# -*- coding: utf-8 -*-
r'''清理 EzHub 发行版里重复的附件。

为什么会重复：
    release_all.py 发现标签已有发行版时会"复用它"，
    但**没有先删同名附件**，于是每跑一次就多传一遍。
    我调试时跑了几次，同一个文件就堆了 2~3 份。

这个脚本：同名附件只保留最新的一份，其余删掉。
（Gitea 的附件用 id 区分，创建时间看 created_at。）
'''
from __future__ import annotations

import json
import sys
import urllib.error
import urllib.request
from collections import defaultdict
from pathlib import Path

TOKEN = (Path.home() / ".ykxmz" / "ezhub_token").read_text(
    encoding="utf-8").strip()
API = "https://git.261826.xyz/api/v1/repos/xmz/ykxmz"
TAG = "v1.8.0"
HEAD = {"Authorization": "token " + TOKEN, "User-Agent": "ykxmz-clean"}


def call(url: str, method: str = "GET"):
    req = urllib.request.Request(url, method=method, headers=HEAD)
    try:
        with urllib.request.urlopen(req, timeout=60) as resp:
            text = resp.read().decode("utf-8", "replace")
            return resp.status, (json.loads(text) if text.strip() else {})
    except urllib.error.HTTPError as exc:
        body = exc.read().decode("utf-8", "replace")[:200]
        return exc.code, body


def main() -> int:
    dry = "--dry" in sys.argv

    status, release = call("%s/releases/tags/%s" % (API, TAG))
    if status != 200:
        print("  [失败] 取发行版 HTTP %s: %s" % (status, release))
        return 1
    rid = release["id"]
    assets = release.get("assets") or []
    print("  发行版 id=%s，附件 %d 个" % (rid, len(assets)))

    # 按文件名分组
    groups = defaultdict(list)
    for a in assets:
        groups[a.get("name") or "?"].append(a)

    print()
    print("  分组情况:")
    to_delete = []
    for name, items in sorted(groups.items()):
        # 新的排在前面（created_at 降序）
        items.sort(key=lambda x: x.get("created_at") or "", reverse=True)
        keep = items[0]
        print("    %-32s 共 %d 份，保留 id=%s（%s）"
              % (name, len(items), keep.get("id"),
                 (keep.get("created_at") or "")[:19]))
        for extra in items[1:]:
            print("        删 id=%s（%s）" % (extra.get("id"),
                                              (extra.get("created_at")
                                               or "")[:19]))
            to_delete.append(extra)

    if not to_delete:
        print()
        print("  ✓ 没有重复，不用清理")
        return 0

    print()
    if dry:
        print("  演练：会删 %d 个（去掉 --dry 真删）" % len(to_delete))
        return 0

    print("  开始删除 %d 个重复附件…" % len(to_delete))
    ok = 0
    for asset in to_delete:
        status, body = call("%s/releases/%s/assets/%s"
                            % (API, rid, asset.get("id")), method="DELETE")
        if status in (200, 204):
            print("    ✓ 删了 id=%s %s" % (asset.get("id"),
                                           asset.get("name")))
            ok += 1
        else:
            print("    ✗ id=%s HTTP %s %s" % (asset.get("id"), status, body))

    print()
    print("  删除 %d/%d" % (ok, len(to_delete)))

    # 复查
    status, release = call("%s/releases/tags/%s" % (API, TAG))
    assets = release.get("assets") or []
    print()
    print("  现在剩 %d 个附件:" % len(assets))
    for a in assets:
        print("    %-32s %8.2f MB"
              % (a.get("name"), (a.get("size") or 0) / 1024 / 1024))
    return 0


if __name__ == "__main__":
    sys.exit(main())