buniutil.c File Reference

#include "bstrlib.h"
#include "buniutil.h"

Macros
#define	UNICODE__CODE_POINT__REPLACEMENT_CHARACTER   (0xFFFDL)
#define	endSwap(cs, mode)    ((mode) ? ((((cs) & 0xFF) << 8) | (((cs) >> 8) & 0xFF)) : (cs))
#define	TEMP_UCS4_BUFFER_SIZE   (64)

Functions
int	buIsUTF8Content (const bstring bu)
int	buGetBlkUTF16 (cpUcs2 *ucs2, int len, cpUcs4 errCh, const bstring bu, int pos)
int	buAppendBlkUcs4 (bstring b, const cpUcs4 *bu, int len, cpUcs4 errCh)
int	buAppendBlkUTF16 (bstring bu, const cpUcs2 *utf16, int len, cpUcs2 *bom, cpUcs4 errCh)

Macro Definition Documentation

endSwap

#define endSwap	(		cs,
			mode
	)		((mode) ? ((((cs) & 0xFF) << 8) | (((cs) >> 8) & 0xFF)) : (cs))

TEMP_UCS4_BUFFER_SIZE

#define TEMP_UCS4_BUFFER_SIZE   (64)

UNICODE__CODE_POINT__REPLACEMENT_CHARACTER

#define UNICODE__CODE_POINT__REPLACEMENT_CHARACTER   (0xFFFDL)

Function Documentation

buAppendBlkUcs4()

int buAppendBlkUcs4	(	bstring	b,
		const cpUcs4 *	bu,
		int	len,
		cpUcs4	errCh
	)

Convert an array of UCS-4 code points (bu, len elements) to UTF-8 and append the result to the bstring b.

Any invalid code point is replaced by errCh. If errCh is itself not a valid code point, translation halts on the first error and BSTR_ERR is returned. Otherwise BSTR_OK is returned.

buAppendBlkUTF16()

int buAppendBlkUTF16	(	bstring	bu,
		const cpUcs2 *	utf16,
		int	len,
		cpUcs2 *	bom,
		cpUcs4	errCh
	)

Append an array of UTF-16 code units (utf16, len elements) to the UTF-8 bstring bu.

Any invalid code point is replaced by errCh. If errCh is itself not a valid code point, translation halts on the first error and BSTR_ERR is returned. Otherwise BSTR_OK is returned. If a byte order mark has been previously read it may be passed in via bom; if *bom is 0 it will be filled in from the first character if it is a BOM.

buGetBlkUTF16()

int buGetBlkUTF16	(	cpUcs2 *	ucs2,
		int	len,
		cpUcs4	errCh,
		const bstring	bu,
		int	pos
	)

Convert the UTF-8 bstring bu (starting at code-point offset pos) to a sequence of UTF-16 encoded code units written to ucs2 (at most len units).

Returns the number of UCS-2 16-bit words written. Any unparsable code point is translated to errCh.

buIsUTF8Content()

int buIsUTF8Content

(

const bstring

bu

)

Scan a bstring and return 1 if its entire content consists of valid UTF-8 encoded code points, otherwise return 0.