extensions/universalchardet/src/base/nsSBCSGroupProber.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 Universal charset detector 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) 2001
  20  * the Initial Developer. All Rights Reserved.
  21  *
  22  * Contributor(s):
  23  *          Shy Shalom <shooshX@gmail.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
  39 #include <stdio.h>
  40 #include "prmem.h"
  41
  42 #include "nsSBCharSetProber.h"
  43 #include "nsSBCSGroupProber.h"
  44
  45 #include "nsHebrewProber.h"
  46
  47 nsSBCSGroupProber::nsSBCSGroupProber()
  48 {
  49   mProbers[0] = new nsSingleByteCharSetProber(&Win1251Model);
  50   mProbers[1] = new nsSingleByteCharSetProber(&Koi8rModel);
  51   mProbers[2] = new nsSingleByteCharSetProber(&Latin5Model);
  52   mProbers[3] = new nsSingleByteCharSetProber(&MacCyrillicModel);
  53   mProbers[4] = new nsSingleByteCharSetProber(&Ibm866Model);
  54   mProbers[5] = new nsSingleByteCharSetProber(&Ibm855Model);
  55   mProbers[6] = new nsSingleByteCharSetProber(&Latin7Model);
  56   mProbers[7] = new nsSingleByteCharSetProber(&Win1253Model);
  57   mProbers[8] = new nsSingleByteCharSetProber(&Latin5BulgarianModel);
  58   mProbers[9] = new nsSingleByteCharSetProber(&Win1251BulgarianModel);
  59
  60   nsHebrewProber *hebprober = new nsHebrewProber();
  61   // Notice: Any change in these indexes - 10,11,12 must be reflected
  62   // in the code below as well.
  63   mProbers[10] = hebprober;
  64   mProbers[11] = new nsSingleByteCharSetProber(&Win1255Model, PR_FALSE, hebprober); // Logical Hebrew
  65   mProbers[12] = new nsSingleByteCharSetProber(&Win1255Model, PR_TRUE, hebprober); // Visual Hebrew
  66   // Tell the Hebrew prober about the logical and visual probers
  67   if (mProbers[10] && mProbers[11] && mProbers[12]) // all are not null
  68   {
  69     hebprober->SetModelProbers(mProbers[11], mProbers[12]);
  70   }
  71   else // One or more is null. avoid any Hebrew probing, null them all
  72   {
  73     for (PRUint32 i = 10; i <= 12; ++i)
  74     {
  75       delete mProbers[i];
  76       mProbers[i] = 0;
  77     }
  78   }
  79
  80   // disable latin2 before latin1 is available, otherwise all latin1
  81   // will be detected as latin2 because of their similarity.
  82   //mProbers[10] = new nsSingleByteCharSetProber(&Latin2HungarianModel);
  83   //mProbers[11] = new nsSingleByteCharSetProber(&Win1250HungarianModel);
  84
  85   Reset();
  86 }
  87
  88 nsSBCSGroupProber::~nsSBCSGroupProber()
  89 {
  90   for (PRUint32 i = 0; i < NUM_OF_SBCS_PROBERS; i++)
  91   {
  92     delete mProbers[i];
  93   }
  94 }
  95
  96
  97 const char* nsSBCSGroupProber::GetCharSetName()
  98 {
  99   //if we have no answer yet
 100   if (mBestGuess == -1)
 101   {
 102     GetConfidence();
 103     //no charset seems positive
 104     if (mBestGuess == -1)
 105       //we will use default.
 106       mBestGuess = 0;
 107   }
 108   return mProbers[mBestGuess]->GetCharSetName();
 109 }
 110
 111 void  nsSBCSGroupProber::Reset(void)
 112 {
 113   mActiveNum = 0;
 114   for (PRUint32 i = 0; i < NUM_OF_SBCS_PROBERS; i++)
 115   {
 116     if (mProbers[i]) // not null
 117     {
 118       mProbers[i]->Reset();
 119       mIsActive[i] = PR_TRUE;
 120       ++mActiveNum;
 121     }
 122     else
 123       mIsActive[i] = PR_FALSE;
 124   }
 125   mBestGuess = -1;
 126   mState = eDetecting;
 127 }
 128
 129
 130 nsProbingState nsSBCSGroupProber::HandleData(const char* aBuf, PRUint32 aLen)
 131 {
 132   nsProbingState st;
 133   PRUint32 i;
 134   char *newBuf1 = 0;
 135   PRUint32 newLen1 = 0;
 136
 137   //apply filter to original buffer, and we got new buffer back
 138   //depend on what script it is, we will feed them the new buffer
 139   //we got after applying proper filter
 140   //this is done without any consideration to KeepEnglishLetters
 141   //of each prober since as of now, there are no probers here which
 142   //recognize languages with English characters.
 143   if (!FilterWithoutEnglishLetters(aBuf, aLen, &newBuf1, newLen1))
 144     goto done;
 145
 146   if (newLen1 == 0)
 147     goto done; // Nothing to see here, move on.
 148
 149   for (i = 0; i < NUM_OF_SBCS_PROBERS; i++)
 150   {
 151      if (!mIsActive[i])
 152        continue;
 153      st = mProbers[i]->HandleData(newBuf1, newLen1);
 154      if (st == eFoundIt)
 155      {
 156        mBestGuess = i;
 157        mState = eFoundIt;
 158        break;
 159      }
 160      else if (st == eNotMe)
 161      {
 162        mIsActive[i] = PR_FALSE;
 163        mActiveNum--;
 164        if (mActiveNum <= 0)
 165        {
 166          mState = eNotMe;
 167          break;
 168        }
 169      }
 170   }
 171
 172 done:
 173   PR_FREEIF(newBuf1);
 174
 175   return mState;
 176 }
 177
 178 float nsSBCSGroupProber::GetConfidence(void)
 179 {
 180   PRUint32 i;
 181   float bestConf = 0.0, cf;
 182
 183   switch (mState)
 184   {
 185   case eFoundIt:
 186     return (float)0.99; //sure yes
 187   case eNotMe:
 188     return (float)0.01;  //sure no
 189   default:
 190     for (i = 0; i < NUM_OF_SBCS_PROBERS; i++)
 191     {
 192       if (!mIsActive[i])
 193         continue;
 194       cf = mProbers[i]->GetConfidence();
 195       if (bestConf < cf)
 196       {
 197         bestConf = cf;
 198         mBestGuess = i;
 199       }
 200     }
 201   }
 202   return bestConf;
 203 }
 204
 205 #ifdef DEBUG_chardet
 206 void nsSBCSGroupProber::DumpStatus()
 207 {
 208   PRUint32 i;
 209   float cf;
 210
 211   cf = GetConfidence();
 212   printf(" SBCS Group Prober --------begin status \r\n");
 213   for (i = 0; i < NUM_OF_SBCS_PROBERS; i++)
 214   {
 215     if (!mIsActive[i])
 216       printf("  inactive: [%s] (i.e. confidence is too low).\r\n", mProbers[i]->GetCharSetName());
 217     else
 218       mProbers[i]->DumpStatus();
 219   }
 220   printf(" SBCS Group found best match [%s] confidence %f.\r\n",
 221          mProbers[mBestGuess]->GetCharSetName(), cf);
 222 }
 223 #endif