1 package org.apache.lucene.index.memory;
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.BufferedReader;
21 import java.io.IOException;
22 import java.io.InputStream;
23 import java.io.InputStreamReader;
24 import java.util.HashSet;
27 import org.apache.lucene.analysis.Analyzer;
28 import org.apache.lucene.analysis.BaseTokenStreamTestCase;
29 import org.apache.lucene.analysis.MockAnalyzer;
30 import org.apache.lucene.analysis.MockTokenizer;
31 import org.apache.lucene.analysis.StopAnalyzer;
32 import org.apache.lucene.document.Document;
33 import org.apache.lucene.document.Field;
34 import org.apache.lucene.index.IndexReader;
35 import org.apache.lucene.index.IndexWriter;
36 import org.apache.lucene.index.IndexWriterConfig;
37 import org.apache.lucene.queryParser.QueryParser;
38 import org.apache.lucene.search.IndexSearcher;
39 import org.apache.lucene.search.TopDocs;
40 import org.apache.lucene.store.Directory;
41 import org.apache.lucene.util._TestUtil;
44 * Verifies that Lucene MemoryIndex and RAMDirectory have the same behaviour,
45 * returning the same results for queries on some randomish indexes.
47 public class MemoryIndexTest extends BaseTokenStreamTestCase {
48 private Set<String> queries = new HashSet<String>();
50 public static final int ITERATIONS = 100 * RANDOM_MULTIPLIER;
53 public void setUp() throws Exception {
55 queries.addAll(readQueries("testqueries.txt"));
56 queries.addAll(readQueries("testqueries2.txt"));
60 * read a set of queries from a resource file
62 private Set<String> readQueries(String resource) throws IOException {
63 Set<String> queries = new HashSet<String>();
64 InputStream stream = getClass().getResourceAsStream(resource);
65 BufferedReader reader = new BufferedReader(new InputStreamReader(stream, "UTF-8"));
67 while ((line = reader.readLine()) != null) {
69 if (line.length() > 0 && !line.startsWith("#") && !line.startsWith("//")) {
78 * runs random tests, up to ITERATIONS times.
80 public void testRandomQueries() throws Exception {
81 for (int i = 0; i < ITERATIONS; i++)
82 assertAgainstRAMDirectory();
86 * Build a randomish document for both RAMDirectory and MemoryIndex,
87 * and run all the queries against it.
89 public void assertAgainstRAMDirectory() throws Exception {
90 StringBuilder fooField = new StringBuilder();
91 StringBuilder termField = new StringBuilder();
93 // add up to 250 terms to field "foo"
94 final int numFooTerms = random.nextInt(250 * RANDOM_MULTIPLIER);
95 for (int i = 0; i < numFooTerms; i++) {
97 fooField.append(randomTerm());
100 // add up to 250 terms to field "term"
101 final int numTermTerms = random.nextInt(250 * RANDOM_MULTIPLIER);
102 for (int i = 0; i < numTermTerms; i++) {
103 termField.append(" ");
104 termField.append(randomTerm());
107 Directory ramdir = newDirectory();
108 Analyzer analyzer = randomAnalyzer();
109 IndexWriter writer = new IndexWriter(ramdir,
110 new IndexWriterConfig(TEST_VERSION_CURRENT, analyzer));
111 Document doc = new Document();
112 Field field1 = newField("foo", fooField.toString(), Field.Store.NO, Field.Index.ANALYZED);
113 Field field2 = newField("term", termField.toString(), Field.Store.NO, Field.Index.ANALYZED);
116 writer.addDocument(doc);
119 MemoryIndex memory = new MemoryIndex();
120 memory.addField("foo", fooField.toString(), analyzer);
121 memory.addField("term", termField.toString(), analyzer);
122 assertAllQueries(memory, ramdir, analyzer);
127 * Run all queries against both the RAMDirectory and MemoryIndex, ensuring they are the same.
129 public void assertAllQueries(MemoryIndex memory, Directory ramdir, Analyzer analyzer) throws Exception {
130 IndexReader reader = IndexReader.open(ramdir);
131 IndexSearcher ram = new IndexSearcher(reader);
132 IndexSearcher mem = memory.createSearcher();
133 QueryParser qp = new QueryParser(TEST_VERSION_CURRENT, "foo", analyzer);
134 for (String query : queries) {
135 TopDocs ramDocs = ram.search(qp.parse(query), 1);
136 TopDocs memDocs = mem.search(qp.parse(query), 1);
137 assertEquals(ramDocs.totalHits, memDocs.totalHits);
145 * Return a random analyzer (Simple, Stop, Standard) to analyze the terms.
147 private Analyzer randomAnalyzer() {
148 switch(random.nextInt(3)) {
149 case 0: return new MockAnalyzer(random, MockTokenizer.SIMPLE, true);
150 case 1: return new StopAnalyzer(TEST_VERSION_CURRENT);
151 default: return new MockAnalyzer(random, MockTokenizer.WHITESPACE, false);
156 * Some terms to be indexed, in addition to random words.
157 * These terms are commonly used in the queries.
159 private static final String[] TEST_TERMS = {"term", "Term", "tErm", "TERM",
160 "telm", "stop", "drop", "roll", "phrase", "a", "c", "bar", "blar",
161 "gack", "weltbank", "worlbank", "hello", "on", "the", "apache", "Apache",
162 "copyright", "Copyright"};
166 * half of the time, returns a random term from TEST_TERMS.
167 * the other half of the time, returns a random unicode string.
169 private String randomTerm() {
170 if (random.nextBoolean()) {
171 // return a random TEST_TERM
172 return TEST_TERMS[random.nextInt(TEST_TERMS.length)];
174 // return a random unicode term
175 return _TestUtil.randomUnicodeString(random);