pg_regress: there's no other way to cope with testing a relocated
installation.  Seems better to call it --psqldir though, since the
only thing we need to find in that case is psql.  It'd be better if
we could use find_other_exec, but that's not happening unless we are
willing to install pg_regress alongside psql, which seems unlikely
to happen.

the check on diff's exit status to check for literally 0 or 1.  Someone
should look into why WIFEXITED/WEXITSTATUS don't work for this, but I've
spent more than enough time on it already.

May help in debugging behavior on Windows.

not when they're started.  This mimics a subtle point of the behavior
of the old shell script, and gives better feedback when watching the
tests.

switches passed from the Makefile.  This looks like it will fix
problem with virtual vs real paths under msys.

just exec instead of creating a subprocess.  This reduces process usage
from four processes per parallel test to two.  I have no idea whether
a comparable optimization is possible or useful in the Windows port.

'make install' or 'initdb' fails.  Also minor simplification of fgets()
usage --- fgets guarantees a trailing null anyway.

This allows it to be used on Windows without installing mingw
(though you do still need 'diff'), and opens the door to future
improvements such as message localization.
Magnus Hagander and Tom Lane.