Re: [Caml-list] Common CGI interface

(*
 * Types and functions shared by all connectors
 ***********************************************************************)

module Random :
sig
  val init : ?lock:(unit -> unit) -> ?unlock:(unit -> unit) -> string -> unit
  val init_from_file : ?lock:(unit -> unit) -> ?unlock:(unit -> unit) ->
    ?length:int -> string -> unit
  val byte : unit -> int
  val sessionid : int -> string
    (** [sessionid length] generates a [8 * length] bit ([lenght] hex
        digits) random string which can be used for session IDs,
        random cookies and so on.  The string returned will be very
        random and hard to predict *)
end


class type argument = (* I do not see the point of the cgi prefix *)
object
  (* ... methods to be discussed ... *)

  method storage : [`Memory | `File of string]
    (* No need to define [store] as it is only used here -- saying it
       here makes it easier to figure out what the method is. *)
  method representation : [ `Simple of Netmime.mime_body
                          | `MIME of Netmime.mime_message ]
    (* Same justification as above: having a single point of entry to
       undertand a method is easier. *)
end


type cookie = ... (* I do not see the point of the cgi prefix *)


class type environment =
object
  (* Only changed methods are listed *)

  method cookie : string -> cookie
  method cookies : (string * cookie) list
    (* The first one is convenient.  Moreover, both should use the
       cookie type. *)

  (* Since [set_input_state] and [set_output_state] are not supposed
     to be for the final user, it would be nicer if they did not
     appear here.

     In the same vein, I would not include [input_ch] and
     [input_state] in the *public* interface: they are only useful for
     the [cgi] to initialize itself. *)
end

class type cgi = (* formerly cgi_activation *)
object
  (* I believe short names are better so long they are as readable *)
  method arg : string -> argument
  method arg_val : ?default:string -> string -> string (*was [argument_value]*)
  method arg_true : string -> bool
    (** This method returns false if the named parameter is missing,
        is an empty string, or is the string ["0"]. Otherwise it
        returns true. Thus the intent of this is to return true in the
        Perl sense of the word.  If a parameter appears multiple
        times, then this uses the first definition and ignores the
        others. *)
  method arg_all : string -> argument list (* formerly [multiple_argument] *)
  method args : (string * argument) list

  method url : ?protocol:Netcgi.protocol -> ... -> unit -> string

  method set_header : ?status:status -> ... -> unit -> unit
  method set_redirection_header : string -> unit
  method output : Netchannels.trans_out_obj_channel

  method log : Netchannels.out_obj_channel
    (** A channel whose data is appended to the webserver log. *)

  method finalize  : unit -> unit

  method environment : Netcgi.environment
  method request_method : [`GET | `HEAD | `POST | `DELETE | `PUT of argument]
    (* Single point of doc. *)
end



type config = {
  tmp_directory : string;
  tmp_prefix : string;
  permitted_http_methods : [`GET | `HEAD | `POST | `DELETE | `PUT] list;
                                                             (* Uniformity *)
  permitted_input_content_types : string list;
  input_content_length_limit : int;
  workarounds : [ `MSIE_Content_type_bug | `backslash_bug ] list;
    (* Single point of documentation. *)
}


(*
 * Connectors
 ***********************************************************************)

(* These names better convey the intent I think *)
type output_type = [`Direct | `Transactional]
type arg_storage = [`Memory | `File | `Automatic]

type connection_handler =
    Unix.file_descr -> Unix.file_descr -> (cgi -> unit) -> connection_status
and connection_status = Ok | Shutdown | Restart

module CGI :
sig
  val run :
    ?config:config ->
    ?output_type:output_type ->
    ?arg_storage:(string -> Netmime.mime_header -> arg_storage) ->
    (cgi -> unit) -> unit
end

module FCGI :
sig
  val run :
    ?config:config ->
    ?output_type:output_type ->
    ?arg_storage:(string -> Netmime.mime_header -> arg_storage) ->
    ?sockaddr:Unix.sockaddr ->
    (cgi -> unit) -> unit
    (* [run] must handle the fact that on windows, apache communicates
       with FCGI scripts through named pipes.  *)

  (* Some flexible functions that allow any concurrency model.  Here is
     a possibility. *)
  val socket : ?backlog:int -> ?reuseaddr:bool ->
    ?addr:Unix.inet_addr -> ?port:int -> Unix.file_descr
    (** [socket ?backlog ?reuseaddr ?addr ?port] setup a FCGI socket
	listening to incomming requests.

	@param backlog Length of the backlog queue (connections not yet
	accepted by the AJP server)
	@param reuseaddr Whether to reuse the port
	@param addr defaults to localhost.
	@param port if not present, uses stdin (which is a socket on
 	Unix or -- contrarily to the spec -- a pipe on win$).
    *)

(* Functions analogous to the ones of AJP *)
end

module AJP :
sig
  val arg_parse : ?anon_fun:(string -> unit) -> ?usage_msg:string ->
    (Arg.key * Arg.spec * Arg.doc) list -> (string * string) list
  val props_of_file : string -> (string * string) list

  val run :
    ?props:(string * string) list
    ?config:config ->
    ?output_type:output_type ->
    ?arg_storage:(string -> Netmime.mime_header -> arg_storage) ->
    ?sockaddr:Unix.sockaddr ->
    (cgi -> unit) -> unit


  val socket : ?props:(string * string) list -> ?backlog:int ->
    ?reuseaddr:bool -> ?addr:Unix.inet_addr -> ?port:int -> Unix.file_descr
    (** [socket ?props ?backlog ?reuseaddr ?addr ?port] setup a AJP
	socket listening to incomming requests.

	@param backlog Length of the backlog queue (connections not yet
	accepted by the AJP server)
	@param reuseaddr Whether to reuse the port
	@param addr defaults to localhost.
	@param port if not present, assume the program is launched
	by the web server.
    *)

  val accept_fork  : ?props:(string * string) list ->
    ?onrestart:(unit -> unit) -> ?onshutdown:(unit -> unit) ->
    ?allow_hosts:Unix.inet_addr list ->
    ?fork:((Unix.file_descr -> unit) -> int * Unix.file_descr) ->
    connection_handler -> Unix.inet_addr -> unit

  val accept_threads : ?props:(string * string) list ->
    ?onrestart:(unit -> unit) -> ?onshutdown:(unit -> unit) ->
    ?allow_hosts:Unix.inet_addr list ->
    ?thread:((unit -> unit) -> unit) ->
    connection_handler -> Unix.inet_addr -> unit

  val handle_connection : ?props:(string * string) list
    ?config:config -> ?auth:(int * string) -> connection_handler
end

module Test :
sig
  val simple_arg : string -> string -> argument
  val mime_arg : ?work_around_backslash_bug:bool ->
    string -> Netmime.mime_message -> argument

  val run :
    ?config:config ->
    ?output_type:output_type ->
    ?arg_storage:(string -> Netmime.mime_header -> arg_storage) ->
    ?args:cgi_argument list ->
    ?meth:request_method ->
    (cgi -> unit) -> unit
    (* More flexibility is definitely required here -- along the lines
       of [custom_environment].  I am thinking one could e.g. be
       general enough to allow the output to be set into a frame, and
       another frame being used for control, logging,... -- a live
       debugger if you like! *)
end