#!/usr/bin/env python3
from __future__ import annotations

import argparse
import asyncio
import os

from config import init_config

from scrape.auth import get_access_token
from scrape.build_snapshot import build_snapshot

from scrape.persist_api import (
    save_nav,
    upsert_product,
    log_product_result,
    capture_listing,
    save_subcategory_redirects,
)



# ------------------------ CLI ------------------------
def main() -> None:
    ap = argparse.ArgumentParser()
    ap.add_argument("--out", default="./snapshot", help="(unused for JSON now; kept for compatibility)")
    ap.add_argument("--max-pages", type=int, default=999)
    ap.add_argument("--max-products", type=int, default=200000)
    ap.add_argument("--concurrency", type=int, default=16)
    ap.add_argument("--user", default=os.getenv("SUMA_USER"))
    ap.add_argument("--pass", dest="password", default=os.getenv("SUMA_PASS"))
    ap.add_argument("--db", dest="database_url", default=os.getenv("DATABASE_URL", "postgresql+asyncpg://user:pass@localhost:5432/suma"))

    args = ap.parse_args()

    # Ensure we have an OAuth token before starting (triggers device flow if needed)
    get_access_token(require=True)

    asyncio.run(init_config())
    asyncio.run(
        build_snapshot(
            args.concurrency,
            args.user,
            args.password,
            save_nav,
            capture_listing,
            upsert_product,
            log_product_result,
            save_subcategory_redirects,
            #save_link_reports
        )
    )


if __name__ == "__main__":
    main()