import torch
import torch.nn.functional as F
from einops import rearrange
from torch import nn


class Residual(nn.Module):
    def __init__(self, fn):
        super().__init__()
        self.fn = fn
    def forward(self, x, **kwargs):
        return self.fn(x, **kwargs) + x


class Residual2(nn.Module):
    def __init__(self, fn):
        super().__init__()
        self.fn = fn
    def forward(self, x, x2, **kwargs):
        return self.fn(x, x2, **kwargs) + x


class PreNorm(nn.Module):
    def __init__(self, dim, fn):
        super().__init__()
        self.norm = nn.LayerNorm(dim)
        self.fn = fn
    def forward(self, x, **kwargs):
        return self.fn(self.norm(x), **kwargs)

class FeedForward(nn.Module):
    def __init__(self, dim, hidden_dim, dropout = 0.):
        super().__init__()
        self.net = nn.Sequential(
            nn.Linear(dim, hidden_dim),
            nn.GELU(),
            nn.Dropout(dropout),
            nn.Linear(hidden_dim, dim),
            nn.Dropout(dropout)
        )
    def forward(self, x):
        return self.net(x)

class Attention(nn.Module):
    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0.):
        super().__init__()
        inner_dim = dim_head *  heads
        project_out = not (heads == 1 and dim_head == dim)

        self.heads = heads
        self.scale = dim_head ** -0.5

        self.attend = nn.Softmax(dim = -1)
        self.to_qkv = nn.Linear(dim, inner_dim * 3, bias = False)

        self.to_out = nn.Sequential(
            nn.Linear(inner_dim, dim),
            nn.Dropout(dropout)
        ) if project_out else nn.Identity()

    def forward(self, x):
        qkv = self.to_qkv(x).chunk(3, dim = -1)

        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = self.heads), qkv)

        dots = torch.matmul(q, k.transpose(-1, -2)) * self.scale

        attn = self.attend(dots)

        out = torch.matmul(attn, v)

        out = rearrange(out, 'b h n d -> b n (h d)')
        out = self.to_out(out)

        return out

class Transformer(nn.Module):
    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout = 0.):
        super().__init__()
        self.layers = nn.ModuleList([])
        for _ in range(depth):
            self.layers.append(nn.ModuleList([
                PreNorm(dim, Attention(dim, heads = heads, dim_head = dim_head, dropout = dropout)),
                PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout))
            ]))
    def forward(self, x):
        for attn, ff in self.layers:
            x = attn(x) + x
            x = ff(x) + x
        return x



class Cross_Attention(nn.Module):
    def __init__(self, dim, heads = 8, dim_head = 64, dropout = 0., softmax=True):
        super().__init__()
        inner_dim = dim_head * heads
        self.heads = heads
        self.scale = dim ** -0.5

        self.softmax = softmax
        self.to_q = nn.Linear(dim, inner_dim, bias=False)
        self.to_k = nn.Linear(dim, inner_dim, bias=False)
        self.to_v = nn.Linear(dim, inner_dim, bias=False)

        self.to_out = nn.Sequential(
            nn.Linear(inner_dim, dim),
            nn.Dropout(dropout)
        )

    def forward(self, x, m, mask = None):

        b, n, _, h = *x.shape, self.heads
        q = self.to_q(x)
        k = self.to_k(m)
        v = self.to_v(m)

        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> b h n d', h = h), [q,k,v])

        dots = torch.einsum('bhid,bhjd->bhij', q, k) * self.scale
        mask_value = -torch.finfo(dots.dtype).max

        if mask is not None:
            mask = F.pad(mask.flatten(1), (1, 0), value = True)
            assert mask.shape[-1] == dots.shape[-1], 'mask has incorrect dimensions'
            mask = mask[:, None, :] * mask[:, :, None]
            dots.masked_fill_(~mask, mask_value)
            del mask

        if self.softmax:
            attn = dots.softmax(dim=-1)
        else:
            attn = dots

        out = torch.einsum('bhij,bhjd->bhid', attn, v)
        out = rearrange(out, 'b h n d -> b n (h d)')
        out = self.to_out(out)

        return out

class PreNorm2(nn.Module):
    def __init__(self, dim, fn):
        super().__init__()
        self.norm = nn.LayerNorm(dim)
        self.fn = fn
    def forward(self, x, x2, **kwargs):
        return self.fn(self.norm(x), self.norm(x2), **kwargs)


class TransformerDecoder(nn.Module):
    def __init__(self, dim, depth, heads, dim_head, mlp_dim, dropout, softmax=True):
        super().__init__()
        self.layers = nn.ModuleList([])
        for _ in range(depth):
            self.layers.append(nn.ModuleList([
                Residual2(PreNorm2(dim, Cross_Attention(dim, heads = heads,
                                                        dim_head = dim_head, dropout = dropout,
                                                        softmax=softmax))),
                Residual(PreNorm(dim, FeedForward(dim, mlp_dim, dropout = dropout)))
            ]))
    def forward(self, x, m, mask = None):
        """target(query), memory"""
        for attn, ff in self.layers:
            x = attn(x, m, mask = mask)
            x = ff(x)
        return x