from __future__ import annotations import argparse import json import logging import sys from pathlib import Path sys.path.insert(0, str(Path(__file__).resolve().parent.parent)) from riemann.data import prepare_all, DATA_DIR def main() -> None: logging.basicConfig( level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s" ) parser = argparse.ArgumentParser(description=__doc__) parser.add_argument( "--only", nargs="*", default=None, help="only run these loader names, e.g. --only fable", ) parser.add_argument( "--append", action="store_true", help="append to existing corpus files instead of overwriting them", ) parser.add_argument( "--data-dir", default=str(DATA_DIR), help="where to write pretrain_corpus.txt and ntk_finetune.jsonl", ) args = parser.parse_args() result = prepare_all( data_dir=Path(args.data_dir), only=args.only, append=args.append ) print(json.dumps(result, indent=2)) if __name__ == "__main__": main()