"""样本初探：检查 mark alpha 通道、尺寸，生成可视化素材到 try/visual/。"""
from pathlib import Path
import cv2
import numpy as np

ROOT = Path(__file__).resolve().parent.parent
CAP = ROOT / "captchas"
OUT = ROOT / "try" / "visual"
OUT.mkdir(parents=True, exist_ok=True)


def mark_stats(path):
    """读取 mark 图，返回 (形状, 通道数, alpha>128 占比, 有效bbox) 或 None。"""
    try:
        m = cv2.imread(str(path), cv2.IMREAD_UNCHANGED)
        if m is None:
            return None
        ch = m.shape[2] if m.ndim == 3 else 1
        a = m[..., 3] if ch == 4 else np.full(m.shape[:2], 255, np.uint8)
        ys, xs = np.where(a > 128)
        if len(xs) == 0:
            return m.shape, ch, 0.0, None
        bbox = (int(xs.min()), int(ys.min()), int(xs.max()) + 1, int(ys.max()) + 1)
        return m.shape, ch, float((a > 128).mean()), bbox
    except Exception as e:  # 坏文件不中断批次
        print(f"  读取失败: {e}")
        return None


def main():
    pairs = sorted({p.name.replace("-mark.png", "") for p in CAP.glob("*-mark.png")})
    print(f"共 {len(pairs)} 对样本\n")
    for name in pairs:
        st = mark_stats(CAP / f"{name}-mark.png")
        if st is None:
            print(f"{name[:12]}  跳过")
            continue
        shape, ch, ratio, bbox = st
        print(f"{name[:12]}  mark={shape[:2]} ch={ch} alpha>128占比={ratio:.2f} 有效bbox={bbox}")
        try:
            m = cv2.imread(str(CAP / f"{name}-mark.png"), cv2.IMREAD_UNCHANGED)
            if m is None or m.ndim < 2:
                print("  读取失败，跳过可视化")
                continue
            a = m[..., 3] if m.ndim == 3 and m.shape[2] == 4 else np.full(m.shape[:2], 255, np.uint8)
            cv2.imwrite(str(OUT / f"{name[:12]}-alpha.png"), a)
        except Exception as e:
            print(f"  可视化失败: {e}")
    print(f"\nalpha 预览已写入 {OUT}/")


if __name__ == "__main__":
    main()