/extensions/universalchardet/src/base/nsEUCJPProber.cpp

  1/* -*- Mode: C; tab-width: 4; 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.org 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// for japanese encoding, obeserve characteristic:
 39// 1, kana character (or hankaku?) often have hight frequency of appereance
 40// 2, kana character often exist in group
 41// 3, certain combination of kana is never used in japanese language
 42
 43#include "nsEUCJPProber.h"
 44#include "nsDebug.h"
 45
 46void  nsEUCJPProber::Reset(void)
 47{
 48  mCodingSM->Reset(); 
 49  mState = eDetecting;
 50  mContextAnalyser.Reset(mIsPreferredLanguage);
 51  mDistributionAnalyser.Reset(mIsPreferredLanguage);
 52}
 53
 54nsProbingState nsEUCJPProber::HandleData(const char* aBuf, PRUint32 aLen)
 55{
 56  NS_ASSERTION(aLen, "HandleData called with empty buffer");
 57  nsSMState codingState;
 58
 59  for (PRUint32 i = 0; i < aLen; i++)
 60  {
 61    codingState = mCodingSM->NextState(aBuf[i]);
 62    if (codingState == eItsMe)
 63    {
 64      mState = eFoundIt;
 65      break;
 66    }
 67    if (codingState == eStart)
 68    {
 69      PRUint32 charLen = mCodingSM->GetCurrentCharLen();
 70
 71      if (i == 0)
 72      {
 73        mLastChar[1] = aBuf[0];
 74        mContextAnalyser.HandleOneChar(mLastChar, charLen);
 75        mDistributionAnalyser.HandleOneChar(mLastChar, charLen);
 76      }
 77      else
 78      {
 79        mContextAnalyser.HandleOneChar(aBuf+i-1, charLen);
 80        mDistributionAnalyser.HandleOneChar(aBuf+i-1, charLen);
 81      }
 82    }
 83  }
 84
 85  mLastChar[0] = aBuf[aLen-1];
 86
 87  if (mState == eDetecting)
 88    if (mContextAnalyser.GotEnoughData() && GetConfidence() > SHORTCUT_THRESHOLD)
 89      mState = eFoundIt;
 90
 91  return mState;
 92}
 93
 94float nsEUCJPProber::GetConfidence(void)
 95{
 96  float contxtCf = mContextAnalyser.GetConfidence();
 97  float distribCf = mDistributionAnalyser.GetConfidence();
 98
 99  return (contxtCf > distribCf ? contxtCf : distribCf);
100}
101