Add explicit `asyncSetUp` and `asyncTearDown` methods.
The rest is the same as for #13228

`AsyncTestCase` create a loop instance for every test for the sake of test isolation.
Sometimes a loop shared between all tests can speed up tests execution time a lot but it requires control of closed resources after every test finish. Basically, it requires nested supervisors support that was discussed with @1st1 many times. Sorry, asyncio supervisors have no chance to land on Python 3.8.

The PR intentionally does not provide API for changing the used event loop or getting the test loop: use `asyncio.set_event_loop_policy()` and `asyncio.get_event_loop()` instead.

The PR adds four overridable methods to base `unittest.TestCase` class:
```
    def _callSetUp(self):
        self.setUp()

    def _callTestMethod(self, method):
        method()

    def _callTearDown(self):
        self.tearDown()

    def _callCleanup(self, function, /, *args, **kwargs):
        function(*args, **kwargs)
```
It allows using asyncio facilities with minimal influence on the unittest code.

The last but not least: the PR respects contextvars. The context variable installed by `asyncSetUp` is available on test, `tearDown` and a coroutine scheduled by `addCleanup`.


https://bugs.python.org/issue32972

* Clean up some comments, fix potential memory leaks, clarify literal and expr_text.

* Fix the implicit string concatenation in `assert_has_awaits` error message.
* Use "await" instead of "call" in `assert_awaited_with` error message.



https://bugs.python.org/issue37075

Drop isinstance checks from create_subprocess_exec function and let
subprocess module do them.

https://bugs.python.org/issue35246


https://bugs.python.org/issue35246

in addition to global-statement also mention nonlocal-statement
(in the paragraph describing access to variables which are non local to a function

_thread.start_new_thread() now logs uncaught exception raised by the
function using sys.unraisablehook(), rather than sys.excepthook(), so
the hook gets access to the function which raised the exception.

* bpo-36540: Documentation for PEP570 - Python positional only arguments

* fixup! bpo-36540: Documentation for PEP570 - Python positional only arguments

* Update reference for compound statements

* Apply suggestions from Carol
Co-Authored-By: Carol Willing <carolcode@willingconsulting.com>

* Update Doc/tutorial/controlflow.rst
Co-Authored-By: Carol Willing <carolcode@willingconsulting.com>

* Add extra bullet point and minor edits

I'm confident that this fixes the reported crash. flags=NULL is treated as using the latest minor version.

https://bugs.python.org/issue37072

The old link had a > in the url which prevented the browser from jumping down to the correct section on that page.

That PSF page itself has an error: There's a duplicate "the" in that paragraph that needs to be removed: "...and conform to **the the** Python Community Code of Conduct."

While I was editing this file, I also fixed some grammar and bolded the 3 important keywords so that they catch the viewer's eyes. I can revert these changes if they are unwanted.

Thanks.

* Makes symtable.symtable have parity for accepted datatypes
for source code as compile()

* Add NEWS blurb

There is an extra "one" in the text description for the constant
socket.CAN_RAW_FD_FRAMES

Original Pr was reformed and news not updated.




https://bugs.python.org/issue36933

On macOS, the multiprocessing module now uses the "spawn" start
method by default.

sys.excepthook() and sys.unraisablehook() now explicitly flush the
file (usually sys.stderr).

If file.flush() fails, sys.excepthook() silently ignores the error,
whereas sys.unraisablehook() logs the new exception.

Fix possible overflow in wrap_lenfunc() when
sizeof(long) < sizeof(Py_ssize_t) (e.g., 64-bit Windows).

Co-authored-by: Mark Shannon <mark@hotpy.org>

Per ae586497, time.monotonic is always available, making the old note outdated.

dynload_hpux.c: add #include "pycore_pystate.h" for
_PyInterpreterState_GET_UNSAFE().

Follow-up for #1067


https://bugs.python.org/issue29883

I tried to get rid of the `_ProtocolMeta`, but unfortunately it didn'y work. My idea to return a generic alias from `@runtime_checkable` made runtime protocols unpickleable. I am not sure what is worse (a custom metaclass or having some classes unpickleable), so I decided to stick with the status quo (since there were no complains so far). So essentially this is a copy of the implementation in `typing_extensions` with two modifications:
* Rename `@runtime` to `@runtime_checkable` (plus corresponding updates).
* Allow protocols that extend `collections.abc.Iterable` etc.

It has been documented as deprecated and to be removed in 3.8; 

From a comment on another thread – which I can't find ; leave get_coro_wrapper() for now, but always return `None`.


https://bugs.python.org/issue36933

Return a coroutine while patching async functions with a decorator. 
Co-authored-by: Andrew Svetlov <andrew.svetlov@gmail.com>


https://bugs.python.org/issue36996

https://bugs.python.org/issue36686