Example usage for org.apache.lucene.analysis.de GermanAnalyzer getDefaultStopSet

Introduction

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

Prototype

public static final CharArraySet getDefaultStopSet() 

Source Link

Document

Returns a set of default German-stopwords

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 www  . j av a2 s.  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 testGetGermanPreBuiltAnalyzer() {
    CharArraySet stopwords = StandardStopwords.GERMAN.get();
    assertEquals("Expected another stopwords", GermanAnalyzer.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./* w  w  w.ja  v  a2s. c  o m*/
 */
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 {/*w  w w .jav  a 2s . com*/
            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.crosswire.jsword.index.lucene.analysis.GermanLuceneAnalyzer.java

License:Open Source License

public GermanLuceneAnalyzer() {
    stopSet = GermanAnalyzer.getDefaultStopSet();
}

---

From source file:org.efaps.esjp.admin.index.AnalyzerProvider_Base.java

License:Apache License

/**
 * Gets the analyzer.//ww  w  .  ja  v  a2 s  .  co m
 *
 * @param _companyId the _company id
 * @param _language the _language
 * @return the analyzer
 */
public Analyzer getAnalyzer(final Long _companyId, final String _language) {
    final StandardAnalyzer ret;
    switch (_language) {
    case "de":
        ret = new StandardAnalyzer(GermanAnalyzer.getDefaultStopSet());
        break;
    case "es":
        ret = new StandardAnalyzer(SpanishAnalyzer.getDefaultStopSet());
        break;
    case "en":
    default:
        ret = new StandardAnalyzer(EnglishAnalyzer.getDefaultStopSet());
        break;
    }
    return ret;
}

---

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

License:Apache License

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

---

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

License:Apache License

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

---

From source file:org.elasticsearch.neolastic.NeolasticAnalyser.java

License:Apache License

@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
    final Tokenizer tok = new StandardTokenizer(version, reader);
    TokenStream filter = new LowerCaseFilter(version, tok);

    filter = new StopFilter(version, filter, GermanAnalyzer.getDefaultStopSet());

    return new TokenStreamComponents(tok, new NeolasticTokenFilter(filter, synonymsService));
}

---

From source file:org.jahia.services.search.analyzer.GermanSnowballAnalyzer.java

License:Open Source License

public GermanSnowballAnalyzer() {
    super(new SnowballAnalyzer(Version.LUCENE_30, "German", GermanAnalyzer.getDefaultStopSet()));
}

---