aboutsummaryrefslogtreecommitdiff
path: root/doc/src
diff options
context:
space:
mode:
authorTom Lane <tgl@sss.pgh.pa.us>2024-06-04 18:02:13 -0400
committerTom Lane <tgl@sss.pgh.pa.us>2024-06-04 18:02:13 -0400
commitb631d014987b9411ed0eeb7dcba9e0a8599bc3cf (patch)
tree28ec173ddb9cc80d8363e321a555fcc40559f6e6 /doc/src
parentcd2624fd97b0c36b68da278abc5362647f69b07d (diff)
downloadpostgresql-b631d014987b9411ed0eeb7dcba9e0a8599bc3cf.tar.gz
postgresql-b631d014987b9411ed0eeb7dcba9e0a8599bc3cf.zip
Fix pl/tcl's handling of errors from Tcl_ListObjGetElements().
In a procedure or function returning tuple, we use that function to parse the Tcl script's result, which is supposed to be a Tcl list. If it isn't, you get an error. Commit 26abb50c4 incautiously supposed that we could use throw_tcl_error() to report such an error. That doesn't actually work, because low-level functions like Tcl_ListObjGetElements() don't fill Tcl's errorInfo variable. The result is either a null-pointer-dereference crash or emission of misleading context information describing the previous Tcl error. Back off to just reporting the interpreter's result string, and improve throw_tcl_error()'s comment to explain when to use it. Also, although the similar code in pltcl_trigger_handler() avoided this mistake, it was using a fairly confusing wording of the error message. Improve that while we're here. Per report from A. Kozhemyakin. Back-patch to all supported branches. Erik Wienhold and Tom Lane Discussion: https://postgr.es/m/6a2a1c40-2b2c-4a33-8b72-243c0766fcda@postgrespro.ru
Diffstat (limited to 'doc/src')
0 files changed, 0 insertions, 0 deletions