blob: 156ad1ff07e2dcac9b7b06ea8b43a8c48cf2befd (
plain)
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
|
/*
* 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;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.core.StopAnalyzer;
import org.apache.lucene.analysis.core.StopFilter;
import org.apache.lucene.analysis.standard.StandardFilter;
import org.apache.lucene.analysis.standard.StandardTokenizer;
import org.apache.lucene.analysis.standard.std40.StandardTokenizer40;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.analysis.util.StopwordAnalyzerBase;
import org.apache.lucene.util.Version;
public class StandardHtmlStripAnalyzer extends StopwordAnalyzerBase {
/**
* @deprecated use {@link StandardHtmlStripAnalyzer#StandardHtmlStripAnalyzer(CharArraySet)} instead
*/
@Deprecated
public StandardHtmlStripAnalyzer() {
super(StopAnalyzer.ENGLISH_STOP_WORDS_SET);
}
public StandardHtmlStripAnalyzer(CharArraySet stopwords) {
super(stopwords);
}
@Override
protected TokenStreamComponents createComponents(final String fieldName) {
final Tokenizer src;
if (getVersion().onOrAfter(Version.LUCENE_4_7_0)) {
src = new StandardTokenizer();
} else {
src = new StandardTokenizer40();
}
TokenStream tok = new StandardFilter(src);
tok = new LowerCaseFilter(tok);
if (!stopwords.isEmpty()) {
tok = new StopFilter(tok, stopwords);
}
return new TokenStreamComponents(src, tok);
}
}
|