private String removeStopWords(String action) { StringBuilder builder = new StringBuilder(); try { FrenchAnalyzer frenchAnalyzer = new FrenchAnalyzer(); TokenStream tokenStream = frenchAnalyzer.tokenStream("contents", action); CharTermAttribute attribute = tokenStream.addAttribute(CharTermAttribute.class); tokenStream.reset(); while (tokenStream.incrementToken()) { String term = attribute.toString(); builder.append(term + " "); } } catch (IOException e) { e.printStackTrace(); } return builder.toString(); }
public FrenchAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings) { super(indexSettings, name, settings); analyzer = new FrenchAnalyzer( Analysis.parseStopWords(env, indexSettings.getIndexVersionCreated(), settings, FrenchAnalyzer.getDefaultStopSet()), Analysis.parseStemExclusion(settings, CharArraySet.EMPTY_SET) ); analyzer.setVersion(version); }
@Override public void inform(ResourceLoader loader) throws IOException { if (articlesFile == null) { articles = FrenchAnalyzer.DEFAULT_ARTICLES; } else { articles = getWordSet(loader, articlesFile, ignoreCase); } }
@Inject public FrenchAnalyzerProvider(Index index, IndexSettingsService indexSettingsService, Environment env, @Assisted String name, @Assisted Settings settings) { super(index, indexSettingsService.getSettings(), name, settings); analyzer = new FrenchAnalyzer(Analysis.parseStopWords(env, settings, FrenchAnalyzer.getDefaultStopSet()), Analysis.parseStemExclusion(settings, CharArraySet.EMPTY_SET)); analyzer.setVersion(version); }
public void testEmptyTerm() throws IOException { Analyzer a = new Analyzer() { @Override protected TokenStreamComponents createComponents(String fieldName, Reader reader) { Tokenizer tokenizer = new KeywordTokenizer(reader); return new TokenStreamComponents(tokenizer, new ElisionFilter(tokenizer, FrenchAnalyzer.DEFAULT_ARTICLES)); } }; checkOneTerm(a, "", ""); }
@Override public void inform(ResourceLoader loader) throws IOException { String articlesFile = args.get("articles"); boolean ignoreCase = getBoolean("ignoreCase", false); if (articlesFile != null) { articles = getWordSet(loader, articlesFile, ignoreCase); } if (articles == null) { articles = FrenchAnalyzer.DEFAULT_ARTICLES; } }
public void testEmptyTerm() throws IOException { Analyzer a = new Analyzer() { @Override protected TokenStreamComponents createComponents(String fieldName, Reader reader) { Tokenizer tokenizer = new KeywordTokenizer(reader); return new TokenStreamComponents(tokenizer, new ElisionFilter(tokenizer, FrenchAnalyzer.DEFAULT_ARTICLES)); } }; checkOneTermReuse(a, "", ""); }
public final Analyzer getAnalyzer(Locale locale) { if (locale.getLanguage().equals(Locale.FRENCH.getLanguage())) { return new FrenchAnalyzer(Version.LUCENE_44); } else { return new StandardAnalyzer(Version.LUCENE_44); } }
@Override public FrenchAnalyzer get() { return this.analyzer; }
protected void configureLucene() { bind(Stemmer.class).to(LuceneStemmer.class).in(Singleton.class); bind(TextNormalizer.class).to(LuceneNormalizer.class).in(Singleton.class); bind(CharArraySet.class).annotatedWith(Models.named(LuceneNormalizer.LUCENE_STOP_WORDS_MODEL)).toInstance(FrenchAnalyzer.getDefaultStopSet()); }
@Singleton @Provides @NoStopWordFiltering public Analyzer getFrenchWithStopWordsAnalyzer() { return new FrenchAnalyzer(CharArraySet.EMPTY_SET); }
@Singleton @Provides public Analyzer getFrenchAnalyzer() { return new FrenchAnalyzer(); }
/** * Returns the default stopwords set used by Lucene language analyzer for the specified language. * * @param language The language for which the stopwords are. The supported languages are English, French, Spanish, * Portuguese, Italian, Romanian, German, Dutch, Swedish, Norwegian, Danish, Russian, Finnish, * Irish, Hungarian, Turkish, Armenian, Basque and Catalan. * @return The default stopwords set used by Lucene language analyzers. */ private static CharArraySet getDefaultStopwords(String language) { switch (language) { case "English": return EnglishAnalyzer.getDefaultStopSet(); case "French": return FrenchAnalyzer.getDefaultStopSet(); case "Spanish": return SpanishAnalyzer.getDefaultStopSet(); case "Portuguese": return PortugueseAnalyzer.getDefaultStopSet(); case "Italian": return ItalianAnalyzer.getDefaultStopSet(); case "Romanian": return RomanianAnalyzer.getDefaultStopSet(); case "German": return GermanAnalyzer.getDefaultStopSet(); case "Dutch": return DutchAnalyzer.getDefaultStopSet(); case "Swedish": return SwedishAnalyzer.getDefaultStopSet(); case "Norwegian": return NorwegianAnalyzer.getDefaultStopSet(); case "Danish": return DanishAnalyzer.getDefaultStopSet(); case "Russian": return RussianAnalyzer.getDefaultStopSet(); case "Finnish": return FinnishAnalyzer.getDefaultStopSet(); case "Irish": return IrishAnalyzer.getDefaultStopSet(); case "Hungarian": return HungarianAnalyzer.getDefaultStopSet(); case "Turkish": return SpanishAnalyzer.getDefaultStopSet(); case "Armenian": return SpanishAnalyzer.getDefaultStopSet(); case "Basque": return BasqueAnalyzer.getDefaultStopSet(); case "Catalan": return CatalanAnalyzer.getDefaultStopSet(); default: return CharArraySet.EMPTY_SET; } }
public Tokenizer() { Analyzer en_analyzer = new EnglishAnalyzer(Version.LUCENE_44); Analyzer es_analyzer = new SpanishAnalyzer(Version.LUCENE_44); Analyzer de_analyzer = new GermanAnalyzer(Version.LUCENE_44); Analyzer da_analyzer = new DanishAnalyzer(Version.LUCENE_44); Analyzer el_analyzer = new GreekAnalyzer(Version.LUCENE_44); Analyzer fr_analyzer = new FrenchAnalyzer(Version.LUCENE_44); Analyzer it_analyzer = new ItalianAnalyzer(Version.LUCENE_44); Analyzer pt_analyzer = new PortugueseAnalyzer(Version.LUCENE_44); Analyzer ru_analyzer = new RussianAnalyzer(Version.LUCENE_44); Analyzer fa_analyzer = new PersianAnalyzer(Version.LUCENE_44); Analyzer ar_analyzer = new ArabicAnalyzer(Version.LUCENE_44); Analyzer id_analyzer = new IndonesianAnalyzer(Version.LUCENE_44); Analyzer pl_analyzer = new MorfologikAnalyzer(Version.LUCENE_44); Analyzer nl_analyzer = new DutchAnalyzer(Version.LUCENE_44); Analyzer no_analyzer = new NorwegianAnalyzer(Version.LUCENE_44); Analyzer ro_analyzer = new RomanianAnalyzer(Version.LUCENE_44); Analyzer sv_analyzer = new SwedishAnalyzer(Version.LUCENE_44); Analyzer fi_analyzer = new FinnishAnalyzer(Version.LUCENE_44); Analyzer tr_analyzer = new TurkishAnalyzer(Version.LUCENE_44); Analyzer hu_analyzer = new HungarianAnalyzer(Version.LUCENE_44); Analyzer bg_analyzer = new BulgarianAnalyzer(Version.LUCENE_44); analyzers.put("en", en_analyzer); analyzers.put("es", es_analyzer); analyzers.put("de", de_analyzer); analyzers.put("da", da_analyzer); analyzers.put("el", el_analyzer); analyzers.put("fr", fr_analyzer); analyzers.put("it", it_analyzer); analyzers.put("pt", pt_analyzer); analyzers.put("ru", ru_analyzer); analyzers.put("fa", fa_analyzer); analyzers.put("ar", ar_analyzer); analyzers.put("id", id_analyzer); analyzers.put("pl", pl_analyzer); analyzers.put("nl", nl_analyzer); analyzers.put("no", no_analyzer); analyzers.put("ro", ro_analyzer); analyzers.put("sv", sv_analyzer); analyzers.put("fi", fi_analyzer); analyzers.put("tr", tr_analyzer); analyzers.put("hu", hu_analyzer); analyzers.put("bg", bg_analyzer); }