parsing_cocci/lexer_script.mll

   1 (*
   2  * Copyright 2012, INRIA
   3  * Julia Lawall, Gilles Muller
   4  * Copyright 2010-2011, INRIA, University of Copenhagen
   5  * Julia Lawall, Rene Rydhof Hansen, Gilles Muller, Nicolas Palix
   6  * Copyright 2005-2009, Ecole des Mines de Nantes, University of Copenhagen
   7  * Yoann Padioleau, Julia Lawall, Rene Rydhof Hansen, Henrik Stuart, Gilles Muller, Nicolas Palix
   8  * This file is part of Coccinelle.
   9  *
  10  * Coccinelle is free software: you can redistribute it and/or modify
  11  * it under the terms of the GNU General Public License as published by
  12  * the Free Software Foundation, according to version 2 of the License.
  13  *
  14  * Coccinelle is distributed in the hope that it will be useful,
  15  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  16  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  17  * GNU General Public License for more details.
  18  *
  19  * You should have received a copy of the GNU General Public License
  20  * along with Coccinelle.  If not, see <http://www.gnu.org/licenses/>.
  21  *
  22  * The authors reserve the right to distribute this or future versions of
  23  * Coccinelle under other licenses.
  24  *)
  25
  26
  27 # 0 "./lexer_script.mll"
  28 {
  29 open Parser_cocci_menhir
  30 module D = Data
  31 module Ast = Ast_cocci
  32 exception Lexical of string
  33 let tok = Lexing.lexeme
  34 let file = ref ""
  35 let language = ref ""
  36 let inc_line _ = Lexer_cocci.line := !Lexer_cocci.line + 1
  37 }
  38 (* ---------------------------------------------------------------------- *)
  39 (* tokens *)
  40
  41 let oct = ['0'-'7']
  42 let hex = ['0'-'9' 'a'-'f' 'A'-'F']
  43
  44 let myrule = [^'\'''"''@''/''\n''\r''\011''\012']+
  45
  46 rule token = parse
  47   | myrule { TScriptData (tok lexbuf) }
  48   | ['\n' '\r' '\011' '\012']
  49       { inc_line();
  50         let text = tok lexbuf in
  51         let text =
  52           if !language = "ocaml"
  53           then
  54             Printf.sprintf "%s# %d \"%s\"%s"
  55               text !Lexer_cocci.line !file text
  56           else text in
  57         TScriptData text }
  58   | "@@" { TArobArob }
  59   | "@"  { TArob }
  60   | "/"  { TScriptData (tok lexbuf) }
  61   | "//" [^ '\n']* { token lexbuf } (* skip SmPL comments *)
  62   | '"'  { TScriptData (Printf.sprintf "\"%s\"" (string lexbuf)) }
  63   | "'"  { TScriptData (Printf.sprintf "'%s'" (cstring lexbuf)) }
  64   | eof  { EOF }
  65   | _ { raise (Lexical ("unrecognised symbol, in token rule:"^tok lexbuf)) }
  66
  67 (* These are C strings.  Perhaps they require some adjustment. *)
  68 and string  = parse
  69   | '"'                 { "" }
  70   | (_ as x)            { (String.make 1 x) ^ string lexbuf }
  71
  72 and cstring  = parse
  73   | "'"                 { "" }
  74   | (_ as x)            { (String.make 1 x) ^ cstring lexbuf }