File indexing completed on 2024-12-22 04:33:41

0001 /* -*- Mode: C; tab-width: 4; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
0002 /* ***** BEGIN LICENSE BLOCK *****
0003  * Version: MPL 1.1/GPL 2.0/LGPL 2.1
0004  *
0005  * The contents of this file are subject to the Mozilla Public License Version
0006  * 1.1 (the "License"); you may not use this file except in compliance with
0007  * the License. You may obtain a copy of the License at
0008  * http://www.mozilla.org/MPL/
0009  *
0010  * Software distributed under the License is distributed on an "AS IS" basis,
0011  * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
0012  * for the specific language governing rights and limitations under the
0013  * License.
0014  *
0015  * The Original Code is mozilla.org code.
0016  *
0017  * The Initial Developer of the Original Code is
0018  * Netscape Communications Corporation.
0019  * Portions created by the Initial Developer are Copyright (C) 1998
0020  * the Initial Developer. All Rights Reserved.
0021  *
0022  * Contributor(s):
0023  *
0024  * Alternatively, the contents of this file may be used under the terms of
0025  * either the GNU General Public License Version 2 or later (the "GPL"), or
0026  * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
0027  * in which case the provisions of the GPL or the LGPL are applicable instead
0028  * of those above. If you wish to allow use of your version of this file only
0029  * under the terms of either the GPL or the LGPL, and not to allow others to
0030  * use your version of this file under the terms of the MPL, indicate your
0031  * decision by deleting the provisions above and replace them with the notice
0032  * and other provisions required by the GPL or the LGPL. If you do not delete
0033  * the provisions above, a recipient may use your version of this file under
0034  * the terms of any one of the MPL, the GPL or the LGPL.
0035  *
0036  * ***** END LICENSE BLOCK ***** */
0037 
0038 // for S-JIS encoding, observed characteristic:
0039 // 1, kana character (or hankaku?) often have hight frequency of appearance
0040 // 2, kana character often exist in group
0041 // 3, certain combination of kana is never used in japanese language
0042 
0043 #ifndef nsEUCJPProber_h__
0044 #define nsEUCJPProber_h__
0045 
0046 #include "nsCharSetProber.h"
0047 #include "nsCodingStateMachine.h"
0048 #include "JpCntx.h"
0049 #include "CharDistribution.h"
0050 
0051 class nsEUCJPProber: public nsCharSetProber, nsCharSetProberHelper {
0052 public:
0053   nsEUCJPProber(void){mCodingSM = new nsCodingStateMachine(&EUCJPSMModel);
0054                       Reset();};
0055   virtual ~nsEUCJPProber(void){delete mCodingSM;};
0056   nsProbingState HandleData(const char* aBuf, PRUint32 aLen);
0057   const char* GetCharSetName() {return "EUC-JP";};
0058   nsProbingState GetState(void) {return mState;};
0059   void      Reset(void);
0060   float     GetConfidence(void);
0061   void      SetOpion() {}
0062 
0063 protected:
0064   nsCodingStateMachine* mCodingSM;
0065   nsProbingState mState;
0066 
0067   EUCJPContextAnalysis mContextAnalyser;
0068   EUCJPDistributionAnalysis mDistributionAnalyser;
0069 };
0070 
0071 
0072 #endif /* nsEUCJPProber_h__ */
0073