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 | *********************************************************************/
|
---|
26 | package org.greenstone.LuceneWrapper;
|
---|
27 |
|
---|
28 |
|
---|
29 | import java.io.*;
|
---|
30 | import java.util.Set;
|
---|
31 |
|
---|
32 | import org.apache.lucene.analysis.*;
|
---|
33 | import org.apache.lucene.analysis.standard.*;
|
---|
34 |
|
---|
35 | import org.apache.lucene.analysis.ASCIIFoldingFilter;
|
---|
36 |
|
---|
37 | import org.apache.lucene.util.Version;
|
---|
38 |
|
---|
39 |
|
---|
40 | public class GS2Analyzer extends GS2StandardAnalyzer
|
---|
41 | {
|
---|
42 |
|
---|
43 | static Version matchVersion = Version.LUCENE_24;
|
---|
44 |
|
---|
45 |
|
---|
46 | public GS2Analyzer()
|
---|
47 | {
|
---|
48 | super(matchVersion);
|
---|
49 | }
|
---|
50 |
|
---|
51 |
|
---|
52 | public GS2Analyzer(Set stopWords)
|
---|
53 | {
|
---|
54 | super(matchVersion,stopWords);
|
---|
55 | }
|
---|
56 |
|
---|
57 |
|
---|
58 | public GS2Analyzer(String [] stopwords)
|
---|
59 | {
|
---|
60 | super(matchVersion,StopFilter.makeStopSet(stopwords));
|
---|
61 | }
|
---|
62 |
|
---|
63 | @Override
|
---|
64 | protected TokenStreamComponents createComponents(final String fieldName, final Reader reader) {
|
---|
65 | final StandardTokenizer src = new StandardTokenizer(matchVersion, reader);
|
---|
66 | src.setMaxTokenLength(maxTokenLength);
|
---|
67 | src.setReplaceInvalidAcronym(replaceInvalidAcronym);
|
---|
68 | TokenStream tok = new StandardFilter(matchVersion, src);
|
---|
69 | tok = new LowerCaseFilter(matchVersion, tok);
|
---|
70 | tok = new StopFilter(matchVersion, tok, stopwords);
|
---|
71 |
|
---|
72 | // top it up with accent folding
|
---|
73 | tok = new ASCIIFoldingFilter(tok);
|
---|
74 |
|
---|
75 | return new TokenStreamComponents(src, tok) {
|
---|
76 | @Override
|
---|
77 | protected boolean reset(final Reader reader) throws IOException {
|
---|
78 | src.setMaxTokenLength(GS2Analyzer.this.maxTokenLength);
|
---|
79 | return super.reset(reader);
|
---|
80 | }
|
---|
81 | };
|
---|
82 | }
|
---|
83 |
|
---|
84 | }
|
---|
85 |
|
---|
86 |
|
---|