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
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/
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
15
* The Original Code is Mozilla Communicator client code.
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.
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.
36
* ***** END LICENSE BLOCK ***** */
38
#include "CharDistribution.h"
40
#include "JISFreq.tab"
41
#include "Big5Freq.tab"
42
#include "EUCKRFreq.tab"
43
#include "EUCTWFreq.tab"
44
#include "GB2312Freq.tab"
46
#define SURE_YES 0.99f
49
//return confidence base on received data
50
float CharDistributionAnalysis::GetConfidence(void)
52
//if we didn't receive any character in our consideration range, or the
53
// number of frequent characters is below the minimum threshold, return
55
if (mTotalChars <= 0 || mFreqChars <= mDataThreshold)
58
if (mTotalChars != mFreqChars) {
59
float r = mFreqChars / ((mTotalChars - mFreqChars) * mTypicalDistributionRatio);
64
//normalize confidence, (we don't want to be 100% sure)
68
EUCTWDistributionAnalysis::EUCTWDistributionAnalysis()
70
mCharToFreqOrder = EUCTWCharToFreqOrder;
71
mTableSize = EUCTW_TABLE_SIZE;
72
mTypicalDistributionRatio = EUCTW_TYPICAL_DISTRIBUTION_RATIO;
75
EUCKRDistributionAnalysis::EUCKRDistributionAnalysis()
77
mCharToFreqOrder = EUCKRCharToFreqOrder;
78
mTableSize = EUCKR_TABLE_SIZE;
79
mTypicalDistributionRatio = EUCKR_TYPICAL_DISTRIBUTION_RATIO;
82
GB2312DistributionAnalysis::GB2312DistributionAnalysis()
84
mCharToFreqOrder = GB2312CharToFreqOrder;
85
mTableSize = GB2312_TABLE_SIZE;
86
mTypicalDistributionRatio = GB2312_TYPICAL_DISTRIBUTION_RATIO;
89
Big5DistributionAnalysis::Big5DistributionAnalysis()
91
mCharToFreqOrder = Big5CharToFreqOrder;
92
mTableSize = BIG5_TABLE_SIZE;
93
mTypicalDistributionRatio = BIG5_TYPICAL_DISTRIBUTION_RATIO;
96
SJISDistributionAnalysis::SJISDistributionAnalysis()
98
mCharToFreqOrder = JISCharToFreqOrder;
99
mTableSize = JIS_TABLE_SIZE;
100
mTypicalDistributionRatio = JIS_TYPICAL_DISTRIBUTION_RATIO;
103
EUCJPDistributionAnalysis::EUCJPDistributionAnalysis()
105
mCharToFreqOrder = JISCharToFreqOrder;
106
mTableSize = JIS_TABLE_SIZE;
107
mTypicalDistributionRatio = JIS_TYPICAL_DISTRIBUTION_RATIO;