Back to index

lightning-sunbird  0.9+nobinonly
nsSBCharSetProber.cpp
Go to the documentation of this file.
00001 /* -*- Mode: C; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
00002 /* ***** BEGIN LICENSE BLOCK *****
00003  * Version: MPL 1.1/GPL 2.0/LGPL 2.1
00004  *
00005  * The contents of this file are subject to the Mozilla Public License Version
00006  * 1.1 (the "License"); you may not use this file except in compliance with
00007  * the License. You may obtain a copy of the License at
00008  * http://www.mozilla.org/MPL/
00009  *
00010  * Software distributed under the License is distributed on an "AS IS" basis,
00011  * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
00012  * for the specific language governing rights and limitations under the
00013  * License.
00014  *
00015  * The Original Code is Mozilla Universal charset detector code.
00016  *
00017  * The Initial Developer of the Original Code is
00018  * Netscape Communications Corporation.
00019  * Portions created by the Initial Developer are Copyright (C) 2001
00020  * the Initial Developer. All Rights Reserved.
00021  *
00022  * Contributor(s):
00023  *          Shy Shalom <shooshX@gmail.com>
00024  *
00025  * Alternatively, the contents of this file may be used under the terms of
00026  * either the GNU General Public License Version 2 or later (the "GPL"), or
00027  * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
00028  * in which case the provisions of the GPL or the LGPL are applicable instead
00029  * of those above. If you wish to allow use of your version of this file only
00030  * under the terms of either the GPL or the LGPL, and not to allow others to
00031  * use your version of this file under the terms of the MPL, indicate your
00032  * decision by deleting the provisions above and replace them with the notice
00033  * and other provisions required by the GPL or the LGPL. If you do not delete
00034  * the provisions above, a recipient may use your version of this file under
00035  * the terms of any one of the MPL, the GPL or the LGPL.
00036  *
00037  * ***** END LICENSE BLOCK ***** */
00038 #include <stdio.h>
00039 #include "nsSBCharSetProber.h"
00040 
00041 nsProbingState nsSingleByteCharSetProber::HandleData(const char* aBuf, PRUint32 aLen)
00042 {
00043   unsigned char order;
00044 
00045   for (PRUint32 i = 0; i < aLen; i++)
00046   {
00047     order = mModel->charToOrderMap[(unsigned char)aBuf[i]];
00048 
00049     if (order < SYMBOL_CAT_ORDER)
00050       mTotalChar++;
00051     if (order < SAMPLE_SIZE)
00052     {
00053         mFreqChar++;
00054 
00055       if (mLastOrder < SAMPLE_SIZE)
00056       {
00057         mTotalSeqs++;
00058         if (!mReversed)
00059           ++(mSeqCounters[mModel->precedenceMatrix[mLastOrder*SAMPLE_SIZE+order]]);
00060         else // reverse the order of the letters in the lookup
00061           ++(mSeqCounters[mModel->precedenceMatrix[order*SAMPLE_SIZE+mLastOrder]]);
00062       }
00063     }
00064     mLastOrder = order;
00065   }
00066 
00067   if (mState == eDetecting)
00068     if (mTotalSeqs > SB_ENOUGH_REL_THRESHOLD)
00069     {
00070       float cf = GetConfidence();
00071       if (cf > POSITIVE_SHORTCUT_THRESHOLD)
00072         mState = eFoundIt;
00073       else if (cf < NEGATIVE_SHORTCUT_THRESHOLD)
00074         mState = eNotMe;
00075     }
00076 
00077   return mState;
00078 }
00079 
00080 void  nsSingleByteCharSetProber::Reset(void)
00081 {
00082   mState = eDetecting;
00083   mLastOrder = 255;
00084   for (PRUint32 i = 0; i < NUMBER_OF_SEQ_CAT; i++)
00085     mSeqCounters[i] = 0;
00086   mTotalSeqs = 0;
00087   mTotalChar = 0;
00088   mFreqChar = 0;
00089 }
00090 
00091 //#define NEGATIVE_APPROACH 1
00092 
00093 float nsSingleByteCharSetProber::GetConfidence(void)
00094 {
00095 #ifdef NEGATIVE_APPROACH
00096   if (mTotalSeqs > 0)
00097     if (mTotalSeqs > mSeqCounters[NEGATIVE_CAT]*10 )
00098       return ((float)(mTotalSeqs - mSeqCounters[NEGATIVE_CAT]*10))/mTotalSeqs * mFreqChar / mTotalChar;
00099   return (float)0.01;
00100 #else  //POSITIVE_APPROACH
00101   float r;
00102 
00103   if (mTotalSeqs > 0) {
00104     r = ((float)1.0) * mSeqCounters[POSITIVE_CAT] / mTotalSeqs / mModel->mTypicalPositiveRatio;
00105     r = r*mFreqChar/mTotalChar;
00106     if (r >= (float)1.00)
00107       r = (float)0.99;
00108     return r;
00109   }
00110   return (float)0.01;
00111 #endif
00112 }
00113 
00114 const char* nsSingleByteCharSetProber::GetCharSetName() 
00115 {
00116   if (!mNameProber)
00117     return mModel->charsetName;
00118   return mNameProber->GetCharSetName();
00119 }
00120 
00121 #ifdef DEBUG_chardet
00122 void nsSingleByteCharSetProber::DumpStatus()
00123 {
00124   printf("  SBCS: %1.3f [%s]\r\n", GetConfidence(), GetCharSetName());
00125 }
00126 #endif