Don't crash on reference to an un-available system column.
Adopt a more consistent policy about what slot-type-specific
getsysattr functions should do when system attributes are not
available. To wit, they should all throw the same user-oriented
error, rather than variously crashing or emitting developer-oriented
messages.
This closes a identifiable problem in commits a71cfc56b and
3fb93103a (in v13 and v12), so back-patch into those branches,
along with a test case to try to ensure we don't break it again.
It is not known that any of the former crash cases are reachable
in HEAD, but this seems like a good safety improvement in any case.
Discussion: https://postgr.es/m/141051591267657@mail.yandex.ru
Branch
------
master
Details
-------
https://git.postgresql.org/pg/commitdiff/d479d00285255d422a2b38f1cfaa35808968a08c
Modified Files
--------------
src/backend/executor/execTuples.c | 40 +++++++++++++++++++++++----
src/test/regress/expected/update.out | 53 ++++++++++++++++++++++++++++++++++++
src/test/regress/sql/update.sql | 32 ++++++++++++++++++++++
3 files changed, 120 insertions(+), 5 deletions(-)