source: indexers/trunk/lucene-gs/src/org/greenstone/LuceneWrapper/GS2Analyzer.java@ 17804

Last change on this file since 17804 was 17804, checked in by davidb, 15 years ago

Introduction of GS2Analyzer, which overrides default behaviour of StandardAnalyzer to make accent folding of Latin-1 *on*

File size: 1.9 KB
Line 
1/**********************************************************************
2 *
3 * GS2Analyzer.java
4 *
5 * Copyright 2004 The New Zealand Digital Library Project
6 *
7 * A component of the Greenstone digital library software
8 * from the New Zealand Digital Library Project at the
9 * University of Waikato, New Zealand.
10 *
11 * This program is free software; you can redistribute it and/or modify
12 * it under the terms of the GNU General Public License as published by
13 * the Free Software Foundation; either version 2 of the License, or
14 * (at your option) any later version.
15 *
16 * This program is distributed in the hope that it will be useful,
17 * but WITHOUT ANY WARRANTY; without even the implied warranty of
18 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
19 * GNU General Public License for more details.
20 *
21 * You should have received a copy of the GNU General Public License
22 * along with this program; if not, write to the Free Software
23 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
24 *
25 *********************************************************************/
26package org.greenstone.LuceneWrapper;
27
28
29import java.io.*;
30import java.util.Set;
31
32import org.apache.lucene.analysis.*;
33import org.apache.lucene.analysis.standard.*;
34
35
36class GS2Analyzer extends StandardAnalyzer
37{
38 public GS2Analyzer()
39 {
40 super();
41 }
42
43 public GS2Analyzer(Set stopWords)
44 {
45 super(stopWords);
46 }
47
48
49 public GS2Analyzer(String [] stopwords)
50 {
51 super(stopwords);
52 }
53
54 public TokenStream tokenStream(String fieldName, Reader reader)
55 {
56 TokenStream result = super.tokenStream(fieldName,reader);
57 result = new ISOLatin1AccentFilter(result);
58
59 return result;
60 }
61
62
63 public TokenStream reusableTokenStream(String fieldName, Reader reader) throws IOException {
64 TokenStream result = super.reusableTokenStream(fieldName,reader);
65
66 result = new ISOLatin1AccentFilter(result);
67
68 return result;
69 }
70
71
72}
73
74
Note: See TracBrowser for help on using the repository browser.