1 package org.apache.lucene.search;
4 * Licensed to the Apache Software Foundation (ASF) under one or more
5 * contributor license agreements. See the NOTICE file distributed with
6 * this work for additional information regarding copyright ownership.
7 * The ASF licenses this file to You under the Apache License, Version 2.0
8 * (the "License"); you may not use this file except in compliance with
9 * the License. You may obtain a copy of the License at
11 * http://www.apache.org/licenses/LICENSE-2.0
13 * Unless required by applicable law or agreed to in writing, software
14 * distributed under the License is distributed on an "AS IS" BASIS,
15 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16 * See the License for the specific language governing permissions and
17 * limitations under the License.
20 import java.io.IOException;
22 import org.apache.lucene.analysis.MockAnalyzer;
23 import org.apache.lucene.analysis.MockTokenizer;
24 import org.apache.lucene.document.Document;
25 import org.apache.lucene.document.Field;
26 import org.apache.lucene.index.IndexReader;
27 import org.apache.lucene.index.Term;
28 import org.apache.lucene.index.RandomIndexWriter;
29 import org.apache.lucene.store.Directory;
30 import org.apache.lucene.util.LuceneTestCase;
31 import org.apache.lucene.util._TestUtil;
34 * Create an index with random unicode terms
35 * Generates random prefix queries, and validates against a simple impl.
37 public class TestPrefixRandom extends LuceneTestCase {
38 private IndexSearcher searcher;
39 private IndexReader reader;
40 private Directory dir;
43 public void setUp() throws Exception {
46 RandomIndexWriter writer = new RandomIndexWriter(random, dir,
47 newIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(random, MockTokenizer.KEYWORD, false))
48 .setMaxBufferedDocs(_TestUtil.nextInt(random, 50, 1000)));
50 Document doc = new Document();
51 Field bogus1 = newField("bogus", "", Field.Store.NO, Field.Index.NOT_ANALYZED_NO_NORMS);
52 Field field = newField("field", "", Field.Store.NO, Field.Index.NOT_ANALYZED);
53 Field bogus2 = newField("zbogus", "", Field.Store.NO, Field.Index.NOT_ANALYZED_NO_NORMS);
58 int num = atLeast(1000);
60 for (int i = 0; i < num; i++) {
61 field.setValue(_TestUtil.randomUnicodeString(random, 10));
62 bogus1.setValue(_TestUtil.randomUnicodeString(random, 10));
63 bogus2.setValue(_TestUtil.randomUnicodeString(random, 10));
64 writer.addDocument(doc);
66 reader = writer.getReader();
67 searcher = newSearcher(reader);
72 public void tearDown() throws Exception {
79 /** a stupid prefix query that just blasts thru the terms */
80 private class DumbPrefixQuery extends MultiTermQuery {
81 private final Term prefix;
83 DumbPrefixQuery(Term term) {
89 protected FilteredTermEnum getEnum(IndexReader reader) throws IOException {
90 return new SimplePrefixTermEnum(reader, prefix);
93 private class SimplePrefixTermEnum extends FilteredTermEnum {
94 private final Term prefix;
95 private boolean endEnum;
97 private SimplePrefixTermEnum(IndexReader reader, Term prefix) throws IOException {
99 setEnum(reader.terms(new Term(prefix.field(), "")));
103 protected boolean termCompare(Term term) {
104 if (term.field() == prefix.field()) {
105 return term.text().startsWith(prefix.text());
113 public float difference() {
118 protected boolean endEnum() {
124 public String toString(String field) {
125 return field.toString() + ":" + prefix.toString();
129 /** test a bunch of random prefixes */
130 public void testPrefixes() throws Exception {
131 int num = atLeast(100);
132 for (int i = 0; i < num; i++)
133 assertSame(_TestUtil.randomUnicodeString(random, 5));
136 /** check that the # of hits is the same as from a very
137 * simple prefixquery implementation.
139 private void assertSame(String prefix) throws IOException {
140 PrefixQuery smart = new PrefixQuery(new Term("field", prefix));
141 DumbPrefixQuery dumb = new DumbPrefixQuery(new Term("field", prefix));
143 TopDocs smartDocs = searcher.search(smart, 25);
144 TopDocs dumbDocs = searcher.search(dumb, 25);
145 CheckHits.checkEqual(smart, smartDocs.scoreDocs, dumbDocs.scoreDocs);