From 1830c011b6fd0e8ee330bdf02059b9d83ff692ba Mon Sep 17 00:00:00 2001 From: Barney Gale Date: Tue, 12 Nov 2024 19:52:30 +0000 Subject: [PATCH] GH-120423: `pathname2url()`: handle forward slashes in Windows paths (GH-126593) Adjust `urllib.request.pathname2url()` so that forward slashes in Windows paths are handled identically to backward slashes. (cherry picked from commit bf224bd7cef5d24eaff35945ebe7ffe14df7710f) Co-authored-by: Barney Gale --- Lib/nturl2path.py | 13 +++++++------ Lib/test/test_urllib.py | 5 +++++ .../2024-11-08-17-05-10.gh-issue-120423.7rdLVV.rst | 2 ++ 3 files changed, 14 insertions(+), 6 deletions(-) create mode 100644 Misc/NEWS.d/next/Library/2024-11-08-17-05-10.gh-issue-120423.7rdLVV.rst diff --git a/Lib/nturl2path.py b/Lib/nturl2path.py index 2f9fec7893afd1..9ecabff21c33e1 100644 --- a/Lib/nturl2path.py +++ b/Lib/nturl2path.py @@ -44,20 +44,21 @@ def pathname2url(p): import urllib.parse # First, clean up some special forms. We are going to sacrifice # the additional information anyway - if p[:4] == '\\\\?\\': + p = p.replace('\\', '/') + if p[:4] == '//?/': p = p[4:] - if p[:4].upper() == 'UNC\\': - p = '\\\\' + p[4:] + if p[:4].upper() == 'UNC/': + p = '//' + p[4:] elif p[1:2] != ':': raise OSError('Bad path: ' + p) if not ':' in p: - # No drive specifier, just convert slashes and quote the name - return urllib.parse.quote(p.replace('\\', '/')) + # No DOS drive specified, just quote the pathname + return urllib.parse.quote(p) 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()) - tail = urllib.parse.quote(comp[1].replace('\\', '/')) + tail = urllib.parse.quote(comp[1]) return '///' + drive + ':' + tail diff --git a/Lib/test/test_urllib.py b/Lib/test/test_urllib.py index 2b59fb617cbdda..5433072bcda741 100644 --- a/Lib/test/test_urllib.py +++ b/Lib/test/test_urllib.py @@ -1551,6 +1551,11 @@ def test_pathname2url_win(self): self.assertEqual(fn('\\\\some\\share\\'), '//some/share/') self.assertEqual(fn('\\\\some\\share\\a\\b.c'), '//some/share/a/b.c') self.assertEqual(fn('\\\\some\\share\\a\\b%#c\xe9'), '//some/share/a/b%25%23c%C3%A9') + # Alternate path separator + self.assertEqual(fn('C:/a/b.c'), '///C:/a/b.c') + self.assertEqual(fn('//some/share/a/b.c'), '//some/share/a/b.c') + self.assertEqual(fn('//?/C:/dir'), '///C:/dir') + self.assertEqual(fn('//?/unc/server/share/dir'), '//server/share/dir') # Round-tripping urls = ['///C:', '///folder/test/', diff --git a/Misc/NEWS.d/next/Library/2024-11-08-17-05-10.gh-issue-120423.7rdLVV.rst b/Misc/NEWS.d/next/Library/2024-11-08-17-05-10.gh-issue-120423.7rdLVV.rst new file mode 100644 index 00000000000000..b475257ceb6610 --- /dev/null +++ b/Misc/NEWS.d/next/Library/2024-11-08-17-05-10.gh-issue-120423.7rdLVV.rst @@ -0,0 +1,2 @@ +Fix issue where :func:`urllib.request.pathname2url` mishandled Windows paths +with embedded forward slashes.