[3.12] GH-126212: Fix removal of slashes in file URIs on Windows (GH-126214) (#126591)

GH-126212: Fix removal of slashes in file URIs on Windows (GH-126214)

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.
(cherry picked from commit 54c63a32d06cb5f07a66245c375eac7d7efb964a)

Co-authored-by: Barney Gale <barney.gale@gmail.com>

diff --git a/Lib/nturl2path.py b/Lib/nturl2path.py
index 6453f202c26d146642b352c3b51334b8532bd2e6..2f9fec7893afd1b2e9770a38df398cdaa315b6d5 100644 (file)
--- a/Lib/nturl2path.py
+++ b/Lib/nturl2path.py
@@ -24,23 +24,15 @@ 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 += '\\'
-    return path
+    tail = urllib.parse.unquote(comp[1].replace('/', '\\'))
+    return drive + ':' + tail
 
 def pathname2url(p):
     """OS-specific conversion from a file system path to a relative URL
@@ -60,17 +52,12 @@ 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)
-    return path
+    tail = urllib.parse.quote(comp[1].replace('\\', '/'))
+    return '///' + drive + ':' + tail

diff --git a/Lib/test/test_urllib.py b/Lib/test/test_urllib.py
index 0e1b13d31c92734709e1bd268339a072ee7911c1..2b59fb617cbdda2e65abff614b9b1d5cd4c271ac 100644 (file)
--- a/Lib/test/test_urllib.py
+++ b/Lib/test/test_urllib.py
@@ -1535,8 +1535,10 @@ class Pathname_Tests(unittest.TestCase):
         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")
@@ -1572,13 +1574,15 @@ class Pathname_Tests(unittest.TestCase):
         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')
@@ -1592,6 +1596,9 @@ class Pathname_Tests(unittest.TestCase):
         # Localhost paths
         self.assertEqual(fn('//localhost/C:/path/to/file'), 'C:\\path\\to\\file')
         self.assertEqual(fn('//localhost/C|/path/to/file'), 'C:\\path\\to\\file')
+        # Percent-encoded forward slashes are preserved for backwards compatibility
+        self.assertEqual(fn('C:/foo%2fbar'), 'C:\\foo/bar')
+        self.assertEqual(fn('//server/share/foo%2fbar'), '\\\\server\\share\\foo/bar')
         # Round-tripping
         paths = ['C:',
                  r'\\\C\test\\',

diff --git a/Misc/NEWS.d/next/Library/2024-10-30-23-59-36.gh-issue-126212._9uYjT.rst b/Misc/NEWS.d/next/Library/2024-10-30-23-59-36.gh-issue-126212._9uYjT.rst
new file mode 100644 (file)
index 0000000..047fe0f
--- /dev/null
+++ b/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.