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);
}
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);
}
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);
}
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);
}
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));
}
Aggregations