textwolf::charset::UTF8 Class Reference

character set encoding UTF-8 More...

#include <charset_utf8.hpp>

Classes
class	CharLengthTab
	Table that maps the first UTF-8 character byte to the length of the character in bytes. More...

Public Types
enum	{ MaxChar =0x7FFFFFFFU }
	Maximum character that can be represented by this encoding implementation. More...
enum	{   B11111111 =0xFF, B01111111 =0x7F, B00111111 =0x3F, B00011111 =0x1F,   B00001111 =0x0F, B00000111 =0x07, B00000011 =0x03, B00000001 =0x01,   B00000000 =0x00, B10000000 =0x80, B11000000 =0xC0, B11100000 =0xE0,   B11110000 =0xF0, B11111000 =0xF8, B11111100 =0xFC, B11111110 =0xFE,   B11011111 =B11000000|B00011111, B11101111 =B11100000|B00001111, B11110111 =B11110000|B00000111, B11111011 =B11111000|B00000011,   B11111101 =B11111100|B00000001 }

Public Member Functions
template<class Iterator >
UChar	value (char *buf, unsigned int &bufpos, Iterator &itr) const
	See template<class Iterator>Interface::value(char*,unsigned int&,Iterator&) More...
template<class Buffer_ >
void	print (UChar chr, Buffer_ &buf) const
	See template<class Buffer>Interface::print(UChar,Buffer&) More...

Static Public Member Functions
template<class Iterator >
static unsigned int	size (char *buf, unsigned int &bufpos, Iterator &itr)
	Get the size of the current character in bytes (variable length encoding) More...
template<class Iterator >
static void	skip (char *buf, unsigned int &bufpos, Iterator &itr)
	See template<class Iterator>Interface::skip(char*,unsigned int&,Iterator&) More...
template<class Iterator >
static signed char	asciichar (char *buf, unsigned int &bufpos, Iterator &itr)
	See template<class Iterator>Interface::asciichar(char*,unsigned int&,Iterator&) More...
template<class Iterator >
static void	fetchbytes (char *buf, unsigned int &bufpos, Iterator &itr)
	See template<class Iterator>Interface::fetch(char*,unsigned int&,Iterator&) More...
static bool	is_equal (const UTF8 &, const UTF8 &)
	See template<class Buffer>Interface::is_equal( const Interface&, const Interface&) More...

Detailed Description

character set encoding UTF-8

Member Enumeration Documentation

anonymous enum

Maximum character that can be represented by this encoding implementation.

Enumerator
MaxChar

anonymous enum

Enumerator
B11111111
B01111111
B00111111
B00011111
B00001111
B00000111
B00000011
B00000001
B00000000
B10000000
B11000000
B11100000
B11110000
B11111000
B11111100
B11111110
B11011111
B11101111
B11110111
B11111011
B11111101

Member Function Documentation

template<class Iterator >

static signed char textwolf::charset::UTF8::asciichar ( char *  buf, unsigned int &  bufpos, Iterator &  itr  )

inlinestatic

See template<class Iterator>Interface::asciichar(char*,unsigned int&,Iterator&)

template<class Iterator >

static void textwolf::charset::UTF8::fetchbytes ( char *  buf, unsigned int &  bufpos, Iterator &  itr  )

inlinestatic

See template<class Iterator>Interface::fetch(char*,unsigned int&,Iterator&)

static bool textwolf::charset::UTF8::is_equal ( const UTF8 &  , const UTF8 &    )

inlinestatic

See template<class Buffer>Interface::is_equal( const Interface&, const Interface&)

template<class Buffer_ >

void textwolf::charset::UTF8::print ( UChar  chr, Buffer_ &  buf  ) const

inline

See template<class Buffer>Interface::print(UChar,Buffer&)

template<class Iterator >

static unsigned int textwolf::charset::UTF8::size ( char *  buf, unsigned int &  bufpos, Iterator &  itr  )

inlinestatic

Get the size of the current character in bytes (variable length encoding)

Parameters

[in]	buf	buffer for the character data
[in,out]	bufpos	position in 'buf'
[in,out]	itr	iterator to skip

template<class Iterator >

static void textwolf::charset::UTF8::skip ( char *  buf, unsigned int &  bufpos, Iterator &  itr  )

inlinestatic

See template<class Iterator>Interface::skip(char*,unsigned int&,Iterator&)

template<class Iterator >

UChar textwolf::charset::UTF8::value ( char *  buf, unsigned int &  bufpos, Iterator &  itr  ) const

inline

See template<class Iterator>Interface::value(char*,unsigned int&,Iterator&)

---

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

• /home/patrick/Projects/github/textwolf/include/textwolf/charset_utf8.hpp