# coding=utf-8
# Copyright 2018 Google AI, Google Brain and Carnegie Mellon University Authors and the HuggingFace Inc. team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
""" Tokenization classes for XLNet model."""
import os
import unicodedata
from shutil import copyfile
from typing import Any, Dict, List, Optional, Tuple
import sentencepiece as spm
from ...file_utils import SPIECE_UNDERLINE
from ...tokenization_utils import AddedToken, PreTrainedTokenizer
from ...utils import logging
logger = logging.get_logger(__name__)
VOCAB_FILES_NAMES = {"vocab_file": "spiece.model"}
PRETRAINED_VOCAB_FILES_MAP = {
"vocab_file": {
"xlnet-base-cased": "https://huggingface.co/xlnet-base-cased/resolve/main/spiece.model",
"xlnet-large-cased": "https://huggingface.co/xlnet-large-cased/resolve/main/spiece.model",
}
}
PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
"xlnet-base-cased": None,
"xlnet-large-cased": None,
}
# Segments (not really needed)
SEG_ID_A = 0
SEG_ID_B = 1
SEG_ID_CLS = 2
SEG_ID_SEP = 3
SEG_ID_PAD = 4
[docs]class XLNetTokenizer(PreTrainedTokenizer):
"""
Construct an XLNet tokenizer. Based on `SentencePiece <https://github.com/google/sentencepiece>`__.
This tokenizer inherits from :class:`~transformers.PreTrainedTokenizer` which contains most of the main methods.
Users should refer to this superclass for more information regarding those methods.
Args:
vocab_file (:obj:`str`):
`SentencePiece <https://github.com/google/sentencepiece>`__ file (generally has a .spm extension) that
contains the vocabulary necessary to instantiate a tokenizer.
do_lower_case (:obj:`bool`, `optional`, defaults to :obj:`True`):
Whether to lowercase the input when tokenizing.
remove_space (:obj:`bool`, `optional`, defaults to :obj:`True`):
Whether to strip the text when tokenizing (removing excess spaces before and after the string).
keep_accents (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether to keep accents when tokenizing.
bos_token (:obj:`str`, `optional`, defaults to :obj:`"<s>"`):
The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
.. note::
When building a sequence using special tokens, this is not the token that is used for the beginning of
sequence. The token used is the :obj:`cls_token`.
eos_token (:obj:`str`, `optional`, defaults to :obj:`"</s>"`):
The end of sequence token.
.. note::
When building a sequence using special tokens, this is not the token that is used for the end of
sequence. The token used is the :obj:`sep_token`.
unk_token (:obj:`str`, `optional`, defaults to :obj:`"<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 (:obj:`str`, `optional`, defaults to :obj:`"<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 (:obj:`str`, `optional`, defaults to :obj:`"<pad>"`):
The token used for padding, for example when batching sequences of different lengths.
cls_token (:obj:`str`, `optional`, defaults to :obj:`"<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 (:obj:`str`, `optional`, defaults to :obj:`"<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.
additional_special_tokens (:obj:`List[str]`, `optional`, defaults to :obj:`["<eop>", "<eod>"]`):
Additional special tokens used by the tokenizer.
sp_model_kwargs (:obj:`dict`, `optional`):
Will be passed to the ``SentencePieceProcessor.__init__()`` method. The `Python wrapper for SentencePiece
<https://github.com/google/sentencepiece/tree/master/python>`__ can be used, among other things, to set:
- ``enable_sampling``: Enable subword regularization.
- ``nbest_size``: Sampling parameters for unigram. Invalid for BPE-Dropout.
- ``nbest_size = {0,1}``: No sampling is performed.
- ``nbest_size > 1``: samples from the nbest_size results.
- ``nbest_size < 0``: assuming that nbest_size is infinite and samples from the all hypothesis (lattice)
using forward-filtering-and-backward-sampling algorithm.
- ``alpha``: Smoothing parameter for unigram sampling, and dropout probability of merge operations for
BPE-dropout.
Attributes:
sp_model (:obj:`SentencePieceProcessor`):
The `SentencePiece` processor that is used for every conversion (string, tokens and IDs).
"""
vocab_files_names = VOCAB_FILES_NAMES
pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
padding_side = "left"
def __init__(
self,
vocab_file,
do_lower_case=False,
remove_space=True,
keep_accents=False,
bos_token="<s>",
eos_token="</s>",
unk_token="<unk>",
sep_token="<sep>",
pad_token="<pad>",
cls_token="<cls>",
mask_token="<mask>",
additional_special_tokens=["<eop>", "<eod>"],
sp_model_kwargs: Optional[Dict[str, Any]] = None,
**kwargs
) -> None:
# Mask token behave like a normal word, i.e. include the space before it
mask_token = AddedToken(mask_token, lstrip=True, rstrip=False) if isinstance(mask_token, str) else mask_token
self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
super().__init__(
do_lower_case=do_lower_case,
remove_space=remove_space,
keep_accents=keep_accents,
bos_token=bos_token,
eos_token=eos_token,
unk_token=unk_token,
sep_token=sep_token,
pad_token=pad_token,
cls_token=cls_token,
mask_token=mask_token,
additional_special_tokens=additional_special_tokens,
sp_model_kwargs=self.sp_model_kwargs,
**kwargs,
)
self._pad_token_type_id = 3
self.do_lower_case = do_lower_case
self.remove_space = remove_space
self.keep_accents = keep_accents
self.vocab_file = vocab_file
self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
self.sp_model.Load(vocab_file)
@property
def vocab_size(self):
return len(self.sp_model)
def get_vocab(self):
vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
vocab.update(self.added_tokens_encoder)
return vocab
def __getstate__(self):
state = self.__dict__.copy()
state["sp_model"] = None
return state
def __setstate__(self, d):
self.__dict__ = d
# for backward compatibility
if not hasattr(self, "sp_model_kwargs"):
self.sp_model_kwargs = {}
self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
self.sp_model.Load(self.vocab_file)
def preprocess_text(self, inputs):
if self.remove_space:
outputs = " ".join(inputs.strip().split())
else:
outputs = inputs
outputs = outputs.replace("``", '"').replace("''", '"')
if not self.keep_accents:
outputs = unicodedata.normalize("NFKD", outputs)
outputs = "".join([c for c in outputs if not unicodedata.combining(c)])
if self.do_lower_case:
outputs = outputs.lower()
return outputs
def _tokenize(self, text: str) -> List[str]:
"""Tokenize a string."""
text = self.preprocess_text(text)
pieces = self.sp_model.encode(text, out_type=str)
new_pieces = []
for piece in pieces:
if len(piece) > 1 and piece[-1] == str(",") and piece[-2].isdigit():
cur_pieces = self.sp_model.EncodeAsPieces(piece[:-1].replace(SPIECE_UNDERLINE, ""))
if piece[0] != SPIECE_UNDERLINE and cur_pieces[0][0] == SPIECE_UNDERLINE:
if len(cur_pieces[0]) == 1:
cur_pieces = cur_pieces[1:]
else:
cur_pieces[0] = cur_pieces[0][1:]
cur_pieces.append(piece[-1])
new_pieces.extend(cur_pieces)
else:
new_pieces.append(piece)
return new_pieces
def _convert_token_to_id(self, token):
"""Converts a token (str) in an id using the vocab."""
return self.sp_model.PieceToId(token)
def _convert_id_to_token(self, index):
"""Converts an index (integer) in a token (str) using the vocab."""
return self.sp_model.IdToPiece(index)
def convert_tokens_to_string(self, tokens):
"""Converts a sequence of tokens (strings for sub-words) in a single string."""
out_string = "".join(tokens).replace(SPIECE_UNDERLINE, " ").strip()
return out_string
[docs] 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 (:obj:`List[int]`):
List of IDs.
token_ids_1 (:obj:`List[int]`, `optional`):
Optional second list of IDs for sequence pairs.
already_has_special_tokens (:obj:`bool`, `optional`, defaults to :obj:`False`):
Whether or not the token list is already formatted with special tokens for the model.
Returns:
:obj:`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 super().get_special_tokens_mask(
token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
)
if token_ids_1 is not None:
return ([0] * len(token_ids_0)) + [1] + ([0] * len(token_ids_1)) + [1, 1]
return ([0] * len(token_ids_0)) + [1, 1]
[docs] def create_token_type_ids_from_sequences(
self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
) -> List[int]:
"""
Create a mask from the two sequences passed to be used in a sequence-pair classification task. An XLNet
sequence pair mask has the following format:
::
0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
| first sequence | second sequence |
If :obj:`token_ids_1` is :obj:`None`, this method only returns the first portion of the mask (0s).
Args:
token_ids_0 (:obj:`List[int]`):
List of IDs.
token_ids_1 (:obj:`List[int]`, `optional`):
Optional second list of IDs for sequence pairs.
Returns:
:obj:`List[int]`: List of `token type IDs <../glossary.html#token-type-ids>`_ according to the given
sequence(s).
"""
sep = [self.sep_token_id]
cls_segment_id = [2]
if token_ids_1 is None:
return len(token_ids_0 + sep) * [0] + cls_segment_id
return len(token_ids_0 + sep) * [0] + len(token_ids_1 + sep) * [1] + cls_segment_id
[docs] def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
if not os.path.isdir(save_directory):
logger.error(f"Vocabulary path ({save_directory}) should be a directory")
return
out_vocab_file = os.path.join(
save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
)
if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file):
copyfile(self.vocab_file, out_vocab_file)
return (out_vocab_file,)