OCamlLex case-insenstitive

Question

Is there a way to have case in-sensitive token in Ocamllex specification? I already tried to make case in-sensitive token in this way:

let token = parser
    ...
   | ['C''c']['A''a']['S''s']['E''e'] { CASE }
    ...

but I'm searching for something else, if exists.

Answer 1

Use an ordinary token lexer that accepts both lower- and upper-case, and look up keywords in a table, ignoring case:

{
type token = Case | Test | Ident of string

let keyword_tbl = Hashtbl.create 64

let _ = List.iter (fun (name, keyword) ->
    Hashtbl.add keyword_tbl name keyword) [
    "case", Case;
    "test", Test;
  ]
}

let ident_char = ['a'-'z' 'A'-'Z' '_']

rule next_token = parse
  | ident_char+ as s {
      let canon = String.lowercase s in
      try Hashtbl.find keyword_tbl canon
      with Not_found ->
        (* `Ident canon` if you want case-insensitive vars as well
         * as keywords *)
        Ident s
    }