Version 1.0.0-rc17 has been released. Some changes are:

[bpt/coccinelle.git] / parsing_cocci / lexer_script.mll

diff --git a/parsing_cocci/lexer_script.mll b/parsing_cocci/lexer_script.mll
index d731460..aacfa8f 100644 (file)
--- a/parsing_cocci/lexer_script.mll
+++ b/parsing_cocci/lexer_script.mll
@@ -1,5 +1,7 @@
 (*
- * Copyright 2010, INRIA, University of Copenhagen
+ * Copyright 2012, INRIA
+ * Julia Lawall, Gilles Muller
+ * Copyright 2010-2011, INRIA, University of Copenhagen
  * Julia Lawall, Rene Rydhof Hansen, Gilles Muller, Nicolas Palix
  * Copyright 2005-2009, Ecole des Mines de Nantes, University of Copenhagen
  * Yoann Padioleau, Julia Lawall, Rene Rydhof Hansen, Henrik Stuart, Gilles Muller, Nicolas Palix
@@ -22,12 +24,15 @@
  *)
 
 
+# 0 "./lexer_script.mll"
 {
 open Parser_cocci_menhir
 module D = Data
 module Ast = Ast_cocci
 exception Lexical of string
 let tok = Lexing.lexeme
+let file = ref ""
+let language = ref ""
 let inc_line _ = Lexer_cocci.line := !Lexer_cocci.line + 1
 }
 (* ---------------------------------------------------------------------- *)
@@ -36,28 +41,36 @@ let inc_line _ = Lexer_cocci.line := !Lexer_cocci.line + 1
 let oct = ['0'-'7']
 let hex = ['0'-'9' 'a'-'f' 'A'-'F']
 
-let myrule = [^'\'''"''@''/''\n''\r''\011''\012']+
+let myrule = [^'\'''"''@''/''\n''\r''\011''\012''('')']+
 
 rule token = parse
   | myrule { TScriptData (tok lexbuf) }
-  | ['\n' '\r' '\011' '\012'] { inc_line(); TScriptData (tok lexbuf) }
+  | '(' { TScriptData (tok lexbuf) }
+  | ')' { TScriptData (tok lexbuf) }
+  | ['\n' '\r' '\011' '\012']
+      { inc_line();
+       let text = tok lexbuf in
+       let text =
+         if !language = "ocaml"
+         then
+           Printf.sprintf "%s# %d \"%s\"%s"
+             text !Lexer_cocci.line !file text
+         else text in
+       TScriptData text }
   | "@@" { TArobArob }
   | "@"  { TArob }
   | "/"  { TScriptData (tok lexbuf) }
   | "//" [^ '\n']* { token lexbuf } (* skip SmPL comments *)
   | '"'  { TScriptData (Printf.sprintf "\"%s\"" (string lexbuf)) }
-  | "'"  { TScriptData (Printf.sprintf "'%s'" (char lexbuf)) }
+  | "'"  { TScriptData (Printf.sprintf "'%s'" (cstring lexbuf)) }
   | eof  { EOF }
   | _ { raise (Lexical ("unrecognised symbol, in token rule:"^tok lexbuf)) }
 
 (* These are C strings.  Perhaps they require some adjustment. *)
 and string  = parse
   | '"'                 { "" }
-  | (_ as x)            { Common.string_of_char x ^ string lexbuf }
-  | ("\\" _) as x       { x ^ string lexbuf }
+  | (_ as x)            { (String.make 1 x) ^ string lexbuf }
 
-and char = parse
-  | (_ as x) "'"                                     { String.make 1 x }
-  | (("\\" (oct | oct oct | oct oct oct)) as x  "'") { x }
-  | (("\\x" (hex | hex hex)) as x  "'")       { x }
-  | (("\\" _ ) as x "'") { x }
+and cstring  = parse
+  | "'"                 { "" }
+  | (_ as x)            { (String.make 1 x) ^ cstring lexbuf }