Examples with StopFilter org.apache.lucene.analysis.StopFilter used on opensource projects

Example 21 with StopFilter

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

the class BulgarianAnalyzer 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 BulgarianStemFilter}.
   */
@Override
public 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 BulgarianStemFilter(result);
    return new TokenStreamComponents(source, result);
}

Example 22 with StopFilter

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

the class GreekAnalyzer 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 GreekLowerCaseFilter}, {@link StandardFilter},
   *         {@link StopFilter}, and {@link GreekStemFilter}
   */
@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new GreekLowerCaseFilter(source);
    result = new StandardFilter(result);
    result = new StopFilter(result, stopwords);
    result = new GreekStemFilter(result);
    return new TokenStreamComponents(source, result);
}

Example 23 with StopFilter

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

the class StandardAnalyzer method createComponents.

@Override
protected TokenStreamComponents createComponents(final String fieldName) {
    final StandardTokenizer src = new StandardTokenizer();
    src.setMaxTokenLength(maxTokenLength);
    TokenStream tok = new StandardFilter(src);
    tok = new LowerCaseFilter(tok);
    tok = new StopFilter(tok, stopwords);
    return new TokenStreamComponents(src, tok) {

        @Override
        protected void setReader(final Reader reader) {
            // So that if maxTokenLength was changed, the change takes
            // effect next time tokenStream is called:
            src.setMaxTokenLength(StandardAnalyzer.this.maxTokenLength);
            super.setReader(reader);
        }
    };
}

Example 24 with StopFilter

use of org.apache.lucene.analysis.StopFilter in project ddf by codice.

the class CaseSensitiveContextualAnalyzer method reusableTokenStream.

@Override
public TokenStream reusableTokenStream(String fieldName, Reader reader) throws IOException {
    if (overridesTokenStreamMethod) {
        // tokenStream but not reusableTokenStream
        return tokenStream(fieldName, reader);
    }
    SavedStreams streams = (SavedStreams) getPreviousTokenStream();
    if (streams == null) {
        streams = new SavedStreams();
        setPreviousTokenStream(streams);
        streams.tokenStream = new ContextualTokenizer(reader);
        streams.filteredTokenStream = new StandardFilter(streams.tokenStream);
        streams.filteredTokenStream = new StopFilter(enableStopPositionIncrements, streams.filteredTokenStream, stopSet);
    } else {
        streams.tokenStream.reset(reader);
    }
    return streams.filteredTokenStream;
}

Example 25 with StopFilter

use of org.apache.lucene.analysis.StopFilter in project elasticsearch by elastic.

the class ShingleTokenFilterFactoryTests method testFillerToken.

public void testFillerToken() throws IOException {
    ESTestCase.TestAnalysis analysis = AnalysisTestsHelper.createTestAnalysisFromClassPath(createTempDir(), RESOURCE);
    TokenFilterFactory tokenFilter = analysis.tokenFilter.get("shingle_filler");
    String source = "simon the sorcerer";
    String[] expected = new String[] { "simon FILLER", "simon FILLER sorcerer", "FILLER sorcerer" };
    Tokenizer tokenizer = new WhitespaceTokenizer();
    tokenizer.setReader(new StringReader(source));
    TokenStream stream = new StopFilter(tokenizer, StopFilter.makeStopSet("the"));
    assertTokenStreamContents(tokenFilter.create(stream), expected);
}