Contains a UTF-8 encoded string. More...

#include <WString.h>

Inheritance diagram for Utf8String:

Public Member Functions
	Utf8String ()

	Utf8String (Utf8CP str)

	Utf8String (bastring const &other)

	Utf8String (bastring const &__str, size_t __pos, size_t __n=npos)

	Utf8String (CharCP __s, size_t __n)

	Utf8String (size_t __n, char __c)

	Utf8String (iterator __beg, iterator __end)

	Utf8String (const_iterator __beg, const_iterator __end)

	Utf8String (reverse_iterator __beg, reverse_iterator __end)

	Utf8String (const_reverse_iterator __beg, const_reverse_iterator __end)

	Utf8String (WCharCP str)
	Construct a Utf8String by converting from a wchar_t string. More...

	Utf8String (WString str)
	Construct a Utf8String by converting from a wchar_t string. More...

Utf8StringR	Assign (WCharCP str)
	Construct a Utf8String by converting from a wchar_t string. More...

size_type	SizeInBytes () const
	Computes the size, in bytes, of this string's data, including its NULL-terminator. More...

bool	IsAscii ()
	Test if this string contains only characters less than or equal to 127. More...

void	VSprintf (Utf8CP format, va_list argptr)
	Replace the contents of this string with a formatted result. More...

void	Sprintf (Utf8CP format,...)
	Replace the contents of this string with a formatted result. More...

int	CompareToI (Utf8CP other) const
	Perform a case-insensitive comparison. More...

int	CompareToI (Utf8StringCR other) const
	Perform a case-insensitive comparison. More...

int	CompareTo (Utf8CP other) const
	Perform a (case-sensitive) comparison. More...

int	CompareTo (Utf8StringCR other) const
	Perform a (case-sensitive) comparison. More...

bool	Equals (Utf8CP other) const
	Test for equality with another string. More...

bool	Equals (Utf8StringCR other) const
	Test for equality with another string. More...

bool	EqualsI (Utf8StringCR other) const
	Test for equality with another string, ignoring case. More...

bool	EqualsI (Utf8CP other) const
	Test for equality with another string, ignoring case. More...

void	Trim ()
	Removes all whitespace from the left and right sides. Whitespace includes space, line feed, carriage return, and tab (e.g. iswspace). More...

void	Trim (Utf8CP trimCharacters)
	Removes all instances of any of the given characters from the left and right sides. More...

Utf8StringR	TrimEnd ()
	Removes all whitespace from the end. Whitespace includes space, line feed, carriage return, and tab (e.g. iswspace). More...

bool	StartsWith (Utf8CP) const
	Determines if this instance starts with the provided string. More...

Utf8StringR	AssignOrClear (Utf8CP in)
	Update this string to be equal to in. If in is NULL, clear this string. More...

size_t	ReplaceAll (Utf8CP subStringToReplace, Utf8CP replacement)
	Replace all instances of a sub string. Returns the number of replacements made. More...

void	ToLower ()
	Converts this string, in-place, to all lower case. More...

size_t	GetNextToken (Utf8StringR next, CharCP delims, size_t offset) const
	Reads the next token delimited by any character in delims or \0. More...

Static Public Member Functions
static bool	IsNullOrEmpty (Utf8CP value)
	Utility function to test if value represents the empty string. This function interprets NULL to be the empty string. More...

static bool	IsAsciiWhiteSpace (char val)
	Determine whether the supplied character is a whitespace character in the ascii (below 128) code page. More...

static char	ToLowerChar (char c)
	Equivalent to tolower. More...

Detailed Description

Contains a UTF-8 encoded string.

This class has many of the capabilities of std::string, except that it is intended to hold only UTF-8 encoded strings. This class also defines utility functions for constructing and manipulating the string.

Constructor & Destructor Documentation

Utf8String ( )

Utf8String ( Utf8CP str )

Utf8String ( bastring const & other )

Utf8String	(	bastring const &	__str,
		size_t	__pos,
		size_t	__n = `npos`
	)

Utf8String	(	CharCP	__s,
		size_t	__n
	)

Utf8String	(	size_t	__n,
		char	__c
	)

Utf8String	(	iterator	__beg,
		iterator	__end
	)

Utf8String	(	const_iterator	__beg,
		const_iterator	__end
	)

Utf8String	(	reverse_iterator	__beg,
		reverse_iterator	__end
	)

Utf8String	(	const_reverse_iterator	__beg,
		const_reverse_iterator	__end
	)

Utf8String ( WCharCP str )

explicit

Construct a Utf8String by converting from a wchar_t string.

Utf8String ( WString str )

explicit

Construct a Utf8String by converting from a wchar_t string.

Member Function Documentation

Utf8StringR Assign ( WCharCP str )

Construct a Utf8String by converting from a wchar_t string.

Utf8StringR AssignOrClear ( Utf8CP in )

Update this string to be equal to in. If in is NULL, clear this string.

References clear(), and NULL.

int CompareTo ( Utf8CP other ) const

Perform a (case-sensitive) comparison.

Returns: 0 if the strings are equal, or -1 or 1 if this string should come before or after other.

Parameters

other The other string.

int CompareTo ( Utf8StringCR other ) const

Perform a (case-sensitive) comparison.

Returns: 0 if the strings are equal, or -1 or 1 if this string should come before or after other.

Parameters

other The other string.

int CompareToI ( Utf8CP other ) const

Perform a case-insensitive comparison.

Returns: 0 if the strings are equal (ignoring case), or -1 or 1 if this string should come before or after other.

Parameters

other The other string.

int CompareToI ( Utf8StringCR other ) const

Perform a case-insensitive comparison.

Returns: 0 if the strings are equal (ignoring case), or -1 or 1 if this string should come before or after other.

Parameters

other The other string.

References Utf8String::CompareToI().

Referenced by Utf8String::CompareToI().

bool Equals ( Utf8CP other ) const

Test for equality with another string.

Returns: true if the strings are equal.

Parameters

other The other string.

bool Equals ( Utf8StringCR other ) const

Test for equality with another string.

Returns: true if the strings are equal.

Parameters

other The other string.

bool EqualsI ( Utf8StringCR other ) const

Test for equality with another string, ignoring case.

Returns: true if the strings are equal (ignoring case).

Parameters

other The other string.

bool EqualsI ( Utf8CP other ) const

Test for equality with another string, ignoring case.

Returns: true if the strings are equal (ignoring case).

Parameters

other The other string.

size_t GetNextToken	(	Utf8StringR	next,
		CharCP	delims,
		size_t	offset
	)		const

Reads the next token delimited by any character in delims or \0.

Parameters

[out]	next	set to next token, if found, or cleared if not
[in]	delims	the characters that could delimit the tokens
[in]	offset	where to start search

Returns: 1 beyond the end of the current token or npos if token not found Example
// Read lines from a string, where each line is delimited by \n. The last line need not have a trailing \n.

size_t offset = 0;

Utf8String m;

while ((offset = m_virtuals.GetNextToken (m, "\n", offset)) != Utf8String::npos)

{

printf ("%s\n", m.c_str());

}

Note: If this string ends with a delimiter, then the last token returned is the one before the trailing delimiter. If this string does not end with a delimiter, then the last token is everything following the last delimiter (if any) and the end of this string. If this string has no delimiters at all, then the first and only token returned is the string itself. So, for example, if this string were "abc\n" then GetNextToken (next, "\n", 0) would set next to "abc" and return 4, and GetNextToken (next, "\n", 4) would return npos. If this string were "abc", the two calls would return the same results.

bool IsAscii ( )

Test if this string contains only characters less than or equal to 127.

static bool IsAsciiWhiteSpace ( char val )

static

Determine whether the supplied character is a whitespace character in the ascii (below 128) code page.

This is necessary since the c "isspace" function is locale specific and sometimes returns true for the non-breaking-space character (0xA0), which is not a valid test for a Utf8 string. Note this does not test for VT, or FF as they are considered obsolete.

static bool IsNullOrEmpty ( Utf8CP value )

static

Utility function to test if value represents the empty string. This function interprets NULL to be the empty string.

References NULL.

size_t ReplaceAll	(	Utf8CP	subStringToReplace,
		Utf8CP	replacement
	)

Replace all instances of a sub string. Returns the number of replacements made.

size_type SizeInBytes ( ) const

Computes the size, in bytes, of this string's data, including its NULL-terminator.

References size().

void Sprintf	(	Utf8CP	format,
			...
	)

Replace the contents of this string with a formatted result.

Parameters

format The sprintf-like format string.

bool StartsWith ( Utf8CP ) const

Determines if this instance starts with the provided string.

void ToLower ( )

Converts this string, in-place, to all lower case.

Remarks: This function can be very slow if the string contains non-ascii characters.

References begin(), clear(), end(), and WString::ToLower().

static char ToLowerChar ( char c )

static

Equivalent to tolower.

void Trim ( )

Removes all whitespace from the left and right sides. Whitespace includes space, line feed, carriage return, and tab (e.g. iswspace).

void Trim ( Utf8CP trimCharacters )

Removes all instances of any of the given characters from the left and right sides.

Utf8StringR TrimEnd ( )

Removes all whitespace from the end. Whitespace includes space, line feed, carriage return, and tab (e.g. iswspace).

void VSprintf	(	Utf8CP	format,
		va_list	argptr
	)

Replace the contents of this string with a formatted result.

Parameters

format	The sprintf-like format string.
argptr	Arguments used by format.

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

WString.h

Public Member Functions

Static Public Member Functions

Detailed Description

Constructor & Destructor Documentation

Member Function Documentation