01: /**
02: * Licensed to the Apache Software Foundation (ASF) under one or more
03: * contributor license agreements. See the NOTICE file distributed with
04: * this work for additional information regarding copyright ownership.
05: * The ASF licenses this file to You under the Apache License, Version 2.0
06: * (the "License"); you may not use this file except in compliance with
07: * the License. You may obtain a copy of the License at
08: *
09: * http://www.apache.org/licenses/LICENSE-2.0
10: *
11: * Unless required by applicable law or agreed to in writing, software
12: * distributed under the License is distributed on an "AS IS" BASIS,
13: * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14: * See the License for the specific language governing permissions and
15: * limitations under the License.
16: */package org.apache.solr.analysis;
17:
18: import org.apache.solr.core.Config;
19: import org.apache.lucene.analysis.StopFilter;
20: import org.apache.lucene.analysis.StopAnalyzer;
21: import org.apache.lucene.analysis.TokenStream;
22:
23: import java.util.Map;
24: import java.util.List;
25: import java.util.Set;
26: import java.io.IOException;
27:
28: /**
29: * @author yonik
30: * @version $Id: StopFilterFactory.java 472574 2006-11-08 18:25:52Z yonik $
31: */
32: public class StopFilterFactory extends BaseTokenFilterFactory {
33: public void init(Map<String, String> args) {
34: super .init(args);
35: String stopWordFile = args.get("words");
36: ignoreCase = getBoolean("ignoreCase", false);
37:
38: if (stopWordFile != null) {
39: try {
40: List<String> wlist = Config.getLines(stopWordFile);
41: stopWords = StopFilter.makeStopSet((String[]) wlist
42: .toArray(new String[0]), ignoreCase);
43: } catch (IOException e) {
44: throw new RuntimeException(e);
45: }
46: }
47: }
48:
49: private Set stopWords = StopFilter
50: .makeStopSet(StopAnalyzer.ENGLISH_STOP_WORDS);
51: private boolean ignoreCase;
52:
53: public TokenStream create(TokenStream input) {
54: return new StopFilter(input, stopWords, ignoreCase);
55: }
56: }
|