Skip to content

P
Postgres FD Implementation
Commit e3d7de6b authored by Bruce Momjian's avatar Bruce Momjian
Browse files
Options

Rename canonical encodings, per Peter: 

	UNICODE => UTF8
	ALT => WIN866
	WIN => WIN1251
	TCVN => WIN1258

The old codes continue to work.
parent c6ad5c2e
Expand all Show whitespace changes
Inline Side-by-side
Showing with 950 additions and 1015 deletions
doc/README.mb.jp
View file @ e3d7de6b
......@@ -299,7 +299,7 @@ o set client_encoding $B%3%^%s%I$r;H$&J}K!(B
PostgreSQL$B$N(BCONVERT$B$H5!G=$O$[$H$s$IF1$8$G$9$,!$8F$S=P$77A<0$,0[$j$^(B
$B$9!%(B
SELECT convert(text using euc_jp_to_utf_8) FROM unicode_tbl;
SELECT convert(text using euc_jp_to_utf8) FROM unicode_tbl;
"using" $B$N8e$N0z?t$O!V%3%s%P!<%8%g%sL>!W$G$9!%$3$NNc$G$O!$(BEUC_JP $B$+(B
$B$i(B UTF-8 $B$KJQ49$9$k%3%s%P!<%8%g%s$r;XDj$7$F$$$^$9!%Dj5A:Q$N%3%s%P!<(B
......
doc/TODO
View file @ e3d7de6b
......@@ -215,7 +215,7 @@ Multi-Language Support
* Optimize locale to have minimal performance impact when not used
* Support multiple simultaneous character sets, per SQL92
* Improve Unicode combined character handling (?)
* Improve UTF8 combined character handling (?)
* Add octet_length_server() and octet_length_client()
* Make octet_length_client() the same as octet_length()?
......
doc/src/sgml/charset.sgml
View file @ e3d7de6b
This diff is collapsed.
doc/src/sgml/func.sgml
View file @ e3d7de6b
This diff is collapsed.
doc/src/sgml/ref/alter_conversion.sgml
View file @ e3d7de6b
<!--
$PostgreSQL: pgsql/doc/src/sgml/ref/alter_conversion.sgml,v 1.5 2004/06/25 21:55:50 tgl Exp $
$PostgreSQL: pgsql/doc/src/sgml/ref/alter_conversion.sgml,v 1.6 2005/03/07 04:30:51 momjian Exp $
PostgreSQL documentation
-->
......@@ -72,18 +72,18 @@ ALTER CONVERSION <replaceable>name</replaceable> OWNER TO <replaceable>newowner<
<title>Examples</title>
<para>
To rename the conversion <literal>iso_8859_1_to_utf_8</literal> to
To rename the conversion <literal>iso_8859_1_to_utf8</literal> to
<literal>latin1_to_unicode</literal>:
<programlisting>
ALTER CONVERSION iso_8859_1_to_utf_8 RENAME TO latin1_to_unicode;
ALTER CONVERSION iso_8859_1_to_utf8 RENAME TO latin1_to_unicode;
</programlisting>
</para>
<para>
To change the owner of the conversion <literal>iso_8859_1_to_utf_8</literal> to
To change the owner of the conversion <literal>iso_8859_1_to_utf8</literal> to
<literal>joe</literal>:
<programlisting>
ALTER CONVERSION iso_8859_1_to_utf_8 OWNER TO joe;
ALTER CONVERSION iso_8859_1_to_utf8 OWNER TO joe;
</programlisting>
</para>
</refsect1>
......
doc/src/sgml/ref/comment.sgml
View file @ e3d7de6b
<!--
$PostgreSQL: pgsql/doc/src/sgml/ref/comment.sgml,v 1.26 2005/01/04 00:39:53 tgl Exp $
$PostgreSQL: pgsql/doc/src/sgml/ref/comment.sgml,v 1.27 2005/03/07 04:30:51 momjian Exp $
PostgreSQL documentation
-->
......@@ -195,7 +195,7 @@ COMMENT ON TABLE mytable IS NULL;
COMMENT ON AGGREGATE my_aggregate (double precision) IS 'Computes sample variance';
COMMENT ON CAST (text AS int4) IS 'Allow casts from text to int4';
COMMENT ON COLUMN my_table.my_column IS 'Employee ID number';
COMMENT ON CONVERSION my_conv IS 'Conversion to Unicode';
COMMENT ON CONVERSION my_conv IS 'Conversion to UTF8';
COMMENT ON DATABASE my_database IS 'Development Database';
COMMENT ON DOMAIN my_domain IS 'Email Address Domain';
COMMENT ON FUNCTION my_function (timestamp) IS 'Returns Roman Numeral';
......
doc/src/sgml/ref/create_conversion.sgml
View file @ e3d7de6b
<!-- $PostgreSQL: pgsql/doc/src/sgml/ref/create_conversion.sgml,v 1.14 2003/11/29 19:51:38 pgsql Exp $ -->
<!-- $PostgreSQL: pgsql/doc/src/sgml/ref/create_conversion.sgml,v 1.15 2005/03/07 04:30:51 momjian Exp $ -->
<refentry id="SQL-CREATECONVERSION">
<refmeta>
......@@ -136,10 +136,10 @@ conv_proc(
<title>Examples</title>
<para>
To create a conversion from encoding <literal>UNICODE</literal> to
To create a conversion from encoding <literal>UTF8</literal> to
<literal>LATIN1</literal> using <function>myfunc</>:
<programlisting>
CREATE CONVERSION myconv FOR 'UNICODE' TO 'LATIN1' FROM myfunc;
CREATE CONVERSION myconv FOR 'UTF8' TO 'LATIN1' FROM myfunc;
</programlisting>
</para>
</refsect1>
......
src/backend/utils/adt/selfuncs.c
View file @ e3d7de6b
......@@ -15,7 +15,7 @@
*
*
* IDENTIFICATION
* $PostgreSQL: pgsql/src/backend/utils/adt/selfuncs.c,v 1.172 2005/03/06 22:15:04 tgl Exp $
* $PostgreSQL: pgsql/src/backend/utils/adt/selfuncs.c,v 1.173 2005/03/07 04:30:51 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......@@ -4035,7 +4035,7 @@ pattern_selectivity(Const *patt, Pattern_Type ptype)
*
* NOTE: at present this assumes we are in the C locale, so that simple
* bytewise comparison applies. However, we might be in a multibyte
* encoding such as UTF-8, so we do have to watch out for generating
* encoding such as UTF8, so we do have to watch out for generating
* invalid encoding sequences.
*/
Const *
......
src/backend/utils/mb/Unicode/Makefile
View file @ e3d7de6b
......@@ -4,7 +4,7 @@
#
# Copyright (c) 2001-2005, PostgreSQL Global Development Group
#
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/Makefile,v 1.8 2005/01/01 20:44:18 tgl Exp $
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/Makefile,v 1.9 2005/03/07 04:30:52 momjian Exp $
#
#-------------------------------------------------------------------------
......@@ -18,8 +18,8 @@ ISO8859MAPS=iso8859_2_to_utf8.map iso8859_3_to_utf8.map \
utf8_to_iso8859_4.map utf8_to_iso8859_5.map
CYRILLICMAPS=koi8r_to_utf8.map win1251_to_utf8.map alt_to_utf8.map\
utf8_to_koi8r.map utf8_to_win1251.map utf8_to_alt.map
CYRILLICMAPS=koi8r_to_utf8.map win1251_to_utf8.map win866_to_utf8.map\
utf8_to_koi8r.map utf8_to_win1251.map utf8_to_win866.map
MAPS= $(ISO8859MAPS) $(CYRILLICMAPS)\
big5_to_utf8.map euc_cn_to_utf8.map euc_jp_to_utf8.map \
......
src/backend/utils/mb/Unicode/UCS_to_8859.pl
View file @ e3d7de6b
......@@ -2,7 +2,7 @@
#
# Copyright (c) 2001-2005, PostgreSQL Global Development Group
#
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_8859.pl,v 1.7 2005/01/01 20:44:18 tgl Exp $
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_8859.pl,v 1.8 2005/03/07 04:30:52 momjian Exp $
#
# Generate UTF-8 <--> ISO8859 code conversion tables from
# map files provided by Unicode organization.
......@@ -39,7 +39,7 @@ foreach $charset (@charsets) {
if( $code >= 0x80){
$utf = &ucs2utf($ucs);
if( $array{ $utf } ne "" ){
printf STDERR "Warning: duplicate unicode: %04x\n",$ucs;
printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs;
next;
}
$count++;
......@@ -83,7 +83,7 @@ foreach $charset (@charsets) {
if($code >= 0x80){
$utf = &ucs2utf($ucs);
if( $array{ $utf } ne "" ){
printf STDERR "Warning: duplicate unicode: %04x\n",$ucs;
printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs;
next;
}
$count++;
......
src/backend/utils/mb/Unicode/UCS_to_BIG5.pl
View file @ e3d7de6b
......@@ -2,7 +2,7 @@
#
# Copyright (c) 2001-2005, PostgreSQL Global Development Group
#
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_BIG5.pl,v 1.6 2005/01/01 20:44:18 tgl Exp $
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_BIG5.pl,v 1.7 2005/03/07 04:30:52 momjian Exp $
#
# Generate UTF-8 <--> BIG5 code conversion tables from
# map files provided by Unicode organization.
......@@ -35,7 +35,7 @@ while( <FILE> ){
if( $code >= 0x80 && $ucs >= 0x0080 ){
$utf = &ucs2utf($ucs);
if( $array{ $utf } ne "" ){
printf STDERR "Warning: duplicate unicode: %04x\n",$ucs;
printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs;
next;
}
$count++;
......
src/backend/utils/mb/Unicode/UCS_to_EUC_CN.pl
View file @ e3d7de6b
......@@ -2,7 +2,7 @@
#
# Copyright (c) 2001-2005, PostgreSQL Global Development Group
#
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_EUC_CN.pl,v 1.6 2005/01/01 20:44:18 tgl Exp $
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_EUC_CN.pl,v 1.7 2005/03/07 04:30:52 momjian Exp $
#
# Generate UTF-8 <--> EUC_CN code conversion tables from
# map files provided by Unicode organization.
......@@ -35,7 +35,7 @@ while( <FILE> ){
if( $code >= 0x80 && $ucs >= 0x0080 ){
$utf = &ucs2utf($ucs);
if( $array{ $utf } ne "" ){
printf STDERR "Warning: duplicate unicode: %04x\n",$ucs;
printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs;
next;
}
$count++;
......
src/backend/utils/mb/Unicode/UCS_to_EUC_JP.pl
View file @ e3d7de6b
......@@ -2,7 +2,7 @@
#
# Copyright (c) 2001-2005, PostgreSQL Global Development Group
#
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_EUC_JP.pl,v 1.6 2005/01/01 20:44:18 tgl Exp $
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_EUC_JP.pl,v 1.7 2005/03/07 04:30:52 momjian Exp $
#
# Generate UTF-8 <--> EUC_JP code conversion tables from
# map files provided by Unicode organization.
......@@ -51,7 +51,7 @@ while( <FILE> ){
if( $code >= 0x80 && $ucs >= 0x0080 ){
$utf = &ucs2utf($ucs);
if( $array{ $utf } ne "" ){
printf STDERR "Warning: duplicate unicode: %04x\n",$ucs;
printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs;
next;
}
$count++;
......@@ -80,7 +80,7 @@ while( <FILE> ){
if( $code >= 0x80 && $ucs >= 0x0080 ){
$utf = &ucs2utf($ucs);
if( $array{ $utf } ne "" ){
printf STDERR "Warning: duplicate unicode: %04x\n",$ucs;
printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs;
next;
}
$count++;
......@@ -108,7 +108,7 @@ while( <FILE> ){
if( $code >= 0x80 && $ucs >= 0x0080 ){
$utf = &ucs2utf($ucs);
if( $array{ $utf } ne "" ){
printf STDERR "Warning: duplicate unicode: %04x\n",$ucs;
printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs;
next;
}
$count++;
......
src/backend/utils/mb/Unicode/UCS_to_EUC_KR.pl
View file @ e3d7de6b
......@@ -2,7 +2,7 @@
#
# Copyright (c) 2001-2005, PostgreSQL Global Development Group
#
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_EUC_KR.pl,v 1.7 2005/01/01 20:44:18 tgl Exp $
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_EUC_KR.pl,v 1.8 2005/03/07 04:30:52 momjian Exp $
#
# Generate UTF-8 <--> EUC_KR code conversion tables from
# map files provided by Unicode organization.
......@@ -35,7 +35,7 @@ while( <FILE> ){
if( $code >= 0x80 && $ucs >= 0x0080 ){
$utf = &ucs2utf($ucs);
if( $array{ $utf } ne "" ){
printf STDERR "Warning: duplicate unicode: %04x\n",$ucs;
printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs;
next;
}
$count++;
......
src/backend/utils/mb/Unicode/UCS_to_EUC_TW.pl
View file @ e3d7de6b
......@@ -2,7 +2,7 @@
#
# Copyright (c) 2001-2005, PostgreSQL Global Development Group
#
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_EUC_TW.pl,v 1.6 2005/01/01 20:44:18 tgl Exp $
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_EUC_TW.pl,v 1.7 2005/03/07 04:30:52 momjian Exp $
#
# Generate UTF-8 <--> EUC_TW code conversion tables from
# map files provided by Unicode organization.
......@@ -36,7 +36,7 @@ while( <FILE> ){
if( $code >= 0x80 && $ucs >= 0x0080 ){
$utf = &ucs2utf($ucs);
if( $array{ $utf } ne "" ){
printf STDERR "Warning: duplicate unicode: %04x\n",$ucs;
printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs;
next;
}
$count++;
......
src/backend/utils/mb/Unicode/UCS_to_GB18030.pl
View file @ e3d7de6b
......@@ -2,7 +2,7 @@
#
# Copyright 2002 by Bill Huang
#
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_GB18030.pl,v 1.4 2003/11/29 22:40:01 pgsql Exp $
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_GB18030.pl,v 1.5 2005/03/07 04:30:52 momjian Exp $
#
# Generate UTF-8 <--> GB18030 code conversion tables from
# map files provided by Unicode organization.
......@@ -35,7 +35,7 @@ while( <FILE> ){
if( $code >= 0x80 && $ucs >= 0x0080 ){
$utf = &ucs2utf($ucs);
if( $array{ $utf } ne "" ){
printf STDERR "Warning: duplicate unicode: %04x\n",$ucs;
printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs;
next;
}
$count++;
......
src/backend/utils/mb/Unicode/UCS_to_GBK.pl
View file @ e3d7de6b
......@@ -2,7 +2,7 @@
#
# Copyright (c) 2001-2005, PostgreSQL Global Development Group
#
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_GBK.pl,v 1.5 2005/01/01 20:44:18 tgl Exp $
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_GBK.pl,v 1.6 2005/03/07 04:30:52 momjian Exp $
#
#
# Generate UTF-8 <--> GBK code conversion tables from
......@@ -36,7 +36,7 @@ while( <FILE> ){
if( $code >= 0x80 && $ucs >= 0x0080 ){
$utf = &ucs2utf($ucs);
if( $array{ $utf } ne "" ){
printf STDERR "Warning: duplicate unicode: %04x\n",$ucs;
printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs;
next;
}
$count++;
......
src/backend/utils/mb/Unicode/UCS_to_JOHAB.pl
View file @ e3d7de6b
......@@ -2,7 +2,7 @@
#
# Copyright (c) 2001-2005, PostgreSQL Global Development Group
#
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_JOHAB.pl,v 1.5 2005/01/01 20:44:18 tgl Exp $
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_JOHAB.pl,v 1.6 2005/03/07 04:30:52 momjian Exp $
#
# Generate UTF-8 <--> JOHAB code conversion tables from
# map files provided by Unicode organization.
......@@ -35,7 +35,7 @@ while( <FILE> ){
if( $code >= 0x80 && $ucs >= 0x0080 ){
$utf = &ucs2utf($ucs);
if( $array{ $utf } ne "" ){
printf STDERR "Warning: duplicate unicode: %04x\n",$ucs;
printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs;
next;
}
$count++;
......
src/backend/utils/mb/Unicode/UCS_to_SJIS.pl
View file @ e3d7de6b
......@@ -2,7 +2,7 @@
#
# Copyright (c) 2001-2005, PostgreSQL Global Development Group
#
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_SJIS.pl,v 1.7 2005/01/01 20:44:18 tgl Exp $
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_SJIS.pl,v 1.8 2005/03/07 04:30:52 momjian Exp $
#
# Generate UTF-8 <--> SJIS code conversion tables from
# map files provided by Unicode organization.
......@@ -52,7 +52,7 @@ while( <FILE> ){
|| (( $code >= 0x879a )
&& ( $code <= 0x879c )))
{
printf STDERR "Warning: duplicate unicode : UCS=0x%04x SJIS=0x%04x\n",$ucs,$code;
printf STDERR "Warning: duplicate UTF8 : UCS=0x%04x SJIS=0x%04x\n",$ucs,$code;
next;
}
$count++;
......
src/backend/utils/mb/Unicode/UCS_to_UHC.pl
View file @ e3d7de6b
......@@ -2,7 +2,7 @@
#
# Copyright (c) 2001-2005, PostgreSQL Global Development Group
#
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_UHC.pl,v 1.5 2005/01/01 20:44:18 tgl Exp $
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_UHC.pl,v 1.6 2005/03/07 04:30:52 momjian Exp $
#
# Generate UTF-8 <--> BIG5 code conversion tables from
# map files provided by Unicode organization.
......@@ -35,7 +35,7 @@ while( <FILE> ){
if( $code >= 0x80 && $ucs >= 0x0080 ){
$utf = &ucs2utf($ucs);
if( $array{ $utf } ne "" ){
printf STDERR "Warning: duplicate unicode: %04x\n",$ucs;
printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs;
next;
}
$count++;
......
src/backend/utils/mb/Unicode/UCS_to_WIN874.pl
View file @ e3d7de6b
......@@ -2,7 +2,7 @@
#
# Copyright (c) 2001-2005, PostgreSQL Global Development Group
#
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_WIN874.pl,v 1.5 2005/01/01 20:44:18 tgl Exp $
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_WIN874.pl,v 1.6 2005/03/07 04:30:52 momjian Exp $
#
# Generate UTF-8 <--> WIN874 code conversion tables from
# map files provided by Unicode organization.
......@@ -35,7 +35,7 @@ while( <FILE> ){
if( $code >= 0x80 && $ucs >= 0x0080 ){
$utf = &ucs2utf($ucs);
if( $array{ $utf } ne "" ){
printf STDERR "Warning: duplicate unicode: %04x\n",$ucs;
printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs;
next;
}
$count++;
......
src/backend/utils/mb/Unicode/UCS_to_WINX.pl
View file @ e3d7de6b
......@@ -2,7 +2,7 @@
#
# Copyright (c) 2001-2005, PostgreSQL Global Development Group
#
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_WINX.pl,v 1.5 2005/01/01 20:44:18 tgl Exp $
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_WINX.pl,v 1.6 2005/03/07 04:30:52 momjian Exp $
#
# Generate UTF-8 <--> WINX code conversion tables from
# map files provided by Unicode organization.
......@@ -42,7 +42,7 @@ foreach $charset (@charsets) {
if( $code >= 0x80){
$utf = &ucs2utf($ucs);
if( $array{ $utf } ne "" ){
printf STDERR "Warning: duplicate unicode: %04x\n",$ucs;
printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs;
next;
}
$count++;
......@@ -86,7 +86,7 @@ foreach $charset (@charsets) {
if($code >= 0x80){
$utf = &ucs2utf($ucs);
if( $array{ $utf } ne "" ){
printf STDERR "Warning: duplicate unicode: %04x\n",$ucs;
printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs;
next;
}
$count++;
......
src/backend/utils/mb/Unicode/UCS_to_cyrillic.pl
View file @ e3d7de6b
......@@ -2,7 +2,7 @@
#
# Copyright (c) 2001-2005, PostgreSQL Global Development Group
#
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_cyrillic.pl,v 1.6 2005/01/01 20:44:18 tgl Exp $
# $PostgreSQL: pgsql/src/backend/utils/mb/Unicode/UCS_to_cyrillic.pl,v 1.7 2005/03/07 04:30:52 momjian Exp $
#
# Generate UTF-8 <--> ISO8859 code conversion tables from
# map files provided by Unicode organization.
......@@ -17,8 +17,8 @@
require "ucs2utf.pl";
%filename = ('KOI8R'=>'koi8-r.txt',
'WIN1251'=>'cp1251.txt',
'ALT'=>'cp866.txt');
@charsets = ('KOI8R','ALT','WIN1251');
'WIN866'=>'cp866.txt');
@charsets = ('KOI8R','WIN866','WIN1251');
foreach $charset (@charsets) {
#
......@@ -41,7 +41,7 @@ foreach $charset (@charsets) {
if( $code >= 0x80){
$utf = &ucs2utf($ucs);
if( $array{ $utf } ne "" ){
printf STDERR "Warning: duplicate unicode: %04x\n",$ucs;
printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs;
next;
}
$count++;
......@@ -85,7 +85,7 @@ foreach $charset (@charsets) {
if($code >= 0x80){
$utf = &ucs2utf($ucs);
if( $array{ $utf } ne "" ){
printf STDERR "Warning: duplicate unicode: %04x\n",$ucs;
printf STDERR "Warning: duplicate UTF8: %04x\n",$ucs;
next;
}
$count++;
......
src/backend/utils/mb/Unicode/utf8_to_tcvn.map → src/backend/utils/mb/Unicode/utf8_to_win1258.map
View file @ e3d7de6b
static pg_utf_to_local ULmapTCVN[ 120 ] = {
static pg_utf_to_local ULmapWIN1258[ 120 ] = {
{0x0000, 0x0081},
{0xc2a0, 0x00a0},
{0xc2a1, 0x00a1},
......
src/backend/utils/mb/Unicode/utf8_to_alt.map → src/backend/utils/mb/Unicode/utf8_to_win866.map
View file @ e3d7de6b
static pg_utf_to_local ULmap_ALT[ 128 ] = {
static pg_utf_to_local ULmap_WIN866[ 128 ] = {
{0xc2a0, 0x00ff},
{0xc2a4, 0x00fd},
{0xc2b0, 0x00f8},
......
src/backend/utils/mb/Unicode/tcvn_to_utf8.map → src/backend/utils/mb/Unicode/win1258_to_utf8.map
View file @ e3d7de6b
static pg_local_to_utf LUmapTCVN[ 128 ] = {
static pg_local_to_utf LUmapWIN1258[ 128 ] = {
{0x0080, 0xe282ac},
{0x0081, 0x0000},
{0x0082, 0xe2809a},
......
src/backend/utils/mb/Unicode/alt_to_utf8.map → src/backend/utils/mb/Unicode/win866_to_utf8.map
View file @ e3d7de6b
static pg_local_to_utf LUmapALT[ 128 ] = {
static pg_local_to_utf LUmapWIN866[ 128 ] = {
{0x0080, 0xd090},
{0x0081, 0xd091},
{0x0082, 0xd092},
......
src/backend/utils/mb/conv.c
View file @ e3d7de6b
......@@ -6,7 +6,7 @@
* Portions Copyright (c) 1994, Regents of the University of California
*
* IDENTIFICATION
* $PostgreSQL: pgsql/src/backend/utils/mb/conv.c,v 1.51 2004/12/31 22:01:42 pgsql Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/conv.c,v 1.52 2005/03/07 04:30:52 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......@@ -303,7 +303,7 @@ mic2latin_with_table(
/*
* comparison routine for bsearch()
* this routine is intended for UTF-8 -> local code
* this routine is intended for UTF8 -> local code
*/
static int
compare1(const void *p1, const void *p2)
......@@ -318,7 +318,7 @@ compare1(const void *p1, const void *p2)
/*
* comparison routine for bsearch()
* this routine is intended for local code -> UTF-8
* this routine is intended for local code -> UTF8
*/
static int
compare2(const void *p1, const void *p2)
......@@ -332,9 +332,9 @@ compare2(const void *p1, const void *p2)
}
/*
* UTF-8 ---> local code
* UTF8 ---> local code
*
* utf: input UTF-8 string. Its length is limited by "len" parameter
* utf: input UTF8 string. Its length is limited by "len" parameter
* or a null terminator.
* iso: pointer to the output.
* map: the conversion map.
......@@ -373,7 +373,7 @@ UtfToLocal(unsigned char *utf, unsigned char *iso,
{
ereport(WARNING,
(errcode(ERRCODE_UNTRANSLATABLE_CHARACTER),
errmsg("ignoring unconvertible UTF-8 character 0x%04x",
errmsg("ignoring unconvertible UTF8 character 0x%04x",
iutf)));
continue;
}
......@@ -390,7 +390,7 @@ UtfToLocal(unsigned char *utf, unsigned char *iso,
}
/*
* local code ---> UTF-8
* local code ---> UTF8
*/
void
LocalToUtf(unsigned char *iso, unsigned char *utf,
......
src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c
View file @ e3d7de6b
......@@ -6,7 +6,7 @@
* Portions Copyright (c) 1994, Regents of the University of California
*
* IDENTIFICATION
* $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c,v 1.9 2004/12/31 22:01:48 pgsql Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/cyrillic_and_mic/cyrillic_and_mic.c,v 1.10 2005/03/07 04:30:52 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......@@ -23,20 +23,20 @@ PG_FUNCTION_INFO_V1(iso_to_mic);
PG_FUNCTION_INFO_V1(mic_to_iso);
PG_FUNCTION_INFO_V1(win1251_to_mic);
PG_FUNCTION_INFO_V1(mic_to_win1251);
PG_FUNCTION_INFO_V1(alt_to_mic);
PG_FUNCTION_INFO_V1(mic_to_alt);
PG_FUNCTION_INFO_V1(win866_to_mic);
PG_FUNCTION_INFO_V1(mic_to_win866);
PG_FUNCTION_INFO_V1(koi8r_to_win1251);
PG_FUNCTION_INFO_V1(win1251_to_koi8r);
PG_FUNCTION_INFO_V1(koi8r_to_alt);
PG_FUNCTION_INFO_V1(alt_to_koi8r);
PG_FUNCTION_INFO_V1(alt_to_win1251);
PG_FUNCTION_INFO_V1(win1251_to_alt);
PG_FUNCTION_INFO_V1(koi8r_to_win866);
PG_FUNCTION_INFO_V1(win866_to_koi8r);
PG_FUNCTION_INFO_V1(win866_to_win1251);
PG_FUNCTION_INFO_V1(win1251_to_win866);
PG_FUNCTION_INFO_V1(iso_to_koi8r);
PG_FUNCTION_INFO_V1(koi8r_to_iso);
PG_FUNCTION_INFO_V1(iso_to_win1251);
PG_FUNCTION_INFO_V1(win1251_to_iso);
PG_FUNCTION_INFO_V1(iso_to_alt);
PG_FUNCTION_INFO_V1(alt_to_iso);
PG_FUNCTION_INFO_V1(iso_to_win866);
PG_FUNCTION_INFO_V1(win866_to_iso);
extern Datum koi8r_to_mic(PG_FUNCTION_ARGS);
extern Datum mic_to_koi8r(PG_FUNCTION_ARGS);
......@@ -44,20 +44,20 @@ extern Datum iso_to_mic(PG_FUNCTION_ARGS);
extern Datum mic_to_iso(PG_FUNCTION_ARGS);
extern Datum win1251_to_mic(PG_FUNCTION_ARGS);
extern Datum mic_to_win1251(PG_FUNCTION_ARGS);
extern Datum alt_to_mic(PG_FUNCTION_ARGS);
extern Datum mic_to_alt(PG_FUNCTION_ARGS);
extern Datum win866_to_mic(PG_FUNCTION_ARGS);
extern Datum mic_to_win866(PG_FUNCTION_ARGS);
extern Datum koi8r_to_win1251(PG_FUNCTION_ARGS);
extern Datum win1251_to_koi8r(PG_FUNCTION_ARGS);
extern Datum koi8r_to_alt(PG_FUNCTION_ARGS);
extern Datum alt_to_koi8r(PG_FUNCTION_ARGS);
extern Datum alt_to_win1251(PG_FUNCTION_ARGS);
extern Datum win1251_to_alt(PG_FUNCTION_ARGS);
extern Datum koi8r_to_win866(PG_FUNCTION_ARGS);
extern Datum win866_to_koi8r(PG_FUNCTION_ARGS);
extern Datum win866_to_win1251(PG_FUNCTION_ARGS);
extern Datum win1251_to_win866(PG_FUNCTION_ARGS);
extern Datum iso_to_koi8r(PG_FUNCTION_ARGS);
extern Datum koi8r_to_iso(PG_FUNCTION_ARGS);
extern Datum iso_to_win1251(PG_FUNCTION_ARGS);
extern Datum win1251_to_iso(PG_FUNCTION_ARGS);
extern Datum iso_to_alt(PG_FUNCTION_ARGS);
extern Datum alt_to_iso(PG_FUNCTION_ARGS);
extern Datum iso_to_win866(PG_FUNCTION_ARGS);
extern Datum win866_to_iso(PG_FUNCTION_ARGS);
/* ----------
* conv_proc(
......@@ -76,8 +76,8 @@ static void iso2mic(unsigned char *l, unsigned char *p, int len);
static void mic2iso(unsigned char *mic, unsigned char *p, int len);
static void win12512mic(unsigned char *l, unsigned char *p, int len);
static void mic2win1251(unsigned char *mic, unsigned char *p, int len);
static void alt2mic(unsigned char *l, unsigned char *p, int len);
static void mic2alt(unsigned char *mic, unsigned char *p, int len);
static void win8662mic(unsigned char *l, unsigned char *p, int len);
static void mic2win866(unsigned char *mic, unsigned char *p, int len);
Datum
koi8r_to_mic(PG_FUNCTION_ARGS)
......@@ -176,33 +176,33 @@ mic_to_win1251(PG_FUNCTION_ARGS)
}
Datum
alt_to_mic(PG_FUNCTION_ARGS)
win866_to_mic(PG_FUNCTION_ARGS)
{
unsigned char *src = PG_GETARG_CSTRING(2);
unsigned char *dest = PG_GETARG_CSTRING(3);
int len = PG_GETARG_INT32(4);
Assert(PG_GETARG_INT32(0) == PG_ALT);
Assert(PG_GETARG_INT32(0) == PG_WIN866);
Assert(PG_GETARG_INT32(1) == PG_MULE_INTERNAL);
Assert(len >= 0);
alt2mic(src, dest, len);
win8662mic(src, dest, len);
PG_RETURN_VOID();
}
Datum
mic_to_alt(PG_FUNCTION_ARGS)
mic_to_win866(PG_FUNCTION_ARGS)
{
unsigned char *src = PG_GETARG_CSTRING(2);
unsigned char *dest = PG_GETARG_CSTRING(3);
int len = PG_GETARG_INT32(4);
Assert(PG_GETARG_INT32(0) == PG_MULE_INTERNAL);
Assert(PG_GETARG_INT32(1) == PG_ALT);
Assert(PG_GETARG_INT32(1) == PG_WIN866);
Assert(len >= 0);
mic2alt(src, dest, len);
mic2win866(src, dest, len);
PG_RETURN_VOID();
}
......@@ -248,7 +248,7 @@ win1251_to_koi8r(PG_FUNCTION_ARGS)
}
Datum
koi8r_to_alt(PG_FUNCTION_ARGS)
koi8r_to_win866(PG_FUNCTION_ARGS)
{
unsigned char *src = PG_GETARG_CSTRING(2);
unsigned char *dest = PG_GETARG_CSTRING(3);
......@@ -256,31 +256,31 @@ koi8r_to_alt(PG_FUNCTION_ARGS)
unsigned char *buf;
Assert(PG_GETARG_INT32(0) == PG_KOI8R);
Assert(PG_GETARG_INT32(1) == PG_ALT);
Assert(PG_GETARG_INT32(1) == PG_WIN866);
Assert(len >= 0);
buf = palloc(len * ENCODING_GROWTH_RATE);
koi8r2mic(src, buf, len);
mic2alt(buf, dest, strlen(buf));
mic2win866(buf, dest, strlen(buf));
pfree(buf);
PG_RETURN_VOID();
}
Datum
alt_to_koi8r(PG_FUNCTION_ARGS)
win866_to_koi8r(PG_FUNCTION_ARGS)
{
unsigned char *src = PG_GETARG_CSTRING(2);
unsigned char *dest = PG_GETARG_CSTRING(3);
int len = PG_GETARG_INT32(4);
unsigned char *buf;
Assert(PG_GETARG_INT32(0) == PG_ALT);
Assert(PG_GETARG_INT32(0) == PG_WIN866);
Assert(PG_GETARG_INT32(1) == PG_KOI8R);
Assert(len >= 0);
buf = palloc(len * ENCODING_GROWTH_RATE);
alt2mic(src, buf, len);
win8662mic(src, buf, len);
mic2koi8r(buf, dest, strlen(buf));
pfree(buf);
......@@ -288,19 +288,19 @@ alt_to_koi8r(PG_FUNCTION_ARGS)
}
Datum
alt_to_win1251(PG_FUNCTION_ARGS)
win866_to_win1251(PG_FUNCTION_ARGS)
{
unsigned char *src = PG_GETARG_CSTRING(2);
unsigned char *dest = PG_GETARG_CSTRING(3);
int len = PG_GETARG_INT32(4);
unsigned char *buf;
Assert(PG_GETARG_INT32(0) == PG_ALT);
Assert(PG_GETARG_INT32(0) == PG_WIN866);
Assert(PG_GETARG_INT32(1) == PG_WIN1251);
Assert(len >= 0);
buf = palloc(len * ENCODING_GROWTH_RATE);
alt2mic(src, buf, len);
win8662mic(src, buf, len);
mic2win1251(buf, dest, strlen(buf));
pfree(buf);
......@@ -308,7 +308,7 @@ alt_to_win1251(PG_FUNCTION_ARGS)
}
Datum
win1251_to_alt(PG_FUNCTION_ARGS)
win1251_to_win866(PG_FUNCTION_ARGS)
{
unsigned char *src = PG_GETARG_CSTRING(2);
unsigned char *dest = PG_GETARG_CSTRING(3);
......@@ -316,12 +316,12 @@ win1251_to_alt(PG_FUNCTION_ARGS)
unsigned char *buf;
Assert(PG_GETARG_INT32(0) == PG_WIN1251);
Assert(PG_GETARG_INT32(1) == PG_ALT);
Assert(PG_GETARG_INT32(1) == PG_WIN866);
Assert(len >= 0);
buf = palloc(len * ENCODING_GROWTH_RATE);
win12512mic(src, buf, len);
mic2alt(buf, dest, strlen(buf));
mic2win866(buf, dest, strlen(buf));
pfree(buf);
PG_RETURN_VOID();
......@@ -408,7 +408,7 @@ win1251_to_iso(PG_FUNCTION_ARGS)
}
Datum
iso_to_alt(PG_FUNCTION_ARGS)
iso_to_win866(PG_FUNCTION_ARGS)
{
unsigned char *src = PG_GETARG_CSTRING(2);
unsigned char *dest = PG_GETARG_CSTRING(3);
......@@ -416,32 +416,32 @@ iso_to_alt(PG_FUNCTION_ARGS)
unsigned char *buf;
Assert(PG_GETARG_INT32(0) == PG_ISO_8859_5);
Assert(PG_GETARG_INT32(1) == PG_ALT);
Assert(PG_GETARG_INT32(1) == PG_WIN866);
Assert(len >= 0);
buf = palloc(len * ENCODING_GROWTH_RATE);
iso2mic(src, buf, len);
mic2alt(buf, dest, strlen(buf));
mic2win866(buf, dest, strlen(buf));
pfree(buf);
PG_RETURN_VOID();
}
Datum
alt_to_iso(PG_FUNCTION_ARGS)
win866_to_iso(PG_FUNCTION_ARGS)
{
unsigned char *src = PG_GETARG_CSTRING(2);
unsigned char *dest = PG_GETARG_CSTRING(3);
int len = PG_GETARG_INT32(4);
unsigned char *buf;
Assert(PG_GETARG_INT32(0) == PG_ALT);
Assert(PG_GETARG_INT32(0) == PG_WIN866);
Assert(PG_GETARG_INT32(1) == PG_ISO_8859_5);
Assert(len >= 0);
buf = palloc(len * ENCODING_GROWTH_RATE);
alt2mic(src, buf, len);
mic2alt(buf, dest, strlen(buf));
win8662mic(src, buf, len);
mic2win866(buf, dest, strlen(buf));
pfree(buf);
PG_RETURN_VOID();
......@@ -576,11 +576,11 @@ mic2win1251(unsigned char *mic, unsigned char *p, int len)
mic2latin_with_table(mic, p, len, LC_KOI8_R, koi2win);
}
/* alt2mic: CP866 to Mule internal code */
/* win8662mic: CP866 to Mule internal code */
static void
alt2mic(unsigned char *l, unsigned char *p, int len)
win8662mic(unsigned char *l, unsigned char *p, int len)
{
static unsigned char alt2koi[] = {
static unsigned char win8662koi[] = {
0xe1, 0xe2, 0xf7, 0xe7, 0xe4, 0xe5, 0xf6, 0xfa,
0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, 0xf0,
0xf2, 0xf3, 0xf4, 0xf5, 0xe6, 0xe8, 0xe3, 0xfe,
......@@ -599,14 +599,14 @@ alt2mic(unsigned char *l, unsigned char *p, int len)
0xb6, 0xa6, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00
};
latin2mic_with_table(l, p, len, LC_KOI8_R, alt2koi);
latin2mic_with_table(l, p, len, LC_KOI8_R, win8662koi);
}
/* mic2alt: Mule internal code to CP866 */
/* mic2win866: Mule internal code to CP866 */
static void
mic2alt(unsigned char *mic, unsigned char *p, int len)
mic2win866(unsigned char *mic, unsigned char *p, int len)
{
static unsigned char koi2alt[] = {
static unsigned char koi2win866[] = {
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
......@@ -625,5 +625,5 @@ mic2alt(unsigned char *mic, unsigned char *p, int len)
0x9c, 0x9b, 0x87, 0x98, 0x9d, 0x99, 0x97, 0x9a
};
mic2latin_with_table(mic, p, len, LC_KOI8_R, koi2alt);
mic2latin_with_table(mic, p, len, LC_KOI8_R, koi2win866);
}
src/backend/utils/mb/conversion_procs/regress_prolog
View file @ e3d7de6b
......@@ -3,19 +3,19 @@
--
CREATE USER conversion_test_user WITH NOCREATEDB NOCREATEUSER;
SET SESSION AUTHORIZATION conversion_test_user;
CREATE CONVERSION myconv FOR 'LATIN1' TO 'UNICODE' FROM iso8859_1_to_utf8;
CREATE CONVERSION myconv FOR 'LATIN1' TO 'UTF8' FROM iso8859_1_to_utf8;
--
-- cannot make same name conversion in same schema
--
CREATE CONVERSION myconv FOR 'LATIN1' TO 'UNICODE' FROM iso8859_1_to_utf8;
CREATE CONVERSION myconv FOR 'LATIN1' TO 'UTF8' FROM iso8859_1_to_utf8;
--
-- create default conversion with qualified name
--
CREATE DEFAULT CONVERSION public.mydef FOR 'LATIN1' TO 'UNICODE' FROM iso8859_1_to_utf8;
CREATE DEFAULT CONVERSION public.mydef FOR 'LATIN1' TO 'UTF8' FROM iso8859_1_to_utf8;
--
-- cannot make default conversion with same shcema/for_encoding/to_encoding
--
CREATE DEFAULT CONVERSION public.mydef2 FOR 'LATIN1' TO 'UNICODE' FROM iso8859_1_to_utf8;
CREATE DEFAULT CONVERSION public.mydef2 FOR 'LATIN1' TO 'UTF8' FROM iso8859_1_to_utf8;
--
-- drop user defined conversion
--
......
src/backend/utils/mb/conversion_procs/utf8_and_ascii/utf8_and_ascii.c
View file @ e3d7de6b
/*-------------------------------------------------------------------------
*
* ASCII <--> UTF-8
* ASCII <--> UTF8
*
* Portions Copyright (c) 1996-2005, 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_ascii/utf8_and_ascii.c,v 1.9 2004/12/31 22:02:11 pgsql Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_ascii/utf8_and_ascii.c,v 1.10 2005/03/07 04:30:52 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......
src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c
View file @ e3d7de6b
/*-------------------------------------------------------------------------
*
* BIG5 <--> UTF-8
* BIG5 <--> UTF8
*
* Portions Copyright (c) 1996-2005, 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_big5/utf8_and_big5.c,v 1.9 2004/12/31 22:02:13 pgsql Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_big5/utf8_and_big5.c,v 1.10 2005/03/07 04:30:53 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......
src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c
View file @ e3d7de6b
......@@ -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 1.9 2004/12/31 22:02:14 pgsql Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_cyrillic/utf8_and_cyrillic.c,v 1.10 2005/03/07 04:30:53 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......@@ -18,22 +18,22 @@
#include "../../Unicode/koi8r_to_utf8.map"
#include "../../Unicode/utf8_to_win1251.map"
#include "../../Unicode/win1251_to_utf8.map"
#include "../../Unicode/utf8_to_alt.map"
#include "../../Unicode/alt_to_utf8.map"
#include "../../Unicode/utf8_to_win866.map"
#include "../../Unicode/win866_to_utf8.map"
PG_FUNCTION_INFO_V1(utf8_to_koi8r);
PG_FUNCTION_INFO_V1(koi8r_to_utf8);
PG_FUNCTION_INFO_V1(utf8_to_win1251);
PG_FUNCTION_INFO_V1(win1251_to_utf8);
PG_FUNCTION_INFO_V1(utf8_to_alt);
PG_FUNCTION_INFO_V1(alt_to_utf8);
PG_FUNCTION_INFO_V1(utf8_to_win866);
PG_FUNCTION_INFO_V1(win866_to_utf8);
extern Datum utf8_to_koi8r(PG_FUNCTION_ARGS);
extern Datum koi8r_to_utf8(PG_FUNCTION_ARGS);
extern Datum utf8_to_win1251(PG_FUNCTION_ARGS);
extern Datum win1251_to_utf8(PG_FUNCTION_ARGS);
extern Datum utf8_to_alt(PG_FUNCTION_ARGS);
extern Datum alt_to_utf8(PG_FUNCTION_ARGS);
extern Datum utf8_to_win866(PG_FUNCTION_ARGS);
extern Datum win866_to_utf8(PG_FUNCTION_ARGS);
/* ----------
* conv_proc(
......@@ -115,35 +115,35 @@ win1251_to_utf8(PG_FUNCTION_ARGS)
}
Datum
utf8_to_alt(PG_FUNCTION_ARGS)
utf8_to_win866(PG_FUNCTION_ARGS)
{
unsigned char *src = PG_GETARG_CSTRING(2);
unsigned char *dest = PG_GETARG_CSTRING(3);
int len = PG_GETARG_INT32(4);
Assert(PG_GETARG_INT32(0) == PG_UTF8);
Assert(PG_GETARG_INT32(1) == PG_ALT);
Assert(PG_GETARG_INT32(1) == PG_WIN866);
Assert(len >= 0);
UtfToLocal(src, dest, ULmap_ALT,
sizeof(ULmap_ALT) / sizeof(pg_utf_to_local), len);
UtfToLocal(src, dest, ULmap_WIN866,
sizeof(ULmap_WIN866) / sizeof(pg_utf_to_local), len);
PG_RETURN_VOID();
}
Datum
alt_to_utf8(PG_FUNCTION_ARGS)
win866_to_utf8(PG_FUNCTION_ARGS)
{
unsigned char *src = PG_GETARG_CSTRING(2);
unsigned char *dest = PG_GETARG_CSTRING(3);
int len = PG_GETARG_INT32(4);
Assert(PG_GETARG_INT32(0) == PG_ALT);
Assert(PG_GETARG_INT32(0) == PG_WIN866);
Assert(PG_GETARG_INT32(1) == PG_UTF8);
Assert(len >= 0);
LocalToUtf(src, dest, LUmapALT,
sizeof(LUmapALT) / sizeof(pg_local_to_utf), PG_ALT, len);
LocalToUtf(src, dest, LUmapWIN866,
sizeof(LUmapWIN866) / sizeof(pg_local_to_utf), PG_WIN866, len);
PG_RETURN_VOID();
}
src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c
View file @ e3d7de6b
/*-------------------------------------------------------------------------
*
* EUC_CN <--> UTF-8
* EUC_CN <--> UTF8
*
* Portions Copyright (c) 1996-2005, 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_cn/utf8_and_euc_cn.c,v 1.9 2004/12/31 22:02:16 pgsql Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_cn/utf8_and_euc_cn.c,v 1.10 2005/03/07 04:30:53 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......
src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c
View file @ e3d7de6b
/*-------------------------------------------------------------------------
*
* EUC_JP <--> UTF-8
* EUC_JP <--> UTF8
*
* Portions Copyright (c) 1996-2005, 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_jp/utf8_and_euc_jp.c,v 1.9 2004/12/31 22:02:17 pgsql Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_jp/utf8_and_euc_jp.c,v 1.10 2005/03/07 04:30:53 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......
src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c
View file @ e3d7de6b
/*-------------------------------------------------------------------------
*
* EUC_KR <--> UTF-8
* EUC_KR <--> UTF8
*
* Portions Copyright (c) 1996-2005, 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_kr/utf8_and_euc_kr.c,v 1.9 2004/12/31 22:02:19 pgsql Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_kr/utf8_and_euc_kr.c,v 1.10 2005/03/07 04:30:53 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......
src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c
View file @ e3d7de6b
/*-------------------------------------------------------------------------
*
* EUC_TW <--> UTF-8
* EUC_TW <--> UTF8
*
* Portions Copyright (c) 1996-2005, 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_tw/utf8_and_euc_tw.c,v 1.9 2004/12/31 22:02:20 pgsql Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_euc_tw/utf8_and_euc_tw.c,v 1.10 2005/03/07 04:30:53 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......
src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c
View file @ e3d7de6b
/*-------------------------------------------------------------------------
*
* GB18030 <--> UTF-8
* GB18030 <--> UTF8
*
* Portions Copyright (c) 1996-2005, 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_gb18030/utf8_and_gb18030.c,v 1.9 2004/12/31 22:02:23 pgsql Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_gb18030/utf8_and_gb18030.c,v 1.10 2005/03/07 04:30:53 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......
src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c
View file @ e3d7de6b
/*-------------------------------------------------------------------------
*
* GBK <--> UTF-8
* GBK <--> UTF8
*
* Portions Copyright (c) 1996-2005, 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_gbk/utf8_and_gbk.c,v 1.9 2004/12/31 22:02:26 pgsql Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_gbk/utf8_and_gbk.c,v 1.10 2005/03/07 04:30:53 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......
src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c
View file @ e3d7de6b
/*-------------------------------------------------------------------------
*
* ISO 8859 2-16 <--> UTF-8
* ISO 8859 2-16 <--> UTF8
*
* Portions Copyright (c) 1996-2005, 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_iso8859/utf8_and_iso8859.c,v 1.11 2004/12/31 22:02:27 pgsql Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_iso8859/utf8_and_iso8859.c,v 1.12 2005/03/07 04:30:54 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......@@ -61,8 +61,8 @@ extern Datum utf8_to_iso8859(PG_FUNCTION_ARGS);
typedef struct
{
pg_enc encoding;
pg_local_to_utf *map1; /* to UTF-8 map name */
pg_utf_to_local *map2; /* from UTF-8 map name */
pg_local_to_utf *map1; /* to UTF8 map name */
pg_utf_to_local *map2; /* from UTF8 map name */
int size1; /* size of map1 */
int size2; /* size of map2 */
} pg_conv_map;
......@@ -74,7 +74,7 @@ static pg_conv_map maps[] = {
{PG_EUC_KR}, /* EUC for Korean */
{PG_EUC_TW}, /* EUC for Taiwan */
{PG_JOHAB}, /* EUC for Korean JOHAB */
{PG_UTF8}, /* Unicode UTF-8 */
{PG_UTF8}, /* Unicode UTF8 */
{PG_MULE_INTERNAL}, /* Mule internal code */
{PG_LATIN1}, /* ISO-8859-1 Latin 1 */
{PG_LATIN2, LUmapISO8859_2, ULmapISO8859_2,
......@@ -105,11 +105,11 @@ static pg_conv_map maps[] = {
sizeof(LUmapISO8859_16) / sizeof(pg_local_to_utf),
sizeof(ULmapISO8859_16) / sizeof(pg_utf_to_local)}, /* ISO-8859-16 Latin 10 */
{PG_WIN1256}, /* windows-1256 */
{PG_TCVN}, /* TCVN (Windows-1258) */
{PG_WIN1258}, /* Windows-1258 */
{PG_WIN874}, /* windows-874 */
{PG_KOI8R}, /* KOI8-R */
{PG_WIN1251}, /* windows-1251 (was: WIN) */
{PG_ALT}, /* (MS-DOS CP866) */
{PG_WIN866}, /* (MS-DOS CP866) */
{PG_ISO_8859_5, LUmapISO8859_5, ULmapISO8859_5,
sizeof(LUmapISO8859_5) / sizeof(pg_local_to_utf),
sizeof(ULmapISO8859_5) / sizeof(pg_utf_to_local)}, /* ISO-8859-5 */
......
src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c
View file @ e3d7de6b
/*-------------------------------------------------------------------------
*
* ISO8859_1 <--> UTF-8
* ISO8859_1 <--> UTF8
*
* Portions Copyright (c) 1996-2005, 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_iso8859_1/utf8_and_iso8859_1.c,v 1.10 2004/12/31 22:02:29 pgsql Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_iso8859_1/utf8_and_iso8859_1.c,v 1.11 2005/03/07 04:30:54 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......@@ -84,7 +84,7 @@ utf8_to_iso8859_1(PG_FUNCTION_ARGS)
len -= 2;
}
else if ((c & 0xe0) == 0xe0)
elog(ERROR, "could not convert UTF-8 character 0x%04x to ISO8859-1",
elog(ERROR, "could not convert UTF8 character 0x%04x to ISO8859-1",
c);
else
{
......
src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c
View file @ e3d7de6b
/*-------------------------------------------------------------------------
*
* JOHAB <--> UTF-8
* JOHAB <--> UTF8
*
* Portions Copyright (c) 1996-2005, 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_johab/utf8_and_johab.c,v 1.9 2004/12/31 22:02:31 pgsql Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_johab/utf8_and_johab.c,v 1.10 2005/03/07 04:30:54 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......
src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c
View file @ e3d7de6b
/*-------------------------------------------------------------------------
*
* SJIS <--> UTF-8
* SJIS <--> UTF8
*
* Portions Copyright (c) 1996-2005, 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_sjis/utf8_and_sjis.c,v 1.9 2004/12/31 22:02:33 pgsql Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_sjis/utf8_and_sjis.c,v 1.10 2005/03/07 04:30:54 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......
src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c
View file @ e3d7de6b
/*-------------------------------------------------------------------------
*
* UHC <--> UTF-8
* UHC <--> UTF8
*
* Portions Copyright (c) 1996-2005, 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_uhc/utf8_and_uhc.c,v 1.9 2004/12/31 22:02:36 pgsql Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_uhc/utf8_and_uhc.c,v 1.10 2005/03/07 04:30:54 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......
src/backend/utils/mb/conversion_procs/utf8_and_win1250/utf8_and_win1250.c
View file @ e3d7de6b
/*-------------------------------------------------------------------------
*
* WIN1250 and UTF-8
* WIN1250 and UTF8
*
* Portions Copyright (c) 1996-2005, 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_win1250/utf8_and_win1250.c,v 1.9 2004/12/31 22:02:38 pgsql Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_win1250/utf8_and_win1250.c,v 1.10 2005/03/07 04:30:54 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......
src/backend/utils/mb/conversion_procs/utf8_and_win1256/utf8_and_win1256.c
View file @ e3d7de6b
/*-------------------------------------------------------------------------
*
* WIN1256 and UTF-8
* WIN1256 and UTF8
*
* Portions Copyright (c) 1996-2005, 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_win1256/utf8_and_win1256.c,v 1.9 2004/12/31 22:02:39 pgsql Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_win1256/utf8_and_win1256.c,v 1.10 2005/03/07 04:30:54 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......
src/backend/utils/mb/conversion_procs/utf8_and_tcvn/Makefile → src/backend/utils/mb/conversion_procs/utf8_and_win1258/Makefile
View file @ e3d7de6b
#-------------------------------------------------------------------------
#
# $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_tcvn/Makefile,v 1.3 2003/11/29 22:40:38 pgsql Exp $
# $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_win1258/Makefile,v 1.1 2005/03/07 04:30:55 momjian Exp $
#
#-------------------------------------------------------------------------
subdir = src/backend/utils/mb/conversion_procs/utf8_and_tcvn
top_builddir = ../../../../../..
include $(top_builddir)/src/Makefile.global
NAME := utf8_and_tcvn
NAME := utf8_and_win1258
include $(srcdir)/../proc.mk
src/backend/utils/mb/conversion_procs/utf8_and_tcvn/utf8_and_tcvn.c → src/backend/utils/mb/conversion_procs/utf8_and_win1258/utf8_and_win1258.c
View file @ e3d7de6b
/*-------------------------------------------------------------------------
*
* TCVN <--> UTF-8
* WIN1258 <--> UTF8
*
* Portions Copyright (c) 1996-2005, 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_tcvn/utf8_and_tcvn.c,v 1.9 2004/12/31 22:02:35 pgsql Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_win1258/utf8_and_win1258.c,v 1.1 2005/03/07 04:30:55 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......@@ -14,14 +14,14 @@
#include "postgres.h"
#include "fmgr.h"
#include "mb/pg_wchar.h"
#include "../../Unicode/tcvn_to_utf8.map"
#include "../../Unicode/utf8_to_tcvn.map"
#include "../../Unicode/win1258_to_utf8.map"
#include "../../Unicode/utf8_to_win1258.map"
PG_FUNCTION_INFO_V1(tcvn_to_utf8);
PG_FUNCTION_INFO_V1(utf8_to_tcvn);
PG_FUNCTION_INFO_V1(win1258_to_utf8);
PG_FUNCTION_INFO_V1(utf8_to_win1258);
extern Datum tcvn_to_utf8(PG_FUNCTION_ARGS);
extern Datum utf8_to_tcvn(PG_FUNCTION_ARGS);
extern Datum win1258_to_utf8(PG_FUNCTION_ARGS);
extern Datum utf8_to_win1258(PG_FUNCTION_ARGS);
/* ----------
* conv_proc(
......@@ -34,35 +34,35 @@ extern Datum utf8_to_tcvn(PG_FUNCTION_ARGS);
* ----------
*/
Datum
tcvn_to_utf8(PG_FUNCTION_ARGS)
win1258_to_utf8(PG_FUNCTION_ARGS)
{
unsigned char *src = PG_GETARG_CSTRING(2);
unsigned char *dest = PG_GETARG_CSTRING(3);
int len = PG_GETARG_INT32(4);
Assert(PG_GETARG_INT32(0) == PG_TCVN);
Assert(PG_GETARG_INT32(0) == PG_WIN1258);
Assert(PG_GETARG_INT32(1) == PG_UTF8);
Assert(len >= 0);
LocalToUtf(src, dest, LUmapTCVN,
sizeof(LUmapTCVN) / sizeof(pg_local_to_utf), PG_TCVN, len);
LocalToUtf(src, dest, LUmapWIN1258,
sizeof(LUmapWIN1258) / sizeof(pg_local_to_utf), PG_WIN1258, len);
PG_RETURN_VOID();
}
Datum
utf8_to_tcvn(PG_FUNCTION_ARGS)
utf8_to_win1258(PG_FUNCTION_ARGS)
{
unsigned char *src = PG_GETARG_CSTRING(2);
unsigned char *dest = PG_GETARG_CSTRING(3);
int len = PG_GETARG_INT32(4);
Assert(PG_GETARG_INT32(0) == PG_UTF8);
Assert(PG_GETARG_INT32(1) == PG_TCVN);
Assert(PG_GETARG_INT32(1) == PG_WIN1258);
Assert(len >= 0);
UtfToLocal(src, dest, ULmapTCVN,
sizeof(ULmapTCVN) / sizeof(pg_utf_to_local), len);
UtfToLocal(src, dest, ULmapWIN1258,
sizeof(ULmapWIN1258) / sizeof(pg_utf_to_local), len);
PG_RETURN_VOID();
}
src/backend/utils/mb/conversion_procs/utf8_and_win874/utf8_and_win874.c
View file @ e3d7de6b
/*-------------------------------------------------------------------------
*
* WIN874 and UTF-8
* WIN874 and UTF8
*
* Portions Copyright (c) 1996-2005, 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_win874/utf8_and_win874.c,v 1.9 2004/12/31 22:02:41 pgsql Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/conversion_procs/utf8_and_win874/utf8_and_win874.c,v 1.10 2005/03/07 04:30:55 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......
src/backend/utils/mb/encnames.c
View file @ e3d7de6b
......@@ -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 1.22 2004/12/04 18:19:31 momjian Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/encnames.c,v 1.23 2005/03/07 04:30:52 momjian Exp $
*/
#ifdef FRONTEND
#include "postgres_fe.h"
......@@ -27,7 +27,7 @@
* isalnum() chars only. It means ISO-8859-1, iso_8859-1 and Iso8859_1
* are always converted to 'iso88591'. All must be lower case.
*
* The table doesn't contain 'cs' aliases (like csISOLatin1). It's needful?
* The table doesn't contain 'cs' aliases (like csISOLatin1). It's needed?
*
* Karel Zak, Aug 2001
* ----------
......@@ -35,10 +35,10 @@
pg_encname pg_encname_tbl[] =
{
{
"abc", PG_TCVN
}, /* alias for TCVN */
"abc", PG_WIN1258
}, /* alias for WIN1258 */
{
"alt", PG_ALT
"alt", PG_WIN866
}, /* IBM866 */
{
"big5", PG_BIG5
......@@ -166,23 +166,26 @@ pg_encname pg_encname_tbl[] =
"sqlascii", PG_SQL_ASCII
},
{
"tcvn", PG_TCVN
}, /* TCVN; Vietnamese TCVN-5712 */
"tcvn", PG_WIN1258
}, /* alias for WIN1258 */
{
"tcvn5712", PG_TCVN
}, /* alias for TCVN */
"tcvn5712", PG_WIN1258
}, /* alias for WIN1258 */
{
"uhc", PG_UHC
}, /* UHC; Korean Windows CodePage 949 */
{
"unicode", PG_UTF8
}, /* alias for UTF-8 */
}, /* alias for UTF8 */
{
"utf-8", PG_UTF8
}, /* UTF8; RFC2279 */
{
"utf8", PG_UTF8
}, /* UTF-8; RFC2279 */
}, /* alias for UTF8 */
{
"vscii", PG_TCVN
}, /* alias for TCVN */
"vscii", PG_WIN1258
}, /* alias for WIN1258 */
{
"win", PG_WIN1251
}, /* _dirty_ alias for windows-1251
......@@ -197,8 +200,11 @@ pg_encname pg_encname_tbl[] =
"win1256", PG_WIN1256
}, /* alias for Windows-1256 */
{
"win1258", PG_TCVN
"win1258", PG_WIN1258
}, /* alias for Windows-1258 */
{
"win866", PG_WIN866
}, /* IBM866 */
{
"win874", PG_WIN874
}, /* alias for Windows-874 */
......@@ -224,8 +230,11 @@ pg_encname pg_encname_tbl[] =
"windows1256", PG_WIN1256
}, /* Windows-1256; Microsoft */
{
"windows1258", PG_TCVN
"windows1258", PG_WIN1258
}, /* Windows-1258; Microsoft */
{
"windows866", PG_WIN866
}, /* IBM866 */
{
"windows874", PG_WIN874
}, /* Windows-874; Microsoft */
......@@ -275,7 +284,7 @@ pg_enc2name pg_enc2name_tbl[] =
"JOHAB", PG_JOHAB
},
{
"UNICODE", PG_UTF8
"UTF8", PG_UTF8
},
{
"MULE_INTERNAL", PG_MULE_INTERNAL
......@@ -314,19 +323,19 @@ pg_enc2name pg_enc2name_tbl[] =
"WIN1256", PG_WIN1256
},
{
"TCVN", PG_TCVN
"WIN1258", PG_WIN1258
},
{
"WIN874", PG_WIN874
"WIN866", PG_WIN866
},
{
"KOI8", PG_KOI8R
"WIN874", PG_WIN874
},
{
"WIN", PG_WIN1251
"KOI8", PG_KOI8R
},
{
"ALT", PG_ALT
"WIN1251", PG_WIN1251
},
{
"ISO_8859_5", PG_ISO_8859_5
......
src/backend/utils/mb/mbutils.c
View file @ e3d7de6b
......@@ -4,7 +4,7 @@
* (currently mule internal code (mic) is used)
* Tatsuo Ishii
*
* $PostgreSQL: pgsql/src/backend/utils/mb/mbutils.c,v 1.48 2004/10/13 01:25:12 neilc Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/mbutils.c,v 1.49 2005/03/07 04:30:52 momjian Exp $
*/
#include "postgres.h"
......@@ -222,7 +222,7 @@ pg_get_client_encoding_name(void)
*
* XXX We assume that storage for converted result is 4-to-1 growth in
* the worst case. The rate for currently supported encoding pares are within 3
* (SJIS JIS X0201 half width kanna -> UTF-8 is the worst case).
* (SJIS JIS X0201 half width kanna -> UTF8 is the worst case).
* So "4" should be enough for the moment.
*/
unsigned char *
......
src/backend/utils/mb/wchar.c
View file @ e3d7de6b
/*
* conversion functions between pg_wchar and multibyte streams.
* Tatsuo Ishii
* $PostgreSQL: pgsql/src/backend/utils/mb/wchar.c,v 1.40 2004/12/03 01:20:20 momjian Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/wchar.c,v 1.41 2005/03/07 04:30:52 momjian Exp $
*
* WIN1250 client encoding updated by Pavel Behal
*
......@@ -344,7 +344,7 @@ pg_johab_dsplen(const unsigned char *s)
}
/*
* convert UTF-8 string to pg_wchar (UCS-2)
* convert UTF8 string to pg_wchar (UCS-2)
* caller should allocate enough space for "to"
* len: length of from.
* "from" not necessarily null terminated.
......@@ -395,7 +395,7 @@ pg_utf2wchar_with_len(const unsigned char *from, pg_wchar *to, int len)
}
/*
* returns the byte length of a UTF-8 word pointed to by s
* returns the byte length of a UTF8 word pointed to by s
*/
int
pg_utf_mblen(const unsigned char *s)
......@@ -721,7 +721,7 @@ pg_wchar_tbl pg_wchar_table[] = {
{pg_euckr2wchar_with_len, pg_euckr_mblen, pg_euckr_dsplen, 3}, /* 3; PG_EUC_KR */
{pg_euctw2wchar_with_len, pg_euctw_mblen, pg_euctw_dsplen, 3}, /* 4; PG_EUC_TW */
{pg_johab2wchar_with_len, pg_johab_mblen, pg_johab_dsplen, 3}, /* 5; PG_JOHAB */
{pg_utf2wchar_with_len, pg_utf_mblen, pg_utf_dsplen, 3}, /* 6; PG_UNICODE */
{pg_utf2wchar_with_len, pg_utf_mblen, pg_utf_dsplen, 3}, /* 6; PG_UTF8 */
{pg_mule2wchar_with_len, pg_mule_mblen, pg_mule_dsplen, 3}, /* 7; PG_MULE_INTERNAL */
{pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 8; PG_LATIN1 */
{pg_latin12wchar_with_len, pg_latin1_mblen, pg_latin1_dsplen, 1}, /* 9; PG_LATIN2 */
......@@ -822,7 +822,7 @@ pg_verifymbstr(const unsigned char *mbstr, int len, bool noError)
while (len > 0 && *mbstr)
{
/* special UTF-8 check */
/* special UTF8 check */
if (encoding == PG_UTF8 && (*mbstr & 0xf8) == 0xf0)
{
if (noError)
......
src/backend/utils/mb/win.c deleted 100644 → 0
View file @ c6ad5c2e
/*
* make KOI8->CP1251(win-1251) and CP1251(win-1251)->KOI8 translation table
* from koi-win.tab.
*
* Tatsuo Ishii
*
* $PostgreSQL: pgsql/src/backend/utils/mb/win.c,v 1.4 2003/11/29 22:39:59 pgsql Exp $
*/
#include <stdio.h>
main()
{
int i;
char koitab[128],
wintab[128];
char buf[4096];
int koi,
win;
for (i = 0; i < 128; i++)
koitab[i] = wintab[i] = 0;
while (fgets(buf, sizeof(buf), stdin) != NULL)
{
if (*buf == '#')
continue;
sscanf(buf, "%d %d", &koi, &win);
if (koi < 128 || koi > 255 || win < 128 || win > 255)
{
fprintf(stderr, "invalid value %d\n", koi);
exit(1);
}
koitab[koi - 128] = win;
wintab[win - 128] = koi;
}
i = 0;
printf("static char koi2win[] = {\n");
while (i < 128)
{
int j = 0;
while (j < 8)
{
printf("0x%02x", koitab[i++]);
j++;
if (i >= 128)
break;
printf(", ");
}
printf("\n");
}
printf("};\n");
i = 0;
printf("static char win2koi[] = {\n");
while (i < 128)
{
int j = 0;
while (j < 8)
{
printf("0x%02x", wintab[i++]);
j++;
if (i >= 128)
break;
printf(", ");
}
printf("\n");
}
printf("};\n");
}
src/backend/utils/mb/alt.c → src/backend/utils/mb/win866.c
View file @ e3d7de6b
......@@ -4,7 +4,7 @@
*
* Tatsuo Ishii
*
* $PostgreSQL: pgsql/src/backend/utils/mb/alt.c,v 1.4 2003/11/29 22:39:59 pgsql Exp $
* $PostgreSQL: pgsql/src/backend/utils/mb/win866.c,v 1.1 2005/03/07 04:30:52 momjian Exp $
*/
#include <stdio.h>
......
src/bin/initdb/initdb.c
View file @ e3d7de6b
......@@ -39,7 +39,7 @@
* Portions Copyright (c) 1994, Regents of the University of California
* Portions taken from FreeBSD.
*
* $PostgreSQL: pgsql/src/bin/initdb/initdb.c,v 1.76 2005/02/26 18:43:34 tgl Exp $
* $PostgreSQL: pgsql/src/bin/initdb/initdb.c,v 1.77 2005/03/07 04:30:55 momjian Exp $
*
*-------------------------------------------------------------------------
*/
......@@ -723,7 +723,7 @@ struct encoding_match encoding_match_list[] = {
{PG_JOHAB, "???"},
#endif
{PG_UTF8, "UTF-8"},
{PG_UTF8, "UTF8"},
{PG_UTF8, "utf8"},
{PG_LATIN1, "ISO-8859-1"},
......@@ -767,13 +767,13 @@ struct encoding_match encoding_match_list[] = {
{PG_LATIN10, "iso885916"},
{PG_WIN1256, "CP1256"},
{PG_TCVN, "CP1258"},
{PG_WIN1258, "CP1258"},
#ifdef NOT_VERIFIED
{PG_WIN874, "???"},
#endif
{PG_KOI8R, "KOI8-R"},
{PG_WIN1251, "CP1251"},
{PG_ALT, "CP866"},
{PG_WIN866, "CP866"},
{PG_ISO_8859_5, "ISO-8859-5"},
{PG_ISO_8859_5, "ISO8859-5"},
......
src/include/mb/pg_wchar.h
View file @ e3d7de6b
/* $PostgreSQL: pgsql/src/include/mb/pg_wchar.h,v 1.56 2004/12/04 18:19:33 momjian Exp $ */
/* $PostgreSQL: pgsql/src/include/mb/pg_wchar.h,v 1.57 2005/03/07 04:30:55 momjian Exp $ */
#ifndef PG_WCHAR_H
#define PG_WCHAR_H
......@@ -155,7 +155,7 @@ typedef enum pg_enc
PG_EUC_KR, /* EUC for Korean */
PG_EUC_TW, /* EUC for Taiwan */
PG_JOHAB, /* EUC for Korean JOHAB */
PG_UTF8, /* Unicode UTF-8 */
PG_UTF8, /* Unicode UTF8 */
PG_MULE_INTERNAL, /* Mule internal code */
PG_LATIN1, /* ISO-8859-1 Latin 1 */
PG_LATIN2, /* ISO-8859-2 Latin 2 */
......@@ -168,11 +168,11 @@ typedef enum pg_enc
PG_LATIN9, /* ISO-8859-15 Latin9 */
PG_LATIN10, /* ISO-8859-16 Latin10 */
PG_WIN1256, /* windows-1256 */
PG_TCVN, /* TCVN (Windows-1258) */
PG_WIN1258, /* Windows-1258 */
PG_WIN866, /* (MS-DOS CP866) */
PG_WIN874, /* windows-874 */
PG_KOI8R, /* KOI8-R */
PG_WIN1251, /* windows-1251 (was: WIN) */
PG_ALT, /* (MS-DOS CP866) */
PG_ISO_8859_5, /* ISO-8859-5 */
PG_ISO_8859_6, /* ISO-8859-6 */
PG_ISO_8859_7, /* ISO-8859-7 */
......@@ -263,21 +263,21 @@ typedef struct
extern pg_wchar_tbl pg_wchar_table[];
/*
* UTF-8 to local code conversion map
* UTF8 to local code conversion map
*/
typedef struct
{
unsigned int utf; /* UTF-8 */
unsigned int utf; /* UTF8 */
unsigned int code; /* local code */
} pg_utf_to_local;
/*
* local code to UTF-8 conversion map
* local code to UTF8 conversion map
*/
typedef struct
{
unsigned int code; /* local code */
unsigned int utf; /* UTF-8 */
unsigned int utf; /* UTF8 */
} pg_local_to_utf;
extern int pg_mb2wchar(const unsigned char *from, pg_wchar *to);
......
src/test/mb/mbregress.sh
View file @ e3d7de6b
#! /bin/sh
# $PostgreSQL: pgsql/src/test/mb/mbregress.sh,v 1.7 2003/11/29 19:52:14 pgsql Exp $
# $PostgreSQL: pgsql/src/test/mb/mbregress.sh,v 1.8 2005/03/07 04:30:55 momjian Exp $
if echo '\c' | grep -s c >/dev/null 2>&1
then
......@@ -15,10 +15,10 @@ if [ ! -d results ];then
fi
dropdb unitest
createdb -E UNICODE unitest
createdb -E UTF8 unitest
PSQL="psql -n -e -q"
tests="euc_jp sjis euc_kr euc_cn euc_tw big5 unicode mule_internal"
tests="euc_jp sjis euc_kr euc_cn euc_tw big5 utf8 mule_internal"
unset PGCLIENTENCODING
for i in $tests
do
......
src/test/regress/expected/conversion.out
View file @ e3d7de6b
This diff is collapsed.
src/test/regress/sql/conversion.sql
View file @ e3d7de6b
This diff is collapsed.
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment