public void testDefaultsPolishAnalysis() throws IOException { final TestAnalysis analysis = createTestAnalysis(new Index("test", "_na_"), Settings.EMPTY, new AnalysisStempelPlugin()); TokenFilterFactory tokenizerFactory = analysis.tokenFilter.get("polish_stem"); MatcherAssert.assertThat(tokenizerFactory, instanceOf(PolishStemTokenFilterFactory.class)); Analyzer analyzer = analysis.indexAnalyzers.get("polish").analyzer(); MatcherAssert.assertThat(analyzer, instanceOf(PolishAnalyzer.class)); }
/** * Ritorna il set di stop words di default per una lingua * * @param language lingua * @return set di stop words */ public static CharArraySet getDefaultStopSet(String language) { try { if ("en".equalsIgnoreCase(language)) { return StandardAnalyzer.STOP_WORDS_SET; } else if ("es".equalsIgnoreCase(language)) { return WordlistLoader.getSnowballWordSet(IOUtils.getDecodingReader(SnowballFilter.class, "spanish_stop.txt", StandardCharsets.UTF_8)); } else if ("fr".equalsIgnoreCase(language)) { return WordlistLoader.getSnowballWordSet(IOUtils.getDecodingReader(SnowballFilter.class, "french_stop.txt", StandardCharsets.UTF_8)); } else if ("de".equalsIgnoreCase(language)) { return WordlistLoader.getSnowballWordSet(IOUtils.getDecodingReader(SnowballFilter.class, "german_stop.txt", StandardCharsets.UTF_8)); } else if ("pl".equalsIgnoreCase(language)) { return WordlistLoader.getWordSet(IOUtils.getDecodingReader(PolishAnalyzer.class, "stopwords.txt", StandardCharsets.UTF_8), "#"); } else if ("pt".equalsIgnoreCase(language) || "br".equalsIgnoreCase(language)) { return WordlistLoader.getSnowballWordSet(IOUtils.getDecodingReader(SnowballFilter.class, "portuguese_stop.txt", StandardCharsets.UTF_8)); } else if ("it".equalsIgnoreCase(language)) { return WordlistLoader.getSnowballWordSet(IOUtils.getDecodingReader(SnowballFilter.class, "italian_stop.txt", StandardCharsets.UTF_8)); } else if ("cz".equalsIgnoreCase(language) || "sk".equalsIgnoreCase(language)) { return WordlistLoader.getWordSet(IOUtils.getDecodingReader(CzechAnalyzer.class, "stopwords.txt", StandardCharsets.UTF_8), "#"); } else if ("tr".equalsIgnoreCase(language)) { return TurkishAnalyzer.loadStopwordSet(false, TurkishAnalyzer.class, "stopwords.txt", "#"); } else if ("ru".equalsIgnoreCase(language)) { return WordlistLoader.getSnowballWordSet(IOUtils.getDecodingReader(SnowballFilter.class, "russian_stop.txt", StandardCharsets.UTF_8)); } else if ("ro".equalsIgnoreCase(language)) { return RomanianAnalyzer.loadStopwordSet(false, RomanianAnalyzer.class, "stopwords.txt", "#"); } else if ("bg".equalsIgnoreCase(language)) { return BulgarianAnalyzer.loadStopwordSet(false, BulgarianAnalyzer.class, "stopwords.txt", "#"); } else if ("nl".equalsIgnoreCase(language)) { return WordlistLoader.getSnowballWordSet(IOUtils.getDecodingReader(SnowballFilter.class, "dutch_stop.txt", StandardCharsets.UTF_8)); } } catch (Exception ignored) { throw new RuntimeException("Unable to load default stopword set"); } return StandardAnalyzer.STOP_WORDS_SET; }
public PolishAnalyzerProvider(IndexSettings indexSettings, Environment environment, String name, Settings settings) { super(indexSettings, name, settings); analyzer = new PolishAnalyzer(PolishAnalyzer.getDefaultStopSet()); analyzer.setVersion(version); }
@Override public PolishAnalyzer get() { return this.analyzer; }
@Override public TokenStream create(TokenStream tokenStream) { return new StempelFilter(tokenStream, new StempelStemmer(PolishAnalyzer.getDefaultTable())); }
@Override public TokenStream create(TokenStream input) { return new StempelFilter(input, new StempelStemmer(PolishAnalyzer.getDefaultTable())); }