Opened up two tests that now pass with pg8000. Also, rewrote two tests
to use actual tables rather than having a round trip in a single select
statement. This is necessary for pg8000 because it sends strings to the
server with type 'unknown' and lets the server work out the type.

based on hash ordering of the ClassManager

mapper is implicitly combining one of its column-based attributes
with that of the parent, where those columns normally don't necessarily
share the same value.  This is an extension of an existing check that
was added via :ticket:`1892`; however this new check emits only a
warning, instead of an exception, to allow for applications that may
be relying upon the existing behavior.
fixes #3042

when that :class:`.Column` is referred to in an explicit
:class:`.PrimaryKeyConstraint` for that table.  This behavior now
matches that of when the :class:`.Column` itself has the
:paramref:`.Column.primary_key` flag set to ``True``, which is
intended to be an exactly equivalent case.
fixes #3023

While "oid" is generally a private type within PG that is not exposed
in modern versions, there are some PG use cases such as large object
support where these types might be exposed, as well as within some
user-reported schema reflection use cases.
fixes #3002

on an index needed to have the same quoting for quoted names in
order to be recognized.  The fix makes the quotes optional but
also provides the old behavior for backwards compatibility with those
using the workaround.
fixes #3085

columns are always added to the list of columns to be "undeferred";
otherwise, the ORM can't load the row's identity.   Apparently,
one can defer the mapped primary keys and the ORM will fail, that
hasn't been changed.  But as load_only is essentially saying
"defer all but X", it's more critical that PK cols not be part of this
deferral. fixes #3080