Example usage for org.apache.lucene.analysis.pt PortugueseAnalyzer getDefaultStopSet

Introduction

In this page you can find the example usage for org.apache.lucene.analysis.pt PortugueseAnalyzer getDefaultStopSet.

Prototype

public static CharArraySet getDefaultStopSet() 

Source Link

Document

Returns an unmodifiable instance of the default stop words set.

Usage

From source file:com.stratio.cassandra.lucene.schema.analysis.SnowballAnalyzerBuilder.java

License:Apache License

/**
 * 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.
 *//*from  w  w w  . ja  v  a 2s  . co  m*/
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;
    }
}

---

From source file:com.stratio.cassandra.lucene.schema.analysis.StandardStopwordsTest.java

License:Apache License

@Test
public void testGetPortuguesePreBuiltAnalyzer() {
    CharArraySet stopwords = StandardStopwords.PORTUGUESE.get();
    assertEquals("Expected another stopwords", PortugueseAnalyzer.getDefaultStopSet(), stopwords);

}

---

From source file:ie.cmrc.smtx.lucene.analysis.EuropeanAnalyzer.java

License:Apache License

/**
 * Gets the stop words set for the provided language
 * @param language Two-letter code of a language
 * @return {@code CharArraySet} containing the stop words of the provided language.
 * If the provided language is not supported,then the Lucene standard stop words set
 * if returned./*www .  j a  v  a2s .  com*/
 */
protected CharArraySet getStopWordsSet(String language) {
    String lang = language;
    if (lang != null)
        lang = lang.trim().toLowerCase();
    CharArraySet charArraySet = cache.get(lang);
    if (charArraySet == null) {
        if (SUPPORTED_LANGUAGES.contains(lang)) {
            if (lang.equals(LANG_EN)) {
                charArraySet = EnglishAnalyzer.getDefaultStopSet();
            } else if (lang.equals(LANG_FR)) {
                charArraySet = FrenchAnalyzer.getDefaultStopSet();
            } else if (lang.equals(LANG_ES)) {
                charArraySet = SpanishAnalyzer.getDefaultStopSet();
            } else if (lang.equals(LANG_PT)) {
                charArraySet = PortugueseAnalyzer.getDefaultStopSet();
            } else if (lang.equals(LANG_IT)) {
                charArraySet = ItalianAnalyzer.getDefaultStopSet();
            } else if (lang.equals(LANG_DE)) {
                charArraySet = GermanAnalyzer.getDefaultStopSet();
            } else if (lang.equals(LANG_NO)) {
                charArraySet = NorwegianAnalyzer.getDefaultStopSet();
            }
        } else {
            charArraySet = StandardAnalyzer.STOP_WORDS_SET;
        }
        cache.put(lang, charArraySet);
    }
    return charArraySet;
}

---

From source file:it.unipd.dei.ims.lucene.clef.AnalyzerFactory.java

License:Apache License

public static CharArraySet createStopset(String language, String stopsetType, String stopsetPath)
        throws Exception {

    CharArraySet stopset = CharArraySet.EMPTY_SET;

    if (stopsetType.equalsIgnoreCase("CUSTOM")) {

        try {//from  w w  w  . ja  va  2 s.c o m
            File f = new File(stopsetPath);
            stopset = new CharArraySet(0, true);
            Scanner sc = new Scanner(f);
            logger.debug("STOPLIST:");
            while (sc.hasNextLine()) {
                String stopword = sc.nextLine().trim();
                logger.debug("=> " + stopword);
                stopset.add(stopword);
            }
            logger.debug("");
            sc.close();

        } catch (FileNotFoundException e) {
            e.printStackTrace();
            throw new Exception("FileNotFoundException when loading stopset");
        }

    } else if (stopsetType.equalsIgnoreCase("DEFAULT")) {

        switch (language) {
        case "bg":
            stopset = BulgarianAnalyzer.getDefaultStopSet();
            break;
        case "de":
            stopset = GermanAnalyzer.getDefaultStopSet();
            break;
        case "es":
            stopset = SpanishAnalyzer.getDefaultStopSet();
            break;
        case "fa":
            stopset = PersianAnalyzer.getDefaultStopSet();
            break;
        case "fi":
            stopset = FinnishAnalyzer.getDefaultStopSet();
            break;
        case "fr":
            stopset = FrenchAnalyzer.getDefaultStopSet();
            break;
        case "hu":
            stopset = HungarianAnalyzer.getDefaultStopSet();
            break;
        case "it":
            stopset = ItalianAnalyzer.getDefaultStopSet();
            break;
        case "nl":
            stopset = DutchAnalyzer.getDefaultStopSet();
            break;
        case "pt":
            stopset = PortugueseAnalyzer.getDefaultStopSet();
            break;
        case "ru":
            stopset = RussianAnalyzer.getDefaultStopSet();
            break;
        case "sv":
            stopset = SwedishAnalyzer.getDefaultStopSet();
            break;
        default:
            throw new UnsupportedOperationException("Language not supported yet");
        }

    }

    return stopset;
}

---

From source file:org.elasticsearch.analysis.common.PortugueseAnalyzerProvider.java

License:Apache License

PortugueseAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings) {
    super(indexSettings, name, settings);
    analyzer = new PortugueseAnalyzer(
            Analysis.parseStopWords(env, settings, PortugueseAnalyzer.getDefaultStopSet()),
            Analysis.parseStemExclusion(settings, CharArraySet.EMPTY_SET));
    analyzer.setVersion(version);// w w  w .j a v a 2 s. c o m
}

---

From source file:org.elasticsearch.index.analysis.PortugueseAnalyzerProvider.java

License:Apache License

@Inject
public PortugueseAnalyzerProvider(Index index, @IndexSettings Settings indexSettings, Environment env,
        @Assisted String name, @Assisted Settings settings) {
    super(index, indexSettings, name, settings);
    analyzer = new PortugueseAnalyzer(version,
            Analysis.parseStopWords(env, settings, PortugueseAnalyzer.getDefaultStopSet(), version),
            Analysis.parseStemExclusion(settings, CharArraySet.EMPTY_SET, version));
}

---

From source file:org.omegat.tokenizer.LucenePortugueseTokenizer.java

License:Open Source License

@Override
protected TokenStream getTokenStream(final String strOrig, final boolean stemsAllowed,
        final boolean stopWordsAllowed) {
    if (stemsAllowed) {
        Set<?> stopWords = stopWordsAllowed ? PortugueseAnalyzer.getDefaultStopSet() : Collections.EMPTY_SET;
        return new PortugueseAnalyzer(getBehavior(), stopWords).tokenStream("", new StringReader(strOrig));
    } else {//from   w  w w.ja v a2 s.c  o m
        return new StandardTokenizer(getBehavior(), new StringReader(strOrig));
    }
}

---