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 58 59 60 61 62 63 64 65 66 67 68 69
|
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
**********************************************************************
* Copyright (C) 2005-2016, International Business Machines
* Corporation and others. All Rights Reserved.
**********************************************************************
*/
#ifndef __CSDETECT_H
#define __CSDETECT_H
#include <_foundation_unicode/uobject.h>
#if !UCONFIG_NO_CONVERSION
#include <_foundation_unicode/uenum.h>
U_NAMESPACE_BEGIN
class InputText;
class CharsetRecognizer;
class CharsetMatch;
class CharsetDetector : public UMemory
{
private:
InputText *textIn;
CharsetMatch **resultArray;
int32_t resultCount;
UBool fStripTags; // If true, setText() will strip tags from input text.
UBool fFreshTextSet;
static void setRecognizers(UErrorCode &status);
UBool *fEnabledRecognizers; // If not null, active set of charset recognizers had
// been changed from the default. The array index is
// corresponding to fCSRecognizers. See setDetectableCharset().
public:
CharsetDetector(UErrorCode &status);
~CharsetDetector();
void setText(const char *in, int32_t len);
const CharsetMatch * const *detectAll(int32_t &maxMatchesFound, UErrorCode &status);
const CharsetMatch *detect(UErrorCode& status);
void setDeclaredEncoding(const char *encoding, int32_t len) const;
UBool setStripTagsFlag(UBool flag);
UBool getStripTagsFlag() const;
// const char *getCharsetName(int32_t index, UErrorCode& status) const;
static int32_t getDetectableCount();
static UEnumeration * getAllDetectableCharsets(UErrorCode &status);
UEnumeration * getDetectableCharsets(UErrorCode &status) const;
void setDetectableCharset(const char *encoding, UBool enabled, UErrorCode &status);
};
U_NAMESPACE_END
#endif
#endif /* __CSDETECT_H */
|