EricWF created this revision. EricWF added a reviewer: mclow.lists. EricWF added a subscriber: cfe-commits.
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>`. It doesn't handle the case for `moneypunct_byname<char>` because it's not clear what to do. Note that the changes to `curr_symbol.pass.cpp` are just drive by fixes. https://reviews.llvm.org/D24218 Files: src/locale.cpp test/std/localization/locale.categories/category.monetary/locale.moneypunct.byname/curr_symbol.pass.cpp test/std/localization/locale.categories/category.monetary/locale.moneypunct.byname/decimal_point.pass.cpp test/std/localization/locale.categories/category.monetary/locale.moneypunct.byname/thousands_sep.pass.cpp test/support/test_macros.h
Index: test/support/test_macros.h =================================================================== --- test/support/test_macros.h +++ test/support/test_macros.h @@ -62,6 +62,13 @@ #endif #endif +// Attempt to deduce GCC version +#if defined(_LIBCPP_VERSION) && __has_include(<features.h>) +#include <features.h> +#define TEST_HAS_GLIBC +#define TEST_GLIBC_PREREQ(major, minor) __GLIBC_PREREQ(major, minor) +#endif + /* Features that were introduced in C++14 */ #if TEST_STD_VER >= 14 #define TEST_HAS_EXTENDED_CONSTEXPR Index: test/std/localization/locale.categories/category.monetary/locale.moneypunct.byname/thousands_sep.pass.cpp =================================================================== --- test/std/localization/locale.categories/category.monetary/locale.moneypunct.byname/thousands_sep.pass.cpp +++ 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 +109,30 @@ Fwt f(LOCALE_fr_FR_UTF_8, 1); assert(f.thousands_sep() == L' '); } - +// The belowe tests fail due to 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 { Fnf f(LOCALE_ru_RU_UTF_8, 1); assert(f.thousands_sep() == ' '); } { Fnt f(LOCALE_ru_RU_UTF_8, 1); assert(f.thousands_sep() == ' '); } + const wchar_t sep = L' '; +#else + const wchar_t sep = L'\u00A0'; +#endif { Fwf f(LOCALE_ru_RU_UTF_8, 1); - assert(f.thousands_sep() == L' '); + assert(f.thousands_sep() == sep); } { Fwt f(LOCALE_ru_RU_UTF_8, 1); - assert(f.thousands_sep() == L' '); + assert(f.thousands_sep() == sep); } { Index: test/std/localization/locale.categories/category.monetary/locale.moneypunct.byname/decimal_point.pass.cpp =================================================================== --- test/std/localization/locale.categories/category.monetary/locale.moneypunct.byname/decimal_point.pass.cpp +++ 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 @@ -112,21 +110,30 @@ assert(f.decimal_point() == L','); } +// The belowe tests fail due to GLIBC's use of U00A0 as mon_decimal_point +// and U002E as mon_decimal_point. +// TODO: Fix decimal_point for 'char'. +// related to https://gcc.gnu.org/bugzilla/show_bug.cgi?id=16006 +#ifndef TEST_HAS_GLIBC { Fnf f(LOCALE_ru_RU_UTF_8, 1); - assert(f.decimal_point() == ','); + assert(f.decimal_point() == '.'); } { Fnt f(LOCALE_ru_RU_UTF_8, 1); - assert(f.decimal_point() == ','); + assert(f.decimal_point() == '.'); } + const wchar_t sep = L'.'; +#else + const wchar_t sep = L'\u002E'; +#endif { Fwf f(LOCALE_ru_RU_UTF_8, 1); - assert(f.decimal_point() == L','); + assert(f.decimal_point() == sep); } { Fwt f(LOCALE_ru_RU_UTF_8, 1); - assert(f.decimal_point() == L','); + assert(f.decimal_point() == sep); } { Index: test/std/localization/locale.categories/category.monetary/locale.moneypunct.byname/curr_symbol.pass.cpp =================================================================== --- test/std/localization/locale.categories/category.monetary/locale.moneypunct.byname/curr_symbol.pass.cpp +++ test/std/localization/locale.categories/category.monetary/locale.moneypunct.byname/curr_symbol.pass.cpp @@ -24,6 +24,7 @@ #include <limits> #include <cassert> +#include "test_macros.h" #include "platform_support.h" // locale name macros class Fnf @@ -113,7 +114,14 @@ { Fnf f(LOCALE_ru_RU_UTF_8, 1); + // GLIBC <= 2.23 uses currency_symbol="<U0440><U0443><U0431>" + // GLIBC >= 2.24 uses currency_symbol="<U20BD>" + // See also: http://www.fileformat.info/info/unicode/char/20bd/index.htm +#if defined(TEST_GLIBC_PREREQ) && TEST_GLIBC_PREREQ(2, 24) + assert(f.curr_symbol() == " \xE2\x82\xBD"); +#else assert(f.curr_symbol() == " \xD1\x80\xD1\x83\xD0\xB1"); +#endif } { Fnt f(LOCALE_ru_RU_UTF_8, 1); Index: src/locale.cpp =================================================================== --- src/locale.cpp +++ src/locale.cpp @@ -5768,6 +5768,26 @@ pat.field[3] = value; } +static char checked_string_to_char_convert(const char* ptr) { + /* + // FIXME: The input character is multiple bytes. Do something... + if (ptr[0] && ptr[1]) + __throw_runtime_error("locale not supported"); + */ + return *ptr; +} + +static wchar_t checked_string_to_wchar_convert(const char* ptr, + __locale_struct* loc) { + mbstate_t mb = {0}; + 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)) { + __throw_runtime_error("locale not supported"); + } + return out; +} + template<> void moneypunct_byname<char, false>::init(const char* nm) @@ -5780,11 +5800,11 @@ lconv* lc = __libcpp_localeconv_l(loc.get()); if (*lc->mon_decimal_point) - __decimal_point_ = *lc->mon_decimal_point; + __decimal_point_ = checked_string_to_char_convert(lc->mon_decimal_point); else __decimal_point_ = base::do_decimal_point(); if (*lc->mon_thousands_sep) - __thousands_sep_ = *lc->mon_thousands_sep; + __thousands_sep_ = checked_string_to_char_convert(lc->mon_thousands_sep); else __thousands_sep_ = base::do_thousands_sep(); __grouping_ = lc->mon_grouping; @@ -5823,12 +5843,12 @@ lconv* lc = __libcpp_localeconv_l(loc.get()); if (*lc->mon_decimal_point) - __decimal_point_ = *lc->mon_decimal_point; + __decimal_point_ = checked_string_to_char_convert(lc->mon_decimal_point); else __decimal_point_ = base::do_decimal_point(); - if (*lc->mon_thousands_sep) - __thousands_sep_ = *lc->mon_thousands_sep; - else + if (*lc->mon_thousands_sep) { + __thousands_sep_ = checked_string_to_char_convert(lc->mon_thousands_sep); + } else __thousands_sep_ = base::do_thousands_sep(); __grouping_ = lc->mon_grouping; __curr_symbol_ = lc->int_curr_symbol; @@ -5882,11 +5902,13 @@ " 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); + __decimal_point_ = checked_string_to_wchar_convert(lc->mon_decimal_point, + loc.get()); else __decimal_point_ = base::do_decimal_point(); if (*lc->mon_thousands_sep) - __thousands_sep_ = static_cast<wchar_t>(*lc->mon_thousands_sep); + __thousands_sep_ = checked_string_to_wchar_convert(lc->mon_thousands_sep, + loc.get()); else __thousands_sep_ = base::do_thousands_sep(); __grouping_ = lc->mon_grouping; @@ -5948,11 +5970,13 @@ lconv* lc = __libcpp_localeconv_l(loc.get()); if (*lc->mon_decimal_point) - __decimal_point_ = static_cast<wchar_t>(*lc->mon_decimal_point); + __decimal_point_ = checked_string_to_wchar_convert(lc->mon_decimal_point, + loc.get()); else __decimal_point_ = base::do_decimal_point(); if (*lc->mon_thousands_sep) - __thousands_sep_ = static_cast<wchar_t>(*lc->mon_thousands_sep); + __thousands_sep_ = checked_string_to_wchar_convert(lc->mon_thousands_sep, + loc.get()); else __thousands_sep_ = base::do_thousands_sep(); __grouping_ = lc->mon_grouping;
_______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org http://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
