01: package org.apache.lucene.analysis.th;
02:
03: /**
04: * Copyright 2006 The Apache Software Foundation
05: *
06: * Licensed under the Apache License, Version 2.0 (the "License");
07: * you may not use this file except in compliance with the License.
08: * You may obtain a copy of the License at
09: *
10: * http://www.apache.org/licenses/LICENSE-2.0
11: *
12: * Unless required by applicable law or agreed to in writing, software
13: * distributed under the License is distributed on an "AS IS" BASIS,
14: * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15: * See the License for the specific language governing permissions and
16: * limitations under the License.
17: */
18:
19: import java.io.Reader;
20: import org.apache.lucene.analysis.Analyzer;
21: import org.apache.lucene.analysis.StopAnalyzer;
22: import org.apache.lucene.analysis.StopFilter;
23: import org.apache.lucene.analysis.TokenStream;
24: import org.apache.lucene.analysis.standard.StandardFilter;
25: import org.apache.lucene.analysis.standard.StandardTokenizer;
26:
27: /**
28: * Analyzer for Thai language. It uses java.text.BreakIterator to break words.
29: * @author Samphan Raruenrom <samphan@osdev.co.th> for To-Be-One Technology Co., Ltd.
30: * @version 0.2
31: */
32: public class ThaiAnalyzer extends Analyzer {
33: public TokenStream tokenStream(String fieldName, Reader reader) {
34: TokenStream ts = new StandardTokenizer(reader);
35: ts = new StandardFilter(ts);
36: ts = new ThaiWordFilter(ts);
37: ts = new StopFilter(ts, StopAnalyzer.ENGLISH_STOP_WORDS);
38: return ts;
39: }
40: }
|