1 package org.apache.lucene.analysis.snowball;
2
3 /**
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
10 *
11 * http://www.apache.org/licenses/LICENSE-2.0
12 *
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.
18 */
19
20 import org.apache.lucene.analysis;
21 import org.apache.lucene.analysis.standard;
22
23 import java.io.Reader;
24 import java.util.Set;
25
26 /** Filters {@link StandardTokenizer} with {@link StandardFilter}, {@link
27 * LowerCaseFilter}, {@link StopFilter} and {@link SnowballFilter}.
28 *
29 * Available stemmers are listed in {@link net.sf.snowball.ext}. The name of a
30 * stemmer is the part of the class name before "Stemmer", e.g., the stemmer in
31 * {@link org.tartarus.snowball.ext.EnglishStemmer} is named "English".
32 */
33 public class SnowballAnalyzer extends Analyzer {
34 private String name;
35 private Set stopSet;
36
37 /** Builds the named analyzer with no stop words. */
38 public SnowballAnalyzer(String name) {
39 this.name = name;
40 }
41
42 /** Builds the named analyzer with the given stop words. */
43 public SnowballAnalyzer(String name, String[] stopWords) {
44 this(name);
45 stopSet = StopFilter.makeStopSet(stopWords);
46 }
47
48 /** Constructs a {@link StandardTokenizer} filtered by a {@link
49 StandardFilter}, a {@link LowerCaseFilter} and a {@link StopFilter}. */
50 public TokenStream tokenStream(String fieldName, Reader reader) {
51 TokenStream result = new StandardTokenizer(reader);
52 result = new StandardFilter(result);
53 result = new LowerCaseFilter(result);
54 if (stopSet != null)
55 result = new StopFilter(result, stopSet);
56 result = new SnowballFilter(result, name);
57 return result;
58 }
59 }
Save This Page