Examples of TermAttribute

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

227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
  }

  public void testLinks() throws Exception {
    String test = "[http://lucene.apache.org/java/docs/index.html#news here] [http://lucene.apache.org/java/docs/index.html?b=c here] [https://lucene.apache.org/java/docs/index.html?b=c here]";
    WikipediaTokenizer tf = new WikipediaTokenizer(new StringReader(test));
    TermAttribute termAtt = (TermAttribute) tf.addAttribute(TermAttribute.class);
    TypeAttribute typeAtt = (TypeAttribute) tf.addAttribute(TypeAttribute.class);
   
    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "http://lucene.apache.org/java/docs/index.html#news",
        termAtt.term().equals("http://lucene.apache.org/java/docs/index.html#news") == true);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.EXTERNAL_LINK_URL, typeAtt.type().equals(WikipediaTokenizer.EXTERNAL_LINK_URL) == true);
    tf.incrementToken();//skip here
   
    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "http://lucene.apache.org/java/docs/index.html?b=c",
        termAtt.term().equals("http://lucene.apache.org/java/docs/index.html?b=c") == true);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.EXTERNAL_LINK_URL, typeAtt.type().equals(WikipediaTokenizer.EXTERNAL_LINK_URL) == true);
    tf.incrementToken();//skip here
   
    assertTrue(tf.incrementToken());
    assertTrue(termAtt.term() + " is not equal to " + "https://lucene.apache.org/java/docs/index.html?b=c",
        termAtt.term().equals("https://lucene.apache.org/java/docs/index.html?b=c") == true);
    assertTrue(typeAtt.type() + " is not equal to " + WikipediaTokenizer.EXTERNAL_LINK_URL, typeAtt.type().equals(WikipediaTokenizer.EXTERNAL_LINK_URL) == true);
   
    assertTrue(tf.incrementToken());
    assertFalse(tf.incrementToken());
  }
View Full Code Here

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

260
261
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
    //should be exactly the same, regardless of untoks
    WikipediaTokenizer tf = new WikipediaTokenizer(new StringReader(LINK_PHRASES), WikipediaTokenizer.TOKENS_ONLY, untoks);
    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

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

336
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
    untoks.add(WikipediaTokenizer.CATEGORY);
    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 = (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);
View Full Code Here

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

75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
  public void testGeneral() throws IOException {
    final TeeSinkTokenFilter source = new TeeSinkTokenFilter(new WhitespaceTokenizer(new StringReader(buffer1.toString())));
    final TokenStream sink1 = source.newSinkTokenStream();
    final TokenStream sink2 = source.newSinkTokenStream(theFilter);
    int i = 0;
    TermAttribute termAtt = (TermAttribute) source.getAttribute(TermAttribute.class);
    while (source.incrementToken()) {
      assertEquals(tokens1[i], termAtt.term());
      i++;
    }
    assertEquals(tokens1.length, i);
   
    i = 0;
    termAtt = (TermAttribute) sink1.getAttribute(TermAttribute.class);
    while (sink1.incrementToken()) {
      assertEquals(tokens1[i], termAtt.term());
      i++;
    }
    assertEquals(tokens1.length, i);
   
    i = 0;
    termAtt = (TermAttribute) sink2.getAttribute(TermAttribute.class);
    while (sink2.incrementToken()) {
      assertTrue(termAtt.term().equalsIgnoreCase("The"));
      i++;
    }
    assertEquals("there should be two times 'the' in the stream", 2, i);
  }
View Full Code Here

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

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
    tee2.addSinkTokenStream(dogDetector);
    tee2.addSinkTokenStream(theDetector);
    final TokenStream source2 = tee2;

    int i = 0;
    TermAttribute termAtt = (TermAttribute) source1.getAttribute(TermAttribute.class);
    while (source1.incrementToken()) {
      assertEquals(tokens1[i], termAtt.term());
      i++;
    }
    assertEquals(tokens1.length, i);
    i = 0;
    termAtt = (TermAttribute) source2.getAttribute(TermAttribute.class);
    while (source2.incrementToken()) {
      assertEquals(tokens2[i], termAtt.term());
      i++;
    }
    assertEquals(tokens2.length, i);
    i = 0;
    termAtt = (TermAttribute) theDetector.getAttribute(TermAttribute.class);
    while (theDetector.incrementToken()) {
      assertTrue("'" + termAtt.term() + "' is not equal to 'The'", termAtt.term().equalsIgnoreCase("The"));
      i++;
    }
    assertEquals("there must be 4 times 'The' in the stream", 4, i);
    i = 0;
    termAtt = (TermAttribute) dogDetector.getAttribute(TermAttribute.class);
    while (dogDetector.incrementToken()) {
      assertTrue("'" + termAtt.term() + "' is not equal to 'Dogs'", termAtt.term().equalsIgnoreCase("Dogs"));
      i++;
    }
    assertEquals("there must be 2 times 'Dog' in the stream", 2, i);
   
    source1.reset();
    TokenStream lowerCasing = new LowerCaseFilter(source1);
    i = 0;
    termAtt = (TermAttribute) lowerCasing.getAttribute(TermAttribute.class);
    while (lowerCasing.incrementToken()) {
      assertEquals(tokens1[i].toLowerCase(), termAtt.term());
      i++;
    }
    assertEquals(i, tokens1.length);
  }
View Full Code Here

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

169
170
171
172
173
174
175
176
177
178
179
180
      //make sure we produce the same tokens
      TeeSinkTokenFilter teeStream = new TeeSinkTokenFilter(new StandardFilter(new StandardTokenizer(new StringReader(buffer.toString()))));
      TokenStream sink = teeStream.newSinkTokenStream(new ModuloSinkFilter(100));
      teeStream.consumeAllTokens();
      TokenStream stream = new ModuloTokenFilter(new StandardFilter(new StandardTokenizer(new StringReader(buffer.toString()))), 100);
      TermAttribute tfTok = (TermAttribute) stream.addAttribute(TermAttribute.class);
      TermAttribute sinkTok = (TermAttribute) sink.addAttribute(TermAttribute.class);
      for (int i=0; stream.incrementToken(); i++) {
        assertTrue(sink.incrementToken());
        assertTrue(tfTok + " is not equal to " + sinkTok + " at token: " + i, tfTok.equals(sinkTok) == true);
      }
     
View Full Code Here

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

94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
  }
 
  private void checkTokens(TokenStream stream) throws IOException {
    int count = 0;
   
    TermAttribute termAtt = (TermAttribute) stream.getAttribute(TermAttribute.class);
    assertNotNull(termAtt);
    while (stream.incrementToken()) {
      assertTrue(count < tokens.length);
      assertEquals(tokens[count], termAtt.term());
      count++;
    }
   
    assertEquals(tokens.length, count);
  }
View Full Code Here

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

207
208
209
210
211
212
213
214
215
216
217
218
219
220
    try {
      TokenStream ts = analyzer.tokenStream(label, reader);
      writer.write(label);
      writer.write('\t'); // edit: Inorder to match Hadoop standard
      // TextInputFormat
      TermAttribute termAtt = (TermAttribute) ts.addAttribute(TermAttribute.class);
      while (ts.incrementToken()) {
        char[] termBuffer = termAtt.termBuffer();
        int termLen = termAtt.termLength();
        writer.write(termBuffer, 0, termLen);
        writer.write(' ');
      }
    } finally {
      IOUtils.quietClose(reader);
View Full Code Here

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

232
233
234
235
236
237
238
239
240
241
242
243
244
245
   */
  public static String[] readerToDocument(Analyzer analyzer, Reader reader) throws IOException {
    TokenStream ts = analyzer.tokenStream("", reader);
   
    List<String> coll = new ArrayList<String>();
    TermAttribute termAtt = (TermAttribute) ts.addAttribute(TermAttribute.class);
    while (ts.incrementToken()) {
      char[] termBuffer = termAtt.termBuffer();
      int termLen = termAtt.termLength();
      String val = new String(termBuffer, 0, termLen);
      coll.add(val);
    }
    return coll.toArray(new String[coll.size()]);
  }
View Full Code Here

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

68
69
70
71
72
73
74
75
76
77
78
79
80
    if (!catMatch.equals("Unknown")) {
      document = StringEscapeUtils.unescapeHtml(WikipediaDatasetCreatorMapper.CLOSE_TEXT_TAG_PATTERN.matcher(
        WikipediaDatasetCreatorMapper.OPEN_TEXT_TAG_PATTERN.matcher(document).replaceFirst(""))
          .replaceAll(""));
      TokenStream stream = analyzer.tokenStream(catMatch, new StringReader(document));
      TermAttribute termAtt = (TermAttribute) stream.addAttribute(TermAttribute.class);
      while (stream.incrementToken()) {
        contents.append(termAtt.termBuffer(), 0, termAtt.termLength()).append(' ');
      }
      output.collect(new Text(WikipediaDatasetCreatorMapper.SPACE_NON_ALPHA_PATTERN.matcher(catMatch)
          .replaceAll("_")), new Text(contents.toString()));
    }
  }
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.