X-Git-Url: http://git.hcoop.net/bpt/coccinelle.git/blobdiff_plain/c491d8eea333ab3273dc415c7d7af192e1d0b682..1b9ae60616d2f065ce16fe26385b684e13b40284:/parsing_cocci/lexer_script.mll diff --git a/parsing_cocci/lexer_script.mll b/parsing_cocci/lexer_script.mll index 5426f9c..aacfa8f 100644 --- 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 @@ -22,32 +24,53 @@ *) +# 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 } (* ---------------------------------------------------------------------- *) (* tokens *) -let myrule = [^'"''@''/''\n''\r''\011''\012']+ +let oct = ['0'-'7'] +let hex = ['0'-'9' 'a'-'f' 'A'-'F'] + +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'" (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 cstring = parse + | "'" { "" } + | (_ as x) { (String.make 1 x) ^ cstring lexbuf }