Add new option, -Wliteral-suffix.

This option, which is enabled by default, causes the preprocessor to warn
when a string or character literal is followed by a ud-suffix which does
not begin with an underscore.  According to [lex.ext]p10, this is
ill-formed.

Also modifies the preprocessor to treat such ill-formed suffixes as separate
preprocessing tokens.  This is consistent with the Clang front end (see
http://llvm.org/viewvc/llvm-project?view=rev&revision=152287), and enables
backwards compatibility with code that uses formatting macros from
<inttypes.h>, as in the following code block:

  int main() {
    int64_t i64 = 123;
    printf("My int64: %"PRId64"\n", i64);
  }

Google ref b/6377711.

2012-04-27   Ollie Wild  <aaw@google.com>

	PR c++/52538
	* gcc/c-family/c-common.c: Add CPP_W_LITERAL_SUFFIX mapping.
	* gcc/c-family/c-opts.c (c_common_handle_option): Handle
	OPT_Wliteral_suffix.
	* gcc/c-family/c.opt: Add Wliteral-suffix.
	* gcc/doc/invoke.texi (Wliteral-suffix): Document new option.
	* gcc/testsuite/g++.dg/cpp0x/Wliteral-suffix.c: New test.
	* libcpp/include/cpplib.h (struct cpp_options): Add new field,
	warn_literal_suffix.
	(CPP_W_LITERAL_SUFFIX): New enum.
	* libcpp/init.c (cpp_create_reader): Default initialization of
	warn_literal_suffix.
	* libcpp/lex.c (lex_raw_string): Treat user-defined literals which
	don't begin with '_' as separate tokens and produce a warning.
	(lex_string): Ditto.

git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@186909 138bc75d-0d04-0410-961f-82ee72b054a4

4 files changed, 56 insertions, 7 deletions

diff --git a/libcpp/ChangeLog b/libcpp/ChangeLog
index 08878b27811..f7c330c5143 100644
--- a/libcpp/ChangeLog
+++ b/libcpp/ChangeLog
@@ -1,3 +1,14 @@
+2012-04-27   Ollie Wild  <aaw@google.com>
+
+	* include/cpplib.h (struct cpp_options): Add new field,
+	warn_literal_suffix.
+	(CPP_W_LITERAL_SUFFIX): New enum.
+	* init.c (cpp_create_reader): Default initialization of
+	warn_literal_suffix.
+	* lex.c (lex_raw_string): Treat user-defined literals which don't
+	begin with '_' as separate tokens and produce a warning.
+	(lex_string): Ditto.
+
 2012-04-26  Manuel López-Ibáñez  <manu@gcc.gnu.org>
 
 	* line-map.c (linemap_resolve_location): Synchronize comments with
diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h
index bf59d016231..9dbc477b61e 100644
--- a/libcpp/include/cpplib.h
+++ b/libcpp/include/cpplib.h
@@ -427,6 +427,10 @@ struct cpp_options
   /* Nonzero for C++ 2011 Standard user-defnied literals.  */
   unsigned char user_literals;
 
+  /* Nonzero means warn when a string or character literal is followed by a
+     ud-suffix which does not beging with an underscore.  */
+  unsigned char warn_literal_suffix;
+
   /* Holds the name of the target (execution) character set.  */
   const char *narrow_charset;
 
@@ -906,7 +910,8 @@ enum {
   CPP_W_CXX_OPERATOR_NAMES,
   CPP_W_NORMALIZE,
   CPP_W_INVALID_PCH,
-  CPP_W_WARNING_DIRECTIVE
+  CPP_W_WARNING_DIRECTIVE,
+  CPP_W_LITERAL_SUFFIX
 };
 
 /* Output a diagnostic of some kind.  */
diff --git a/libcpp/init.c b/libcpp/init.c
index 5fa82ca9c3e..3262184c9c5 100644
--- a/libcpp/init.c
+++ b/libcpp/init.c
@@ -175,6 +175,7 @@ cpp_create_reader (enum c_lang lang, hash_table *table,
   CPP_OPTION (pfile, warn_variadic_macros) = 1;
   CPP_OPTION (pfile, warn_builtin_macro_redefined) = 1;
   CPP_OPTION (pfile, warn_normalize) = normalized_C;
+  CPP_OPTION (pfile, warn_literal_suffix) = 1;
 
   /* Default CPP arithmetic to something sensible for the host for the
      benefit of dumb users like fix-header.  */
diff --git a/libcpp/lex.c b/libcpp/lex.c
index 9d23002d84b..7e2671ef026 100644
--- a/libcpp/lex.c
+++ b/libcpp/lex.c
@@ -1553,14 +1553,30 @@ lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base,
 
   if (CPP_OPTION (pfile, user_literals))
     {
+      /* According to C++11 [lex.ext]p10, a ud-suffix not starting with an
+	 underscore is ill-formed.  Since this breaks programs using macros
+	 from inttypes.h, we generate a warning and treat the ud-suffix as a
+	 separate preprocessing token.  This approach is under discussion by
+	 the standards committee, and has been adopted as a conforming
+	 extension by other front ends such as clang. */
+      if (ISALPHA (*cur))
+	{
+	  // Raise a warning, but do not consume subsequent tokens.
+	  if (CPP_OPTION (pfile, warn_literal_suffix))
+	    cpp_warning_with_line (pfile, CPP_W_LITERAL_SUFFIX,
+				   token->src_loc, 0,
+				   "invalid suffix on literal; C++11 requires "
+				   "a space between literal and identifier");
+	}
       /* Grab user defined literal suffix.  */
-      if (ISIDST (*cur))
+      else if (*cur == '_')
 	{
 	  type = cpp_userdef_string_add_type (type);
 	  ++cur;
+
+	  while (ISIDNUM (*cur))
+	    ++cur;
 	}
-      while (ISIDNUM (*cur))
-	++cur;
     }
 
   pfile->buffer->cur = cur;
@@ -1668,15 +1684,31 @@ lex_string (cpp_reader *pfile, cpp_token *token, const uchar *base)
 
   if (CPP_OPTION (pfile, user_literals))
     {
+      /* According to C++11 [lex.ext]p10, a ud-suffix not starting with an
+	 underscore is ill-formed.  Since this breaks programs using macros
+	 from inttypes.h, we generate a warning and treat the ud-suffix as a
+	 separate preprocessing token.  This approach is under discussion by
+	 the standards committee, and has been adopted as a conforming
+	 extension by other front ends such as clang. */
+      if (ISALPHA (*cur))
+	{
+	  // Raise a warning, but do not consume subsequent tokens.
+	  if (CPP_OPTION (pfile, warn_literal_suffix))
+	    cpp_warning_with_line (pfile, CPP_W_LITERAL_SUFFIX,
+				   token->src_loc, 0,
+				   "invalid suffix on literal; C++11 requires "
+				   "a space between literal and identifier");
+	}
       /* Grab user defined literal suffix.  */
-      if (ISIDST (*cur))
+      else if (*cur == '_')
 	{
 	  type = cpp_userdef_char_add_type (type);
 	  type = cpp_userdef_string_add_type (type);
           ++cur;
+
+	  while (ISIDNUM (*cur))
+	    ++cur;
 	}
-      while (ISIDNUM (*cur))
-	++cur;
     }
 
   pfile->buffer->cur = cur;