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

Example 66 with StandardTokenizer

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

the class LatvianAnalyzer 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 LatvianStemFilter}.
   */
@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 LatvianStemFilter(result);
    return new TokenStreamComponents(source, result);
}

Example 67 with StandardTokenizer

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

the class TestMorfologikAnalyzer method testKeywordAttrTokens.

/** */
public final void testKeywordAttrTokens() throws IOException {
    Analyzer a = new MorfologikAnalyzer() {

        @Override
        protected TokenStreamComponents createComponents(String field) {
            final CharArraySet keywords = new CharArraySet(1, false);
            keywords.add("liście");
            final Tokenizer src = new StandardTokenizer();
            TokenStream result = new StandardFilter(src);
            result = new SetKeywordMarkerFilter(result, keywords);
            result = new MorfologikFilter(result);
            return new TokenStreamComponents(src, result);
        }
    };
    assertAnalyzesTo(a, "liście danych", new String[] { "liście", "dany", "dana", "dane", "dać" }, new int[] { 0, 7, 7, 7, 7 }, new int[] { 6, 13, 13, 13, 13 }, new int[] { 1, 1, 0, 0, 0 });
    a.close();
}

Example 68 with StandardTokenizer

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

the class PolishAnalyzer 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 StempelFilter}.
   */
@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 StempelFilter(result, new StempelStemmer(stemTable));
    return new TokenStreamComponents(source, result);
}

Example 69 with StandardTokenizer

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

the class SpanishAnalyzer 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 SpanishLightStemFilter}.
   */
@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 SpanishLightStemFilter(result);
    return new TokenStreamComponents(source, result);
}

Example 70 with StandardTokenizer

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

the class PersianAnalyzer method createComponents.

/**
   * Creates
   * {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   * used to tokenize all the text in the provided {@link Reader}.
   * 
   * @return {@link org.apache.lucene.analysis.Analyzer.TokenStreamComponents}
   *         built from a {@link StandardTokenizer} filtered with
   *         {@link LowerCaseFilter}, {@link DecimalDigitFilter}, {@link ArabicNormalizationFilter},
   *         {@link PersianNormalizationFilter} and Persian Stop words
   */
@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new LowerCaseFilter(source);
    result = new DecimalDigitFilter(result);
    result = new ArabicNormalizationFilter(result);
    /* additional persian-specific normalization */
    result = new PersianNormalizationFilter(result);
    /*
     * the order here is important: the stopword list is normalized with the
     * above!
     */
    return new TokenStreamComponents(source, new StopFilter(result, stopwords));
}