Blame src/CharDistribution.cpp

Packit 67f6e7
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
Packit 67f6e7
/* ***** BEGIN LICENSE BLOCK *****
Packit 67f6e7
 * Version: MPL 1.1/GPL 2.0/LGPL 2.1
Packit 67f6e7
 *
Packit 67f6e7
 * The contents of this file are subject to the Mozilla Public License Version
Packit 67f6e7
 * 1.1 (the "License"); you may not use this file except in compliance with
Packit 67f6e7
 * the License. You may obtain a copy of the License at
Packit 67f6e7
 * http://www.mozilla.org/MPL/
Packit 67f6e7
 *
Packit 67f6e7
 * Software distributed under the License is distributed on an "AS IS" basis,
Packit 67f6e7
 * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
Packit 67f6e7
 * for the specific language governing rights and limitations under the
Packit 67f6e7
 * License.
Packit 67f6e7
 *
Packit 67f6e7
 * The Original Code is Mozilla Communicator client code.
Packit 67f6e7
 *
Packit 67f6e7
 * The Initial Developer of the Original Code is
Packit 67f6e7
 * Netscape Communications Corporation.
Packit 67f6e7
 * Portions created by the Initial Developer are Copyright (C) 1998
Packit 67f6e7
 * the Initial Developer. All Rights Reserved.
Packit 67f6e7
 *
Packit 67f6e7
 * Contributor(s):
Packit 67f6e7
 *
Packit 67f6e7
 * Alternatively, the contents of this file may be used under the terms of
Packit 67f6e7
 * either the GNU General Public License Version 2 or later (the "GPL"), or
Packit 67f6e7
 * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
Packit 67f6e7
 * in which case the provisions of the GPL or the LGPL are applicable instead
Packit 67f6e7
 * of those above. If you wish to allow use of your version of this file only
Packit 67f6e7
 * under the terms of either the GPL or the LGPL, and not to allow others to
Packit 67f6e7
 * use your version of this file under the terms of the MPL, indicate your
Packit 67f6e7
 * decision by deleting the provisions above and replace them with the notice
Packit 67f6e7
 * and other provisions required by the GPL or the LGPL. If you do not delete
Packit 67f6e7
 * the provisions above, a recipient may use your version of this file under
Packit 67f6e7
 * the terms of any one of the MPL, the GPL or the LGPL.
Packit 67f6e7
 *
Packit 67f6e7
 * ***** END LICENSE BLOCK ***** */
Packit 67f6e7
Packit 67f6e7
#include "CharDistribution.h"
Packit 67f6e7
Packit 67f6e7
#include "JISFreq.tab"
Packit 67f6e7
#include "Big5Freq.tab"
Packit 67f6e7
#include "EUCKRFreq.tab"
Packit 67f6e7
#include "EUCTWFreq.tab"
Packit 67f6e7
#include "GB2312Freq.tab"
Packit 67f6e7
Packit 67f6e7
#define SURE_YES 0.99f
Packit 67f6e7
#define SURE_NO  0.01f
Packit 67f6e7
Packit 67f6e7
//return confidence base on received data
Packit 67f6e7
float CharDistributionAnalysis::GetConfidence()
Packit 67f6e7
{ 
Packit 67f6e7
  //if we didn't receive any character in our consideration range, return negative answer
Packit 67f6e7
  if (mTotalChars <= 0)
Packit 67f6e7
    return SURE_NO;
Packit 67f6e7
Packit 67f6e7
  if (mTotalChars != mFreqChars) {
Packit 67f6e7
    float r = mFreqChars / ((mTotalChars - mFreqChars) * mTypicalDistributionRatio);
Packit 67f6e7
Packit 67f6e7
    if (r < SURE_YES)
Packit 67f6e7
      return r;
Packit 67f6e7
  }
Packit 67f6e7
  //normalize confidence, (we don't want to be 100% sure)
Packit 67f6e7
  return SURE_YES;
Packit 67f6e7
}
Packit 67f6e7
Packit 67f6e7
EUCTWDistributionAnalysis::EUCTWDistributionAnalysis()
Packit 67f6e7
{
Packit 67f6e7
  mCharToFreqOrder = EUCTWCharToFreqOrder;
Packit 67f6e7
  mTableSize = EUCTW_TABLE_SIZE;
Packit 67f6e7
  mTypicalDistributionRatio = EUCTW_TYPICAL_DISTRIBUTION_RATIO;
Packit 67f6e7
}
Packit 67f6e7
Packit 67f6e7
EUCKRDistributionAnalysis::EUCKRDistributionAnalysis()
Packit 67f6e7
{
Packit 67f6e7
  mCharToFreqOrder = EUCKRCharToFreqOrder;
Packit 67f6e7
  mTableSize = EUCKR_TABLE_SIZE;
Packit 67f6e7
  mTypicalDistributionRatio = EUCKR_TYPICAL_DISTRIBUTION_RATIO;
Packit 67f6e7
}
Packit 67f6e7
Packit 67f6e7
GB2312DistributionAnalysis::GB2312DistributionAnalysis()
Packit 67f6e7
{
Packit 67f6e7
  mCharToFreqOrder = GB2312CharToFreqOrder;
Packit 67f6e7
  mTableSize = GB2312_TABLE_SIZE;
Packit 67f6e7
  mTypicalDistributionRatio = GB2312_TYPICAL_DISTRIBUTION_RATIO;
Packit 67f6e7
}
Packit 67f6e7
Packit 67f6e7
Big5DistributionAnalysis::Big5DistributionAnalysis()
Packit 67f6e7
{
Packit 67f6e7
  mCharToFreqOrder = Big5CharToFreqOrder;
Packit 67f6e7
  mTableSize = BIG5_TABLE_SIZE;
Packit 67f6e7
  mTypicalDistributionRatio = BIG5_TYPICAL_DISTRIBUTION_RATIO;
Packit 67f6e7
}
Packit 67f6e7
Packit 67f6e7
SJISDistributionAnalysis::SJISDistributionAnalysis()
Packit 67f6e7
{
Packit 67f6e7
  mCharToFreqOrder = JISCharToFreqOrder;
Packit 67f6e7
  mTableSize = JIS_TABLE_SIZE;
Packit 67f6e7
  mTypicalDistributionRatio = JIS_TYPICAL_DISTRIBUTION_RATIO;
Packit 67f6e7
}
Packit 67f6e7
Packit 67f6e7
EUCJPDistributionAnalysis::EUCJPDistributionAnalysis()
Packit 67f6e7
{
Packit 67f6e7
  mCharToFreqOrder = JISCharToFreqOrder;
Packit 67f6e7
  mTableSize = JIS_TABLE_SIZE;
Packit 67f6e7
  mTypicalDistributionRatio = JIS_TYPICAL_DISTRIBUTION_RATIO;
Packit 67f6e7
}
Packit 67f6e7