This patch implements the core language and compiler dependent library
changes proposed in WG14 N2653 [1] for C2x. The changes include:
- Change of type for UTF-8 string literals from array of char to array
of char8_t (unsigned char) when targeting C2x.
- A new atomic_char8_t typedef.
- A new ATOMIC_CHAR8_T_LOCK_FREE macro defined in terms of the existing
__GCC_ATOMIC_CHAR8_T_LOCK_FREE predefined macro.
Tested on Linux x86_64.
gcc/ChangeLog:
2022-01-07 Tom Honermann <t...@honermann.net>
* ginclude/stdatomic.h (atomic_char8_t,
ATOMIC_CHAR8_T_LOCK_FREE): New typedef and macro.
gcc/c/ChangeLog:
2022-01-07 Tom Honermann <t...@honermann.net>
* c-parser.c (c_parser_string_literal): Use char8_t as the type
of CPP_UTF8STRING when char8_t support is enabled.
* c-typeck.c (digest_init): Allow initialization of an array
of character type by a string literal with type array of
char8_t.
gcc/c-family/ChangeLog:
2022-01-07 Tom Honermann <t...@honermann.net>
* c-lex.c (lex_string, lex_charconst): Use char8_t as the type
of CPP_UTF8CHAR and CPP_UTF8STRING when char8_t support is
enabled.
* c-opts.c (c_common_post_options): Set flag_char8_t if
targeting C2x.
Tom.
[1]: WG14 N2653
"char8_t: A type for UTF-8 characters and strings (Revision 1)"
http://www.open-std.org/jtc1/sc22/wg14/www/docs/n2653.htm
commit c041cce5d262908349be3f1f2e361c824db15845
Author: Tom Honermann <t...@honermann.net>
Date: Sat Jan 1 18:10:41 2022 -0500
N2653 char8_t for C: Language support
This patch implements the core language and compiler dependent library
changes proposed in WG14 N2653 for C2X. The changes include:
- Change of type for UTF-8 string literals from array of const char to
array of const char8_t (unsigned char).
- A new atomic_char8_t typedef.
- A new ATOMIC_CHAR8_T_LOCK_FREE macro defined in terms of the existing
__GCC_ATOMIC_CHAR8_T_LOCK_FREE predefined macro.
diff --git a/gcc/c-family/c-lex.c b/gcc/c-family/c-lex.c
index 2651331e683..0b3debbb9bd 100644
--- a/gcc/c-family/c-lex.c
+++ b/gcc/c-family/c-lex.c
@@ -1352,7 +1352,14 @@ lex_string (const cpp_token *tok, tree *valp, bool objc_string, bool translate)
default:
case CPP_STRING:
case CPP_UTF8STRING:
- value = build_string (1, "");
+ if (type == CPP_UTF8STRING && flag_char8_t)
+ {
+ value = build_string (TYPE_PRECISION (char8_type_node)
+ / TYPE_PRECISION (char_type_node),
+ ""); /* char8_t is 8 bits */
+ }
+ else
+ value = build_string (1, "");
break;
case CPP_STRING16:
value = build_string (TYPE_PRECISION (char16_type_node)
@@ -1425,10 +1432,10 @@ lex_charconst (const cpp_token *token)
type = char16_type_node;
else if (token->type == CPP_UTF8CHAR)
{
- if (!c_dialect_cxx ())
- type = unsigned_char_type_node;
- else if (flag_char8_t)
+ if (flag_char8_t)
type = char8_type_node;
+ else if (!c_dialect_cxx ())
+ type = unsigned_char_type_node;
else
type = char_type_node;
}
diff --git a/gcc/c-family/c-opts.c b/gcc/c-family/c-opts.c
index 4c20e44f5b5..bd96e1319ad 100644
--- a/gcc/c-family/c-opts.c
+++ b/gcc/c-family/c-opts.c
@@ -1060,9 +1060,9 @@ c_common_post_options (const char **pfilename)
if (flag_sized_deallocation == -1)
flag_sized_deallocation = (cxx_dialect >= cxx14);
- /* char8_t support is new in C++20. */
+ /* char8_t support is implicitly enabled in C++20 and C2x. */
if (flag_char8_t == -1)
- flag_char8_t = (cxx_dialect >= cxx20);
+ flag_char8_t = (cxx_dialect >= cxx20) || flag_isoc2x;
if (flag_extern_tls_init)
{
diff --git a/gcc/c/c-parser.c b/gcc/c/c-parser.c
index b09ad307acd..4239633e295 100644
--- a/gcc/c/c-parser.c
+++ b/gcc/c/c-parser.c
@@ -7439,7 +7439,14 @@ c_parser_string_literal (c_parser *parser, bool translate, bool wide_ok)
default:
case CPP_STRING:
case CPP_UTF8STRING:
- value = build_string (1, "");
+ if (type == CPP_UTF8STRING && flag_char8_t)
+ {
+ value = build_string (TYPE_PRECISION (char8_type_node)
+ / TYPE_PRECISION (char_type_node),
+ ""); /* char8_t is 8 bits */
+ }
+ else
+ value = build_string (1, "");
break;
case CPP_STRING16:
value = build_string (TYPE_PRECISION (char16_type_node)
@@ -7464,9 +7471,14 @@ c_parser_string_literal (c_parser *parser, bool translate, bool wide_ok)
{
default:
case CPP_STRING:
- case CPP_UTF8STRING:
TREE_TYPE (value) = char_array_type_node;
break;
+ case CPP_UTF8STRING:
+ if (flag_char8_t)
+ TREE_TYPE (value) = char8_array_type_node;
+ else
+ TREE_TYPE (value) = char_array_type_node;
+ break;
case CPP_STRING16:
TREE_TYPE (value) = char16_array_type_node;
break;
diff --git a/gcc/c/c-typeck.c b/gcc/c/c-typeck.c
index 78a6c68aaa6..b4eeea545a9 100644
--- a/gcc/c/c-typeck.c
+++ b/gcc/c/c-typeck.c
@@ -8028,7 +8028,7 @@ digest_init (location_t init_loc, tree type, tree init, tree origtype,
if (char_array)
{
- if (typ2 != char_type_node)
+ if (typ2 != char_type_node && typ2 != char8_type_node)
incompat_string_cst = true;
}
else if (!comptypes (typ1, typ2))
diff --git a/gcc/ginclude/stdatomic.h b/gcc/ginclude/stdatomic.h
index 23c07be2a48..b36703b2dc2 100644
--- a/gcc/ginclude/stdatomic.h
+++ b/gcc/ginclude/stdatomic.h
@@ -49,6 +49,10 @@ typedef _Atomic long atomic_long;
typedef _Atomic unsigned long atomic_ulong;
typedef _Atomic long long atomic_llong;
typedef _Atomic unsigned long long atomic_ullong;
+#if (defined(__CHAR8_TYPE__) \
+ && (defined(_GNU_SOURCE) || defined(_ISOC2X_SOURCE)))
+typedef _Atomic __CHAR8_TYPE__ atomic_char8_t;
+#endif
typedef _Atomic __CHAR16_TYPE__ atomic_char16_t;
typedef _Atomic __CHAR32_TYPE__ atomic_char32_t;
typedef _Atomic __WCHAR_TYPE__ atomic_wchar_t;
@@ -97,6 +101,10 @@ extern void atomic_signal_fence (memory_order);
#define ATOMIC_BOOL_LOCK_FREE __GCC_ATOMIC_BOOL_LOCK_FREE
#define ATOMIC_CHAR_LOCK_FREE __GCC_ATOMIC_CHAR_LOCK_FREE
+#if (defined(__GCC_ATOMIC_CHAR8_T_LOCK_FREE) \
+ && (defined(_GNU_SOURCE) || defined(_ISOC2X_SOURCE)))
+#define ATOMIC_CHAR8_T_LOCK_FREE __GCC_ATOMIC_CHAR8_T_LOCK_FREE
+#endif
#define ATOMIC_CHAR16_T_LOCK_FREE __GCC_ATOMIC_CHAR16_T_LOCK_FREE
#define ATOMIC_CHAR32_T_LOCK_FREE __GCC_ATOMIC_CHAR32_T_LOCK_FREE
#define ATOMIC_WCHAR_T_LOCK_FREE __GCC_ATOMIC_WCHAR_T_LOCK_FREE
