Examples of EdgeNGramTokenFilter

org.apache.lucene.analysis.ngram.EdgeNGramTokenFilter
Tokenizes the given token into n-grams of given size(s).
This {@link TokenFilter} create n-grams from the beginning edge or ending edge of a input token.

Examples of org.apache.lucene.analysis.ngram.EdgeNGramTokenFilter

      side = EdgeNGramTokenFilter.Side.FRONT.getLabel();
    }
  }


  public EdgeNGramTokenFilter create(TokenStream input) {
    return new EdgeNGramTokenFilter(input, side, minGramSize, maxGramSize);
  }

View Full Code Here

Examples of org.apache.lucene.analysis.ngram.EdgeNGramTokenFilter

    result = new LowerCaseFilter(result);
    result = new ASCIIFoldingFilter(result);
    List<String> list = Arrays.asList(ENGLISH_STOP_WORDS);
    Set<String> set = new HashSet<String>(list);
    result = new StopFilter(false, result, set, true);
    result = new EdgeNGramTokenFilter(result, Side.FRONT, 1, 20);
    return result;
  }

View Full Code Here

Examples of org.apache.lucene.analysis.ngram.EdgeNGramTokenFilter


          @Override
          protected TokenStreamComponents wrapComponents(String fieldName, TokenStreamComponents components) {
            if (fieldName.equals("textgrams") && minPrefixChars > 0) {
              return new TokenStreamComponents(components.getTokenizer(),
                                               new EdgeNGramTokenFilter(matchVersion,
                                                                        components.getTokenStream(),
                                                                        1, minPrefixChars));
            } else {
              return components;
            }

View Full Code Here

Examples of org.apache.lucene.analysis.ngram.EdgeNGramTokenFilter


          @Override
          protected TokenStreamComponents wrapComponents(String fieldName, TokenStreamComponents components) {
            if (fieldName.equals("textgrams") && minPrefixChars > 0) {
              return new TokenStreamComponents(components.getTokenizer(),
                                               new EdgeNGramTokenFilter(matchVersion,
                                                                        components.getTokenStream(),
                                                                        1, minPrefixChars));
            } else {
              return components;
            }

View Full Code Here

Examples of org.apache.lucene.analysis.ngram.EdgeNGramTokenFilter

      side = EdgeNGramTokenFilter.Side.FRONT.getLabel();
    }
  }


  public EdgeNGramTokenFilter create(TokenStream input) {
    return new EdgeNGramTokenFilter(input, side, minGramSize, maxGramSize);
  }

View Full Code Here

Examples of org.apache.lucene.analysis.ngram.EdgeNGramTokenFilter

            @Override public String name() {
                return "edgeNGram";
            }


            @Override public TokenStream create(TokenStream tokenStream) {
                return new EdgeNGramTokenFilter(tokenStream, EdgeNGramTokenFilter.DEFAULT_SIDE, EdgeNGramTokenFilter.DEFAULT_MIN_GRAM_SIZE, EdgeNGramTokenFilter.DEFAULT_MAX_GRAM_SIZE);
            }
        }));


        tokenFilterFactories.put("edge_ngram", new PreBuiltTokenFilterFactoryFactory(new TokenFilterFactory() {
            @Override public String name() {
                return "edge_ngram";
            }


            @Override public TokenStream create(TokenStream tokenStream) {
                return new EdgeNGramTokenFilter(tokenStream, EdgeNGramTokenFilter.DEFAULT_SIDE, EdgeNGramTokenFilter.DEFAULT_MIN_GRAM_SIZE, EdgeNGramTokenFilter.DEFAULT_MAX_GRAM_SIZE);
            }
        }));


        tokenFilterFactories.put("shingle", new PreBuiltTokenFilterFactoryFactory(new TokenFilterFactory() {
            @Override public String name() {

View Full Code Here

Examples of org.apache.lucene.analysis.ngram.EdgeNGramTokenFilter

        this.maxGram = settings.getAsInt("max_gram", NGramTokenFilter.DEFAULT_MAX_NGRAM_SIZE);
        this.side = EdgeNGramTokenFilter.Side.getSide(settings.get("side", EdgeNGramTokenizer.DEFAULT_SIDE.getLabel()));
    }


    @Override public TokenStream create(TokenStream tokenStream) {
        return new EdgeNGramTokenFilter(tokenStream, side, minGram, maxGram);
    }

View Full Code Here

Examples of org.apache.lucene.analysis.ngram.EdgeNGramTokenFilter

    }
  }


  @Override
  public EdgeNGramTokenFilter create(TokenStream input) {
    return new EdgeNGramTokenFilter(input, side, minGramSize, maxGramSize);
  }

View Full Code Here

Examples of org.apache.lucene.analysis.ngram.EdgeNGramTokenFilter


      @Override
      protected TokenStreamComponents wrapComponents(String fieldName, TokenStreamComponents components) {
        if (fieldName.equals("textgrams") && minPrefixChars > 0) {
          return new TokenStreamComponents(components.getTokenizer(),
                                           new EdgeNGramTokenFilter(matchVersion,
                                                                    components.getTokenStream(),
                                                                    1, minPrefixChars));
        } else {
          return components;
        }

View Full Code Here

Examples of org.apache.lucene.analysis.ngram.EdgeNGramTokenFilter


  private class NGramAnalyzer extends Analyzer {
    @Override
    protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
      final Tokenizer tokenizer = new KeywordTokenizer(reader);
      return new TokenStreamComponents(tokenizer, new ReverseStringFilter(TEST_VERSION_CURRENT, new EdgeNGramTokenFilter(TEST_VERSION_CURRENT, new ReverseStringFilter(TEST_VERSION_CURRENT, tokenizer), 10, 20)));
    }

View Full Code Here

0 1

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.