diff options
| author | Tom Lane <tgl@sss.pgh.pa.us> | 2021-04-22 17:30:42 -0400 |
|---|---|---|
| committer | Tom Lane <tgl@sss.pgh.pa.us> | 2021-04-22 17:30:42 -0400 |
| commit | 05ce4bf8b1d45cc55762fab627ea91d1ffbbdc03 (patch) | |
| tree | 8299fa5af0eb65850b42776c18080ad3eb0d5284 /src/backend/executor/nodeCustom.c | |
| parent | 3fb93103a9fd5182f4f75d6da87dadcb3b36d7b1 (diff) | |
| download | postgresql-05ce4bf8b1d45cc55762fab627ea91d1ffbbdc03.tar.gz postgresql-05ce4bf8b1d45cc55762fab627ea91d1ffbbdc03.zip | |
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
Diffstat (limited to 'src/backend/executor/nodeCustom.c')
0 files changed, 0 insertions, 0 deletions