libcpp: Named universal character escapes and delimited escape sequence tweaks

On Tue, Aug 30, 2022 at 09:10:37PM +0000, Joseph Myers wrote:
> I'm seeing build failures of glibc for powerpc64, as illustrated by the
> following C code:
>
> #if 0
> \NARG
> #endif
>
> (the actual sysdeps/powerpc/powerpc64/sysdep.h code is inside #ifdef
> __ASSEMBLER__).
>
> This shows some problems with this feature - and with delimited escape
> sequences - as it affects C.  It's fine to accept it as an extension
> inside string and character literals, because \N or \u{...} would be
> invalid in the absence of the feature (i.e. the syntax for such literals
> fails to match, meaning that the rule about undefined behavior for a
> single ' or " as a pp-token applies).  But outside string and character
> literals, the usual lexing rules apply, the \ is a pp-token on its own and
> the code is valid at the preprocessing level, and with expansion of macros
> appearing before or after the \ (e.g. u defined as a macro in the \u{...}
> case) it may be valid code at the language level as well.  I don't know
> what older C++ versions say about this, but for C this means e.g.
>
> #define z(x) 0
> #define a z(
> int x = a\NARG);
>
> needs to be accepted as expanding to "int x = 0;", not interpreted as
> using the \N feature in an identifier and produce an error.

The following patch changes this, so that:
1) outside of string/character literals, \N without following { is never
   treated as an error nor warning, it is silently treated as \ separate
   token followed by whatever is after it
2) \u{123} and \N{LATIN SMALL LETTER A WITH ACUTE} are not handled as
   extension at all outside of string/character literals in the strict
   standard modes (-std=c*) except for -std=c++{23,2b}, only in the
   -std=gnu* modes, because it changes behavior on valid sources, e.g.
   #define z(x) 0
   #define a z(
   int x = a\u{123});
   int y = a\N{LATIN SMALL LETTER A WITH ACUTE});
3) introduces -Wunicode warning (on by default) and warns for cases
   of what looks like invalid delimited escape sequence or named
   universal character escape outside of string/character literals
   and is treated as separate tokens

2022-09-07  Jakub Jelinek  <jakub@redhat.com>

libcpp/
	* include/cpplib.h (struct cpp_options): Add cpp_warn_unicode member.
	(enum cpp_warning_reason): Add CPP_W_UNICODE.
	* init.cc (cpp_create_reader): Initialize cpp_warn_unicode.
	* charset.cc (_cpp_valid_ucn): In possible identifier contexts, don't
	handle \u{ or \N{ specially in -std=c* modes except -std=c++2{3,b}.
	In possible identifier contexts, don't emit an error and punt
	if \N isn't followed by {, or if \N{} surrounds some lower case
	letters or _.  In possible identifier contexts when not C++23, don't
	emit an error but warning about unknown character names and treat as
	separate tokens.  When treating as separate tokens \u{ or \N{, emit
	warnings.
gcc/
	* doc/invoke.texi (-Wno-unicode): Document.
gcc/c-family/
	* c.opt (Winvalid-utf8): Use ObjC instead of objC.  Remove
	" in comments" from description.
	(Wunicode): New option.
gcc/testsuite/
	* c-c++-common/cpp/delimited-escape-seq-4.c: New test.
	* c-c++-common/cpp/delimited-escape-seq-5.c: New test.
	* c-c++-common/cpp/delimited-escape-seq-6.c: New test.
	* c-c++-common/cpp/delimited-escape-seq-7.c: New test.
	* c-c++-common/cpp/named-universal-char-escape-5.c: New test.
	* c-c++-common/cpp/named-universal-char-escape-6.c: New test.
	* c-c++-common/cpp/named-universal-char-escape-7.c: New test.
	* g++.dg/cpp23/named-universal-char-escape1.C: New test.
	* g++.dg/cpp23/named-universal-char-escape2.C: New test.

3 files changed, 78 insertions, 16 deletions

diff --git a/libcpp/charset.cc b/libcpp/charset.cc
index c9656db..6834969 100644
--- a/libcpp/charset.cc
+++ b/libcpp/charset.cc
@@ -1448,7 +1448,11 @@ _cpp_valid_ucn (cpp_reader *pfile, const uchar **pstr,
   if (str[-1] == 'u')
     {
       length = 4;
-      if (str < limit && *str == '{')
+      if (str < limit
+	  && *str == '{'
+	  && (!identifier_pos
+	      || CPP_OPTION (pfile, delimited_escape_seqs)
+	      || !CPP_OPTION (pfile, std)))
 	{
 	  str++;
 	  /* Magic value to indicate no digits seen.  */
@@ -1462,8 +1466,22 @@ _cpp_valid_ucn (cpp_reader *pfile, const uchar **pstr,
   else if (str[-1] == 'N')
     {
       length = 4;
+      if (identifier_pos
+	  && !CPP_OPTION (pfile, delimited_escape_seqs)
+	  && CPP_OPTION (pfile, std))
+	{
+	  *cp = 0;
+	  return false;
+	}
       if (str == limit || *str != '{')
-	cpp_error (pfile, CPP_DL_ERROR, "'\\N' not followed by '{'");
+	{
+	  if (identifier_pos)
+	    {
+	      *cp = 0;
+	      return false;
+	    }
+	  cpp_error (pfile, CPP_DL_ERROR, "'\\N' not followed by '{'");
+	}
       else
 	{
 	  str++;
@@ -1489,15 +1507,19 @@ _cpp_valid_ucn (cpp_reader *pfile, const uchar **pstr,
 
 	  if (str < limit && *str == '}')
 	    {
-	      if (name == str && identifier_pos)
+	      if (identifier_pos && name == str)
 		{
+		  cpp_warning (pfile, CPP_W_UNICODE,
+			       "empty named universal character escape "
+			       "sequence; treating it as separate tokens");
 		  *cp = 0;
 		  return false;
 		}
 	      if (name == str)
 		cpp_error (pfile, CPP_DL_ERROR,
 			   "empty named universal character escape sequence");
-	      else if (!CPP_OPTION (pfile, delimited_escape_seqs)
+	      else if ((!identifier_pos || strict)
+		       && !CPP_OPTION (pfile, delimited_escape_seqs)
 		       && CPP_OPTION (pfile, cpp_pedantic))
 		cpp_error (pfile, CPP_DL_PEDWARN,
 			   "named universal character escapes are only valid "
@@ -1515,27 +1537,51 @@ _cpp_valid_ucn (cpp_reader *pfile, const uchar **pstr,
 					   uname2c_tree, NULL);
 		  if (result == (cppchar_t) -1)
 		    {
-		      cpp_error (pfile, CPP_DL_ERROR,
-				 "\\N{%.*s} is not a valid universal "
-				 "character", (int) (str - name), name);
+		      bool ret = true;
+		      if (identifier_pos
+			  && (!CPP_OPTION (pfile, delimited_escape_seqs)
+			      || !strict))
+			ret = cpp_warning (pfile, CPP_W_UNICODE,
+					   "\\N{%.*s} is not a valid "
+					   "universal character; treating it "
+					   "as separate tokens",
+					   (int) (str - name), name);
+		      else
+			cpp_error (pfile, CPP_DL_ERROR,
+				   "\\N{%.*s} is not a valid universal "
+				   "character", (int) (str - name), name);
 
 		      /* Try to do a loose name lookup according to
 			 Unicode loose matching rule UAX44-LM2.  */
 		      char canon_name[uname2c_max_name_len + 1];
 		      result = _cpp_uname2c_uax44_lm2 ((const char *) name,
 						       str - name, canon_name);
-		      if (result != (cppchar_t) -1)
+		      if (result != (cppchar_t) -1 && ret)
 			cpp_error (pfile, CPP_DL_NOTE,
 				   "did you mean \\N{%s}?", canon_name);
 		      else
-			result = 0x40;
+			result = 0xC0;
+		      if (identifier_pos
+			  && (!CPP_OPTION (pfile, delimited_escape_seqs)
+			      || !strict))
+			{
+			  *cp = 0;
+			  return false;
+			}
 		    }
 		}
 	      str++;
 	      extend_char_range (char_range, loc_reader);
 	    }
 	  else if (identifier_pos)
-	    length = 1;
+	    {
+	      cpp_warning (pfile, CPP_W_UNICODE,
+			   "'\\N{' not terminated with '}' after %.*s; "
+			   "treating it as separate tokens",
+			   (int) (str - base), base);
+	      *cp = 0;
+	      return false;
+	    }
 	  else
 	    {
 	      cpp_error (pfile, CPP_DL_ERROR,
@@ -1584,12 +1630,17 @@ _cpp_valid_ucn (cpp_reader *pfile, const uchar **pstr,
       }
     while (--length);
 
-  if (delimited
-      && str < limit
-      && *str == '}'
-      && (length != 32 || !identifier_pos))
+  if (delimited && str < limit && *str == '}')
     {
-      if (length == 32)
+      if (length == 32 && identifier_pos)
+	{
+	  cpp_warning (pfile, CPP_W_UNICODE,
+		       "empty delimited escape sequence; "
+		       "treating it as separate tokens");
+	  *cp = 0;
+	  return false;
+	}
+      else if (length == 32)
 	cpp_error (pfile, CPP_DL_ERROR,
 		   "empty delimited escape sequence");
       else if (!CPP_OPTION (pfile, delimited_escape_seqs)
@@ -1607,6 +1658,11 @@ _cpp_valid_ucn (cpp_reader *pfile, const uchar **pstr,
      error message in that case.  */
   if (length && identifier_pos)
     {
+      if (delimited)
+	cpp_warning (pfile, CPP_W_UNICODE,
+		     "'\\u{' not terminated with '}' after %.*s; "
+		     "treating it as separate tokens",
+		     (int) (str - base), base);
       *cp = 0;
       return false;
     }
diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h
index 1a3fb19..c25bcf2 100644
--- a/libcpp/include/cpplib.h
+++ b/libcpp/include/cpplib.h
@@ -565,6 +565,10 @@ struct cpp_options
      2 if it should be a pedwarn.  */
   unsigned char cpp_warn_invalid_utf8;
 
+  /* True if libcpp should warn about invalid forms of delimited or named
+     escape sequences.  */
+  bool cpp_warn_unicode;
+
   /* True if -finput-charset= option has been used explicitly.  */
   bool cpp_input_charset_explicit;
 
@@ -675,7 +679,8 @@ enum cpp_warning_reason {
   CPP_W_CXX20_COMPAT,
   CPP_W_EXPANSION_TO_DEFINED,
   CPP_W_BIDIRECTIONAL,
-  CPP_W_INVALID_UTF8
+  CPP_W_INVALID_UTF8,
+  CPP_W_UNICODE
 };
 
 /* Callback for header lookup for HEADER, which is the name of a
diff --git a/libcpp/init.cc b/libcpp/init.cc
index 3e5601a..6292524 100644
--- a/libcpp/init.cc
+++ b/libcpp/init.cc
@@ -228,6 +228,7 @@ cpp_create_reader (enum c_lang lang, cpp_hash_table *table,
   CPP_OPTION (pfile, warn_date_time) = 0;
   CPP_OPTION (pfile, cpp_warn_bidirectional) = bidirectional_unpaired;
   CPP_OPTION (pfile, cpp_warn_invalid_utf8) = 0;
+  CPP_OPTION (pfile, cpp_warn_unicode) = 1;
   CPP_OPTION (pfile, cpp_input_charset_explicit) = 0;
 
   /* Default CPP arithmetic to something sensible for the host for the