Created
March 19, 2024 15:13
-
-
Save lemire/bb56fa88129b4c3e84c45271f51acce2 to your computer and use it in GitHub Desktop.
core utf-8 validation algorithm in C#
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Vector128<byte> shuf1 = Vector128.Create(TOO_LONG, TOO_LONG, TOO_LONG, TOO_LONG, | |
TOO_LONG, TOO_LONG, TOO_LONG, TOO_LONG, | |
TWO_CONTS, TWO_CONTS, TWO_CONTS, TWO_CONTS, | |
TOO_SHORT | OVERLONG_2, | |
TOO_SHORT, | |
TOO_SHORT | OVERLONG_3 | SURROGATE, | |
TOO_SHORT | TOO_LARGE | TOO_LARGE_1000 | OVERLONG_4); | |
Vector128<byte> shuf2 = Vector128.Create(CARRY | OVERLONG_3 | OVERLONG_2 | OVERLONG_4, | |
CARRY | OVERLONG_2, | |
CARRY, | |
CARRY, | |
CARRY | TOO_LARGE, | |
CARRY | TOO_LARGE | TOO_LARGE_1000, | |
CARRY | TOO_LARGE | TOO_LARGE_1000, | |
CARRY | TOO_LARGE | TOO_LARGE_1000, | |
CARRY | TOO_LARGE | TOO_LARGE_1000, | |
CARRY | TOO_LARGE | TOO_LARGE_1000, | |
CARRY | TOO_LARGE | TOO_LARGE_1000, | |
CARRY | TOO_LARGE | TOO_LARGE_1000, | |
CARRY | TOO_LARGE | TOO_LARGE_1000, | |
CARRY | TOO_LARGE | TOO_LARGE_1000 | SURROGATE, | |
CARRY | TOO_LARGE | TOO_LARGE_1000, | |
CARRY | TOO_LARGE | TOO_LARGE_1000); | |
Vector128<byte> shuf3 = Vector128.Create(TOO_SHORT, TOO_SHORT, TOO_SHORT, TOO_SHORT, | |
TOO_SHORT, TOO_SHORT, TOO_SHORT, TOO_SHORT, | |
TOO_LONG | OVERLONG_2 | TWO_CONTS | OVERLONG_3 | TOO_LARGE_1000 | OVERLONG_4, | |
TOO_LONG | OVERLONG_2 | TWO_CONTS | OVERLONG_3 | TOO_LARGE, | |
TOO_LONG | OVERLONG_2 | TWO_CONTS | SURROGATE | TOO_LARGE, | |
TOO_LONG | OVERLONG_2 | TWO_CONTS | SURROGATE | TOO_LARGE, | |
TOO_SHORT, TOO_SHORT, TOO_SHORT, TOO_SHORT); | |
Vector128<byte> thirdByte = Vector128.Create((byte)(0b11100000u - 0x80)); | |
Vector128<byte> fourthByte = Vector128.Create((byte)(0b11110000u - 0x80)); | |
Vector128<byte> v0f = Vector128.Create((byte)0x0F); | |
Vector128<byte> v80 = Vector128.Create((byte)0x80); | |
// Performance note: we could process 64 bytes at a time for better speed in some cases. | |
for (; processedLength + 16 <= inputLength; processedLength += 16) | |
{ | |
Vector128<byte> currentBlock = AdvSimd.LoadVector128(pInputBuffer + processedLength); | |
if (AdvSimd.Arm64.MaxAcross(currentBlock).ToScalar() > 127) | |
{ | |
// We have an ASCII block, no need to process it, but | |
// we need to check if the previous block was incomplete. | |
if (AdvSimd.Arm64.MaxAcross(prevIncomplete).ToScalar() != 0) | |
{ | |
return SimdUnicode.UTF8.RewindAndValidateWithErrors(processedLength, pInputBuffer + processedLength, inputLength - processedLength); | |
} | |
prevIncomplete = Vector128<byte>.Zero; | |
} | |
else | |
{ | |
// Contains non-ASCII characters, we need to do non-trivial processing | |
//vextq | |
Vector128<byte> prev1 = AdvSimd.ExtractVector128(prevInputBlock, currentBlock, (byte)(16 - 1)); | |
Vector128<byte> byte_1_high = Vector128.Shuffle(shuf1, AdvSimd.ShiftRightLogical(prev1.AsUInt16(), 4).AsByte() & v0f); | |
Vector128<byte> byte_1_low = Vector128.Shuffle(shuf2, (prev1 & v0f)); | |
Vector128<byte> byte_2_high = Vector128.Shuffle(shuf3, AdvSimd.ShiftRightLogical(currentBlock.AsUInt16(), 4).AsByte() & v0f); | |
Vector128<byte> sc = AdvSimd.And(AdvSimd.And(byte_1_high, byte_1_low), byte_2_high); | |
Vector128<byte> prev2 = AdvSimd.ExtractVector128 (prevInputBlock, currentBlock, (byte)(16 - 2)); | |
Vector128<byte> prev3 = AdvSimd.ExtractVector128 (prevInputBlock, currentBlock, (byte)(16 - 3)); | |
prevInputBlock = currentBlock; | |
Vector128<byte> isThirdByte = AdvSimd.SubtractSaturate(prev2, thirdByte); | |
Vector128<byte> isFourthByte = AdvSimd.SubtractSaturate(prev3, fourthByte); | |
Vector128<byte> must23 = AdvSimd.Or(isThirdByte, isFourthByte); | |
Vector128<byte> must23As80 = AdvSimd.And(must23, v80); | |
Vector128<byte> error = AdvSimd.Xor(must23As80, sc); | |
if (AdvSimd.Arm64.MaxAcross(error).ToScalar() != 0) | |
{ | |
return SimdUnicode.UTF8.RewindAndValidateWithErrors(processedLength, pInputBuffer + processedLength, inputLength - processedLength); | |
} | |
prevIncomplete = AdvSimd.SubtractSaturate(currentBlock, maxValue); | |
} | |
} | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment