number of columns we're actually reporting on
- add more tests for negative row index
- changelog/migration

via :paramref:`.create_engine.isolation_level` and
:paramref:`.Connection.execution_options.isolation_level`
parameters.  fixes #3534

handled within visit_select(); this attribute was added in the
1.0 series to accommodate the subquery wrapping behavior of
SQL Server and Oracle while also working with positional
column targeting and no longer relying upon "key fallback"
in order to target columns in such a statement.  The IBM DB2
third-party dialect also has this use case, but its implementation
is using regular expressions to rewrite the textual SELECT only
and does not make use of a "wrapped" select at this time.
The logic no longer attempts to reconcile proxy set collections as
this was not deterministic, and instead assumes that the select()
and the wrapper select() match their columns postionally,
at least for the column positions they have in common,
so it is now very simple and safe.  fixes #3657.
- as a side effect of #3657 it was also revealed that the
strategy of calling upon a ResultProxy._getter was not
correctly calling into NoSuchColumnError when an expected
column was not present, and instead returned None up to
loading.instances() to produce NoneType failures; added
a raiseerr argument to _getter() which is called when we
aren't expecting None, fixes #3658.

logging, exception, and  ``repr()`` purposes now truncate very large
scalar values within each collection, including an
"N characters truncated"
notation, similar to how the display for large multiple-parameter sets
are themselves truncated.
fixes #2837

and this time also fix the cext itself to properly handle int vs. long
on py2k