import torch
import torch.nn as nn
from Sublayers import FeedForward, MultiHeadAttention, Norm


class DecoderLayer(nn.Module):
    def __init__(self, d_model, heads, dropout=0.1):
        super().__init__()
        self.norm_1 = Norm(d_model)
        self.norm_2 = Norm(d_model)
        self.norm_3 = Norm(d_model)
        
        self.dropout_1 = nn.Dropout(dropout)
        self.dropout_2 = nn.Dropout(dropout)
        self.dropout_3 = nn.Dropout(dropout)
        
        self.attn_1 = MultiHeadAttention(heads, d_model, dropout=dropout)
        self.attn_2 = MultiHeadAttention(heads, d_model, dropout=dropout)
        self.ff = FeedForward(d_model, dropout=dropout)

    def forward(self, x,  trg_mask):
        x2 = self.norm_1(x)
        x = x + self.dropout_1(self.attn_1(x2, x2, x2, trg_mask))
        x2 = self.norm_3(x)
        x2 = self.ff(x2)
        x = x + self.dropout_3(x2)
        return x