Examples of TokenFilterFactory


Examples of org.apache.uima.lucas.indexer.analysis.TokenFilterFactory

      String className = filterDescription.getClassName();
      currentLocateable = filterDescription;
     
      // use cached factory to create filter
      if (filterName != null && factoryClassName == null) {
        TokenFilterFactory tokenFilterFactory = cachedFactories.get(filterName);
        if (tokenFilterFactory == null)
          throw createException("No factory registered for " + filterName
                  + ". Please provide a factory");
       
        filteredTokenStream = createTokenFilter(filteredTokenStream, filterDescription, tokenFilterFactory);
      }
      // use single argument constructor of a token filter
      else if (className != null)
      {
        filteredTokenStream = createTokenFilterWithClassName(filteredTokenStream, className);
      }
      // use factory for creating the filter and cache it if needed
      else if (factoryClassName != null)
      {
        TokenFilterFactory tokenFilterFactory = createTokenFilterFactory(factoryClassName);
        filteredTokenStream = createTokenFilter(filteredTokenStream, filterDescription, tokenFilterFactory);
        if( filterDescription.isReuseFactory() ){
          if( filterName == null )
            throw createException("Provide a name for factory reuse ");
          cachedFactories.put(filterName, tokenFilterFactory);
View Full Code Here

Examples of org.elasticsearch.index.analysis.TokenFilterFactory

    @Test
    public void test() throws IOException {
        AnalysisService analysisService = createAnalysisService();


        TokenFilterFactory tokenFilter = analysisService.tokenFilter("decomp");
        MatcherAssert.assertThat(tokenFilter, Matchers.instanceOf(DecompoundTokenFilterFactory.class));

        String source = "Die Jahresfeier der Rechtsanwaltskanzleien auf dem Donaudampfschiff hat viel Ökosteuer gekostet";

        String[] expected = {
            "Die",
            "Die",
            "Jahresfeier",
            "Jahr",
            "feier",
            "der",
            "der",
            "Rechtsanwaltskanzleien",
            "Recht",
            "anwalt",
            "kanzlei",
            "auf",
            "auf",
            "dem",
            "dem",
            "Donaudampfschiff",
            "Donau",
            "dampf",
            "schiff",
            "hat",
            "hat",
            "viel",
            "viel",
            "Ökosteuer",
            "Ökosteuer",
            "gekostet",
            "gekosten"
        };

        Tokenizer tokenizer = new StandardTokenizer(Version.LUCENE_36, new StringReader(source));

        assertSimpleTSOutput(tokenFilter.create(tokenizer), expected);

    }
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.