Adjust os.path.realpath to match pathlib.Path.resolve() behaviour when a new strict=True keyword-only argument is passed.

Author: barneygale

Doc/library/os.path.rst

@@ -344,22 +344,29 @@ the :mod:`glob` module.)
       Accepts a :term:`path-like object`.
 
 
-.. function:: realpath(path)
+.. function:: realpath(path, *, strict=False)
 
    Return the canonical path of the specified filename, eliminating any symbolic
    links encountered in the path (if they are supported by the operating
    system).
 
-   .. note::
-      When symbolic link cycles occur, the returned path will be one member of
-      the cycle, but no guarantee is made about which member that will be.
+   In non-strict mode (the default), missing or inaccessible ancestors are
+   permitted; when encountered, the remainder of the path joined on and
+   returned. In strict mode an :exc:`OSError` is raised in this scenario.
 
    .. versionchanged:: 3.6
       Accepts a :term:`path-like object`.
 
    .. versionchanged:: 3.8
       Symbolic links and junctions are now resolved on Windows.
 
+   .. versionchanged:: 3.10
+      The *strict* parameter was added.
+
+   .. versionchanged:: 3.10
+      Raises :exc:`OSError` with :const:`~errno.ELOOP` when a symbolic link
+      cycle occurs. Previously returned one member of the cycle.
+
 
 .. function:: relpath(path, start=os.curdir)
 

Lib/ntpath.py

@@ -635,7 +635,7 @@ def _getfinalpathname_nonstrict(path):
                 tail = join(name, tail) if tail else name
         return tail
 
-    def realpath(path):
+    def realpath(path, *, strict=False):
         path = normpath(path)
         if isinstance(path, bytes):
             prefix = b'\\\\?\\'
@@ -660,6 +660,8 @@ def realpath(path):
             path = _getfinalpathname(path)
             initial_winerror = 0
         except OSError as ex:
+            if strict:
+                raise
             initial_winerror = ex.winerror
             path = _getfinalpathname_nonstrict(path)
         # The path returned by _getfinalpathname will always start with \\?\ -

Lib/pathlib.py

@@ -1058,14 +1058,13 @@ def resolve(self, strict=False):
         normalizing it (for example turning slashes into backslashes under
         Windows).
         """
-        p = self._from_parts((self._accessor.realpath(self),))
         try:
-            if S_ISLNK(self.lstat().st_mode):
-                raise RuntimeError("Symlink loop from %r" % str(p))
-        except OSError:
-            if strict:
-                raise
-        return p
+            p = self._accessor.realpath(self, strict=strict)
+        except OSError as ex:
+            if ex.errno == ELOOP:
+                raise RuntimeError("Symlink loop from %r", ex.filename)
+            raise
+        return self._from_parts((p,))
 
     def stat(self, *, follow_symlinks=True):
         """

Lib/posixpath.py

@@ -22,6 +22,7 @@
 altsep = None
 devnull = '/dev/null'
 
+import errno
 import os
 import sys
 import stat
@@ -387,16 +388,16 @@ def abspath(path):
 # Return a canonical path (i.e. the absolute location of a file on the
 # filesystem).
 
-def realpath(filename):
+def realpath(filename, *, strict=False):
     """Return the canonical path of the specified filename, eliminating any
 symbolic links encountered in the path."""
     filename = os.fspath(filename)
-    path, ok = _joinrealpath(filename[:0], filename, {})
+    path = _joinrealpath(filename[:0], filename, strict, {})
     return abspath(path)
 
 # Join two paths, normalizing and eliminating any symbolic links
 # encountered in the second path.
-def _joinrealpath(path, rest, seen):
+def _joinrealpath(path, rest, strict, seen):
     if isinstance(path, bytes):
         sep = b'/'
         curdir = b'.'
@@ -425,9 +426,17 @@ def _joinrealpath(path, rest, seen):
                 path = pardir
             continue
         newpath = join(path, name)
-        if not islink(newpath):
-            path = newpath
-            continue
+        try:
+            st = os.lstat(newpath)
+        except OSError:
+            if strict:
+                raise
+            is_link = False
+        else:
+            is_link = stat.S_ISLNK(st.st_mode)
+        if not is_link:
+             path = newpath
+             continue
         # Resolve the symbolic link
         if newpath in seen:
             # Already seen this path
@@ -436,15 +445,11 @@ def _joinrealpath(path, rest, seen):
                 # use cached value
                 continue
             # The symlink is not resolved, so we must have a symlink loop.
-            # Return already resolved part + rest of the path unchanged.
-            return join(newpath, rest), False
-        seen[newpath] = None # not resolved symlink
-        path, ok = _joinrealpath(path, os.readlink(newpath), seen)
-        if not ok:
-            return join(path, rest), False
+            raise OSError(errno.ELOOP, os.strerror(errno.ELOOP), newpath)
+        path = _joinrealpath(path, os.readlink(newpath), strict, seen)
         seen[newpath] = path # resolved symlink
 
-    return path, True
+    return path
 
 
 supports_unicode_filenames = (sys.platform == 'darwin')