Record dependencies of a cast on other casts that it requires.

When creating a cast that uses a conversion function, we've
historically allowed the input and result types to be
binary-compatible with the function's input and result types,
rather than necessarily being identical.  This means that the new
cast is logically dependent on the binary-compatible cast or casts
that it references: if those are defined by pg_cast entries, and you
try to restore the new cast without having defined them, it'll fail.
Hence, we should make pg_depend entries to record these dependencies
so that pg_dump knows that there is an ordering requirement.

This is not the only place where we allow such shortcuts; aggregate
functions for example are similarly lax, and in principle should gain
similar dependencies.  However, for now it seems sufficient to fix
the cast-versus-cast case, as pg_dump's other ordering heuristics
should keep it out of trouble for other object types.

Per report from David Turoň; thanks also to Robert Haas for
preliminary investigation.  I considered back-patching, but
seeing that this issue has existed for many years without
previous reports, it's not clear it's worth the trouble.
Moreover, back-patching wouldn't be enough to ensure that the
new pg_depend entries exist in existing databases anyway.

Discussion: https://postgr.es/m/OF0A160F3E.578B15D1-ONC12588DA.003E4857-C12588DA.0045A428@notes.linuxbox.cz

1 files changed, 1 insertions, 1 deletions

diff --git a/src/tools/valgrind.supp b/src/tools/valgrind.supp
index 4e8c482757..7ea464c809 100644
--- a/src/tools/valgrind.supp
+++ b/src/tools/valgrind.supp
@@ -113,7 +113,7 @@
 	overread_tuplestruct_pg_cast
 	Memcheck:Addr4
 
-	fun:IsBinaryCoercible
+	fun:IsBinaryCoercibleWithCast
 }
 
 # Python's allocator does some low-level tricks for efficiency. Those