intl/chardet/tools/GenCyrillicClass.cpp

   1 /* -*- Mode: C++; tab-width: 2; 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  *   Pierre Phaneuf <pp@ludusdesign.com>
  24  *
  25  * Alternatively, the contents of this file may be used under the terms of
  26  * either the GNU General Public License Version 2 or later (the "GPL"), or
  27  * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
  28  * in which case the provisions of the GPL or the LGPL are applicable instead
  29  * of those above. If you wish to allow use of your version of this file only
  30  * under the terms of either the GPL or the LGPL, and not to allow others to
  31  * use your version of this file under the terms of the MPL, indicate your
  32  * decision by deleting the provisions above and replace them with the notice
  33  * and other provisions required by the GPL or the LGPL. If you do not delete
  34  * the provisions above, a recipient may use your version of this file under
  35  * the terms of any one of the MPL, the GPL or the LGPL.
  36  *
  37  * ***** END LICENSE BLOCK ***** */
  38 #include "nsICharsetConverterManager.h"
  39 #include <iostream.h>
  40 #include "nsISupports.h"
  41 #include "nsIComponentManager.h"
  42 #include "nsIServiceManager.h"
  43 #include "nsIUnicodeDecoder.h"
  44 #include "nsIUnicodeEncoder.h"
  45 #include "nsCRT.h"
  46 #include <stdio.h>
  47 #include <stdlib.h>
  48 #if defined(XP_WIN) || defined(XP_OS2)
  49 #include <io.h>
  50 #endif
  51 #ifdef XP_UNIX
  52 #include <unistd.h>
  53 #endif
  54
  55 //---------------------------------------------------------------------------
  56 void header()
  57 {
  58 char *header=
  59 "#ifndef nsCyrillicClass_h__\n"
  60 "#define nsCyrillicClass_h__\n"
  61 "/* PLEASE DO NOT EDIT THIS FILE DIRECTLY. THIS FILE IS GENERATED BY \n"
  62 "   GenCyrllicClass found in mozilla/intl/chardet/tools\n"
  63 " */\n";
  64    printf(header);
  65 }
  66 //---------------------------------------------------------------------------
  67 void footer()
  68 {
  69    printf("#endif\n");
  70 }
  71 //---------------------------------------------------------------------------
  72 void npl()
  73 {
  74 char *npl=
  75 "/* -*- Mode: C; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 2 -*- */\n"
  76 "/* ***** BEGIN LICENSE BLOCK *****\n"
  77 " * Version: MPL 1.1/GPL 2.0/LGPL 2.1\n"
  78 " *\n"
  79 " * The contents of this file are subject to the Mozilla Public License Version\n"
  80 " * 1.1 (the \"License\"); you may not use this file except in compliance with\n"
  81 " * the License. You may obtain a copy of the License at\n"
  82 " * http://www.mozilla.org/MPL/\n"
  83 " *\n"
  84 " * Software distributed under the License is distributed on an \"AS IS\" basis,\n"
  85 " * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License\n"
  86 " * for the specific language governing rights and limitations under the\n"
  87 " * License.\n"
  88 " *\n"
  89 " * The Original Code is mozilla.org code.\n"
  90 " *\n"
  91 " * The Initial Developer of the Original Code is\n"
  92 " * Netscape Communications Corporation.\n"
  93 " * Portions created by the Initial Developer are Copyright (C) 2001\n"
  94 " * the Initial Developer. All Rights Reserved.\n"
  95 " *\n"
  96 " * Contributor(s):\n"
  97 " *\n"
  98 " * Alternatively, the contents of this file may be used under the terms of\n"
  99 " * either the GNU General Public License Version 2 or later (the \"GPL\"), or\n"
 100 " * the GNU Lesser General Public License Version 2.1 or later (the \"LGPL\"),\n"
 101 " * in which case the provisions of the GPL or the LGPL are applicable instead\n"
 102 " * of those above. If you wish to allow use of your version of this file only\n"
 103 " * under the terms of either the GPL or the LGPL, and not to allow others to\n"
 104 " * use your version of this file under the terms of the MPL, indicate your\n"
 105 " * decision by deleting the provisions above and replace them with the notice\n"
 106 " * and other provisions required by the GPL or the LGPL. If you do not delete\n"
 107 " * the provisions above, a recipient may use your version of this file under\n"
 108 " * the terms of any one of the MPL, the GPL or the LGPL.\n"
 109 " *\n"
 110 " * ***** END LICENSE BLOCK ***** */\n";
 111    printf(npl);
 112 }
 113 //---------------------------------------------------------------------------
 114 static nsIUnicodeEncoder* gKOI8REncoder = nsnull;
 115 static nsICharsetConverterManager* gCCM = nsnull;
 116
 117 //---------------------------------------------------------------------------
 118 PRUint8 CyrillicClass(nsIUnicodeDecoder* decoder, PRUint8 byte)
 119 {
 120    PRUnichar ubuf[2];
 121    PRUint8 bbuf[2];
 122
 123    PRInt32 blen = 1;
 124    PRInt32 ulen = 1;
 125    nsresult res = decoder->Convert((char*)&byte, &blen, ubuf, &ulen);
 126    if(NS_SUCCEEDED(res) && (1 == ulen ))
 127    {
 128      ubuf[0] = nsCRT::ToUpper(ubuf[0]);
 129      blen=1;
 130      res = gKOI8REncoder->Convert(ubuf,&ulen,(char*)bbuf,&blen);
 131      if(NS_SUCCEEDED(res) && (1 == blen))
 132      {
 133         if(0xe0 <= bbuf[0])
 134         {
 135               return bbuf[0] - (PRUint8)0xdf;
 136         }
 137      }
 138    }
 139    return 0;
 140 }
 141 //---------------------------------------------------------------------------
 142 void genCyrillicClass(const char* name, const char* charset)
 143 {
 144    nsIUnicodeDecoder *decoder = nsnull;
 145    nsresult res = NS_OK;
 146    nsAutoString str(charset);
 147    res = gCCM->GetUnicodeDecoder(&str, &decoder);
 148    if(NS_FAILED(res))
 149    {
 150       printf("cannot locate %s Decoder\n", charset);
 151       return;
 152    }
 153    printf("static const PRUint8 %sMap [128] = {\n",name);
 154    PRUint8 i,j;
 155    for(i=0x80;i!=0x00;i+=0x10)
 156    {
 157      for(j=0;j<=0x0f;j++)
 158      {
 159         PRUint8 cls = CyrillicClass(decoder, i+j);
 160         printf(" %2d, ",cls);
 161      }
 162      printf("\n");
 163    }
 164    printf("};\n");
 165    NS_IF_RELEASE(decoder);
 166 }
 167 //---------------------------------------------------------------------------
 168
 169
 170 int main(int argc, char** argv) {
 171   nsresult res = nsnull;
 172
 173   nsCOMPtr<nsICharsetConverterManager> gCCM = do_GetService(kCharsetConverterManagerCID, &res);
 174
 175   if(NS_FAILED(res) && (nsnull != gCCM))
 176    {
 177       printf("cannot locate CharsetConverterManager\n");
 178       return(-1);
 179    }
 180    nsAutoString koi8r("KOI8-R");
 181    res = gCCM->GetUnicodeEncoder(&koi8r,&gKOI8REncoder);
 182    if(NS_FAILED(res) && (nsnull != gKOI8REncoder))
 183    {
 184       printf("cannot locate KOI8-R Encoder\n");
 185       return(-1);
 186    }
 187
 188
 189    npl();
 190    header();
 191
 192      genCyrillicClass("KOI8", "KOI8-R");
 193      genCyrillicClass("CP1251", "windows-1251");
 194      genCyrillicClass("IBM866", "IBM866");
 195      genCyrillicClass("ISO88595", "ISO-8859-5");
 196      genCyrillicClass("MacCyrillic", "x-mac-cyrillic");
 197    footer();
 198    NS_IF_RELEASE(gKOI8REncoder);
 199    return(0);
 200 };