Refactor AcBinary string markers; charset/test renames
- Replace single String marker with StringLen8/16/32 (167–169) for explicit string length encoding (1/2/4 bytes) - Update serialization/deserialization logic and marker checks for new scheme - Rename charset suffixes: Latin1FixAscii → AsciiFix, add Latin1Fix (5-char Hungarian) - Update menu, argument parsing, and references for new charset/test names and order - Swap MaxDepthBehavior enum values: Throw=0, Truncate=1 - Update comments and docs for new marker and charset conventions
This commit is contained in:
parent
7f677418af
commit
c2a22e5215
|
|
@ -90,17 +90,18 @@ public static class BdnSummaryAdapter
|
|||
var s = BenchmarkTestDataProvider.LongStringSuffix;
|
||||
return s switch
|
||||
{
|
||||
CharsetSuffixes.Latin1FixAscii => "Latin1FixAscii",
|
||||
CharsetSuffixes.AsciiShort => "AsciiShort",
|
||||
CharsetSuffixes.AsciiLong => "AsciiLong",
|
||||
CharsetSuffixes.Latin1Short => "Latin1Short",
|
||||
CharsetSuffixes.Latin1Long => "Latin1Long",
|
||||
CharsetSuffixes.CjkBmpShort => "CjkBmpShort",
|
||||
CharsetSuffixes.CjkBmpLong => "CjkBmpLong",
|
||||
CharsetSuffixes.CyrillicShort => "CyrillicShort",
|
||||
CharsetSuffixes.CyrillicLong => "CyrillicLong",
|
||||
CharsetSuffixes.MixedShort => "MixedShort",
|
||||
CharsetSuffixes.MixedLong => "MixedLong",
|
||||
CharsetSuffixes.AsciiFix => nameof(CharsetSuffixes.AsciiFix),
|
||||
CharsetSuffixes.AsciiShort => nameof(CharsetSuffixes.AsciiShort),
|
||||
CharsetSuffixes.AsciiLong => nameof(CharsetSuffixes.AsciiLong),
|
||||
CharsetSuffixes.Latin1Fix => nameof(CharsetSuffixes.Latin1Fix),
|
||||
CharsetSuffixes.Latin1Short => nameof(CharsetSuffixes.Latin1Short),
|
||||
CharsetSuffixes.Latin1Long => nameof(CharsetSuffixes.Latin1Long),
|
||||
CharsetSuffixes.CjkBmpShort => nameof(CharsetSuffixes.CjkBmpShort),
|
||||
CharsetSuffixes.CjkBmpLong => nameof(CharsetSuffixes.CjkBmpLong),
|
||||
CharsetSuffixes.CyrillicShort => nameof(CharsetSuffixes.CyrillicShort),
|
||||
CharsetSuffixes.CyrillicLong => nameof(CharsetSuffixes.CyrillicLong),
|
||||
CharsetSuffixes.MixedShort => nameof(CharsetSuffixes.MixedShort),
|
||||
CharsetSuffixes.MixedLong => nameof(CharsetSuffixes.MixedLong),
|
||||
_ => "Custom"
|
||||
};
|
||||
}
|
||||
|
|
|
|||
|
|
@ -86,17 +86,18 @@ internal static class Configuration
|
|||
|
||||
return s switch
|
||||
{
|
||||
CharsetSuffixes.Latin1FixAscii => "Latin1FixAscii",
|
||||
CharsetSuffixes.AsciiShort => "AsciiShort",
|
||||
CharsetSuffixes.AsciiLong => "AsciiLong",
|
||||
CharsetSuffixes.Latin1Short => "Latin1Short",
|
||||
CharsetSuffixes.Latin1Long => "Latin1Long",
|
||||
CharsetSuffixes.CjkBmpShort => "CjkBmpShort",
|
||||
CharsetSuffixes.CjkBmpLong => "CjkBmpLong",
|
||||
CharsetSuffixes.CyrillicShort => "CyrillicShort",
|
||||
CharsetSuffixes.CyrillicLong => "CyrillicLong",
|
||||
CharsetSuffixes.MixedShort => "MixedShort",
|
||||
CharsetSuffixes.MixedLong => "MixedLong",
|
||||
CharsetSuffixes.AsciiFix => nameof(CharsetSuffixes.AsciiFix),
|
||||
CharsetSuffixes.AsciiShort => nameof(CharsetSuffixes.AsciiShort),
|
||||
CharsetSuffixes.AsciiLong => nameof(CharsetSuffixes.AsciiLong),
|
||||
CharsetSuffixes.Latin1Fix => nameof(CharsetSuffixes.Latin1Fix),
|
||||
CharsetSuffixes.Latin1Short => nameof(CharsetSuffixes.Latin1Short),
|
||||
CharsetSuffixes.Latin1Long => nameof(CharsetSuffixes.Latin1Long),
|
||||
CharsetSuffixes.CjkBmpShort => nameof(CharsetSuffixes.CjkBmpShort),
|
||||
CharsetSuffixes.CjkBmpLong => nameof(CharsetSuffixes.CjkBmpLong),
|
||||
CharsetSuffixes.CyrillicShort => nameof(CharsetSuffixes.CyrillicShort),
|
||||
CharsetSuffixes.CyrillicLong => nameof(CharsetSuffixes.CyrillicLong),
|
||||
CharsetSuffixes.MixedShort => nameof(CharsetSuffixes.MixedShort),
|
||||
CharsetSuffixes.MixedLong => nameof(CharsetSuffixes.MixedLong),
|
||||
_ => "Custom"
|
||||
};
|
||||
}
|
||||
|
|
|
|||
|
|
@ -109,17 +109,18 @@ internal static class Menu
|
|||
System.Console.WriteLine();
|
||||
System.Console.WriteLine(" All *Short = 40 char, all *Long = 280 char (= Short × 7) — length-consistent across charsets.");
|
||||
System.Console.WriteLine();
|
||||
System.Console.WriteLine(" [1] Latin1FixAscii — empty suffix; baseline-only short values → FixStrAscii tier");
|
||||
System.Console.WriteLine(" [1] AsciiFix — empty suffix; baseline-only short values → FixStrAscii tier");
|
||||
System.Console.WriteLine(" [2] AsciiShort — 40 char pure ASCII (quic × 8) → StringAscii tier");
|
||||
System.Console.WriteLine(" [3] AsciiLong — 280 char pure ASCII → StringAscii tier");
|
||||
System.Console.WriteLine(" [4] Latin1Short — 40 char Hungarian (árví × 8) → StringSmall tier");
|
||||
System.Console.WriteLine(" [5] Latin1Long — 280 char Hungarian (default) → StringMedium tier");
|
||||
System.Console.WriteLine(" [6] CjkBmpShort — 40 char CJK BMP (3-byte runs) → StringSmall tier");
|
||||
System.Console.WriteLine(" [7] CjkBmpLong — 280 char CJK BMP → StringMedium tier");
|
||||
System.Console.WriteLine(" [8] CyrillicShort — 40 char Cyrillic (2-byte runs) → StringSmall tier");
|
||||
System.Console.WriteLine(" [9] CyrillicLong — 280 char Cyrillic → StringMedium tier");
|
||||
System.Console.WriteLine(" [0] MixedShort — 40 char multi-codepage → StringSmall tier");
|
||||
System.Console.WriteLine(" [A] MixedLong — 280 char multi-codepage → StringMedium tier");
|
||||
System.Console.WriteLine(" [4] Latin1Fix — 5 char Hungarian (árví) → FixStr-lean tier");
|
||||
System.Console.WriteLine(" [5] Latin1Short — 40 char Hungarian (árví × 8) → StringSmall tier");
|
||||
System.Console.WriteLine(" [6] Latin1Long — 280 char Hungarian (default) → StringMedium tier");
|
||||
System.Console.WriteLine(" [7] CjkBmpShort — 40 char CJK BMP (3-byte runs) → StringSmall tier");
|
||||
System.Console.WriteLine(" [8] CjkBmpLong — 280 char CJK BMP → StringMedium tier");
|
||||
System.Console.WriteLine(" [9] CyrillicShort — 40 char Cyrillic (2-byte runs) → StringSmall tier");
|
||||
System.Console.WriteLine(" [0] CyrillicLong — 280 char Cyrillic → StringMedium tier");
|
||||
System.Console.WriteLine(" [A] MixedShort — 40 char multi-codepage → StringSmall tier");
|
||||
System.Console.WriteLine(" [C] MixedLong — 280 char multi-codepage → StringMedium tier");
|
||||
System.Console.WriteLine(" [B] Back");
|
||||
System.Console.Write("\nSelection: ");
|
||||
|
||||
|
|
@ -129,8 +130,8 @@ internal static class Menu
|
|||
switch (char.ToLower(key))
|
||||
{
|
||||
case '1':
|
||||
BenchmarkTestDataProvider.LongStringSuffix = CharsetSuffixes.Latin1FixAscii;
|
||||
System.Console.WriteLine("✓ Charset set to Latin1FixAscii");
|
||||
BenchmarkTestDataProvider.LongStringSuffix = CharsetSuffixes.AsciiFix;
|
||||
System.Console.WriteLine("✓ Charset set to AsciiFix");
|
||||
return;
|
||||
case '2':
|
||||
BenchmarkTestDataProvider.LongStringSuffix = CharsetSuffixes.AsciiShort;
|
||||
|
|
@ -141,34 +142,38 @@ internal static class Menu
|
|||
System.Console.WriteLine("✓ Charset set to AsciiLong");
|
||||
return;
|
||||
case '4':
|
||||
BenchmarkTestDataProvider.LongStringSuffix = CharsetSuffixes.Latin1Fix;
|
||||
System.Console.WriteLine("✓ Charset set to Latin1Fix");
|
||||
return;
|
||||
case '5':
|
||||
BenchmarkTestDataProvider.LongStringSuffix = CharsetSuffixes.Latin1Short;
|
||||
System.Console.WriteLine("✓ Charset set to Latin1Short");
|
||||
return;
|
||||
case '5':
|
||||
case '6':
|
||||
BenchmarkTestDataProvider.LongStringSuffix = CharsetSuffixes.Latin1Long;
|
||||
System.Console.WriteLine("✓ Charset set to Latin1Long");
|
||||
return;
|
||||
case '6':
|
||||
case '7':
|
||||
BenchmarkTestDataProvider.LongStringSuffix = CharsetSuffixes.CjkBmpShort;
|
||||
System.Console.WriteLine("✓ Charset set to CjkBmpShort");
|
||||
return;
|
||||
case '7':
|
||||
case '8':
|
||||
BenchmarkTestDataProvider.LongStringSuffix = CharsetSuffixes.CjkBmpLong;
|
||||
System.Console.WriteLine("✓ Charset set to CjkBmpLong");
|
||||
return;
|
||||
case '8':
|
||||
case '9':
|
||||
BenchmarkTestDataProvider.LongStringSuffix = CharsetSuffixes.CyrillicShort;
|
||||
System.Console.WriteLine("✓ Charset set to CyrillicShort");
|
||||
return;
|
||||
case '9':
|
||||
case '0':
|
||||
BenchmarkTestDataProvider.LongStringSuffix = CharsetSuffixes.CyrillicLong;
|
||||
System.Console.WriteLine("✓ Charset set to CyrillicLong");
|
||||
return;
|
||||
case '0':
|
||||
case 'a':
|
||||
BenchmarkTestDataProvider.LongStringSuffix = CharsetSuffixes.MixedShort;
|
||||
System.Console.WriteLine("✓ Charset set to MixedShort");
|
||||
return;
|
||||
case 'a':
|
||||
case 'c':
|
||||
BenchmarkTestDataProvider.LongStringSuffix = CharsetSuffixes.MixedLong;
|
||||
System.Console.WriteLine("✓ Charset set to MixedLong");
|
||||
return;
|
||||
|
|
|
|||
|
|
@ -149,9 +149,10 @@ public static class Program
|
|||
{
|
||||
string? suffix = arg.ToLowerInvariant() switch
|
||||
{
|
||||
"latin1fixascii" => CharsetSuffixes.Latin1FixAscii,
|
||||
"asciifix" => CharsetSuffixes.AsciiFix,
|
||||
"asciishort" => CharsetSuffixes.AsciiShort,
|
||||
"asciilong" => CharsetSuffixes.AsciiLong,
|
||||
"latin1fix" => CharsetSuffixes.Latin1Fix,
|
||||
"latin1short" => CharsetSuffixes.Latin1Short,
|
||||
"latin1long" => CharsetSuffixes.Latin1Long,
|
||||
"cjkbmpshort" => CharsetSuffixes.CjkBmpShort,
|
||||
|
|
|
|||
|
|
@ -242,8 +242,10 @@ public partial class AcBinarySourceGenerator
|
|||
sb.AppendLine($"{i} case BinaryTypeCode.StringUtf16:");
|
||||
sb.AppendLine($"{i} {a} = context.ReadStringUtf16Marker();");
|
||||
sb.AppendLine($"{i} break;");
|
||||
sb.AppendLine($"{i} case BinaryTypeCode.String:");
|
||||
sb.AppendLine($"{i} {a} = context.ReadUniversalLongString();");
|
||||
sb.AppendLine($"{i} case BinaryTypeCode.StringLen8:");
|
||||
sb.AppendLine($"{i} case BinaryTypeCode.StringLen16:");
|
||||
sb.AppendLine($"{i} case BinaryTypeCode.StringLen32:");
|
||||
sb.AppendLine($"{i} {a} = context.ReadUniversalLongStringByMarker({tc});");
|
||||
sb.AppendLine($"{i} break;");
|
||||
// Interning first-occurrence cases — see comment above.
|
||||
if (enableInternString)
|
||||
|
|
|
|||
|
|
@ -32,7 +32,7 @@ public static class CharsetSuffixes
|
|||
|
||||
/// <summary>Empty suffix — baseline string property values stay short, hitting the
|
||||
/// <c>FixStrAscii</c> / short-string fast-path. Stress-test for short-string code paths.</summary>
|
||||
public const string Latin1FixAscii = "";
|
||||
public const string AsciiFix = "";
|
||||
|
||||
// ── Pure ASCII (every byte < 0x80) ──
|
||||
// Tier: StringAscii (167) — byte→char SIMD widening, zero UTF-8 decode.
|
||||
|
|
@ -47,6 +47,7 @@ public static class CharsetSuffixes
|
|||
// Tier: StringSmall (91) Short / StringMedium (94) Long.
|
||||
// UTF-8 byte count: ~72 byte Short (5 char base = 9 byte UTF-8: space+á+r+v+í), ~504 byte Long.
|
||||
private const string Latin1Base = " árví"; // 5 char (space + á + r + v + í) — multi-byte mix
|
||||
public const string Latin1Fix = Latin1Base; // 5 char (FixStr-lean profile)
|
||||
public const string Latin1Short = Latin1Base + Latin1Base + Latin1Base + Latin1Base
|
||||
+ Latin1Base + Latin1Base + Latin1Base + Latin1Base; // 40 char
|
||||
public const string Latin1Long = Latin1Short + Latin1Short + Latin1Short + Latin1Short
|
||||
|
|
|
|||
|
|
@ -110,6 +110,15 @@ public enum AcSerializerType : byte
|
|||
/// </summary>
|
||||
public enum MaxDepthBehavior : byte
|
||||
{
|
||||
/// <summary>
|
||||
/// Throw <see cref="System.InvalidOperationException"/> when depth limit is reached — cycle
|
||||
/// detection and bug surfacing. Recommended default: an over-depth payload is almost always a bug
|
||||
/// (circular reference without proper <see cref="ReferenceHandlingMode"/> tracking, or
|
||||
/// pathologically deep graph). The exception message reports the offending type and depth so the
|
||||
/// failure mode is debuggable rather than silent.
|
||||
/// </summary>
|
||||
Throw = 0,
|
||||
|
||||
/// <summary>
|
||||
/// Replace the over-depth value with a <c>Null</c> marker in the wire stream — intentional shallow
|
||||
/// serialization. Use when sending partial graphs (e.g., client → server delta updates, view-model
|
||||
|
|
@ -118,16 +127,7 @@ public enum MaxDepthBehavior : byte
|
|||
/// the consumer must encode that semantic in its protocol (e.g., "only modified properties are
|
||||
/// persisted; nested nulls are skipped, not overwritten").
|
||||
/// </summary>
|
||||
Truncate = 0,
|
||||
|
||||
/// <summary>
|
||||
/// Throw <see cref="System.InvalidOperationException"/> when depth limit is reached — cycle
|
||||
/// detection and bug surfacing. Recommended default: an over-depth payload is almost always a bug
|
||||
/// (circular reference without proper <see cref="ReferenceHandlingMode"/> tracking, or
|
||||
/// pathologically deep graph). The exception message reports the offending type and depth so the
|
||||
/// failure mode is debuggable rather than silent.
|
||||
/// </summary>
|
||||
Throw = 1,
|
||||
Truncate = 1,
|
||||
|
||||
/// <summary>
|
||||
/// Skip the depth limit check entirely — maximum hot-path performance. Use only when the developer
|
||||
|
|
|
|||
|
|
@ -700,7 +700,14 @@ public static partial class AcBinaryDeserializer
|
|||
[MethodImpl(MethodImplOptions.AggressiveInlining)]
|
||||
internal string ReadUniversalLongString()
|
||||
{
|
||||
ReadUniversalLongStringHeader(out var charLength, out var excess);
|
||||
ReadUniversalLongStringHeader(BinaryTypeCode.StringLen32, out var charLength, out var excess);
|
||||
return ReadStringByUnsignedExcess(charLength, excess);
|
||||
}
|
||||
|
||||
[MethodImpl(MethodImplOptions.AggressiveInlining)]
|
||||
internal string ReadUniversalLongStringByMarker(byte marker)
|
||||
{
|
||||
ReadUniversalLongStringHeader(marker, out var charLength, out var excess);
|
||||
return ReadStringByUnsignedExcess(charLength, excess);
|
||||
}
|
||||
|
||||
|
|
@ -712,9 +719,23 @@ public static partial class AcBinaryDeserializer
|
|||
}
|
||||
|
||||
[MethodImpl(MethodImplOptions.AggressiveInlining)]
|
||||
internal void ReadUniversalLongStringHeader(out int charLength, out uint excess)
|
||||
internal void ReadUniversalLongStringHeader(byte marker, out int charLength, out uint excess)
|
||||
{
|
||||
charLength = (int)ReadVarUInt();
|
||||
if (marker == BinaryTypeCode.StringLen8)
|
||||
{
|
||||
charLength = ReadByte();
|
||||
}
|
||||
else if (marker == BinaryTypeCode.StringLen16)
|
||||
{
|
||||
charLength = ReadUInt16Unsafe();
|
||||
}
|
||||
else
|
||||
{
|
||||
charLength = ReadInt32Unsafe();
|
||||
if (charLength < 0)
|
||||
throw new AcBinaryDeserializationException($"Invalid string header: negative charLength ({charLength}).", _position);
|
||||
}
|
||||
|
||||
var slotSize = BinaryTypeCode.GetUniversalStringExcessSlotSize(charLength);
|
||||
|
||||
if (slotSize == 1) excess = ReadByte();
|
||||
|
|
@ -804,8 +825,10 @@ public static partial class AcBinaryDeserializer
|
|||
case BinaryTypeCode.StringUtf16:
|
||||
value = ReadStringUtf16Marker();
|
||||
return true;
|
||||
case BinaryTypeCode.String:
|
||||
ReadUniversalLongStringHeader(out charLength, out excess);
|
||||
case BinaryTypeCode.StringLen8:
|
||||
case BinaryTypeCode.StringLen16:
|
||||
case BinaryTypeCode.StringLen32:
|
||||
ReadUniversalLongStringHeader(tc, out charLength, out excess);
|
||||
break;
|
||||
case BinaryTypeCode.Null:
|
||||
return true;
|
||||
|
|
@ -820,6 +843,7 @@ public static partial class AcBinaryDeserializer
|
|||
ReadUniversalFixStrHeader(tc, out charLength, out excess);
|
||||
break;
|
||||
}
|
||||
|
||||
// Interning marker, PropertySkip, or unknown — caller continues via short-circuit ||
|
||||
// to TryReadStringColdPath (interning types) or leaves the property at default.
|
||||
return false;
|
||||
|
|
|
|||
|
|
@ -105,7 +105,9 @@ public static partial class AcBinaryDeserializer
|
|||
// H2Q6 interning tier readers (Compact mode only — Big tier never engages on interning path)
|
||||
readers[BinaryTypeCode.StringInternFirstSmall] = static (ctx, _) => ctx.ReadAndRegisterInternedStringSmall();
|
||||
readers[BinaryTypeCode.StringInternFirstMedium] = static (ctx, _) => ctx.ReadAndRegisterInternedStringMedium();
|
||||
readers[BinaryTypeCode.String] = static (ctx, _) => ctx.ReadUniversalLongString();
|
||||
readers[BinaryTypeCode.StringLen8] = static (ctx, _) => ctx.ReadUniversalLongStringByMarker(BinaryTypeCode.StringLen8);
|
||||
readers[BinaryTypeCode.StringLen16] = static (ctx, _) => ctx.ReadUniversalLongStringByMarker(BinaryTypeCode.StringLen16);
|
||||
readers[BinaryTypeCode.StringLen32] = static (ctx, _) => ctx.ReadUniversalLongStringByMarker(BinaryTypeCode.StringLen32);
|
||||
readers[BinaryTypeCode.DateTime] = static (ctx, _) => ctx.ReadDateTimeUnsafe();
|
||||
readers[BinaryTypeCode.DateTimeOffset] = static (ctx, _) => ctx.ReadDateTimeOffsetUnsafe();
|
||||
readers[BinaryTypeCode.TimeSpan] = static (ctx, _) => ctx.ReadTimeSpanUnsafe();
|
||||
|
|
@ -1048,8 +1050,10 @@ public static partial class AcBinaryDeserializer
|
|||
case BinaryTypeCode.StringUtf16:
|
||||
propInfo.SetValue(target, context.ReadStringUtf16Marker());
|
||||
return true;
|
||||
case BinaryTypeCode.String:
|
||||
propInfo.SetValue(target, context.ReadUniversalLongString());
|
||||
case BinaryTypeCode.StringLen8:
|
||||
case BinaryTypeCode.StringLen16:
|
||||
case BinaryTypeCode.StringLen32:
|
||||
propInfo.SetValue(target, context.ReadUniversalLongStringByMarker(typeCode));
|
||||
return true;
|
||||
case BinaryTypeCode.StringEmpty:
|
||||
propInfo.SetValue(target, string.Empty);
|
||||
|
|
@ -2041,10 +2045,27 @@ public static partial class AcBinaryDeserializer
|
|||
case BinaryTypeCode.Decimal:
|
||||
context.Skip(16);
|
||||
return;
|
||||
case BinaryTypeCode.String:
|
||||
// Skip layout: [VarUInt charLength][unsigned excess slot][bytes]
|
||||
case BinaryTypeCode.StringLen8:
|
||||
case BinaryTypeCode.StringLen16:
|
||||
case BinaryTypeCode.StringLen32:
|
||||
// Skip layout: [charLength:1|2|4 by marker][unsigned excess slot][bytes]
|
||||
{
|
||||
var charLength = (int)context.ReadVarUInt();
|
||||
int charLength;
|
||||
if (typeCode == BinaryTypeCode.StringLen8)
|
||||
{
|
||||
charLength = context.ReadByte();
|
||||
}
|
||||
else if (typeCode == BinaryTypeCode.StringLen16)
|
||||
{
|
||||
charLength = context.ReadUInt16Unsafe();
|
||||
}
|
||||
else
|
||||
{
|
||||
charLength = context.ReadInt32Unsafe();
|
||||
if (charLength < 0)
|
||||
throw new AcBinaryDeserializationException($"Invalid string header while skipping: negative charLength ({charLength}).", context.Position);
|
||||
}
|
||||
|
||||
var slotSize = BinaryTypeCode.GetUniversalStringExcessSlotSize(charLength);
|
||||
var excess = slotSize switch
|
||||
{
|
||||
|
|
|
|||
|
|
@ -863,7 +863,7 @@ public static partial class AcBinarySerializer
|
|||
/// Header is fully determined before encode:
|
||||
/// <list type="bullet">
|
||||
/// <item><c>charLength <= 31</c>: <c>[FixStr(marker carries charLength)][unsigned excess:1]</c></item>
|
||||
/// <item><c>charLength > 31</c>: <c>[String][VarUInt(charLength)][unsigned excess:1|2|4]</c></item>
|
||||
/// <item><c>charLength > 31</c>: <c>[StringLen8|StringLen16|StringLen32][charLength:1|2|4][unsigned excess:1|2|4]</c></item>
|
||||
/// </list>
|
||||
/// Body is UTF-8-encoded exactly once to the final destination (<c>encodeStart</c>) — no post-encode
|
||||
/// body shift/copy. For the current path, <c>excess = bytesWritten - charLength</c> is expected to be
|
||||
|
|
@ -888,16 +888,16 @@ public static partial class AcBinarySerializer
|
|||
// Tight UTF-8 upper bound for valid UTF-16 input: max 3 bytes per UTF-16 code unit.
|
||||
var maxBytes = charLength * 3;
|
||||
var isFixStr = charLength <= BinaryTypeCode.FixStrMaxLength;
|
||||
var charLengthSize = isFixStr ? 0 : charLength <= byte.MaxValue ? 1 : charLength <= ushort.MaxValue ? 2 : 4;
|
||||
// IMPORTANT: the slot VALUE (excess) is not known before UTF-8 encode, but the slot SIZE is.
|
||||
// We reserve the slot by width (1/2/4) from charLength, so encodeStart is final and no body shift is needed.
|
||||
var slotSize = isFixStr ? 1 : BinaryTypeCode.GetUniversalStringExcessSlotSize(charLength);
|
||||
var varUIntSize = isFixStr ? 0 : VarUIntSize((uint)charLength);
|
||||
var headerSize = isFixStr ? 2 : 1 + varUIntSize + slotSize;
|
||||
var headerSize = isFixStr ? 2 : 1 + charLengthSize + slotSize;
|
||||
|
||||
EnsureCapacity(headerSize + maxBytes);
|
||||
|
||||
var headerPos = _position;
|
||||
var slotPos = isFixStr ? headerPos + 1 : headerPos + 1 + varUIntSize;
|
||||
var slotPos = isFixStr ? headerPos + 1 : headerPos + 1 + charLengthSize;
|
||||
var encodeStart = headerPos + headerSize;
|
||||
|
||||
if (isFixStr)
|
||||
|
|
@ -907,10 +907,22 @@ public static partial class AcBinarySerializer
|
|||
}
|
||||
else
|
||||
{
|
||||
// Universal long-form string marker + VarUInt(charLength) + unsigned excess slot.
|
||||
BufferAt(headerPos) = BinaryTypeCode.String;
|
||||
_position = headerPos + 1;
|
||||
WriteVarUIntUnsafe((uint)charLength);
|
||||
// Universal long-form markers with marker-coded charLength width.
|
||||
if (charLengthSize == 1)
|
||||
{
|
||||
BufferAt(headerPos) = BinaryTypeCode.StringLen8;
|
||||
BufferAt(headerPos + 1) = unchecked((byte)charLength);
|
||||
}
|
||||
else if (charLengthSize == 2)
|
||||
{
|
||||
BufferAt(headerPos) = BinaryTypeCode.StringLen16;
|
||||
Unsafe.WriteUnaligned(ref BufferAt(headerPos + 1), unchecked((ushort)charLength));
|
||||
}
|
||||
else
|
||||
{
|
||||
BufferAt(headerPos) = BinaryTypeCode.StringLen32;
|
||||
Unsafe.WriteUnaligned(ref BufferAt(headerPos + 1), charLength);
|
||||
}
|
||||
}
|
||||
|
||||
var status = System.Text.Unicode.Utf8.FromUtf16(value.AsSpan(), _buffer.AsSpan(encodeStart, maxBytes), out _, out var bytesWritten, replaceInvalidSequences: false);
|
||||
|
|
|
|||
|
|
@ -70,8 +70,8 @@ internal static class BinaryTypeCode
|
|||
// Marker 91 is reserved for FastWire UTF-16 payloads:
|
||||
// [StringUtf16][charLen:int32 LE][UTF-16 raw bytes]
|
||||
//
|
||||
// Universal compact-mode strings use FixStr (135..166) + String (167):
|
||||
// [FixStr] / [String][VarUInt charLen][unsigned excess slot][UTF-8 bytes]
|
||||
// Universal compact-mode strings use FixStr (135..166) + StringLen8/16/32 (167..169):
|
||||
// [FixStr] / [StringLenN][charLen:N][unsigned excess slot][UTF-8 bytes]
|
||||
//
|
||||
// Interning tiers keep dedicated markers.
|
||||
public const byte StringUtf16 = SlotCount + 27; // 91 — FastWire UTF-16 marker payload
|
||||
|
|
@ -128,15 +128,22 @@ internal static class BinaryTypeCode
|
|||
public const byte FixStrAsciiMax = FixStrMax;
|
||||
public const int FixStrAsciiMaxLength = FixStrMaxLength;
|
||||
|
||||
// Long universal string marker: 167
|
||||
// Layout: [String] [VarUInt charLength] [excess slot] [bytes]
|
||||
public const byte String = SlotCount + 103; // 167
|
||||
// Backward-compatible alias (old naming)
|
||||
public const byte StringAscii = String;
|
||||
// Long universal string markers (marker encodes charLength field width)
|
||||
// Layout:
|
||||
// StringLen8 (167): [marker][charLen:1][excess slot][bytes]
|
||||
// StringLen16 (168): [marker][charLen:2][excess slot][bytes]
|
||||
// StringLen32 (169): [marker][charLen:4][excess slot][bytes]
|
||||
public const byte StringLen8 = SlotCount + 103; // 167
|
||||
public const byte StringLen16 = SlotCount + 104; // 168
|
||||
public const byte StringLen32 = SlotCount + 105; // 169
|
||||
|
||||
// Reserved slot block: 168..175 (8 slots) for future string-related markers
|
||||
// (e.g., StringCompressed, StringEncoded, StringMixedAscii, etc.). Keeping the 135..167 range
|
||||
// dedicated to ASCII variants for clean range-checks (see IsAsciiString below).
|
||||
// Backward-compatible aliases
|
||||
public const byte String = StringLen32;
|
||||
public const byte StringAscii = StringLen32;
|
||||
|
||||
// Reserved slot block: 170..175 (6 slots) for future string-related markers
|
||||
// (e.g., StringCompressed, StringEncoded, StringMixedAscii, etc.). Keeping the 135..169 range
|
||||
// dedicated to universal compact string markers for clean range-checks (see IsString below).
|
||||
|
||||
// Flag-based header markers (must be 16-aligned for flag bits in lower nibble).
|
||||
// Header byte structure: (marker & 0xF0) == HeaderFlagsBase, flags in (marker & 0x0F).
|
||||
|
|
@ -186,7 +193,7 @@ internal static class BinaryTypeCode
|
|||
|| typeCode == StringEmpty
|
||||
|| typeCode == StringInternFirstSmall
|
||||
|| typeCode == StringInternFirstMedium
|
||||
|| (typeCode is >= FixStrBase and <= String); // 135..167: FixStr + String
|
||||
|| (typeCode is >= FixStrBase and <= StringLen32); // 135..169: FixStr + StringLen8/16/32
|
||||
|
||||
/// <summary>
|
||||
/// Check if type code is the FastWire UTF-16 string marker.
|
||||
|
|
@ -203,11 +210,11 @@ internal static class BinaryTypeCode
|
|||
=> typeCode == StringInternFirstSmall || typeCode == StringInternFirstMedium;
|
||||
|
||||
/// <summary>
|
||||
/// Check if type code is any universal string marker — FixStr (short) or String (long).
|
||||
/// Single contiguous range (135..167) for branch-friendly dispatch on the reader hot path.
|
||||
/// Check if type code is any universal string marker — FixStr (short) or StringLen8/16/32 (long).
|
||||
/// Single contiguous range (135..169) for branch-friendly dispatch on the reader hot path.
|
||||
/// </summary>
|
||||
[MethodImpl(MethodImplOptions.AggressiveInlining)]
|
||||
public static bool IsStringUniversalMarker(byte typeCode) => typeCode is >= FixStrBase and <= String;
|
||||
public static bool IsStringUniversalMarker(byte typeCode) => typeCode is >= FixStrBase and <= StringLen32;
|
||||
|
||||
[MethodImpl(MethodImplOptions.AggressiveInlining)]
|
||||
public static bool IsAsciiString(byte typeCode) => IsStringUniversalMarker(typeCode);
|
||||
|
|
|
|||
Loading…
Reference in New Issue