* charset.c (cpp_init_iconv): Initialize utf8_cset_desc.

	(_cpp_destroy_iconv): Destroy utf8_cset_desc, char16_cset_desc
	and char32_cset_desc.
	(converter_for_type): Handle CPP_UTF8STRING.
	(cpp_interpret_string): Handle CPP_UTF8STRING and raw-strings.
	* directives.c (get__Pragma_string): Handle CPP_UTF8STRING.
	(parse_include): Reject raw strings.
	* include/cpplib.h (CPP_UTF8STRING): New token type.
	* internal.h (struct cpp_reader): Add utf8_cset_desc field.
	* lex.c (lex_raw_string): New function.
	(lex_string): Handle u8 string literals, call lex_raw_string
	for raw string literals.
	(_cpp_lex_direct): Call lex_string even for u8" and {,u,U,L,u8}R"
	sequences.
	* macro.c (stringify_arg): Handle CPP_UTF8STRING.

	* c-common.c (c_parse_error): Handle CPP_UTF8STRING.
	* c-lex.c (c_lex_with_flags): Likewise.  Test C_LEX_STRING_NO_JOIN
	instead of C_LEX_RAW_STRINGS.
	(lex_string): Handle CPP_UTF8STRING.
	* c-parser.c (c_parser_postfix_expression): Likewise.
	* c-pragma.h (C_LEX_RAW_STRINGS): Rename to ...
	(C_LEX_STRING_NO_JOIN): ... this.

	* parser.c (cp_lexer_print_token, cp_parser_is_string_literal,
	cp_parser_string_literal, cp_parser_primary_expression): Likewise.
	(cp_lexer_get_preprocessor_token): Use C_LEX_STRING_JOIN instead
	of C_LEX_RAW_STRINGS.

	* gcc.dg/raw-string-1.c: New test.
	* gcc.dg/raw-string-2.c: New test.
	* gcc.dg/raw-string-3.c: New test.
	* gcc.dg/raw-string-4.c: New test.
	* gcc.dg/raw-string-5.c: New test.
	* gcc.dg/raw-string-6.c: New test.
	* gcc.dg/raw-string-7.c: New test.
	* gcc.dg/utf8-1.c: New test.
	* gcc.dg/utf8-2.c: New test.
	* gcc.dg/utf-badconcat2.c: New test.
	* gcc.dg/utf-dflt2.c: New test.
	* gcc.dg/cpp/include6.c: New test.
	* g++.dg/ext/raw-string-1.C: New test.
	* g++.dg/ext/raw-string-2.C: New test.
	* g++.dg/ext/raw-string-3.C: New test.
	* g++.dg/ext/raw-string-4.C: New test.
	* g++.dg/ext/raw-string-5.C: New test.
	* g++.dg/ext/raw-string-6.C: New test.
	* g++.dg/ext/raw-string-7.C: New test.
	* g++.dg/ext/utf8-1.C: New test.
	* g++.dg/ext/utf8-2.C: New test.
	* g++.dg/ext/utf-badconcat2.C: New test.
	* g++.dg/ext/utf-dflt2.C: New test.


git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@152995 138bc75d-0d04-0410-961f-82ee72b054a4

1 files changed, 26 insertions, 0 deletions

diff --git a/gcc/testsuite/gcc.dg/utf8-2.c b/gcc/testsuite/gcc.dg/utf8-2.c
new file mode 100644
index 00000000000..9c0442fde3f
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/utf8-2.c
@@ -0,0 +1,26 @@
+/* { dg-do compile } */
+/* { dg-options "-std=gnu99" } */
+
+#include <wchar.h>
+
+typedef __CHAR16_TYPE__	char16_t;
+typedef __CHAR32_TYPE__ char32_t;
+
+const char	s0[]	= u8"ab";
+const char16_t	s1[]	= u8"ab";	/* { dg-error "from non-wide" } */
+const char32_t  s2[]    = u8"ab";	/* { dg-error "from non-wide" } */
+const wchar_t   s3[]    = u8"ab";	/* { dg-error "from non-wide" } */
+
+const char      t0[0]   = u8"ab";	/* { dg-warning "chars is too long" } */
+const char      t1[1]   = u8"ab";	/* { dg-warning "chars is too long" } */
+const char      t2[2]   = u8"ab";
+const char      t3[3]   = u8"ab";
+const char      t4[4]   = u8"ab";
+
+const char      u0[0]   = u8"\u2160.";	/* { dg-warning "chars is too long" } */
+const char      u1[1]   = u8"\u2160.";	/* { dg-warning "chars is too long" } */
+const char      u2[2]   = u8"\u2160.";	/* { dg-warning "chars is too long" } */
+const char      u3[3]   = u8"\u2160.";	/* { dg-warning "chars is too long" } */
+const char      u4[4]   = u8"\u2160.";
+const char      u5[5]   = u8"\u2160.";
+const char      u6[6]   = u8"\u2160.";