GH-126212: Fix removal of slashes in file URIs on Windows

Adjust `urllib.request.pathname2url()` and `url2pathname()` so that they
don't remove slashes from Windows DOS drive paths and URLs. There was no
basis for this behaviour, and it conflicts with how UNC and POSIX paths are
handled.

Author: barneygale

Lib/nturl2path.py

@@ -24,22 +24,14 @@ def url2pathname(url):
             # convert this to \\host\path\on\remote\host
             # (notice halving of slashes at the start of the path)
             url = url[2:]
-        components = url.split('/')
-        # make sure not to convert quoted slashes :-)
-        return urllib.parse.unquote('\\'.join(components))
+        return urllib.parse.unquote(url.replace('/', '\\'))
     comp = url.split('|')
     if len(comp) != 2 or comp[0][-1] not in string.ascii_letters:
         error = 'Bad URL: ' + url
         raise OSError(error)
     drive = comp[0][-1].upper()
-    components = comp[1].split('/')
-    path = drive + ':'
-    for comp in components:
-        if comp:
-            path = path + '\\' + urllib.parse.unquote(comp)
-    # Issue #11474 - handing url such as |c/|
-    if path.endswith(':') and url.endswith('/'):
-        path += '\\'
+    tail = comp[1].replace('/', '\\')
+    path = drive + ':' + urllib.parse.unquote(tail)
     return path
 
 def pathname2url(p):
@@ -60,17 +52,13 @@ def pathname2url(p):
             raise OSError('Bad path: ' + p)
     if not ':' in p:
         # No drive specifier, just convert slashes and quote the name
-        components = p.split('\\')
-        return urllib.parse.quote('/'.join(components))
+        return urllib.parse.quote(p.replace('\\', '/'))
     comp = p.split(':', maxsplit=2)
     if len(comp) != 2 or len(comp[0]) > 1:
         error = 'Bad path: ' + p
         raise OSError(error)
 
     drive = urllib.parse.quote(comp[0].upper())
-    components = comp[1].split('\\')
-    path = '///' + drive + ':'
-    for comp in components:
-        if comp:
-            path = path + '/' + urllib.parse.quote(comp)
+    tail = comp[1].replace('\\', '/')
+    path = '///' + drive + ':' + urllib.parse.quote(tail)
     return path

Lib/test/test_urllib.py

@@ -1526,8 +1526,10 @@ def test_pathname2url_win(self):
         self.assertEqual(fn('\\\\?\\C:\\dir'), '///C:/dir')
         self.assertEqual(fn('\\\\?\\unc\\server\\share\\dir'), '//server/share/dir')
         self.assertEqual(fn("C:"), '///C:')
-        self.assertEqual(fn("C:\\"), '///C:')
+        self.assertEqual(fn("C:\\"), '///C:/')
         self.assertEqual(fn('C:\\a\\b.c'), '///C:/a/b.c')
+        self.assertEqual(fn('C:\\a\\b.c\\'), '///C:/a/b.c/')
+        self.assertEqual(fn('C:\\a\\\\b.c'), '///C:/a//b.c')
         self.assertEqual(fn('C:\\a\\b%#c'), '///C:/a/b%25%23c')
         self.assertEqual(fn('C:\\a\\b\xe9'), '///C:/a/b%C3%A9')
         self.assertEqual(fn('C:\\foo\\bar\\spam.foo'), "///C:/foo/bar/spam.foo")
@@ -1563,13 +1565,15 @@ def test_url2pathname_win(self):
         self.assertEqual(fn("///C|"), 'C:')
         self.assertEqual(fn("///C:"), 'C:')
         self.assertEqual(fn('///C:/'), 'C:\\')
-        self.assertEqual(fn('/C|//'), 'C:\\')
+        self.assertEqual(fn('/C|//'), 'C:\\\\')
         self.assertEqual(fn('///C|/path'), 'C:\\path')
         # No DOS drive
         self.assertEqual(fn("///C/test/"), '\\\\\\C\\test\\')
         self.assertEqual(fn("////C/test/"), '\\\\C\\test\\')
         # DOS drive paths
         self.assertEqual(fn('C:/path/to/file'), 'C:\\path\\to\\file')
+        self.assertEqual(fn('C:/path/to/file/'), 'C:\\path\\to\\file\\')
+        self.assertEqual(fn('C:/path/to//file'), 'C:\\path\\to\\\\file')
         self.assertEqual(fn('C|/path/to/file'), 'C:\\path\\to\\file')
         self.assertEqual(fn('/C|/path/to/file'), 'C:\\path\\to\\file')
         self.assertEqual(fn('///C|/path/to/file'), 'C:\\path\\to\\file')

Misc/NEWS.d/next/Library/2024-10-30-23-59-36.gh-issue-126212._9uYjT.rst

@@ -0,0 +1,3 @@
+Fix issue where :func:`urllib.request.pathname2url` and
+:func:`~urllib.request.url2pathname` removed slashes from Windows DOS drive
+paths and URLs.