Apache
/
lucene
mirror of https://github.com/apache/lucene.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

LUCENE-5221: SimilarityBase.computeNorm is inconsistent with TFIDFSimilarity 

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1524457 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Robert Muir 2013-09-18 15:29:11 +00:00
parent 60e7475519
commit 3eb1e1ac54
3 changed files with 22 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
lucene/CHANGES.txt
View File

@ -193,6 +193,10 @@ Bug Fixes
* LUCENE-5201: Fixed compression bug in LZ4.compressHC when the input is highly * LUCENE-5201: Fixed compression bug in LZ4.compressHC when the input is highly
compressible and the start offset of the array to compress is > 0. compressible and the start offset of the array to compress is > 0.
(Adrien Grand) (Adrien Grand)
* LUCENE-5221: SimilarityBase did not write norms the same way as DefaultSimilarity
if discountOverlaps == false and index-time boosts are present for the field.
(Yubin Kim via Robert Muir)
API Changes API Changes

2
lucene/core/src/java/org/apache/lucene/search/similarities/SimilarityBase.java
View File

@ -233,7 +233,7 @@ public abstract class SimilarityBase extends Similarity {
if (discountOverlaps) if (discountOverlaps)
numTerms = state.getLength() - state.getNumOverlap(); numTerms = state.getLength() - state.getNumOverlap();
else else
numTerms = state.getLength() / state.getBoost(); numTerms = state.getLength();
return encodeNormValue(state.getBoost(), numTerms); return encodeNormValue(state.getBoost(), numTerms);
} }

17
lucene/core/src/test/org/apache/lucene/search/similarities/TestSimilarityBase.java
View File

@ -25,6 +25,7 @@ import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field; import org.apache.lucene.document.Field;
import org.apache.lucene.document.FieldType; import org.apache.lucene.document.FieldType;
import org.apache.lucene.document.TextField; import org.apache.lucene.document.TextField;
import org.apache.lucene.index.FieldInvertState;
import org.apache.lucene.index.IndexReader; import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.RandomIndexWriter; import org.apache.lucene.index.RandomIndexWriter;
import org.apache.lucene.index.Term; import org.apache.lucene.index.Term;
@ -572,4 +573,20 @@ public class TestSimilarityBase extends LuceneTestCase {
dir.close(); dir.close();
super.tearDown(); super.tearDown();
} }
// LUCENE-5221
public void testDiscountOverlapsBoost() throws IOException {
DefaultSimilarity expected = new DefaultSimilarity();
SimilarityBase actual = new DFRSimilarity(new BasicModelIne(), new AfterEffectB(), new NormalizationH2());
expected.setDiscountOverlaps(false);
actual.setDiscountOverlaps(false);
FieldInvertState state = new FieldInvertState("foo");
state.setLength(5);
state.setNumOverlap(2);
state.setBoost(3);
assertEquals(expected.computeNorm(state), actual.computeNorm(state));
expected.setDiscountOverlaps(true);
actual.setDiscountOverlaps(true);
assertEquals(expected.computeNorm(state), actual.computeNorm(state));
}
} }