import math
import torch
from einops import rearrange
from torch import Tensor


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 attention_masked(q: Tensor, k: Tensor, v: Tensor, pe: Tensor, patch_ids: list[int], mask: Tensor, return_weight:bool=False) -> Tensor:
    q, k = apply_rope(q, k, pe)
    # x = torch.nn.functional.scaled_dot_product_attention(q,k,v,attn_mask=attn_mask)
    if return_weight:
        x, m = scaled_dot_product_attention_masked(q, k, v, patch_ids, mask, return_weight)
        x = rearrange(x, "B H L D -> B L (H D)")
        return x, m
    else:
        x = scaled_dot_product_attention_masked(q, k, v, patch_ids, mask, return_weight)
        x = rearrange(x, "B H L D -> B L (H D)")
        return x

    # return x, m

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)


def scaled_dot_product_attention_masked(query, key, value, patch_ids, attn_mask, return_weight=False):
    scale_factor = 1 / math.sqrt(query.size(-1))
    attn_weight = query @ key.transpose(-2, -1) * scale_factor
    attn_weight += attn_mask
    attn_weight = torch.softmax(attn_weight, dim=-1)
    if return_weight:
        return attn_weight @ value, attn_weight
    return attn_weight @ value