Feedback-ID: ia2694551:Fastmail
Date: Wed, 8 Jan 2025 14:10:45 +0100
From: Alvaro Herrera <alvherre@alvh.no-ip.org>
To: shammat@gmx.net
Cc: pgsql-general@lists.postgresql.org
Subject: Re: Postgres 17 domains with NOT NULL and pg_get_constraintdef()
Message-ID: <202501081310.k4vpnx4wa623@alvherre.pgsql>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
Content-Transfer-Encoding: 8bit
In-Reply-To: <f90c6099-521e-48d7-99eb-07e85f606be4@gmx.net>
Archived-At: <https://www.postgresql.org/message-id/202501081310.k4vpnx4wa623%40alvherre.pgsql>
Precedence: bulk

On 2025-Jan-08, shammat@gmx.net wrote:

Hello,

> However, because the domain is defined with NOT NULL, this fails with
> 
> > ERROR: invalid constraint type "n"
> 
> with 17.2 on Windows and Linux.
> 
> This is a result of storing the NOT NULL constraint in pg_constraint
> and can easily be avoided by either using contype <> 'n' or by not calling
> pg_get_constraintdef if contype = 'n'

Yeah, thanks for the report -- this is clearly a bug and it was fixed
already in the 17 branch, but it's not been released yet.  It'll be in
the February release.

Author: Álvaro Herrera <alvherre@alvh.no-ip.org>
Branch: master [09d09d429] 2024-11-27 13:50:27 +0100
Branch: REL_17_STABLE [6e793582b] 2024-11-27 13:50:27 +0100

    Fix pg_get_constraintdef for NOT NULL constraints on domains
    
    We added pg_constraint rows for all not-null constraints, first for
    tables and later for domains; but while the ones for tables were
    reverted, the ones for domains were not.  However, we did accidentally
    revert ruleutils.c support for the ones on domains in 6f8bb7c1e961,
    which breaks running pg_get_constraintdef() on them.  Put that back.
    
    This is only needed in branch 17, because we've reinstated this code in
    branch master with commit 14e87ffa5c54.  Add some new tests in both
    branches.
    
    I couldn't find anything else that needs de-reverting.
    
    Reported-by: Erki Eessaar <erki.eessaar@taltech.ee>
    Reviewed-by: Magnus Hagander <magnus@hagander.net>
    Discussion: https://postgr.es/m/AS8PR01MB75110350415AAB8BBABBA1ECFE222@AS8PR01MB7511.eurprd01.prod.exchangelabs.com

-- 
Álvaro Herrera        Breisgau, Deutschland  —  https://www.EnterpriseDB.com/
"Right now the sectors on the hard disk run clockwise, but I heard a rumor that
you can squeeze 0.2% more throughput by running them counterclockwise.
It's worth the effort. Recommended."  (Gerry Pourwelle)