from typing import Optional

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


def get_sinusoid_encoding_table(n_position, d_hid, padding_idx=None):
    ''' Sinusoid position encoding table '''
    def cal_angle(position, hid_idx):
        return position / np.power(10000, 2 * (hid_idx // 2) / d_hid)

    def get_posi_angle_vec(position):
        return [cal_angle(position, hid_j) for hid_j in range(d_hid)]

    sinusoid_table = np.array([get_posi_angle_vec(pos_i) for pos_i in range(n_position)])

    sinusoid_table[:, 0::2] = np.sin(sinusoid_table[:, 0::2])  # dim 2i
    sinusoid_table[:, 1::2] = np.cos(sinusoid_table[:, 1::2])  # dim 2i+1

    if padding_idx is not None:
        # zero vector for padding dimension
        sinusoid_table[padding_idx] = 0.

    return torch.FloatTensor(sinusoid_table)


class ScaledDotProductAttention(nn.Module):
    ''' Scaled Dot-Product Attention '''
    def __init__(self, temperature):
        super().__init__()
        self.temperature = temperature
        self.softmax = nn.Softmax(dim=2)

    def forward(self, q, k, v, mask=None):

        attn = torch.bmm(q, k.transpose(1, 2))
        attn = attn / self.temperature
        if mask is not None:
            attn = attn.masked_fill(mask, -np.inf)

        attn = self.softmax(attn)
        output = torch.bmm(attn, v)

        return output, attn


class MultiHeadAttention(nn.Module):
    ''' Multi-Head Attention module '''
    def __init__(self, n_head, d_model, d_k, d_v, dropout=0.1):
        super().__init__()

        self.n_head = n_head
        self.d_k = d_k
        self.d_v = d_v

        self.w_qs = nn.Linear(d_model, n_head * d_k)
        self.w_ks = nn.Linear(d_model, n_head * d_k)
        self.w_vs = nn.Linear(d_model, n_head * d_v)

        self.attention = ScaledDotProductAttention(temperature=np.power(d_k, 0.5))
        self.layer_norm = nn.LayerNorm(d_model)

        self.fc = nn.Linear(n_head * d_v, d_model)

        self.dropout = nn.Dropout(dropout)

    def forward(self, q: Tensor, k: Tensor, v: Tensor, mask: Optional[Tensor] = None):

        d_k, d_v, n_head = self.d_k, self.d_v, self.n_head

        sz_b, len_q, _ = q.size()
        sz_b, len_k, _ = k.size()
        sz_b, len_v, _ = v.size()

        residual = q

        q = self.w_qs(q).view(sz_b, len_q, n_head, d_k)
        k = self.w_ks(k).view(sz_b, len_k, n_head, d_k)
        v = self.w_vs(v).view(sz_b, len_v, n_head, d_v)
        q = q.permute(2, 0, 1, 3).contiguous().view(-1, len_q, d_k)  # (n*b) x lq x dk
        k = k.permute(2, 0, 1, 3).contiguous().view(-1, len_k, d_k)  # (n*b) x lk x dk
        v = v.permute(2, 0, 1, 3).contiguous().view(-1, len_v, d_v)  # (n*b) x lv x dv

        mask = mask.repeat(n_head, 1, 1).to(q.device)
        output, attn = self.attention(q, k, v, mask=mask)

        output = output.view(n_head, sz_b, len_q, d_v)
        output = output.permute(1, 2, 0, 3).contiguous().view(sz_b, len_q, -1)  # b x lq x (n*dv)

        output = self.dropout(self.fc(output))
        output = self.layer_norm(output + residual)

        return output, attn


class PositionwiseFeedForward(nn.Module):
    ''' A two-feed-forward-layer module '''
    def __init__(self, d_in: int, d_hid: int, kernel_size: int = 9, dropout: float = 0.1):
        super().__init__()

        # Use Conv1D
        # position-wise
        self.w_1 = nn.Conv1d(d_in, d_hid, kernel_size=kernel_size, padding=(kernel_size - 1) // 2)
        # position-wise
        self.w_2 = nn.Conv1d(d_hid, d_in, kernel_size=1, padding=0)

        self.layer_norm = nn.LayerNorm(d_in)
        self.dropout = nn.Dropout(dropout)

    def forward(self, x: Tensor):
        residual = x
        output = x.transpose(1, 2)
        output = self.w_2(F.relu(self.w_1(output)))
        output = output.transpose(1, 2)
        output = self.dropout(output)
        output = self.layer_norm(output + residual)

        return output


class FFTBlock(torch.nn.Module):
    """FFT Block"""
    def __init__(self, d_model: int, d_inner: int, n_head: int, d_k: int, d_v: int, dropout: float = 0.1):
        super(FFTBlock, self).__init__()

        self.slf_attn = MultiHeadAttention(n_head, d_model, d_k, d_v, dropout=dropout)
        self.pos_ffn = PositionwiseFeedForward(d_model, d_inner, dropout=dropout)

    def forward(self, enc_input: Tensor, mask: Optional[Tensor] = None, attn_mask: Optional[Tensor] = None):

        enc_output, enc_slf_attn = self.slf_attn(enc_input, enc_input, enc_input, mask=attn_mask)
        enc_output = enc_output.masked_fill(mask.unsqueeze(-1), 0)

        enc_output = self.pos_ffn(enc_output)
        enc_output = enc_output.masked_fill(mask.unsqueeze(-1), 0)

        return enc_output, enc_slf_attn


class ConvNorm(torch.nn.Module):
    def __init__(self,
                 in_channels,
                 out_channels,
                 kernel_size=1,
                 stride=1,
                 padding=None,
                 dilation=1,
                 bias=True,
                 w_init_gain='linear'):
        super(ConvNorm, self).__init__()

        if padding is None:
            assert (kernel_size % 2 == 1)
            padding = int(dilation * (kernel_size - 1) / 2)

        self.conv = torch.nn.Conv1d(in_channels,
                                    out_channels,
                                    kernel_size=kernel_size,
                                    stride=stride,
                                    padding=padding,
                                    dilation=dilation,
                                    bias=bias)

    def forward(self, signal):
        conv_signal = self.conv(signal)

        return conv_signal