1 package org.apache.lucene.analysis.fr;
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;
29 import static org.apache.lucene.analysis.VocabularyAssert.*;
32 * Simple tests for {@link FrenchMinimalStemFilter}
34 public class TestFrenchMinimalStemFilter extends BaseTokenStreamTestCase {
35 private Analyzer analyzer = new ReusableAnalyzerBase() {
37 protected TokenStreamComponents createComponents(String fieldName,
39 Tokenizer source = new MockTokenizer(reader, MockTokenizer.WHITESPACE, false);
40 return new TokenStreamComponents(source, new FrenchMinimalStemFilter(source));
44 /** Test some examples from the paper */
45 public void testExamples() throws IOException {
46 checkOneTerm(analyzer, "chevaux", "cheval");
47 checkOneTerm(analyzer, "hiboux", "hibou");
49 checkOneTerm(analyzer, "chantés", "chant");
50 checkOneTerm(analyzer, "chanter", "chant");
51 checkOneTerm(analyzer, "chante", "chant");
53 checkOneTerm(analyzer, "baronnes", "baron");
54 checkOneTerm(analyzer, "barons", "baron");
55 checkOneTerm(analyzer, "baron", "baron");
58 /** Test against a vocabulary from the reference impl */
59 public void testVocabulary() throws IOException {
60 assertVocabulary(analyzer, getDataFile("frminimaltestdata.zip"), "frminimal.txt");
63 /** blast some random strings through the analyzer */
64 public void testRandomStrings() throws Exception {
65 checkRandomData(random, analyzer, 10000*RANDOM_MULTIPLIER);