utf8.c File Reference

#include <arpa/inet.h>
#include <errno.h>
#include <stdlib.h>
#include <atalk/byteorder.h>
#include <atalk/logger.h>
#include <atalk/unicode.h>

Macros
#define	GETUCVAL(utf8_trailbyte, shift)
#define	GETUTF8TRAILBYTE(uc, shift)

Functions
static size_t	utf8_pull (void *cd, char **inbuf, size_t *inbytesleft, char **outbuf, size_t *outbytesleft)
	Convert from UTF-8 to UTF-16.
static size_t	utf8_push (void *, char **, size_t *, char **, size_t *)

Variables
struct charset_functions	charset_utf8
struct charset_functions	charset_utf8_mac

Detailed Description

See also

The Unicode Standard Version 6.2 – Core Specification http://www.unicode.org/versions/Unicode6.2.0/ch03.pdf

Scalar Value               First    Second   Third    Fourth
00000000 0xxxxxxx          0xxxxxxx
00000yyy yyxxxxxx          110yyyyy 10xxxxxx
zzzzyyyy yyxxxxxx          1110zzzz 10yyyyyy 10xxxxxx
000uuuuu zzzzyyyy yyxxxxxx 11110uuu 10uuzzzz 10yyyyyy 10xxxxxx

Macro Definition Documentation

GETUCVAL

#define GETUCVAL	(		utf8_trailbyte,
			shift )

Value:

((unsigned int) (( utf8_trailbyte & 0x3F) << shift))

Given a trailing UTF-8 byte, get the contribution from it to the Unicode scalar value for a particular bit shift amount

GETUTF8TRAILBYTE

#define GETUTF8TRAILBYTE	(		uc,
			shift )

Value:

((char)( 0x80 | ((uc >> shift) & 0x3F) ) )

Given a unicode scalar, get a trail UTF-8 byte for a particular bit shift amount

Function Documentation

utf8_pull()

size_t utf8_pull ( void * cd, char ** inbuf, size_t * inbytesleft, char ** outbuf, size_t * outbytesleft )

static

Convert from UTF-8 to UTF-16.

Code Points         First   Second  Third   Fourth
U+0000..U+007F      00..7F
U+0080..U+07FF      C2..DF  80..BF
U+0800..U+0FFF      E0      A0..BF  80..BF
U+1000..U+CFFF      E1..EC  80..BF  80..BF
U+D000..U+D7FF      ED      80..9F  80..BF
U+E000..U+FFFF      EE..EF  80..BF  80..BF
U+10000..U+3FFFF    F0      90..BF  80..BF  80..BF
U+40000..U+FFFFF    F1..F3  80..BF  80..BF  80..BF
U+100000..U+10FFFF  F4      80..8F  80..BF  80..BF

utf8_push()

size_t utf8_push ( void * cd, char ** inbuf, size_t * inbytesleft, char ** outbuf, size_t * outbytesleft )

static

Convert from UTF-16 to UTF-8

Variable Documentation

charset_utf8

struct charset_functions charset_utf8

Initial value:

= {
    "UTF8",
    0x08000103,
    utf8_pull,
    utf8_push,
    CHARSET_VOLUME | CHARSET_MULTIBYTE | CHARSET_PRECOMPOSED,
    NULL,
    NULL,
    NULL
}

charset_utf8_mac

struct charset_functions charset_utf8_mac

Initial value:

= {
    "UTF8-MAC",
    0x08000103,
    utf8_pull,
    utf8_push,
    CHARSET_VOLUME | CHARSET_CLIENT | CHARSET_MULTIBYTE | CHARSET_DECOMPOSED,
    NULL,
    NULL,
    NULL
}