use of org.apache.lucene.analysis.standard.StandardTokenizer in project lucene-solr by apache.
the class DanishAnalyzer 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 DanishStemmer());
return new TokenStreamComponents(source, result);
}
use of org.apache.lucene.analysis.standard.StandardTokenizer in project lucene-solr by apache.
the class GermanAnalyzer 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 StandardFilter}, {@link LowerCaseFilter}, {@link StopFilter}
* , {@link SetKeywordMarkerFilter} if a stem exclusion set is
* provided, {@link GermanNormalizationFilter} and {@link GermanLightStemFilter}
*/
@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);
result = new SetKeywordMarkerFilter(result, exclusionSet);
result = new GermanNormalizationFilter(result);
result = new GermanLightStemFilter(result);
return new TokenStreamComponents(source, result);
}
use of org.apache.lucene.analysis.standard.StandardTokenizer in project lucene-solr by apache.
the class CatalanAnalyzer 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 ElisionFilter}, {@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 ElisionFilter(result, DEFAULT_ARTICLES);
result = new LowerCaseFilter(result);
result = new StopFilter(result, stopwords);
if (!stemExclusionSet.isEmpty())
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
result = new SnowballFilter(result, new CatalanStemmer());
return new TokenStreamComponents(source, result);
}
use of org.apache.lucene.analysis.standard.StandardTokenizer in project lucene-solr by apache.
the class CzechAnalyzer 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 StandardFilter}, {@link LowerCaseFilter}, {@link StopFilter}
* , and {@link CzechStemFilter} (only if version is >= LUCENE_31). If
* a stem exclusion set is provided via
* {@link #CzechAnalyzer(CharArraySet, CharArraySet)} a
* {@link SetKeywordMarkerFilter} is added before
* {@link CzechStemFilter}.
*/
@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 (!this.stemExclusionTable.isEmpty())
result = new SetKeywordMarkerFilter(result, stemExclusionTable);
result = new CzechStemFilter(result);
return new TokenStreamComponents(source, result);
}
use of org.apache.lucene.analysis.standard.StandardTokenizer in project lucene-solr by apache.
the class BrazilianAnalyzer 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 StandardFilter}, {@link StopFilter}
* , and {@link BrazilianStemFilter}.
*/
@Override
protected TokenStreamComponents createComponents(String fieldName) {
Tokenizer source = new StandardTokenizer();
TokenStream result = new LowerCaseFilter(source);
result = new StandardFilter(result);
result = new StopFilter(result, stopwords);
if (excltable != null && !excltable.isEmpty())
result = new SetKeywordMarkerFilter(result, excltable);
return new TokenStreamComponents(source, new BrazilianStemFilter(result));
}
Aggregations