…y from cpython.

…ntax for positional-only parameters would limit this codebase to being Py3.8+ only.

…s child with attach_mock (GH 14688)

* Clear name and parent of mock in autospecced objects used with attach_mock

* Add NEWS entry

* Fix reversed order of comparison

* Test child and standalone function calls

* Use a helper function extracting mock to avoid code duplication and refactor tests.

Backports: 7397cda99795a4a8d96193d710105e77a07b7411
Signed-off-by: Chris Withers <chris@withers.org>

* Fix typos in comments, docs and test names

* Update test_pyparse.py

account for change in string length

* Apply suggestion: splitable -> splittable

Co-Authored-By: Terry Jan Reedy <tjreedy@udel.edu>

* Apply suggestion: splitable -> splittable

Co-Authored-By: Terry Jan Reedy <tjreedy@udel.edu>

* Apply suggestion: Dealloccte -> Deallocate

Co-Authored-By: Terry Jan Reedy <tjreedy@udel.edu>

* Update posixmodule checksum.

* Reverse idlelib changes.

Backports: c4cacc8c5eab50db8da3140353596f38a01115ca
Signed-off-by: Chris Withers <chris@withers.org>

…(GH-14952)

They now return NotImplemented for unsupported type of the other operand.

Backports: 662db125cddbca1db68116c547c290eb3943d98e
Signed-off-by: Chris Withers <chris@withers.org>

…to a method (GH13261)

* Fix call_matcher for mock when using methods

* Add NEWS entry

* Use None check and convert doctest to unittest

* Use better name for mock in tests. Handle _SpecState when the attribute was not accessed and add tests.

* Use reset_mock instead of reinitialization. Change inner class constructor signature for check

* Reword comment regarding call object lookup logic

Backports: c96127821ebda50760e788b1213975a0d5bea37f
Signed-off-by: Chris Withers <chris@withers.org>

Backports: f5896a05edf5df91fb1b55bd481ba5b2a3682f4e
Signed-off-by: Chris Withers <chris@withers.org>

…2992)

Backports: 0dac68f1e593c11612ed54af9edb865d398f3b05
Signed-off-by: Chris Withers <chris@withers.org>

Backports: 39d87b54715197ca9dcb6902bb43461c0ed701a2
Signed-off-by: Chris Withers <chris@withers.org>

…cuted (GH-14154)

Backports: aa515082749687c1e3bc9ec5e2296368191b9f84
Signed-off-by: Chris Withers <chris@withers.org>

…error messages (GH-14310)

Backports: 9d607061c9c888913ae2c18543775cf360d55f27
Signed-off-by: Chris Withers <chris@withers.org>

Update the docs as patch can now return an AsyncMock if the patched
object is an async function.

Backports: f5e7f39d2916ed150e80381faed125f405a11e11
Signed-off-by: Chris Withers <chris@withers.org>

Backports: f1a297acb60b88917712450ebd3cfa707e6efd6b
Signed-off-by: Chris Withers <chris@withers.org>

* Flip equality to use mock calls' __eq__

* bpo-37555: Regression test demonstrating assert_has_calls not working with ANY and spec_set

Co-authored-by: Neal Finne <neal@nealfinne.com>

* Revert "Flip equality to use mock calls' __eq__"

This reverts commit 94ddf54c5a8aab7d00d9ab93e1cc5695c28d73e7.

* bpo-37555: Add regression tests for mock ANY ordering issues

Add regression tests for whether __eq__ is order agnostic on _Call and _CallList, which is useful for comparisons involving ANY, especially if the ANY comparison is to a class not defaulting __eq__ to NotImplemented.

Co-authored-by: Neal Finne <neal@nealfinne.com>

* bpo-37555: Fix _CallList and _Call order sensitivity

_Call and _CallList depend on ordering to correctly process that an object being compared to ANY with __eq__ should return True. This fix updates the comparison to check both a == b and b == a and return True if either condition is met, fixing situations from the tests in the previous two commits where assertEqual would not be commutative if checking _Call or _CallList objects. This seems like a reasonable fix considering that the Python data model specifies that if an object doesn't know how to compare itself to another object it should return NotImplemented, and that on getting NotImplemented from a == b, it should try b == a, implying that good behavior for __eq__ is commutative. This also flips the order of comparison in _CallList's __contains__ method, guaranteeing ANY will be on the left and have it's __eq__ called for equality checking, fixing the interaction between assert_has_calls and ANY.

Co-author: Neal Finne <neal@neal.finne.com>

* bpo-37555: Ensure _call_matcher returns _Call object

* Adding ACK and news entry

* bpo-37555: Replacing __eq__ with == to sidestep NotImplemented

bool(NotImplemented) returns True, so it's necessary to use ==
instead of __eq__ in this comparison.

* bpo-37555: cleaning up changes unnecessary to the final product

* bpo-37555: Fixed call on bound arguments to respect args and kwargs

* Revert "bpo-37555: Add regression tests for mock ANY ordering issues"

This reverts commit 49c5310ad493c4356dd3bc58c03653cd9466c4fa.

* Revert "bpo-37555: cleaning up changes unnecessary to the final product"

This reverts commit 18e964ba0126d8964d89842cb95534b63c2d326e.

* Revert "bpo-37555: Replacing __eq__ with == to sidestep NotImplemented"

This reverts commit f295eaca5bceac6636c0e2b10e6c7d9a8ee8296a.

* Revert "bpo-37555: Fix _CallList and _Call order sensitivity"

This reverts commit 874fb697b8376fcea130116e56189061f944fde6.

* Updated NEWS.d

* bpo-37555: Add tests checking every function using _call_matcher both with and without spec

* bpo-37555: Ensure all assert methods using _call_matcher are actually passing calls

* Remove AnyCompare and use call objects everywhere.

* Revert "Remove AnyCompare and use call objects everywhere."

This reverts commit 24973c0b32ce7d796a7f4eeaf259832222aae0f5.

* Check for exception in assert_any_await

Backports: d6a9d17d8b6c68073931dd8ffa213b4ac351a4ab
Signed-off-by: Chris Withers <chris@withers.org>

Backports: 14fd925a18fe3db0922a7d798e373102fe7a8a9c
Signed-off-by: Chris Withers <chris@withers.org>

Backports: a9187c31185fe7ea47271839898416400cc3d976
Signed-off-by: Chris Withers <chris@withers.org>

… (GH-16166)

In the format string for assert_called the evaluation order is incorrect and hence for mock's without name, 'None' is printed whereas it should be 'mock' like for other messages. The error message is ("Expected '%s' to have been called." % self._mock_name or 'mock').

Backports: 5f5f11faf9de0d8dcbe1a8a4eb35d2a4232d6eaa
Signed-off-by: Chris Withers <chris@withers.org>

Backports: 8b03f943c37e07fb2394acdcfacd066647f9b1fd
Signed-off-by: Chris Withers <chris@withers.org>

…(GH-16192)

Backports: ef048517755db1f0d211fb6dfc655a8b412cc96f
Signed-off-by: Chris Withers <chris@withers.org>

The fix in PR 13261 handled the underlying issue about the spec for specific methods not being applied correctly, but it didn't fix the issue that was causing the misleading error message.

The code currently grabs a list of responses from _call_matcher (which may include exceptions). But it doesn't reach inside the list when checking if the result is an exception. This results in a misleading error message when one of the provided calls does not match the spec.

https://bugs.python.org/issue36871

Automerge-Triggered-By: @gpshead
Backports: b5a7a4f0c20717a4c92c371583b5521b83f40f32
Signed-off-by: Chris Withers <chris@withers.org>

Fixes an issue caught after merge of PR 16005.

Tightened test assertions to check the entire assertion message.

Backports: 2180f6b058effbf49ec819f7cedbe76ddd4b700c
Signed-off-by: Chris Withers <chris@withers.org>

Backports: 9a7d9519506ae807ca48ff02e2ea117ebac3450e
Signed-off-by: Chris Withers <chris@withers.org>

Backports: 25e115ec00b5f75e3589c9f21013c47c21e1753f
Signed-off-by: Chris Withers <chris@withers.org>

Backports: 3667e1ee6c90e6d3b6a745cd590ece87118f81ad
Signed-off-by: Chris Withers <chris@withers.org>

Backports: 892221bfa04a41cf581f988ba19dc263f557e157
Signed-off-by: Chris Withers <chris@withers.org>

…3.8] (GH-17269)

Backports: 046442d02bcc6e848e71e93e47f6cde9e279e993
Signed-off-by: Chris Withers <chris@withers.org>

…y3.6

This means a clearer message is now shown when patch.object is called with two string arguments, rather than a class and a string argument.

Backports: cd90a52983db34896a6335a572d55bdda274778f
Signed-off-by: Chris Withers <chris@withers.org>

This isn't included in `__all__` and could be a source of confusion.

Backports: 31d6de5aba009914efa8f0f3c3d7da35217578eb
Signed-off-by: Chris Withers <chris@withers.org>

* Add test for nested async decorator patch.
* Add test for side_effect and wraps with a function.
* Add test for side_effect with an exception in the iterable.

Backports: 54f743eb315f00b0ff45e115dde7a5d506034153
Signed-off-by: Chris Withers <chris@withers.org>

* add test for path.dict using OrderedDict

Co-authored-by: Yu Tomita nekobon@users.noreply.github.com
Backports: 1d0c5e16eab29d55773cc4196bb90d2bf12e09dd
Signed-off-by: Chris Withers <chris@withers.org>

As the function was not registering in the active patches, the mocks
started by `mock.patch.dict` were not being stopped when
`mock.patch.stopall` was being called.

Backports: e131c9720d087c0c4988bd2a5c62020feb9d1d77
Signed-off-by: Chris Withers <chris@withers.org>

…mock (GH-16784)

Backports: 66b00a9d3aacf6ed49412f48743e4913104a2bb3
Signed-off-by: Chris Withers <chris@withers.org>

…pstream imports

…H-18116)

Backports: 62865f4532094017a9b780b704686ca9734bc329
Signed-off-by: Chris Withers <chris@withers.org>

…(GH-15521)

Backports: 40c080934b3d49311209b1cb690c2ea1e04df7e7
Signed-off-by: Chris Withers <chris@withers.org>

Backports: aef7dc89879d099dc704bd8037b8a7686fb72838
Signed-off-by: Chris Withers <chris@withers.org>

…gicMock (#16029)

Backports: 72b1004657e60c900e4cd031b2635b587f4b280e
Signed-off-by: Chris Withers <chris@withers.org>

… applied

- The gc.collect is needed for other implementations, such as pypy
- Using context managers over multiple lines will only catch the warning from the first line in the context!
- remove a skip for a test that no longer fails on pypy

Backports: a46575a8f2ded8b49e26c25bb67192e1500e76ca
Signed-off-by: Chris Withers <chris@withers.org>

Replace check for whether something is a method in the mock module. The
previous version fails on PyPy, because there no method wrappers exist
(everything looks like a regular Python-defined function). Thus the
isinstance(getattr(result, '__get__', None), MethodWrapperTypes) check
returns True for any descriptor, not just methods.

This condition could also return erroneously True in CPython for
C-defined descriptors.

Instead to decide whether something is a method, just check directly
whether it's a function defined on the class. This passes all tests on
CPython and fixes the bug on PyPy.

Backports: a327677905956ae0b239ff430a1346dfe265709e
Signed-off-by: Chris Withers <chris@withers.org>

* use the `: pass` and `: yield` patterns for code that isn't expected to ever be executed.

* The _Call items passed to _AnyComparer are only ever of length two, so assert instead of if/else

* fix typo

* Fix bug, where stop-without-start patching dict blows up with `TypeError: 'NoneType' object is not iterable`, highlighted by lack of coverage of an except branch.

* The fix for bpo-37972 means _Call.count and _Call.index are no longer needed.

* add coverage for calling next() on a mock_open with readline.return_value set.

* __aiter__ is defined on the Mock so the one on _AsyncIterator is never called.

Backports: db5e86adbce12350c26e7ffc2c6673369971a2dc
Signed-off-by: Chris Withers <chris@withers.org>

…attr__ chaining so that call() can be subscriptable (GH-15565)

* bpo-37972: unittest.mock._Call now passes on __getitem__ to the __getattr__ chaining so that call() can be subscriptable

* 📜🤖 Added by blurb_it.

* Update 2019-08-28-21-40-12.bpo-37972.kP-n4L.rst

added name of the contributor

* bpo-37972: made all dunder methods chainable for _Call

* bpo-37972: delegate only attributes of tuple instead to __getattr__

Backports: 72c359912d36705a94fca8b63d80451905a14ae4
Signed-off-by: Chris Withers <chris@withers.org>