"""检测 recordings/ 目录下内容完全相同（字节级重复）的录像文件。

根因：automate.py 的 ADB 自动化下载在滚动/点击时序上有已知问题，会把同一张
缩略图卡片的下载重复触发，导致同一段录像被存成多份文件名不同的拷贝。

先按文件大小分组（成本低，能筛掉绝大多数内容不同的文件），只对同大小的文件
再计算 MD5 确认是否真的内容相同，避免对全部文件逐个算 MD5 的开销。

只生成报告，不删除任何文件、不改动数据库。
"""
from collections import defaultdict

from analysis.config import PROJECT_ROOT, RECORDINGS_DIR
from analysis.hashing import compute_md5

REPORT_PATH = PROJECT_ROOT / "dedup_report.txt"


def find_duplicates():
    """返回 {md5: [文件路径, ...]}，只包含重复数≥2的分组。"""
    by_size = defaultdict(list)
    for path in RECORDINGS_DIR.rglob("*.mp4"):
        by_size[path.stat().st_size].append(path)

    by_md5 = defaultdict(list)
    for size, paths in by_size.items():
        if len(paths) < 2:
            continue
        for path in paths:
            by_md5[compute_md5(path)].append(path)

    return {md5: paths for md5, paths in by_md5.items() if len(paths) > 1}


def build_report():
    dup_groups = find_duplicates()

    lines = []
    total_extra_files = 0
    total_wasted_bytes = 0
    for md5, paths in sorted(dup_groups.items(), key=lambda kv: -len(kv[1])):
        paths = sorted(paths, key=lambda p: p.name)
        size = paths[0].stat().st_size
        extra = len(paths) - 1
        total_extra_files += extra
        total_wasted_bytes += extra * size

        lines.append(f"[{md5}] {len(paths)} 份重复，单份 {size / 1024:.1f} KB")
        for p in paths:
            lines.append(f"  {p.relative_to(PROJECT_ROOT)}")

    summary = (
        f"重复分组数：{len(dup_groups)}\n"
        f"多余拷贝数（可释放的文件数）：{total_extra_files}\n"
        f"可释放空间：{total_wasted_bytes / 1024 / 1024:.1f} MB\n"
    )

    return summary + "\n" + "\n".join(lines)


if __name__ == "__main__":
    print("===== 开始检测重复视频 =====")
    report = build_report()
    REPORT_PATH.write_text(report, encoding="utf-8")
    print(report.split("\n\n")[0])
    print(f"→ 详细清单已写入 {REPORT_PATH.relative_to(PROJECT_ROOT)}")
    print("===== 检测完成 =====")