org.apache.lucene.analysis.cjk.CJKAnalyzer Java Examples
The following examples show how to use
org.apache.lucene.analysis.cjk.CJKAnalyzer.
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example #1
Source File: TestSynonymFilterFactory.java From lucene-solr with Apache License 2.0 | 6 votes |
/** Test that analyzer and tokenizerFactory is both specified */ public void testAnalyzer() throws Exception { final String analyzer = CJKAnalyzer.class.getName(); final String tokenizerFactory = PatternTokenizerFactory.class.getName(); TokenFilterFactory factory = null; factory = tokenFilterFactory("Synonym", "synonyms", "synonyms2.txt", "analyzer", analyzer); assertNotNull(factory); IllegalArgumentException expected = expectThrows(IllegalArgumentException.class, () -> { tokenFilterFactory("Synonym", "synonyms", "synonyms.txt", "analyzer", analyzer, "tokenizerFactory", tokenizerFactory); }); assertTrue(expected.getMessage().contains("Analyzer and TokenizerFactory can't be specified both")); }
Example #2
Source File: CjkAnalyzerProvider.java From Elasticsearch with Apache License 2.0 | 5 votes |
@Inject public CjkAnalyzerProvider(Index index, IndexSettingsService indexSettingsService, Environment env, @Assisted String name, @Assisted Settings settings) { super(index, indexSettingsService.getSettings(), name, settings); CharArraySet stopWords = Analysis.parseStopWords(env, settings, CJKAnalyzer.getDefaultStopSet()); analyzer = new CJKAnalyzer(stopWords); analyzer.setVersion(version); }
Example #3
Source File: LuceneHelperImpl.java From tephra with MIT License | 5 votes |
private Analyzer newAnalyzer() { switch (analyzer) { case "char": return new CharAnalyzer(); case "simple": return new SimpleAnalyzer(); case "standard": return new StandardAnalyzer(); default: return new CJKAnalyzer(); } }
Example #4
Source File: TestRemoveOneClauseHeuristic.java From solr-researcher with Apache License 2.0 | 5 votes |
private Map<Pattern, Analyzer> createCJKAnalyzer() { Analyzer analyzer = new CJKAnalyzer(); Map<Pattern, Analyzer> fieldAnalyzerMaps = new LinkedHashMap<Pattern, Analyzer>(); Pattern fieldPattern = Pattern.compile("cjk"); fieldAnalyzerMaps.put(fieldPattern, analyzer); return fieldAnalyzerMaps; }
Example #5
Source File: CjkAnalyzerProvider.java From crate with Apache License 2.0 | 5 votes |
CjkAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings) { super(indexSettings, name, settings); CharArraySet stopWords = Analysis.parseStopWords( env, settings, CJKAnalyzer.getDefaultStopSet()); analyzer = new CJKAnalyzer(stopWords); analyzer.setVersion(version); }
Example #6
Source File: LuceneTokenizerTestCase.java From jstarcraft-nlp with Apache License 2.0 | 4 votes |
@Override protected NlpTokenizer<? extends NlpToken> getTokenizer() { CJKAnalyzer analyzer = new CJKAnalyzer(); return new LuceneTokenizer(analyzer); }
Example #7
Source File: CjkAnalyzerProvider.java From Elasticsearch with Apache License 2.0 | 4 votes |
@Override public CJKAnalyzer get() { return this.analyzer; }
Example #8
Source File: CjkAnalyzerProvider.java From crate with Apache License 2.0 | 4 votes |
@Override public CJKAnalyzer get() { return this.analyzer; }
Example #9
Source File: CommonAnalysisPlugin.java From crate with Apache License 2.0 | 4 votes |
@Override public List<PreBuiltAnalyzerProviderFactory> getPreBuiltAnalyzerProviderFactories() { List<PreBuiltAnalyzerProviderFactory> analyzers = new ArrayList<>(); analyzers.add(new PreBuiltAnalyzerProviderFactory("standard_html_strip", CachingStrategy.ELASTICSEARCH, () -> new StandardHtmlStripAnalyzer(CharArraySet.EMPTY_SET))); analyzers.add(new PreBuiltAnalyzerProviderFactory("pattern", CachingStrategy.ELASTICSEARCH, () -> new PatternAnalyzer(Regex.compile("\\W+" /*PatternAnalyzer.NON_WORD_PATTERN*/, null), true, CharArraySet.EMPTY_SET))); analyzers.add(new PreBuiltAnalyzerProviderFactory("snowball", CachingStrategy.LUCENE, () -> new SnowballAnalyzer("English", EnglishAnalyzer.ENGLISH_STOP_WORDS_SET))); // Language analyzers: analyzers.add(new PreBuiltAnalyzerProviderFactory("arabic", CachingStrategy.LUCENE, ArabicAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("armenian", CachingStrategy.LUCENE, ArmenianAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("basque", CachingStrategy.LUCENE, BasqueAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("bengali", CachingStrategy.LUCENE, BengaliAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("brazilian", CachingStrategy.LUCENE, BrazilianAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("bulgarian", CachingStrategy.LUCENE, BulgarianAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("catalan", CachingStrategy.LUCENE, CatalanAnalyzer::new)); // chinese analyzer: only for old indices, best effort analyzers.add(new PreBuiltAnalyzerProviderFactory("chinese", CachingStrategy.ONE, StandardAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("cjk", CachingStrategy.LUCENE, CJKAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("czech", CachingStrategy.LUCENE, CzechAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("danish", CachingStrategy.LUCENE, DanishAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("dutch", CachingStrategy.LUCENE, DutchAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("english", CachingStrategy.LUCENE, EnglishAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("finnish", CachingStrategy.LUCENE, FinnishAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("french", CachingStrategy.LUCENE, FrenchAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("galician", CachingStrategy.LUCENE, GalicianAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("german", CachingStrategy.LUCENE, GermanAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("greek", CachingStrategy.LUCENE, GreekAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("hindi", CachingStrategy.LUCENE, HindiAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("hungarian", CachingStrategy.LUCENE, HungarianAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("indonesian", CachingStrategy.LUCENE, IndonesianAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("irish", CachingStrategy.LUCENE, IrishAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("italian", CachingStrategy.LUCENE, ItalianAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("latvian", CachingStrategy.LUCENE, LatvianAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("lithuanian", CachingStrategy.LUCENE, LithuanianAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("norwegian", CachingStrategy.LUCENE, NorwegianAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("persian", CachingStrategy.LUCENE, PersianAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("portuguese", CachingStrategy.LUCENE, PortugueseAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("romanian", CachingStrategy.LUCENE, RomanianAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("russian", CachingStrategy.LUCENE, RussianAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("sorani", CachingStrategy.LUCENE, SoraniAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("spanish", CachingStrategy.LUCENE, SpanishAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("swedish", CachingStrategy.LUCENE, SwedishAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("turkish", CachingStrategy.LUCENE, TurkishAnalyzer::new)); analyzers.add(new PreBuiltAnalyzerProviderFactory("thai", CachingStrategy.LUCENE, ThaiAnalyzer::new)); return analyzers; }