01: package org.apache.solr.analysis;
02:
03: /**
04: * Licensed to the Apache Software Foundation (ASF) under one or more
05: * contributor license agreements. See the NOTICE file distributed with
06: * this work for additional information regarding copyright ownership.
07: * The ASF licenses this file to You under the Apache License, Version 2.0
08: * (the "License"); you may not use this file except in compliance with
09: * the License. You may obtain a copy of the License at
10: *
11: * http://www.apache.org/licenses/LICENSE-2.0
12: *
13: * Unless required by applicable law or agreed to in writing, software
14: * distributed under the License is distributed on an "AS IS" BASIS,
15: * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16: * See the License for the specific language governing permissions and
17: * limitations under the License.
18: */
19:
20: import org.apache.lucene.analysis.TokenStream;
21: import org.apache.lucene.analysis.ngram.EdgeNGramTokenizer;
22:
23: import java.io.Reader;
24: import java.util.Map;
25:
26: /**
27: * Creates new instances of {@link EdgeNGramTokenizer}.
28: * @author Otis Gospodnetic
29: * @author Adam Hiatt
30: */
31: public class EdgeNGramTokenizerFactory extends BaseTokenizerFactory {
32: private int maxGramSize = 0;
33:
34: private int minGramSize = 0;
35:
36: private String side;
37:
38: public void init(Map<String, String> args) {
39: super .init(args);
40: String maxArg = args.get("maxGramSize");
41: maxGramSize = (maxArg != null ? Integer.parseInt(maxArg)
42: : EdgeNGramTokenizer.DEFAULT_MAX_GRAM_SIZE);
43:
44: String minArg = args.get("minGramSize");
45: minGramSize = (minArg != null ? Integer.parseInt(minArg)
46: : EdgeNGramTokenizer.DEFAULT_MIN_GRAM_SIZE);
47:
48: side = args.get("side");
49: if (side == null) {
50: side = EdgeNGramTokenizer.Side.FRONT.getLabel();
51: }
52: }
53:
54: public TokenStream create(Reader input) {
55: return new EdgeNGramTokenizer(input, side, minGramSize,
56: maxGramSize);
57: }
58: }
|