Update the compile tests for optimization levels to also check that
__debug__ blocks are included or excluded based on the optimization
level.
Patch by Diana Clarke.

to integer with binary base.

It shows show import time of each module.
It's useful for optimizing startup time.

Typical usage: python -X importtime -c 'import requests'

On macOS, a process can exit with -SIGKILL if it is killed "early"
with SIGTERM.

On macOS, use uuid_generate_time() instead of
uuid_generate_time_safe() of libuuid, since uuid_generate_time_safe()
is not available.

bpo-31516: current_thread() should not return a dummy thread at shutdown

* bpo-31158: Fix nondeterministic read in test_pty

* Reuse existing readline implementation from io.

Thx to @pitrou

* Updated comment

Ideally, this commit is fixuped into the previous commit. Since there is
already a comment on github, I won't rebase.

DER_cert_to_PEM_cert() used textwrap.fill() to format PEM.
But it's library to wrap lines on word boundary, while PEM is
base64 encoded string.

Additionally, importing textwrap is little slow.

Save a bit of code, plus non-tuples get converted anyway to tuples by tkinter for the tk call.

Speed up class creation by 10-20% by reducing the overhead in the
necessary special method lookups.

Passing a widget instead of an flist with a root widget opens the option of
creating a browser frame that is only part of a window. Passing a full file
name instead of pieces assumed to come from a .py file opens the possibility
of browsing python files that do not end in .py.

bpo-31592: Fix an assertion failure in Python parser in case of a bad unicodedata.normalize(). (#3767)

* Allow whitespace inside of ElementPath predicates.
* Add ElementPath predicate support for text comparison of the current node, like "[.='text']".

netrc file format doesn't support quotes and escapes.

See https://linux.die.net/man/5/netrc

Importlib was instrumented with two dtrace probes to profile import timing.
Signed-off-by: Christian Heimes <christian@python.org>

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.