Package org.apache.lucene.analysis.tokenattributes

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

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";

    TokenOffsetPayloadTokenFilter nptf = new TokenOffsetPayloadTokenFilter(new WhitespaceTokenizer(new StringReader(test)));
    int count = 0;
    PayloadAttribute payloadAtt = nptf.getAttribute(PayloadAttribute.class);
    OffsetAttribute offsetAtt = nptf.getAttribute(OffsetAttribute.class);
   
    while (nptf.incrementToken()) {
      Payload pay = payloadAtt.getPayload();
      assertTrue("pay is null and it shouldn't be", pay != null);
      byte [] data = pay.getData();
      int start = PayloadHelper.decodeInt(data, 0);
      assertTrue(start + " does not equal: " + offsetAtt.startOffset(), start == offsetAtt.startOffset());
      int end = PayloadHelper.decodeInt(data, 4);
      assertTrue(end + " does not equal: " + offsetAtt.endOffset(), end == offsetAtt.endOffset());
      count++;
    }
    assertTrue(count + " does not equal: " + 10, count == 10);

  }
View Full Code Here
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
    checkLinkPhrases(tf);
    String test = "[[Category:a b c d]] [[Category:e f g]] [[link here]] [[link there]] ''italics here'' something ''more italics'' [[Category:h   i   j]]";
    tf = new WikipediaTokenizer(new StringReader(test), WikipediaTokenizer.UNTOKENIZED_ONLY, untoks);
    TermAttribute termAtt = tf.addAttribute(TermAttribute.class);
    PositionIncrementAttribute posIncrAtt = tf.addAttribute(PositionIncrementAttribute.class);
    OffsetAttribute offsetAtt = tf.addAttribute(OffsetAttribute.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(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 " + "e f g",
        termAtt.term().equals("e f g") == true);
    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 " + "link",
        termAtt.term().equals("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(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(offsetAtt.startOffset() + " does not equal: " + 56, offsetAtt.startOffset() == 56);
    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(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(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 " + "something",
        termAtt.term().equals("something") == true);
    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(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 " + "h   i   j",
        termAtt.term().equals("h   i   j") == true);
    assertTrue(offsetAtt.startOffset() + " does not equal: " + 124, offsetAtt.startOffset() == 124);
    assertTrue(offsetAtt.endOffset() + " does not equal: " + 133, offsetAtt.endOffset() == 133);

    assertFalse(tf.incrementToken());
  }
View Full Code Here
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
    //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
136
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
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
           
            boolean hasMoreTokens = stream.incrementToken();

            fieldState.attributeSource = stream;

            OffsetAttribute offsetAttribute = fieldState.attributeSource.addAttribute(OffsetAttribute.class);
            PositionIncrementAttribute posIncrAttribute = fieldState.attributeSource.addAttribute(PositionIncrementAttribute.class);
           
            consumer.start(field);
           
            for(;;) {

              // If we hit an exception in stream.next below
              // (which is fairly common, eg if analyzer
              // chokes on a given document), then it's
              // non-aborting and (above) this one document
              // will be marked as deleted, but still
              // consume a docID
             
              if (!hasMoreTokens) break;
             
              final int posIncr = posIncrAttribute.getPositionIncrement();
              fieldState.position += posIncr;
              if (fieldState.position > 0) {
                fieldState.position--;
              }

              if (posIncr == 0)
                fieldState.numOverlap++;

              boolean success = false;
              try {
                // If we hit an exception in here, we abort
                // all buffered documents since the last
                // flush, on the likelihood that the
                // internal state of the consumer is now
                // corrupt and should not be flushed to a
                // new segment:
                consumer.add();
                success = true;
              } finally {
                if (!success)
                  docState.docWriter.setAborting();
              }
              fieldState.position++;
              offsetEnd = fieldState.offset + offsetAttribute.endOffset();
              if (++fieldState.length >= maxFieldLength) {
                if (docState.infoStream != null)
                  docState.infoStream.println("maxFieldLength " +maxFieldLength+ " reached for field " + fieldInfo.name + ", ignoring following tokens");
                break;
              }

              hasMoreTokens = stream.incrementToken();
            }
            // trigger streams to perform end-of-stream operations
            stream.end();
           
            fieldState.offset += offsetAttribute.endOffset();
            anyToken = fieldState.length > startLength;
          } finally {
            stream.close();
          }
        }
View Full Code Here
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
            new TreeMap<String, TermVectorOffsetInfo[]>();
        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;
                    info = new TermVectorOffsetInfo[tmp.length + 1];
                    System.arraycopy(tmp, 0, info, 0, tmp.length);
                }
                info[info.length - 1] = new TermVectorOffsetInfo(
                    offset.startOffset(), offset.endOffset());
                termMap.put(termText, info);
            }
            ts.end();
            ts.close();
        } catch (IOException e) {
View Full Code Here
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
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
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
          boolean hasMoreTokens = stream.incrementToken();

          fieldState.attributeSource = stream;

          OffsetAttribute offsetAttribute = fieldState.attributeSource.addAttribute(OffsetAttribute.class);
          PositionIncrementAttribute posIncrAttribute = fieldState.attributeSource.addAttribute(PositionIncrementAttribute.class);

          if (hasMoreTokens) {
            consumer.start(field);

            do {
              // If we hit an exception in stream.next below
              // (which is fairly common, eg if analyzer
              // chokes on a given document), then it's
              // non-aborting and (above) this one document
              // will be marked as deleted, but still
              // consume a docID

              final int posIncr = posIncrAttribute.getPositionIncrement();
              if (posIncr < 0) {
                throw new IllegalArgumentException("position increment must be >=0 (got " + posIncr + ") for field '" + field.name() + "'");
              }
              if (fieldState.position == 0 && posIncr == 0) {
                throw new IllegalArgumentException("first position increment must be > 0 (got 0) for field '" + field.name() + "'");
              }
              int position = fieldState.position + posIncr;
              if (position > 0) {
                // NOTE: confusing: this "mirrors" the
                // position++ we do below
                position--;
              } else if (position < 0) {
                throw new IllegalArgumentException("position overflow for field '" + field.name() + "'");
              }
             
              // position is legal, we can safely place it in fieldState now.
              // not sure if anything will use fieldState after non-aborting exc...
              fieldState.position = position;

              if (posIncr == 0)
                fieldState.numOverlap++;
             
              if (checkOffsets) {
                int startOffset = fieldState.offset + offsetAttribute.startOffset();
                int endOffset = fieldState.offset + offsetAttribute.endOffset();
                if (startOffset < 0 || endOffset < startOffset) {
                  throw new IllegalArgumentException("startOffset must be non-negative, and endOffset must be >= startOffset, "
                      + "startOffset=" + startOffset + ",endOffset=" + endOffset + " for field '" + field.name() + "'");
                }
                if (startOffset < lastStartOffset) {
                  throw new IllegalArgumentException("offsets must not go backwards startOffset="
                       + startOffset + " is < lastStartOffset=" + lastStartOffset + " for field '" + field.name() + "'");
                }
                lastStartOffset = startOffset;
              }

              boolean success = false;
              try {
                // If we hit an exception in here, we abort
                // all buffered documents since the last
                // flush, on the likelihood that the
                // internal state of the consumer is now
                // corrupt and should not be flushed to a
                // new segment:
                consumer.add();
                success = true;

              } finally {
                if (!success) {
                  docState.docWriter.setAborting();
                }
              }
              fieldState.length++;
              fieldState.position++;

            } while (stream.incrementToken());
          }
          // trigger streams to perform end-of-stream operations
          stream.end();
          // TODO: maybe add some safety? then again, its already checked
          // when we come back around to the field...
          fieldState.position += posIncrAttribute.getPositionIncrement();
          fieldState.offset += offsetAttribute.endOffset();


          if (docState.maxTermPrefix != null) {
            final String msg = "Document contains at least one immense term in field=\"" + fieldInfo.name + "\" (whose UTF8 encoding is longer than the max length " + DocumentsWriterPerThread.MAX_TERM_LENGTH_UTF8 + "), all of which were skipped.  Please correct the analyzer to not produce such terms.  The prefix of the first immense term is: '" + docState.maxTermPrefix + "...'";
            if (docState.infoStream.isEnabled("IW")) {
View Full Code Here
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
    Collection<Token> result = new HashSet<Token>();
    WhitespaceAnalyzer analyzer = new WhitespaceAnalyzer(Version.LUCENE_31);
    TokenStream ts = analyzer.tokenStream("", new StringReader(origQuery));
    // 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);
   
    try {
      ts.reset();
      while (ts.incrementToken()){
        Token tok = new Token();
        tok.copyBuffer(termAtt.buffer(), 0, termAtt.length());
        tok.setOffset(offsetAtt.startOffset(), offsetAtt.endOffset());
        tok.setFlags(flagsAtt.getFlags());
        tok.setPayload(payloadAtt.getPayload());
        tok.setPositionIncrement(posIncAtt.getPositionIncrement());
        tok.setType(typeAtt.type());
        result.add(tok);
View Full Code Here
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
    Collection<Token> result = new ArrayList<Token>();
    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
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
      for (int i=0; i<result.synonyms.length; i++) {
        Token repTok = result.synonyms[i];
        AttributeSource newTok = firstTok.cloneAttributes();
        CharTermAttribute newTermAtt = newTok.addAttribute(CharTermAttribute.class);
        OffsetAttribute newOffsetAtt = newTok.addAttribute(OffsetAttribute.class);
        PositionIncrementAttribute newPosIncAtt = newTok.addAttribute(PositionIncrementAttribute.class);

        OffsetAttribute lastOffsetAtt = lastTok.addAttribute(OffsetAttribute.class);

        newOffsetAtt.setOffset(newOffsetAtt.startOffset(), lastOffsetAtt.endOffset());
        newTermAtt.copyBuffer(repTok.buffer(), 0, repTok.length());
        repPos += repTok.getPositionIncrement();
        if (i==0) repPos=origPos;  // make position of first token equal to original

        // if necessary, insert original tokens and adjust position increment
View Full Code Here
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
      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());
    ts.close();
  }
View Full Code Here
TOP

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

  • com.chenlb.mmseg4j.analysis.TokenUtils
  • com.flaptor.indextank.query.IndexEngineParser
  • com.github.le11.nls.lucene.UIMABaseAnalyzerTest
  • com.github.le11.nls.lucene.UIMATypeAwareAnalyzerTest
  • com.o19s.RegexPathHierarchyTokenizerTest
  • com.tamingtext.texttamer.solr.NameFilterTest
  • com.tamingtext.texttamer.solr.SentenceTokenizerTest
  • com.tistory.devyongsik.crescent.admin.service.MorphServiceImpl
  • it.unibz.instasearch.indexing.StorageIndexer
  • me.shenfeng.mmseg.HashSetDictionaryTest
    • 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.