1 | // © 2016 and later: Unicode, Inc. and others. |
2 | // License & terms of use: http://www.unicode.org/copyright.html |
3 | /* |
4 | ********************************************************************** |
5 | * Copyright (C) 2005-2012, International Business Machines |
6 | * Corporation and others. All Rights Reserved. |
7 | ********************************************************************** |
8 | */ |
9 | |
10 | #ifndef __CSRECOG_H |
11 | #define __CSRECOG_H |
12 | |
13 | #include "unicode/uobject.h" |
14 | |
15 | #if !UCONFIG_NO_CONVERSION |
16 | |
17 | #include "inputext.h" |
18 | |
19 | U_NAMESPACE_BEGIN |
20 | |
21 | class CharsetMatch; |
22 | |
23 | class CharsetRecognizer : public UMemory |
24 | { |
25 | public: |
26 | /** |
27 | * Get the IANA name of this charset. |
28 | * Note that some recognizers can recognize more than one charset, but that this API |
29 | * assumes just one name per recognizer. |
30 | * TODO: need to account for multiple names in public API that enumerates over the |
31 | * known detectable charsets. |
32 | * @return the charset name. |
33 | */ |
34 | virtual const char *getName() const = 0; |
35 | |
36 | /** |
37 | * Get the ISO language code for this charset. |
38 | * @return the language code, or <code>null</code> if the language cannot be determined. |
39 | */ |
40 | virtual const char *getLanguage() const; |
41 | |
42 | /* |
43 | * Try the given input text against this Charset, and fill in the results object |
44 | * with the quality of the match plus other information related to the match. |
45 | * |
46 | * Return TRUE if the the input bytes are a potential match, and |
47 | * FALSE if the input data is not compatible with, or illegal in this charset. |
48 | */ |
49 | virtual UBool match(InputText *textIn, CharsetMatch *results) const = 0; |
50 | |
51 | virtual ~CharsetRecognizer(); |
52 | }; |
53 | |
54 | U_NAMESPACE_END |
55 | |
56 | #endif |
57 | #endif /* __CSRECOG_H */ |
58 | |