pgsql: Fix failure with SQL-procedure polymorphic output arguments in v

Поиск
Список
Период
Сортировка
От Tom Lane
Тема pgsql: Fix failure with SQL-procedure polymorphic output arguments in v
Дата
Msg-id E1sFIbl-000IrJ-Uz@gemulon.postgresql.org
обсуждение исходный текст
Список pgsql-committers
Fix failure with SQL-procedure polymorphic output arguments in v12.

Before the v13-era commit 913bbd88d, check_sql_fn_retval fails to
resolve polymorphic output types and then just throws up its hands and
assumes the check will be made at runtime.  I think that's true for
ordinary functions returning RECORD, but it doesn't happen in CALL,
potentially resulting in crashes if the actual output of the SQL
procedure's SELECT doesn't match the type inferred from polymorphism.
With a little bit of rearrangement, we can use get_call_result_type
instead of get_func_result_type and thereby infer the correct types.

I'm still unwilling to back-patch all of 913bbd88d, so if the types
don't match you'll get an error rather than perhaps silently inserting
a cast as v13 and later can.  That's consistent with prior behavior
though, so it seems fine.

Prior to 70ffb27b2, you'd typically get other errors due to other
shortcomings of CALL's management of polymorphism.  Nonetheless,
this is an independent bug.

Although there is no bug in v13 and up, it seems prudent to add
the test case for this to the newer branches too.  It's clearly
an under-tested area.

Per report from Andrew Bille.

Discussion: https://postgr.es/m/CAJnzarw9EeWHAQRm76dXd=7j+rgw6ERqC=nCay8jeFqTwKwhqQ@mail.gmail.com

Branch
------
REL_12_STABLE

Details
-------
https://git.postgresql.org/pg/commitdiff/4208f44c9469fa6b105bbb1d1f7ee18b37472860

Modified Files
--------------
src/backend/executor/functions.c               | 66 +++++++++++++++++++-------
src/test/regress/expected/create_procedure.out | 15 ++++++
src/test/regress/sql/create_procedure.sql      |  9 ++++
3 files changed, 74 insertions(+), 16 deletions(-)


В списке pgsql-committers по дате отправления:

Предыдущее
От: Heikki Linnakangas
Дата:
Сообщение: pgsql: Make RelationFlushRelation() work without ResourceOwner during a
Следующее
От: Peter Eisentraut
Дата:
Сообщение: pgsql: Add meson NLS support for pg_walsummary