Issue #25221: Fix corrupted result from PyLong_FromLong(0) when Python is compiled with NSMALLPOSINTS = 0.

appropriate types. Improved some error messages and debugging output.

This change didn't have the intended effect.

json.loads (and hence json.load) now support binary input
encoded as UTF-8, UTF-16 or UTF-32.

Patch by Serhiy Storchaka.

The pure Python fallback implementation of functools.partial
now matches the behaviour of its accelerated C counterpart for
subclassing, pickling and text representation purposes.

Patch by Emanuel Barry and Serhiy Storchaka.

Issue #27829: don't pass --quiet option to regrtest to see
"Warning -- xxx was modified by ..." warnings.

between 1.0 and 2.0 to 1.

between 1.0 and 2.0 to 1.

* Use "with Popen" to cleanup properly the process
* Use support.temp_cwd() to properly change the working directory
* Use environ.pop() to cleanup the code

Issue #27938: Normalize aliases of the ASCII encoding, because
_Py_normalize_encoding() now correctly normalize encoding names.

HOME is not set on Windows for example.

Use also textwrap.dedent() for the script.

Patch by Martin Matusiak and Sam Kimbrel.

Issue #28056 and issue #26058.

by the user.

It turns out we can't depend on email.message getting imported every place
message_factory is needed, so to avoid a circular import we need to special
case Policy.message_factory=None in the parser instead of using monkey
patching.  I had a feeling that was a bad idea when I did it.

generalizations added in 3.5.