01: package org.tigris.scarab.util.word;
02:
03: /* ================================================================
04: * Copyright (c) 2001 Collab.Net. All rights reserved.
05: *
06: * Redistribution and use in source and binary forms, with or without
07: * modification, are permitted provided that the following conditions are
08: * met:
09: *
10: * 1. Redistributions of source code must retain the above copyright
11: * notice, this list of conditions and the following disclaimer.
12: *
13: * 2. Redistributions in binary form must reproduce the above copyright
14: * notice, this list of conditions and the following disclaimer in the
15: * documentation and/or other materials provided with the distribution.
16: *
17: * 3. The end-user documentation included with the redistribution, if
18: * any, must include the following acknowlegement: "This product includes
19: * software developed by Collab.Net <http://www.Collab.Net/>."
20: * Alternately, this acknowlegement may appear in the software itself, if
21: * and wherever such third-party acknowlegements normally appear.
22: *
23: * 4. The hosted project names must not be used to endorse or promote
24: * products derived from this software without prior written
25: * permission. For written permission, please contact info@collab.net.
26: *
27: * 5. Products derived from this software may not use the "Tigris" or
28: * "Scarab" names nor may "Tigris" or "Scarab" appear in their names without
29: * prior written permission of Collab.Net.
30: *
31: * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
32: * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
33: * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
34: * IN NO EVENT SHALL COLLAB.NET OR ITS CONTRIBUTORS BE LIABLE FOR ANY
35: * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
36: * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE
37: * GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
38: * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER
39: * IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
40: * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
41: * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
42: *
43: * ====================================================================
44: *
45: * This software consists of voluntary contributions made by many
46: * individuals on behalf of Collab.Net.
47: */
48:
49: import java.io.Reader;
50: import java.io.IOException;
51: import org.apache.lucene.analysis.PorterStemFilter;
52: import org.apache.lucene.analysis.Analyzer;
53: import org.apache.lucene.analysis.TokenStream;
54: import org.apache.lucene.analysis.Token;
55: import org.apache.lucene.analysis.standard.StandardAnalyzer;
56: import org.tigris.scarab.util.Log;
57:
58: public class PorterStemAnalyzer extends Analyzer {
59: private static final boolean DEBUG = false;
60:
61: /**
62: * Constructs a {@link StandardAnalyzer} filtered by a {@link
63: * PorterStemFilter}.
64: */
65: public final TokenStream tokenStream(String fieldName, Reader reader) {
66: TokenStream result = new StandardAnalyzer().tokenStream(
67: fieldName, reader);
68: result = new PorterStemFilter(result);
69: if (DEBUG) {
70: final TokenStream delegate = result;
71: result = new TokenStream() {
72: /**
73: * Returns the next token in the stream, or null at EOS.
74: */
75: public Token next() throws IOException {
76: Token token = delegate.next();
77: if (token != null) {
78: if (Log.get().isDebugEnabled()) {
79: Log.get().debug(
80: "Token (" + token.type() + "): "
81: + token.termText());
82: }
83: }
84: return token;
85: }
86:
87: /**
88: * Releases resources associated with this stream.
89: */
90: public void close() throws IOException {
91: delegate.close();
92: }
93: };
94: }
95:
96: return result;
97: }
98: }
|