rework for scans

rework for scans

This seems to actually kind of work, but there are definitely some things
that are broken.

In particular, PARTITIONWISE() advice is being emitted for plans where
Append nodes are induced by setops rather than by table inheritance;
and what looks like extra PARTITIONWISE() advice is also being emitted
for non-obvious reasons in some table inheritance cases.

Also, INDEX_SCAN(), INDEX_ONLY_SCAN(), and BITMAP_HEAP_SCAN() output
needs revising, and ORDINARY_SCAN() output needs suppressing.