Message-ID: <3A42C05C.8BC5858D@xythos.com>
Date: Thu, 21 Dec 2000 18:45:48 -0800
From: Barry Lind <barry@xythos.com>
MIME-Version: 1.0
To: pgsql-interfaces@postgresql.org
CC: pgsql-patches@postgresql.org
Subject: patch for character set encoding detection for JDBC
Content-Type: multipart/mixed; boundary="------------F58CD7E14C5DB056B6438612"

This is a multi-part message in MIME format.
--------------F58CD7E14C5DB056B6438612
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit


In looking at the 7.1beta1 code for JDBC, I noticed that support was
added to support character set encodings.  However I noticed that the
encoding that is used isn't obtained from the DB.  Since Java uses
unicode UCS2 internally the character set encoding is used to translate
strings from/to the DB encoding.  So it seems logical that the code
would get the encoding from the DB instead of the current method of
requiring the user pass it as a parameter.

Attached is a patch that gets the DB encoding from the DB in the same
manner as is done in libpq/fe-connect.c.  The patch is created off of
the latest CVS sources (Connection.java version 1.10). 

thanks,
--Barry
--------------F58CD7E14C5DB056B6438612
Content-Type: text/plain; charset=UTF-8; name="patch.diff"
Content-Transfer-Encoding: 7bit
Content-Disposition: inline; filename="patch.diff"

*** ./Connection.java.orig	Thu Dec 21 18:20:36 2000
--- ./Connection.java	Thu Dec 21 18:21:49 2000
***************
*** 125,132 ****
      PG_HOST = host;
      PG_STATUS = CONNECTION_BAD;
  
-     encoding = info.getProperty("charSet");  // could be null
-     
      // Now make the initial connection
      try
        {
--- 125,130 ----
***************
*** 265,274 ****
        // This may cause some clients to break when they assume anything other than ISO,
        // but then - they should be using the proper methods ;-)
        //
        //
        firstWarning = null;
        
!       ExecSQL("set datestyle to 'ISO'");
        
        // Initialise object handling
        initObjectTypes();
--- 263,346 ----
        // This may cause some clients to break when they assume anything other than ISO,
        // but then - they should be using the proper methods ;-)
        //
+       // We also ask the DB for certain properties (i.e. DatabaseEncoding at this time)
        //
        firstWarning = null;
        
!       java.sql.ResultSet initrset = ExecSQL("set datestyle to 'ISO'; select getdatabaseencoding()");
! 
!       String dbEncoding = null;
!       //retrieve DB properties
!       if(initrset.next()) {
! 
!         //handle DatabaseEncoding
!         dbEncoding = initrset.getString(1);
!         //convert from the PostgreSQL name to the Java name
!         if (dbEncoding.equals("SQL_ASCII")) {
!           dbEncoding = "ASCII";
!         } else if (dbEncoding.equals("UNICODE")) {
!           dbEncoding = "UTF8";
!         } else if (dbEncoding.equals("LATIN1")) {
!           dbEncoding = "ISO8859_1";
!         } else if (dbEncoding.equals("LATIN2")) {
!           dbEncoding = "ISO8859_2";
!         } else if (dbEncoding.equals("LATIN3")) {
!           dbEncoding = "ISO8859_3";
!         } else if (dbEncoding.equals("LATIN4")) {
!           dbEncoding = "ISO8859_4";
!         } else if (dbEncoding.equals("LATIN5")) {
!           dbEncoding = "ISO8859_5";
!         } else if (dbEncoding.equals("LATIN6")) {
!           dbEncoding = "ISO8859_6";
!         } else if (dbEncoding.equals("LATIN7")) {
!           dbEncoding = "ISO8859_7";
!         } else if (dbEncoding.equals("LATIN8")) {
!           dbEncoding = "ISO8859_8";
!         } else if (dbEncoding.equals("LATIN9")) {
!           dbEncoding = "ISO8859_9";
!         } else if (dbEncoding.equals("EUC_JP")) {
!           dbEncoding = "EUC_JP";
!         } else if (dbEncoding.equals("EUC_CN")) {
!           dbEncoding = "EUC_CN";
!         } else if (dbEncoding.equals("EUC_KR")) {
!           dbEncoding = "EUC_KR";
!         } else if (dbEncoding.equals("EUC_TW")) {
!           dbEncoding = "EUC_TW";
!         } else if (dbEncoding.equals("KOI8")) {
!           dbEncoding = "KOI8_R";
!         } else if (dbEncoding.equals("WIN")) {
!           dbEncoding = "Cp1252";
!         } else {
!           dbEncoding = null;
!         }
!       }
! 
! 
!       //Set the encoding for this connection
!       //Since the encoding could be specified or obtained from the DB we use the
!       //following order:
!       //  1.  passed as a property
!       //  2.  value from DB if supported by current JVM
!       //  3.  default for JVM (leave encoding null)
!       String passedEncoding = info.getProperty("charSet");  // could be null
! 
!       if (passedEncoding != null) {
!         encoding = passedEncoding;
!       } else {
!         if (dbEncoding != null) {
!           //test DB encoding
!           try {
!             "TEST".getBytes(dbEncoding);
!             //no error the encoding is supported by the current JVM
!             encoding = dbEncoding;
!           } catch (UnsupportedEncodingException uee) {
!             //dbEncoding is not supported by the current JVM
!             encoding = null;
!           }
!         } else {
!           encoding = null;
!         }
!       }
        
        // Initialise object handling
        initObjectTypes();

--------------F58CD7E14C5DB056B6438612--