This script searches for Python files in a given directory and its subdirectories, then finds and prints the longest line of each file if the line length is greater than a specified threshold.

find_longest_line_in_files.py

"""
This script searches for Python files in a given directory and its
subdirectories, then finds and prints the longest line of each file if the
line length is greater than a specified threshold.

Output:
    - The file path.
    - The line number of the longest line.
    - The first 100 characters of the longest line.
    - The length of the longest line.

Args in main():
    dir_root (str): The root directory to search for Python files.
    length_threshold (int, optional): The minimum length required to print
    the line. Defaults to 80.
"""

import pathlib


def get_python_files(dir_root: str) -> list[str]:
    file_list = [str(p) for p in pathlib.Path(dir_root).glob('**/*.py')]
    return file_list


def find_longest_line(file_path: str) -> tuple[str, int, int]:
    with open(file_path) as f:
        max_length_line = ''
        max_length = 0
        line_number = 0
        for i, line in enumerate(f, start=1):
            if len(line) > max_length:
                max_length_line = line
                max_length = len(line)
                line_number = i
    return max_length_line, max_length, line_number


def print_longest_line_info(
    file_path: str,
    max_length_line: str,
    max_length: int,
    line_number: int,
    length_threshold: int = 80,
    print_length: int = 100,
):
    if max_length > length_threshold:
        print(file_path)
        print(f"Line {line_number}: {max_length_line[:print_length]}")
        print(f"Length: {max_length}")
        print("---")


def main():
    dir_to_check = '/path/to/your/dir/'
    python_files = get_python_files(dir_to_check)
    length_threshold = 80

    for file_path in python_files:
        max_length_line, max_length, line_number = find_longest_line(file_path)
        print_longest_line_info(
            file_path, max_length_line, max_length, line_number, length_threshold
        )


if __name__ == '__main__':
    main()