public static string Get_Location(DataConsumer <char> Stream)
{
return(Stream.AsMemory().Slice((int)Stream.LongPosition, 32).ToString());
}
public static bool Parse_FloatingPoint(DataConsumer <char> Stream, out double outValue)
{/* Docs: https://html.spec.whatwg.org/multipage/common-microsyntaxes.html#rules-for-parsing-floating-point-number-values */
if (Stream is null)
{
throw new ArgumentNullException(nameof(Stream));
}
Contract.EndContractBlock();
double value = 1;
double divisor = 1;
double exponent = 1;
/* Skip ASCII whitespace */
Stream.Consume_While(Is_Ascii_Whitespace);
if (Stream.Next == EOF)
{
throw new DomSyntaxError();
}
switch (Stream.Next)
{
case CHAR_HYPHEN_MINUS:
{
value = divisor = -1;
Stream.Consume();
}
break;
case CHAR_PLUS_SIGN:
{
Stream.Consume();
}
break;
}
if (Stream.Next == EOF)
{
throw new DomSyntaxError();
}
/* 9) If the character indicated by position is a U+002E FULL STOP (.),
* and that is not the last character in input,
* and the character after the character indicated by position is an ASCII digit,
* then set value to zero and jump to the step labeled fraction. */
if (Stream.Next == CHAR_FULL_STOP && Stream.NextNext != EOF && Is_Ascii_Digit(Stream.NextNext))
{
value = 0;
}
else if (!Is_Ascii_Digit(Stream.Next))
{
outValue = double.NaN;
return(false);
}
else
{
/* 11) Collect a sequence of code points that are ASCII digits from input given position, and interpret the resulting sequence as a base-ten integer. Multiply value by that integer. */
Stream.Consume_While(Is_Ascii_Digit, out ReadOnlySpan <char> outDigits);
value *= Digits_To_Base10(outDigits);//double.Parse(outDigits.ToString(), CultureInfo.InvariantCulture);
}
/* 12) If position is past the end of input, jump to the step labeled conversion. */
if (Stream.Next != EOF)
{
/* 13) Fraction: If the character indicated by position is a U+002E FULL STOP (.), run these substeps: */
if (Stream.Next == CHAR_FULL_STOP)
{
Stream.Consume();
/* 2) If position is past the end of input, or if the character indicated by position is not an ASCII digit, U+0065 LATIN SMALL LETTER E (e), or U+0045 LATIN CAPITAL LETTER E (E), then jump to the step labeled conversion. */
if (Stream.Next != EOF && (Is_Ascii_Digit(Stream.Next) || Stream.Next == CHAR_E_LOWER || Stream.Next == CHAR_E_UPPER))
{
/* 3) If the character indicated by position is a U+0065 LATIN SMALL LETTER E character (e) or a U+0045 LATIN CAPITAL LETTER E character (E), skip the remainder of these substeps. */
if (Is_Ascii_Digit(Stream.Next))
{
while (Is_Ascii_Digit(Stream.Next))
{
/* 4) Fraction loop: Multiply divisor by ten. */
divisor *= 10;
/* 5) Add the value of the character indicated by position, interpreted as a base-ten digit (0..9) and divided by divisor, to value. */
double n = Ascii_Digit_To_Value(Stream.Next) / divisor;
value += n;
/* 6) Advance position to the next character. */
Stream.Consume();
/* 7) If position is past the end of input, then jump to the step labeled conversion. */
if (Stream.Next == EOF)
{
break;
}
}
}
}
}
/* 14) If the character indicated by position is U+0065 (e) or a U+0045 (E), then: */
if (Stream.Next == CHAR_E_LOWER || Stream.Next == CHAR_E_UPPER)
{
Stream.Consume();
/* 2) If position is past the end of input, then jump to the step labeled conversion. */
/* 3) If the character indicated by position is a U+002D HYPHEN-MINUS character (-): */
if (Stream.Next == CHAR_HYPHEN_MINUS)
{
exponent = -1;
Stream.Consume();
}
else if (Stream.Next == CHAR_PLUS_SIGN)
{
Stream.Consume();
}
/* 4) If the character indicated by position is not an ASCII digit, then jump to the step labeled conversion. */
if (Is_Ascii_Digit(Stream.Next))
{
/* 5) Collect a sequence of code points that are ASCII digits from input given position, and interpret the resulting sequence as a base-ten integer. Multiply exponent by that integer. */
Stream.Consume_While(Is_Ascii_Digit, out ReadOnlySpan <char> outDigits);
exponent *= Digits_To_Base10(outDigits);//double.Parse(outDigits.ToString(), CultureInfo.InvariantCulture);
/* 6) Multiply value by ten raised to the exponentth power. */
value *= Math.Pow(10, exponent);
}
}
}
/* 15) Conversion: Let S be the set of finite IEEE 754 double-precision floating-point values except −0, but with two special values added: 2^1024 and −2^1024. */
/* 16) Let rounded-value be the number in S that is closest to value,
* selecting the number with an even significand if there are two equally close values.
* (The two special values 2^1024 and −2^1024 are considered to have even significands for this purpose.) */
var roundedValue = value;
if (roundedValue == -0D)
{
roundedValue = -roundedValue;
}
/* 17) If rounded-value is 2^1024 or −2^1024, return an error. */
if (roundedValue == double.MinValue || roundedValue == double.MaxValue)
{
outValue = double.NaN;
return(false);
}
/* 18) Return rounded-value. */
outValue = roundedValue;
return(true);
}
public static byte[] Percent_Decode(ReadOnlyMemory <byte> input)
{/* Docs: https://url.spec.whatwg.org/#percent-decode */
DataConsumer <byte> Stream = new DataConsumer <byte>(input, byte.MinValue);
/* Create a list of memory chunks that make up the final string */
ulong newLength = 0;
ulong?chunkStart = null;
ulong chunkCount = 0;
var chunks = new LinkedList <Tuple <ReadOnlyMemory <byte>, byte?> >();
while (!Stream.atEnd)
{
EFilterResult filterResult = EFilterResult.FILTER_ACCEPT;
byte? bytePoint = null;
if (Stream.Next == CHAR_PERCENT && Is_Ascii_Hex_Digit((char)Stream.NextNext) && Is_Ascii_Hex_Digit((char)Stream.NextNextNext))
{
filterResult = EFilterResult.FILTER_SKIP;
uint low = (uint)Ascii_Hex_To_Value((char)Stream.NextNext);
uint high = (uint)Ascii_Hex_To_Value((char)Stream.NextNextNext);
bytePoint = (byte)(low | (high >> 4));
Stream.Consume(2);
break;
}
/* When filter result:
* ACCEPT: Char should be included in chunk
* SKIP: Char should not be included in chunk, if at chunk-start shift chunk-start past char, otherwise end chunk
* REJECT: Char should not be included in chunk, current chunk ends
*/
bool end_chunk = false;
switch (filterResult)
{
case EFilterResult.FILTER_ACCEPT: // Char should be included in the chunk
{
if (!chunkStart.HasValue)
{
chunkStart = Stream.LongPosition; /* Start new chunk (if one isnt started yet) */
}
}
break;
case EFilterResult.FILTER_REJECT: // Char should not be included in chunk, current chunk ends
{
end_chunk = true;
}
break;
case EFilterResult.FILTER_SKIP: // Char should not be included in chunk, if at chunk-start shift chunk-start past char, otherwise end chunk
{
if (!chunkStart.HasValue)
{
chunkStart = Stream.LongPosition + 1; /* At chunk-start */
}
else
{
end_chunk = true;
}
}
break;
}
if (end_chunk || Stream.Remaining <= 1)
{
if (!chunkStart.HasValue)
{
chunkStart = Stream.LongPosition;
}
/* Push new chunk to our list */
var chunkSize = Stream.LongPosition - chunkStart.Value;
var Mem = Stream.AsMemory().Slice((int)chunkStart.Value, (int)chunkSize);
var chunk = new Tuple <ReadOnlyMemory <byte>, byte?>(Mem, bytePoint);
chunks.AddLast(chunk);
chunkCount++;
chunkStart = null;
newLength += chunkSize;
/* If we actually decoded a byte then account for it in the newLength */
if (filterResult != EFilterResult.FILTER_ACCEPT)
{
newLength++;
}
}
Stream.Consume();
}
/* Compile the string */
var dataPtr = new byte[newLength];
Memory <byte> data = new Memory <byte>(dataPtr);
ulong index = 0;
foreach (var tpl in chunks)
{
var chunk = tpl.Item1;
/* Copy chunk data */
chunk.CopyTo(data.Slice((int)index));
index += (ulong)chunk.Length;
if (tpl.Item2.HasValue)
{
data.Span[(int)index] = tpl.Item2.Value;
index++;
}
}
return(dataPtr);
}