tsk_unicode.c File Reference

A local copy of the Unicode conversion routines from unicode.org. More...

#include "tsk_base_i.h"
#include <wchar.h>

Macros
#define	FALLTHROUGH   /* fall through */
#define	false   0
#define	true   1
#define	TSK_UNI_MAX_BMP   (UTF32)0x0000FFFF
#define	TSK_UNI_MAX_LEGAL_UTF32   (UTF32)0x0010FFFF
#define	TSK_UNI_MAX_UTF16   (UTF32)0x0010FFFF
#define	TSK_UNI_MAX_UTF32   (UTF32)0x7FFFFFFF
#define	TSK_UNI_REPLACEMENT_CHAR   (UTF32)0x0000FFFD
#define	UNI_SUR_HIGH_END   (UTF32)0xDBFF
#define	UNI_SUR_HIGH_START   (UTF32)0xD800
#define	UNI_SUR_LOW_END   (UTF32)0xDFFF
#define	UNI_SUR_LOW_START   (UTF32)0xDC00

Typedefs
typedef unsigned long	UTF32

Functions
void	tsk_cleanupUTF16 (TSK_ENDIAN_ENUM endian, wchar_t *source, size_t source_len, const wchar_t replacement)
	Cleans up the passed in string to replace invalid UTF-16 values with the passed in character.
void	tsk_cleanupUTF8 (char *source, const char replacement)
	Cleans up the passed in string to replace invalid UTF-8 values with the passed in character.
Boolean	tsk_isLegalUTF8Sequence (const UTF8 *source, const UTF8 *sourceEnd)
TSKConversionResult	tsk_UTF16toUTF8 (TSK_ENDIAN_ENUM endian, const UTF16 **sourceStart, const UTF16 *sourceEnd, UTF8 **targetStart, UTF8 *targetEnd, TSKConversionFlags flags)
	Convert a UTF-16 string to UTF-8.
TSKConversionResult	tsk_UTF16toUTF8_lclorder (const UTF16 **sourceStart, const UTF16 *sourceEnd, UTF8 **targetStart, UTF8 *targetEnd, TSKConversionFlags flags)
	Convert a UTF-16 string in local endian ordering to UTF-8.
TSKConversionResult	tsk_UTF16WtoUTF8_lclorder (const wchar_t **sourceStart, const wchar_t *sourceEnd, UTF8 **targetStart, UTF8 *targetEnd, TSKConversionFlags flags)
TSKConversionResult	tsk_UTF8toUTF16 (const UTF8 **sourceStart, const UTF8 *sourceEnd, UTF16 **targetStart, UTF16 *targetEnd, TSKConversionFlags flags)
	Convert a UTF-8 string to UTF-16 (in local endian ordering).

Detailed Description

A local copy of the Unicode conversion routines from unicode.org.

Function Documentation

tsk_cleanupUTF16()

void tsk_cleanupUTF16	(	TSK_ENDIAN_ENUM	endian,
		wchar_t *	source,
		size_t	source_len,
		const wchar_t	replacement )

Cleans up the passed in string to replace invalid UTF-16 values with the passed in character.

Parameters

endian	Ordering that data is stored in
source	String to be cleaned up
source_len	Number of wchar_t characters in source
replacement	Character to insert into source as needed.

tsk_cleanupUTF8()

void tsk_cleanupUTF8	(	char *	source,
		const char	replacement )

Cleans up the passed in string to replace invalid UTF-8 values with the passed in character.

Parameters

source	String to be cleaned up
replacement	Character to insert into source as needed.