# coding=utf-8
# Copyright 2020 The HuggingFace Team 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.
"""
Fine-tuning the library models for masked language modeling (BERT, ALBERT, RoBERTa...) with whole word masking on a
text file or a dataset.

Here is the full list of checkpoints on the hub that can be fine-tuned by this script:
https://huggingface.co/models?filter=masked-lm
"""
# You can also adapt this script on your own masked language modeling task. Pointers for this are left as comments.

import json
import logging
import math
import os
import sys
from dataclasses import dataclass, field
from typing import Optional

from datasets import Dataset, load_dataset

import transformers
from transformers import (
    CONFIG_MAPPING,
    MODEL_FOR_MASKED_LM_MAPPING,
    AutoConfig,
    AutoModelForMaskedLM,
    AutoTokenizer,
    DataCollatorForWholeWordMask,
    HfArgumentParser,
    Trainer,
    TrainingArguments,
    set_seed,
)
from transformers.trainer_utils import is_main_process


logger = logging.getLogger(__name__)
MODEL_CONFIG_CLASSES = list(MODEL_FOR_MASKED_LM_MAPPING.keys())
MODEL_TYPES = tuple(conf.model_type for conf in MODEL_CONFIG_CLASSES)


@dataclass
class ModelArguments:
    """
    Arguments pertaining to which model/config/tokenizer we are going to fine-tune, or train from scratch.
    """

    model_name_or_path: Optional[str] = field(
        default=None,
        metadata={
            "help": "The model checkpoint for weights initialization."
            "Don't set if you want to train a model from scratch."
        },
    )
    model_type: Optional[str] = field(
        default=None,
        metadata={"help": "If training from scratch, pass a model type from the list: " + ", ".join(MODEL_TYPES)},
    )
    config_name: Optional[str] = field(
        default=None, metadata={"help": "Pretrained config name or path if not the same as model_name"}
    )
    tokenizer_name: Optional[str] = field(
        default=None, metadata={"help": "Pretrained tokenizer name or path if not the same as model_name"}
    )
    cache_dir: Optional[str] = field(
        default=None, metadata={"help": "Where do you want to store the pretrained models downloaded from s3"}
    )
    use_fast_tokenizer: bool = field(
        default=True,
        metadata={"help": "Whether to use one of the fast tokenizer (backed by the tokenizers library) or not."},
    )


@dataclass
class DataTrainingArguments:
    """
    Arguments pertaining to what data we are going to input our model for training and eval.
    """

    train_file: Optional[str] = field(default=None, metadata={"help": "The input training data file (a text file)."})
    validation_file: Optional[str] = field(
        default=None,
        metadata={"help": "An optional input evaluation data file to evaluate the perplexity on (a text file)."},
    )
    train_ref_file: Optional[str] = field(
        default=None,
        metadata={"help": "An optional input train ref data file for whole word masking in Chinese."},
    )
    validation_ref_file: Optional[str] = field(
        default=None,
        metadata={"help": "An optional input validation ref data file for whole word masking in Chinese."},
    )
    overwrite_cache: bool = field(
        default=False, metadata={"help": "Overwrite the cached training and evaluation sets"}
    )
    max_seq_length: Optional[int] = field(
        default=None,
        metadata={
            "help": "The maximum total input sequence length after tokenization. Sequences longer "
            "than this will be truncated. Default to the max input length of the model."
        },
    )
    preprocessing_num_workers: Optional[int] = field(
        default=None,
        metadata={"help": "The number of processes to use for the preprocessing."},
    )
    mlm_probability: float = field(
        default=0.15, metadata={"help": "Ratio of tokens to mask for masked language modeling loss"}
    )
    pad_to_max_length: bool = field(
        default=False,
        metadata={
            "help": "Whether to pad all samples to `max_seq_length`. "
            "If False, will pad the samples dynamically when batching to the maximum length in the batch."
        },
    )

    def __post_init__(self):
        if self.train_file is not None:
            extension = self.train_file.split(".")[-1]
            assert extension in ["csv", "json", "txt"], "`train_file` should be a csv, a json or a txt file."
        if self.validation_file is not None:
            extension = self.validation_file.split(".")[-1]
            assert extension in ["csv", "json", "txt"], "`validation_file` should be a csv, a json or a txt file."


def add_chinese_references(dataset, ref_file):
    with open(ref_file, "r", encoding="utf-8") as f:
        refs = [json.loads(line) for line in f.read().splitlines() if (len(line) > 0 and not line.isspace())]
    assert len(dataset) == len(refs)

    dataset_dict = {c: dataset[c] for c in dataset.column_names}
    dataset_dict["chinese_ref"] = refs
    return Dataset.from_dict(dataset_dict)


def main():
    # See all possible arguments in src/transformers/training_args.py
    # or by passing the --help flag to this script.
    # We now keep distinct sets of args, for a cleaner separation of concerns.

    parser = HfArgumentParser((ModelArguments, DataTrainingArguments, TrainingArguments))
    if len(sys.argv) == 2 and sys.argv[1].endswith(".json"):
        # If we pass only one argument to the script and it's the path to a json file,
        # let's parse it to get our arguments.
        model_args, data_args, training_args = parser.parse_json_file(json_file=os.path.abspath(sys.argv[1]))
    else:
        model_args, data_args, training_args = parser.parse_args_into_dataclasses()

    if (
        os.path.exists(training_args.output_dir)
        and os.listdir(training_args.output_dir)
        and training_args.do_train
        and not training_args.overwrite_output_dir
    ):
        raise ValueError(
            f"Output directory ({training_args.output_dir}) already exists and is not empty."
            "Use --overwrite_output_dir to overcome."
        )

    # Setup logging
    logging.basicConfig(
        format="%(asctime)s - %(levelname)s - %(name)s -   %(message)s",
        datefmt="%m/%d/%Y %H:%M:%S",
        level=logging.INFO if is_main_process(training_args.local_rank) else logging.WARN,
    )

    # Log on each process the small summary:
    logger.warning(
        f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}"
        + f"distributed training: {bool(training_args.local_rank != -1)}, 16-bits training: {training_args.fp16}"
    )
    # Set the verbosity to info of the Transformers logger (on main process only):
    if is_main_process(training_args.local_rank):
        transformers.utils.logging.set_verbosity_info()
    logger.info("Training/evaluation parameters %s", training_args)

    # Set seed before initializing model.
    set_seed(training_args.seed)

    # Get the datasets: you can either provide your own CSV/JSON/TXT training and evaluation files (see below)
    # or just provide the name of one of the public datasets available on the hub at https://huggingface.co/datasets/
    # (the dataset will be downloaded automatically from the datasets Hub).
    #
    # For CSV/JSON files, this script will use the column called 'text' or the first column if no column called
    # 'text' is found. You can easily tweak this behavior (see below).
    #
    # In distributed training, the load_dataset function guarantee that only one local process can concurrently
    # download the dataset.
    data_files = {}
    if data_args.train_file is not None:
        data_files["train"] = data_args.train_file
    if data_args.validation_file is not None:
        data_files["validation"] = data_args.validation_file
    extension = data_args.train_file.split(".")[-1]
    if extension == "txt":
        extension = "text"
    datasets = load_dataset(extension, data_files=data_files)
    # See more about loading any type of standard or custom dataset (from files, python dict, pandas DataFrame, etc) at
    # https://huggingface.co/docs/datasets/loading_datasets.html.

    # Load pretrained model and tokenizer
    #
    # Distributed training:
    # The .from_pretrained methods guarantee that only one local process can concurrently
    # download model & vocab.
    if model_args.config_name:
        config = AutoConfig.from_pretrained(model_args.config_name, cache_dir=model_args.cache_dir)
    elif model_args.model_name_or_path:
        config = AutoConfig.from_pretrained(model_args.model_name_or_path, cache_dir=model_args.cache_dir)
    else:
        config = CONFIG_MAPPING[model_args.model_type]()
        logger.warning("You are instantiating a new config instance from scratch.")

    if model_args.tokenizer_name:
        tokenizer = AutoTokenizer.from_pretrained(
            model_args.tokenizer_name, cache_dir=model_args.cache_dir, use_fast=model_args.use_fast_tokenizer
        )
    elif model_args.model_name_or_path:
        tokenizer = AutoTokenizer.from_pretrained(
            model_args.model_name_or_path, cache_dir=model_args.cache_dir, use_fast=model_args.use_fast_tokenizer
        )
    else:
        raise ValueError(
            "You are instantiating a new tokenizer from scratch. This is not supported by this script."
            "You can do it from another script, save it, and load it from here, using --tokenizer_name."
        )

    if model_args.model_name_or_path:
        model = AutoModelForMaskedLM.from_pretrained(
            model_args.model_name_or_path,
            from_tf=bool(".ckpt" in model_args.model_name_or_path),
            config=config,
            cache_dir=model_args.cache_dir,
        )
    else:
        logger.info("Training new model from scratch")
        model = AutoModelForMaskedLM.from_config(config)

    model.resize_token_embeddings(len(tokenizer))

    # Preprocessing the datasets.
    # First we tokenize all the texts.
    if training_args.do_train:
        column_names = datasets["train"].column_names
    else:
        column_names = datasets["validation"].column_names
    text_column_name = "text" if "text" in column_names else column_names[0]

    padding = "max_length" if data_args.pad_to_max_length else False

    def tokenize_function(examples):
        # Remove empty lines
        examples["text"] = [line for line in examples["text"] if len(line) > 0 and not line.isspace()]
        return tokenizer(examples["text"], padding=padding, truncation=True, max_length=data_args.max_seq_length)

    tokenized_datasets = datasets.map(
        tokenize_function,
        batched=True,
        num_proc=data_args.preprocessing_num_workers,
        remove_columns=[text_column_name],
        load_from_cache_file=not data_args.overwrite_cache,
    )

    # Add the chinese references if provided
    if data_args.train_ref_file is not None:
        tokenized_datasets["train"] = add_chinese_references(tokenized_datasets["train"], data_args.train_ref_file)
    if data_args.valid_ref_file is not None:
        tokenized_datasets["validation"] = add_chinese_references(
            tokenized_datasets["validation"], data_args.validation_ref_file
        )

    # Data collator
    # This one will take care of randomly masking the tokens.
    data_collator = DataCollatorForWholeWordMask(tokenizer=tokenizer, mlm_probability=data_args.mlm_probability)

    # Initialize our Trainer
    trainer = Trainer(
        model=model,
        args=training_args,
        train_dataset=tokenized_datasets["train"] if training_args.do_train else None,
        eval_dataset=tokenized_datasets["validation"] if training_args.do_eval else None,
        tokenizer=tokenizer,
        data_collator=data_collator,
    )

    # Training
    if training_args.do_train:
        trainer.train(
            model_path=model_args.model_name_or_path if os.path.isdir(model_args.model_name_or_path) else None
        )
        trainer.save_model()  # Saves the tokenizer too for easy upload

    # Evaluation
    results = {}
    if training_args.do_eval:
        logger.info("*** Evaluate ***")

        eval_output = trainer.evaluate()

        perplexity = math.exp(eval_output["eval_loss"])
        results["perplexity"] = perplexity

        output_eval_file = os.path.join(training_args.output_dir, "eval_results_mlm_wwm.txt")
        if trainer.is_world_process_zero():
            with open(output_eval_file, "w") as writer:
                logger.info("***** Eval results *****")
                for key, value in results.items():
                    logger.info(f"  {key} = {value}")
                    writer.write(f"{key} = {value}\n")

    return results


def _mp_fn(index):
    # For xla_spawn (TPUs)
    main()


if __name__ == "__main__":
    main()