libcpp: Implement P2362R3 - Remove non-encodable wide character literals and multicha...

My understanding of the paper is that we just want to promote the CPP_WCHAR
"character constant too long for its type" warning to error as it is already
error for u8, u and U literals.

2022-08-26  Jakub Jelinek  <jakub@redhat.com>

	PR c++/106647
	* charset.cc (wide_str_to_charconst): Implement P2362R3 - Remove
	non-encodable wide character literals and multicharacter.  For
	C++23 use CPP_DL_ERROR instead of CPP_DL_WARNING for
	"character constant too long for its type" diagnostics on CPP_WCHAR
	literals.

	* g++.dg/cpp23/wchar-multi1.C: New test.
	* g++.dg/cpp23/wchar-multi2.C: New test.

diff --git a/gcc/testsuite/g++.dg/cpp23/wchar-multi1.C b/gcc/testsuite/g++.dg/cpp23/wchar-multi1.C
new file mode 100644 (file)
index 0000000..77fa3a6
--- /dev/null
+++ b/gcc/testsuite/g++.dg/cpp23/wchar-multi1.C
@@ -0,0 +1,42 @@
+// P2362R3 - Remove non-encodable wide character literals and multicharacter
+// wide character literals.
+// { dg-do compile }
+
+char a = 'a';
+int b = 'ab';                  // { dg-warning "multi-character character constant" }
+int c = '\u05D9';              // { dg-warning "multi-character character constant" }
+#if __SIZEOF_INT__ > 2
+int d = '\U0001F525';          // { dg-warning "multi-character character constant" "" { target int32 } }
+#endif
+int e = 'abcd';                        // { dg-warning "multi-character character constant" }
+wchar_t f = L'f';
+wchar_t g = L'gh';             // { dg-error "character constant too long for its type" "" { target c++23 } }
+                               // { dg-warning "character constant too long for its type" "" { target c++20_down } .-1 }
+wchar_t h = L'ijkl';           // { dg-error "character constant too long for its type" "" { target c++23 } }
+                               // { dg-warning "character constant too long for its type" "" { target c++20_down } .-1 }
+wchar_t i = L'\U0001F525';     // { dg-error "character constant too long for its type" "" { target { c++23 && { ! 4byte_wchar_t } } } }
+                               // { dg-warning "character constant too long for its type" "" { target { c++20_down && { ! 4byte_wchar_t } } } .-1 }
+#ifdef __cpp_char8_t
+typedef char8_t u8;
+#else
+typedef char u8;
+#endif
+#if __cpp_unicode_characters >= 201411 
+u8 j = u8'j';
+u8 k = u8'kl';                 // { dg-error "character constant too long for its type" "" { target c++17 } }
+u8 l = u8'\U0001F525';         // { dg-error "character constant too long for its type" "" { target c++17 }  }
+#endif
+#if __cpp_unicode_characters >= 200704
+char16_t m = u'm';
+char16_t n = u'no';            // { dg-error "character constant too long for its type" "" { target c++11 } }
+char16_t o = u'\u05D9';
+char16_t p = u'\U0001F525';    // { dg-error "character constant too long for its type" "" { target c++11 } }
+char32_t q = U'm';
+char32_t r = U'no';            // { dg-error "character constant too long for its type" "" { target c++11 } }
+char32_t s = U'\u05D9';
+char32_t t = U'\U0001F525';
+#endif
+wchar_t u = L'\u0065\u0301';           // { dg-error "character constant too long for its type" "" { target c++23 } }
+                               // { dg-warning "character constant too long for its type" "" { target c++20_down } .-1 }
+wchar_t v = L'é';            // { dg-error "character constant too long for its type" "" { target c++23 } }
+                               // { dg-warning "character constant too long for its type" "" { target c++20_down } .-1 }

diff --git a/gcc/testsuite/g++.dg/cpp23/wchar-multi2.C b/gcc/testsuite/g++.dg/cpp23/wchar-multi2.C
new file mode 100644 (file)
index 0000000..a63e0ff
--- /dev/null
+++ b/gcc/testsuite/g++.dg/cpp23/wchar-multi2.C
@@ -0,0 +1,43 @@
+// P2362R3 - Remove non-encodable wide character literals and multicharacter
+// wide character literals.
+// { dg-do compile }
+// { dg-options "-fshort-wchar" }
+
+char a = 'a';
+int b = 'ab';                  // { dg-warning "multi-character character constant" }
+int c = '\u05D9';              // { dg-warning "multi-character character constant" }
+#if __SIZEOF_INT__ > 2
+int d = '\U0001F525';          // { dg-warning "multi-character character constant" "" { target int32 } }
+#endif
+int e = 'abcd';                        // { dg-warning "multi-character character constant" }
+wchar_t f = L'f';
+wchar_t g = L'gh';             // { dg-error "character constant too long for its type" "" { target c++23 } }
+                               // { dg-warning "character constant too long for its type" "" { target c++20_down } .-1 }
+wchar_t h = L'ijkl';           // { dg-error "character constant too long for its type" "" { target c++23 } }
+                               // { dg-warning "character constant too long for its type" "" { target c++20_down } .-1 }
+wchar_t i = L'\U0001F525';     // { dg-error "character constant too long for its type" "" { target { c++23 } } }
+                               // { dg-warning "character constant too long for its type" "" { target { c++20_down } } .-1 }
+#ifdef __cpp_char8_t
+typedef char8_t u8;
+#else
+typedef char u8;
+#endif
+#if __cpp_unicode_characters >= 201411 
+u8 j = u8'j';
+u8 k = u8'kl';                 // { dg-error "character constant too long for its type" "" { target c++17 } }
+u8 l = u8'\U0001F525';         // { dg-error "character constant too long for its type" "" { target c++17 }  }
+#endif
+#if __cpp_unicode_characters >= 200704
+char16_t m = u'm';
+char16_t n = u'no';            // { dg-error "character constant too long for its type" "" { target c++11 } }
+char16_t o = u'\u05D9';
+char16_t p = u'\U0001F525';    // { dg-error "character constant too long for its type" "" { target c++11 } }
+char32_t q = U'm';
+char32_t r = U'no';            // { dg-error "character constant too long for its type" "" { target c++11 } }
+char32_t s = U'\u05D9';
+char32_t t = U'\U0001F525';
+#endif
+wchar_t u = L'\u0065\u0301';           // { dg-error "character constant too long for its type" "" { target c++23 } }
+                               // { dg-warning "character constant too long for its type" "" { target c++20_down } .-1 }
+wchar_t v = L'é';            // { dg-error "character constant too long for its type" "" { target c++23 } }
+                               // { dg-warning "character constant too long for its type" "" { target c++20_down } .-1 }

diff --git a/libcpp/charset.cc b/libcpp/charset.cc
index 47a36d8b01e1ad2ee553ea9fa2c7efdf1d9d9924..d3c07d6c82d1cbcb516079c2f526c8965f6da93f 100644 (file)
--- a/libcpp/charset.cc
+++ b/libcpp/charset.cc
@@ -2593,7 +2593,11 @@ wide_str_to_charconst (cpp_reader *pfile, cpp_string str,
      character constant is guaranteed to overflow.  */
   if (str.len > nbwc * 2)
     cpp_error (pfile, (CPP_OPTION (pfile, cplusplus)
-                      && (type == CPP_CHAR16 || type == CPP_CHAR32))
+                      && (type == CPP_CHAR16
+                          || type == CPP_CHAR32
+                          /* In C++23 this is error even for L'ab'.  */
+                          || (type == CPP_WCHAR
+                              && CPP_OPTION (pfile, size_t_literals))))
                      ? CPP_DL_ERROR : CPP_DL_WARNING,
               "character constant too long for its type");