Package org.apache.lucene.analysis.tokenattributes

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

337
338
339
340
341
342
343
344
345
346
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
    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
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
  private static void displayTokensWithFullDetails(TokenStream stream) throws IOException {
    final CharTermAttribute term = stream.addAttribute(CharTermAttribute.class);
    final PositionIncrementAttribute posIncr = stream.addAttribute(PositionIncrementAttribute.class);
    final OffsetAttribute offset = stream.addAttribute(OffsetAttribute.class);
    final TypeAttribute type = stream.addAttribute(TypeAttribute.class);
    int position = 0;
    while (stream.incrementToken()) {
      final int increment = posIncr.getPositionIncrement();
      if (increment > 0) {
        position = position + increment;
        System.out.println();
        System.out.print(position + ": ");
      }
      System.out.print("[" + term.toString() + ":" + offset.startOffset() + "->"
          + offset.endOffset() + ":" + type.type() + "] ");
    }
    System.out.println();
  }
View Full Code Here
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
    testPositons(typeTokenFilter);

  }

  private void testPositons(TypeTokenFilter stpf) throws IOException {
    TypeAttribute typeAtt = stpf.getAttribute(TypeAttribute.class);
    CharTermAttribute termAttribute = stpf.getAttribute(CharTermAttribute.class);
    PositionIncrementAttribute posIncrAtt = stpf.getAttribute(PositionIncrementAttribute.class);
    stpf.reset();
    boolean enablePositionIncrements = stpf.getEnablePositionIncrements();
    while (stpf.incrementToken()) {
      log("Token: " + termAttribute.toString() + ": " + typeAtt.type() + " - " + posIncrAtt.getPositionIncrement());
      assertEquals("if position increment is enabled the positionIncrementAttribute value should be 3, otherwise 1",
          posIncrAtt.getPositionIncrement(), enablePositionIncrements ? 3 : 1);
    }
    stpf.end();
    stpf.close();
View Full Code Here
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
 
  public void testFilterTokens() throws Exception {
    SnowballFilter filter = new SnowballFilter(new TestTokenStream(), "English");
    CharTermAttribute termAtt = filter.getAttribute(CharTermAttribute.class);
    OffsetAttribute offsetAtt = filter.getAttribute(OffsetAttribute.class);
    TypeAttribute typeAtt = filter.getAttribute(TypeAttribute.class);
    PayloadAttribute payloadAtt = filter.getAttribute(PayloadAttribute.class);
    PositionIncrementAttribute posIncAtt = filter.getAttribute(PositionIncrementAttribute.class);
    FlagsAttribute flagsAtt = filter.getAttribute(FlagsAttribute.class);
   
    filter.incrementToken();

    assertEquals("accent", termAtt.toString());
    assertEquals(2, offsetAtt.startOffset());
    assertEquals(7, offsetAtt.endOffset());
    assertEquals("wrd", typeAtt.type());
    assertEquals(3, posIncAtt.getPositionIncrement());
    assertEquals(77, flagsAtt.getFlags());
    assertEquals(new Payload(new byte[]{0,1,2,3}), payloadAtt.getPayload());
  }
View Full Code Here
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
      record.put( "flags", narrowedAttr.getFlags() );
      return record;
    }
    else if (attr instanceof TypeAttribute ) {
      GenericRecord record = new GenericData.Record( protocol.getType( "TypeAttribute" ) );
      TypeAttribute narrowedAttr = (TypeAttribute) attr;
      record.put( "type", narrowedAttr.type() );
      return record;
    }
    else if (attr instanceof OffsetAttribute ) {
      GenericRecord record = new GenericData.Record( protocol.getType( "OffsetAttribute" ) );
      OffsetAttribute narrowedAttr = (OffsetAttribute) attr;
      record.put( "startOffset", narrowedAttr.startOffset() );
      record.put( "endOffset", narrowedAttr.endOffset() );
      return record;
    }
    else if (attr instanceof Serializable) {
      return ByteBuffer.wrap( toByteArray( attr ) );
    }
View Full Code Here
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
      record.put( "flags", narrowedAttr.getFlags() );
      return record;
    }
    else if ( attr instanceof TypeAttribute ) {
      GenericRecord record = new GenericData.Record( protocol.getType( "TypeAttribute" ) );
      TypeAttribute narrowedAttr = (TypeAttribute) attr;
      record.put( "type", narrowedAttr.type() );
      return record;
    }
    else if ( attr instanceof OffsetAttribute ) {
      GenericRecord record = new GenericData.Record( protocol.getType( "OffsetAttribute" ) );
      OffsetAttribute narrowedAttr = (OffsetAttribute) attr;
      record.put( "startOffset", narrowedAttr.startOffset() );
      record.put( "endOffset", narrowedAttr.endOffset() );
      return record;
    }
    else if ( attr instanceof Serializable ) {
      return ByteBuffer.wrap( toByteArray( (Serializable) attr ) );
    }
View Full Code Here
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
            stream = analyzer.tokenStream(field, request.text());
            stream.reset();
            CharTermAttribute term = stream.addAttribute(CharTermAttribute.class);
            PositionIncrementAttribute posIncr = stream.addAttribute(PositionIncrementAttribute.class);
            OffsetAttribute offset = stream.addAttribute(OffsetAttribute.class);
            TypeAttribute type = stream.addAttribute(TypeAttribute.class);

            int position = 0;
            while (stream.incrementToken()) {
                int increment = posIncr.getPositionIncrement();
                if (increment > 0) {
                    position = position + increment;
                }
                tokens.add(new AnalyzeResponse.AnalyzeToken(term.toString(), position, offset.startOffset(), offset.endOffset(), type.type()));
            }
            stream.end();
        } catch (IOException e) {
            throw new ElasticsearchException("failed to analyze", e);
        } finally {
View Full Code Here
28
29
30
31
32
33
34
35
36
37
38
39
40
  public void testLongStream() throws Exception {
    final NumericTokenStream stream=new NumericTokenStream().setLongValue(lvalue);
    // use getAttribute to test if attributes really exist, if not an IAE will be throwed
    final TermAttribute termAtt = stream.getAttribute(TermAttribute.class);
    final TypeAttribute typeAtt = stream.getAttribute(TypeAttribute.class);
    for (int shift=0; shift<64; shift+=NumericUtils.PRECISION_STEP_DEFAULT) {
      assertTrue("New token is available", stream.incrementToken());
      assertEquals("Term is correctly encoded", NumericUtils.longToPrefixCoded(lvalue, shift), termAtt.term());
      assertEquals("Type correct", (shift == 0) ? NumericTokenStream.TOKEN_TYPE_FULL_PREC : NumericTokenStream.TOKEN_TYPE_LOWER_PREC, typeAtt.type());
    }
    assertFalse("No more tokens available", stream.incrementToken());
  }
View Full Code Here
41
42
43
44
45
46
47
48
49
50
51
52
53
  public void testIntStream() throws Exception {
    final NumericTokenStream stream=new NumericTokenStream().setIntValue(ivalue);
    // use getAttribute to test if attributes really exist, if not an IAE will be throwed
    final TermAttribute termAtt = stream.getAttribute(TermAttribute.class);
    final TypeAttribute typeAtt = stream.getAttribute(TypeAttribute.class);
    for (int shift=0; shift<32; shift+=NumericUtils.PRECISION_STEP_DEFAULT) {
      assertTrue("New token is available", stream.incrementToken());
      assertEquals("Term is correctly encoded", NumericUtils.intToPrefixCoded(ivalue, shift), termAtt.term());
      assertEquals("Type correct", (shift == 0) ? NumericTokenStream.TOKEN_TYPE_FULL_PREC : NumericTokenStream.TOKEN_TYPE_LOWER_PREC, typeAtt.type());
    }
    assertFalse("No more tokens available", stream.incrementToken());
  }
View Full Code Here
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
    String test = "The quick red fox jumped over the lazy brown dogs";

    NumericPayloadTokenFilter nptf = new NumericPayloadTokenFilter(new WordTokenFilter(new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader(test))), 3, "D");
    boolean seenDogs = false;
    CharTermAttribute termAtt = nptf.getAttribute(CharTermAttribute.class);
    TypeAttribute typeAtt = nptf.getAttribute(TypeAttribute.class);
    PayloadAttribute payloadAtt = nptf.getAttribute(PayloadAttribute.class);
    while (nptf.incrementToken()) {
      if (termAtt.toString().equals("dogs")) {
        seenDogs = true;
        assertTrue(typeAtt.type() + " is not equal to " + "D", typeAtt.type().equals("D") == true);
        assertTrue("payloadAtt.getPayload() is null and it shouldn't be", payloadAtt.getPayload() != null);
        byte [] bytes = payloadAtt.getPayload().getData();//safe here to just use the bytes, otherwise we should use offset, length
        assertTrue(bytes.length + " does not equal: " + payloadAtt.getPayload().length(), bytes.length == payloadAtt.getPayload().length());
        assertTrue(payloadAtt.getPayload().getOffset() + " does not equal: " + 0, payloadAtt.getPayload().getOffset() == 0);
        float pay = PayloadHelper.decodeFloat(bytes);
        assertTrue(pay + " does not equal: " + 3, pay == 3);
      } else {
        assertTrue(typeAtt.type() + " is not null and it should be", typeAtt.type().equals("word"));
      }
    }
    assertTrue(seenDogs + " does not equal: " + true, seenDogs == true);
  }
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.