Programming ngram sensor data models in OCaml exercised various language features.

-- String continuation -- breaking long strings across the lines

“he\
   llo”

-- glues it together without the leading spaces.

Using, as a parameter, a function with optional parameters, and using them, requires that the function type is fully known. Example is from cells/genlm.ml:

let dirwalk (f:?mincount:int -> ?date:string -> string -> unit) ?date root =
  let numbers = Str.regexp "^[0-9]+$" in
  let subdirs = Array.to_list (Sys.readdir root) in
  let subdirs = List.filter (fun x -> Str.string_match numbers x 0 && x <> "0") subdirs in
  (* let subdirs = ["9"] in *)
  
  match date with
    | Some date ->
      List.iter (fun x -> f (Filename.concat root x) ~date:date) subdirs
    | None ->
      List.iter (fun x -> f (Filename.concat root x)) subdirs