summaryrefslogtreecommitdiff
path: root/src/tutorial/funcs.c
diff options
context:
space:
mode:
authorDavid Rowley <drowley@postgresql.org>2025-10-07 14:15:04 +1300
committerDavid Rowley <drowley@postgresql.org>2025-10-07 14:15:04 +1300
commit928df067d1e6ca5b747722d32c79bc3efa891a32 (patch)
treeba30ee4ca91862371e3091cffe0b007a785f3b24 /src/tutorial/funcs.c
parent771cfe22a0982f8716abfa253707e74fbbad873a (diff)
Fix incorrect targetlist in dummy UNIONs
The prior code, added in 03d40e4b5 attempted to use the targetlist of the first UNION child when all UNION children were proven as dummy rels. That's not going to work when some operation atop of the Result node must find target entries within the Result's targetlist. This could have been something as simple as trying to sort the results of the UNION operation, which would lead to: ERROR: could not find pathkey item to sort Instead, use the top-level UNION's targetlist and fix the varnos in setrefs.c. Because set operation targetlists always use varno==0, we can rewrite those to become varno==1, i.e. use the Vars from the first UNION child. This does result in showing Vars from relations that are not present in the final plan, but that's no different to what we see when normal base relations are proven dummy. Without this fix it would be possible to see the following error in EXPLAIN VERBOSE when all UNION inputs were proven empty. ERROR: bogus varno: 0 Author: David Rowley <dgrowleyml@gmail.com> Discussion: https://postgr.es/m/CAApHDvrUASy9sfULMEsM2udvZJP6AoBRCZvHYXYxZTy2tX9FYw@mail.gmail.com
Diffstat (limited to 'src/tutorial/funcs.c')
0 files changed, 0 insertions, 0 deletions