From: | Michał Kłeczek <michal(at)kleczek(dot)org> |
---|---|
To: | Thiemo Kellner <thiemo(at)gelassene-pferde(dot)biz> |
Cc: | pgsql-general(at)lists(dot)postgresql(dot)org |
Subject: | Re: Lookup tables |
Date: | 2025-02-05 18:13:49 |
Message-ID: | 4B983ADC-3A5C-442F-B377-D0C10FC1C100@kleczek.org |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgadmin-support pgsql-general |
> On 5 Feb 2025, at 19:07, Thiemo Kellner <thiemo(at)gelassene-pferde(dot)biz> wrote:
>
> El 04-02-25 a las 18:08, Michał Kłeczek escribió:
>>> Reality tends to become so ambiguous as to not be
>>> reflectable (two entirely different restaurants eventually,
>>> within the flow of time, carry the very same name).
>>>
>>> A primary key is very likely not the proper place to reflect
>>> arbitrary business logic (is it the same restaurant or not ?
>>> what if two restaurants have the same name at the same time
>> These are of course problems ( and beyond the scope of my contrived example ).
>>
>> The point is though, that having surrogate PK not only does not solve these issues but makes them worse by kicking the can down the road and allowing for inconsistencies.
> Only if you do not see the primary key as the main immutable value identifying an object, entity, you name it.
Surrogate key cannot identify any (real) object by definition :)
What object is identified by PK value 42 in “restaurants” table?
> Having said that, it is very questionable that a natural key (names to name one) can be a suitable primary key (think of typo).
Typos are indeed a problem but adding surrogate key does not solve it, I’m afraid.
—
Michal
From | Date | Subject | |
---|---|---|---|
Next Message | Thiemo Kellner | 2025-02-05 20:15:41 | Re: Lookup tables |
Previous Message | Thiemo Kellner | 2025-02-05 18:07:30 | Re: Lookup tables |
From | Date | Subject | |
---|---|---|---|
Next Message | Adrian Klaver | 2025-02-05 19:06:16 | Re: Table copy |
Previous Message | Thiemo Kellner | 2025-02-05 18:07:30 | Re: Lookup tables |