A unicode string. More...

Inheritance diagram for DtUcString:

Collaboration diagram for DtUcString:

Classes
struct	CodeUnitArray
	Internal structure used to store the code units. More...

Public Types
typedef unsigned short	CodeUnit

Public Member Functions
	DtUcString ()
	CTOR creates an empty string. More...

	DtUcString (size_t len, DtUnicodeChar c=DtUnicodeChar('\0'))
	CTOR create a string of n length filled with the unicode character c. More...

	DtUcString (const DtUcString &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. More...

	~DtUcString ()
	DTOR may NOT deallocate memory as this string may share data. More...

DtUcString &	operator= (const DtUcString &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. More...

template<typename QStringType , typename QCoreApp >
QStringType	translate () const
	Utility function for translating a DtUcString variable initialized using the static DtUcString::tr function, and QLinguist. More...

void	setFromWCharArray (const wchar_t utf16[], int len=-1)
	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. More...

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. More...

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. More...

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. More...

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. More...

void	setFromAscii (const std::string &ascii)
	Set from an ascii string, the string MUST be zero terminated if the length is not passed. More...

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. More...

template<typename QStringType >
void	setFromQString (QStringType qstr)
	Template function for setting from Qt 4 style string. More...

void	toAscii (std::string &str) const
	Encode to an ascii string. More...

std::string	toAscii () const

void	toLatin1 (std::string &str) const
	Encode to an Latin-1 string. More...

std::string	toLatin1 () const

void	toUtf8 (std::string &str) const
	Encode to a UTF-8 string. More...

std::string	toUtf8 () const

void	toWideString (std::wstring &str) const
	Encode to a wstring. More...

std::wstring	toWideString () const

template<typename QStringType >
QStringType	toQString () const
	Template function for outputting a Qt 4 style string. More...

template<typename QStringType >
void	toQString (QStringType &qstr) const
	Template function for initializing a Qt 4 style string. More...

DtUcString &	operator+= (const DtUcString &str)
	Append a string to the end. More...

DtUcString &	operator+= (const DtUnicodeChar &x)
	Append a character to the end. More...

DtUcString	operator+ (const DtUcString &str) const
	Append two strings together. More...

bool	operator== (const DtUcString &other) const
	Test if two strings are identical. More...

bool	operator!= (const DtUcString &other) const
	Test if two strings are not identical. More...

bool	operator< (const DtUcString &other) const
	Test if a string is less than another based on their first different character or the length. More...

size_t	length () const
	Get the length in Code Units. More...

size_t	sizeInBytes () const
	Get the size in 8bit bytes. More...

size_t	calculateCodePoints () const
	Calculate the number of Code Points. More...

const CodeUnit *	codeUnits () const
	Get an array of code units. More...

int	indexOf (const DtUnicodeChar &x, size_t pos=0) const
	Search for a character starting a pos, returns index, or -1 if not found. More...

int	indexOf (const DtUcString &x, size_t pos=0) const
	Search for a string starting a pos, returns index, or -1 if not found. More...

int	lastIndexOf (const DtUnicodeChar &x, size_t pos=0) const
	Search for a character starting a pos, returns index, or -1 if not found. More...

int	lastIndexOf (const DtUcString &x, size_t pos=0) const
	Search for a string starting a pos, returns index, or -1 if not found. More...

DtUcString	subString (size_t pos=0, int len=-1) const
	Create a substring starting at position, for n characters. More...

void	push_back (const DtUnicodeChar &x)
	Append a unicode character to the string. More...

void	resize (int size)
	Resize a string to a new size, if the size < 0 the string will be empty. More...


virtual bool	snipFront (const char ch, bool toLastCh=false)
	Truncates everything before or after the character, including the character, respectively. More...

virtual bool	snipBack (const char ch, bool fromFirstCh=false)
	Truncates everything before or after the character, including the character, respectively. More...

Static Public Member Functions
static DtUcString	fromWCharArray (const wchar_t utf16[], int len=-1)
	Set from a wchar_t array, compiler encoding specific, the string MUST be zero terminated if the length is not passed. More...

static DtUcString	fromWideString (const std::wstring &str)
	Set from a std::wstring. More...

static DtUcString	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. More...

static DtUcString	fromUtf8 (const std::string &utf8)

static DtUcString	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. More...

static DtUcString	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. More...

static DtUcString	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. More...

static DtUcString	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. More...

static DtUcString	tr (const char *ascii)
	Ascii translation function, used to be compatible with Qt's translation tools. More...

template<typename QStringType >
static DtUcString	fromQString (QStringType qstr)
	Template function for setting from Qt 4 style string. More...

Protected Types
enum	Encoding { Ascii, Latin1, Utf8 }

Protected Member Functions
	DtUcString (const char *ascii, int len=-1, Encoding encoding=Ascii)

	DtUcString (const unsigned short *utf16, int len=-1)

	DtUcString (const unsigned int *utf32, int len=-1)

	DtUcString (const std::string &ascii)

	DtUcString (const DtUcString &a, const DtUcString &b)

Protected Attributes
CodeUnitArray	myCodeUnits

Detailed Description

A unicode string.

DtUcString 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.

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

Member Typedef Documentation

typedef unsigned short DtUcString::CodeUnit

Member Enumeration Documentation

enum DtUcString::Encoding

protected

Enumerator
Ascii
Latin1
Utf8

Constructor & Destructor Documentation

DtUcString::DtUcString ( )

inline

CTOR creates an empty string.

DtUcString::DtUcString	(	size_t	len,
		DtUnicodeChar	c = `DtUnicodeChar('\0')`
	)

inlineexplicit

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

DtUcString::DtUcString ( const DtUcString & 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.

DtUcString::~DtUcString ( )

inline

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

DtUcString::DtUcString	(	const char *	ascii,
		int	len = `-1`,
		Encoding	encoding = `Ascii`
	)

inlineexplicitprotected

DtUcString::DtUcString	(	const unsigned short *	utf16,
		int	len = `-1`
	)

inlineexplicitprotected

DtUcString::DtUcString	(	const unsigned int *	utf32,
		int	len = `-1`
	)

inlineexplicitprotected

DtUcString::DtUcString ( const std::string & ascii )

inlineexplicitprotected

DtUcString::DtUcString	(	const DtUcString &	a,
		const DtUcString &	b
	)

inlineexplicitprotected

Member Function Documentation

size_t DtUcString::calculateCodePoints ( ) const

inline

Calculate the number of Code Points.

const CodeUnit* DtUcString::codeUnits ( ) const

inline

Get an array of code units.

Referenced by hash_value().

static DtUcString DtUcString::fromAscii ( const std::string & ascii )

inlinestatic

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

static DtUcString DtUcString::fromAscii	(	const char *	ascii,
		int	len = `-1`
	)

inlinestatic

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

template<typename QStringType >

static DtUcString DtUcString::fromQString ( QStringType qstr )

inlinestatic

Template function for setting from Qt 4 style string.

static DtUcString DtUcString::fromUtf16	(	const unsigned short *	utf16,
		int	len = `-1`
	)

inlinestatic

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

static DtUcString DtUcString::fromUtf32	(	const unsigned int *	utf32,
		int	len = `-1`
	)

inlinestatic

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

static DtUcString DtUcString::fromUtf8	(	const unsigned char *	utf8,
		int	len = `-1`
	)

inlinestatic

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

static DtUcString DtUcString::fromUtf8 ( const std::string & utf8 )

inlinestatic

static DtUcString DtUcString::fromWCharArray	(	const wchar_t	utf16[],
		int	len = `-1`
	)

inlinestatic

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

static DtUcString DtUcString::fromWideString ( const std::wstring & str )

inlinestatic

Set from a std::wstring.

int DtUcString::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 DtUcString::indexOf	(	const DtUcString &	x,
		size_t	pos = `0`
	)		const

inline

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

int DtUcString::lastIndexOf	(	const DtUnicodeChar &	x,
		size_t	pos = `0`
	)		const

inline

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

int DtUcString::lastIndexOf	(	const DtUcString &	x,
		size_t	pos = `0`
	)		const

inline

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

size_t DtUcString::length ( ) const

inline

Get the length in Code Units.

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

Referenced by hash_value().

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

inline

Test if two strings are not identical.

DtUcString DtUcString::operator+ ( const DtUcString & str ) const

inline

Append two strings together.

DtUcString& DtUcString::operator+= ( const DtUcString & str )

inline

Append a string to the end.

DtUcString& DtUcString::operator+= ( const DtUnicodeChar & x )

inline

Append a character to the end.

bool DtUcString::operator< ( const DtUcString & other ) const

inline

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

Used for sorting strings.

DtUcString& DtUcString::operator= ( const DtUcString & 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.

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

inline

Test if two strings are identical.

void DtUcString::push_back ( const DtUnicodeChar & x )

inline

Append a unicode character to the string.

void DtUcString::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.

void DtUcString::setFromAscii ( const std::string & ascii )

inline

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

void DtUcString::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.

void DtUcString::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.

template<typename QStringType >

void DtUcString::setFromQString ( QStringType qstr )

inline

Template function for setting from Qt 4 style string.

void DtUcString::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.

void DtUcString::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 DtUcString::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 DtUcString::setFromUtf8 ( const std::string & utf8 )

inline

void DtUcString::setFromWCharArray	(	const wchar_t	utf16[],
		int	len = `-1`
	)

inline

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.

size_t DtUcString::sizeInBytes ( ) const

inline

Get the size in 8bit bytes.

virtual bool DtUcString::snipBack	(	const char	ch,
		bool	fromFirstCh = `false`
	)

virtual

Truncates everything before or after the character, including the character, respectively.

Normally, snipFront stops at the first occurrence of "ch", and snipBack stops at the last occurrence of "ch". The second argument flags reverse this. Return value is true if "ch" was found in the string. Does not include the null terminator (only searches characters counted by size).

virtual bool DtUcString::snipFront	(	const char	ch,
		bool	toLastCh = `false`
	)

virtual

Truncates everything before or after the character, including the character, respectively.

Normally, snipFront stops at the first occurrence of "ch", and snipBack stops at the last occurrence of "ch". The second argument flags reverse this. Return value is true if "ch" was found in the string. Does not include the null terminator (only searches characters counted by size).

DtUcString DtUcString::subString	(	size_t	pos = `0`,
		int	len = `-1`
	)		const

inline

Create a substring starting at position, for n characters.

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

void DtUcString::toAscii ( std::string & str ) const

inline

Encode to an ascii string.

All non Ascii characters are skipped. Ascii is 0-127

std::string DtUcString::toAscii ( ) const

inline

void DtUcString::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 DtUcString::toLatin1 ( ) const

inline

template<typename QStringType >

QStringType DtUcString::toQString ( ) const

inline

Template function for outputting a Qt 4 style string.

template<typename QStringType >

void DtUcString::toQString ( QStringType & qstr ) const

inline

Template function for initializing a Qt 4 style string.

void DtUcString::toUtf8 ( std::string & str ) const

inline

Encode to a UTF-8 string.

std::string DtUcString::toUtf8 ( ) const

inline

void DtUcString::toWideString ( std::wstring & str ) const

inline

Encode to a wstring.

std::wstring DtUcString::toWideString ( ) const

inline

static DtUcString DtUcString::tr ( const char * ascii )

inlinestatic

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.

template<typename QStringType , typename QCoreApp >

QStringType DtUcString::translate ( ) const

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

Member Data Documentation

CodeUnitArray DtUcString::myCodeUnits

protected

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

vlUnicode.h

Classes

Public Types

Public Member Functions

Static Public Member Functions

Protected Types

Protected Member Functions

Protected Attributes

Detailed Description

Member Typedef Documentation

Member Enumeration Documentation

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation