a function in Python that given a string path to a directory, converts it to a pathlib Path object and then loads all text files in the directory. The text files are sorted using the natsorted function and then each file is read and appended to a new file that is all the text files files merged. each file has its filename printed to the file bef…

merge_text_files.py

from natsort import natsorted
from pathlib import Path
import argparse


def merge_files(path, output_path=None, outname=None):
    """
    Given a path to a directory, merge all text files in the directory.
    """
    path = Path(path)
    output_path = Path(output_path) if output_path else path.parent
    outname = outname if outname else f"merged_{path.name}.txt"
    files = natsorted(path.glob("*.txt"))
    with open(output_path / outname, "w", encoding="utf-8", errors="utf-8") as outfile:
        for file in files:
            with open(file) as infile:
                outfile.write(f"{file.name}\n")
                outfile.write(infile.read())
                outfile.write("\n")

    return output_path / outname


def get_parser():
    """
    get_parser - a helper function for the argparse module
    """
    parser = argparse.ArgumentParser("merge_text_dir.py")
    parser.add_argument(
        "-i",
        "--input-path",
        type=str,
        help="path to directory of text files",
        required=True,
    )
    parser.add_argument(
        "-o",
        "--output-path",
        type=str,
        required=False,
        default=None,
        help="path to output directory (optional)",
    )
    parser.add_argument(
        "-n",
        "--outname",
        type=str,
        required=False,
        default=None,
        help="name of output file (optional)",
    )
    return parser


if __name__ == "__main__":

    args = get_parser().parse_args()

    input_path = args.input_path
    output_path = args.output_path
    outname = args.outname

    output_file = merge_files(input_path, output_path, outname)

    print(f"Merged files into {output_file.name}")