Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
8 changes: 8 additions & 0 deletions Morpheus.Tests/SimHasherTests.cs
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,14 @@ namespace Morpheus.Tests;

public class SimHasherTests
{
[Theory]
[InlineData("a ! b", "a b")]
[InlineData("a \u0301 b", "a b")]
public void Normalize_CollapsesWhitespaceAcrossRemovedCharacters(string input, string expected)
{
Assert.Equal(expected, SimHasher.Normalize(input));
}

[Fact]
public void ComputeSimHash_ReturnsZeroHashForVeryShortNormalizedText()
{
Expand Down
3 changes: 2 additions & 1 deletion Utilities/Text/SimHasher.cs
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,6 @@ public static string Normalize(string input)
}
continue;
}
lastWasSpace = false;

// Strip combining marks (diacritics)
var cat = CharUnicodeInfo.GetUnicodeCategory(ch.ToString(), 0);
Expand All @@ -42,6 +41,7 @@ public static string Normalize(string input)
if (Rune.IsDigit(ch))
{
sb.Append('0');
lastWasSpace = false;
continue;
}

Expand All @@ -50,6 +50,7 @@ public static string Normalize(string input)
continue;

sb.Append(ch.ToString());
lastWasSpace = false;
}

var result = sb.ToString().Trim();
Expand Down