from __future__ import annotations

import argparse
import json
import math
import os

import numpy as np
import torch
from PIL import Image
from safetensors.torch import load_file

from voxel_dit import VoxelDiT

def encode(weights, png_path, cfg_path, config="config.json"):
    c = json.load(open(config))["dit"]
    model = VoxelDiT(vox_size=c["vox_size"], patch=c["patch"], dim=c["dim"],
                     depth=c["depth"], heads=c["heads"], text_dim=c["text_dim"])
    model.load_state_dict(load_file(weights))
    parts, manifest = [], []
    for name, p in model.named_parameters():
        a = p.detach().to(torch.float16).contiguous().view(-1).numpy()
        parts.append(a)
        manifest.append({"name": name, "shape": list(p.shape), "numel": int(a.size)})
    flat = np.concatenate(parts)
    N = flat.size
    side = math.ceil(math.sqrt(N))
    u16 = flat.view(np.uint16)
    img = np.zeros((side * side, 3), dtype=np.uint8)
    img[:N, 0] = (u16 >> 8).astype(np.uint8)
    img[:N, 1] = (u16 & 0xFF).astype(np.uint8)
    Image.fromarray(img.reshape(side, side, 3), "RGB").save(png_path)
    total = sum(m["numel"] for m in manifest)
    json.dump({"cfg": c, "params": manifest, "total_parameters": total,
               "side": side, "dtype": "float16", "channels": "R=hi,G=lo,B=unused"},
              open(cfg_path, "w"))
    mb = os.path.getsize(png_path) / 1e6
    print(f"[png] encoded {total:,} params -> {side}x{side} PNG ({mb:.1f} MB)")
    return total, side

def load_model_png(png_path, cfg_path, device="cpu"):
    meta = json.load(open(cfg_path))
    c = meta["cfg"]
    model = VoxelDiT(vox_size=c["vox_size"], patch=c["patch"], dim=c["dim"],
                     depth=c["depth"], heads=c["heads"], text_dim=c["text_dim"])
    arr = np.asarray(Image.open(png_path).convert("RGB")).reshape(-1, 3)
    total = meta["total_parameters"]
    hi = arr[:total, 0].astype(np.uint16)
    lo = arr[:total, 1].astype(np.uint16)
    flat = ((hi << 8) | lo).astype(np.uint16).view(np.float16)
    sd = dict(model.named_parameters())
    off = 0
    with torch.no_grad():
        for m in meta["params"]:
            n = m["numel"]
            chunk = flat[off:off + n].astype(np.float16)
            sd[m["name"]].copy_(torch.from_numpy(chunk.copy()).view(*m["shape"]).to(torch.float32))
            off += n
    return model.to(device).eval()

def verify(weights, png_path, cfg_path, config="config.json"):
    model = load_model_png(png_path, cfg_path)
    ref = load_file(weights)
    worst, name = 0.0, ""
    for k, p in model.named_parameters():
        d = (p.detach() - ref[k].float()).abs().max().item()
        if d > worst:
            worst, name = d, k
    rel = worst / max(1e-12, ref[name].float().abs().max().item())
    print(f"[png] round-trip max abs err {worst:.3e} on {name} (relative {rel:.2e})")
    return worst

def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("--weights", default="model.safetensors")
    ap.add_argument("--png", default="model.png")
    ap.add_argument("--manifest", default="model_png.json")
    ap.add_argument("--config", default="config.json")
    args = ap.parse_args()
    encode(args.weights, args.png, args.manifest, args.config)
    verify(args.weights, args.png, args.manifest, args.config)

if __name__ == "__main__":
    main()