libstdc++: Declare std::c8rtomb and std::mbrtoc8 if provided by the C library

This patch completes implementation of the C++20 proposal P0482R6 [1] by
adding declarations of std::c8rtomb() and std::mbrtoc8() in <cuchar> if
provided by the C library in <uchar.h>.

This patch addresses feedback provided in response to a previous patch
submission [2].

Autoconf changes determine if the C library declares c8rtomb and mbrtoc8
at global scope when uchar.h is included and compiled with either
-fchar8_t or -std=c++20. New _GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_FCHAR8_T
and _GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_CXX20 configuration macros
reflect the probe results. The <cuchar> header declares these functions
in the std namespace only if available and the _GLIBCXX_USE_CHAR8_T
configuration macro is defined (by default it is defined if the C++20
__cpp_char8_t feature test macro is defined)

Patches to glibc to implement c8rtomb and mbrtoc8 have been submitted [3].

New tests validate the presence of these declarations. The tests pass
trivially if the C library does not provide these functions. Otherwise
they ensure that the functions are declared when <cuchar> is included
and either -fchar8_t or -std=c++20 is enabled.

1]: WG21 P0482R6
      "char8_t: A type for UTF-8 characters and strings (Revision 6)"
      https://wg21.link/p0482r6

[2]: [PATCH] C++ P0482R6 char8_t: declare std::c8rtomb and std::mbrtoc8
if provided by the C library
      https://gcc.gnu.org/pipermail/libstdc++/2021-June/052685.html

[3]: "C++20 P0482R6 and C2X N2653"
      [Patch 0/3]:
https://sourceware.org/pipermail/libc-alpha/2022-January/135061.html
      [Patch 1/3]:
https://sourceware.org/pipermail/libc-alpha/2022-January/135062.html
      [Patch 2/3]:
https://sourceware.org/pipermail/libc-alpha/2022-January/135063.html
      [Patch 3/3]:
https://sourceware.org/pipermail/libc-alpha/2022-January/135064.html

libstdc++-v3/ChangeLog:

	* acinclude.m4: Define config macros if uchar.h provides
	c8rtomb() and mbrtoc8().
	* config.h.in: Regenerate.
	* configure: Regenerate.
	* include/c_compatibility/uchar.h (c8rtomb, mbrtoc8): Define.
	* include/c_global/cuchar (c8rtomb, mbrtoc8): Likewise.
	* include/c_std/cuchar (c8rtomb, mbrtoc8): Likewise.
	* testsuite/21_strings/headers/cuchar/functions_std_cxx20.cc:
	New test.
	* testsuite/21_strings/headers/cuchar/functions_std_fchar8_t.cc:
	New test.

diff --git a/libstdc++-v3/acinclude.m4 b/libstdc++-v3/acinclude.m4
index 930861e..d996477 100644 (file)
--- a/libstdc++-v3/acinclude.m4
+++ b/libstdc++-v3/acinclude.m4
@@ -2044,6 +2044,50 @@ AC_DEFUN([GLIBCXX_CHECK_UCHAR_H], [
              namespace std in <cuchar>.])
   fi
 
+  CXXFLAGS="$CXXFLAGS -fchar8_t"
+  if test x"$ac_has_uchar_h" = x"yes"; then
+    AC_MSG_CHECKING([for c8rtomb and mbrtoc8 in <uchar.h> with -fchar8_t])
+    AC_TRY_COMPILE([#include <uchar.h>
+                   namespace test
+                   {
+                     using ::c8rtomb;
+                     using ::mbrtoc8;
+                   }
+                  ],
+                  [], [ac_uchar_c8rtomb_mbrtoc8_fchar8_t=yes],
+                      [ac_uchar_c8rtomb_mbrtoc8_fchar8_t=no])
+  else
+    ac_uchar_c8rtomb_mbrtoc8_fchar8_t=no
+  fi
+  AC_MSG_RESULT($ac_uchar_c8rtomb_mbrtoc8_fchar8_t)
+  if test x"$ac_uchar_c8rtomb_mbrtoc8_fchar8_t" = x"yes"; then
+    AC_DEFINE(_GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_FCHAR8_T, 1,
+             [Define if c8rtomb and mbrtoc8 functions in <uchar.h> should be
+             imported into namespace std in <cuchar> for -fchar8_t.])
+  fi
+
+  CXXFLAGS="$CXXFLAGS -std=c++20"
+  if test x"$ac_has_uchar_h" = x"yes"; then
+    AC_MSG_CHECKING([for c8rtomb and mbrtoc8 in <uchar.h> with -std=c++20])
+    AC_TRY_COMPILE([#include <uchar.h>
+                   namespace test
+                   {
+                     using ::c8rtomb;
+                     using ::mbrtoc8;
+                   }
+                  ],
+                  [], [ac_uchar_c8rtomb_mbrtoc8_cxx20=yes],
+                      [ac_uchar_c8rtomb_mbrtoc8_cxx20=no])
+  else
+    ac_uchar_c8rtomb_mbrtoc8_cxx20=no
+  fi
+  AC_MSG_RESULT($ac_uchar_c8rtomb_mbrtoc8_cxx20)
+  if test x"$ac_uchar_c8rtomb_mbrtoc8_cxx20" = x"yes"; then
+    AC_DEFINE(_GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_CXX20, 1,
+             [Define if c8rtomb and mbrtoc8 functions in <uchar.h> should be
+             imported into namespace std in <cuchar> for C++20.])
+  fi
+
   CXXFLAGS="$ac_save_CXXFLAGS"
   AC_LANG_RESTORE
 ])

diff --git a/libstdc++-v3/config.h.in b/libstdc++-v3/config.h.in
index 168961a..235d256 100644 (file)
--- a/libstdc++-v3/config.h.in
+++ b/libstdc++-v3/config.h.in
@@ -1010,6 +1010,14 @@
 /* Define if obsolescent tmpnam is available in <stdio.h>. */
 #undef _GLIBCXX_USE_TMPNAM
 
+/* Define if c8rtomb and mbrtoc8 functions in <uchar.h> should be imported
+   into namespace std in <cuchar> for C++20. */
+#undef _GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_CXX20
+
+/* Define if c8rtomb and mbrtoc8 functions in <uchar.h> should be imported
+   into namespace std in <cuchar> for -fchar8_t. */
+#undef _GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_FCHAR8_T
+
 /* Define if utime is available in <utime.h>. */
 #undef _GLIBCXX_USE_UTIME
 

diff --git a/libstdc++-v3/configure b/libstdc++-v3/configure
index 4c9be00..6b7cd24 100755 (executable)
--- a/libstdc++-v3/configure
+++ b/libstdc++-v3/configure
@@ -19151,6 +19151,82 @@ $as_echo "#define _GLIBCXX_USE_C11_UCHAR_CXX11 1" >>confdefs.h
 
   fi
 
+  CXXFLAGS="$CXXFLAGS -fchar8_t"
+  if test x"$ac_has_uchar_h" = x"yes"; then
+    { $as_echo "$as_me:${as_lineno-$LINENO}: checking for c8rtomb and mbrtoc8 in <uchar.h> with -fchar8_t" >&5
+$as_echo_n "checking for c8rtomb and mbrtoc8 in <uchar.h> with -fchar8_t... " >&6; }
+    cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <uchar.h>
+                   namespace test
+                   {
+                     using ::c8rtomb;
+                     using ::mbrtoc8;
+                   }
+
+int
+main ()
+{
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_cxx_try_compile "$LINENO"; then :
+  ac_uchar_c8rtomb_mbrtoc8_fchar8_t=yes
+else
+  ac_uchar_c8rtomb_mbrtoc8_fchar8_t=no
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+  else
+    ac_uchar_c8rtomb_mbrtoc8_fchar8_t=no
+  fi
+  { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_uchar_c8rtomb_mbrtoc8_fchar8_t" >&5
+$as_echo "$ac_uchar_c8rtomb_mbrtoc8_fchar8_t" >&6; }
+  if test x"$ac_uchar_c8rtomb_mbrtoc8_fchar8_t" = x"yes"; then
+
+$as_echo "#define _GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_FCHAR8_T 1" >>confdefs.h
+
+  fi
+
+  CXXFLAGS="$CXXFLAGS -std=c++20"
+  if test x"$ac_has_uchar_h" = x"yes"; then
+    { $as_echo "$as_me:${as_lineno-$LINENO}: checking for c8rtomb and mbrtoc8 in <uchar.h> with -std=c++20" >&5
+$as_echo_n "checking for c8rtomb and mbrtoc8 in <uchar.h> with -std=c++20... " >&6; }
+    cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+#include <uchar.h>
+                   namespace test
+                   {
+                     using ::c8rtomb;
+                     using ::mbrtoc8;
+                   }
+
+int
+main ()
+{
+
+  ;
+  return 0;
+}
+_ACEOF
+if ac_fn_cxx_try_compile "$LINENO"; then :
+  ac_uchar_c8rtomb_mbrtoc8_cxx20=yes
+else
+  ac_uchar_c8rtomb_mbrtoc8_cxx20=no
+fi
+rm -f core conftest.err conftest.$ac_objext conftest.$ac_ext
+  else
+    ac_uchar_c8rtomb_mbrtoc8_cxx20=no
+  fi
+  { $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_uchar_c8rtomb_mbrtoc8_cxx20" >&5
+$as_echo "$ac_uchar_c8rtomb_mbrtoc8_cxx20" >&6; }
+  if test x"$ac_uchar_c8rtomb_mbrtoc8_cxx20" = x"yes"; then
+
+$as_echo "#define _GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_CXX20 1" >>confdefs.h
+
+  fi
+
   CXXFLAGS="$ac_save_CXXFLAGS"
   ac_ext=c
 ac_cpp='$CPP $CPPFLAGS'

diff --git a/libstdc++-v3/include/c_compatibility/uchar.h b/libstdc++-v3/include/c_compatibility/uchar.h
index ac65730..bf25538 100644 (file)
--- a/libstdc++-v3/include/c_compatibility/uchar.h
+++ b/libstdc++-v3/include/c_compatibility/uchar.h
@@ -33,6 +33,14 @@
 
 #ifdef _GLIBCXX_NAMESPACE_C
 
+#if (_GLIBCXX_USE_CHAR8_T \
+     && (_GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_FCHAR8_T \
+        || (__cplusplus >= 202002 \
+            && _GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_CXX20)))
+using std::mbrtoc8;
+using std::c8rtomb;
+#endif // _GLIBCXX_USE_CHAR8_T
+
 #if _GLIBCXX_USE_C11_UCHAR_CXX11
 using std::mbrtoc16;
 using std::c16rtomb;

diff --git a/libstdc++-v3/include/c_global/cuchar b/libstdc++-v3/include/c_global/cuchar
index b91ea66..bca2540 100644 (file)
--- a/libstdc++-v3/include/c_global/cuchar
+++ b/libstdc++-v3/include/c_global/cuchar
@@ -48,10 +48,41 @@
 #include <bits/c++config.h>
 #include <cwchar>
 
-#if _GLIBCXX_USE_C11_UCHAR_CXX11
+#if (_GLIBCXX_USE_C11_UCHAR_CXX11 \
+     || (_GLIBCXX_USE_CHAR8_T \
+        && (_GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_FCHAR8_T \
+            || (__cplusplus >= 202002 \
+                && _GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_CXX20))))
 
 #include <uchar.h>
 
+#endif
+
+
+// Support for mbrtoc8 and c8rtomb is conditioned on support by the C library.
+#if (_GLIBCXX_USE_CHAR8_T \
+     && (_GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_FCHAR8_T \
+        || (__cplusplus >= 202002 \
+            && _GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_CXX20)))
+
+#undef mbrtoc8
+#undef c8rtomb
+
+namespace std _GLIBCXX_VISIBILITY(default)
+{
+_GLIBCXX_BEGIN_NAMESPACE_VERSION
+
+  using ::mbrtoc8;
+  using ::c8rtomb;
+
+_GLIBCXX_END_NAMESPACE_VERSION
+} // namespace std
+
+#endif // _GLIBCXX_USE_CHAR8_T
+
+
+#if _GLIBCXX_USE_C11_UCHAR_CXX11
+
 // Get rid of those macros defined in <uchar.h> in lieu of real functions.
 #undef mbrtoc16
 #undef c16rtomb

diff --git a/libstdc++-v3/include/c_std/cuchar b/libstdc++-v3/include/c_std/cuchar
index 05e1ffa..241009a 100644 (file)
--- a/libstdc++-v3/include/c_std/cuchar
+++ b/libstdc++-v3/include/c_std/cuchar
@@ -50,7 +50,42 @@
 
 #if _GLIBCXX_USE_C11_UCHAR_CXX11
 
+#if (_GLIBCXX_USE_C11_UCHAR_CXX11 \
+     || (_GLIBCXX_USE_CHAR8_T \
+        && (_GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_FCHAR8_T \
+            || (__cplusplus >= 202002 \
+                && _GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_CXX20))))
+ 
 #include <uchar.h>
+ 
+#endif
+
+
+// Support for mbrtoc8 and c8rtomb is conditioned on support by the C library.
+#if (_GLIBCXX_USE_CHAR8_T \
+     && (_GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_FCHAR8_T \
+        || (__cplusplus >= 202002 \
+            && _GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_CXX20)))
+
+// Get rid of those macros defined in <uchar.h> in lieu of real functions.
+#undef mbrtoc8
+#undef c8rtomb
+
+namespace std _GLIBCXX_VISIBILITY(default)
+{
+_GLIBCXX_BEGIN_NAMESPACE_VERSION
+
+  using ::mbrtoc8;
+  using ::c8rtomb;
+
+_GLIBCXX_END_NAMESPACE_VERSION
+} // namespace std
+
+#endif // _GLIBCXX_USE_CHAR8_T
+
+
+#if _GLIBCXX_USE_C11_UCHAR_CXX11
+
 
 // Get rid of those macros defined in <uchar.h> in lieu of real functions.
 #undef mbrtoc16

diff --git a/libstdc++-v3/testsuite/21_strings/headers/cuchar/functions_std_cxx20.cc b/libstdc++-v3/testsuite/21_strings/headers/cuchar/functions_std_cxx20.cc
new file mode 100644 (file)
index 0000000..df68fb7
--- /dev/null
+++ b/libstdc++-v3/testsuite/21_strings/headers/cuchar/functions_std_cxx20.cc
@@ -0,0 +1,12 @@
+// { dg-options "-std=c++20" }
+// { dg-do compile { target c++20 } }
+
+#include <cuchar>
+
+namespace gnu
+{
+#if _GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_CXX20
+  using std::mbrtoc8;
+  using std::c8rtomb;
+#endif // _GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_CXX20
+}

diff --git a/libstdc++-v3/testsuite/21_strings/headers/cuchar/functions_std_fchar8_t.cc b/libstdc++-v3/testsuite/21_strings/headers/cuchar/functions_std_fchar8_t.cc
new file mode 100644 (file)
index 0000000..a780583
--- /dev/null
+++ b/libstdc++-v3/testsuite/21_strings/headers/cuchar/functions_std_fchar8_t.cc
@@ -0,0 +1,12 @@
+// { dg-options "-fchar8_t" }
+// { dg-do compile { target c++11 } }
+
+#include <cuchar>
+
+namespace gnu
+{
+#if _GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_FCHAR8_T
+  using std::mbrtoc8;
+  using std::c8rtomb;
+#endif // _GLIBCXX_USE_UCHAR_C8RTOMB_MBRTOC8_FCHAR8_T
+}