Unable to locate files with long names on Windows with Python

Question

I need to walk through folders with long file names in Windows.

I tried using os.listdir(), but it crashes with long pathnames, which is bad.

I tried using os.walk(), but it ignores the pathnames longer than ~256, which is worse.

I tried the magic word workaround described here, but it only works with mapped drives, not with UNC pathnames.

Here is an example with short pathnames, that shows that UNC pathnames don't work with the magic word trick.

>>> os.listdir('c:\\drivers') ['nusb3hub.cat', 'nusb3hub.inf', 'nusb3hub.sys', 'nusb3xhc.cat', 'nusb3xhc.inf', 'nusb3xhc.sys'] >>> os.listdir('\\\\Uni-hq-srv6\\router') ['2009-04-0210', '2010-11-0909', ... ]  >>> mw=u'\\\\?\\' >>> os.listdir(mw+'c:\\drivers') [u'nusb3hub.cat', u'nusb3hub.inf', u'nusb3hub.sys', u'nusb3xhc.cat', u'nusb3xhc.inf', u'nusb3xhc.sys'] >>> os.listdir(mw+'\\\\Uni-hq-srv6\\router')  Traceback (most recent call last):   File "<pyshell#160>", line 1, in <module>     os.listdir(mw+'\\\\Uni-hq-srv6\\router') WindowsError: [Error 123] The filename, directory name, or volume label syntax is incorrect: u'\\\\?\\\\\\Uni-hq-srv6\\router\\*.*' 

Any idea on how to deal with long pathnames or with unicode UNC pathnames?

Edit:

Following the suggestion of the comments below, I created some test functions to compare Python 2.7 and 3.3, and I added the test of glob.glob and os.listdir after os.chdir.

The os.chdir didn't help as expected (see this comment).

The glob.glob is the only one that in Python 3.3 works better, but only in one condition: using the magic word and with the drive name.

Here is the code I used (it works on both 2.7 and 3.3). I am learning Python now, and I hope these tests make sense:

from __future__ import print_function import os, glob  mw = u'\\\\?\\'  def walk(root):     n = 0     for root, dirs, files in os.walk(root):         n += len(files)     return n  def walk_mw(root):     n = 0     for root, dirs, files in os.walk(mw + root):         n += len(files)     return n  def listdir(root):     try:         folders = [f for f in os.listdir(root) if os.path.isdir(os.path.join(root, f))]         files = [f for f in os.listdir(root) if os.path.isfile(os.path.join(root, f))]         n = len(files)         for f in folders:             n += listdir(os.path.join(root, f))         return n     except:         return 'Crash'  def listdir_mw(root):     if not root.startswith(mw):         root = mw + root     try:         folders = [f for f in os.listdir(root) if os.path.isdir(os.path.join(root, f))]         files = [f for f in os.listdir(root) if os.path.isfile(os.path.join(root, f))]         n = len(files)         for f in folders:             n += listdir_mw(os.path.join(root, f))         return n     except:         return 'Crash'  def listdir_cd(root):     try:         os.chdir(root)         folders = [f for f in os.listdir('.') if os.path.isdir(os.path.join(f))]         files = [f for f in os.listdir('.') if os.path.isfile(os.path.join(f))]         n = len(files)         for f in folders:             n += listdir_cd(f)         return n     except:         return 'Crash'  def listdir_mw_cd(root):     if not root.startswith(mw):         root = mw + root     try:         os.chdir(root)         folders = [f for f in os.listdir('.') if os.path.isdir(os.path.join(f))]         files = [f for f in os.listdir('.') if os.path.isfile(os.path.join(f))]         n = len(files)         for f in folders:             n += listdir_cd(f) # the magic word can only be added the first time         return n     except:         return 'Crash'  def glb(root):     folders = [f for f in glob.glob(root + '\\*') if os.path.isdir(os.path.join(root, f))]     files = [f for f in glob.glob(root + '\\*') if os.path.isfile(os.path.join(root, f))]     n = len(files)     for f in folders:         n += glb(os.path.join(root, f))     return n  def glb_mw(root):     if not root.startswith(mw):         root = mw + root     folders = [f for f in glob.glob(root + '\\*') if os.path.isdir(os.path.join(root, f))]     files = [f for f in glob.glob(root + '\\*') if os.path.isfile(os.path.join(root, f))]     n = len(files)     for f in folders:         n += glb_mw(os.path.join(root, f))     return n  def test():     for txt1, root in [('drive ', r'C:\test'),                     ('UNC   ', r'\\Uni-hq-srv6\router\test')]:         for txt2, func in [('walk                    ', walk),                            ('walk     magic word     ', walk_mw),                            ('listdir                 ', listdir),                            ('listdir  magic word     ', listdir_mw),                            ('listdir              cd ', listdir_cd),                            ('listdir  magic word  cd ', listdir_mw_cd),                            ('glob                    ', glb),                            ('glob     magic word     ', glb_mw)]:             print(txt1, txt2, func(root))  test() 

And here is the result:

• The number 8 means all the files were found
• The number 0 means it didn't even try without crashing
• Any number between 1 and 7 means it failed half way without crashing
• The word Crash means it crashed

-

Python 2.7 drive  walk                     5 drive  walk     magic word      8      * GOOD * drive  listdir                  Crash drive  listdir  magic word      8      * GOOD * drive  listdir              cd  Crash drive  listdir  magic word  cd  5 drive  glob                     5 drive  glob     magic word      0 UNC    walk                     6 UNC    walk     magic word      0 UNC    listdir                  5 UNC    listdir  magic word      Crash UNC    listdir              cd  5 UNC    listdir  magic word  cd  Crash UNC    glob                     5 UNC    glob     magic word      0  Python 3.3 drive  walk                     5 drive  walk     magic word      8      * GOOD * drive  listdir                  Crash drive  listdir  magic word      8      * GOOD * drive  listdir              cd  Crash drive  listdir  magic word  cd  5 drive  glob                     5 drive  glob     magic word      8      * GOOD * UNC    walk                     6 UNC    walk     magic word      0 UNC    listdir                  5 UNC    listdir  magic word      Crash UNC    listdir              cd  5 UNC    listdir  magic word  cd  Crash UNC    glob                     5 UNC    glob     magic word      0 

Answer 1

Use the 8.3 fallback to avoid the long pathname, browsing in Win7 explorer this seems to be what windows itself does, ie every long paths has a shorter 'true name':

>>> long_unc="\\\\K53\\Users\\Tolan\\testing\\xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx\\xxxxxxxxxxxxxxxxxxxxxxxxdddddddddddddddddddddwgggggggggggggggggggggggggggggggggggxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx\\esssssssssssssssssssssggggggggggggggggggggggggggggggggggggggggggggggeee" >>> os.listdir(long_unc) FileNotFoundError: [WinError 3] 

but you can use win32api (pywin32) to 'build' up a shorter version, ie

short_unc=win32api.GetShortPathName(win32api.GetShortPathName(win32api.GetShortPathName("\\\\K53\\Users\\Tolan\\testing\\xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx")+"\\xxxxxxxxxxxxxxxxxxxxxxxxdddddddddddddddddddddwgggggggggggggggggggggggggggggggggggxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx") + "\\esssssssssssssssssssssggggggggggggggggggggggggggggggggggggggggggggggeee") >>> print(short_unc) \\K53\Users\Tolan\testing\XXXXXX~1\XXXXXX~1\ESSSSS~1 >>> import os >>> os.listdir(short_unc) ['test.txt'] 

clearly you can just fold the win32api.GetShortPathName call into you dir exploration rather than nesting as in my example. I've done it like this with 3 calls because if you've already got a 'too long' path then win32api.GetShortPathName wont cope with it either, but you can do it per dir and stay below the limit.