utf8util.h File Reference

Interface for low-level UTF-8 utility functions. More...

#include <limits.h>

Go to the source code of this file.

Data Structures
struct	utf8Iterator

Macros
#define	BSTR_PUBLIC
#define	isLegalUnicodeCodePoint(v)
#define	utf8IteratorNoMore(it)

Functions
BSTR_PUBLIC void	utf8IteratorInit (struct utf8Iterator *iter, unsigned char *data, int slen)
BSTR_PUBLIC void	utf8IteratorUninit (struct utf8Iterator *iter)
BSTR_PUBLIC cpUcs4	utf8IteratorGetNextCodePoint (struct utf8Iterator *iter, cpUcs4 errCh)
BSTR_PUBLIC cpUcs4	utf8IteratorGetCurrCodePoint (struct utf8Iterator *iter, cpUcs4 errCh)
BSTR_PUBLIC int	utf8ScanBackwardsForCodePoint (const unsigned char *msg, int len, int pos, cpUcs4 *out)

Detailed Description

Interface for low-level UTF-8 utility functions.

This module is standalone and does not depend on bstrlib.

Macro Definition Documentation

BSTR_PUBLIC

#define BSTR_PUBLIC

isLegalUnicodeCodePoint

#define isLegalUnicodeCodePoint

(

v

)

Value:

((((v) < 0xD800L) || ((v) > 0xDFFFL)) && \
 (((unsigned long)(v)) <= 0x0010FFFFL) && \
 (((v)|0x1F0001) != 0x1FFFFFL))

utf8IteratorNoMore

#define utf8IteratorNoMore

(

it

)

Value:

(!(it) || (it)->next >= (it)->slen)

Function Documentation

utf8IteratorGetCurrCodePoint()

BSTR_PUBLIC cpUcs4 utf8IteratorGetCurrCodePoint	(	struct utf8Iterator *	iter,
		cpUcs4	errCh )

utf8IteratorGetNextCodePoint()

BSTR_PUBLIC cpUcs4 utf8IteratorGetNextCodePoint	(	struct utf8Iterator *	iter,
		cpUcs4	errCh )

utf8IteratorInit()

BSTR_PUBLIC void utf8IteratorInit	(	struct utf8Iterator *	iter,
		unsigned char *	data,
		int	slen )

utf8IteratorUninit()

BSTR_PUBLIC void utf8IteratorUninit

(

struct utf8Iterator *

iter

)

utf8ScanBackwardsForCodePoint()

BSTR_PUBLIC int utf8ScanBackwardsForCodePoint	(	const unsigned char *	msg,
		int	len,
		int	pos,
		cpUcs4 *	out )