intl/uconv/ucvcn/nsUnicodeToHZ.cpp

   1 /* -*- Mode: C; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
   2 /* ***** BEGIN LICENSE BLOCK *****
   3  * Version: MPL 1.1/GPL 2.0/LGPL 2.1
   4  *
   5  * The contents of this file are subject to the Mozilla Public License Version
   6  * 1.1 (the "License"); you may not use this file except in compliance with
   7  * the License. You may obtain a copy of the License at
   8  * http://www.mozilla.org/MPL/
   9  *
  10  * Software distributed under the License is distributed on an "AS IS" basis,
  11  * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
  12  * for the specific language governing rights and limitations under the
  13  * License.
  14  *
  15  * The Original Code is mozilla.org code.
  16  *
  17  * The Initial Developer of the Original Code is
  18  * Netscape Communications Corporation.
  19  * Portions created by the Initial Developer are Copyright (C) 1998
  20  * the Initial Developer. All Rights Reserved.
  21  *
  22  * Contributor(s):
  23  *
  24  * Alternatively, the contents of this file may be used under the terms of
  25  * either of the GNU General Public License Version 2 or later (the "GPL"),
  26  * or the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
  27  * in which case the provisions of the GPL or the LGPL are applicable instead
  28  * of those above. If you wish to allow use of your version of this file only
  29  * under the terms of either the GPL or the LGPL, and not to allow others to
  30  * use your version of this file under the terms of the MPL, indicate your
  31  * decision by deleting the provisions above and replace them with the notice
  32  * and other provisions required by the GPL or the LGPL. If you do not delete
  33  * the provisions above, a recipient may use your version of this file under
  34  * the terms of any one of the MPL, the GPL or the LGPL.
  35  *
  36  * ***** END LICENSE BLOCK ***** */
  37  /**
  38  * A character set converter from Unicode to HZ.
  39  *
  40  *
  41  * @created         08/Sept/1999
  42  * @author  Yueheng Xu, Yueheng.Xu@intel.com
  43  * Revision History
  44  * 04/Oct/1999. Yueheng Xu: Fixed line continuation problem when line
  45  *                          ended by '~';
  46  *              Used table UnicodeToGBK[] to speed up the mapping.
  47  */
  48 #include "nsUnicodeToHZ.h"
  49 #include "nsUCvCnDll.h"
  50 #include "gbku.h"
  51 //----------------------------------------------------------------------
  52 // Class nsUnicodeToGBK [implementation]
  53 #define HZ_STATE_GB             1
  54 #define HZ_STATE_ASCII  2
  55 #define HZ_STATE_TILD   3
  56 #define HZLEAD1 '~'
  57 #define HZLEAD2 '{'
  58 #define HZLEAD3 '}'
  59 #define UNICODE_TILD    0x007E
  60 nsUnicodeToHZ::nsUnicodeToHZ() : nsEncoderSupport(6)
  61 {
  62   mUtil.InitToGBKTable();
  63   mHZState = HZ_STATE_ASCII;    // per HZ spec, default to HZ mode
  64 }
  65 NS_IMETHODIMP nsUnicodeToHZ::ConvertNoBuff(
  66   const PRUnichar * aSrc,
  67   PRInt32 * aSrcLength,
  68   char * aDest,
  69   PRInt32 * aDestLength)
  70 {
  71   PRInt32 i=0;
  72   PRInt32 iSrcLength = *aSrcLength;
  73   PRInt32 iDestLength = 0;
  74
  75   for (i=0;i< iSrcLength;i++)
  76   {
  77     if(! IS_ASCII(*aSrc))
  78     {
  79       // hi byte has something, it is not ASCII, process as a GB
  80       if ( mHZState != HZ_STATE_GB )
  81       {
  82         // we are adding a '~{' ESC sequence to star a HZ string
  83         mHZState = HZ_STATE_GB;
  84         aDest[0] = '~';
  85         aDest[1] = '{';
  86         aDest += 2;     // increment 2 bytes
  87         iDestLength +=2;
  88       }
  89       if(mUtil.UnicodeToGBKChar(*aSrc, PR_TRUE, &aDest[0], &aDest[1])) {
  90         aDest += 2;     // increment 2 bytes
  91         iDestLength +=2;
  92       } else {
  93         // some thing that we cannot convert
  94         // xxx fix me ftang
  95         // error handling here
  96       }
  97     } else {
  98       // this is an ASCII
  99
 100       // if we are in HZ mode, end it by adding a '~}' ESC sequence
 101       if ( mHZState == HZ_STATE_GB )
 102       {
 103         mHZState = HZ_STATE_ASCII;
 104         aDest[0] = '~';
 105         aDest[1] = '}';
 106         aDest += 2; // increment 2 bytes
 107         iDestLength +=2;
 108       }
 109
 110       // if this is a regular char '~' , convert it to two '~'
 111       if ( *aSrc == UNICODE_TILD )
 112       {
 113         aDest[0] = '~';
 114         aDest[1] = '~';
 115         aDest += 2; // increment 2 bytes
 116         iDestLength +=2;
 117       } else {
 118         // other regular ASCII chars convert by normal ways
 119
 120         // Is this works for both little endian and big endian machines ?
 121         *aDest = (char) ( (PRUnichar)(*aSrc) );
 122         aDest++; // increment 1 byte
 123         iDestLength +=1;
 124       }
 125     }
 126     aSrc++;      // increment 2 bytes
 127     if ( iDestLength >= (*aDestLength) )
 128     {
 129       break;
 130     }
 131   }
 132   *aDestLength = iDestLength;
 133   *aSrcLength = i;
 134   return NS_OK;
 135 }
 136
 137 NS_IMETHODIMP nsUnicodeToHZ::FinishNoBuff(char * aDest, PRInt32 * aDestLength)
 138 {
 139   if ( mHZState == HZ_STATE_GB )
 140   {
 141     // if we are in HZ mode, end it by adding a '~}' ESC sequence
 142     mHZState = HZ_STATE_ASCII;
 143     aDest[0] = '~';
 144     aDest[1] = '}';
 145     *aDestLength = 2;
 146   } else {
 147     *aDestLength = 0;
 148   }
 149   return NS_OK;
 150 }
 151
 152 NS_IMETHODIMP nsUnicodeToHZ::FillInfo(PRUint32 *aInfo)
 153 {
 154   mUtil.FillGB2312Info(aInfo);
 155   //GB2312 font lib also have single byte ASCII characters, set them here
 156   for ( PRUint16 u = 0x0000; u <= 0x007F; u++)
 157     SET_REPRESENTABLE(aInfo, u);
 158   return NS_OK;
 159 }