"""
    Modified: https://github.com/datnguyen-tien204
    Flux Project: https://github.com/black-forest-labs/flux/blob/main/src/flux/modules/layers.py
"""
import math
import torch
from torch import nn, Tensor
from einops import rearrange
from flux.utils.math import attention, rope


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):
    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)

        # --- DEBUG PRINT ---
        if x.shape[-1] != self.scale.shape[0]:
            print(f"!!! SHAPE MISMATCH ERROR !!!")
            print(f"Input x shape: {x.shape}")
            print(f"Scale shape: {self.scale.shape}")
        # -------------------

        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