bpo-36582: Make collections.UserString.encode() return bytes, not str (GH-13138)...

(cherry picked from commit 2a16eea71f56c2d8f38c295c8ce71a9a9a140aff)

Co-authored-by: Daniel Fortunov <asqui@users.noreply.github.com>

diff --git a/Lib/collections/__init__.py b/Lib/collections/__init__.py
index 469690be8c8e444aa23a8cfae00c8103b6387512..cadf1c72f08d47c7abe787df9ea8e182f0dd4a35 100644 (file)
--- a/Lib/collections/__init__.py
+++ b/Lib/collections/__init__.py
@@ -1200,12 +1200,10 @@ class UserString(_collections_abc.Sequence):
         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 19b0acfc760fa4e220f79e7f6f3e4f5a2c666ac0..4d1d8b6b6fe2d951d2899e9931ab95b42051d4ca 100644 (file)
--- a/Lib/test/test_userstring.py
+++ b/Lib/test/test_userstring.py
@@ -51,6 +51,20 @@ class UserStringTest(
         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 ab874e9299313aa7fbfcf551a551376108ba3409..5a8494f1a827c71cf04115a0ca4a1fec610bac7d 100644 (file)
--- 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 (file)
index 0000000..34f16fc
--- /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