This implementation was wrong anyway because it did not respect
scoping rules. This will need to be revisited soon. The most likely
result is that the grammar is going to need some significant re-work
to be able to use a IDENTIFIER in all the places where a TYPE_NAME is
currently used.
Add a constructor that uses an ast_struct_specifier and one that uses
a type name. This saves a (trivial) bit of code, but it also ensures
some of the class invariants (i.e., type_name != NULL) are met.
When the implementation of function_call_header and
function_identifier were changed a few commits ago, the types of the
production changed. This just updates the types specified for the
productions to match reality.
