makVrv::DtUnicode Class Reference

A unicode string. More...

List of all members.

Classes
struct	CodeUnitArray
	Internal structure used to store the code units. More...
Public Types
typedef unsigned short	CodeUnit
Public Member Functions
	DtUnicode ()
	CTOR creates an empty string.
	~DtUnicode ()
	DTOR may NOT deallocate memory as this string may share data.
	DtUnicode (size_t len, DtUnicodeChar c=DtUnicodeChar('\0'))
	CTOR create a string of n length filled with the unicode character c.
	DtUnicode (const DtUnicode &str)
	Copy ctor copies the string, this function will NOT allocate memory for the string, and thus it is fast to pass by value, and create many identical copies of a string.
DtUnicode &	operator= (const DtUnicode &str)
	Assignment operator copies the string, this function will NOT allocate memory for the string, and thus it is fast to pass by value, and create many identical copies of a string.
template<typename QStringType , typename QCoreApp >
QStringType	translate () const
	Utility function for translating a DtUnicode variable initialized using the static DtUnicode::tr function, and QLinguist.
void	setFromWCharArray (const wchar_t utf16[], int len=-1)
	Initialize via specifying encoding.
void	setFromUtf8 (const unsigned char *utf8, int len=-1)
	Set from an UTF-8 encoded string, the string MUST be zero terminated if the length is not passed.
void	setFromUtf8 (const std::string &utf8)
void	setFromLatin1 (const char *latin, int len=-1)
	Set from an UTF-8 encoded string, the string MUST be zero terminated if the length is not passed.
void	setFromUtf16 (const unsigned short *utf16, int len=-1)
	Set from an UTF-16 encoded string, the string MUST be zero terminated if the length is not passed.
void	setFromUtf32 (const unsigned int *utf32, int len=-1)
	Set from an UTF-32 encoded string, the string MUST be zero terminated if the length is not passed.
void	setFromAscii (const std::string &ascii)
	Set from an ascii string, the string MUST be zero terminated if the length is not passed.
void	setFromAscii (const char *ascii, int len=-1)
	Set from an ascii string, the string MUST be zero terminated if the length is not passed.
template<typename QStringType >
void	setFromQString (QStringType qstr)
	Template function for setting from Qt 4 style string.
void	toAscii (std::string &str) const
	Decode via specifying encoding.
std::string	toAscii () const
void	toLatin1 (std::string &str) const
	Encode to an Latin-1 string.
std::string	toLatin1 () const
void	toUtf8 (std::string &str) const
std::string	toUtf8 () const
void	toWideString (std::wstring &str) const
std::wstring	toWideString () const
template<typename QStringType >
QStringType	toQString () const
	Template function for outputting a Qt 4 style string.
template<typename QStringType >
void	toQString (QStringType &qstr) const
	Template function for initializing a Qt 4 style string.
DtUnicode &	operator+= (const DtUnicode &str)
	Append a string to the end.
DtUnicode &	operator+= (const DtUnicodeChar &x)
	Append a character to the end.
DtUnicode	operator+ (const DtUnicode &str) const
	Append two strings together.
bool	operator== (const DtUnicode &other) const
	Test if two strings are identical.
bool	operator!= (const DtUnicode &other) const
	Test if two strings are not identical.
bool	operator< (const DtUnicode &other) const
	Test if a string is less than another based on their first different character or the length.
size_t	length () const
	Get the length in Code Units.
size_t	sizeInBytes () const
	Get the size in 8bit bytes.
size_t	calculateCodePoints () const
	Calculate the number of Code Points.
const CodeUnit *	codeUnits () const
	Get an array of code units.
int	indexOf (const DtUnicodeChar &x, size_t pos=0) const
	Search for a character starting a pos, returns index, or -1 if not found.
int	indexOf (const DtUnicode &x, size_t pos=0) const
	Search for a string starting a pos, returns index, or -1 if not found.
DtUnicode	subString (size_t pos=0, int len=-1) const
	Create a substring starting at position, for n characters.
void	push_back (const DtUnicodeChar &x)
	Append a unicode character to the string.
void	resize (int size)
	Resize a string to a new size, if the size < 0 the string will be empty.
Static Public Member Functions
static DtUnicode	fromWCharArray (const wchar_t utf16[], int len=-1)
	Static create via specifying encoding.
static DtUnicode	fromWideString (const std::wstring &str)
	Set from a std::wstring.
static DtUnicode	fromUtf8 (const unsigned char *utf8, int len=-1)
	Create a unicode string from an UTF-16 encoded string, the string MUST be zero terminated if the length is not passed.
static DtUnicode	fromUtf8 (const std::string &utf8)
static DtUnicode	fromUtf16 (const unsigned short *utf16, int len=-1)
	Create a unicode string from an UTF-16 encoded string, the string MUST be zero terminated if the length is not passed.
static DtUnicode	fromUtf32 (const unsigned int *utf32, int len=-1)
	Create a unicode string from an UTF-32 encoded string, the string MUST be zero terminated if the length is not passed.
static DtUnicode	fromAscii (const std::string &ascii)
	Create a unicode string from an ascii string, the string MUST be zero terminated if the length is not passed.
static DtUnicode	fromAscii (const char *ascii, int len=-1)
	Create a unicode string from an ascii string, the string MUST be zero terminated if the length is not passed.
static DtUnicode	tr (const char *ascii)
	Ascii translation function, used to be compatible with Qt's translation tools.
template<typename QStringType >
static DtUnicode	fromQString (QStringType qstr)
	Template function for setting from Qt 4 style string.
Protected Types
enum	Encoding { Ascii, Latin1, Utf8 }
Protected Member Functions
	DtUnicode (const char *ascii, int len=-1, Encoding encoding=Ascii)
	DtUnicode (const unsigned short *utf16, int len=-1)
	DtUnicode (const unsigned int *utf32, int len=-1)
	DtUnicode (const std::string &ascii)
	DtUnicode (const DtUnicode &a, const DtUnicode &b)
Protected Attributes
CodeUnitArray	myCodeUnits

---

Detailed Description

A unicode string.

DtUnicode stores a UTF-16 encoded unicode string. Code Point, a Unicode character, UTF encodes a Code Point in 1 or 2 Code Units. Code Unit, a 16 bit word. Each character is 1 or 2 code units.

DtUnicode uses copy on write, thus creating copies and passing by value is cheap, however special care must be taken when passing between threads. DtUnicode reference counts are thread safe, however the content is not so thread synchronization is required when modifying strings.

---

Member Typedef Documentation

typedef unsigned short makVrv::DtUnicode::CodeUnit

---

Member Enumeration Documentation

enum makVrv::DtUnicode::Encoding [protected]

Enumerator:

Ascii
Latin1
Utf8

---

Constructor & Destructor Documentation

makVrv::DtUnicode::DtUnicode

(

)

[inline]

CTOR creates an empty string.

makVrv::DtUnicode::~DtUnicode

(

)

[inline]

DTOR may NOT deallocate memory as this string may share data.

makVrv::DtUnicode::DtUnicode	(	size_t	len,
		DtUnicodeChar	c = DtUnicodeChar('\0')
	)		[inline, explicit]

CTOR create a string of n length filled with the unicode character c.

makVrv::DtUnicode::DtUnicode

(

const DtUnicode &

str

)

[inline]

Copy ctor copies the string, this function will NOT allocate memory for the string, and thus it is fast to pass by value, and create many identical copies of a string.

makVrv::DtUnicode::DtUnicode	(	const char *	ascii,
		int	len = -1,
		Encoding	encoding = Ascii
	)		[inline, explicit, protected]

makVrv::DtUnicode::DtUnicode	(	const unsigned short *	utf16,
		int	len = -1
	)		[inline, explicit, protected]

makVrv::DtUnicode::DtUnicode	(	const unsigned int *	utf32,
		int	len = -1
	)		[inline, explicit, protected]

makVrv::DtUnicode::DtUnicode

(

const std::string &

ascii

)

[inline, explicit, protected]

makVrv::DtUnicode::DtUnicode	(	const DtUnicode &	a,
		const DtUnicode &	b
	)		[inline, explicit, protected]

---

Member Function Documentation

DtUnicode& makVrv::DtUnicode::operator=

(

const DtUnicode &

str

)

[inline]

Assignment operator copies the string, this function will NOT allocate memory for the string, and thus it is fast to pass by value, and create many identical copies of a string.

static DtUnicode makVrv::DtUnicode::fromWCharArray	(	const wchar_t	utf16[],
		int	len = -1
	)		[inline, static]

Static create via specifying encoding.

Set from a wchar_t array, compiler encoding specific, the string MUST be zero terminated if the length is not passed.

static DtUnicode makVrv::DtUnicode::fromWideString

(

const std::wstring &

str

)

[inline, static]

Set from a std::wstring.

static DtUnicode makVrv::DtUnicode::fromUtf8	(	const unsigned char *	utf8,
		int	len = -1
	)		[inline, static]

Create a unicode string from an UTF-16 encoded string, the string MUST be zero terminated if the length is not passed.

Referenced by makVrv::DtPageConfiguration::PageCollectionState::serialize().

static DtUnicode makVrv::DtUnicode::fromUtf8

(

const std::string &

utf8

)

[inline, static]

static DtUnicode makVrv::DtUnicode::fromUtf16	(	const unsigned short *	utf16,
		int	len = -1
	)		[inline, static]

Create a unicode string from an UTF-16 encoded string, the string MUST be zero terminated if the length is not passed.

Referenced by fromQString(), and toQString().

static DtUnicode makVrv::DtUnicode::fromUtf32	(	const unsigned int *	utf32,
		int	len = -1
	)		[inline, static]

Create a unicode string from an UTF-32 encoded string, the string MUST be zero terminated if the length is not passed.

static DtUnicode makVrv::DtUnicode::fromAscii

(

const std::string &

ascii

)

[inline, static]

Create a unicode string from an ascii string, the string MUST be zero terminated if the length is not passed.

Referenced by makVrf::DtRangeRingsSettingsRecord::ColorOption::serialize(), and tr().

static DtUnicode makVrv::DtUnicode::fromAscii	(	const char *	ascii,
		int	len = -1
	)		[inline, static]

Create a unicode string from an ascii string, the string MUST be zero terminated if the length is not passed.

static DtUnicode makVrv::DtUnicode::tr

(

const char *

ascii

)

[inline, static]

Ascii translation function, used to be compatible with Qt's translation tools.

This will simply call fromAscii. The name 'tr' is used by Qt's translation tools when scanning source code for translatable strings. This function should only take string literals aka "characters" and should never take pointer variables.

References fromAscii().

template<typename QStringType , typename QCoreApp >

QStringType makVrv::DtUnicode::translate

(

)

const [inline]

Utility function for translating a DtUnicode variable initialized using the static DtUnicode::tr function, and QLinguist.

References toUtf8().

template<typename QStringType >

static DtUnicode makVrv::DtUnicode::fromQString

(

QStringType

qstr

)

[inline, static]

Template function for setting from Qt 4 style string.

References fromUtf16().

void makVrv::DtUnicode::setFromWCharArray	(	const wchar_t	utf16[],
		int	len = -1
	)		[inline]

Initialize via specifying encoding.

Set from an wchar string, the string MUST be zero terminated if the length is not passed, the encoding of wchar arrays are different on each platform. Do NOT assume a wchar string is UTF16 or UTF32.

void makVrv::DtUnicode::setFromUtf8	(	const unsigned char *	utf8,
		int	len = -1
	)		[inline]

Set from an UTF-8 encoded string, the string MUST be zero terminated if the length is not passed.

void makVrv::DtUnicode::setFromUtf8

(

const std::string &

utf8

)

[inline]

void makVrv::DtUnicode::setFromLatin1	(	const char *	latin,
		int	len = -1
	)		[inline]

Set from an UTF-8 encoded string, the string MUST be zero terminated if the length is not passed.

void makVrv::DtUnicode::setFromUtf16	(	const unsigned short *	utf16,
		int	len = -1
	)		[inline]

Set from an UTF-16 encoded string, the string MUST be zero terminated if the length is not passed.

Referenced by setFromQString().

void makVrv::DtUnicode::setFromUtf32	(	const unsigned int *	utf32,
		int	len = -1
	)		[inline]

Set from an UTF-32 encoded string, the string MUST be zero terminated if the length is not passed.

void makVrv::DtUnicode::setFromAscii

(

const std::string &

ascii

)

[inline]

Set from an ascii string, the string MUST be zero terminated if the length is not passed.

void makVrv::DtUnicode::setFromAscii	(	const char *	ascii,
		int	len = -1
	)		[inline]

Set from an ascii string, the string MUST be zero terminated if the length is not passed.

template<typename QStringType >

void makVrv::DtUnicode::setFromQString

(

QStringType

qstr

)

[inline]

Template function for setting from Qt 4 style string.

References setFromUtf16().

void makVrv::DtUnicode::toAscii

(

std::string &

str

)

const [inline]

Decode via specifying encoding.

Encode to an ascii string. All non Ascii characters are skipped. Ascii is 0-127

Referenced by makVrf::DtRangeRingsSettingsRecord::ColorOption::serialize().

std::string makVrv::DtUnicode::toAscii

(

)

const [inline]

References toAscii().

Referenced by toAscii().

void makVrv::DtUnicode::toLatin1

(

std::string &

str

)

const [inline]

Encode to an Latin-1 string.

All non Latin-1 characters are skipped. Latin-1 is is 0-255

std::string makVrv::DtUnicode::toLatin1

(

)

const [inline]

References toLatin1().

Referenced by toLatin1().

void makVrv::DtUnicode::toUtf8

(

std::string &

str

)

const [inline]

std::string makVrv::DtUnicode::toUtf8

(

)

const [inline]

References toUtf8().

Referenced by toUtf8(), and translate().

void makVrv::DtUnicode::toWideString

(

std::wstring &

str

)

const [inline]

std::wstring makVrv::DtUnicode::toWideString

(

)

const [inline]

References toWideString().

Referenced by toWideString().

template<typename QStringType >

QStringType makVrv::DtUnicode::toQString

(

)

const [inline]

Template function for outputting a Qt 4 style string.

References codeUnits(), fromUtf16(), and length().

template<typename QStringType >

void makVrv::DtUnicode::toQString

(

QStringType &

qstr

)

const [inline]

Template function for initializing a Qt 4 style string.

References codeUnits(), and length().

DtUnicode& makVrv::DtUnicode::operator+=

(

const DtUnicode &

str

)

[inline]

Append a string to the end.

DtUnicode& makVrv::DtUnicode::operator+=

(

const DtUnicodeChar &

x

)

[inline]

Append a character to the end.

DtUnicode makVrv::DtUnicode::operator+

(

const DtUnicode &

str

)

const [inline]

Append two strings together.

bool makVrv::DtUnicode::operator==

(

const DtUnicode &

other

)

const [inline]

Test if two strings are identical.

bool makVrv::DtUnicode::operator!=

(

const DtUnicode &

other

)

const [inline]

Test if two strings are not identical.

bool makVrv::DtUnicode::operator<

(

const DtUnicode &

other

)

const [inline]

Test if a string is less than another based on their first different character or the length.

Used for sorting strings.

size_t makVrv::DtUnicode::length

(

)

const [inline]

Get the length in Code Units.

This is NOT the length in bytes, or the number of code points.

Referenced by makVrv::hash_value(), sizeInBytes(), and toQString().

size_t makVrv::DtUnicode::sizeInBytes

(

)

const [inline]

Get the size in 8bit bytes.

References length().

size_t makVrv::DtUnicode::calculateCodePoints

(

)

const [inline]

Calculate the number of Code Points.

const CodeUnit* makVrv::DtUnicode::codeUnits

(

)

const [inline]

Get an array of code units.

References makVrv::DtUnicode::CodeUnitArray::begin, and myCodeUnits.

Referenced by makVrv::hash_value(), and toQString().

int makVrv::DtUnicode::indexOf	(	const DtUnicodeChar &	x,
		size_t	pos = 0
	)		const [inline]

Search for a character starting a pos, returns index, or -1 if not found.

int makVrv::DtUnicode::indexOf	(	const DtUnicode &	x,
		size_t	pos = 0
	)		const [inline]

Search for a string starting a pos, returns index, or -1 if not found.

DtUnicode makVrv::DtUnicode::subString	(	size_t	pos = 0,
		int	len = -1
	)		const [inline]

Create a substring starting at position, for n characters.

If n is -1. for the remaining characters. if pos is out of range then a null string is returned.

void makVrv::DtUnicode::push_back

(

const DtUnicodeChar &

x

)

[inline]

Append a unicode character to the string.

void makVrv::DtUnicode::resize

(

int

size

)

[inline]

Resize a string to a new size, if the size < 0 the string will be empty.

If size is greater than the current size, the string is extended to make it size characters long with the extra characters added to the end. The new characters are uninitialized. If size is less than the current size, characters are removed from the end. If the size is less than 0, the string will be resized to 0 without deallocating if possible.

---

Member Data Documentation

CodeUnitArray makVrv::DtUnicode::myCodeUnits [protected]

Referenced by codeUnits().

---

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

• include/vrvUtil/DtUnicode.h