We now follow the order of checks from HeapTupleSatisfies* more
closely to avoid coming to erroneous conclusions.

Mark Dilger and Robert Haas

Discussion: http://postgr.es/m/CA+Tgmob6sii0yTvULYJ0Vq4w6ZBmj7zUhddL3b+SKDi9z9NA7Q@mail.gmail.com