aboutsummaryrefslogtreecommitdiff
path: root/contrib/postgres_fdw/postgres_fdw.c
diff options
context:
space:
mode:
authorTom Lane <tgl@sss.pgh.pa.us>2024-06-06 15:16:56 -0400
committerTom Lane <tgl@sss.pgh.pa.us>2024-06-06 15:16:56 -0400
commit7515982636902ad1e945b4606b02ee706dadb83e (patch)
tree07224e4456926a67d77f9f53c2f9de2eca611419 /contrib/postgres_fdw/postgres_fdw.c
parente6cd85772647099563da5ada53bd6ab7d096ce00 (diff)
downloadpostgresql-7515982636902ad1e945b4606b02ee706dadb83e.tar.gz
postgresql-7515982636902ad1e945b4606b02ee706dadb83e.zip
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
Diffstat (limited to 'contrib/postgres_fdw/postgres_fdw.c')
0 files changed, 0 insertions, 0 deletions