"""Batch-ingest mock KB/playbook files and emit normalized knowledge JSON documents."""
from __future__ import annotations

import json
from dataclasses import asdict
from pathlib import Path

from pipeline.transforms.normalize_kb import load_and_normalize_kb


def ingest_kb(input_dir: str | Path, output_dir: str | Path) -> list[Path]:
    input_dir = Path(input_dir)
    output_dir = Path(output_dir)
    output_dir.mkdir(parents=True, exist_ok=True)

    written: list[Path] = []
    for src in sorted(input_dir.rglob("*.json")):
        normalized = load_and_normalize_kb(src)
        dest = output_dir / f"{normalized.id}.json"
        with dest.open("w", encoding="utf-8") as f:
            json.dump(asdict(normalized), f, ensure_ascii=False, indent=2)
        written.append(dest)
    return written


def main() -> None:
    import argparse

    parser = argparse.ArgumentParser(description="Normalize a directory of mock KB/playbook JSON files.")
    parser.add_argument("--input-dir", default="evaluation/datasets/mock_kb", help="Directory containing raw mock KB/playbook files")
    parser.add_argument("--output-dir", default="evaluation/datasets/normalized_kb", help="Directory to write normalized KB/playbook files")
    args = parser.parse_args()

    written = ingest_kb(args.input_dir, args.output_dir)
    print(f"normalized_kb={len(written)}")
    for path in written:
        print(path)


if __name__ == "__main__":
    main()