# Adapted from Tencent-Hunyuan/AuK (MIT). Weight normalization is folded into the checkpoint.

import torch
from torch import nn
from models.TTS.auk.vae.modules.commons.layers import Conv1d

def fused_add_tanh_sigmoid_multiply(input_a, input_b, n_channels):
    n_channels_int = n_channels[0]
    in_act = input_a + input_b
    t_act = torch.tanh(in_act[:, :n_channels_int, :])
    s_act = torch.sigmoid(in_act[:, n_channels_int:, :])
    acts = t_act * s_act
    return acts

class WN(torch.nn.Module):

    def __init__(self, hidden_channels, kernel_size, dilation_rate, n_layers, gin_channels=0, p_dropout=0, causal=False):
        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 = Conv1d(gin_channels, 2 * hidden_channels * n_layers, 1, causal=causal)
            self.cond_layer = cond_layer
        for i in range(n_layers):
            dilation = dilation_rate ** i
            in_layer = Conv1d(hidden_channels, 2 * hidden_channels, kernel_size, dilation=dilation, causal=causal)
            self.in_layers.append(in_layer)
            if i < n_layers - 1:
                res_skip_channels = 2 * hidden_channels
            else:
                res_skip_channels = hidden_channels
            res_skip_layer = Conv1d(hidden_channels, res_skip_channels, 1, causal=causal)
            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 = 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

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 ResidualCouplingLayer(nn.Module):

    def __init__(self, channels, hidden_channels, kernel_size, dilation_rate, n_layers, p_dropout=0, gin_channels=0, mean_only=False, causal=True):
        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 = Conv1d(self.half_channels, hidden_channels, 1, causal=causal)
        self.enc = WN(hidden_channels, kernel_size, dilation_rate, n_layers, p_dropout=p_dropout, gin_channels=gin_channels, causal=causal)
        self.post = Conv1d(hidden_channels, self.half_channels * (2 - mean_only), 1, causal=causal)
        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 ResidualCouplingBlock(nn.Module):

    def __init__(self, channels, hidden_channels, kernel_size, dilation_rate, n_layers, n_flows=4, gin_channels=0, causal=True):
        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.n_flows = n_flows
        self.gin_channels = gin_channels
        self.flows = nn.ModuleList()
        for i in range(n_flows):
            self.flows.append(ResidualCouplingLayer(channels, hidden_channels, kernel_size, dilation_rate, n_layers, gin_channels=gin_channels, mean_only=True, causal=causal))
            self.flows.append(Flip())

    def forward(self, x, x_mask, g=None, reverse=False):
        if not reverse:
            for flow in self.flows:
                x, _ = flow(x, x_mask, g=g, reverse=reverse)
        else:
            for flow in reversed(self.flows):
                x = flow(x, x_mask, g=g, reverse=reverse)
        return x