# --------------------------------------------------------
# Based on BEiT, timm, DINO and DeiT code bases
# https://github.com/microsoft/unilm/tree/master/beit
# https://github.com/rwightman/pytorch-image-models/tree/master/timm
# https://github.com/facebookresearch/deit
# https://github.com/facebookresearch/dino
# --------------------------------------------------------

import os
import pickle
import shutil
import tempfile

import torch
import torch.distributed as dist


def setup_for_distributed(is_master):
    """
    This function disables printing when not in master process
    """
    import builtins as __builtin__
    builtin_print = __builtin__.print

    def print(*args, **kwargs):
        force = kwargs.pop('force', False)
        if is_master or force:
            builtin_print(*args, **kwargs)

    __builtin__.print = print


def is_dist_avail_and_initialized():
    if not dist.is_available():
        return False
    if not dist.is_initialized():
        return False
    return True


def get_world_size():
    if not is_dist_avail_and_initialized():
        return 1
    return dist.get_world_size()


def get_rank():
    if not is_dist_avail_and_initialized():
        return 0
    return dist.get_rank()


def is_main_process():
    return get_rank() == 0


def save_on_master(*args, **kwargs):
    if is_main_process():
        torch.save(*args, **kwargs)


def init_distributed_mode(args):
    if args.dist_on_itp:
        args.rank = int(os.environ['OMPI_COMM_WORLD_RANK'])
        args.world_size = int(os.environ['OMPI_COMM_WORLD_SIZE'])
        args.gpu = int(os.environ['OMPI_COMM_WORLD_LOCAL_RANK'])
        args.dist_url = "tcp://%s:%s" % (os.environ['MASTER_ADDR'], os.environ['MASTER_PORT'])
        os.environ['LOCAL_RANK'] = str(args.gpu)
        os.environ['RANK'] = str(args.rank)
        os.environ['WORLD_SIZE'] = str(args.world_size)
        # ["RANK", "WORLD_SIZE", "MASTER_ADDR", "MASTER_PORT", "LOCAL_RANK"]
    elif 'RANK' in os.environ and 'WORLD_SIZE' in os.environ:
        args.rank = int(os.environ["RANK"])
        args.world_size = int(os.environ['WORLD_SIZE'])
        args.gpu = int(os.environ['LOCAL_RANK'])
    elif 'SLURM_PROCID' in os.environ:
        args.rank = int(os.environ['SLURM_PROCID'])
        args.gpu = args.rank % torch.cuda.device_count()
    else:
        print('Not using distributed mode')
        args.distributed = False
        return

    args.distributed = True

    torch.cuda.set_device(args.gpu)
    args.dist_backend = 'nccl'
    print('| distributed init (rank {}): {}, gpu {}'.format(
        args.rank, args.dist_url, args.gpu), flush=True)
    torch.distributed.init_process_group(backend=args.dist_backend, init_method=args.dist_url,
                                         world_size=args.world_size, rank=args.rank)
    torch.distributed.barrier()
    setup_for_distributed(args.rank == 0)

# # From MMCV
def collect_results_cpu(result_part, size, tmpdir=None):
    """Collect results under cpu mode.

    On cpu mode, this function will save the results on different gpus to
    ``tmpdir`` and collect them by the rank 0 worker.

    Args:
        result_part (list): Result list containing result parts
            to be collected.
        size (int): Size of the results, commonly equal to length of
            the results.
        tmpdir (str | None): temporal directory for collected results to
            store. If set to None, it will create a random temporal directory
            for it.

    Returns:
        list: The collected results.
    """
    rank = get_rank()
    world_size = get_world_size()
    # create a tmp dir if it is not specified
    if tmpdir is None:
        MAX_LEN = 512
        # 32 is whitespace
        dir_tensor = torch.full((MAX_LEN, ),
                                32,
                                dtype=torch.uint8,
                                device='cuda')
        if rank == 0:
            os.makedirs('/tmp/dist_test', exist_ok=True)
            tmpdir = tempfile.mkdtemp(dir='/tmp/dist_test')
            tmpdir = torch.tensor(
                bytearray(tmpdir.encode()), dtype=torch.uint8, device='cuda')
            dir_tensor[:len(tmpdir)] = tmpdir
        dist.broadcast(dir_tensor, 0)
        tmpdir = dir_tensor.cpu().numpy().tobytes().decode().rstrip()
    else:
        os.makedirs(tmpdir, exist_ok=True)
    # dump the part result to the dir
    tmp_file = os.path.join(tmpdir, f'part_{rank}.pkl')
    pickle.dump(result_part, open(str(tmp_file), "wb"))
    dist.barrier()
    # collect all parts
    if rank != 0:
        return None
    else:
        # load results of all parts from tmp dir
        part_list = []
        for i in range(world_size):
            part_file = os.path.join(tmpdir, f'part_{i}.pkl')
            part_result = pickle.load(open(str(part_file), "rb"))
            # When data is severely insufficient, an empty part_result
            # on a certain gpu could makes the overall outputs empty.
            if part_result:
                part_list.append(part_result)
        # sort the results
        ordered_results = []
        for res in zip(*part_list):
            ordered_results.extend(list(res))
        # the dataloader may pad some samples
        ordered_results = ordered_results[:size]
        # remove tmp dir
        shutil.rmtree(tmpdir)
        return ordered_results