Checking if CLI arguments are valid files/directories in Python

I frequently write Python scripts that require three command line arguments:

• config_file — A CSV configuration file

• input_dir — The directory containing the input files to be processed

• output_dir — The directory where the output files should be stored

I found myself copying/pasting two functions all the time: is_valid_file and is_valid_directory.

Questions

• How can I consolidate the is_valid_file and is_valid_directory functions to eliminate duplicate code?

• Is there a better way to check that files/directories provided in CLI arguments actually exist?

Code

Here is the code for process_the_data.py:

if __name__ == "__main__":
    # Process the arguments
    import argparse
    import arghelper
    parser = argparse.ArgumentParser(
        description='Process the data.')
    parser.add_argument(
        'config_file',
        help='CSV configuration file.',
        metavar='FILE', type=lambda x: arghelper.is_valid_file(parser, x))
    parser.add_argument(
        'input_dir',
        help='Directory containing the input files.',
        metavar='DIR', type=lambda x: arghelper.is_valid_directory(parser, x))
    parser.add_argument(
        'output_dir',
        help='Directory where the output files should be saved.',
        metavar='DIR', type=lambda x: arghelper.is_valid_directory(parser, x))
    args = parser.parse_args()

Here is the code for arghelper.py:

import os

def is_valid_file(parser, arg):
    if not os.path.isfile(arg):
        parser.error('The file {} does not exist!'.format(arg))
    else:
        # File exists so return the filename
        return arg

def is_valid_directory(parser, arg):
    if not os.path.isdir(arg):
        parser.error('The directory {} does not exist!'.format(arg))
    else:
        # File exists so return the directory
        return arg

You can address some of this by subclassing ArgumentParser. This will allow you hide the lambda calls that may turn off some and leave you scratching your head if you come back to that file later.

Your Script

if __name__ == "__main__":
    # Process the arguments
    #import argparse
    import arghelper
    parser = arghelper.FileArgumentParser(
        description='Process the data.')
    parser.add_argument_with_check(
        'config_file',
        help='CSV configuration file.',
        metavar='FILE')
    parser.add_argument_with_check(
        'input_dir',
        help='Directory containing the input files.',
        metavar='DIR')
    parser.add_argument_with_check(
        'output_dir',
        help='Directory where the output files should be saved.',
        metavar='DIR')
    args = parser.parse_args()
    print args

New ArgHelper

import argparse
import os

class FileArgumentParser(argparse.ArgumentParser):
    def __is_valid_file(self, parser, arg):
        if not os.path.isfile(arg):
            parser.error('The file {} does not exist!'.format(arg))
        else:
            # File exists so return the filename
            return arg

    def __is_valid_directory(self, parser, arg):
        if not os.path.isdir(arg):
            parser.error('The directory {} does not exist!'.format(arg))
        else:
            # File exists so return the directory
            return arg

    def add_argument_with_check(self, *args, **kwargs):
        # Look for your FILE or DIR settings
        if 'metavar' in kwargs and 'type' not in kwargs:
            if kwargs['metavar'] is 'FILE':
                type=lambda x: self.__is_valid_file(self, x)
                kwargs['type'] = type
            elif kwargs['metavar'] is 'DIR':
                type=lambda x: self.__is_valid_directory(self, x)
                kwargs['type'] = type
        self.add_argument(*args, **kwargs)

StackExchange Code Review Q#28608, answer score: 4