# Trouve-KA — chargeur de seeds
# Author: Simon-Pierre Boucher
# Contact: contact@spboucher.ai

"""Charge les seeds dans le frontier avec priorité maximale.

Usage : python -m trouveka.crawler.seed [chemin/vers/seeds.txt]
"""

import asyncio
import pathlib
import sys

from trouveka.config import get_settings
from trouveka.database import Database, run_migrations
from trouveka.logging import get_logger
from trouveka.shared import canonicalize_url, extract_domain

log = get_logger("crawler.seed")

DEFAULT_SEEDS = pathlib.Path(__file__).resolve().parents[2] / "scripts" / "bootstrap-seeds" / "seeds.txt"


async def load_seeds(path: pathlib.Path) -> int:
    settings = get_settings()
    applied = await run_migrations(settings.database_url)
    if applied:
        log.info("migrations appliquées", extra={"ctx": {"files": applied}})

    db = Database(settings.database_url, pool_min=1, pool_max=3)
    await db.connect()
    added = 0
    try:
        for line in path.read_text(encoding="utf-8").splitlines():
            line = line.strip()
            if not line or line.startswith("#"):
                continue
            url = canonicalize_url(line)
            domain = extract_domain(url) if url else None
            if not url or not domain:
                log.info("seed ignorée (URL invalide)", extra={"ctx": {"line": line}})
                continue
            if await db.enqueue_url(url, domain, priority=1.0, depth=0, is_seed=True):
                added += 1
    finally:
        await db.close()
    log.info("seeds chargées", extra={"ctx": {"added": added, "file": str(path)}})
    return added


def main() -> None:
    path = pathlib.Path(sys.argv[1]) if len(sys.argv) > 1 else DEFAULT_SEEDS
    asyncio.run(load_seeds(path))


if __name__ == "__main__":
    main()