[Linux-kernel-mentees] [PATCH v5 1/3] parsing_c: Align C AST and Cocci AST for pointer

[Jaskaran Singh]

For a pointer, the C parser constructed an AST dissimilar from that
of the Cocci AST. This caused failures in matching with certain
pointer types. For example, for the following case:

char *1 const *2 id;

The C AST constructed would be:
const Pointer1 -> Pointer2 -> char

The Cocci AST constructed would be:
Pointer2 -> const Pointer1 -> char

Change the pointer rule in the C parser so that an AST similar to the
Cocci AST is constructed.

Make necessary changes in the C pretty printer so that the pointer type
is printed correctly.

Signed-off-by: Jaskaran Singh <jaskaransingh7654321 at gmail.com>
---
 parsing_c/parser_c.mly      |  4 ++--
 parsing_c/pretty_print_c.ml | 15 ++++++++++-----
 2 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/parsing_c/parser_c.mly b/parsing_c/parser_c.mly
index 8d7b761e..4c74f15a 100644
--- a/parsing_c/parser_c.mly
+++ b/parsing_c/parser_c.mly
@@ -1333,14 +1333,14 @@ pointer:
  | tmul                   { (Ast_c.noattr,fun x -> mk_ty (Pointer x) [$1]) }
  | tmul pointer
      { let (attr,ptr) = $2 in
-       (attr,fun x -> mk_ty (Pointer (ptr x)) [$1]) }
+       (attr,fun x -> ptr (mk_ty (Pointer x) [$1])) }
  | tmul type_qualif_list
      { let (attr,tq) = $2 in
        (attr,fun x -> (tq.qualifD, mk_tybis (Pointer x) [$1]))}
  | tmul type_qualif_list pointer
      { let (attr1,tq) = $2 in
        let (attr2,ptr) = $3 in
-       (attr1 at attr2,fun x -> (tq.qualifD, mk_tybis (Pointer (ptr x)) [$1])) }
+       (attr1 at attr2,fun x -> ptr (tq.qualifD, mk_tybis (Pointer x) [$1])) }
 
 tmul:
    TMul { $1 }
diff --git a/parsing_c/pretty_print_c.ml b/parsing_c/pretty_print_c.ml
index a2e35588..f4821d5c 100644
--- a/parsing_c/pretty_print_c.ml
+++ b/parsing_c/pretty_print_c.ml
@@ -804,11 +804,14 @@ and pp_string_format (e,ii) =
              (FunctionType (return=void, params=int i) *)
           (*WRONG I THINK, use left & right function *)
           (* bug: pp_type_with_ident_rest None t;      print_ident ident *)
+          pp_type_left t;
           pr_elem i;
-          iiqu +> List.iter pr_elem; (* le const est forcement apres le '*' *)
+          iiqu +>
+          List.iter (* le const est forcement apres le '*' *)
+            (function x -> pr_space(); pr_elem x);
           if iiqu <> [] || get_comments_after i <> []
           then pr_space();
-          pp_type_with_ident_rest ident t attrs Ast_c.noattr;
+          print_ident ident
 
       (* ugly special case ... todo? maybe sufficient in practice *)
       | (ParenType ttop, [i1;i2]) ->
@@ -885,11 +888,13 @@ and pp_string_format (e,ii) =
       match ty, iity with
 	(NoType,_) -> failwith "pp_type_left: unexpected NoType"
       | (Pointer t, [i]) ->
+          pp_type_left t;
           pr_elem i;
-          iiqu +> List.iter pr_elem; (* le const est forcement apres le '*' *)
+          iiqu +>
+          List.iter (* le const est forcement apres le '*' *)
+            (function x -> pr_space(); pr_elem x);
           if iiqu <> [] || get_comments_after i <> []
-          then pr_space();
-          pp_type_left t
+          then pr_space()
 
       | (Array (eopt, t), [i1;i2]) -> pp_type_left t
       | (FunctionType (returnt, paramst), [i1;i2]) -> pp_type_left returnt
-- 
2.21.1