commit 4dd3e3f9bbd320f0dd556688e04db0a6b55a7b52
author Andrew Svetlov <andrew.svetlov@gmail.com> Wed May 29 12:33:59 2019 +0300
committer Miss Islington (bot) <31488909+miss-islington@users.noreply.github.com> Wed May 29 02:33:59 2019 -0700
tree 405a7629dbb3ef8e53cfa873443ec4eacdf3a1b5
parent 7d408697a96953a182328ec0b0650e9999da4116

bpo-32972: Async test case (GH-13386)



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

Lib/unittest/case.py

diff --git a/Lib/unittest/case.py b/Lib/unittest/case.py
index 8e01c3d..7b1e869 100644
--- a/Lib/unittest/case.py
+++ b/Lib/unittest/case.py
@@ -645,6 +645,18 @@
         else:
             addUnexpectedSuccess(self)
 
+    def _callSetUp(self):
+        self.setUp()
+
+    def _callTestMethod(self, method):
+        method()
+
+    def _callTearDown(self):
+        self.tearDown()
+
+    def _callCleanup(self, function, /, *args, **kwargs):
+        function(*args, **kwargs)
+
     def run(self, result=None):
         orig_result = result
         if result is None:
@@ -676,14 +688,14 @@
             self._outcome = outcome
 
             with outcome.testPartExecutor(self):
-                self.setUp()
+                self._callSetUp()
             if outcome.success:
                 outcome.expecting_failure = expecting_failure
                 with outcome.testPartExecutor(self, isTest=True):
-                    testMethod()
+                    self._callTestMethod(testMethod)
                 outcome.expecting_failure = False
                 with outcome.testPartExecutor(self):
-                    self.tearDown()
+                    self._callTearDown()
 
             self.doCleanups()
             for test, reason in outcome.skipped:
@@ -721,7 +733,7 @@
         while self._cleanups:
             function, args, kwargs = self._cleanups.pop()
             with outcome.testPartExecutor(self):
-                function(*args, **kwargs)
+                self._callCleanup(function, *args, **kwargs)
 
         # return this for backwards compatibility
         # even though we no longer use it internally