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
#ifndef nsEUCJPProber_h__
44
#define nsEUCJPProber_h__
45
46
#include "nsCharSetProber.h"
47
#include "nsCodingStateMachine.h"
48
#include "JpCntx.h"
49
#include "CharDistribution.h"
50
51
class nsEUCJPProber: public nsCharSetProber {
52
public:
53
  nsEUCJPProber(PRBool aIsPreferredLanguage)
54
    :mIsPreferredLanguage(aIsPreferredLanguage)
55
  {mCodingSM = new nsCodingStateMachine(&EUCJPSMModel);
56
    Reset();}
57
  virtual ~nsEUCJPProber(void){delete mCodingSM;}
58
  nsProbingState HandleData(const char* aBuf, PRUint32 aLen);
59
  const char* GetCharSetName() {return "EUC-JP";}
60
  nsProbingState GetState(void) {return mState;}
61
  void      Reset(void);
62
  float     GetConfidence(void);
63
  void      SetOpion() {}
64
65
protected:
66
  nsCodingStateMachine* mCodingSM;
67
  nsProbingState mState;
68
69
  EUCJPContextAnalysis mContextAnalyser;
70
  EUCJPDistributionAnalysis mDistributionAnalyser;
71
72
  char mLastChar[2];
73
  PRBool mIsPreferredLanguage;
74
};
75
76
77
#endif /* nsEUCJPProber_h__ */