From f8be3f5f2937b053b9cb75ada7937a6c1b20f019 Mon Sep 17 00:00:00 2001
From: François Pottier <francois.pottier@inria.fr>
Date: Fri, 23 Oct 2015 13:34:43 +0200
Subject: Install the new system for reporting syntax errors. This requires the
 development version of Menhir, to be released soon. In summary:

handcrafted.messages is new.
  It contains a mapping of erroneous sentences to error messages,
  together with a lot of comments.

Makefile.extr is new.
  It contains a rule to generate cparser/pre_parser_messages.ml
  based on this mapping.

cparser/ErrorReports.{ml,mli} are new.
  They construct syntax error messages, based on the compiled mapping.

cparser/Lexer.mll is modified.
  The last two tokens that have been read are stored in a buffer.
  ErrorReports is called to construct a syntax error message.

cparser/GNUmakefile is new.
  It offers several commands for working on the pre-parser.

cparser/deLexer.ml is new.
  It is a script (it is not linked into CompCert).
  It translates the symbolic name of a token to an example of this
  token in concrete C syntax.
  It is used by [make -C cparser concrete] to produce the .c files
  in tests/generated/.

cparser/tests/generated/Makefile is new.
  It runs ccomp, clang and gcc on each of the generated C files,
  so as to allow a comparison of the error messages.
---
 cparser/deLexer.ml | 120 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 120 insertions(+)
 create mode 100644 cparser/deLexer.ml

(limited to 'cparser/deLexer.ml')

diff --git a/cparser/deLexer.ml b/cparser/deLexer.ml
new file mode 100644
index 00000000..7ecfca0c
--- /dev/null
+++ b/cparser/deLexer.ml
@@ -0,0 +1,120 @@
+(* [delex] converts a terminal symbol (represented as a symbolic string) to a
+   concrete string, which the lexer would accept. *)
+
+(* This can be used to convert an error sentence produced by Menhir to C code. *)
+
+(* [delex] should be maintained in sync with the lexer! *)
+
+let delex (symbol : string) : string =
+  match symbol with
+  | "ALIGNAS" -> "_Alignas"
+  | "ALIGNOF" -> "__alignof__" (* use the gcc-compatible form *)
+  | "UNDERSCORE_BOOL" -> "_Bool"
+  | "ASM" -> "__asm"
+  | "ATTRIBUTE" -> "__attribute"
+  | "BUILTIN_VA_ARG" -> "__builtin_va_arg"
+  | "CONST" -> "const"
+  | "INLINE" -> "inline"
+  | "PACKED" -> "__packed__"
+  | "RESTRICT" -> "restrict"
+  | "SIGNED" -> "signed"
+  | "VOLATILE" -> "volatile"
+  | "AUTO" -> "auto"
+  | "BREAK" -> "break"
+  | "CASE" -> "case"
+  | "CHAR" -> "char"
+  | "CONTINUE" -> "continue"
+  | "DEFAULT" -> "default"
+  | "DO" -> "do"
+  | "DOUBLE" -> "double"
+  | "ELSE" -> "else"
+  | "ENUM" -> "enum"
+  | "EXTERN" -> "extern"
+  | "FLOAT" -> "float"
+  | "FOR" -> "for"
+  | "GOTO" -> "goto"
+  | "IF" -> "if"
+  | "INT" -> "int"
+  | "LONG" -> "long"
+  | "REGISTER" -> "register"
+  | "RETURN" -> "return"
+  | "SHORT" -> "short"
+  | "SIZEOF" -> "sizeof"
+  | "STATIC" -> "static"
+  | "STRUCT" -> "struct"
+  | "SWITCH" -> "switch"
+  | "TYPEDEF" -> "typedef"
+  | "UNION" -> "union"
+  | "UNSIGNED" -> "unsigned"
+  | "VOID" -> "void"
+  | "WHILE" -> "while"
+  | "TYPEDEF_NAME" -> "t"          (* this should be a type name *)
+  | "VAR_NAME" -> "x"          (* this should be a variable name *)
+  | "CONSTANT" -> "42"
+  | "STRING_LITERAL" -> "\"\""
+  | "ELLIPSIS" -> "..."
+  | "ADD_ASSIGN" -> "+="
+  | "SUB_ASSIGN" -> "-="
+  | "MUL_ASSIGN" -> "*="
+  | "DIV_ASSIGN" -> "/="
+  | "MOD_ASSIGN" -> "%="
+  | "OR_ASSIGN" -> "|="
+  | "AND_ASSIGN" -> "&="
+  | "XOR_ASSIGN" -> "^="
+  | "LEFT_ASSIGN" -> "<<="
+  | "RIGHT_ASSIGN" -> ">>="
+  | "LEFT" -> "<<"
+  | "RIGHT" -> ">>"
+  | "EQEQ" -> "=="
+  | "NEQ" -> "!="
+  | "LEQ" -> "<="
+  | "GEQ" -> ">="
+  | "EQ" -> "="
+  | "LT" -> "<"
+  | "GT" -> ">"
+  | "INC" -> "++"
+  | "DEC" -> "--"
+  | "PTR" -> "->"
+  | "PLUS" -> "+"
+  | "MINUS" -> "-"
+  | "STAR" -> "*"
+  | "SLASH" -> "/"
+  | "PERCENT" -> "%"
+  | "BANG" -> "!"
+  | "ANDAND" -> "&&"
+  | "BARBAR" -> "||"
+  | "AND" -> "&"
+  | "BAR" -> "|"
+  | "HAT" -> "^"
+  | "QUESTION" -> "?"
+  | "COLON" -> ":"
+  | "TILDE" -> "~"
+  | "LBRACE" -> "{"
+  | "RBRACE" -> "}"
+  | "LBRACK" -> "["
+  | "RBRACK" -> "]"
+  | "LPAREN" -> "("
+  | "RPAREN" -> ")"
+  | "SEMICOLON" -> ";"
+  | "COMMA" -> ","
+  | "DOT" -> "."
+  | "PRAGMA" -> "#pragma \n"
+  | "EOF" -> ""                             (* this should be ok *)
+  | _ -> raise Not_found               (* this should not happen *)
+
+(* De-lexing a sentence. *)
+
+let delex sentence =
+  let symbols = Str.split (Str.regexp " ") sentence in
+  let symbols = List.map delex symbols in
+  List.iter (fun symbol ->
+    Printf.printf "%s " symbol
+  ) symbols
+
+(* This file is meant to be run as a script. We read one line from the standard
+   input channel and delex it. *)
+
+let () =
+  delex (input_line stdin);
+  print_newline()
+
-- 
cgit