blob: 944a5007fe5f9a5eba6400cce421f24bab87fadc (
plain) (
blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
|
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
* Copyright (C) 2005-2012, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*/
#ifndef __CSRECOG_H
#define __CSRECOG_H
#include "unicode/uobject.h"
#if !UCONFIG_NO_CONVERSION
#include "inputext.h"
U_NAMESPACE_BEGIN
class CharsetMatch;
class CharsetRecognizer : public UMemory
{
public:
/**
* Get the IANA name of this charset.
* Note that some recognizers can recognize more than one charset, but that this API
* assumes just one name per recognizer.
* TODO: need to account for multiple names in public API that enumerates over the
* known detectable charsets.
* @return the charset name.
*/
virtual const char *getName() const = 0;
/**
* Get the ISO language code for this charset.
* @return the language code, or <code>null</code> if the language cannot be determined.
*/
virtual const char *getLanguage() const;
/*
* Try the given input text against this Charset, and fill in the results object
* with the quality of the match plus other information related to the match.
*
* Return true if the the input bytes are a potential match, and
* false if the input data is not compatible with, or illegal in this charset.
*/
virtual UBool match(InputText *textIn, CharsetMatch *results) const = 0;
virtual ~CharsetRecognizer();
};
U_NAMESPACE_END
#endif
#endif /* __CSRECOG_H */
|
