From aad2ee01561f260c69af1951c0d6fcaf75c4d41b Mon Sep 17 00:00:00 2001 From: Stein Karlsen Date: Mon, 14 Oct 2019 12:36:29 +0200 Subject: bpo-32498: urllib.parse.unquote also accepts bytes (GH-7768) --- Doc/library/urllib.parse.rst | 7 +++++- Lib/test/test_urllib.py | 25 ++++++++++++++++++++-- Lib/urllib/parse.py | 2 ++ .../2018-06-17-21-02-25.bpo-32498.La3TZz.rst | 2 ++ 4 files changed, 33 insertions(+), 3 deletions(-) create mode 100644 Misc/NEWS.d/next/Library/2018-06-17-21-02-25.bpo-32498.La3TZz.rst diff --git a/Doc/library/urllib.parse.rst b/Doc/library/urllib.parse.rst index 49276daa7f..84d289bc44 100644 --- a/Doc/library/urllib.parse.rst +++ b/Doc/library/urllib.parse.rst @@ -571,7 +571,7 @@ task isn't already covered by the URL parsing functions above. percent-encoded sequences into Unicode characters, as accepted by the :meth:`bytes.decode` method. - *string* must be a :class:`str`. + *string* may be either a :class:`str` or a :class:`bytes`. *encoding* defaults to ``'utf-8'``. *errors* defaults to ``'replace'``, meaning invalid sequences are replaced @@ -579,6 +579,11 @@ task isn't already covered by the URL parsing functions above. Example: ``unquote('/El%20Ni%C3%B1o/')`` yields ``'/El NiƱo/'``. + .. versionchanged:: 3.9 + *string* parameter supports bytes and str objects (previously only str). + + + .. function:: unquote_plus(string, encoding='utf-8', errors='replace') diff --git a/Lib/test/test_urllib.py b/Lib/test/test_urllib.py index 9a6b5f66b7..3f59c66084 100644 --- a/Lib/test/test_urllib.py +++ b/Lib/test/test_urllib.py @@ -1049,8 +1049,6 @@ class UnquotingTests(unittest.TestCase): "%s" % result) self.assertRaises((TypeError, AttributeError), urllib.parse.unquote, None) self.assertRaises((TypeError, AttributeError), urllib.parse.unquote, ()) - with support.check_warnings(('', BytesWarning), quiet=True): - self.assertRaises((TypeError, AttributeError), urllib.parse.unquote, b'') def test_unquoting_badpercent(self): # Test unquoting on bad percent-escapes @@ -1210,6 +1208,29 @@ class UnquotingTests(unittest.TestCase): self.assertEqual(expect, result, "using unquote(): %r != %r" % (expect, result)) + def test_unquoting_with_bytes_input(self): + # ASCII characters decoded to a string + given = b'blueberryjam' + expect = 'blueberryjam' + result = urllib.parse.unquote(given) + self.assertEqual(expect, result, + "using unquote(): %r != %r" % (expect, result)) + + # A mix of non-ASCII hex-encoded characters and ASCII characters + given = b'bl\xc3\xa5b\xc3\xa6rsyltet\xc3\xb8y' + expect = 'bl\u00e5b\u00e6rsyltet\u00f8y' + result = urllib.parse.unquote(given) + self.assertEqual(expect, result, + "using unquote(): %r != %r" % (expect, result)) + + # A mix of non-ASCII percent-encoded characters and ASCII characters + given = b'bl%c3%a5b%c3%a6rsyltet%c3%b8j' + expect = 'bl\u00e5b\u00e6rsyltet\u00f8j' + result = urllib.parse.unquote(given) + self.assertEqual(expect, result, + "using unquote(): %r != %r" % (expect, result)) + + class urlencode_Tests(unittest.TestCase): """Tests for urlencode()""" diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py index b6608783a8..3a38dc14c9 100644 --- a/Lib/urllib/parse.py +++ b/Lib/urllib/parse.py @@ -631,6 +631,8 @@ def unquote(string, encoding='utf-8', errors='replace'): unquote('abc%20def') -> 'abc def'. """ + if isinstance(string, bytes): + return unquote_to_bytes(string).decode(encoding, errors) if '%' not in string: string.split return string diff --git a/Misc/NEWS.d/next/Library/2018-06-17-21-02-25.bpo-32498.La3TZz.rst b/Misc/NEWS.d/next/Library/2018-06-17-21-02-25.bpo-32498.La3TZz.rst new file mode 100644 index 0000000000..9df9e65e55 --- /dev/null +++ b/Misc/NEWS.d/next/Library/2018-06-17-21-02-25.bpo-32498.La3TZz.rst @@ -0,0 +1,2 @@ +Made :func:`urllib.parse.unquote()` accept bytes in addition to strings. +Patch by Stein Karlsen. -- cgit v1.2.1