import torch
import torch.nn as nn
import torch.nn.functional as F

import numpy as np

from math import sqrt


class TriangularCausalMask():
    def __init__(self, B, L, device="cpu"):
        mask_shape = [B, 1, L, L]
        with torch.no_grad():
            self._mask = torch.triu(torch.ones(mask_shape, dtype=torch.bool), diagonal=1).to(device)

    @property
    def mask(self):
        return self._mask


class ProbMask():
    def __init__(self, B, H, L, index, scores, device="cpu"):
        _mask = torch.ones(L, scores.shape[-1], dytpe=torch.bool).to(device).triu(1)
        _mask_ex = _mask[None, None, :].expand(B, H, L, scores.shape[-1])
        indicator = _mask_ex[torch.arange(B)[:, None, None],
                    torch.arange(H)[None, :, None],
                    index, :].to(device)
        self._mask = indicator.view(scores.shape).to(device)

    @property
    def mask(self):
        return self._mask


class FullAttention(nn.Module):
    def __init__(self, mask_flag=True, factor=5, scale=None, attention_dropout=0.1):
        super(FullAttention, self).__init__()
        self.scale = scale
        self.mask_flag = mask_flag
        self.dropout = nn.Dropout(attention_dropout)

    def forward(self, queries, keys, values, attn_mask):
        B, L, H, E = queries.shape
        _, S, _, D = values.shape
        scale = self.scale or 1. / sqrt(E)

        scores = torch.einsum("blhe,bshe->bhls", queries, keys)
        if self.mask_flag:
            if attn_mask is None:
                attn_mask = TriangularCausalMask(B, L, device=queries.device)

            scores.masked_fill_(attn_mask.mask, -np.inf)

        A = self.dropout(torch.softmax(scale * scores, dim=-1))
        V = torch.einsum("bhls,bshd->blhd", A, values)

        return V.contiguous()


class ProbAttention(nn.Module):
    def __init__(self, mask_flag=True, factor=5, scale=None, attention_dropout=0.1):
        super(ProbAttention, self).__init__()
        self.factor = factor
        self.scale = scale
        self.mask_flag = mask_flag
        self.dropout = nn.Dropout(attention_dropout)

    def _prob_QK(self, Q, K, sample_k, n_top):
        # Q [B, H, L, D]
        B, H, L, E = K.shape
        _, _, S, _ = Q.shape

        # calculate the sampled Q_K
        K_expand = K.unsqueeze(-3).expand(B, H, S, L, E)
        indx_sample = torch.randint(L, (S, sample_k))
        K_sample = K_expand[:, :, torch.arange(S).unsqueeze(1), indx_sample, :]
        Q_K_sample = torch.matmul(Q.unsqueeze(-2), K_sample.transpose(-2, -1)).squeeze()

        # find the Top_k query with sparisty measurement
        M = Q_K_sample.max(-1)[0] - torch.div(Q_K_sample.sum(-1), L)
        M_top = M.topk(n_top, sorted=False)[1]

        # use the reduced Q to calculate Q_K
        Q_reduce = Q[torch.arange(B)[:, None, None],
                   torch.arange(H)[None, :, None],
                   M_top, :]
        Q_K = torch.matmul(Q_reduce, K.transpose(-2, -1))

        return Q_K, M_top

    def _get_initial_context(self, V, L_Q):
        B, H, L_V, D = V.shape
        if not self.mask_flag:
            V_sum = V.sum(dim=-2)
            contex = V_sum.unsqueeze(-2).expand(B, H, L_Q, V_sum.shape[-1]).clone()
        else:  # use mask
            assert (L_Q == L_V)  # requires that L_Q == L_V, i.e. for self-attention only
            contex = V.cumsum(dim=-1)
        return contex

    def _update_context(self, context_in, V, scores, index, L_Q, attn_mask):
        B, H, L_V, D = V.shape

        if self.mask_flag:
            attn_mask = ProbMask(B, H, L_Q, index, scores, device=V.device)
            scores.masked_fill_(attn_mask.mask, -np.inf)

        attn = torch.softmax(scores, dim=-1)  # nn.Softmax(dim=-1)(scores)

        context_in[torch.arange(B)[:, None, None],
        torch.arange(H)[None, :, None],
        index, :] = torch.matmul(attn, V)
        return context_in

    def forward(self, queries, keys, values, attn_mask):
        B, L, H, D = queries.shape
        _, S, _, _ = keys.shape

        queries = queries.view(B, H, L, -1)
        keys = keys.view(B, H, S, -1)
        values = values.view(B, H, S, -1)

        U = self.factor * np.ceil(np.log(S)).astype('int').item()
        u = self.factor * np.ceil(np.log(L)).astype('int').item()

        scores_top, index = self._prob_QK(queries, keys, u, U)
        # add scale factor
        scale = self.scale or 1. / sqrt(D)
        if scale is not None:
            scores_top = scores_top * scale
        # get the context
        context = self._get_initial_context(values, L)
        # update the context with selected top_k queries
        context = self._update_context(context, values, scores_top, index, L, attn_mask)

        return context.contiguous()


class AttentionLayer(nn.Module):
    def __init__(self, attention, d_model, n_heads, d_keys=None,
                 d_values=None):
        super(AttentionLayer, self).__init__()

        d_keys = d_keys or (d_model // n_heads)
        d_values = d_values or (d_model // n_heads)

        self.inner_attention = attention
        self.query_projection = nn.Linear(d_model, d_keys * n_heads)
        self.key_projection = nn.Linear(d_model, d_keys * n_heads)
        self.value_projection = nn.Linear(d_model, d_values * n_heads)
        self.out_projection = nn.Linear(d_values * n_heads, d_model)
        self.n_heads = n_heads

    def forward(self, queries, keys, values, attn_mask):
        B, L, _ = queries.shape
        _, S, _ = keys.shape
        H = self.n_heads

        queries = self.query_projection(queries).view(B, L, H, -1)
        keys = self.key_projection(keys).view(B, S, H, -1)
        values = self.value_projection(values).view(B, S, H, -1)

        out = self.inner_attention(
            queries,
            keys,
            values,
            attn_mask
        ).view(B, L, -1)

        return self.out_projection(out)