Horton

Re: Reorganize GUC structs

Peter Eisentraut <peter@eisentraut.org>

View thread View on postgr.es
From: Peter Eisentraut <peter@eisentraut.org>
To: Álvaro Herrera <alvherre@kurilemu.de>
Cc: pgsql-hackers <pgsql-hackers@postgresql.org>
Date: 2025-11-12T08:41:07Z
Lists: pgsql-hackers 
On 07.11.25 16:53, Álvaro Herrera wrote:
> On 2025-Nov-07, Peter Eisentraut wrote:
> 
>> Actually, the ", " already exists in the message catalog, so adding a
>> comment here might confuse the other site.
> 
> This one?
> #: replication/logical/relation.c:245
> #, c-format
> msgid ", \"%s\""
> msgstr ", »%s«"
> 
> It's different.  (And warrants a comment too, IMO)

Well, that's the one, but the code actually looks like this now:

     while ((i = bms_next_member(atts, i)) >= 0)
     {
         attcnt++;
         if (attcnt > 1)
             appendStringInfoString(&attsbuf, _(", "));

         appendStringInfo(&attsbuf, _("\"%s\""), remoterel->attnames[i]);
     }

The catalog entries you are showing appear to be from pre-PG18.

There are also similar instances in ExecBuildSlotValueDescription() that 
are not marked up for gettext but perhaps should be.  There might be 
others, and I would expect more like this to appear over time, as people 
like to add more detail like this to diagnostics messages.

Do you have a suggestion what kind of comment to attach there?

Commits

  1. Remove extraneous newlines from guc_parameters.dat

  2. Fix NLS for incorrect GUC enum value hint message

  3. Clean up qsort comparison function for GUC entries

  4. Sort guc_parameters.dat alphabetically by name

  5. Reorganize GUC structs

  6. Change config_generic.vartype to be initialized at compile time

  7. Use designated initializers for guc_tables

  8. Change reset_extra into a config_generic common field

  9. Add some const qualifiers

  10. Modernize some for loops