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
|
/*
* 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 com.ibm.icu.text.FilteredNormalizer2;
import com.ibm.icu.text.Normalizer2;
import com.ibm.icu.text.UnicodeSet;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.icu.ICUFoldingFilter;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.env.Environment;
import org.elasticsearch.index.IndexSettings;
/**
* Uses the {@link org.apache.lucene.analysis.icu.ICUFoldingFilter}.
* Applies foldings from UTR#30 Character Foldings.
* <p>
* Can be filtered to handle certain characters in a specified way (see http://icu-project.org/apiref/icu4j/com/ibm/icu/text/UnicodeSet.html)
* E.g national chars that should be retained (filter : "[^åäöÅÄÖ]").
*
* <p>The <tt>unicodeSetFilter</tt> attribute can be used to provide the UniCodeSet for filtering.
*
* @author kimchy (shay.banon)
*/
public class IcuFoldingTokenFilterFactory extends AbstractTokenFilterFactory {
private final String unicodeSetFilter;
public IcuFoldingTokenFilterFactory(IndexSettings indexSettings, Environment environment, String name, Settings settings) {
super(indexSettings, name, settings);
this.unicodeSetFilter = settings.get("unicodeSetFilter");
}
@Override
public TokenStream create(TokenStream tokenStream) {
// The ICUFoldingFilter is in fact implemented as a ICUNormalizer2Filter.
// ICUFoldingFilter lacks a constructor for adding filtering so we implemement it here
if (unicodeSetFilter != null) {
Normalizer2 base = Normalizer2.getInstance(
ICUFoldingFilter.class.getResourceAsStream("utr30.nrm"),
"utr30", Normalizer2.Mode.COMPOSE);
UnicodeSet unicodeSet = new UnicodeSet(unicodeSetFilter);
unicodeSet.freeze();
Normalizer2 filtered = new FilteredNormalizer2(base, unicodeSet);
return new org.apache.lucene.analysis.icu.ICUNormalizer2Filter(tokenStream, filtered);
}
else {
return new ICUFoldingFilter(tokenStream);
}
}
}
|
