Examples of org.apache.lucene.analysis.en.PorterStemFilter

org.apache.lucene.analysis.en.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 { {@literal @Override}protected TokenStreamComponents createComponents(String fieldName, Reader reader) { Tokenizer source = new LowerCaseTokenizer(version, reader); return new TokenStreamComponents(source, new PorterStemFilter(source)); } } 
```
Note: This filter is aware of the {@link KeywordAttribute}. To prevent certain terms from being passed to the stemmer {@link KeywordAttribute#isKeyword()} should be set to truein a previous {@link TokenStream}.

    Tokenizer tokenizer = new SentenceTokenizer(reader);
    TokenStream result = new WordTokenFilter(tokenizer);
    // result = new LowerCaseFilter(result);
    // LowerCaseFilter is not needed, as SegTokenFilter lowercases Basic Latin text.
    // The porter stemming is too strict, this is not a bug, this is a feature:)
    result = new PorterStemFilter(result);
    if (!stopWords.isEmpty()) {
      result = new StopFilter(matchVersion, result, stopWords);
    }
    return new TokenStreamComponents(tokenizer, result);
  }

View Full Code Here

    // the override filter will convert "booked" to "books",
    // but also mark it with KeywordAttribute so Porter will not change it.
    StemmerOverrideFilter.Builder builder = new StemmerOverrideFilter.Builder();
    builder.add("booked", "books");
    Tokenizer tokenizer = new KeywordTokenizer(new StringReader("booked"));
    TokenStream stream = new PorterStemFilter(new StemmerOverrideFilter(
        tokenizer, builder.build()));
    assertTokenStreamContents(stream, new String[] {"books"});
  }

View Full Code Here

    // the override filter will convert "booked" to "books",
    // but also mark it with KeywordAttribute so Porter will not change it.
    StemmerOverrideFilter.Builder builder = new StemmerOverrideFilter.Builder(true);
    builder.add("boOkEd", "books");
    Tokenizer tokenizer = new KeywordTokenizer(new StringReader("BooKeD"));
    TokenStream stream = new PorterStemFilter(new StemmerOverrideFilter(
        tokenizer, builder.build()));
    assertTokenStreamContents(stream, new String[] {"books"});
  }

View Full Code Here

  }


  public void testNoOverrides() throws IOException {
    StemmerOverrideFilter.Builder builder = new StemmerOverrideFilter.Builder(true);
    Tokenizer tokenizer = new KeywordTokenizer(new StringReader("book"));
    TokenStream stream = new PorterStemFilter(new StemmerOverrideFilter(
        tokenizer, builder.build()));
    assertTokenStreamContents(stream, new String[] {"book"});
  }

View Full Code Here

        output.add(entry.getValue());
      }
    }
    Tokenizer tokenizer = new WhitespaceTokenizer(TEST_VERSION_CURRENT,
        new StringReader(input.toString()));
    TokenStream stream = new PorterStemFilter(new StemmerOverrideFilter(
        tokenizer, builder.build()));
    assertTokenStreamContents(stream, output.toArray(new String[0]));
  }

View Full Code Here

    StemmerOverrideMap build = builder.build();
    for (Entry<String,String> entry : entrySet) {
      if (random().nextBoolean()) {
        Tokenizer tokenizer = new KeywordTokenizer(new StringReader(
            entry.getKey()));
        TokenStream stream = new PorterStemFilter(new StemmerOverrideFilter(
            tokenizer, build));
        assertTokenStreamContents(stream, new String[] {entry.getValue()});
      }
    }
  }

View Full Code Here

  protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
    final StandardTokenizer src = new StandardTokenizer(version, reader);
      TokenStream tok = new StandardFilter(version, src);
      tok = new LowerCaseFilter(version, tok);
      tok = new StopFilter(version, tok, StandardAnalyzer.STOP_WORDS_SET);
      tok = new PorterStemFilter(tok);
      return new TokenStreamComponents(src, tok);
  }

View Full Code Here

 *
 */
public class PorterStemFilterFactory extends TokenFilterFactory {
  @Override
  public PorterStemFilter create(TokenStream input) {
    return new PorterStemFilter(input);
  }

View Full Code Here

    args.put("dictionary", "stemdict.txt");
    factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
    factory.init(args);
    factory.inform(loader);
    
    TokenStream ts = new PorterStemFilter(factory.create(tokenizer));
    assertTokenStreamContents(ts, new String[] { "test", "cat" });
  }

View Full Code Here

    args.put("ignoreCase", "true");
    factory.setLuceneMatchVersion(TEST_VERSION_CURRENT);
    factory.init(args);
    factory.inform(loader);
    
    TokenStream ts = new PorterStemFilter(factory.create(tokenizer));
    assertTokenStreamContents(ts, new String[] { "test", "cat" });
  }

View Full Code Here

0 1 2 3

TOP

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

cc.twittertools.index.TweetAnalyzer

cc.twittertools.search.indexing.TweetAnalyzer

com.github.rnewson.couchdb.lucene.util.PorterStemAnalyzer

com.googlecode.lucene.PorterAnalyzer

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

org.apache.lucene.analysis.en.PorterStemFilterFactory

org.apache.lucene.analysis.miscellaneous.TestKeywordMarkerFilterFactory

org.apache.lucene.analysis.miscellaneous.TestStemmerOverrideFilter

org.apache.lucene.analysis.miscellaneous.TestStemmerOverrideFilterFactory

org.apache.mahout.text.MailArchivesClusteringAnalyzer

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.