Skip to content

Correct truncation in calculations of byte and character counts. #80

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
ssg merged 1 commit into from
Jun 17, 2026
Merged

Correct truncation in calculations of byte and character counts. #80

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 3 additions & 3 deletions src/DividingCoder.cs
View file
Open in desktop

@marcasburnett marcasburnett Jun 16, 2026

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Alternatively, an approach like in this fix could be used.

Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ public abstract class DividingCoder<TAlphabet>(TAlphabet alphabet)
: IBaseCoder, INonAllocatingBaseCoder
where TAlphabet: CodingAlphabet
{
readonly int reductionFactor = Convert.ToInt32(1000 * Math.Log2(alphabet.Length) / 8);
readonly int reductionFactor = Convert.ToInt32(10_000 * Math.Log2(alphabet.Length) / 8);
readonly char zeroChar = alphabet.Value[0];

/// <summary>
Expand All @@ -40,7 +40,7 @@ public virtual int GetSafeByteCountForDecoding(ReadOnlySpan<char> text)
[MethodImpl(MethodImplOptions.AggressiveInlining)]
int getSafeByteCountForDecoding(int textLen, int zeroPrefixLen)
{
return zeroPrefixLen + ((textLen - zeroPrefixLen) * reductionFactor / 1000) + 1;
return zeroPrefixLen + ((textLen - zeroPrefixLen) * reductionFactor / 10_000) + 1;
}

[MethodImpl(MethodImplOptions.AggressiveInlining)]
Expand All @@ -62,7 +62,7 @@ public virtual int GetSafeCharCountForEncoding(ReadOnlySpan<byte> bytes)
[MethodImpl(MethodImplOptions.AggressiveInlining)]
int getSafeCharCountForEncoding(int bytesLen, int zeroPrefixLen)
{
return zeroPrefixLen + ((bytesLen - zeroPrefixLen) * 1000 / reductionFactor) + 1;
return zeroPrefixLen + ((bytesLen - zeroPrefixLen) * 10_000 / reductionFactor) + 1;
}

/// <summary>
Expand Down
17 changes: 16 additions & 1 deletion test/Base62/DefaultTest.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,5 +61,20 @@ public void TryDecode_ReturnsCorrectValues(string decoded, string encoded)
Assert.That(result, Is.True);
Assert.That(Encoding.UTF8.GetString(output[..bytesWritten]), Is.EqualTo(decoded));
}


[Test]
public void Roundtrip_DoesNotTruncateHighByte()
{
// https://github.com/ssg/SimpleBase/issues/79

// 2762 is the smallest length where (textLen * 744 / 1000) + 1 underestimates
// the required output buffer by 1, dropping the most-significant byte.
var bytes = new byte[2762];
Array.Fill(bytes, (byte)0xFF);

var encoded = Base62.Default.Encode(bytes);
var decoded = Base62.Default.Decode(encoded);

Assert.That(decoded, Is.EqualTo(bytes));
}
}