Package org.apache.lucene.analysis

Examples of org.apache.lucene.analysis.LengthFilter

22
23
24
25
26
27
28
29
30
31
  @Override
  public TokenStream tokenStream(String fieldName, Reader reader) {
    TokenStream result = new StandardTokenizer(
        Version.LUCENE_CURRENT, reader);
    result = new LowerCaseFilter(result);
    result = new LengthFilter(result, 3, 50);
    result = new StopFilter(true, result, StandardAnalyzer.STOP_WORDS_SET);
    result = new PorterStemFilter(result);
    return result;
  }
View Full Code Here
46
47
48
49
50
51
52
    max=Integer.parseInt(args.get(MAX_KEY));
    enablePositionIncrements = getBoolean("enablePositionIncrements",false);
  }
 
  public LengthFilter create(TokenStream input) {
    return new LengthFilter(enablePositionIncrements, input,min,max);
  }
View Full Code Here
35
36
37
38
39
40
41
    super.init(args);
    min=Integer.parseInt(args.get(MIN_KEY));
    max=Integer.parseInt(args.get(MAX_KEY));
  }
  public LengthFilter create(TokenStream input) {
    return new LengthFilter(input,min,max);
  }
View Full Code Here
42
43
44
45
46
47
48
        max = settings.getAsInt("max", Integer.MAX_VALUE);
        enablePositionIncrements = settings.getAsBoolean("enabled_position_increments", true);
    }

    @Override public TokenStream create(TokenStream tokenStream) {
        return new LengthFilter(enablePositionIncrements, tokenStream, min, max);
    }
View Full Code Here
37
38
39
40
41
42
43
    min = Integer.parseInt( args.get( MIN_KEY ) );
    max = Integer.parseInt( args.get( MAX_KEY ) );
  }

  public LengthFilter create(TokenStream input) {
    return new LengthFilter( input, min, max );
  }
View Full Code Here
269
270
271
272
273
274
275
276
    public TokenStream tokenStream(String fieldName, Reader reader) {
      StandardAnalyzer analyzer = new StandardAnalyzer(VERSION);
//      Set<String> stopWords = new HashSet<String>();
//      stopWords.add("gt");
//      stopWords.add("lt");
      LengthFilter lengthFilter = new LengthFilter(true, analyzer.tokenStream(fieldName, reader), 3, 1000);
      return lengthFilter;
    }
View Full Code Here
65
66
67
68
69
70
71
72
73
74
75
            // streams.tokenizer = new LetterTokenizer(reader);
            streams.tokenizer = new CustomTokenizer(reader);
           
            streams.stream = new StandardFilter(streams.tokenizer);
            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);
View Full Code Here
92
93
94
95
96
97
98
99
100
101
102
        // Tokenizer tokenizer = new LetterTokenizer(reader);
      Tokenizer tokenizer = new CustomTokenizer(reader);

        TokenStream stream = new StandardFilter(tokenizer);
        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);
View Full Code Here
32
33
34
35
36
37
38
    super.init(args);
    min=Integer.parseInt(args.get("min"));
    max=Integer.parseInt(args.get("max"));
  }
  public TokenStream create(TokenStream input) {
    return new LengthFilter(input,min,max);
  }
View Full Code Here
46
47
48
49
50
51
52
53
54
55
56
      result = new WordSplitTokenizer(result);   // non-alphanumerics
      result = new DotSplitTokenizer(result);   // com.package.names
      result = new CamelCaseTokenizer(result);   // CamelCaseIdentifiers
     
      //result = new LowerCaseFilter(result);
      result = new LengthFilter(result, minWordLength, MAX_WORD_LENGTH);
     
      return result;
     
    } else { // PROJECT, EXT fields
      return new KeywordTokenizer(reader); // return whole stream contents as token
View Full Code Here
TOP

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

  • edu.wiki.index.WikipediaAnalyzer
  • it.unibz.instasearch.indexing.FileAnalyzer
  • it.unibz.instasearch.indexing.QueryAnalyzer
  • mia.clustering.ch10.MyAnalyzer
  • org.apache.solr.analysis.LengthFilterFactory
  • org.elasticsearch.index.analysis.LengthTokenFilterFactory
  • srmdata.NSDLIndex$MyAnalyzer
    • Copyright © 2018 www.massapicom. All rights reserved.
    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.