pg_dump: provide a stable sort order for rules.

tglsfdc · nmisch · commit cc9a62c51a18 · 2025-07-31T06:38:03.000-07:00
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 350e6b8 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
diff --git a/src/bin/pg_dump/pg_dump_sort.c b/src/bin/pg_dump/pg_dump_sort.c
@@ -238,6 +238,17 @@ DOTypeNameCompare(const void *p1, const void *p2)
 		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;
