1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/intl/icu/source/i18n/csrecog.h Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,55 @@
1.4 +/*
1.5 + **********************************************************************
1.6 + * Copyright (C) 2005-2012, International Business Machines
1.7 + * Corporation and others. All Rights Reserved.
1.8 + **********************************************************************
1.9 + */
1.10 +
1.11 +#ifndef __CSRECOG_H
1.12 +#define __CSRECOG_H
1.13 +
1.14 +#include "unicode/uobject.h"
1.15 +
1.16 +#if !UCONFIG_NO_CONVERSION
1.17 +
1.18 +#include "inputext.h"
1.19 +
1.20 +U_NAMESPACE_BEGIN
1.21 +
1.22 +class CharsetMatch;
1.23 +
1.24 +class CharsetRecognizer : public UMemory
1.25 +{
1.26 + public:
1.27 + /**
1.28 + * Get the IANA name of this charset.
1.29 + * Note that some recognizers can recognize more than one charset, but that this API
1.30 + * assumes just one name per recognizer.
1.31 + * TODO: need to account for multiple names in public API that enumerates over the
1.32 + * known detectable charsets.
1.33 + * @return the charset name.
1.34 + */
1.35 + virtual const char *getName() const = 0;
1.36 +
1.37 + /**
1.38 + * Get the ISO language code for this charset.
1.39 + * @return the language code, or <code>null</code> if the language cannot be determined.
1.40 + */
1.41 + virtual const char *getLanguage() const;
1.42 +
1.43 + /*
1.44 + * Try the given input text against this Charset, and fill in the results object
1.45 + * with the quality of the match plus other information related to the match.
1.46 + *
1.47 + * Return TRUE if the the input bytes are a potential match, and
1.48 + * FALSE if the input data is not compatible with, or illegal in this charset.
1.49 + */
1.50 + virtual UBool match(InputText *textIn, CharsetMatch *results) const = 0;
1.51 +
1.52 + virtual ~CharsetRecognizer();
1.53 +};
1.54 +
1.55 +U_NAMESPACE_END
1.56 +
1.57 +#endif
1.58 +#endif /* __CSRECOG_H */
