1
/* -*- Mode: C++; tab-width: 2; 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 Communicator client 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
#ifndef nsUniversalDetector_h__
39
#define nsUniversalDetector_h__
40
41
class nsCharSetProber;
42
43
#define NUM_OF_CHARSET_PROBERS  3
44
45
typedef enum {
46
  ePureAscii = 0,
47
  eEscAscii  = 1,
48
  eHighbyte  = 2
49
} nsInputState;
50
51
#define NS_FILTER_CHINESE_SIMPLIFIED  0x01
52
#define NS_FILTER_CHINESE_TRADITIONAL 0x02
53
#define NS_FILTER_JAPANESE            0x04
54
#define NS_FILTER_KOREAN              0x08
55
#define NS_FILTER_NON_CJK             0x10
56
#define NS_FILTER_ALL                 0x1F
57
#define NS_FILTER_CHINESE (NS_FILTER_CHINESE_SIMPLIFIED | \
58
                           NS_FILTER_CHINESE_TRADITIONAL)
59
#define NS_FILTER_CJK (NS_FILTER_CHINESE_SIMPLIFIED | \
60
                       NS_FILTER_CHINESE_TRADITIONAL | \
61
                       NS_FILTER_JAPANESE | \
62
                       NS_FILTER_KOREAN)
63
64
class nsUniversalDetector {
65
public:
66
   nsUniversalDetector(PRUint32 aLanguageFilter);
67
   virtual ~nsUniversalDetector();
68
   virtual nsresult HandleData(const char* aBuf, PRUint32 aLen);
69
   virtual void DataEnd(void);
70
71
protected:
72
   virtual void Report(const char* aCharset) = 0;
73
   virtual void Reset();
74
   nsInputState  mInputState;
75
   PRBool  mDone;
76
   PRBool  mInTag;
77
   PRBool  mStart;
78
   PRBool  mGotData;
79
   char    mLastChar;
80
   const char *  mDetectedCharset;
81
   PRInt32 mBestGuess;
82
   PRUint32 mLanguageFilter;
83
84
   nsCharSetProber  *mCharSetProbers[NUM_OF_CHARSET_PROBERS];
85
   nsCharSetProber  *mEscCharSetProber;
86
};
87
88
#endif