Message-ID: <49EC426F.5020602@hagander.net>
Date: Mon, 20 Apr 2009 11:37:51 +0200
From: Magnus Hagander <magnus@hagander.net>
User-Agent: Thunderbird 2.0.0.21 (X11/20090318)
MIME-Version: 1.0
To: Heikki Linnakangas <heikki.linnakangas@enterprisedb.com>
CC: Tom Lane <tgl@sss.pgh.pa.us>, pgsql-hackers@postgreSQL.org
Subject: Re: Re: [COMMITTERS] pgsql: Explicitly bind gettext to
	the correct encoding on Windows.
References: <20090122100948.89F977559ED@cvs.postgresql.org>
	<20643.1232666867@sss.pgh.pa.us> <499821F3.7050004@hagander.net>
	<22474.1234718514@sss.pgh.pa.us> <49D47C40.5040300@hagander.net>
	<49DC7E11.2050501@enterprisedb.com>
In-Reply-To: <49DC7E11.2050501@enterprisedb.com>
Content-Type: multipart/mixed; boundary="------------050005090506000602040207"

This is a multi-part message in MIME format.
--------------050005090506000602040207
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit

Heikki Linnakangas wrote:
> Magnus Hagander wrote:
>> Tom Lane wrote:
>>> Magnus Hagander <magnus@hagander.net> writes:
>>>> Tom Lane wrote:
>>>>> What makes more sense to me is to add a table to encnames.c that
>>>>> provides the gettext name of every encoding that we support.
>>>> Do you mean a separate table there, or should we add a new column to
>>>> one
>>>> of the existing tables?
>>> Whichever seems to make more sense is fine with me.  I just don't want
>>> add-an-encoding maintenance requirements spread across N different
>>> source files.
>>
>> I was about to start looking at this when that other thread
>> (http://archives.postgresql.org//pgsql-hackers/2009-03/msg01270.php)
>> started about related issues on other platforms. Seems we should have a
>> "coordinated fix" for this, so I'm going to want and see what come sout
>> of that one. Unless I'm misunderstanding thigns and they're not related?
> 
> I've committed a fairly trivial patch per Peter's suggestion to fix the
> other thread's issue. I left the table as is, so whatever refactorings
> were planned can now be applied.

Here's a patch that moves the table over to encnames.c, and renames it
to look like the others.

I don't know what it should be doing if it can't find a match, so I
haven't changed that behavior.

Comments?

//Magnus


--------------050005090506000602040207
Content-Type: text/x-diff;
 name="enctable.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="enctable.patch"

*** a/src/backend/utils/mb/encnames.c
--- b/src/backend/utils/mb/encnames.c
***************
*** 431,436 **** pg_enc2name pg_enc2name_tbl[] =
--- 431,478 ----
  };
  
  /* ----------
+  * These are encoding names for gettext.
+  * ----------
+  */
+ pg_enc2gettext pg_enc2gettext_tbl[] =
+ {
+ 	{PG_UTF8, "UTF-8"},
+ 	{PG_LATIN1, "LATIN1"},
+ 	{PG_LATIN2, "LATIN2"},
+ 	{PG_LATIN3, "LATIN3"},
+ 	{PG_LATIN4, "LATIN4"},
+ 	{PG_ISO_8859_5, "ISO-8859-5"},
+ 	{PG_ISO_8859_6, "ISO_8859-6"},
+ 	{PG_ISO_8859_7, "ISO-8859-7"},
+ 	{PG_ISO_8859_8, "ISO-8859-8"},
+ 	{PG_LATIN5, "LATIN5"},
+ 	{PG_LATIN6, "LATIN6"},
+ 	{PG_LATIN7, "LATIN7"},
+ 	{PG_LATIN8, "LATIN8"},
+ 	{PG_LATIN9, "LATIN-9"},
+ 	{PG_LATIN10, "LATIN10"},
+ 	{PG_KOI8R, "KOI8-R"},
+ 	{PG_KOI8U, "KOI8-U"},
+ 	{PG_WIN1250, "CP1250"},
+ 	{PG_WIN1251, "CP1251"},
+ 	{PG_WIN1252, "CP1252"},
+ 	{PG_WIN1253, "CP1253"},
+ 	{PG_WIN1254, "CP1254"},
+ 	{PG_WIN1255, "CP1255"},
+ 	{PG_WIN1256, "CP1256"},
+ 	{PG_WIN1257, "CP1257"},
+ 	{PG_WIN1258, "CP1258"},
+ 	{PG_WIN866, "CP866"},
+ 	{PG_WIN874, "CP874"},
+ 	{PG_EUC_CN, "EUC-CN"},
+ 	{PG_EUC_JP, "EUC-JP"},
+ 	{PG_EUC_KR, "EUC-KR"},
+ 	{PG_EUC_TW, "EUC-TW"},
+ 	{PG_EUC_JIS_2004, "EUC-JP"}
+ };
+ 
+ 
+ /* ----------
   * Encoding checks, for error returns -1 else encoding id
   * ----------
   */
*** a/src/backend/utils/mb/mbutils.c
--- b/src/backend/utils/mb/mbutils.c
***************
*** 890,936 **** cliplen(const char *str, int len, int limit)
  	return l;
  }
  
- #if defined(ENABLE_NLS)
- static const struct codeset_map {
- 	int	encoding;
- 	const char *codeset;
- } codeset_map_array[] = {
- 	{PG_UTF8, "UTF-8"},
- 	{PG_LATIN1, "LATIN1"},
- 	{PG_LATIN2, "LATIN2"},
- 	{PG_LATIN3, "LATIN3"},
- 	{PG_LATIN4, "LATIN4"},
- 	{PG_ISO_8859_5, "ISO-8859-5"},
- 	{PG_ISO_8859_6, "ISO_8859-6"},
- 	{PG_ISO_8859_7, "ISO-8859-7"},
- 	{PG_ISO_8859_8, "ISO-8859-8"},
- 	{PG_LATIN5, "LATIN5"},
- 	{PG_LATIN6, "LATIN6"},
- 	{PG_LATIN7, "LATIN7"},
- 	{PG_LATIN8, "LATIN8"},
- 	{PG_LATIN9, "LATIN-9"},
- 	{PG_LATIN10, "LATIN10"},
- 	{PG_KOI8R, "KOI8-R"},
- 	{PG_KOI8U, "KOI8-U"},
- 	{PG_WIN1250, "CP1250"},
- 	{PG_WIN1251, "CP1251"},
- 	{PG_WIN1252, "CP1252"},
- 	{PG_WIN1253, "CP1253"},
- 	{PG_WIN1254, "CP1254"},
- 	{PG_WIN1255, "CP1255"},
- 	{PG_WIN1256, "CP1256"},
- 	{PG_WIN1257, "CP1257"},
- 	{PG_WIN1258, "CP1258"},
- 	{PG_WIN866, "CP866"},
- 	{PG_WIN874, "CP874"},
- 	{PG_EUC_CN, "EUC-CN"},
- 	{PG_EUC_JP, "EUC-JP"},
- 	{PG_EUC_KR, "EUC-KR"},
- 	{PG_EUC_TW, "EUC-TW"},
- 	{PG_EUC_JIS_2004, "EUC-JP"}
- };
- #endif /* ENABLE_NLS */
- 
  void
  SetDatabaseEncoding(int encoding)
  {
--- 890,895 ----
***************
*** 969,980 **** pg_bind_textdomain_codeset(const char *domainname)
  		return;
  #endif
  
! 	for (i = 0; i < lengthof(codeset_map_array); i++)
  	{
! 		if (codeset_map_array[i].encoding == encoding)
  		{
  			if (bind_textdomain_codeset(domainname,
! 										codeset_map_array[i].codeset) == NULL)
  				elog(LOG, "bind_textdomain_codeset failed");
  			break;
  		}
--- 928,939 ----
  		return;
  #endif
  
! 	for (i = 0; pg_enc2gettext_tbl[i].name != NULL; i++)
  	{
! 		if (pg_enc2gettext_tbl[i].encoding == encoding)
  		{
  			if (bind_textdomain_codeset(domainname,
! 										pg_enc2gettext_tbl[i].name) == NULL)
  				elog(LOG, "bind_textdomain_codeset failed");
  			break;
  		}
*** a/src/include/mb/pg_wchar.h
--- b/src/include/mb/pg_wchar.h
***************
*** 262,267 **** typedef struct pg_enc2name
--- 262,278 ----
  extern pg_enc2name pg_enc2name_tbl[];
  
  /*
+  * Encoding names for gettext
+  */
+ typedef struct pg_enc2gettext
+ {
+ 	pg_enc		encoding;
+ 	const char *name;
+ } pg_enc2gettext;
+ 
+ extern pg_enc2gettext pg_enc2gettext_tbl[];
+ 
+ /*
   * pg_wchar stuff
   */
  typedef int (*mb2wchar_with_len_converter) (const unsigned char *from,

--------------050005090506000602040207--