ca40eb0fda
When a tasks raises an exception which is uncaught, and no other task await's on that task, then an error message is printed (or a user function called) via a call to Loop.call_exception_handler. In CPython this call is made when the Task object is freed (eg via reference counting) because it's at that point that it is known that the exception that was raised will never be handled. MicroPython does not have reference counting and the current behaviour is to deal with uncaught exceptions as early as possible, ie as soon as they terminate the task. But this can be undesirable because in certain cases a task can start and raise an exception immediately (before any await is executed in that task's coro) and before any other task gets a chance to await on it to catch the exception. This commit changes the behaviour so that tasks which end due to an uncaught exception are scheduled one more time for execution, and if they are not await'ed on by the next scheduling loop, then the exception handler is called (eg the exception is printed out). Signed-off-by: Damien George <damien@micropython.org>
10 lines
140 B
Plaintext
10 lines
140 B
Plaintext
None
|
|
True
|
|
sleep
|
|
custom_handler ValueError(0, 1)
|
|
sleep
|
|
custom_handler ValueError(1, 2)
|
|
custom_handler ValueError(2, 3)
|
|
ValueError(3, 4)
|
|
done
|