from torch.nn import DataParallel
from torch.nn.parallel import DistributedDataParallel
import itertools

import threading
import torch
from torch.cuda._utils import _get_device_index
import pdb


def _find_tensors(obj):
    r"""
    Recursively find all tensors contained in the specified object.
    """
    if isinstance(obj, torch.Tensor):
        return [obj]
    if isinstance(obj, (list, tuple)):
        return itertools.chain(*map(_find_tensors, obj))
    if isinstance(obj, dict):
        return itertools.chain(*map(_find_tensors, obj.values()))
    return []



def get_a_var(obj):
    if isinstance(obj, torch.Tensor):
        return obj

    if isinstance(obj, list) or isinstance(obj, tuple):
        for result in map(get_a_var, obj):
            if isinstance(result, torch.Tensor):
                return result
    if isinstance(obj, dict):
        for result in map(get_a_var, obj.items()):
            if isinstance(result, torch.Tensor):
                return result
    return None


class LightningDataParallel(DataParallel):
    """
    Override the forward call in lightning so it goes to training and validation step respectively
    """

    def parallel_apply(self, replicas, inputs, kwargs):
        return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])


class LightningDistributedDataParallel(DistributedDataParallel):
    """
    Override the forward call in lightning so it goes to training and validation step respectively
    """

    def parallel_apply(self, replicas, inputs, kwargs):
        return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])

    def forward(self, *inputs, **kwargs):
        self._sync_params()
        if self.device_ids:
            inputs, kwargs = self.scatter(inputs, kwargs, self.device_ids)
            if len(self.device_ids) == 1:
                # --------------
                # LIGHTNING MOD
                # --------------
                # normal
                # output = self.module(*inputs[0], **kwargs[0])

                # lightning
                if self.module.training:
                    output = self.module.training_step(*inputs[0], **kwargs[0])
                else:
                    output = self.module.validation_step(*inputs[0], **kwargs[0])
            else:
                outputs = self.parallel_apply(self._module_copies[:len(inputs)], inputs, kwargs)
                output = self.gather(outputs, self.output_device)
        else:
            output = self.module(*inputs, **kwargs)

        if torch.is_grad_enabled():
            # We'll return the output object verbatim since it is a freeform
            # object. We need to find any tensors in this object, though,
            # because we need to figure out which parameters were used during
            # this forward pass, to ensure we short circuit reduction for any
            # unused parameters. Only if `find_unused_parameters` is set.
            if self.find_unused_parameters:
                self.reducer.prepare_for_backward(list(_find_tensors(output)))
            else:
                self.reducer.prepare_for_backward([])
        return output


def parallel_apply(modules, inputs, kwargs_tup=None, devices=None):
    r"""Applies each `module` in :attr:`modules` in parallel on arguments
    contained in :attr:`inputs` (positional) and :attr:`kwargs_tup` (keyword)
    on each of :attr:`devices`.

    Args:
        modules (Module): modules to be parallelized
        inputs (tensor): inputs to the modules
        devices (list of int or torch.device): CUDA devices

    :attr:`modules`, :attr:`inputs`, :attr:`kwargs_tup` (if given), and
    :attr:`devices` (if given) should all have same length. Moreover, each
    element of :attr:`inputs` can either be a single object as the only argument
    to a module, or a collection of positional arguments.
    """
    assert len(modules) == len(inputs)
    if kwargs_tup is not None:
        assert len(modules) == len(kwargs_tup)
    else:
        kwargs_tup = ({},) * len(modules)
    if devices is not None:
        assert len(modules) == len(devices)
    else:
        devices = [None] * len(modules)
    devices = list(map(lambda x: _get_device_index(x, True), devices))
    lock = threading.Lock()
    results = {}
    grad_enabled = torch.is_grad_enabled()

    def _worker(i, module, input, kwargs, device=None):
        torch.set_grad_enabled(grad_enabled)
        if device is None:
            device = get_a_var(input).get_device()
        try:
            with torch.cuda.device(device):
                # this also avoids accidental slicing of `input` if it is a Tensor
                if not isinstance(input, (list, tuple)):
                    input = (input,)

                # ---------------
                # CHANGE
                if module.training:
                    output = module.training_step(*input, **kwargs)
                else:
                    output = module.validation_step(*input, **kwargs)
                # ---------------

            with lock:
                results[i] = output
        except Exception as e:
            with lock:
                results[i] = e

    if len(modules) > 1:
        threads = [threading.Thread(target=_worker,
                                    args=(i, module, input, kwargs, device))
                   for i, (module, input, kwargs, device) in
                   enumerate(zip(modules, inputs, kwargs_tup, devices))]

        for thread in threads:
            thread.start()
        for thread in threads:
            thread.join()
    else:
        _worker(0, modules[0], inputs[0], kwargs_tup[0], devices[0])

    outputs = []
    for i in range(len(inputs)):
        output = results[i]
        if isinstance(output, Exception):
            raise output
        outputs.append(output)
    return outputs