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 Universal charset detector 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) 2001
20 
 * the Initial Developer. All Rights Reserved.
21 
 *
22 
 * Contributor(s):
23 
 *          Shy Shalom <shooshX@gmail.com>
24 
 *
25 
 * Alternatively, the contents of this file may be used under the terms of
26 
 * either the GNU General Public License Version 2 or later (the "GPL"), or
27 
 * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
28 
 * in which case the provisions of the GPL or the LGPL are applicable instead
29 
 * of those above. If you wish to allow use of your version of this file only
30 
 * under the terms of either the GPL or the LGPL, and not to allow others to
31 
 * use your version of this file under the terms of the MPL, indicate your
32 
 * decision by deleting the provisions above and replace them with the notice
33 
 * and other provisions required by the GPL or the LGPL. If you do not delete
34 
 * the provisions above, a recipient may use your version of this file under
35 
 * the terms of any one of the MPL, the GPL or the LGPL.
36 
 *
37 
 * ***** END LICENSE BLOCK ***** */
38 
#ifndef nsCharSetProber_h__
39 
#define nsCharSetProber_h__
40 





41

#include "nscore.h"





42






43

//#define DEBUG_chardet // Uncomment this for debug dump.





44






45

typedef enum {





46

  eDetecting = 0,   //We are still detecting, no sure answer yet, but caller can ask for confidence.





47

  eFoundIt = 1,     //That's a positive answer





48

  eNotMe = 2        //Negative answer





49

} nsProbingState;





50






51

#define SHORTCUT_THRESHOLD      (float)0.95





52






53

class nsCharSetProber {





54

public:





55

  virtual ~nsCharSetProber() {}





56

  virtual const char* GetCharSetName() = 0;





57

  virtual nsProbingState HandleData(const char* aBuf, PRUint32 aLen) = 0;





58

  virtual nsProbingState GetState(void) = 0;





59

  virtual void      Reset(void)  = 0;





60

  virtual float     GetConfidence(void) = 0;





61

  virtual void      SetOpion() = 0;





62






63

#ifdef DEBUG_chardet





64

  virtual void  DumpStatus() {};





65

#endif





66






67

  // Helper functions used in the Latin1 and Group probers.





68

  // both functions Allocate a new buffer for newBuf. This buffer should be 





69

  // freed by the caller using PR_FREEIF.





70

  // Both functions return PR_FALSE in case of memory allocation failure.





71

  static PRBool FilterWithoutEnglishLetters(const char* aBuf, PRUint32 aLen, char** newBuf, PRUint32& newLen);





72

  static PRBool FilterWithEnglishLetters(const char* aBuf, PRUint32 aLen, char** newBuf, PRUint32& newLen);





73






74

};





75






76

#endif /* nsCharSetProber_h__ */