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
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
|
/*
* 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.synonyms;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.elasticsearch.Version;
import org.elasticsearch.cluster.metadata.IndexMetaData;
import org.elasticsearch.common.logging.ESLogger;
import org.elasticsearch.common.logging.Loggers;
import org.elasticsearch.common.lucene.all.AllEntries;
import org.elasticsearch.common.lucene.all.AllTokenStream;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.env.Environment;
import org.elasticsearch.index.Index;
import org.elasticsearch.index.IndexSettings;
import org.elasticsearch.index.analysis.AnalysisRegistry;
import org.elasticsearch.index.analysis.AnalysisService;
import org.elasticsearch.test.ESTestCase;
import org.elasticsearch.test.IndexSettingsModule;
import org.hamcrest.MatcherAssert;
import java.io.IOException;
import java.io.InputStream;
import java.nio.file.Files;
import java.nio.file.Path;
import static org.elasticsearch.common.settings.Settings.settingsBuilder;
import static org.hamcrest.Matchers.equalTo;
/**
*/
public class SynonymsAnalysisTests extends ESTestCase {
protected final ESLogger logger = Loggers.getLogger(getClass());
private AnalysisService analysisService;
public void testSynonymsAnalysis() throws IOException {
InputStream synonyms = getClass().getResourceAsStream("synonyms.txt");
InputStream synonymsWordnet = getClass().getResourceAsStream("synonyms_wordnet.txt");
Path home = createTempDir();
Path config = home.resolve("config");
Files.createDirectory(config);
Files.copy(synonyms, config.resolve("synonyms.txt"));
Files.copy(synonymsWordnet, config.resolve("synonyms_wordnet.txt"));
String json = "/org/elasticsearch/index/analysis/synonyms/synonyms.json";
Settings settings = settingsBuilder().
loadFromStream(json, getClass().getResourceAsStream(json))
.put(Environment.PATH_HOME_SETTING.getKey(), home)
.put(IndexMetaData.SETTING_VERSION_CREATED, Version.CURRENT).build();
IndexSettings idxSettings = IndexSettingsModule.newIndexSettings(new Index("index"), settings);
analysisService = new AnalysisRegistry(null, new Environment(settings)).build(idxSettings);
match("synonymAnalyzer", "kimchy is the dude abides", "shay is the elasticsearch man!");
match("synonymAnalyzer_file", "kimchy is the dude abides", "shay is the elasticsearch man!");
match("synonymAnalyzerWordnet", "abstain", "abstain refrain desist");
match("synonymAnalyzerWordnet_file", "abstain", "abstain refrain desist");
match("synonymAnalyzerWithsettings", "kimchy", "sha hay");
}
private void match(String analyzerName, String source, String target) throws IOException {
Analyzer analyzer = analysisService.analyzer(analyzerName).analyzer();
AllEntries allEntries = new AllEntries();
allEntries.addText("field", source, 1.0f);
allEntries.reset();
TokenStream stream = AllTokenStream.allTokenStream("_all", allEntries, analyzer);
stream.reset();
CharTermAttribute termAtt = stream.addAttribute(CharTermAttribute.class);
StringBuilder sb = new StringBuilder();
while (stream.incrementToken()) {
sb.append(termAtt.toString()).append(" ");
}
MatcherAssert.assertThat(target, equalTo(sb.toString().trim()));
}
}
|
