Package org.apache.lucene.analysis.tokenattributes

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

137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
    int numItalics = 0;
    int numBoldItalics = 0;
    int numCategory = 0;
    int numCitation = 0;
    TermAttribute termAtt = tf.addAttribute(TermAttribute.class);
    TypeAttribute typeAtt = tf.addAttribute(TypeAttribute.class);
   
    while (tf.incrementToken()) {
      String tokText = termAtt.term();
      //System.out.println("Text: " + tokText + " Type: " + token.type());
      String expectedType = (String) tcm.get(tokText);
      assertTrue("expectedType is null and it shouldn't be for: " + tf.toString(), expectedType != null);
      assertTrue(typeAtt.type() + " is not equal to " + expectedType + " for " + tf.toString(), typeAtt.type().equals(expectedType) == true);
      count++;
      if (typeAtt.type().equals(WikipediaTokenizer.ITALICS)  == true){
        numItalics++;
      } else if (typeAtt.type().equals(WikipediaTokenizer.BOLD_ITALICS)  == true){
        numBoldItalics++;
      } else if (typeAtt.type().equals(WikipediaTokenizer.CATEGORY)  == true){
        numCategory++;
      }
      else if (typeAtt.type().equals(WikipediaTokenizer.CITATION)  == true){
        numCitation++;
      }
    }
    assertTrue("We have not seen enough tokens: " + count + " is not >= " + tcm.size(), count >= tcm.size());
    assertTrue(numItalics + " does not equal: " + 4 + " for numItalics", numItalics == 4);
View Full Code Here
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
  public void testLinks() throws Exception {
    String test = "[http://lucene.apache.org/java/docs/index.html#news here] [http://lucene.apache.org/java/docs/index.html?b=c here] [https://lucene.apache.org/java/docs/index.html?b=c here]";
    WikipediaTokenizer tf = new WikipediaTokenizer(new StringReader(test));
    TermAttribute termAtt = tf.addAttribute(TermAttribute.class);
    TypeAttribute typeAtt = tf.addAttribute(TypeAttribute.class);
   
    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "http://lucene.apache.org/java/docs/index.html#news",
        termAtt.term().equals("http://lucene.apache.org/java/docs/index.html#news") == true);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.EXTERNAL_LINK_URL, typeAtt.type().equals(WikipediaTokenizer.EXTERNAL_LINK_URL) == true);
    tf.incrementToken();//skip here
   
    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "http://lucene.apache.org/java/docs/index.html?b=c",
        termAtt.term().equals("http://lucene.apache.org/java/docs/index.html?b=c") == true);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.EXTERNAL_LINK_URL, typeAtt.type().equals(WikipediaTokenizer.EXTERNAL_LINK_URL) == true);
    tf.incrementToken();//skip here
   
    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "https://lucene.apache.org/java/docs/index.html?b=c",
        termAtt.term().equals("https://lucene.apache.org/java/docs/index.html?b=c") == true);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.EXTERNAL_LINK_URL, typeAtt.type().equals(WikipediaTokenizer.EXTERNAL_LINK_URL) == true);
   
    assertTrue(tf.incrementToken());
    assertFalse(tf.incrementToken());
  }
View Full Code Here
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
    untoks.add(WikipediaTokenizer.ITALICS);
    String test = "[[Category:a b c d]] [[Category:e f g]] [[link here]] [[link there]] ''italics here'' something ''more italics'' [[Category:h   i   j]]";
    //should output all the indivual tokens plus the untokenized tokens as well.  Untokenized tokens
    WikipediaTokenizer tf = new WikipediaTokenizer(new StringReader(test), WikipediaTokenizer.BOTH, untoks);
    TermAttribute termAtt = tf.addAttribute(TermAttribute.class);
    TypeAttribute typeAtt = tf.addAttribute(TypeAttribute.class);
    PositionIncrementAttribute posIncrAtt = tf.addAttribute(PositionIncrementAttribute.class);
    OffsetAttribute offsetAtt = tf.addAttribute(OffsetAttribute.class);
    FlagsAttribute flagsAtt = tf.addAttribute(FlagsAttribute.class);
   
    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "a b c d",
            termAtt.term().equals("a b c d") == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 1, posIncrAtt.getPositionIncrement() == 1);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.CATEGORY, typeAtt.type().equals(WikipediaTokenizer.CATEGORY) == true);
    assertTrue(flagsAtt.getFlags() + " does not equal: " + WikipediaTokenizer.UNTOKENIZED_TOKEN_FLAG, flagsAtt.getFlags() == WikipediaTokenizer.UNTOKENIZED_TOKEN_FLAG);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 11, offsetAtt.startOffset() == 11);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 18, offsetAtt.endOffset() == 18);
   
    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "a",
            termAtt.term().equals("a") == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 0, posIncrAtt.getPositionIncrement() == 0);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.CATEGORY, typeAtt.type().equals(WikipediaTokenizer.CATEGORY) == true);
    assertTrue(flagsAtt.getFlags() + " equals: " + WikipediaTokenizer.UNTOKENIZED_TOKEN_FLAG + " and it shouldn't", flagsAtt.getFlags() != WikipediaTokenizer.UNTOKENIZED_TOKEN_FLAG);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 11, offsetAtt.startOffset() == 11);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 12, offsetAtt.endOffset() == 12);

    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "b",
            termAtt.term().equals("b") == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 1, posIncrAtt.getPositionIncrement() == 1);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.CATEGORY, typeAtt.type().equals(WikipediaTokenizer.CATEGORY) == true);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 13, offsetAtt.startOffset() == 13);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 14, offsetAtt.endOffset() == 14);

    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "c",
            termAtt.term().equals("c") == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 1, posIncrAtt.getPositionIncrement() == 1);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.CATEGORY, typeAtt.type().equals(WikipediaTokenizer.CATEGORY) == true);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 15, offsetAtt.startOffset() == 15);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 16, offsetAtt.endOffset() == 16);

    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "d",
            termAtt.term().equals("d") == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 1, posIncrAtt.getPositionIncrement() == 1);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.CATEGORY, typeAtt.type().equals(WikipediaTokenizer.CATEGORY) == true);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 17, offsetAtt.startOffset() == 17);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 18, offsetAtt.endOffset() == 18);



    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "e f g",
            termAtt.term().equals("e f g") == true);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.CATEGORY, typeAtt.type().equals(WikipediaTokenizer.CATEGORY) == true);
    assertTrue(flagsAtt.getFlags() + " does not equal: " + WikipediaTokenizer.UNTOKENIZED_TOKEN_FLAG, flagsAtt.getFlags() == WikipediaTokenizer.UNTOKENIZED_TOKEN_FLAG);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 32, offsetAtt.startOffset() == 32);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 37, offsetAtt.endOffset() == 37);

    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "e",
            termAtt.term().equals("e") == true);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.CATEGORY, typeAtt.type().equals(WikipediaTokenizer.CATEGORY) == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 0, posIncrAtt.getPositionIncrement() == 0);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 32, offsetAtt.startOffset() == 32);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 33, offsetAtt.endOffset() == 33);

    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "f",
            termAtt.term().equals("f") == true);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.CATEGORY, typeAtt.type().equals(WikipediaTokenizer.CATEGORY) == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 1, posIncrAtt.getPositionIncrement() == 1);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 34, offsetAtt.startOffset() == 34);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 35, offsetAtt.endOffset() == 35);

    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "g",
            termAtt.term().equals("g") == true);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.CATEGORY, typeAtt.type().equals(WikipediaTokenizer.CATEGORY) == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 1, posIncrAtt.getPositionIncrement() == 1);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 36, offsetAtt.startOffset() == 36);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 37, offsetAtt.endOffset() == 37);

    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "link",
            termAtt.term().equals("link") == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 1, posIncrAtt.getPositionIncrement() == 1);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.INTERNAL_LINK, typeAtt.type().equals(WikipediaTokenizer.INTERNAL_LINK) == true);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 42, offsetAtt.startOffset() == 42);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 46, offsetAtt.endOffset() == 46);
   
    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "here",
            termAtt.term().equals("here") == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 1, posIncrAtt.getPositionIncrement() == 1);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.INTERNAL_LINK, typeAtt.type().equals(WikipediaTokenizer.INTERNAL_LINK) == true);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 47, offsetAtt.startOffset() == 47);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 51, offsetAtt.endOffset() == 51);
   
    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "link",
            termAtt.term().equals("link") == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 1, posIncrAtt.getPositionIncrement() == 1);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 56, offsetAtt.startOffset() == 56);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.INTERNAL_LINK, typeAtt.type().equals(WikipediaTokenizer.INTERNAL_LINK) == true);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 60, offsetAtt.endOffset() == 60);
   
    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "there",
            termAtt.term().equals("there") == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 1, posIncrAtt.getPositionIncrement() == 1);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.INTERNAL_LINK, typeAtt.type().equals(WikipediaTokenizer.INTERNAL_LINK) == true);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 61, offsetAtt.startOffset() == 61);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 66, offsetAtt.endOffset() == 66);
   
    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "italics here",
            termAtt.term().equals("italics here") == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 1, posIncrAtt.getPositionIncrement() == 1);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.ITALICS, typeAtt.type().equals(WikipediaTokenizer.ITALICS) == true);
    assertTrue(flagsAtt.getFlags() + " does not equal: " + WikipediaTokenizer.UNTOKENIZED_TOKEN_FLAG, flagsAtt.getFlags() == WikipediaTokenizer.UNTOKENIZED_TOKEN_FLAG);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 71, offsetAtt.startOffset() == 71);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 83, offsetAtt.endOffset() == 83);

    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "italics",
            termAtt.term().equals("italics") == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 0, posIncrAtt.getPositionIncrement() == 0);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.ITALICS, typeAtt.type().equals(WikipediaTokenizer.ITALICS) == true);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 71, offsetAtt.startOffset() == 71);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 78, offsetAtt.endOffset() == 78);

    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "here",
            termAtt.term().equals("here") == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 1, posIncrAtt.getPositionIncrement() == 1);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.ITALICS, typeAtt.type().equals(WikipediaTokenizer.ITALICS) == true);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 79, offsetAtt.startOffset() == 79);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 83, offsetAtt.endOffset() == 83);

    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "something",
            termAtt.term().equals("something") == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 1, posIncrAtt.getPositionIncrement() == 1);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 86, offsetAtt.startOffset() == 86);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 95, offsetAtt.endOffset() == 95);
   
    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "more italics",
            termAtt.term().equals("more italics") == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 1, posIncrAtt.getPositionIncrement() == 1);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.ITALICS, typeAtt.type().equals(WikipediaTokenizer.ITALICS) == true);
    assertTrue(flagsAtt.getFlags() + " does not equal: " + WikipediaTokenizer.UNTOKENIZED_TOKEN_FLAG, flagsAtt.getFlags() == WikipediaTokenizer.UNTOKENIZED_TOKEN_FLAG);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 98, offsetAtt.startOffset() == 98);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 110, offsetAtt.endOffset() == 110);

    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "more",
            termAtt.term().equals("more") == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 0, posIncrAtt.getPositionIncrement() == 0);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.ITALICS, typeAtt.type().equals(WikipediaTokenizer.ITALICS) == true);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 98, offsetAtt.startOffset() == 98);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 102, offsetAtt.endOffset() == 102);

    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "italics",
            termAtt.term().equals("italics") == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 1, posIncrAtt.getPositionIncrement() == 1);
        assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.ITALICS, typeAtt.type().equals(WikipediaTokenizer.ITALICS) == true);

    assertTrue(offsetAtt.startOffset() + " does not equal: " + 103, offsetAtt.startOffset() == 103);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 110, offsetAtt.endOffset() == 110);

    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "h   i   j",
            termAtt.term().equals("h   i   j") == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 1, posIncrAtt.getPositionIncrement() == 1);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.CATEGORY, typeAtt.type().equals(WikipediaTokenizer.CATEGORY) == true);
    assertTrue(flagsAtt.getFlags() + " does not equal: " + WikipediaTokenizer.UNTOKENIZED_TOKEN_FLAG, flagsAtt.getFlags() == WikipediaTokenizer.UNTOKENIZED_TOKEN_FLAG);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 124, offsetAtt.startOffset() == 124);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 133, offsetAtt.endOffset() == 133);

    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "h",
            termAtt.term().equals("h") == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 0, posIncrAtt.getPositionIncrement() == 0);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.CATEGORY, typeAtt.type().equals(WikipediaTokenizer.CATEGORY) == true);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 124, offsetAtt.startOffset() == 124);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 125, offsetAtt.endOffset() == 125);

    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "i",
            termAtt.term().equals("i") == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 1, posIncrAtt.getPositionIncrement() == 1);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.CATEGORY, typeAtt.type().equals(WikipediaTokenizer.CATEGORY) == true);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 128, offsetAtt.startOffset() == 128);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 129, offsetAtt.endOffset() == 129);
   
    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "j",
            termAtt.term().equals("j") == true);
    assertTrue(posIncrAtt.getPositionIncrement() + " does not equal: " + 1, posIncrAtt.getPositionIncrement() == 1);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.CATEGORY, typeAtt.type().equals(WikipediaTokenizer.CATEGORY) == true);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 132, offsetAtt.startOffset() == 132);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 133, offsetAtt.endOffset() == 133);

    assertFalse(tf.incrementToken());
  }
View Full Code Here
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
    String test = "The quick red fox jumped over the lazy brown dogs";

    TypeAsPayloadTokenFilter nptf = new TypeAsPayloadTokenFilter(new WordTokenFilter(new MockTokenizer(new StringReader(test), MockTokenizer.WHITESPACE, false)));
    int count = 0;
    CharTermAttribute termAtt = nptf.getAttribute(CharTermAttribute.class);
    TypeAttribute typeAtt = nptf.getAttribute(TypeAttribute.class);
    PayloadAttribute payloadAtt = nptf.getAttribute(PayloadAttribute.class);
    nptf.reset();
    while (nptf.incrementToken()) {
      assertTrue(typeAtt.type() + " is not null and it should be", typeAtt.type().equals(String.valueOf(Character.toUpperCase(termAtt.buffer()[0]))));
      assertTrue("nextToken.getPayload() is null and it shouldn't be", payloadAtt.getPayload() != null);
      String type = new String(payloadAtt.getPayload().bytes, "UTF-8");
      assertTrue(type + " is not equal to " + typeAtt.type(), type.equals(typeAtt.type()) == true);
      count++;
    }

    assertTrue(count + " does not equal: " + 10, count == 10);
  }
View Full Code Here
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
      UIMATypeAwareAnalyzer analyzer = new UIMATypeAwareAnalyzer("/HmmTaggerAggregate.xml",
              "org.apache.uima.TokenAnnotation", "posTag");
      TokenStream ts = analyzer.tokenStream("text", new StringReader("the big brown fox jumped on the wood"));
      CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
      OffsetAttribute offsetAtt = ts.addAttribute(OffsetAttribute.class);
      TypeAttribute typeAttr = ts.addAttribute(TypeAttribute.class);
      PositionIncrementAttribute posAtt = ts.addAttribute(PositionIncrementAttribute.class);
      while (ts.incrementToken()) {
        assertNotNull(offsetAtt);
        assertNotNull(termAtt);
        assertNotNull(posAtt);
        assertNotNull(typeAttr);
        System.out.println("token '" + termAtt.toString() + "' has type " + typeAttr.type());
      }
    } catch (Exception e) {
      e.printStackTrace();
      fail(e.getLocalizedMessage());
    }
View Full Code Here
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
    TokenStream ts = analyzer.reusableTokenStream("", new StringReader(q));
    ts.reset();
    // TODO: support custom attributes
    CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
    OffsetAttribute offsetAtt = ts.addAttribute(OffsetAttribute.class);
    TypeAttribute typeAtt = ts.addAttribute(TypeAttribute.class);
    FlagsAttribute flagsAtt = ts.addAttribute(FlagsAttribute.class);
    PayloadAttribute payloadAtt = ts.addAttribute(PayloadAttribute.class);
    PositionIncrementAttribute posIncAtt = ts.addAttribute(PositionIncrementAttribute.class);
   
    while (ts.incrementToken()){
      Token token = new Token();
      token.copyBuffer(termAtt.buffer(), 0, termAtt.length());
      token.setOffset(offsetAtt.startOffset(), offsetAtt.endOffset());
      token.setType(typeAtt.type());
      token.setFlags(flagsAtt.getFlags());
      token.setPayload(payloadAtt.getPayload());
      token.setPositionIncrement(posIncAtt.getPositionIncrement());
      result.add(token);
    }
View Full Code Here
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
        try {
          stream = analyzer.reusableTokenStream("", new StringReader(word));
          // TODO: support custom attributes
          CharTermAttribute termAtt = stream.addAttribute(CharTermAttribute.class);
          FlagsAttribute flagsAtt = stream.addAttribute(FlagsAttribute.class);
          TypeAttribute typeAtt = stream.addAttribute(TypeAttribute.class);
          PayloadAttribute payloadAtt = stream.addAttribute(PayloadAttribute.class);
          PositionIncrementAttribute posIncAtt = stream.addAttribute(PositionIncrementAttribute.class);
          stream.reset();
          while (stream.incrementToken()) {
            Token token = new Token();
            token.copyBuffer(termAtt.buffer(), 0, termAtt.length());
            token.setStartOffset(matcher.start());
            token.setEndOffset(matcher.end());
            token.setFlags(flagsAtt.getFlags());
            token.setType(typeAtt.type());
            token.setPayload(payloadAtt.getPayload());
            token.setPositionIncrement(posIncAtt.getPositionIncrement());
            result.add(token);
          }
          stream.end();
View Full Code Here
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
  throws IOException {
    assertTrue("has CharTermAttribute", t.hasAttribute(CharTermAttribute.class));
    final CharTermAttribute termAtt = t.getAttribute(CharTermAttribute.class);

    assertTrue("has TypeAttribute", t.hasAttribute(TypeAttribute.class));
    final TypeAttribute typeAtt = t.getAttribute(TypeAttribute.class);

    assertTrue("has PositionIncrementAttribute", t.hasAttribute(PositionIncrementAttribute.class));
    final PositionIncrementAttribute posIncrAtt = t.getAttribute(PositionIncrementAttribute.class);

    t.setReader(new StringReader(uri));
    t.reset();

    final URIDecodingFilter filter = new URIDecodingFilter(t, encoding);
    for (int i = 0; i < expectedStems.length; i++) {
        assertTrue("token " + i + " exists", filter.incrementToken());
        assertEquals(expectedStems[i], termAtt.toString());
        if (expectedTypes == null)
          assertEquals(uritype, typeAtt.type());
        else
          assertEquals(expectedTypes[i], typeAtt.type());
        if (expectedPosIncr != null)
          assertEquals(expectedPosIncr[i], posIncrAtt.getPositionIncrement());
    }
    filter.end();
    filter.close();
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
   throws Exception {

     assertTrue("has CharTermAttribute", t.hasAttribute(CharTermAttribute.class));
     final CharTermAttribute termAtt = t.getAttribute(CharTermAttribute.class);

     TypeAttribute typeAtt = null;
     if (expectedTypes != null) {
       assertTrue("has TypeAttribute", t.hasAttribute(TypeAttribute.class));
       typeAtt = t.getAttribute(TypeAttribute.class);
     }

     t.setReader(new StringReader(input));
     t.reset();

     final TokenStream filter = new URINormalisationFilter(t);

     for (int i = 0; i < expectedImages.length; i++) {

       assertTrue("token "+i+" exists", filter.incrementToken());

       assertEquals(expectedImages[i], termAtt.toString());

       if (expectedTypes != null) {
         assertEquals(expectedTypes[i], typeAtt.type());
       }

     }

     assertFalse("end of stream", filter.incrementToken());
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
  throws IOException {
    assertTrue("has CharTermAttribute", t.hasAttribute(CharTermAttribute.class));
    final CharTermAttribute termAtt = t.getAttribute(CharTermAttribute.class);

    assertTrue("has TypeAttribute", t.hasAttribute(TypeAttribute.class));
    final TypeAttribute typeAtt = t.getAttribute(TypeAttribute.class);

    assertTrue("has PositionIncrementAttribute", t.hasAttribute(PositionIncrementAttribute.class));
    final PositionIncrementAttribute posIncrAtt = t.getAttribute(PositionIncrementAttribute.class);

    t.setReader(new StringReader(uri));
    t.reset();

    final TokenFilter filter = new MailtoFilter(t);
    for (int i = 0; i < expectedStems.length; i++) {
        assertTrue("token " + i + " exists", filter.incrementToken());
        assertEquals(expectedStems[i], termAtt.toString());
        if (expectedTypes == null)
          assertEquals(uritype, typeAtt.type());
        else
          assertEquals(expectedTypes[i], typeAtt.type());
        if (expectedPosIncr != null)
          assertEquals(expectedPosIncr[i], posIncrAtt.getPositionIncrement());
    }
    filter.end();
    filter.close();
View Full Code Here
TOP

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

  • com.chenlb.mmseg4j.analysis.TokenUtils
  • com.github.le11.nls.lucene.UIMATypeAwareAnalyzerTest
  • com.tistory.devyongsik.crescent.admin.service.MorphServiceImpl
  • org.apache.jackrabbit.core.query.lucene.JackrabbitQueryParser
  • org.apache.lucene.analysis.cjk.TestCJKTokenizer
  • org.apache.lucene.analysis.core.TestTypeTokenFilter
  • org.apache.lucene.analysis.payloads.NumericPayloadTokenFilterTest
  • org.apache.lucene.analysis.payloads.TypeAsPayloadTokenFilterTest
  • org.apache.lucene.analysis.sinks.TokenTypeSinkTokenizerTest
  • org.apache.lucene.analysis.snowball.TestSnowball
    • 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.