1 package org.wikimedia.search.extra.analysis.khmer;
2
3 import static org.hamcrest.CoreMatchers.equalTo;
4
5 import java.io.IOException;
6
7 import org.apache.lucene.analysis.Analyzer;
8 import org.apache.lucene.analysis.TokenStream;
9 import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
10 import org.elasticsearch.Version;
11 import org.elasticsearch.cluster.metadata.IndexMetadata;
12 import org.elasticsearch.common.settings.Settings;
13 import org.elasticsearch.env.Environment;
14 import org.elasticsearch.index.IndexSettings;
15 import org.elasticsearch.index.analysis.IndexAnalyzers;
16 import org.elasticsearch.test.ESTestCase;
17 import org.elasticsearch.test.IndexSettingsModule;
18 import org.hamcrest.MatcherAssert;
19 import org.junit.Test;
20
21 public class KhmerCharFilterESTest extends ESTestCase {
22 private IndexAnalyzers indexAnalyzers;
23
24 @Test
25 public void testPrebuilt() throws IOException {
26 assertAnalyzerAvailable("khmer_prebuilt", "prebuilt.json");
27 }
28
29 private void assertAnalyzerAvailable(String analyzerName, String analysisResource) throws IOException {
30 Settings indexSettings = settings(Version.CURRENT)
31 .loadFromStream(analysisResource, this.getClass().getResourceAsStream(analysisResource), false)
32 .put(IndexMetadata.SETTING_VERSION_CREATED, Version.CURRENT)
33 .build();
34 IndexSettings indexProps = IndexSettingsModule.newIndexSettings("test", indexSettings);
35 Settings settings = Settings.builder()
36 .put(Environment.PATH_HOME_SETTING.getKey(), createTempDir())
37 .build();
38 indexAnalyzers = createTestAnalysis(indexProps, settings, new ExtraAnalysisKhmerPlugin()).indexAnalyzers;
39 match(analyzerName, "វិគីីភីឌាភាសាខ្្មែរ សូមសា្វគមន៍!", "វិគីភីឌាភាសាខ្មែរ សូមស្វាគមន៍");
40 }
41
42 private void match(String analyzerName, String source, String target) throws IOException {
43 Analyzer analyzer = indexAnalyzers.get(analyzerName).analyzer();
44
45 TokenStream stream = analyzer.tokenStream("_all", source);
46
47 stream.reset();
48 CharTermAttribute termAtt = stream.addAttribute(CharTermAttribute.class);
49
50 StringBuilder sb = new StringBuilder();
51 while (stream.incrementToken()) {
52 sb.append(termAtt.toString()).append(" ");
53 }
54
55 MatcherAssert.assertThat(target, equalTo(sb.toString().trim()));
56 }
57
58 }