DtUnicodeChar Class Reference

A single unicode character. More...

Collaboration diagram for DtUnicodeChar:

Public Types
typedef unsigned int	CodePoint
typedef unsigned short	Surrogate
typedef unsigned char	Octet
	A Unicode Octet is 8bit byte used in UTF-8 encoding. More...

Public Member Functions
	DtUnicodeChar ()
	DtUnicodeChar (const char c)
	Construct a unicode character for a character c. More...
	DtUnicodeChar (const wchar_t c)
	Construct a unicode character for a character c. More...
	DtUnicodeChar (const unsigned short s, const unsigned short c)
	Construct a pair of UTF-16 code units, where the first character must be a surrogate pair. More...
	DtUnicodeChar (const DtUnicodeChar &other)
DtUnicodeChar &	operator= (const DtUnicodeChar &other)
bool	operator== (const DtUnicodeChar &other) const
bool	operator!= (const DtUnicodeChar &other) const
unsigned int	utf8Length () const
	Calculate the utf-8 length of a code point. More...
template<int sizeofWChar_t>
unsigned int	wchartLength () const
unsigned int	wideStringLength () const
unsigned int	utf16Length () const
unsigned int	utf32Length () const
unsigned int	utf16CodeUnits () const
unsigned int	readUtf16 (const Surrogate *memory)
	Read from UTF-16 encoded memory, Returns number of code units read, NOT number of bytes. More...
void	writeUtf16 (Surrogate *memory) const
void	readUtf32 (const unsigned int *memory)
void	writeUtf32 (unsigned int *memory) const
unsigned int	readUtf8 (const unsigned char *memory)
void	writeUtf8 (char *memory) const
template<int sizeofWchart>
void	writeWCharT (wchar_t *memory) const
void	writeWChar (wchar_t *memory) const
CodePoint	codePoint () const
template<>
unsigned int	wchartLength () const
template<>
unsigned int	wchartLength () const
template<>
DtUnicodeChar::CodePoint	widechar (const wchar_t c)
template<>
void	writeWCharT (wchar_t *memory) const
template<>
void	writeWCharT (wchar_t *memory) const

Static Public Member Functions
template<int sizeof_wchar_t>
static CodePoint	widechar (const wchar_t c)
static bool	isCodePointValid (CodePoint codePoint)
static bool	isSurrogateSubstringValid (const Surrogate *start, const Surrogate *end, const Surrogate *substringStart, const Surrogate *substringEnd)
static bool	isSurrogate (Surrogate cp)
static DtUnicodeChar	fromUtf32 (unsigned int character)
static CodePoint	decodeSurrogatePair (Surrogate hi, Surrogate lo)
static void	encodeSurrogatePair (CodePoint cp, Surrogate &hi, Surrogate &lo)
static unsigned int	utf8Length (const unsigned char c)
	Get the length based upon the first character. More...

Static Public Attributes
static const CodePoint	CodePointMax = 0x0010ffff
static const Surrogate	LeadSurrogateMin = 0xd800
static const Surrogate	LeadSurrogateMax = 0xdbff
static const Surrogate	TrailSurrogateMin = 0xdc00
static const Surrogate	TrailSurrogateMax = 0xdfff

Protected Member Functions
	DtUnicodeChar (unsigned int utf32c)

Private Attributes
CodePoint	myCodePoint

Detailed Description

A single unicode character.

Member Typedef Documentation

typedef unsigned int DtUnicodeChar::CodePoint

typedef unsigned char DtUnicodeChar::Octet

A Unicode Octet is 8bit byte used in UTF-8 encoding.

typedef unsigned short DtUnicodeChar::Surrogate

Constructor & Destructor Documentation

DtUnicodeChar::DtUnicodeChar ( )

inline

Referenced by fromUtf32().

DtUnicodeChar::DtUnicodeChar ( const char  c )

inlineexplicit

Construct a unicode character for a character c.

C is assumed to be either ASCII or Latin-1

DtUnicodeChar::DtUnicodeChar ( const wchar_t  c )

inlineexplicit

Construct a unicode character for a character c.

C is assumed to be either UTF-16 or UTF-32 depending on encoding. If an invalid UTF-16 character is supplied an exception will be thrown.

DtUnicodeChar::DtUnicodeChar ( const unsigned short  s, const unsigned short  c  )

inlineexplicit

Construct a pair of UTF-16 code units, where the first character must be a surrogate pair.

References isSurrogate().

DtUnicodeChar::DtUnicodeChar ( const DtUnicodeChar &  other )

inline

DtUnicodeChar::DtUnicodeChar ( unsigned int  utf32c )

inlineprotected

Member Function Documentation

CodePoint DtUnicodeChar::codePoint ( ) const

inline

References myCodePoint.

static CodePoint DtUnicodeChar::decodeSurrogatePair ( Surrogate  hi, Surrogate  lo  )

inlinestatic

Referenced by readUtf16().

static void DtUnicodeChar::encodeSurrogatePair ( CodePoint  cp, Surrogate &  hi, Surrogate &  lo  )

inlinestatic

References LeadSurrogateMin, and TrailSurrogateMin.

Referenced by writeUtf16().

static DtUnicodeChar DtUnicodeChar::fromUtf32 ( unsigned int  character )

inlinestatic

Exceptions

DtInvalidInput

if the character is not valid.

References DtUnicodeChar(), and isCodePointValid().

static bool DtUnicodeChar::isCodePointValid ( CodePoint  codePoint )

inlinestatic

References CodePointMax, and isSurrogate().

Referenced by fromUtf32().

static bool DtUnicodeChar::isSurrogate ( Surrogate  cp )

inlinestatic

References LeadSurrogateMin, and TrailSurrogateMax.

Referenced by DtUnicodeChar(), isCodePointValid(), and readUtf16().

static bool DtUnicodeChar::isSurrogateSubstringValid ( const Surrogate *  start, const Surrogate *  end, const Surrogate *  substringStart, const Surrogate *  substringEnd  )

inlinestatic

References LeadSurrogateMin, and TrailSurrogateMin.

bool DtUnicodeChar::operator!= ( const DtUnicodeChar &  other ) const

inline

References myCodePoint.

DtUnicodeChar& DtUnicodeChar::operator= ( const DtUnicodeChar &  other )

inline

References myCodePoint.

bool DtUnicodeChar::operator== ( const DtUnicodeChar &  other ) const

inline

References myCodePoint.

unsigned int DtUnicodeChar::readUtf16 ( const Surrogate *  memory )

inline

Read from UTF-16 encoded memory, Returns number of code units read, NOT number of bytes.

References decodeSurrogatePair(), isSurrogate(), and myCodePoint.

void DtUnicodeChar::readUtf32 ( const unsigned int *  memory )

inline

References myCodePoint.

unsigned int DtUnicodeChar::readUtf8 ( const unsigned char *  memory )

inline

References myCodePoint.

unsigned int DtUnicodeChar::utf16CodeUnits ( ) const

inline

References myCodePoint.

unsigned int DtUnicodeChar::utf16Length ( ) const

inline

References myCodePoint.

unsigned int DtUnicodeChar::utf32Length ( ) const

inline

unsigned int DtUnicodeChar::utf8Length ( ) const

inline

Calculate the utf-8 length of a code point.

References myCodePoint.

static unsigned int DtUnicodeChar::utf8Length ( const unsigned char  c )

inlinestatic

Get the length based upon the first character.

template<int sizeofWChar_t>

unsigned int DtUnicodeChar::wchartLength ( ) const

inline

template<>

unsigned int DtUnicodeChar::wchartLength ( ) const

inline

template<>

unsigned int DtUnicodeChar::wchartLength ( ) const

inline

template<int sizeof_wchar_t>

DtUnicodeChar::CodePoint DtUnicodeChar::widechar ( const wchar_t  c )

inlinestatic

template<>

DtUnicodeChar::CodePoint DtUnicodeChar::widechar ( const wchar_t  c )

inline

unsigned int DtUnicodeChar::wideStringLength ( ) const

inline

void DtUnicodeChar::writeUtf16 ( Surrogate *  memory ) const

inline

References encodeSurrogatePair(), and myCodePoint.

void DtUnicodeChar::writeUtf32 ( unsigned int *  memory ) const

inline

References myCodePoint.

void DtUnicodeChar::writeUtf8 ( char *  memory ) const

inline

References myCodePoint.

void DtUnicodeChar::writeWChar ( wchar_t *  memory ) const

inline

template<int sizeofWchart>

void DtUnicodeChar::writeWCharT ( wchar_t *  memory ) const

inline

template<>

void DtUnicodeChar::writeWCharT ( wchar_t *  memory ) const

inline

template<>

void DtUnicodeChar::writeWCharT ( wchar_t *  memory ) const

inline

Member Data Documentation

const CodePoint DtUnicodeChar::CodePointMax = 0x0010ffff

static

Referenced by isCodePointValid().

const Surrogate DtUnicodeChar::LeadSurrogateMax = 0xdbff

static

const Surrogate DtUnicodeChar::LeadSurrogateMin = 0xd800

static

Referenced by encodeSurrogatePair(), isSurrogate(), and isSurrogateSubstringValid().

CodePoint DtUnicodeChar::myCodePoint

private

Referenced by codePoint(), operator!=(), operator=(), operator==(), readUtf16(), readUtf32(), readUtf8(), utf16CodeUnits(), utf16Length(), utf8Length(), writeUtf16(), writeUtf32(), and writeUtf8().

const Surrogate DtUnicodeChar::TrailSurrogateMax = 0xdfff

static

Referenced by isSurrogate().

const Surrogate DtUnicodeChar::TrailSurrogateMin = 0xdc00

static

Referenced by encodeSurrogatePair(), and isSurrogateSubstringValid().

---

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

• vlUnicodeChar.h