bpo-9949: Enable symlink traversal for ntpath.realpath (GH-15287)
diff --git a/Lib/ntpath.py b/Lib/ntpath.py
index f3cfabf..ef4999e 100644
--- a/Lib/ntpath.py
+++ b/Lib/ntpath.py
@@ -519,8 +519,94 @@
except (OSError, ValueError):
return _abspath_fallback(path)
-# realpath is a no-op on systems without islink support
-realpath = abspath
+try:
+ from nt import _getfinalpathname, readlink as _nt_readlink
+except ImportError:
+ # realpath is a no-op on systems without _getfinalpathname support.
+ realpath = abspath
+else:
+ def _readlink_deep(path, seen=None):
+ if seen is None:
+ seen = set()
+
+ while normcase(path) not in seen:
+ seen.add(normcase(path))
+ try:
+ path = _nt_readlink(path)
+ except OSError as ex:
+ # Stop on file (2) or directory (3) not found, or
+ # paths that are not reparse points (4390)
+ if ex.winerror in (2, 3, 4390):
+ break
+ raise
+ except ValueError:
+ # Stop on reparse points that are not symlinks
+ break
+ return path
+
+ def _getfinalpathname_nonstrict(path):
+ # Fast path to get the final path name. If this succeeds, there
+ # is no need to go any further.
+ try:
+ return _getfinalpathname(path)
+ except OSError:
+ pass
+
+ # Allow file (2) or directory (3) not found, invalid syntax (123),
+ # and symlinks that cannot be followed (1921)
+ allowed_winerror = 2, 3, 123, 1921
+
+ # Non-strict algorithm is to find as much of the target directory
+ # as we can and join the rest.
+ tail = ''
+ seen = set()
+ while path:
+ try:
+ path = _readlink_deep(path, seen)
+ path = _getfinalpathname(path)
+ return join(path, tail) if tail else path
+ except OSError as ex:
+ if ex.winerror not in allowed_winerror:
+ raise
+ path, name = split(path)
+ if path and not name:
+ return abspath(path + tail)
+ tail = join(name, tail) if tail else name
+ return abspath(tail)
+
+ def realpath(path):
+ path = os.fspath(path)
+ if isinstance(path, bytes):
+ prefix = b'\\\\?\\'
+ unc_prefix = b'\\\\?\\UNC\\'
+ new_unc_prefix = b'\\\\'
+ cwd = os.getcwdb()
+ else:
+ prefix = '\\\\?\\'
+ unc_prefix = '\\\\?\\UNC\\'
+ new_unc_prefix = '\\\\'
+ cwd = os.getcwd()
+ had_prefix = path.startswith(prefix)
+ path = _getfinalpathname_nonstrict(path)
+ # The path returned by _getfinalpathname will always start with \\?\ -
+ # strip off that prefix unless it was already provided on the original
+ # path.
+ if not had_prefix and path.startswith(prefix):
+ # For UNC paths, the prefix will actually be \\?\UNC\
+ # Handle that case as well.
+ if path.startswith(unc_prefix):
+ spath = new_unc_prefix + path[len(unc_prefix):]
+ else:
+ spath = path[len(prefix):]
+ # Ensure that the non-prefixed path resolves to the same path
+ try:
+ if _getfinalpathname(spath) == path:
+ path = spath
+ except OSError as ex:
+ pass
+ return path
+
+
# Win9x family and earlier have no Unicode filename support.
supports_unicode_filenames = (hasattr(sys, "getwindowsversion") and
sys.getwindowsversion()[3] >= 2)
@@ -633,23 +719,6 @@
raise
-# determine if two files are in fact the same file
-try:
- # GetFinalPathNameByHandle is available starting with Windows 6.0.
- # Windows XP and non-Windows OS'es will mock _getfinalpathname.
- if sys.getwindowsversion()[:2] >= (6, 0):
- from nt import _getfinalpathname
- else:
- raise ImportError
-except (AttributeError, ImportError):
- # On Windows XP and earlier, two files are the same if their absolute
- # pathnames are the same.
- # Non-Windows operating systems fake this method with an XP
- # approximation.
- def _getfinalpathname(f):
- return normcase(abspath(f))
-
-
try:
# The genericpath.isdir implementation uses os.stat and checks the mode
# attribute to tell whether or not the path is a directory.