Skip to content
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

Jump to bottom

⚡ Completely remove back tracking #98

Merged
merged 4 commits into from
Aug 9, 2023
Merged

⚡ Completely remove back tracking #98

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
aae1a18
Completely remove back-tracking
greymistcube Aug 5, 2023
f639499
Remove unnecessary array allocation
greymistcube Aug 5, 2023
82812ff
Cleanup
greymistcube Aug 5, 2023
d5c1493
Changelog
greymistcube Aug 5, 2023
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
155 changes: 35 additions & 120 deletions Bencodex/Decoder.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,10 +12,8 @@ namespace Bencodex
{
internal sealed class Decoder
{
private readonly byte[] _tinyBuffer = new byte[1];
private readonly Stream _stream;
private byte _lastRead;
private bool _didBack;
private int _offset;

public Decoder(Stream stream)
Expand All @@ -24,7 +22,6 @@ public Decoder(Stream stream)
// with BufferedStream: stream = new BufferedStream(stream);
_stream = stream;
_lastRead = 0;
_didBack = false;
_offset = 0;
}

Expand Down Expand Up @@ -95,21 +92,8 @@ public IValue Decode()

return new Dictionary(builder.ToImmutable());

case 0x30: // '0'
case 0x31: // '1'
case 0x32: // '2'
case 0x33: // '3'
case 0x34: // '4'
case 0x35: // '5'
case 0x36: // '6'
case 0x37: // '7'
case 0x38: // '8'
case 0x39: // '9'
Back();
default:
return ReadBinary();

case { } b:
throw new DecodingException($"An unexpected byte 0x{b:x} at {_offset - 1}.");
}
}

Expand All @@ -123,107 +107,57 @@ public IValue Decode()
case 0x75: // 'u':
return ReadTextAfterPrefix();

case 0x30: // '0'
case 0x31: // '1'
case 0x32: // '2'
case 0x33: // '3'
case 0x34: // '4'
case 0x35: // '5'
case 0x36: // '6'
case 0x37: // '7'
case 0x38: // '8'
case 0x39: // '9'
Back();
default:
return ReadBinary();

case { } b:
throw new DecodingException(
$"Expected a dictionary key, but got an unexpected byte 0x{b:x} at " +
$"{_offset - 1}."
);
}
}

private byte[] Read(byte[] buffer)
/// <summary>
/// Fills given <paramref name="buffer"/> from the internal <see cref="Stream"/>.
/// </summary>
/// <param name="buffer">The buffer to fill.</param>
/// <exception cref="DecodingException">Thrown when the internal <see cref="Stream"/>
/// terminates before <paramref name="buffer"/> is completely filled.</exception>
/// <remarks>This is used only for decoding a <see cref="Text"/> or
/// a <see cref="Binary"/> after the separator token ':' has been consumed.
/// </remarks>
private void Read(byte[] buffer)
{
var length = buffer.Length;
if (_didBack)
{
buffer[0] = _lastRead;
length--;
}
int read = _stream.Read(buffer, 0, length);
_offset += read;

int correction = _didBack ? 1 : 0;
int read = _stream.Read(buffer, correction, length);
if (read < length)
{
Array.Resize(ref buffer, read + correction);
}

_offset += read + correction;
if (buffer.Length > 0)
{
_lastRead = buffer[buffer.Length - 1];
throw new DecodingException(
$"The byte stream terminates at {_offset}.");
}

_didBack = false;
return buffer;
}

private byte ReadByte()
{
if (_didBack)
{
_didBack = false;
_offset++;
return _lastRead;
}

int read = _stream.Read(_tinyBuffer, 0, 1);
if (read > 0)
{
_lastRead = _tinyBuffer[0];
}

_offset++;
_didBack = false;
return read == 0
int read = _stream.ReadByte();
_lastRead = read < 0
? throw new DecodingException($"The byte stream terminates unexpectedly at {_offset}.")
: _tinyBuffer[0];
: (byte)read;
_offset++;
return _lastRead;
}

// Checks end of stream. Should be called only once at the very end.
private bool EndOfStream()
{
if (_didBack)
{
return false;
}

return _stream.Read(_tinyBuffer, 0, 1) == 0;
}

private void Back()
{
if (_offset < 1)
{
throw new DecodingException(
"Unexpected internal error: failed to rewind the stream buffer."
);
}

_didBack = true;
_offset--;
return _stream.ReadByte() < 0;
}

// Reads the length portion for byte strings and unicode strings.
private int ReadLength()
private int ReadLength(bool peeked)
{
const byte colon = 0x3a; // ':'
const int asciiZero = 0x30; // '0'
int length = 0;

byte lastByte = ReadByte();
byte lastByte = peeked ? _lastRead : ReadByte();
while (lastByte != colon)
{
#pragma warning disable SA1131
Expand Down Expand Up @@ -340,49 +274,30 @@ private BigInteger ReadInteger()
}
}

private (byte[] ByteArray, int OffsetAfterColon) ReadByteArray()
{
int length = ReadLength();
if (length < 1)
{
return (Array.Empty<byte>(), _offset);
}

int pos = _offset;
byte[] buffer = new byte[length];
byte[] bytes = Read(buffer);
if (bytes.Length < length)
{
throw new DecodingException(
$"The byte stream terminates at {_offset} with insufficient " +
$"{length - bytes.Length} bytes."
);
}

return (bytes, pos);
}

private Binary ReadBinary()
{
(byte[] bytes, _) = ReadByteArray();
return new Binary(bytes);
int length = ReadLength(peeked: true);
byte[] buffer = new byte[length];
Read(buffer);
return new Binary(buffer);
}

private Text ReadTextAfterPrefix()
{
(byte[] bytes, int pos) = ReadByteArray();
int start = _offset - 1;
int length = ReadLength(peeked: false);
byte[] buffer = new byte[length];
Read(buffer);

string textContent;
try
{
textContent = Encoding.UTF8.GetString(bytes);
return new Text(Encoding.UTF8.GetString(buffer));
}
catch (ArgumentException e)
{
throw new DecodingException($"Expected a UTF-8 sequence at {pos}.", e);
throw new DecodingException(
$"Failed to decode {nameof(Text)} starting from {start}.", e);
}

return new Text(textContent);
}
}
}
2 changes: 2 additions & 0 deletions CHANGES.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,8 +9,10 @@ To be released.
- Fixed a bug where a wrongly encoded `byte[]` could be decoded into
an `Integer`. [[#97]]
- Optimized decoding `Integer`s both for speed and memory. [[#97]]
- Optimized for faster decoding on encoded `List`s and `Dictionary`s. [[#98]]

[#97]: https://github.com/planetarium/bencodex.net/pull/97
[#98]: https://github.com/planetarium/bencodex.net/pull/98


Version 0.13.0
Expand Down
Loading