Char Class Reference

Represents a single Unicode character. More...

#include <maxchar.h>

Inheritance diagram for Char:

Public Member Functions
	Char ()
	Char (char)
	Create a character with a single-byte Active Code Page character. More...
	Char (wchar_t)
	Create a character with a single-WCHAR UTF16 character. More...
	Char (const MaxString &)
	Char (const wchar_t *)
	Char (const char *)
	Char (unsigned int code_page, const char *)
	Char (unsigned int ch)
	Create a character using a UCS4 character. More...
MaxString	ToMaxString () const
	Convert this character to a MaxString. More...
size_t	ToUTF16 (wchar_t *string, size_t length) const
	Convert this character to UTF16. More...
size_t	ToACP (char *string, size_t length) const
	Convert this character to the active code page. More...
size_t	ToCP (unsigned int cp, char *string, size_t length) const
	Convert this character to the specified code page. More...
size_t	ToMCHAR (MCHAR *s, size_t length) const
	Convert this character to an MCHAR (Active Code Page or UTF16). More...
bool	operator== (char) const
	Compare this character to an active code page character. More...
bool	operator== (wchar_t) const
	Compare this character to a UTF16 character. More...
bool	operator== (const Char &) const
	Compare this character to a UTF16 character. More...
bool	operator!= (char c) const
	Not equal operator for an active code page character. More...
bool	operator!= (wchar_t c) const
	Not equal operator for a UTF16 character. More...
bool	operator!= (const Char &c) const
	Not equal operator for a UTF16 character. More...
Char &	operator= (wchar_t)
	Assignment operator for a UTF16 character. More...
Char &	operator= (char)
	Assignment operator for an active code page character. More...
Char &	operator= (const MaxString &)
	Assignment operator for a MaxString. More...
Char &	operator= (const wchar_t *)
	Assignment operator for a constant UTF16 character. More...
Char &	operator= (const char *)
	Assignment operator for a constant active code page character. More...
Char &	Set (unsigned int cp, const char *string)
	Change this character to represents the first character of the string specified, based on the code page specified. More...
bool	IsNull () const
	Returns true if this character represents a NULL character. More...
bool	IsValid () const
	Returns true if this character represents a non-NULL character. More...
unsigned int	CharCode () const
	Returns the character as UTF32. More...
bool	IsSpace () const
bool	IsDigit () const
bool	IsAlpha () const
bool	IsAlphaNumeric () const
bool	IsPunctuation () const
bool	IsUnicode () const
Char	ToUpper () const
Char	ToLower () const
MCHAR *	IsInCharacterSet (const MCHAR *) const
	Determine if this character is found inside a particular character set. More...

Static Public Member Functions
static bool	IsValidUTF8 (const void *data, size_t len, bool *pFoundExtendedChar=0, size_t *pPartialCharAtEnd=0)
	Determine if the UTF-8 string is valid. More...
static unsigned int	UTF8CharLength (unsigned char character)
	Determine the length of an UTF-8 character. More...
static bool	IsUTF16LeadChar (wchar_t character)
	Determine if the UTF-16 char is a lead character. More...
Static Public Member Functions inherited from MaxHeapOperators
static UtilExport void *	operator new (size_t size)
	Standard new operator used to allocate objects If there is insufficient memory, an exception will be thrown. More...
static UtilExport void *	operator new (size_t size, const std::nothrow_t &e)
	Standard new operator used to allocate objects if there is insufficient memory, NULL will be returned. More...
static UtilExport void *	operator new (size_t size, const char *filename, int line)
	New operator used to allocate objects that takes the filename and line number where the new was called If there is insufficient memory, an exception will be thrown. More...
static UtilExport void *	operator new (size_t size, int block_type, const char *filename, int line)
	New operator used to allocate objects that takes the type of memory, filename and line number where the new was called If there is insufficient memory, an exception will be thrown. More...
static UtilExport void *	operator new (size_t size, const std::nothrow_t &e, const char *filename, int line)
	New operator used to allocate objects that takes the filename and line number where the new was called If there is insufficient memory, NULL will be returned. More...
static UtilExport void *	operator new (size_t size, unsigned long flags)
	New operator used to allocate objects that takes extra flags to specify special operations If there is insufficient memory, an exception will be thrown. More...
static UtilExport void *	operator new (size_t size, const std::nothrow_t &e, unsigned long flags)
	New operator used to allocate objects that takes extra flags to specify special operations If there is insufficient memory, NULL will be returned. More...
static UtilExport void *	operator new[] (size_t size)
	New operator used to allocate arrays of objects If there is insufficient memory, an exception will be thrown. More...
static UtilExport void *	operator new[] (size_t size, const std::nothrow_t &e)
	New operator used to allocate arrays of objects If there is insufficient memory, NULL will be returned. More...
static UtilExport void *	operator new[] (size_t size, const char *filename, int line)
	New operator used to allocate arrays of objects If there is insufficient memory, an exception will be thrown. More...
static UtilExport void *	operator new[] (size_t size, int block_type, const char *filename, int line)
	New operator used to allocate arrays of objects. More...
static UtilExport void *	operator new[] (size_t size, const std::nothrow_t &e, const char *filename, int line)
	New operator used to allocate arrays of objects If there is insufficient memory, NULL will be returned. More...
static UtilExport void *	operator new[] (size_t size, unsigned long flags)
	New operator used to allocate arrays of objects If there is insufficient memory, an exception will be thrown. More...
static UtilExport void *	operator new[] (size_t size, const std::nothrow_t &e, unsigned long flags)
	New operator used to allocate arrays of objects If there is insufficient memory, NULL will be returned. More...
static UtilExport void	operator delete (void *ptr)
	Standard delete operator used to deallocate an object If the pointer is invalid, an exception will be thrown. More...
static UtilExport void	operator delete (void *ptr, const std::nothrow_t &e)
	Standard delete operator used to deallocate an object If the pointer is invalid, nothing will happen. More...
static UtilExport void	operator delete (void *ptr, const char *filename, int line)
	Delete operator used to deallocate an object that takes the filename and line number where the delete was called If the pointer is invalid, an exception will be thrown. More...
static UtilExport void	operator delete (void *ptr, int block_type, const char *filename, int line)
	Delete operator used to deallocate an object that takes the type of memory, filename and line number where the delete was called If the pointer is invalid, an exception will be thrown. More...
static UtilExport void	operator delete (void *ptr, const std::nothrow_t &e, const char *filename, int line)
	Delete operator used to deallocate an object that takes the filename and line number where the delete was called If the pointer is invalid, nothing will happen. More...
static UtilExport void	operator delete (void *ptr, unsigned long flags)
	Delete operator used to deallocate an object that takes extra flags to specify special operations If the pointer is invalid, an exception will be thrown. More...
static UtilExport void	operator delete (void *ptr, const std::nothrow_t &e, unsigned long flags)
	Delete operator used to deallocate an object that takes extra flags to specify special operations If the pointer is invalid, nothing will happen. More...
static UtilExport void	operator delete[] (void *ptr)
	Standard delete operator used to deallocate an array of objects If the pointer is invalid, an exception will be thrown. More...
static UtilExport void	operator delete[] (void *ptr, const std::nothrow_t &e)
	Standard delete operator used to deallocate an array of objects If the pointer is invalid, nothing will happen. More...
static UtilExport void	operator delete[] (void *ptr, const char *filename, int line)
	Delete operator used to deallocate an array of objects that takes the filename and line number where the delete was called If the pointer is invalid, an exception will be thrown. More...
static UtilExport void	operator delete[] (void *ptr, int block_type, const char *filename, int line)
	Delete operator used to deallocate an array of objects that takes the type of memory, filename and line number where the delete was called If the pointer is invalid, an exception will be thrown. More...
static UtilExport void	operator delete[] (void *ptr, const std::nothrow_t &e, const char *filename, int line)
	Delete operator used to deallocate an array of objects that takes the filename and line number where the delete was called If the pointer is invalid, nothing will happen. More...
static UtilExport void	operator delete[] (void *ptr, unsigned long flags)
	Delete operator used to deallocate an array of objects that takes extra flags to specify special operations If the pointer is invalid, an exception will be thrown. More...
static UtilExport void	operator delete[] (void *ptr, const std::nothrow_t &e, unsigned long flags)
	Delete operator used to deallocate an array of objects that takes extra flags to specify special operations If the pointer is invalid, an exception will be thrown. More...
static UtilExport void *	operator new (size_t size, void *placement_ptr)
	Placement new operator. More...
static UtilExport void	operator delete (void *ptr, void *placement_ptr)
	Placement delete operator. More...
static UtilExport void *	aligned_malloc (size_t size, size_t alignment)
	Allocates memory on a specified alignment boundary. More...
static UtilExport void *	aligned_realloc (void *ptr, size_t size, size_t alignment)
	Reallocates memory on a specified alignment boundary. More...
static UtilExport void	aligned_free (void *ptr)
	Frees a block of memory that was allocated with aligned_malloc/aligned_realloc. More...

Protected Attributes
unsigned int	_ch

Detailed Description

Represents a single Unicode character.

The main advantage of this class is the ability of representing them without allocating external memory.

This class was designed to be able to cast "unsigned int*" array to a "Char*" array. This class doesn't have any destructor or virtual functions.

Constructor & Destructor Documentation

Char() [1/8]

Char

(

)

Char() [2/8]

Char

(

char

)

Create a character with a single-byte Active Code Page character.

This constructor is best used with a compile-time constant because if you specify a only the first half of a DBCS character this function will throw an exception.

Char() [3/8]

Char

(

wchar_t

)

Create a character with a single-WCHAR UTF16 character.

This constructor is best used with a compile-time constant because if you specify a only the first half of a UTF16 character this function will throw an exception.

Char() [4/8]

Char

(

const MaxString &

)

Char() [5/8]

Char

(

const wchar_t *

)

Char() [6/8]

Char

(

const char *

)

Char() [7/8]

Char	(	unsigned int	code_page,
		const char *
	)

Char() [8/8]

Char ( unsigned int  ch )

explicit

Create a character using a UCS4 character.

We specified "explicit" because "unsigned int" are so generic that we didn't want to construct a "Char" implicitly by mistake.

Member Function Documentation

ToMaxString()

MaxString ToMaxString

(

)

const

Convert this character to a MaxString.

ToUTF16()

size_t ToUTF16	(	wchar_t *	string,
		size_t	length
	)		const

Convert this character to UTF16.

Parameters

string	string buffer to put the converted characters
length	the buffer size of param string in number characters

Returns

number of characters converted.

ToACP()

size_t ToACP	(	char *	string,
		size_t	length
	)		const

Convert this character to the active code page.

Parameters

string	- string buffer to put the converted characters
length	- the buffer size of param string in number characters

Returns

- number of characters converted.

ToCP()

size_t ToCP	(	unsigned int	cp,
		char *	string,
		size_t	length
	)		const

Convert this character to the specified code page.

Parameters

cp	The specified code page
string	string buffer to put the converted characters
length	the buffer size of param string in number characters

Returns

number of characters converted.

ToMCHAR()

size_t ToMCHAR ( MCHAR *  s, size_t  length  ) const

inline

Convert this character to an MCHAR (Active Code Page or UTF16).

Parameters

s	string buffer to put the converted characters
length	the buffer size of param s in number characters

Returns

number of characters converted.

{ return ToUTF16(s, length); };

operator==() [1/3]

bool operator==

(

char

)

const

Compare this character to an active code page character.

operator==() [2/3]

bool operator==

(

wchar_t

)

const

Compare this character to a UTF16 character.

operator==() [3/3]

bool operator==

(

const Char &

)

const

Compare this character to a UTF16 character.

operator!=() [1/3]

bool operator!= ( char  c ) const

inline

Not equal operator for an active code page character.

{ return !(*this == c); }

operator!=() [2/3]

bool operator!= ( wchar_t  c ) const

inline

Not equal operator for a UTF16 character.

{ return !(*this == c); }

operator!=() [3/3]

bool operator!= ( const Char &  c ) const

inline

Not equal operator for a UTF16 character.

{ return !(*this == c); }

operator=() [1/5]

Char& operator=

(

wchar_t

)

Assignment operator for a UTF16 character.

operator=() [2/5]

Char& operator=

(

char

)

Assignment operator for an active code page character.

operator=() [3/5]

Char& operator=

(

const MaxString &

)

Assignment operator for a MaxString.

operator=() [4/5]

Char& operator=

(

const wchar_t *

)

Assignment operator for a constant UTF16 character.

operator=() [5/5]

Char& operator=

(

const char *

)

Assignment operator for a constant active code page character.

Set()

Char& Set	(	unsigned int	cp,
		const char *	string
	)

Change this character to represents the first character of the string specified, based on the code page specified.

Parameters

cp	- The specified code page
string	- The string to use as a copy source

IsNull()

bool IsNull ( ) const

inline

Returns true if this character represents a NULL character.

{ return _ch == 0; }

IsValid()

bool IsValid ( ) const

inline

Returns true if this character represents a non-NULL character.

{ return _ch != 0; }

CharCode()

unsigned int CharCode ( ) const

inline

Returns the character as UTF32.

{ return _ch; }

IsSpace()

bool IsSpace

(

)

const

IsDigit()

bool IsDigit

(

)

const

IsAlpha()

bool IsAlpha

(

)

const

IsAlphaNumeric()

bool IsAlphaNumeric

(

)

const

IsPunctuation()

bool IsPunctuation

(

)

const

IsUnicode()

bool IsUnicode ( ) const

inline

{ return _ch > 0x7e; }

ToUpper()

Char ToUpper

(

)

const

ToLower()

Char ToLower

(

)

const

IsValidUTF8()

static bool IsValidUTF8 ( const void *  data, size_t  len, bool *  pFoundExtendedChar = 0, size_t *  pPartialCharAtEnd = 0  )

static

Determine if the UTF-8 string is valid.

Parameters

data	Buffer pointer to validate encoding of
len	Size of the buffer to validate
pFoundExtendedChar	If not null, returns if the presence of multi-bytes character was found.
pPartialCharAtEnd	If not null, returns if the number of bytes missing for the last character. The beginning was correct, but it missed the ending.

Returns

True if the string is a valid UTF8, False otherwise

UTF8CharLength()

static unsigned int UTF8CharLength ( unsigned char  character )

static

Determine the length of an UTF-8 character.

Parameters

character

UTF-8 character to get the length of

Returns

length of the character in bytes.

IsUTF16LeadChar()

static bool IsUTF16LeadChar ( wchar_t  character )

static

Determine if the UTF-16 char is a lead character.

In some situation, UTF-16 can be stored on four bytes instead of two.

Parameters

character

Character to test

Returns

True if the character is a lead character, False otherwise

IsInCharacterSet()

MCHAR* IsInCharacterSet

(

const MCHAR *

)

const

Determine if this character is found inside a particular character set.

This function slightly differs from strrchr or wcsrchr, because it can search DBCS or UTF16 character accurately inside a string without partially matching it.

Member Data Documentation

_ch

unsigned int _ch

protected