src/utf8.c File Reference

Source - Unicode utf-8. More...

#include <stdio.h>
#include "check.h"

Go to the source code of this file.

Defines
#define	UTF8_HEAD_7   0x00
	header bits added to one-byte utf8 characters
#define	UTF8_HEAD_7_MASK   0x80
	header mask used to add bits to one-byte utf8 characters
#define	UTF8_HEAD_11   0xc0
	header bits added to two-bytes utf8 characters
#define	UTF8_HEAD_11_MASK   0xe0
	header mask used to add bits to two-bytes utf8 characters
#define	UTF8_TAIL   0x80
	bits added to non-first bytes of multi-bytes utf8 characters
#define	UTF8_TAIL_MASK   0xc0
	mask used to add bits to non-first bytes of multi-bytes utf8 characters
#define	UTF8_TAIL_SHIFT   6
	multi-bytes utf8 characters bit shift
#define	UTF8_SHIFTER(data, byte)   (data >> (byte*UTF8_TAIL_SHIFT))
	shift data to be coded in utf8
#define	UTF8_HEADER_7(data)   (UTF8_HEAD_7 | (data & ~UTF8_HEAD_7_MASK))
	add utf-8 one-byte bits header
#define	UTF8_HEADER_11(data)   (UTF8_HEAD_11 | (data & ~UTF8_HEAD_11_MASK))
	add utf-8 two-bytes bits header
#define	UTF8_TAILER(data)   (UTF8_TAIL | (data & ~UTF8_TAIL_MASK))
	add utf-8 non-first bytes bits header
#define	IS_UTF8_HEADER_7(byte)   ((unsigned char)(byte & UTF8_HEAD_7_MASK) == UTF8_HEAD_7)
	test if the byte is a one-byte utf8 character
#define	IS_UTF8_HEADER_11(byte)   ((unsigned char)(byte & UTF8_HEAD_11_MASK) == UTF8_HEAD_11)
	test if the byte is a two-byte utf8 character
#define	IS_UTF8_TAIL(byte)   ((unsigned char)(byte & UTF8_TAIL_MASK) == UTF8_TAIL)
	test if the byte is a part of (and not the first of) a multi-byte utf8 character
#define	UTF8_UNSHIFTER(data, byte)   (data << (byte*UTF8_TAIL_SHIFT))
	unshift utf8 character to retrieve data
#define	UTF8_UNHEADER_7(data)   (data & ~UTF8_HEAD_7_MASK)
	remove utf-8 one-byte bits header
#define	UTF8_UNHEADER_11(data)   (data & ~UTF8_HEAD_11_MASK)
	remove utf-8 two-bytes bits header
#define	UTF8_UNTAILER(data)   (data & ~UTF8_TAIL_MASK)
	remove utf-8 non-first bytes bits header
Functions
size_t	iso8859_utf8 (const char *source, char *dest, const size_t dest_size)
	convert iso to unicode
size_t	utf8_iso8859 (const char *source, char *dest, const size_t dest_size)
	convert iso to unicode

---

Detailed Description

Source - Unicode utf-8.

Author:

Julien Blitte

Version:

0.1

Definition in file utf8.c.

---

Function Documentation

size_t iso8859_utf8	(	const char *	source,
		char *	dest,
		const size_t	dest_size
	)

convert iso to unicode

Parameters:

	source	latin1 string to convert to utf8 - latin1
	dest	destination where new string is stored - utf8
	dest_size	size of dest

Returns:

size of new string

Definition at line 58 of file utf8.c.

References check, UTF8_HEADER_11, UTF8_HEADER_7, UTF8_SHIFTER, and UTF8_TAILER.

Referenced by db5_select_filename(), db5_shortname_to_localfile(), and log_dump_latin1().

size_t utf8_iso8859	(	const char *	source,
		char *	dest,
		const size_t	dest_size
	)

convert iso to unicode

Parameters:

	source	utf8 string to convert to latin1 - utf8
	dest	destination where new string is stored - latin1
	dest_size	size of dest

Returns:

size of new string

Definition at line 95 of file utf8.c.

References check, IS_UTF8_HEADER_11, IS_UTF8_HEADER_7, UTF8_UNHEADER_11, UTF8_UNHEADER_7, UTF8_UNSHIFTER, and UTF8_UNTAILER.

Referenced by db5_generate_row(), db5_insert(), and db5_longname_to_shortname().