Previously, we sorted rules by schema name and then rule name;
if that wasn't unique, we sorted by rule OID. This can be
problematic for comparing dumps from databases with different
histories, especially since certain rule names like "_RETURN"
are very common. Let's make the sort key schema name, rule name,
table name, which should be unique. (This is the same behavior
we've long used for triggers and RLS policies.)
Andreas Karlsson
This back-patches v18 commit
350e6b8ea86c22c0b95c2e32a4e8d109255b5596 to
all supported branches. The next commit will assert that pg_dump
provides a stable sort order for all object types. That assertion would
fail without stabilizing DO_RULE order as this commit did.
Discussion: https://postgr.es/m/
b4e468d8-0cd6-42e6-ac8a-
1d6afa6e0cf1@proxel.se
Discussion: https://postgr.es/m/
20250707192654.9e.nmisch@google.com
Backpatch-through: 13-17
if (cmpval != 0)
return cmpval;
}
+ else if (obj1->objType == DO_RULE)
+ {
+ RuleInfo *robj1 = *(RuleInfo *const *) p1;
+ RuleInfo *robj2 = *(RuleInfo *const *) p2;
+
+ /* Sort by table name (table namespace was considered already) */
+ cmpval = strcmp(robj1->ruletable->dobj.name,
+ robj2->ruletable->dobj.name);
+ if (cmpval != 0)
+ return cmpval;
+ }
else if (obj1->objType == DO_TRIGGER)
{
TriggerInfo *tobj1 = *(TriggerInfo *const *) p1;