Implementation of [#1546 (BitBucket)](https://bitbucket.org/zzzeek/sqlalchemy/issues/1546).

Very unfinished but I have reflection and setting after table creation working for PostgreSQL.

If you're not opposed, perhaps best to continue discussion on Gerrit?

Change-Id: Ib90683850805a2b4ee198e420dc294f32f15d35d
Pull-request: https://github.com/zzzeek/sqlalchemy/pull/284

Co-Authored-By: Mike Bayer <mike_mp@zzzcomputing.com>
Change-Id: Ie6cf2d2958d1c567324db9e08fef2d3186e97350
Pull-request: https://bitbucket.org/zzzeek/sqlalchemy/pull-requests/80

Previously, it was impossible to have a Table that has
None for a schema name when the "schema" parameter on
MetaData was set.  A new symbol sqlalchemy.schema.BLANK_SCHEMA
is added which indicates that the schema name should unconditionally
be set to None.  In particular, this value must be passed within
cross-schema foreign key reflection, so that a Table which
is in the "default" schema can be represented properly.

Fixes: #3716
Change-Id: I3d24f99c22cded206c5379fd32a225e74edb7a8e

Fixed a bug in the result proxy used mainly by Oracle when binary and
other LOB types are in play, such that when query / statement caching
were used, the type-level result processors, notably that required by
the binary type itself but also any other processor, would become lost
after the first run of the statement due to it being removed from the
cached result metadata.

Change-Id: I751940866cffb4f48de46edc8137482eab59790c
Fixes: #3699

Fixed bug where when using ``case_sensitive=False`` with an
:class:`.Engine`, the result set would fail to correctly accomodate
for duplicate column names in the result set, causing an error
when the statement is executed in 1.0, and preventing the
"ambiguous column" exception from functioning in 1.1.

Change-Id: If582bb9fdd057e4da3ae42f7180b17d1a1a2d98e
Fixes: #3690