import copy
import math

import numpy as np
import scipy
import torch
from torch import nn
from torch.nn import AvgPool1d, Conv1d, Conv2d, ConvTranspose1d
from torch.nn import functional as F
from torch.nn.utils import remove_weight_norm, weight_norm

from tools import commons
from tools.commons import get_padding, init_weights
from tools.transforms import piecewise_rational_quadratic_transform


LRELU_SLOPE = 0.1


class LayerNorm(nn.Module):
    def __init__(self, channels, eps=1e-5):
        super().__init__()
        self.channels = channels
        self.eps = eps

        self.gamma = nn.Parameter(torch.ones(channels))
        self.beta = nn.Parameter(torch.zeros(channels))

    def forward(self, x):
        x = x.transpose(1, -1).contiguous()
        x = F.layer_norm(x, (self.channels,), self.gamma, self.beta, self.eps)
        return x.transpose(1, -1).contiguous()


class ConvReluNorm(nn.Module):
    def __init__(
        self,
        in_channels,
        hidden_channels,
        out_channels,
        kernel_size,
        n_layers,
        p_dropout,
    ):
        super().__init__()
        self.in_channels = in_channels
        self.hidden_channels = hidden_channels
        self.out_channels = out_channels
        self.kernel_size = kernel_size
        self.n_layers = n_layers
        self.p_dropout = p_dropout
        assert n_layers > 1, "Number of layers should be larger than 0."

        self.conv_layers = nn.ModuleList()
        self.norm_layers = nn.ModuleList()
        self.conv_layers.append(
            nn.Conv1d(
                in_channels, hidden_channels, kernel_size, padding=kernel_size // 2
            )
        )
        self.norm_layers.append(LayerNorm(hidden_channels))
        self.relu_drop = nn.Sequential(nn.ReLU(), nn.Dropout(p_dropout))
        for _ in range(n_layers - 1):
            self.conv_layers.append(
                nn.Conv1d(
                    hidden_channels,
                    hidden_channels,
                    kernel_size,
                    padding=kernel_size // 2,
                )
            )
            self.norm_layers.append(LayerNorm(hidden_channels))
        self.proj = nn.Conv1d(hidden_channels, out_channels, 1)
        self.proj.weight.data.zero_()
        self.proj.bias.data.zero_()

    def forward(self, x, x_mask):
        x_org = x
        for i in range(self.n_layers):
            x = self.conv_layers[i](x * x_mask)
            x = self.norm_layers[i](x)
            x = self.relu_drop(x)
        x = x_org + self.proj(x)
        return x * x_mask


class DDSConv(nn.Module):
    """
    Dialted and Depth-Separable Convolution
    """

    def __init__(self, channels, kernel_size, n_layers, p_dropout=0.0):
        super().__init__()
        self.channels = channels
        self.kernel_size = kernel_size
        self.n_layers = n_layers
        self.p_dropout = p_dropout

        self.drop = nn.Dropout(p_dropout)
        self.convs_sep = nn.ModuleList()
        self.convs_1x1 = nn.ModuleList()
        self.norms_2 = nn.ModuleList()
        for i in range(n_layers):
            dilation = kernel_size**i

            padding = (kernel_size * dilation - dilation) // 2
            conv = nn.Conv1d(
                channels,
                channels,
                kernel_size,
                groups=channels,
                dilation=dilation,
                padding=padding,
            )
            self.convs_sep.append(conv)
            self.convs_1x1.append(nn.Conv1d(channels, channels, 1))
            self.norms_2.append(LayerNorm(channels))

    def forward(self, x, x_mask, g=None):
        if g is not None:
            x = x + g
        for i in range(self.n_layers):
            y = self.convs_sep[i](x * x_mask)
            y = F.gelu(y)
            y = self.convs_1x1[i](y)
            y = self.norms_2[i](y)
            y = F.gelu(y)
            y = self.drop(y)
            x = x + y
        return x * x_mask


class WN(torch.nn.Module):
    def __init__(
        self,
        hidden_channels,
        kernel_size,
        dilation_rate,
        n_layers,
        gin_channels=0,
        p_dropout=0,
    ):
        super(WN, self).__init__()
        assert kernel_size % 2 == 1
        self.hidden_channels = hidden_channels
        self.kernel_size = (kernel_size,)
        self.dilation_rate = dilation_rate
        self.n_layers = n_layers
        self.gin_channels = gin_channels
        self.p_dropout = p_dropout

        self.in_layers = torch.nn.ModuleList()
        self.res_skip_layers = torch.nn.ModuleList()
        self.drop = nn.Dropout(p_dropout)

        if gin_channels != 0:
            cond_layer = torch.nn.Conv1d(
                gin_channels, 2 * hidden_channels * n_layers, 1
            )
            self.cond_layer = torch.nn.utils.weight_norm(cond_layer, name="weight")

        for i in range(n_layers):
            dilation = dilation_rate**i
            padding = int((kernel_size * dilation - dilation) / 2)

            in_layer = Conv1d(
                hidden_channels,
                2 * hidden_channels,
                kernel_size,
                padding=padding,
                dilation=dilation,
            )
            in_layer = torch.nn.utils.weight_norm(in_layer, name="weight")
            self.in_layers.append(in_layer)

            # last one is not necessary
            if i < n_layers - 1:
                res_skip_channels = 2 * hidden_channels
            else:
                res_skip_channels = hidden_channels

            res_skip_layer = torch.nn.Conv1d(hidden_channels, res_skip_channels, 1)
            res_skip_layer = torch.nn.utils.weight_norm(res_skip_layer, name="weight")
            self.res_skip_layers.append(res_skip_layer)

    def forward(self, x, x_mask, g=None, **kwargs):
        output = torch.zeros_like(x)
        n_channels_tensor = torch.IntTensor([self.hidden_channels])

        if g is not None:
            g = self.cond_layer(g)

        for i in range(self.n_layers):
            x_in = self.in_layers[i](x)
            if g is not None:
                cond_offset = i * 2 * self.hidden_channels
                g_l = g[:, cond_offset : cond_offset + 2 * self.hidden_channels, :]
            else:
                g_l = torch.zeros_like(x_in)

            acts = commons.fused_add_tanh_sigmoid_multiply(x_in, g_l, n_channels_tensor)
            acts = self.drop(acts)

            res_skip_acts = self.res_skip_layers[i](acts)
            if i < self.n_layers - 1:
                res_acts = res_skip_acts[:, : self.hidden_channels, :]
                x = (x + res_acts) * x_mask
                output = output + res_skip_acts[:, self.hidden_channels :, :]
            else:
                output = output + res_skip_acts
        return output * x_mask

    def remove_weight_norm(self):
        if self.gin_channels != 0:
            torch.nn.utils.remove_weight_norm(self.cond_layer)
        for l in self.in_layers:
            torch.nn.utils.remove_weight_norm(l)
        for l in self.res_skip_layers:
            torch.nn.utils.remove_weight_norm(l)


class Log(nn.Module):
    def forward(self, x, x_mask, reverse=False, **kwargs):
        if not reverse:
            y = torch.log(torch.clamp_min(x, 1e-5)) * x_mask
            logdet = torch.sum(-y, [1, 2])
            return y, logdet
        else:
            x = torch.exp(x) * x_mask
            return x


class Flip(nn.Module):
    def forward(self, x, *args, reverse=False, **kwargs):
        x = torch.flip(x, [1])
        if not reverse:
            logdet = torch.zeros(x.size(0)).to(dtype=x.dtype, device=x.device)
            return x, logdet
        else:
            return x


class ElementwiseAffine(nn.Module):
    def __init__(self, channels):
        super().__init__()
        self.channels = channels
        self.m = nn.Parameter(torch.zeros(channels, 1))
        self.logs = nn.Parameter(torch.zeros(channels, 1))

    def forward(self, x, x_mask, reverse=False, **kwargs):
        if not reverse:
            y = self.m + torch.exp(self.logs) * x
            y = y * x_mask
            logdet = torch.sum(self.logs * x_mask, [1, 2])
            return y, logdet
        else:
            x = (x - self.m) * torch.exp(-self.logs) * x_mask
            return x


class ResidualCouplingLayer(nn.Module):
    def __init__(
        self,
        channels,
        hidden_channels,
        kernel_size,
        dilation_rate,
        n_layers,
        p_dropout=0,
        gin_channels=0,
        mean_only=False,
    ):
        assert channels % 2 == 0, "channels should be divisible by 2"
        super().__init__()
        self.channels = channels
        self.hidden_channels = hidden_channels
        self.kernel_size = kernel_size
        self.dilation_rate = dilation_rate
        self.n_layers = n_layers
        self.half_channels = channels // 2
        self.mean_only = mean_only

        self.pre = nn.Conv1d(self.half_channels, hidden_channels, 1)
        self.enc = WN(
            hidden_channels,
            kernel_size,
            dilation_rate,
            n_layers,
            p_dropout=p_dropout,
            gin_channels=gin_channels,
        )
        self.post = nn.Conv1d(hidden_channels, self.half_channels * (2 - mean_only), 1)
        self.post.weight.data.zero_()
        self.post.bias.data.zero_()

    def forward(self, x, x_mask, g=None, reverse=False):
        x0, x1 = torch.split(x, [self.half_channels] * 2, 1)
        h = self.pre(x0) * x_mask
        h = self.enc(h, x_mask, g=g)
        stats = self.post(h) * x_mask
        if not self.mean_only:
            m, logs = torch.split(stats, [self.half_channels] * 2, 1)
        else:
            m = stats
            logs = torch.zeros_like(m)

        if not reverse:
            x1 = m + x1 * torch.exp(logs) * x_mask
            x = torch.cat([x0, x1], 1)
            logdet = torch.sum(logs, [1, 2])
            return x, logdet
        else:
            x1 = (x1 - m) * torch.exp(-logs) * x_mask
            x = torch.cat([x0, x1], 1)
            return x


class ConvFlow(nn.Module):
    def __init__(
        self,
        in_channels,
        filter_channels,
        kernel_size,
        n_layers,
        num_bins=10,
        tail_bound=5.0,
    ):
        super().__init__()
        self.in_channels = in_channels
        self.filter_channels = filter_channels
        self.kernel_size = kernel_size
        self.n_layers = n_layers
        self.num_bins = num_bins
        self.tail_bound = tail_bound
        self.half_channels = in_channels // 2

        self.pre = nn.Conv1d(self.half_channels, filter_channels, 1)
        self.convs = DDSConv(filter_channels, kernel_size, n_layers, p_dropout=0.0)
        self.proj = nn.Conv1d(
            filter_channels, self.half_channels * (num_bins * 3 - 1), 1
        )
        self.proj.weight.data.zero_()
        self.proj.bias.data.zero_()

    def forward(self, x, x_mask, g=None, reverse=False):
        x0, x1 = torch.split(x, [self.half_channels] * 2, 1)

        h = self.pre(x0)
        h = self.convs(h, x_mask, g=g)
        h = self.proj(h) * x_mask

        b, c, t = x0.shape
        h = (
            h.reshape(b, c, -1, t).permute(0, 1, 3, 2).contiguous()
        )  # [b, cx?, t] -> [b, c, t, ?]

        unnormalized_widths = h[..., : self.num_bins] / math.sqrt(self.filter_channels)
        unnormalized_heights = h[..., self.num_bins : 2 * self.num_bins] / math.sqrt(
            self.filter_channels
        )
        unnormalized_derivatives = h[..., 2 * self.num_bins :]

        x1, logabsdet = piecewise_rational_quadratic_transform(
            x1,
            unnormalized_widths,
            unnormalized_heights,
            unnormalized_derivatives,
            inverse=reverse,
            tails="linear",
            tail_bound=self.tail_bound,
        )

        x = torch.cat([x0, x1], 1) * x_mask
        logdet = torch.sum(logabsdet * x_mask, [1, 2])
        if not reverse:
            return x, logdet
        else:
            return x


class LinearNorm(nn.Module):
    def __init__(
        self,
        in_channels,
        out_channels,
        bias=True,
        spectral_norm=False,
    ):
        super(LinearNorm, self).__init__()
        self.fc = nn.Linear(in_channels, out_channels, bias)

        if spectral_norm:
            self.fc = nn.utils.spectral_norm(self.fc)

    def forward(self, input):
        out = self.fc(input)
        return out


class Mish(nn.Module):
    def __init__(self):
        super(Mish, self).__init__()

    def forward(self, x):
        return x * torch.tanh(F.softplus(x))


class LinearNorm(nn.Module):
    def __init__(
        self,
        in_channels,
        out_channels,
        bias=True,
        spectral_norm=False,
    ):
        super(LinearNorm, self).__init__()
        self.fc = nn.Linear(in_channels, out_channels, bias)

        if spectral_norm:
            self.fc = nn.utils.spectral_norm(self.fc)

    def forward(self, input):
        out = self.fc(input)
        return out


class ConvNorm(nn.Module):
    def __init__(
        self,
        in_channels,
        out_channels,
        kernel_size=1,
        stride=1,
        padding=None,
        dilation=1,
        bias=True,
        spectral_norm=False,
    ):
        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,
        )

        if spectral_norm:
            self.conv = nn.utils.spectral_norm(self.conv)

    def forward(self, input):
        out = self.conv(input)
        return out


class MultiHeadAttention(nn.Module):
    """Multi-Head Attention module"""

    def __init__(self, n_head, d_model, d_k, d_v, dropout=0.0, spectral_norm=False):
        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_model, 0.5), dropout=dropout
        )

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

        if spectral_norm:
            self.w_qs = nn.utils.spectral_norm(self.w_qs)
            self.w_ks = nn.utils.spectral_norm(self.w_ks)
            self.w_vs = nn.utils.spectral_norm(self.w_vs)
            self.fc = nn.utils.spectral_norm(self.fc)

    def forward(self, x, mask=None):
        d_k, d_v, n_head = self.d_k, self.d_v, self.n_head
        sz_b, len_x, _ = x.size()

        residual = x

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

        if mask is not None:
            slf_mask = mask.repeat(n_head, 1, 1)  # (n*b) x .. x ..
        else:
            slf_mask = None
        output, attn = self.attention(q, k, v, mask=slf_mask)

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

        output = self.fc(output)

        output = self.dropout(output) + residual
        return output, attn


class ScaledDotProductAttention(nn.Module):
    """Scaled Dot-Product Attention"""

    def __init__(self, temperature, dropout):
        super().__init__()
        self.temperature = temperature
        self.softmax = nn.Softmax(dim=2)
        self.dropout = nn.Dropout(dropout)

    def forward(self, q, k, v, mask=None):
        attn = torch.bmm(q, k.transpose(1, 2).contiguous())
        attn = attn / self.temperature

        if mask is not None:
            attn = attn.masked_fill(mask, -np.inf)

        attn = self.softmax(attn)
        p_attn = self.dropout(attn)

        output = torch.bmm(p_attn, v)
        return output, attn


class Conv1dGLU(nn.Module):
    """
    Conv1d + GLU(Gated Linear Unit) with residual connection.
    For GLU refer to https://arxiv.org/abs/1612.08083 paper.
    """

    def __init__(self, in_channels, out_channels, kernel_size, dropout):
        super(Conv1dGLU, self).__init__()
        self.out_channels = out_channels
        self.conv1 = ConvNorm(in_channels, 2 * out_channels, kernel_size=kernel_size)
        self.dropout = nn.Dropout(dropout)

    def forward(self, x):
        residual = x
        x = self.conv1(x)
        x1, x2 = torch.split(x, split_size_or_sections=self.out_channels, dim=1)
        x = x1 * torch.sigmoid(x2)
        x = residual + self.dropout(x)
        return x