Implement N4197 - Adding u8 character literals

libcpp:

2015-06-30  Edward Smith-Rowland  <3dw4rd@verizon.net>

	Implement N4197 - Adding u8 character literals
	* include/cpplib.h (UTF8CHAR, UTF8CHAR_USERDEF): New cpp tokens;
	(struct cpp_options): Add utf8_char_literals.
	* init.c (struct lang_flags): Add utf8_char_literals;
	(struct lang_flags lang_defaults): Add column for utf8_char_literals.
	* macro.c (stringify_arg()): Treat CPP_UTF8CHAR token; 
	* expr.c (cpp_userdef_char_remove_type(), cpp_userdef_char_add_type()):
	Treat CPP_UTF8CHAR_USERDEF, CPP_UTF8CHAR tokens;
	(cpp_userdef_char_p()): Treat CPP_UTF8CHAR_USERDEF token;
	(eval_token(), _cpp_parse_expr()): Treat CPP_UTF8CHAR token.
	* lex.c (lex_string(), _cpp_lex_direct()): Include CPP_UTF8CHAR tokens.
	* charset.c (converter_for_type(), cpp_interpret_charconst()):
	Treat CPP_UTF8CHAR token.


gcc/c-family:

2015-06-30  Edward Smith-Rowland  <3dw4rd@verizon.net>

	Implement N4197 - Adding u8 character literals
	* c-family/c-ada-spec.c (print_ada_macros()): Treat CPP_UTF8CHAR
	like CPP_CHAR.
	* c-family/c-common.c (c_parse_error()): print CPP_UTF8CHAR
	and CPP_UTF8CHAR_USERDEF tokens.
	* c-family/c-lex.c (c_lex_with_flags()): Treat CPP_UTF8CHAR_USERDEF
	and CPP_UTF8CHAR tokens; (lex_charconst()): Treat CPP_UTF8CHAR token.


gcc/cp:

2015-06-30  Edward Smith-Rowland  <3dw4rd@verizon.net>

	Implement N4197 - Adding u8 character literals
	* parser.c (cp_parser_primary_expression()): Treat CPP_UTF8CHAR
	and CPP_UTF8CHAR_USERDEF tokens;
	(cp_parser_parenthesized_expression_list()): Treat CPP_UTF8CHAR token.


gcc/testsuite:

2015-06-30  Edward Smith-Rowland  <3dw4rd@verizon.net>

	Implement N4197 - Adding u8 character literals
	* g++.dg/cpp1z/utf8.C: New.
	* g++.dg/cpp1z/utf8-neg.C: New.
	* g++.dg/cpp1z/udlit-utf8char.C: New.

From-SVN: r225185

10 files changed, 69 insertions, 2 deletions

diff --git a/gcc/c-family/ChangeLog b/gcc/c-family/ChangeLog
index 0e03e7e..66ae6a8 100644
--- a/gcc/c-family/ChangeLog
+++ b/gcc/c-family/ChangeLog
@@ -1,3 +1,13 @@
+2015-06-30  Edward Smith-Rowland  <3dw4rd@verizon.net>
+
+	Implement N4197 - Adding u8 character literals
+	* c-family/c-ada-spec.c (print_ada_macros()): Treat CPP_UTF8CHAR
+	like CPP_CHAR.
+	* c-family/c-common.c (c_parse_error()): print CPP_UTF8CHAR
+	and CPP_UTF8CHAR_USERDEF tokens.
+	* c-family/c-lex.c (c_lex_with_flags()): Treat CPP_UTF8CHAR_USERDEF
+	and CPP_UTF8CHAR tokens; (lex_charconst()): Treat CPP_UTF8CHAR token.
+
 2015-06-29  Manuel López-Ibáñez  <manu@gcc.gnu.org>
 
 	PR fortran/66605
diff --git a/gcc/c-family/c-ada-spec.c b/gcc/c-family/c-ada-spec.c
index ef3c5e3..41d612f 100644
--- a/gcc/c-family/c-ada-spec.c
+++ b/gcc/c-family/c-ada-spec.c
@@ -249,6 +249,7 @@ print_ada_macros (pretty_printer *pp, cpp_hashnode **macros, int max_ada_macros)
 		  case CPP_WCHAR:
 		  case CPP_CHAR16:
 		  case CPP_CHAR32:
+		  case CPP_UTF8CHAR:
 		  case CPP_NAME:
 		  case CPP_STRING:
 		  case CPP_NUMBER:
diff --git a/gcc/c-family/c-common.c b/gcc/c-family/c-common.c
index ac42e4a..835fc2c 100644
--- a/gcc/c-family/c-common.c
+++ b/gcc/c-family/c-common.c
@@ -10256,7 +10256,8 @@ c_parse_error (const char *gmsgid, enum cpp_ttype token_type,
   else if (token_type == CPP_CHAR
 	   || token_type == CPP_WCHAR
 	   || token_type == CPP_CHAR16
-	   || token_type == CPP_CHAR32)
+	   || token_type == CPP_CHAR32
+	   || token_type == CPP_UTF8CHAR)
     {
       unsigned int val = TREE_INT_CST_LOW (value);
       const char *prefix;
@@ -10275,6 +10276,9 @@ c_parse_error (const char *gmsgid, enum cpp_ttype token_type,
 	case CPP_CHAR32:
 	  prefix = "U";
 	  break;
+	case CPP_UTF8CHAR:
+	  prefix = "u8";
+	  break;
         }
 
       if (val <= UCHAR_MAX && ISGRAPH (val))
@@ -10289,7 +10293,8 @@ c_parse_error (const char *gmsgid, enum cpp_ttype token_type,
   else if (token_type == CPP_CHAR_USERDEF
 	   || token_type == CPP_WCHAR_USERDEF
 	   || token_type == CPP_CHAR16_USERDEF
-	   || token_type == CPP_CHAR32_USERDEF)
+	   || token_type == CPP_CHAR32_USERDEF
+	   || token_type == CPP_UTF8CHAR_USERDEF)
     message = catenate_messages (gmsgid,
 				 " before user-defined character literal");
   else if (token_type == CPP_STRING_USERDEF
diff --git a/gcc/c-family/c-lex.c b/gcc/c-family/c-lex.c
index 9c56832..aa5d6e2 100644
--- a/gcc/c-family/c-lex.c
+++ b/gcc/c-family/c-lex.c
@@ -536,6 +536,7 @@ c_lex_with_flags (tree *value, location_t *loc, unsigned char *cpp_flags,
     case CPP_WCHAR_USERDEF:
     case CPP_CHAR16_USERDEF:
     case CPP_CHAR32_USERDEF:
+    case CPP_UTF8CHAR_USERDEF:
       {
 	tree literal;
 	cpp_token temp_tok = *tok;
@@ -553,6 +554,7 @@ c_lex_with_flags (tree *value, location_t *loc, unsigned char *cpp_flags,
     case CPP_WCHAR:
     case CPP_CHAR16:
     case CPP_CHAR32:
+    case CPP_UTF8CHAR:
       *value = lex_charconst (tok);
       break;
 
@@ -1250,6 +1252,8 @@ lex_charconst (const cpp_token *token)
     type = char32_type_node;
   else if (token->type == CPP_CHAR16)
     type = char16_type_node;
+  else if (token->type == CPP_UTF8CHAR)
+    type = char_type_node;
   /* In C, a character constant has type 'int'.
      In C++ 'char', but multi-char charconsts have type 'int'.  */
   else if (!c_dialect_cxx () || chars_seen > 1)
diff --git a/gcc/cp/ChangeLog b/gcc/cp/ChangeLog
index 843b7ed..04fb007 100644
--- a/gcc/cp/ChangeLog
+++ b/gcc/cp/ChangeLog
@@ -1,3 +1,10 @@
+2015-06-30  Edward Smith-Rowland  <3dw4rd@verizon.net>
+
+	Implement N4197 - Adding u8 character literals
+	* parser.c (cp_parser_primary_expression()): Treat CPP_UTF8CHAR
+	and CPP_UTF8CHAR_USERDEF tokens;
+	(cp_parser_parenthesized_expression_list()): Treat CPP_UTF8CHAR token.
+
 2015-06-29  Paolo Carlini  <paolo.carlini@oracle.com>
 
 	PR c++/65977
diff --git a/gcc/cp/parser.c b/gcc/cp/parser.c
index acf147c..bb3d636 100644
--- a/gcc/cp/parser.c
+++ b/gcc/cp/parser.c
@@ -4284,6 +4284,7 @@ cp_parser_primary_expression (cp_parser *parser,
     case CPP_CHAR16:
     case CPP_CHAR32:
     case CPP_WCHAR:
+    case CPP_UTF8CHAR:
     case CPP_NUMBER:
     case CPP_PREPARSED_EXPR:
       if (TREE_CODE (token->u.value) == USERDEF_LITERAL)
@@ -4345,6 +4346,7 @@ cp_parser_primary_expression (cp_parser *parser,
     case CPP_CHAR16_USERDEF:
     case CPP_CHAR32_USERDEF:
     case CPP_WCHAR_USERDEF:
+    case CPP_UTF8CHAR_USERDEF:
       return cp_parser_userdef_char_literal (parser);
 
     case CPP_STRING:
@@ -6887,6 +6889,7 @@ cp_parser_parenthesized_expression_list (cp_parser* parser,
 		  case CPP_WCHAR:
 		  case CPP_CHAR16:
 		  case CPP_CHAR32:
+		  case CPP_UTF8CHAR:
 		    /* If a parameter is literal zero alone, remember it
 		       for -Wmemset-transposed-args warning.  */
 		    if (integer_zerop (tok->u.value)
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index f14bbb1..f766b0d 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,10 @@
+2015-06-30  Edward Smith-Rowland  <3dw4rd@verizon.net>
+
+	Implement N4197 - Adding u8 character literals
+	* g++.dg/cpp1z/utf8.C: New.
+	* g++.dg/cpp1z/utf8-neg.C: New.
+	* g++.dg/cpp1z/udlit-utf8char.C: New.
+
 2015-06-30  Marek Polacek  <polacek@redhat.com>
 
 	* gcc.dg/fold-ior-2.c (fn4): Swap operands.
diff --git a/gcc/testsuite/g++.dg/cpp1z/udlit-utf8char.C b/gcc/testsuite/g++.dg/cpp1z/udlit-utf8char.C
new file mode 100644
index 0000000..fb9cdf18
--- /dev/null
+++ b/gcc/testsuite/g++.dg/cpp1z/udlit-utf8char.C
@@ -0,0 +1,8 @@
+// { dg-do compile }
+// { dg-options "-std=c++1z" }
+
+constexpr int
+operator""_foo(char c)
+{ return c * 100; }
+
+auto cc = u8'8'_foo;
diff --git a/gcc/testsuite/g++.dg/cpp1z/utf8-neg.C b/gcc/testsuite/g++.dg/cpp1z/utf8-neg.C
new file mode 100644
index 0000000..339f0e3
--- /dev/null
+++ b/gcc/testsuite/g++.dg/cpp1z/utf8-neg.C
@@ -0,0 +1,7 @@
+/* { dg-do compile } */
+/* { dg-options "-std=c++1z" } */
+
+const static char c0 = u8'';		// { dg-error "empty character" }
+const static char c1 = u8'ab';  	// { dg-warning "multi-character character constant" }
+const static char c2 = u8'\u0124';	// { dg-warning "multi-character character constant" }
+const static char c3 = u8'\U00064321';  // { dg-warning "multi-character character constant" }
diff --git a/gcc/testsuite/g++.dg/cpp1z/utf8.C b/gcc/testsuite/g++.dg/cpp1z/utf8.C
new file mode 100644
index 0000000..52816f8
--- /dev/null
+++ b/gcc/testsuite/g++.dg/cpp1z/utf8.C
@@ -0,0 +1,15 @@
+// { dg-do compile }
+// { dg-options "-std=c++1z" }
+
+#include <cassert>
+#include <experimental/type_traits>
+
+auto c = 'c';
+auto u8c = u8'c';
+
+static_assert(std::experimental::is_same_v<decltype(u8c), decltype(c)>, "");
+
+auto u8s = u8"c";
+auto x = u8s[0];
+
+static_assert(std::experimental::is_same_v<decltype(u8c), decltype(x)>, "");