[libc++] Fix support for multibyte thousands_sep and decimal_point in moneypunct_byname and numpunct_byname.

Summary:
The underlying C locales provide the `thousands_sep` and `decimal_point` as strings, possible with more than one character. We currently don't handle this case even for `wchar_t`.

This patch properly converts the mbs -> wide character for `moneypunct_byname<wchar_t>`. For the `moneypunct_byname<char>` case we attempt to narrow the WC and if that fails we also attempt to translate it to some reasonable value. For example we translate U00A0 (non-breaking space) into U0020 (regular space). If none of these conversions succeed then we simply allow the base class to provide a fallback value.


Reviewers: mclow.lists, EricWF

Subscribers: vangyzen, george.burgess.iv, cfe-commits

Differential Revision: https://reviews.llvm.org/D24218

llvm-svn: 289347

4 files changed, 49 insertions, 28 deletions

diff --git a/libcxx/test/std/localization/locale.categories/category.monetary/locale.moneypunct.byname/decimal_point.pass.cpp b/libcxx/test/std/localization/locale.categories/category.monetary/locale.moneypunct.byname/decimal_point.pass.cpp
index 8270377f3ab..4051d451fcb 100644
--- a/libcxx/test/std/localization/locale.categories/category.monetary/locale.moneypunct.byname/decimal_point.pass.cpp
+++ b/libcxx/test/std/localization/locale.categories/category.monetary/locale.moneypunct.byname/decimal_point.pass.cpp
@@ -12,9 +12,6 @@
 // REQUIRES: locale.ru_RU.UTF-8
 // REQUIRES: locale.zh_CN.UTF-8
 
-// Russia uses ',' for the decimal separator. GLIBC returns '.'
-// XFAIL: linux
-
 // <locale>
 
 // class moneypunct_byname<charT, International>
@@ -25,6 +22,7 @@
 #include <limits>
 #include <cassert>
 
+#include "test_macros.h"
 #include "platform_support.h" // locale name macros
 
 class Fnf
@@ -111,22 +109,29 @@ int main()
         Fwt f(LOCALE_fr_FR_UTF_8, 1);
         assert(f.decimal_point() == L',');
     }
-
+// GLIBC 2.23 uses '.' as the decimal point while other C libraries use ','
+#ifndef TEST_HAS_GLIBC
+    const char sep = ',';
+    const wchar_t wsep = L',';
+#else
+    const char sep = '.';
+    const wchar_t wsep = L'.';
+#endif
     {
         Fnf f(LOCALE_ru_RU_UTF_8, 1);
-        assert(f.decimal_point() == ',');
+        assert(f.decimal_point() == sep);
     }
     {
         Fnt f(LOCALE_ru_RU_UTF_8, 1);
-        assert(f.decimal_point() == ',');
+        assert(f.decimal_point() == sep);
     }
     {
         Fwf f(LOCALE_ru_RU_UTF_8, 1);
-        assert(f.decimal_point() == L',');
+        assert(f.decimal_point() == wsep);
     }
     {
         Fwt f(LOCALE_ru_RU_UTF_8, 1);
-        assert(f.decimal_point() == L',');
+        assert(f.decimal_point() == wsep);
     }
 
     {
diff --git a/libcxx/test/std/localization/locale.categories/category.monetary/locale.moneypunct.byname/thousands_sep.pass.cpp b/libcxx/test/std/localization/locale.categories/category.monetary/locale.moneypunct.byname/thousands_sep.pass.cpp
index a8782832de5..aa585a436e6 100644
--- a/libcxx/test/std/localization/locale.categories/category.monetary/locale.moneypunct.byname/thousands_sep.pass.cpp
+++ b/libcxx/test/std/localization/locale.categories/category.monetary/locale.moneypunct.byname/thousands_sep.pass.cpp
@@ -18,16 +18,11 @@
 
 // charT thousands_sep() const;
 
-// Failure related to GLIBC's use of U00A0 as mon_thousands_sep
-// and U002E as mon_decimal_point.
-// TODO: U00A0 should be investigated.
-// Possibly related to https://gcc.gnu.org/bugzilla/show_bug.cgi?id=16006
-// XFAIL: linux-gnu
-
 #include <locale>
 #include <limits>
 #include <cassert>
 
+#include "test_macros.h"
 #include "platform_support.h" // locale name macros
 
 class Fnf
@@ -114,22 +109,34 @@ int main()
         Fwt f(LOCALE_fr_FR_UTF_8, 1);
         assert(f.thousands_sep() == L' ');
     }
-
+// The below tests work around GLIBC's use of U00A0 as mon_thousands_sep
+// and U002E as mon_decimal_point.
+// TODO: Fix thousands_sep for 'char'.
+// related to https://gcc.gnu.org/bugzilla/show_bug.cgi?id=16006
+#ifndef TEST_HAS_GLIBC
+    const char sep = ' ';
+    const wchar_t wsep = L' ';
+#else
+    // FIXME libc++ specifically works around \u00A0 by translating it into
+    // a regular space.
+    const char sep = ' ';
+    const wchar_t wsep = L'\u00A0';
+#endif
     {
         Fnf f(LOCALE_ru_RU_UTF_8, 1);
-        assert(f.thousands_sep() == ' ');
+        assert(f.thousands_sep() == sep);
     }
     {
         Fnt f(LOCALE_ru_RU_UTF_8, 1);
-        assert(f.thousands_sep() == ' ');
+        assert(f.thousands_sep() == sep);
     }
     {
         Fwf f(LOCALE_ru_RU_UTF_8, 1);
-        assert(f.thousands_sep() == L' ');
+        assert(f.thousands_sep() == wsep);
     }
     {
         Fwt f(LOCALE_ru_RU_UTF_8, 1);
-        assert(f.thousands_sep() == L' ');
+        assert(f.thousands_sep() == wsep);
     }
 
     {
diff --git a/libcxx/test/std/localization/locale.categories/facet.numpunct/locale.numpunct.byname/grouping.pass.cpp b/libcxx/test/std/localization/locale.categories/facet.numpunct/locale.numpunct.byname/grouping.pass.cpp
index d5112a9508b..f3df52a21b8 100644
--- a/libcxx/test/std/localization/locale.categories/facet.numpunct/locale.numpunct.byname/grouping.pass.cpp
+++ b/libcxx/test/std/localization/locale.categories/facet.numpunct/locale.numpunct.byname/grouping.pass.cpp
@@ -16,12 +16,10 @@
 
 // string grouping() const;
 
-// TODO: investigation needed
-// XFAIL: linux-gnu
-
 #include <locale>
 #include <cassert>
 
+#include "test_macros.h"
 #include "platform_support.h" // locale name macros
 
 int main()
@@ -54,15 +52,20 @@ int main()
     }
     {
         std::locale l(LOCALE_fr_FR_UTF_8);
+#if defined(TEST_HAS_GLIBC)
+        const char* const group = "\3";
+#else
+        const char* const group = "\x7f";
+#endif
         {
             typedef char C;
             const std::numpunct<C>& np = std::use_facet<std::numpunct<C> >(l);
-            assert(np.grouping() == "\x7F");
+            assert(np.grouping() ==  group);
         }
         {
             typedef wchar_t C;
             const std::numpunct<C>& np = std::use_facet<std::numpunct<C> >(l);
-            assert(np.grouping() == "\x7F");
+            assert(np.grouping() == group);
         }
     }
 }
diff --git a/libcxx/test/std/localization/locale.categories/facet.numpunct/locale.numpunct.byname/thousands_sep.pass.cpp b/libcxx/test/std/localization/locale.categories/facet.numpunct/locale.numpunct.byname/thousands_sep.pass.cpp
index b1bd03ff736..38cbcfda4f0 100644
--- a/libcxx/test/std/localization/locale.categories/facet.numpunct/locale.numpunct.byname/thousands_sep.pass.cpp
+++ b/libcxx/test/std/localization/locale.categories/facet.numpunct/locale.numpunct.byname/thousands_sep.pass.cpp
@@ -16,12 +16,11 @@
 
 // char_type thousands_sep() const;
 
-// TODO: investigation needed
-// XFAIL: linux-gnu
 
 #include <locale>
 #include <cassert>
 
+#include "test_macros.h"
 #include "platform_support.h" // locale name macros
 
 int main()
@@ -54,15 +53,22 @@ int main()
     }
     {
         std::locale l(LOCALE_fr_FR_UTF_8);
+#if defined(TEST_HAS_GLIBC)
+        const char sep = ' ';
+        const wchar_t wsep = L' ';
+#else
+        const char sep = ',';
+        const wchar_t wsep = L',';
+#endif
         {
             typedef char C;
             const std::numpunct<C>& np = std::use_facet<std::numpunct<C> >(l);
-            assert(np.thousands_sep() == ',');
+            assert(np.thousands_sep() == sep);
         }
         {
             typedef wchar_t C;
             const std::numpunct<C>& np = std::use_facet<std::numpunct<C> >(l);
-            assert(np.thousands_sep() == L',');
+            assert(np.thousands_sep() == wsep);
         }
     }
 }