1
package org.apache.lucene.analysis.en;
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;
23
import org.apache.lucene.analysis.Analyzer;
24
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
25
import org.apache.lucene.analysis.MockTokenizer;
26
import org.apache.lucene.analysis.Tokenizer;
27
import org.apache.lucene.analysis.ReusableAnalyzerBase;
30
* Simple tests for {@link EnglishMinimalStemFilter}
32
public class TestEnglishMinimalStemFilter extends BaseTokenStreamTestCase {
33
private Analyzer analyzer = new ReusableAnalyzerBase() {
35
protected TokenStreamComponents createComponents(String fieldName,
37
Tokenizer source = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
38
return new TokenStreamComponents(source, new EnglishMinimalStemFilter(source));
42
/** Test some examples from various papers about this technique */
43
public void testExamples() throws IOException {
44
checkOneTerm(analyzer, "queries", "query");
45
checkOneTerm(analyzer, "phrases", "phrase");
46
checkOneTerm(analyzer, "corpus", "corpus");
47
checkOneTerm(analyzer, "stress", "stress");
48
checkOneTerm(analyzer, "kings", "king");
49
checkOneTerm(analyzer, "panels", "panel");
50
checkOneTerm(analyzer, "aerodynamics", "aerodynamic");
51
checkOneTerm(analyzer, "congress", "congress");
52
checkOneTerm(analyzer, "serious", "serious");
55
/** blast some random strings through the analyzer */
56
public void testRandomStrings() throws Exception {
57
checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);