extensions/universalchardet/src/base/nsSJISProber.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 S-JIS 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 "nsSJISProber.h"
  44
  45 void  nsSJISProber::Reset(void)
  46 {
  47   mCodingSM->Reset();
  48   mState = eDetecting;
  49   mContextAnalyser.Reset();
  50   mDistributionAnalyser.Reset();
  51 }
  52
  53 nsProbingState nsSJISProber::HandleData(const char* aBuf, PRUint32 aLen)
  54 {
  55   nsSMState codingState;
  56
  57   for (PRUint32 i = 0; i < aLen; i++)
  58   {
  59     codingState = mCodingSM->NextState(aBuf[i]);
  60     if (codingState == eItsMe)
  61     {
  62       mState = eFoundIt;
  63       break;
  64     }
  65     if (codingState == eStart)
  66     {
  67       PRUint32 charLen = mCodingSM->GetCurrentCharLen();
  68       if (i == 0)
  69       {
  70         mLastChar[1] = aBuf[0];
  71         mContextAnalyser.HandleOneChar(mLastChar+2-charLen, charLen);
  72         mDistributionAnalyser.HandleOneChar(mLastChar, charLen);
  73       }
  74       else
  75       {
  76         mContextAnalyser.HandleOneChar(aBuf+i+1-charLen, charLen);
  77         mDistributionAnalyser.HandleOneChar(aBuf+i-1, charLen);
  78       }
  79     }
  80   }
  81
  82   mLastChar[0] = aBuf[aLen-1];
  83
  84   if (mState == eDetecting)
  85     if (mContextAnalyser.GotEnoughData() && GetConfidence() > SHORTCUT_THRESHOLD)
  86       mState = eFoundIt;
  87
  88   return mState;
  89 }
  90
  91 float nsSJISProber::GetConfidence(void)
  92 {
  93   float contxtCf = mContextAnalyser.GetConfidence(mIsPreferredLanguage);
  94   float distribCf = mDistributionAnalyser.GetConfidence(mIsPreferredLanguage);
  95
  96   return (contxtCf > distribCf ? contxtCf : distribCf);
  97 }
  98