import math

import torch
import torch.nn.functional as F
from torch import nn
from torch.nn.modules.transformer import _get_activation_fn


class TransformerDecoderLayer(nn.Module):
    r"""TransformerDecoderLayer is made up of self-attn, multi-head-attn and feedforward network.
    This standard decoder layer is based on the paper "Attention Is All You Need".
    Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez,
    Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in
    Neural Information Processing Systems, pages 6000-6010. Users may modify or implement
    in a different way during application.

    Args:
        d_model: the number of expected features in the input (required).
        nhead: the number of heads in the multiheadattention models (required).
        dim_feedforward: the dimension of the feedforward network model (default=2048).
        dropout: the dropout value (default=0.1).
        activation: the activation function of intermediate layer, relu or gelu (default=relu).

    Examples::
        >>> decoder_layer = nn.TransformerDecoderLayer(d_model=512, nhead=8)
        >>> memory = torch.rand(10, 32, 512)
        >>> tgt = torch.rand(20, 32, 512)
        >>> out = decoder_layer(tgt, memory)
    """

    def __init__(self, d_model, nhead, dim_feedforward=2048, dropout=0.1,
                 activation="relu", self_attn=True, siamese=False, debug=False):
        super().__init__()
        self.has_self_attn, self.siamese = self_attn, siamese
        self.debug = debug
        if self.has_self_attn:
            self.self_attn = nn.MultiheadAttention(d_model, nhead, dropout=dropout)
            self.norm1 = nn.LayerNorm(d_model)
            self.dropout1 = nn.Dropout(dropout)
        self.multihead_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.norm2 = nn.LayerNorm(d_model)
        self.norm3 = nn.LayerNorm(d_model)
        self.dropout2 = nn.Dropout(dropout)
        self.dropout3 = nn.Dropout(dropout)
        if self.siamese:
            self.multihead_attn2 = nn.MultiheadAttention(d_model, nhead, dropout=dropout)

        self.activation = _get_activation_fn(activation)

    def __setstate__(self, state):
        if 'activation' not in state:
            state['activation'] = F.relu
        super().__setstate__(state)

    def forward(self, tgt, memory, tgt_mask=None, memory_mask=None,
                tgt_key_padding_mask=None, memory_key_padding_mask=None,
                memory2=None, memory_mask2=None, memory_key_padding_mask2=None):
        # type: (Tensor, Tensor, Optional[Tensor], Optional[Tensor], Optional[Tensor], Optional[Tensor]) -> Tensor
        r"""Pass the inputs (and mask) through the decoder layer.

        Args:
            tgt: the sequence to the decoder layer (required).
            memory: the sequence from the last layer of the encoder (required).
            tgt_mask: the mask for the tgt sequence (optional).
            memory_mask: the mask for the memory sequence (optional).
            tgt_key_padding_mask: the mask for the tgt keys per batch (optional).
            memory_key_padding_mask: the mask for the memory keys per batch (optional).

        Shape:
            see the docs in Transformer class.
        """
        if self.has_self_attn:
            tgt2, attn = self.self_attn(tgt, tgt, tgt, attn_mask=tgt_mask,
                                        key_padding_mask=tgt_key_padding_mask)
            tgt = tgt + self.dropout1(tgt2)
            tgt = self.norm1(tgt)
            if self.debug: self.attn = attn
        tgt2, attn2 = self.multihead_attn(tgt, memory, memory, attn_mask=memory_mask,
                                          key_padding_mask=memory_key_padding_mask)
        if self.debug: self.attn2 = attn2

        if self.siamese:
            tgt3, attn3 = self.multihead_attn2(tgt, memory2, memory2, attn_mask=memory_mask2,
                                               key_padding_mask=memory_key_padding_mask2)
            tgt = tgt + self.dropout2(tgt3)
            if self.debug: self.attn3 = attn3

        tgt = tgt + self.dropout2(tgt2)
        tgt = self.norm2(tgt)
        tgt2 = self.linear2(self.dropout(self.activation(self.linear1(tgt))))
        tgt = tgt + self.dropout3(tgt2)
        tgt = self.norm3(tgt)

        return tgt


class PositionalEncoding(nn.Module):
    r"""Inject some information about the relative or absolute position of the tokens
        in the sequence. The positional encodings have the same dimension as
        the embeddings, so that the two can be summed. Here, we use sine and cosine
        functions of different frequencies.
    .. math::
        \text{PosEncoder}(pos, 2i) = sin(pos/10000^(2i/d_model))
        \text{PosEncoder}(pos, 2i+1) = cos(pos/10000^(2i/d_model))
        \text{where pos is the word position and i is the embed idx)
    Args:
        d_model: the embed dim (required).
        dropout: the dropout value (default=0.1).
        max_len: the max. length of the incoming sequence (default=5000).
    Examples:
        >>> pos_encoder = PositionalEncoding(d_model)
    """

    def __init__(self, d_model, dropout=0.1, max_len=5000):
        super().__init__()
        self.dropout = nn.Dropout(p=dropout)

        pe = torch.zeros(max_len, d_model)
        position = torch.arange(0, max_len, dtype=torch.float).unsqueeze(1)
        div_term = torch.exp(torch.arange(0, d_model, 2).float() * (-math.log(10000.0) / d_model))
        pe[:, 0::2] = torch.sin(position * div_term)
        pe[:, 1::2] = torch.cos(position * div_term)
        pe = pe.unsqueeze(0).transpose(0, 1)
        self.register_buffer('pe', pe)

    def forward(self, x):
        r"""Inputs of forward function
        Args:
            x: the sequence fed to the positional encoder model (required).
        Shape:
            x: [sequence length, batch size, embed dim]
            output: [sequence length, batch size, embed dim]
        Examples:
            >>> output = pos_encoder(x)
        """

        x = x + self.pe[:x.size(0), :]
        return self.dropout(x)