# -*- coding: utf-8 -*-
"""OpenCreator 文件树分片拉取（避 recursive=1 整树响应过大）
来源：GitHub git/trees API —— /repos/krillinai/OpenCreator/git/trees/<sha>?recursive=1
用法：python _opencreator_tree.py            # 拉取并把每片落盘到 取证/opencreator/
输出：tree_<name>.json（逐片），并打印 truncated 与条目数（可复算）
"""
import json, os, sys, time, urllib.request, urllib.error

REPO = "krillinai/OpenCreator"
HERE = os.path.dirname(os.path.abspath(__file__))
OUT = os.path.join(HERE, "opencreator")
os.makedirs(OUT, exist_ok=True)

# 顶层目录 -> sha（取自第 1 棒已拉的 opencreator.tree.top.json，2026-10-07 16:14）
TOPS = {
    ".github":   "6a9815862c407991905d5d57cb41fcd1082acf70",
    "apps":      "45bca5790d008582b2f0b83acd5d0282c17f1e02",
    "assets":    "44fa661ea45db7aab343c7d541826a622234d2df",
    "packages":  "1f1151f4b61203f37cb39a716fc5d750f9e773b2",
    "resources": "7a1e6ecd1b55ae1ac8cf7d88aaf5155a860ee4f2",
    "runtime":   "0c8a1a4247afcc15dbd04c7995b58530a1ac1e8f",
    "scripts":   "f28df95991fe5c753464d5049b99fdddda6cc27c",
    "skills":    "40072888acdf2a87b463f174842558c52ba36168",
    "template":  "553e77dffa5a1d746cda0745c22f9cf60897b00b",
    "docs/specs":"8d12278b08121a91ec71db6c83ce0727a6669817",
}

def get(url, tries=3):
    last = None
    for i in range(tries):
        try:
            req = urllib.request.Request(url, headers={
                "User-Agent": "wb-research/1.0",
                "Accept": "application/vnd.github+json",
            })
            with urllib.request.urlopen(req, timeout=45) as r:
                return json.loads(r.read().decode("utf-8"))
        except Exception as e:
            last = e
            sys.stderr.write("  retry %d %s -> %s\n" % (i + 1, url, e))
            time.sleep(2)
    raise last

def main():
    summary = {}
    for name, sha in TOPS.items():
        url = "https://api.github.com/repos/%s/git/trees/%s?recursive=1" % (REPO, sha)
        d = get(url)
        safe = name.replace("/", "_")
        p = os.path.join(OUT, "tree_%s.json" % safe)
        with open(p, "w", encoding="utf-8") as f:
            json.dump(d, f, ensure_ascii=False, indent=1)
        n = len(d.get("tree", []))
        blobn = sum(1 for e in d.get("tree", []) if e.get("type") == "blob")
        summary[name] = {"sha": sha, "truncated": d.get("truncated", False),
                         "entries": n, "blobs": blobn, "file": os.path.basename(p)}
        print("%-12s truncated=%-5s entries=%-5d blobs=%-5d -> %s"
              % (name, d.get("truncated", False), n, blobn, os.path.basename(p)))
    with open(os.path.join(OUT, "_tree_summary.json"), "w", encoding="utf-8") as f:
        json.dump(summary, f, ensure_ascii=False, indent=1)

if __name__ == "__main__":
    main()