use of org.apache.lucene.analysis.standard.StandardTokenizer in project lucene-solr by apache.
the class ItalianAnalyzer 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 ItalianLightStemFilter}.
*/
@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 ItalianLightStemFilter(result);
return new TokenStreamComponents(source, result);
}
use of org.apache.lucene.analysis.standard.StandardTokenizer in project lucene-solr by apache.
the class RussianAnalyzer 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, 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 org.tartarus.snowball.ext.RussianStemmer());
return new TokenStreamComponents(source, result);
}
use of org.apache.lucene.analysis.standard.StandardTokenizer in project lucene-solr by apache.
the class CJKAnalyzer method createComponents.
@Override
protected TokenStreamComponents createComponents(String fieldName) {
final Tokenizer source = new StandardTokenizer();
// run the widthfilter first before bigramming, it sometimes combines characters.
TokenStream result = new CJKWidthFilter(source);
result = new LowerCaseFilter(result);
result = new CJKBigramFilter(result);
return new TokenStreamComponents(source, new StopFilter(result, stopwords));
}
use of org.apache.lucene.analysis.standard.StandardTokenizer in project lucene-solr by apache.
the class ArabicAnalyzer 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 LowerCaseFilter}, {@link DecimalDigitFilter}, {@link StopFilter},
* {@link ArabicNormalizationFilter}, {@link SetKeywordMarkerFilter}
* if a stem exclusion set is provided and {@link ArabicStemFilter}.
*/
@Override
protected TokenStreamComponents createComponents(String fieldName) {
final Tokenizer source = new StandardTokenizer();
TokenStream result = new LowerCaseFilter(source);
result = new DecimalDigitFilter(result);
// the order here is important: the stopword list is not normalized!
result = new StopFilter(result, stopwords);
// TODO maybe we should make ArabicNormalization filter also KeywordAttribute aware?!
result = new ArabicNormalizationFilter(result);
if (!stemExclusionSet.isEmpty()) {
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
}
return new TokenStreamComponents(source, new ArabicStemFilter(result));
}
use of org.apache.lucene.analysis.standard.StandardTokenizer 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);
}
Aggregations