diff options
author | Joseph Myers <joseph@codesourcery.com> | 2019-11-14 20:18:33 +0000 |
---|---|---|
committer | Joseph Myers <jsm28@gcc.gnu.org> | 2019-11-14 20:18:33 +0000 |
commit | 7c5890cc0a0ecea0e88cc39e9fba6385fb579e61 (patch) | |
tree | f751de7e59697865e2ffa028877728284227c355 /gcc | |
parent | 3771033244b3ee1b53a8a00d734580b16384fdd3 (diff) | |
download | gcc-7c5890cc0a0ecea0e88cc39e9fba6385fb579e61.zip gcc-7c5890cc0a0ecea0e88cc39e9fba6385fb579e61.tar.gz gcc-7c5890cc0a0ecea0e88cc39e9fba6385fb579e61.tar.bz2 |
Support UTF-8 character constants for C2x.
C2x adds u8'' character constants to C. This patch adds the
corresponding GCC support.
Most of the support was already present for C++ and just needed
enabling for C2x. However, in C2x these constants have type unsigned
char, which required corresponding adjustments in the compiler and the
preprocessor to give them that type for C.
For C, it seems clear to me that having type unsigned char means the
constants are unsigned in the preprocessor (and thus treated as having
type uintmax_t in #if conditionals), so this patch implements that. I
included a conditional in the libcpp change to avoid affecting
signedness for C++, but I'm not sure if in fact these constants should
also be unsigned in the preprocessor for C++ in which case that
!CPP_OPTION (pfile, cplusplus) conditional would not be needed.
Bootstrapped with no regressions on x86_64-pc-linux-gnu.
gcc/c:
* c-parser.c (c_parser_postfix_expression)
(c_parser_check_literal_zero): Handle CPP_UTF8CHAR.
* gimple-parser.c (c_parser_gimple_postfix_expression): Likewise.
gcc/c-family:
* c-lex.c (lex_charconst): Make CPP_UTF8CHAR constants unsigned
char for C.
gcc/testsuite:
* gcc.dg/c11-utf8char-1.c, gcc.dg/c2x-utf8char-1.c,
gcc.dg/c2x-utf8char-2.c, gcc.dg/c2x-utf8char-3.c,
gcc.dg/gnu2x-utf8char-1.c: New tests.
libcpp:
* charset.c (narrow_str_to_charconst): Make CPP_UTF8CHAR constants
unsigned for C.
* init.c (lang_defaults): Set utf8_char_literals for GNUC2X and
STDC2X.
From-SVN: r278265
Diffstat (limited to 'gcc')
-rw-r--r-- | gcc/c-family/ChangeLog | 5 | ||||
-rw-r--r-- | gcc/c-family/c-lex.c | 4 | ||||
-rw-r--r-- | gcc/c/ChangeLog | 6 | ||||
-rw-r--r-- | gcc/c/c-parser.c | 2 | ||||
-rw-r--r-- | gcc/c/gimple-parser.c | 1 | ||||
-rw-r--r-- | gcc/testsuite/ChangeLog | 6 | ||||
-rw-r--r-- | gcc/testsuite/gcc.dg/c11-utf8char-1.c | 7 | ||||
-rw-r--r-- | gcc/testsuite/gcc.dg/c2x-utf8char-1.c | 29 | ||||
-rw-r--r-- | gcc/testsuite/gcc.dg/c2x-utf8char-2.c | 8 | ||||
-rw-r--r-- | gcc/testsuite/gcc.dg/c2x-utf8char-3.c | 8 | ||||
-rw-r--r-- | gcc/testsuite/gcc.dg/gnu2x-utf8char-1.c | 5 |
11 files changed, 80 insertions, 1 deletions
diff --git a/gcc/c-family/ChangeLog b/gcc/c-family/ChangeLog index 336159d..f4fdccc 100644 --- a/gcc/c-family/ChangeLog +++ b/gcc/c-family/ChangeLog @@ -1,3 +1,8 @@ +2019-11-14 Joseph Myers <joseph@codesourcery.com> + + * c-lex.c (lex_charconst): Make CPP_UTF8CHAR constants unsigned + char for C. + 2019-11-14 Jakub Jelinek <jakub@redhat.com> * c-omp.c (c_omp_check_context_selector): Add nvidia to the list of diff --git a/gcc/c-family/c-lex.c b/gcc/c-family/c-lex.c index 42010a7..d446633f 100644 --- a/gcc/c-family/c-lex.c +++ b/gcc/c-family/c-lex.c @@ -1376,7 +1376,9 @@ lex_charconst (const cpp_token *token) type = char16_type_node; else if (token->type == CPP_UTF8CHAR) { - if (flag_char8_t) + if (!c_dialect_cxx ()) + type = unsigned_char_type_node; + else if (flag_char8_t) type = char8_type_node; else type = char_type_node; diff --git a/gcc/c/ChangeLog b/gcc/c/ChangeLog index 04dce4b..b881cab 100644 --- a/gcc/c/ChangeLog +++ b/gcc/c/ChangeLog @@ -1,3 +1,9 @@ +2019-11-14 Joseph Myers <joseph@codesourcery.com> + + * c-parser.c (c_parser_postfix_expression) + (c_parser_check_literal_zero): Handle CPP_UTF8CHAR. + * gimple-parser.c (c_parser_gimple_postfix_expression): Likewise. + 2019-11-14 Richard Sandiford <richard.sandiford@arm.com> * c-typeck.c (build_conditional_expr): Use truth_type_for instead diff --git a/gcc/c/c-parser.c b/gcc/c/c-parser.c index 5e30a7f..8ce4e70 100644 --- a/gcc/c/c-parser.c +++ b/gcc/c/c-parser.c @@ -8783,6 +8783,7 @@ c_parser_postfix_expression (c_parser *parser) case CPP_CHAR: case CPP_CHAR16: case CPP_CHAR32: + case CPP_UTF8CHAR: case CPP_WCHAR: expr.value = c_parser_peek_token (parser)->value; /* For the purpose of warning when a pointer is compared with @@ -10459,6 +10460,7 @@ c_parser_check_literal_zero (c_parser *parser, unsigned *literal_zero_mask, 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->value) diff --git a/gcc/c/gimple-parser.c b/gcc/c/gimple-parser.c index 6fdb83c..c16d0df 100644 --- a/gcc/c/gimple-parser.c +++ b/gcc/c/gimple-parser.c @@ -1395,6 +1395,7 @@ c_parser_gimple_postfix_expression (gimple_parser &parser) case CPP_CHAR: case CPP_CHAR16: case CPP_CHAR32: + case CPP_UTF8CHAR: case CPP_WCHAR: expr.value = c_parser_peek_token (parser)->value; set_c_expr_source_range (&expr, tok_range); diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog index 6684448..51624b7 100644 --- a/gcc/testsuite/ChangeLog +++ b/gcc/testsuite/ChangeLog @@ -1,3 +1,9 @@ +2019-11-14 Joseph Myers <joseph@codesourcery.com> + + * gcc.dg/c11-utf8char-1.c, gcc.dg/c2x-utf8char-1.c, + gcc.dg/c2x-utf8char-2.c, gcc.dg/c2x-utf8char-3.c, + gcc.dg/gnu2x-utf8char-1.c: New tests. + 2019-11-14 Richard Sandiford <richard.sandiford@arm.com> PR testsuite/92366 diff --git a/gcc/testsuite/gcc.dg/c11-utf8char-1.c b/gcc/testsuite/gcc.dg/c11-utf8char-1.c new file mode 100644 index 0000000..26dbd92 --- /dev/null +++ b/gcc/testsuite/gcc.dg/c11-utf8char-1.c @@ -0,0 +1,7 @@ +/* Test C2x UTF-8 characters. Test not accepted for C11. */ +/* { dg-do compile } */ +/* { dg-options "-std=c11 -pedantic-errors" } */ + +#define z(x) 0 +#define u8 z( +unsigned char a = u8'a'); diff --git a/gcc/testsuite/gcc.dg/c2x-utf8char-1.c b/gcc/testsuite/gcc.dg/c2x-utf8char-1.c new file mode 100644 index 0000000..76543af --- /dev/null +++ b/gcc/testsuite/gcc.dg/c2x-utf8char-1.c @@ -0,0 +1,29 @@ +/* Test C2x UTF-8 characters. Test valid usages. */ +/* { dg-do compile } */ +/* { dg-options "-std=c2x -pedantic-errors" } */ + +unsigned char a = u8'a'; +_Static_assert (u8'a' == 97); + +unsigned char b = u8'\0'; +_Static_assert (u8'\0' == 0); + +unsigned char c = u8'\xff'; +_Static_assert (u8'\xff' == 255); + +unsigned char d = u8'\377'; +_Static_assert (u8'\377' == 255); + +_Static_assert (sizeof (u8'a') == 1); +_Static_assert (sizeof (u8'\0') == 1); +_Static_assert (sizeof (u8'\xff') == 1); +_Static_assert (sizeof (u8'\377') == 1); + +_Static_assert (_Generic (u8'a', unsigned char: 1, default: 2) == 1); +_Static_assert (_Generic (u8'\0', unsigned char: 1, default: 2) == 1); +_Static_assert (_Generic (u8'\xff', unsigned char: 1, default: 2) == 1); +_Static_assert (_Generic (u8'\377', unsigned char: 1, default: 2) == 1); + +#if u8'\0' - 1 < 0 +#error "UTF-8 constants not unsigned in preprocessor" +#endif diff --git a/gcc/testsuite/gcc.dg/c2x-utf8char-2.c b/gcc/testsuite/gcc.dg/c2x-utf8char-2.c new file mode 100644 index 0000000..4e6a2f6 --- /dev/null +++ b/gcc/testsuite/gcc.dg/c2x-utf8char-2.c @@ -0,0 +1,8 @@ +/* Test C2x UTF-8 characters. Character values not affected by + different execution character set. */ +/* { dg-do compile } */ +/* { dg-require-iconv "IBM1047" } */ +/* { dg-options "-std=c2x -pedantic-errors -fexec-charset=IBM1047" } */ + +_Static_assert (u8'a' == 97); +_Static_assert (u8'a' != (unsigned char) 'a'); diff --git a/gcc/testsuite/gcc.dg/c2x-utf8char-3.c b/gcc/testsuite/gcc.dg/c2x-utf8char-3.c new file mode 100644 index 0000000..7c48983 --- /dev/null +++ b/gcc/testsuite/gcc.dg/c2x-utf8char-3.c @@ -0,0 +1,8 @@ +/* Test C2x UTF-8 characters. Test errors for invalid code. */ +/* { dg-do compile } */ +/* { dg-options "-std=c2x -pedantic-errors" } */ + +unsigned char a = u8''; /* { dg-error "empty character constant" } */ +unsigned char b = u8'ab'; /* { dg-error "character constant too long for its type" } */ +unsigned char c = u8'\u00ff'; /* { dg-error "character constant too long for its type" } */ +unsigned char d = u8'\x100'; /* { dg-error "hex escape sequence out of range" } */ diff --git a/gcc/testsuite/gcc.dg/gnu2x-utf8char-1.c b/gcc/testsuite/gcc.dg/gnu2x-utf8char-1.c new file mode 100644 index 0000000..9c3add2 --- /dev/null +++ b/gcc/testsuite/gcc.dg/gnu2x-utf8char-1.c @@ -0,0 +1,5 @@ +/* Test C2x UTF-8 characters. Test accepted with -std=gnu2x. */ +/* { dg-do compile } */ +/* { dg-options "-std=gnu2x" } */ + +#include "c2x-utf8char-1.c" |