summaryrefslogtreecommitdiff
path: root/core/src/test/java/org/elasticsearch/index/analysis/StemmerTokenFilterFactoryTests.java
blob: 737a991f0e05fe998e42eccf31c390dbbd8c8c6c (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
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
103
104
105
106
107
/*
 * 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.WhitespaceTokenizer;
import org.apache.lucene.analysis.en.PorterStemFilter;
import org.apache.lucene.analysis.snowball.SnowballFilter;
import org.elasticsearch.Version;
import org.elasticsearch.common.settings.Settings;
import org.elasticsearch.test.ESTokenStreamTestCase;
import org.elasticsearch.test.VersionUtils;

import java.io.IOException;
import java.io.StringReader;

import static com.carrotsearch.randomizedtesting.RandomizedTest.scaledRandomIntBetween;
import static org.elasticsearch.cluster.metadata.IndexMetaData.SETTING_VERSION_CREATED;
import static org.hamcrest.Matchers.instanceOf;

/**
 *
 */
public class StemmerTokenFilterFactoryTests extends ESTokenStreamTestCase {
    public void testEnglishBackwardsCompatibility() throws IOException {
        int iters = scaledRandomIntBetween(20, 100);
        for (int i = 0; i < iters; i++) {

            Version v = VersionUtils.randomVersion(random());
            Settings settings = Settings.settingsBuilder()
                    .put("index.analysis.filter.my_english.type", "stemmer")
                    .put("index.analysis.filter.my_english.language", "english")
                    .put("index.analysis.analyzer.my_english.tokenizer","whitespace")
                    .put("index.analysis.analyzer.my_english.filter","my_english")
                    .put(SETTING_VERSION_CREATED,v)
                    .put("path.home", createTempDir().toString())
                    .build();

            AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settings);
            TokenFilterFactory tokenFilter = analysisService.tokenFilter("my_english");
            assertThat(tokenFilter, instanceOf(StemmerTokenFilterFactory.class));
            Tokenizer tokenizer = new WhitespaceTokenizer();
            tokenizer.setReader(new StringReader("foo bar"));
            TokenStream create = tokenFilter.create(tokenizer);
            NamedAnalyzer analyzer = analysisService.analyzer("my_english");

            if (v.onOrAfter(Version.V_1_3_0)) {
                assertThat(create, instanceOf(PorterStemFilter.class));
                assertAnalyzesTo(analyzer, "consolingly", new String[]{"consolingli"});
            } else {
                assertThat(create, instanceOf(SnowballFilter.class));
                assertAnalyzesTo(analyzer, "consolingly", new String[]{"consol"});
            }
        }

    }

    public void testPorter2BackwardsCompatibility() throws IOException {
        int iters = scaledRandomIntBetween(20, 100);
        for (int i = 0; i < iters; i++) {

            Version v = VersionUtils.randomVersion(random());
            Settings settings = Settings.settingsBuilder()
                    .put("index.analysis.filter.my_porter2.type", "stemmer")
                    .put("index.analysis.filter.my_porter2.language", "porter2")
                    .put("index.analysis.analyzer.my_porter2.tokenizer","whitespace")
                    .put("index.analysis.analyzer.my_porter2.filter","my_porter2")
                    .put(SETTING_VERSION_CREATED,v)
                    .put("path.home", createTempDir().toString())
                    .build();

            AnalysisService analysisService = AnalysisTestsHelper.createAnalysisServiceFromSettings(settings);
            TokenFilterFactory tokenFilter = analysisService.tokenFilter("my_porter2");
            assertThat(tokenFilter, instanceOf(StemmerTokenFilterFactory.class));
            Tokenizer tokenizer = new WhitespaceTokenizer();
            tokenizer.setReader(new StringReader("foo bar"));
            TokenStream create = tokenFilter.create(tokenizer);
            NamedAnalyzer analyzer = analysisService.analyzer("my_porter2");
            assertThat(create, instanceOf(SnowballFilter.class));

            if (v.onOrAfter(Version.V_1_3_0)) {
                assertAnalyzesTo(analyzer, "possibly", new String[]{"possibl"});
            } else {
                assertAnalyzesTo(analyzer, "possibly", new String[]{"possibli"});
            }
        }

    }

}