Thanks rpbarlow for the suggestion; and loic, akaariai, and jorgecarleitao
for reviews.

This prevents silent data loss.

Thanks Aymeric Augustin for the initial patch and Loic Bistuer for the review.

Thanks to Aymeric Augustin for the review and Trac alias monkut for the report.

Signed-off-by: Jason Myers <jason@jasonamyers.com>

Squashed commit of the following:

commit 63ddb271a44df389b2c302e421fc17b7f0529755
Author: Aymeric Augustin <aymeric.augustin@m4x.org>
Date:   Sun Sep 29 22:51:00 2013 +0200

    Clarified interactions between atomic and exceptions.

commit 2899ec299228217c876ba3aa4024e523a41c8504
Author: Aymeric Augustin <aymeric.augustin@m4x.org>
Date:   Sun Sep 22 22:45:32 2013 +0200

    Fixed TransactionManagementError in tests.

    Previous commit introduced an additional check to prevent running
    queries in transactions that will be rolled back, which triggered a few
    failures in the tests. In practice using transaction.atomic instead of
    the low-level savepoint APIs was enough to fix the problems.

commit 4a639b059ea80aeb78f7f160a7d4b9f609b9c238
Author: Aymeric Augustin <aymeric.augustin@m4x.org>
Date:   Tue Sep 24 22:24:17 2013 +0200

    Allowed nesting constraint_checks_disabled inside atomic.

    Since MySQL handles transactions loosely, this isn't a problem.

commit 2a4ab1cb6e83391ff7e25d08479e230ca564bfef
Author: Aymeric Augustin <aymeric.augustin@m4x.org>
Date:   Sat Sep 21 18:43:12 2013 +0200

    Prevented running queries in transactions that will be rolled back.

    This avoids a counter-intuitive behavior in an edge case on databases
    with non-atomic transaction semantics.

    It prevents using savepoint_rollback() inside an atomic block without
    calling set_rollback(False) first, which is backwards-incompatible in
    tests.

    Refs #21134.

commit 8e3db393853c7ac64a445b66e57f3620a3fde7b0
Author: Aymeric Augustin <aymeric.augustin@m4x.org>
Date:   Sun Sep 22 22:14:17 2013 +0200

    Replaced manual savepoints by atomic blocks.

    This ensures the rollback flag is handled consistently in internal APIs.

Thanks to Collin Anderson for the suggestion and Tim Graham for
reviewing the patch.

Should be unneeded with Python 2.7 and up.
Added some unicode_literals along the way.

Thanks simon@ for the suggestion and JordanPowell
for the initial patch.