import csv, json, sys, urllib.request

EXPECTED_COLS = ["iso3", "iso2", "name", "region", "incomeLevel", "capital", "latitude", "longitude"]
CSV_PATH = "/root/troupe-standup/wizard-work/ledger/countries-table-2026-11-02.csv"

def fetch():
    url = "https://api.worldbank.org/v2/country/all?format=json&per_page=1000"
    req = urllib.request.Request(url, headers={"User-Agent": "ledger-wizard-extract/1.0"})
    with urllib.request.urlopen(req, timeout=60) as r:
        payload = json.load(r)
    out = []
    for rec in payload[1]:
        out.append((rec.get("id", ""),
                    rec.get("iso2Code", ""),
                    rec.get("name", ""),
                    ((rec.get("region") or {}).get("value", "")),
                    ((rec.get("incomeLevel") or {}).get("value", "")),
                    rec.get("capitalCity", ""),
                    rec.get("latitude", ""),
                    rec.get("longitude", "")))
    return out

def main():
    fresh = sorted(fetch())
    with open(CSV_PATH, newline="") as f:
        reader = csv.reader(f)
        header = next(reader)
        rows = [tuple(r) for r in reader]
    rows = sorted(rows)
    errors = []
    if header != EXPECTED_COLS:
        errors.append("header mismatch: %r" % (header,))
    if len(rows) != len(fresh):
        errors.append("row count mismatch: artifact=%d fresh=%d" % (len(rows), len(fresh)))
    if rows != fresh:
        for i, (a, b) in enumerate(zip(rows, fresh)):
            if a != b:
                errors.append("first diff at row %d: artifact=%r fresh=%r" % (i, a, b))
                break
    if errors:
        print("FAIL")
        for e in errors:
            print(" -", e)
        sys.exit(1)
    print("OK: %d rows match fresh World Bank extraction; header=%r" % (len(rows), header))

if __name__ == "__main__":
    main()