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

[EricWF]

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.

[EricWF]

Remove secondary locale fix.

[george.burgess.iv]

Just a few drive-by nits. Thanks for the patch!

src/locale.cpp

5849

Are the newly-added braces necessary?

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

113

s/belowe/below

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

112–124

s/belowe/below/

[EricWF]

Address all inline comments.

[vangyzen]

src/locale.cpp

4339

While you're here, you might change char to wchar_t.

4348

Maybe fix the spelling of "localization".

[EricWF]

Address inline comments.

src/locale.cpp

 }
 
 // __widen_from_utf8<32>
 
 __widen_from_utf8<32>::~__widen_from_utf8()
 {
 }
 
+
+static bool checked_string_to_wchar_convert(wchar_t& dest,
+                                            const char* ptr,
+                                            __locale_struct* loc) {
+  if (*ptr == '\0')
+    return false;
+  mbstate_t mb = {};
+  wchar_t out;
+  size_t ret = __libcpp_mbrtowc_l(&out, ptr, strlen(ptr), &mb, loc);
+  if (ret == static_cast<size_t>(-1) || ret == static_cast<size_t>(-2)) {
+    return false;
+  }
+  dest = out;
+  return true;
+}
+
+static bool checked_string_to_char_convert(char& dest,
+                                           const char* ptr,
+                                           __locale_struct* __loc) {
+  if (*ptr == '\0')
+    return false;
+  if (!ptr[1]) {
+    dest = *ptr;
+    return true;
+  }
+  // First convert the MBS into a wide char then attempt to narrow it using
+  // wctob_l.
+  wchar_t wout;
+  if (!checked_string_to_wchar_convert(wout, ptr, __loc))
+    return false;
+  int res;
+  if ((res = __libcpp_wctob_l(wout, __loc)) != char_traits<char>::eof()) {
+    dest = res;
+    return true;
+  }
+  // FIXME: Work around specific multibyte sequences that we can reasonable
+  // translate into a different single byte.
+  switch (wout) {
+  case L'\u00A0': // non-breaking space
+    dest = ' ';
+    return true;
+  default:
+    return false;
+  }
+  _LIBCPP_UNREACHABLE();
+}
+
+
 // numpunct<char> && numpunct<wchar_t>
 
 locale::id numpunct< char  >::id;
 locale::id numpunct<wchar_t>::id;
 
 numpunct<char>::numpunct(size_t refs)
     : locale::facet(refs),
       __decimal_point_('.'),

     if (strcmp(nm, "C") != 0)
     {
         __locale_unique_ptr loc(newlocale(LC_ALL_MASK, nm, 0), freelocale);
         if (loc == nullptr)
             __throw_runtime_error("numpunct_byname<char>::numpunct_byname"
                                 " failed to construct for " + string(nm));
 
         lconv* lc = __libcpp_localeconv_l(loc.get());
-        if (*lc->decimal_point)
-            __decimal_point_ = *lc->decimal_point;
-        if (*lc->thousands_sep)
-            __thousands_sep_ = *lc->thousands_sep;
+        checked_string_to_char_convert(__decimal_point_, lc->decimal_point,
+                                       loc.get());
+        checked_string_to_char_convert(__thousands_sep_, lc->thousands_sep,
+                                       loc.get());
         __grouping_ = lc->grouping;
         // localization for truename and falsename is not available
     }
 }
 
 // numpunct_byname<wchar_t>
 
 numpunct_byname<wchar_t>::numpunct_byname(const char* nm, size_t refs)

 
 void
 numpunct_byname<wchar_t>::__init(const char* nm)
 {
     if (strcmp(nm, "C") != 0)
     {
         __locale_unique_ptr loc(newlocale(LC_ALL_MASK, nm, 0), freelocale);
         if (loc == nullptr)
-            __throw_runtime_error("numpunct_byname<char>::numpunct_byname"
+            __throw_runtime_error("numpunct_byname<wchar_t>::numpunct_byname"
                                 " failed to construct for " + string(nm));
 
         lconv* lc = __libcpp_localeconv_l(loc.get());
-        if (*lc->decimal_point)
-            __decimal_point_ = *lc->decimal_point;
-        if (*lc->thousands_sep)
-            __thousands_sep_ = *lc->thousands_sep;
+        checked_string_to_wchar_convert(__decimal_point_, lc->decimal_point,
+                                        loc.get());
+        checked_string_to_wchar_convert(__thousands_sep_, lc->thousands_sep,
+                                        loc.get());
         __grouping_ = lc->grouping;
-        // locallization for truename and falsename is not available
+        // localization for truename and falsename is not available
     }
 }
 
 // num_get helpers
 
 int
 __num_get_base::__get_base(ios_base& iob)
 {

 {
     typedef moneypunct<char, false> base;
     __locale_unique_ptr loc(newlocale(LC_ALL_MASK, nm, 0), freelocale);
     if (loc == nullptr)
         __throw_runtime_error("moneypunct_byname"
                             " failed to construct for " + string(nm));
 
     lconv* lc = __libcpp_localeconv_l(loc.get());
-    if (*lc->mon_decimal_point)
-        __decimal_point_ = *lc->mon_decimal_point;
-    else
-        __decimal_point_ = base::do_decimal_point();
-    if (*lc->mon_thousands_sep)
-        __thousands_sep_ = *lc->mon_thousands_sep;
-    else
-        __thousands_sep_ = base::do_thousands_sep();
+    if (!checked_string_to_char_convert(__decimal_point_,
+                                        lc->mon_decimal_point,
+                                        loc.get()))
+    if (!checked_string_to_char_convert(__thousands_sep_,
+                                        lc->mon_thousands_sep,
+                                        loc.get()))
+
     __grouping_ = lc->mon_grouping;
     __curr_symbol_ = lc->currency_symbol;
     if (lc->frac_digits != CHAR_MAX)
         __frac_digits_ = lc->frac_digits;
     else
         __frac_digits_ = base::do_frac_digits();
     if (lc->p_sign_posn == 0)
         __positive_sign_ = "()";
     else
         __positive_sign_ = lc->positive_sign;
     if (lc->n_sign_posn == 0)
         __negative_sign_ = "()";
     else
         __negative_sign_ = lc->negative_sign;
     // Assume the positive and negative formats will want spaces in
     // the same places in curr_symbol since there's no way to
     // represent anything else.
     string_type __dummy_curr_symbol = __curr_symbol_;
     __init_pat(__pos_format_, __dummy_curr_symbol, false,
                lc->p_cs_precedes, lc->p_sep_by_space, lc->p_sign_posn, ' ');
     __init_pat(__neg_format_, __curr_symbol_, false,
                lc->n_cs_precedes, lc->n_sep_by_space, lc->n_sign_posn, ' ');
 }
 
 template<>
 void
 moneypunct_byname<char, true>::init(const char* nm)
 {
     typedef moneypunct<char, true> base;
     __locale_unique_ptr loc(newlocale(LC_ALL_MASK, nm, 0), freelocale);
     if (loc == nullptr)
         __throw_runtime_error("moneypunct_byname"
                             " failed to construct for " + string(nm));
 
     lconv* lc = __libcpp_localeconv_l(loc.get());
-    if (*lc->mon_decimal_point)
-        __decimal_point_ = *lc->mon_decimal_point;
-    else
-        __decimal_point_ = base::do_decimal_point();
-    if (*lc->mon_thousands_sep)
-        __thousands_sep_ = *lc->mon_thousands_sep;
-    else
-        __thousands_sep_ = base::do_thousands_sep();
+    if (!checked_string_to_char_convert(__decimal_point_,
+                                        lc->mon_decimal_point,
+                                        loc.get()))
+    if (!checked_string_to_char_convert(__thousands_sep_,
+                                        lc->mon_thousands_sep,
+                                        loc.get()))
     __grouping_ = lc->mon_grouping;
     __curr_symbol_ = lc->int_curr_symbol;
     if (lc->int_frac_digits != CHAR_MAX)
         __frac_digits_ = lc->int_frac_digits;
     else
         __frac_digits_ = base::do_frac_digits();
 #if defined(_LIBCPP_MSVCRT) || defined(__MINGW32__)
     if (lc->p_sign_posn == 0)

 moneypunct_byname<wchar_t, false>::init(const char* nm)
 {
     typedef moneypunct<wchar_t, false> base;
     __locale_unique_ptr loc(newlocale(LC_ALL_MASK, nm, 0), freelocale);
     if (loc == nullptr)
         __throw_runtime_error("moneypunct_byname"
                             " failed to construct for " + string(nm));
     lconv* lc = __libcpp_localeconv_l(loc.get());
-    if (*lc->mon_decimal_point)
-        __decimal_point_ = static_cast<wchar_t>(*lc->mon_decimal_point);
-    else
-        __decimal_point_ = base::do_decimal_point();
-    if (*lc->mon_thousands_sep)
-        __thousands_sep_ = static_cast<wchar_t>(*lc->mon_thousands_sep);
-    else
-        __thousands_sep_ = base::do_thousands_sep();
+    if (!checked_string_to_wchar_convert(__decimal_point_,
+                                         lc->mon_decimal_point,
+                                         loc.get()))
+    if (!checked_string_to_wchar_convert(__thousands_sep_,
+                                         lc->mon_thousands_sep,
+                                         loc.get()))
     __grouping_ = lc->mon_grouping;
     wchar_t wbuf[100];
     mbstate_t mb = {0};
     const char* bb = lc->currency_symbol;
     size_t j = __libcpp_mbsrtowcs_l(wbuf, &bb, countof(wbuf), &mb, loc.get());
     if (j == size_t(-1))
         __throw_runtime_error("locale not supported");
     wchar_t* wbe = wbuf + j;

 {
     typedef moneypunct<wchar_t, true> base;
     __locale_unique_ptr loc(newlocale(LC_ALL_MASK, nm, 0), freelocale);
     if (loc == nullptr)
         __throw_runtime_error("moneypunct_byname"
                             " failed to construct for " + string(nm));
 
     lconv* lc = __libcpp_localeconv_l(loc.get());
-    if (*lc->mon_decimal_point)
-        __decimal_point_ = static_cast<wchar_t>(*lc->mon_decimal_point);
-    else
-        __decimal_point_ = base::do_decimal_point();
-    if (*lc->mon_thousands_sep)
-        __thousands_sep_ = static_cast<wchar_t>(*lc->mon_thousands_sep);
-    else
-        __thousands_sep_ = base::do_thousands_sep();
+    if (!checked_string_to_wchar_convert(__decimal_point_,
+                                         lc->mon_decimal_point,
+                                         loc.get()))
+    if (!checked_string_to_wchar_convert(__thousands_sep_,
+                                         lc->mon_thousands_sep,
+                                         loc.get()))
     __grouping_ = lc->mon_grouping;
     wchar_t wbuf[100];
     mbstate_t mb = {0};
     const char* bb = lc->int_curr_symbol;
     size_t j = __libcpp_mbsrtowcs_l(wbuf, &bb, countof(wbuf), &mb, loc.get());
     if (j == size_t(-1))
         __throw_runtime_error("locale not supported");
     wchar_t* wbe = wbuf + j;

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

 //===----------------------------------------------------------------------===//
 //
 //                     The LLVM Compiler Infrastructure
 //
 // This file is dual licensed under the MIT and the University of Illinois Open
 // Source Licenses. See LICENSE.TXT for details.
 //
 //===----------------------------------------------------------------------===//
 
 // REQUIRES: locale.en_US.UTF-8
 // REQUIRES: locale.fr_FR.UTF-8
 // 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>
 
 // charT decimal_point() const;
 
 #include <locale>
 #include <limits>
 #include <cassert>
 
+#include "test_macros.h"
 #include "platform_support.h" // locale name macros
 
 class Fnf
     : public std::moneypunct_byname<char, false>
 {
 public:
     explicit Fnf(const std::string& nm, std::size_t refs = 0)
         : std::moneypunct_byname<char, false>(nm, refs) {}
int main()
     {
         Fwf f(LOCALE_fr_FR_UTF_8, 1);
         assert(f.decimal_point() == L',');
     }
     {
         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);
     }
 
     {
         Fnf f(LOCALE_zh_CN_UTF_8, 1);
         assert(f.decimal_point() == '.');
     }
     {
         Fnt f(LOCALE_zh_CN_UTF_8, 1);

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

 // REQUIRES: locale.zh_CN.UTF-8
 
 // <locale>
 
 // class moneypunct_byname<charT, International>
 
 // 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
     : public std::moneypunct_byname<char, false>
 {
 public:
     explicit Fnf(const std::string& nm, std::size_t refs = 0)
         : std::moneypunct_byname<char, false>(nm, refs) {}
int main()
     {
         Fwf f(LOCALE_fr_FR_UTF_8, 1);
         assert(f.thousands_sep() == L' ');
     }
     {
         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);
     }
 
     {
         Fnf f(LOCALE_zh_CN_UTF_8, 1);
         assert(f.thousands_sep() == ',');
     }
     {
         Fnt f(LOCALE_zh_CN_UTF_8, 1);

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

 // REQUIRES: locale.fr_FR.UTF-8
 
 // <locale>
 
 // template <class charT> class numpunct_byname;
 
 // 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()
 {
     {
         std::locale l("C");
         {
             typedef char C;
int main()
         {
             typedef wchar_t C;
             const std::numpunct<C>& np = std::use_facet<std::numpunct<C> >(l);
             assert(np.grouping() == "\3\3");
         }
     }
     {
         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);
         }
     }
 }

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

 // REQUIRES: locale.fr_FR.UTF-8
 
 // <locale>
 
 // template <class charT> class numpunct_byname;
 
 // 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()
 {
     {
         std::locale l("C");
         {
             typedef char C;
int main()
         {
             typedef wchar_t C;
             const std::numpunct<C>& np = std::use_facet<std::numpunct<C> >(l);
             assert(np.thousands_sep() == L',');
         }
     }
     {
         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);
         }
     }
 }