[libc++] Improve no wide characters configuration.

[Mordante]

Summary

When wide characters are supported libc++ manually translates a
narrow non-breaking space and a non-breaking space to a space.
This behaviour wasn't available when wide characters were disabled.
This enables an emulation for that configuration.

Updating the libc++ Docker image to Ubuntu Focal caused some breakage.
This was temporary disabled in D112737. This re-enables four of these
tests.

[ldionne]

Awesome, thanks a lot for looking into it!

libcxx/src/locale.cpp

4607–4613

This appears to be the same as the checked_string_to_char_convert function above -- could we hoist it out of the #if to avoid duplication?

[Mordante]

Addresses review comment.

[Mordante]

Thanks for the review. I'll give it another CI run before committing.

libcxx/src/locale.cpp

4546

Note I could have used an #else here. But since this #ifdef isn't related to the #ifndef above using an #else feels wrong.

4607–4613

I was doubting between an #else in the original function or a copy. I now switched to the #else which addresses your issue.

libcxx/src/locale.cpp

static bool checked_string_to_wchar_convert(wchar_t& dest,
   if (ret == static_cast<size_t>(-1) || ret == static_cast<size_t>(-2)) {
     return false;
   }
   dest = out;
   return true;
 }
 #endif // _LIBCPP_HAS_NO_WIDE_CHARACTERS
 
+#ifdef _LIBCPP_HAS_NO_WIDE_CHARACTERS
+static bool is_narrow_non_breaking_space(const char* ptr) {
+  // https://www.fileformat.info/info/unicode/char/202f/index.htm
+  return ptr[0] == '\xe2' && ptr[1] == '\x80' && ptr[2] == '\xaf';
+}
+
+static bool is_non_breaking_space(const char* ptr) {
+  // https://www.fileformat.info/info/unicode/char/0a/index.htm
+  return ptr[0] == '\xc2' && ptr[1] == '\xa0';
+}
+#endif // _LIBCPP_HAS_NO_WIDE_CHARACTERS
+
 static bool checked_string_to_char_convert(char& dest,
                                            const char* ptr,
                                            locale_t __loc) {
   if (*ptr == '\0')
     return false;
   if (!ptr[1]) {
     dest = *ptr;
     return true;
#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
   case L'\u202F': // narrow non-breaking space
   case L'\u00A0': // non-breaking space
     dest = ' ';
     return true;
   default:
     return false;
   }
 #else // _LIBCPP_HAS_NO_WIDE_CHARACTERS
+  // FIXME: Work around specific multibyte sequences that we can reasonably
+  // translate into a different single byte.
+  if (is_narrow_non_breaking_space(ptr) || is_non_breaking_space(ptr)) {
+    dest = ' ';
+    return true;
+  }
+
   return false;
 #endif // _LIBCPP_HAS_NO_WIDE_CHARACTERS
   _LIBCPP_UNREACHABLE();
 }
 
 
 // numpunct<char> && numpunct<wchar_t>
 
 locale::id numpunct< char  >::id;
 #ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
 locale::id numpunct<wchar_t>::id;
 #endif
 
 numpunct<char>::numpunct(size_t refs)
     : locale::facet(refs),
       __decimal_point_('.'),
       __thousands_sep_(',')
 {
 }
 
 #ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
 numpunct<wchar_t>::numpunct(size_t refs)
     : locale::facet(refs),
       __decimal_point_(L'.'),
       __thousands_sep_(L',')

libcxx/test/std/localization/locale.categories/category.monetary/locale.money.get/locale.money.get.members/get_long_double_fr_FR.pass.cpp

 //===----------------------------------------------------------------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 // XFAIL: darwin
 
 // NetBSD does not support LC_MONETARY at the moment
 // XFAIL: netbsd
 
 // XFAIL: LIBCXX-WINDOWS-FIXME
 
-// TODO(mordante): Investigate these localization/format failures since updating the Docker image in CI
-// UNSUPPORTED: stdlib=libc++
-
 // REQUIRES: locale.fr_FR.UTF-8
 
 // <locale>
 
 // class money_get<charT, InputIterator>
 
 // iter_type get(iter_type b, iter_type e, bool intl, ios_base& iob,
 //               ios_base::iostate& err, long double& v) const;

libcxx/test/std/localization/locale.categories/category.monetary/locale.money.put/locale.money.put.members/put_long_double_fr_FR.pass.cpp

 //===----------------------------------------------------------------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 // XFAIL: darwin
 
 // NetBSD does not support LC_MONETARY at the moment
 // XFAIL: netbsd
 
 // XFAIL: LIBCXX-WINDOWS-FIXME
 
-// TODO(mordante): Investigate these localization/format failures since updating the Docker image in CI
-// UNSUPPORTED: stdlib=libc++
-
 // REQUIRES: locale.fr_FR.UTF-8
 
 // <locale>
 
 // class money_put<charT, OutputIterator>
 
 // iter_type put(iter_type s, bool intl, ios_base& f, char_type fill,
 //               long double units) const;

libcxx/test/std/localization/locale.categories/category.monetary/locale.moneypunct.byname/thousands_sep.pass.cpp

 //===----------------------------------------------------------------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 // NetBSD does not support LC_MONETARY at the moment
 // XFAIL: netbsd
 
 // XFAIL: LIBCXX-WINDOWS-FIXME
 
-// TODO(mordante): Investigate these localization/format failures since updating the Docker image in CI
-// UNSUPPORTED: stdlib=libc++
-
 // REQUIRES: locale.en_US.UTF-8
 // REQUIRES: locale.fr_FR.UTF-8
 // REQUIRES: locale.ru_RU.UTF-8
 // REQUIRES: locale.zh_CN.UTF-8
 
 // <locale>
 
 // class moneypunct_byname<charT, International>

libcxx/test/std/localization/locale.categories/facet.numpunct/locale.numpunct.byname/thousands_sep.pass.cpp

 //===----------------------------------------------------------------------===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 // NetBSD does not support LC_NUMERIC at the moment
 // XFAIL: netbsd
 
 // XFAIL: LIBCXX-WINDOWS-FIXME
 
-// TODO(mordante): Investigate these localization/format failures since updating the Docker image in CI
-// UNSUPPORTED: stdlib=libc++
-
 // REQUIRES: locale.en_US.UTF-8
 // REQUIRES: locale.fr_FR.UTF-8
 
 // <locale>
 
 // template <class charT> class numpunct_byname;
 
 // char_type thousands_sep() const;