diff -r 000000000000 -r 6474c204b198 intl/icu/source/i18n/csrecog.h --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/intl/icu/source/i18n/csrecog.h Wed Dec 31 06:09:35 2014 +0100 @@ -0,0 +1,55 @@ +/* + ********************************************************************** + * 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 null 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 */