Examples of SetKeywordMarkerFilter

org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter
Marks terms as keywords via the {@link KeywordAttribute}. Each token contained in the provided set is marked as a keyword by setting {@link KeywordAttribute#setKeyword(boolean)} to true.

Examples of org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter

        final CharArraySet keywords = new CharArraySet(version, 1, false);
        keywords.add("liście");


        final Tokenizer src = new StandardTokenizer(TEST_VERSION_CURRENT, reader);
        TokenStream result = new StandardFilter(TEST_VERSION_CURRENT, src);
        result = new SetKeywordMarkerFilter(result, keywords);
        result = new MorfologikFilter(result, TEST_VERSION_CURRENT); 


        return new TokenStreamComponents(src, result);
      }
    };

View Full Code Here

Examples of org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter

    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new FinnishStemmer());
    return new TokenStreamComponents(source, result);
  }

View Full Code Here

Examples of org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter

    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new NorwegianStemmer());
    return new TokenStreamComponents(source, result);
  }

View Full Code Here

Examples of org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter

    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    if (matchVersion.onOrAfter(Version.LUCENE_36)) {
      result = new SpanishLightStemFilter(result);
    } else {
      result = new SnowballFilter(result, new SpanishStemmer());
    }

View Full Code Here

Examples of org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter

      final Tokenizer source = new StandardTokenizer(matchVersion, aReader);
      TokenStream result = new StandardFilter(matchVersion, source);
      result = new LowerCaseFilter(matchVersion, result);
      result = new StopFilter(matchVersion, result, stoptable);
      if (!excltable.isEmpty())
        result = new SetKeywordMarkerFilter(result, excltable);
      if (stemdict != null)
        result = new StemmerOverrideFilter(result, stemdict);
      result = new SnowballFilter(result, new org.tartarus.snowball.ext.DutchStemmer());
      return new TokenStreamComponents(source, result);
    } else {
      final Tokenizer source = new StandardTokenizer(matchVersion, aReader);
      TokenStream result = new StandardFilter(matchVersion, source);
      result = new StopFilter(matchVersion, result, stoptable);
      if (!excltable.isEmpty())
        result = new SetKeywordMarkerFilter(result, excltable);
      result = new DutchStemFilter(result, origStemdict);
      return new TokenStreamComponents(source, result);
    }
  }

View Full Code Here

Examples of org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter

    final Tokenizer source = new StandardTokenizer(matchVersion, reader);
    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new HungarianStemmer());
    return new TokenStreamComponents(source, result);
  }

View Full Code Here

Examples of org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter

      result = new ElisionFilter(result, DEFAULT_ARTICLES);
    }
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    if (matchVersion.onOrAfter(Version.LUCENE_36)) {
      result = new ItalianLightStemFilter(result);
    } else {
      result = new SnowballFilter(result, new ItalianStemmer());
    }

View Full Code Here

Examples of org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter

      result = new ElisionFilter(result, DEFAULT_ARTICLES);
    }
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new SetKeywordMarkerFilter(result, stemExclusionSet);
    if (matchVersion.onOrAfter(Version.LUCENE_36)) {
      result = new ItalianLightStemFilter(result);
    } else {
      result = new SnowballFilter(result, new ItalianStemmer());
    }

View Full Code Here

Examples of org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter

    TokenStream result = new StandardFilter(matchVersion, source);
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter( matchVersion, result, stopwords);
    if (matchVersion.onOrAfter(Version.LUCENE_31)) {
      if(!this.stemExclusionTable.isEmpty())
        result = new SetKeywordMarkerFilter(result, stemExclusionTable);
      result = new CzechStemFilter(result);
    }
    return new TokenStreamComponents(source, result);
  }

View Full Code Here

Examples of org.apache.lucene.analysis.miscellaneous.SetKeywordMarkerFilter

      TokenStream result = new StandardFilter(matchVersion, source);
      result = new ElisionFilter(result, DEFAULT_ARTICLES);
      result = new LowerCaseFilter(matchVersion, result);
      result = new StopFilter(matchVersion, result, stopwords);
      if(!excltable.isEmpty())
        result = new SetKeywordMarkerFilter(result, excltable);
      if (matchVersion.onOrAfter(Version.LUCENE_36)) {
        result = new FrenchLightStemFilter(result);
      } else {
        result = new SnowballFilter(result, new org.tartarus.snowball.ext.FrenchStemmer());
      }
      return new TokenStreamComponents(source, result);
    } else {
      final Tokenizer source = new StandardTokenizer(matchVersion, reader);
      TokenStream result = new StandardFilter(matchVersion, source);
      result = new StopFilter(matchVersion, result, stopwords);
      if(!excltable.isEmpty())
        result = new SetKeywordMarkerFilter(result, excltable);
      result = new FrenchStemFilter(result);
      // Convert to lowercase after stemming!
      return new TokenStreamComponents(source, new LowerCaseFilter(matchVersion, result));
    }
  }

View Full Code Here

0 1 2 3 4 5

TOP

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.