import torch
import torch.nn.functional as F
from torch import nn, Tensor

import copy
from typing import Optional, List


def _get_clones(module, N):
    return nn.ModuleList([copy.deepcopy(module) for i in range(N)])


def _get_activation_fn(activation):
    """Return an activation function given a string"""
    if activation == "relu":
        return F.relu
    if activation == "gelu":
        return F.gelu
    if activation == "glu":
        return F.glu
    raise RuntimeError(f"activation should be relu/gelu, not {activation}.")


class TransformerEncoderLayer(nn.Module):
    def __init__(self, d_model, nhead, dim_feedforward=2048, dropout=0.1, activation="relu", normalize_before=False):
        super(TransformerEncoderLayer, self).__init__()
        self.self_attn = nn.MultiheadAttention(d_model, nhead, dropout=dropout)
        # Implementation of Feedforward model
        self.linear1 = nn.Linear(d_model, dim_feedforward)
        self.dropout = nn.Dropout(dropout)
        self.linear2 = nn.Linear(dim_feedforward, d_model)

        self.norm1 = nn.LayerNorm(d_model)
        self.norm2 = nn.LayerNorm(d_model)
        self.dropout1 = nn.Dropout(dropout)
        self.dropout2 = nn.Dropout(dropout)

        self.activation = _get_activation_fn(activation)
        self.normalize_before = normalize_before

    def forward(self, src, src_mask: Optional[Tensor] = None, src_key_padding_mask: Optional[Tensor] = None):
        src2 = self.self_attn(src, src, src, attn_mask=src_mask, key_padding_mask=src_key_padding_mask)[0]
        src = src + self.dropout1(src2)
        src = self.norm1(src)
        src2 = self.linear2(self.dropout(self.activation(self.linear1(src))))
        src = src + self.dropout2(src2)
        src = self.norm2(src)
        return src