David Rowley writes:
> On Tue, 30 Apr 2024 at 14:14, Tom Lane wrote:
>> Yeah, the affected buildfarm members seem still not happy.
> Isn't your latest fix adding COLLATE "C" to the wrong test?
Oh! No, it was definitely adjusting a test that needed it,
just not the only one :-(. Thanks for
On Tue, 30 Apr 2024 at 14:14, Tom Lane wrote:
> Yeah, the affected buildfarm members seem still not happy.
Isn't your latest fix adding COLLATE "C" to the wrong test?
Crake is failing with [1]:
---
/home/andrew/bf/root/HEAD/pgsql/src/test/modules/test_pg_dump/expected/test_pg_dump.out
I wrote:
> I committed that suggestion, but I'm not sure it's enough to fix it,
> because if I do
> LANG=cs_CZ.utf8 make check
> then I still get variant output order. I tried about six different
> spellings of the query without improving matters, so I'm totally
> baffled. Have we managed
David Rowley writes:
> Still failing for me and [1].
> Maybe:
> SELECT pg_describe_object(classid,objid,objsubid) COLLATE "C" AS obj,
> Gets me the results in the expected order.
I committed that suggestion, but I'm not sure it's enough to fix it,
because if I do
LANG=cs_CZ.utf8 make
David Rowley writes:
> Maybe:
> SELECT pg_describe_object(classid,objid,objsubid) COLLATE "C" AS obj,
Argh, I knew better than to not specify COLLATE "C".
This commit's feeling a little snakebit.
regards, tom lane
On Tue, 30 Apr 2024 at 12:23, Tom Lane wrote:
>
> Fix test case from b0c5b215d.
Still failing for me and [1].
Maybe:
SELECT pg_describe_object(classid,objid,objsubid) COLLATE "C" AS obj,
Gets me the results in the expected order.
David
[1]
Fix test case from b0c5b215d.
I'd not checked that this iteration of the test actually worked
with a bootstrap superuser not named 'postgres'. It didn't,
because the coercion rules for CASE caused us to try to cast
the 'postgres' literal to regrole. Mea culpa.
Per buildfarm (via Alexander
