home | career | drupal | java | mac | mysql | perl | scala | uml | unix  

Lucene example source code file (SynLookup.java)

This example Lucene source code file (SynLookup.java) is included in the DevDaily.com "Java Source Code Warehouse" project. The intent of this project is to help you "Learn Java by Example" TM.

Java - Lucene tags/keywords

booleanquery, countingcollector, document, indexsearcher, io, ioexception, ioexception, override, override, query, string, string, term, termquery, termquery, util

The Lucene SynLookup.java source code

package org.apache.lucene.wordnet;

 * 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,
 * See the License for the specific language governing permissions and
 * limitations under the License.

import java.io.File;
import java.io.IOException;
import java.io.StringReader;
import java.util.HashSet;
import java.util.Iterator;
import java.util.LinkedList;
import java.util.List;
import java.util.Set;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanQuery;
import org.apache.lucene.search.Collector;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.Scorer;
import org.apache.lucene.search.Searcher;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.store.FSDirectory;

 * Test program to look up synonyms.
public class SynLookup {

  final static class CountingCollector extends Collector {
    public int numHits = 0;
    public void setScorer(Scorer scorer) throws IOException {}
    public void collect(int doc) throws IOException {

    public void setNextReader(IndexReader reader, int docBase) {}
    public boolean acceptsDocsOutOfOrder() {
      return true;
	public static void main(String[] args) throws IOException {
		if (args.length != 2) {
							   "java org.apache.lucene.wordnet.SynLookup <index path> ");

		FSDirectory directory = FSDirectory.open(new File(args[0]));
		IndexSearcher searcher = new IndexSearcher(directory, true);

		String word = args[1];
		Query query = new TermQuery(new Term(Syns2Index.F_WORD, word));
		CountingCollector countingCollector = new CountingCollector();
		searcher.search(query, countingCollector);

		if (countingCollector.numHits == 0) {
			System.out.println("No synonyms found for " + word);
		} else {
			System.out.println("Synonyms found for \"" + word + "\":");

		ScoreDoc[] hits = searcher.search(query, countingCollector.numHits).scoreDocs;
		for (int i = 0; i < hits.length; i++) {
			Document doc = searcher.doc(hits[i].doc);

			String[] values = doc.getValues(Syns2Index.F_SYN);

			for (int j = 0; j < values.length; j++) {


	 * Perform synonym expansion on a query.
	 * @param query
	 * @param syns
	 * @param a
	 * @param field
	 * @param boost
	public static Query expand( String query,
								Searcher syns,
								Analyzer a,
								final String field,
								final float boost)
		throws IOException
		final Set<String> already = new HashSet(); // avoid dups		
		List<String> top = new LinkedList(); // needs to be separately listed..

		// [1] Parse query into separate words so that when we expand we can avoid dups
		TokenStream ts = a.reusableTokenStream( field, new StringReader( query));
    CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
		while (ts.incrementToken()) {
			String word = termAtt.toString();
			if ( already.add( word))
				top.add( word);
		final BooleanQuery tmp = new BooleanQuery();
		// [2] form query
		Iterator<String> it = top.iterator();
		while ( it.hasNext())
			// [2a] add to level words in
			String word = it.next();
			TermQuery tq = new TermQuery( new Term( field, word));
			tmp.add( tq, BooleanClause.Occur.SHOULD);

			// [2b] add in unique synonums
			syns.search(new TermQuery( new Term(Syns2Index.F_WORD, word)), new Collector() {
			  IndexReader reader;
        public boolean acceptsDocsOutOfOrder() {
          return true;

        public void collect(int doc) throws IOException {
          Document d = reader.document(doc);
          String[] values = d.getValues( Syns2Index.F_SYN);
          for ( int j = 0; j < values.length; j++)
            String syn = values[ j];
            if ( already.add( syn))
              TermQuery tq = new TermQuery( new Term( field, syn));
              if ( boost > 0) // else keep normal 1.0
                tq.setBoost( boost);
              tmp.add( tq, BooleanClause.Occur.SHOULD); 

        public void setNextReader(IndexReader reader, int docBase)
            throws IOException {
          this.reader = reader;

        public void setScorer(Scorer scorer) throws IOException {}

		return tmp;

Other Lucene examples (source code examples)

Here is a short list of links related to this Lucene SynLookup.java source code file:

my book on functional programming


new blog posts


Copyright 1998-2019 Alvin Alexander, alvinalexander.com
All Rights Reserved.

A percentage of advertising revenue from
pages under the /java/jwarehouse URI on this website is
paid back to open source projects.