Examples with StandardTokenizer org.apache.lucene.analysis.standard.StandardTokenizer used on opensource projects

Example 71 with StandardTokenizer

use of org.apache.lucene.analysis.standard.StandardTokenizer in project lucene-solr by apache.

the class FinnishAnalyzer method createComponents.

/**
   * Creates a
   * {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   * which tokenizes all the text in the provided {@link Reader}.
   * 
   * @return A
   *         {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   *         built from an {@link StandardTokenizer} filtered with
   *         {@link StandardFilter}, {@link LowerCaseFilter}, {@link StopFilter}
   *         , {@link SetKeywordMarkerFilter} if a stem exclusion set is
   *         provided and {@link SnowballFilter}.
   */
@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new StandardFilter(source);
    result = new LowerCaseFilter(result);
    result = new StopFilter(result, stopwords);
    if (!stemExclusionSet.isEmpty())
        result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new FinnishStemmer());
    return new TokenStreamComponents(source, result);
}

Example 72 with StandardTokenizer

use of org.apache.lucene.analysis.standard.StandardTokenizer in project lucene-solr by apache.

the class TurkishAnalyzer method createComponents.

/**
   * Creates a
   * {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   * which tokenizes all the text in the provided {@link Reader}.
   * 
   * @return A
   *         {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   *         built from an {@link StandardTokenizer} filtered with
   *         {@link StandardFilter}, {@link TurkishLowerCaseFilter},
   *         {@link StopFilter}, {@link SetKeywordMarkerFilter} if a stem
   *         exclusion set is provided and {@link SnowballFilter}.
   */
@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new StandardFilter(source);
    result = new ApostropheFilter(result);
    result = new TurkishLowerCaseFilter(result);
    result = new StopFilter(result, stopwords);
    if (!stemExclusionSet.isEmpty()) {
        result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    }
    result = new SnowballFilter(result, new TurkishStemmer());
    return new TokenStreamComponents(source, result);
}

Example 73 with StandardTokenizer

use of org.apache.lucene.analysis.standard.StandardTokenizer in project lucene-solr by apache.

the class SwedishAnalyzer method createComponents.

/**
   * Creates a
   * {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   * which tokenizes all the text in the provided {@link Reader}.
   * 
   * @return A
   *         {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   *         built from an {@link StandardTokenizer} filtered with
   *         {@link StandardFilter}, {@link LowerCaseFilter}, {@link StopFilter}
   *         , {@link SetKeywordMarkerFilter} if a stem exclusion set is
   *         provided and {@link SnowballFilter}.
   */
@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new StandardFilter(source);
    result = new LowerCaseFilter(result);
    result = new StopFilter(result, stopwords);
    if (!stemExclusionSet.isEmpty())
        result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new SwedishStemmer());
    return new TokenStreamComponents(source, result);
}

Example 74 with StandardTokenizer

use of org.apache.lucene.analysis.standard.StandardTokenizer in project lucene-solr by apache.

the class PortugueseAnalyzer method createComponents.

/**
   * Creates a
   * {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   * which tokenizes all the text in the provided {@link Reader}.
   * 
   * @return A
   *         {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   *         built from an {@link StandardTokenizer} filtered with
   *         {@link StandardFilter}, {@link LowerCaseFilter}, {@link StopFilter}
   *         , {@link SetKeywordMarkerFilter} if a stem exclusion set is
   *         provided and {@link PortugueseLightStemFilter}.
   */
@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new StandardFilter(source);
    result = new LowerCaseFilter(result);
    result = new StopFilter(result, stopwords);
    if (!stemExclusionSet.isEmpty())
        result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new PortugueseLightStemFilter(result);
    return new TokenStreamComponents(source, result);
}

Example 75 with StandardTokenizer

use of org.apache.lucene.analysis.standard.StandardTokenizer in project lucene-solr by apache.

the class TestElision method testElision.

public void testElision() throws Exception {
    String test = "Plop, juste pour voir l'embrouille avec O'brian. M'enfin.";
    Tokenizer tokenizer = new StandardTokenizer(newAttributeFactory());
    tokenizer.setReader(new StringReader(test));
    CharArraySet articles = new CharArraySet(asSet("l", "M"), false);
    TokenFilter filter = new ElisionFilter(tokenizer, articles);
    List<String> tas = filter(filter);
    assertEquals("embrouille", tas.get(4));
    assertEquals("O'brian", tas.get(6));
    assertEquals("enfin", tas.get(7));
}