"""Reports when a scrape last ran and when cron will next run it.

"Last ran" is read from the mtime of the scraper's output file - true
regardless of how/when the scrape was actually invoked. "Next run" requires
telling this module the cron schedule via an env var (there's no reliable,
portable way to introspect another process's crontab from here), given as
a standard 5-field cron expression, e.g. "0 * * * *".
"""

from datetime import datetime
from pathlib import Path
from typing import Optional

from croniter import croniter


def _now_local() -> datetime:
    return datetime.now().astimezone()


def _file_mtime_local(path: Path) -> Optional[datetime]:
    try:
        return datetime.fromtimestamp(path.stat().st_mtime).astimezone()
    except FileNotFoundError:
        return None


def _next_cron_run(cron_expr: str, after: datetime) -> Optional[datetime]:
    try:
        naive_after = after.replace(tzinfo=None)
        return croniter(cron_expr, naive_after).get_next(datetime).astimezone()
    except (ValueError, KeyError):
        return None


def get_schedule_info(path: Path, cron_expr: Optional[str]) -> dict:
    """Build the last/next-scrape block for one scraper output file.

    ``cron_expr`` is that scrape's cron expression (e.g. "0 * * * *");
    None/invalid -> next-run fields are null.
    """
    now = _now_local()
    cron_expr = (cron_expr or "").strip() or None

    last_scrape_at = _file_mtime_local(path)
    next_scrape_at = _next_cron_run(cron_expr, now) if cron_expr else None

    return {
        "cron_schedule": cron_expr,
        "last_scrape_at": last_scrape_at.isoformat() if last_scrape_at else None,
        "seconds_since_last_scrape": (
            round((now - last_scrape_at).total_seconds()) if last_scrape_at else None
        ),
        "next_scrape_at": next_scrape_at.isoformat() if next_scrape_at else None,
        "seconds_until_next_scrape": (
            round((next_scrape_at - now).total_seconds()) if next_scrape_at else None
        ),
    }