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

LUCENE-1124: make sure FuzzyQuery matches the exact term 

git-svn-id: https://svn.apache.org/repos/asf/lucene/java/trunk@826013 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Michael McCandless 2009-10-16 17:37:16 +00:00
parent 74b190f4b7
commit ad6bbdd02e
3 changed files with 47 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
CHANGES.txt
View File

@ -87,6 +87,9 @@ Bug fixes
BooleanScorer for scoring), whereby some matching documents fail to
be collected. (Fulin Tang via Mike McCandless)
* LUCENE-1124: Make sure FuzzyQuery always matches the precise term.
(stefatwork@gmail.com via Mike McCandless)
New features
* LUCENE-1933: Provide a convenience AttributeFactory that creates a

4
src/java/org/apache/lucene/search/FuzzyQuery.java
View File

@ -126,8 +126,8 @@ public class FuzzyQuery extends MultiTermQuery {
@Override
public Query rewrite(IndexReader reader) throws IOException {
if(!termLongEnough) { // can't match
return new BooleanQuery();
if(!termLongEnough) { // can only match if it's exact
return new TermQuery(term);
}
FilteredTermEnum enumerator = getEnum(reader);

42
src/test/org/apache/lucene/search/TestFuzzyQuery.java
View File

@ -19,13 +19,18 @@ package org.apache.lucene.search;
import java.io.IOException;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.util.LuceneTestCase;
import org.apache.lucene.analysis.WhitespaceAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.MockRAMDirectory;
import org.apache.lucene.queryParser.QueryParser;
/**
* Tests {@link FuzzyQuery}.
@ -281,6 +286,43 @@ public class TestFuzzyQuery extends LuceneTestCase {
assertEquals(0, hits.length);
}
public void testGiga() throws Exception {
StandardAnalyzer analyzer = new StandardAnalyzer();
Directory index = new MockRAMDirectory();
IndexWriter w = new IndexWriter(index, analyzer, true, IndexWriter.MaxFieldLength.UNLIMITED);
addDoc("Lucene in Action", w);
addDoc("Lucene for Dummies", w);
//addDoc("Giga", w);
addDoc("Giga byte", w);
addDoc("ManagingGigabytesManagingGigabyte", w);
addDoc("ManagingGigabytesManagingGigabytes", w);
addDoc("The Art of Computer Science", w);
addDoc("J. K. Rowling", w);
addDoc("JK Rowling", w);
addDoc("Joanne K Roling", w);
addDoc("Bruce Willis", w);
addDoc("Willis bruce", w);
addDoc("Brute willis", w);
addDoc("B. willis", w);
IndexReader r = w.getReader();
w.close();
Query q = new QueryParser("field", analyzer).parse( "giga~0.9" );
// 3. search
IndexSearcher searcher = new IndexSearcher(r);
ScoreDoc[] hits = searcher.search(q, 10).scoreDocs;
assertEquals(1, hits.length);
assertEquals("Giga byte", searcher.doc(hits[0].doc).get("field"));
r.close();
}
private void addDoc(String text, IndexWriter writer) throws IOException {
Document doc = new Document();
doc.add(new Field("field", text, Field.Store.YES, Field.Index.ANALYZED));