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
72
73
74
75
76
77
78
79
80
81
82
83
|
/*
* 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.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.core.KeywordTokenizer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.index.Index;
import org.elasticsearch.plugin.analysis.stempel.AnalysisStempelPlugin;
import org.elasticsearch.test.ESTestCase;
import java.io.IOException;
import java.io.StringReader;
import static org.hamcrest.Matchers.equalTo;
public class SimplePolishTokenFilterTests extends ESTestCase {
public void testBasicUsage() throws Exception {
testToken("kwiaty", "kwć");
testToken("canona", "ć");
testToken("wirtualna", "wirtualny");
testToken("polska", "polski");
testAnalyzer("wirtualna polska", "wirtualny", "polski");
}
private void testToken(String source, String expected) throws IOException {
Index index = new Index("test", "_na_");
Settings settings = Settings.builder()
.put("index.analysis.filter.myStemmer.type", "polish_stem")
.build();
AnalysisService analysisService = createAnalysisService(index, settings, new AnalysisStempelPlugin());
TokenFilterFactory filterFactory = analysisService.tokenFilter("myStemmer");
Tokenizer tokenizer = new KeywordTokenizer();
tokenizer.setReader(new StringReader(source));
TokenStream ts = filterFactory.create(tokenizer);
CharTermAttribute term1 = ts.addAttribute(CharTermAttribute.class);
ts.reset();
assertThat(ts.incrementToken(), equalTo(true));
assertThat(term1.toString(), equalTo(expected));
}
private void testAnalyzer(String source, String... expected_terms) throws IOException {
AnalysisService analysisService = createAnalysisService(new Index("test", "_na_"), Settings.EMPTY, new AnalysisStempelPlugin());
Analyzer analyzer = analysisService.analyzer("polish").analyzer();
TokenStream ts = analyzer.tokenStream("test", source);
CharTermAttribute term1 = ts.addAttribute(CharTermAttribute.class);
ts.reset();
for (String expected : expected_terms) {
assertThat(ts.incrementToken(), equalTo(true));
assertThat(term1.toString(), equalTo(expected));
}
}
}
|
