Examples of org.apache.lucene.analysis.PorterStemFilter

org.apache.lucene.analysis.PorterStemFilter
Transforms the token stream as per the Porter stemming algorithm. Note: the input to the stemming filter must already be in lower case, so you will need to use LowerCaseFilter or LowerCaseTokenizer farther down the Tokenizer chain in order for this to work properly!
To use this filter with other analyzers, you'll want to write an Analyzer class that sets up the TokenStream chain as you want it. To use this with LowerCaseTokenizer, for example, you'd write an analyzer like this:
```
 class MyAnalyzer extends Analyzer { public final TokenStream tokenStream(String fieldName, Reader reader) { return new PorterStemFilter(new LowerCaseTokenizer(reader)); } } 
```

     *               provides access to the input text
     * @return an instance of TokenStream
     */
    @Override
    public TokenStream tokenStream(String fieldName, Reader reader) {
       return new PorterStemFilter(new StopFilter(enablePositionIncements, new LowerCaseTokenizer(reader), stopWords));
    }

View Full Code Here

    if (child == null) 
      throw new IllegalArgumentException("child analyzer must not be null");
  
    return new Analyzer() {
      public TokenStream tokenStream(String fieldName, Reader reader) {
        return new PorterStemFilter(
            child.tokenStream(fieldName, reader));
//        /* PorterStemFilter and SnowballFilter have the same behaviour, 
//        but PorterStemFilter is much faster. */
//        return new org.apache.lucene.analysis.snowball.SnowballFilter(
//            child.tokenStream(fieldName, reader), "English");

View Full Code Here

/**
 * @version $Id: PorterStemFilterFactory.java 591158 2007-11-01 22:37:42Z hossman $
 */
public class PorterStemFilterFactory extends BaseTokenFilterFactory {
  public PorterStemFilter create(TokenStream input) {
    return new PorterStemFilter( input );
  }

View Full Code Here

        TokenStream result = new DSTokenizer(reader);


        result = new StandardFilter(result);
        result = new LowerCaseFilter(result);
        result = new StopFilter(result, stopSet);
        result = new PorterStemFilter(result);


        return result;
    }

View Full Code Here

            streams.stream = new LengthFilter(streams.stream, 3, 100);
            streams.stream = new LowerCaseFilter(streams.stream);
            // streams.stream = new StopFilter(true, streams.stream, StopAnalyzer.ENGLISH_STOP_WORDS_SET);
            streams.stream = new StopFilter(true, streams.stream, ENGLISH_STOP_WORDS_SET);
            streams.stream = new CustomFilter(streams.stream);
            streams.stream = new PorterStemFilter(streams.stream);
            streams.stream = new PorterStemFilter(streams.stream);
            streams.stream = new PorterStemFilter(streams.stream);
        } else {
            streams.tokenizer.reset(reader);
        }


        return streams.stream;

View Full Code Here

        stream = new LengthFilter(stream, 3, 100);
        stream = new LowerCaseFilter(stream);
        // stream = new StopFilter(true, stream, StopAnalyzer.ENGLISH_STOP_WORDS_SET);
        stream = new StopFilter(true, stream, ENGLISH_STOP_WORDS_SET);
        stream = new CustomFilter(stream);
        stream = new PorterStemFilter(stream);
        stream = new PorterStemFilter(stream);
        stream = new PorterStemFilter(stream);


        return stream;
    }

View Full Code Here

    result = new StandardFilter(Version.LUCENE_31, result);
    result = new LowerCaseFilter(Version.LUCENE_31, result);
    result = new ASCIIFoldingFilter(result);
    result = new AlphaNumericMaxLengthFilter(result);
    result = new StopFilter(Version.LUCENE_31, result, stopSet);
    return new PorterStemFilter(result);
  }

View Full Code Here

    if (child == null) 
      throw new IllegalArgumentException("child analyzer must not be null");
  
    return new Analyzer() {
      public TokenStream tokenStream(String fieldName, Reader reader) {
        return new PorterStemFilter(
            child.tokenStream(fieldName, reader));
//        /* PorterStemFilter and SnowballFilter have the same behaviour, 
//        but PorterStemFilter is much faster. */
//        return new org.apache.lucene.analysis.snowball.SnowballFilter(
//            child.tokenStream(fieldName, reader), "English");

View Full Code Here

 * @author yonik
 * @version $Id: PorterStemFilterFactory.java 472574 2006-11-08 18:25:52Z yonik $
 */
public class PorterStemFilterFactory extends BaseTokenFilterFactory {
  public TokenStream create(TokenStream input) {
    return new PorterStemFilter(input);
  }

View Full Code Here

    if (child == null) 
      throw new IllegalArgumentException("child analyzer must not be null");
  
    return new Analyzer() {
      public TokenStream tokenStream(String fieldName, Reader reader) {
        return new PorterStemFilter(
            child.tokenStream(fieldName, reader));
//        /* PorterStemFilter and SnowballFilter have the same behaviour, 
//        but PorterStemFilter is much faster. */
//        return new org.apache.lucene.analysis.snowball.SnowballFilter(
//            child.tokenStream(fieldName, reader), "English");

View Full Code Here

0 1 2 3 4

TOP

Related Classes of org.apache.lucene.analysis.PorterStemFilter

BugAnalyzer.PorterStemAnalyzer

com.mozilla.grouperfish.lucene.analysis.en.EnglishAnalyzer

com.mozilla.grouperfish.lucene.analysis.en.NGramEnglishAnalyzer

com.mozilla.grouperfish.transforms.coclustering.lucene.analysis.en.EnglishAnalyzer

com.mozilla.grouperfish.transforms.coclustering.lucene.analysis.en.NGramEnglishAnalyzer

edu.wiki.index.WikipediaAnalyzer

ivory.core.tokenize.LuceneTokenizer

mia.clustering.ch10.MyAnalyzer

mia.clustering.ch12.TwitterAnalyzer

org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.