Re: Lookup tables
От | Michał Kłeczek |
---|---|
Тема | Re: Lookup tables |
Дата | |
Msg-id | 4B983ADC-3A5C-442F-B377-D0C10FC1C100@kleczek.org обсуждение исходный текст |
Ответ на | Re: Lookup tables (Thiemo Kellner <thiemo@gelassene-pferde.biz>) |
Ответы |
Re: Lookup tables
|
Список | 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
В списке pgsql-general по дате отправления: