package org.apache.lucene.search;
/**
* Licensed to the Apache Software Foundation (ASF) under one or more
* contributor license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright ownership.
* The ASF licenses this file to You under the Apache License, Version 2.0
* (the "License"); you may not use this file except in compliance with
* the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
import java.util.Random;
import org.apache.lucene.util.LuceneTestCase;
import org.apache.lucene.analysis.MockAnalyzer;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.RandomIndexWriter;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.store.Directory;
public class TestSloppyPhraseQuery extends LuceneTestCase {
private static final String S_1 = "A A A";
private static final String S_2 = "A 1 2 3 A 4 5 6 A";
private static final Document DOC_1 = makeDocument("X " + S_1 + " Y");
private static final Document DOC_2 = makeDocument("X " + S_2 + " Y");
private static final Document DOC_3 = makeDocument("X " + S_1 + " A Y");
private static final Document DOC_1_B = makeDocument("X " + S_1 + " Y N N N N " + S_1 + " Z");
private static final Document DOC_2_B = makeDocument("X " + S_2 + " Y N N N N " + S_2 + " Z");
private static final Document DOC_3_B = makeDocument("X " + S_1 + " A Y N N N N " + S_1 + " A Y");
private static final Document DOC_4 = makeDocument("A A X A X B A X B B A A X B A A");
private static final PhraseQuery QUERY_1 = makePhraseQuery( S_1 );
private static final PhraseQuery QUERY_2 = makePhraseQuery( S_2 );
private static final PhraseQuery QUERY_4 = makePhraseQuery( "X A A");
private Random random;
@Override
public void setUp() throws Exception {
super.setUp();
random = newRandom();
}
/**
* Test DOC_4 and QUERY_4.
* QUERY_4 has a fuzzy (len=1) match to DOC_4, so all slop values > 0 should succeed.
* But only the 3rd sequence of A's in DOC_4 will do.
*/
public void testDoc4_Query4_All_Slops_Should_match() throws Exception {
for (int slop=0; slop<30; slop++) {
int numResultsExpected = slop<1 ? 0 : 1;
checkPhraseQuery(DOC_4, QUERY_4, slop, numResultsExpected);
}
}
/**
* Test DOC_1 and QUERY_1.
* QUERY_1 has an exact match to DOC_1, so all slop values should succeed.
* Before LUCENE-1310, a slop value of 1 did not succeed.
*/
public void testDoc1_Query1_All_Slops_Should_match() throws Exception {
for (int slop=0; slop<30; slop++) {
float score1 = checkPhraseQuery(DOC_1, QUERY_1, slop, 1);
float score2 = checkPhraseQuery(DOC_1_B, QUERY_1, slop, 1);
assertTrue("slop="+slop+" score2="+score2+" should be greater than score1 "+score1, score2>score1);
}
}
/**
* Test DOC_2 and QUERY_1.
* 6 should be the minimum slop to make QUERY_1 match DOC_2.
* Before LUCENE-1310, 7 was the minimum.
*/
public void testDoc2_Query1_Slop_6_or_more_Should_match() throws Exception {
for (int slop=0; slop<30; slop++) {
int numResultsExpected = slop<6 ? 0 : 1;
float score1 = checkPhraseQuery(DOC_2, QUERY_1, slop, numResultsExpected);
if (numResultsExpected>0) {
float score2 = checkPhraseQuery(DOC_2_B, QUERY_1, slop, 1);
assertTrue("slop="+slop+" score2="+score2+" should be greater than score1 "+score1, score2>score1);
}
}
}
/**
* Test DOC_2 and QUERY_2.
* QUERY_2 has an exact match to DOC_2, so all slop values should succeed.
* Before LUCENE-1310, 0 succeeds, 1 through 7 fail, and 8 or greater succeeds.
*/
public void testDoc2_Query2_All_Slops_Should_match() throws Exception {
for (int slop=0; slop<30; slop++) {
float score1 = checkPhraseQuery(DOC_2, QUERY_2, slop, 1);
float score2 = checkPhraseQuery(DOC_2_B, QUERY_2, slop, 1);
assertTrue("slop="+slop+" score2="+score2+" should be greater than score1 "+score1, score2>score1);
}
}
/**
* Test DOC_3 and QUERY_1.
* QUERY_1 has an exact match to DOC_3, so all slop values should succeed.
*/
public void testDoc3_Query1_All_Slops_Should_match() throws Exception {
for (int slop=0; slop<30; slop++) {
float score1 = checkPhraseQuery(DOC_3, QUERY_1, slop, 1);
float score2 = checkPhraseQuery(DOC_3_B, QUERY_1, slop, 1);
assertTrue("slop="+slop+" score2="+score2+" should be greater than score1 "+score1, score2>score1);
}
}
private float checkPhraseQuery(Document doc, PhraseQuery query, int slop, int expectedNumResults) throws Exception {
query.setSlop(slop);
Directory ramDir = newDirectory(random);
RandomIndexWriter writer = new RandomIndexWriter(random, ramDir, new MockAnalyzer(MockTokenizer.WHITESPACE, false));
writer.addDocument(doc);
IndexReader reader = writer.getReader();
IndexSearcher searcher = new IndexSearcher(reader);
TopDocs td = searcher.search(query,null,10);
//System.out.println("slop: "+slop+" query: "+query+" doc: "+doc+" Expecting number of hits: "+expectedNumResults+" maxScore="+td.getMaxScore());
assertEquals("slop: "+slop+" query: "+query+" doc: "+doc+" Wrong number of hits", expectedNumResults, td.totalHits);
//QueryUtils.check(query,searcher);
writer.close();
searcher.close();
reader.close();
ramDir.close();
return td.getMaxScore();
}
private static Document makeDocument(String docText) {
Document doc = new Document();
Field f = new Field("f", docText, Field.Store.NO, Field.Index.ANALYZED);
f.setOmitNorms(true);
doc.add(f);
return doc;
}
private static PhraseQuery makePhraseQuery(String terms) {
PhraseQuery query = new PhraseQuery();
String[] t = terms.split(" +");
for (int i=0; i<t.length; i++) {
query.add(new Term("f", t[i]));
}
return query;
}
}