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 __CSMATCH_H 11 #define __CSMATCH_H 12 13 #include "unicode/uobject.h" 14 15 #if !UCONFIG_NO_CONVERSION 16 17 U_NAMESPACE_BEGIN 18 19 class InputText; 20 class CharsetRecognizer; 21 22 /* 23 * CharsetMatch represents the results produced by one Charset Recognizer for one input text 24 * Any confidence > 0 indicates a possible match, meaning that the input bytes 25 * are at least legal. 26 * 27 * The full results of a detect are represented by an array of these 28 * CharsetMatch objects, each representing a possible matching charset. 29 * 30 * Note that a single charset recognizer may detect multiple closely related 31 * charsets, and set different names depending on the exact input bytes seen. 32 */ 33 class CharsetMatch : public UMemory 34 { 35 private: 36 InputText *textIn; 37 int32_t confidence; 38 const char *fCharsetName; 39 const char *fLang; 40 41 public: 42 CharsetMatch(); 43 44 /** 45 * fully set the state of this CharsetMatch. 46 * Called by the CharsetRecognizers to record match results. 47 * Default (NULL) parameters for names will be filled by calling the 48 * corresponding getters on the recognizer. 49 */ 50 void set(InputText *input, 51 const CharsetRecognizer *cr, 52 int32_t conf, 53 const char *csName=NULL, 54 const char *lang=NULL); 55 56 /** 57 * Return the name of the charset for this Match 58 */ 59 const char *getName() const; 60 61 const char *getLanguage()const; 62 63 int32_t getConfidence()const; 64 65 int32_t getUChars(UChar *buf, int32_t cap, UErrorCode *status) const; 66 }; 67 68 U_NAMESPACE_END 69 70 #endif 71 #endif /* __CSMATCH_H */ 72
