Traverse irregular list of list

Question

I have a very irregular list of list containing a folder structure, and I want to iterate through the list and check whether that folder/sub-folder exist or not.

folderStructure = [['Folder1', [subfolder1, [sub-sub-folder1, sub-sub-folder2]]], ['Folder2', [sub-folder2], [sub-folder3]], ['Folder3', [sub-folder4]], ['Folder4'], [file1, file2, file3]]

How can I test if this folder structure exist?

Answer 1

In order to actually check if the folder exists, you have to specify its path and use os.path.exists. The difficult part is that the nested lists have strings that sometimes represent a folder's name, and other times a file name. I wrote a function that tests if the members of the supplied structure exist or not, and tries to determine if the content represents a folder name or not.

import os
folderStructure = [
    ['Folder1', 
        ['subfolder1', 
            ['sub-sub-folder1', 'sub-sub-folder2']
        ]
    ], 
    ['Folder2', 
        ['sub-folder2'], ['sub-folder3']
    ], 
    ['Folder3', 
        ['sub-folder4']
    ], 
    ['Folder4'], 
    ['file1', 'file2', 'file3']
]

def path_hierarchy_exists(pathslist,base_path='.'):
    print pathslist,base_path
    if isinstance(pathslist,basestring): # pathslist is a string that names a file
        return os.path.exists(os.path.join(base_path,pathslist))
    elif len(pathslist)==1: # Leaf sub-folders or leaf files
        if not path_hierarchy_exists(pathslist[0],base_path):
            return False
    elif isinstance(pathslist[0],basestring) and isinstance(pathslist[1],list):
        # pathslist is a list starting with the folder name and following with a list of folder contents
        folderName = pathslist[0]
        if not os.path.exists(os.path.join(base_path,folderName)): # Folder does not exist
            return False
        for folderContents in pathslist[1:]:
            if not path_hierarchy_exists(folderContents,os.path.join(base_path,folderName)):
                return False # Folder contents do not exist
    else: # pathslist is a list of nested folders
        for paths in pathslist:
            if not path_hierarchy_exists(paths,base_path):
                return False
    return True

print(path_hierarchy_exists(folderStructure))