Skip to content

GH-85168: Use filesystem encoding when converting to/from file URIs #126852

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
barneygale merged 5 commits into from
Nov 19, 2024
Merged

GH-85168: Use filesystem encoding when converting to/from file URIs #126852

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
11b9602
GH-85168: Use filesystem encoding when converting to/from `file` URIs
barneygale Nov 15, 2024
a6f57d3
Address review feedback
barneygale Nov 15, 2024
f123044
Undo unnecessary import
barneygale Nov 15, 2024
b03b10d
Add test for unquoted non-ASCII character in URL.
barneygale Nov 16, 2024
224c252
Merge branch 'main' into gh-85168
barneygale Nov 19, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Address review feedback
  • Loading branch information
@barneygale
barneygale committed Nov 15, 2024
commit a6f57d333994ee4066f0e7ba00bc0d8d9c5f090a
27 changes: 14 additions & 13 deletions Lib/test/test_urllib.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1557,13 +1557,13 @@ def test_pathname2url_posix(self):
self.assertEqual(fn('/'), '/')
self.assertEqual(fn('/a/b.c'), '/a/b.c')
self.assertEqual(fn('/a/b%#c'), '/a/b%25%23c')
try:
expect = os.fsencode('\xe9')
except UnicodeEncodeError:
pass
else:
expect = urllib.parse.quote_from_bytes(expect)
self.assertEqual(fn('\xe9'), expect)

@unittest.skipUnless(os_helper.FS_NONASCII, 'need os_helper.FS_NONASCII')
def test_pathname2url_nonascii(self):
encoding = sys.getfilesystemencoding()
errors = sys.getfilesystemencodeerrors()
url = urllib.parse.quote(os_helper.FS_NONASCII, encoding=encoding, errors=errors)
self.assertEqual(urllib.request.pathname2url(os_helper.FS_NONASCII), url)

@unittest.skipUnless(sys.platform == 'win32',
'test specific to Windows pathnames.')
Expand Down Expand Up @@ -1614,12 +1614,13 @@ def test_url2pathname_posix(self):
self.assertEqual(fn('///foo/bar'), '/foo/bar')
self.assertEqual(fn('////foo/bar'), '//foo/bar')
self.assertEqual(fn('//localhost/foo/bar'), '//localhost/foo/bar')
try:
expect = os.fsdecode(b'\xe9')
except UnicodeDecodeError:
pass
else:
self.assertEqual(fn('%e9'), expect)

@unittest.skipUnless(os_helper.FS_NONASCII, 'need os_helper.FS_NONASCII')
def test_url2pathname_nonascii(self):
encoding = sys.getfilesystemencoding()
errors = sys.getfilesystemencodeerrors()
url = urllib.parse.quote(os_helper.FS_NONASCII, encoding=encoding, errors=errors)
self.assertEqual(urllib.request.url2pathname(url), os_helper.FS_NONASCII)

class Utility_Tests(unittest.TestCase):
"""Testcase to test the various utility functions in the urllib."""
Expand Down
8 changes: 6 additions & 2 deletions Lib/urllib/request.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1660,12 +1660,16 @@ def url2pathname(pathname):
# URL has an empty authority section, so the path begins on the
# third character.
pathname = pathname[2:]
return os.fsdecode(unquote_to_bytes(pathname))
encoding = sys.getfilesystemencoding()
errors = sys.getfilesystemencodeerrors()
return unquote(pathname, encoding=encoding, errors=errors)

def pathname2url(pathname):
"""OS-specific conversion from a file system path to a relative URL
of the 'file' scheme; not recommended for general use."""
return quote_from_bytes(os.fsencode(pathname))
encoding = sys.getfilesystemencoding()
errors = sys.getfilesystemencodeerrors()
return quote(pathname, encoding=encoding, errors=errors)


ftpcache = {}
Expand Down