#!/usr/bin/env python3
"""Generate catalog.json — the reviewable list of every skill in this repo.

Usage: python3 scripts/generate-catalog.py [--check]
  (default) write catalog.json
  --check   fail if catalog.json is out of date (for CI)
"""
from __future__ import annotations

import hashlib
import json
import re
import sys
from datetime import datetime, timezone
from pathlib import Path

ROOT = Path(__file__).resolve().parent.parent
CATALOG = ROOT / "catalog.json"


def frontmatter(text: str) -> dict:
    if not text.startswith("---"):
        return {}
    end = text.find("\n---", 3)
    if end == -1:
        return {}
    data: dict = {}
    metadata: dict = {}
    key = None
    for line in text[3:end].splitlines():
        if not line.strip():
            continue
        m = re.match(r"^([A-Za-z0-9_-]+):\s*(.*)$", line)
        if m:
            key = m.group(1)
            data[key] = m.group(2).strip().strip('"').strip("'")
            continue
        m = re.match(r"^\s+([A-Za-z0-9_-]+):\s*(.*)$", line)
        if m and key == "metadata":
            metadata[m.group(1)] = m.group(2).strip().strip('"').strip("'")
    if metadata:
        data["metadata"] = metadata
    return data


def build() -> dict:
    skills = []
    for plugin_json in sorted(ROOT.glob("skills-*/*-plugin/.claude-plugin/plugin.json")):
        plugin_dir = plugin_json.parent.parent
        meta = json.loads(plugin_json.read_text(encoding="utf-8"))
        skill_files = sorted((plugin_dir / "skills").rglob("SKILL.md"))
        if not skill_files:
            continue
        skill_md = skill_files[0]
        fm = frontmatter(skill_md.read_text(encoding="utf-8", errors="replace"))
        desc = fm.get("description", "")
        body = skill_md.read_text(encoding="utf-8", errors="replace")
        skills.append(
            {
                "name": meta.get("install_name") or fm.get("name"),
                "category": meta.get("dir_category"),
                "version": meta.get("version"),
                "status": meta.get("status", "promoted"),
                "invocation": (fm.get("metadata") or {}).get("invocation", "model-invoked"),
                "description": desc,
                "description_len": len(desc),
                "path": str(skill_md.relative_to(ROOT)),
                "digest": hashlib.sha256(body.encode("utf-8")).hexdigest()[:16],
            }
        )
    counts: dict = {}
    for skill in skills:
        key = f"{skill['status']}/{skill['invocation']}"
        counts[key] = counts.get(key, 0) + 1
    return {
        "repo": "ai-proj-helper",
        "generated_at": datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ"),
        "total": len(skills),
        "counts": counts,
        "skills": skills,
    }


def main() -> int:
    catalog = build()
    text = json.dumps(catalog, ensure_ascii=False, indent=2) + "\n"
    if "--check" in sys.argv:
        if not CATALOG.is_file():
            print("catalog.json 不存在，请运行 python3 scripts/generate-catalog.py")
            return 1
        current = json.loads(CATALOG.read_text(encoding="utf-8"))
        current.pop("generated_at", None)
        fresh = dict(catalog)
        fresh.pop("generated_at", None)
        if current != fresh:
            print("catalog.json 已过期，请重新生成")
            return 1
        print("catalog.json 是最新的")
        return 0
    CATALOG.write_text(text, encoding="utf-8")
    print(f"写入 {CATALOG.relative_to(ROOT)}：{catalog['total']} 个技能 {catalog['counts']}")
    return 0


if __name__ == "__main__":
    raise SystemExit(main())