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.StringReader;
22 import java.util.ArrayList;
23 import java.util.HashSet;
24 import java.util.List;
27 import org.apache.lucene.analysis.BaseTokenStreamTestCase;
28 import org.apache.lucene.analysis.TokenFilter;
29 import org.apache.lucene.analysis.Tokenizer;
30 import org.apache.lucene.analysis.standard.StandardTokenizer;
31 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
36 public class TestElision extends BaseTokenStreamTestCase {
38 public void testElision() throws Exception {
39 String test = "Plop, juste pour voir l'embrouille avec O'brian. M'enfin.";
40 Tokenizer tokenizer = new StandardTokenizer(TEST_VERSION_CURRENT, new StringReader(test));
41 Set<String> articles = new HashSet<String>();
44 TokenFilter filter = new ElisionFilter(TEST_VERSION_CURRENT, tokenizer, articles);
45 List<String> tas = filter(filter);
46 assertEquals("embrouille", tas.get(4));
47 assertEquals("O'brian", tas.get(6));
48 assertEquals("enfin", tas.get(7));
51 private List<String> filter(TokenFilter filter) throws IOException {
52 List<String> tas = new ArrayList<String>();
53 CharTermAttribute termAtt = filter.getAttribute(CharTermAttribute.class);
54 while (filter.incrementToken()) {
55 tas.add(termAtt.toString());