Re: Lookup tables - Mailing list pgsql-general

From Michał Kłeczek
Subject Re: Lookup tables
Date
Msg-id 4B983ADC-3A5C-442F-B377-D0C10FC1C100@kleczek.org
Whole thread Raw
In response to Re: Lookup tables  (Thiemo Kellner <thiemo@gelassene-pferde.biz>)
Responses Re: Lookup tables
List pgsql-general

> On 5 Feb 2025, at 19:07, Thiemo Kellner <thiemo@gelassene-pferde.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
thecan 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
oftypo). 

Typos are indeed a problem but adding surrogate key does not solve it, I’m afraid.

—
Michal


pgsql-general by date:

Previous
From: Thiemo Kellner
Date:
Subject: Re: Lookup tables
Next
From: Adrian Klaver
Date:
Subject: Re: Table copy