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.NGramTokenizer;
22:
23: import java.io.Reader;
24: import java.util.Map;
25:
26: /**
27: * Creates new instances of {@link NGramTokenizer}.
28: * @author Otis Gospodnetic
29: * @author Adam Hiatt
30: */
31: public class NGramTokenizerFactory extends BaseTokenizerFactory {
32: private int maxGramSize = 0;
33: private int minGramSize = 0;
34:
35: /** Initializes the n-gram min and max sizes and the side from which one should start tokenizing. */
36: public void init(Map<String, String> args) {
37: super .init(args);
38: String maxArg = args.get("maxGramSize");
39: maxGramSize = (maxArg != null ? Integer.parseInt(maxArg)
40: : NGramTokenizer.DEFAULT_MAX_NGRAM_SIZE);
41:
42: String minArg = args.get("minGramSize");
43: minGramSize = (minArg != null ? Integer.parseInt(minArg)
44: : NGramTokenizer.DEFAULT_MIN_NGRAM_SIZE);
45: }
46:
47: /** Creates the {@link TokenStream} of n-grams from the given {@link Reader}. */
48: public TokenStream create(Reader input) {
49: return new NGramTokenizer(input, minGramSize, maxGramSize);
50: }
51: }
|