Skip to content

Tweak Rune.DecodeFromUtf8 #68799

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
May 10, 2022
Merged

Tweak Rune.DecodeFromUtf8 #68799

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7b196f8
Tweak Rune.DecodeFromUtf8
stephentoub May 3, 2022
2bb7491
Address PR feedback
stephentoub May 3, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
73 changes: 34 additions & 39 deletions src/libraries/System.Private.CoreLib/src/System/Text/Rune.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -395,46 +395,38 @@ public static OperationStatus DecodeFromUtf8(ReadOnlySpan<byte> source, out Rune
// it tries to consume as many code units as possible as long as those code
// units constitute the beginning of a longer well-formed subsequence per Table 3-7.

int index = 0;

// Try reading input[0].
// Try reading source[0].

if ((uint)index >= (uint)source.Length)
int index = 0;
if (source.IsEmpty)
{
goto NeedsMoreData;
}

uint tempValue = source[index];
if (!UnicodeUtility.IsAsciiCodePoint(tempValue))
uint tempValue = source[0];
if (UnicodeUtility.IsAsciiCodePoint(tempValue))
{
goto NotAscii;
bytesConsumed = 1;
result = UnsafeCreate(tempValue);
return OperationStatus.Done;
}

Finish:

bytesConsumed = index + 1;
Debug.Assert(1 <= bytesConsumed && bytesConsumed <= 4); // Valid subsequences are always length [1..4]
result = UnsafeCreate(tempValue);
return OperationStatus.Done;

NotAscii:

// Per Table 3-7, the beginning of a multibyte sequence must be a code unit in
// the range [C2..F4]. If it's outside of that range, it's either a standalone
// continuation byte, or it's an overlong two-byte sequence, or it's an out-of-range
// four-byte sequence.

// Try reading source[1].

index = 1;
if (!UnicodeUtility.IsInRangeInclusive(tempValue, 0xC2, 0xF4))
{
goto FirstByteInvalid;
goto Invalid;
}

tempValue = (tempValue - 0xC2) << 6;

// Try reading input[1].

index++;
if ((uint)index >= (uint)source.Length)
if (source.Length <= 1)
{
goto NeedsMoreData;
}
Expand All @@ -443,7 +435,7 @@ public static OperationStatus DecodeFromUtf8(ReadOnlySpan<byte> source, out Rune
// complement representation is in the range [-65..-128]. This allows us to
// perform a single comparison to see if a byte is a continuation byte.

int thisByteSignExtended = (sbyte)source[index];
int thisByteSignExtended = (sbyte)source[1];
if (thisByteSignExtended >= -64)
{
goto Invalid;
Expand Down Expand Up @@ -485,15 +477,15 @@ public static OperationStatus DecodeFromUtf8(ReadOnlySpan<byte> source, out Rune
// The first two bytes were just fine. We don't need to perform any other checks
// on the remaining bytes other than to see that they're valid continuation bytes.

// Try reading input[2].
// Try reading source[2].

index++;
if ((uint)index >= (uint)source.Length)
index = 2;
if (source.Length <= 2)
{
goto NeedsMoreData;
}

thisByteSignExtended = (sbyte)source[index];
thisByteSignExtended = (sbyte)source[2];
if (thisByteSignExtended >= -64)
{
goto Invalid; // this byte is not a UTF-8 continuation byte
Expand All @@ -510,15 +502,15 @@ public static OperationStatus DecodeFromUtf8(ReadOnlySpan<byte> source, out Rune
goto Finish; // this is a valid 3-byte sequence
}

// Try reading input[3].
// Try reading source[3].

index++;
if ((uint)index >= (uint)source.Length)
index = 3;
if (source.Length <= 3)
{
goto NeedsMoreData;
}

thisByteSignExtended = (sbyte)source[index];
thisByteSignExtended = (sbyte)source[3];
if (thisByteSignExtended >= -64)
{
goto Invalid; // this byte is not a UTF-8 continuation byte
Expand All @@ -529,26 +521,29 @@ public static OperationStatus DecodeFromUtf8(ReadOnlySpan<byte> source, out Rune
tempValue += 0x80; // remove the continuation byte marker
tempValue -= (0xF0 - 0xE0) << 18; // remove the leading byte marker

// Valid 4-byte sequence
UnicodeDebug.AssertIsValidSupplementaryPlaneScalar(tempValue);
goto Finish; // this is a valid 4-byte sequence

FirstByteInvalid:
Finish:

index = 1; // Invalid subsequences are always at least length 1.
bytesConsumed = index + 1;
Debug.Assert(1 <= bytesConsumed && bytesConsumed <= 4); // Valid subsequences are always length [1..4]
result = UnsafeCreate(tempValue);
return OperationStatus.Done;

Invalid:
NeedsMoreData:

Debug.Assert(1 <= index && index <= 3); // Invalid subsequences are always length 1..3
Debug.Assert(0 <= index && index <= 3); // Incomplete subsequences are always length 0..3
bytesConsumed = index;
result = ReplacementChar;
return OperationStatus.InvalidData;
return OperationStatus.NeedMoreData;

NeedsMoreData:
Invalid:

Debug.Assert(0 <= index && index <= 3); // Incomplete subsequences are always length 0..3
Debug.Assert(1 <= index && index <= 3); // Invalid subsequences are always length 1..3
bytesConsumed = index;
result = ReplacementChar;
return OperationStatus.NeedMoreData;
return OperationStatus.InvalidData;
}

/// <summary>
Expand Down