scripts/validate_u2_schema.py

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

import argparse
import json
from pathlib import Path


REQUIRED = ("qhash", "question", "gold_answer")


def main() -> None:
    ap = argparse.ArgumentParser()
    ap.add_argument("--input", required=True, help="Path to non-STEM QA JSONL file")
    args = ap.parse_args()

    path = Path(args.input)
    if not path.exists():
        raise SystemExit(f"Input file does not exist: {path}")

    n = 0
    with path.open("r", encoding="utf-8", errors="ignore") as f:
        for i, line in enumerate(f, 1):
            s = line.strip()
            if not s:
                continue
            n += 1
            try:
                obj = json.loads(s)
            except Exception as exc:  # noqa: BLE001
                raise SystemExit(f"Line {i} is not valid JSON: {exc}") from exc
            missing = [k for k in REQUIRED if k not in obj]
            if missing:
                raise SystemExit(f"Line {i} missing fields: {missing}")

    print(f"OK: {n} rows validated with fields {REQUIRED}")


if __name__ == "__main__":
    main()