python - directory path types with argparse

Question

My python script needs to read files from a directory passed on the command line. I have defined a readable_dir type as below to be used with argparse for validating that the directory passed on the command line is existent and readable. Additionally, a default value (/tmp/non_existent_dir in the example below) has also been specified for the directory argument. The problem here is that argparse invokes readable_dir() on the default value even in a situation where a directory argument is explicitly passed in on the command line. This causes the script to crap out as the default path /tmp/non_existent_dir does not exist in a context where a directory is explicitly passed in on the command line. I could get around this by not specifying a default value and making this argument mandatory, or by deferring the validation until later in the script but is a more elegant solution that anyone is aware of?

#!/usr/bin/python
import argparse
import os

def readable_dir(prospective_dir):
  if not os.path.isdir(prospective_dir):
    raise Exception("readable_dir:{0} is not a valid path".format(prospective_dir))
  if os.access(prospective_dir, os.R_OK):
    return prospective_dir
  else:
    raise Exception("readable_dir:{0} is not a readable dir".format(prospective_dir))

parser = argparse.ArgumentParser(description='test', fromfile_prefix_chars="@")
parser.add_argument('-l', '--launch_directory', type=readable_dir, default='/tmp/non_existent_dir')
args = parser.parse_args()

Answer 1

I submitted a patch for "path arguments" to the Python standard library mailing list a few months ago.

With this PathType class, you can simply specify the following argument type to match only an existing directory--anything else will give an error message:

type = PathType(exists=True, type='dir')

Here's the code, which could be easily modified to require specific file/directory permissions as well:

from argparse import ArgumentTypeError as err
import os

class PathType(object):
    def __init__(self, exists=True, type='file', dash_ok=True):
        '''exists:
                True: a path that does exist
                False: a path that does not exist, in a valid parent directory
                None: don't care
           type: file, dir, symlink, None, or a function returning True for valid paths
                None: don't care
           dash_ok: whether to allow "-" as stdin/stdout'''

        assert exists in (True, False, None)
        assert type in ('file','dir','symlink',None) or hasattr(type,'__call__')

        self._exists = exists
        self._type = type
        self._dash_ok = dash_ok

    def __call__(self, string):
        if string=='-':
            # the special argument "-" means sys.std{in,out}
            if self._type == 'dir':
                raise err('standard input/output (-) not allowed as directory path')
            elif self._type == 'symlink':
                raise err('standard input/output (-) not allowed as symlink path')
            elif not self._dash_ok:
                raise err('standard input/output (-) not allowed')
        else:
            e = os.path.exists(string)
            if self._exists==True:
                if not e:
                    raise err("path does not exist: '%s'" % string)

                if self._type is None:
                    pass
                elif self._type=='file':
                    if not os.path.isfile(string):
                        raise err("path is not a file: '%s'" % string)
                elif self._type=='symlink':
                    if not os.path.symlink(string):
                        raise err("path is not a symlink: '%s'" % string)
                elif self._type=='dir':
                    if not os.path.isdir(string):
                        raise err("path is not a directory: '%s'" % string)
                elif not self._type(string):
                    raise err("path not valid: '%s'" % string)
            else:
                if self._exists==False and e:
                    raise err("path exists: '%s'" % string)

                p = os.path.dirname(os.path.normpath(string)) or '.'
                if not os.path.isdir(p):
                    raise err("parent path is not a directory: '%s'" % p)
                elif not os.path.exists(p):
                    raise err("parent directory does not exist: '%s'" % p)

        return string