Search in sources :

Example 16 with StandardTokenizer

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

the class GalicianAnalyzer 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 GalicianStemFilter}.
   */
@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 GalicianStemFilter(result);
    return new TokenStreamComponents(source, result);
}
Also used : TokenStream(org.apache.lucene.analysis.TokenStream) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) StopFilter(org.apache.lucene.analysis.StopFilter) SetKeywordMarkerFilter(org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter) StandardFilter(org.apache.lucene.analysis.standard.StandardFilter) Tokenizer(org.apache.lucene.analysis.Tokenizer) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) LowerCaseFilter(org.apache.lucene.analysis.LowerCaseFilter)

Example 17 with StandardTokenizer

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

the class HindiAnalyzer 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 IndicNormalizationFilter},
   *         {@link HindiNormalizationFilter}, {@link SetKeywordMarkerFilter}
   *         if a stem exclusion set is provided, {@link HindiStemFilter}, and
   *         Hindi Stop words
   */
@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new LowerCaseFilter(source);
    result = new DecimalDigitFilter(result);
    if (!stemExclusionSet.isEmpty())
        result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new IndicNormalizationFilter(result);
    result = new HindiNormalizationFilter(result);
    result = new StopFilter(result, stopwords);
    result = new HindiStemFilter(result);
    return new TokenStreamComponents(source, result);
}
Also used : DecimalDigitFilter(org.apache.lucene.analysis.core.DecimalDigitFilter) TokenStream(org.apache.lucene.analysis.TokenStream) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) SetKeywordMarkerFilter(org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter) StopFilter(org.apache.lucene.analysis.StopFilter) IndicNormalizationFilter(org.apache.lucene.analysis.in.IndicNormalizationFilter) Tokenizer(org.apache.lucene.analysis.Tokenizer) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) LowerCaseFilter(org.apache.lucene.analysis.LowerCaseFilter)

Example 18 with StandardTokenizer

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

the class EnglishAnalyzer 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 EnglishPossessiveFilter}, 
   *         {@link LowerCaseFilter}, {@link StopFilter}
   *         , {@link SetKeywordMarkerFilter} if a stem exclusion set is
   *         provided and {@link PorterStemFilter}.
   */
@Override
protected TokenStreamComponents createComponents(String fieldName) {
    final Tokenizer source = new StandardTokenizer();
    TokenStream result = new StandardFilter(source);
    result = new EnglishPossessiveFilter(result);
    result = new LowerCaseFilter(result);
    result = new StopFilter(result, stopwords);
    if (!stemExclusionSet.isEmpty())
        result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new PorterStemFilter(result);
    return new TokenStreamComponents(source, result);
}
Also used : TokenStream(org.apache.lucene.analysis.TokenStream) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) StopFilter(org.apache.lucene.analysis.StopFilter) SetKeywordMarkerFilter(org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter) StandardFilter(org.apache.lucene.analysis.standard.StandardFilter) Tokenizer(org.apache.lucene.analysis.Tokenizer) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) LowerCaseFilter(org.apache.lucene.analysis.LowerCaseFilter)

Example 19 with StandardTokenizer

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

the class BasqueAnalyzer 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 BasqueStemmer());
    return new TokenStreamComponents(source, result);
}
Also used : BasqueStemmer(org.tartarus.snowball.ext.BasqueStemmer) TokenStream(org.apache.lucene.analysis.TokenStream) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) StopFilter(org.apache.lucene.analysis.StopFilter) SetKeywordMarkerFilter(org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter) StandardFilter(org.apache.lucene.analysis.standard.StandardFilter) SnowballFilter(org.apache.lucene.analysis.snowball.SnowballFilter) Tokenizer(org.apache.lucene.analysis.Tokenizer) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) LowerCaseFilter(org.apache.lucene.analysis.LowerCaseFilter)

Example 20 with StandardTokenizer

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

the class IndonesianAnalyzer 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 an {@link StandardTokenizer} filtered with
   *         {@link StandardFilter}, {@link LowerCaseFilter},
   *         {@link StopFilter}, {@link SetKeywordMarkerFilter}
   *         if a stem exclusion set is provided and {@link IndonesianStemFilter}.
   */
@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);
    }
    return new TokenStreamComponents(source, new IndonesianStemFilter(result));
}
Also used : TokenStream(org.apache.lucene.analysis.TokenStream) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) StopFilter(org.apache.lucene.analysis.StopFilter) SetKeywordMarkerFilter(org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter) StandardFilter(org.apache.lucene.analysis.standard.StandardFilter) Tokenizer(org.apache.lucene.analysis.Tokenizer) StandardTokenizer(org.apache.lucene.analysis.standard.StandardTokenizer) LowerCaseFilter(org.apache.lucene.analysis.LowerCaseFilter)

Aggregations

StandardTokenizer (org.apache.lucene.analysis.standard.StandardTokenizer)82 Tokenizer (org.apache.lucene.analysis.Tokenizer)68 TokenStream (org.apache.lucene.analysis.TokenStream)57 LowerCaseFilter (org.apache.lucene.analysis.LowerCaseFilter)43 StopFilter (org.apache.lucene.analysis.StopFilter)43 StandardFilter (org.apache.lucene.analysis.standard.StandardFilter)36 SetKeywordMarkerFilter (org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter)35 StringReader (java.io.StringReader)18 SnowballFilter (org.apache.lucene.analysis.snowball.SnowballFilter)16 Analyzer (org.apache.lucene.analysis.Analyzer)10 LowerCaseFilter (org.apache.lucene.analysis.core.LowerCaseFilter)10 ASCIIFoldingFilter (org.apache.lucene.analysis.miscellaneous.ASCIIFoldingFilter)7 EnglishPossessiveFilter (org.apache.lucene.analysis.en.EnglishPossessiveFilter)6 ElisionFilter (org.apache.lucene.analysis.util.ElisionFilter)6 DecimalDigitFilter (org.apache.lucene.analysis.core.DecimalDigitFilter)5 StopFilter (org.apache.lucene.analysis.core.StopFilter)5 ESTestCase (org.elasticsearch.test.ESTestCase)5 HashMap (java.util.HashMap)4 TokenFilter (org.apache.lucene.analysis.TokenFilter)4 PorterStemFilter (org.apache.lucene.analysis.en.PorterStemFilter)4