import math
from dataclasses import dataclass

import torch
from einops import rearrange
from torch import Tensor, nn
import torch
from einops import rearrange
from torch import Tensor

try:
    import flash_attn
    if hasattr(flash_attn, '__version__') and int(flash_attn.__version__[0]) == 2:
        from flash_attn.flash_attn_interface import flash_attn_kvpacked_func
        from flash_attn.modules.mha import FlashSelfAttention 
    else:
        from flash_attn.flash_attn_interface import flash_attn_unpadded_kvpacked_func
        from flash_attn.modules.mha import FlashSelfAttention
except Exception as e:
    print(f'flash_attn import failed: {e}')


def attention(q: Tensor, k: Tensor, v: Tensor, pe: Tensor) -> Tensor:
    q, k = apply_rope(q, k, pe)

    x = torch.nn.functional.scaled_dot_product_attention(q, k, v)
    x = rearrange(x, "B H L D -> B L (H D)")

    return x


def rope(pos: Tensor, dim: int, theta: int) -> Tensor:
    assert dim % 2 == 0
    scale = torch.arange(0, dim, 2, dtype=torch.float64, device=pos.device) / dim
    omega = 1.0 / (theta**scale)
    out = torch.einsum("...n,d->...nd", pos, omega)
    out = torch.stack([torch.cos(out), -torch.sin(out), torch.sin(out), torch.cos(out)], dim=-1)
    out = rearrange(out, "b n d (i j) -> b n d i j", i=2, j=2)
    return out.float()


def apply_rope(xq: Tensor, xk: Tensor, freqs_cis: Tensor) -> tuple[Tensor, Tensor]:
    xq_ = xq.float().reshape(*xq.shape[:-1], -1, 1, 2)
    xk_ = xk.float().reshape(*xk.shape[:-1], -1, 1, 2)
    xq_out = freqs_cis[..., 0] * xq_[..., 0] + freqs_cis[..., 1] * xq_[..., 1]
    xk_out = freqs_cis[..., 0] * xk_[..., 0] + freqs_cis[..., 1] * xk_[..., 1]
    return xq_out.reshape(*xq.shape).type_as(xq), xk_out.reshape(*xk.shape).type_as(xk)


class EmbedND(nn.Module):
    def __init__(self, dim: int, theta: int, axes_dim: list[int]):
        super().__init__()
        self.dim = dim
        self.theta = theta
        self.axes_dim = axes_dim

    def forward(self, ids: Tensor) -> Tensor:
        n_axes = ids.shape[-1]
        emb = torch.cat(
            [rope(ids[..., i], self.axes_dim[i], self.theta) for i in range(n_axes)],
            dim=-3,
        )

        return emb.unsqueeze(1)


def timestep_embedding(t: Tensor, dim, max_period=10000, time_factor: float = 1000.0):
    """
    Create sinusoidal timestep embeddings.
    :param t: a 1-D Tensor of N indices, one per batch element.
                      These may be fractional.
    :param dim: the dimension of the output.
    :param max_period: controls the minimum frequency of the embeddings.
    :return: an (N, D) Tensor of positional embeddings.
    """
    t = time_factor * t
    half = dim // 2
    freqs = torch.exp(-math.log(max_period) * torch.arange(start=0, end=half, dtype=torch.float32) / half).to(
        t.device
    )

    args = t[:, None].float() * freqs[None]
    embedding = torch.cat([torch.cos(args), torch.sin(args)], dim=-1)
    if dim % 2:
        embedding = torch.cat([embedding, torch.zeros_like(embedding[:, :1])], dim=-1)
    if torch.is_floating_point(t):
        embedding = embedding.to(t)
    return embedding


class MLPEmbedder(nn.Module):
    def __init__(self, in_dim: int, hidden_dim: int):
        super().__init__()
        self.in_layer = nn.Linear(in_dim, hidden_dim, bias=True)
        self.silu = nn.SiLU()
        self.out_layer = nn.Linear(hidden_dim, hidden_dim, bias=True)

    def forward(self, x: Tensor) -> Tensor:
        return self.out_layer(self.silu(self.in_layer(x)))


class RMSNorm(torch.nn.Module):
    def __init__(self, dim: int):
        super().__init__()
        self.scale = nn.Parameter(torch.ones(dim))

    def forward(self, x: Tensor):
        x_dtype = x.dtype
        x = x.float()
        rrms = torch.rsqrt(torch.mean(x**2, dim=-1, keepdim=True) + 1e-6)
        return (x * rrms).to(dtype=x_dtype) * self.scale


class QKNorm(torch.nn.Module):
    def __init__(self, dim: int):
        super().__init__()
        self.query_norm = RMSNorm(dim)
        self.key_norm = RMSNorm(dim)

    def forward(self, q: Tensor, k: Tensor, v: Tensor) -> tuple[Tensor, Tensor]:
        q = self.query_norm(q)
        k = self.key_norm(k)
        return q.to(v), k.to(v)


class SelfAttention(nn.Module):
    def __init__(self, dim: int, num_heads: int = 8, qkv_bias: bool = False):
        super().__init__()
        self.num_heads = num_heads
        head_dim = dim // num_heads

        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
        self.norm = QKNorm(head_dim)
        self.proj = nn.Linear(dim, dim)

    def forward(self, x: Tensor, pe: Tensor) -> Tensor:
        qkv = self.qkv(x)
        q, k, v = rearrange(qkv, "B L (K H D) -> K B H L D", K=3, H=self.num_heads)
        q, k = self.norm(q, k, v)
        x = attention(q, k, v, pe=pe)
        x = self.proj(x)
        return x



class FlashSelfMHAModified(nn.Module):
    """
    self-attention with flashattention
    """
    def __init__(self,
                 dim,
                 num_heads,
                 qkv_bias=False,
                 qk_norm=True,
                 attn_drop=0.0,
                 proj_drop=0.0,
                 device=None,
                 dtype=None,
                 norm_layer=RMSNorm,
                 ):
        factory_kwargs = {'device': device, 'dtype': dtype}
        super().__init__()
        self.dim = dim
        self.num_heads = num_heads
        assert self.dim % num_heads == 0, "self.kdim must be divisible by num_heads"
        self.head_dim = self.dim // num_heads
        assert self.head_dim % 8 == 0 and self.head_dim <= 128, "Only support head_dim <= 128 and divisible by 8"

        self.Wqkv = nn.Linear(dim, 3 * dim, bias=qkv_bias, **factory_kwargs)
        # TODO: eps should be 1 / 65530 if using fp16
        self.q_norm = norm_layer(self.head_dim) if qk_norm else nn.Identity()
        self.k_norm = norm_layer(self.head_dim) if qk_norm else nn.Identity()
        self.inner_attn = FlashSelfAttention(attention_dropout=attn_drop)
        self.out_proj = nn.Linear(dim, dim, bias=qkv_bias, **factory_kwargs)
        self.proj_drop = nn.Dropout(proj_drop)

    def forward(self, x, pe):
        """
        Parameters
        ----------
        x: torch.Tensor
            (batch, seqlen, hidden_dim) (where hidden_dim = num heads * head dim)
        """
        b, s, d = x.shape

        qkv = self.Wqkv(x)
        qkv = qkv.view(b, s, 3, self.num_heads, self.head_dim)  # [b, s, 3, h, d]
        q, k, v = qkv.unbind(dim=2) # [b, s, h, d]
        q = self.q_norm(q).half()   # [b, s, h, d]
        k = self.k_norm(k).half()
        q, k = apply_rope(q, k, pe)

        qkv = torch.stack([q, k, v], dim=2)     # [b, s, 3, h, d]
        context = self.inner_attn(qkv)
        out = self.out_proj(context.view(b, s, d))
        out = self.proj_drop(out)

        return out


@dataclass
class ModulationOut:
    shift: Tensor
    scale: Tensor
    gate: Tensor


class Modulation(nn.Module):
    def __init__(self, dim: int, double: bool):
        super().__init__()
        self.is_double = double
        self.multiplier = 6 if double else 3
        self.lin = nn.Linear(dim, self.multiplier * dim, bias=True)

    def forward(self, vec: Tensor) -> tuple[ModulationOut, ModulationOut | None]:
        out = self.lin(nn.functional.silu(vec))[:, None, :].chunk(self.multiplier, dim=-1)

        return (
            ModulationOut(*out[:3]),
            ModulationOut(*out[3:]) if self.is_double else None,
        )


class DoubleStreamBlock(nn.Module):
    def __init__(self, hidden_size: int, num_heads: int, mlp_ratio: float, qkv_bias: bool = False):
        super().__init__()

        mlp_hidden_dim = int(hidden_size * mlp_ratio)
        self.num_heads = num_heads
        self.hidden_size = hidden_size
        self.img_mod = Modulation(hidden_size, double=True)
        self.img_norm1 = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
        self.img_attn = SelfAttention(dim=hidden_size, num_heads=num_heads, qkv_bias=qkv_bias)

        self.img_norm2 = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
        self.img_mlp = nn.Sequential(
            nn.Linear(hidden_size, mlp_hidden_dim, bias=True),
            nn.GELU(approximate="tanh"),
            nn.Linear(mlp_hidden_dim, hidden_size, bias=True),
        )

        self.txt_mod = Modulation(hidden_size, double=True)
        self.txt_norm1 = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
        self.txt_attn = SelfAttention(dim=hidden_size, num_heads=num_heads, qkv_bias=qkv_bias)

        self.txt_norm2 = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
        self.txt_mlp = nn.Sequential(
            nn.Linear(hidden_size, mlp_hidden_dim, bias=True),
            nn.GELU(approximate="tanh"),
            nn.Linear(mlp_hidden_dim, hidden_size, bias=True),
        )

    def forward(self, img: Tensor, txt: Tensor, vec: Tensor, pe: Tensor) -> tuple[Tensor, Tensor]:
        img_mod1, img_mod2 = self.img_mod(vec)
        txt_mod1, txt_mod2 = self.txt_mod(vec)

        # prepare image for attention
        img_modulated = self.img_norm1(img)
        img_modulated = (1 + img_mod1.scale) * img_modulated + img_mod1.shift
        img_qkv = self.img_attn.qkv(img_modulated)
        img_q, img_k, img_v = rearrange(img_qkv, "B L (K H D) -> K B H L D", K=3, H=self.num_heads)
        img_q, img_k = self.img_attn.norm(img_q, img_k, img_v)

        # prepare txt for attention
        txt_modulated = self.txt_norm1(txt)
        txt_modulated = (1 + txt_mod1.scale) * txt_modulated + txt_mod1.shift
        txt_qkv = self.txt_attn.qkv(txt_modulated)
        txt_q, txt_k, txt_v = rearrange(txt_qkv, "B L (K H D) -> K B H L D", K=3, H=self.num_heads)
        txt_q, txt_k = self.txt_attn.norm(txt_q, txt_k, txt_v)

        # run actual attention
        q = torch.cat((txt_q, img_q), dim=2)
        k = torch.cat((txt_k, img_k), dim=2)
        v = torch.cat((txt_v, img_v), dim=2)

        attn = attention(q, k, v, pe=pe)
        txt_attn, img_attn = attn[:, : txt.shape[1]], attn[:, txt.shape[1] :]

        # calculate the img bloks
        img = img + img_mod1.gate * self.img_attn.proj(img_attn)
        img = img + img_mod2.gate * self.img_mlp((1 + img_mod2.scale) * self.img_norm2(img) + img_mod2.shift)

        # calculate the txt bloks
        txt = txt + txt_mod1.gate * self.txt_attn.proj(txt_attn)
        txt = txt + txt_mod2.gate * self.txt_mlp((1 + txt_mod2.scale) * self.txt_norm2(txt) + txt_mod2.shift)
        return img, txt


class SingleStreamBlock(nn.Module):
    """
    A DiT block with parallel linear layers as described in
    https://arxiv.org/abs/2302.05442 and adapted modulation interface.
    """

    def __init__(
        self,
        hidden_size: int,
        num_heads: int,
        mlp_ratio: float = 4.0,
        qk_scale: float | None = None,
    ):
        super().__init__()
        self.hidden_dim = hidden_size
        self.num_heads = num_heads
        head_dim = hidden_size // num_heads
        self.scale = qk_scale or head_dim**-0.5

        self.mlp_hidden_dim = int(hidden_size * mlp_ratio)
        # qkv and mlp_in
        self.linear1 = nn.Linear(hidden_size, hidden_size * 3 + self.mlp_hidden_dim)
        # proj and mlp_out
        self.linear2 = nn.Linear(hidden_size + self.mlp_hidden_dim, hidden_size)

        self.norm = QKNorm(head_dim)

        self.hidden_size = hidden_size
        self.pre_norm = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)

        self.mlp_act = nn.GELU(approximate="tanh")
        self.modulation = Modulation(hidden_size, double=False)

    def forward(self, x: Tensor, vec: Tensor, pe: Tensor) -> Tensor:
        mod, _ = self.modulation(vec)
        x_mod = (1 + mod.scale) * self.pre_norm(x) + mod.shift
        qkv, mlp = torch.split(self.linear1(x_mod), [3 * self.hidden_size, self.mlp_hidden_dim], dim=-1)

        q, k, v = rearrange(qkv, "B L (K H D) -> K B H L D", K=3, H=self.num_heads)
        q, k = self.norm(q, k, v)

        # compute attention
        attn = attention(q, k, v, pe=pe)
        # compute activation in mlp stream, cat again and run second linear layer
        output = self.linear2(torch.cat((attn, self.mlp_act(mlp)), 2))
        return x + mod.gate * output


class LastLayer(nn.Module):
    def __init__(self, hidden_size: int, patch_size: int, out_channels: int):
        super().__init__()
        self.norm_final = nn.LayerNorm(hidden_size, elementwise_affine=False, eps=1e-6)
        self.linear = nn.Linear(hidden_size, patch_size * patch_size * out_channels, bias=True)
        self.adaLN_modulation = nn.Sequential(nn.SiLU(), nn.Linear(hidden_size, 2 * hidden_size, bias=True))

    def forward(self, x: Tensor, vec: Tensor) -> Tensor:
        shift, scale = self.adaLN_modulation(vec).chunk(2, dim=1)
        x = (1 + scale[:, None, :]) * self.norm_final(x) + shift[:, None, :]
        x = self.linear(x)
        return x