cpplib: Varargs extension tweak

[Neil Booth <neil at daikokuya dot co dot uk>]

Here's the final version of the patch I'll commit to 3.3.  When 3.2
is out I'll apply something similar there, too.

Bootstrapped x86 Linux, no regressions.

Neil.

	* cppinit.c (struct lang_flags): Rename trigraphs std.
	(set_lang): Update.
	* cpplib.h (struct cpp_options): New member std.
	* cppmacro.c (_cpp_builtin_macro_text): Use std.
	(collect_args): Flag whether to swallow a possible future
	comma pasted with varargs.
	(replace_args): Use this flag.
	* doc/cpp.texi: Update varargs extension documentation.
testsuite:
	* gcc.dg/cpp/vararg3.c, gcc.dg/cpp/vararg4.c: New tests.

Index: cppinit.c
===================================================================
RCS file: /cvs/gcc/gcc/gcc/cppinit.c,v
retrieving revision 1.248
diff -u -p -r1.248 cppinit.c
--- cppinit.c	2 Aug 2002 04:18:16 -0000	1.248
+++ cppinit.c	6 Aug 2002 17:43:07 -0000
@@ -384,7 +384,7 @@ struct lang_flags
   char c99;
   char cplusplus;
   char extended_numbers;
-  char trigraphs;
+  char std;
   char dollars_in_ident;
   char cplusplus_comments;
   char digraphs;
@@ -392,7 +392,7 @@ struct lang_flags
 
 /* ??? Enable $ in identifiers in assembly? */
 static const struct lang_flags lang_defaults[] =
-{ /*              c99 c++ xnum trig dollar c++comm digr  */
+{ /*              c99 c++ xnum std dollar c++comm digr  */
   /* GNUC89 */  { 0,  0,  1,   0,   1,     1,      1     },
   /* GNUC99 */  { 1,  0,  1,   0,   1,     1,      1     },
   /* STDC89 */  { 0,  0,  0,   1,   0,     0,      0     },
@@ -416,7 +416,8 @@ set_lang (pfile, lang)
   CPP_OPTION (pfile, c99)		 = l->c99;
   CPP_OPTION (pfile, cplusplus)		 = l->cplusplus;
   CPP_OPTION (pfile, extended_numbers)	 = l->extended_numbers;
-  CPP_OPTION (pfile, trigraphs)		 = l->trigraphs;
+  CPP_OPTION (pfile, std)		 = l->std;
+  CPP_OPTION (pfile, trigraphs)		 = l->std;
   CPP_OPTION (pfile, dollars_in_ident)	 = l->dollars_in_ident;
   CPP_OPTION (pfile, cplusplus_comments) = l->cplusplus_comments;
   CPP_OPTION (pfile, digraphs)		 = l->digraphs;
Index: cpplib.h
===================================================================
RCS file: /cvs/gcc/gcc/gcc/cpplib.h,v
retrieving revision 1.227
diff -u -p -r1.227 cpplib.h
--- cpplib.h	23 Jul 2002 22:57:44 -0000	1.227
+++ cpplib.h	6 Aug 2002 17:43:07 -0000
@@ -367,6 +367,9 @@ struct cpp_options
   /* Nonzero for the 1999 C Standard, including corrigenda and amendments.  */
   unsigned char c99;
 
+  /* Nonzero if we are conforming to a specific C or C++ standard.  */
+  unsigned char std;
+
   /* Nonzero means give all the error messages the ANSI standard requires.  */
   unsigned char pedantic;
 
Index: cppmacro.c
===================================================================
RCS file: /cvs/gcc/gcc/gcc/cppmacro.c,v
retrieving revision 1.120
diff -u -p -r1.120 cppmacro.c
--- cppmacro.c	2 Aug 2002 04:18:16 -0000	1.120
+++ cppmacro.c	6 Aug 2002 17:43:07 -0000
@@ -191,8 +191,7 @@ _cpp_builtin_macro_text (pfile, node)
 	enum c_lang lang = CPP_OPTION (pfile, lang);
 	if (CPP_IN_SYSTEM_HEADER (pfile)
 	    && CPP_OPTION (pfile, stdc_0_in_system_headers)
-	    && !(lang == CLK_STDC89 || lang == CLK_STDC94
-		 || lang == CLK_STDC99))  /* || lang == CLK_CXX98 ? */
+	    && !CPP_OPTION (pfile,std))
 	  number = 0;
 	else
 	  number = 1;
@@ -672,7 +671,20 @@ collect_args (pfile, node)
       if (argc == 1 && macro->paramc == 0 && args[0].count == 0)
 	argc = 0;
       if (_cpp_arguments_ok (pfile, macro, node, argc))
-	return base_buff;
+	{
+	  /* GCC has special semantics for , ## b where b is a varargs
+	     parameter: we remove the comma if b was omitted entirely.
+	     If b was merely an empty argument, the comma is retained.
+	     If the macro takes just one (varargs) parameter, then we
+	     retain the comma only if we are standards conforming.
+
+	     If FIRST is NULL replace_args () swallows the comma.  */
+	  if (macro->variadic && (argc < macro->paramc
+				  || (argc == 1 && args[0].count == 0
+				      && !CPP_OPTION (pfile, std))))
+	    args[macro->paramc - 1].first = NULL;
+	  return base_buff;
+	}
     }
 
   /* An error occurred.  */
@@ -861,15 +873,13 @@ replace_args (pfile, node, macro, args)
 	  count = arg->count, from = arg->first;
 	  if (dest != first)
 	    {
-	      /* GCC has special semantics for , ## b where b is a
-		 varargs parameter: the comma disappears if b was
-		 given no actual arguments (not merely if b is an
-		 empty argument); otherwise the paste flag is removed.  */
 	      if (dest[-1]->type == CPP_COMMA
 		  && macro->variadic
 		  && src->val.arg_no == macro->paramc)
 		{
-		  if (count == 0)
+		  /* Swallow a pasted comma if from == NULL, otherwise
+		     drop the paste flag.  */
+		  if (from == NULL)
 		    dest--;
 		  else
 		    paste_flag = dest - 1;
Index: doc/cpp.texi
===================================================================
RCS file: /cvs/gcc/gcc/gcc/doc/cpp.texi,v
retrieving revision 1.39
diff -u -p -r1.39 cpp.texi
--- doc/cpp.texi	2 Aug 2002 04:18:16 -0000	1.39
+++ doc/cpp.texi	6 Aug 2002 17:43:09 -0000
@@ -1620,7 +1620,7 @@ The @code{eprintf} macro above could be 
 @end example
 
 @noindent
-using this extension.  You cannot use @code{__VA_ARGS__} and this
+using this extension.  You cannot use @code{@w{__VA_ARGS__}} and this
 extension in the same macro.
 
 You can have named arguments as well as variable arguments in a variadic
@@ -1669,6 +1669,15 @@ the token preceding @samp{##} is anythin
 eprintf ("success!\n")
      @expansion{} fprintf(stderr, "success!\n");
 @end example
+
+@noindent
+The above explanation is ambiguous about the case where the only macro
+parameter is a variable arguments parameter, as it is meaningless to
+try to distinguish whether no argument at all is an empty argument or
+a missing argument.  In this case the C99 standard is clear that the
+comma must remain, however the existing GCC extension used to swallow
+the comma.  So CPP retains the comma when conforming to a specific C
+standard, and drops it otherwise.
 
 C99 mandates that the only place the identifier @code{@w{__VA_ARGS__}}
 can appear is in the replacement list of a variadic macro.  It may not
Index: testsuite/gcc.dg/cpp/vararg3.c
===================================================================
RCS file: testsuite/gcc.dg/cpp/vararg3.c
diff -N testsuite/gcc.dg/cpp/vararg3.c
--- /dev/null	1 Jan 1970 00:00:00 -0000
+++ testsuite/gcc.dg/cpp/vararg3.c	6 Aug 2002 17:43:09 -0000
@@ -0,0 +1,17 @@
+/* Copyright (C) 2002 Free Software Foundation, Inc.  */
+
+/* { dg-do preprocess } */
+/* { dg-options "-std=c99" } */
+
+/* Source: Neil Booth, 6 Aug 2002.
+
+   Tests that we DTRT with varargs commas for a single-parameter macro
+   when in standards-conforming mode.  */
+
+#define f(...) , ## __VA_ARGS__
+
+/* The comma from f's expansion should be retained (standards
+   conforming mode only).  Tests that it isn't in non-standards mode
+   include macro8.c and vararg1.c.  */
+#if 2 f() 3		  /* { dg-bogus "missing binary operator" } */
+#endif
Index: testsuite/gcc.dg/cpp/vararg4.c
===================================================================
RCS file: testsuite/gcc.dg/cpp/vararg4.c
diff -N testsuite/gcc.dg/cpp/vararg4.c
--- /dev/null	1 Jan 1970 00:00:00 -0000
+++ testsuite/gcc.dg/cpp/vararg4.c	6 Aug 2002 17:43:09 -0000
@@ -0,0 +1,14 @@
+/* Copyright (C) 2002 Free Software Foundation, Inc.  */
+
+/* { dg-do preprocess } */
+/* { dg-options -std=gnu99 } */
+
+/* Source: Neil Booth, 6 Aug 2002.
+
+   Tests that we DTRT with varargs commas.  */
+
+#define g(a, ...) a , ## __VA_ARGS__
+
+/* The comma from g's expansion should be retained.  */
+#if g (2, ) 3		  /* { dg-bogus "missing binary operator" } */
+#endif