tokenization_phobert.py

# coding=utf-8
# Copyright (c) 2020, VinAI Research and the HuggingFace Inc. team.
# Copyright 2018 The Open AI Team 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 PhoBERT"""


import os
import re
from shutil import copyfile
from typing import List, Optional, Tuple

from transformers.tokenization_utils import PreTrainedTokenizer
from transformers.utils import logging


logger = logging.get_logger(__name__)

VOCAB_FILES_NAMES = {
    "vocab_file": "vocab.txt",
    "merges_file": "bpe.codes",
}

PRETRAINED_VOCAB_FILES_MAP = {
    "vocab_file": {
        "vinai/phobert-base": "https://huggingface.co/vinai/phobert-base/resolve/main/vocab.txt",
        "vinai/phobert-large": "https://huggingface.co/vinai/phobert-large/resolve/main/vocab.txt",
    },
    "merges_file": {
        "vinai/phobert-base": "https://huggingface.co/vinai/phobert-base/resolve/main/bpe.codes",
        "vinai/phobert-large": "https://huggingface.co/vinai/phobert-large/resolve/main/bpe.codes",
    },
}

PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
    "vinai/phobert-base": 256,
    "vinai/phobert-large": 256,
}


def get_pairs(word):
    """
    Return set of symbol pairs in a word.

    Word is represented as tuple of symbols (symbols being variable-length strings).
    """
    pairs = set()
    prev_char = word[0]
    for char in word[1:]:
        pairs.add((prev_char, char))
        prev_char = char

    pairs = set(pairs)
    return pairs


class PhobertTokenizer(PreTrainedTokenizer):
    """
    Construct a PhoBERT tokenizer. Based on Byte-Pair-Encoding.

    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`):
            Path to the vocabulary file.
        merges_file (`str`):
            Path to the merges file.
        bos_token (`st`, *optional*, defaults to `"<s>"`):
            The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.

            <Tip>

            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 `cls_token`.

            </Tip>

        eos_token (`str`, *optional*, defaults to `"</s>"`):
            The end of sequence token.

            <Tip>

            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 `sep_token`.

            </Tip>

        sep_token (`str`, *optional*, defaults to `"</s>"`):
            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.
        cls_token (`str`, *optional*, defaults to `"<s>"`):
            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.
        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.
        pad_token (`str`, *optional*, defaults to `"<pad>"`):
            The token used for padding, for example when batching sequences of different lengths.
        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.
    """

    vocab_files_names = VOCAB_FILES_NAMES
    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
    model_input_names = ["input_ids", "attention_mask"]

    def __init__(
        self,
        vocab_file,
        merges_file,
        bos_token="<s>",
        eos_token="</s>",
        sep_token="</s>",
        cls_token="<s>",
        unk_token="<unk>",
        pad_token="<pad>",
        mask_token="<mask>",
        **kwargs
    ):
        super().__init__(
            bos_token=bos_token,
            eos_token=eos_token,
            unk_token=unk_token,
            sep_token=sep_token,
            cls_token=cls_token,
            pad_token=pad_token,
            mask_token=mask_token,
            **kwargs,
        )

        self.vocab_file = vocab_file
        self.merges_file = merges_file

        self.encoder = {}
        self.encoder[self.bos_token] = 0
        self.encoder[self.pad_token] = 1
        self.encoder[self.eos_token] = 2
        self.encoder[self.unk_token] = 3

        self.add_from_file(vocab_file)
        self.encoder[self.mask_token] = len(self.encoder)

        self.decoder = {v: k for k, v in self.encoder.items()}

        with open(merges_file, encoding="utf-8") as merges_handle:
            merges = merges_handle.read().split("\n")[:-1]
        merges = [tuple(merge.split()[:-1]) for merge in merges]
        self.bpe_ranks = dict(zip(merges, range(len(merges))))
        self.cache = {}

    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 sequence for sequence classification tasks by concatenating and
        adding special tokens. A PhoBERT sequence has the following format:

        - single sequence: `<s> X </s>`
        - pair of sequences: `<s> A </s></s> B </s>`

        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 [self.cls_token_id] + token_ids_0 + [self.sep_token_id]
        cls = [self.cls_token_id]
        sep = [self.sep_token_id]
        return cls + token_ids_0 + sep + sep + token_ids_1 + sep

    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 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 None:
            return [1] + ([0] * len(token_ids_0)) + [1]
        return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]

    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. PhoBERT does not
        make use of token type ids, therefore a list of zeros is returned.

        Args:
            token_ids_0 (`List[int]`):
                List of IDs.
            token_ids_1 (`List[int]`, *optional*):
                Optional second list of IDs for sequence pairs.

        Returns:
            `List[int]`: List of zeros.
        """

        sep = [self.sep_token_id]
        cls = [self.cls_token_id]

        if token_ids_1 is None:
            return len(cls + token_ids_0 + sep) * [0]
        return len(cls + token_ids_0 + sep + sep + token_ids_1 + sep) * [0]

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

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

    def bpe(self, token):
        if token in self.cache:
            return self.cache[token]
        word = tuple(token)
        word = tuple(list(word[:-1]) + [word[-1] + "</w>"])
        pairs = get_pairs(word)

        if not pairs:
            return token

        while True:
            bigram = min(pairs, key=lambda pair: self.bpe_ranks.get(pair, float("inf")))
            if bigram not in self.bpe_ranks:
                break
            first, second = bigram
            new_word = []
            i = 0
            while i < len(word):
                try:
                    j = word.index(first, i)
                except ValueError:
                    new_word.extend(word[i:])
                    break
                else:
                    new_word.extend(word[i:j])
                    i = j

                if word[i] == first and i < len(word) - 1 and word[i + 1] == second:
                    new_word.append(first + second)
                    i += 2
                else:
                    new_word.append(word[i])
                    i += 1
            new_word = tuple(new_word)
            word = new_word
            if len(word) == 1:
                break
            else:
                pairs = get_pairs(word)
        word = "@@ ".join(word)
        word = word[:-4]
        self.cache[token] = word
        return word

    def _tokenize(self, text):
        """Tokenize a string."""
        split_tokens = []

        words = re.findall(r"\S+\n?", text)

        for token in words:
            split_tokens.extend([t for t in self.bpe(token).split(" ")])
        return split_tokens

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

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

    def convert_tokens_to_string(self, tokens):
        """Converts a sequence of tokens (string) in a single string."""
        out_string = " ".join(tokens).replace("@@ ", "").strip()
        return out_string

    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) and os.path.isfile(self.vocab_file):
            copyfile(self.vocab_file, out_vocab_file)
        elif not os.path.isfile(self.vocab_file):
            with open(out_vocab_file, "w", encoding="utf-8") as fp:
                for token, value in self.encoder.items():
                    if token not in self.all_special_tokens:
                        fp.write(f"{str(token)} 1\n")

        out_merges_file = os.path.join(
            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["merges_file"]
        )

        if os.path.abspath(self.merges_file) != os.path.abspath(out_merges_file) and os.path.isfile(self.merges_file):
            copyfile(self.merges_file, out_merges_file)
        elif not os.path.isfile(self.merges_file):
            index = 0
            with open(out_merges_file, "w", encoding="utf-8") as writer:
                for bpe_tokens, token_index in sorted(self.bpe_ranks.items(), key=lambda kv: kv[1]):
                    if index != token_index:
                        logger.warning(
                            f"Saving vocabulary to {out_merges_file}: BPE merge indices are not consecutive."
                            " Please check that the tokenizer is not corrupted!"
                        )
                        index = token_index
                    writer.write(" ".join(bpe_tokens) + " 1\n")
                    index += 1

        return (out_vocab_file, out_merges_file)

    # def decode(self, token_ids, skip_special_tokens=False, clean_up_tokenization_spaces=True):
    #     filtered_tokens = ' '.join(self.convert_ids_to_tokens(token_ids, skip_special_tokens=skip_special_tokens))
    #     tokens_generated_so_far = re.sub('(@@ )', '', string=filtered_tokens)
    #     tokens_generated_so_far = re.sub('(@@ ?$)', '', string=tokens_generated_so_far)
    #     return ''.join(tokens_generated_so_far)

    def add_from_file(self, f):
        """
        Loads a pre-existing dictionary from a text file and adds its symbols to this instance.
        """
        if isinstance(f, str):
            try:
                with open(f, "r", encoding="utf-8") as fd:
                    self.add_from_file(fd)
            except FileNotFoundError as fnfe:
                raise fnfe
            except UnicodeError:
                raise Exception(f"Incorrect encoding detected in {f}, please rebuild the dataset")
            return

        lines = f.readlines()
        for lineTmp in lines:
            line = lineTmp.strip()
            idx = line.rfind(" ")
            if idx == -1:
                raise ValueError("Incorrect dictionary format, expected '<token> <cnt>'")
            word = line[:idx]
            self.encoder[word] = len(self.encoder)