MergeAttributes: convert pg_attribute back to ColumnDef before comparing

MergeAttributes() has a loop to merge multiple inheritance parents
into a column column definition.  The merged-so-far definition is
stored in a ColumnDef node.  If we have to merge columns from multiple
inheritance parents (if the name matches), then we have to check
whether various column properties (type, collation, etc.) match.  The
current code extracts the pg_attribute value of the
currently-considered inheritance parent and compares it against the
merged-so-far ColumnDef value.  If the currently considered column
doesn't match any previously inherited column, we make a new ColumnDef
node from the pg_attribute information and add it to the column list.

This patch rearranges this so that we create the ColumnDef node first
in either case.  Then the code that checks the column properties for
compatibility compares ColumnDef against ColumnDef (instead of
ColumnDef against pg_attribute).  This makes the code more symmetric
and easier to follow.  Also, later in MergeAttributes(), there is a
similar but separate loop that merges the new local column definition
with the combination of the inheritance parents established in the
first loop.  That comparison is already ColumnDef-vs-ColumnDef.  With
this change, both of these can use similar-looking logic.  (A future
project might be to extract these two sets of code into a common
routine that encodes all the knowledge of whether two column
definitions are compatible.  But this isn't currently straightforward
because we want to give different error messages in the two cases.)
Furthermore, by avoiding the use of Form_pg_attribute here, we make it
easier to make changes in the pg_attribute layout without having to
worry about the local needs of tablecmds.c.

Because MergeAttributes() is hugely long, it's sometimes hard to know
where in the function you are currently looking.  To help with that, I
also renamed some variables to make it clearer where you are currently
looking.  The first look is "prev" vs. "new", the second loop is "inh"
vs. "new".

Reviewed-by: Ashutosh Bapat <ashutosh.bapat.oss@gmail.com>
Discussion: https://www.postgresql.org/message-id/flat/52a125e4-ff9a-95f5-9f61-b87cf447e4da@eisentraut.org

Author: petere