This was possible before.  GH-1560 introduced a regression after 3.6.2 got
released where only sequences were accepted now.  This commit addresses this
problem.

bpo-31602: Fix an assertion failure in zipimporter.get_source() in case of a bad zlib.decompress() (GH-3784)

While a rare potential failure (it requires swapping out zlib.decompress() itself and forcing it to return a non-bytes object), this change prevents a potential C-level assertion failure and instead substitutes it with an exception.

Thanks to Oren Milman for the patch.

(forgot to remove it in #3219)

Add optional argument `compressed` to `zipapp.create_archive`, and add
option `--compress` to the command line interface of `zipapp`.

$^ is not portable.

closes bpo-31625

Instead, simply pass 's' to ar.

bpo-11063, bpo-20519: avoid ctypes and improve import time for uuid.

Replace "restriction" with "restrictions".

bpo-31478: Fix an assertion failure in random.seed() in case a seed has a bad __abs__() method. (#3596)

Class execution requires that __prepare__() methods return
a proper execution namespace. Check for that immediately
after calling __prepare__(), rather than passing it through
to the code execution machinery and potentially triggering
SystemError (in debug builds) or a cryptic TypeError
(in release builds).

Patch by Oren Milman.

Fix the logic in python-config.sh to avoid attempting to substitute
prefix in a variable that might have already been subject to
substitution. This e.g. happened if @exec_prefix@ was defined as
"${prefix}" (which is the default of the configure script) -- in which
case the exec_prefix_build variable was initialized with
already-subtituted prefix, and then another round of substitution was
performed which might have resulted in duplicate prefix.

To avoid that, rename the variables so that the variables matching
likely configure names (prefix, exec_prefix) retain their original
values and a '_real' suffix is used for the real values of prefix.

Furthermore, replace the unnecessary prefix and exec_prefix
substitutions with direct prefix_real references since the sed
always replaced the whole string anyway by design.

- Remove the second mention about the `u` prefix
- Remove the second mention about numeric literals do not include a sign

Non-regression tests for the Expat 2.2.3 UTF-8 decoder bug.

bpo-31311: Fix a SystemError and a crash in ctypes._CData.__setstate__(), in case of a bad __dict__. (#3254)

Python requires C implementations provide memmove, so we shouldn't need to check for it. The only place using this configure check was expat, where we can simply always define HAVE_MEMMOVE.

The dunderless functions are preferred; dunder are retained for back compatilibity.
Patch by Sanket Dasgupta.

A `"` was missing from an `<a href>` tag.

Defer removing old behavior to 3.8.
Document new feature of selection_set() and friends.

now becames exhausted after advancing the groupby iterator.

bpo-31311: Impove error reporting in case the first argument to PyCData_setstate() isn't a dictionary. (#3255)

bpo-31505: Fix an assertion failure in json, in case _json.make_encoder() received a bad encoder() argument. (#3643)

Mention that ``NewType`` can derive from another ``NewType``.