mikav / scripts /clean_text.py
mikav-dev's picture
Initial Mikav project scaffold
0912b10 verified
Raw
History Blame Contribute Delete
395 Bytes
"""Clean Malayalam text files."""
from pathlib import Path
def clean_line(line: str) -> str:
return " ".join(line.strip().split())
def main() -> None:
input_dir = Path("data/raw")
output_dir = Path("data/cleaned")
output_dir.mkdir(parents=True, exist_ok=True)
print(f"Add cleaning logic for files in {input_dir} -> {output_dir}")
if __name__ == "__main__":
main()