Re: pgsql: Catalog changes preparing for builtin collation provider.
От | Tom Lane |
---|---|
Тема | Re: pgsql: Catalog changes preparing for builtin collation provider. |
Дата | |
Msg-id | 1553991.1710191312@sss.pgh.pa.us обсуждение исходный текст |
Ответ на | Re: pgsql: Catalog changes preparing for builtin collation provider. (Jeff Davis <pgsql@j-davis.com>) |
Ответы |
Re: pgsql: Catalog changes preparing for builtin collation provider.
|
Список | pgsql-committers |
Jeff Davis <pgsql@j-davis.com> writes: > My commit adds a line using the s/// operator. Oh, independently of the empty-pattern problem: what you added is +# Numeric major version of old cluster, ignoring "devel" suffix. +# Needed for testing upgrades from development version to itself. +my $old_major_version = int($oldnode->pg_version =~ s/devel//rg); Surely this will break the moment we enter beta. Rather than trying to fix that directly, what we should be doing is realizing that you've reinvented -- badly -- the facilities provided by the PostgreSQL::Version package. The code you changed, if ($oldnode->pg_version >= 15 && $ENV{with_icu} eq 'yes') was perfectly correct as it stood, because pg_version is a PostgreSQL::Version object. Why did you feel a need to editorialize on that? regards, tom lane
В списке pgsql-committers по дате отправления: