tokenizer/my_tokenizers.py

import collections
import logging
import os
import re
import codecs
import unicodedata
from typing import List, Optional
from transformers import PreTrainedTokenizer
from SmilesPE.tokenizer import SPE_Tokenizer
import torch

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

class Atomwise_Tokenizer(object):
    """Run atom-level SMILES tokenization"""

    def __init__(self):
        """ Constructs a atom-level Tokenizer.
        """
        # self.regex_pattern = r"(\[[^\]]+]|Br?|Cl?|N|O|S|P|F|I|b|c|n|o|s|p|\(|\)|\.|=|#|-|\+|\\|\/|:|~|@|\?|>>?|\*|\$|\%[0-9]{2}|[0-9])"
        self.regex_pattern = r"(\([^\(\)]{0,4}\)|\[[^\]]+]|Br?|Cl?|N|O|S|P|F|I|b|c|n|o|s|p|\(|\)|\.|=|#|-|\+|\\|\/\/?|:|~|@|\?|>>?|\*|\$|\%[0-9]{2}|[0-9])"

        self.regex = re.compile(self.regex_pattern)

    def tokenize(self, text):
        """ Basic Tokenization of a SMILES.
        """
        tokens = [token for token in self.regex.findall(text)]
        return tokens
    
class SMILES_SPE_Tokenizer(PreTrainedTokenizer):
    r"""
    Constructs a SMILES tokenizer. Based on SMILES Pair Encoding (https://github.com/XinhaoLi74/SmilesPE).
    This tokenizer inherits from :class:`~transformers.PreTrainedTokenizer` which contains most of the methods. Users
    should refer to the superclass for more information regarding methods.
    Args:
        vocab_file (:obj:`string`):
            File containing the vocabulary.
        spe_file (:obj:`string`):
            File containing the trained SMILES Pair Encoding vocabulary.
        unk_token (:obj:`string`, `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 (:obj:`string`, `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 (:obj:`string`, `optional`, defaults to "[PAD]"):
            The token used for padding, for example when batching sequences of different lengths.
        cls_token (:obj:`string`, `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 (:obj:`string`, `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.
    """

    def __init__(self, vocab_file, spe_file,
                unk_token="[UNK]",
                sep_token="[SEP]",
                pad_token="[PAD]",
                cls_token="[CLS]",
                mask_token="[MASK]",
                **kwargs):
        if not os.path.isfile(vocab_file):
            raise ValueError("Can't find a vocabulary file at path '{}'.".format(vocab_file))
        if not os.path.isfile(spe_file):
            raise ValueError("Can't find a SPE vocabulary file at path '{}'.".format(spe_file))

        self.vocab = load_vocab(vocab_file)
        self.spe_vocab = open(spe_file, 'r', encoding='utf-8')
        self.ids_to_tokens = collections.OrderedDict([(ids, tok) for tok, ids in self.vocab.items()])
        self.spe_tokenizer = SPE_Tokenizer(self.spe_vocab)

        super().__init__(
            unk_token=unk_token,
            sep_token=sep_token,
            pad_token=pad_token,
            cls_token=cls_token,
            mask_token=mask_token,
            **kwargs)

    @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):
        return self.spe_tokenizer.tokenize(text).split(' ')

    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))
    
    # changed encode and decode functions
    def encode(self, token_array):
        token_ids = []
        token_ids.append(2)
        for token in token_array:
            id = self._convert_token_to_id(token)
            token_ids.append(id)
        token_ids.append(3)
        token_ids = torch.tensor([token_ids])
        attn_mask = torch.ones_like(token_ids)
        return {'input_ids': token_ids, 'attention_mask': attn_mask}
    
    def decode(self, token_ids, skip_special_tokens=True):
        token_ids = token_ids.squeeze(0).cpu().tolist()
        token_array = []
        for idx in token_ids:
            if idx == 3:  # Stop decoding when token ID 3 is encountered
                break
            if skip_special_tokens and idx in self.all_special_ids:
                continue  
            token = self._convert_id_to_token(idx)
            token_array.append(token)
        sequence = "".join(token_array)
        return sequence
    
    def batch_decode(self, batch_token_ids, skip_special_tokens=True):
        sequences = []
        for token_ids in batch_token_ids:
            sequences.append(self.decode(token_ids))
        return sequences
    
    def get_token_split(self, token_ids):
        if isinstance(token_ids, torch.Tensor):
            token_ids = token_ids.cpu().tolist()
        
        token_array = []
        for seq_ids in token_ids:
            seq_array = []
            for id in seq_ids:
                token = self._convert_id_to_token(id)
                seq_array.append(token)
            token_array.append(seq_array)
            
        return token_array
    
    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)

    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 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 BERT sequence has the following format:
        - single sequence: ``[CLS] X [SEP]``
        - pair of sequences: ``[CLS] A [SEP] B [SEP]``
        Args:
            token_ids_0 (:obj:`List[int]`):
                List of IDs to which the special tokens will be added
            token_ids_1 (:obj:`List[int]`, `optional`, defaults to :obj:`None`):
                Optional second list of IDs for sequence pairs.
        Returns:
            :obj:`List[int]`: list of `input IDs <../glossary.html#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 + 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]:
        """
        Retrieves 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`, defaults to :obj:`None`):
                Optional second list of IDs for sequence pairs.
            already_has_special_tokens (:obj:`bool`, `optional`, defaults to :obj:`False`):
                Set to True if 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:
            if token_ids_1 is not None:
                raise ValueError(
                    "You should not supply a second sequence if the provided sequence of "
                    "ids is already formated with special tokens for the model."
                )
            return list(map(lambda x: 1 if x in [self.sep_token_id, self.cls_token_id] else 0, token_ids_0))

        if token_ids_1 is not None:
            return [1] + ([0] * len(token_ids_0)) + [1] + ([0] * len(token_ids_1)) + [1]
        return [1] + ([0] * len(token_ids_0)) + [1]

    def create_token_type_ids_from_sequences(
        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
    ) -> List[int]:
        """
        Creates a mask from the two sequences passed to be used in a sequence-pair classification task.
        A BERT 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 token_ids_1 is None, only returns the first portion of the mask (0's).
        Args:
            token_ids_0 (:obj:`List[int]`):
                List of ids.
            token_ids_1 (:obj:`List[int]`, `optional`, defaults to :obj:`None`):
                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 = [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) * [0] + len(token_ids_1 + sep) * [1]

    def save_vocabulary(self, vocab_path):
        """
        Save the sentencepiece vocabulary (copy original file) and special tokens file to a directory.
        Args:
            vocab_path (:obj:`str`):
                The directory in which to save the vocabulary.
        Returns:
            :obj:`Tuple(str)`: Paths to the files saved.
        """
        index = 0
        if os.path.isdir(vocab_path):
            vocab_file = os.path.join(vocab_path, VOCAB_FILES_NAMES["vocab_file"])
        else:
            vocab_file = vocab_path
        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(
                        "Saving vocabulary to {}: vocabulary indices are not consecutive."
                        " Please check that the vocabulary is not corrupted!".format(vocab_file)
                    )
                    index = token_index
                writer.write(token + "\n")
                index += 1
        return (vocab_file,)

class SMILES_Atomwise_Tokenizer(PreTrainedTokenizer):
    r"""
    Constructs a SMILES tokenizer. Based on SMILES Pair Encoding (https://github.com/XinhaoLi74/SmilesPE).
    This tokenizer inherits from :class:`~transformers.PreTrainedTokenizer` which contains most of the methods. Users
    should refer to the superclass for more information regarding methods.
    Args:
        vocab_file (:obj:`string`):
            File containing the vocabulary.
        unk_token (:obj:`string`, `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 (:obj:`string`, `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 (:obj:`string`, `optional`, defaults to "[PAD]"):
            The token used for padding, for example when batching sequences of different lengths.
        cls_token (:obj:`string`, `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 (:obj:`string`, `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.
    """

    def __init__(
        self,
        vocab_file,
        unk_token="[UNK]",
        sep_token="[SEP]",
        pad_token="[PAD]",
        cls_token="[CLS]",
        mask_token="[MASK]",
        **kwargs
    ):
        super().__init__(
            unk_token=unk_token,
            sep_token=sep_token,
            pad_token=pad_token,
            cls_token=cls_token,
            mask_token=mask_token,
            **kwargs,
        )

        if not os.path.isfile(vocab_file):
            raise ValueError(
                "Can't find a vocabulary file at path '{}'.".format(vocab_file)
            )
        self.vocab = load_vocab(vocab_file)
        self.ids_to_tokens = collections.OrderedDict([(ids, tok) for tok, ids in self.vocab.items()])
        self.tokenizer = Atomwise_Tokenizer()

    @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):
        return self.tokenizer.tokenize(text)

    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)

    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 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 BERT sequence has the following format:
        - single sequence: ``[CLS] X [SEP]``
        - pair of sequences: ``[CLS] A [SEP] B [SEP]``
        Args:
            token_ids_0 (:obj:`List[int]`):
                List of IDs to which the special tokens will be added
            token_ids_1 (:obj:`List[int]`, `optional`, defaults to :obj:`None`):
                Optional second list of IDs for sequence pairs.
        Returns:
            :obj:`List[int]`: list of `input IDs <../glossary.html#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 + 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]:
        """
        Retrieves 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`, defaults to :obj:`None`):
                Optional second list of IDs for sequence pairs.
            already_has_special_tokens (:obj:`bool`, `optional`, defaults to :obj:`False`):
                Set to True if 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:
            if token_ids_1 is not None:
                raise ValueError(
                    "You should not supply a second sequence if the provided sequence of "
                    "ids is already formated with special tokens for the model."
                )
            return list(map(lambda x: 1 if x in [self.sep_token_id, self.cls_token_id] else 0, token_ids_0))

        if token_ids_1 is not None:
            return [1] + ([0] * len(token_ids_0)) + [1] + ([0] * len(token_ids_1)) + [1]
        return [1] + ([0] * len(token_ids_0)) + [1]

    def create_token_type_ids_from_sequences(
        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
    ) -> List[int]:
        """
        Creates a mask from the two sequences passed to be used in a sequence-pair classification task.
        A BERT 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 token_ids_1 is None, only returns the first portion of the mask (0's).
        Args:
            token_ids_0 (:obj:`List[int]`):
                List of ids.
            token_ids_1 (:obj:`List[int]`, `optional`, defaults to :obj:`None`):
                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 = [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) * [0] + len(token_ids_1 + sep) * [1]

    def save_vocabulary(self, vocab_path):
        """
        Save the sentencepiece vocabulary (copy original file) and special tokens file to a directory.
        Args:
            vocab_path (:obj:`str`):
                The directory in which to save the vocabulary.
        Returns:
            :obj:`Tuple(str)`: Paths to the files saved.
        """
        index = 0
        if os.path.isdir(vocab_path):
            vocab_file = os.path.join(vocab_path, VOCAB_FILES_NAMES["vocab_file"])
        else:
            vocab_file = vocab_path
        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(
                        "Saving vocabulary to {}: vocabulary indices are not consecutive."
                        " Please check that the vocabulary is not corrupted!".format(vocab_file)
                    )
                    index = token_index
                writer.write(token + "\n")
                index += 1
        return (vocab_file,)