UTF8Str Class Reference

Search for all occurrences

#include <strclass.h>

Inheritance diagram for UTF8Str:

---

Class Description

See also:

Class CStr, WStr and MaxString, Character Strings.

Description:

A UTF8 encoded character string class. This class uses UTF8 encode to hold each character. This UTF8Str class provide very basic functionality Methods and operators are provided for calculating lengths, concatenation, case conversion, comparison.

Note:

The memory occupied by a UTF8Str object is cannot be larger than 2Gb.

Public Member Functions
	UTF8Str ()
	UTF8Str (const char *cs)
	UTF8Str (const UTF8Str &ws)
	UTF8Str (const MaxSDK::Util::MaxString &ws)
	UTF8Str (const MaxSDK::Util::MaxStringCastUTF8 &)
	~UTF8Str ()
char *	dataForWrite (size_t nchars=(size_t)-1)
const char *	data () const
	operator const char * () const
void	Resize (int nchars)
int	Length () const
int	length () const
int	ByteCount () const
int	LanguageCharacterCount () const
size_t	AllocatedChars () const
bool	isNull () const
UTF8Str &	operator= (const UTF8Str &cs)
UTF8Str &	operator= (const MaxSDK::Util::MaxString &mstr)
UTF8Str &	operator= (const MaxSDK::Util::MaxStringCastUTF8 &)
UTF8Str &	operator= (const char *cs)
UTF8Str	operator+ (const UTF8Str &cs) const
UTF8Str &	operator+= (const UTF8Str &cs)
UTF8Str &	Append (const UTF8Str &cs)
UTF8Str &	append (const UTF8Str &cs)
UTF8Str	MultiByteCharacterSubString (int firstCharacterIndex, int numberOfMBCharacters) const
int	FindMultiByteCharacterFirstByteIndex (int characterIndex) const
int	FindMultiByteCharacterLastByteIndex (int characterIndex) const
bool	operator== (const UTF8Str &cs) const
bool	operator!= (const UTF8Str &cs) const
bool	operator< (const UTF8Str &cs) const
bool	operator<= (const UTF8Str &ws) const
bool	operator> (const UTF8Str &ws) const
bool	operator>= (const UTF8Str &ws) const
void	toUpper ()
void	toLower ()
int	printf (const char *format,...)
	Write a formatted string into this UTF8Str.
int	vprintf (const char *format, va_list args)
	Write a formatted string into this UTF8Str.
wchar_t *	ToBSTR () const
MaxSDK::Util::MaxStringCastCP	ToCP (UINT cp, size_t *length=NULL) const
MaxSDK::Util::MaxStringCast< char >	ToACP (size_t *length=NULL) const
MaxSDK::Util::MaxStringCastUTF8	ToUTF8 (size_t *length=NULL) const
MaxSDK::Util::MaxStringCast < WCHAR >	ToOLESTR (size_t *length=NULL) const
MaxSDK::Util::MaxStringCast < WCHAR >	ToUTF16 (size_t *length=NULL) const
MaxSDK::Util::MaxStringCast < unsigned int >	ToUTF32 (size_t *length=NULL) const
MaxSDK::Util::MaxString	ToMaxString () const
void	ToMaxString (MaxSDK::Util::MaxString &) const
UTF8Str	ToUTF8Str () const
WStr	ToWStr () const
MaxSDK::Util::MaxStringCast< char >	ToMCHAR (size_t *length=NULL) const
UTF8Str	ToMSTR () const
bool	EndsWith (const UTF8Str &s, bool caseSensitive=true)
	Returns true if the string ends with s; otherwise returns false.
bool	StartsWith (const UTF8Str &s, bool caseSensitive=true)
	Returns true if the string starts with s; otherwise returns false.
size_t	NumberOfLines () const
	Returns the number of lines inside a string.
Static Public Member Functions
static UTF8Str	FromBSTR (const wchar_t *string, size_t length=(size_t)-1)
static UTF8Str	FromCP (UINT cp, const char *string, size_t length=(size_t)-1)
static UTF8Str	FromACP (const char *string, size_t length=(size_t)-1)
static UTF8Str	FromUTF8 (const char *string, size_t length=(size_t)-1)
static UTF8Str	FromOLESTR (const wchar_t *string, size_t length=(size_t)-1)
static UTF8Str	FromUTF16 (const wchar_t *string, size_t length=(size_t)-1)
static UTF8Str	FromUTF32 (const unsigned int *string, size_t length=(size_t)-1)
static UTF8Str	FromMaxString (MaxSDK::Util::MaxString &string)
static UTF8Str	FromUTF8Str (const UTF8Str &string)
static UTF8Str	FromWStr (const WStr &string)
static UTF8Str	FromMCHAR (const char *string, size_t length=(size_t)-1)
static UTF8Str	FromMSTR (const UTF8Str &string)

---

Constructor & Destructor Documentation

UTF8Str

(

)

Remarks:

Constructor. The string is set to NULL.

UTF8Str

(

const char *

cs

)

Remarks:

Constructor. The string is initialized to the string passed.

UTF8Str

(

const UTF8Str &

ws

)

Remarks:

Constructor. The string is initialized to the string passed.

UTF8Str

(

const MaxSDK::Util::MaxString &

ws

)

Remarks:

Constructor. The string is initialized to the string passed.

UTF8Str

(

const MaxSDK::Util::MaxStringCastUTF8 &

)

Remarks:

Constructor. The string is initialized to the string passed.

~UTF8Str

(

)

Remarks:

Destructor. The string is deleted.

---

Member Function Documentation

char* dataForWrite

(

size_t

nchars = (size_t)-1

)

Search for all occurrences

Remarks:

Returns a pointer to this string. But the returned string can be modified safely up to nchars.

const char* data

(

)

const

Search for all occurrences

Remarks:

Returns a const pointer to the string. If the string is NULL, a pointer to 0 is returned.

operator const char *

(

)

const

Remarks:

Returns a const pointer to the string. If the string is NULL, a pointer to 0 is returned.

void Resize

(

int

nchars

)

Search for all occurrences

Remarks:

Reallocates the string to contain nchars characters. If the string is enlarged it is padded with blanks.

Parameters:

int nchars

Specifies the new number of characters for the string.

int Length

(

)

const [inline]

Search for all occurrences

Remarks:

Returns the number of chars used to store the string in memory, including spaces, but excluding the terminating NULL character.

{ return ByteCount(); }

int length

(

)

const [inline]

Search for all occurrences

Remarks:

Returns the number of chars used to store the string in memory, including spaces, but excluding the terminating NULL character.

{ return Length(); }

int ByteCount

(

)

const

Search for all occurrences

Remarks:

Returns the number of bytes used to store the string in memory, including spaces, but excluding the terminating NULL character.

int LanguageCharacterCount

(

)

const

Search for all occurrences

Remarks:

Returns the number of natural language characters the string is represented on, including spaces, but excluding the terminal NULL character. This may be equal or less than the amount of bytes used to store the string in memory. For example, a chinese character might take up to 4 bytes. Length() or ByteCount() will count the character as up to 4 distinct chars. LanguageCharacterCount() will count it as a single char.

size_t AllocatedChars

(

)

const

Search for all occurrences

Remarks:

Returns the total number of char allocated to store the string. Including the NULL character and any unused char.

bool isNull

(

)

const [inline]

Search for all occurrences

Remarks:

Returns TRUE if the string length is 0; otherwise FALSE.

{ return data()[0]==0; }

UTF8Str& operator=

(

const UTF8Str &

cs

)

Remarks:

Assignment operator.

UTF8Str& operator=

(

const MaxSDK::Util::MaxString &

mstr

)

Remarks:

Assignment operator.

UTF8Str& operator=

(

const MaxSDK::Util::MaxStringCastUTF8 &

)

Remarks:

Assignment operator.

UTF8Str& operator=

(

const char *

cs

)

Remarks:

Assignment operator. In release 3.0 and later this method check for self-assignment.

UTF8Str operator+

(

const UTF8Str &

cs

)

const

Remarks:

Concatenation operator. Returns a new string that is this string with string cs appended.

UTF8Str& operator+=

(

const UTF8Str &

cs

)

Remarks:

Concatenation. Returns this string with cs appended.

UTF8Str& Append

(

const UTF8Str &

cs

)

[inline]

Search for all occurrences

Remarks:

Concatenation. Returns this string with cs appended.

{ return ((*this) += cs); }

UTF8Str& append

(

const UTF8Str &

cs

)

[inline]

Search for all occurrences

Remarks:

Concatenation. Returns this string with cs appended to the end.

{ return ((*this) += cs); }

UTF8Str MultiByteCharacterSubString	(	int	firstCharacterIndex,
		int	numberOfMBCharacters
	)		const

Search for all occurrences

Remarks:

Returns a substring of this string, beginning at multi-byte character position firstCharacterIndex, of length numberOfMBCharacters.

int FindMultiByteCharacterFirstByteIndex

(

int

characterIndex

)

const

Search for all occurrences

Remarks:

Returns the first byte index value of the multi-byte character position characterIndex.

int FindMultiByteCharacterLastByteIndex

(

int

characterIndex

)

const

Search for all occurrences

Remarks:

Returns the last byte index value of the multi-byte character position characterIndex.

bool operator==

(

const UTF8Str &

cs

)

const

Remarks:

Equality operator.

Returns:

true if the strings are equal; otherwise false.

bool operator!=

(

const UTF8Str &

cs

)

const

Remarks:

Inequality operator.

Returns:

false if the strings are equal; otherwise true.

bool operator<

(

const UTF8Str &

cs

)

const

Remarks:

Returns true if this string is less than cs; otherwise false.

bool operator<=

(

const UTF8Str &

ws

)

const

Remarks:

Returns true if this string is less than or equal to ws; otherwise false.

bool operator>

(

const UTF8Str &

ws

)

const

Remarks:

Returns true if this string is greater than ws; otherwise false.

bool operator>=

(

const UTF8Str &

ws

)

const

Remarks:

Returns true if this string is greater than or equal to ws; otherwise false.

void toUpper

(

)

Search for all occurrences

Remarks:

Converts all character of this string to uppercase.

void toLower

(

)

Search for all occurrences

Remarks:

Converts all character of this string to lowercase.

int printf	(	const char *	format,
			...
	)

Search for all occurrences

Write a formatted string into this UTF8Str.

Writes the format string, filled in by the optional arguments into this UTF8Str. See the ISO C++ documentation for more information on printf and format strings. Note: do not use ls formatting since conversion from wide string to narrow string will occur using active code page encoding rather than utf8 encoding

Parameters:

format	Specifies how to format the destination string.
...	optional arguments to format into the destination string.

Precondition:

format is not null.

There are the correct number of elliptical arguments to fill the format string.

Postcondition:

This string is replaced with the formatted string.

Returns:

The number of characters written to this string, not including the null terminating character, or a negative value if an error occurs.

int vprintf	(	const char *	format,
		va_list	args
	)

Search for all occurrences

Write a formatted string into this UTF8Str.

This method is similar to UTF8Str::printf. Instead of taking a variable list of arguments as parameter, it takes a structure representing a variable list of argument. This allows UTF8Str objects to be used to build strings based on a format string and a variable number of arguments. Note: do not use ls formatting since conversion from wide string to narrow string will occur using active code page encoding rather than utf8 encoding

wchar_t* ToBSTR

(

)

const

Search for all occurrences

Remarks:

Returns the string in memory allocated by SysAllocString. Caller is responsible for freeing memory using SysFreeString.

static UTF8Str FromBSTR	(	const wchar_t *	string,
		size_t	length = (size_t)-1
	)		[static]

Search for all occurrences

MaxSDK::Util::MaxStringCastCP ToCP	(	UINT	cp,
		size_t *	length = NULL
	)		const

Search for all occurrences

static UTF8Str FromCP	(	UINT	cp,
		const char *	string,
		size_t	length = (size_t)-1
	)		[static]

Search for all occurrences

MaxSDK::Util::MaxStringCast<char> ToACP

(

size_t *

length = NULL

)

const

Search for all occurrences

static UTF8Str FromACP	(	const char *	string,
		size_t	length = (size_t)-1
	)		[static]

Search for all occurrences

MaxSDK::Util::MaxStringCastUTF8 ToUTF8

(

size_t *

length = NULL

)

const

Search for all occurrences

static UTF8Str FromUTF8	(	const char *	string,
		size_t	length = (size_t)-1
	)		[static]

Search for all occurrences

MaxSDK::Util::MaxStringCast<WCHAR> ToOLESTR

(

size_t *

length = NULL

)

const

Search for all occurrences

static UTF8Str FromOLESTR	(	const wchar_t *	string,
		size_t	length = (size_t)-1
	)		[static]

Search for all occurrences

MaxSDK::Util::MaxStringCast<WCHAR> ToUTF16

(

size_t *

length = NULL

)

const

Search for all occurrences

static UTF8Str FromUTF16	(	const wchar_t *	string,
		size_t	length = (size_t)-1
	)		[static]

Search for all occurrences

MaxSDK::Util::MaxStringCast<unsigned int> ToUTF32

(

size_t *

length = NULL

)

const

Search for all occurrences

static UTF8Str FromUTF32	(	const unsigned int *	string,
		size_t	length = (size_t)-1
	)		[static]

Search for all occurrences

MaxSDK::Util::MaxString ToMaxString

(

)

const

Search for all occurrences

void ToMaxString

(

MaxSDK::Util::MaxString &

)

const

Search for all occurrences

static UTF8Str FromMaxString

(

MaxSDK::Util::MaxString &

string

)

[inline, static]

Search for all occurrences

{ return UTF8Str(string); }

UTF8Str ToUTF8Str

(

)

const [inline]

Search for all occurrences

{ return *this; }

static UTF8Str FromUTF8Str

(

const UTF8Str &

string

)

[inline, static]

Search for all occurrences

{ return UTF8Str(string); }

WStr ToWStr

(

)

const

Search for all occurrences

static UTF8Str FromWStr

(

const WStr &

string

)

[static]

Search for all occurrences

MaxSDK::Util::MaxStringCast<char> ToMCHAR

(

size_t *

length = NULL

)

const [inline]

Search for all occurrences

{ return ToACP(length); }

static UTF8Str FromMCHAR	(	const char *	string,
		size_t	length = (size_t)-1
	)		[inline, static]

Search for all occurrences

{ return FromACP(string, length); }

UTF8Str ToMSTR

(

)

const [inline]

Search for all occurrences

{ return *this; }

static UTF8Str FromMSTR

(

const UTF8Str &

string

)

[inline, static]

Search for all occurrences

{ return UTF8Str(string); }

bool EndsWith	(	const UTF8Str &	s,
		bool	caseSensitive = true
	)

Search for all occurrences

Returns true if the string ends with s; otherwise returns false.

Parameters:

s	The string to be searched.
caseSensitive	If it is true(default), the search is case sensitive; otherwise the search is case insensitive.

bool StartsWith	(	const UTF8Str &	s,
		bool	caseSensitive = true
	)

Search for all occurrences

Returns true if the string starts with s; otherwise returns false.

Parameters:

s	The string to be searched.
caseSensitive	If it is true(default), the search is case sensitive; otherwise the search is case insensitive.

size_t NumberOfLines

(

)

const

Search for all occurrences

Returns the number of lines inside a string.