C++ (Cpp) Length_As_UTF8 Examples

Example #1

File: d-print.c Project: kealist/ren-c

*/	void Debug_Uni(const REBSER *ser)
/*
**		Print debug unicode string followed by a newline.
**
***********************************************************************/
{
	REBCNT ul;
	REBCNT bl;
	REBYTE buf[1024];
	REBUNI *up = UNI_HEAD(ser);
	REBINT size = Length_As_UTF8(up, SERIES_TAIL(ser), TRUE, OS_CRLF);

	REBINT disabled = GC_Disabled;
	GC_Disabled = 1;

	while (size > 0) {
		ul = Encode_UTF8(buf, MIN(size, 1020), up, &bl, TRUE, OS_CRLF);
		Debug_String(buf, bl, 0, 0);
		size -= ul;
		up += ul;
	}

	Debug_Line();

	assert(GC_Disabled == 1);
	GC_Disabled = disabled;
}

Example #2

File: a-lib.c Project: asampal/ren-c

*/	RL_API REBCNT RL_Length_As_UTF8(const void *p, REBCNT len, REBOOL uni, REBOOL ccr)
/*
**		Calculate the UTF8 length of an array of unicode codepoints
**
**	Returns:
**		How long the UTF8 encoded string would be
**
**	Arguments:
**		p - pointer to array of bytes or wide characters
**		len - length of src in codepoints (not including terminator)
**		uni - true if src is in wide character format
**		ccr - convert linefeeds into linefeed + carraige-return
**
**		!!! Host code is not supposed to call any Rebol routines except
**		for those in the RL_Api.  This exposes Rebol's internal UTF8
**		length routine, as it was being used by host code.  It should
**		be reviewed along with the rest of the RL_Api.
**
***********************************************************************/
{
	return Length_As_UTF8(
		p,
		len,
		(uni ? OPT_ENC_UNISRC : 0) | (ccr ? OPT_ENC_CRLF : 0)
	);
}

Example #3

File: a-lib.c Project: kjanz1899/ren-c

//
//  RL_Length_As_UTF8: C
// 
// Calculate the UTF8 length of an array of unicode codepoints
// 
// Returns:
// How long the UTF8 encoded string would be
// 
// Arguments:
// p - pointer to array of bytes or wide characters
// len - length of src in codepoints (not including terminator)
// unicode - true if src is in wide character format
// lf_to_crlf - convert linefeeds into carraige-return + linefeed
// 
// !!! Host code is not supposed to call any Rebol routines except
// for those in the RL_Api.  This exposes Rebol's internal UTF8
// length routine, as it was being used by host code.  It should
// be reviewed along with the rest of the RL_Api.
//
RL_API REBCNT RL_Length_As_UTF8(
    const void *p,
    REBCNT len,
    REBOOL unicode,
    REBOOL lf_to_crlf
) {
    return Length_As_UTF8(
        p,
        len,
        (unicode ? OPT_ENC_UNISRC : 0) | (lf_to_crlf ? OPT_ENC_CRLF : 0)
    );
}

Example #4

File: s-unicode.c Project: Oldes/r3

*/	REBSER *Encode_UTF8_String(void *src, REBCNT len, REBFLG uni, REBFLG opts)
/*
**		Do all the details to encode a string as UTF8.
**		No_copy means do not make a copy.
**		Result can be a shared buffer!
**
***********************************************************************/
{
	REBSER *ser = BUF_FORM; // a shared buffer
	REBCNT size;
	REBYTE *cp;
	REBFLG ccr = GET_FLAG(opts, ENC_OPT_CRLF);

	if (uni) {
		REBUNI *up = (REBUNI*)src;

		size = Length_As_UTF8(up, len, TRUE, (REBOOL)ccr);
		cp = Reset_Buffer(ser, size + (GET_FLAG(opts, ENC_OPT_BOM) ? 3 : 0));
        UNUSED(cp);
		Encode_UTF8(Reset_Buffer(ser, size), size, up, &len, TRUE, ccr);
	}
	else {
		REBYTE *bp = (REBYTE*)src;

		if (Is_Not_ASCII(bp, len)) {
			size = Length_As_UTF8((REBUNI*)bp, len, FALSE, (REBOOL)ccr);
			cp = Reset_Buffer(ser, size + (GET_FLAG(opts, ENC_OPT_BOM) ? 3 : 0));
			Encode_UTF8(cp, size, bp, &len, FALSE, ccr);
		}
		else if (GET_FLAG(opts, ENC_OPT_NO_COPY)) return 0;
		else return Copy_Bytes(bp, len);
	}

	SERIES_TAIL(ser) = len;
	STR_TERM(ser);

	return Copy_Bytes(BIN_HEAD(ser), len);
}