Examples of termLength()

Examples of org.apache.lucene.analysis.tokenattributes.TermAttribute.termLength()

77
78
79
80
81
82
83
84
85
86
87
    TokenStream stream = analyzer.reusableTokenStream( fieldName, reader);
    TermAttribute attribute = (TermAttribute) stream.addAttribute( TermAttribute.class );
    stream.reset();

    while ( stream.incrementToken() ) {
      if ( attribute.termLength() > 0 ) {
        String term = attribute.term();
        terms.add( term );
      }
    }
    stream.end();
View Full Code Here

Examples of org.apache.lucene.analysis.tokenattributes.TermAttribute.termLength()

210
211
212
213
214
215
216
217
218
219
220
      writer.write('\t'); // edit: Inorder to match Hadoop standard
      // TextInputFormat
      TermAttribute termAtt = (TermAttribute) ts.addAttribute(TermAttribute.class);
      while (ts.incrementToken()) {
        char[] termBuffer = termAtt.termBuffer();
        int termLen = termAtt.termLength();
        writer.write(termBuffer, 0, termLen);
        writer.write(' ');
      }
    } finally {
      IOUtils.quietClose(reader);
View Full Code Here

Examples of org.apache.lucene.analysis.tokenattributes.TermAttribute.termLength()

235
236
237
238
239
240
241
242
243
244
245
   
    List<String> coll = new ArrayList<String>();
    TermAttribute termAtt = (TermAttribute) ts.addAttribute(TermAttribute.class);
    while (ts.incrementToken()) {
      char[] termBuffer = termAtt.termBuffer();
      int termLen = termAtt.termLength();
      String val = new String(termBuffer, 0, termLen);
      coll.add(val);
    }
    return coll.toArray(new String[coll.size()]);
  }
View Full Code Here

Examples of org.apache.lucene.analysis.tokenattributes.TermAttribute.termLength()

70
71
72
73
74
75
76
77
78
79
80
        WikipediaDatasetCreatorMapper.OPEN_TEXT_TAG_PATTERN.matcher(document).replaceFirst(""))
          .replaceAll(""));
      TokenStream stream = analyzer.tokenStream(catMatch, new StringReader(document));
      TermAttribute termAtt = (TermAttribute) stream.addAttribute(TermAttribute.class);
      while (stream.incrementToken()) {
        contents.append(termAtt.termBuffer(), 0, termAtt.termLength()).append(' ');
      }
      output.collect(new Text(WikipediaDatasetCreatorMapper.SPACE_NON_ALPHA_PATTERN.matcher(catMatch)
          .replaceAll("_")), new Text(contents.toString()));
    }
  }
View Full Code Here

Examples of org.apache.lucene.analysis.tokenattributes.TermAttribute.termLength()

45
46
47
48
49
50
51
52
53
54
55
                  OutputCollector<Text,StringTuple> output, Reporter reporter) throws IOException {
    TokenStream stream = analyzer.tokenStream(key.toString(), new StringReader(value.toString()));
    TermAttribute termAtt = (TermAttribute) stream.addAttribute(TermAttribute.class);
    StringTuple document = new StringTuple();
    while (stream.incrementToken()) {
      if (termAtt.termLength() > 0) {
        document.add(new String(termAtt.termBuffer(), 0, termAtt.termLength()));
      }
    }
    output.collect(key, document);
  }
View Full Code Here

Examples of org.apache.lucene.analysis.tokenattributes.TermAttribute.termLength()

46
47
48
49
50
51
52
53
54
55
56
    TokenStream stream = analyzer.tokenStream(key.toString(), new StringReader(value.toString()));
    TermAttribute termAtt = (TermAttribute) stream.addAttribute(TermAttribute.class);
    StringTuple document = new StringTuple();
    while (stream.incrementToken()) {
      if (termAtt.termLength() > 0) {
        document.add(new String(termAtt.termBuffer(), 0, termAtt.termLength()));
      }
    }
    output.collect(key, document);
  }
 
View Full Code Here

Examples of org.apache.lucene.analysis.tokenattributes.TermAttribute.termLength()

1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
                           //t = field.tokenStreamValue().next(t);
                           field.tokenStreamValue().incrementToken();
                           TermAttribute term = field.tokenStreamValue().getAttribute(TermAttribute.class);
                           PayloadAttribute payload = field.tokenStreamValue().getAttribute(PayloadAttribute.class);

                           String value = new String(term.termBuffer(), 0, term.termLength());

                           if (value.startsWith(namePrefix))
                           {
                              // extract value
                              value = value.substring(namePrefix.length());
View Full Code Here

Examples of org.apache.lucene.analysis.tokenattributes.TermAttribute.termLength()

1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
                                    PayloadAttribute payloadAttribute = tokenStream.addAttribute(PayloadAttribute.class);
                                    tokenStream.incrementToken();
                                    tokenStream.end();
                                    tokenStream.close();

                                    String value = new String(termAttribute.termBuffer(), 0, termAttribute.termLength());
                                    if (value.startsWith(namePrefix)) {
                                        // extract value
                                        value = value.substring(namePrefix.length());
                                        // create new named value
                                        Path p = getRelativePath(state, propState);
View Full Code Here

Examples of org.apache.lucene.analysis.tokenattributes.TermAttribute.termLength()

85
86
87
88
89
90
91
92
93
94
95
    TokenStream stream = analyzer.reusableTokenStream( fieldName, reader);
    TermAttribute attribute = stream.addAttribute( TermAttribute.class );
    stream.reset();

    while ( stream.incrementToken() ) {
      if ( attribute.termLength() > 0 ) {
        String term = attribute.term();
        terms.add( term );
      }
    }
    stream.end();
View Full Code Here

Examples of org.apache.lucene.analysis.tokenattributes.TermAttribute.termLength()

85
86
87
88
89
90
91
92
93
94
95
    TokenStream stream = analyzer.reusableTokenStream( fieldName, reader);
    TermAttribute attribute = stream.addAttribute( TermAttribute.class );
    stream.reset();

    while ( stream.incrementToken() ) {
      if ( attribute.termLength() > 0 ) {
        String term = attribute.term();
        terms.add( term );
      }
    }
    stream.end();
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.