| GermanLuceneAnalyzer.java |
1 /**
2 * Distribution License:
3 * JSword is free software; you can redistribute it and/or modify it under
4 * the terms of the GNU Lesser General Public License, version 2.1 as published by
5 * the Free Software Foundation. This program is distributed in the hope
6 * that it will be useful, but WITHOUT ANY WARRANTY; without even the
7 * implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
8 * See the GNU Lesser General Public License for more details.
9 *
10 * The License is available on the internet at:
11 * http://www.gnu.org/copyleft/lgpl.html
12 * or by writing to:
13 * Free Software Foundation, Inc.
14 * 59 Temple Place - Suite 330
15 * Boston, MA 02111-1307, USA
16 *
17 * Copyright: 2007
18 * The copyright to this program is held by it's authors.
19 *
20 * ID: $Id: KeyAnalyzer.java 1376 2007-06-01 18:27:01Z dmsmith $
21 */
22 package org.crosswire.jsword.index.lucene.analysis;
23
24 import java.io.IOException;
25 import java.io.Reader;
26
27 import org.apache.lucene.analysis.LowerCaseTokenizer;
28 import org.apache.lucene.analysis.StopFilter;
29 import org.apache.lucene.analysis.TokenStream;
30 import org.apache.lucene.analysis.de.GermanAnalyzer;
31 import org.apache.lucene.analysis.de.GermanStemFilter;
32 import org.apache.lucene.util.Version;
33
34 /**
35 * Based on Lucene's GermanAnalyzer
36 *
37 * @see gnu.lgpl.License for license details.<br>
38 * The copyright to this program is held by it's authors.
39 * @author Sijo Cherian [sijocherian at yahoo dot com]
40 */
41 public class GermanLuceneAnalyzer extends AbstractBookAnalyzer {
42 public GermanLuceneAnalyzer() {
43 stopSet = GermanAnalyzer.getDefaultStopSet();
44 }
45
46 /* (non-Javadoc)
47 * @see org.apache.lucene.analysis.Analyzer#tokenStream(java.lang.String, java.io.Reader)
48 */
49 @Override
50 public TokenStream tokenStream(String fieldName, Reader reader) {
51 TokenStream result = new LowerCaseTokenizer(reader);
52
53 if (doStopWords && stopSet != null) {
54 result = new StopFilter(false, result, stopSet);
55 }
56
57 if (doStemming) {
58 result = new GermanStemFilter(result);
59 }
60
61 return result;
62 }
63
64 /* (non-Javadoc)
65 * @see org.apache.lucene.analysis.Analyzer#reusableTokenStream(java.lang.String, java.io.Reader)
66 */
67 @Override
68 public TokenStream reusableTokenStream(String fieldName, Reader reader) throws IOException {
69 SavedStreams streams = (SavedStreams) getPreviousTokenStream();
70 if (streams == null) {
71 streams = new SavedStreams(new LowerCaseTokenizer(reader));
72 if (doStopWords && stopSet != null) {
73 streams.setResult(new StopFilter(StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion), streams.getResult(), stopSet));
74 }
75
76 if (doStemming) {
77 streams.setResult(new GermanStemFilter(streams.getResult()));
78 }
79
80 setPreviousTokenStream(streams);
81 } else {
82 streams.getSource().reset(reader);
83 }
84 return streams.getResult();
85 }
86
87 private final Version matchVersion = Version.LUCENE_29;
88 }
89