gh-96290: support partial/invalid UNC drives in normpath() and splitd…

…rive()

This brings the Python implementation of `ntpath.normpath()` in line with
the C implementation added in 99fcf15

Co-authored-by: Eryk Sun <eryksun@gmail.com>

Lib/ntpath.py

@@ -87,16 +87,20 @@ def normcase(s):
 def isabs(s):
  """Test whether a path is absolute"""
  s = os.fspath(s)
- # Paths beginning with \\?\ are always absolute, but do not
- # necessarily contain a drive.
  if isinstance(s, bytes):
- if s.replace(b'/', b'\\').startswith(b'\\\\?\\'):
- return True
+ sep = b'\\'
+ altsep = b'/'
+ colon_sep = b':\\'
  else:
- if s.replace('/', '\\').startswith('\\\\?\\'):
- return True
- s = splitdrive(s)[1]
- return len(s) > 0 and s[0] and s[0] in _get_bothseps(s)
+ sep = '\\'
+ altsep = '/'
+ colon_sep = ':\\'
+ s = s[:3].replace(altsep, sep)
+ # Absolute: UNC, device, and paths with a drive and root.
+ # LEGACY BUG: isabs("/x") should be false since the path has no drive.
+ if s.startswith(sep) or s.startswith(colon_sep, 1):
+ return True
+ return False
 
 
 # Join two (or more) paths.
@@ -167,40 +171,31 @@ def splitdrive(p):
 
  """
  p = os.fspath(p)
- if len(p) >= 2:
- if isinstance(p, bytes):
- sep = b'\\'
- altsep = b'/'
- colon = b':'
- unc_prefix = b'\\\\?\\UNC'
- else:
- sep = '\\'
- altsep = '/'
- colon = ':'
- unc_prefix = '\\\\?\\UNC'
- normp = p.replace(altsep, sep)
- if (normp[0:2] == sep*2) and (normp[2:3] != sep):
- # is a UNC path:
- # vvvvvvvvvvvvvvvvvvvv drive letter or UNC path
- # \\machine\mountpoint\directory\etc\...
- # directory ^^^^^^^^^^^^^^^
- if normp[:8].upper().rstrip(sep) == unc_prefix:
- start = 8
- else:
- start = 2
- index = normp.find(sep, start)
- if index == -1:
- return p[:0], p
- index2 = normp.find(sep, index + 1)
- # a UNC path can't have two slashes in a row
- # (after the initial two)
- if index2 == index + 1:
- return p[:0], p
- if index2 == -1:
- index2 = len(p)
- return p[:index2], p[index2:]
- if normp[1:2] == colon:
- return p[:2], p[2:]
+ if isinstance(p, bytes):
+ sep = b'\\'
+ altsep = b'/'
+ colon = b':'
+ unc_prefix = b'\\\\?\\UNC\\'
+ else:
+ sep = '\\'
+ altsep = '/'
+ colon = ':'
+ unc_prefix = '\\\\?\\UNC\\'
+ normp = p.replace(altsep, sep)
+ if normp[1:2] == colon and normp[:1] != sep:
+ # Drive-letter logical drives, e.g. X:
+ return p[:2], p[2:]
+ if normp[:2] == sep * 2:
+ # UNC drives, e.g. \\server\share or \\?\UNC\server\share
+ # Device drives, e.g. \\.\device or \\?\device
+ start = 8 if normp[:8].upper() == unc_prefix else 2
+ index = normp.find(sep, start)
+ if index == -1:
+ return p, p[:0]
+ index = normp.find(sep, index + 1)
+ if index == -1:
+ return p, p[:0]
+ return p[:index], p[index:]
  return p[:0], p
 
 
@@ -523,20 +518,11 @@ def normpath(path):
  altsep = b'/'
  curdir = b'.'
  pardir = b'..'
- special_prefixes = (b'\\\\.\\', b'\\\\?\\')
  else:
  sep = '\\'
  altsep = '/'
  curdir = '.'
  pardir = '..'
- special_prefixes = ('\\\\.\\', '\\\\?\\')
- if path.startswith(special_prefixes):
- # in the case of paths with these prefixes:
- # \\.\ -> device names
- # \\?\ -> literal paths
- # do not do any normalization, but return the path
- # unchanged apart from the call to os.fspath()
- return path
  path = path.replace(altsep, sep)
  prefix, path = splitdrive(path)
 

Lib/test/test_ntpath.py

@@ -107,22 +107,22 @@ def test_splitdrive(self):
  tester('ntpath.splitdrive("//conky/mountpoint/foo/bar")',
  ('//conky/mountpoint', '/foo/bar'))
  tester('ntpath.splitdrive("\\\\\\conky\\mountpoint\\foo\\bar")',
- ('', '\\\\\\conky\\mountpoint\\foo\\bar'))
+ ('\\\\\\conky', '\\mountpoint\\foo\\bar'))
  tester('ntpath.splitdrive("///conky/mountpoint/foo/bar")',
- ('', '///conky/mountpoint/foo/bar'))
+ ('///conky', '/mountpoint/foo/bar'))
  tester('ntpath.splitdrive("\\\\conky\\\\mountpoint\\foo\\bar")',
- ('', '\\\\conky\\\\mountpoint\\foo\\bar'))
+ ('\\\\conky\\', '\\mountpoint\\foo\\bar'))
  tester('ntpath.splitdrive("//conky//mountpoint/foo/bar")',
- ('', '//conky//mountpoint/foo/bar'))
+ ('//conky/', '/mountpoint/foo/bar'))
  # Issue #19911: UNC part containing U+0130
  self.assertEqual(ntpath.splitdrive('//conky/MOUNTPOİNT/foo/bar'),
  ('//conky/MOUNTPOİNT', '/foo/bar'))
  # gh-81790: support device namespace, including UNC drives.
  tester('ntpath.splitdrive("//?/c:")', ("//?/c:", ""))
  tester('ntpath.splitdrive("//?/c:/")', ("//?/c:", "/"))
  tester('ntpath.splitdrive("//?/c:/dir")', ("//?/c:", "/dir"))
- tester('ntpath.splitdrive("//?/UNC")', ("", "//?/UNC"))
- tester('ntpath.splitdrive("//?/UNC/")', ("", "//?/UNC/"))
+ tester('ntpath.splitdrive("//?/UNC")', ("//?/UNC", ""))
+ tester('ntpath.splitdrive("//?/UNC/")', ("//?/UNC/", ""))
  tester('ntpath.splitdrive("//?/UNC/server/")', ("//?/UNC/server/", ""))
  tester('ntpath.splitdrive("//?/UNC/server/share")', ("//?/UNC/server/share", ""))
  tester('ntpath.splitdrive("//?/UNC/server/share/dir")', ("//?/UNC/server/share", "/dir"))
@@ -133,8 +133,8 @@ def test_splitdrive(self):
  tester('ntpath.splitdrive("\\\\?\\c:")', ("\\\\?\\c:", ""))
  tester('ntpath.splitdrive("\\\\?\\c:\\")', ("\\\\?\\c:", "\\"))
  tester('ntpath.splitdrive("\\\\?\\c:\\dir")', ("\\\\?\\c:", "\\dir"))
- tester('ntpath.splitdrive("\\\\?\\UNC")', ("", "\\\\?\\UNC"))
- tester('ntpath.splitdrive("\\\\?\\UNC\\")', ("", "\\\\?\\UNC\\"))
+ tester('ntpath.splitdrive("\\\\?\\UNC")', ("\\\\?\\UNC", ""))
+ tester('ntpath.splitdrive("\\\\?\\UNC\\")', ("\\\\?\\UNC\\", ""))
  tester('ntpath.splitdrive("\\\\?\\UNC\\server\\")', ("\\\\?\\UNC\\server\\", ""))
  tester('ntpath.splitdrive("\\\\?\\UNC\\server\\share")', ("\\\\?\\UNC\\server\\share", ""))
  tester('ntpath.splitdrive("\\\\?\\UNC\\server\\share\\dir")',
@@ -143,6 +143,13 @@ def test_splitdrive(self):
  ('\\\\?\\VOLUME{00000000-0000-0000-0000-000000000000}', '\\spam'))
  tester('ntpath.splitdrive("\\\\?\\BootPartition\\")', ("\\\\?\\BootPartition", "\\"))
 
+ # gh-96290: support partial/invalid UNC drives
+ tester('ntpath.splitdrive("//")', ("//", "")) # empty server & missing share
+ tester('ntpath.splitdrive("///")', ("///", "")) # empty server & empty share
+ tester('ntpath.splitdrive("///y")', ("///y", "")) # empty server & valid share
+ tester('ntpath.splitdrive("//x")', ("//x", "")) # valid server & missing share
+ tester('ntpath.splitdrive("//x/")', ("//x/", "")) # valid server & empty share
+
  def test_split(self):
  tester('ntpath.split("c:\\foo\\bar")', ('c:\\foo', 'bar'))
  tester('ntpath.split("\\\\conky\\mountpoint\\foo\\bar")',