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

Example 46 with StandardTokenizer

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

the class SnowballAnalyzer method createComponents.

/** Constructs a {@link StandardTokenizer} filtered by a {@link
      StandardFilter}, a {@link LowerCaseFilter}, a {@link StopFilter},
      and a {@link SnowballFilter} */
@Override
public TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer tokenizer = new StandardTokenizer();
    TokenStream result = tokenizer;
    // remove the possessive 's for english stemmers
    if (name.equals("English") || name.equals("Porter") || name.equals("Lovins"))
        result = new EnglishPossessiveFilter(result);
    // Use a special lowercase filter for turkish, the stemmer expects it.
    if (name.equals("Turkish"))
        result = new TurkishLowerCaseFilter(result);
    else
        result = new LowerCaseFilter(result);
    if (stopSet != null)
        result = new StopFilter(result, stopSet);
    result = new SnowballFilter(result, name);
    return new TokenStreamComponents(tokenizer, result);
}

Example 47 with StandardTokenizer

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

the class StandardHtmlStripAnalyzer method createComponents.

@Override
protected TokenStreamComponents createComponents(final String fieldName) {
    final Tokenizer src = new StandardTokenizer();
    TokenStream tok = new StandardFilter(src);
    tok = new LowerCaseFilter(tok);
    if (!stopwords.isEmpty()) {
        tok = new StopFilter(tok, stopwords);
    }
    return new TokenStreamComponents(src, tok);
}

Example 48 with StandardTokenizer

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

the class FingerprintAnalyzer method createComponents.

@Override
protected TokenStreamComponents createComponents(String s) {
    final Tokenizer tokenizer = new StandardTokenizer();
    TokenStream stream = tokenizer;
    stream = new LowerCaseFilter(stream);
    stream = new ASCIIFoldingFilter(stream, false);
    stream = new StopFilter(stream, stopWords);
    stream = new FingerprintFilter(stream, maxOutputSize, separator);
    return new TokenStreamComponents(tokenizer, stream);
}

Example 49 with StandardTokenizer

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

the class SoraniAnalyzer 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 SoraniNormalizationFilter}, 
   *         {@link LowerCaseFilter}, {@link DecimalDigitFilter}, {@link StopFilter}
   *         , {@link SetKeywordMarkerFilter} if a stem exclusion set is
   *         provided and {@link SoraniStemFilter}.
   */
@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new StandardFilter(source);
    result = new SoraniNormalizationFilter(result);
    result = new LowerCaseFilter(result);
    result = new DecimalDigitFilter(result);
    result = new StopFilter(result, stopwords);
    if (!stemExclusionSet.isEmpty())
        result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SoraniStemFilter(result);
    return new TokenStreamComponents(source, result);
}

Example 50 with StandardTokenizer

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

the class TestCJKAnalyzer method testChangedOffsets.

/** test that offsets are correct when mappingcharfilter is previously applied */
public void testChangedOffsets() throws IOException {
    final NormalizeCharMap.Builder builder = new NormalizeCharMap.Builder();
    builder.add("a", "一二");
    builder.add("b", "二三");
    final NormalizeCharMap norm = builder.build();
    Analyzer analyzer = new Analyzer() {

        @Override
        protected TokenStreamComponents createComponents(String fieldName) {
            Tokenizer tokenizer = new StandardTokenizer();
            return new TokenStreamComponents(tokenizer, new CJKBigramFilter(tokenizer));
        }

        @Override
        protected Reader initReader(String fieldName, Reader reader) {
            return new MappingCharFilter(norm, reader);
        }
    };
    assertAnalyzesTo(analyzer, "ab", new String[] { "一二", "二二", "二三" }, new int[] { 0, 0, 1 }, new int[] { 1, 1, 2 });
    // note: offsets are strange since this is how the charfilter maps them... 
    // before bigramming, the 4 tokens look like:
    //   { 0, 0, 1, 1 },
    //   { 0, 1, 1, 2 }
    analyzer.close();
}