c, libcpp: Partially implement C2Y N3353 paper [PR117028]

The following patch partially implements the N3353 paper.
In particular, it adds support for the delimited escape sequences
(\u{123}, \x{123}, \o{123}) which were added already for C++23,
all I had to do is split the delimited escape sequence guarding from
named universal character escape sequence guards
(\N{LATIN CAPITAL LETTER C WITH CARON}), which C++23 has but C2Y doesn't
and emit different diagnostics for C from C++ for the delimited escape
sequences.
And it adds support for the new style of octal literals, 0o137 or 0O1777.
I have so far added that just for C and not C++, because I have no idea
whether C++ will want to handle it similarly.

What the patch doesn't do is any kind of diagnostics for obsoletion of
\137 or 0137, as discussed in the PR, I think it is way too early for that.
Perhaps some non-default warning later on.

2024-10-17  Jakub Jelinek  <jakub@redhat.com>

	PR c/117028
libcpp/
	* include/cpplib.h (struct cpp_options): Add named_uc_escape_seqs,
	octal_constants and cpp_warn_c23_c2y_compat members.
	(enum cpp_warning_reason): Add CPP_W_C23_C2Y_COMPAT enumerator.
	* init.cc (struct lang_flags): Add named_uc_escape_seqs and
	octal_constants bit-fields.
	(lang_defaults): Add initializers for them into the table.
	(cpp_set_lang): Initialize named_uc_escape_seqs and octal_constants.
	(cpp_create_reader): Initialize cpp_warn_c23_c2y_compat to -1.
	* charset.cc (_cpp_valid_ucn): Test
	CPP_OPTION (pfile, named_uc_escape_seqs) rather than
	CPP_OPTION (pfile, delimited_escape_seqs) in \N{} related tests.
	Change wording of C cpp_pedwarning for \u{} and emit
	-Wc23-c2y-compat warning for it too if needed.  Formatting fixes.
	(convert_hex): Change wording of C cpp_pedwarning for \u{} and emit
	-Wc23-c2y-compat warning for it too if needed.
	(convert_oct): Likewise.
	* expr.cc (cpp_classify_number): Handle C2Y 0o or 0O prefixed
	octal constants.
	(cpp_interpret_integer): Likewise.
gcc/c-family/
	* c.opt (Wc23-c2y-compat): Add CPP and CppReason parameters.
	* c-opts.cc (set_std_c2y): Use CLK_STDC2Y or CLK_GNUC2Y rather
	than CLK_STDC23 and CLK_GNUC23.  Formatting fix.
	* c-lex.cc (interpret_integer): Handle C2Y 0o or 0O prefixed
	and wb/WB/uwb/UWB suffixed octal constants.
gcc/testsuite/
	* gcc.dg/bitint-112.c: New test.
	* gcc.dg/c23-digit-separators-1.c: Add _Static_assert for
	valid binary constant with digit separator.
	* gcc.dg/c23-octal-constants-1.c: New test.
	* gcc.dg/c23-octal-constants-2.c: New test.
	* gcc.dg/c2y-digit-separators-1.c: New test.
	* gcc.dg/c2y-digit-separators-2.c: New test.
	* gcc.dg/c2y-octal-constants-1.c: New test.
	* gcc.dg/c2y-octal-constants-2.c: New test.
	* gcc.dg/c2y-octal-constants-3.c: New test.
	* gcc.dg/cpp/c23-delimited-escape-seq-1.c: New test.
	* gcc.dg/cpp/c23-delimited-escape-seq-2.c: New test.
	* gcc.dg/cpp/c2y-delimited-escape-seq-1.c: New test.
	* gcc.dg/cpp/c2y-delimited-escape-seq-2.c: New test.
	* gcc.dg/cpp/c2y-delimited-escape-seq-3.c: New test.
	* gcc.dg/cpp/c2y-delimited-escape-seq-4.c: New test.
	* gcc.dg/octal-constants-1.c: New test.
	* gcc.dg/octal-constants-2.c: New test.
	* gcc.dg/octal-constants-3.c: New test.
	* gcc.dg/octal-constants-4.c: New test.
	* gcc.dg/system-octal-constants-1.c: New test.
	* gcc.dg/system-octal-constants-1.h: New file.

1 files changed, 35 insertions, 2 deletions

diff --git a/libcpp/expr.cc b/libcpp/expr.cc
index 67d021f..2a57dc79d 100644
--- a/libcpp/expr.cc
+++ b/libcpp/expr.cc
@@ -556,6 +556,7 @@ cpp_classify_number (cpp_reader *pfile, const cpp_token *token,
   enum {NOT_FLOAT = 0, AFTER_POINT, AFTER_EXPON} float_flag;
   bool seen_digit;
   bool seen_digit_sep;
+  bool zero_o_prefix;
 
   if (ud_suffix)
     *ud_suffix = NULL;
@@ -571,6 +572,7 @@ cpp_classify_number (cpp_reader *pfile, const cpp_token *token,
   radix = 10;
   seen_digit = false;
   seen_digit_sep = false;
+  zero_o_prefix = false;
 
   /* First, interpret the radix.  */
   if (*str == '0')
@@ -601,6 +603,17 @@ cpp_classify_number (cpp_reader *pfile, const cpp_token *token,
 	    SYNTAX_ERROR_AT (virtual_location,
 			     "digit separator after base indicator");
 	}
+      else if ((*str == 'o' || *str == 'O') && !CPP_OPTION (pfile, cplusplus))
+	{
+	  if (ISDIGIT (str[1]))
+	    {
+	      zero_o_prefix = true;
+	      str++;
+	    }
+	  else if (DIGIT_SEP (str[1]))
+	    SYNTAX_ERROR_AT (virtual_location,
+			     "digit separator after base indicator");
+	}
     }
 
   /* Now scan for a well-formed integer or float.  */
@@ -694,6 +707,12 @@ cpp_classify_number (cpp_reader *pfile, const cpp_token *token,
 			       "invalid prefix %<0b%> for floating constant");
 	  return CPP_N_INVALID;
 	}
+      if (zero_o_prefix)
+	{
+	  cpp_error_with_line (pfile, CPP_DL_ERROR, virtual_location, 0,
+			       "invalid prefix %<0o%> for floating constant");
+	  return CPP_N_INVALID;
+	}
 
       if (radix == 16 && !seen_digit)
 	SYNTAX_ERROR_AT (virtual_location,
@@ -897,8 +916,7 @@ cpp_classify_number (cpp_reader *pfile, const cpp_token *token,
   if (radix == 2)
     {
       bool warned = false;
-      if (!CPP_OPTION (pfile, binary_constants)
-	  && CPP_PEDANTIC (pfile))
+      if (!CPP_OPTION (pfile, binary_constants) && CPP_PEDANTIC (pfile))
 	{
 	  if (CPP_OPTION (pfile, cplusplus))
 	    warned
@@ -916,6 +934,19 @@ cpp_classify_number (cpp_reader *pfile, const cpp_token *token,
 			       virtual_location, 0,
 			       "binary constants are a C23 feature");
     }
+  if (zero_o_prefix)
+    {
+      bool warned = false;
+      if (!CPP_OPTION (pfile, octal_constants) && CPP_PEDANTIC (pfile))
+	warned
+	  = cpp_pedwarning_with_line (pfile, CPP_W_PEDANTIC, virtual_location,
+				      0, "%<0o%> prefixed constants are a C2Y "
+					 "feature or GCC extension");
+      if (!warned && CPP_OPTION (pfile, cpp_warn_c23_c2y_compat) > 0)
+	cpp_warning_with_line (pfile, CPP_W_C23_C2Y_COMPAT,
+			       virtual_location, 0,
+			       "%<0o%> prefixed constants are a C2Y feature");
+    }
 
   if (radix == 10)
     result |= CPP_N_DECIMAL;
@@ -967,6 +998,8 @@ cpp_interpret_integer (cpp_reader *pfile, const cpp_token *token,
 	{
 	  base = 8;
 	  p++;
+	  if (*p == 'o' || *p == 'O')
+	    p++;
 	}
       else if ((type & CPP_N_RADIX) == CPP_N_HEX)
 	{