Preserve original spellings of extended identifiers.

This patch makes cpplib track the original spellings of extended
identifiers, as well as the canonical UTF-8 version, in order to
follow standard semantics properly without needing a convoluted and
undocumented canonicalization in translation phase 1 (see bug 9449
comments 39-46 regarding such a canonicalization).

The spelling is tracked in cpp_identifier and cpp_macro_arg without
making cpp_token any larger.  The original spelling is used for checks
of duplicate macro definitions, stringizing (see the C++ tests added;
this case is only an issue for C++ not C because C makes it
implementation-defined whether a \ is inserted before the \ of a UCN
in a string or character constant when stringizing, while C++ does
not), pasting (relevant when the result is then stringized for C++)
and when macro definitions are output as text (e.g. for -d options).

Once a macro has been defined, only the original spelling of the
argument names needs keeping in the argument list.  While it is being
defined, however, both spellings are needed: the original one for
subsequent saving for checks of duplicate macro definitions, and the
canonical one which is the node marked specially to generate macro
argument tokens rather than normal identifier tokens.  The buffer that
is used to save the original values of the identifier tokens is
changed so that it stores both those original values and a pointer to
the canonical hash nodes, so that those canonical nodes can be found
when their values need restoring after the macro definition has been
parsed.

I believe this covers the known standards issues in extended
identifiers support (the remaining unimplemented C99 areas in GCC all
being floating-point-related), except for C++ translation of extended
characters to UCNs in phase 1 (which I have no plans to work on).
There are however probably issues left with handling of extended
identifiers in other places, as listed in
<https://gcc.gnu.org/ml/gcc-patches/2014-11/msg00337.html> (those
issues are generally the sort of thing that could be addressed as bugs
outside development stage 1).  (The bulk of the potential issues Zack
was concerned about in 2003-5, that resulted in extended identifiers
being disabled in the absence of -fextended-identifiers, were
effectively eliminated by the audit and fixes I did in 2009, however;
that todo list reflects what was left over after that audit.)

Bootstrapped with no regressions on x86_64-unknown-linux-gnu.

libcpp:
	* include/cpp-id-data.h (struct cpp_macro): Update comment
	regarding parameters.
	* include/cpplib.h (struct cpp_macro_arg, struct cpp_identifier):
	Add spelling fields.
	(struct cpp_token): Update comment on macro_arg.
	* internal.h (_cpp_save_parameter): Add extra argument.
	(_cpp_spell_ident_ucns): New declaration.
	* lex.c (lex_identifier): Add SPELLING argument.  Set *SPELLING to
	original spelling of identifier.
	(_cpp_lex_direct): Update calls to lex_identifier.
	(_cpp_spell_ident_ucns): New function, factored out of
	cpp_spell_token.
	(cpp_spell_token): Adjust FORSTRING argument semantics to return
	original spelling of identifiers.  Use _cpp_spell_ident_ucns in
	!FORSTRING case.
	(_cpp_equiv_tokens): Check spellings of identifiers and macro
	arguments are identical.
	* macro.c (macro_arg_saved_data): New structure.
	(paste_tokens): Use original spellings of identifiers from
	cpp_spell_token.
	(_cpp_save_parameter): Add argument SPELLING.  Save both canonical
	node and its value.
	(parse_params): Update calls to _cpp_save_parameter.
	(lex_expansion_token): Save spelling of macro argument tokens.
	(_cpp_create_definition): Extract canonical node from saved data.
	(cpp_macro_definition): Use UCNs in spelling of macro name.  Use
	original spellings of macro argument tokens and identifiers.
	* traditional.c (scan_parameters): Update call to
	_cpp_save_parameter.

gcc:
	* doc/invoke.texi (-std=c99, -std=c11): Don't refer to corner
	cases of extended identifiers.

gcc/testsuite:
	* g++.dg/cpp/ucnid-2.C, g++.dg/cpp/ucnid-3.C,
	gcc.dg/cpp/ucnid-11.c, gcc.dg/cpp/ucnid-12.c,
	gcc.dg/cpp/ucnid-13.c, gcc.dg/cpp/ucnid-14.c,
	gcc.dg/cpp/ucnid-15.c: New tests.


git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@217202 138bc75d-0d04-0410-961f-82ee72b054a4

7 files changed, 132 insertions, 46 deletions

diff --git a/libcpp/ChangeLog b/libcpp/ChangeLog
index fc577f1ac75..c29fe87e219 100644
--- a/libcpp/ChangeLog
+++ b/libcpp/ChangeLog
@@ -1,3 +1,35 @@
+2014-11-06  Joseph Myers  <joseph@codesourcery.com>
+
+	* include/cpp-id-data.h (struct cpp_macro): Update comment
+	regarding parameters.
+	* include/cpplib.h (struct cpp_macro_arg, struct cpp_identifier):
+	Add spelling fields.
+	(struct cpp_token): Update comment on macro_arg.
+	* internal.h (_cpp_save_parameter): Add extra argument.
+	(_cpp_spell_ident_ucns): New declaration.
+	* lex.c (lex_identifier): Add SPELLING argument.  Set *SPELLING to
+	original spelling of identifier.
+	(_cpp_lex_direct): Update calls to lex_identifier.
+	(_cpp_spell_ident_ucns): New function, factored out of
+	cpp_spell_token.
+	(cpp_spell_token): Adjust FORSTRING argument semantics to return
+	original spelling of identifiers.  Use _cpp_spell_ident_ucns in
+	!FORSTRING case.
+	(_cpp_equiv_tokens): Check spellings of identifiers and macro
+	arguments are identical.
+	* macro.c (macro_arg_saved_data): New structure.
+	(paste_tokens): Use original spellings of identifiers from
+	cpp_spell_token.
+	(_cpp_save_parameter): Add argument SPELLING.  Save both canonical
+	node and its value.
+	(parse_params): Update calls to _cpp_save_parameter.
+	(lex_expansion_token): Save spelling of macro argument tokens.
+	(_cpp_create_definition): Extract canonical node from saved data.
+	(cpp_macro_definition): Use UCNs in spelling of macro name.  Use
+	original spellings of macro argument tokens and identifiers.
+	* traditional.c (scan_parameters): Update call to
+	_cpp_save_parameter.
+
 2014-11-05  Joseph Myers  <joseph@codesourcery.com>
 
 	PR preprocessor/9449
diff --git a/libcpp/include/cpp-id-data.h b/libcpp/include/cpp-id-data.h
index d4c00912a37..97a2f670cf5 100644
--- a/libcpp/include/cpp-id-data.h
+++ b/libcpp/include/cpp-id-data.h
@@ -33,7 +33,9 @@ struct GTY(()) answer {
 /* Each macro definition is recorded in a cpp_macro structure.
    Variadic macros cannot occur with traditional cpp.  */
 struct GTY(()) cpp_macro {
-  /* Parameters, if any.  */
+  /* Parameters, if any.  If parameter names use extended identifiers,
+     the original spelling of those identifiers, not the canonical
+     UTF-8 spelling, goes here.  */
   cpp_hashnode ** GTY ((nested_ptr (union tree_node,
 		"%h ? CPP_HASHNODE (GCC_IDENT_TO_HT_IDENT (%h)) : NULL",
 			"%h ? HT_IDENT_TO_GCC_IDENT (HT_NODE (%h)) : NULL"),
diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h
index 06d18d49ca7..7f8e719ef8e 100644
--- a/libcpp/include/cpplib.h
+++ b/libcpp/include/cpplib.h
@@ -208,6 +208,12 @@ enum cpp_token_fld_kind {
 struct GTY(()) cpp_macro_arg {
   /* Argument number.  */
   unsigned int arg_no;
+  /* The original spelling of the macro argument token.  */
+  cpp_hashnode *
+    GTY ((nested_ptr (union tree_node,
+		"%h ? CPP_HASHNODE (GCC_IDENT_TO_HT_IDENT (%h)) : NULL",
+			"%h ? HT_IDENT_TO_GCC_IDENT (HT_NODE (%h)) : NULL")))
+       spelling;
 };
 
 /* An identifier in the cpp_token union.  */
@@ -218,6 +224,12 @@ struct GTY(()) cpp_identifier {
 		"%h ? CPP_HASHNODE (GCC_IDENT_TO_HT_IDENT (%h)) : NULL",
 			"%h ? HT_IDENT_TO_GCC_IDENT (HT_NODE (%h)) : NULL")))
        node;
+  /* The original spelling of the identifier.  */
+  cpp_hashnode *
+    GTY ((nested_ptr (union tree_node,
+		"%h ? CPP_HASHNODE (GCC_IDENT_TO_HT_IDENT (%h)) : NULL",
+			"%h ? HT_IDENT_TO_GCC_IDENT (HT_NODE (%h)) : NULL")))
+       spelling;
 };
 
 /* A preprocessing token.  This has been carefully packed and should
@@ -238,7 +250,7 @@ struct GTY(()) cpp_token {
     /* A string, or number.  */
     struct cpp_string GTY ((tag ("CPP_TOKEN_FLD_STR"))) str;
 
-    /* Argument no. for a CPP_MACRO_ARG.  */
+    /* Argument no. (and original spelling) for a CPP_MACRO_ARG.  */
     struct cpp_macro_arg GTY ((tag ("CPP_TOKEN_FLD_ARG_NO"))) macro_arg;
 
     /* Original token no. for a CPP_PASTE (from a sequence of
diff --git a/libcpp/internal.h b/libcpp/internal.h
index 602a5035a11..427f4c6def6 100644
--- a/libcpp/internal.h
+++ b/libcpp/internal.h
@@ -616,7 +616,8 @@ extern bool _cpp_create_definition (cpp_reader *, cpp_hashnode *);
 extern void _cpp_pop_context (cpp_reader *);
 extern void _cpp_push_text_context (cpp_reader *, cpp_hashnode *,
 				    const unsigned char *, size_t);
-extern bool _cpp_save_parameter (cpp_reader *, cpp_macro *, cpp_hashnode *);
+extern bool _cpp_save_parameter (cpp_reader *, cpp_macro *, cpp_hashnode *,
+				 cpp_hashnode *);
 extern bool _cpp_arguments_ok (cpp_reader *, cpp_macro *, const cpp_hashnode *,
 			       unsigned int);
 extern const unsigned char *_cpp_builtin_macro_text (cpp_reader *,
@@ -665,6 +666,7 @@ extern bool _cpp_skip_block_comment (cpp_reader *);
 extern cpp_token *_cpp_temp_token (cpp_reader *);
 extern const cpp_token *_cpp_lex_token (cpp_reader *);
 extern cpp_token *_cpp_lex_direct (cpp_reader *);
+extern unsigned char *_cpp_spell_ident_ucns (unsigned char *, cpp_hashnode *);
 extern int _cpp_equiv_tokens (const cpp_token *, const cpp_token *);
 extern void _cpp_init_tokenrun (tokenrun *, unsigned int);
 extern cpp_hashnode *_cpp_lex_identifier (cpp_reader *, const char *);
diff --git a/libcpp/lex.c b/libcpp/lex.c
index 45eaca7ab4f..2247386f829 100644
--- a/libcpp/lex.c
+++ b/libcpp/lex.c
@@ -1302,7 +1302,7 @@ _cpp_lex_identifier (cpp_reader *pfile, const char *name)
 /* Lex an identifier starting at BUFFER->CUR - 1.  */
 static cpp_hashnode *
 lex_identifier (cpp_reader *pfile, const uchar *base, bool starts_ucn,
-		struct normalize_state *nst)
+		struct normalize_state *nst, cpp_hashnode **spelling)
 {
   cpp_hashnode *result;
   const uchar *cur;
@@ -1332,6 +1332,7 @@ lex_identifier (cpp_reader *pfile, const uchar *base, bool starts_ucn,
       } while (forms_identifier_p (pfile, false, nst));
       result = _cpp_interpret_identifier (pfile, base,
 					  pfile->buffer->cur - base);
+      *spelling = cpp_lookup (pfile, base, pfile->buffer->cur - base);
     }
   else
     {
@@ -1340,6 +1341,7 @@ lex_identifier (cpp_reader *pfile, const uchar *base, bool starts_ucn,
 
       result = CPP_HASHNODE (ht_lookup_with_hash (pfile->hash_table,
 						  base, len, hash, HT_ALLOC));
+      *spelling = result;
     }
 
   /* Rarely, identifiers require diagnostics when lexed.  */
@@ -2388,7 +2390,8 @@ _cpp_lex_direct (cpp_reader *pfile)
       {
 	struct normalize_state nst = INITIAL_NORMALIZE_STATE;
 	result->val.node.node = lex_identifier (pfile, buffer->cur - 1, false,
-						&nst);
+						&nst,
+						&result->val.node.spelling);
 	warn_about_normalization (pfile, result, &nst);
       }
 
@@ -2666,7 +2669,8 @@ _cpp_lex_direct (cpp_reader *pfile)
 	if (forms_identifier_p (pfile, true, &nst))
 	  {
 	    result->type = CPP_NAME;
-	    result->val.node.node = lex_identifier (pfile, base, true, &nst);
+	    result->val.node.node = lex_identifier (pfile, base, true, &nst,
+						    &result->val.node.spelling);
 	    warn_about_normalization (pfile, result, &nst);
 	    break;
 	  }
@@ -2740,11 +2744,35 @@ cpp_digraph2name (enum cpp_ttype type)
   return digraph_spellings[(int) type - (int) CPP_FIRST_DIGRAPH];
 }
 
+/* Write the spelling of an identifier IDENT, using UCNs, to BUFFER.
+   The buffer must already contain the enough space to hold the
+   token's spelling.  Returns a pointer to the character after the
+   last character written.  */
+unsigned char *
+_cpp_spell_ident_ucns (unsigned char *buffer, cpp_hashnode *ident)
+{
+  size_t i;
+  const unsigned char *name = NODE_NAME (ident);
+	  
+  for (i = 0; i < NODE_LEN (ident); i++)
+    if (name[i] & ~0x7F)
+      {
+	i += utf8_to_ucn (buffer, name + i) - 1;
+	buffer += 10;
+      }
+    else
+      *buffer++ = name[i];
+
+  return buffer;
+}
+
 /* Write the spelling of a token TOKEN to BUFFER.  The buffer must
    already contain the enough space to hold the token's spelling.
    Returns a pointer to the character after the last character written.
    FORSTRING is true if this is to be the spelling after translation
-   phase 1 (this is different for UCNs).
+   phase 1 (with the original spelling of extended identifiers), false
+   if extended identifiers should always be written using UCNs (there is
+   no option for always writing them in the internal UTF-8 form).
    FIXME: Would be nice if we didn't need the PFILE argument.  */
 unsigned char *
 cpp_spell_token (cpp_reader *pfile, const cpp_token *token,
@@ -2773,24 +2801,12 @@ cpp_spell_token (cpp_reader *pfile, const cpp_token *token,
     case SPELL_IDENT:
       if (forstring)
 	{
-	  memcpy (buffer, NODE_NAME (token->val.node.node),
-		  NODE_LEN (token->val.node.node));
-	  buffer += NODE_LEN (token->val.node.node);
+	  memcpy (buffer, NODE_NAME (token->val.node.spelling),
+		  NODE_LEN (token->val.node.spelling));
+	  buffer += NODE_LEN (token->val.node.spelling);
 	}
       else
-	{
-	  size_t i;
-	  const unsigned char * name = NODE_NAME (token->val.node.node);
-	  
-	  for (i = 0; i < NODE_LEN (token->val.node.node); i++)
-	    if (name[i] & ~0x7F)
-	      {
-		i += utf8_to_ucn (buffer, name + i) - 1;
-		buffer += 10;
-	      }
-	    else
-	      *buffer++ = NODE_NAME (token->val.node.node)[i];
-	}
+	buffer = _cpp_spell_ident_ucns (buffer, token->val.node.node);
       break;
 
     case SPELL_LITERAL:
@@ -2904,9 +2920,11 @@ _cpp_equiv_tokens (const cpp_token *a, const cpp_token *b)
 	return (a->type != CPP_PASTE || a->val.token_no == b->val.token_no);
       case SPELL_NONE:
 	return (a->type != CPP_MACRO_ARG
-		|| a->val.macro_arg.arg_no == b->val.macro_arg.arg_no);
+		|| (a->val.macro_arg.arg_no == b->val.macro_arg.arg_no
+		    && a->val.macro_arg.spelling == b->val.macro_arg.spelling));
       case SPELL_IDENT:
-	return a->val.node.node == b->val.node.node;
+	return (a->val.node.node == b->val.node.node
+		&& a->val.node.spelling == b->val.node.spelling);
       case SPELL_LITERAL:
 	return (a->val.str.len == b->val.str.len
 		&& !memcmp (a->val.str.text, b->val.str.text,
diff --git a/libcpp/macro.c b/libcpp/macro.c
index 8fa97705740..678bf2b6253 100644
--- a/libcpp/macro.c
+++ b/libcpp/macro.c
@@ -80,6 +80,15 @@ struct macro_arg_token_iter
 #endif
 };
 
+/* Saved data about an identifier being used as a macro argument
+   name.  */
+struct macro_arg_saved_data {
+  /* The canonical (UTF-8) spelling of this identifier.  */
+  cpp_hashnode *canonical_node;
+  /* The previous value of this identifier.  */
+  union _cpp_hashnode_value value;
+};
+
 /* Macro expansion.  */
 
 static int enter_macro_context (cpp_reader *, cpp_hashnode *,
@@ -590,7 +599,7 @@ paste_tokens (cpp_reader *pfile, source_location location,
 
   len = cpp_token_len (*plhs) + cpp_token_len (rhs) + 1;
   buf = (unsigned char *) alloca (len);
-  end = lhsend = cpp_spell_token (pfile, *plhs, buf, false);
+  end = lhsend = cpp_spell_token (pfile, *plhs, buf, true);
 
   /* Avoid comment headers, since they are still processed in stage 3.
      It is simpler to insert a space here, rather than modifying the
@@ -600,7 +609,7 @@ paste_tokens (cpp_reader *pfile, source_location location,
     *end++ = ' ';
   /* In one obscure case we might see padding here.  */
   if (rhs->type != CPP_PADDING)
-    end = cpp_spell_token (pfile, rhs, end, false);
+    end = cpp_spell_token (pfile, rhs, end, true);
   *end = '\n';
 
   cpp_push_buffer (pfile, buf, end - buf, /* from_stage3 */ true);
@@ -2748,10 +2757,12 @@ _cpp_free_definition (cpp_hashnode *h)
   h->flags &= ~(NODE_BUILTIN | NODE_DISABLED | NODE_USED);
 }
 
-/* Save parameter NODE to the parameter list of macro MACRO.  Returns
-   zero on success, nonzero if the parameter is a duplicate.  */
+/* Save parameter NODE (spelling SPELLING) to the parameter list of
+   macro MACRO.  Returns zero on success, nonzero if the parameter is
+   a duplicate.  */
 bool
-_cpp_save_parameter (cpp_reader *pfile, cpp_macro *macro, cpp_hashnode *node)
+_cpp_save_parameter (cpp_reader *pfile, cpp_macro *macro, cpp_hashnode *node,
+		     cpp_hashnode *spelling)
 {
   unsigned int len;
   /* Constraint 6.10.3.6 - duplicate parameter names.  */
@@ -2766,17 +2777,20 @@ _cpp_save_parameter (cpp_reader *pfile, cpp_macro *macro, cpp_hashnode *node)
       < (macro->paramc + 1) * sizeof (cpp_hashnode *))
     _cpp_extend_buff (pfile, &pfile->a_buff, sizeof (cpp_hashnode *));
 
-  ((cpp_hashnode **) BUFF_FRONT (pfile->a_buff))[macro->paramc++] = node;
+  ((cpp_hashnode **) BUFF_FRONT (pfile->a_buff))[macro->paramc++] = spelling;
   node->flags |= NODE_MACRO_ARG;
-  len = macro->paramc * sizeof (union _cpp_hashnode_value);
+  len = macro->paramc * sizeof (struct macro_arg_saved_data);
   if (len > pfile->macro_buffer_len)
     {
       pfile->macro_buffer = XRESIZEVEC (unsigned char, pfile->macro_buffer,
                                         len);
       pfile->macro_buffer_len = len;
     }
-  ((union _cpp_hashnode_value *) pfile->macro_buffer)[macro->paramc - 1]
-    = node->value;
+  struct macro_arg_saved_data save;
+  save.value = node->value;
+  save.canonical_node = node;
+  ((struct macro_arg_saved_data *) pfile->macro_buffer)[macro->paramc - 1]
+    = save;
   
   node->value.arg_index  = macro->paramc;
   return false;
@@ -2816,7 +2830,8 @@ parse_params (cpp_reader *pfile, cpp_macro *macro)
 	    }
 	  prev_ident = 1;
 
-	  if (_cpp_save_parameter (pfile, macro, token->val.node.node))
+	  if (_cpp_save_parameter (pfile, macro, token->val.node.node,
+				   token->val.node.spelling))
 	    return false;
 	  continue;
 
@@ -2839,6 +2854,7 @@ parse_params (cpp_reader *pfile, cpp_macro *macro)
 	  if (!prev_ident)
 	    {
 	      _cpp_save_parameter (pfile, macro,
+				   pfile->spec_nodes.n__VA_ARGS__,
 				   pfile->spec_nodes.n__VA_ARGS__);
 	      pfile->state.va_args_ok = 1;
 	      if (! CPP_OPTION (pfile, c99)
@@ -2909,8 +2925,10 @@ lex_expansion_token (cpp_reader *pfile, cpp_macro *macro)
   if (token->type == CPP_NAME
       && (token->val.node.node->flags & NODE_MACRO_ARG) != 0)
     {
+      cpp_hashnode *spelling = token->val.node.spelling;
       token->type = CPP_MACRO_ARG;
       token->val.macro_arg.arg_no = token->val.node.node->value.arg_index;
+      token->val.macro_arg.spelling = spelling;
     }
   else if (CPP_WTRADITIONAL (pfile) && macro->paramc > 0
 	   && (token->type == CPP_STRING || token->type == CPP_CHAR))
@@ -3162,9 +3180,11 @@ _cpp_create_definition (cpp_reader *pfile, cpp_hashnode *node)
   /* Clear the fast argument lookup indices.  */
   for (i = macro->paramc; i-- > 0; )
     {
-      struct cpp_hashnode *node = macro->params[i];
+      struct macro_arg_saved_data *save =
+	&((struct macro_arg_saved_data *) pfile->macro_buffer)[i];
+      struct cpp_hashnode *node = save->canonical_node;
       node->flags &= ~ NODE_MACRO_ARG;
-      node->value = ((union _cpp_hashnode_value *) pfile->macro_buffer)[i];
+      node->value = save->value;
     }
 
   if (!ok)
@@ -3285,7 +3305,7 @@ cpp_macro_definition (cpp_reader *pfile, cpp_hashnode *node)
 
   macro = node->value.macro;
   /* Calculate length.  */
-  len = NODE_LEN (node) + 2;			/* ' ' and NUL.  */
+  len = NODE_LEN (node) * 10 + 2;		/* ' ' and NUL.  */
   if (macro->fun_like)
     {
       len += 4;		/* "()" plus possible final ".." of named
@@ -3305,7 +3325,7 @@ cpp_macro_definition (cpp_reader *pfile, cpp_hashnode *node)
 	  cpp_token *token = &macro->exp.tokens[i];
 
 	  if (token->type == CPP_MACRO_ARG)
-	    len += NODE_LEN (macro->params[token->val.macro_arg.arg_no - 1]);
+	    len += NODE_LEN (token->val.macro_arg.spelling);
 	  else
 	    len += cpp_token_len (token);
 
@@ -3327,8 +3347,7 @@ cpp_macro_definition (cpp_reader *pfile, cpp_hashnode *node)
 
   /* Fill in the buffer.  Start with the macro name.  */
   buffer = pfile->macro_buffer;
-  memcpy (buffer, NODE_NAME (node), NODE_LEN (node));
-  buffer += NODE_LEN (node);
+  buffer = _cpp_spell_ident_ucns (buffer, node);
 
   /* Parameter names.  */
   if (macro->fun_like)
@@ -3377,12 +3396,12 @@ cpp_macro_definition (cpp_reader *pfile, cpp_hashnode *node)
 	  if (token->type == CPP_MACRO_ARG)
 	    {
 	      memcpy (buffer,
-		      NODE_NAME (macro->params[token->val.macro_arg.arg_no - 1]),
-		      NODE_LEN (macro->params[token->val.macro_arg.arg_no - 1]));
-	      buffer += NODE_LEN (macro->params[token->val.macro_arg.arg_no - 1]);
+		      NODE_NAME (token->val.macro_arg.spelling),
+		      NODE_LEN (token->val.macro_arg.spelling));
+	      buffer += NODE_LEN (token->val.macro_arg.spelling);
 	    }
 	  else
-	    buffer = cpp_spell_token (pfile, token, buffer, false);
+	    buffer = cpp_spell_token (pfile, token, buffer, true);
 
 	  if (token->flags & PASTE_LEFT)
 	    {
diff --git a/libcpp/traditional.c b/libcpp/traditional.c
index dfb53787a04..3d40c2f2122 100644
--- a/libcpp/traditional.c
+++ b/libcpp/traditional.c
@@ -959,8 +959,9 @@ scan_parameters (cpp_reader *pfile, cpp_macro *macro)
 
       if (is_idstart (*cur))
 	{
+	  struct cpp_hashnode *id = lex_identifier (pfile, cur);
 	  ok = false;
-	  if (_cpp_save_parameter (pfile, macro, lex_identifier (pfile, cur)))
+	  if (_cpp_save_parameter (pfile, macro, id, id))
 	    break;
 	  cur = skip_whitespace (pfile, CUR (pfile->context),
 				 true /* skip_comments */);