charset.c (cpp_init_iconv): Initialize utf8_cset_desc.

	* 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.

From-SVN: r152995

1 files changed, 45 insertions, 0 deletions

diff --git a/gcc/testsuite/gcc.dg/utf8-1.c b/gcc/testsuite/gcc.dg/utf8-1.c
new file mode 100644
index 0000000..e287e06
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/utf8-1.c
@@ -0,0 +1,45 @@
+/* { dg-do run } */
+/* { dg-require-iconv "ISO-8859-2" } */
+/* { dg-options "-std=gnu99 -fexec-charset=ISO-8859-2" } */
+
+const char *str1 = "h\u00e1\U0000010Dky ";
+const char *str2 = "\u010d\u00E1rky\n";
+const char *str3 = u8"h\u00e1\U0000010Dky ";
+const char *str4 = u8"\u010d\u00E1rky\n";
+const char *str5 = "h\u00e1\U0000010Dky " "\u010d\u00E1rky\n";
+const char *str6 = u8"h\u00e1\U0000010Dky " "\u010d\u00E1rky\n";
+const char *str7 = "h\u00e1\U0000010Dky " u8"\u010d\u00E1rky\n";
+#define u8
+const char *str8 = u8"h\u00e1\U0000010Dky " u8"\u010d\u00E1rky\n";
+
+const char latin2_1[] = "\x68\xe1\xe8\x6b\x79\x20";
+const char latin2_2[] = "\xe8\xe1\x72\x6b\x79\n";
+const char utf8_1[] = "\x68\xc3\xa1\xc4\x8d\x6b\x79\x20";
+const char utf8_2[] = "\xc4\x8d\xc3\xa1\x72\x6b\x79\n";
+
+int
+main (void)
+{
+  if (__builtin_strcmp (str1, latin2_1) != 0
+      || __builtin_strcmp (str2, latin2_2) != 0
+      || __builtin_strcmp (str3, utf8_1) != 0
+      || __builtin_strcmp (str4, utf8_2) != 0
+      || __builtin_strncmp (str5, latin2_1, sizeof (latin2_1) - 1) != 0
+      || __builtin_strcmp (str5 + sizeof (latin2_1) - 1, latin2_2) != 0
+      || __builtin_strncmp (str6, utf8_1, sizeof (utf8_1) - 1) != 0
+      || __builtin_strcmp (str6 + sizeof (utf8_1) - 1, utf8_2) != 0
+      || __builtin_strncmp (str7, utf8_1, sizeof (utf8_1) - 1) != 0
+      || __builtin_strcmp (str7 + sizeof (utf8_1) - 1, utf8_2) != 0
+      || __builtin_strncmp (str8, utf8_1, sizeof (utf8_1) - 1) != 0
+      || __builtin_strcmp (str8 + sizeof (utf8_1) - 1, utf8_2) != 0)
+    __builtin_abort ();
+  if (sizeof ("a" u8"b"[0]) != 1
+      || sizeof (u8"a" "b"[0]) != 1
+      || sizeof (u8"a" u8"b"[0]) != 1
+      || sizeof ("a" "\u010d") != 3
+      || sizeof ("a" u8"\u010d") != 4
+      || sizeof (u8"a" "\u010d") != 4
+      || sizeof (u8"a" "\u010d") != 4)
+    __builtin_abort ();
+  return 0;
+}