image-match/python/py/Lib/site-packages/transformers/models/biogpt/tokenization_biogpt.py

# Copyright 2022 The HuggingFace Team and Microsoft Research AI4Science. All rights reserved.
#
# 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 BioGPT."""

import json
import os

from ...tokenization_python import PreTrainedTokenizer
from ...utils import logging


logger = logging.get_logger(__name__)

VOCAB_FILES_NAMES = {
    "vocab_file": "vocab.json",
    "merges_file": "merges.txt",
}


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
    return pairs


class BioGptTokenizer(PreTrainedTokenizer):
    """
    Construct an FAIRSEQ Transformer tokenizer. Moses tokenization followed by 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`):
            Merges file.
        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.
        bos_token (`str`, *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.
        pad_token (`str`, *optional*, defaults to `"<pad>"`):
            The token used for padding, for example when batching sequences of different lengths.
    """

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

    def __init__(
        self,
        vocab_file,
        merges_file,
        unk_token="<unk>",
        bos_token="<s>",
        eos_token="</s>",
        sep_token="</s>",
        pad_token="<pad>",
        **kwargs,
    ):
        try:
            import sacremoses
        except ImportError:
            raise ImportError(
                "You need to install sacremoses to use BioGptTokenizer. "
                "See https://pypi.org/project/sacremoses/ for installation."
            )

        self.lang = "en"
        self.sm = sacremoses
        # cache of sm.MosesTokenizer instance
        self.cache_moses_tokenizer = {}
        self.cache_moses_detokenizer = {}

        """ Initialisation"""
        with open(vocab_file, encoding="utf-8") as vocab_handle:
            self.encoder = json.load(vocab_handle)
        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()[:2]) for merge in merges]
        self.bpe_ranks = dict(zip(merges, range(len(merges))))
        self.cache = {}

        super().__init__(
            bos_token=bos_token,
            eos_token=eos_token,
            sep_token=sep_token,
            unk_token=unk_token,
            pad_token=pad_token,
            **kwargs,
        )

    @property
    def vocab_size(self):
        """Returns vocab size"""
        return len(self.encoder)

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

    def moses_tokenize(self, text, lang):
        if lang not in self.cache_moses_tokenizer:
            moses_tokenizer = self.sm.MosesTokenizer(lang=lang)
            self.cache_moses_tokenizer[lang] = moses_tokenizer
        return self.cache_moses_tokenizer[lang].tokenize(
            text, aggressive_dash_splits=True, return_str=False, escape=True
        )

    def moses_detokenize(self, tokens, lang):
        if lang not in self.cache_moses_detokenizer:
            moses_detokenizer = self.sm.MosesDetokenizer(lang=lang)
            self.cache_moses_detokenizer[lang] = moses_detokenizer
        return self.cache_moses_detokenizer[lang].detokenize(tokens)

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

        if not pairs:
            return token + "</w>"

        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)
        if word == "\n  </w>":
            word = "\n</w>"
        self.cache[token] = word
        return word

    def _tokenize(self, text, bypass_tokenizer=False):
        """Returns a tokenized string."""
        if bypass_tokenizer:
            text = text.split()
        else:
            text = self.moses_tokenize(text, self.lang)

        split_tokens = []
        for token in text:
            if token:
                split_tokens.extend(list(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."""
        # remove BPE
        tokens = [t.replace(" ", "").replace("</w>", " ") for t in tokens]
        tokens = "".join(tokens).split()
        # detokenize
        text = self.moses_detokenize(tokens, self.lang)
        return text

    def build_inputs_with_special_tokens(
        self, token_ids_0: list[int], token_ids_1: list[int] | None = 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 BioGPT sequence has the following format:

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

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

    def get_special_tokens_mask(
        self, token_ids_0: list[int], token_ids_1: list[int] | None = 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
            )
        # no bos used in fairseq
        if token_ids_1 is not None:
            return [1] + ([0] * len(token_ids_0)) + [1] + ([0] * len(token_ids_1))
        return [1] + ([0] * len(token_ids_0))

    def save_vocabulary(self, save_directory: str, filename_prefix: str | None = None) -> tuple[str]:
        if not os.path.isdir(save_directory):
            logger.error(f"Vocabulary path ({save_directory}) should be a directory")
            return
        vocab_file = os.path.join(
            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
        )
        merge_file = os.path.join(
            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["merges_file"]
        )

        with open(vocab_file, "w", encoding="utf-8") as f:
            f.write(json.dumps(self.encoder, indent=2, sort_keys=True, ensure_ascii=False) + "\n")

        index = 0
        with open(merge_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 {merge_file}: BPE merge indices are not consecutive."
                        " Please check that the tokenizer is not corrupted!"
                    )
                    index = token_index
                writer.write(" ".join(bpe_tokens) + "\n")
                index += 1

        return vocab_file, merge_file

    def __getstate__(self):
        state = self.__dict__.copy()
        state["sm"] = None
        return state

    def __setstate__(self, d):
        self.__dict__ = d

        try:
            import sacremoses
        except ImportError:
            raise ImportError(
                "You need to install sacremoses to use XLMTokenizer. "
                "See https://pypi.org/project/sacremoses/ for installation."
            )

        self.sm = sacremoses


__all__ = ["BioGptTokenizer"]