"""One-off dev script: fetch and trim public airport/airline reference data.

Not run inside the container - output is committed to data/*.csv and loaded
at runtime by reference_data.py with zero network dependency.

Usage: python3 scripts/build_reference_data.py
"""

import csv
import io
import urllib.request
from pathlib import Path

DATA_DIR = Path(__file__).resolve().parent.parent / "data"

AIRPORTS_URL = "https://davidmegginson.github.io/ourairports-data/airports.csv"
AIRLINES_URL = "https://raw.githubusercontent.com/jpatokal/openflights/master/data/airlines.dat"

USER_AGENT = "Mozilla/5.0 (compatible; boarding-pass-pipeline/1.0)"


def fetch(url: str) -> bytes:
    req = urllib.request.Request(url, headers={"User-Agent": USER_AGENT})
    with urllib.request.urlopen(req, timeout=30) as resp:
        return resp.read()


def build_airports() -> None:
    raw = fetch(AIRPORTS_URL).decode("utf-8", errors="replace")
    reader = csv.DictReader(io.StringIO(raw))
    out_path = DATA_DIR / "airports.csv"
    seen = set()
    rows = []
    for row in reader:
        iata = (row.get("iata_code") or "").strip().upper()
        icao = (row.get("ident") or row.get("gps_code") or "").strip().upper()
        name = (row.get("name") or "").strip()
        if not iata or not icao or len(iata) != 3 or len(icao) != 4:
            continue
        if iata in seen:
            continue
        seen.add(iata)
        rows.append((iata, icao, name))
    rows.sort(key=lambda r: r[0])
    with out_path.open("w", newline="", encoding="utf-8") as f:
        writer = csv.writer(f)
        writer.writerow(["iata", "icao", "name"])
        writer.writerows(rows)
    print(f"wrote {len(rows)} airports to {out_path}")


def build_airlines() -> None:
    raw = fetch(AIRLINES_URL).decode("utf-8", errors="replace")
    reader = csv.reader(io.StringIO(raw))
    out_path = DATA_DIR / "airlines.csv"
    seen = set()
    rows = []
    for cols in reader:
        # OpenFlights airlines.dat columns (no header):
        # id, name, alias, iata, icao, callsign, country, active
        if len(cols) < 5:
            continue
        name = cols[1].strip().strip('"')
        iata = cols[3].strip().strip('"').upper()
        icao = cols[4].strip().strip('"').upper()
        if not iata or not icao or iata == r"\N" or icao == r"\N":
            continue
        if len(iata) != 2 or len(icao) != 3:
            continue
        if iata in seen:
            continue
        seen.add(iata)
        rows.append((iata, icao, name))
    rows.sort(key=lambda r: r[0])
    with out_path.open("w", newline="", encoding="utf-8") as f:
        writer = csv.writer(f)
        writer.writerow(["iata", "icao", "name"])
        writer.writerows(rows)
    print(f"wrote {len(rows)} airlines to {out_path}")


if __name__ == "__main__":
    DATA_DIR.mkdir(exist_ok=True)
    build_airports()
    build_airlines()