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.


git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@134438 138bc75d-0d04-0410-961f-82ee72b054a4

1 files changed, 23 insertions, 14 deletions

diff --git a/libcpp/lex.c b/libcpp/lex.c
index 2eaf6105922..772a8701654 100644
--- a/libcpp/lex.c
+++ b/libcpp/lex.c
@@ -39,10 +39,10 @@ struct token_spelling
 };
 
 static const unsigned char *const digraph_spellings[] =
-{ U"%:", U"%:%:", U"<:", U":>", U"<%", U"%>" };
+{ UC"%:", UC"%:%:", UC"<:", UC":>", UC"<%", UC"%>" };
 
-#define OP(e, s) { SPELL_OPERATOR, U s  },
-#define TK(e, s) { SPELL_ ## s,    U #e },
+#define OP(e, s) { SPELL_OPERATOR, UC s  },
+#define TK(e, s) { SPELL_ ## s,    UC #e },
 static const struct token_spelling token_spellings[N_TTYPES] = { TTYPE_TABLE };
 #undef OP
 #undef TK
@@ -611,8 +611,8 @@ create_literal (cpp_reader *pfile, cpp_token *token, const uchar *base,
 
 /* Lexes a string, character constant, or angle-bracketed header file
    name.  The stored string contains the spelling, including opening
-   quote and leading any leading 'L'.  It returns the type of the
-   literal, or CPP_OTHER if it was not properly terminated.
+   quote and leading any leading 'L', 'u' or 'U'.  It returns the type
+   of the literal, or CPP_OTHER if it was not properly terminated.
 
    The spelling is NUL-terminated, but it is not guaranteed that this
    is the first NUL since embedded NULs are preserved.  */
@@ -626,12 +626,16 @@ lex_string (cpp_reader *pfile, cpp_token *token, const uchar *base)
 
   cur = base;
   terminator = *cur++;
-  if (terminator == 'L')
+  if (terminator == 'L' || terminator == 'u' || terminator == 'U')
     terminator = *cur++;
   if (terminator == '\"')
-    type = *base == 'L' ? CPP_WSTRING: CPP_STRING;
+    type = (*base == 'L' ? CPP_WSTRING :
+	    *base == 'U' ? CPP_STRING32 :
+	    *base == 'u' ? CPP_STRING16 : CPP_STRING);
   else if (terminator == '\'')
-    type = *base == 'L' ? CPP_WCHAR: CPP_CHAR;
+    type = (*base == 'L' ? CPP_WCHAR :
+	    *base == 'U' ? CPP_CHAR32 :
+	    *base == 'u' ? CPP_CHAR16 : CPP_CHAR);
   else
     terminator = '>', type = CPP_HEADER_NAME;
 
@@ -965,11 +969,16 @@ _cpp_lex_direct (cpp_reader *pfile)
       }
 
     case 'L':
-      /* 'L' may introduce wide characters or strings.  */
-      if (*buffer->cur == '\'' || *buffer->cur == '"')
+    case 'u':
+    case 'U':
+      /* 'L', 'u' or 'U' may introduce wide characters or strings.  */
+      if (c == 'L' || CPP_OPTION (pfile, uliterals))
 	{
-	  lex_string (pfile, result, buffer->cur - 1);
-	  break;
+	  if (*buffer->cur == '\'' || *buffer->cur == '"')
+	    {
+	      lex_string (pfile, result, buffer->cur - 1);
+	      break;
+	    }
 	}
       /* Fall through.  */
 
@@ -977,12 +986,12 @@ _cpp_lex_direct (cpp_reader *pfile)
     case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
     case 'g': case 'h': case 'i': case 'j': case 'k': case 'l':
     case 'm': case 'n': case 'o': case 'p': case 'q': case 'r':
-    case 's': case 't': case 'u': case 'v': case 'w': case 'x':
+    case 's': case 't':           case 'v': case 'w': case 'x':
     case 'y': case 'z':
     case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
     case 'G': case 'H': case 'I': case 'J': case 'K':
     case 'M': case 'N': case 'O': case 'P': case 'Q': case 'R':
-    case 'S': case 'T': case 'U': case 'V': case 'W': case 'X':
+    case 'S': case 'T':           case 'V': case 'W': case 'X':
     case 'Y': case 'Z':
       result->type = CPP_NAME;
       {