Re: pgsql: Catalog changes preparing for builtin collation provider.

Jeff Davis <pgsql@j-davis.com> writes:
> I am still confused on a couple of points here, such as: why does my
> example work fine on newer versions of perl?

I'm not sure about that either.  The discussions of this that I found
on-line say that it's not something the Perl gurus want to get rid of,
but it sure seems like they must have tightened the behavior to some
extent.

Another question is why it didn't fail on all the animals with similar
Perl vintage.  My guess about that is that there's some configuration
difference causing the Perl script to take slightly different code
paths, but it's just a guess.

> But I agree: if the empty pattern is magical, we should get rid of it,
> even if we don't understand the exact conditions under which it behaves
> magically.

Yeah.  I was dismayed to find that there's no perlcritic check for
this, because it sure seems like the kind of thing you don't want
to invoke by accident.

            regards, tom lane