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

On Mon, 2024-03-11 at 16:21 -0400, Tom Lane wrote:
> Oh!  No, it's a "feature": man perlop quoth

Wow.

> So we actually need to find and nuke all of these, not just the one
> that's causing trouble.

For now I committed the one change to fix the buildfarm.

I am still confused on a couple of points here, such as: why does my
example work fine on newer versions of perl?

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.

Reagrds,
    Jeff Davis