Example usage for org.apache.lucene.analysis.es SpanishAnalyzer SpanishAnalyzer

Introduction

In this page you can find the example usage for org.apache.lucene.analysis.es SpanishAnalyzer SpanishAnalyzer.

Prototype

public SpanishAnalyzer(CharArraySet stopwords, CharArraySet stemExclusionSet) 

Source Link

Document

Builds an analyzer with the given stop words.

Usage

From source file:indexer.files.LuceneWriter.java

public boolean openIndex() {
    try {// w w  w  .  j  a va2s .c  om
        //Abrimos el directorio
        Directory dir = FSDirectory.open(new File(pathToIndex));

        //Elegimos un Analyzer . Y especificamos la versin de Lucene que usamos
        SpanishAnalyzer analyzer = new SpanishAnalyzer(Version.LUCENE_43, new CharArraySet(Version.LUCENE_43,
                Arrays.asList(
                        StringUtils.split(FileUtils.readFileToString(new File(this.pathToStopWords), "UTF-8"))),
                true));

        //Creamos un IndexWriterConfig 
        IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_43, analyzer);
        //Siempre vamos a sobreescribir el indice que tenemos en el directorio
        iwc.setOpenMode(OpenMode.CREATE);

        indexWriter = new IndexWriter(dir, iwc);

        return true;
    } catch (Exception e) {
        System.out.println("Ocurrio un problema abriendo el documento para escritura: " + e.getClass() + " :: "
                + e.getMessage());
        return false;
    }
}

---

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

License:Apache License

SpanishAnalyzerProvider(IndexSettings indexSettings, Environment env, String name, Settings settings) {
    super(indexSettings, name, settings);
    analyzer = new SpanishAnalyzer(Analysis.parseStopWords(env, settings, SpanishAnalyzer.getDefaultStopSet()),
            Analysis.parseStemExclusion(settings, CharArraySet.EMPTY_SET));
    analyzer.setVersion(version);//from  w ww. ja v a2s. co m
}

---

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

License:Open Source License

@Override
protected TokenStream getTokenStream(final String strOrig, final boolean stemsAllowed,
        final boolean stopWordsAllowed) {
    if (stemsAllowed) {
        Set<?> stopWords = stopWordsAllowed ? SpanishAnalyzer.getDefaultStopSet() : Collections.EMPTY_SET;
        return new SpanishAnalyzer(getBehavior(), stopWords).tokenStream("", new StringReader(strOrig));
    } else {/*from  www . ja  v  a  2 s .co  m*/
        return new StandardTokenizer(getBehavior(), new StringReader(strOrig));
    }
}

---