cross-platform splitting of path in python

python

Solution

The OP specified "will work with Windows paths too". There are a few wrinkles with Windows paths.

Firstly, Windows has the concept of multiple drives, each with its own current working directory, and `'c:foo'` and `'c:\\foo'` are often not the same. Consequently it is a very good idea to separate out any drive designator first, using os.path.splitdrive(). Then reassembling the path (if required) can be done correctly by `drive + os.path.join(*other_pieces)`

Secondly, Windows paths can contain slashes or backslashes or a mixture. Consequently, using `os.sep` when parsing an unnormalised path is not useful.

More generally:

The results produced for `'foo'` and `'foo/'` should not be identical.

The loop termination condition seems to be best expressed as "os.path.split() treated its input as unsplittable".

Here's a suggested solution, with tests, including a comparison with @Spacedman's solution

import os.path

def os_path_split_asunder(path, debug=False):
    parts = []
    while True:
        newpath, tail = os.path.split(path)
        if debug: print repr(path), (newpath, tail)
        if newpath == path:
            assert not tail
            if path: parts.append(path)
            break
        parts.append(tail)
        path = newpath
    parts.reverse()
    return parts

def spacedman_parts(path):
    components = [] 
    while True:
        (path,tail) = os.path.split(path)
        if not tail:
            return components
        components.insert(0,tail)

if __name__ == "__main__":
    tests = [
        '',
        'foo',
        'foo/',
        'foo\\',
        '/foo',
        '\\foo',
        'foo/bar',
        '/',
        'c:',
        'c:/',
        'c:foo',
        'c:/foo',
        'c:/users/john/foo.txt',
        '/users/john/foo.txt',
        'foo/bar/baz/loop',
        'foo/bar/baz/',
        '//hostname/foo/bar.txt',
        ]
    for i, test in enumerate(tests):
        print "\nTest %d: %r" % (i, test)
        drive, path = os.path.splitdrive(test)
        print 'drive, path', repr(drive), repr(path)
        a = os_path_split_asunder(path)
        b = spacedman_parts(path)
        print "a ... %r" % a
        print "b ... %r" % b
        print a == b

and here's the output (Python 2.7.1, Windows 7 Pro):

Test 0: ''
drive, path '' ''
a ... []
b ... []
True

Test 1: 'foo'
drive, path '' 'foo'
a ... ['foo']
b ... ['foo']
True

Test 2: 'foo/'
drive, path '' 'foo/'
a ... ['foo', '']
b ... []
False

Test 3: 'foo\\'
drive, path '' 'foo\\'
a ... ['foo', '']
b ... []
False

Test 4: '/foo'
drive, path '' '/foo'
a ... ['/', 'foo']
b ... ['foo']
False

Test 5: '\\foo'
drive, path '' '\\foo'
a ... ['\\', 'foo']
b ... ['foo']
False

Test 6: 'foo/bar'
drive, path '' 'foo/bar'
a ... ['foo', 'bar']
b ... ['foo', 'bar']
True

Test 7: '/'
drive, path '' '/'
a ... ['/']
b ... []
False

Test 8: 'c:'
drive, path 'c:' ''
a ... []
b ... []
True

Test 9: 'c:/'
drive, path 'c:' '/'
a ... ['/']
b ... []
False

Test 10: 'c:foo'
drive, path 'c:' 'foo'
a ... ['foo']
b ... ['foo']
True

Test 11: 'c:/foo'
drive, path 'c:' '/foo'
a ... ['/', 'foo']
b ... ['foo']
False

Test 12: 'c:/users/john/foo.txt'
drive, path 'c:' '/users/john/foo.txt'
a ... ['/', 'users', 'john', 'foo.txt']
b ... ['users', 'john', 'foo.txt']
False

Test 13: '/users/john/foo.txt'
drive, path '' '/users/john/foo.txt'
a ... ['/', 'users', 'john', 'foo.txt']
b ... ['users', 'john', 'foo.txt']
False

Test 14: 'foo/bar/baz/loop'
drive, path '' 'foo/bar/baz/loop'
a ... ['foo', 'bar', 'baz', 'loop']
b ... ['foo', 'bar', 'baz', 'loop']
True

Test 15: 'foo/bar/baz/'
drive, path '' 'foo/bar/baz/'
a ... ['foo', 'bar', 'baz', '']
b ... []
False

Test 16: '//hostname/foo/bar.txt'
drive, path '' '//hostname/foo/bar.txt'
a ... ['//', 'hostname', 'foo', 'bar.txt']
b ... ['hostname', 'foo', 'bar.txt']
False

Problem

Original source