# --------------------------------------------------------
# Images Speak in Images: A Generalist Painter for In-Context Visual Learning (https://arxiv.org/abs/2212.02499)
# Github source: https://github.com/baaivision/Painter
# Copyright (c) 2022 Beijing Academy of Artificial Intelligence (BAAI)
# Licensed under The MIT License [see LICENSE for details]
# By Xinlong Wang, Wen Wang
# Based on MAE, BEiT, detectron2, Mask2Former, bts, mmcv, mmdetetection, mmpose, MIRNet, MPRNet, and Uformer codebases
# --------------------------------------------------------'

from typing import Iterator, List, Optional, Union
from collections import Counter
import logging
from operator import itemgetter
from random import choices, sample

import numpy as np

import torch
from torch.utils.data import Dataset, Sampler
from torch.utils.data import DistributedSampler


class DatasetFromSampler(Dataset):
    """Dataset to create indexes from `Sampler`.
    Args:
        sampler: PyTorch sampler
    """

    def __init__(self, sampler: Sampler):
        """Initialisation for DatasetFromSampler."""
        self.sampler = sampler
        self.sampler_list = None

    def __getitem__(self, index: int):
        """Gets element of the dataset.
        Args:
            index: index of the element in the dataset
        Returns:
            Single element by index
        """
        if self.sampler_list is None:
            self.sampler_list = list(self.sampler)
        return self.sampler_list[index]

    def __len__(self) -> int:
        """
        Returns:
            int: length of the dataset
        """
        return len(self.sampler)


class DistributedSamplerWrapper(DistributedSampler):
    """
    Wrapper over `Sampler` for distributed training.
    Allows you to use any sampler in distributed mode.
    It is especially useful in conjunction with
    `torch.nn.parallel.DistributedDataParallel`. In such case, each
    process can pass a DistributedSamplerWrapper instance as a DataLoader
    sampler, and load a subset of subsampled data of the original dataset
    that is exclusive to it.
    .. note::
        Sampler is assumed to be of constant size.
    """

    def __init__(
        self,
        sampler,
        num_replicas: Optional[int] = None,
        rank: Optional[int] = None,
        shuffle: bool = True,
    ):
        """
        Args:
            sampler: Sampler used for subsampling
            num_replicas (int, optional): Number of processes participating in
              distributed training
            rank (int, optional): Rank of the current process
              within ``num_replicas``
            shuffle (bool, optional): If true (default),
              sampler will shuffle the indices
        """
        super(DistributedSamplerWrapper, self).__init__(
            DatasetFromSampler(sampler),
            num_replicas=num_replicas,
            rank=rank,
            shuffle=shuffle,
        )
        self.sampler = sampler

    def __iter__(self):
        """@TODO: Docs. Contribution is welcome."""
        self.dataset = DatasetFromSampler(self.sampler)
        indexes_of_indexes = super().__iter__()
        subsampler_indexes = self.dataset
        return iter(itemgetter(*indexes_of_indexes)(subsampler_indexes))