Package org.apache.lucene.analysis

Examples of org.apache.lucene.analysis.TokenStream$TokenWrapperAttributeFactory

485
486
487
488
489
490
491
492
493
494
495
496
497
  }
 
  protected Set<String> getHighlightWords(String searchString) {
    try {
      Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT);
      TokenStream stream = analyzer.tokenStream("content", new StringReader(searchString));
      TermAttribute termAtt = (TermAttribute) stream.addAttribute(TermAttribute.class);
      for (boolean next = stream.incrementToken(); next; next = stream.incrementToken()) {
        String term = termAtt.term();
        if(log.isDebug()) log.debug(term);
      }
    } catch (IOException e) {
      log.error("", e);
View Full Code Here
204
205
206
207
208
209
210
211
212
213
214
    Set terms = new HashSet();
    query.extractTerms(terms);
   
    try {
      //highlight content
      TokenStream tokenStream = analyzer.tokenStream(OlatDocument.CONTENT_FIELD_NAME, new StringReader(content));               
      String highlightResult = highlighter.getBestFragments(tokenStream, content, 3, HIGHLIGHT_SEPARATOR);
      // if no highlightResult is in content => look in description
      if (highlightResult.length() == 0) {
        String description = doc.get(OlatDocument.DESCRIPTION_FIELD_NAME);    
        tokenStream = analyzer.tokenStream(OlatDocument.DESCRIPTION_FIELD_NAME, new StringReader(description));               
View Full Code Here
86
87
88
89
90
91
92
93
94
95
96
      {
        String text = hits.doc(i).get(FIELD_NAME);
        int maxNumFragmentsRequired = 5;
        String fragmentSeparator = "...";
        TermPositionVector tpv = (TermPositionVector)reader.getTermFreqVector(hits.id(i),FIELD_NAME);
        TokenStream tokenStream=TokenSources.getTokenStream(tpv);
        /*
        TokenStream tokenStream2=
          (new StandardAnalyzer())
          //XFactory.getWriterAnalyzer()
            .tokenStream(FIELD_NAME,new StringReader(text));
View Full Code Here
69
70
71
72
73
74
75
76
77
78
79
      String text = hit.get(FIELD_NAME);
      int maxNumFragmentsRequired = 5;
      String fragmentSeparator = "...";
      TermPositionVector tpv = (TermPositionVector) reader
          .getTermFreqVector(docId, FIELD_NAME);
      TokenStream tokenStream = TokenSources.getTokenStream(tpv);
      String result = highlighter.getBestFragments(tokenStream, text,
          maxNumFragmentsRequired, fragmentSeparator);
      System.out.println("\n" + result);
    }
    reader.close();
View Full Code Here
69
70
71
72
73
74
75
76
77
78
79
      String text = hit.get(FIELD_NAME);
      int maxNumFragmentsRequired = 5;
      String fragmentSeparator = "...";
      TermPositionVector tpv = (TermPositionVector) reader
          .getTermFreqVector(docId, FIELD_NAME);
      TokenStream tokenStream = TokenSources.getTokenStream(tpv);
      String result = highlighter.getBestFragments(tokenStream, text,
          maxNumFragmentsRequired, fragmentSeparator);
      System.out.println("\n" + result);
    }
    reader.close();
View Full Code Here
77
78
79
80
81
82
83
84
85
86
87
88
89
      e1.printStackTrace();
    }
   
    long begin = System.currentTimeMillis();  
   
    TokenStream tokenStream = ss.tokenStream("", reader);
    try {
      while(tokenStream.incrementToken()){
//        TermAttribute termAttribute = tokenStream.getAttribute(TermAttribute.class);
//        System.out.println(termAttribute.toString());
       
      }
    } catch (IOException e) {
View Full Code Here
69
70
71
72
73
74
75
76
77
78
79
      String text = hit.get(FIELD_NAME);
      int maxNumFragmentsRequired = 5;
      String fragmentSeparator = "...";
      TermPositionVector tpv = (TermPositionVector) reader
          .getTermFreqVector(docId, FIELD_NAME);
      TokenStream tokenStream = TokenSources.getTokenStream(tpv);
      String result = highlighter.getBestFragments(tokenStream, text,
          maxNumFragmentsRequired, fragmentSeparator);
      System.out.println("\n" + result);
    }
    reader.close();
View Full Code Here
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
     
      LinkedList<CToken> list = new LinkedList<CToken>();
      int wordsCount = 0;
     
      //collect token
      TokenStream ts = analyzer.tokenStream("", reader);
      ts.reset();
      TermAttribute termAtt = (TermAttribute) ts
          .addAttribute(TermAttribute.class);
      while (ts.incrementToken()) {
        if (printGate != null && printGate.filter(wordsCount)) {
          list.add(new CToken(termAtt.term(), wordsCount));
        }
        wordsCount++;
      }
View Full Code Here
69
70
71
72
73
74
75
76
77
78
79
      String text = hit.get(FIELD_NAME);
      int maxNumFragmentsRequired = 5;
      String fragmentSeparator = "...";
      TermPositionVector tpv = (TermPositionVector) reader
          .getTermFreqVector(docId, FIELD_NAME);
      TokenStream tokenStream = TokenSources.getTokenStream(tpv);
      String result = highlighter.getBestFragments(tokenStream, text,
          maxNumFragmentsRequired, fragmentSeparator);
      System.out.println("\n" + result);
    }
    reader.close();
View Full Code Here
69
70
71
72
73
74
75
76
77
78
79
      String text = hit.get(FIELD_NAME);
      int maxNumFragmentsRequired = 5;
      String fragmentSeparator = "...";
      TermPositionVector tpv = (TermPositionVector) reader
          .getTermFreqVector(docId, FIELD_NAME);
      TokenStream tokenStream = TokenSources.getTokenStream(tpv);
      String result = highlighter.getBestFragments(tokenStream, text,
          maxNumFragmentsRequired, fragmentSeparator);
      System.out.println("\n" + result);
    }
    reader.close();
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.TokenStream$TokenWrapperAttributeFactory

  • com.code972.elasticsearch.rest.action.RestHebrewAnalyzerCheckWordAction
  • com.gentics.cr.lucene.analysis.CustomPatternAnalyzerTest
  • com.github.pmerienne.trident.ml.preprocessing.EnglishTokenizer
  • com.o19s.RegexPathHierarchyTokenizerTest
  • com.stimulus.archiva.search.FileNameAnalyzer
  • com.stimulus.archiva.search.FileNameAnalyzer$LowercaseDelimiterAnalyzer
  • ivory.core.tokenize.LuceneAnalyzer
  • ivory.core.tokenize.LuceneArabicAnalyzer
  • ivory.core.tokenize.LuceneTokenizer
  • org.apache.jackrabbit.core.query.lucene.SearchIndex
    • 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.