cpp-id-data.h (UC): Was U, conflicts with U...

libcpp/ChangeLog:
2008-04-14  Kris Van Hees <kris.van.hees@oracle.com>

* include/cpp-id-data.h (UC): Was U, conflicts with U... literal.
* include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens.
(struct cpp_options): Added uliterals.
(cpp_interpret_string): Update prototype.
(cpp_interpret_string_notranslate): Idem.
* charset.c (init_iconv_desc): New width member in cset_converter.
(cpp_init_iconv): Add support for char{16,32}_cset_desc.
(convert_ucn): Idem.
(emit_numeric_escape): Idem.
(convert_hex): Idem.
(convert_oct): Idem.
(convert_escape): Idem.
(converter_for_type): New function.
(cpp_interpret_string): Use converter_for_type, support u and U prefix.
(cpp_interpret_string_notranslate): Match changed prototype.
(wide_str_to_charconst): Use converter_for_type.
(cpp_interpret_charconst): Add support for CPP_CHAR{16,32}.
* directives.c (linemarker_dir): Macro U changed to UC.
(parse_include): Idem.
(register_pragma_1): Idem.
(restore_registered_pragmas): Idem.
(get__Pragma_string): Support CPP_STRING{16,32}.
* expr.c (eval_token): Support CPP_CHAR{16,32}.
* init.c (struct lang_flags): Added uliterals.
(lang_defaults): Idem.
* internal.h (struct cset_converter) <width>: New field.
(struct cpp_reader) <char16_cset_desc>: Idem.
(struct cpp_reader) <char32_cset_desc>: Idem.
* lex.c (digraph_spellings): Macro U changed to UC.
(OP, TK): Idem.
(lex_string): Add support for u'...', U'...', u... and U....
(_cpp_lex_direct): Idem.
* macro.c (_cpp_builtin_macro_text): Macro U changed to UC.
(stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}.

gcc/ChangeLog:
2008-04-14  Kris Van Hees <kris.van.hees@oracle.com>
  
* c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros.
(fname_as_string): Match updated cpp_interpret_string prototype.
(fix_string_type): Support char16_t* and char32_t*.
(c_common_nodes_and_builtins): Add char16_t and char32_t (and
derivative) nodes.  Register as builtin if C++0x.
(c_parse_error): Support CPP_CHAR{16,32}.
* c-common.h (RID_CHAR16, RID_CHAR32): New elements. 
(enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE,
CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE,
CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE,
CTI_CHAR32_ARRAY_TYPE>: New elements.
(char16_type_node, signed_char16_type_node, unsigned_char16_type_node,
char32_type_node, signed_char32_type_node, char16_array_type_node,
char32_array_type_node): New defines.
* c-lex.c (cb_ident): Match updated cpp_interpret_string prototype.
(c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}.
(lex_string): Support CPP_STRING{16,32}, match updated
cpp_interpret_string and cpp_interpret_string_notranslate prototypes.
(lex_charconst): Support CPP_CHAR{16,32}.
* c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32}
and CPP_STRING{16,32}.

gcc/cp/ChangeLog:
2008-04-14  Kris Van Hees <kris.van.hees@oracle.com>

* cvt.c (type_promotes_to): Support char16_t and char32_t.
* decl.c (grokdeclarator): Disallow signed/unsigned/short/long on
char16_t and char32_t.
* lex.c (reswords): Add char16_t and char32_t (for c++0x).
* mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor
extended builtin type u8char32_t.
* parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support
RID_CHAR{16,32}.
(cp_lexer_print_token): Support CPP_STRING{16,32}.
(cp_parser_is_string_literal): Idem.
(cp_parser_string_literal): Idem.
(cp_parser_primary_expression): Support CPP_CHAR{16,32} and
CPP_STRING{16,32}.
(cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. 
* tree.c (char_type_p): Support char16_t and char32_t as char types.
* typeck.c (string_conv_p): Support char16_t and char32_t.

gcc/testsuite/ChangeLog:
2008-04-14  Kris Van Hees <kris.van.hees@oracle.com>

Tests for char16_t and char32_t support.
* g++.dg/ext/utf-cvt.C: New
* g++.dg/ext/utf-cxx0x.C: New
* g++.dg/ext/utf-cxx98.C: New
* g++.dg/ext/utf-dflt.C: New
* g++.dg/ext/utf-gnuxx0x.C: New
* g++.dg/ext/utf-gnuxx98.C: New
* g++.dg/ext/utf-mangle.C: New
* g++.dg/ext/utf-typedef-cxx0x.C: New
* g++.dg/ext/utf-typedef-
* g++.dg/ext/utf-typespec.C: New
* g++.dg/ext/utf16-1.C: New
* g++.dg/ext/utf16-2.C: New
* g++.dg/ext/utf16-3.C: New
* g++.dg/ext/utf16-4.C: New
* g++.dg/ext/utf32-1.C: New
* g++.dg/ext/utf32-2.C: New
* g++.dg/ext/utf32-3.C: New
* g++.dg/ext/utf32-4.C: New
* gcc.dg/utf-cvt.c: New
* gcc.dg/utf-dflt.c: New
* gcc.dg/utf16-1.c: New
* gcc.dg/utf16-2.c: New
* gcc.dg/utf16-3.c: New
* gcc.dg/utf16-4.c: New
* gcc.dg/utf32-1.c: New
* gcc.dg/utf32-2.c: New
* gcc.dg/utf32-3.c: New
* gcc.dg/utf32-4.c: New

libiberty/ChangeLog:
2008-04-14  Kris Van Hees <kris.van.hees@oracle.com>

* testsuite/demangle-expected: Added tests for char16_t and char32_t.

From-SVN: r134438

8 files changed, 99 insertions, 17 deletions

diff --git a/gcc/cp/ChangeLog b/gcc/cp/ChangeLog
index 3169ba0..b348c0d 100644
--- a/gcc/cp/ChangeLog
+++ b/gcc/cp/ChangeLog
@@ -1,3 +1,22 @@
+2008-04-18  Kris Van Hees <kris.van.hees@oracle.com>
+
+	* cvt.c (type_promotes_to): Support char16_t and char32_t.
+	* decl.c (grokdeclarator): Disallow signed/unsigned/short/long on
+	char16_t and char32_t.
+	* lex.c (reswords): Add char16_t and char32_t (for c++0x).
+	* mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor
+	extended builtin type "u8char{16,32}_t".
+	* parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support
+	RID_CHAR{16,32}.
+	(cp_lexer_print_token): Support CPP_STRING{16,32}.
+	(cp_parser_is_string_literal): Idem.
+	(cp_parser_string_literal): Idem.
+	(cp_parser_primary_expression): Support CPP_CHAR{16,32} and
+	CPP_STRING{16,32}.
+	(cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. 
+	* tree.c (char_type_p): Support char16_t and char32_t as char types.
+	* typeck.c (string_conv_p): Support char16_t and char32_t.
+
 2008-04-17  Jason Merrill  <jason@redhat.com>
 
 	PR c++/35773
diff --git a/gcc/cp/cvt.c b/gcc/cp/cvt.c
index fe1ed29..b2c17c5 100644
--- a/gcc/cp/cvt.c
+++ b/gcc/cp/cvt.c
@@ -1219,6 +1219,8 @@ type_promotes_to (tree type)
   /* Normally convert enums to int, but convert wide enums to something
      wider.  */
   else if (TREE_CODE (type) == ENUMERAL_TYPE
+	   || type == char16_type_node
+	   || type == char32_type_node
 	   || type == wchar_type_node)
     {
       int precision = MAX (TYPE_PRECISION (type),
diff --git a/gcc/cp/decl.c b/gcc/cp/decl.c
index 66e8f42..d16cb78 100644
--- a/gcc/cp/decl.c
+++ b/gcc/cp/decl.c
@@ -7732,6 +7732,13 @@ grokdeclarator (const cp_declarator *declarator,
 	error ("%<long%> or %<short%> specified with char for %qs", name);
       else if (long_p && short_p)
 	error ("%<long%> and %<short%> specified together for %qs", name);
+      else if (type == char16_type_node || type == char32_type_node)
+	{
+	  if (signed_p || unsigned_p)
+	    error ("%<signed%> or %<unsigned%> invalid for %qs", name);
+	  else if (short_p || long_p)
+	    error ("%<short%> or %<long%> invalid for %qs", name);
+	}
       else
 	{
 	  ok = 1;
diff --git a/gcc/cp/lex.c b/gcc/cp/lex.c
index 4552305..8484a4b 100644
--- a/gcc/cp/lex.c
+++ b/gcc/cp/lex.c
@@ -241,6 +241,8 @@ static const struct resword reswords[] =
   { "case",		RID_CASE,	0 },
   { "catch",		RID_CATCH,	0 },
   { "char",		RID_CHAR,	0 },
+  { "char16_t",		RID_CHAR16,	D_CXX0X },
+  { "char32_t",		RID_CHAR32,	D_CXX0X },
   { "class",		RID_CLASS,	0 },
   { "const",		RID_CONST,	0 },
   { "const_cast",	RID_CONSTCAST,	0 },
diff --git a/gcc/cp/mangle.c b/gcc/cp/mangle.c
index 09a34562..5ac5bce 100644
--- a/gcc/cp/mangle.c
+++ b/gcc/cp/mangle.c
@@ -1782,10 +1782,14 @@ write_builtin_type (tree type)
       break;
 
     case INTEGER_TYPE:
-      /* TYPE may still be wchar_t, since that isn't in
-	 integer_type_nodes.  */
+      /* TYPE may still be wchar_t, char16_t, or char32_t, since that
+	 isn't in integer_type_nodes.  */
       if (type == wchar_type_node)
 	write_char ('w');
+      else if (type == char16_type_node)
+	write_string ("u8char16_t");
+      else if (type == char32_type_node)
+	write_string ("u8char32_t");
       else if (TYPE_FOR_JAVA (type))
 	write_java_integer_type_codes (type);
       else
diff --git a/gcc/cp/parser.c b/gcc/cp/parser.c
index f57ce28..f2acddb 100644
--- a/gcc/cp/parser.c
+++ b/gcc/cp/parser.c
@@ -556,6 +556,8 @@ cp_lexer_next_token_is_decl_specifier_keyword (cp_lexer *lexer)
     case RID_TYPENAME:
       /* Simple type specifiers.  */
     case RID_CHAR:
+    case RID_CHAR16:
+    case RID_CHAR32:
     case RID_WCHAR:
     case RID_BOOL:
     case RID_SHORT:
@@ -789,6 +791,8 @@ cp_lexer_print_token (FILE * stream, cp_token *token)
       break;
 
     case CPP_STRING:
+    case CPP_STRING16:
+    case CPP_STRING32:
     case CPP_WSTRING:
       fprintf (stream, " \"%s\"", TREE_STRING_POINTER (token->u.value));
       break;
@@ -2033,7 +2037,10 @@ cp_parser_parsing_tentatively (cp_parser* parser)
 static bool
 cp_parser_is_string_literal (cp_token* token)
 {
-  return (token->type == CPP_STRING || token->type == CPP_WSTRING);
+  return (token->type == CPP_STRING ||
+	  token->type == CPP_STRING16 ||
+	  token->type == CPP_STRING32 ||
+	  token->type == CPP_WSTRING);
 }
 
 /* Returns nonzero if TOKEN is the indicated KEYWORD.  */
@@ -2867,11 +2874,11 @@ static tree
 cp_parser_string_literal (cp_parser *parser, bool translate, bool wide_ok)
 {
   tree value;
-  bool wide = false;
   size_t count;
   struct obstack str_ob;
   cpp_string str, istr, *strs;
   cp_token *tok;
+  enum cpp_ttype type;
 
   tok = cp_lexer_peek_token (parser->lexer);
   if (!cp_parser_is_string_literal (tok))
@@ -2880,6 +2887,8 @@ cp_parser_string_literal (cp_parser *parser, bool translate, bool wide_ok)
       return error_mark_node;
     }
 
+  type = tok->type;
+
   /* Try to avoid the overhead of creating and destroying an obstack
      for the common case of just one string.  */
   if (!cp_parser_is_string_literal
@@ -2890,8 +2899,6 @@ cp_parser_string_literal (cp_parser *parser, bool translate, bool wide_ok)
       str.text = (const unsigned char *)TREE_STRING_POINTER (tok->u.value);
       str.len = TREE_STRING_LENGTH (tok->u.value);
       count = 1;
-      if (tok->type == CPP_WSTRING)
-	wide = true;
 
       strs = &str;
     }
@@ -2906,8 +2913,14 @@ cp_parser_string_literal (cp_parser *parser, bool translate, bool wide_ok)
 	  count++;
 	  str.text = (const unsigned char *)TREE_STRING_POINTER (tok->u.value);
 	  str.len = TREE_STRING_LENGTH (tok->u.value);
-	  if (tok->type == CPP_WSTRING)
-	    wide = true;
+
+	  if (type != tok->type)
+	    {
+	      if (type == CPP_STRING)
+		type = tok->type;
+	      else if (tok->type != CPP_STRING)
+		error ("unsupported non-standard concatenation of string literals");
+	    }
 
 	  obstack_grow (&str_ob, &str, sizeof (cpp_string));
 
@@ -2918,19 +2931,35 @@ cp_parser_string_literal (cp_parser *parser, bool translate, bool wide_ok)
       strs = (cpp_string *) obstack_finish (&str_ob);
     }
 
-  if (wide && !wide_ok)
+  if (type != CPP_STRING && !wide_ok)
     {
       cp_parser_error (parser, "a wide string is invalid in this context");
-      wide = false;
+      type = CPP_STRING;
     }
 
   if ((translate ? cpp_interpret_string : cpp_interpret_string_notranslate)
-      (parse_in, strs, count, &istr, wide))
+      (parse_in, strs, count, &istr, type))
     {
       value = build_string (istr.len, (const char *)istr.text);
       free (CONST_CAST (unsigned char *, istr.text));
 
-      TREE_TYPE (value) = wide ? wchar_array_type_node : char_array_type_node;
+      switch (type)
+	{
+	default:
+	case CPP_STRING:
+	  TREE_TYPE (value) = char_array_type_node;
+	  break;
+	case CPP_STRING16:
+	  TREE_TYPE (value) = char16_array_type_node;
+	  break;
+	case CPP_STRING32:
+	  TREE_TYPE (value) = char32_array_type_node;
+	  break;
+	case CPP_WSTRING:
+	  TREE_TYPE (value) = wchar_array_type_node;
+	  break;
+	}
+
       value = fix_string_type (value);
     }
   else
@@ -3085,6 +3114,8 @@ cp_parser_primary_expression (cp_parser *parser,
 	   string-literal
 	   boolean-literal  */
     case CPP_CHAR:
+    case CPP_CHAR16:
+    case CPP_CHAR32:
     case CPP_WCHAR:
     case CPP_NUMBER:
       token = cp_lexer_consume_token (parser->lexer);
@@ -3136,6 +3167,8 @@ cp_parser_primary_expression (cp_parser *parser,
       return token->u.value;
 
     case CPP_STRING:
+    case CPP_STRING16:
+    case CPP_STRING32:
     case CPP_WSTRING:
       /* ??? Should wide strings be allowed when parser->translate_strings_p
 	 is false (i.e. in attributes)?  If not, we can kill the third
@@ -10762,6 +10795,8 @@ cp_parser_type_specifier (cp_parser* parser,
    simple-type-specifier:
      auto
      decltype ( expression )   
+     char16_t
+     char32_t
 
    GNU Extension:
 
@@ -10791,6 +10826,12 @@ cp_parser_simple_type_specifier (cp_parser* parser,
 	decl_specs->explicit_char_p = true;
       type = char_type_node;
       break;
+    case RID_CHAR16:
+      type = char16_type_node;
+      break;
+    case RID_CHAR32:
+      type = char32_type_node;
+      break;
     case RID_WCHAR:
       type = wchar_type_node;
       break;
@@ -17754,13 +17795,16 @@ 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 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 the user tries to redeclare bool, 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_specs->specs[(int) ds_typedef]
       && !user_defined_p
       && (type_spec == boolean_type_node
+	  || type_spec == char16_type_node
+	  || type_spec == char32_type_node
 	  || type_spec == wchar_type_node)
       && (decl_specs->type
 	  || decl_specs->specs[(int) ds_long]
diff --git a/gcc/cp/tree.c b/gcc/cp/tree.c
index 027f1c9..73adbb5 100644
--- a/gcc/cp/tree.c
+++ b/gcc/cp/tree.c
@@ -2474,6 +2474,8 @@ char_type_p (tree type)
   return (same_type_p (type, char_type_node)
 	  || same_type_p (type, unsigned_char_type_node)
 	  || same_type_p (type, signed_char_type_node)
+	  || same_type_p (type, char16_type_node)
+	  || same_type_p (type, char32_type_node)
 	  || same_type_p (type, wchar_type_node));
 }
 
diff --git a/gcc/cp/typeck.c b/gcc/cp/typeck.c
index de10c0e..9e9d461 100644
--- a/gcc/cp/typeck.c
+++ b/gcc/cp/typeck.c
@@ -1722,12 +1722,14 @@ string_conv_p (const_tree totype, const_tree exp, int warn)
 
   t = TREE_TYPE (totype);
   if (!same_type_p (t, char_type_node)
+      && !same_type_p (t, char16_type_node)
+      && !same_type_p (t, char32_type_node)
       && !same_type_p (t, wchar_type_node))
     return 0;
 
   if (TREE_CODE (exp) == STRING_CST)
     {
-      /* Make sure that we don't try to convert between char and wchar_t.  */
+      /* Make sure that we don't try to convert between char and wide chars.  */
       if (!same_type_p (TYPE_MAIN_VARIANT (TREE_TYPE (TREE_TYPE (exp))), t))
 	return 0;
     }