#!/usr/bin/env python3
"""Fetch the top 20 most-starred public Python repos and write the artifact."""
import json
import urllib.request
import urllib.parse
from datetime import datetime, timezone

OUT = "/root/.hermes/wizard-outputs/ledger/python-repos-top20.json"
CSV_OUT = "/root/.hermes/wizard-outputs/ledger/python-repos-top20.csv"

QUERY = "language:python"
PAGE = 20

def fetch(url):
    req = urllib.request.Request(url, headers={"User-Agent": "ledger-wizard"})
    with urllib.request.urlopen(req, timeout=60) as r:
        return json.loads(r.read().decode("utf-8"))

def main():
    q = urllib.parse.quote(QUERY)
    url = f"https://api.github.com/search/repositories?q={q}&sort=stars&order=desc&per_page={PAGE}"
    data = fetch(url)

    items = data.get("items", [])
    # search API returns already-ordered by stars desc; we still enforce order.
    rows = []
    for i, it in enumerate(items, start=1):
        rows.append({
            "rank": i,
            "name": it["name"],
            "full_name": it["full_name"],
            "owner": it["owner"]["login"],
            "stars": it["stargazers_count"],
            "url": it["html_url"],
            "description": (it.get("description") or "").replace("\n", " ")[:400],
        })

    payload = {
        "source": "https://api.github.com/search/repositories",
        "query": f"language:python sort:stars order:desc per_page={PAGE}",
        "total_count": data.get("total_count"),
        "incomplete_results": data.get("incomplete_results"),
        "fetched_at": datetime.now(timezone.utc).isoformat(),
        "rows": rows,
    }

    with open(OUT, "w", encoding="utf-8") as f:
        json.dump(payload, f, indent=2)

    with open(CSV_OUT, "w", encoding="utf-8") as f:
        f.write("rank,name,owner,stars,url,description\n")
        for r in rows:
            desc = r["description"].replace(",", " ").replace("\n", " ")
            f.write(f'{r["rank"]},{r["name"]},{r["owner"]},{r["stars"]},{r["url"]},{desc}\n')

    print(f"wrote {OUT}")
    print(f"wrote {CSV_OUT}")
    print(f"total_count={payload['total_count']} rows={len(rows)} top_stars={rows[0]['stars']}")
    print("top:", rows[0]["full_name"], rows[0]["stars"])

if __name__ == "__main__":
    main()