testmultisearcher.java

Lucene a java open-source SearchEngine Framework

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 org.apache.lucene.util.LuceneTestCase;
import org.apache.lucene.analysis.KeywordAnalyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.SetBasedFieldSelector;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.Term;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.store.MockRAMDirectory;

import java.io.IOException;
import java.util.Collections;
import java.util.HashSet;
import java.util.Set;

/**
 * Tests {@link MultiSearcher} class.
 *
 * @version $Id: TestMultiSearcher.java 583534 2007-10-10 16:46:35Z mikemccand $
 */
public class TestMultiSearcher extends LuceneTestCase
{
    public TestMultiSearcher(String name)
    {
        super(name);
    }

	/**
	 * ReturnS a new instance of the concrete MultiSearcher class
	 * used in this test.
	 */
	protected MultiSearcher getMultiSearcherInstance(Searcher[] searchers) throws IOException {
		return new MultiSearcher(searchers);
	}

    public void testEmptyIndex()
        throws Exception
    {
        // creating two directories for indices
        Directory indexStoreA = new MockRAMDirectory();
        Directory indexStoreB = new MockRAMDirectory();

        // creating a document to store
        Document lDoc = new Document();
        lDoc.add(new Field("fulltext", "Once upon a time.....", Field.Store.YES, Field.Index.TOKENIZED));
        lDoc.add(new Field("id", "doc1", Field.Store.YES, Field.Index.UN_TOKENIZED));
        lDoc.add(new Field("handle", "1", Field.Store.YES, Field.Index.UN_TOKENIZED));

        // creating a document to store
        Document lDoc2 = new Document();
        lDoc2.add(new Field("fulltext", "in a galaxy far far away.....",
            Field.Store.YES, Field.Index.TOKENIZED));
        lDoc2.add(new Field("id", "doc2", Field.Store.YES, Field.Index.UN_TOKENIZED));
        lDoc2.add(new Field("handle", "1", Field.Store.YES, Field.Index.UN_TOKENIZED));

        // creating a document to store
        Document lDoc3 = new Document();
        lDoc3.add(new Field("fulltext", "a bizarre bug manifested itself....",
            Field.Store.YES, Field.Index.TOKENIZED));
        lDoc3.add(new Field("id", "doc3", Field.Store.YES, Field.Index.UN_TOKENIZED));
        lDoc3.add(new Field("handle", "1", Field.Store.YES, Field.Index.UN_TOKENIZED));

        // creating an index writer for the first index
        IndexWriter writerA = new IndexWriter(indexStoreA, new StandardAnalyzer(), true);
        // creating an index writer for the second index, but writing nothing
        IndexWriter writerB = new IndexWriter(indexStoreB, new StandardAnalyzer(), true);

        //--------------------------------------------------------------------
        // scenario 1
        //--------------------------------------------------------------------

        // writing the documents to the first index
        writerA.addDocument(lDoc);
        writerA.addDocument(lDoc2);
        writerA.addDocument(lDoc3);
        writerA.optimize();
        writerA.close();

        // closing the second index
        writerB.close();

        // creating the query
        QueryParser parser = new QueryParser("fulltext", new StandardAnalyzer());
        Query query = parser.parse("handle:1");

        // building the searchables
        Searcher[] searchers = new Searcher[2];
        // VITAL STEP:adding the searcher for the empty index first, before the searcher for the populated index
        searchers[0] = new IndexSearcher(indexStoreB);
        searchers[1] = new IndexSearcher(indexStoreA);
        // creating the multiSearcher
        Searcher mSearcher = getMultiSearcherInstance(searchers);
        // performing the search
        Hits hits = mSearcher.search(query);

        assertEquals(3, hits.length());

        // iterating over the hit documents
        for (int i = 0; i < hits.length(); i++) {
            Document d = hits.doc(i);
        }
        mSearcher.close();


        //--------------------------------------------------------------------
        // scenario 2
        //--------------------------------------------------------------------

        // adding one document to the empty index
        writerB = new IndexWriter(indexStoreB, new StandardAnalyzer(), false);
        writerB.addDocument(lDoc);
        writerB.optimize();
        writerB.close();

        // building the searchables
        Searcher[] searchers2 = new Searcher[2];
        // VITAL STEP:adding the searcher for the empty index first, before the searcher for the populated index
        searchers2[0] = new IndexSearcher(indexStoreB);
        searchers2[1] = new IndexSearcher(indexStoreA);
        // creating the mulitSearcher
        MultiSearcher mSearcher2 = getMultiSearcherInstance(searchers2);
        // performing the same search
        Hits hits2 = mSearcher2.search(query);

        assertEquals(4, hits2.length());

        // iterating over the hit documents
        for (int i = 0; i < hits2.length(); i++) {
            // no exception should happen at this point
            Document d = hits2.doc(i);
        }

        // test the subSearcher() method:
        Query subSearcherQuery = parser.parse("id:doc1");
        hits2 = mSearcher2.search(subSearcherQuery);
        assertEquals(2, hits2.length());
        assertEquals(0, mSearcher2.subSearcher(hits2.id(0)));   // hit from searchers2[0]
        assertEquals(1, mSearcher2.subSearcher(hits2.id(1)));   // hit from searchers2[1]
        subSearcherQuery = parser.parse("id:doc2");
        hits2 = mSearcher2.search(subSearcherQuery);
        assertEquals(1, hits2.length());
        assertEquals(1, mSearcher2.subSearcher(hits2.id(0)));   // hit from searchers2[1]
        mSearcher2.close();

        //--------------------------------------------------------------------
        // scenario 3
        //--------------------------------------------------------------------

        // deleting the document just added, this will cause a different exception to take place
        Term term = new Term("id", "doc1");
        IndexReader readerB = IndexReader.open(indexStoreB);
        readerB.deleteDocuments(term);
        readerB.close();

        // optimizing the index with the writer
        writerB = new IndexWriter(indexStoreB, new StandardAnalyzer(), false);
        writerB.optimize();
        writerB.close();

        // building the searchables
        Searcher[] searchers3 = new Searcher[2];

        searchers3[0] = new IndexSearcher(indexStoreB);
        searchers3[1] = new IndexSearcher(indexStoreA);
        // creating the mulitSearcher
        Searcher mSearcher3 = getMultiSearcherInstance(searchers3);
        // performing the same search
        Hits hits3 = mSearcher3.search(query);

        assertEquals(3, hits3.length());

        // iterating over the hit documents
        for (int i = 0; i < hits3.length(); i++) {
            Document d = hits3.doc(i);
        }