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:  $
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.cz.CzechAnalyzer;
31  import org.apache.lucene.util.Version;
32  
33  /**
34   * An Analyzer whose {@link TokenStream} is built from a
35   * {@link LowerCaseTokenizer} filtered with {@link StopFilter} (optional).
36   * Stemming not implemented yet
37   * 
38   * @see gnu.lgpl.License for license details.<br>
39   *      The copyright to this program is held by it's authors.
40   * @author Sijo Cherian [sijocherian at yahoo dot com]
41   * @author DM SMITH [dmsmith555 at yahoo dot com]
42   */
43  public class CzechLuceneAnalyzer extends AbstractBookAnalyzer {
44      public CzechLuceneAnalyzer() {
45          stopSet = CzechAnalyzer.getDefaultStopSet();
46      }
47  
48      /* (non-Javadoc)
49       * @see org.apache.lucene.analysis.Analyzer#tokenStream(java.lang.String, java.io.Reader)
50       */
51      @Override
52      public final TokenStream tokenStream(String fieldName, Reader reader) {
53          TokenStream result = new LowerCaseTokenizer(reader);
54  
55          if (doStopWords && stopSet != null) {
56              result = new StopFilter(false, result, stopSet);
57          }
58  
59          return result;
60      }
61  
62      /* (non-Javadoc)
63       * @see org.apache.lucene.analysis.Analyzer#reusableTokenStream(java.lang.String, java.io.Reader)
64       */
65      @Override
66      public TokenStream reusableTokenStream(String fieldName, Reader reader) throws IOException {
67          SavedStreams streams = (SavedStreams) getPreviousTokenStream();
68          if (streams == null) {
69              streams = new SavedStreams(new LowerCaseTokenizer(reader));
70              if (doStopWords && stopSet != null) {
71                  streams.setResult(new StopFilter(StopFilter.getEnablePositionIncrementsVersionDefault(matchVersion), streams.getResult(), stopSet));
72              }
73  
74              setPreviousTokenStream(streams);
75          } else {
76              streams.getSource().reset(reader);
77          }
78          return streams.getResult();
79      }
80  
81      private final Version matchVersion = Version.LUCENE_29;
82  }
83