COPY TO released the ACCESS SHARE lock immediately when it was done rather
than holding on to it until the end of the transaction.

This breaks the case where a REPEATABLE READ transaction could see an
empty table if it repeats a COPY statement and somebody truncated the
table in the meantime.

Before 4dded12f the lock was also released after COPY FROM, but the
commit failed to notice the irregularity in COPY TO.

This is old behavior but doesn't seem important enough to backpatch.

Author: Laurenz Albe, based on suggestion by Robert Haas and Tom Lane
Reviewed-by: Amit Kapila
Discussion: https://postgr.es/m/7bcfc39d4176faf85ab317d0c26786953646a411.camel@cybertec.at