Mercurial > hg > LGDataverses

comparison src/main/java/lia/analysis/positional/PositionalPorterStopAnalyzer.java @ 0:fcb8807fbd84

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Fist commit!
author "jurzua <jurzua@mpiwg-berlin.mpg.de>"
date Tue, 10 Mar 2015 15:15:30 +0100
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:fcb8807fbd84
1 /*
2 Copyright (C) 2005-2012, by the President and Fellows of Harvard College.
3
4 Licensed under the Apache License, Version 2.0 (the "License");
5 you may not use this file except in compliance with the License.
6 You may obtain a copy of the License at
7
8 http://www.apache.org/licenses/LICENSE-2.0
9
10 Unless required by applicable law or agreed to in writing, software
11 distributed under the License is distributed on an "AS IS" BASIS,
12 WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 See the License for the specific language governing permissions and
14 limitations under the License.
15
16 Dataverse Network - A web application to share, preserve and analyze research data.
17 Developed at the Institute for Quantitative Social Science, Harvard University.
18 Version 3.0.
19 */
20 package lia.analysis.positional;
21
22 import org.apache.lucene.analysis.Analyzer;
23 import org.apache.lucene.analysis.LowerCaseTokenizer;
24 import org.apache.lucene.analysis.PorterStemFilter;
25 import org.apache.lucene.analysis.StopAnalyzer;
26 import org.apache.lucene.analysis.StopFilter;
27 import org.apache.lucene.analysis.TokenStream;
28
29 import java.io.Reader;
30 import java.util.Set;
31
32 public class PositionalPorterStopAnalyzer extends Analyzer {
33 private Set stopWords;
34
35 public PositionalPorterStopAnalyzer() {
36 this(StopAnalyzer.ENGLISH_STOP_WORDS_SET);
37 }
38
39 public PositionalPorterStopAnalyzer(Set stopWords) {
40 this.stopWords = stopWords;
41 }
42
43 public TokenStream tokenStream(String fieldName, Reader reader) {
44 StopFilter stopFilter = new StopFilter(true,
45 new LowerCaseTokenizer(reader),
46 stopWords);
47 stopFilter.setEnablePositionIncrements(true);
48 return new PorterStemFilter(stopFilter);
49 }
50 }