Add APIs to BlobBuilder for customizing the underlying byte array et al.
#115294
+621
−456
There are no files selected for viewing
This file contains hidden or 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
This file contains hidden or 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
This file contains hidden or 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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,11 +1,16 @@ | ||
| // Licensed to the .NET Foundation under one or more agreements. | ||
| // The .NET Foundation licenses this file to you under the MIT license. | ||
|
|
||
| using System.Buffers; | ||
| using System.Buffers.Binary; | ||
| using System.Diagnostics; | ||
| using System.Reflection.Internal; | ||
| using System.Runtime.CompilerServices; | ||
| using System.Runtime.InteropServices; | ||
| using System.Text; | ||
| #if NET | ||
| using System.Text.Unicode; | ||
| #endif | ||
|
|
||
| namespace System.Reflection | ||
| { | ||
|
|
@@ -123,148 +128,135 @@ public static void WriteGuid(this byte[] buffer, int start, Guid value) | |
| #endif | ||
| } | ||
|
|
||
| #if NET | ||
| public static void WriteUtf8(ReadOnlySpan<char> source, Span<byte> destination, out int charsRead, out int bytesWritten, bool allowUnpairedSurrogates) | ||
teo-tsirpanis marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| { | ||
| int sourceLength = source.Length; | ||
| int destinationLength = destination.Length; | ||
|
|
||
| while (true) | ||
| { | ||
| OperationStatus status = Utf8.FromUtf16(source, destination, out int consumed, out int written, replaceInvalidSequences: !allowUnpairedSurrogates, isFinalBlock: true); | ||
| source = source.Slice(consumed); | ||
| destination = destination.Slice(written); | ||
|
|
||
| if (status <= OperationStatus.DestinationTooSmall) | ||
| { | ||
| break; | ||
| } | ||
|
|
||
| // NeedsMoreData is not expected because isFinalBlock is set to true. | ||
| Debug.Assert(status == OperationStatus.InvalidData); | ||
| // If we don't allow unpaired surrogates, they should have been replaced by FromUtf16. | ||
| Debug.Assert(allowUnpairedSurrogates); | ||
| char c = source[0]; | ||
| Debug.Assert(char.IsSurrogate(c)); | ||
| if (destination.Length < 3) | ||
| { | ||
| break; | ||
| } | ||
| destination[0] = (byte)(((c >> 12) & 0xF) | 0xE0); | ||
| destination[1] = (byte)(((c >> 6) & 0x3F) | 0x80); | ||
| destination[2] = (byte)((c & 0x3F) | 0x80); | ||
| source = source.Slice(1); | ||
| destination = destination.Slice(3); | ||
| } | ||
|
|
||
| charsRead = sourceLength - source.Length; | ||
| bytesWritten = destinationLength - destination.Length; | ||
| } | ||
| #else | ||
| public static void WriteUtf8(ReadOnlySpan<char> source, Span<byte> destination, out int charsRead, out int bytesWritten, bool allowUnpairedSurrogates) | ||
|
Member
There was a problem hiding this comment. Does this need to change at all? If this is for .NET Framework, I would just leave it as-is. There is little benefit to changing anything due to possibility of regressions.
Contributor
Author
There was a problem hiding this comment. Yes. The method's old signature was harder to work with; it uses pointers, does not clearly state which buffer is read-only, and requires pre-computing the UTF-8 byte count. I had to refactor SRM's UTF-8 encoder1 in order to improve code reusability and memory safety in modern frameworks, and take advantage of the Another idea if we want to avoid the extra package dependency, is to vendor the sources of Footnotes |
||
| { | ||
| const char ReplacementCharacter = '\uFFFD'; | ||
|
|
||
| int sourceLength = source.Length; | ||
| int destinationLength = destination.Length; | ||
|
|
||
| unsafe | ||
| { | ||
| fixed (char* pSource = &MemoryMarshal.GetReference(source)) | ||
| fixed (byte* pDestination = &MemoryMarshal.GetReference(destination)) | ||
| { | ||
| char* src = pSource, srcEnd = pSource + source.Length; | ||
| byte* dst = pDestination, dstEnd = pDestination + destination.Length; | ||
|
|
||
| while (src < srcEnd) | ||
| { | ||
| char c = *src; | ||
| if (c < 0x80) | ||
| { | ||
| if (dstEnd - dst < 1) | ||
| { | ||
| break; | ||
| } | ||
| *dst++ = (byte)c; | ||
| src++; | ||
| } | ||
| else if (c < 0x7FF) | ||
| { | ||
| if (dstEnd - dst < 2) | ||
| { | ||
| break; | ||
| } | ||
| *dst++ = (byte)((c >> 6) | 0xC0); | ||
| *dst++ = (byte)((c & 0x3F) | 0x80); | ||
| src++; | ||
| } | ||
| else | ||
| { | ||
| if (char.IsSurrogate(c)) | ||
| { | ||
| // surrogate pair | ||
| if (char.IsHighSurrogate(c) && src - srcEnd < 2 && src[1] is char cLow && char.IsLowSurrogate(cLow)) | ||
| { | ||
| if (dstEnd - dst < 4) | ||
| { | ||
| break; | ||
| } | ||
| int codepoint = ((c - 0xd800) << 10) + cLow - 0xdc00 + 0x10000; | ||
| *dst++ = (byte)((codepoint >> 18) | 0xF0); | ||
| *dst++ = (byte)(((codepoint >> 12) & 0x3F) | 0x80); | ||
| *dst++ = (byte)(((codepoint >> 6) & 0x3F) | 0x80); | ||
| *dst++ = (byte)((codepoint & 0x3F) | 0x80); | ||
| src += 2; | ||
| continue; | ||
| } | ||
|
|
||
| // unpaired high/low surrogate | ||
| if (!allowUnpairedSurrogates) | ||
| { | ||
| c = ReplacementCharacter; | ||
| } | ||
| } | ||
|
|
||
| if (dstEnd - dst < 3) | ||
| { | ||
| break; | ||
| } | ||
| *dst++ = (byte)((c >> 12) | 0xE0); | ||
| *dst++ = (byte)(((c >> 6) & 0x3F) | 0x80); | ||
| *dst++ = (byte)((c & 0x3F) | 0x80); | ||
| src++; | ||
| } | ||
| } | ||
|
|
||
| charsRead = (int)(src - pSource); | ||
| bytesWritten = (int)(dst - pDestination); | ||
| } | ||
| } | ||
| } | ||
| #endif | ||
|
|
||
| #if !NET | ||
AaronRobinsonMSFT marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| internal static unsafe int GetByteCount(this Encoding encoding, ReadOnlySpan<char> str) | ||
| { | ||
| fixed (char* ptr = &MemoryMarshal.GetReference(str)) | ||
| { | ||
| return encoding.GetByteCount(ptr, str.Length); | ||
| } | ||
| } | ||
| #endif | ||
|
|
||
| [MethodImpl(MethodImplOptions.AggressiveInlining)] | ||
| internal static void ValidateRange(int bufferLength, int start, int byteCount, string byteCountParameterName) | ||
|
|
||
This file contains hidden or 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
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.