GetCodepointsFromUtf8String

Short summary

This function creates a code point array from an UTF-8 string and writes to the given codepoint buffer.

Example:

myString :String := 'Test';
myCodepoints :Array[0..10] OF UnicodeCodepoint;
codepointCount :UDINT;
------------------
GetCodepointsFromUtf8String(
	utf8StringAddress := ADR(myString),
	utf8StringByteCount := GetUtf8StringLength(myString),
	codePointBuffer := ADR(myCodepoints),
	bufferSize := SIZEOF(myCodepoints),
	codePointsCount => codepointCount
);

• Return type: UDINT

Parameters

Name	Type	Comment	Kind
utf8StringAddress	POINTER TO BYTE	pointer to utf-8 string buffer	input
utf8StringByteCount	UDINT	length of the utf-8 string in bytes	input
codePointBuffer	POINTER TO UnicodeCodePoint	buffer where the codepoint sequence is stored	input
bufferSize	UDINT	size of the codepoint buffer in bytes, e.g. SIZEOF(codePointBuffer)	input
codePointsCount	UDINT	number of decoded codepoints	output

Code

Declaration

FUNCTION GetCodepointsFromUtf8String
VAR_INPUT
	(* pointer to utf-8 string buffer *)
	utf8StringAddress	:POINTER TO BYTE;
	(* length of the utf-8 string in bytes *)
	utf8StringByteCount	:UDINT;
	(* buffer where the codepoint sequence is stored *)
	codePointBuffer	:POINTER TO UnicodeCodePoint;
	(*size of the codepoint buffer in bytes, e.g. SIZEOF(codePointBuffer)*)
	bufferSize :UDINT;
END_VAR
VAR_OUTPUT	
	(* number of decoded codepoints *)
	codePointsCount		:UDINT := 0;
END_VAR
VAR CONSTANT
	END_OF_STRING		:BYTE := 16#00;
END_VAR
VAR
	byteIndex			:UDINT;
	octetCount			:BYTE(1..4);
END_VAR

Implementation

RETURN((utf8StringAddress = 0) OR_ELSE (codePointBuffer = 0));

WHILE (byteIndex < utf8StringByteCount AND_THEN utf8StringAddress[byteIndex] <> END_OF_STRING) DO
	octetCount := GetOctetCountByFirstOctet(utf8StringAddress[byteIndex]);
	
	IF (octetCount = 0) THEN	
		codePointsCount := 0;
		RETURN;
	END_IF

	IF (octetCount <= utf8StringByteCount - byteIndex) 
		AND_THEN ( codePointsCount*4 < bufferSize )
	THEN
		codePointBuffer[codePointsCount] := DecodeCodepointFromOctets(ADR(utf8StringAddress[byteIndex]), octetCount);
		
		byteIndex := byteIndex + octetCount;		
		codePointsCount := codePointsCount + 1;
	ELSE
		RETURN;
	END_IF
END_WHILE