Back to index

lightning-sunbird  0.9+nobinonly
CharDistribution.cpp
Go to the documentation of this file.
00001 /* -*- Mode: C++; tab-width: 2; 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 Communicator client 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) 1998
00020  * the Initial Developer. All Rights Reserved.
00021  *
00022  * Contributor(s):
00023  *
00024  * Alternatively, the contents of this file may be used under the terms of
00025  * either the GNU General Public License Version 2 or later (the "GPL"), or
00026  * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
00027  * in which case the provisions of the GPL or the LGPL are applicable instead
00028  * of those above. If you wish to allow use of your version of this file only
00029  * under the terms of either the GPL or the LGPL, and not to allow others to
00030  * use your version of this file under the terms of the MPL, indicate your
00031  * decision by deleting the provisions above and replace them with the notice
00032  * and other provisions required by the GPL or the LGPL. If you do not delete
00033  * the provisions above, a recipient may use your version of this file under
00034  * the terms of any one of the MPL, the GPL or the LGPL.
00035  *
00036  * ***** END LICENSE BLOCK ***** */
00037 
00038 #include "CharDistribution.h"
00039 
00040 #include "JISFreq.tab"
00041 #include "Big5Freq.tab"
00042 #include "EUCKRFreq.tab"
00043 #include "EUCTWFreq.tab"
00044 #include "GB2312Freq.tab"
00045 
00046 #define SURE_YES 0.99f
00047 #define SURE_NO  0.01f
00048 
00049 #define MINIMUM_DATA_THRESHOLD  4
00050 
00051 //return confidence base on received data
00052 float CharDistributionAnalysis::GetConfidence()
00053 { 
00054   //if we didn't receive any character in our consideration range, or the
00055   // number of frequent characters is below the minimum threshold, return
00056   // negative answer
00057   if (mTotalChars <= 0 || mFreqChars <= MINIMUM_DATA_THRESHOLD)
00058     return SURE_NO;
00059 
00060   if (mTotalChars != mFreqChars) {
00061     float r = mFreqChars / ((mTotalChars - mFreqChars) * mTypicalDistributionRatio);
00062 
00063     if (r < SURE_YES)
00064       return r;
00065   }
00066   //normalize confidence, (we don't want to be 100% sure)
00067   return SURE_YES;
00068 }
00069 
00070 EUCTWDistributionAnalysis::EUCTWDistributionAnalysis()
00071 {
00072   mCharToFreqOrder = EUCTWCharToFreqOrder;
00073   mTableSize = EUCTW_TABLE_SIZE;
00074   mTypicalDistributionRatio = EUCTW_TYPICAL_DISTRIBUTION_RATIO;
00075 }
00076 
00077 EUCKRDistributionAnalysis::EUCKRDistributionAnalysis()
00078 {
00079   mCharToFreqOrder = EUCKRCharToFreqOrder;
00080   mTableSize = EUCKR_TABLE_SIZE;
00081   mTypicalDistributionRatio = EUCKR_TYPICAL_DISTRIBUTION_RATIO;
00082 }
00083 
00084 GB2312DistributionAnalysis::GB2312DistributionAnalysis()
00085 {
00086   mCharToFreqOrder = GB2312CharToFreqOrder;
00087   mTableSize = GB2312_TABLE_SIZE;
00088   mTypicalDistributionRatio = GB2312_TYPICAL_DISTRIBUTION_RATIO;
00089 }
00090 
00091 Big5DistributionAnalysis::Big5DistributionAnalysis()
00092 {
00093   mCharToFreqOrder = Big5CharToFreqOrder;
00094   mTableSize = BIG5_TABLE_SIZE;
00095   mTypicalDistributionRatio = BIG5_TYPICAL_DISTRIBUTION_RATIO;
00096 }
00097 
00098 SJISDistributionAnalysis::SJISDistributionAnalysis()
00099 {
00100   mCharToFreqOrder = JISCharToFreqOrder;
00101   mTableSize = JIS_TABLE_SIZE;
00102   mTypicalDistributionRatio = JIS_TYPICAL_DISTRIBUTION_RATIO;
00103 }
00104 
00105 EUCJPDistributionAnalysis::EUCJPDistributionAnalysis()
00106 {
00107   mCharToFreqOrder = JISCharToFreqOrder;
00108   mTableSize = JIS_TABLE_SIZE;
00109   mTypicalDistributionRatio = JIS_TYPICAL_DISTRIBUTION_RATIO;
00110 }
00111