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.

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

FuzzyQuery produces a wrong result when prefix is equal to the term length #1002

Merged
merged 2 commits into from
Nov 4, 2024
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
44 changes: 43 additions & 1 deletion src/Lucene.Net.Tests/Search/TestFuzzyQuery.cs
Original file line number Diff line number Diff line change
Expand Up @@ -196,6 +196,48 @@ public virtual void TestFuzziness()
directory.Dispose();
}

// LUCENENET-specific: backported fix from Lucene 9.0.0 (lucene@45611d0, LUCENE-9365)
[Test]
public void TestPrefixLengthEqualStringLength()
{
Directory directory = NewDirectory();
RandomIndexWriter writer = new RandomIndexWriter(Random, directory);
AddDoc("b*a", writer);
AddDoc("b*ab", writer);
AddDoc("b*abc", writer);
AddDoc("b*abcd", writer);
const string multibyte = "아프리카코끼리속"; // LUCENENET-specific: made const
AddDoc(multibyte, writer);
IndexReader reader = writer.GetReader();
IndexSearcher searcher = NewSearcher(reader);
writer.Dispose();

int maxEdits = 0;
int prefixLength = 3;
FuzzyQuery query = new FuzzyQuery(new Term("field", "b*a"), maxEdits, prefixLength);
ScoreDoc[] hits = searcher.Search(query, 1000).ScoreDocs;
assertEquals(1, hits.Length);

maxEdits = 1;
query = new FuzzyQuery(new Term("field", "b*a"), maxEdits, prefixLength);
hits = searcher.Search(query, 1000).ScoreDocs;
assertEquals(2, hits.Length);

maxEdits = 2;
query = new FuzzyQuery(new Term("field", "b*a"), maxEdits, prefixLength);
hits = searcher.Search(query, 1000).ScoreDocs;
assertEquals(3, hits.Length);

maxEdits = 1;
prefixLength = multibyte.Length - 1;
query = new FuzzyQuery(new Term("field", multibyte.Substring(0, prefixLength)), maxEdits, prefixLength);
hits = searcher.Search(query, 1000).ScoreDocs;
assertEquals(1, hits.Length);

reader.Dispose();
directory.Dispose();
}

[Test]
public virtual void Test2()
{
Expand Down Expand Up @@ -384,4 +426,4 @@ private void AddDoc(string text, RandomIndexWriter writer)
writer.AddDocument(doc);
}
}
}
}
5 changes: 3 additions & 2 deletions src/Lucene.Net/Search/FuzzyQuery.cs
Original file line number Diff line number Diff line change
Expand Up @@ -148,7 +148,8 @@ public FuzzyQuery(Term term)

protected override TermsEnum GetTermsEnum(Terms terms, AttributeSource atts)
{
if (maxEdits == 0 || prefixLength >= term.Text.Length) // can only match if it's exact
// LUCENENET-specific: backported fix from Lucene 9.0.0 (lucene@45611d0, LUCENE-9365)
if (maxEdits == 0) // can only match if it's exact
{
return new SingleTermsEnum(terms.GetEnumerator(), term.Bytes);
}
Expand Down Expand Up @@ -262,4 +263,4 @@ public static int SingleToEdits(float minimumSimilarity, int termLen)
}
}
}
}
}
Loading