Implement P0482R5, char8_t: A type for UTF-8 characters and strings

gcc/cp/
	* cvt.c (type_promotes_to): Handle char8_t promotion.
	* decl.c (grokdeclarator): Handle invalid type specifier
	combinations involving char8_t.
	* lex.c (init_reswords): Add char8_t as a reserved word.
	* mangle.c (write_builtin_type): Add name mangling for char8_t (Du).
	* parser.c (cp_keyword_starts_decl_specifier_p)
	(cp_parser_simple_type_specifier): Recognize char8_t as a simple
	type specifier.
	(cp_parser_string_literal): Use char8_array_type_node for the type
	of CPP_UTF8STRING.
	(cp_parser_set_decl_spec_type): Tolerate char8_t typedefs in system
	headers.
	* rtti.c (emit_support_tinfos): type_info support for char8_t.
	* tree.c (char_type_p): Recognize char8_t as a character type.
	* typeck.c (string_conv_p): Handle conversions of u8 string
	literals of char8_t type.
	(check_literal_operator_args): Handle UDLs with u8 string literals
	of char8_t type.
	* typeck2.c (ordinary_char_type_p): New.
	(digest_init_r): Disallow initializing a char array with a u8 string
	literal.
gcc/c-family/
	* c-common.c (c_common_reswords): Add char8_t.
	(fix_string_type): Use char8_t for the type of u8 string literals.
	(c_common_get_alias_set): char8_t doesn't alias.
	(c_common_nodes_and_builtins): Define char8_t as a builtin type in
	C++.
	(c_stddef_cpp_builtins): Add __CHAR8_TYPE__.
	(keyword_begins_type_specifier): Add RID_CHAR8.
	* c-common.h (rid): Add RID_CHAR8.
	(c_tree_index): Add CTI_CHAR8_TYPE and CTI_CHAR8_ARRAY_TYPE.
	Define D_CXX_CHAR8_T and D_CXX_CHAR8_T_FLAGS.
	Define char8_type_node and char8_array_type_node.
	* c-cppbuiltin.c (cpp_atomic_builtins): Predefine
	__GCC_ATOMIC_CHAR8_T_LOCK_FREE.
	(c_cpp_builtins): Predefine __cpp_char8_t.
	* c-lex.c (lex_string): Use char8_array_type_node as the type of
	CPP_UTF8STRING.
	(lex_charconst): Use char8_type_node as the type of CPP_UTF8CHAR.
	* c-opts.c: If not otherwise specified, enable -fchar8_t when
	targeting C++2a.
	* c.opt: Add the -fchar8_t command line option.
libiberty/
	* cp-demangle.c (cplus_demangle_builtin_types)
	(cplus_demangle_type): Add name demangling for char8_t (Du).
	* cp-demangle.h: Increase D_BUILTIN_TYPE_COUNT to accommodate the
	new char8_t type.

From-SVN: r267923

1 files changed, 13 insertions, 3 deletions

diff --git a/gcc/cp/parser.c b/gcc/cp/parser.c
index be669f2..7d7b029 100644
--- a/gcc/cp/parser.c
+++ b/gcc/cp/parser.c
@@ -948,6 +948,7 @@ cp_keyword_starts_decl_specifier_p (enum rid keyword)
     case RID_TYPENAME:
       /* Simple type specifiers.  */
     case RID_CHAR:
+    case RID_CHAR8:
     case RID_CHAR16:
     case RID_CHAR32:
     case RID_WCHAR:
@@ -4235,9 +4236,14 @@ cp_parser_string_literal (cp_parser *parser, bool translate, bool wide_ok,
 	{
 	default:
 	case CPP_STRING:
-	case CPP_UTF8STRING:
 	  TREE_TYPE (value) = char_array_type_node;
 	  break;
+	case CPP_UTF8STRING:
+	  if (flag_char8_t)
+	    TREE_TYPE (value) = char8_array_type_node;
+	  else
+	    TREE_TYPE (value) = char_array_type_node;
+	  break;
 	case CPP_STRING16:
 	  TREE_TYPE (value) = char16_array_type_node;
 	  break;
@@ -17504,6 +17510,9 @@ cp_parser_simple_type_specifier (cp_parser* parser,
 	decl_specs->explicit_char_p = true;
       type = char_type_node;
       break;
+    case RID_CHAR8:
+      type = char8_type_node;
+      break;
     case RID_CHAR16:
       type = char16_type_node;
       break;
@@ -28919,14 +28928,15 @@ cp_parser_set_decl_spec_type (cp_decl_specifier_seq *decl_specs,
 {
   decl_specs->any_specifiers_p = true;
 
-  /* If the user tries to redeclare bool, char16_t, char32_t, or wchar_t
-     (with, for example, in "typedef int wchar_t;") we remember that
+  /* If the user tries to redeclare bool, char8_t, char16_t, char32_t, or
+     wchar_t (with, for example, in "typedef int wchar_t;") we remember that
      this is what happened.  In system headers, we ignore these
      declarations so that G++ can work with system headers that are not
      C++-safe.  */
   if (decl_spec_seq_has_spec_p (decl_specs, ds_typedef)
       && !type_definition_p
       && (type_spec == boolean_type_node
+	  || type_spec == char8_type_node
 	  || type_spec == char16_type_node
 	  || type_spec == char32_type_node
 	  || type_spec == wchar_type_node)