import copy
from typing import Optional

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch import Tensor


class MLP(nn.Module):
    """ Very simple multi-layer perceptron (also called FFN)"""

    def __init__(self, input_dim, hidden_dim, output_dim, num_layers):
        super().__init__()
        self.num_layers = num_layers
        h = [hidden_dim] * (num_layers - 1)
        self.layers = nn.ModuleList(
            nn.Linear(n, k) for n, k in zip([input_dim] + h, h + [output_dim]))

    def forward(self, x):
        for i, layer in enumerate(self.layers):
            x = F.relu(layer(x)) if i < self.num_layers - 1 else layer(x)
        return x


class Mlp(nn.Module):
    """ Multilayer perceptron.
    Parameters:
        act_layer: Specify the activate function, default use nn.GELU.
    """

    def __init__(self,
                 in_features,
                 hidden_features=None,
                 out_features=None,
                 act_layer=nn.GELU,
                 drop=0.):
        super().__init__()
        out_features = out_features or in_features
        hidden_features = hidden_features or in_features
        self.fc1 = nn.Linear(in_features, hidden_features)
        self.act = act_layer()
        self.fc2 = nn.Linear(hidden_features, out_features)
        self.drop = nn.Dropout(drop)

    def forward(self, x):
        x = self.fc1(x)
        x = self.act(x)
        x = self.drop(x)
        x = self.fc2(x)
        x = self.drop(x)
        return x


def drop_path(x, drop_prob: float = 0., training: bool = False):
    if drop_prob == 0. or not training:
        return x
    keep_prob = 1 - drop_prob
    shape = (x.shape[0], ) + (1, ) * (
        x.ndim - 1)  # work with diff dim tensors, not just 2D ConvNets
    random_tensor = keep_prob + torch.rand(
        shape, dtype=x.dtype, device=x.device)
    random_tensor.floor_()  # binarize
    output = x.div(keep_prob) * random_tensor
    return output


class DropPath(nn.Module):
    """Drop paths (Stochastic Depth) per sample  (when applied in main path of residual blocks).
    """

    def __init__(self, drop_prob=None):
        super(DropPath, self).__init__()
        self.drop_prob = drop_prob

    def forward(self, x):
        return drop_path(x, self.drop_prob, self.training)

    def extra_repr(self):
        return 'p={}'.format(self.drop_prob)


class TransformerEncoder(nn.Module):

    def __init__(self,
                 encoder_layer,
                 num_layers,
                 norm=None,
                 d_model=256,
                 query_scale_type=None):
        super().__init__()
        self.layers = _get_clones(encoder_layer, num_layers)
        self.num_layers = num_layers
        self.query_scale_type = query_scale_type
        if query_scale_type == 'cond_elewise':
            self.query_scale = MLP(d_model, d_model, d_model, 2)
        self.norm = norm

    def forward(self,
                src,
                mask: Optional[Tensor] = None,
                src_key_padding_mask: Optional[Tensor] = None,
                pos: Optional[Tensor] = None):
        output = src

        for layer_id, layer in enumerate(self.layers):
            # rescale the content and pos sim
            if self.query_scale_type == 'cond_elewise':
                pos_scales = self.query_scale(output)
            else:
                pos_scales = 1
            output = layer(
                output,
                src_mask=mask,
                src_key_padding_mask=src_key_padding_mask,
                pos=pos * pos_scales)

        if self.norm is not None:
            output = self.norm(output)

        return output


class TransformerEncoderLayer(nn.Module):

    def __init__(self,
                 d_model,
                 nhead,
                 dim_feedforward=2048,
                 dropout=0.1,
                 activation='relu',
                 normalize_before=False):
        super().__init__()
        self.self_attn = nn.MultiheadAttention(d_model, nhead, dropout=dropout)
        # Implementation of Feedforward model
        self.linear1 = nn.Linear(d_model, dim_feedforward)
        self.dropout = nn.Dropout(dropout)
        self.linear2 = nn.Linear(dim_feedforward, d_model)

        self.norm1 = nn.LayerNorm(d_model)
        self.norm2 = nn.LayerNorm(d_model)
        self.dropout1 = nn.Dropout(dropout)
        self.dropout2 = nn.Dropout(dropout)

        self.activation = _get_activation_fn(activation)
        self.normalize_before = normalize_before

    def with_pos_embed(self, tensor, pos: Optional[Tensor]):
        return tensor if pos is None else tensor + pos

    def forward(self,
                src,
                src_mask: Optional[Tensor] = None,
                src_key_padding_mask: Optional[Tensor] = None,
                pos: Optional[Tensor] = None):
        q = k = self.with_pos_embed(src, pos)
        src2 = self.self_attn(
            q,
            k,
            value=src,
            attn_mask=src_mask,
            key_padding_mask=src_key_padding_mask)[0]
        src = src + self.dropout1(src2)
        src = self.norm1(src)
        src2 = self.linear2(self.dropout(self.activation(self.linear1(src))))
        src = src + self.dropout2(src2)
        src = self.norm2(src)
        return src


def _get_clones(module, N, layer_share=False):
    if layer_share:
        return nn.ModuleList([module for i in range(N)])
    else:
        return nn.ModuleList([copy.deepcopy(module) for i in range(N)])


def _get_activation_fn(activation):
    """Return an activation function given a string"""
    if activation == 'relu':
        return F.relu
    if activation == 'gelu':
        return F.gelu
    if activation == 'glu':
        return F.glu
    if activation == 'prelu':
        return nn.PReLU()
    if activation == 'selu':
        return F.selu
    raise RuntimeError(F'activation should be relu/gelu, not {activation}.')