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

Lucene example source code file (TestComplexPhraseQuery.java)

This example Lucene source code file (TestComplexPhraseQuery.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

complexphrasequeryparser, docdata, docdata, document, document, exception, exception, hashset, indexwriter, override, simple, string, string, throwable, util

The Lucene TestComplexPhraseQuery.java source code

package org.apache.lucene.queryParser.complexPhrase;

 * 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.util.HashSet;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.MockAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.util.LuceneTestCase;

public class TestComplexPhraseQuery extends LuceneTestCase {
  Directory rd;
  Analyzer analyzer = new MockAnalyzer(random);

  DocData docsContent[] = { new DocData("john smith", "1"),
      new DocData("johathon smith", "2"),
      new DocData("john percival smith", "3"),
      new DocData("jackson waits tom", "4") };

  private IndexSearcher searcher;

  String defaultFieldName = "name";

  public void testComplexPhrases() throws Exception {
    checkMatches("\"john smith\"", "1"); // Simple multi-term still works
    checkMatches("\"j*   smyth~\"", "1,2"); // wildcards and fuzzies are OK in
    // phrases
    checkMatches("\"(jo* -john)  smith\"", "2"); // boolean logic works
    checkMatches("\"jo*  smith\"~2", "1,2,3"); // position logic works.
    checkMatches("\"jo* [sma TO smZ]\" ", "1,2"); // range queries supported
    checkMatches("\"john\"", "1,3"); // Simple single-term still works
    checkMatches("\"(john OR johathon)  smith\"", "1,2"); // boolean logic with
    // brackets works.
    checkMatches("\"(jo* -john) smyth~\"", "2"); // boolean logic with
    // brackets works.

    // checkMatches("\"john -percival\"", "1"); // not logic doesn't work
    // currently :(.

    checkMatches("\"john  nosuchword*\"", ""); // phrases with clauses producing
    // empty sets

    checkBadQuery("\"jo*  id:1 smith\""); // mixing fields in a phrase is bad
    checkBadQuery("\"jo* \"smith\" \""); // phrases inside phrases is bad

  private void checkBadQuery(String qString) {
    QueryParser qp = new ComplexPhraseQueryParser(TEST_VERSION_CURRENT, defaultFieldName, analyzer);
    Throwable expected = null;
    try {
    } catch (Throwable e) {
      expected = e;
    assertNotNull("Expected parse error in " + qString, expected);


  private void checkMatches(String qString, String expectedVals)
      throws Exception {
    QueryParser qp = new ComplexPhraseQueryParser(TEST_VERSION_CURRENT, defaultFieldName, analyzer);
    qp.setFuzzyPrefixLength(1); // usually a good idea

    Query q = qp.parse(qString);

    HashSet<String> expecteds = new HashSet();
    String[] vals = expectedVals.split(",");
    for (int i = 0; i < vals.length; i++) {
      if (vals[i].length() > 0)

    TopDocs td = searcher.search(q, 10);
    ScoreDoc[] sd = td.scoreDocs;
    for (int i = 0; i < sd.length; i++) {
      Document doc = searcher.doc(sd[i].doc);
      String id = doc.get("id");
      assertTrue(qString + "matched doc#" + id + " not expected", expecteds

    assertEquals(qString + " missing some matches ", 0, expecteds.size());


  public void setUp() throws Exception {
    rd = newDirectory();
    IndexWriter w = new IndexWriter(rd, newIndexWriterConfig(TEST_VERSION_CURRENT, analyzer));
    for (int i = 0; i < docsContent.length; i++) {
      Document doc = new Document();
      doc.add(newField("name", docsContent[i].name, Field.Store.YES,
      doc.add(newField("id", docsContent[i].id, Field.Store.YES,
    searcher = new IndexSearcher(rd, true);

  public void tearDown() throws Exception {

  static class DocData {
    String name;

    String id;

    public DocData(String name, String id) {
      this.name = name;
      this.id = id;


Other Lucene examples (source code examples)

Here is a short list of links related to this Lucene TestComplexPhraseQuery.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.