1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
|
/*
* Licensed to Elasticsearch under one or more contributor
* license agreements. See the NOTICE file distributed with
* this work for additional information regarding copyright
* ownership. Elasticsearch licenses this file to you under
* the Apache License, Version 2.0 (the "License"); you may
* not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing,
* software distributed under the License is distributed on an
* "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
* KIND, either express or implied. See the License for the
* specific language governing permissions and limitations
* under the License.
*/
package org.elasticsearch.index.analysis.compound;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.compound.HyphenationCompoundWordTokenFilter;
import org.apache.lucene.analysis.compound.Lucene43HyphenationCompoundWordTokenFilter;
import org.apache.lucene.analysis.compound.hyphenation.HyphenationTree;
import org.apache.lucene.util.Version;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.env.Environment;
import org.elasticsearch.index.IndexSettings;
import org.xml.sax.InputSource;
import java.nio.file.Files;
import java.nio.file.Path;
/**
* Uses the {@link org.apache.lucene.analysis.compound.HyphenationCompoundWordTokenFilter} to decompound tokens based on hyphenation rules.
*
* @see org.apache.lucene.analysis.compound.HyphenationCompoundWordTokenFilter
*/
public class HyphenationCompoundWordTokenFilterFactory extends AbstractCompoundWordTokenFilterFactory {
private final HyphenationTree hyphenationTree;
public HyphenationCompoundWordTokenFilterFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
super(indexSettings, env, name, settings);
String hyphenationPatternsPath = settings.get("hyphenation_patterns_path", null);
if (hyphenationPatternsPath == null) {
throw new IllegalArgumentException("hyphenation_patterns_path is a required setting.");
}
Path hyphenationPatternsFile = env.configFile().resolve(hyphenationPatternsPath);
try {
hyphenationTree = HyphenationCompoundWordTokenFilter.getHyphenationTree(new InputSource(Files.newInputStream(hyphenationPatternsFile)));
} catch (Exception e) {
throw new IllegalArgumentException("Exception while reading hyphenation_patterns_path.", e);
}
}
@Override
public TokenStream create(TokenStream tokenStream) {
if (version.onOrAfter(Version.LUCENE_4_4_0)) {
return new HyphenationCompoundWordTokenFilter(tokenStream, hyphenationTree, wordList, minWordSize,
minSubwordSize, maxSubwordSize, onlyLongestMatch);
} else {
return new Lucene43HyphenationCompoundWordTokenFilter(tokenStream, hyphenationTree, wordList, minWordSize,
minSubwordSize, maxSubwordSize, onlyLongestMatch);
}
}
}
|