import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.utils.checkpoint as checkpoint
from typing import Optional
import math

# =============================================
# 1. Window Partition & Reverse (Core of Swin)
# =============================================
def window_partition(x, window_size):
    """
    Args:
        x: (B, H, W, C)
        window_size (int): window size
    Returns:
        windows: (num_windows*B, window_size, window_size, C)
    """
    B, H, W, C = x.shape
    x = x.view(B, H // window_size, window_size, W // window_size, window_size, C)
    windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C)
    return windows

def window_reverse(windows, window_size, H, W):
    """
    Args:
        windows: (num_windows*B, window_size, window_size, C)
        window_size (int): Window size
        H (int): Height of image
        W (int): Width of image
    Returns:
        x: (B, H, W, C)
    """
    B = int(windows.shape[0] / (H * W / window_size / window_size))
    x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1)
    x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1)
    return x


# =============================================
# 2. Shifted Window Multi-Head Self Attention
# =============================================
class WindowAttention(nn.Module):
    def __init__(self, dim, window_size, num_heads, qkv_bias=True, attn_drop=0., proj_drop=0.):
        super().__init__()
        self.dim = dim
        self.window_size = window_size
        self.num_heads = num_heads
        head_dim = dim // num_heads
        self.scale = head_dim ** -0.5

        # Relative position bias table
        self.relative_position_bias_table = nn.Parameter(
            torch.zeros((2 * window_size[0] - 1) * (2 * window_size[1] - 1), num_heads))

        # Get pair-wise relative position index
        coords_h = torch.arange(self.window_size[0])
        coords_w = torch.arange(self.window_size[1])
        coords = torch.stack(torch.meshgrid([coords_h, coords_w], indexing='ij'))
        coords_flatten = torch.flatten(coords, 1)
        relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :]
        relative_coords = relative_coords.permute(1, 2, 0).contiguous()
        relative_coords[:, :, 0] += self.window_size[0] - 1
        relative_coords[:, :, 1] += self.window_size[1] - 1
        relative_coords[:, :, 0] *= 2 * self.window_size[1] - 1
        relative_position_index = relative_coords.sum(-1)
        self.register_buffer("relative_position_index", relative_position_index)

        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
        self.attn_drop = nn.Dropout(attn_drop)
        self.proj = nn.Linear(dim, dim)
        self.proj_drop = nn.Dropout(proj_drop)

        nn.init.trunc_normal_(self.relative_position_bias_table, std=.02)
        self.softmax = nn.Softmax(dim=-1)

    def forward(self, x, mask=None):
        B_, N, C = x.shape
        qkv = self.qkv(x).reshape(B_, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1,  # 3, B_, H, N, D
        q, k, v = qkv.unbind(0)

        q = q * self.scale
        attn = (q @ k.transpose(-2, -1))

        relative_position_bias = self.relative_position_bias_table[
            self.relative_position_index.view(-1)].view(
            self.window_size[0]*self.window_size[1],
            self.window_size[0]*self.window_size[1], -1)
        relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous()
        attn = attn + relative_position_bias.unsqueeze(0)

        if mask is not None:
            nW = mask.shape[0]
            attn = attn.view(B_ // nW, nW, self.num_heads, N, N) + mask.unsqueeze(1).unsqueeze(0)
            attn = attn.view(-1, self.num_heads, N, N)
        attn = self.softmax(attn)
        attn = self.attn_drop(attn)

        x = (attn @ v).transpose(1, 2).reshape(B_, N, C)
        x = self.proj(x)
        x = self.proj_drop(x)
        return x


# =============================================
# 3. Swin Transformer Block
# =============================================
class SwinTransformerBlock(nn.Module):
    def __init__(self, dim, num_heads, window_size=7, shift_size=0,
                 mlp_ratio=4., qkv_bias=True, drop=0., attn_drop=0., drop_path=0.,
                 act_layer=nn.GELU, norm_layer=nn.LayerNorm):
        super().__init__()
        self.dim = dim
        self.num_heads = num_heads
        self.window_size = window_size
        self.shift_size = shift_size
        self.mlp_ratio = mlp_ratio

        self.norm1 = norm_layer(dim)
        self.attn = WindowAttention(
            dim, window_size=(window_size, window_size), num_heads=num_heads,
            qkv_bias=qkv_bias, attn_drop=attn_drop, proj_drop=drop)

        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
        self.norm2 = norm_layer(dim)
        mlp_hidden_dim = int(dim * mlp_ratio)
        self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)

        # Cyclic shift mask
        if self.shift_size > 0:
            H = W = self.window_size
            img_mask = torch.zeros((1, H, W, 1))
            h_slices = (slice(0, -window_size), slice(-window_size, -shift_size), slice(-shift_size, None))
            w_slices = (slice(0, -window_size), slice(-window_size, -shift_size), slice(-shift_size, None))
            cnt = 0
            for h in h_slices:
                for w in w_slices:
                    img_mask[:, h, w, :] = cnt
                    cnt += 1

            mask_windows = window_partition(img_mask, window_size)
            mask_windows = mask_windows.view(-1, window_size * window_size)
            attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)
            attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0))
            self.register_buffer("attn_mask", attn_mask)
        else:
            self.attn_mask = None

    def forward(self, x, H, W):
        B, L, C = x.shape
        shortcut = x

        x = self.norm1(x)
        x = x.view(B, H, W, C)

        # Cyclic shift
        if self.shift_size > 0:
            shifted_x = torch.roll(x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2))
        else:
            shifted_x = x

        # Partition windows
        x_windows = window_partition(shifted_x, self.window_size)  # nW*B, window_size, window_size, C
        x_windows = x_windows.view(-1, self.window_size * self.window_size, C)
        attn_windows = self.attn(x_windows, mask=self.attn_mask)

        # Merge windows
        attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C)
        shifted_x = window_reverse(attn_windows, self.window_size, H, W)

        # Reverse cyclic shift
        if self.shift_size > 0:
            x = torch.roll(shifted_x, shifts=(self.shift_size, self.shift_size), dims=(1, 2))
        else:
            x = shifted_x
        x = x.view(B, H * W, C)

        # FFN
        x = shortcut + self.drop_path(x)
        x = x + self.drop_path(self.mlp(self.norm2(x)))

        return x


# =============================================
# 4. Patch Merging (Downsampling)
# =============================================
class PatchMerging(nn.Module):
    def __init__(self, input_resolution, dim, norm_layer=nn.LayerNorm):
        super().__init__()
        self.input_resolution = input_resolution
        self.dim = dim
        self.reduction = nn.Linear(4 * dim, 2 * dim, bias=False)
        self.norm = norm_layer(4 * dim)

    def forward(self, x):
        H, W = self.input_resolution
        B, L, C = x.shape
        assert L == H * W, "input feature has wrong size"

        x = x.view(B, H, W, C)

        x = x[:, 0::2, 0::2, :] + x[:, 1::2, 0::2, :] + \
             x[:, 0::2, 1::2, :] + x[:, 1::2, 1::2, :]
        x = x.view(B, -1, 4 * C)  # B H/2 W/2 4*C

        x = self.norm(x)
        x = self.reduction(x)
        return x


# =============================================
# 5. Full Swin Transformer
# =============================================
class SwinTransformer(nn.Module):
    def __init__(self, img_size=224, patch_size=4, in_chans=3, num_classes=1000,
                 embed_dim=96, depths=[2,2,6,2], num_heads=[3,6,12,24],
                 window_size=7, mlp_ratio=4., qkv_bias=True, drop_rate=0.,
                 attn_drop_rate=0., drop_path_rate=0.1, norm_layer=nn.LayerNorm,
                 ape=False, patch_norm=True, **kwargs):
        super().__init__()

        self.num_classes = num_classes
        self.num_layers = len(depths)
        self.embed_dim = embed_dim
        self.ape = ape
        self.patch_norm = patch_norm
        self.num_features = int(embed_dim * 2 ** (self.num_layers - 1))

        # Split image into non-overlapping patches
        self.patch_embed = PatchEmbed(
            img_size=img_size, patch_size=patch_size, in_chans=in_chans,
            embed_dim=embed_dim, norm_layer=norm_layer if self.patch_norm else None)
        num_patches = self.patch_embed.num_patches
        patches_resolution = self.patch_embed.grid_size

        # Absolute position embedding
        if self.ape:
            self.absolute_pos_embed = nn.Parameter(torch.zeros(1, num_patches, embed_dim))
            nn.init.trunc_normal_(self.absolute_pos_embed, std=.02)

        self.pos_drop = nn.Dropout(p=drop_rate)

        # Stochastic depth
        dpr = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))]

        # Build layers
        self.layers = nn.ModuleList()
        for i_layer in range(self.num_layers):
            layer = BasicLayer(dim=int(embed_dim * 2 ** i_layer),
                              input_resolution=(patches_resolution[0] // (2 ** i_layer),
                                               patches_resolution[1] // (2 ** i_layer)),
                              depth=depths[i_layer],
                              num_heads=num_heads[i_layer],
                              window_size=window_size,
                              mlp_ratio=mlp_ratio,
                              qkv_bias=qkv_bias, drop=drop_rate,
                              attn_drop=attn_drop_rate,
                              drop_path=dpr[sum(depths[:i_layer]):sum(depths[:i_layer + 1])],
                              norm_layer=norm_layer,
                              downsample=PatchMerging if (i_layer < self.num_layers - 1) else None)
            self.layers.append(layer)

        # Final norm & head
        self.norm = norm_layer(self.num_features)
        self.avgpool = nn.AdaptiveAvgPool1d(1)
        self.head = nn.Linear(self.num_features, num_classes) if num_classes > 0 else nn.Identity()

        self.apply(self._init_weights)

    def _init_weights(self, m):
        if isinstance(m, nn.Linear):
            nn.init.trunc_normal_(m.weight, std=.02)
            if isinstance(m, nn.Linear) and m.bias is not None:
                nn.init.constant_(m.bias, 0)
        elif isinstance(m, nn.LayerNorm):
            nn.init.constant_(m.bias, 0)
            nn.init.constant_(m.weight, 1.0)

    def forward(self, x):
        x = self.patch_embed(x)
        if self.ape:
            x = x + self.absolute_pos_embed
        x = self.pos_drop(x)

        for layer in self.layers:
            x = layer(x)

        x = self.norm(x)
        x = self.avgpool(x.transpose(1, 2))
        x = torch.flatten(x, 1)
        x = self.head(x)
        return x


# =============================================
# Predefined Models (Same as official)
# =============================================
def swin_tiny_patch4_window7_224(**kwargs):
    return SwinTransformer(patch_size=4, embed_dim=96, depths=[2,2,6,2], num_heads=[3,6,12,24], window_size=7, **kwargs)

def swin_small_patch4_window7_224(**kwargs):
    return SwinTransformer(patch_size=4, embed_dim=96, depths=[2,2,18,2], num_heads=[3,6,12,24], window_size=7, **kwargs)

def swin_base_patch4_window7_224(**kwargs):
    return SwinTransformer(patch_size=4, embed_dim=128, depths=[2,2,18,2], num_heads=[4,8,16,32], window_size=7, **kwargs)

def swin_base_patch4_window12_384(**kwargs):
    return SwinTransformer(img_size=384, patch_size=4, embed_dim=128, depths=[2,2,18,2], num_heads=[4,8,16,32], window_size=12, **kwargs)

def swin_large_patch4_window12_384(**kwargs):
    return SwinTransformer(img_size=384, patch_size=4, embed_dim=192, depths=[2,2,18,2], num_heads=[6,12,24,48], window_size=12, **kwargs)


# =============================================
# Test
# =============================================
if __name__ == "__main__":
    model = swin_tiny_patch4_window7_224(num_classes=1000)
    x = torch.randn(2, 3, 224, 224)
    out = model(x)
    print(f"Swin-T Output: {out.shape}")  # → [2, 1000]

    # CIFAR-10 version
    model_cifar = swin_tiny_patch4_window7_224(num_classes=10)
    model_cifar.patch_embed = PatchEmbed(img_size=32, patch_size=4, embed_dim=96)
    x_cifar = torch.randn(8, 3, 32, 32)
    print("CIFAR-10 Swin:", model_cifar(x_cifar).shape)