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

3 files changed, 155 insertions, 69 deletions

diff --git a/src/include/catalog/pg_proc.h b/src/include/catalog/pg_proc.h
index fbea1d09a5c..fc1a5a73b67 100644
--- a/src/include/catalog/pg_proc.h
+++ b/src/include/catalog/pg_proc.h
@@ -7,7 +7,7 @@
  * 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
@@ -2136,6 +2136,8 @@ DATA(insert OID =  937 (  substring    PGUID 14 f t t t 2 f 25 "25 23" 100 0 0 1
 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");
 
diff --git a/src/include/mb/pg_wchar.h b/src/include/mb/pg_wchar.h
index 6df58708f67..ed1a6e19093 100644
--- a/src/include/mb/pg_wchar.h
+++ b/src/include/mb/pg_wchar.h
@@ -1,4 +1,4 @@
-/* $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
@@ -12,30 +12,9 @@
 #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;
 
@@ -67,12 +46,12 @@ 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 */
@@ -81,27 +60,129 @@ typedef unsigned int pg_wchar;
 #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[];
 
@@ -110,25 +191,25 @@ 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 *);
@@ -137,25 +218,25 @@ extern int	pg_mbstrlen(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);
 
diff --git a/src/include/utils/builtins.h b/src/include/utils/builtins.h
index bb91e1166e1..cb3a0a8913b 100644
--- a/src/include/utils/builtins.h
+++ b/src/include/utils/builtins.h
@@ -7,7 +7,7 @@
  * 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 $
  *
  *-------------------------------------------------------------------------
  */
@@ -579,8 +579,11 @@ extern Datum RI_FKey_setdefault_upd(PG_FUNCTION_ARGS);
  * 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);