Example usage for org.apache.lucene.analysis.tr TurkishAnalyzer getDefaultStopSet

Introduction

In this page you can find the example usage for org.apache.lucene.analysis.tr TurkishAnalyzer 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.StandardStopwordsTest.java

License:Apache License

@Test
public void testGetTurkishPreBuiltAnalyzer() {
    CharArraySet stopwords = StandardStopwords.TURKISH.get();
    assertEquals("Expected another stopwords", TurkishAnalyzer.getDefaultStopSet(), stopwords);

}

---

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

License:Apache License

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

---

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

License:Apache License

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

---

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

License:Open Source License

@Override
protected TokenStream getTokenStream(final String strOrig, final boolean stemsAllowed,
        final boolean stopWordsAllowed) {
    if (stemsAllowed) {
        Set<?> stopWords = stopWordsAllowed ? TurkishAnalyzer.getDefaultStopSet() : Collections.EMPTY_SET;
        return new TurkishAnalyzer(getBehavior(), stopWords).tokenStream("", new StringReader(strOrig));
    } else {//from  ww  w . ja va 2 s  . c o  m
        return new StandardTokenizer(getBehavior(), new StringReader(strOrig));
    }
}

---