 	PG_WIN1257,					/* windows-1257 */
+	PG_EUC_JIS_2004,			/* EUC-JIS-2004 */
 	/* PG_ENCODING_BE_LAST points to the above entry */
 
 	/* followings are for client encoding only */
@@ -195,11 +196,12 @@ typedef enum pg_enc
 	PG_GBK,						/* GBK (Windows-936) */
 	PG_UHC,						/* UHC (Windows-949) */
 	PG_GB18030,					/* GB18030 */
+	PG_SHIFT_JIS_2004,			/* Shift-JIS-2004 */
 	_PG_LAST_ENCODING_			/* mark only */
 
 } pg_enc;
 
-#define PG_ENCODING_BE_LAST PG_WIN1257
+#define PG_ENCODING_BE_LAST PG_EUC_JIS_2004
 
 /*
  * Please use these tests before access to pg_encconv_tbl[]
@@ -274,23 +276,45 @@ typedef struct
 extern pg_wchar_tbl pg_wchar_table[];
 
 /*
- * UTF8 to local code conversion map
+ * UTF-8 to local code conversion map
+ * Note that we limit the max length of UTF-8 to 4 bytes,
+ * which is UCS-4 00010000-001FFFFF range.
  */
 typedef struct
 {
-	unsigned int utf;			/* UTF8 */
-	unsigned int code;			/* local code */
+	uint32 utf;			/* UTF-8 */
+	uint32 code;		/* local code */
 } pg_utf_to_local;
 
 /*
- * local code to UTF8 conversion map
+ * local code to UTF-8 conversion map
  */
 typedef struct
 {
-	unsigned int code;			/* local code */
-	unsigned int utf;			/* UTF8 */
+	uint32 code;		/* local code */
+	uint32 utf;			/* UTF-8 */
 } pg_local_to_utf;
 
+/*
+ * UTF-8 to local code conversion map(combined characters)
+ */
+typedef struct
+{
+	uint32 utf1;			/* UTF-8 code 1 */
+	uint32 utf2;			/* UTF-8 code 2 */
+	uint32 code;			/* local code */
+} pg_utf_to_local_combined;
+
+/*
+ * local code to UTF-8 conversion map(combined characters)
+ */
+typedef struct
+{
+	uint32 code;			/* local code */
+	uint32 utf1;			/* UTF-8 code 1 */
+	uint32 utf2;			/* UTF-8 code 2 */
+} pg_local_to_utf_combined;
+
 extern int	pg_mb2wchar(const char *from, pg_wchar *to);
 extern int	pg_mb2wchar_with_len(const char *from, pg_wchar *to, int len);
 extern int	pg_encoding_mb2wchar_with_len(int encoding,
@@ -338,10 +362,12 @@ extern unsigned short BIG5toCNS(unsigned short big5, unsigned char *lc);
 extern unsigned short CNStoBIG5(unsigned short cns, unsigned char lc);
 
 extern void LocalToUtf(const unsigned char *iso, unsigned char *utf,
-		   const pg_local_to_utf *map, int size, int encoding, int len);
+					   const pg_local_to_utf *map, const pg_local_to_utf_combined *cmap,
+					   int size1, int size2, int encoding, int len);
 
 extern void UtfToLocal(const unsigned char *utf, unsigned char *iso,
-		   const pg_utf_to_local *map, int size, int encoding, int len);
+					   const pg_utf_to_local *map, const pg_utf_to_local_combined *cmap,
+					   int size1, int size2, int encoding, int len);
 
 extern bool pg_verifymbstr(const char *mbstr, int len, bool noError);
 extern bool pg_verify_mbstr(int encoding, const char *mbstr, int len,

src/test/regress/expected/conversion.out

@@ -1642,6 +1642,84 @@ SELECT CONVERT('foo', 'WIN1257', 'UTF8');
  foo
 (1 row)
 
+-- UTF8 --> EUC_JIS_2004
+SELECT CONVERT('foo' USING utf8_to_euc_jis_2004);
+ convert_using 
+---------------
+ foo
+(1 row)
+
+SELECT CONVERT('foo', 'UTF8', 'EUC_JIS_2004');
+ convert 
+---------
+ foo
+(1 row)
+
+-- EUC_JIS_2004 --> UTF8
+SELECT CONVERT('foo' USING euc_jis_2004_to_utf8);
+ convert_using 
+---------------
+ foo
+(1 row)
+
+SELECT CONVERT('foo', 'EUC_JIS_2004', 'UTF8');
+ convert 
+---------
+ foo
+(1 row)
+
+-- UTF8 --> SHIFT_JIS_2004
+SELECT CONVERT('foo' USING utf8_to_euc_jis_2004);
+ convert_using 
+---------------
+ foo
+(1 row)
+
+SELECT CONVERT('foo', 'UTF8', 'SHIFT_JIS_2004');
+ convert 
+---------
+ foo
+(1 row)
+
+-- SHIFT_JIS_2004 --> UTF8
+SELECT CONVERT('foo' USING shift_jis_2004_to_utf8);
+ convert_using 
+---------------
+ foo
+(1 row)
+
+SELECT CONVERT('foo', 'SHIFT_JIS_2004', 'UTF8');
+ convert 
+---------
+ foo
+(1 row)
+
+-- EUC_JIS_2004 --> SHIFT_JIS_2004
+SELECT CONVERT('foo' USING euc_jis_2004_to_shift_jis_2004);
+ convert_using 
+---------------
+ foo
+(1 row)
+
+SELECT CONVERT('foo', 'EUC_JIS_2004', 'SHIFT_JIS_2004');
+ convert 
+---------
+ foo
+(1 row)
+
+-- SHIFT_JIS_2004 --> EUC_JIS_2004
+SELECT CONVERT('foo' USING shift_jis_2004_to_euc_jis_2004);
+ convert_using 
+---------------
+ foo
+(1 row)
+
+SELECT CONVERT('foo', 'SHIFT_JIS_2004', 'EUC_JIS_2004');
+ convert 
+---------
+ foo
+(1 row)
+
 --
 -- return to the super user
 --

src/test/regress/sql/conversion.sql

@@ -399,6 +399,24 @@ SELECT CONVERT('foo', 'UTF8', 'WIN1257');
 -- WIN1257 --> UTF8
 SELECT CONVERT('foo' USING windows_1257_to_utf8);
 SELECT CONVERT('foo', 'WIN1257', 'UTF8');
+-- UTF8 --> EUC_JIS_2004
+SELECT CONVERT('foo' USING utf8_to_euc_jis_2004);
+SELECT CONVERT('foo', 'UTF8', 'EUC_JIS_2004');
+-- EUC_JIS_2004 --> UTF8
+SELECT CONVERT('foo' USING euc_jis_2004_to_utf8);
+SELECT CONVERT('foo', 'EUC_JIS_2004', 'UTF8');
+-- UTF8 --> SHIFT_JIS_2004
+SELECT CONVERT('foo' USING utf8_to_euc_jis_2004);
+SELECT CONVERT('foo', 'UTF8', 'SHIFT_JIS_2004');
+-- SHIFT_JIS_2004 --> UTF8
+SELECT CONVERT('foo' USING shift_jis_2004_to_utf8);
+SELECT CONVERT('foo', 'SHIFT_JIS_2004', 'UTF8');
+-- EUC_JIS_2004 --> SHIFT_JIS_2004
+SELECT CONVERT('foo' USING euc_jis_2004_to_shift_jis_2004);
+SELECT CONVERT('foo', 'EUC_JIS_2004', 'SHIFT_JIS_2004');
+-- SHIFT_JIS_2004 --> EUC_JIS_2004
+SELECT CONVERT('foo' USING shift_jis_2004_to_euc_jis_2004);
+SELECT CONVERT('foo', 'SHIFT_JIS_2004', 'EUC_JIS_2004');
 --
 -- return to the super user
 --