makVrv::DtUnicodeChar Class Reference

A single unicode character. More...

List of all members.

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.
Public Member Functions
	DtUnicodeChar ()
	DtUnicodeChar (const char c)
	Construct a unicode character for a character c.
	DtUnicodeChar (const wchar_t c)
	Construct a unicode character for a character c.
	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.
	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.
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.
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
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.
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 makVrv::DtUnicodeChar::CodePoint

typedef unsigned short makVrv::DtUnicodeChar::Surrogate

typedef unsigned char makVrv::DtUnicodeChar::Octet

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

---

Constructor & Destructor Documentation

makVrv::DtUnicodeChar::DtUnicodeChar

(

)

[inline]

Referenced by fromUtf32().

makVrv::DtUnicodeChar::DtUnicodeChar

(

const char

c

)

[inline, explicit]

Construct a unicode character for a character c.

C is assumed to be either ASCII or Latin-1

makVrv::DtUnicodeChar::DtUnicodeChar

(

const wchar_t

c

)

[inline, explicit]

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.

makVrv::DtUnicodeChar::DtUnicodeChar	(	const unsigned short	s,
		const unsigned short	c
	)		[inline, explicit]

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

References isSurrogate().

makVrv::DtUnicodeChar::DtUnicodeChar

(

const DtUnicodeChar &

other

)

[inline]

makVrv::DtUnicodeChar::DtUnicodeChar

(

unsigned int

utf32c

)

[inline, protected]

---

Member Function Documentation

DtUnicodeChar::CodePoint makVrv::DtUnicodeChar::widechar< 2 >

(

const wchar_t

c

)

[inline, static]

DtUnicodeChar& makVrv::DtUnicodeChar::operator=

(

const DtUnicodeChar &

other

)

[inline]

References myCodePoint.

bool makVrv::DtUnicodeChar::operator==

(

const DtUnicodeChar &

other

)

const [inline]

References myCodePoint.

bool makVrv::DtUnicodeChar::operator!=

(

const DtUnicodeChar &

other

)

const [inline]

References myCodePoint.

static bool makVrv::DtUnicodeChar::isCodePointValid

(

CodePoint

codePoint

)

[inline, static]

References CodePointMax, and isSurrogate().

Referenced by fromUtf32().

static bool makVrv::DtUnicodeChar::isSurrogateSubstringValid	(	const Surrogate *	start,
		const Surrogate *	end,
		const Surrogate *	substringStart,
		const Surrogate *	substringEnd
	)		[inline, static]

References LeadSurrogateMin, and TrailSurrogateMin.

static bool makVrv::DtUnicodeChar::isSurrogate

(

Surrogate

cp

)

[inline, static]

References LeadSurrogateMin, and TrailSurrogateMax.

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

static DtUnicodeChar makVrv::DtUnicodeChar::fromUtf32

(

unsigned int

character

)

[inline, static]

Exceptions:

DtInvalidInput

if the character is not valid.

References DtUnicodeChar(), and isCodePointValid().

unsigned int makVrv::DtUnicodeChar::utf8Length

(

)

const [inline]

Calculate the utf-8 length of a code point.

References myCodePoint.

unsigned int makVrv::DtUnicodeChar::wchartLength< 4 >

(

)

const [inline]

unsigned int makVrv::DtUnicodeChar::wideStringLength

(

)

const [inline]

unsigned int makVrv::DtUnicodeChar::utf16Length

(

)

const [inline]

References myCodePoint.

unsigned int makVrv::DtUnicodeChar::utf32Length

(

)

const [inline]

static CodePoint makVrv::DtUnicodeChar::decodeSurrogatePair	(	Surrogate	hi,
		Surrogate	lo
	)		[inline, static]

References X.

Referenced by readUtf16().

static void makVrv::DtUnicodeChar::encodeSurrogatePair	(	CodePoint	cp,
		Surrogate &	hi,
		Surrogate &	lo
	)		[inline, static]

References LeadSurrogateMin, and TrailSurrogateMin.

Referenced by writeUtf16().

unsigned int makVrv::DtUnicodeChar::utf16CodeUnits

(

)

const [inline]

References myCodePoint.

unsigned int makVrv::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 makVrv::DtUnicodeChar::writeUtf16

(

Surrogate *

memory

)

const [inline]

References encodeSurrogatePair(), and myCodePoint.

void makVrv::DtUnicodeChar::readUtf32

(

const unsigned int *

memory

)

[inline]

References myCodePoint.

void makVrv::DtUnicodeChar::writeUtf32

(

unsigned int *

memory

)

const [inline]

References myCodePoint.

static unsigned int makVrv::DtUnicodeChar::utf8Length

(

const unsigned char

c

)

[inline, static]

Get the length based upon the first character.

unsigned int makVrv::DtUnicodeChar::readUtf8

(

const unsigned char *

memory

)

[inline]

References myCodePoint.

void makVrv::DtUnicodeChar::writeUtf8

(

char *

memory

)

const [inline]

References myCodePoint.

void makVrv::DtUnicodeChar::writeWCharT< 4 >

(

wchar_t *

memory

)

const [inline]

void makVrv::DtUnicodeChar::writeWChar

(

wchar_t *

memory

)

const [inline]

CodePoint makVrv::DtUnicodeChar::codePoint

(

)

const [inline]

References myCodePoint.

---

Member Data Documentation

const CodePoint makVrv::DtUnicodeChar::CodePointMax = 0x0010ffff [static]

Referenced by isCodePointValid().

const Surrogate makVrv::DtUnicodeChar::LeadSurrogateMin = 0xd800 [static]

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

const Surrogate makVrv::DtUnicodeChar::LeadSurrogateMax = 0xdbff [static]

const Surrogate makVrv::DtUnicodeChar::TrailSurrogateMin = 0xdc00 [static]

Referenced by encodeSurrogatePair(), and isSurrogateSubstringValid().

const Surrogate makVrv::DtUnicodeChar::TrailSurrogateMax = 0xdfff [static]

Referenced by isSurrogate().

CodePoint makVrv::DtUnicodeChar::myCodePoint [private]

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

---

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

• include/vrvUtil/DtUnicodeChar.h