NCollection_UtfIterator< Type > Class Template Reference

Template class for Unicode strings support. More...

#include <NCollection_UtfIterator.hxx>

Public Member Functions
	NCollection_UtfIterator (const Type *theString)
	Constructor. More...
void	Init (const Type *theString)
	Initialize iterator within specified NULL-terminated string. More...
NCollection_UtfIterator &	operator++ ()
	Pre-increment operator. Reads the next unicode symbol. Notice - no protection against overrun! More...
NCollection_UtfIterator	operator++ (int)
	Post-increment operator. Notice - no protection against overrun! More...
bool	operator== (const NCollection_UtfIterator &theRight) const
	Equality operator. More...
bool	IsValid () const
	Return true if Unicode symbol is within valid range. More...
Standard_Utf32Char	operator* () const
	Dereference operator. More...
const Type *	BufferHere () const
	Buffer-fetching getter. More...
Type *	ChangeBufferHere ()
	Buffer-fetching getter. Dangerous! Iterator should be reinitialized on buffer change. More...
const Type *	BufferNext () const
	Buffer-fetching getter. More...
Standard_Integer	Index () const
Standard_Integer	AdvanceBytesUtf8 () const
Standard_Integer	AdvanceBytesUtf16 () const
Standard_Integer	AdvanceCodeUnitsUtf16 () const
Standard_Integer	AdvanceBytesUtf32 () const
Standard_Utf8Char *	GetUtf8 (Standard_Utf8Char *theBuffer) const
	Fill the UTF-8 buffer within current Unicode symbol. Use method AdvanceUtf8() to allocate buffer with enough size. More...
Standard_Utf8UChar *	GetUtf8 (Standard_Utf8UChar *theBuffer) const
Standard_Utf16Char *	GetUtf16 (Standard_Utf16Char *theBuffer) const
	Fill the UTF-16 buffer within current Unicode symbol. Use method AdvanceUtf16() to allocate buffer with enough size. More...
Standard_Utf32Char *	GetUtf32 (Standard_Utf32Char *theBuffer) const
	Fill the UTF-32 buffer within current Unicode symbol. Use method AdvanceUtf32() to allocate buffer with enough size. More...
template<typename TypeWrite >
Standard_Integer	AdvanceBytesUtf () const
template<typename TypeWrite >
TypeWrite *	GetUtf (TypeWrite *theBuffer) const
	Fill the UTF-** buffer within current Unicode symbol. Use method AdvanceUtf**() to allocate buffer with enough size. More...

Detailed Description

template<typename Type>
class NCollection_UtfIterator< Type >

Template class for Unicode strings support.

It defines an iterator and provide correct way to read multi-byte text (UTF-8 and UTF-16) and convert it from one to another. The current value of iterator is returned as UTF-32 Unicode symbol.

Here and below term "Unicode symbol" is used as synonym of "Unicode code point".

Constructor & Destructor Documentation

NCollection_UtfIterator()

template<typename Type >

NCollection_UtfIterator< Type >::NCollection_UtfIterator ( const Type *  theString )

inline

Constructor.

Parameters

theString

buffer to iterate

Member Function Documentation

AdvanceBytesUtf()

template<typename Type >

template<typename TypeWrite >

Standard_Integer NCollection_UtfIterator< Type >::AdvanceBytesUtf ( ) const

inline

Returns

the advance in TypeWrite chars needed to store current symbol

AdvanceBytesUtf16()

template<typename Type >

Standard_Integer NCollection_UtfIterator< Type >::AdvanceBytesUtf16

(

)

const

Returns

the advance in bytes to store current symbol in UTF-16. 0 means an invalid symbol; 2 bytes is a general case; 4 bytes for surrogate pair.

AdvanceBytesUtf32()

template<typename Type >

Standard_Integer NCollection_UtfIterator< Type >::AdvanceBytesUtf32 ( ) const

inline

Returns

the advance in bytes to store current symbol in UTF-32. Always 4 bytes (method for consistency).

AdvanceBytesUtf8()

template<typename Type >

Standard_Integer NCollection_UtfIterator< Type >::AdvanceBytesUtf8

(

)

const

Returns

the advance in bytes to store current symbol in UTF-8. 0 means an invalid symbol; 1-4 bytes are valid range.

AdvanceCodeUnitsUtf16()

template<typename Type >

Standard_Integer NCollection_UtfIterator< Type >::AdvanceCodeUnitsUtf16

(

)

const

Returns

the advance in bytes to store current symbol in UTF-16. 0 means an invalid symbol; 1 16-bit code unit is a general case; 2 16-bit code units for surrogate pair.

BufferHere()

template<typename Type >

const Type* NCollection_UtfIterator< Type >::BufferHere ( ) const

inline

Buffer-fetching getter.

BufferNext()

template<typename Type >

const Type* NCollection_UtfIterator< Type >::BufferNext ( ) const

inline

Buffer-fetching getter.

ChangeBufferHere()

template<typename Type >

Type* NCollection_UtfIterator< Type >::ChangeBufferHere ( )

inline

Buffer-fetching getter. Dangerous! Iterator should be reinitialized on buffer change.

GetUtf()

template<typename Type >

template<typename TypeWrite >

TypeWrite* NCollection_UtfIterator< Type >::GetUtf ( TypeWrite *  theBuffer ) const

inline

Fill the UTF-** buffer within current Unicode symbol. Use method AdvanceUtf**() to allocate buffer with enough size.

Parameters

theBuffer

buffer to fill

Returns

new buffer position (for next char)

GetUtf16()

template<typename Type >

Standard_Utf16Char* NCollection_UtfIterator< Type >::GetUtf16

(

Standard_Utf16Char *

theBuffer

)

const

Fill the UTF-16 buffer within current Unicode symbol. Use method AdvanceUtf16() to allocate buffer with enough size.

Parameters

theBuffer

buffer to fill

Returns

new buffer position (for next char)

GetUtf32()

template<typename Type >

Standard_Utf32Char* NCollection_UtfIterator< Type >::GetUtf32

(

Standard_Utf32Char *

theBuffer

)

const

Fill the UTF-32 buffer within current Unicode symbol. Use method AdvanceUtf32() to allocate buffer with enough size.

Parameters

theBuffer

buffer to fill

Returns

new buffer position (for next char)

GetUtf8() [1/2]

template<typename Type >

Standard_Utf8Char* NCollection_UtfIterator< Type >::GetUtf8

(

Standard_Utf8Char *

theBuffer

)

const

Fill the UTF-8 buffer within current Unicode symbol. Use method AdvanceUtf8() to allocate buffer with enough size.

Parameters

theBuffer

buffer to fill

Returns

new buffer position (for next char)

GetUtf8() [2/2]

template<typename Type >

Standard_Utf8UChar* NCollection_UtfIterator< Type >::GetUtf8

(

Standard_Utf8UChar *

theBuffer

)

const

Index()

template<typename Type >

Standard_Integer NCollection_UtfIterator< Type >::Index ( ) const

inline

Returns

the index displacement from iterator intialization (first symbol has index 0)

Init()

template<typename Type >

void NCollection_UtfIterator< Type >::Init ( const Type *  theString )

inline

Initialize iterator within specified NULL-terminated string.

IsValid()

template<typename Type >

bool NCollection_UtfIterator< Type >::IsValid ( ) const

inline

Return true if Unicode symbol is within valid range.

operator*()

template<typename Type >

Standard_Utf32Char NCollection_UtfIterator< Type >::operator* ( ) const

inline

Dereference operator.

Returns

the UTF-32 codepoint of the symbol currently pointed by iterator.

operator++() [1/2]

template<typename Type >

NCollection_UtfIterator& NCollection_UtfIterator< Type >::operator++ ( )

inline

Pre-increment operator. Reads the next unicode symbol. Notice - no protection against overrun!

operator++() [2/2]

template<typename Type >

NCollection_UtfIterator NCollection_UtfIterator< Type >::operator++ ( int  )

inline

Post-increment operator. Notice - no protection against overrun!

operator==()

template<typename Type >

bool NCollection_UtfIterator< Type >::operator== ( const NCollection_UtfIterator< Type > &  theRight ) const

inline

Equality operator.

---

The documentation for this class was generated from the following file:

• NCollection_UtfIterator.hxx