Package org.apache.lucene.analysis.tokenattributes

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

262
263
264
265
266
267
268
269
270
271
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
    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 = (TermAttribute) tf.addAttribute(TermAttribute.class);
    PositionIncrementAttribute posIncrAtt = (PositionIncrementAttribute) tf.addAttribute(PositionIncrementAttribute.class);
    OffsetAttribute offsetAtt = (OffsetAttribute) 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
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
    //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 = (TermAttribute) tf.addAttribute(TermAttribute.class);
    TypeAttribute typeAtt = (TypeAttribute) tf.addAttribute(TypeAttribute.class);
    PositionIncrementAttribute posIncrAtt = (PositionIncrementAttribute) tf.addAttribute(PositionIncrementAttribute.class);
    OffsetAttribute offsetAtt = (OffsetAttribute) tf.addAttribute(OffsetAttribute.class);
    FlagsAttribute flagsAtt = (FlagsAttribute) 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
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
      int numOverlapTokens = 0;
      int pos = -1;
     
      TermAttribute termAtt = (TermAttribute) stream.addAttribute(TermAttribute.class);
      PositionIncrementAttribute posIncrAttribute = (PositionIncrementAttribute) stream.addAttribute(PositionIncrementAttribute.class);
      OffsetAttribute offsetAtt = (OffsetAttribute) stream.addAttribute(OffsetAttribute.class);
     
      stream.reset();
      while (stream.incrementToken()) {
        String term = termAtt.term();
        if (term.length() == 0) continue; // nothing to do
//        if (DEBUG) System.err.println("token='" + term + "'");
        numTokens++;
        final int posIncr = posIncrAttribute.getPositionIncrement();
        if (posIncr == 0)
          numOverlapTokens++;
        pos += posIncr;
       
        ArrayIntList positions = (ArrayIntList) terms.get(term);
        if (positions == null) { // term not seen before
          positions = new ArrayIntList(stride);
          terms.put(term, positions);
        }
        if (stride == 1) {
          positions.add(pos);
        } else {
          positions.add(pos, offsetAtt.startOffset(), offsetAtt.endOffset());
        }
      }
      stream.end();

      // ensure infos.numTokens > 0 invariant; needed for correct operation of terms()
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
      int numOverlapTokens = 0;
      int pos = -1;
     
      CharTermAttribute termAtt = stream.addAttribute(CharTermAttribute.class);
      PositionIncrementAttribute posIncrAttribute = stream.addAttribute(PositionIncrementAttribute.class);
      OffsetAttribute offsetAtt = stream.addAttribute(OffsetAttribute.class);
      stream.reset();
      while (stream.incrementToken()) {
        String term = termAtt.toString();
        if (term.length() == 0) continue; // nothing to do
//        if (DEBUG) System.err.println("token='" + term + "'");
        numTokens++;
        final int posIncr = posIncrAttribute.getPositionIncrement();
        if (posIncr == 0)
          numOverlapTokens++;
        pos += posIncr;
       
        ArrayIntList positions = terms.get(term);
        if (positions == null) { // term not seen before
          positions = new ArrayIntList(stride);
          terms.put(term, positions);
        }
        if (stride == 1) {
          positions.add(pos);
        } else {
          positions.add(pos, offsetAtt.startOffset(), offsetAtt.endOffset());
        }
      }
      stream.end();

      // ensure infos.numTokens > 0 invariant; needed for correct operation of terms()
View Full Code Here
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
          try {
            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++;
              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();
          } finally {
            stream.close();
          }
        }
View Full Code Here
88
89
90
91
92
93
94
95
96
97
  }

  // LUCENE-1441
  public void testOffsets() throws Exception {
    TokenStream stream = new KeywordAnalyzer().tokenStream("field", new StringReader("abcd"));
    OffsetAttribute offsetAtt = stream.addAttribute(OffsetAttribute.class);
    assertTrue(stream.incrementToken());
    assertEquals(0, offsetAtt.startOffset());
    assertEquals(4, offsetAtt.endOffset());
  }
View Full Code Here
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
  {
    ArrayList<TextFragment> docFrags = new ArrayList<TextFragment>();
    StringBuilder newText=new StringBuilder();
   
      CharTermAttribute termAtt = tokenStream.addAttribute(CharTermAttribute.class);
      OffsetAttribute offsetAtt = tokenStream.addAttribute(OffsetAttribute.class);
      tokenStream.addAttribute(PositionIncrementAttribute.class);
      tokenStream.reset();
     
    TextFragment currentFrag =  new TextFragment(newText,newText.length(), docFrags.size());
   
    if (fragmentScorer instanceof QueryScorer) {
      ((QueryScorer) fragmentScorer).setMaxDocCharsToAnalyze(maxDocCharsToAnalyze);
    }
   
    TokenStream newStream = fragmentScorer.init(tokenStream);
    if(newStream != null) {
      tokenStream = newStream;
    }
    fragmentScorer.startFragment(currentFrag);
    docFrags.add(currentFrag);

    FragmentQueue fragQueue = new FragmentQueue(maxNumFragments);

    try
    {

      String tokenText;
      int startOffset;
      int endOffset;
      int lastEndOffset = 0;
      textFragmenter.start(text, tokenStream);

      TokenGroup tokenGroup=new TokenGroup(tokenStream);

      for (boolean next = tokenStream.incrementToken(); next && (offsetAtt.startOffset()< maxDocCharsToAnalyze);
            next = tokenStream.incrementToken())
      {
        if(  (offsetAtt.endOffset()>text.length())
          ||
          (offsetAtt.startOffset()>text.length())
          )           
        {
          throw new InvalidTokenOffsetsException("Token "+ termAtt.toString()
              +" exceeds length of provided text sized "+text.length());
        }
View Full Code Here
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
        try {
            stream = analyzer.tokenStream(FieldNames.FULLTEXT,
                    new StringReader(text));
            CharTermAttribute termAtt = stream
                    .addAttribute(CharTermAttribute.class);
            OffsetAttribute offsetAtt = stream
                    .addAttribute(OffsetAttribute.class);
            // TypeAttribute type = stream.addAttribute(TypeAttribute.class);

            stream.reset();

            int poz = 0;
            boolean hasFulltextToken = false;
            StringBuilder token = new StringBuilder();
            while (stream.incrementToken()) {
                String term = termAtt.toString();
                int start = offsetAtt.startOffset();
                int end = offsetAtt.endOffset();
                if (start > poz) {
                    for (int i = poz; i < start; i++) {
                        for (char c : fulltextTokens) {
                            if (c == text.charAt(i)) {
                                token.append(c);
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
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
 
  public void testNext() throws IOException {
   
   
    TermAttribute termAtt = (TermAttribute)merger.getAttribute(TermAttribute.class);
    OffsetAttribute offsetAtt = (OffsetAttribute)merger.getAttribute(OffsetAttribute.class);
    PositionIncrementAttribute posIncAtt = (PositionIncrementAttribute)merger.getAttribute(PositionIncrementAttribute.class);
   
    merger.incrementToken();
   
    assertEquals("1111", termAtt.term());
    assertEquals(0, offsetAtt.startOffset());
    assertEquals(4, offsetAtt.endOffset());
    assertEquals(1, posIncAtt.getPositionIncrement());
   
    merger.incrementToken();   
    assertEquals("1111",  termAtt.term());
    assertEquals(5,  offsetAtt.startOffset());
    assertEquals(9,  offsetAtt.endOffset());
    assertEquals(1,  posIncAtt.getPositionIncrement());

    merger.incrementToken();
    assertEquals("2222",  termAtt.term());
    assertEquals(5,  offsetAtt.startOffset());
    assertEquals(9,  offsetAtt.endOffset());
    assertEquals(0,  posIncAtt.getPositionIncrement());

    merger.incrementToken();
    assertEquals("1111",  termAtt.term());
    assertEquals(10,  offsetAtt.startOffset());
    assertEquals(14,  offsetAtt.endOffset());
    assertEquals(1,  posIncAtt.getPositionIncrement());

    merger.incrementToken();
    assertEquals("3333",  termAtt.term());
    assertEquals(10,  offsetAtt.startOffset());
    assertEquals(14,  offsetAtt.endOffset());
    assertEquals(0,  posIncAtt.getPositionIncrement());

    merger.incrementToken();
    assertEquals("1111",  termAtt.term());
    assertEquals(15, offsetAtt.startOffset());
    assertEquals(19, offsetAtt.endOffset());
    assertEquals(1,  posIncAtt.getPositionIncrement());

    merger.incrementToken();
    assertEquals("2222",  termAtt.term());
    assertEquals(15,  offsetAtt.startOffset());
    assertEquals(19, offsetAtt.endOffset());
    assertEquals(0, posIncAtt.getPositionIncrement());
  }
View Full Code Here
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
                new StringReader(text));

        CharTermAttribute term = stream.addAttribute(CharTermAttribute.class);
        PositionIncrementAttribute posIncr = stream
                .addAttribute(PositionIncrementAttribute.class);
        OffsetAttribute offset = stream.addAttribute(OffsetAttribute.class);
        TypeAttribute type = stream.addAttribute(TypeAttribute.class);
        PayloadAttribute payload = stream.addAttribute(PayloadAttribute.class);

        int position = 0;
        while (stream.incrementToken()) {

            int increment = posIncr.getPositionIncrement();
            if (increment > 0) {
                position = position + increment;
                System.out.println();
                System.out.print(position + ":");
            }

            BytesRef pl = payload.getPayload();

            if (pl != null) {
                System.out.print("[" + term.toString() + ":" + offset.startOffset()
                        + "->" + offset.endOffset() + ":" + type.type() + ":"
                        + new String(pl.bytes) + "] ");

            } else {
                System.out.print("[" + term.toString() + ":" + offset.startOffset()
                        + "->" + offset.endOffset() + ":" + type.type() + "] ");

            }
        }
        System.out.println();
    }
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.