Check Files in a Directory for Bad Unicode Characters

check.py

from unicodedata import category
import os


class FileSet:
    def __init__(self, path):
        self.path = path
        self.bad_files = self.__check_files()

    @staticmethod
    def __check_files():
        bad_files = []
        for path, directories, files in os.walk(self.path):
            for file in files:
                x = DataChecker(f"{path}/{file}").check_if_contains_control_characters()
                if len(x) > 0:
                    bad_files.append((f"{path}/{file}", x))
        return bad_files


class DataChecker:
    def __init__(self, filename):
        self.filename = filename
        self.good = ("\n", "\t", "\u0009", "\u000A", "\u000D")

    def check_if_contains_control_characters(self):
        bad_characters = []
        with open(self.filename, "r") as current_file:
            for line in current_file:
                for character in line:
                    if category(character) == "Cc" and character not in self.good:
                        bad_characters.append(
                            f"{category(character)} > {character.encode('unicode_escape')}"
                        )
        return bad_characters


if __name__ == "__main__":
    print(FileSet("data").bad_files)