extensions/universalchardet/src/base/CharDistribution.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 Communicator client 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 the GNU General Public License Version 2 or later (the "GPL"), or
  26  * 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 #include "CharDistribution.h"
  39
  40 #include "JISFreq.tab"
  41 #include "Big5Freq.tab"
  42 #include "EUCKRFreq.tab"
  43 #include "EUCTWFreq.tab"
  44 #include "GB2312Freq.tab"
  45
  46 #define SURE_YES 0.99f
  47 #define SURE_NO  0.01f
  48
  49 #define MINIMUM_DATA_THRESHOLD  4
  50
  51 //return confidence base on received data
  52 float CharDistributionAnalysis::GetConfidence(PRBool aIsPreferredLanguage)
  53 {
  54   //if we didn't receive any character in our consideration range, or the
  55   // number of frequent characters is below the minimum threshold, return
  56   // negative answer
  57   if (mTotalChars <= 0 ||
  58       !aIsPreferredLanguage && mFreqChars <= MINIMUM_DATA_THRESHOLD)
  59     return SURE_NO;
  60
  61   if (mTotalChars != mFreqChars) {
  62     float r = mFreqChars / ((mTotalChars - mFreqChars) * mTypicalDistributionRatio);
  63
  64     if (r < SURE_YES)
  65       return r;
  66   }
  67   //normalize confidence, (we don't want to be 100% sure)
  68   return SURE_YES;
  69 }
  70
  71 EUCTWDistributionAnalysis::EUCTWDistributionAnalysis()
  72 {
  73   mCharToFreqOrder = EUCTWCharToFreqOrder;
  74   mTableSize = EUCTW_TABLE_SIZE;
  75   mTypicalDistributionRatio = EUCTW_TYPICAL_DISTRIBUTION_RATIO;
  76 }
  77
  78 EUCKRDistributionAnalysis::EUCKRDistributionAnalysis()
  79 {
  80   mCharToFreqOrder = EUCKRCharToFreqOrder;
  81   mTableSize = EUCKR_TABLE_SIZE;
  82   mTypicalDistributionRatio = EUCKR_TYPICAL_DISTRIBUTION_RATIO;
  83 }
  84
  85 GB2312DistributionAnalysis::GB2312DistributionAnalysis()
  86 {
  87   mCharToFreqOrder = GB2312CharToFreqOrder;
  88   mTableSize = GB2312_TABLE_SIZE;
  89   mTypicalDistributionRatio = GB2312_TYPICAL_DISTRIBUTION_RATIO;
  90 }
  91
  92 Big5DistributionAnalysis::Big5DistributionAnalysis()
  93 {
  94   mCharToFreqOrder = Big5CharToFreqOrder;
  95   mTableSize = BIG5_TABLE_SIZE;
  96   mTypicalDistributionRatio = BIG5_TYPICAL_DISTRIBUTION_RATIO;
  97 }
  98
  99 SJISDistributionAnalysis::SJISDistributionAnalysis()
 100 {
 101   mCharToFreqOrder = JISCharToFreqOrder;
 102   mTableSize = JIS_TABLE_SIZE;
 103   mTypicalDistributionRatio = JIS_TYPICAL_DISTRIBUTION_RATIO;
 104 }
 105
 106 EUCJPDistributionAnalysis::EUCJPDistributionAnalysis()
 107 {
 108   mCharToFreqOrder = JISCharToFreqOrder;
 109   mTableSize = JIS_TABLE_SIZE;
 110   mTypicalDistributionRatio = JIS_TYPICAL_DISTRIBUTION_RATIO;
 111 }
 112