File indexing completed on 2024-12-22 04:33:40
0001 /* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */ 0002 /* ***** BEGIN LICENSE BLOCK ***** 0003 * Version: MPL 1.1/GPL 2.0/LGPL 2.1 0004 * 0005 * The contents of this file are subject to the Mozilla Public License Version 0006 * 1.1 (the "License"); you may not use this file except in compliance with 0007 * the License. You may obtain a copy of the License at 0008 * http://www.mozilla.org/MPL/ 0009 * 0010 * Software distributed under the License is distributed on an "AS IS" basis, 0011 * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License 0012 * for the specific language governing rights and limitations under the 0013 * License. 0014 * 0015 * The Original Code is Mozilla Communicator client code. 0016 * 0017 * The Initial Developer of the Original Code is 0018 * Netscape Communications Corporation. 0019 * Portions created by the Initial Developer are Copyright (C) 1998 0020 * the Initial Developer. All Rights Reserved. 0021 * 0022 * Contributor(s): 0023 * 0024 * Alternatively, the contents of this file may be used under the terms of 0025 * either the GNU General Public License Version 2 or later (the "GPL"), or 0026 * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"), 0027 * in which case the provisions of the GPL or the LGPL are applicable instead 0028 * of those above. If you wish to allow use of your version of this file only 0029 * under the terms of either the GPL or the LGPL, and not to allow others to 0030 * use your version of this file under the terms of the MPL, indicate your 0031 * decision by deleting the provisions above and replace them with the notice 0032 * and other provisions required by the GPL or the LGPL. If you do not delete 0033 * the provisions above, a recipient may use your version of this file under 0034 * the terms of any one of the MPL, the GPL or the LGPL. 0035 * 0036 * ***** END LICENSE BLOCK ***** */ 0037 0038 #pragma GCC visibility push(hidden) 0039 0040 #include "CharDistribution.h" 0041 0042 #include "JISFreq.tab" 0043 #include "Big5Freq.tab" 0044 #include "EUCKRFreq.tab" 0045 #include "EUCTWFreq.tab" 0046 #include "GB2312Freq.tab" 0047 0048 #define SURE_YES 0.99f 0049 #define SURE_NO 0.01f 0050 0051 //return confidence base on received data 0052 float CharDistributionAnalysis::GetConfidence() 0053 { 0054 //if we didn't receive any character in our consideration range, return negative answer 0055 if (mTotalChars <= 0) 0056 return SURE_NO; 0057 0058 if (mTotalChars != mFreqChars) { 0059 float r = mFreqChars / ((mTotalChars - mFreqChars) * mTypicalDistributionRatio); 0060 0061 if (r < SURE_YES) 0062 return r; 0063 } 0064 //normalize confidence, (we don't want to be 100% sure) 0065 return SURE_YES; 0066 } 0067 0068 EUCTWDistributionAnalysis::EUCTWDistributionAnalysis() 0069 { 0070 mCharToFreqOrder = EUCTWCharToFreqOrder; 0071 mTableSize = EUCTW_TABLE_SIZE; 0072 mTypicalDistributionRatio = EUCTW_TYPICAL_DISTRIBUTION_RATIO; 0073 } 0074 0075 EUCKRDistributionAnalysis::EUCKRDistributionAnalysis() 0076 { 0077 mCharToFreqOrder = EUCKRCharToFreqOrder; 0078 mTableSize = EUCKR_TABLE_SIZE; 0079 mTypicalDistributionRatio = EUCKR_TYPICAL_DISTRIBUTION_RATIO; 0080 } 0081 0082 GB2312DistributionAnalysis::GB2312DistributionAnalysis() 0083 { 0084 mCharToFreqOrder = GB2312CharToFreqOrder; 0085 mTableSize = GB2312_TABLE_SIZE; 0086 mTypicalDistributionRatio = GB2312_TYPICAL_DISTRIBUTION_RATIO; 0087 } 0088 0089 Big5DistributionAnalysis::Big5DistributionAnalysis() 0090 { 0091 mCharToFreqOrder = Big5CharToFreqOrder; 0092 mTableSize = BIG5_TABLE_SIZE; 0093 mTypicalDistributionRatio = BIG5_TYPICAL_DISTRIBUTION_RATIO; 0094 } 0095 0096 SJISDistributionAnalysis::SJISDistributionAnalysis() 0097 { 0098 mCharToFreqOrder = JISCharToFreqOrder; 0099 mTableSize = JIS_TABLE_SIZE; 0100 mTypicalDistributionRatio = JIS_TYPICAL_DISTRIBUTION_RATIO; 0101 } 0102 0103 EUCJPDistributionAnalysis::EUCJPDistributionAnalysis() 0104 { 0105 mCharToFreqOrder = JISCharToFreqOrder; 0106 mTableSize = JIS_TABLE_SIZE; 0107 mTypicalDistributionRatio = JIS_TYPICAL_DISTRIBUTION_RATIO; 0108 } 0109 0110 #pragma GCC visibility pop