1 package org.wikimedia.search.extra.analysis.textify;
2
3 import static org.elasticsearch.common.xcontent.XContentFactory.jsonBuilder;
4 import static org.elasticsearch.test.hamcrest.ElasticsearchAssertions.assertAcked;
5 import static org.elasticsearch.test.hamcrest.ElasticsearchAssertions.assertSearchHits;
6
7 import java.io.IOException;
8 import java.util.Arrays;
9 import java.util.Collection;
10 import java.util.Collections;
11 import java.util.HashMap;
12 import java.util.Map;
13 import java.util.concurrent.ExecutionException;
14
15 import org.apache.lucene.analysis.core.WhitespaceTokenizer;
16 import org.elasticsearch.action.index.IndexRequestBuilder;
17 import org.elasticsearch.action.search.SearchResponse;
18 import org.elasticsearch.common.xcontent.XContentBuilder;
19 import org.elasticsearch.index.analysis.TokenizerFactory;
20 import org.elasticsearch.index.query.QueryBuilders;
21 import org.elasticsearch.indices.analysis.AnalysisModule;
22 import org.elasticsearch.plugins.AnalysisPlugin;
23 import org.elasticsearch.plugins.Plugin;
24 import org.elasticsearch.test.ESIntegTestCase;
25 import org.elasticsearch.test.ESIntegTestCase.ClusterScope;
26 import org.junit.Before;
27 import org.junit.Test;
28
29 @ClusterScope(scope = ESIntegTestCase.Scope.SUITE, transportClientRatio = 0.0)
30 public class LimitedMappingIntegrationTest extends ESIntegTestCase {
31 @Before
32 public void init() throws IOException, InterruptedException, ExecutionException {
33 XContentBuilder settings = jsonBuilder()
34 .startObject()
35 .field("number_of_shards", 1)
36 .startObject("analysis")
37 .startObject("char_filter")
38 .startObject("apos_mini")
39 .field("type", "limited_mapping")
40 .array("mappings", "`=>'", "‘=>'", "\u2019=>'")
41 .endObject()
42 .endObject()
43 .startObject("analyzer")
44 .startObject("ltdmap")
45 .field("tokenizer", "whitespace")
46 .array("char_filter", "apos_mini")
47 .endObject()
48 .endObject()
49 .endObject()
50 .endObject();
51
52 XContentBuilder mapping = jsonBuilder()
53 .startObject()
54 .startObject("test")
55 .startObject("properties")
56 .startObject("test")
57 .field("type", "text")
58 .field("analyzer", "ltdmap")
59 .field("similarity", "BM25")
60 .endObject()
61 .endObject()
62 .endObject()
63 .endObject();
64
65 assertAcked(prepareCreate("test").addMapping("test", mapping).setSettings(settings));
66 ensureGreen();
67 indexRandom(false, doc("curly", "hello w‘orl’d"));
68 indexRandom(false, doc("straight", "hello w'orl'd"));
69 refresh();
70 }
71
72 @Test
73 public void testCurlyAndStraightQuotes() {
74 SearchResponse sr = client().prepareSearch("test")
75 .setQuery(QueryBuilders.matchQuery("test", "w‘orl’d"))
76 .get();
77 assertSearchHits(sr, "curly", "straight");
78
79 sr = client().prepareSearch("test")
80 .setQuery(QueryBuilders.matchQuery("test", "w'orl'd"))
81 .get();
82 assertSearchHits(sr, "curly", "straight");
83 }
84
85 private IndexRequestBuilder doc(String id, String fieldValue) {
86 return client().prepareIndex("test", "test", id).setSource("test", fieldValue);
87 }
88
89 @Override
90 protected Collection<Class<? extends Plugin>> nodePlugins() {
91 return Collections.<Class<? extends
92 Plugin>>unmodifiableList(Arrays.asList(ExtraAnalysisTextifyPlugin.class, MockPlugin.class));
93 }
94
95 public static class MockPlugin extends Plugin implements AnalysisPlugin {
96 @Override
97 public Map<String, AnalysisModule.AnalysisProvider<TokenizerFactory>> getTokenizers() {
98 Map<String, AnalysisModule.AnalysisProvider<TokenizerFactory>> map = new HashMap<>();
99 map.put("whitespace", (isettings, env, name, settings) ->
100 TokenizerFactory.newFactory("whitespace", WhitespaceTokenizer::new));
101 return Collections.unmodifiableMap(map);
102 }
103 }
104
105 }