Convert our manager usage to be done via type annotations.

Now to define a manager to be used in a RESTObject subclass can simply
do:
      class ExampleClass(CRUDMixin, RESTObject):
          my_manager: MyManager

Any type-annotation that annotates it to be of type *Manager (with the
exception of RESTManager) will cause the manager to be created on the
object.

The 'managers' are dynamically created. This unfortunately means that
we don't have any type-hints for them and so editors which understand
type-hints won't know that they are valid attributes.

 * Add the type-hints for the managers we define.
 * Add a unit test that makes sure that the type-hints and the
   '_managers' attribute are kept in sync with each other.
 * Add unit test that makes sure specified managers in '_managers'
   have a name ending in 'Managers' to keep with current convention.
 * Make RESTObject._managers always present with a default value of
   None.
 * Fix a type-issue revealed now that mypy knows what the type is

Fix the import ordering using isort.

https://pycqa.github.io/isort/

Set the 'iids' values as type ListAttribute so it will pass the list
as a comma-separated string, instead of a list.

Add a functional test.

Closes: #1407

Fix all issues reported by running: tox -e pep8 and enable pep8 as a linter check

F401: Module imported but unused

https://www.flake8rules.com/rules/F401.html

Convert _create_attrs and _update_attrs to use a NamedTuple
(RequiredOptional) to help with code readability. Update all code to
use the NamedTuple.

In gitlab/v4/objects/*.py remove usage of:
  * from gitlab.base import *
  * from gitlab.mixins import *

Change them to:
  * from gitlab.base import CLASS_NAME
  * from gitlab.mixins import CLASS_NAME

Programmatically update code to explicitly import needed classes only.

After the change the output of:
  $ flake8 gitlab/v4/objects/*py | grep 'REST\|Mixin'

Is empty. Before many messages about unable to determine if it was a
valid name.