diff options
38 files changed, 1244 insertions, 28 deletions
diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 83b507adb28..548cc0b36ed 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,13 @@ +2009-10-19 Jakub Jelinek <jakub@redhat.com> + + * 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. + 2009-10-19 Anatoly Sokolov <aesok@post.ru> * config/cris/cris.c (cris_function_value, cris_libcall_value, diff --git a/gcc/c-common.c b/gcc/c-common.c index fb2a84ebbf4..16e17b39d1d 100644 --- a/gcc/c-common.c +++ b/gcc/c-common.c @@ -8181,7 +8181,8 @@ c_parse_error (const char *gmsgid, enum cpp_ttype token_type, else if (token_type == CPP_STRING || token_type == CPP_WSTRING || token_type == CPP_STRING16 - || token_type == CPP_STRING32) + || token_type == CPP_STRING32 + || token_type == CPP_UTF8STRING) message = catenate_messages (gmsgid, " before string constant"); else if (token_type == CPP_NUMBER) message = catenate_messages (gmsgid, " before numeric constant"); diff --git a/gcc/c-lex.c b/gcc/c-lex.c index 0c6cdab9dff..fd3df8c0a48 100644 --- a/gcc/c-lex.c +++ b/gcc/c-lex.c @@ -365,6 +365,7 @@ c_lex_with_flags (tree *value, location_t *loc, unsigned char *cpp_flags, case CPP_WSTRING: case CPP_STRING16: case CPP_STRING32: + case CPP_UTF8STRING: type = lex_string (tok, value, true, true); break; @@ -423,7 +424,8 @@ c_lex_with_flags (tree *value, location_t *loc, unsigned char *cpp_flags, case CPP_WSTRING: case CPP_STRING16: case CPP_STRING32: - if ((lex_flags & C_LEX_RAW_STRINGS) == 0) + case CPP_UTF8STRING: + if ((lex_flags & C_LEX_STRING_NO_JOIN) == 0) { type = lex_string (tok, value, false, (lex_flags & C_LEX_STRING_NO_TRANSLATE) == 0); @@ -871,12 +873,13 @@ interpret_fixed (const cpp_token *token, unsigned int flags) return value; } -/* Convert a series of STRING, WSTRING, STRING16 and/or STRING32 tokens - into a tree, performing string constant concatenation. TOK is the - first of these. VALP is the location to write the string into. - OBJC_STRING indicates whether an '@' token preceded the incoming token. +/* Convert a series of STRING, WSTRING, STRING16, STRING32 and/or + UTF8STRING tokens into a tree, performing string constant + concatenation. TOK is the first of these. VALP is the location + to write the string into. OBJC_STRING indicates whether an '@' token + preceded the incoming token. Returns the CPP token type of the result (CPP_STRING, CPP_WSTRING, - CPP_STRING32, CPP_STRING16, or CPP_OBJC_STRING). + CPP_STRING32, CPP_STRING16, CPP_UTF8STRING, or CPP_OBJC_STRING). This is unfortunately more work than it should be. If any of the strings in the series has an L prefix, the result is a wide string @@ -921,6 +924,7 @@ lex_string (const cpp_token *tok, tree *valp, bool objc_string, bool translate) case CPP_WSTRING: case CPP_STRING16: case CPP_STRING32: + case CPP_UTF8STRING: if (type != tok->type) { if (type == CPP_STRING) @@ -966,6 +970,7 @@ lex_string (const cpp_token *tok, tree *valp, bool objc_string, bool translate) { default: case CPP_STRING: + case CPP_UTF8STRING: value = build_string (1, ""); break; case CPP_STRING16: @@ -991,6 +996,7 @@ lex_string (const cpp_token *tok, tree *valp, bool objc_string, bool translate) { default: case CPP_STRING: + case CPP_UTF8STRING: TREE_TYPE (value) = char_array_type_node; break; case CPP_STRING16: diff --git a/gcc/c-parser.c b/gcc/c-parser.c index 3f6e949fe8e..767d97fbe58 100644 --- a/gcc/c-parser.c +++ b/gcc/c-parser.c @@ -5349,6 +5349,7 @@ c_parser_postfix_expression (c_parser *parser) case CPP_STRING16: case CPP_STRING32: case CPP_WSTRING: + case CPP_UTF8STRING: expr.value = c_parser_peek_token (parser)->value; expr.original_code = STRING_CST; c_parser_consume_token (parser); diff --git a/gcc/c-pragma.h b/gcc/c-pragma.h index 188afb8dbaa..be085ee1115 100644 --- a/gcc/c-pragma.h +++ b/gcc/c-pragma.h @@ -118,9 +118,9 @@ extern enum cpp_ttype pragma_lex (tree *); so that 0 means to translate and join strings. */ #define C_LEX_STRING_NO_TRANSLATE 1 /* Do not lex strings into execution character set. */ -#define C_LEX_RAW_STRINGS 2 /* Return raw strings -- no - concatenation, no - translation. */ +#define C_LEX_STRING_NO_JOIN 2 /* Do not concatenate strings + nor translate them into execution + character set. */ /* This is not actually available to pragma parsers. It's merely a convenient location to declare this function for c-lex, after diff --git a/gcc/cp/ChangeLog b/gcc/cp/ChangeLog index 279ba9e6419..a068a432b1f 100644 --- a/gcc/cp/ChangeLog +++ b/gcc/cp/ChangeLog @@ -1,3 +1,10 @@ +2009-10-19 Jakub Jelinek <jakub@redhat.com> + + * 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. + 2009-10-15 Jason Merrill <jason@redhat.com> PR c++/38888 diff --git a/gcc/cp/parser.c b/gcc/cp/parser.c index b9b53e5ebaf..7fd995f9e83 100644 --- a/gcc/cp/parser.c +++ b/gcc/cp/parser.c @@ -402,7 +402,7 @@ cp_lexer_get_preprocessor_token (cp_lexer *lexer, cp_token *token) /* Get a new token from the preprocessor. */ token->type = c_lex_with_flags (&token->u.value, &token->location, &token->flags, - lexer == NULL ? 0 : C_LEX_RAW_STRINGS); + lexer == NULL ? 0 : C_LEX_STRING_NO_JOIN); token->keyword = RID_MAX; token->pragma_kind = PRAGMA_NONE; @@ -792,6 +792,7 @@ cp_lexer_print_token (FILE * stream, cp_token *token) case CPP_STRING16: case CPP_STRING32: case CPP_WSTRING: + case CPP_UTF8STRING: fprintf (stream, " \"%s\"", TREE_STRING_POINTER (token->u.value)); break; @@ -2065,7 +2066,8 @@ cp_parser_is_string_literal (cp_token* token) return (token->type == CPP_STRING || token->type == CPP_STRING16 || token->type == CPP_STRING32 || - token->type == CPP_WSTRING); + token->type == CPP_WSTRING || + token->type == CPP_UTF8STRING); } /* Returns nonzero if TOKEN is the indicated KEYWORD. */ @@ -3004,6 +3006,7 @@ cp_parser_string_literal (cp_parser *parser, bool translate, bool wide_ok) { default: case CPP_STRING: + case CPP_UTF8STRING: TREE_TYPE (value) = char_array_type_node; break; case CPP_STRING16: @@ -3233,6 +3236,7 @@ cp_parser_primary_expression (cp_parser *parser, case CPP_STRING16: case CPP_STRING32: case CPP_WSTRING: + case CPP_UTF8STRING: /* ??? Should wide strings be allowed when parser->translate_strings_p is false (i.e. in attributes)? If not, we can kill the third argument to cp_parser_string_literal. */ diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog index 8fce05cd9ed..c91c4d427c3 100644 --- a/gcc/testsuite/ChangeLog +++ b/gcc/testsuite/ChangeLog @@ -1,5 +1,29 @@ 2009-10-19 Jakub Jelinek <jakub@redhat.com> + * 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. + * gcc.dg/cleanup-13.c: New test. 2009-10-19 Janus Weil <janus@gcc.gnu.org> diff --git a/gcc/testsuite/g++.dg/ext/raw-string-1.C b/gcc/testsuite/g++.dg/ext/raw-string-1.C new file mode 100644 index 00000000000..0e8abf8b498 --- /dev/null +++ b/gcc/testsuite/g++.dg/ext/raw-string-1.C @@ -0,0 +1,96 @@ +// { dg-do run } +// { dg-options "-std=c++0x" } + +const char s0[] = R"[a\ +\u010d\U0000010D\\\'\"\?\a\b\f\n\r\t\v\0\00\000\xa\xabb +c]"; +const char s1[] = "a\U0000010d\u010d\\\\\\'\\\"\\?\\a\\b\\f\\n\\r\\t\\v\\0\\00\\000\\xa\\xabb\nc"; +const char s2[] = R"*|*[a\ +b +c]" +c]*|" +c]*|*"; +const char s3[] = "ab\nc]\"\nc]*|\"\nc"; + +const char t0[] = u8R"[a\ +\u010d\U0000010D\\\'\"\?\a\b\f\n\r\t\v\0\00\000\xa\xabb +c]"; +const char t1[] = u8"a\U0000010d\u010d\\\\\\'\\\"\\?\\a\\b\\f\\n\\r\\t\\v\\0\\00\\000\\xa\\xabb\nc"; +const char t2[] = u8R"*|*[a\ +b +c]" +c]*|" +c]*|*"; +const char t3[] = u8"ab\nc]\"\nc]*|\"\nc"; + +const char16_t u0[] = uR"[a\ +\u010d\U0000010D\\\'\"\?\a\b\f\n\r\t\v\0\00\000\xa\xabb +c]"; +const char16_t u1[] = u"a\U0000010d\u010d\\\\\\'\\\"\\?\\a\\b\\f\\n\\r\\t\\v\\0\\00\\000\\xa\\xabb\nc"; +const char16_t u2[] = uR"*|*[a\ +b +c]" +c]*|" +c]*|*"; +const char16_t u3[] = u"ab\nc]\"\nc]*|\"\nc"; + +const char32_t U0[] = UR"[a\ +\u010d\U0000010D\\\'\"\?\a\b\f\n\r\t\v\0\00\000\xa\xabb +c]"; +const char32_t U1[] = U"a\U0000010d\u010d\\\\\\'\\\"\\?\\a\\b\\f\\n\\r\\t\\v\\0\\00\\000\\xa\\xabb\nc"; +const char32_t U2[] = UR"*|*[a\ +b +c]" +c]*|" +c]*|*"; +const char32_t U3[] = U"ab\nc]\"\nc]*|\"\nc"; + +const wchar_t L0[] = LR"[a\ +\u010d\U0000010D\\\'\"\?\a\b\f\n\r\t\v\0\00\000\xa\xabb +c]"; +const wchar_t L1[] = L"a\U0000010d\u010d\\\\\\'\\\"\\?\\a\\b\\f\\n\\r\\t\\v\\0\\00\\000\\xa\\xabb\nc"; +const wchar_t L2[] = LR"*|*[a\ +b +c]" +c]*|" +c]*|*"; +const wchar_t L3[] = L"ab\nc]\"\nc]*|\"\nc"; + +int +main (void) +{ + if (sizeof (s0) != sizeof (s1) + || __builtin_memcmp (s0, s1, sizeof (s0)) != 0) + __builtin_abort (); + if (sizeof (s2) != sizeof (s3) + || __builtin_memcmp (s2, s3, sizeof (s2)) != 0) + __builtin_abort (); + if (sizeof (t0) != sizeof (t1) + || __builtin_memcmp (t0, t1, sizeof (t0)) != 0) + __builtin_abort (); + if (sizeof (t2) != sizeof (t3) + || __builtin_memcmp (t2, t3, sizeof (t2)) != 0) + __builtin_abort (); + if (sizeof (u0) != sizeof (u1) + || __builtin_memcmp (u0, u1, sizeof (u0)) != 0) + __builtin_abort (); + if (sizeof (u2) != sizeof (u3) + || __builtin_memcmp (u2, u3, sizeof (u2)) != 0) + __builtin_abort (); + if (sizeof (U0) != sizeof (U1) + || __builtin_memcmp (U0, U1, sizeof (U0)) != 0) + __builtin_abort (); + if (sizeof (U2) != sizeof (U3) + || __builtin_memcmp (U2, U3, sizeof (U2)) != 0) + __builtin_abort (); + if (sizeof (L0) != sizeof (L1) + || __builtin_memcmp (L0, L1, sizeof (L0)) != 0) + __builtin_abort (); + if (sizeof (L2) != sizeof (L3) + || __builtin_memcmp (L2, L3, sizeof (L2)) != 0) + __builtin_abort (); + if (sizeof (R"*[]*") != 1 + || __builtin_memcmp (R"*[]*", "", 1) != 0) + __builtin_abort (); + return 0; +} diff --git a/gcc/testsuite/g++.dg/ext/raw-string-2.C b/gcc/testsuite/g++.dg/ext/raw-string-2.C new file mode 100644 index 00000000000..c7eb602afec --- /dev/null +++ b/gcc/testsuite/g++.dg/ext/raw-string-2.C @@ -0,0 +1,104 @@ +// { dg-do run } +// { dg-options "-std=c++0x" } + +#define R +#define u +#define uR +#define U +#define UR +#define u8 +#define u8R +#define L +#define LR + +const char s00[] = R"[a]" "[b]"; +const char s01[] = "[a]" R"*[b]*"; +const char s02[] = R"[a]" R"[b]"; +const char s03[] = R"-[a]-" u8"[b]"; +const char s04[] = "[a]" u8R"MNOPQRSTUVWXYZ[b]MNOPQRSTUVWXYZ"; +const char s05[] = R"[a]" u8R"wxyzABCDEFGHIJKL[b]wxyzABCDEFGHIJKL"; +const char s06[] = u8R";([a];(" "[b]"; +const char s07[] = u8"[a]" R"[b]"; +const char s08[] = u8R"[a]" R"_{}#()<>%:;.?*+-[b]_{}#()<>%:;.?*+-"; +const char s09[] = u8R"/^&|~!=,"'\[a]/^&|~!=,"'\" u8"[b]"; +const char s10[] = u8"[a]" u8R"0123456789abcdef[b]0123456789abcdef"; +const char s11[] = u8R"ghijklmnopqrstuv[a]ghijklmnopqrstuv" u8R"w[b]w"; + +const char16_t u03[] = R"-[a]-" u"[b]"; +const char16_t u04[] = "[a]" uR"MNOPQRSTUVWXYZ[b]MNOPQRSTUVWXYZ"; +const char16_t u05[] = R"[a]" uR"wxyzABCDEFGHIJKL[b]wxyzABCDEFGHIJKL"; +const char16_t u06[] = uR";([a];(" "[b]"; +const char16_t u07[] = u"[a]" R"[b]"; +const char16_t u08[] = uR"[a]" R"_{}#()<>%:;.?*+-[b]_{}#()<>%:;.?*+-"; +const char16_t u09[] = uR"/^&|~!=,"'\[a]/^&|~!=,"'\" u"[b]"; +const char16_t u10[] = u"[a]" uR"0123456789abcdef[b]0123456789abcdef"; +const char16_t u11[] = uR"ghijklmnopqrstuv[a]ghijklmnopqrstuv" uR"w[b]w"; + +const char32_t U03[] = R"-[a]-" U"[b]"; +const char32_t U04[] = "[a]" UR"MNOPQRSTUVWXYZ[b]MNOPQRSTUVWXYZ"; +const char32_t U05[] = R"[a]" UR"wxyzABCDEFGHIJKL[b]wxyzABCDEFGHIJKL"; +const char32_t U06[] = UR";([a];(" "[b]"; +const char32_t U07[] = U"[a]" R"[b]"; +const char32_t U08[] = UR"[a]" R"_{}#()<>%:;.?*+-[b]_{}#()<>%:;.?*+-"; +const char32_t U09[] = UR"/^&|~!=,"'\[a]/^&|~!=,"'\" U"[b]"; +const char32_t U10[] = U"[a]" UR"0123456789abcdef[b]0123456789abcdef"; +const char32_t U11[] = UR"ghijklmnopqrstuv[a]ghijklmnopqrstuv" UR"w[b]w"; + +const wchar_t L03[] = R"-[a]-" L"[b]"; +const wchar_t L04[] = "[a]" LR"MNOPQRSTUVWXYZ[b]MNOPQRSTUVWXYZ"; +const wchar_t L05[] = R"[a]" LR"wxyzABCDEFGHIJKL[b]wxyzABCDEFGHIJKL"; +const wchar_t L06[] = LR";([a];(" "[b]"; +const wchar_t L07[] = L"[a]" R"[b]"; +const wchar_t L08[] = LR"[a]" R"_{}#()<>%:;.?*+-[b]_{}#()<>%:;.?*+-"; +const wchar_t L09[] = LR"/^&|~!=,"'\[a]/^&|~!=,"'\" L"[b]"; +const wchar_t L10[] = L"[a]" LR"0123456789abcdef[b]0123456789abcdef"; +const wchar_t L11[] = LR"ghijklmnopqrstuv[a]ghijklmnopqrstuv" LR"w[b]w"; + +int +main (void) +{ +#define TEST(str, val) \ + if (sizeof (str) != sizeof (val) \ + || __builtin_memcmp (str, val, sizeof (str)) != 0) \ + __builtin_abort () + TEST (s00, "a[b]"); + TEST (s01, "[a]b"); + TEST (s02, "ab"); + TEST (s03, "a[b]"); + TEST (s04, "[a]b"); + TEST (s05, "ab"); + TEST (s06, "a[b]"); + TEST (s07, "[a]b"); + TEST (s08, "ab"); + TEST (s09, "a[b]"); + TEST (s10, "[a]b"); + TEST (s11, "ab"); + TEST (u03, u"a[b]"); + TEST (u04, u"[a]b"); + TEST (u05, u"ab"); + TEST (u06, u"a[b]"); + TEST (u07, u"[a]b"); + TEST (u08, u"ab"); + TEST (u09, u"a[b]"); + TEST (u10, u"[a]b"); + TEST (u11, u"ab"); + TEST (U03, U"a[b]"); + TEST (U04, U"[a]b"); + TEST (U05, U"ab"); + TEST (U06, U"a[b]"); + TEST (U07, U"[a]b"); + TEST (U08, U"ab"); + TEST (U09, U"a[b]"); + TEST (U10, U"[a]b"); + TEST (U11, U"ab"); + TEST (L03, L"a[b]"); + TEST (L04, L"[a]b"); + TEST (L05, L"ab"); + TEST (L06, L"a[b]"); + TEST (L07, L"[a]b"); + TEST (L08, L"ab"); + TEST (L09, L"a[b]"); + TEST (L10, L"[a]b"); + TEST (L11, L"ab"); + return 0; +} diff --git a/gcc/testsuite/g++.dg/ext/raw-string-3.C b/gcc/testsuite/g++.dg/ext/raw-string-3.C new file mode 100644 index 00000000000..46c48620905 --- /dev/null +++ b/gcc/testsuite/g++.dg/ext/raw-string-3.C @@ -0,0 +1,58 @@ +// If c++98, the {,u,u8,U,L}R prefix should be parsed as separate +// token. +// { dg-do compile } +// { dg-options "-std=c++98" } + +const void *s0 = R"[a]"; // { dg-error "was not declared" } + // { dg-error "expected ',' or ';'" "" { target *-*-* } 6 } +const void *s1 = uR"[a]"; // { dg-error "was not declared" } + // { dg-error "expected ',' or ';'" "" { target *-*-* } 8 } +const void *s2 = UR"[a]"; // { dg-error "was not declared" } + // { dg-error "expected ',' or ';'" "" { target *-*-* } 10 } +const void *s3 = u8R"[a]"; // { dg-error "was not declared" } + // { dg-error "expected ',' or ';'" "" { target *-*-* } 12 } +const void *s4 = LR"[a]"; // { dg-error "was not declared" } + // { dg-error "expected ',' or ';'" "" { target *-*-* } 14 } + +const int i0 = R'a'; // { dg-error "was not declared" } + // { dg-error "expected ',' or ';'" "" { target *-*-* } 17 } +const int i1 = uR'a'; // { dg-error "was not declared" } + // { dg-error "expected ',' or ';'" "" { target *-*-* } 19 } +const int i2 = UR'a'; // { dg-error "was not declared" } + // { dg-error "expected ',' or ';'" "" { target *-*-* } 21 } +const int i3 = u8R'a'; // { dg-error "was not declared" } + // { dg-error "expected ',' or ';'" "" { target *-*-* } 23 } +const int i4 = LR'a'; // { dg-error "was not declared" } + // { dg-error "expected ',' or ';'" "" { target *-*-* } 25 } + +#define R "a" +#define uR "b" +#define UR "c" +#define u8R "d" +#define LR "e" + +const void *s5 = R"[a]"; +const void *s6 = uR"[a]"; +const void *s7 = UR"[a]"; +const void *s8 = u8R"[a]"; +const void *s9 = LR"[a]"; + +#undef R +#undef uR +#undef UR +#undef u8R +#undef LR + +#define R 1 + +#define uR 2 + +#define UR 3 + +#define u8R 4 + +#define LR 5 + + +const int i5 = R'a'; +const int i6 = uR'a'; +const int i7 = UR'a'; +const int i8 = u8R'a'; +const int i9 = LR'a'; + +int main () {} diff --git a/gcc/testsuite/g++.dg/ext/raw-string-4.C b/gcc/testsuite/g++.dg/ext/raw-string-4.C new file mode 100644 index 00000000000..03179befac8 --- /dev/null +++ b/gcc/testsuite/g++.dg/ext/raw-string-4.C @@ -0,0 +1,28 @@ +// R is not applicable for character literals. +// { dg-do compile } +// { dg-options "-std=c++0x" } + +const int i0 = R'a'; // { dg-error "was not declared" } + // { dg-error "expected ',' or ';'" "" { target *-*-* } 5 } +const int i1 = uR'a'; // { dg-error "was not declared" } + // { dg-error "expected ',' or ';'" "" { target *-*-* } 7 } +const int i2 = UR'a'; // { dg-error "was not declared" } + // { dg-error "expected ',' or ';'" "" { target *-*-* } 9 } +const int i3 = u8R'a'; // { dg-error "was not declared" } + // { dg-error "expected ',' or ';'" "" { target *-*-* } 11 } +const int i4 = LR'a'; // { dg-error "was not declared" } + // { dg-error "expected ',' or ';'" "" { target *-*-* } 13 } + +#define R 1 + +#define uR 2 + +#define UR 3 + +#define u8R 4 + +#define LR 5 + + +const int i5 = R'a'; +const int i6 = uR'a'; +const int i7 = UR'a'; +const int i8 = u8R'a'; +const int i9 = LR'a'; + +int main () {} diff --git a/gcc/testsuite/g++.dg/ext/raw-string-5.C b/gcc/testsuite/g++.dg/ext/raw-string-5.C new file mode 100644 index 00000000000..b815eb23b16 --- /dev/null +++ b/gcc/testsuite/g++.dg/ext/raw-string-5.C @@ -0,0 +1,23 @@ +// { dg-do compile } +// { dg-options "-std=c++0x" } + +const void *s0 = R"0123456789abcdefg[]0123456789abcdefg"; + // { dg-error "raw string delimiter longer" "" { target *-*-* } 4 } + // { dg-error "stray" "" { target *-*-* } 4 } +const void *s1 = R" [] "; + // { dg-error "invalid character" "" { target *-*-* } 7 } + // { dg-error "stray" "" { target *-*-* } 7 } +const void *s2 = R" [] "; + // { dg-error "invalid character" "" { target *-*-* } 10 } + // { dg-error "stray" "" { target *-*-* } 10 } +const void *s3 = R"][]]"; + // { dg-error "invalid character" "" { target *-*-* } 13 } + // { dg-error "stray" "" { target *-*-* } 13 } +const void *s4 = R"@[]@"; + // { dg-error "invalid character" "" { target *-*-* } 16 } + // { dg-error "stray" "" { target *-*-* } 16 } +const void *s5 = R"$[]$"; + // { dg-error "invalid character" "" { target *-*-* } 19 } + // { dg-error "stray" "" { target *-*-* } 19 } + +int main () {} diff --git a/gcc/testsuite/g++.dg/ext/raw-string-6.C b/gcc/testsuite/g++.dg/ext/raw-string-6.C new file mode 100644 index 00000000000..a97d95d5693 --- /dev/null +++ b/gcc/testsuite/g++.dg/ext/raw-string-6.C @@ -0,0 +1,5 @@ +// { dg-do compile } +// { dg-options "-std=c++0x" } + +const void *s0 = R"ouch[]ouCh"; // { dg-error "at end of input" } + // { dg-error "unterminated raw string" "" { target *-*-* } 4 } diff --git a/gcc/testsuite/g++.dg/ext/raw-string-7.C b/gcc/testsuite/g++.dg/ext/raw-string-7.C new file mode 100644 index 00000000000..0f479193433 --- /dev/null +++ b/gcc/testsuite/g++.dg/ext/raw-string-7.C @@ -0,0 +1,23 @@ +// The trailing whitespace after \ and before newline extension +// breaks full compliance for raw strings. +// { dg-do run { xfail *-*-* } } +// { dg-options "-std=c++0x" } + +// Note, there is a single space after \ on the following line. +const char *s0 = R"[\ +]"; +// { dg-bogus "backslash and newline separated by space" "" { xfail *-*-* } 7 } + +// Note, there is a single tab after \ on the following line. +const char *s1 = R"[\ +]"; +// { dg-bogus "backslash and newline separated by space" "" { xfail *-*-* } 12 } + +int +main (void) +{ + if (__builtin_strcmp (s0, "\\ \n") != 0 + || __builtin_strcmp (s1, "\\\t\n") != 0) + __builtin_abort (); + return 0; +} diff --git a/gcc/testsuite/g++.dg/ext/utf-badconcat2.C b/gcc/testsuite/g++.dg/ext/utf-badconcat2.C new file mode 100644 index 00000000000..499b323fc19 --- /dev/null +++ b/gcc/testsuite/g++.dg/ext/utf-badconcat2.C @@ -0,0 +1,15 @@ +// Test unsupported concatenation of UTF-8 string literals. +// { dg-do compile } +// { dg-options "-std=c++0x" } + +const void *s0 = u8"a" "b"; +const void *s1 = "a" u8"b"; +const void *s2 = u8"a" u8"b"; +const void *s3 = u8"a" u"b"; // { dg-error "non-standard concatenation" } +const void *s4 = u"a" u8"b"; // { dg-error "non-standard concatenation" } +const void *s5 = u8"a" U"b"; // { dg-error "non-standard concatenation" } +const void *s6 = U"a" u8"b"; // { dg-error "non-standard concatenation" } +const void *s7 = u8"a" L"b"; // { dg-error "non-standard concatenation" } +const void *s8 = L"a" u8"b"; // { dg-error "non-standard concatenation" } + +int main () {} diff --git a/gcc/testsuite/g++.dg/ext/utf-dflt2.C b/gcc/testsuite/g++.dg/ext/utf-dflt2.C new file mode 100644 index 00000000000..fd2222f672e --- /dev/null +++ b/gcc/testsuite/g++.dg/ext/utf-dflt2.C @@ -0,0 +1,12 @@ +// In C++0x, the u8 prefix should be parsed as separate tokens. +// { dg-do compile } +// { dg-options "-std=c++98" } + +const void *s0 = u8"a"; // { dg-error "was not declared" } + // { dg-error "expected ',' or ';'" "" { target *-*-* } 5 } + +#define u8 "a" + +const void *s1 = u8"a"; + +int main () {} diff --git a/gcc/testsuite/g++.dg/ext/utf8-1.C b/gcc/testsuite/g++.dg/ext/utf8-1.C new file mode 100644 index 00000000000..203b326af79 --- /dev/null +++ b/gcc/testsuite/g++.dg/ext/utf8-1.C @@ -0,0 +1,45 @@ +// { dg-do run } +// { dg-require-iconv "ISO-8859-2" } +// { dg-options "-std=c++0x -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; +} diff --git a/gcc/testsuite/g++.dg/ext/utf8-2.C b/gcc/testsuite/g++.dg/ext/utf8-2.C new file mode 100644 index 00000000000..417a8bfdc1e --- /dev/null +++ b/gcc/testsuite/g++.dg/ext/utf8-2.C @@ -0,0 +1,21 @@ +// { dg-do compile } +// { dg-options "-std=c++0x" } + +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-error "chars is too long" } +const char t1[1] = u8"ab"; // { dg-error "chars is too long" } +const char t2[2] = u8"ab"; // { dg-error "chars is too long" } +const char t3[3] = u8"ab"; +const char t4[4] = u8"ab"; + +const char u0[0] = u8"\u2160."; // { dg-error "chars is too long" } +const char u1[1] = u8"\u2160."; // { dg-error "chars is too long" } +const char u2[2] = u8"\u2160."; // { dg-error "chars is too long" } +const char u3[3] = u8"\u2160."; // { dg-error "chars is too long" } +const char u4[4] = u8"\u2160."; // { dg-error "chars is too long" } +const char u5[5] = u8"\u2160."; +const char u6[6] = u8"\u2160."; diff --git a/gcc/testsuite/gcc.dg/cpp/include6.c b/gcc/testsuite/gcc.dg/cpp/include6.c new file mode 100644 index 00000000000..2bb1320daa2 --- /dev/null +++ b/gcc/testsuite/gcc.dg/cpp/include6.c @@ -0,0 +1,14 @@ +/* { dg-do preprocess } */ +/* { dg-options "-std=gnu99" } */ + +#include <stddef.h> +#include "stddef.h" +#include L"stddef.h" /* { dg-error "include expects" } */ +#include u"stddef.h" /* { dg-error "include expects" } */ +#include U"stddef.h" /* { dg-error "include expects" } */ +#include u8"stddef.h" /* { dg-error "include expects" } */ +#include R"[stddef.h]" /* { dg-error "include expects" } */ +#include LR"[stddef.h]" /* { dg-error "include expects" } */ +#include uR"[stddef.h]" /* { dg-error "include expects" } */ +#include UR"[stddef.h]" /* { dg-error "include expects" } */ +#include u8R"[stddef.h]" /* { dg-error "include expects" } */ diff --git a/gcc/testsuite/gcc.dg/raw-string-1.c b/gcc/testsuite/gcc.dg/raw-string-1.c new file mode 100644 index 00000000000..b499e5cce69 --- /dev/null +++ b/gcc/testsuite/gcc.dg/raw-string-1.c @@ -0,0 +1,101 @@ +/* { dg-do run } */ +/* { dg-options "-std=gnu99" } */ + +#include <wchar.h> + +typedef __CHAR16_TYPE__ char16_t; +typedef __CHAR32_TYPE__ char32_t; + +const char s0[] = R"[a\ +\u010d\U0000010D\\\'\"\?\a\b\f\n\r\t\v\0\00\000\xa\xabb +c]"; +const char s1[] = "a\U0000010d\u010d\\\\\\'\\\"\\?\\a\\b\\f\\n\\r\\t\\v\\0\\00\\000\\xa\\xabb\nc"; +const char s2[] = R"*|*[a\ +b +c]" +c]*|" +c]*|*"; +const char s3[] = "ab\nc]\"\nc]*|\"\nc"; + +const char t0[] = u8R"[a\ +\u010d\U0000010D\\\'\"\?\a\b\f\n\r\t\v\0\00\000\xa\xabb +c]"; +const char t1[] = u8"a\U0000010d\u010d\\\\\\'\\\"\\?\\a\\b\\f\\n\\r\\t\\v\\0\\00\\000\\xa\\xabb\nc"; +const char t2[] = u8R"*|*[a\ +b +c]" +c]*|" +c]*|*"; +const char t3[] = u8"ab\nc]\"\nc]*|\"\nc"; + +const char16_t u0[] = uR"[a\ +\u010d\U0000010D\\\'\"\?\a\b\f\n\r\t\v\0\00\000\xa\xabb +c]"; +const char16_t u1[] = u"a\U0000010d\u010d\\\\\\'\\\"\\?\\a\\b\\f\\n\\r\\t\\v\\0\\00\\000\\xa\\xabb\nc"; +const char16_t u2[] = uR"*|*[a\ +b +c]" +c]*|" +c]*|*"; +const char16_t u3[] = u"ab\nc]\"\nc]*|\"\nc"; + +const char32_t U0[] = UR"[a\ +\u010d\U0000010D\\\'\"\?\a\b\f\n\r\t\v\0\00\000\xa\xabb +c]"; +const char32_t U1[] = U"a\U0000010d\u010d\\\\\\'\\\"\\?\\a\\b\\f\\n\\r\\t\\v\\0\\00\\000\\xa\\xabb\nc"; +const char32_t U2[] = UR"*|*[a\ +b +c]" +c]*|" +c]*|*"; +const char32_t U3[] = U"ab\nc]\"\nc]*|\"\nc"; + +const wchar_t L0[] = LR"[a\ +\u010d\U0000010D\\\'\"\?\a\b\f\n\r\t\v\0\00\000\xa\xabb +c]"; +const wchar_t L1[] = L"a\U0000010d\u010d\\\\\\'\\\"\\?\\a\\b\\f\\n\\r\\t\\v\\0\\00\\000\\xa\\xabb\nc"; +const wchar_t L2[] = LR"*|*[a\ +b +c]" +c]*|" +c]*|*"; +const wchar_t L3[] = L"ab\nc]\"\nc]*|\"\nc"; + +int +main (void) +{ + if (sizeof (s0) != sizeof (s1) + || __builtin_memcmp (s0, s1, sizeof (s0)) != 0) + __builtin_abort (); + if (sizeof (s2) != sizeof (s3) + || __builtin_memcmp (s2, s3, sizeof (s2)) != 0) + __builtin_abort (); + if (sizeof (t0) != sizeof (t1) + || __builtin_memcmp (t0, t1, sizeof (t0)) != 0) + __builtin_abort (); + if (sizeof (t2) != sizeof (t3) + || __builtin_memcmp (t2, t3, sizeof (t2)) != 0) + __builtin_abort (); + if (sizeof (u0) != sizeof (u1) + || __builtin_memcmp (u0, u1, sizeof (u0)) != 0) + __builtin_abort (); + if (sizeof (u2) != sizeof (u3) + || __builtin_memcmp (u2, u3, sizeof (u2)) != 0) + __builtin_abort (); + if (sizeof (U0) != sizeof (U1) + || __builtin_memcmp (U0, U1, sizeof (U0)) != 0) + __builtin_abort (); + if (sizeof (U2) != sizeof (U3) + || __builtin_memcmp (U2, U3, sizeof (U2)) != 0) + __builtin_abort (); + if (sizeof (L0) != sizeof (L1) + || __builtin_memcmp (L0, L1, sizeof (L0)) != 0) + __builtin_abort (); + if (sizeof (L2) != sizeof (L3) + || __builtin_memcmp (L2, L3, sizeof (L2)) != 0) + __builtin_abort (); + if (sizeof (R"*[]*") != 1 + || __builtin_memcmp (R"*[]*", "", 1) != 0) + __builtin_abort (); + return 0; +} diff --git a/gcc/testsuite/gcc.dg/raw-string-2.c b/gcc/testsuite/gcc.dg/raw-string-2.c new file mode 100644 index 00000000000..533abe2bc89 --- /dev/null +++ b/gcc/testsuite/gcc.dg/raw-string-2.c @@ -0,0 +1,109 @@ +/* { dg-do run } */ +/* { dg-options "-std=gnu99" } */ + +#include <wchar.h> + +typedef __CHAR16_TYPE__ char16_t; +typedef __CHAR32_TYPE__ char32_t; + +#define R +#define u +#define uR +#define U +#define UR +#define u8 +#define u8R +#define L +#define LR + +const char s00[] = R"[a]" "[b]"; +const char s01[] = "[a]" R"*[b]*"; +const char s02[] = R"[a]" R"[b]"; +const char s03[] = R"-[a]-" u8"[b]"; +const char s04[] = "[a]" u8R"MNOPQRSTUVWXYZ[b]MNOPQRSTUVWXYZ"; +const char s05[] = R"[a]" u8R"wxyzABCDEFGHIJKL[b]wxyzABCDEFGHIJKL"; +const char s06[] = u8R";([a];(" "[b]"; +const char s07[] = u8"[a]" R"[b]"; +const char s08[] = u8R"[a]" R"_{}#()<>%:;.?*+-[b]_{}#()<>%:;.?*+-"; +const char s09[] = u8R"/^&|~!=,"'\[a]/^&|~!=,"'\" u8"[b]"; +const char s10[] = u8"[a]" u8R"0123456789abcdef[b]0123456789abcdef"; +const char s11[] = u8R"ghijklmnopqrstuv[a]ghijklmnopqrstuv" u8R"w[b]w"; + +const char16_t u03[] = R"-[a]-" u"[b]"; +const char16_t u04[] = "[a]" uR"MNOPQRSTUVWXYZ[b]MNOPQRSTUVWXYZ"; +const char16_t u05[] = R"[a]" uR"wxyzABCDEFGHIJKL[b]wxyzABCDEFGHIJKL"; +const char16_t u06[] = uR";([a];(" "[b]"; +const char16_t u07[] = u"[a]" R"[b]"; +const char16_t u08[] = uR"[a]" R"_{}#()<>%:;.?*+-[b]_{}#()<>%:;.?*+-"; +const char16_t u09[] = uR"/^&|~!=,"'\[a]/^&|~!=,"'\" u"[b]"; +const char16_t u10[] = u"[a]" uR"0123456789abcdef[b]0123456789abcdef"; +const char16_t u11[] = uR"ghijklmnopqrstuv[a]ghijklmnopqrstuv" uR"w[b]w"; + +const char32_t U03[] = R"-[a]-" U"[b]"; +const char32_t U04[] = "[a]" UR"MNOPQRSTUVWXYZ[b]MNOPQRSTUVWXYZ"; +const char32_t U05[] = R"[a]" UR"wxyzABCDEFGHIJKL[b]wxyzABCDEFGHIJKL"; +const char32_t U06[] = UR";([a];(" "[b]"; +const char32_t U07[] = U"[a]" R"[b]"; +const char32_t U08[] = UR"[a]" R"_{}#()<>%:;.?*+-[b]_{}#()<>%:;.?*+-"; +const char32_t U09[] = UR"/^&|~!=,"'\[a]/^&|~!=,"'\" U"[b]"; +const char32_t U10[] = U"[a]" UR"0123456789abcdef[b]0123456789abcdef"; +const char32_t U11[] = UR"ghijklmnopqrstuv[a]ghijklmnopqrstuv" UR"w[b]w"; + +const wchar_t L03[] = R"-[a]-" L"[b]"; +const wchar_t L04[] = "[a]" LR"MNOPQRSTUVWXYZ[b]MNOPQRSTUVWXYZ"; +const wchar_t L05[] = R"[a]" LR"wxyzABCDEFGHIJKL[b]wxyzABCDEFGHIJKL"; +const wchar_t L06[] = LR";([a];(" "[b]"; +const wchar_t L07[] = L"[a]" R"[b]"; +const wchar_t L08[] = LR"[a]" R"_{}#()<>%:;.?*+-[b]_{}#()<>%:;.?*+-"; +const wchar_t L09[] = LR"/^&|~!=,"'\[a]/^&|~!=,"'\" L"[b]"; +const wchar_t L10[] = L"[a]" LR"0123456789abcdef[b]0123456789abcdef"; +const wchar_t L11[] = LR"ghijklmnopqrstuv[a]ghijklmnopqrstuv" LR"w[b]w"; + +int +main (void) +{ +#define TEST(str, val) \ + if (sizeof (str) != sizeof (val) \ + || __builtin_memcmp (str, val, sizeof (str)) != 0) \ + __builtin_abort () + TEST (s00, "a[b]"); + TEST (s01, "[a]b"); + TEST (s02, "ab"); + TEST (s03, "a[b]"); + TEST (s04, "[a]b"); + TEST (s05, "ab"); + TEST (s06, "a[b]"); + TEST (s07, "[a]b"); + TEST (s08, "ab"); + TEST (s09, "a[b]"); + TEST (s10, "[a]b"); + TEST (s11, "ab"); + TEST (u03, u"a[b]"); + TEST (u04, u"[a]b"); + TEST (u05, u"ab"); + TEST (u06, u"a[b]"); + TEST (u07, u"[a]b"); + TEST (u08, u"ab"); + TEST (u09, u"a[b]"); + TEST (u10, u"[a]b"); + TEST (u11, u"ab"); + TEST (U03, U"a[b]"); + TEST (U04, U"[a]b"); + TEST (U05, U"ab"); + TEST (U06, U"a[b]"); + TEST (U07, U"[a]b"); + TEST (U08, U"ab"); + TEST (U09, U"a[b]"); + TEST (U10, U"[a]b"); + TEST (U11, U"ab"); + TEST (L03, L"a[b]"); + TEST (L04, L"[a]b"); + TEST (L05, L"ab"); + TEST (L06, L"a[b]"); + TEST (L07, L"[a]b"); + TEST (L08, L"ab"); + TEST (L09, L"a[b]"); + TEST (L10, L"[a]b"); + TEST (L11, L"ab"); + return 0; +} diff --git a/gcc/testsuite/gcc.dg/raw-string-3.c b/gcc/testsuite/gcc.dg/raw-string-3.c new file mode 100644 index 00000000000..9226411d2e0 --- /dev/null +++ b/gcc/testsuite/gcc.dg/raw-string-3.c @@ -0,0 +1,53 @@ +/* If not gnu99, the {,u,u8,U,L}R prefix should be parsed as separate + token. */ +/* { dg-do compile } */ +/* { dg-options "" } */ + +const void *s0 = R"[a]"; /* { dg-error "undeclared" } */ + /* { dg-error "expected ',' or ';'" "" { target *-*-* } 6 } */ +const void *s1 = uR"[a]"; /* { dg-error "undeclared" } */ + /* { dg-error "expected ',' or ';'" "" { target *-*-* } 8 } */ +const void *s2 = UR"[a]"; /* { dg-error "undeclared" } */ + /* { dg-error "expected ',' or ';'" "" { target *-*-* } 10 } */ +const void *s3 = u8R"[a]"; /* { dg-error "undeclared" } */ + /* { dg-error "expected ',' or ';'" "" { target *-*-* } 12 } */ +const void *s4 = LR"[a]"; /* { dg-error "undeclared" } */ + /* { dg-error "expected ',' or ';'" "" { target *-*-* } 14 } */ + +const int i0 = R'a'; /* { dg-error "expected ',' or ';'" } */ +const int i1 = uR'a'; /* { dg-error "expected ',' or ';'" } */ +const int i2 = UR'a'; /* { dg-error "expected ',' or ';'" } */ +const int i3 = u8R'a'; /* { dg-error "expected ',' or ';'" } */ +const int i4 = LR'a'; /* { dg-error "expected ',' or ';'" } */ + +#define R "a" +#define uR "b" +#define UR "c" +#define u8R "d" +#define LR "e" + +const void *s5 = R"[a]"; +const void *s6 = uR"[a]"; +const void *s7 = UR"[a]"; +const void *s8 = u8R"[a]"; +const void *s9 = LR"[a]"; + +#undef R +#undef uR +#undef UR +#undef u8R +#undef LR + +#define R 1 + +#define uR 2 + +#define UR 3 + +#define u8R 4 + +#define LR 5 + + +const int i5 = R'a'; +const int i6 = uR'a'; +const int i7 = UR'a'; +const int i8 = u8R'a'; +const int i9 = LR'a'; + +int main () {} diff --git a/gcc/testsuite/gcc.dg/raw-string-4.c b/gcc/testsuite/gcc.dg/raw-string-4.c new file mode 100644 index 00000000000..24d56ed7464 --- /dev/null +++ b/gcc/testsuite/gcc.dg/raw-string-4.c @@ -0,0 +1,28 @@ +/* R is not applicable for character literals. */ +/* { dg-do compile } */ +/* { dg-options "-std=gnu99" } */ + +const int i0 = R'a'; /* { dg-error "undeclared" } */ + /* { dg-error "expected ',' or ';'" "" { target *-*-* } 5 } */ +const int i1 = uR'a'; /* { dg-error "undeclared" } */ + /* { dg-error "expected ',' or ';'" "" { target *-*-* } 7 } */ +const int i2 = UR'a'; /* { dg-error "undeclared" } */ + /* { dg-error "expected ',' or ';'" "" { target *-*-* } 9 } */ +const int i3 = u8R'a'; /* { dg-error "undeclared" } */ + /* { dg-error "expected ',' or ';'" "" { target *-*-* } 11 } */ +const int i4 = LR'a'; /* { dg-error "undeclared" } */ + /* { dg-error "expected ',' or ';'" "" { target *-*-* } 13 } */ + +#define R 1 + +#define uR 2 + +#define UR 3 + +#define u8R 4 + +#define LR 5 + + +const int i5 = R'a'; +const int i6 = uR'a'; +const int i7 = UR'a'; +const int i8 = u8R'a'; +const int i9 = LR'a'; + +int main () {} diff --git a/gcc/testsuite/gcc.dg/raw-string-5.c b/gcc/testsuite/gcc.dg/raw-string-5.c new file mode 100644 index 00000000000..3dbf97ded90 --- /dev/null +++ b/gcc/testsuite/gcc.dg/raw-string-5.c @@ -0,0 +1,23 @@ +/* { dg-do compile } */ +/* { dg-options "-std=gnu99" } */ + +const void *s0 = R"0123456789abcdefg[]0123456789abcdefg"; + /* { dg-error "raw string delimiter longer" "" { target *-*-* } 4 } */ + /* { dg-error "stray" "" { target *-*-* } 4 } */ +const void *s1 = R" [] "; + /* { dg-error "invalid character" "" { target *-*-* } 7 } */ + /* { dg-error "stray" "" { target *-*-* } 7 } */ +const void *s2 = R" [] "; + /* { dg-error "invalid character" "" { target *-*-* } 10 } */ + /* { dg-error "stray" "" { target *-*-* } 10 } */ +const void *s3 = R"][]]"; + /* { dg-error "invalid character" "" { target *-*-* } 13 } */ + /* { dg-error "stray" "" { target *-*-* } 13 } */ +const void *s4 = R"@[]@"; + /* { dg-error "invalid character" "" { target *-*-* } 16 } */ + /* { dg-error "stray" "" { target *-*-* } 16 } */ +const void *s5 = R"$[]$"; + /* { dg-error "invalid character" "" { target *-*-* } 19 } */ + /* { dg-error "stray" "" { target *-*-* } 19 } */ + +int main () {} diff --git a/gcc/testsuite/gcc.dg/raw-string-6.c b/gcc/testsuite/gcc.dg/raw-string-6.c new file mode 100644 index 00000000000..338087a25fd --- /dev/null +++ b/gcc/testsuite/gcc.dg/raw-string-6.c @@ -0,0 +1,5 @@ +/* { dg-do compile } */ +/* { dg-options "-std=gnu99" } */ + +const void *s0 = R"ouch[]ouCh"; /* { dg-error "expected expression at end of input" } */ + /* { dg-error "unterminated raw string" "" { target *-*-* } 4 } */ diff --git a/gcc/testsuite/gcc.dg/raw-string-7.c b/gcc/testsuite/gcc.dg/raw-string-7.c new file mode 100644 index 00000000000..5bb4bec2085 --- /dev/null +++ b/gcc/testsuite/gcc.dg/raw-string-7.c @@ -0,0 +1,23 @@ +/* The trailing whitespace after \ and before newline extension + breaks full compliance for raw strings. */ +/* { dg-do run { xfail *-*-* } } */ +/* { dg-options "-std=gnu99" } */ + +/* Note, there is a single space after \ on the following line. */ +const void *s0 = R"[\ +]"; +/* { dg-bogus "backslash and newline separated by space" "" { xfail *-*-* } 7 } */ + +/* Note, there is a single tab after \ on the following line. */ +const void *s1 = R"[\ +]"; +/* { dg-bogus "backslash and newline separated by space" "" { xfail *-*-* } 12 } */ + +int +main (void) +{ + if (__builtin_strcmp (s0, "\\ \n") != 0 + || __builtin_strcmp (s1, "\\\t\n") != 0) + __builtin_abort (); + return 0; +} diff --git a/gcc/testsuite/gcc.dg/utf-badconcat2.c b/gcc/testsuite/gcc.dg/utf-badconcat2.c new file mode 100644 index 00000000000..ea71a7f6857 --- /dev/null +++ b/gcc/testsuite/gcc.dg/utf-badconcat2.c @@ -0,0 +1,15 @@ +/* Test unsupported concatenation of UTF-8 string literals. */ +/* { dg-do compile } */ +/* { dg-options "-std=gnu99" } */ + +void *s0 = u8"a" "b"; +void *s1 = "a" u8"b"; +void *s2 = u8"a" u8"b"; +void *s3 = u8"a" u"b"; /* { dg-error "non-standard concatenation" } */ +void *s4 = u"a" u8"b"; /* { dg-error "non-standard concatenation" } */ +void *s5 = u8"a" U"b"; /* { dg-error "non-standard concatenation" } */ +void *s6 = U"a" u8"b"; /* { dg-error "non-standard concatenation" } */ +void *s7 = u8"a" L"b"; /* { dg-error "non-standard concatenation" } */ +void *s8 = L"a" u8"b"; /* { dg-error "non-standard concatenation" } */ + +int main () {} diff --git a/gcc/testsuite/gcc.dg/utf-dflt2.c b/gcc/testsuite/gcc.dg/utf-dflt2.c new file mode 100644 index 00000000000..ab101f45b78 --- /dev/null +++ b/gcc/testsuite/gcc.dg/utf-dflt2.c @@ -0,0 +1,12 @@ +/* If not gnu99, the u8 prefix should be parsed as separate tokens. */ +/* { dg-do compile } */ +/* { dg-options "" } */ + +const void *s0 = u8"a"; /* { dg-error "undeclared" } */ + /* { dg-error "expected ',' or ';'" "" { target *-*-* } 5 } */ + +#define u8 "a" + +const void *s1 = u8"a"; + +int main () {} diff --git a/gcc/testsuite/gcc.dg/utf8-1.c b/gcc/testsuite/gcc.dg/utf8-1.c new file mode 100644 index 00000000000..e287e065688 --- /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; +} 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."; diff --git a/libcpp/ChangeLog b/libcpp/ChangeLog index 3259c56f46e..5946b29dc56 100644 --- a/libcpp/ChangeLog +++ b/libcpp/ChangeLog @@ -1,3 +1,21 @@ +2009-10-19 Jakub Jelinek <jakub@redhat.com> + + * 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. + 2009-10-14 Jakub Jelinek <jakub@redhat.com> PR preprocessor/41543 diff --git a/libcpp/charset.c b/libcpp/charset.c index bd24ec2490d..837ccd77aab 100644 --- a/libcpp/charset.c +++ b/libcpp/charset.c @@ -721,6 +721,8 @@ cpp_init_iconv (cpp_reader *pfile) pfile->narrow_cset_desc = init_iconv_desc (pfile, ncset, SOURCE_CHARSET); pfile->narrow_cset_desc.width = CPP_OPTION (pfile, char_precision); + pfile->utf8_cset_desc = init_iconv_desc (pfile, "UTF-8", SOURCE_CHARSET); + pfile->utf8_cset_desc.width = CPP_OPTION (pfile, char_precision); pfile->char16_cset_desc = init_iconv_desc (pfile, be ? "UTF-16BE" : "UTF-16LE", SOURCE_CHARSET); @@ -741,6 +743,12 @@ _cpp_destroy_iconv (cpp_reader *pfile) { if (pfile->narrow_cset_desc.func == convert_using_iconv) iconv_close (pfile->narrow_cset_desc.cd); + if (pfile->utf8_cset_desc.func == convert_using_iconv) + iconv_close (pfile->utf8_cset_desc.cd); + if (pfile->char16_cset_desc.func == convert_using_iconv) + iconv_close (pfile->char16_cset_desc.cd); + if (pfile->char32_cset_desc.func == convert_using_iconv) + iconv_close (pfile->char32_cset_desc.cd); if (pfile->wide_cset_desc.func == convert_using_iconv) iconv_close (pfile->wide_cset_desc.cd); } @@ -1339,6 +1347,8 @@ converter_for_type (cpp_reader *pfile, enum cpp_ttype type) { default: return pfile->narrow_cset_desc; + case CPP_UTF8STRING: + return pfile->utf8_cset_desc; case CPP_CHAR16: case CPP_STRING16: return pfile->char16_cset_desc; @@ -1373,7 +1383,47 @@ cpp_interpret_string (cpp_reader *pfile, const cpp_string *from, size_t count, for (i = 0; i < count; i++) { p = from[i].text; - if (*p == 'L' || *p == 'u' || *p == 'U') p++; + if (*p == 'u') + { + if (*++p == '8') + p++; + } + else if (*p == 'L' || *p == 'U') p++; + if (*p == 'R') + { + const uchar *prefix; + + /* Skip over 'R"'. */ + p += 2; + prefix = p; + while (*p != '[') + p++; + p++; + limit = from[i].text + from[i].len; + if (limit >= p + (p - prefix) + 1) + limit -= (p - prefix) + 1; + + for (;;) + { + base = p; + while (p < limit && (*p != '\\' || (p[1] != 'u' && p[1] != 'U'))) + p++; + if (p > base) + { + /* We have a run of normal characters; these can be fed + directly to convert_cset. */ + if (!APPLY_CONVERSION (cvt, base, p - base, &tbuf)) + goto fail; + } + if (p == limit) + break; + + p = convert_ucn (pfile, p + 1, limit, &tbuf, cvt); + } + + continue; + } + p++; /* Skip leading quote. */ limit = from[i].text + from[i].len - 1; /* Skip trailing quote. */ diff --git a/libcpp/directives.c b/libcpp/directives.c index f9dba539ea2..01bb599e266 100644 --- a/libcpp/directives.c +++ b/libcpp/directives.c @@ -697,7 +697,8 @@ parse_include (cpp_reader *pfile, int *pangle_brackets, /* Allow macro expansion. */ header = get_token_no_padding (pfile); *location = header->src_loc; - if (header->type == CPP_STRING || header->type == CPP_HEADER_NAME) + if ((header->type == CPP_STRING && header->val.str.text[0] != 'R') + || header->type == CPP_HEADER_NAME) { fname = XNEWVEC (char, header->val.str.len - 1); memcpy (fname, header->val.str.text + 1, header->val.str.len - 2); @@ -1537,7 +1538,8 @@ get__Pragma_string (cpp_reader *pfile) if (string->type == CPP_EOF) _cpp_backup_tokens (pfile, 1); if (string->type != CPP_STRING && string->type != CPP_WSTRING - && string->type != CPP_STRING32 && string->type != CPP_STRING16) + && string->type != CPP_STRING32 && string->type != CPP_STRING16 + && string->type != CPP_UTF8STRING) return NULL; paren = get_token_no_padding (pfile); diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h index df04668dda0..e95f01a412a 100644 --- a/libcpp/include/cpplib.h +++ b/libcpp/include/cpplib.h @@ -127,6 +127,7 @@ struct _cpp_file; TK(WSTRING, LITERAL) /* L"string" */ \ TK(STRING16, LITERAL) /* u"string" */ \ TK(STRING32, LITERAL) /* U"string" */ \ + TK(UTF8STRING, LITERAL) /* u8"string" */ \ TK(OBJC_STRING, LITERAL) /* @"string" - Objective-C */ \ TK(HEADER_NAME, LITERAL) /* <stdio.h> in #include */ \ \ @@ -728,10 +729,10 @@ extern const unsigned char *cpp_macro_definition (cpp_reader *, extern void _cpp_backup_tokens (cpp_reader *, unsigned int); extern const cpp_token *cpp_peek_token (cpp_reader *, int); -/* Evaluate a CPP_CHAR or CPP_WCHAR token. */ +/* Evaluate a CPP_*CHAR* token. */ extern cppchar_t cpp_interpret_charconst (cpp_reader *, const cpp_token *, unsigned int *, int *); -/* Evaluate a vector of CPP_STRING or CPP_WSTRING tokens. */ +/* Evaluate a vector of CPP_*STRING* tokens. */ extern bool cpp_interpret_string (cpp_reader *, const cpp_string *, size_t, cpp_string *, enum cpp_ttype); diff --git a/libcpp/internal.h b/libcpp/internal.h index 21e51c6553c..aaa231c2ab1 100644 --- a/libcpp/internal.h +++ b/libcpp/internal.h @@ -397,6 +397,10 @@ struct cpp_reader struct cset_converter narrow_cset_desc; /* Descriptor for converting from the source character set to the + UTF-8 execution character set. */ + struct cset_converter utf8_cset_desc; + + /* Descriptor for converting from the source character set to the UTF-16 execution character set. */ struct cset_converter char16_cset_desc; diff --git a/libcpp/lex.c b/libcpp/lex.c index bab14a4baa3..55bffa9a326 100644 --- a/libcpp/lex.c +++ b/libcpp/lex.c @@ -617,12 +617,192 @@ create_literal (cpp_reader *pfile, cpp_token *token, const uchar *base, token->val.str.text = dest; } +/* Lexes a raw string. The stored string contains the spelling, including + double quotes, delimiter string, '[' and ']', any leading + 'L', 'u', 'U' or 'u8' and 'R' modifier. 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. */ + +static void +lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base, + const uchar *cur) +{ + source_location saw_NUL = 0; + const uchar *raw_prefix; + unsigned int raw_prefix_len = 0; + enum cpp_ttype type; + size_t total_len = 0; + _cpp_buff *first_buff = NULL, *last_buff = NULL; + + type = (*base == 'L' ? CPP_WSTRING : + *base == 'U' ? CPP_STRING32 : + *base == 'u' ? (base[1] == '8' ? CPP_UTF8STRING : CPP_STRING16) + : CPP_STRING); + + raw_prefix = cur + 1; + while (raw_prefix_len < 16) + { + switch (raw_prefix[raw_prefix_len]) + { + case ' ': case '[': case ']': case '\t': + case '\v': case '\f': case '\n': default: + break; + /* Basic source charset except the above chars. */ + 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 '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 '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 'Y': case 'Z': + case '0': case '1': case '2': case '3': case '4': case '5': + case '6': case '7': case '8': case '9': + case '_': case '{': case '}': case '#': case '(': case ')': + case '<': case '>': case '%': case ':': case ';': case '.': + case '?': case '*': case '+': case '-': case '/': case '^': + case '&': case '|': case '~': case '!': case '=': case ',': + case '\\': case '"': case '\'': + raw_prefix_len++; + continue; + } + break; + } + + if (raw_prefix[raw_prefix_len] != '[') + { + int col = CPP_BUF_COLUMN (pfile->buffer, raw_prefix + raw_prefix_len) + + 1; + if (raw_prefix_len == 16) + cpp_error_with_line (pfile, CPP_DL_ERROR, token->src_loc, col, + "raw string delimiter longer than 16 characters"); + else + cpp_error_with_line (pfile, CPP_DL_ERROR, token->src_loc, col, + "invalid character '%c' in raw string delimiter", + (int) raw_prefix[raw_prefix_len]); + pfile->buffer->cur = raw_prefix - 1; + create_literal (pfile, token, base, raw_prefix - 1 - base, CPP_OTHER); + return; + } + + cur = raw_prefix + raw_prefix_len + 1; + for (;;) + { + cppchar_t c = *cur++; + + if (c == ']' + && strncmp ((const char *) cur, (const char *) raw_prefix, + raw_prefix_len) == 0 + && cur[raw_prefix_len] == '"') + { + cur += raw_prefix_len + 1; + break; + } + else if (c == '\n') + { + if (pfile->state.in_directive + || pfile->state.parsing_args + || pfile->state.in_deferred_pragma) + { + cur--; + type = CPP_OTHER; + cpp_error_with_line (pfile, CPP_DL_ERROR, token->src_loc, 0, + "unterminated raw string"); + break; + } + + /* raw strings allow embedded non-escaped newlines, which + complicates this routine a lot. */ + if (first_buff == NULL) + { + total_len = cur - base; + first_buff = last_buff = _cpp_get_buff (pfile, total_len); + memcpy (BUFF_FRONT (last_buff), base, total_len); + raw_prefix = BUFF_FRONT (last_buff) + (raw_prefix - base); + BUFF_FRONT (last_buff) += total_len; + } + else + { + size_t len = cur - base; + size_t cur_len = len > BUFF_ROOM (last_buff) + ? BUFF_ROOM (last_buff) : len; + + total_len += len; + memcpy (BUFF_FRONT (last_buff), base, cur_len); + BUFF_FRONT (last_buff) += cur_len; + if (len > cur_len) + { + last_buff = _cpp_append_extend_buff (pfile, last_buff, + len - cur_len); + memcpy (BUFF_FRONT (last_buff), base + cur_len, + len - cur_len); + BUFF_FRONT (last_buff) += len - cur_len; + } + } + + if (pfile->buffer->cur < pfile->buffer->rlimit) + CPP_INCREMENT_LINE (pfile, 0); + pfile->buffer->need_line = true; + + if (!_cpp_get_fresh_line (pfile)) + { + source_location src_loc = token->src_loc; + token->type = CPP_EOF; + /* Tell the compiler the line number of the EOF token. */ + token->src_loc = pfile->line_table->highest_line; + token->flags = BOL; + if (first_buff != NULL) + _cpp_release_buff (pfile, first_buff); + cpp_error_with_line (pfile, CPP_DL_ERROR, src_loc, 0, + "unterminated raw string"); + return; + } + + cur = base = pfile->buffer->cur; + } + else if (c == '\0' && !saw_NUL) + LINEMAP_POSITION_FOR_COLUMN (saw_NUL, pfile->line_table, + CPP_BUF_COLUMN (pfile->buffer, cur)); + } + + if (saw_NUL && !pfile->state.skipping) + cpp_error_with_line (pfile, CPP_DL_WARNING, saw_NUL, 0, + "null character(s) preserved in literal"); + + pfile->buffer->cur = cur; + if (first_buff == NULL) + create_literal (pfile, token, base, cur - base, type); + else + { + uchar *dest = _cpp_unaligned_alloc (pfile, total_len + (cur - base) + 1); + + token->type = type; + token->val.str.len = total_len + (cur - base); + token->val.str.text = dest; + last_buff = first_buff; + while (last_buff != NULL) + { + memcpy (dest, last_buff->base, + BUFF_FRONT (last_buff) - last_buff->base); + dest += BUFF_FRONT (last_buff) - last_buff->base; + last_buff = last_buff->next; + } + _cpp_release_buff (pfile, first_buff); + memcpy (dest, base, cur - base); + dest[cur - base] = '\0'; + } +} + /* 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', 'u' or 'U'. It returns the type - of the literal, or CPP_OTHER if it was not properly terminated, or - CPP_LESS for an unterminated header name which must be relexed as - normal tokens. + quote and any leading 'L', 'u', 'U' or 'u8' and optional + 'R' modifier. It returns the type of the literal, or CPP_OTHER + if it was not properly terminated, or CPP_LESS for an unterminated + header name which must be relexed as normal tokens. The spelling is NUL-terminated, but it is not guaranteed that this is the first NUL since embedded NULs are preserved. */ @@ -636,12 +816,24 @@ lex_string (cpp_reader *pfile, cpp_token *token, const uchar *base) cur = base; terminator = *cur++; - if (terminator == 'L' || terminator == 'u' || terminator == 'U') + if (terminator == 'L' || terminator == 'U') terminator = *cur++; - if (terminator == '\"') + else if (terminator == 'u') + { + terminator = *cur++; + if (terminator == '8') + terminator = *cur++; + } + if (terminator == 'R') + { + lex_raw_string (pfile, token, base, cur); + return; + } + if (terminator == '"') type = (*base == 'L' ? CPP_WSTRING : *base == 'U' ? CPP_STRING32 : - *base == 'u' ? CPP_STRING16 : CPP_STRING); + *base == 'u' ? (base[1] == '8' ? CPP_UTF8STRING : CPP_STRING16) + : CPP_STRING); else if (terminator == '\'') type = (*base == 'L' ? CPP_WCHAR : *base == 'U' ? CPP_CHAR32 : @@ -1101,10 +1293,21 @@ _cpp_lex_direct (cpp_reader *pfile) case 'L': case 'u': case 'U': - /* 'L', 'u' or 'U' may introduce wide characters or strings. */ + case 'R': + /* 'L', 'u', 'U', 'u8' or 'R' may introduce wide characters, + wide strings or raw strings. */ if (c == 'L' || CPP_OPTION (pfile, uliterals)) { - if (*buffer->cur == '\'' || *buffer->cur == '"') + if ((*buffer->cur == '\'' && c != 'R') + || *buffer->cur == '"' + || (*buffer->cur == 'R' + && c != 'R' + && buffer->cur[1] == '"' + && CPP_OPTION (pfile, uliterals)) + || (*buffer->cur == '8' + && c == 'u' + && (buffer->cur[1] == '"' + || (buffer->cur[1] == 'R' && buffer->cur[2] == '"')))) { lex_string (pfile, result, buffer->cur - 1); break; @@ -1120,7 +1323,7 @@ _cpp_lex_direct (cpp_reader *pfile) 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 'M': case 'N': case 'O': case 'P': case 'Q': case 'S': case 'T': case 'V': case 'W': case 'X': case 'Y': case 'Z': result->type = CPP_NAME; diff --git a/libcpp/macro.c b/libcpp/macro.c index f31805955c6..1d284cf9f8a 100644 --- a/libcpp/macro.c +++ b/libcpp/macro.c @@ -379,7 +379,8 @@ stringify_arg (cpp_reader *pfile, macro_arg *arg) escape_it = (token->type == CPP_STRING || token->type == CPP_CHAR || token->type == CPP_WSTRING || token->type == CPP_WCHAR || token->type == CPP_STRING32 || token->type == CPP_CHAR32 - || token->type == CPP_STRING16 || token->type == CPP_CHAR16); + || token->type == CPP_STRING16 || token->type == CPP_CHAR16 + || token->type == CPP_UTF8STRING); /* Room for each char being written in octal, initial space and final quote and NUL. */ |