1
0
mirror of https://github.com/postgres/postgres.git synced 2025-11-12 05:01:15 +03:00

Commit Karel's patch.

-------------------------------------------------------------------
Subject: Re: [PATCHES] encoding names
From: Karel Zak <zakkr@zf.jcu.cz>
To: Peter Eisentraut <peter_e@gmx.net>
Cc: pgsql-patches <pgsql-patches@postgresql.org>
Date: Fri, 31 Aug 2001 17:24:38 +0200

On Thu, Aug 30, 2001 at 01:30:40AM +0200, Peter Eisentraut wrote:
> > 		- convert encoding 'name' to 'id'
>
> I thought we decided not to add functions returning "new" names until we
> know exactly what the new names should be, and pending schema

 Ok, the patch not to add functions.

> better
>
>     ...(): encoding name too long

 Fixed.

 I found new bug in command/variable.c in parse_client_encoding(), nobody
probably never see this error:

if (pg_set_client_encoding(encoding))
{
	elog(ERROR, "Conversion between %s and %s is not supported",
                     value, GetDatabaseEncodingName());
}

because pg_set_client_encoding() returns -1 for error and 0 as true.
It's fixed too.

 IMHO it can be apply.

		Karel
PS:

    * following files are renamed:

src/utils/mb/Unicode/KOI8_to_utf8.map  -->
        src/utils/mb/Unicode/koi8r_to_utf8.map

src/utils/mb/Unicode/WIN_to_utf8.map  -->
        src/utils/mb/Unicode/win1251_to_utf8.map

src/utils/mb/Unicode/utf8_to_KOI8.map -->
        src/utils/mb/Unicode/utf8_to_koi8r.map

src/utils/mb/Unicode/utf8_to_WIN.map -->
        src/utils/mb/Unicode/utf8_to_win1251.map

   * new file:

src/utils/mb/encname.c

   * removed file:

src/utils/mb/common.c

--
 Karel Zak  <zakkr@zf.jcu.cz>
 http://home.zf.jcu.cz/~zakkr/

 C, PostgreSQL, PHP, WWW, http://docs.linux.cz, http://mape.jcu.cz
This commit is contained in:
Tatsuo Ishii
2001-09-06 04:57:30 +00:00
parent 50aa3020ac
commit 227767112c
21 changed files with 479 additions and 402 deletions

View File

@@ -1,7 +1,7 @@
/* -----------------------------------------------------------------------
* ascii.c
*
* $Header: /cvsroot/pgsql/src/backend/utils/adt/ascii.c,v 1.8 2001/03/22 06:16:17 momjian Exp $
* $Header: /cvsroot/pgsql/src/backend/utils/adt/ascii.c,v 1.9 2001/09/06 04:57:29 ishii Exp $
*
* Portions Copyright (c) 1999-2000, PostgreSQL Global Development Group
*
@@ -78,7 +78,7 @@ pg_to_ascii(unsigned char *src, unsigned char *src_end, unsigned char *desc, int
#define RANGE_160 160
if (enc == LATIN1)
if (enc == PG_LATIN1)
{
/*
@@ -87,7 +87,7 @@ pg_to_ascii(unsigned char *src, unsigned char *src_end, unsigned char *desc, int
ascii = " cL Y \"Ca -R 'u ., ?AAAAAAACEEEEIIII NOOOOOxOUUUUYTBaaaaaaaceeeeiiii nooooo/ouuuuyty";
range = RANGE_160;
}
else if (enc == LATIN2)
else if (enc == PG_LATIN2)
{
/*
@@ -96,7 +96,7 @@ pg_to_ascii(unsigned char *src, unsigned char *src_end, unsigned char *desc, int
ascii = " A L LS \"SSTZ-ZZ a,l'ls ,sstz\"zzRAAAALCCCEEEEIIDDNNOOOOxRUUUUYTBraaaalccceeeeiiddnnoooo/ruuuuyt.";
range = RANGE_160;
}
else if (enc == WIN1250)
else if (enc == PG_WIN1250)
{
/*

View File

@@ -8,7 +8,7 @@
*
*
* IDENTIFICATION
* $Header: /cvsroot/pgsql/src/backend/utils/init/postinit.c,v 1.88 2001/08/25 18:52:42 tgl Exp $
* $Header: /cvsroot/pgsql/src/backend/utils/init/postinit.c,v 1.89 2001/09/06 04:57:29 ishii Exp $
*
*
*-------------------------------------------------------------------------
@@ -127,7 +127,7 @@ ReverifyMyDatabase(const char *name)
#ifdef MULTIBYTE
SetDatabaseEncoding(dbform->encoding);
#else
if (dbform->encoding != SQL_ASCII)
if (dbform->encoding != PG_SQL_ASCII)
elog(FATAL, "database was initialized with MULTIBYTE encoding %d,\n\tbut the backend was compiled without multibyte support.\n\tlooks like you need to initdb or recompile.",
dbform->encoding);
#endif

View File

@@ -4,7 +4,7 @@
# Makefile for utils/mb
#
# IDENTIFICATION
# $Header: /cvsroot/pgsql/src/backend/utils/mb/Makefile,v 1.15 2000/11/30 20:36:11 petere Exp $
# $Header: /cvsroot/pgsql/src/backend/utils/mb/Makefile,v 1.16 2001/09/06 04:57:29 ishii Exp $
#
#-------------------------------------------------------------------------
@@ -12,7 +12,7 @@ subdir = src/backend/utils/mb
top_builddir = ../../../..
include $(top_builddir)/src/Makefile.global
OBJS = common.o conv.o mbutils.o wchar.o wstrcmp.o wstrncmp.o big5.o
OBJS = encnames.o conv.o mbutils.o wchar.o wstrcmp.o wstrncmp.o big5.o
all: SUBSYS.o
@@ -21,13 +21,13 @@ SUBSYS.o: $(OBJS)
utftest.o: utftest.c conv.c wchar.c mbutils.c
sjistest: sjistest.o palloc.o common.o mbutils.o wchar.o wstrcmp.o wstrncmp.o big5.o
sjistest: sjistest.o palloc.o encnames.o mbutils.o wchar.o wstrcmp.o wstrncmp.o big5.o
$(CC) $(CFLAGS) $(LDFLAGS) $^ $(LIBS) -o $@
liketest: liketest.o palloc.o $(OBJS)
$(CC) $(CFLAGS) $(LDFLAGS) $^ $(LIBS) -o $@
utftest: utftest.o palloc.o common.o wstrcmp.o wstrncmp.o big5.o
utftest: utftest.o palloc.o encnames.o wstrcmp.o wstrncmp.o big5.o
$(CC) $(CFLAGS) $(LDFLAGS) $^ $(LIBS) -o $@
depend dep:

View File

@@ -4,7 +4,7 @@
#
# Copyright 2001 by PostgreSQL Global Development Group
#
# $Header: /cvsroot/pgsql/src/backend/utils/mb/Unicode/Makefile,v 1.2 2001/04/29 07:27:38 ishii Exp $
# $Header: /cvsroot/pgsql/src/backend/utils/mb/Unicode/Makefile,v 1.3 2001/09/06 04:57:29 ishii 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=KOI8_to_utf8.map WIN_to_utf8.map ALT_to_utf8.map\
utf8_to_KOI8.map utf8_to_WIN.map utf8_to_ALT.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
MAPS= $(ISO8859MAPS) $(CYRILLICMAPS)\
big5_to_utf8.map euc_cn_to_utf8.map euc_jp_to_utf8.map \

View File

@@ -2,7 +2,7 @@
#
# Copyright 2001 by PostgreSQL Global Development Group
#
# $Id: UCS_to_cyrillic.pl,v 1.1 2001/04/29 07:27:38 ishii Exp $
# $Id: UCS_to_cyrillic.pl,v 1.2 2001/09/06 04:57:29 ishii Exp $
#
# Generate UTF-8 <--> ISO8859 code conversion tables from
# map files provided by Unicode organization.
@@ -15,10 +15,10 @@
# # and Unicode name (not used in this script)
require "ucs2utf.pl";
%filename = ('KOI8'=>'koi8-r.txt',
'WIN'=>'cp1251.txt',
%filename = ('KOI8R'=>'koi8-r.txt',
'WIN1251'=>'cp1251.txt',
'ALT'=>'cp866.txt');
@charsets = ('KOI8','ALT','WIN');
@charsets = ('KOI8R','ALT','WIN1251');
foreach $charset (@charsets) {
#

View File

@@ -6,7 +6,7 @@
* WIN1250 client encoding support contributed by Pavel Behal
* SJIS UDC (NEC selection IBM kanji) support contributed by Eiji Tokuya
*
* $Id: conv.c,v 1.26 2001/05/28 01:00:25 ishii Exp $
* $Id: conv.c,v 1.27 2001/09/06 04:57:29 ishii Exp $
*
*
*/
@@ -39,12 +39,12 @@
#include "Unicode/utf8_to_big5.map"
#include "Unicode/big5_to_utf8.map"
/* Cyrillic charset conversion */
#include "Unicode/ALT_to_utf8.map"
#include "Unicode/KOI8_to_utf8.map"
#include "Unicode/WIN_to_utf8.map"
#include "Unicode/utf8_to_ALT.map"
#include "Unicode/utf8_to_KOI8.map"
#include "Unicode/utf8_to_WIN.map"
#include "Unicode/alt_to_utf8.map"
#include "Unicode/koi8r_to_utf8.map"
#include "Unicode/win1251_to_utf8.map"
#include "Unicode/utf8_to_alt.map"
#include "Unicode/utf8_to_koi8r.map"
#include "Unicode/utf8_to_win1251.map"
#endif /* UNICODE_CONVERSION */
@@ -824,16 +824,16 @@ mic2ascii(unsigned char *mic, unsigned char *p, int len)
* Alternativny Variant (MS-DOS CP866)
*/
/* koi2mic: KOI8-R to Mule internal code */
/* koi8r2mic: KOI8-R to Mule internal code */
static void
koi2mic(unsigned char *l, unsigned char *p, int len)
koi8r2mic(unsigned char *l, unsigned char *p, int len)
{
latin2mic(l, p, len, LC_KOI8_R);
}
/* mic2koi: Mule internal code to KOI8-R */
/* mic2koi8r: Mule internal code to KOI8-R */
static void
mic2koi(unsigned char *mic, unsigned char *p, int len)
mic2koi8r(unsigned char *mic, unsigned char *p, int len)
{
mic2latin(mic, p, len, LC_KOI8_R);
}
@@ -981,7 +981,7 @@ mic2iso(unsigned char *mic, unsigned char *p, int len)
/* win2mic: CP1251 to Mule internal code */
static void
win2mic(unsigned char *l, unsigned char *p, int len)
win12512mic(unsigned char *l, unsigned char *p, int len)
{
static unsigned char win2koi[] = {
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
@@ -1007,7 +1007,7 @@ win2mic(unsigned char *l, unsigned char *p, int len)
/* mic2win: Mule internal code to CP1251 */
static void
mic2win(unsigned char *mic, unsigned char *p, int len)
mic2win1251(unsigned char *mic, unsigned char *p, int len)
{
static unsigned char koi2win[] = {
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
@@ -1343,23 +1343,23 @@ utf_to_latin5(unsigned char *utf, unsigned char *iso, int len)
*/
/*
* UTF-8 --->KOI8
* UTF-8 --->KOI8-R
*/
static void
utf_to_KOI8(unsigned char *utf, unsigned char *iso, int len)
utf_to_KOI8R(unsigned char *utf, unsigned char *iso, int len)
{
utf_to_local(utf, iso, ULmap_KOI8, sizeof(ULmap_KOI8) / sizeof(pg_utf_to_local), len);
utf_to_local(utf, iso, ULmap_KOI8R, sizeof(ULmap_KOI8R) / sizeof(pg_utf_to_local), len);
}
/*
* UTF-8 --->WIN
* UTF-8 --->WIN1251
*/
static void
utf_to_WIN(unsigned char *utf, unsigned char *iso, int len)
utf_to_WIN1251(unsigned char *utf, unsigned char *iso, int len)
{
utf_to_local(utf, iso, ULmap_WIN, sizeof(ULmap_WIN) / sizeof(pg_utf_to_local), len);
utf_to_local(utf, iso, ULmap_WIN1251, sizeof(ULmap_WIN1251) / sizeof(pg_utf_to_local), len);
}
/*
@@ -1382,10 +1382,8 @@ local_to_utf(unsigned char *iso, unsigned char *utf,
unsigned int iiso;
int l;
pg_local_to_utf *p;
pg_encoding_conv_tbl *e;
e = pg_get_enc_ent(encoding);
if (e == 0)
if (!PG_VALID_ENCODING(encoding))
elog(ERROR, "Invalid encoding number %d", encoding);
for (; len > 0 && *iso; len -= l)
@@ -1424,7 +1422,7 @@ local_to_utf(unsigned char *iso, unsigned char *utf,
if (p == NULL)
{
elog(NOTICE, "local_to_utf: could not convert (0x%04x) %s to UTF-8. Ignored",
iiso, e->name);
iiso, (&pg_enc2name_tbl[ encoding ])->name);
continue;
}
if (p->utf & 0xff000000)
@@ -1445,7 +1443,7 @@ local_to_utf(unsigned char *iso, unsigned char *utf,
static void
latin2_to_utf(unsigned char *iso, unsigned char *utf, int len)
{
local_to_utf(iso, utf, LUmapISO8859_2, sizeof(LUmapISO8859_2) / sizeof(pg_local_to_utf), LATIN2, len);
local_to_utf(iso, utf, LUmapISO8859_2, sizeof(LUmapISO8859_2) / sizeof(pg_local_to_utf), PG_LATIN2, len);
}
/*
@@ -1454,7 +1452,7 @@ latin2_to_utf(unsigned char *iso, unsigned char *utf, int len)
static void
latin3_to_utf(unsigned char *iso, unsigned char *utf, int len)
{
local_to_utf(iso, utf, LUmapISO8859_3, sizeof(LUmapISO8859_3) / sizeof(pg_local_to_utf), LATIN3, len);
local_to_utf(iso, utf, LUmapISO8859_3, sizeof(LUmapISO8859_3) / sizeof(pg_local_to_utf), PG_LATIN3, len);
}
/*
@@ -1463,7 +1461,7 @@ latin3_to_utf(unsigned char *iso, unsigned char *utf, int len)
static void
latin4_to_utf(unsigned char *iso, unsigned char *utf, int len)
{
local_to_utf(iso, utf, LUmapISO8859_4, sizeof(LUmapISO8859_4) / sizeof(pg_local_to_utf), LATIN4, len);
local_to_utf(iso, utf, LUmapISO8859_4, sizeof(LUmapISO8859_4) / sizeof(pg_local_to_utf), PG_LATIN4, len);
}
/*
@@ -1472,25 +1470,25 @@ latin4_to_utf(unsigned char *iso, unsigned char *utf, int len)
static void
latin5_to_utf(unsigned char *iso, unsigned char *utf, int len)
{
local_to_utf(iso, utf, LUmapISO8859_5, sizeof(LUmapISO8859_5) / sizeof(pg_local_to_utf), LATIN5, len);
local_to_utf(iso, utf, LUmapISO8859_5, sizeof(LUmapISO8859_5) / sizeof(pg_local_to_utf), PG_LATIN5, len);
}
/*
* KOI8 ---> UTF-8
* KOI8-R ---> UTF-8
*/
static void
KOI8_to_utf(unsigned char *iso, unsigned char *utf, int len)
KOI8R_to_utf(unsigned char *iso, unsigned char *utf, int len)
{
local_to_utf(iso, utf, LUmapKOI8, sizeof(LUmapKOI8) / sizeof(pg_local_to_utf), KOI8, len);
local_to_utf(iso, utf, LUmapKOI8R, sizeof(LUmapKOI8R) / sizeof(pg_local_to_utf), PG_KOI8R, len);
}
/*
* WIN ---> UTF-8
* WIN1251 ---> UTF-8
*/
static void
WIN_to_utf(unsigned char *iso, unsigned char *utf, int len)
WIN1251_to_utf(unsigned char *iso, unsigned char *utf, int len)
{
local_to_utf(iso, utf, LUmapWIN, sizeof(LUmapWIN) / sizeof(pg_local_to_utf), WIN, len);
local_to_utf(iso, utf, LUmapWIN1251, sizeof(LUmapWIN1251) / sizeof(pg_local_to_utf), PG_WIN1251, len);
}
/*
@@ -1499,7 +1497,7 @@ WIN_to_utf(unsigned char *iso, unsigned char *utf, int len)
static void
ALT_to_utf(unsigned char *iso, unsigned char *utf, int len)
{
local_to_utf(iso, utf, LUmapALT, sizeof(LUmapALT) / sizeof(pg_local_to_utf), ALT, len);
local_to_utf(iso, utf, LUmapALT, sizeof(LUmapALT) / sizeof(pg_local_to_utf), PG_ALT, len);
}
/*
* UTF-8 ---> EUC_JP
@@ -1519,7 +1517,7 @@ static void
euc_jp_to_utf(unsigned char *euc, unsigned char *utf, int len)
{
local_to_utf(euc, utf, LUmapEUC_JP,
sizeof(LUmapEUC_JP) / sizeof(pg_local_to_utf), EUC_JP, len);
sizeof(LUmapEUC_JP) / sizeof(pg_local_to_utf), PG_EUC_JP, len);
}
/*
@@ -1540,7 +1538,7 @@ static void
euc_cn_to_utf(unsigned char *euc, unsigned char *utf, int len)
{
local_to_utf(euc, utf, LUmapEUC_CN,
sizeof(LUmapEUC_CN) / sizeof(pg_local_to_utf), EUC_CN, len);
sizeof(LUmapEUC_CN) / sizeof(pg_local_to_utf), PG_EUC_CN, len);
}
/*
@@ -1561,7 +1559,7 @@ static void
euc_kr_to_utf(unsigned char *euc, unsigned char *utf, int len)
{
local_to_utf(euc, utf, LUmapEUC_KR,
sizeof(LUmapEUC_KR) / sizeof(pg_local_to_utf), EUC_KR, len);
sizeof(LUmapEUC_KR) / sizeof(pg_local_to_utf), PG_EUC_KR, len);
}
/*
@@ -1582,7 +1580,7 @@ static void
euc_tw_to_utf(unsigned char *euc, unsigned char *utf, int len)
{
local_to_utf(euc, utf, LUmapEUC_TW,
sizeof(LUmapEUC_TW) / sizeof(pg_local_to_utf), EUC_TW, len);
sizeof(LUmapEUC_TW) / sizeof(pg_local_to_utf), PG_EUC_TW, len);
}
/*
@@ -1603,7 +1601,7 @@ static void
sjis_to_utf(unsigned char *euc, unsigned char *utf, int len)
{
local_to_utf(euc, utf, LUmapSJIS,
sizeof(LUmapSJIS) / sizeof(pg_local_to_utf), SJIS, len);
sizeof(LUmapSJIS) / sizeof(pg_local_to_utf), PG_SJIS, len);
}
/*
@@ -1624,85 +1622,59 @@ static void
big5_to_utf(unsigned char *euc, unsigned char *utf, int len)
{
local_to_utf(euc, utf, LUmapBIG5,
sizeof(LUmapBIG5) / sizeof(pg_local_to_utf), BIG5, len);
sizeof(LUmapBIG5) / sizeof(pg_local_to_utf), PG_BIG5, len);
}
/*-----------------------------------------------------------------*/
pg_encoding_conv_tbl pg_conv_tbl[] = {
{SQL_ASCII, "SQL_ASCII", 0, ascii2mic, mic2ascii,
ascii2utf, utf2ascii}, /* SQL/ASCII */
{EUC_JP, "EUC_JP", 0, euc_jp2mic, mic2euc_jp,
euc_jp_to_utf, utf_to_euc_jp}, /* EUC_JP */
{EUC_CN, "EUC_CN", 0, euc_cn2mic, mic2euc_cn,
euc_cn_to_utf, utf_to_euc_cn}, /* EUC_CN */
{EUC_KR, "EUC_KR", 0, euc_kr2mic, mic2euc_kr,
euc_kr_to_utf, utf_to_euc_kr}, /* EUC_KR */
{EUC_TW, "EUC_TW", 0, euc_tw2mic, mic2euc_tw,
euc_tw_to_utf, utf_to_euc_tw}, /* EUC_TW */
{UNICODE, "UNICODE", 0, 0, 0}, /* UNICODE */
{MULE_INTERNAL, "MULE_INTERNAL", 0, 0, 0}, /* MULE_INTERNAL */
{LATIN1, "LATIN1", 0, latin12mic, mic2latin1,
latin1_to_utf, utf_to_latin1}, /* ISO 8859 Latin 1 */
{LATIN2, "LATIN2", 0, latin22mic, mic2latin2,
latin2_to_utf, utf_to_latin2}, /* ISO 8859 Latin 2 */
{LATIN3, "LATIN3", 0, latin32mic, mic2latin3,
latin3_to_utf, utf_to_latin3}, /* ISO 8859 Latin 3 */
{LATIN4, "LATIN4", 0, latin42mic, mic2latin4,
latin4_to_utf, utf_to_latin4}, /* ISO 8859 Latin 4 */
{LATIN5, "LATIN5", 0, iso2mic, mic2iso,
latin5_to_utf, utf_to_latin5}, /* ISO 8859 Latin 5 */
{KOI8, "KOI8", 0, koi2mic, mic2koi,
KOI8_to_utf, utf_to_KOI8}, /* KOI8-R */
{WIN, "WIN", 0, win2mic, mic2win,
WIN_to_utf , utf_to_WIN}, /* CP1251 */
{ALT, "ALT", 0, alt2mic, mic2alt,
ALT_to_utf, utf_to_ALT}, /* CP866 */
{SJIS, "SJIS", 1, sjis2mic, mic2sjis,
sjis_to_utf, utf_to_sjis}, /* SJIS */
{BIG5, "BIG5", 1, big52mic, mic2big5,
big5_to_utf, utf_to_big5}, /* Big5 */
{WIN1250, "WIN1250", 1, win12502mic, mic2win1250,
0, 0}, /* WIN 1250 */
{-1, "", 0, 0, 0, 0} /* end mark */
/* ----------
* Encoding conversion routines
*
* WARINIG: must by same order as pg_enc in include/mb/pg_wchar.h!
* ----------
*/
pg_enconv pg_enconv_tbl[] =
{
{ PG_SQL_ASCII, ascii2mic, mic2ascii, ascii2utf, utf2ascii },
{ PG_EUC_JP, euc_jp2mic, mic2euc_jp, euc_jp_to_utf, utf_to_euc_jp },
{ PG_EUC_CN, euc_cn2mic, mic2euc_cn, euc_cn_to_utf, utf_to_euc_cn },
{ PG_EUC_KR, euc_kr2mic, mic2euc_kr, euc_kr_to_utf, utf_to_euc_kr },
{ PG_EUC_TW, euc_tw2mic, mic2euc_tw, euc_tw_to_utf, utf_to_euc_tw },
{ PG_UTF8, 0, 0, 0, 0 },
{ PG_MULE_INTERNAL, 0, 0, 0, 0 },
{ PG_LATIN1, latin12mic, mic2latin1, latin1_to_utf, utf_to_latin1 },
{ PG_LATIN2, latin22mic, mic2latin2, latin2_to_utf, utf_to_latin2 },
{ PG_LATIN3, latin32mic, mic2latin3, latin3_to_utf, utf_to_latin3 },
{ PG_LATIN4, latin42mic, mic2latin4, latin4_to_utf, utf_to_latin4 },
{ PG_LATIN5, iso2mic, mic2iso, latin5_to_utf, utf_to_latin5 },
{ PG_KOI8R, koi8r2mic, mic2koi8r, KOI8R_to_utf, utf_to_KOI8R },
{ PG_WIN1251, win12512mic, mic2win1251, WIN1251_to_utf, utf_to_WIN1251 },
{ PG_ALT, alt2mic, mic2alt, ALT_to_utf, utf_to_ALT },
{ PG_SJIS, sjis2mic, mic2sjis, sjis_to_utf, utf_to_sjis },
{ PG_BIG5, big52mic, mic2big5, big5_to_utf, utf_to_big5},
{ PG_WIN1250, win12502mic, mic2win1250, 0, 0 },
};
#else
pg_encoding_conv_tbl pg_conv_tbl[] = {
{SQL_ASCII, "SQL_ASCII", 0, ascii2mic, mic2ascii,
0, 0}, /* SQL/ASCII */
{EUC_JP, "EUC_JP", 0, euc_jp2mic, mic2euc_jp,
0, 0}, /* EUC_JP */
{EUC_CN, "EUC_CN", 0, euc_cn2mic, mic2euc_cn,
0, 0}, /* EUC_CN */
{EUC_KR, "EUC_KR", 0, euc_kr2mic, mic2euc_kr}, /* EUC_KR */
{EUC_TW, "EUC_TW", 0, euc_tw2mic, mic2euc_tw}, /* EUC_TW */
{UNICODE, "UNICODE", 0, 0, 0}, /* UNICODE */
{MULE_INTERNAL, "MULE_INTERNAL", 0, 0, 0}, /* MULE_INTERNAL */
{LATIN1, "LATIN1", 0, latin12mic, mic2latin1,
0, 0}, /* ISO 8859 Latin 1 */
{LATIN2, "LATIN2", 0, latin22mic, mic2latin2,
0, 0}, /* ISO 8859 Latin 2 */
{LATIN3, "LATIN3", 0, latin32mic, mic2latin3,
0, 0}, /* ISO 8859 Latin 3 */
{LATIN4, "LATIN4", 0, latin42mic, mic2latin4,
0, 0}, /* ISO 8859 Latin 4 */
{LATIN5, "LATIN5", 0, iso2mic, mic2iso,
0, 0}, /* ISO 8859 Latin 5 */
{KOI8, "KOI8", 0, koi2mic, mic2koi,
0, 0}, /* KOI8-R */
{WIN, "WIN", 0, win2mic, mic2win,
0, 0}, /* CP1251 */
{ALT, "ALT", 0, alt2mic, mic2alt,
0, 0}, /* CP866 */
{SJIS, "SJIS", 1, sjis2mic, mic2sjis,
0, 0}, /* SJIS */
{BIG5, "BIG5", 1, big52mic, mic2big5,
0, 0}, /* Big5 */
{WIN1250, "WIN1250", 1, win12502mic, mic2win1250,
0, 0}, /* WIN 1250 */
{-1, "", 0, 0, 0, 0} /* end mark */
pg_enconv pg_enconv_tbl[] =
{
{ PG_SQL_ASCII, ascii2mic, mic2ascii, 0, 0 },
{ PG_EUC_JP, euc_jp2mic, mic2euc_jp, 0, 0 },
{ PG_EUC_CN, euc_cn2mic, mic2euc_cn, 0, 0 },
{ PG_EUC_KR, euc_kr2mic, mic2euc_kr, 0, 0 },
{ PG_EUC_TW, euc_tw2mic, mic2euc_tw, 0, 0 },
{ PG_UTF8, 0, 0, 0, 0 },
{ PG_MULE_INTERNAL, 0, 0, 0, 0 },
{ PG_LATIN1, latin12mic, mic2latin1, 0, 0 },
{ PG_LATIN2, latin22mic, mic2latin2, 0, 0 },
{ PG_LATIN3, latin32mic, mic2latin3, 0, 0 },
{ PG_LATIN4, latin42mic, mic2latin4, 0, 0 },
{ PG_LATIN5, iso2mic, mic2iso, 0, 0 },
{ PG_KOI8R, koi8r2mic, mic2koi8r, 0, 0 },
{ PG_WIN1251, win12512mic, mic2win1251, 0, 0 },
{ PG_ALT, alt2mic, mic2alt, 0, 0 },
{ PG_SJIS, sjis2mic, mic2sjis, 0, 0 },
{ PG_BIG5, big52mic, mic2big5, 0, 0 },
{ PG_WIN1250, win12502mic, mic2win1250, 0, 0 },
};
#endif /* UNICODE_CONVERSION */

View File

@@ -3,7 +3,7 @@
* client encoding and server internal encoding.
* (currently mule internal code (mic) is used)
* Tatsuo Ishii
* $Id: mbutils.c,v 1.19 2001/08/15 07:07:40 ishii Exp $
* $Id: mbutils.c,v 1.20 2001/09/06 04:57:29 ishii Exp $
*/
#include "postgres.h"
@@ -11,26 +11,36 @@
#include "mb/pg_wchar.h"
#include "utils/builtins.h"
static int client_encoding = -1;
static void (*client_to_mic) ();/* something to MIC */
static void (*client_from_mic) (); /* MIC to something */
static void (*server_to_mic) ();/* something to MIC */
static void (*server_from_mic) (); /* MIC to something */
/*
* We handle for actual FE and BE encoding setting encoding-identificator
* and encoding-name too. It prevent searching and conversion from encoding
* to encoding name in getdatabaseencoding() and other routines.
*
* Default is PG_SQL_ASCII encoding (but this is never used, because
* backend during startup init it by SetDatabaseEncoding()).
*
* Karel Zak (Aug 2001)
*/
static pg_enc2name *ClientEncoding = NULL;
static pg_enc2name *DatabaseEncoding = &pg_enc2name_tbl[ PG_SQL_ASCII ];
static void (*client_to_mic) (); /* something to MIC */
static void (*client_from_mic) (); /* MIC to something */
static void (*server_to_mic) (); /* something to MIC */
static void (*server_from_mic) (); /* MIC to something */
/*
* find encoding table entry by encoding
*/
pg_encoding_conv_tbl *
pg_get_enc_ent(int encoding)
pg_enconv *
pg_get_enconv_by_encoding(int encoding)
{
pg_encoding_conv_tbl *p = pg_conv_tbl;
for (; p->encoding >= 0; p++)
if (PG_VALID_ENCODING(encoding))
{
if (p->encoding == encoding)
return (p);
Assert((&pg_enconv_tbl[ encoding ])->encoding == encoding);
return &pg_enconv_tbl[ encoding ];
}
return (0);
return 0;
}
/*
@@ -56,38 +66,38 @@ pg_find_encoding_converters(int src, int dest, void (**src_to_mic)(), void (**de
{ /* src == dest? */
*src_to_mic = *dest_from_mic = 0;
}
else if (src == MULE_INTERNAL)
else if (src == PG_MULE_INTERNAL)
{ /* src == MULE_INETRNAL? */
*dest_from_mic = pg_get_enc_ent(dest)->from_mic;
*dest_from_mic = pg_get_enconv_by_encoding(dest)->from_mic;
if (*dest_from_mic == 0)
return (-1);
*src_to_mic = 0;
}
else if (dest == MULE_INTERNAL)
else if (dest == PG_MULE_INTERNAL)
{ /* dest == MULE_INETRNAL? */
*src_to_mic = pg_get_enc_ent(src)->to_mic;
*src_to_mic = pg_get_enconv_by_encoding(src)->to_mic;
if (*src_to_mic == 0)
return (-1);
*dest_from_mic = 0;
}
else if (src == UNICODE)
else if (src == PG_UTF8)
{ /* src == UNICODE? */
*dest_from_mic = pg_get_enc_ent(dest)->from_unicode;
*dest_from_mic = pg_get_enconv_by_encoding(dest)->from_unicode;
if (*dest_from_mic == 0)
return (-1);
*src_to_mic = 0;
}
else if (dest == UNICODE)
else if (dest == PG_UTF8)
{ /* dest == UNICODE? */
*src_to_mic = pg_get_enc_ent(src)->to_unicode;
*src_to_mic = pg_get_enconv_by_encoding(src)->to_unicode;
if (*src_to_mic == 0)
return (-1);
*dest_from_mic = 0;
}
else
{
*src_to_mic = pg_get_enc_ent(src)->to_mic;
*dest_from_mic = pg_get_enc_ent(dest)->from_mic;
*src_to_mic = pg_get_enconv_by_encoding(src)->to_mic;
*dest_from_mic = pg_get_enconv_by_encoding(dest)->from_mic;
if (*src_to_mic == 0 || *dest_from_mic == 0)
return (-1);
}
@@ -101,11 +111,17 @@ pg_find_encoding_converters(int src, int dest, void (**src_to_mic)(), void (**de
int
pg_set_client_encoding(int encoding)
{
int current_server_encoding = GetDatabaseEncoding();
int current_server_encoding = DatabaseEncoding->encoding;
if (!PG_VALID_FE_ENCODING(encoding))
return (-1);
if (pg_find_encoding_converters(encoding, current_server_encoding, &client_to_mic, &server_from_mic) < 0)
return (-1);
client_encoding = encoding;
ClientEncoding = &pg_enc2name_tbl[ encoding ];
Assert(ClientEncoding->encoding == encoding);
if (pg_find_encoding_converters(current_server_encoding, encoding, &server_to_mic, &client_from_mic) < 0)
return (-1);
@@ -118,12 +134,30 @@ pg_set_client_encoding(int encoding)
int
pg_get_client_encoding()
{
if (client_encoding == -1)
Assert(DatabaseEncoding);
if (ClientEncoding == NULL)
{
/* this is the first time */
client_encoding = GetDatabaseEncoding();
ClientEncoding = DatabaseEncoding;
}
return (client_encoding);
return (ClientEncoding->encoding);
}
/*
* returns the current client encoding name
*/
const char *
pg_get_client_encoding_name()
{
Assert(DatabaseEncoding);
if (ClientEncoding == NULL)
{
/* this is the first time */
ClientEncoding = DatabaseEncoding;
}
return (ClientEncoding->name);
}
/*
@@ -189,7 +223,7 @@ pg_convert(PG_FUNCTION_ARGS)
text *string = PG_GETARG_TEXT_P(0);
Name s = PG_GETARG_NAME(1);
int encoding = pg_char_to_encoding(NameStr(*s));
int db_encoding = GetDatabaseEncoding();
int db_encoding = DatabaseEncoding->encoding;
void (*src)(), (*dest)();
unsigned char *result;
text *retval;
@@ -277,7 +311,10 @@ pg_convert2(PG_FUNCTION_ARGS)
unsigned char *
pg_client_to_server(unsigned char *s, int len)
{
if (client_encoding == GetDatabaseEncoding())
Assert(ClientEncoding);
Assert(DatabaseEncoding);
if (ClientEncoding->encoding == DatabaseEncoding->encoding)
return s;
return pg_do_encoding_conversion(s, len, client_to_mic, server_from_mic);
@@ -299,7 +336,10 @@ pg_client_to_server(unsigned char *s, int len)
unsigned char *
pg_server_to_client(unsigned char *s, int len)
{
if (client_encoding == GetDatabaseEncoding())
Assert(ClientEncoding);
Assert(DatabaseEncoding);
if (ClientEncoding->encoding == DatabaseEncoding->encoding)
return s;
return pg_do_encoding_conversion(s, len, server_to_mic, client_from_mic);
@@ -309,21 +349,21 @@ pg_server_to_client(unsigned char *s, int len)
int
pg_mb2wchar(const unsigned char *from, pg_wchar * to)
{
return (*pg_wchar_table[GetDatabaseEncoding()].mb2wchar_with_len) (from, to, strlen(from));
return (*pg_wchar_table[ DatabaseEncoding->encoding ].mb2wchar_with_len) (from, to, strlen(from));
}
/* convert a multi-byte string to a wchar with a limited length */
int
pg_mb2wchar_with_len(const unsigned char *from, pg_wchar * to, int len)
{
return (*pg_wchar_table[GetDatabaseEncoding()].mb2wchar_with_len) (from, to, len);
return (*pg_wchar_table[ DatabaseEncoding->encoding ].mb2wchar_with_len) (from, to, len);
}
/* returns the byte length of a multi-byte word */
int
pg_mblen(const unsigned char *mbstr)
{
return ((*pg_wchar_table[GetDatabaseEncoding()].mblen) (mbstr));
return ((*pg_wchar_table[ DatabaseEncoding->encoding ].mblen) (mbstr));
}
/* returns the length (counted as a wchar) of a multi-byte string */
@@ -407,27 +447,33 @@ pg_mbcharcliplen(const unsigned char *mbstr, int len, int limit)
return (clen);
}
/*
* functions for utils/init */
static int DatabaseEncoding = MULTIBYTE;
void
SetDatabaseEncoding(int encoding)
{
DatabaseEncoding = encoding;
if (!PG_VALID_BE_ENCODING(encoding))
elog(ERROR, "SetDatabaseEncoding(): invalid database encoding");
DatabaseEncoding = &pg_enc2name_tbl[ encoding ];
Assert(DatabaseEncoding->encoding == encoding);
}
int
GetDatabaseEncoding()
{
return (DatabaseEncoding);
Assert(DatabaseEncoding);
return (DatabaseEncoding->encoding);
}
const char *
GetDatabaseEncodingName()
{
Assert(DatabaseEncoding);
return (DatabaseEncoding->name);
}
/* for builtin-function */
Datum
getdatabaseencoding(PG_FUNCTION_ARGS)
{
const char *encoding_name = pg_encoding_to_char(DatabaseEncoding);
return DirectFunctionCall1(namein, CStringGetDatum(encoding_name));
Assert(DatabaseEncoding);
return DirectFunctionCall1(namein, CStringGetDatum(DatabaseEncoding->name));
}

View File

@@ -1,16 +1,22 @@
/*
* conversion functions between pg_wchar and multi-byte streams.
* Tatsuo Ishii
* $Id: wchar.c,v 1.18 2001/04/19 02:34:35 ishii Exp $
* $Id: wchar.c,v 1.19 2001/09/06 04:57:29 ishii Exp $
*
* WIN1250 client encoding updated by Pavel Behal
*
*/
/* can be used in either frontend or backend */
#include "postgres_fe.h"
#include "mb/pg_wchar.h"
#ifdef FRONTEND
#define Assert(condition)
#else
#include "postgres.h"
#endif
/*
* conversion to pg_wchar is done by "table driven."
* to add an encoding support, define mb2wchar_with_len(), mblen()
@@ -452,41 +458,24 @@ pg_big5_mblen(const unsigned char *s)
}
pg_wchar_tbl pg_wchar_table[] = {
{pg_ascii2wchar_with_len, pg_ascii_mblen}, /* 0 */
{pg_eucjp2wchar_with_len, pg_eucjp_mblen}, /* 1 */
{pg_euccn2wchar_with_len, pg_euccn_mblen}, /* 2 */
{pg_euckr2wchar_with_len, pg_euckr_mblen}, /* 3 */
{pg_euctw2wchar_with_len, pg_euctw_mblen}, /* 4 */
{pg_utf2wchar_with_len, pg_utf_mblen}, /* 5 */
{pg_mule2wchar_with_len, pg_mule_mblen}, /* 6 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 7 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 8 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 9 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 10 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 11 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 12 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 13 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 14 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 15 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 16 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 17 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 18 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 19 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 20 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 21 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 22 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 23 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 24 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 25 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 26 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 27 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 28 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 29 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 30 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 31 */
{0, pg_sjis_mblen}, /* 32 */
{0, pg_big5_mblen}, /* 33 */
{pg_latin12wchar_with_len, pg_latin1_mblen} /* 34 */
{pg_ascii2wchar_with_len, pg_ascii_mblen}, /* 0; PG_SQL_ASCII */
{pg_eucjp2wchar_with_len, pg_eucjp_mblen}, /* 1; PG_EUC_JP */
{pg_euccn2wchar_with_len, pg_euccn_mblen}, /* 2; PG_EUC_CN */
{pg_euckr2wchar_with_len, pg_euckr_mblen}, /* 3; PG_EUC_KR */
{pg_euctw2wchar_with_len, pg_euctw_mblen}, /* 4; PG_EUC_TW */
{pg_utf2wchar_with_len, pg_utf_mblen}, /* 5; PG_UNICODE */
{pg_mule2wchar_with_len, pg_mule_mblen}, /* 6; PG_MULE_INTERNAL */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 7; PG_LATIN1 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 8; PG_LATIN2 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 9; PG_LATIN3 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 10; PG_LATIN4 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 11; PG_LATIN5 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 12; PG_KOI8 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 13; PG_WIN1251 */
{pg_latin12wchar_with_len, pg_latin1_mblen}, /* 14; PG_ALT */
{0, pg_sjis_mblen}, /* 15; PG_SJIS */
{0, pg_big5_mblen}, /* 17; PG_BIG5 */
{pg_latin12wchar_with_len, pg_latin1_mblen} /* 18; PG_WIN1250 */
};
/* returns the byte length of a word for mule internal code */
@@ -502,5 +491,10 @@ pg_mic_mblen(const unsigned char *mbstr)
int
pg_encoding_mblen(int encoding, const unsigned char *mbstr)
{
return( (encoding >= 0 && encoding < sizeof(pg_wchar_table)/sizeof(pg_wchar_tbl))? ((*pg_wchar_table[encoding].mblen) (mbstr)) : ((*pg_wchar_table[SQL_ASCII].mblen) (mbstr)));
Assert(PG_VALID_ENCODING(encoding));
return( (encoding >= 0 &&
encoding < sizeof(pg_wchar_table)/sizeof(pg_wchar_tbl)) ?
((*pg_wchar_table[encoding].mblen) (mbstr)) :
((*pg_wchar_table[PG_SQL_ASCII].mblen) (mbstr)));
}