Back to index

lightning-sunbird  0.9+nobinonly
nsSJISProber.cpp
Go to the documentation of this file.
00001 /* -*- Mode: C; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
00002 /* ***** BEGIN LICENSE BLOCK *****
00003  * Version: MPL 1.1/GPL 2.0/LGPL 2.1
00004  *
00005  * The contents of this file are subject to the Mozilla Public License Version
00006  * 1.1 (the "License"); you may not use this file except in compliance with
00007  * the License. You may obtain a copy of the License at
00008  * http://www.mozilla.org/MPL/
00009  *
00010  * Software distributed under the License is distributed on an "AS IS" basis,
00011  * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
00012  * for the specific language governing rights and limitations under the
00013  * License.
00014  *
00015  * The Original Code is mozilla.org code.
00016  *
00017  * The Initial Developer of the Original Code is
00018  * Netscape Communications Corporation.
00019  * Portions created by the Initial Developer are Copyright (C) 1998
00020  * the Initial Developer. All Rights Reserved.
00021  *
00022  * Contributor(s):
00023  *
00024  * Alternatively, the contents of this file may be used under the terms of
00025  * either the GNU General Public License Version 2 or later (the "GPL"), or
00026  * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
00027  * in which case the provisions of the GPL or the LGPL are applicable instead
00028  * of those above. If you wish to allow use of your version of this file only
00029  * under the terms of either the GPL or the LGPL, and not to allow others to
00030  * use your version of this file under the terms of the MPL, indicate your
00031  * decision by deleting the provisions above and replace them with the notice
00032  * and other provisions required by the GPL or the LGPL. If you do not delete
00033  * the provisions above, a recipient may use your version of this file under
00034  * the terms of any one of the MPL, the GPL or the LGPL.
00035  *
00036  * ***** END LICENSE BLOCK ***** */
00037 
00038 // for S-JIS encoding, obeserve characteristic:
00039 // 1, kana character (or hankaku?) often have hight frequency of appereance
00040 // 2, kana character often exist in group
00041 // 3, certain combination of kana is never used in japanese language
00042 
00043 #include "nsSJISProber.h"
00044 
00045 void  nsSJISProber::Reset(void)
00046 {
00047   mCodingSM->Reset(); 
00048   mState = eDetecting;
00049   mContextAnalyser.Reset();
00050   mDistributionAnalyser.Reset();
00051 }
00052 
00053 nsProbingState nsSJISProber::HandleData(const char* aBuf, PRUint32 aLen)
00054 {
00055   nsSMState codingState;
00056 
00057   for (PRUint32 i = 0; i < aLen; i++)
00058   {
00059     codingState = mCodingSM->NextState(aBuf[i]);
00060     if (codingState == eError)
00061     {
00062       mState = eNotMe;
00063       break;
00064     }
00065     if (codingState == eItsMe)
00066     {
00067       mState = eFoundIt;
00068       break;
00069     }
00070     if (codingState == eStart)
00071     {
00072       PRUint32 charLen = mCodingSM->GetCurrentCharLen();
00073       if (i == 0)
00074       {
00075         mLastChar[1] = aBuf[0];
00076         mContextAnalyser.HandleOneChar(mLastChar+2-charLen, charLen);
00077         mDistributionAnalyser.HandleOneChar(mLastChar, charLen);
00078       }
00079       else
00080       {
00081         mContextAnalyser.HandleOneChar(aBuf+i+1-charLen, charLen);
00082         mDistributionAnalyser.HandleOneChar(aBuf+i-1, charLen);
00083       }
00084     }
00085   }
00086 
00087   mLastChar[0] = aBuf[aLen-1];
00088 
00089   if (mState == eDetecting)
00090     if (mContextAnalyser.GotEnoughData() && GetConfidence() > SHORTCUT_THRESHOLD)
00091       mState = eFoundIt;
00092 
00093   return mState;
00094 }
00095 
00096 float nsSJISProber::GetConfidence(void)
00097 {
00098   float contxtCf = mContextAnalyser.GetConfidence();
00099   float distribCf = mDistributionAnalyser.GetConfidence();
00100 
00101   return (contxtCf > distribCf ? contxtCf : distribCf);
00102 }
00103