core-python/scripts/validate_datasets.py

"""CLI bootstrap dataset validācijai."""

from __future__ import annotations

import argparse
import sys
from pathlib import Path

PROJECT_ROOT = Path(__file__).resolve().parents[1]
if str(PROJECT_ROOT) not in sys.path:
    sys.path.insert(0, str(PROJECT_ROOT))

from maris_core.data.validator import (  # noqa: E402
    DatasetValidationError,
    format_summary,
    validate_dataset_dir,
)


def main() -> int:
    """Palaiž bootstrap dataset validāciju."""
    parser = argparse.ArgumentParser(description="Validē Maris bootstrap dataset JSONL failus")
    parser.add_argument(
        "--profile",
        choices=("auto", "bootstrap", "eval"),
        default="auto",
        help="Validācijas profils: bootstrap, eval vai auto (pēc direktorijas nosaukuma).",
    )
    parser.add_argument(
        "dataset_dir",
        nargs="?",
        default=PROJECT_ROOT.parent / "data",
        type=Path,
        help="Bootstrap dataset direktorija",
    )
    args = parser.parse_args()

    try:
        summary = validate_dataset_dir(args.dataset_dir, profile=args.profile)
    except DatasetValidationError as exc:
        print(str(exc), file=sys.stderr)
        return 1

    print(format_summary(summary))
    return 0


if __name__ == "__main__":
    raise SystemExit(main())