On Mon, Oct 06, 2003 at 09:37:40AM +0800, Rafael 'Dido' Sevilla wrote:
> Now I'm stuck again.  I'm revising the lexical analyzer for my compiler
> to enable it to recognize escaped strings, with conventions different
> from OCaml's.  Currently, I'm using this regex:
> 
> '\'' ("\\\\"|"\\'"|[^'\''])* '\''
> 
> in an attempt to recognize strings that begin and end with single
> quotes, but may possibly include sequences like \' that represent
> escaped quotes, and '\\' that represent escaped backslashes.  -- 

As you discovered, you cannot recognize strings with a single regular
expression. You need a sub-lexer:

{
let get         = Lexing.lexeme
let getchar     = Lexing.lexeme_char
}

rule token = parse (* main lexer *)
    eof ->
  | ...
  | "'" -> string lexbuf (Buffer.create 80) (* use sub-lexer *)


and string = parse (* lexer for strings *)
    eof     -> { fun buf -> error "EOF in string" } 
  | '\\' _  -> { fun buf -> let c = getchar lexbuf 1 in
                            let k = match c with
                            | 'n'   -> '\n'
                            | 't'   -> '\t'
                            | .... 
                            in
                                ( Buffer.add_char buf k
                                ; string lexbuf buf
                                )
               }                 
  | _       -> { fun buf -> string lexbuf (Buffer.add_string (get lexbuf)
  | "'"     -> { fun buf -> Buffer.contents buf } (* return string *)

-- Christian

--
Christian Lindig         http://www.st.cs.uni-sb.de/~lindig/

-------------------
To unsubscribe, mail caml-list-request@inria.fr Archives: http://caml.inria.fr
Bug reports: http://caml.inria.fr/bin/caml-bugs FAQ: http://caml.inria.fr/FAQ/
Beginner's list: http://groups.yahoo.com/group/ocaml_beginners