# Copyright 2021 AlQuraishi Laboratory
# Copyright 2021 DeepMind Technologies Limited
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#      http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from functools import partialmethod, partial
import math
from typing import Optional, List

import torch
import torch.nn as nn

from dockformer.model.primitives import Linear, LayerNorm, Attention
from dockformer.utils.tensor_utils import permute_final_dims


class TriangleAttention(nn.Module):
    def __init__(
        self, c_in, c_hidden, no_heads, starting=True, inf=1e9
    ):
        """
        Args:
            c_in:
                Input channel dimension
            c_hidden:
                Overall hidden channel dimension (not per-head)
            no_heads:
                Number of attention heads
        """
        super(TriangleAttention, self).__init__()

        self.c_in = c_in
        self.c_hidden = c_hidden
        self.no_heads = no_heads
        self.starting = starting
        self.inf = inf

        self.layer_norm = LayerNorm(self.c_in)

        self.linear = Linear(c_in, self.no_heads, bias=False, init="normal")

        self.mha = Attention(
            self.c_in, self.c_in, self.c_in, self.c_hidden, self.no_heads
        )

    def forward(self, 
        x: torch.Tensor, 
        mask: Optional[torch.Tensor] = None,
        use_memory_efficient_kernel: bool = False,
        use_lma: bool = False,
    ) -> torch.Tensor:
        """
        Args:
            x:
                [*, I, J, C_in] input tensor (e.g. the pair representation)
        Returns:
            [*, I, J, C_in] output tensor
        """ 
        if mask is None:
            # [*, I, J]
            mask = x.new_ones(
                x.shape[:-1],
            )

        if(not self.starting):
            x = x.transpose(-2, -3)
            mask = mask.transpose(-1, -2)

        # [*, I, J, C_in]
        x = self.layer_norm(x)

        # [*, I, 1, 1, J]
        mask_bias = (self.inf * (mask - 1))[..., :, None, None, :]

        # [*, H, I, J]
        triangle_bias = permute_final_dims(self.linear(x), (2, 0, 1))

        # [*, 1, H, I, J]
        triangle_bias = triangle_bias.unsqueeze(-4)

        biases = [mask_bias, triangle_bias]

        x = self.mha(
            q_x=x,
            kv_x=x,
            biases=biases,
            use_memory_efficient_kernel=use_memory_efficient_kernel,
            use_lma=use_lma
        )

        if(not self.starting):
            x = x.transpose(-2, -3)

        return x