Simple script to count character frequencies in text files

character_frequency_counter.py

#!/usr/bin/python3


import argparse
import string
from os.path import join
from glob import glob
from collections import Counter


def main():
    parser = argparse.ArgumentParser()
    parser.add_argument("directory", help="directory to scan")
    parser.add_argument("extensions", help="file extensions, e.g. \"c,h\"")
    parser.add_argument("-l", "--letters", help="count ASCII letters",
        action="store_true")
    parser.add_argument("-d", "--digits", help="count digits",
        action="store_true")
    parser.add_argument("-p", "--punctuation", help="count punctuation",
        action="store_true")
    parser.add_argument("-w", "--whitespace", help="count whitespace",
        action="store_true")
    args = parser.parse_args()

    # Build the list of relevant file paths
    file_paths = []
    for extension in args.extensions.split(','):
        ext = "**/*." + extension.strip()
        file_paths.extend(glob(join(args.directory, ext), recursive=True))
    
    # For each file, add the character counts to the total
    counter = Counter()
    for file_path in file_paths:
        counter += Counter(open(file_path, 'r').read())
    
    chars_to_count = ((string.ascii_letters if args.letters else "")
        + (string.digits if args.digits else "")
        + (string.punctuation if args.punctuation else "")
        + (string.whitespace if args.whitespace else ""))

    # Print results
    frequencies = dict(counter)
    for char in sorted(frequencies, key=frequencies.get, reverse=True):
        if (char in chars_to_count):
            print (f"{repr(char)} \t {frequencies[char]}")


if __name__ == "__main__":
    main()