Examples of KeywordMarkerFilter

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

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

    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 KeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new NorwegianStemmer());
    return new TokenStreamComponents(source, result);
  }

View Full Code Here

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

    return ignoreCase;
  }


  @Override
  public TokenStream create(TokenStream input) {
    return protectedWords == null ? input : new KeywordMarkerFilter(input, protectedWords);
  }

View Full Code Here

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

    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 KeywordMarkerFilter(result, stemExclusionSet);
    result = new GalicianStemFilter(result);
    return new TokenStreamComponents(source, result);
  }

View Full Code Here

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

      result = new ElisionFilter(result, DEFAULT_ARTICLES);
    }
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new KeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new CatalanStemmer());
    return new TokenStreamComponents(source, result);
  }

View Full Code Here

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

    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 KeywordMarkerFilter(result, stemExclusionSet);
    if (matchVersion.onOrAfter(Version.LUCENE_36)) {
      result = new PortugueseLightStemFilter(result);
    } else {
      result = new SnowballFilter(result, new PortugueseStemmer());
    }

View Full Code Here

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

    } else {
      source = new IndicTokenizer(matchVersion, reader);
    }
    TokenStream result = new LowerCaseFilter(matchVersion, source);
    if (!stemExclusionSet.isEmpty())
      result = new KeywordMarkerFilter(result, stemExclusionSet);
    result = new IndicNormalizationFilter(result);
    result = new HindiNormalizationFilter(result);
    result = new StopFilter(matchVersion, result, stopwords);
    result = new HindiStemFilter(result);
    return new TokenStreamComponents(source, result);

View Full Code Here

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

    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 KeywordMarkerFilter(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.KeywordMarkerFilter

      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 KeywordMarkerFilter(result, excltable);
      if (!stemdict.isEmpty())
        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 KeywordMarkerFilter(result, excltable);
      result = new DutchStemFilter(result, stemdict);
      return new TokenStreamComponents(source, result);
    }
  }

View Full Code Here

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

      result = new ElisionFilter(result, DEFAULT_ARTICLES);
    }
    result = new LowerCaseFilter(matchVersion, result);
    result = new StopFilter(matchVersion, result, stopwords);
    if(!stemExclusionSet.isEmpty())
      result = new KeywordMarkerFilter(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.KeywordMarkerFilter

    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 KeywordMarkerFilter(result, stemExclusionSet);
    result = new SnowballFilter(result, new BasqueStemmer());
    return new TokenStreamComponents(source, 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.