*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/commands/dbcommands.c,v 1.79 2001/08/26 16:55:59 tgl Exp $
+ * $Header: /cvsroot/pgsql/src/backend/commands/dbcommands.c,v 1.80 2001/09/06 04:57:28 ishii Exp $
*
*-------------------------------------------------------------------------
*/
#include "utils/fmgroids.h"
#include "utils/syscache.h"
+#ifdef MULTIBYTE
+#include "mb/pg_wchar.h" /* encoding check */
+#endif
+
/* non-export function prototypes */
static bool get_db_info(const char *name, Oid *dbIdP, int4 *ownerIdP,
if (encoding < 0)
encoding = src_encoding;
+#ifdef MULTIBYTE
+ /* Some encodings are client only */
+ if (!PG_VALID_BE_ENCODING( encoding ))
+ elog(ERROR, "CREATE DATABASE: invalid backend encoding");
+#else
+ Assert(encoding == 0); /* zero is PG_SQL_ASCII */
+#endif
/*
* Preassign OID for pg_database tuple, so that we can compute db
* path.
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/commands/variable.c,v 1.51 2001/06/30 22:03:25 petere Exp $
+ * $Header: /cvsroot/pgsql/src/backend/commands/variable.c,v 1.52 2001/09/06 04:57:28 ishii Exp $
*
*-------------------------------------------------------------------------
*/
#include "mb/pg_wchar.h"
#else
/* Grand unified hard-coded badness */
-#define pg_encoding_to_char(x) "SQL_ASCII"
-#define pg_get_client_encoding() 0
+#define pg_get_client_encoding_name() "SQL_ASCII"
+#define GetDatabaseEncodingName() "SQL_ASCII"
#endif
}
else
{
- if (pg_set_client_encoding(encoding))
+ if (pg_set_client_encoding(encoding) < 0)
{
elog(ERROR, "Conversion between %s and %s is not supported",
- value, pg_encoding_to_char(GetDatabaseEncoding()));
+ value, GetDatabaseEncodingName());
}
}
#else
if (value &&
- strcasecmp(value, pg_encoding_to_char(pg_get_client_encoding())) != 0)
+ strcasecmp(value, pg_get_client_encoding_name()) != 0)
elog(ERROR, "Client encoding %s is not supported", value);
#endif
return TRUE;
show_client_encoding(void)
{
elog(NOTICE, "Current client encoding is %s",
- pg_encoding_to_char(pg_get_client_encoding()));
+ pg_get_client_encoding_name());
return TRUE;
}
static bool
show_server_encoding(void)
{
- elog(NOTICE, "Current server encoding is %s",
- pg_encoding_to_char(GetDatabaseEncoding()));
+ elog(NOTICE, "Current server encoding is %s", GetDatabaseEncodingName());
return TRUE;
}
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/backend/parser/gram.y,v 2.249 2001/08/26 16:55:59 tgl Exp $
+ * $Header: /cvsroot/pgsql/src/backend/parser/gram.y,v 2.250 2001/09/06 04:57:28 ishii Exp $
*
* HISTORY
* AUTHOR DATE MAJOR EVENT
#ifdef MULTIBYTE
#include "mb/pg_wchar.h"
#else
-#define GetStandardEncoding() 0 /* SQL_ASCII */
+#define GetStandardEncoding() 0 /* PG_SQL_ASCII */
#define GetStandardEncodingName() "SQL_ASCII"
#endif
| ENCODING '=' Iconst
{
#ifdef MULTIBYTE
- if (!pg_get_encent_by_encoding($3))
+ if (!pg_get_enconv_by_encoding($3))
elog(ERROR, "%d is not a valid encoding code", $3);
#else
if ($3 != GetStandardEncoding())
/* -----------------------------------------------------------------------
* 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
*
#define RANGE_160 160
- if (enc == LATIN1)
+ if (enc == PG_LATIN1)
{
/*
ascii = " cL Y \"Ca -R 'u ., ?AAAAAAACEEEEIIII NOOOOOxOUUUUYTBaaaaaaaceeeeiiii nooooo/ouuuuyty";
range = RANGE_160;
}
- else if (enc == LATIN2)
+ else if (enc == PG_LATIN2)
{
/*
ascii = " A L LS \"SSTZ-ZZ a,l'ls ,sstz\"zzRAAAALCCCEEEEIIDDNNOOOOxRUUUUYTBraaaalccceeeeiiddnnoooo/ruuuuyt.";
range = RANGE_160;
}
- else if (enc == WIN1250)
+ else if (enc == PG_WIN1250)
{
/*
*
*
* 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 $
*
*
*-------------------------------------------------------------------------
#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
# 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 $
#
#-------------------------------------------------------------------------
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
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:
#
# 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 $
#
#-------------------------------------------------------------------------
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 \
#
# 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.
# # 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) {
#
* 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 $
*
*
*/
#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 */
* 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);
}
/* 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,
/* 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,
*/
/*
- * 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);
}
/*
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)
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)
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);
}
/*
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);
}
/*
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);
}
/*
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);
}
/*
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
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);
}
/*
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);
}
/*
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);
}
/*
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);
}
/*
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);
}
/*
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);
-}
-
-/*-----------------------------------------------------------------*/
-
-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 */
+ sizeof(LUmapBIG5) / sizeof(pg_local_to_utf), PG_BIG5, len);
+}
+
+/* ----------
+ * 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 */
* 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"
#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;
}
/*
{ /* 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);
}
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);
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);
}
/*
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;
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);
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);
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 */
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));
}
/*
* 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()
}
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 */
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)));
}
# Portions Copyright (c) 1996-2001, PostgreSQL Global Development Group
# Portions Copyright (c) 1994, Regents of the University of California
#
-# $Header: /cvsroot/pgsql/src/bin/initdb/Attic/initdb.sh,v 1.135 2001/08/26 16:56:00 tgl Exp $
+# $Header: /cvsroot/pgsql/src/bin/initdb/Attic/initdb.sh,v 1.136 2001/09/06 04:57:29 ishii Exp $
#
#-------------------------------------------------------------------------
if [ "$MULTIBYTE" ]
then
- MULTIBYTEID=`$PGPATH/pg_encoding $MULTIBYTE`
+ MULTIBYTEID=`$PGPATH/pg_encoding -b $MULTIBYTE`
if [ "$?" -ne 0 ]
then
(
fi
if [ -z "$MULTIBYTEID" ]
then
- echo "$CMDNAME: $MULTIBYTE is not a valid encoding name" 1>&2
- exit 1
- elif [ $MULTIBYTEID -gt 31 ]
- then
- echo "$CMDNAME: $MULTIBYTE cannot be used as a database encoding" 1>&2
+ echo "$CMDNAME: $MULTIBYTE is not a valid backend encoding name" 1>&2
exit 1
fi
fi
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/bin/pg_encoding/Attic/pg_encoding.c,v 1.8 2000/02/19 04:59:30 ishii Exp $
+ * $Header: /cvsroot/pgsql/src/bin/pg_encoding/Attic/pg_encoding.c,v 1.9 2001/09/06 04:57:29 ishii Exp $
*
*-------------------------------------------------------------------------
*/
#include "miscadmin.h"
#include "mb/pg_wchar.h"
+#include <ctype.h>
+
static void usage(void);
int
main(int argc, char **argv)
{
- char c;
- char *p;
- int rtn;
+ char *p;
+ int enc;
+ bool be_only = FALSE;
if (argc < 2)
{
usage();
exit(1);
}
- p = argv[1];
- while ((c = *p++))
+
+ if (strcmp(argv[1], "-b")==0)
{
- if (c < '0' || c > '9')
+ if (argc < 3)
{
- rtn = pg_char_to_encoding(argv[1]);
- if (rtn >= 0)
- printf("%d\n", rtn);
- exit(0);
+ usage();
+ exit(1);
}
+ be_only = TRUE;
+ p = argv[2];
}
- printf("%s\n", pg_encoding_to_char(atoi(argv[1])));
- exit(0);
+ else
+ p = argv[1];
+
+ if (p && *p && isdigit((unsigned char) *p))
+ {
+ /*
+ * Encoding number to name
+ */
+ char *name;
+
+ enc = atoi(p);
+
+ if ((name = (char *) pg_encoding_to_char(enc)))
+ {
+ if (be_only && pg_valid_server_encoding(name) < 0)
+ exit(0);
+ printf("%s\n", name);
+ }
+ exit(0);
+ }
+ else if (p && *p)
+ {
+ /*
+ * Encoding name to encoding number
+ */
+ if ((enc = pg_char_to_encoding(p)) >= 0)
+ {
+ if (be_only && pg_valid_server_encoding(p) < 0)
+ exit(0);
+ printf("%d\n", enc);
+ }
+ exit(0);
+ }
+ exit(1);
}
static void
usage()
{
- fprintf(stderr, "\nUsage: pg_encoding encoding_name | encoding_number\n\n");
+ fprintf(stderr,
+ "\nUsage: pg_encoding [options] encoding_name | encoding_number\n\n"
+ "options:"
+ " -b check if encoding is valid for backend\n\n"
+ );
}
#
#
# IDENTIFICATION
-# $Header: /cvsroot/pgsql/src/bin/scripts/Attic/createdb,v 1.15 2001/03/27 05:47:13 ishii Exp $
+# $Header: /cvsroot/pgsql/src/bin/scripts/Attic/createdb,v 1.16 2001/09/06 04:57:29 ishii Exp $
#
#-------------------------------------------------------------------------
then
echo "$CMDNAME: \"$MB\" is not a valid encoding name" 1>&2
exit 1
- elif [ $mbcode -gt 31 ]
- then
- echo "$CMDNAME: $MB cannot be used as a database encoding" 1>&2
- exit 1
fi
fi
* Portions Copyright (c) 1996-2001, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $Id: pg_proc.h,v 1.208 2001/09/06 03:22:42 momjian Exp $
+ * $Id: pg_proc.h,v 1.209 2001/09/06 04:57:29 ishii Exp $
*
* NOTES
* The script catalog/genbki.sh reads this file and generates .bki
DESCR("return portion of string");
/* for multi-byte support */
+
+/* old encoding names - back compatibility only */
DATA(insert OID = 1039 ( getdatabaseencoding PGUID 12 f t f t 0 f 19 "0" 100 0 0 100 getdatabaseencoding - ));
DESCR("encoding name of current database");
-/* $Id: pg_wchar.h,v 1.28 2001/08/15 07:07:40 ishii Exp $ */
+/* $Id: pg_wchar.h,v 1.29 2001/09/06 04:57:29 ishii Exp $ */
#ifndef PG_WCHAR_H
#define PG_WCHAR_H
#define pfree free
#endif
-#define SQL_ASCII 0 /* SQL/ASCII */
-#define EUC_JP 1 /* EUC for Japanese */
-#define EUC_CN 2 /* EUC for Chinese */
-#define EUC_KR 3 /* EUC for Korean */
-#define EUC_TW 4 /* EUC for Taiwan */
-#define UNICODE 5 /* Unicode UTF-8 */
-#define MULE_INTERNAL 6 /* Mule internal code */
-#define LATIN1 7 /* ISO-8859 Latin 1 */
-#define LATIN2 8 /* ISO-8859 Latin 2 */
-#define LATIN3 9 /* ISO-8859 Latin 3 */
-#define LATIN4 10 /* ISO-8859 Latin 4 */
-#define LATIN5 11 /* ISO-8859 Latin 5 */
-#define LATIN6 12 /* ISO-8859 Latin 6 */
-#define LATIN7 13 /* ISO-8859 Latin 7 */
-#define LATIN8 14 /* ISO-8859 Latin 8 */
-#define LATIN9 15 /* ISO-8859 Latin 9 */
-#define KOI8 16 /* KOI8-R/U */
-#define WIN 17 /* windows-1251 */
-#define ALT 18 /* Alternativny Variant (MS-DOS CP866) */
-/* followings are for client encoding only */
-#define SJIS 32 /* Shift JIS */
-#define BIG5 33 /* Big5 */
-#define WIN1250 34 /* windows-1250 */
-
+/*
+ * The pg_wchar
+ */
#ifdef MULTIBYTE
typedef unsigned int pg_wchar;
#define LC_ISO8859_5 0x8d /* ISO8859 Latin 5 */
#define LC_JISX0201K 0x89 /* Japanese 1 byte kana */
#define LC_JISX0201R 0x8a /* Japanese 1 byte Roman */
-#define LC_KOI8_R 0x8c /* Cyrillic KOI8-R */
-#define LC_KOI8_U 0x8c /* Cyrillic KOI8-U */
+#define LC_KOI8_R 0x8c /* Cyrillic KOI8-R */
+#define LC_KOI8_U 0x8c /* Cyrillic KOI8-U */
#define LC_GB2312_80 0x91 /* Chinese */
-#define LC_JISX0208 0x92 /* Japanese Kanji */
-#define LC_KS5601 0x93 /* Korean */
-#define LC_JISX0212 0x94 /* Japanese Kanji (JISX0212) */
+#define LC_JISX0208 0x92 /* Japanese Kanji */
+#define LC_KS5601 0x93 /* Korean */
+#define LC_JISX0212 0x94 /* Japanese Kanji (JISX0212) */
#define LC_CNS11643_1 0x95 /* CNS 11643-1992 Plane 1 */
#define LC_CNS11643_2 0x96 /* CNS 11643-1992 Plane 2 */
#define LC_CNS11643_3 0xf6 /* CNS 11643-1992 Plane 3 */
#define LC_CNS11643_6 0xf9 /* CNS 11643-1992 Plane 6 */
#define LC_CNS11643_7 0xfa /* CNS 11643-1992 Plane 7 */
+/*
+ * Encoding numeral identificators
+ *
+ * WARNING: the order of this table must be same as order
+ * in the pg_enconv[] (mb/conv.c) and pg_enc2name[] (mb/names.c) array!
+ *
+ * If you add some encoding don'y forget check
+ * PG_ENCODING_[BE|FE]_LAST macros.
+ *
+ * The PG_SQL_ASCII is default encoding and must be = 0.
+ */
+typedef enum pg_enc
+{
+ PG_SQL_ASCII = 0, /* SQL/ASCII */
+ PG_EUC_JP, /* EUC for Japanese */
+ PG_EUC_CN, /* EUC for Chinese */
+ PG_EUC_KR, /* EUC for Korean */
+ PG_EUC_TW, /* EUC for Taiwan */
+ PG_UTF8, /* Unicode UTF-8 */
+ PG_MULE_INTERNAL, /* Mule internal code */
+ PG_LATIN1, /* ISO-8859 Latin 1 */
+ PG_LATIN2, /* ISO-8859 Latin 2 */
+ PG_LATIN3, /* ISO-8859 Latin 3 */
+ PG_LATIN4, /* ISO-8859 Latin 4 */
+ PG_LATIN5, /* ISO-8859 Latin 5 */
+ PG_KOI8R, /* KOI8-R */
+ PG_WIN1251, /* windows-1251 (was: WIN) */
+ PG_ALT, /* (MS-DOS CP866) */
+
+ /* followings are for client encoding only */
+ PG_SJIS, /* Shift JIS */
+ PG_BIG5, /* Big5 */
+ PG_WIN1250, /* windows-1250 */
+
+ _PG_LAST_ENCODING_ /* mark only */
+
+} pg_enc;
+
+#define PG_ENCODING_BE_LAST PG_ALT
+#define PG_ENCODING_FE_LAST PG_WIN1250
+
+
#ifdef MULTIBYTE
-typedef struct
+
+/*
+ * Please use these tests before access to pg_encconv_tbl[]
+ * or to other places...
+ */
+#define PG_VALID_BE_ENCODING(_enc) \
+ ((_enc) >= 0 && (_enc) <= PG_ENCODING_BE_LAST)
+
+#define PG_ENCODING_IS_CLIEN_ONLY(_enc) \
+ (((_enc) > PG_ENCODING_BE_LAST && (_enc) <= PG_ENCODING_FE_LAST)
+
+#define PG_VALID_ENCODING(_enc) \
+ ((_enc) >= 0 && (_enc) < _PG_LAST_ENCODING_)
+
+/* On FE are possible all encodings
+ */
+#define PG_VALID_FE_ENCODING(_enc) PG_VALID_ENCODING(_enc)
+
+/*
+ * Encoding names with all aliases
+ */
+typedef struct pg_encname
+{
+ char *name;
+ pg_enc encoding;
+} pg_encname;
+
+extern pg_encname pg_encname_tbl[];
+extern unsigned int pg_encname_tbl_sz;
+
+/*
+ * Careful:
+ *
+ * if (PG_VALID_ENCODING(encoding))
+ * pg_enc2name_tbl[ encoding ];
+ */
+typedef struct pg_enc2name
{
- int encoding; /* encoding symbol value */
- char *name; /* encoding name */
- int is_client_only; /* 0: server/client both supported 1:
- * client only */
- void (*to_mic) (); /* client encoding to MIC */
- void (*from_mic) (); /* MIC to client encoding */
- void (*to_unicode) (); /* client encoding to UTF-8 */
- void (*from_unicode) (); /* UTF-8 to client encoding */
-} pg_encoding_conv_tbl;
-
-extern pg_encoding_conv_tbl pg_conv_tbl[];
+ char *name;
+ pg_enc encoding;
+} pg_enc2name;
+
+extern pg_enc2name pg_enc2name_tbl[];
+
+extern pg_encname *pg_char_to_encname_struct(const char *name);
+extern int pg_char_to_encoding(const char *s);
+extern const char *pg_encoding_to_char(int encoding);
+
+/*
+ * The backend encoding conversion routines
+ * Careful:
+ *
+ * if (PG_VALID_ENCODING(enc))
+ * pg_encconv_tbl[ enc ]->foo
+ */
+#ifndef FRONTEND
+typedef struct pg_enconv
+{
+ pg_enc encoding; /* encoding identificator */
+ void (*to_mic) (); /* client encoding to MIC */
+ void (*from_mic) (); /* MIC to client encoding */
+ void (*to_unicode) (); /* client encoding to UTF-8 */
+ void (*from_unicode) (); /* UTF-8 to client encoding */
+} pg_enconv;
+
+extern pg_enconv pg_enconv_tbl[];
+extern pg_enconv *pg_get_enconv_by_encoding(int encoding);
+
+#endif /* FRONTEND */
+
+/*
+ * pg_wchar stuff
+ */
typedef struct
{
- int (*mb2wchar_with_len) (); /* convert a multi-byte
- * string to a wchar */
- int (*mblen) (); /* returns the length of a multi-byte word */
-} pg_wchar_tbl;
+ int (*mb2wchar_with_len) (); /* convert a multi-byte
+ * string to a wchar */
+ int (*mblen) (); /* returns the length of a multi-byte word */
+} pg_wchar_tbl;
extern pg_wchar_tbl pg_wchar_table[];
*/
typedef struct
{
- unsigned int utf; /* UTF-8 */
- unsigned int code; /* local code */
-} pg_utf_to_local;
+ unsigned int utf; /* UTF-8 */
+ unsigned int code; /* local code */
+} pg_utf_to_local;
/*
* local code to UTF-8 conversion map
*/
typedef struct
{
- unsigned int code; /* local code */
- unsigned int utf; /* UTF-8 */
-} pg_local_to_utf;
+ unsigned int code; /* local code */
+ unsigned int utf; /* UTF-8 */
+} pg_local_to_utf;
extern int pg_mb2wchar(const unsigned char *, pg_wchar *);
extern int pg_mb2wchar_with_len(const unsigned char *, pg_wchar *, int);
extern int pg_char_and_wchar_strcmp(const char *, const pg_wchar *);
extern int pg_wchar_strncmp(const pg_wchar *, const pg_wchar *, size_t);
extern int pg_char_and_wchar_strncmp(const char *, const pg_wchar *, size_t);
-extern size_t pg_wchar_strlen(const pg_wchar *);
+extern size_t pg_wchar_strlen(const pg_wchar *);
extern int pg_mblen(const unsigned char *);
extern int pg_encoding_mblen(int, const unsigned char *);
extern int pg_mule_mblen(const unsigned char *);
extern int pg_mbstrlen_with_len(const unsigned char *, int);
extern int pg_mbcliplen(const unsigned char *, int, int);
extern int pg_mbcharcliplen(const unsigned char *, int, int);
-extern pg_encoding_conv_tbl *pg_get_encent_by_encoding(int);
-extern int pg_set_client_encoding(int);
-extern int pg_get_client_encoding(void);
-extern unsigned char *pg_client_to_server(unsigned char *, int);
-extern unsigned char *pg_server_to_client(unsigned char *, int);
-extern int pg_valid_client_encoding(const char *);
-extern pg_encoding_conv_tbl *pg_get_enc_ent(int);
+
+extern int pg_set_client_encoding(int);
+extern int pg_get_client_encoding(void);
+extern const char *pg_get_client_encoding_name(void);
+
+extern void SetDatabaseEncoding(int);
+extern int GetDatabaseEncoding(void);
+extern const char *GetDatabaseEncodingName(void);
+
+extern int pg_valid_client_encoding(const char *name);
+extern int pg_valid_server_encoding(const char *name);
+
extern int pg_utf_mblen(const unsigned char *);
extern int pg_find_encoding_converters(int, int, void (**)(), void (**)());
extern unsigned char *pg_do_encoding_conversion(unsigned char *, int, void (*)(), void (*)());
-/* internally-used versions of functions. The PG_xxx forms of these
- * functions have fmgr-compatible interfaves.
- */
-extern const char *pg_encoding_to_char(int);
-extern int pg_char_to_encoding(const char *);
+extern unsigned char *pg_client_to_server(unsigned char *, int);
+extern unsigned char *pg_server_to_client(unsigned char *, int);
-extern int GetDatabaseEncoding(void);
-extern void SetDatabaseEncoding(int);
extern unsigned short BIG5toCNS(unsigned short, unsigned char *);
extern unsigned short CNStoBIG5(unsigned short, unsigned char);
* Portions Copyright (c) 1996-2001, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
- * $Id: builtins.h,v 1.162 2001/08/15 07:07:40 ishii Exp $
+ * $Id: builtins.h,v 1.163 2001/09/06 04:57:29 ishii Exp $
*
*-------------------------------------------------------------------------
*/
* since pg_proc.h has references to them.
*/
extern Datum getdatabaseencoding(PG_FUNCTION_ARGS);
+extern Datum database_character_set(PG_FUNCTION_ARGS);
extern Datum PG_encoding_to_char(PG_FUNCTION_ARGS);
extern Datum PG_char_to_encoding(PG_FUNCTION_ARGS);
+extern Datum PG_character_set_name(PG_FUNCTION_ARGS);
+extern Datum PG_character_set_id(PG_FUNCTION_ARGS);
extern Datum pg_convert(PG_FUNCTION_ARGS);
extern Datum pg_convert2(PG_FUNCTION_ARGS);
#
# Copyright (c) 1994, Regents of the University of California
#
-# $Header: /cvsroot/pgsql/src/interfaces/libpq/Makefile,v 1.56 2001/08/28 14:20:28 petere Exp $
+# $Header: /cvsroot/pgsql/src/interfaces/libpq/Makefile,v 1.57 2001/09/06 04:57:30 ishii Exp $
#
#-------------------------------------------------------------------------
$(INET_ATON) $(SNPRINTF) $(STRERROR)
ifdef MULTIBYTE
-OBJS+= wchar.o
+OBJS+= wchar.o encnames.o
endif
# Add libraries that libpq depends (or might depend) on into the
ifdef MULTIBYTE
wchar.c : % : $(backend_src)/utils/mb/%
rm -f $@ && $(LN_S) $< .
+encnames.c : % : $(backend_src)/utils/mb/%
+ rm -f $@ && $(LN_S) $< .
endif
rm -f $(DESTDIR)$(includedir)/libpq-fe.h $(DESTDIR)$(includedir_internal)/libpq-int.h $(includedir_internal)/pqexpbuffer.h
clean distclean maintainer-clean: clean-lib
- rm -f $(OBJS) dllist.c md5.c md5.h wchar.c
+ rm -f $(OBJS) dllist.c md5.c md5.h wchar.c encnames.c
rm -f $(OBJS) inet_aton.c snprintf.c strerror.c
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/interfaces/libpq/fe-connect.c,v 1.176 2001/08/21 20:39:52 momjian Exp $
+ * $Header: /cvsroot/pgsql/src/interfaces/libpq/fe-connect.c,v 1.177 2001/09/06 04:57:30 ishii Exp $
*
*-------------------------------------------------------------------------
*/
/* set client encoding in pg_conn struct */
encoding = PQgetvalue(res, 0, 0);
if (!encoding) /* this should not happen */
- conn->client_encoding = SQL_ASCII;
+ conn->client_encoding = PG_SQL_ASCII;
else
conn->client_encoding = pg_char_to_encoding(encoding);
PQclear(res);
return (status);
}
-#else
+#else /* without multibytle support */
+
int
PQsetClientEncoding(PGconn *conn, const char *encoding)
{
/* Note: we expect the supplied string to end with a newline already. */
fprintf(stderr, "%s", message);
}
-
-#ifdef MULTIBYTE
-/*
- * convert an encoding string to encoding symbol value.
- * case is ignored.
- * if there's no valid encoding, returns -1
- */
-
-typedef struct
-{
- int encoding; /* encoding symbol value */
- char *name; /* encoding string */
-} PQ_encoding_conv_tbl;
-
-static PQ_encoding_conv_tbl pq_conv_tbl[] = {
- {SQL_ASCII, "SQL_ASCII"},
- {EUC_JP, "EUC_JP"},
- {EUC_CN, "EUC_CN"},
- {EUC_KR, "EUC_KR"},
- {EUC_TW, "EUC_TW"},
- {UNICODE, "UNICODE"},
- {MULE_INTERNAL, "MULE_INTERNAL"},
- {LATIN1, "LATIN1"},
- {LATIN2, "LATIN2"},
- {LATIN3, "LATIN3"},
- {LATIN4, "LATIN4"},
- {LATIN5, "LATIN5"},
- {KOI8, "KOI8"},
- {WIN, "WIN"},
- {ALT, "ALT"},
- {SJIS, "SJIS"},
- {BIG5, "BIG5"},
- {WIN1250, "WIN1250"},
- {-1, ""}
-};
-
-int
-pg_char_to_encoding(const char *s)
-{
- PQ_encoding_conv_tbl *p = pq_conv_tbl;
-
- if (!s)
- return (-1);
-
- for (; p->encoding >= 0; p++)
- {
- if (!strcasecmp(s, p->name))
- break;
- }
- return (p->encoding);
-}
-
-/*
- * convert encoding symbol to encoding char.
- * if there's no valid encoding symbol, returns ""
- */
-const char *
-pg_encoding_to_char(int encoding)
-{
- PQ_encoding_conv_tbl *p = pq_conv_tbl;
-
- for (; p->encoding >= 0; p++)
- {
- if (p->encoding == encoding)
- return (p->name);
- }
- return ("");
-}
-
-#endif
*
*
* IDENTIFICATION
- * $Header: /cvsroot/pgsql/src/interfaces/libpq/fe-misc.c,v 1.55 2001/09/06 02:52:00 momjian Exp $
+ * $Header: /cvsroot/pgsql/src/interfaces/libpq/fe-misc.c,v 1.56 2001/09/06 04:57:30 ishii Exp $
*
*-------------------------------------------------------------------------
*/
PQenv2encoding(void)
{
char *str;
- int encoding = SQL_ASCII;
+ int encoding = PG_SQL_ASCII;
str = getenv("PGCLIENTENCODING");
if (str && *str != '\0')
unsigned char *
check_client_encoding(unsigned char *str)
{
- if (strstr(str, "%27SJIS%27") || strstr(str, "'SJIS'") || strstr(str, "'sjis'"))
+ if (strstr(str, "%27SJIS%27") ||
+ strstr(str, "'SJIS'") ||
+ strstr(str, "'sjis'") ||
+ strstr(str, "'Shift_JIS'"))
{
multibyte_client_encoding = SJIS;
return ("SJIS");
}
- if (strstr(str, "%27BIG5%27") || strstr(str, "'BIG5'") || strstr(str, "'big5'"))
+ if (strstr(str, "%27BIG5%27") ||
+ strstr(str, "'BIG5'") ||
+ strstr(str, "'big5'")
+ strstr(str, "'Big5'"))
{
multibyte_client_encoding = BIG5;
return ("BIG5");
projects / users / rhaas / postgres.git / commitdiff