This patch implements the core language and compiler dependent library
changes proposed in WG14 N2653 [1] for C. The changes include:
- Use of the existing -fchar8_t and -fno-char8_t options to opt-in to
(or opt-out of) the following changes when compiling C code.
- Change of type for UTF-8 string literals from array of char to array
of char8_t (unsigned char).
- A new atomic_char8_t typedef.
- A new ATOMIC_CHAR8_T_LOCK_FREE macro defined in terms of a new
predefined ATOMIC_CHAR8_T_LOCK_FREE macro.
When -fchar8_t support is enabled for non-C++ modes, the _CHAR8_T_SOURCE
macro is predefined. This is the mechanism proposed to glibc to opt-in
to declarations of the char8_t typedef and c8rtomb and mbrtoc8 functions
proposed in N2653. See [2].
Tested on Linux x86_64.
gcc/ChangeLog:
2021-05-31 Tom Honermann <t...@honermann.net>
* ginclude/stdatomic.h (atomic_char8_t, ATOMIC_CHAR8_T_LOCK_FREE):
New typedef and macro.
gcc/c/ChangeLog:
2021-05-31 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): Handle initialization of an array
of character type by a string literal with type array of
unsigned char.
gcc/c-family/ChangeLog:
2021-05-31 Tom Honermann <t...@honermann.net>
* c-cppbuiltin.c (c_cpp_builtins): Define _CHAR8_T_SOURCE if
char8_t support is enabled in non-C++ language modes.
* c-lex.c (lex_string): Use char8_t as the type of
CPP_UTF8STRING when char8_t support is enabled.
* c-opts.c (c_common_handle_option): Inform the preprocessor if
char8_t support is enabled.
* c.opt (fchar8_t): Enable for C language modes.
libcpp/ChangeLog:
2021-05-31 Tom Honermann <t...@honermann.net>
* include/cpplib.h (cpp_options): Add char8.
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
[2]: C++20 P0482R6 and C2X N2653: support for char8_t, mbrtoc8(), and
c8rtomb().
[Patch 0]:
https://sourceware.org/pipermail/libc-alpha/2021-June/127230.html
[Patch 1]:
https://sourceware.org/pipermail/libc-alpha/2021-June/127231.html
[Patch 2]:
https://sourceware.org/pipermail/libc-alpha/2021-June/127232.html
[Patch 3]:
https://sourceware.org/pipermail/libc-alpha/2021-June/127233.html
commit c4260c7c49822522945377cc2fb93ee9830cefc8
Author: Tom Honermann <t...@honermann.net>
Date: Sat Feb 13 09:02:34 2021 -0500
N2653 char8_t for C: Language support
This patch implements the core language and compiler dependent library
changes proposed in WG14 N2653 for C. The changes include:
- Use of the existing -fchar8_t and -fno-char8_t options to opt-in to
(or opt-out of) the following changes when compiling C code.
- 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 a new
predefined ATOMIC_CHAR8_T_LOCK_FREE macro.
When -fchar8_t support is enabled for non-C++ modes, the _CHAR8_T_SOURCE
macro is predefined. This is the mechanism proposed to glibc to opt-in
to declarations of the char8_t typedef and c8rtomb and mbrtoc8 functions
proposed in N2653.
diff --git a/gcc/c-family/c-cppbuiltin.c b/gcc/c-family/c-cppbuiltin.c
index 42b7604c9ac..3e944ec2b86 100644
--- a/gcc/c-family/c-cppbuiltin.c
+++ b/gcc/c-family/c-cppbuiltin.c
@@ -1467,6 +1467,11 @@ c_cpp_builtins (cpp_reader *pfile)
if (flag_iso)
cpp_define (pfile, "__STRICT_ANSI__");
+ /* Express intent for char8_t support in C (not C++) to the C library if
+ requested. */
+ if (!c_dialect_cxx () && flag_char8_t)
+ cpp_define (pfile, "_CHAR8_T_SOURCE");
+
if (!flag_signed_char)
cpp_define (pfile, "__CHAR_UNSIGNED__");
diff --git a/gcc/c-family/c-lex.c b/gcc/c-family/c-lex.c
index c44e7a13489..e30e44e9f5c 100644
--- a/gcc/c-family/c-lex.c
+++ b/gcc/c-family/c-lex.c
@@ -1335,7 +1335,14 @@ 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)
diff --git a/gcc/c-family/c-opts.c b/gcc/c-family/c-opts.c
index 60b5802722c..eefc607dac6 100644
--- a/gcc/c-family/c-opts.c
+++ b/gcc/c-family/c-opts.c
@@ -718,6 +718,10 @@ c_common_handle_option (size_t scode, const char *arg, HOST_WIDE_INT value,
case OPT_v:
verbose = true;
break;
+
+ case OPT_fchar8_t:
+ cpp_opts->char8 = value;
+ break;
}
switch (c_language)
diff --git a/gcc/c-family/c.opt b/gcc/c-family/c.opt
index 91929706aff..eadb2468aa9 100644
--- a/gcc/c-family/c.opt
+++ b/gcc/c-family/c.opt
@@ -1451,8 +1451,8 @@ C ObjC C++ ObjC++
Where shorter, use canonicalized paths to systems headers.
fchar8_t
-C++ ObjC++ Var(flag_char8_t) Init(-1)
-Enable the char8_t fundamental type and use it as the type for UTF-8 string
+C ObjC C++ ObjC++ Var(flag_char8_t) Init(-1)
+Enable the char8_t type and use it as the type for UTF-8 string
and character literals.
fcheck-pointer-bounds
diff --git a/gcc/c/c-parser.c b/gcc/c/c-parser.c
index d71fd0abe90..501253d0ffe 100644
--- a/gcc/c/c-parser.c
+++ b/gcc/c/c-parser.c
@@ -7425,7 +7425,14 @@ 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)
@@ -7450,9 +7457,14 @@ 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 5f322874423..1fa95949919 100644
--- a/gcc/c/c-typeck.c
+++ b/gcc/c/c-typeck.c
@@ -7979,7 +7979,8 @@ 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 != unsigned_char_type_node) /* char8_t literal */
incompat_string_cst = true;
}
else if (!comptypes (typ1, typ2))
diff --git a/gcc/ginclude/stdatomic.h b/gcc/ginclude/stdatomic.h
index 23c07be2a48..6629902a666 100644
--- a/gcc/ginclude/stdatomic.h
+++ b/gcc/ginclude/stdatomic.h
@@ -49,6 +49,9 @@ 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_T_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 +100,9 @@ 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(_CHAR8_T_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
diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h
index 7e840635a38..4c90f8bbbda 100644
--- a/libcpp/include/cpplib.h
+++ b/libcpp/include/cpplib.h
@@ -358,6 +358,9 @@ struct cpp_options
/* Nonzero means process u8 prefixed character literals (UTF-8). */
unsigned char utf8_char_literals;
+ /* Nonzero means char8_t support is enabled. */
+ unsigned char char8;
+
/* Nonzero means process r/R raw strings. If this is set, uliterals
must be set as well. */
unsigned char rliterals;
