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.io.IOException;
import java.util.HashSet;
import java.util.Random;
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.index.DocsEnum;
import org.apache.lucene.index.MultiFields;
import org.apache.lucene.store.Directory;
import org.apache.lucene.util.LuceneTestCase;
import org.apache.lucene.util.BytesRef;
public class DuplicateFilterTest extends LuceneTestCase {
private static final String KEY_FIELD = "url";
private Directory directory;
private IndexReader reader;
TermQuery tq=new TermQuery(new Term("text","lucene"));
private IndexSearcher searcher;
@Override
protected void setUp() throws Exception {
super.setUp();
Random random = newRandom();
directory = newDirectory(random);
RandomIndexWriter writer = new RandomIndexWriter(random, directory);
//Add series of docs with filterable fields : url, text and dates flags
addDoc(writer, "http://lucene.apache.org", "lucene 1.4.3 available", "20040101");
addDoc(writer, "http://lucene.apache.org", "New release pending", "20040102");
addDoc(writer, "http://lucene.apache.org", "Lucene 1.9 out now", "20050101");
addDoc(writer, "http://www.bar.com", "Local man bites dog", "20040101");
addDoc(writer, "http://www.bar.com", "Dog bites local man", "20040102");
addDoc(writer, "http://www.bar.com", "Dog uses Lucene", "20050101");
addDoc(writer, "http://lucene.apache.org", "Lucene 2.0 out", "20050101");
addDoc(writer, "http://lucene.apache.org", "Oops. Lucene 2.1 out", "20050102");
// Until we fix LUCENE-2348, the index must
// have only 1 segment:
writer.optimize();
reader = writer.getReader();
writer.close();
searcher =new IndexSearcher(reader);
}
@Override
protected void tearDown() throws Exception {
reader.close();
searcher.close();
directory.close();
super.tearDown();
}
private void addDoc(RandomIndexWriter writer, String url, String text, String date) throws IOException
{
Document doc=new Document();
doc.add(new Field(KEY_FIELD,url,Field.Store.YES,Field.Index.NOT_ANALYZED));
doc.add(new Field("text",text,Field.Store.YES,Field.Index.ANALYZED));
doc.add(new Field("date",date,Field.Store.YES,Field.Index.ANALYZED));
writer.addDocument(doc);
}
public void testDefaultFilter() throws Throwable
{
DuplicateFilter df=new DuplicateFilter(KEY_FIELD);
HashSet<String> results=new HashSet<String>();
ScoreDoc[] hits = searcher.search(tq,df, 1000).scoreDocs;
for(int i=0;i<hits.length;i++)
{
Document d=searcher.doc(hits[i].doc);
String url=d.get(KEY_FIELD);
assertFalse("No duplicate urls should be returned",results.contains(url));
results.add(url);
}
}
public void testNoFilter() throws Throwable
{
HashSet<String> results=new HashSet<String>();
ScoreDoc[] hits = searcher.search(tq, null, 1000).scoreDocs;
assertTrue("Default searching should have found some matches",hits.length>0);
boolean dupsFound=false;
for(int i=0;i<hits.length;i++)
{
Document d=searcher.doc(hits[i].doc);
String url=d.get(KEY_FIELD);
if(!dupsFound)
dupsFound=results.contains(url);
results.add(url);
}
assertTrue("Default searching should have found duplicate urls",dupsFound);
}
public void testFastFilter() throws Throwable
{
DuplicateFilter df=new DuplicateFilter(KEY_FIELD);
df.setProcessingMode(DuplicateFilter.PM_FAST_INVALIDATION);
HashSet<String> results=new HashSet<String>();
ScoreDoc[] hits = searcher.search(tq,df, 1000).scoreDocs;
assertTrue("Filtered searching should have found some matches",hits.length>0);
for(int i=0;i<hits.length;i++)
{
Document d=searcher.doc(hits[i].doc);
String url=d.get(KEY_FIELD);
assertFalse("No duplicate urls should be returned",results.contains(url));
results.add(url);
}
assertEquals("Two urls found",2, results.size());
}
public void testKeepsLastFilter() throws Throwable
{
DuplicateFilter df=new DuplicateFilter(KEY_FIELD);
df.setKeepMode(DuplicateFilter.KM_USE_LAST_OCCURRENCE);
ScoreDoc[] hits = searcher.search(tq,df, 1000).scoreDocs;
assertTrue("Filtered searching should have found some matches",hits.length>0);
for(int i=0;i<hits.length;i++)
{
Document d=searcher.doc(hits[i].doc);
String url=d.get(KEY_FIELD);
DocsEnum td = MultiFields.getTermDocsEnum(reader,
MultiFields.getDeletedDocs(reader),
KEY_FIELD,
new BytesRef(url));
int lastDoc=0;
while(td.nextDoc() != DocsEnum.NO_MORE_DOCS)
{
lastDoc=td.docID();
}
assertEquals("Duplicate urls should return last doc",lastDoc, hits[i].doc);
}
}
public void testKeepsFirstFilter() throws Throwable
{
DuplicateFilter df=new DuplicateFilter(KEY_FIELD);
df.setKeepMode(DuplicateFilter.KM_USE_FIRST_OCCURRENCE);
ScoreDoc[] hits = searcher.search(tq,df, 1000).scoreDocs;
assertTrue("Filtered searching should have found some matches",hits.length>0);
for(int i=0;i<hits.length;i++)
{
Document d=searcher.doc(hits[i].doc);
String url=d.get(KEY_FIELD);
DocsEnum td = MultiFields.getTermDocsEnum(reader,
MultiFields.getDeletedDocs(reader),
KEY_FIELD,
new BytesRef(url));
int lastDoc=0;
td.nextDoc();
lastDoc=td.docID();
assertEquals("Duplicate urls should return first doc",lastDoc, hits[i].doc);
}
}
}