Co-Authored-By: Barry Warsaw <barry@python.org>

* bpo-21315: Fix parsing of encoded words with missing leading ws.

Because of missing leading whitespace, encoded word would get parsed as
unstructured token. This patch fixes that by looking for encoded words when
splitting tokens with whitespace.

Missing trailing whitespace around encoded word now register a defect
instead.

Original patch suggestion by David R. Murray on bpo-21315.

Turn deprecation warnings added in 3.8 into TypeError.

https://bugs.python.org/issue26836

https://bugs.python.org/issue34767

Based on the source code https://github.com/python/cpython/blob/4a686504eb2bbf69adf78077458508a7ba131667/Lib/multiprocessing/pool.py#L755 AsyncResult.successful() raises a ValueError, not an AssertionError.

This PR deprecate explicit loop parameters in all public asyncio APIs

This issues is split to be easier to review.

Second step: streams.py





https://bugs.python.org/issue36373

Add it to the end of the first line if there is room.  Tests were reworked.

Python 3.8.0b1

* bpo-30835: email: Fix AttributeError when parsing invalid Content-Transfer-Encoding

Parsing an email containing a multipart Content-Type, along with a
Content-Transfer-Encoding containing an invalid (non-ASCII-decodable) byte
will fail. email.feedparser.FeedParser._parsegen() gets the header and
attempts to convert it to lowercase before comparing it with the accepted
encodings, but as the header contains an invalid byte, it's returned as a
Header object rather than a str.

Cast the Content-Transfer-Encoding header to a str to avoid this.

Found using the AFL fuzzer.
Reported-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Andrew Donnellan <andrew@donnellan.id.au>

* Add email and NEWS entry for the bugfix.

* bpo-35805: Add parser for Message-ID header.

This parser is based on the definition of Identification Fields from RFC 5322
Sec 3.6.4.

This should also prevent folding of Message-ID header using RFC 2047 encoded
words and hence fix bpo-35805.

* Prevent folding of non-ascii message-id headers.
* Add fold method to MsgID token to prevent folding.

test_venv.test_mutiprocessing() now explicitly calls pool.terminate()
to wait until the pool completes.

* Improve example on tzinfo instances

Move from GMTX to TZX when naming the classes, as GMT1 might be rather
confusing as seen in the reported issue.
In addition, move to UTC over GMT and improve the tzname implementation.

* Simplify datetime with tzinfo example

Move the example in the documentation to just use timezone.utc and a
user defined Kabul timezone rather than having two user defined
timezones with DST.

Kabul timezone is still interesting as it changes its offset but not
based on DST. This is more accurate as the previous example was missing
information about the fold attribute. Additionally, implementing the fold
attribute was rather complex and probably not relevant enough for the
section "datetime with tzinfo".

CP65001Test has been removed.

Fix this MSVC warning:

    objects\codeobject.c(264): warning C4244: '=':
    conversion from 'Py_ssize_t' to 'unsigned char', possible loss of data

Make test_stream_server_close() implementation following test_stream_server_abort().
 Add explicit timeout for tests that can hang.

This reverts commit 0f0a30f4.

bpo-37148: Fix asyncio test that check for warning when running the test suite with huntleaks (GH-13800)

This reverts commit 396e0a8d.

Revert "bpo-35621: Support running subprocesses in asyncio when loop is executed in non-main thread (#13630)" (GH-13793)



https://bugs.python.org/issue35621

--with-pydebug is commonly used to find memory leaks.
But opcache makes it harder.
So disable opcache when Py_DEBUG is defined.

Add BaseEventLoop.wait_executor_on_close attribute: true by default.

loop.close() now waits for the default executor to finish by default.
Set loop.wait_executor_on_close attribute to False to not wait for
the executor.