GH-107465: Add pathlib.Path.from_uri() classmethod.

This method supports file URIs (including variants) as described in RFC 8089, such as URIs generated by `pathlib.Path.as_uri()` and `urllib.request.pathname2url`. The method is added to `Path` rather than `PurePath` because it uses `os.fsdecode()`, and so its results vary from system to system. I intend to deprecate `PurePath.as_uri()` and move it to `Path` for the same reason.
python · barneygale · Oct 1, 2023 · Aug 4, 2023 · Aug 4, 2023 · Aug 4, 2023
commit 0f51181345dcf3a3bc5978ef451dcdce41914368
@@ -850,6 +850,51 @@ call fails (for example because the path doesn't exist).
    .. versionadded:: 3.5
 
 
+.. classmethod:: Path.from_uri(uri)
+
+   Return a new path object from parsing a 'file' URI conforming to
+   :rfc:`8089`. For example::
+
+       >>> p = Path.from_uri('file:///etc/hosts')
+       PosixPath('/etc/hosts')
+
+   On Windows, DOS device and UNC paths may be parsed from URIs::
+
+       >>> p = Path.from_uri('file:///c:/windows')
+       WindowsPath('c:/windows')
+       >>> p = Path.from_uri('file://server/share')
+       WindowsPath('//server/share')
+
+   Several variant forms are supported::
+
+       >>> p = Path.from_uri('file:////server/share')
+       WindowsPath('//server/share')
+       >>> p = Path.from_uri('file://///server/share')
+       WindowsPath('//server/share')
+       >>> p = Path.from_uri('file:c:/windows')
+       WindowsPath('c:/windows')
+       >>> p = Path.from_uri('file:/c|/windows')
+       WindowsPath('c:/windows')
+       >>> p = Path.from_uri('file://///c:/windows')
+       WindowsPath('c:/windows')
+
+   URIs with no slash after the scheme (and no drive letter) are parsed as
+   relative paths::
+
+       >>> p = Path.from_uri('file:foo/bar')
+       WindowsPath('foo/bar')
+
+   Users may wish to test the result with :meth:`~PurePath.is_absolute` and
+   reject relative paths, as these are not portable across processes with
+   differing working directories.
+
+   :func:`os.fsdecode` is used to decode percent-escaped byte sequences, and
+   so file URIs are not portable across machines with differing
+   :ref:`filesystem encodings <filesystem-encoding>`.
+
+   .. versionadded:: 3.13
+
+
 .. method:: Path.stat(*, follow_symlinks=True)
 
    Return a :class:`os.stat_result` object containing information about this path, like :func:`os.stat`.

@@ -118,6 +118,9 @@ pathlib
   :exc:`NotImplementedError` when a path operation isn't supported.
   (Contributed by Barney Gale in :gh:`89812`.)
 
+* Add :method:`Path.from_uri` classmethod.
+  (Contributed by Barney Gale in :gh:`107465`.)
+
 * Add support for recursive wildcards in :meth:`pathlib.PurePath.match`.
   (Contributed by Barney Gale in :gh:`73435`.)
 

diff --git a/Lib/pathlib.py b/Lib/pathlib.py
@@ -17,7 +17,6 @@
 from _collections_abc import Sequence
 from errno import ENOENT, ENOTDIR, EBADF, ELOOP
 from stat import S_ISDIR, S_ISLNK, S_ISREG, S_ISSOCK, S_ISBLK, S_ISCHR, S_ISFIFO
-from urllib.parse import quote_from_bytes as urlquote_from_bytes
 
 
 __all__ = [
@@ -433,7 +432,8 @@ def as_uri(self):
             # It's a posix path => 'file:///etc/hosts'
             prefix = 'file://'
             path = str(self)
-        return prefix + urlquote_from_bytes(os.fsencode(path))
+        from urllib.parse import quote_from_bytes
+        return prefix + quote_from_bytes(os.fsencode(path))
 
     @property
     def _str_normcase(self):
@@ -1178,6 +1178,22 @@ def __new__(cls, *args, **kwargs):
             cls = WindowsPath if os.name == 'nt' else PosixPath
         return object.__new__(cls)
 
+    @classmethod
+    def from_uri(cls, uri):
+        """Return a new path from the given 'file' URI."""
+        uri = uri.removeprefix('file:')
+        if uri[:3] == '///':
+            # Remove empty authority
+            uri = uri[2:]
+        if uri[:1] == '/' and (uri[2:3] in ':|' or uri[1:3] == '//'):
+            # Remove slash before DOS device/UNC path
+            uri = uri[1:]
+        if uri[1:2] == '|':
+            # Replace bar with colon in DOS drive
+            uri = uri[:1] + ':' + uri[2:]
+        from urllib.parse import unquote_to_bytes
+        return cls(os.fsdecode(unquote_to_bytes(uri)))
+
     @classmethod
     def cwd(cls):
         """Return a new path pointing to the current working directory."""

diff --git a/Lib/test/test_pathlib.py b/Lib/test/test_pathlib.py
@@ -11,6 +11,7 @@
 import tempfile
 import unittest
 from unittest import mock
+from urllib.request import pathname2url
 
 from test.support import import_helper
 from test.support import set_recursion_limit
@@ -2913,6 +2914,20 @@ def test_passing_kwargs_deprecated(self):
         with self.assertWarns(DeprecationWarning):
             self.cls(foo="bar")
 
+    def test_from_uri_common(self):
+        P = self.cls
+        self.assertEqual(P.from_uri('file:foo/bar'), P('foo/bar'))
+        self.assertEqual(P.from_uri('file:/foo/bar'), P('/foo/bar'))
+        self.assertEqual(P.from_uri('file://foo/bar'), P('//foo/bar'))
+        self.assertEqual(P.from_uri('file:///foo/bar'), P('/foo/bar'))
+        self.assertEqual(P.from_uri('file:////foo/bar'), P('//foo/bar'))
+
+    def test_from_uri_pathname2url_common(self):
+        P = self.cls
+        self.assertEqual(P.from_uri(pathname2url('foo/bar')), P('foo/bar'))
+        self.assertEqual(P.from_uri(pathname2url('/foo/bar')), P('/foo/bar'))
+        self.assertEqual(P.from_uri(pathname2url('//foo/bar')), P('//foo/bar'))
+
 
 class WalkTests(unittest.TestCase):
 
@@ -3441,7 +3456,23 @@ def check():
             env['HOME'] = 'C:\\Users\\eve'
             check()
 
+    def test_from_uri(self):
+        P = self.cls
+        # DOS drive paths
+        self.assertEqual(P.from_uri('file:c:/path/to/file'), P('c:/path/to/file'))
+        self.assertEqual(P.from_uri('file:c|/path/to/file'), P('c:/path/to/file'))
+        self.assertEqual(P.from_uri('file:/c|/path/to/file'), P('c:/path/to/file'))
+        self.assertEqual(P.from_uri('file:///c|/path/to/file'), P('c:/path/to/file'))
+        self.assertEqual(P.from_uri('file://///c|/path/to/file'), P('c:/path/to/file'))
+        # UNC paths
+        self.assertEqual(P.from_uri('file://server/path/to/file'), P('//server/path/to/file'))
+        self.assertEqual(P.from_uri('file:////server/path/to/file'), P('//server/path/to/file'))
+        self.assertEqual(P.from_uri('file://///server/path/to/file'), P('//server/path/to/file'))
 
+    def test_from_uri_pathname2url(self):
+        P = self.cls
+        self.assertEqual(P.from_uri(pathname2url(r'c:\path\to\file')), P('c:/path/to/file'))
+        self.assertEqual(P.from_uri(pathname2url(r'\\server\path\to\file')), P('//server/path/to/file'))
 
 class PathSubclassTest(PathTest):
     class cls(pathlib.Path):