mikav / scripts /deduplicate.py
mikav-dev's picture
Initial Mikav project scaffold
0912b10 verified
Raw
History Blame Contribute Delete
320 Bytes
"""Deduplicate cleaned text."""
from pathlib import Path
def main() -> None:
input_dir = Path("data/cleaned")
output_dir = Path("data/deduplicated")
output_dir.mkdir(parents=True, exist_ok=True)
print(f"Add deduplication logic for {input_dir} -> {output_dir}")
if __name__ == "__main__":
main()