From bf383f9d276ccb2ae5bf8cc966349910ffe427fd Mon Sep 17 00:00:00 2001 From: Daniel Fortunov Date: Wed, 28 Aug 2019 06:38:09 +0200 Subject: [PATCH] bpo-36582: Make collections.UserString.encode() return bytes, not str (GH-13138) (cherry picked from commit 2a16eea71f56c2d8f38c295c8ce71a9a9a140aff) Co-authored-by: Daniel Fortunov --- Lib/collections/__init__.py | 10 ++++------ Lib/test/test_userstring.py | 14 ++++++++++++++ Misc/ACKS | 1 + .../2019-05-07-17-42-36.bpo-36582.L_dxR6.rst | 1 + 4 files changed, 20 insertions(+), 6 deletions(-) create mode 100644 Misc/NEWS.d/next/Library/2019-05-07-17-42-36.bpo-36582.L_dxR6.rst diff --git a/Lib/collections/__init__.py b/Lib/collections/__init__.py index 469690be8c8e44..cadf1c72f08d47 100644 --- a/Lib/collections/__init__.py +++ b/Lib/collections/__init__.py @@ -1200,12 +1200,10 @@ def count(self, sub, start=0, end=_sys.maxsize): if isinstance(sub, UserString): sub = sub.data return self.data.count(sub, start, end) - def encode(self, encoding=None, errors=None): # XXX improve this? - if encoding: - if errors: - return self.__class__(self.data.encode(encoding, errors)) - return self.__class__(self.data.encode(encoding)) - return self.__class__(self.data.encode()) + def encode(self, encoding='utf-8', errors='strict'): + encoding = 'utf-8' if encoding is None else encoding + errors = 'strict' if errors is None else errors + return self.data.encode(encoding, errors) def endswith(self, suffix, start=0, end=_sys.maxsize): return self.data.endswith(suffix, start, end) def expandtabs(self, tabsize=8): diff --git a/Lib/test/test_userstring.py b/Lib/test/test_userstring.py index 19b0acfc760fa4..4d1d8b6b6fe2d9 100644 --- a/Lib/test/test_userstring.py +++ b/Lib/test/test_userstring.py @@ -51,6 +51,20 @@ def __rmod__(self, other): str3 = ustr3('TEST') self.assertEqual(fmt2 % str3, 'value is TEST') + def test_encode_default_args(self): + self.checkequal(b'hello', 'hello', 'encode') + # Check that encoding defaults to utf-8 + self.checkequal(b'\xf0\xa3\x91\x96', '\U00023456', 'encode') + # Check that errors defaults to 'strict' + self.checkraises(UnicodeError, '\ud800', 'encode') + + def test_encode_explicit_none_args(self): + self.checkequal(b'hello', 'hello', 'encode', None, None) + # Check that encoding defaults to utf-8 + self.checkequal(b'\xf0\xa3\x91\x96', '\U00023456', 'encode', None, None) + # Check that errors defaults to 'strict' + self.checkraises(UnicodeError, '\ud800', 'encode', None, None) + if __name__ == "__main__": unittest.main() diff --git a/Misc/ACKS b/Misc/ACKS index ab874e9299313a..5a8494f1a827c7 100644 --- a/Misc/ACKS +++ b/Misc/ACKS @@ -509,6 +509,7 @@ Arnaud Fontaine Michael Foord Amaury Forgeot d'Arc Doug Fort +Daniel Fortunov Evens Fortuné Chris Foster John Fouhy diff --git a/Misc/NEWS.d/next/Library/2019-05-07-17-42-36.bpo-36582.L_dxR6.rst b/Misc/NEWS.d/next/Library/2019-05-07-17-42-36.bpo-36582.L_dxR6.rst new file mode 100644 index 00000000000000..34f16fcde879cd --- /dev/null +++ b/Misc/NEWS.d/next/Library/2019-05-07-17-42-36.bpo-36582.L_dxR6.rst @@ -0,0 +1 @@ +Fix ``UserString.encode()`` to correctly return ``bytes`` rather than a ``UserString`` instance. \ No newline at end of file pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.

Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy