A core class of ut8 encoded string functions. More...

#include <unicode.h>

Inheritance diagram for ucommon::utf8:

Static Public Member Functions
static unsigned	ccount (char *string, ucs4_t character)
	Count occurrences of a unicode character in string.
static size_t	chars (unicode_t string)
	How many chars requires to encode a given wchar string.
static size_t	chars (ucs4_t character)
	How many chars requires to encode a given unicode character.
static ucs4_t	codepoint (char *encoded)
	Convert a utf8 encoded codepoint to a ucs4 character value.
static size_t	count (char *string)
	Count ut8 encoded ucs4 codepoints in string.
static char *	find (char *string, ucs4_t character, size_t start=0)
	Find first occurance of character in string.
static ucs4_t	get (CharacterProtocol &buffer)
	Get a unicode character from a character protocol.
static char *	offset (char *string, ssize_t position)
	Get codepoint offset in a string.
static size_t	pack (unicode_t unicode, CharacterProtocol &buffer, size_t size)
	Convert a utf8 string into a unicode data buffer.
static ucs4_t	put (ucs4_t character, CharacterProtocol &buffer)
	Push a unicode character to a character protocol.
static char *	rfind (char *string, ucs4_t character, size_t end=(size_t)-1l)
	Find last occurrence of character in string.
static unsigned	size (char *codepoint)
	Compute character size of utf8 string codepoint.
static ucs4_t *	udup (char *string)
	Dup a utf8 string into a ucs4_t string.
static size_t	unpack (unicode_t string, CharacterProtocol &buffer)
	Convert a unicode string into utf8.
static ucs2_t *	wdup (char *string)
	Dup a utf8 string into a ucs2_t representation.
Static Public Attributes
static char *	nil
	A convenient NULL pointer value.
static unsigned	ucsize
	Size of "unicode_t" character codes, may not be ucs4_t size.

Detailed Description

A core class of ut8 encoded string functions.

This is a foundation for all utf8 string processing.

Author:: David Sugar

Definition at line 62 of file unicode.h.

Member Function Documentation

static unsigned ucommon::utf8::ccount	(	char *	string,
		ucs4_t	character
	)		`[static]`

Count occurrences of a unicode character in string.

Parameters:

string	to search in.
character	code to search for.

Returns:: count of occurrences.

static size_t ucommon::utf8::chars ( unicode_t string ) [static]

How many chars requires to encode a given wchar string.

Parameters:

string of ucs4 data.

Returns:: number of chars required to encode given string.

static size_t ucommon::utf8::chars ( ucs4_t character ) [static]

How many chars requires to encode a given unicode character.

Parameters:

character to encode.

Returns:: number of chars required to encode given character.

static ucs4_t ucommon::utf8::codepoint ( char * encoded ) [static]

Convert a utf8 encoded codepoint to a ucs4 character value.

Parameters:

encoded utf8 codepoint.

Returns:: ucs4 string or 0 if invalid.

static size_t ucommon::utf8::count ( char * string ) [static]

Count ut8 encoded ucs4 codepoints in string.

Parameters:

string of utf8 data.

Returns:: codepount count, 0 if empty or invalid.

static char* ucommon::utf8::find	(	char *	string,
		ucs4_t	character,
		size_t	start = `0`
	)		`[static]`

Find first occurance of character in string.

Parameters:

string	to search in.
character	code to search for.
start	offset in string in codepoints.

Returns:: pointer to first instance or NULL if not found.

static ucs4_t ucommon::utf8::get ( CharacterProtocol & buffer ) [static]

Get a unicode character from a character protocol.

Parameters:

buffer of character protocol to read from.

Returns:: unicode character or EOF error.

static char* ucommon::utf8::offset	(	char *	string,
		ssize_t	position
	)		`[static]`

Get codepoint offset in a string.

Parameters:

string	of utf8 data.
position	of codepoint in string, negative offsets are from tail.

Returns:: offset of codepoint or NULL if invalid.

static size_t ucommon::utf8::pack	(	unicode_t	unicode,
		CharacterProtocol &	buffer,
		size_t	size
	)		`[static]`

Convert a utf8 string into a unicode data buffer.

Parameters:

unicode	data buffer.
buffer	of character protocol to pack from.
size	of unicode data buffer in codepoints.

Returns:: number of code points converted.

static ucs4_t ucommon::utf8::put	(	ucs4_t	character,
		CharacterProtocol &	buffer
	)		`[static]`

Push a unicode character to a character protocol.

Parameters:

character	to push to file.
buffer	of character protocol to push character to.

Returns:: unicode character or EOF on error.

static char* ucommon::utf8::rfind	(	char *	string,
		ucs4_t	character,
		size_t	end = `(size_t)-1l`
	)		`[static]`

Find last occurrence of character in string.

Parameters:

string	to search in.
character	code to search for.
end	offset to start from in codepoints.

Returns:: pointer to last instance or NULL if not found.

static unsigned ucommon::utf8::size ( char * codepoint ) [static]

Compute character size of utf8 string codepoint.

Parameters:

codepoint in string.

Returns:: size of codepoint as utf8 encoded data, 0 if invalid.

static size_t ucommon::utf8::unpack	(	unicode_t	string,
		CharacterProtocol &	buffer
	)		`[static]`

Convert a unicode string into utf8.

Parameters:

string	of unicode data to pack
buffer	of character protocol to put data into.

Returns:: number of code points converted.

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

ucommon/unicode.h

Static Public Member Functions

Static Public Attributes

Detailed Description

Member Function Documentation