d0e8f58b81
It is autumn again and there is a new Unicode version 16.0. The following patch updates our Unicode stuff in contrib, libcpp and libstdc++ from that Unicode version. 2024-10-08 Jakub Jelinek <jakub@redhat.com> contrib/ * unicode/README: Update glibc git commit hash, replace Unicode 15 or 15.1 versions with 16. * unicode/gen_libstdcxx_unicode_data.py: Use 160000 instead of 150100 in _GLIBCXX_GET_UNICODE_DATA test. * unicode/from_glibc/utf8_gen.py: Updated from glibc 064c708c78cc2a6b5802dce73108fc0c1c6bfc80 commit. * unicode/DerivedCoreProperties.txt: Updated from Unicode 16.0. * unicode/emoji-data.txt: Likewise. * unicode/PropList.txt: Likewise. * unicode/GraphemeBreakProperty.txt: Likewise. * unicode/DerivedNormalizationProps.txt: Likewise. * unicode/NameAliases.txt: Likewise. * unicode/UnicodeData.txt: Likewise. * unicode/EastAsianWidth.txt: Likewise. gcc/testsuite/ * c-c++-common/cpp/named-universal-char-escape-1.c: Add tests for some Unicode 16.0 characters, both normal and generated. libcpp/ * makeucnid.cc (write_copyright): Update Unicode Copyright years. * makeuname2c.cc (generated_ranges): Adjust Unicode version from 15.1 to 16.0. Add EGYPTIAN HIEROGLYPH- generated range, adjust indexes in following entries. (write_copyright): Update Unicode Copyright years. * generated_cpp_wcwidth.h: Regenerated. * ucnid.h: Regenerated. * uname2c.h: Regenerated. libstdc++-v3/ * include/bits/unicode.h (std::__unicode::__v15_1_0): Rename inline namespace to ... (std::__unicode::__v16_0_0): ... this. (_GLIBCXX_GET_UNICODE_DATA): Change from 150100 to 160000. * include/bits/unicode-data.h: Regenerated. * testsuite/ext/unicode/properties.cc: Check for _Gcb_SpacingMark on U+11F03 rather than U+1D16D as the latter lost SpacingMark property in Unicode 16.0.
128 lines
6.4 KiB
C++
128 lines
6.4 KiB
C++
// { dg-do compile { target c++20 } }
|
|
|
|
#include <format> // includes <bits/unicode.h>
|
|
#include <string_view>
|
|
#include <ranges>
|
|
#include <testsuite_hooks.h>
|
|
|
|
namespace uc = std::__unicode;
|
|
using namespace std::string_view_literals;
|
|
|
|
constexpr char32_t riA = U'\N{REGIONAL INDICATOR SYMBOL LETTER A}';
|
|
constexpr char32_t riZ = U'\N{REGIONAL INDICATOR SYMBOL LETTER Z}';
|
|
|
|
static_assert( uc::__field_width(U'\0') == 1 );
|
|
static_assert( uc::__field_width(U'1') == 1 );
|
|
static_assert( uc::__field_width(U'a') == 1 );
|
|
static_assert( uc::__field_width(riA) == 1 );
|
|
static_assert( uc::__field_width(U'\N{OBLIQUE HYPHEN}') == 1 );
|
|
static_assert( uc::__field_width(U'\N{CIRCLED NUMBER EIGHTY ON BLACK SQUARE}')
|
|
== 1 );
|
|
|
|
static_assert( uc::__field_width(U'\N{SESQUIQUADRATE}') == 1 );
|
|
static_assert( uc::__field_width(U'\N{SOCCER BALL}') == 2 );
|
|
static_assert( uc::__field_width(U'\N{BASEBALL}') == 2 );
|
|
static_assert( uc::__field_width(U'\N{SQUARED KEY}') == 1 );
|
|
static_assert( uc::__field_width(U'\N{BLACK DRAUGHTS KING}') == 1 );
|
|
static_assert( uc::__field_width(U'\N{SNOWMAN WITHOUT SNOW}') == 2 );
|
|
|
|
static_assert( uc::__field_width(U'\N{IDEOGRAPHIC SPACE}') == 2 );
|
|
static_assert( uc::__field_width(U'\N{IDEOGRAPHIC COMMA}') == 2 );
|
|
static_assert( uc::__field_width(U'\N{CIRCLED IDEOGRAPH ONE}') == 2 );
|
|
|
|
// EastAsianWidth.txt says these are normal width, but C++ says width 2:
|
|
static_assert( uc::__field_width(U'\u4DC0') == 2 );
|
|
static_assert( uc::__field_width(U'\u4DC1') == 2 );
|
|
static_assert( uc::__field_width(U'\u4DFF') == 2 );
|
|
// EastAsianWidth.txt says W and C++ says 2:
|
|
static_assert( uc::__field_width(U'\U0001F300') == 2 );
|
|
static_assert( uc::__field_width(U'\U0001F320') == 2 );
|
|
// EastAsianWidth.txt says N but C++ says 2:
|
|
static_assert( uc::__field_width(U'\U0001F321') == 2 );
|
|
static_assert( uc::__field_width(U'\U0001F5FA') == 2 );
|
|
// EastAsianWidth.txt says W and C++ says 2:
|
|
static_assert( uc::__field_width(U'\U0001F5FF') == 2 );
|
|
static_assert( uc::__field_width(U'\U0001F600') == 2 );
|
|
|
|
static_assert( uc::__field_width(U'\U0001F900') == 2 );
|
|
static_assert( uc::__field_width(U'\U0001F90B') == 2 );
|
|
static_assert( uc::__field_width(U'\U0001F90C') == 2 );
|
|
static_assert( uc::__field_width(U'\U0001F93B') == 2 );
|
|
static_assert( uc::__field_width(U'\U0001F9FF') == 2 );
|
|
static_assert( uc::__field_width(U'\U0001FA00') == 1 );
|
|
static_assert( uc::__field_width(U'\U0001FA69') == 1 );
|
|
static_assert( uc::__field_width(U'\U0001FA70') == 2 );
|
|
static_assert( uc::__field_width(U'\U0001FAF8') == 2 );
|
|
static_assert( uc::__field_width(U'\U0001FAF9') == 1 );
|
|
|
|
using enum uc::_Gcb_property;
|
|
static_assert( uc::__grapheme_cluster_break_property(U'\0') == _Gcb_Control );
|
|
static_assert( uc::__grapheme_cluster_break_property(U'a') == _Gcb_Other );
|
|
static_assert( uc::__grapheme_cluster_break_property(riA)
|
|
== _Gcb_Regional_Indicator );
|
|
static_assert( uc::__grapheme_cluster_break_property(riZ)
|
|
== _Gcb_Regional_Indicator );
|
|
static_assert( uc::__grapheme_cluster_break_property(riA - 1) == _Gcb_Other );
|
|
static_assert( uc::__grapheme_cluster_break_property(riZ + 1) == _Gcb_Other );
|
|
static_assert( uc::__grapheme_cluster_break_property(U'\uD788') == _Gcb_LV );
|
|
static_assert( uc::__grapheme_cluster_break_property(U'\uD7A3') == _Gcb_LVT );
|
|
static_assert( uc::__grapheme_cluster_break_property(U'\u200D') == _Gcb_ZWJ );
|
|
static_assert( uc::__grapheme_cluster_break_property(U'\U00011F03')
|
|
== _Gcb_SpacingMark );
|
|
static_assert( uc::__grapheme_cluster_break_property(U'\U0001D16E')
|
|
== _Gcb_Extend );
|
|
static_assert( uc::__grapheme_cluster_break_property(U'\U000E01EF')
|
|
== _Gcb_Extend );
|
|
static_assert( uc::__grapheme_cluster_break_property(U'\U000E01F0')
|
|
== _Gcb_Control );
|
|
static_assert( uc::__grapheme_cluster_break_property(U'\U000E0FFF')
|
|
== _Gcb_Control );
|
|
static_assert( uc::__grapheme_cluster_break_property(U'\U000E1000')
|
|
== _Gcb_Other );
|
|
|
|
static_assert( uc::__incb_property(U'\0') == uc::_InCB{0} );
|
|
static_assert( uc::__incb_property(U'a') == uc::_InCB{0} );
|
|
static_assert( uc::__incb_property(U'\N{DEVANAGARI LETTER KA}')
|
|
== uc::_InCB::_Consonant );
|
|
static_assert( uc::__incb_property(U'\N{DEVANAGARI LETTER RA}')
|
|
== uc::_InCB::_Consonant );
|
|
static_assert( uc::__incb_property(U'\N{DEVANAGARI LETTER YYA}')
|
|
== uc::_InCB::_Consonant );
|
|
static_assert( uc::__incb_property(U'\N{DEVANAGARI LETTER YYA}' + 1)
|
|
== uc::_InCB{0} );
|
|
static_assert( uc::__incb_property(U'\N{DEVANAGARI SIGN NUKTA}')
|
|
== uc::_InCB::_Extend );
|
|
static_assert( uc::__incb_property(U'\N{DEVANAGARI SIGN NUKTA}' + 1)
|
|
== uc::_InCB{0} );
|
|
static_assert( uc::__incb_property(U'\U0001E94A') == uc::_InCB::_Extend );
|
|
static_assert( uc::__incb_property(U'\U0001E94B') == uc::_InCB{0} );
|
|
|
|
static_assert( ! uc::__is_incb_linker(U'\0') );
|
|
static_assert( ! uc::__is_incb_linker(U'a') );
|
|
static_assert( uc::__is_incb_linker(U'\N{DEVANAGARI SIGN VIRAMA}') );
|
|
static_assert( ! uc::__is_incb_linker(U'\N{DEVANAGARI SIGN VIRAMA}' + 1) );
|
|
static_assert( ! uc::__is_incb_linker(U'\N{DEVANAGARI SIGN VIRAMA}' - 1) );
|
|
static_assert( ! uc::__is_incb_linker(U'\u0FFF') );
|
|
static_assert( ! uc::__is_incb_linker(U'\uFFFD') );
|
|
|
|
static_assert( ! uc::__is_extended_pictographic(U'\0') );
|
|
static_assert( ! uc::__is_extended_pictographic(U'a') );
|
|
static_assert( ! uc::__is_extended_pictographic(riA) );
|
|
static_assert( ! uc::__is_extended_pictographic(riZ) );
|
|
static_assert( ! uc::__is_extended_pictographic(U'\N{COPYRIGHT SIGN}' - 1) );
|
|
static_assert( uc::__is_extended_pictographic(U'\N{COPYRIGHT SIGN}') );
|
|
static_assert( ! uc::__is_extended_pictographic(U'\N{COPYRIGHT SIGN}' + 1) );
|
|
static_assert( ! uc::__is_extended_pictographic(U'\N{INFORMATION SOURCE}' - 1) );
|
|
static_assert( uc::__is_extended_pictographic(U'\N{INFORMATION SOURCE}') );
|
|
static_assert( ! uc::__is_extended_pictographic(U'\N{INFORMATION SOURCE}' + 1) );
|
|
static_assert( ! uc::__is_extended_pictographic(U'\N{LEFT RIGHT ARROW}' - 1) );
|
|
static_assert( uc::__is_extended_pictographic(U'\N{LEFT RIGHT ARROW}') );
|
|
static_assert( uc::__is_extended_pictographic(U'\N{LEFT RIGHT ARROW}' + 1) );
|
|
static_assert( uc::__is_extended_pictographic(U'\N{SOUTH WEST ARROW}') );
|
|
static_assert( ! uc::__is_extended_pictographic(U'\N{SOUTH WEST ARROW}' + 1) );
|
|
static_assert( uc::__is_extended_pictographic(U'\N{POSTBOX}') );
|
|
static_assert( ! uc::__is_extended_pictographic(U'\U0001EFFF') );
|
|
static_assert( uc::__is_extended_pictographic(U'\U0001F000') );
|
|
static_assert( uc::__is_extended_pictographic(U'\U0001FFFD') );
|
|
static_assert( ! uc::__is_extended_pictographic(U'\U0001FFFE') );
|
|
static_assert( ! uc::__is_extended_pictographic(U'\U0001FFFF') );
|