File size: 25,475 Bytes
f22c20e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
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
94
95
96
97
98
99
100
101
102
103
104
105
106
107
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
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
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
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
333
334
335
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
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600

from fengshen.examples.pegasus.data_utils import (
    _is_control,
    _is_punctuation,
    _is_whitespace,
    _is_chinese_char)
from transformers import PreTrainedTokenizer
from transformers import logging
from typing import List, Optional, Tuple, Union
import collections
import os
import unicodedata
import re
import jieba
import sys

sys.path.append("../../../../")

jieba.dt.tmp_dir = os.path.expanduser(
    "/cognitive_comp/dongxiaoqun/software/jieba/tmp/")
# jieba.enable_parallel(8)
jieba.initialize()

logger = logging.get_logger(__name__)

VOCAB_FILES_NAMES = {"vocab_file": "vocab.txt"}


def load_vocab(vocab_file):
    """Loads a vocabulary file into a dictionary."""
    vocab = collections.OrderedDict()
    with open(vocab_file, "r", encoding="utf-8") as reader:
        tokens = reader.readlines()
    for index, token in enumerate(tokens):
        token = token.rstrip("\n")
        vocab[token] = index
    return vocab


def whitespace_tokenize(text):
    """Runs basic whitespace cleaning and splitting on a piece of text."""
    text = text.strip()
    if not text:
        return []
    tokens = text.split()
    return tokens


class PegasusTokenizer(PreTrainedTokenizer):
    # copy from BertTokenizer
    r"""
    Construct a Pegasus tokenizer. Based on WordPiece.
    This tokenizer inherits from [`PreTrainedTokenizer`] which contains most of the main methods. Users should refer to
    this superclass for more information regarding those methods.
    Args:
        vocab_file (`str`):
            File containing the vocabulary.
        do_lower_case (`bool`, *optional*, defaults to `True`):
            Whether or not to lowercase the input when tokenizing.
        do_basic_tokenize (`bool`, *optional*, defaults to `True`):
            Whether or not to do basic tokenization before WordPiece.
        never_split (`Iterable`, *optional*):
            Collection of tokens which will never be split during tokenization. Only has an effect when
            `do_basic_tokenize=True`
        unk_token (`str`, *optional*, defaults to `"[UNK]"`):
            The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
            token instead.
        sep_token (`str`, *optional*, defaults to `"[SEP]"`):
            The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for
            sequence classification or for a text and a question for question answering. It is also used as the last
            token of a sequence built with special tokens.
        pad_token (`str`, *optional*, defaults to `"[PAD]"`):
            The token used for padding, for example when batching sequences of different lengths.
        cls_token (`str`, *optional*, defaults to `"[CLS]"`):
            The classifier token which is used when doing sequence classification (classification of the whole sequence
            instead of per-token classification). It is the first token of the sequence when built with special tokens.
        mask_token (`str`, *optional*, defaults to `"[MASK]"`):
            The token used for masking values. This is the token used when training this model with masked language
            modeling. This is the token which the model will try to predict.
        tokenize_chinese_chars (`bool`, *optional*, defaults to `True`):
            Whether or not to tokenize Chinese characters.
            This should likely be deactivated for Japanese (see this
            [issue](https://github.com/huggingface/transformers/issues/328)).
        strip_accents (`bool`, *optional*):
            Whether or not to strip all accents. If this option is not specified, then it will be determined by the
            value for `lowercase` (as in the original BERT).
    """

    vocab_files_names = VOCAB_FILES_NAMES
    model_input_names = ["input_ids", "attention_mask"]

    #     pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
    #     pretrained_init_configuration = PRETRAINED_INIT_CONFIGURATION
    #     max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES

    def __init__(self,
                 vocab_file,
                 do_lower_case=True,
                 do_basic_tokenize=True,
                 never_split=None,
                 pad_token="<pad>",
                 eos_token="</s>",
                 unk_token="<unk>",
                 mask_token="<mask_2>",
                 mask_token_sent="<mask_1>",
                 additional_special_tokens=None,
                 sep_token="[SEP]",
                 cls_token="[CLS]",
                 tokenize_chinese_chars=True,
                 strip_accents=None,
                 offset=100,
                 pre_tokenizer=lambda x: jieba.cut(x, HMM=False),
                 **kwargs):
        self.offset = offset

        if additional_special_tokens is not None:
            if not isinstance(additional_special_tokens, list):
                raise TypeError(
                    f"additional_special_tokens should be of type {type(list)}, \
                     but is {type(additional_special_tokens)}"
                )

            additional_special_tokens_extended = (
                ([mask_token_sent] + additional_special_tokens)
                if mask_token_sent not in additional_special_tokens
                and mask_token_sent is not None else additional_special_tokens)

            # fill additional tokens with ..., <unk_token_102> in case not all additional tokens are already taken
            additional_special_tokens_extended += [
                f"<unk_{i}>" for i in range(
                    len(additional_special_tokens_extended), self.offset - 1)
            ]

            if len(set(additional_special_tokens_extended)) != len(
                    additional_special_tokens_extended):
                raise ValueError(
                    f"Please make sure that the provided additional_special_tokens \
                        do not contain an incorrectly shifted list of <unk_x> tokens. \
                        Found {additional_special_tokens_extended}."
                )
            additional_special_tokens = additional_special_tokens_extended
        else:
            additional_special_tokens = [
                mask_token_sent
            ] if mask_token_sent is not None else []
            # additional_special_tokens += [f"<unk_{i}>" for i in range(3, self.offset)]

        # print("additional_special_tokens: ", additional_special_tokens)

        if not os.path.isfile(vocab_file):
            raise ValueError(
                f"Can't find a vocabulary file at path '{vocab_file}'. \
                To load the vocabulary from a Google pretrained "
                "model use `tokenizer = BertTokenizer.from_pretrained(PRETRAINED_MODEL_NAME)`"
            )

        super().__init__(
            do_lower_case=do_lower_case,
            do_basic_tokenize=do_basic_tokenize,
            never_split=never_split,
            unk_token=unk_token,
            sep_token=sep_token,
            pad_token=pad_token,
            cls_token=cls_token,
            mask_token=mask_token,
            eos_token=eos_token,
            tokenize_chinese_chars=tokenize_chinese_chars,
            additional_special_tokens=additional_special_tokens,
            strip_accents=strip_accents,
            **kwargs,
        )

        self.pre_tokenizer = pre_tokenizer
        self.mask_token_sent = mask_token_sent
        self.vocab = load_vocab(vocab_file)

        self.vocab[self.eos_token] = self.vocab.pop("[unused1]")
        # self.vocab[self.eos_token] = self.vocab.pop("[unused2]")
        self.vocab[self.pad_token] = self.vocab.pop("[PAD]")
        self.vocab[self.unk_token] = self.vocab.pop("[UNK]")

        if self.mask_token_sent is not None:
            self.vocab[self.mask_token] = self.vocab.pop("[unused3]")
            self.vocab[self.mask_token_sent] = self.vocab.pop("[unused2]")

        self.ids_to_tokens = collections.OrderedDict([
            (ids, tok) for tok, ids in self.vocab.items()
        ])
        self.do_basic_tokenize = do_basic_tokenize
        if do_basic_tokenize:
            self.basic_tokenizer = BasicTokenizer(
                do_lower_case=do_lower_case,
                never_split=never_split,
                tokenize_chinese_chars=tokenize_chinese_chars,
                strip_accents=strip_accents,
            )
        self.wordpiece_tokenizer = WordpieceTokenizer(vocab=self.vocab,
                                                      unk_token=self.unk_token)

    @property
    def do_lower_case(self):
        return self.basic_tokenizer.do_lower_case

    @property
    def vocab_size(self):
        return len(self.vocab)

    def get_vocab(self):
        return dict(self.vocab, **self.added_tokens_encoder)

    def _tokenize(self, text):
        split_tokens = []
        # print("pegasus_tokenizer: ", text)
        for text in self.pre_tokenizer(text):
            if text in self.vocab:
                split_tokens.append(text)
            else:
                if self.do_basic_tokenize:
                    for token in self.basic_tokenizer.tokenize(
                            text, never_split=self.all_special_tokens):

                        # If the token is part of the never_split set
                        if token in self.basic_tokenizer.never_split:
                            split_tokens.append(token)
                        else:
                            split_tokens += self.wordpiece_tokenizer.tokenize(
                                token)
                else:
                    split_tokens = self.wordpiece_tokenizer.tokenize(text)
        return split_tokens

    def _convert_token_to_id(self, token):
        """Converts a token (str) in an id using the vocab."""
        return self.vocab.get(token, self.vocab.get(self.unk_token))

    def _convert_id_to_token(self, index):
        """Converts an index (integer) in a token (str) using the vocab."""
        return self.ids_to_tokens.get(index, self.unk_token)

    @staticmethod
    def _cjk_punctuation():
        return u'\uff02\uff03\uff04\uff05\uff06\uff07\uff08\uff09\uff0a\uff0b\uff0c\uff0d\uff0f\uff1a\uff1b\uff1c\uff1d\
            \uff1e\uff20\uff3b\uff3c\uff3d\uff3e\uff3f\uff40\uff5b\uff5c\uff5d\uff5e\uff5f\uff60\uff62\
            \uff63\uff64\u3000\u3001\u3003\u3008\u3009\u300a\u300b\u300c\u300d\u300e\u300f\u3010\u3011\u3014\
            \u3015\u3016\u3017\u3018\u3019\u301a\u301b\u301c\u301d\u301e\u301f\u3030\u303e\u303f\u2013\u2014\
            \u2018\u2019\u201b\u201c\u201d\u201e\u201f\u2026\u2027\ufe4f\ufe51\ufe54\u00b7\uff01\uff1f\uff61\u3002'

    def convert_ids_to_tokens(
            self,
            ids: Union[int, List[int]],
            skip_special_tokens: bool = False) -> Union[str, List[str]]:
        """
        Converts a single index or a sequence of indices in a token or a sequence of tokens, using the vocabulary and
        added tokens.
        Args:
            ids (`int` or `List[int]`):
                The token id (or token ids) to convert to tokens.
            skip_special_tokens (`bool`, *optional*, defaults to `False`):
                Whether or not to remove special tokens in the decoding.
        Returns:
            `str` or `List[str]`: The decoded token(s).
        """
        if isinstance(ids, int):
            if ids in self.added_tokens_decoder:
                return self.added_tokens_decoder[ids]
            else:
                return self._convert_id_to_token(ids)
        tokens = []
        for index in ids:
            index = int(index)
            if skip_special_tokens and index in self.all_special_ids and index != 2:
                continue
            if index in self.added_tokens_decoder:
                tokens.append(self.added_tokens_decoder[index])
            else:
                tokens.append(self._convert_id_to_token(index))
        return tokens

    def convert_tokens_to_string(self, tokens):
        """Converts a sequence of tokens (string) in a single string."""
        # for token in
        # tokens = tokens or self.ids_to_tokens(ids)
        # tokens = [token for token in tokens if not self._is_special(token)]

        text = ''
        for i, token in enumerate(tokens):
            if token[:2] == '##':
                text += token[2:]
            elif len(token) == 1 and _is_chinese_char(ord(token)):
                text += token
            elif len(token) == 1 and _is_punctuation(token):
                text += token
                text += ' '
            elif i > 0 and _is_chinese_char(ord(text[-1])):
                text += token
            elif tokens == "</s>":
                continue
            else:
                text += ' '
                text += token

        text = re.sub(' +', ' ', text)
        text = re.sub('\' (re|m|s|t|ve|d|ll) ', '\'\\1 ', text)
        punctuation = re.sub(' +', '', self._cjk_punctuation()).strip() + '+-/={(<['
        punctuation_regex = '|'.join([re.escape(p) for p in punctuation])
        punctuation_regex = '(%s) ' % punctuation_regex
        text = re.sub(punctuation_regex, '\\1', text)
        text = re.sub(r'(\d\.) (\d)', '\\1\\2', text)

        return text.strip()
        # out_string = " ".join(tokens).replace(" ##", "").strip()

    def build_inputs_with_special_tokens(
            self,
            token_ids_0: List[int],
            token_ids_1: Optional[List[int]] = None) -> List[int]:
        """
        Build model inputs from a sequence or a pair of sequences for sequence classification tasks by concatenating
        and adding special tokens. A PEGASUS sequence has the following format, where `X` represents the sequence:
        - single sequence: `X </s>`
        - pair of sequences: `A B </s>` (not intended use)
        BOS is never used. Pairs of sequences are not the expected use case, but they will be handled without a
        separator.
        Args:
            token_ids_0 (`List[int]`):
                List of IDs to which the special tokens will be added.
            token_ids_1 (`List[int]`, *optional*):
                Optional second list of IDs for sequence pairs.
        Returns:
            `List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
        """
        if token_ids_1 is None:
            return token_ids_0 + [self.eos_token_id]
        return token_ids_0 + token_ids_1 + [self.eos_token_id]

    def _special_token_mask(self, seq):
        all_special_ids = set(
            self.all_special_ids)  # call it once instead of inside list comp
        # all_special_ids.remove(self.unk_token_id)  # <unk> is only sometimes special

        return [1 if x in all_special_ids else 0 for x in seq]

    def get_special_tokens_mask(
            self,
            token_ids_0: List[int],
            token_ids_1: Optional[List[int]] = None,
            already_has_special_tokens: bool = False) -> List[int]:
        """
        Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
        special tokens using the tokenizer `prepare_for_model` method.
        Args:
            token_ids_0 (`List[int]`):
                List of IDs.
            token_ids_1 (`List[int]`, *optional*):
                Optional second list of IDs for sequence pairs.
            already_has_special_tokens (`bool`, *optional*, defaults to `False`):
                Whether or not the token list is already formatted with special tokens for the model.
        Returns:
            `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
        """

        if already_has_special_tokens:
            return self._special_token_mask(token_ids_0)
        elif token_ids_1 is None:
            return self._special_token_mask(token_ids_0) + [self.eos_token_id]
        else:
            return self._special_token_mask(token_ids_0 +
                                            token_ids_1) + [self.eos_token_id]

    def num_special_tokens_to_add(self, pair=False):
        """Just EOS"""
        return 1

    def save_vocabulary(self,
                        save_directory: str,
                        filename_prefix: Optional[str] = None) -> Tuple[str]:
        index = 0
        if os.path.isdir(save_directory):
            vocab_file = os.path.join(
                save_directory,
                (filename_prefix + "-" if filename_prefix else "") +
                VOCAB_FILES_NAMES["vocab_file"])
        else:
            vocab_file = (filename_prefix +
                          "-" if filename_prefix else "") + save_directory
        with open(vocab_file, "w", encoding="utf-8") as writer:
            for token, token_index in sorted(self.vocab.items(),
                                             key=lambda kv: kv[1]):
                if index != token_index:
                    logger.warning(
                        f"Saving vocabulary to {vocab_file}: vocabulary indices are not consecutive."
                        " Please check that the vocabulary is not corrupted!")
                    index = token_index
                writer.write(token + "\n")
                index += 1
        return (vocab_file, )


class BasicTokenizer(object):
    """
    Constructs a BasicTokenizer that will run basic tokenization (punctuation splitting, lower casing, etc.).
    Args:
        do_lower_case (`bool`, *optional*, defaults to `True`):
            Whether or not to lowercase the input when tokenizing.
        never_split (`Iterable`, *optional*):
            Collection of tokens which will never be split during tokenization. Only has an effect when
            `do_basic_tokenize=True`
        tokenize_chinese_chars (`bool`, *optional*, defaults to `True`):
            Whether or not to tokenize Chinese characters.
            This should likely be deactivated for Japanese (see this
            [issue](https://github.com/huggingface/transformers/issues/328)).
        strip_accents: (`bool`, *optional*):
            Whether or not to strip all accents. If this option is not specified, then it will be determined by the
            value for `lowercase` (as in the original BERT).
    """

    def __init__(self,
                 do_lower_case=True,
                 never_split=None,
                 tokenize_chinese_chars=True,
                 strip_accents=None):
        if never_split is None:
            never_split = []
        self.do_lower_case = do_lower_case
        self.never_split = set(never_split)
        self.tokenize_chinese_chars = tokenize_chinese_chars
        self.strip_accents = strip_accents

    def tokenize(self, text, never_split=None):
        """
        Basic Tokenization of a piece of text. Split on "white spaces" only, for sub-word tokenization, see
        WordPieceTokenizer.
        Args:
            never_split (`List[str]`, *optional*)
                Kept for backward compatibility purposes. Now implemented directly at the base class level (see
                [`PreTrainedTokenizer.tokenize`]) List of token not to split.
        """
        # union() returns a new set by concatenating the two sets.
        never_split = self.never_split.union(
            set(never_split)) if never_split else self.never_split
        text = self._clean_text(text)

        # This was added on November 1st, 2018 for the multilingual and Chinese
        # models. This is also applied to the English models now, but it doesn't
        # matter since the English models were not trained on any Chinese data
        # and generally don't have any Chinese data in them (there are Chinese
        # characters in the vocabulary because Wikipedia does have some Chinese
        # words in the English Wikipedia.).
        if self.tokenize_chinese_chars:
            text = self._tokenize_chinese_chars(text)
        orig_tokens = whitespace_tokenize(text)
        split_tokens = []
        for token in orig_tokens:
            if token not in never_split:
                if self.do_lower_case:
                    token = token.lower()
                    if self.strip_accents is not False:
                        token = self._run_strip_accents(token)
                elif self.strip_accents:
                    token = self._run_strip_accents(token)
            split_tokens.extend(self._run_split_on_punc(token, never_split))

        output_tokens = whitespace_tokenize(" ".join(split_tokens))
        return output_tokens

    def _run_strip_accents(self, text):
        """Strips accents from a piece of text."""
        text = unicodedata.normalize("NFD", text)
        output = []
        for char in text:
            cat = unicodedata.category(char)
            if cat == "Mn":
                continue
            output.append(char)
        return "".join(output)

    def _run_split_on_punc(self, text, never_split=None):
        """Splits punctuation on a piece of text."""
        if never_split is not None and text in never_split:
            return [text]
        chars = list(text)
        i = 0
        start_new_word = True
        output = []
        while i < len(chars):
            char = chars[i]
            if _is_punctuation(char):
                output.append([char])
                start_new_word = True
            else:
                if start_new_word:
                    output.append([])
                start_new_word = False
                output[-1].append(char)
            i += 1

        return ["".join(x) for x in output]

    def _tokenize_chinese_chars(self, text):
        """Adds whitespace around any CJK character."""
        output = []
        for char in text:
            cp = ord(char)
            if self._is_chinese_char(cp):
                output.append(" ")
                output.append(char)
                output.append(" ")
            else:
                output.append(char)
        return "".join(output)

    def _is_chinese_char(self, cp):
        """Checks whether CP is the codepoint of a CJK character."""
        # This defines a "chinese character" as anything in the CJK Unicode block:
        #   https://en.wikipedia.org/wiki/CJK_Unified_Ideographs_(Unicode_block)
        #
        # Note that the CJK Unicode block is NOT all Japanese and Korean characters,
        # despite its name. The modern Korean Hangul alphabet is a different block,
        # as is Japanese Hiragana and Katakana. Those alphabets are used to write
        # space-separated words, so they are not treated specially and handled
        # like the all of the other languages.
        if ((cp >= 0x4E00 and cp <= 0x9FFF)
            or (cp >= 0x3400 and cp <= 0x4DBF)  #
            or (cp >= 0x20000 and cp <= 0x2A6DF)  #
            or (cp >= 0x2A700 and cp <= 0x2B73F)  #
            or (cp >= 0x2B740 and cp <= 0x2B81F)  #
            or (cp >= 0x2B820 and cp <= 0x2CEAF)  #
            or (cp >= 0xF900 and cp <= 0xFAFF)
                or (cp >= 0x2F800 and cp <= 0x2FA1F)):  #
            return True

        return False

    def _clean_text(self, text):
        """Performs invalid character removal and whitespace cleanup on text."""
        output = []
        for char in text:
            cp = ord(char)
            if cp == 0 or cp == 0xFFFD or _is_control(char):
                continue
            if _is_whitespace(char):
                output.append(" ")
            else:
                output.append(char)
        return "".join(output)


class WordpieceTokenizer(object):
    """Runs WordPiece tokenization."""

    def __init__(self, vocab, unk_token, max_input_chars_per_word=100):
        self.vocab = vocab
        self.unk_token = unk_token
        self.max_input_chars_per_word = max_input_chars_per_word

    def tokenize(self, text):
        """
        Tokenizes a piece of text into its word pieces. This uses a greedy longest-match-first algorithm to perform
        tokenization using the given vocabulary.
        For example, `input = "unaffable"` wil return as output `["un", "##aff", "##able"]`.
        Args:
            text: A single token or whitespace separated tokens. This should have
                already been passed through *BasicTokenizer*.
        Returns:
            A list of wordpiece tokens.
        """

        output_tokens = []
        for token in whitespace_tokenize(text):
            chars = list(token)
            if len(chars) > self.max_input_chars_per_word:
                output_tokens.append(self.unk_token)
                continue

            is_bad = False
            start = 0
            sub_tokens = []
            while start < len(chars):
                end = len(chars)
                cur_substr = None
                while start < end:
                    substr = "".join(chars[start:end])
                    if start > 0:
                        substr = "##" + substr
                    if substr in self.vocab:
                        cur_substr = substr
                        break
                    end -= 1
                if cur_substr is None:
                    is_bad = True
                    break
                sub_tokens.append(cur_substr)
                start = end

            if is_bad:
                output_tokens.append(self.unk_token)
            else:
                output_tokens.extend(sub_tokens)
        return output_tokens