Search code examples
c++std-variant

How to use alternative types of std::variant polymorphically


I am writing a parser and am using a std::variant to represent the nodes of the AST. For basic expressions, I have something like:

struct Add;
struct Sub;
struct Mul;
struct Div;
typedef std::variant<Add, Sub, Mul, Div> Node;

(The actual structure definitions come later, because some of them refer to Node.)

I find this approach better than declaring Node as an abstract base class and Add etc. as subclasses because it enables me to separate the logic for using the AST from the AST itself. For example, the code that evaluates the expression can use std::visit without Node needing a virtual evaluate method or doing type checks and downcasts.

My problem it that there are some fields that I want every Node to have, and I'd like to be able to treat all Node variants the same when using those fields.

The only strategies I've come with are:

  • Define Node as a struct that has the common fields and a separate std::variant member.
  • Define the fields separately in each Node alternative, and for each field, define a visitor with a const auto & member that selects that field. In other words, just use visitors.

Is there any other way? What I'd really like to do is define an abstract base class with the fields, have all the Node alternatives (Add etc.) inherit from that class, and then be able to say, "I don't know what alternative this std::variant contains, but I know that they all are instances of this base class, and I just want to use it as an instance of that class.”


Solution

  • Assuming every type in the variant has some field std::string_view token; (whether this is written out in each one or comes from a common, not necessarily polymorphic, base class is up to you), you could write accessors like the following:

    std::string_view getToken(const Node& node)
    {
      return std::visit([](const auto& n) { return n.token; }, node);
    }
    

    https://godbolt.org/z/B8tAdY

    Note that you don't have to manually add overloads - the auto in the lambda essentially makes the lambda a template, so you just rely on compile-time polymorphism. You end up with a nice jump table (each one just returning the appropriate member offsets):

    std::__detail::__variant::__gen_vtable_impl<true, std::__detail::__variant::_Multi_array<std::basic_string_view<char, std::char_traits<char> > (*)(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&)>, std::tuple<std::variant<Add, Sub, Mul, Div> const&>, std::integer_sequence<unsigned long, 0ul> >::__visit_invoke(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&): # @"std::__detail::__variant::__gen_vtable_impl<true, std::__detail::__variant::_Multi_array<std::basic_string_view<char, std::char_traits<char> > (*)(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&)>, std::tuple<std::variant<Add, Sub, Mul, Div> const&>, std::integer_sequence<unsigned long, 0ul> >::__visit_invoke(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&)"
            mov     rax, qword ptr [rsi + 8]
            mov     rdx, qword ptr [rsi + 16]
            ret
    std::__detail::__variant::__gen_vtable_impl<true, std::__detail::__variant::_Multi_array<std::basic_string_view<char, std::char_traits<char> > (*)(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&)>, std::tuple<std::variant<Add, Sub, Mul, Div> const&>, std::integer_sequence<unsigned long, 1ul> >::__visit_invoke(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&): # @"std::__detail::__variant::__gen_vtable_impl<true, std::__detail::__variant::_Multi_array<std::basic_string_view<char, std::char_traits<char> > (*)(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&)>, std::tuple<std::variant<Add, Sub, Mul, Div> const&>, std::integer_sequence<unsigned long, 1ul> >::__visit_invoke(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&)"
            mov     rax, qword ptr [rsi + 16]
            mov     rdx, qword ptr [rsi + 24]
            ret
    std::__detail::__variant::__gen_vtable_impl<true, std::__detail::__variant::_Multi_array<std::basic_string_view<char, std::char_traits<char> > (*)(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&)>, std::tuple<std::variant<Add, Sub, Mul, Div> const&>, std::integer_sequence<unsigned long, 2ul> >::__visit_invoke(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&): # @"std::__detail::__variant::__gen_vtable_impl<true, std::__detail::__variant::_Multi_array<std::basic_string_view<char, std::char_traits<char> > (*)(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&)>, std::tuple<std::variant<Add, Sub, Mul, Div> const&>, std::integer_sequence<unsigned long, 2ul> >::__visit_invoke(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&)"
            mov     rax, qword ptr [rsi + 8]
            mov     rdx, qword ptr [rsi + 16]
            ret
    std::__detail::__variant::__gen_vtable_impl<true, std::__detail::__variant::_Multi_array<std::basic_string_view<char, std::char_traits<char> > (*)(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&)>, std::tuple<std::variant<Add, Sub, Mul, Div> const&>, std::integer_sequence<unsigned long, 3ul> >::__visit_invoke(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&): # @"std::__detail::__variant::__gen_vtable_impl<true, std::__detail::__variant::_Multi_array<std::basic_string_view<char, std::char_traits<char> > (*)(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&)>, std::tuple<std::variant<Add, Sub, Mul, Div> const&>, std::integer_sequence<unsigned long, 3ul> >::__visit_invoke(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&)"
            mov     rax, qword ptr [rsi + 16]
            mov     rdx, qword ptr [rsi + 24]
            ret
    
    std::__detail::__variant::__gen_vtable<true, std::basic_string_view<char, std::char_traits<char> >, getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&>::_S_vtable:
            .quad   std::__detail::__variant::__gen_vtable_impl<true, std::__detail::__variant::_Multi_array<std::basic_string_view<char, std::char_traits<char> > (*)(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&)>, std::tuple<std::variant<Add, Sub, Mul, Div> const&>, std::integer_sequence<unsigned long, 0ul> >::__visit_invoke(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&)
            .quad   std::__detail::__variant::__gen_vtable_impl<true, std::__detail::__variant::_Multi_array<std::basic_string_view<char, std::char_traits<char> > (*)(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&)>, std::tuple<std::variant<Add, Sub, Mul, Div> const&>, std::integer_sequence<unsigned long, 1ul> >::__visit_invoke(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&)
            .quad   std::__detail::__variant::__gen_vtable_impl<true, std::__detail::__variant::_Multi_array<std::basic_string_view<char, std::char_traits<char> > (*)(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&)>, std::tuple<std::variant<Add, Sub, Mul, Div> const&>, std::integer_sequence<unsigned long, 2ul> >::__visit_invoke(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&)
            .quad   std::__detail::__variant::__gen_vtable_impl<true, std::__detail::__variant::_Multi_array<std::basic_string_view<char, std::char_traits<char> > (*)(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&)>, std::tuple<std::variant<Add, Sub, Mul, Div> const&>, std::integer_sequence<unsigned long, 3ul> >::__visit_invoke(getToken(std::variant<Add, Sub, Mul, Div> const&)::$_0&&, std::variant<Add, Sub, Mul, Div> const&)
    

    Sadly, using the common base class does not lead to the compiler realizing that all the cases have identical code - you still keep the jump table: https://godbolt.org/z/GTyNgP

    You could theoretically roll with a custom variant-like type erasure data structure that is aware of all the types having a common base class and going through that instead. But this moves in the direction of just having a NodeBase class with the common interface etc.