[libcpp] Issue a pedantic warning for UCNs outside UCS codespace

[Eric Botcazou]

Hi,

the Universal Character Names accepted by the C family of compilers are mapped 
to those of ISO/IEC 10646, which defines the Universal Character Set codespace 
as the range 0-0x10FFFF inclusive.  The upper bound is already enforced for 
identifiers but not for literals, so the following code is accepted in C99:

#include <stddef.h>

wchar_t a = L'\U00110000';

whereas it is rejected with an error by other compilers (Clang, MSVC).

I'm not sure whether the compiler is really equired to issue a diagnostic in 
this case.  Moreover a few tests in the testsuite manipulate UCNs outside the 
UCS codespace.  That's why I suggest issuing a pedantic warning.

Tested on x86_64-suse-linux, OK for the mainline?


2019-09-24  Eric Botcazou  <ebotca...@adacore.com>

libcpp/
        * charset.c (UCS_LIMIT): New macro.
        (ucn_valid_in_identifier): Use it instead of a hardcoded constant.
        (_cpp_valid_ucn): Issue a pedantic warning for UCNs larger than
        UCS_LIMIT outside of identifiers.


2019-09-24  Eric Botcazou  <ebotca...@adacore.com>

gcc/testsuite/
        * gcc.dg/cpp/ucs.c: Add test for new warning and adjust.
        * gcc.dg/cpp/utf8-5byte-1.c: Add -w to the options.
        * gcc.dg/attr-alias-5.c: Likewise.

-- 
Eric Botcazou
Index: libcpp/charset.c
===================================================================
--- libcpp/charset.c	(revision 275988)
+++ libcpp/charset.c	(working copy)
@@ -901,6 +901,9 @@ struct ucnrange {
 };
 #include "ucnid.h"
 
+/* ISO 10646 defines the UCS codespace as the range 0-0x10FFFF inclusive.  */
+#define UCS_LIMIT 0x10FFFF
+
 /* Returns 1 if C is valid in an identifier, 2 if C is valid except at
    the start of an identifier, and 0 if C is not valid in an
    identifier.  We assume C has already gone through the checks of
@@ -915,7 +918,7 @@ ucn_valid_in_identifier (cpp_reader *pfi
   int mn, mx, md;
   unsigned short valid_flags, invalid_start_flags;
 
-  if (c > 0x10FFFF)
+  if (c > UCS_LIMIT)
     return 0;
 
   mn = 0;
@@ -1016,6 +1019,9 @@ ucn_valid_in_identifier (cpp_reader *pfi
    whose short identifier is less than 00A0 other than 0024 ($), 0040 (@),
    or 0060 (`), nor one in the range D800 through DFFF inclusive.
 
+   If the hexadecimal value is larger than the upper bound of the UCS
+   codespace specified in ISO/IEC 10646, a pedantic warning is issued.
+
    *PSTR must be preceded by "\u" or "\U"; it is assumed that the
    buffer end is delimited by a non-hex digit.  Returns false if the
    UCN has not been consumed, true otherwise.
@@ -1135,6 +1141,10 @@ _cpp_valid_ucn (cpp_reader *pfile, const
    "universal character %.*s is not valid at the start of an identifier",
 		   (int) (str - base), base);
     }
+  else if (result > UCS_LIMIT)
+    cpp_error (pfile, CPP_DL_PEDWARN,
+	       "%.*s is outside the UCS codespace",
+	       (int) (str - base), base);
 
   *cp = result;
   return true;
Index: gcc/testsuite/gcc.dg/attr-alias-5.c
===================================================================
--- gcc/testsuite/gcc.dg/attr-alias-5.c	(revision 275988)
+++ gcc/testsuite/gcc.dg/attr-alias-5.c	(working copy)
@@ -1,7 +1,7 @@
 /* Verify diagnostics for aliases to strings containing extended
    identifiers or bad characters.  */
 /* { dg-do compile } */
-/* { dg-options "-std=gnu99" } */
+/* { dg-options "-std=gnu99 -w" } */
 /* { dg-require-alias "" } */
 /* { dg-require-ascii-locale "" } */
 /* { dg-skip-if "" { powerpc*-*-aix* } } */
Index: gcc/testsuite/gcc.dg/cpp/ucs.c
===================================================================
--- gcc/testsuite/gcc.dg/cpp/ucs.c	(revision 275988)
+++ gcc/testsuite/gcc.dg/cpp/ucs.c	(working copy)
@@ -39,7 +39,7 @@
 #endif
 
 #if WCHAR_MAX >= 0x7ffffff
-# if L'\U1234abcd' != 0x1234abcd
+# if L'\U1234abcd' != 0x1234abcd /* { dg-warning "outside" "" } */
 #  error bad long ucs	/* { dg-bogus "bad" "bad U1234abcd evaluation" } */
 # endif
 #endif
@@ -49,7 +49,7 @@ void foo ()
   int c;
 
   c = L'\ubad';		/* { dg-error "incomplete" "incomplete UCN 1" } */
-  c = L"\U1234"[0];	/* { dg-error "incomplete" "incompete UCN 2" } */
+  c = L"\U1234"[0];	/* { dg-error "incomplete" "incomplete UCN 2" } */
 
   c = L'\u000x';	/* { dg-error "incomplete" "non-hex digit in UCN" } */
   /* If sizeof(HOST_WIDE_INT) > sizeof(wchar_t), we can get a multi-character
@@ -64,4 +64,6 @@ void foo ()
   c = '\u0025';		/* { dg-error "not a valid" "0025 invalid UCN" } */
   c = L"\uD800"[0];	/* { dg-error "not a valid" "D800 invalid UCN" } */
   c = L'\U0000DFFF';	/* { dg-error "not a valid" "DFFF invalid UCN" } */
+
+  c = L'\U00110000';	/* { dg-warning "outside" "110000 outside UCS" } */
 }
Index: gcc/testsuite/gcc.dg/cpp/utf8-5byte-1.c
===================================================================
--- gcc/testsuite/gcc.dg/cpp/utf8-5byte-1.c	(revision 275988)
+++ gcc/testsuite/gcc.dg/cpp/utf8-5byte-1.c	(working copy)
@@ -1,7 +1,7 @@
 /* Test for bug in conversions from 5-byte UTF-8 sequences in
    cpplib.  */
 /* { dg-do run { target { 4byte_wchar_t } } } */
-/* { dg-options "-std=gnu99" } */
+/* { dg-options "-std=gnu99 -w" } */
 
 extern void abort (void);
 extern void exit (int);