From: Tom Lane <tgl@sss.pgh.pa.us>
To: Jeff Davis <pgsql@j-davis.com>
cc: pgsql-committers@lists.postgresql.org
Subject: Re: pgsql: Catalog changes preparing for builtin collation provider.
In-reply-to: <0ef325fa06e7a1605c4e119c4ecb637c67e5fb4e.camel@j-davis.com>
References: <E1rj5WA-002z5V-WA@gemulon.postgresql.org>
 <8899c7c62b86370076110920686fd24863b69a01.camel@j-davis.com>
 <1222780.1710047108@sss.pgh.pa.us>
 <0ef325fa06e7a1605c4e119c4ecb637c67e5fb4e.camel@j-davis.com>
Comments: In-reply-to Jeff Davis <pgsql@j-davis.com>
	message dated "Mon, 11 Mar 2024 12:26:55 -0700"
MIME-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-ID: <1553990.1710191312.1@sss.pgh.pa.us>
Date: Mon, 11 Mar 2024 17:08:32 -0400
Message-ID: <1553991.1710191312@sss.pgh.pa.us>
Archived-At: 
 <https://www.postgresql.org/message-id/1553991.1710191312%40sss.pgh.pa.us>
Precedence: bulk

Jeff Davis <pgsql@j-davis.com> writes:
> My commit adds a line using the s/// operator.

Oh, independently of the empty-pattern problem: what you added is

+# Numeric major version of old cluster, ignoring "devel" suffix.
+# Needed for testing upgrades from development version to itself.
+my $old_major_version = int($oldnode->pg_version =~ s/devel//rg);

Surely this will break the moment we enter beta.  Rather than
trying to fix that directly, what we should be doing is realizing
that you've reinvented -- badly -- the facilities provided by
the PostgreSQL::Version package.  The code you changed,

	if ($oldnode->pg_version >= 15 && $ENV{with_icu} eq 'yes')

was perfectly correct as it stood, because pg_version is a
PostgreSQL::Version object.  Why did you feel a need to
editorialize on that?

			regards, tom lane