extensions/universalchardet/src/base/nsSBCharSetProber.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 #include <stdio.h>
  39 #include "nsSBCharSetProber.h"
  40
  41 nsProbingState nsSingleByteCharSetProber::HandleData(const char* aBuf, PRUint32 aLen)
  42 {
  43   unsigned char order;
  44
  45   for (PRUint32 i = 0; i < aLen; i++)
  46   {
  47     order = mModel->charToOrderMap[(unsigned char)aBuf[i]];
  48
  49     if (order < SYMBOL_CAT_ORDER)
  50       mTotalChar++;
  51     if (order < SAMPLE_SIZE)
  52     {
  53         mFreqChar++;
  54
  55       if (mLastOrder < SAMPLE_SIZE)
  56       {
  57         mTotalSeqs++;
  58         if (!mReversed)
  59           ++(mSeqCounters[mModel->precedenceMatrix[mLastOrder*SAMPLE_SIZE+order]]);
  60         else // reverse the order of the letters in the lookup
  61           ++(mSeqCounters[mModel->precedenceMatrix[order*SAMPLE_SIZE+mLastOrder]]);
  62       }
  63     }
  64     mLastOrder = order;
  65   }
  66
  67   if (mState == eDetecting)
  68     if (mTotalSeqs > SB_ENOUGH_REL_THRESHOLD)
  69     {
  70       float cf = GetConfidence();
  71       if (cf > POSITIVE_SHORTCUT_THRESHOLD)
  72         mState = eFoundIt;
  73       else if (cf < NEGATIVE_SHORTCUT_THRESHOLD)
  74         mState = eNotMe;
  75     }
  76
  77   return mState;
  78 }
  79
  80 void  nsSingleByteCharSetProber::Reset(void)
  81 {
  82   mState = eDetecting;
  83   mLastOrder = 255;
  84   for (PRUint32 i = 0; i < NUMBER_OF_SEQ_CAT; i++)
  85     mSeqCounters[i] = 0;
  86   mTotalSeqs = 0;
  87   mTotalChar = 0;
  88   mFreqChar = 0;
  89 }
  90
  91 //#define NEGATIVE_APPROACH 1
  92
  93 float nsSingleByteCharSetProber::GetConfidence(void)
  94 {
  95 #ifdef NEGATIVE_APPROACH
  96   if (mTotalSeqs > 0)
  97     if (mTotalSeqs > mSeqCounters[NEGATIVE_CAT]*10 )
  98       return ((float)(mTotalSeqs - mSeqCounters[NEGATIVE_CAT]*10))/mTotalSeqs * mFreqChar / mTotalChar;
  99   return (float)0.01;
 100 #else  //POSITIVE_APPROACH
 101   float r;
 102
 103   if (mTotalSeqs > 0) {
 104     r = ((float)1.0) * mSeqCounters[POSITIVE_CAT] / mTotalSeqs / mModel->mTypicalPositiveRatio;
 105     r = r*mFreqChar/mTotalChar;
 106     if (r >= (float)1.00)
 107       r = (float)0.99;
 108     return r;
 109   }
 110   return (float)0.01;
 111 #endif
 112 }
 113
 114 const char* nsSingleByteCharSetProber::GetCharSetName()
 115 {
 116   if (!mNameProber)
 117     return mModel->charsetName;
 118   return mNameProber->GetCharSetName();
 119 }
 120
 121 #ifdef DEBUG_chardet
 122 void nsSingleByteCharSetProber::DumpStatus()
 123 {
 124   printf("  SBCS: %1.3f [%s]\r\n", GetConfidence(), GetCharSetName());
 125 }
 126 #endif