Package org.apache.lucene.analysis.tokenattributes

Examples of org.apache.lucene.analysis.tokenattributes.TermAttribute

84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
                      String field,
                      Set<?> stop)
                      throws IOException
  { 
    TokenStream ts = a.tokenStream( field, new StringReader( body));
    TermAttribute termAtt = ts.addAttribute(TermAttribute.class);
   
    BooleanQuery tmp = new BooleanQuery();
    Set<String> already = new HashSet<String>(); // ignore dups
    while (ts.incrementToken()) {
      String word = termAtt.term();
      // ignore opt stop words
      if ( stop != null &&
         stop.contains( word)) continue;
      // ignore dups
      if ( ! already.add( word)) continue;
View Full Code Here
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
                                Fieldable[] fields = aDoc.getFieldables(FieldNames.PROPERTIES);
                                for (Fieldable field : fields) {

                                    // assume properties fields use SingleTokenStream
                                    TokenStream tokenStream = field.tokenStreamValue();
                                    TermAttribute termAttribute = tokenStream.addAttribute(TermAttribute.class);
                                    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);
                                        String path = getNamespaceMappings().translatePath(p);
                                        value = FieldNames.createNamedValue(path, value);
                                        termAttribute.setTermBuffer(value);
                                        doc.add(new Field(field.name(),
                                                new SingletonTokenStream(value, (Payload) payloadAttribute.getPayload().clone())));
                                        doc.add(new Field(
                                                FieldNames.AGGREGATED_NODE_UUID,
                                                false,
View Full Code Here
267
268
269
270
271
272
273
274
275
276
277
278
        Reader r = new StringReader(text);
        TokenStream ts = index.getTextAnalyzer().tokenStream("", r);
        try {
            while (ts.incrementToken()) {
                OffsetAttribute offset = ts.getAttribute(OffsetAttribute.class);
                TermAttribute term = ts.getAttribute(TermAttribute.class);
                String termText = term.term();
                TermVectorOffsetInfo[] info = termMap.get(termText);
                if (info == null) {
                    info = new TermVectorOffsetInfo[1];
                } else {
                    TermVectorOffsetInfo[] tmp = info;
View Full Code Here
23
24
25
26
27
28
29
30
31
32
33
34
35
36
    rules.add("a b c,d");
    SynonymMap synMap = new SynonymMap(true);
    SynonymFilterFactory.parseRules(rules, synMap, "=>", ",", true, null);

    SynonymFilter ts = new SynonymFilter(new WhitespaceTokenizer(new StringReader("a e")), synMap);
    TermAttribute termAtt = (TermAttribute) ts.getAttribute(TermAttribute.class);

    ts.reset();
    List<String> tokens = new ArrayList<String>();
    while (ts.incrementToken()) tokens.add(termAtt.term());

    // This fails because ["e","e"] is the value of the token stream
    Assert.assertEquals(Arrays.asList("a", "e"), tokens);
  }
View Full Code Here
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
  private void assertAnalyzesTo(Analyzer a, String input, String[] output,
      int startOffsets[], int endOffsets[], int posIncs[]) throws Exception {

    TokenStream ts = a.tokenStream("dummy", new StringReader(input));
    TermAttribute termAtt = (TermAttribute) ts
        .getAttribute(TermAttribute.class);
    OffsetAttribute offsetAtt = (OffsetAttribute) ts
        .getAttribute(OffsetAttribute.class);
    PositionIncrementAttribute posIncAtt = (PositionIncrementAttribute) ts
        .getAttribute(PositionIncrementAttribute.class);
    for (int i = 0; i < output.length; i++) {
      assertTrue(ts.incrementToken());
      assertEquals(output[i], termAtt.term());
      assertEquals(startOffsets[i], offsetAtt.startOffset());
      assertEquals(endOffsets[i], offsetAtt.endOffset());
      assertEquals(posIncs[i], posIncAtt.getPositionIncrement());
    }
    assertFalse(ts.incrementToken());
View Full Code Here
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
  public void testReset() throws Exception {
    final String input = "How the s a brown s cow d like A B thing?";
    WhitespaceTokenizer wt = new WhitespaceTokenizer(new StringReader(input));
    CommonGramsFilter cgf = new CommonGramsFilter(wt, commonWords);
   
    TermAttribute term = (TermAttribute) cgf.addAttribute(TermAttribute.class);
    assertTrue(cgf.incrementToken());
    assertEquals("How", term.term());
    assertTrue(cgf.incrementToken());
    assertEquals("How_the", term.term());
    assertTrue(cgf.incrementToken());
    assertEquals("the", term.term());
    assertTrue(cgf.incrementToken());
    assertEquals("the_s", term.term());
   
    wt.reset(new StringReader(input));
    cgf.reset();
    assertTrue(cgf.incrementToken());
    assertEquals("How", term.term());
  }
View Full Code Here
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
 
  public void testReset() throws Exception {
    final String input = "How now A B brown A cow B like A B thing?";
    Tokenizer tokenizer = new WhitespaceTokenizer(new StringReader(input));
    TokenStream ts = new AB_AAB_Stream(tokenizer);
    TermAttribute term = (TermAttribute) ts.addAttribute(TermAttribute.class);
    assertTrue(ts.incrementToken());
    assertEquals("How", term.term());
    assertTrue(ts.incrementToken());
    assertEquals("now", term.term());
    assertTrue(ts.incrementToken());
    assertEquals("A", term.term());
    // reset back to input,
    // if reset() does not work correctly then previous buffered tokens will remain
    tokenizer.reset(new StringReader(input));
    ts.reset();
    assertTrue(ts.incrementToken());
    assertEquals("How", term.term());
  }
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
    final String input = "How the s a brown s cow d like A B thing?";
    WhitespaceTokenizer wt = new WhitespaceTokenizer(new StringReader(input));
    CommonGramsFilter cgf = new CommonGramsFilter(wt, commonWords);
    CommonGramsQueryFilter nsf = new CommonGramsQueryFilter(cgf);
   
    TermAttribute term = (TermAttribute) wt.addAttribute(TermAttribute.class);
    assertTrue(nsf.incrementToken());
    assertEquals("How_the", term.term());
    assertTrue(nsf.incrementToken());
    assertEquals("the_s", term.term());
   
    wt.reset(new StringReader(input));
    nsf.reset();
    assertTrue(nsf.incrementToken());
    assertEquals("How_the", term.term());
  }
View Full Code Here
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
                    new Token(b, 0, b.length, 6, 10),
                    new Token(ccc, 0, ccc.length, 11, 15),
                    new Token(whitespace, 0, whitespace.length, 16, 20),
                    new Token(empty, 0, empty.length, 21, 21)), false);

    TermAttribute token;
    assertTrue(ts.incrementToken());
    token = (TermAttribute) ts.getAttribute(TermAttribute.class);
    assertEquals("a", new String(token.termBuffer(), 0, token.termLength()));
    assertTrue(ts.incrementToken());
    assertEquals("b", new String(token.termBuffer(), 0, token.termLength()));
    assertTrue(ts.incrementToken());
    assertEquals("cCc", new String(token.termBuffer(), 0, token.termLength()));
    assertTrue(ts.incrementToken());
    assertEquals("", new String(token.termBuffer(), 0, token.termLength()));
    assertTrue(ts.incrementToken());
    assertEquals("", new String(token.termBuffer(), 0, token.termLength()));
    assertFalse(ts.incrementToken());

    a = " a".toCharArray();
    b = "b ".toCharArray();
    ccc = " c ".toCharArray();
View Full Code Here
37
38
39
40
41
42
43
44
45
46
47
48
49
50
  private Analyzer analyzer;

  @Override
  protected void map(Text key, Text value, Context context) throws IOException, InterruptedException {
    TokenStream stream = analyzer.tokenStream(key.toString(), new StringReader(value.toString()));
    TermAttribute termAtt = stream.addAttribute(TermAttribute.class);
    StringTuple document = new StringTuple();
    while (stream.incrementToken()) {
      if (termAtt.termLength() > 0) {
        document.add(new String(termAtt.termBuffer(), 0, termAtt.termLength()));
      }
    }
    context.write(key, document);
  }
View Full Code Here
TOP

Related Classes of org.apache.lucene.analysis.tokenattributes.TermAttribute

  • com.alimama.mdrill.index.IndexReducer
  • com.flaptor.indextank.query.IndexEngineParser
  • com.jayway.mongodb.AnalyzedDBObject
  • com.senseidb.search.query.TextQueryConstructor
  • edu.wiki.search.ESASearcher
  • it.unibz.instasearch.indexing.StorageIndexer
  • lucli.LuceneMethods
  • mia.classifier.ch14.TokenizingAndVectorizingText
  • mia.clustering.ch09.MyAnalyzer
  • mia.clustering.ch12.TwitterAnalyzer
    • 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.