1 package org.apache.lucene.analysis;
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;
21 import java.io.Reader;
22 import java.io.StringReader;
24 import org.apache.lucene.analysis.BaseTokenStreamTestCase;
25 import org.apache.lucene.analysis.Analyzer;
26 import org.apache.lucene.analysis.MockTokenizer;
27 import org.apache.lucene.analysis.TokenStream;
28 import org.apache.lucene.analysis.Tokenizer;
30 import static org.apache.lucene.analysis.VocabularyAssert.*;
33 * Test the PorterStemFilter with Martin Porter's test data.
35 public class TestPorterStemFilter extends BaseTokenStreamTestCase {
36 Analyzer a = new ReusableAnalyzerBase() {
38 protected TokenStreamComponents createComponents(String fieldName,
40 Tokenizer t = new MockTokenizer(reader, MockTokenizer.KEYWORD, false);
41 return new TokenStreamComponents(t, new PorterStemFilter(t));
46 * Run the stemmer against all strings in voc.txt
47 * The output should be the same as the string in output.txt
49 public void testPorterStemFilter() throws Exception {
50 assertVocabulary(a, getDataFile("porterTestData.zip"), "voc.txt", "output.txt");
53 public void testWithKeywordAttribute() throws IOException {
54 CharArraySet set = new CharArraySet(TEST_VERSION_CURRENT, 1, true);
55 set.add("yourselves");
56 Tokenizer tokenizer = new MockTokenizer(new StringReader("yourselves yours"), MockTokenizer.WHITESPACE, false);
57 TokenStream filter = new PorterStemFilter(new KeywordMarkerFilter(tokenizer, set));
58 assertTokenStreamContents(filter, new String[] {"yourselves", "your"});
61 /** blast some random strings through the analyzer */
62 public void testRandomStrings() throws Exception {
63 checkRandomData(random, a, 10000*RANDOM_MULTIPLIER);