Use latest pfff and fix no_file_info error (#1988)

* Use latest pfff not generating NO_FILE_INFO_YET when parsing invalid C code

Fixes #1925

test plan:
$ /home/pad/semgrep/_build/default/cli/Main.exe -dump_ast foo.c
foo.c:3:0: Lexical error: unrecognised symbol, in token rule:#
Raised at file "parsing/Parse_code.ml", line 144, characters 24-27
Called from file "parsing/Parse_code.ml", line 236, characters 18-48

no more NO_FILE_INFO_YET error (which causes the python wrapper
to crash).

Also:
$ semgrep -l c -e 'FOO' tests/OTHER/parsing_errors/foo.c
ran 1 rules on 1 files: 0 findings
1 files could not be analyzed; run with --verbose for details or run with --strict to exit non-zero if any file cannot be analyzed

* Use latest pfff not generating NO_FILE_INFO_YET when parsing invalid C code

Fixes #1925

test plan:
$ /home/pad/semgrep/_build/default/cli/Main.exe -dump_ast foo.c
foo.c:3:0: Lexical error: unrecognised symbol, in token rule:#
Raised at file "parsing/Parse_code.ml", line 144, characters 24-27
Called from file "parsing/Parse_code.ml", line 236, characters 18-48

no more NO_FILE_INFO_YET error (which causes the python wrapper
to crash).

Also:
$ semgrep -l c -e 'FOO' tests/OTHER/parsing_errors/foo.c
ran 1 rules on 1 files: 0 findings
1 files could not be analyzed; run with --verbose for details or run with --strict to exit non-zero if any file cannot be analyzed

semgrep-core/cli/Main.ml

@@ -850,13 +850,15 @@ let dump_pattern (file: Common.filename) =
 let dump_ast file =
   match Lang.langs_of_filename file with
   | lang::_ ->
+   E.try_with_print_exn_and_reraise file (fun () ->
     let (x, errs) =
       Parse_code.parse_and_resolve_name_use_pfff_or_treesitter lang file in
     if errs <> []
     then failwith (spf "fail to fully parse %s" file);
     let v = Meta_AST.vof_any (AST_generic.Pr x) in
     let s = dump_v_to_format v in
     pr s
+   )
   | [] -> failwith (spf "unsupported language for %s" file)
 (*e: function [[Main_semgrep_core.dump_ast]] *)
 

semgrep-core/parsing/Parse_code.ml

@@ -223,7 +223,7 @@ let just_parse_with_lang lang file =
        * a generic AST (no kotlin_to_generic here)
        *)
       run file [TreeSitter Parse_kotlin_tree_sitter.parse] (fun x -> x)
-      
+
   (* default to the one in pfff for the other languages *)
   | _ ->
       run file [Pfff (Parse_generic.parse_with_lang lang)] (fun x -> x)

semgrep-core/parsing/Parse_kotlin_tree_sitter.ml

@@ -57,7 +57,7 @@ let blank (env : env) () =
 let todo (env : env) _ =
    failwith "not implemented"
 
-let token_todo (env : env) _ = 
+let token_todo (env : env) _ =
     failwith "token Todo"
 
 let escaped_identifier (env : env) (tok : CST.escaped_identifier) =
@@ -226,14 +226,14 @@ let semi (env : env) (tok : CST.semi) =
   token env tok (* pattern [\r\n]+ *)
 
 let prefix_unary_operator (env : env) (x : CST.prefix_unary_operator) =
-  let _ = 
+  let _ =
   (match x with
   | `PLUSPLUS tok -> token env tok (* "++" *)
   | `DASHDASH tok -> token env tok (* "--" *)
   | `DASH tok -> token env tok (* "-" *)
   | `PLUS tok -> token env tok (* "+" *)
   | `BANG tok -> token env tok (* "!" *)
-  ) in 
+  ) in
     raise Todo
 
 let in_operator (env : env) (x : CST.in_operator) =
@@ -464,7 +464,7 @@ and annotation (env : env) (x : CST.annotation) =
 and anon_choice_param_b77c1d8 (env : env) (x : CST.anon_choice_param_b77c1d8) =
   (match x with
   | `Param x -> parameter env x
-  | `Type x -> let _ =  type_ env x in 
+  | `Type x -> let _ =  type_ env x in
         raise Todo
   )
 
@@ -1506,7 +1506,7 @@ and simple_user_type (env : env) ((v1, v2) : CST.simple_user_type) =
 
 and statement (env : env) (x : CST.statement) : AST.stmt =
   (match x with
-  | `Decl x -> let _ = declaration env x in 
+  | `Decl x -> let _ = declaration env x in
       raise Todo
   | `Rep_choice_label_choice_assign (v1, v2) ->
       let v1 =
@@ -1571,7 +1571,7 @@ and string_literal (env : env) (x : CST.string_literal) =
       in
       let v3 = token env v3 (* "\"\"\"" *) in
       todo env (v1, v2, v3)
-  ) in 
+  ) in
     raise Todo
 
 and type_ (env : env) ((v1, v2) : CST.type_) : AST.type_ =
@@ -1625,7 +1625,7 @@ and type_constraints (env : env) ((v1, v2, v3) : CST.type_constraints) =
 and type_modifier (env : env) (x : CST.type_modifier) =
   (match x with
   | `Anno x -> annotation env x
-  | `Susp tok -> let t = token env tok (* "suspend" *) in 
+  | `Susp tok -> let t = token env tok (* "suspend" *) in
       raise Todo
   )
 
@@ -1651,7 +1651,7 @@ and type_parameter (env : env) ((v1, v2, v3) : CST.type_parameter) =
 
 and type_parameter_modifier (env : env) (x : CST.type_parameter_modifier) =
   (match x with
-  | `Reif_modi tok -> let t = token env tok in (* "reified" *) 
+  | `Reif_modi tok -> let t = token env tok in (* "reified" *)
       raise Todo
   | `Vari_modi x -> type_projection_modifier env x
   | `Anno x -> annotation env x
@@ -1719,7 +1719,7 @@ and unary_expression (env : env) (x : CST.unary_expression) =
       let v1 =
         (match v1 with
         | `Anno x -> annotation env x
-        | `Label tok -> let _ = token env tok in (* label *) 
+        | `Label tok -> let _ = token env tok in (* label *)
             raise Todo
         | `Prefix_un_op x -> prefix_unary_operator env x
         )
@@ -1934,4 +1934,4 @@ let source_file (env : env) ((v1, v2, v3, v4, v5) : CST.source_file) : AST.progr
           pr2 "Original backtrace:";
           pr2 s;
           raise exn
-   )
+   )

semgrep-core/tests/OTHER/parsing_errors/foo.c

@@ -0,0 +1,4 @@
+
+
+# this is invalid code
+int x = 1

spacegrep/examples/python-from.doc

@@ -30,7 +30,7 @@
 function GLVertexBuffer(gl, shader, dataComponents
 /* , type */
 ) {
-    var buffer = false, vertAttribute = false, components = dataComponents || 2, preAllocated = false, iterator = 0, 
+    var buffer = false, vertAttribute = false, components = dataComponents || 2, preAllocated = false, iterator = 0,
     // farray = false,
     data;
     // type = type || 'float';