aboutsummaryrefslogtreecommitdiff
path: root/contrib/jsonb_plpython
diff options
context:
space:
mode:
authorTom Lane <tgl@sss.pgh.pa.us>2025-03-25 20:03:56 -0400
committerTom Lane <tgl@sss.pgh.pa.us>2025-03-25 20:03:56 -0400
commitcb36f8ec2124b0c495da057a2f55735fe858be0e (patch)
treec1101b85117423742a905da492cb6ec3fc626863 /contrib/jsonb_plpython
parent3430215fe35f96e4be355c93e275f00656800602 (diff)
downloadpostgresql-cb36f8ec2124b0c495da057a2f55735fe858be0e.tar.gz
postgresql-cb36f8ec2124b0c495da057a2f55735fe858be0e.zip
Fix order of -I switches for building pg_regress.o.
We need the -I switch for libpq_srcdir to come before any -I switches injected by configure. Otherwise there is a risk of pulling in a mismatched version of libpq_fe.h from someplace like /usr/local/include, if the platform has another Postgres version installed there. This evidently accounts for today's buildfarm failures on "anaconda". In principle the -I switch for src/port/ is at similar hazard, and has been for a very long time. But the only .h files we keep there are pg_config_paths.h and pthread-win32.h, neither of which get installed on Unix-ish systems, so the odds of picking up a conflicting header seem pretty small. That doubtless accounts for the lack of prior reports. Back-patch to v17 where pg_regress acquired a build dependency on libpq_fe.h. We could go back further to fix the hazard for src/port/ in older branches, but it seems unlikely to be worth troubling over. Reported-by: Nathan Bossart <nathandbossart@gmail.com> Author: Tom Lane <tgl@sss.pgh.pa.us> Discussion: https://postgr.es/m/Z-MhRzoc7t-nPUQG@nathan Backpatch-through: 17
Diffstat (limited to 'contrib/jsonb_plpython')
0 files changed, 0 insertions, 0 deletions