[libcxx-commits] [libcxx] Implement P1885R12: `<text_encoding>` header (PR #141312)
William Tran-Viet via libcxx-commits
libcxx-commits at lists.llvm.org
Fri May 23 20:48:56 PDT 2025
https://github.com/smallp-o-p updated https://github.com/llvm/llvm-project/pull/141312
>From 4ecef4f3d68fac70395e621a6a4e578f97769dcf Mon Sep 17 00:00:00 2001
From: William Tran-Viet <wtranviet at proton.me>
Date: Fri, 23 May 2025 22:08:36 -0400
Subject: [PATCH 1/3] Implement P1885R12
---
libcxx/docs/FeatureTestMacroTable.rst | 2 +-
libcxx/docs/Status/Cxx2cPapers.csv | 4 +-
libcxx/include/CMakeLists.txt | 2 +
libcxx/include/__locale | 9 +
.../include/__text_encoding/text_encoding.h | 1483 +++++++++++++++++
libcxx/include/module.modulemap.in | 7 +
libcxx/include/text_encoding | 68 +
libcxx/include/version | 2 +-
libcxx/modules/std.compat.cppm.in | 3 -
libcxx/modules/std.cppm.in | 6 +-
libcxx/modules/std/text_encoding.inc | 9 +-
libcxx/src/CMakeLists.txt | 1 +
libcxx/src/locale.cpp | 13 +
libcxx/src/text_encoding.cpp | 49 +
.../test/libcxx/transitive_includes/cxx26.csv | 15 +
.../text_encoding.version.compile.pass.cpp | 63 +
.../version.version.compile.pass.cpp | 16 +-
.../locale/locale.members/encoding.pass.cpp | 56 +
.../text_encoding.ctor/default.pass.cpp | 39 +
.../text_encoding.ctor/id.pass.cpp | 56 +
.../text_encoding.ctor/string_view.pass.cpp | 73 +
.../text_encoding.eq/equal.id.pass.cpp | 69 +
.../text_encoding.eq/equal.pass.cpp | 66 +
.../text_encoding.members/aliases.pass.cpp | 37 +
.../environment.pass.cpp | 83 +
.../text_encoding.members/literal.pass.cpp | 49 +
.../text_encoding.aliases_view/begin.pass.cpp | 66 +
.../text_encoding.aliases_view/empty.pass.cpp | 64 +
.../text_encoding.aliases_view/front.pass.cpp | 66 +
libcxx/test/support/test_text_encoding.h | 1173 +++++++++++++
.../generate_feature_test_macro_components.py | 1 -
libcxx/utils/libcxx/header_information.py | 3 +-
32 files changed, 3624 insertions(+), 29 deletions(-)
create mode 100644 libcxx/include/__text_encoding/text_encoding.h
create mode 100644 libcxx/include/text_encoding
create mode 100644 libcxx/src/text_encoding.cpp
create mode 100644 libcxx/test/std/language.support/support.limits/support.limits.general/text_encoding.version.compile.pass.cpp
create mode 100644 libcxx/test/std/localization/locales/locale/locale.members/encoding.pass.cpp
create mode 100644 libcxx/test/std/utilities/text_encoding/text_encoding.ctor/default.pass.cpp
create mode 100644 libcxx/test/std/utilities/text_encoding/text_encoding.ctor/id.pass.cpp
create mode 100644 libcxx/test/std/utilities/text_encoding/text_encoding.ctor/string_view.pass.cpp
create mode 100644 libcxx/test/std/utilities/text_encoding/text_encoding.eq/equal.id.pass.cpp
create mode 100644 libcxx/test/std/utilities/text_encoding/text_encoding.eq/equal.pass.cpp
create mode 100644 libcxx/test/std/utilities/text_encoding/text_encoding.members/aliases.pass.cpp
create mode 100644 libcxx/test/std/utilities/text_encoding/text_encoding.members/environment.pass.cpp
create mode 100644 libcxx/test/std/utilities/text_encoding/text_encoding.members/literal.pass.cpp
create mode 100644 libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/begin.pass.cpp
create mode 100644 libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/empty.pass.cpp
create mode 100644 libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/front.pass.cpp
create mode 100644 libcxx/test/support/test_text_encoding.h
diff --git a/libcxx/docs/FeatureTestMacroTable.rst b/libcxx/docs/FeatureTestMacroTable.rst
index 9b57b7c8eeb52..93308e4078075 100644
--- a/libcxx/docs/FeatureTestMacroTable.rst
+++ b/libcxx/docs/FeatureTestMacroTable.rst
@@ -500,7 +500,7 @@ Status
---------------------------------------------------------- -----------------
``__cpp_lib_submdspan`` *unimplemented*
---------------------------------------------------------- -----------------
- ``__cpp_lib_text_encoding`` *unimplemented*
+ ``__cpp_lib_text_encoding`` ``202306L``
---------------------------------------------------------- -----------------
``__cpp_lib_to_chars`` *unimplemented*
---------------------------------------------------------- -----------------
diff --git a/libcxx/docs/Status/Cxx2cPapers.csv b/libcxx/docs/Status/Cxx2cPapers.csv
index 3809446a57896..a7dfa75df7c87 100644
--- a/libcxx/docs/Status/Cxx2cPapers.csv
+++ b/libcxx/docs/Status/Cxx2cPapers.csv
@@ -13,7 +13,7 @@
"`P2013R5 <https://wg21.link/P2013R5>`__","Freestanding Language: Optional ``::operator new``","2023-06 (Varna)","","",""
"`P2363R5 <https://wg21.link/P2363R5>`__","Extending associative containers with the remaining heterogeneous overloads","2023-06 (Varna)","","",""
"`P1901R2 <https://wg21.link/P1901R2>`__","Enabling the Use of ``weak_ptr`` as Keys in Unordered Associative Containers","2023-06 (Varna)","","",""
-"`P1885R12 <https://wg21.link/P1885R12>`__","Naming Text Encodings to Demystify Them","2023-06 (Varna)","","",""
+"`P1885R12 <https://wg21.link/P1885R12>`__","Naming Text Encodings to Demystify Them","2023-06 (Varna)","|Complete|","21",""
"`P0792R14 <https://wg21.link/P0792R14>`__","``function_ref``: a type-erased callable reference","2023-06 (Varna)","","",""
"`P2874R2 <https://wg21.link/P2874R2>`__","P2874R2: Mandating Annex D Require No More","2023-06 (Varna)","|Complete|","12",""
"`P2757R3 <https://wg21.link/P2757R3>`__","Type-checking format args","2023-06 (Varna)","","",""
@@ -79,7 +79,7 @@
"`P3136R1 <https://wg21.link/P3136R1>`__","Retiring niebloids","2024-11 (Wrocław)","|Complete|","14",""
"`P3138R5 <https://wg21.link/P3138R5>`__","``views::cache_latest``","2024-11 (Wrocław)","","",""
"`P3379R0 <https://wg21.link/P3379R0>`__","Constrain ``std::expected`` equality operators","2024-11 (Wrocław)","|Complete|","21",""
-"`P2862R1 <https://wg21.link/P2862R1>`__","``text_encoding::name()`` should never return null values","2024-11 (Wrocław)","","",""
+"`P2862R1 <https://wg21.link/P2862R1>`__","``text_encoding::name()`` should never return null values","2024-11 (Wrocław)","|Complete|","21",""
"`P2897R7 <https://wg21.link/P2897R7>`__","``aligned_accessor``: An ``mdspan`` accessor expressing pointer over-alignment","2024-11 (Wrocław)","|Complete|","21",""
"`P3355R1 <https://wg21.link/P3355R1>`__","Fix ``submdspan`` for C++26","2024-11 (Wrocław)","","",""
"`P3222R0 <https://wg21.link/P3222R0>`__","Fix C++26 by adding transposed special cases for P2642 layouts","2024-11 (Wrocław)","","",""
diff --git a/libcxx/include/CMakeLists.txt b/libcxx/include/CMakeLists.txt
index 43cefd5600646..ba61ee7c11e35 100644
--- a/libcxx/include/CMakeLists.txt
+++ b/libcxx/include/CMakeLists.txt
@@ -751,6 +751,7 @@ set(files
__system_error/error_condition.h
__system_error/system_error.h
__system_error/throw_system_error.h
+ __text_encoding/text_encoding.h
__thread/formatter.h
__thread/id.h
__thread/jthread.h
@@ -1062,6 +1063,7 @@ set(files
strstream
syncstream
system_error
+ text_encoding
tgmath.h
thread
tuple
diff --git a/libcxx/include/__locale b/libcxx/include/__locale
index d6c6ef19627ff..4da3f38ac408f 100644
--- a/libcxx/include/__locale
+++ b/libcxx/include/__locale
@@ -31,6 +31,10 @@
# include <cstddef>
# include <cstring>
+# if _LIBCPP_STD_VER >= 26
+# include <__text_encoding/text_encoding.h>
+# endif
+
# if _LIBCPP_HAS_WIDE_CHARACTERS
# include <cwchar>
# else
@@ -99,6 +103,11 @@ public:
// locale operations:
string name() const;
+
+# if _LIBCPP_STD_VER >= 26 && __CHAR_BIT__ == 8
+ text_encoding encoding() const;
+# endif // _LIBCPP_STD_VER >= 26
+
bool operator==(const locale&) const;
# if _LIBCPP_STD_VER <= 17
_LIBCPP_HIDE_FROM_ABI bool operator!=(const locale& __y) const { return !(*this == __y); }
diff --git a/libcxx/include/__text_encoding/text_encoding.h b/libcxx/include/__text_encoding/text_encoding.h
new file mode 100644
index 0000000000000..93d0ae2ab6b89
--- /dev/null
+++ b/libcxx/include/__text_encoding/text_encoding.h
@@ -0,0 +1,1483 @@
+// -*- C++ -*-
+//===----------------------------------------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef _LIBCPP___TEXT_ENCODING_TEXT_ENCODING_H
+#define _LIBCPP___TEXT_ENCODING_TEXT_ENCODING_H
+
+#include <__config>
+
+#if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
+# pragma GCC system_header
+#endif
+
+#if _LIBCPP_HAS_LOCALIZATION
+
+#include <__algorithm/copy_n.h>
+#include <__algorithm/lower_bound.h>
+#include <__algorithm/min.h>
+#include <__functional/hash.h>
+#include <__iterator/iterator_traits.h>
+#include <__locale_dir/locale_base_api.h>
+#include <__ranges/view_interface.h>
+#include <__string/char_traits.h>
+#include <__utility/unreachable.h>
+#include <cstdint>
+#include <string_view>
+
+_LIBCPP_PUSH_MACROS
+#include <__undef_macros>
+
+#if _LIBCPP_STD_VER >= 26
+_LIBCPP_BEGIN_NAMESPACE_STD
+
+struct _LIBCPP_EXPORTED_FROM_ABI text_encoding {
+ static constexpr size_t max_name_length = 63;
+
+private:
+ struct __encoding_data {
+ using __id_rep _LIBCPP_NODEBUG = int_least32_t;
+ __id_rep __mib_rep;
+ const char* __name;
+
+ friend constexpr bool operator==(const __encoding_data& __e, const __encoding_data& __other) _NOEXCEPT {
+ return __e.__mib_rep == __other.__mib_rep || __comp_name(__e.__name, __other.__name);
+ }
+
+ friend constexpr bool operator<(const __encoding_data& __e, const __id_rep __i) _NOEXCEPT {
+ return __e.__mib_rep < __i;
+ }
+ };
+
+public:
+ enum class id : __encoding_data::__id_rep {
+ other = 1,
+ unknown = 2,
+ ASCII = 3,
+ ISOLatin1 = 4,
+ ISOLatin2 = 5,
+ ISOLatin3 = 6,
+ ISOLatin4 = 7,
+ ISOLatinCyrillic = 8,
+ ISOLatinArabic = 9,
+ ISOLatinGreek = 10,
+ ISOLatinHebrew = 11,
+ ISOLatin5 = 12,
+ ISOLatin6 = 13,
+ ISOTextComm = 14,
+ HalfWidthKatakana = 15,
+ JISEncoding = 16,
+ ShiftJIS = 17,
+ EUCPkdFmtJapanese = 18,
+ EUCFixWidJapanese = 19,
+ ISO4UnitedKingdom = 20,
+ ISO11SwedishForNames = 21,
+ ISO15Italian = 22,
+ ISO17Spanish = 23,
+ ISO21German = 24,
+ ISO60DanishNorwegian = 25,
+ ISO69French = 26,
+ ISO10646UTF1 = 27,
+ ISO646basic1983 = 28,
+ INVARIANT = 29,
+ ISO2IntlRefVersion = 30,
+ NATSSEFI = 31,
+ NATSSEFIADD = 32,
+ NATSDANO = 33,
+ NATSDANOADD = 34,
+ ISO10Swedish = 35,
+ KSC56011987 = 36,
+ ISO2022KR = 37,
+ EUCKR = 38,
+ ISO2022JP = 39,
+ ISO2022JP2 = 40,
+ ISO13JISC6220jp = 41,
+ ISO14JISC6220ro = 42,
+ ISO16Portuguese = 43,
+ ISO18Greek7Old = 44,
+ ISO19LatinGreek = 45,
+ ISO25French = 46,
+ ISO27LatinGreek1 = 47,
+ ISO5427Cyrillic = 48,
+ ISO42JISC62261978 = 49,
+ ISO47BSViewdata = 50,
+ ISO49INIS = 51,
+ ISO50INIS8 = 52,
+ ISO51INISCyrillic = 53,
+ ISO54271981 = 54,
+ ISO5428Greek = 55,
+ ISO57GB1988 = 56,
+ ISO58GB231280 = 57,
+ ISO61Norwegian2 = 58,
+ ISO70VideotexSupp1 = 59,
+ ISO84Portuguese2 = 60,
+ ISO85Spanish2 = 61,
+ ISO86Hungarian = 62,
+ ISO87JISX0208 = 63,
+ ISO88Greek7 = 64,
+ ISO89ASMO449 = 65,
+ ISO90 = 66,
+ ISO91JISC62291984a = 67,
+ ISO92JISC62991984b = 68,
+ ISO93JIS62291984badd = 69,
+ ISO94JIS62291984hand = 70,
+ ISO95JIS62291984handadd = 71,
+ ISO96JISC62291984kana = 72,
+ ISO2033 = 73,
+ ISO99NAPLPS = 74,
+ ISO102T617bit = 75,
+ ISO103T618bit = 76,
+ ISO111ECMACyrillic = 77,
+ ISO121Canadian1 = 78,
+ ISO122Canadian2 = 79,
+ ISO123CSAZ24341985gr = 80,
+ ISO88596E = 81,
+ ISO88596I = 82,
+ ISO128T101G2 = 83,
+ ISO88598E = 84,
+ ISO88598I = 85,
+ ISO139CSN369103 = 86,
+ ISO141JUSIB1002 = 87,
+ ISO143IECP271 = 88,
+ ISO146Serbian = 89,
+ ISO147Macedonian = 90,
+ ISO150 = 91,
+ ISO151Cuba = 92,
+ ISO6937Add = 93,
+ ISO153GOST1976874 = 94,
+ ISO8859Supp = 95,
+ ISO10367Box = 96,
+ ISO158Lap = 97,
+ ISO159JISX02121990 = 98,
+ ISO646Danish = 99,
+ USDK = 100,
+ DKUS = 101,
+ KSC5636 = 102,
+ Unicode11UTF7 = 103,
+ ISO2022CN = 104,
+ ISO2022CNEXT = 105,
+ UTF8 = 106,
+ ISO885913 = 109,
+ ISO885914 = 110,
+ ISO885915 = 111,
+ ISO885916 = 112,
+ GBK = 113,
+ GB18030 = 114,
+ OSDEBCDICDF0415 = 115,
+ OSDEBCDICDF03IRV = 116,
+ OSDEBCDICDF041 = 117,
+ ISO115481 = 118,
+ KZ1048 = 119,
+ UCS2 = 1000,
+ UCS4 = 1001,
+ UnicodeASCII = 1002,
+ UnicodeLatin1 = 1003,
+ UnicodeJapanese = 1004,
+ UnicodeIBM1261 = 1005,
+ UnicodeIBM1268 = 1006,
+ UnicodeIBM1276 = 1007,
+ UnicodeIBM1264 = 1008,
+ UnicodeIBM1265 = 1009,
+ Unicode11 = 1010,
+ SCSU = 1011,
+ UTF7 = 1012,
+ UTF16BE = 1013,
+ UTF16LE = 1014,
+ UTF16 = 1015,
+ CESU8 = 1016,
+ UTF32 = 1017,
+ UTF32BE = 1018,
+ UTF32LE = 1019,
+ BOCU1 = 1020,
+ UTF7IMAP = 1021,
+ Windows30Latin1 = 2000,
+ Windows31Latin1 = 2001,
+ Windows31Latin2 = 2002,
+ Windows31Latin5 = 2003,
+ HPRoman8 = 2004,
+ AdobeStandardEncoding = 2005,
+ VenturaUS = 2006,
+ VenturaInternational = 2007,
+ DECMCS = 2008,
+ PC850Multilingual = 2009,
+ PC8DanishNorwegian = 2012,
+ PC862LatinHebrew = 2013,
+ PC8Turkish = 2014,
+ IBMSymbols = 2015,
+ IBMThai = 2016,
+ HPLegal = 2017,
+ HPPiFont = 2018,
+ HPMath8 = 2019,
+ HPPSMath = 2020,
+ HPDesktop = 2021,
+ VenturaMath = 2022,
+ MicrosoftPublishing = 2023,
+ Windows31J = 2024,
+ GB2312 = 2025,
+ Big5 = 2026,
+ Macintosh = 2027,
+ IBM037 = 2028,
+ IBM038 = 2029,
+ IBM273 = 2030,
+ IBM274 = 2031,
+ IBM275 = 2032,
+ IBM277 = 2033,
+ IBM278 = 2034,
+ IBM280 = 2035,
+ IBM281 = 2036,
+ IBM284 = 2037,
+ IBM285 = 2038,
+ IBM290 = 2039,
+ IBM297 = 2040,
+ IBM420 = 2041,
+ IBM423 = 2042,
+ IBM424 = 2043,
+ PC8CodePage437 = 2011,
+ IBM500 = 2044,
+ IBM851 = 2045,
+ PCp852 = 2010,
+ IBM855 = 2046,
+ IBM857 = 2047,
+ IBM860 = 2048,
+ IBM861 = 2049,
+ IBM863 = 2050,
+ IBM864 = 2051,
+ IBM865 = 2052,
+ IBM868 = 2053,
+ IBM869 = 2054,
+ IBM870 = 2055,
+ IBM871 = 2056,
+ IBM880 = 2057,
+ IBM891 = 2058,
+ IBM903 = 2059,
+ IBBM904 = 2060,
+ IBM905 = 2061,
+ IBM918 = 2062,
+ IBM1026 = 2063,
+ IBMEBCDICATDE = 2064,
+ EBCDICATDEA = 2065,
+ EBCDICCAFR = 2066,
+ EBCDICDKNO = 2067,
+ EBCDICDKNOA = 2068,
+ EBCDICFISE = 2069,
+ EBCDICFISEA = 2070,
+ EBCDICFR = 2071,
+ EBCDICIT = 2072,
+ EBCDICPT = 2073,
+ EBCDICES = 2074,
+ EBCDICESA = 2075,
+ EBCDICESS = 2076,
+ EBCDICUK = 2077,
+ EBCDICUS = 2078,
+ Unknown8BiT = 2079,
+ Mnemonic = 2080,
+ Mnem = 2081,
+ VISCII = 2082,
+ VIQR = 2083,
+ KOI8R = 2084,
+ HZGB2312 = 2085,
+ IBM866 = 2086,
+ PC775Baltic = 2087,
+ KOI8U = 2088,
+ IBM00858 = 2089,
+ IBM00924 = 2090,
+ IBM01140 = 2091,
+ IBM01141 = 2092,
+ IBM01142 = 2093,
+ IBM01143 = 2094,
+ IBM01144 = 2095,
+ IBM01145 = 2096,
+ IBM01146 = 2097,
+ IBM01147 = 2098,
+ IBM01148 = 2099,
+ IBM01149 = 2100,
+ Big5HKSCS = 2101,
+ IBM1047 = 2102,
+ PTCP154 = 2103,
+ Amiga1251 = 2104,
+ KOI7switched = 2105,
+ BRF = 2106,
+ TSCII = 2107,
+ CP51932 = 2108,
+ windows874 = 2109,
+ windows1250 = 2250,
+ windows1251 = 2251,
+ windows1252 = 2252,
+ windows1253 = 2253,
+ windows1254 = 2254,
+ windows1255 = 2255,
+ windows1256 = 2256,
+ windows1257 = 2257,
+ windows1258 = 2258,
+ TIS620 = 2259,
+ CP50220 = 2260,
+ reserved = 3000
+ };
+
+ using enum id;
+
+ _LIBCPP_HIDE_FROM_ABI constexpr text_encoding() = default;
+ _LIBCPP_HIDE_FROM_ABI constexpr explicit text_encoding(string_view __enc) _NOEXCEPT
+ : __encoding_rep_(__find_encoding_data(__enc)) {
+ __enc.copy(__name_, max_name_length, 0);
+ }
+ _LIBCPP_HIDE_FROM_ABI constexpr text_encoding(id __i) _NOEXCEPT : __encoding_rep_(__find_encoding_data_by_id(__i)) {
+ if (__encoding_rep_->__name[0] != '\0')
+ std::copy_n(__encoding_rep_->__name, std::char_traits<char>::length(__encoding_rep_->__name), __name_);
+ }
+
+ [[nodiscard]] _LIBCPP_HIDE_FROM_ABI constexpr id mib() const _NOEXCEPT { return id(__encoding_rep_->__mib_rep); }
+ [[nodiscard]] _LIBCPP_HIDE_FROM_ABI constexpr const char* name() const _NOEXCEPT { return __name_; }
+
+ // [text.encoding.aliases], class text_encoding::aliases_view
+ struct aliases_view : ranges::view_interface<aliases_view> {
+ constexpr aliases_view() = default;
+ constexpr aliases_view(const __encoding_data* __d) : __view_data_(__d) {}
+ struct __end_sentinel {};
+ struct __iterator {
+ using value_type = const char*;
+ using reference = const char*;
+ using difference_type = ptrdiff_t;
+
+ _LIBCPP_HIDE_FROM_ABI constexpr __iterator() noexcept = default;
+
+ _LIBCPP_HIDE_FROM_ABI constexpr value_type operator*() const {
+ if (__can_dereference())
+ return __data_->__name;
+ std::unreachable();
+ }
+
+ _LIBCPP_HIDE_FROM_ABI constexpr value_type operator[](difference_type __n) const {
+ auto __it = *this;
+ return *(__it + __n);
+ }
+
+ _LIBCPP_HIDE_FROM_ABI friend constexpr __iterator operator+(__iterator __it, difference_type __n) {
+ __it += __n;
+ return __it;
+ }
+
+ _LIBCPP_HIDE_FROM_ABI friend constexpr __iterator operator+(difference_type __n, __iterator __it) {
+ __it += __n;
+ return __it;
+ }
+
+ _LIBCPP_HIDE_FROM_ABI friend constexpr __iterator operator-(__iterator __it, difference_type __n) {
+ __it -= __n;
+ return __it;
+ }
+
+ _LIBCPP_HIDE_FROM_ABI constexpr difference_type operator-(const __iterator& __other) const
+ {
+ if(__other.__mib_rep_ == __mib_rep_)
+ return __mib_rep_ - __other.__mib_rep_;
+ std::unreachable();
+ }
+
+ _LIBCPP_HIDE_FROM_ABI friend constexpr __iterator operator-(difference_type __n, __iterator& __it) {
+ __it -= __n;
+ return __it;
+ }
+
+ _LIBCPP_HIDE_FROM_ABI constexpr __iterator& operator++() {
+ __data_++;
+ return *this;
+ }
+
+ _LIBCPP_HIDE_FROM_ABI constexpr __iterator operator++(int) {
+ auto __old = *this;
+ __data_++;
+ return __old;
+ }
+
+ _LIBCPP_HIDE_FROM_ABI constexpr __iterator& operator--() {
+ __data_--;
+ return *this;
+ }
+
+ _LIBCPP_HIDE_FROM_ABI constexpr __iterator operator--(int) {
+ auto __old = *this;
+ __data_--;
+ return __old;
+ }
+
+ // Check if going past the encoding data list array and if the new index has the same id, if not then
+ // replace it with a sentinel "out-of-bounds" iterator.
+ _LIBCPP_HIDE_FROM_ABI constexpr __iterator& operator+=(difference_type __n) {
+ if (__data_) [[__likely__]] {
+ if (__n > 0) {
+ if ((__data_ + __n) < std::end(__text_encoding_data) && __data_[__n - 1].__mib_rep == __mib_rep_)
+ __data_ += __n;
+ else
+ *this = __iterator{};
+ } else if (__n < 0) {
+ if ((__data_ + __n) > __text_encoding_data && __data_[__n].__mib_rep == __mib_rep_)
+ __data_ += __n;
+ else
+ *this = __iterator{};
+ }
+ }
+ return *this;
+ }
+
+ _LIBCPP_HIDE_FROM_ABI constexpr __iterator& operator-=(difference_type __n) { return operator+=(-__n); }
+
+ _LIBCPP_HIDE_FROM_ABI constexpr bool operator==(const __iterator& __it) const {
+ return __data_ == __it.__data_ && __it.__mib_rep_ == __mib_rep_;
+ }
+
+ _LIBCPP_HIDE_FROM_ABI constexpr bool operator==(__end_sentinel) const { return !__can_dereference(); }
+
+ _LIBCPP_HIDE_FROM_ABI constexpr auto operator<=>(__iterator __it) const { return __data_ <=> __it.__data_; }
+
+ private:
+ friend struct text_encoding;
+
+ _LIBCPP_HIDE_FROM_ABI constexpr __iterator(const __encoding_data* __enc_d) noexcept
+ : __data_(__enc_d), __mib_rep_(__enc_d ? __enc_d->__mib_rep : 0) {}
+
+ _LIBCPP_HIDE_FROM_ABI bool __can_dereference() const { return __data_ && __data_->__mib_rep == __mib_rep_; }
+
+ // default iterator is a sentinel
+ const __encoding_data* __data_ = nullptr;
+ __encoding_data::__id_rep __mib_rep_ = 0;
+ };
+
+ constexpr __iterator begin() const { return __iterator{__view_data_}; }
+ constexpr __end_sentinel end() const { return __end_sentinel{}; }
+
+ private:
+ const __encoding_data* __view_data_ = nullptr;
+ };
+
+ [[nodiscard]] _LIBCPP_HIDE_FROM_ABI constexpr aliases_view aliases() const _NOEXCEPT {
+ auto __rep = __encoding_rep_ - 1;
+ if (__encoding_rep_->__name[0]) {
+ while (__rep > std::begin(__text_encoding_data) && (__rep--)->__mib_rep == __encoding_rep_->__mib_rep)
+ ;
+ } else {
+ __rep = nullptr;
+ }
+
+ return aliases_view(__rep);
+ }
+
+ _LIBCPP_HIDE_FROM_ABI friend constexpr bool operator==(const text_encoding& __a, const text_encoding& __b) _NOEXCEPT {
+ if (__a.mib() == id::other && __b.mib() == id::other)
+ return __comp_name(__a.__name_, __b.__name_);
+
+ return __a.mib() == __b.mib();
+ }
+
+ _LIBCPP_HIDE_FROM_ABI friend constexpr bool operator==(const text_encoding& __encoding, id __i) _NOEXCEPT {
+ return __encoding.mib() == __i;
+ }
+
+# if __CHAR_BIT__ == 8
+ [[nodiscard]] _LIBCPP_HIDE_FROM_ABI static consteval text_encoding literal() _NOEXCEPT {
+# ifdef __GNUC_EXECUTION_CHARSET_NAME
+ return text_encoding(__GNUC_EXECUTION_CHARSET_NAME);
+# elif defined(__clang_literal_encoding__)
+ return text_encoding(__clang_literal_encoding__);
+# elif defined(__clang__)
+ return text_encoding(id::UTF8);
+# else
+ return {};
+# endif
+ }
+
+ [[nodiscard]] static text_encoding environment();
+
+ template <id __i>
+ [[nodiscard]] _LIBCPP_HIDE_FROM_ABI static bool environment_is() {
+ return environment() == __i;
+ }
+
+# else
+ [[nodiscard]] _LIBCPP_HIDE_FROM_ABI static consteval text_encoding literal() = delete;
+ [[nodiscard]] _LIBCPP_HIDE_FROM_ABI static text_encoding environment() = delete;
+ template <id __i>
+ [[nodiscard]] _LIBCPP_HIDE_FROM_ABI static bool environment_is() = delete;
+# endif
+
+private:
+ _LIBCPP_HIDE_FROM_ABI static constexpr bool __comp_name(string_view __a, string_view __b) {
+ if (__a.empty() || __b.empty()) {
+ return false;
+ }
+
+ // map any non-alphanumeric character to 255, skip prefix 0s, else get tolower(__n)
+ auto __map_char = [](char __n, bool& __in_number) -> unsigned char {
+ auto __to_lower = [](char __n) -> char { return (__n >= 'A' && __n <= 'Z') ? __n + ('a' - 'A') : __n; };
+ if (__n == '0') {
+ return __in_number ? '0' : 255;
+ }
+ __in_number = __n >= '1' && __n <= '9';
+ return (__n >= '1' && __n <= '9') || (__n >= 'A' && __n <= 'Z') || (__n >= 'a' && __n <= 'z')
+ ? __to_lower(__n)
+ : 255;
+ };
+
+ auto __a_ptr = __a.begin(), __b_ptr = __b.begin();
+ bool __a_in_number = false, __b_in_number = false;
+
+ unsigned char __a_val = 255, __b_val = 255;
+ for (;; __a_ptr++, __b_ptr++) {
+ while ((__a_val = __map_char(*__a_ptr, __a_in_number)) == 255 && __a_ptr != __a.end())
+ __a_ptr++;
+ while ((__b_val = __map_char(*__b_ptr, __b_in_number)) == 255 && __b_ptr != __b.end())
+ __b_ptr++;
+
+ if (__a_ptr == __a.end())
+ return __b_ptr == __b.end();
+ if (__b_ptr == __b.end())
+ return false;
+ if (__a_val != __b_val)
+ return false;
+ }
+ return true;
+ }
+
+ _LIBCPP_HIDE_FROM_ABI static constexpr const __encoding_data* __find_encoding_data(string_view __a) {
+ auto __data_ptr = __text_encoding_data + 2, __data_last = std::end(__text_encoding_data) - 1;
+
+ for (; __data_ptr != __data_last; __data_ptr++) {
+ if (__comp_name(__a, __data_ptr->__name)) {
+ const auto __found_id = __data_ptr->__mib_rep;
+ while (__data_ptr[-1].__mib_rep == __found_id)
+ __data_ptr--;
+ return __data_ptr;
+ }
+ }
+
+ return __text_encoding_data; // other
+ }
+
+ _LIBCPP_HIDE_FROM_ABI static constexpr const __encoding_data* __find_encoding_data_by_id(id __i) {
+ auto __found = std::lower_bound(
+ std::begin(__text_encoding_data), std::end(__text_encoding_data) - 1, __encoding_data::__id_rep(__i));
+ return __found != std::end(__text_encoding_data) - 1 ? __found : __text_encoding_data + 1; // unknown
+ }
+
+ _LIBCPP_HIDE_FROM_ABI static constexpr __encoding_data __text_encoding_data[] = {
+ {1, ""},
+ {2, ""},
+ {3, "ANSI_X3.4-1968"},
+ {3, "ANSI_X3.4-1986"},
+ {3, "IBM367"},
+ {3, "ISO646-US"},
+ {3, "ISO_646.irv:1991"},
+ {3, "cp367"},
+ {3, "csASCII"},
+ {3, "iso-ir-6"},
+ {3, "us"},
+ {4, "ISO-8859-1"},
+ {4, "ISO_8859-1:1987"},
+ {4, "CP819"},
+ {4, "IBM819"},
+ {4, "ISO_8859-1"},
+ {4, "csISOLatin1"},
+ {4, "iso-ir-100"},
+ {4, "l1"},
+ {4, "latin1"},
+ {5, "ISO-8859-2"},
+ {5, "ISO_8859-2:1987"},
+ {5, "ISO_8859-2"},
+ {5, "csISOLatin2"},
+ {5, "iso-ir-101"},
+ {5, "l2"},
+ {5, "latin2"},
+ {6, "ISO-8859-3"},
+ {6, "ISO_8859-3:1988"},
+ {6, "ISO_8859-3"},
+ {6, "csISOLatin3"},
+ {6, "iso-ir-109"},
+ {6, "l3"},
+ {6, "latin3"},
+ {7, "ISO-8859-4"},
+ {7, "ISO_8859-4:1988"},
+ {7, "ISO_8859-4"},
+ {7, "csISOLatin4"},
+ {7, "iso-ir-110"},
+ {7, "l4"},
+ {7, "latin4"},
+ {8, "ISO-8859-5"},
+ {8, "ISO_8859-5:1988"},
+ {8, "ISO_8859-5"},
+ {8, "csISOLatinCyrillic"},
+ {8, "cyrillic"},
+ {8, "iso-ir-144"},
+ {9, "ISO-8859-6"},
+ {9, "ISO_8859-6:1987"},
+ {9, "ASMO-708"},
+ {9, "ECMA-114"},
+ {9, "ISO_8859-6"},
+ {9, "arabic"},
+ {9, "csISOLatinArabic"},
+ {9, "iso-ir-127"},
+ {10, "ISO-8859-7"},
+ {10, "ISO_8859-7:1987"},
+ {10, "ECMA-118"},
+ {10, "ELOT_928"},
+ {10, "ISO_8859-7"},
+ {10, "csISOLatinGreek"},
+ {10, "greek"},
+ {10, "greek8"},
+ {10, "iso-ir-126"},
+ {11, "ISO-8859-8"},
+ {11, "ISO_8859-8:1988"},
+ {11, "ISO_8859-8"},
+ {11, "csISOLatinHebrew"},
+ {11, "hebrew"},
+ {11, "iso-ir-138"},
+ {12, "ISO-8859-9"},
+ {12, "ISO_8859-9:1989"},
+ {12, "ISO_8859-9"},
+ {12, "csISOLatin5"},
+ {12, "iso-ir-148"},
+ {12, "l5"},
+ {12, "latin5"},
+ {13, "ISO-8859-10"},
+ {13, "ISO_8859-10:1992"},
+ {13, "csISOLatin6"},
+ {13, "iso-ir-157"},
+ {13, "l6"},
+ {13, "latin6"},
+ {14, "ISO_6937-2-add"},
+ {14, "csISOTextComm"},
+ {14, "iso-ir-142"},
+ {15, "JIS_X0201"},
+ {15, "X0201"},
+ {15, "csHalfWidthKatakana"},
+ {16, "JIS_Encoding"},
+ {16, "csJISEncoding"},
+ {17, "Shift_JIS"},
+ {17, "MS_Kanji"},
+ {17, "csShiftJIS"},
+ {18, "EUC-JP"},
+ {18, "Extended_UNIX_Code_Packed_Format_for_Japanese"},
+ {18, "csEUCPkdFmtJapanese"},
+ {19, "Extended_UNIX_Code_Fixed_Width_for_Japanese"},
+ {19, "csEUCFixWidJapanese"},
+ {20, "BS_4730"},
+ {20, "ISO646-GB"},
+ {20, "csISO4UnitedKingdom"},
+ {20, "gb"},
+ {20, "iso-ir-4"},
+ {20, "uk"},
+ {21, "SEN_850200_C"},
+ {21, "ISO646-SE2"},
+ {21, "csISO11SwedishForNames"},
+ {21, "iso-ir-11"},
+ {21, "se2"},
+ {22, "IT"},
+ {22, "ISO646-IT"},
+ {22, "csISO15Italian"},
+ {22, "iso-ir-15"},
+ {23, "ES"},
+ {23, "ISO646-ES"},
+ {23, "csISO17Spanish"},
+ {23, "iso-ir-17"},
+ {24, "DIN_66003"},
+ {24, "ISO646-DE"},
+ {24, "csISO21German"},
+ {24, "de"},
+ {24, "iso-ir-21"},
+ {25, "NS_4551-1"},
+ {25, "ISO646-NO"},
+ {25, "csISO60DanishNorwegian"},
+ {25, "csISO60Norwegian1"},
+ {25, "iso-ir-60"},
+ {25, "no"},
+ {26, "NF_Z_62-010"},
+ {26, "ISO646-FR"},
+ {26, "csISO69French"},
+ {26, "fr"},
+ {26, "iso-ir-69"},
+ {27, "ISO-10646-UTF-1"},
+ {27, "csISO10646UTF1"},
+ {28, "ISO_646.basic:1983"},
+ {28, "csISO646basic1983"},
+ {28, "ref"},
+ {29, "INVARIANT"},
+ {29, "csINVARIANT"},
+ {30, "ISO_646.irv:1983"},
+ {30, "csISO2IntlRefVersion"},
+ {30, "irv"},
+ {30, "iso-ir-2"},
+ {31, "NATS-SEFI"},
+ {31, "csNATSSEFI"},
+ {31, "iso-ir-8-1"},
+ {32, "NATS-SEFI-ADD"},
+ {32, "csNATSSEFIADD"},
+ {32, "iso-ir-8-2"},
+ {33, "NATS-DANO"},
+ {33, "csNATSDANO"},
+ {33, "iso-ir-9-1"},
+ {34, "NATS-DANO-ADD"},
+ {34, "csNATSDANOADD"},
+ {34, "iso-ir-9-2"},
+ {35, "SEN_850200_B"},
+ {35, "FI"},
+ {35, "ISO646-FI"},
+ {35, "ISO646-SE"},
+ {35, "csISO10Swedish"},
+ {35, "iso-ir-10"},
+ {35, "se"},
+ {36, "KS_C_5601-1987"},
+ {36, "KSC_5601"},
+ {36, "KS_C_5601-1989"},
+ {36, "csKSC56011987"},
+ {36, "iso-ir-149"},
+ {36, "korean"},
+ {37, "ISO-2022-KR"},
+ {37, "csISO2022KR"},
+ {38, "EUC-KR"},
+ {38, "csEUCKR"},
+ {39, "ISO-2022-JP"},
+ {39, "csISO2022JP"},
+ {40, "ISO-2022-JP-2"},
+ {40, "csISO2022JP2"},
+ {41, "JIS_C6220-1969-jp"},
+ {41, "JIS_C6220-1969"},
+ {41, "csISO13JISC6220jp"},
+ {41, "iso-ir-13"},
+ {41, "katakana"},
+ {41, "x0201-7"},
+ {42, "JIS_C6220-1969-ro"},
+ {42, "ISO646-JP"},
+ {42, "csISO14JISC6220ro"},
+ {42, "iso-ir-14"},
+ {42, "jp"},
+ {43, "PT"},
+ {43, "ISO646-PT"},
+ {43, "csISO16Portuguese"},
+ {43, "iso-ir-16"},
+ {44, "greek7-old"},
+ {44, "csISO18Greek7Old"},
+ {44, "iso-ir-18"},
+ {45, "latin-greek"},
+ {45, "csISO19LatinGreek"},
+ {45, "iso-ir-19"},
+ {46, "NF_Z_62-010_(1973)"},
+ {46, "ISO646-FR1"},
+ {46, "csISO25French"},
+ {46, "iso-ir-25"},
+ {47, "Latin-greek-1"},
+ {47, "csISO27LatinGreek1"},
+ {47, "iso-ir-27"},
+ {48, "ISO_5427"},
+ {48, "csISO5427Cyrillic"},
+ {48, "iso-ir-37"},
+ {49, "JIS_C6226-1978"},
+ {49, "csISO42JISC62261978"},
+ {49, "iso-ir-42"},
+ {50, "BS_viewdata"},
+ {50, "csISO47BSViewdata"},
+ {50, "iso-ir-47"},
+ {51, "INIS"},
+ {51, "csISO49INIS"},
+ {51, "iso-ir-49"},
+ {52, "INIS-8"},
+ {52, "csISO50INIS8"},
+ {52, "iso-ir-50"},
+ {53, "INIS-cyrillic"},
+ {53, "csISO51INISCyrillic"},
+ {53, "iso-ir-51"},
+ {54, "ISO_5427:1981"},
+ {54, "ISO5427Cyrillic1981"},
+ {54, "csISO54271981"},
+ {54, "iso-ir-54"},
+ {55, "ISO_5428:1980"},
+ {55, "csISO5428Greek"},
+ {55, "iso-ir-55"},
+ {56, "GB_1988-80"},
+ {56, "ISO646-CN"},
+ {56, "cn"},
+ {56, "csISO57GB1988"},
+ {56, "iso-ir-57"},
+ {57, "GB_2312-80"},
+ {57, "chinese"},
+ {57, "csISO58GB231280"},
+ {57, "iso-ir-58"},
+ {58, "NS_4551-2"},
+ {58, "ISO646-NO2"},
+ {58, "csISO61Norwegian2"},
+ {58, "iso-ir-61"},
+ {58, "no2"},
+ {59, "videotex-suppl"},
+ {59, "csISO70VideotexSupp1"},
+ {59, "iso-ir-70"},
+ {60, "PT2"},
+ {60, "ISO646-PT2"},
+ {60, "csISO84Portuguese2"},
+ {60, "iso-ir-84"},
+ {61, "ES2"},
+ {61, "ISO646-ES2"},
+ {61, "csISO85Spanish2"},
+ {61, "iso-ir-85"},
+ {62, "MSZ_7795.3"},
+ {62, "ISO646-HU"},
+ {62, "csISO86Hungarian"},
+ {62, "hu"},
+ {62, "iso-ir-86"},
+ {63, "JIS_C6226-1983"},
+ {63, "JIS_X0208-1983"},
+ {63, "csISO87JISX0208"},
+ {63, "iso-ir-87"},
+ {63, "x0208"},
+ {64, "greek7"},
+ {64, "csISO88Greek7"},
+ {64, "iso-ir-88"},
+ {65, "ASMO_449"},
+ {65, "ISO_9036"},
+ {65, "arabic7"},
+ {65, "csISO89ASMO449"},
+ {65, "iso-ir-89"},
+ {66, "iso-ir-90"},
+ {66, "csISO90"},
+ {67, "JIS_C6229-1984-a"},
+ {67, "csISO91JISC62291984a"},
+ {67, "iso-ir-91"},
+ {67, "jp-ocr-a"},
+ {68, "JIS_C6229-1984-b"},
+ {68, "ISO646-JP-OCR-B"},
+ {68, "csISO92JISC62991984b"},
+ {68, "iso-ir-92"},
+ {68, "jp-ocr-b"},
+ {69, "JIS_C6229-1984-b-add"},
+ {69, "csISO93JIS62291984badd"},
+ {69, "iso-ir-93"},
+ {69, "jp-ocr-b-add"},
+ {70, "JIS_C6229-1984-hand"},
+ {70, "csISO94JIS62291984hand"},
+ {70, "iso-ir-94"},
+ {70, "jp-ocr-hand"},
+ {71, "JIS_C6229-1984-hand-add"},
+ {71, "csISO95JIS62291984handadd"},
+ {71, "iso-ir-95"},
+ {71, "jp-ocr-hand-add"},
+ {72, "JIS_C6229-1984-kana"},
+ {72, "csISO96JISC62291984kana"},
+ {72, "iso-ir-96"},
+ {73, "ISO_2033-1983"},
+ {73, "csISO2033"},
+ {73, "e13b"},
+ {73, "iso-ir-98"},
+ {74, "ANSI_X3.110-1983"},
+ {74, "CSA_T500-1983"},
+ {74, "NAPLPS"},
+ {74, "csISO99NAPLPS"},
+ {74, "iso-ir-99"},
+ {75, "T.61-7bit"},
+ {75, "csISO102T617bit"},
+ {75, "iso-ir-102"},
+ {76, "T.61-8bit"},
+ {76, "T.61"},
+ {76, "csISO103T618bit"},
+ {76, "iso-ir-103"},
+ {77, "ECMA-cyrillic"},
+ {77, "KOI8-E"},
+ {77, "csISO111ECMACyrillic"},
+ {77, "iso-ir-111"},
+ {78, "CSA_Z243.4-1985-1"},
+ {78, "ISO646-CA"},
+ {78, "ca"},
+ {78, "csISO121Canadian1"},
+ {78, "csa7-1"},
+ {78, "csa71"},
+ {78, "iso-ir-121"},
+ {79, "CSA_Z243.4-1985-2"},
+ {79, "ISO646-CA2"},
+ {79, "csISO122Canadian2"},
+ {79, "csa7-2"},
+ {79, "csa72"},
+ {79, "iso-ir-122"},
+ {80, "CSA_Z243.4-1985-gr"},
+ {80, "csISO123CSAZ24341985gr"},
+ {80, "iso-ir-123"},
+ {81, "ISO-8859-6-E"},
+ {81, "ISO_8859-6-E"},
+ {81, "csISO88596E"},
+ {82, "ISO-8859-6-I"},
+ {82, "ISO_8859-6-I"},
+ {82, "csISO88596I"},
+ {83, "T.101-G2"},
+ {83, "csISO128T101G2"},
+ {83, "iso-ir-128"},
+ {84, "ISO-8859-8-E"},
+ {84, "ISO_8859-8-E"},
+ {84, "csISO88598E"},
+ {85, "ISO-8859-8-I"},
+ {85, "ISO_8859-8-I"},
+ {85, "csISO88598I"},
+ {86, "CSN_369103"},
+ {86, "csISO139CSN369103"},
+ {86, "iso-ir-139"},
+ {87, "JUS_I.B1.002"},
+ {87, "ISO646-YU"},
+ {87, "csISO141JUSIB1002"},
+ {87, "iso-ir-141"},
+ {87, "js"},
+ {87, "yu"},
+ {88, "IEC_P27-1"},
+ {88, "csISO143IECP271"},
+ {88, "iso-ir-143"},
+ {89, "JUS_I.B1.003-serb"},
+ {89, "csISO146Serbian"},
+ {89, "iso-ir-146"},
+ {89, "serbian"},
+ {90, "JUS_I.B1.003-mac"},
+ {90, "csISO147Macedonian"},
+ {90, "iso-ir-147"},
+ {90, "macedonian"},
+ {91, "greek-ccitt"},
+ {91, "csISO150"},
+ {91, "csISO150GreekCCITT"},
+ {91, "iso-ir-150"},
+ {92, "NC_NC00-10:81"},
+ {92, "ISO646-CU"},
+ {92, "csISO151Cuba"},
+ {92, "cuba"},
+ {92, "iso-ir-151"},
+ {93, "ISO_6937-2-25"},
+ {93, "csISO6937Add"},
+ {93, "iso-ir-152"},
+ {94, "GOST_19768-74"},
+ {94, "ST_SEV_358-88"},
+ {94, "csISO153GOST1976874"},
+ {94, "iso-ir-153"},
+ {95, "ISO_8859-supp"},
+ {95, "csISO8859Supp"},
+ {95, "iso-ir-154"},
+ {95, "latin1-2-5"},
+ {96, "ISO_10367-box"},
+ {96, "csISO10367Box"},
+ {96, "iso-ir-155"},
+ {97, "latin-lap"},
+ {97, "csISO158Lap"},
+ {97, "iso-ir-158"},
+ {97, "lap"},
+ {98, "JIS_X0212-1990"},
+ {98, "csISO159JISX02121990"},
+ {98, "iso-ir-159"},
+ {98, "x0212"},
+ {99, "DS_2089"},
+ {99, "DS2089"},
+ {99, "ISO646-DK"},
+ {99, "csISO646Danish"},
+ {99, "dk"},
+ {100, "us-dk"},
+ {100, "csUSDK"},
+ {101, "dk-us"},
+ {101, "csDKUS"},
+ {102, "KSC5636"},
+ {102, "ISO646-KR"},
+ {102, "csKSC5636"},
+ {103, "UNICODE-1-1-UTF-7"},
+ {103, "csUnicode11UTF7"},
+ {104, "ISO-2022-CN"},
+ {104, "csISO2022CN"},
+ {105, "ISO-2022-CN-EXT"},
+ {105, "csISO2022CNEXT"},
+ {106, "UTF-8"},
+ {106, "csUTF8"},
+ {109, "ISO-8859-13"},
+ {109, "csISO885913"},
+ {110, "ISO-8859-14"},
+ {110, "ISO_8859-14"},
+ {110, "ISO_8859-14:1998"},
+ {110, "csISO885914"},
+ {110, "iso-celtic"},
+ {110, "iso-ir-199"},
+ {110, "l8"},
+ {110, "latin8"},
+ {111, "ISO-8859-15"},
+ {111, "ISO_8859-15"},
+ {111, "Latin-9"},
+ {111, "csISO885915"},
+ {112, "ISO-8859-16"},
+ {112, "ISO_8859-16"},
+ {112, "ISO_8859-16:2001"},
+ {112, "csISO885916"},
+ {112, "iso-ir-226"},
+ {112, "l10"},
+ {112, "latin10"},
+ {113, "GBK"},
+ {113, "CP936"},
+ {113, "MS936"},
+ {113, "csGBK"},
+ {113, "windows-936"},
+ {114, "GB18030"},
+ {114, "csGB18030"},
+ {115, "OSD_EBCDIC_DF04_15"},
+ {115, "csOSDEBCDICDF0415"},
+ {116, "OSD_EBCDIC_DF03_IRV"},
+ {116, "csOSDEBCDICDF03IRV"},
+ {117, "OSD_EBCDIC_DF04_1"},
+ {117, "csOSDEBCDICDF041"},
+ {118, "ISO-11548-1"},
+ {118, "ISO_11548-1"},
+ {118, "ISO_TR_11548-1"},
+ {118, "csISO115481"},
+ {119, "KZ-1048"},
+ {119, "RK1048"},
+ {119, "STRK1048-2002"},
+ {119, "csKZ1048"},
+ {1000, "ISO-10646-UCS-2"},
+ {1000, "csUnicode"},
+ {1001, "ISO-10646-UCS-4"},
+ {1001, "csUCS4"},
+ {1002, "ISO-10646-UCS-Basic"},
+ {1002, "csUnicodeASCII"},
+ {1003, "ISO-10646-Unicode-Latin1"},
+ {1003, "ISO-10646"},
+ {1003, "csUnicodeLatin1"},
+ {1004, "ISO-10646-J-1"},
+ {1004, "csUnicodeJapanese"},
+ {1005, "ISO-Unicode-IBM-1261"},
+ {1005, "csUnicodeIBM1261"},
+ {1006, "ISO-Unicode-IBM-1268"},
+ {1006, "csUnicodeIBM1268"},
+ {1007, "ISO-Unicode-IBM-1276"},
+ {1007, "csUnicodeIBM1276"},
+ {1008, "ISO-Unicode-IBM-1264"},
+ {1008, "csUnicodeIBM1264"},
+ {1009, "ISO-Unicode-IBM-1265"},
+ {1009, "csUnicodeIBM1265"},
+ {1010, "UNICODE-1-1"},
+ {1010, "csUnicode11"},
+ {1011, "SCSU"},
+ {1011, "csSCSU"},
+ {1012, "UTF-7"},
+ {1012, "csUTF7"},
+ {1013, "UTF-16BE"},
+ {1013, "csUTF16BE"},
+ {1014, "UTF-16LE"},
+ {1014, "csUTF16LE"},
+ {1015, "UTF-16"},
+ {1015, "csUTF16"},
+ {1016, "CESU-8"},
+ {1016, "csCESU-8"},
+ {1016, "csCESU8"},
+ {1017, "UTF-32"},
+ {1017, "csUTF32"},
+ {1018, "UTF-32BE"},
+ {1018, "csUTF32BE"},
+ {1019, "UTF-32LE"},
+ {1019, "csUTF32LE"},
+ {1020, "BOCU-1"},
+ {1020, "csBOCU-1"},
+ {1020, "csBOCU1"},
+ {1021, "UTF-7-IMAP"},
+ {1021, "csUTF7IMAP"},
+ {2000, "ISO-8859-1-Windows-3.0-Latin-1"},
+ {2000, "csWindows30Latin1"},
+ {2001, "ISO-8859-1-Windows-3.1-Latin-1"},
+ {2001, "csWindows31Latin1"},
+ {2002, "ISO-8859-2-Windows-Latin-2"},
+ {2002, "csWindows31Latin2"},
+ {2003, "ISO-8859-9-Windows-Latin-5"},
+ {2003, "csWindows31Latin5"},
+ {2004, "hp-roman8"},
+ {2004, "csHPRoman8"},
+ {2004, "r8"},
+ {2004, "roman8"},
+ {2005, "Adobe-Standard-Encoding"},
+ {2005, "csAdobeStandardEncoding"},
+ {2006, "Ventura-US"},
+ {2006, "csVenturaUS"},
+ {2007, "Ventura-International"},
+ {2007, "csVenturaInternational"},
+ {2008, "DEC-MCS"},
+ {2008, "csDECMCS"},
+ {2008, "dec"},
+ {2009, "IBM850"},
+ {2009, "850"},
+ {2009, "cp850"},
+ {2009, "csPC850Multilingual"},
+ {2010, "IBM852"},
+ {2010, "852"},
+ {2010, "cp852"},
+ {2010, "csPCp852"},
+ {2011, "IBM437"},
+ {2011, "437"},
+ {2011, "cp437"},
+ {2011, "csPC8CodePage437"},
+ {2012, "PC8-Danish-Norwegian"},
+ {2012, "csPC8DanishNorwegian"},
+ {2013, "IBM862"},
+ {2013, "862"},
+ {2013, "cp862"},
+ {2013, "csPC862LatinHebrew"},
+ {2014, "PC8-Turkish"},
+ {2014, "csPC8Turkish"},
+ {2015, "IBM-Symbols"},
+ {2015, "csIBMSymbols"},
+ {2016, "IBM-Thai"},
+ {2016, "csIBMThai"},
+ {2017, "HP-Legal"},
+ {2017, "csHPLegal"},
+ {2018, "HP-Pi-font"},
+ {2018, "csHPPiFont"},
+ {2019, "HP-Math8"},
+ {2019, "csHPMath8"},
+ {2020, "Adobe-Symbol-Encoding"},
+ {2020, "csHPPSMath"},
+ {2021, "HP-DeskTop"},
+ {2021, "csHPDesktop"},
+ {2022, "Ventura-Math"},
+ {2022, "csVenturaMath"},
+ {2023, "Microsoft-Publishing"},
+ {2023, "csMicrosoftPublishing"},
+ {2024, "Windows-31J"},
+ {2024, "csWindows31J"},
+ {2025, "GB2312"},
+ {2025, "csGB2312"},
+ {2026, "Big5"},
+ {2026, "csBig5"},
+ {2027, "macintosh"},
+ {2027, "csMacintosh"},
+ {2027, "mac"},
+ {2028, "IBM037"},
+ {2028, "cp037"},
+ {2028, "csIBM037"},
+ {2028, "ebcdic-cp-ca"},
+ {2028, "ebcdic-cp-nl"},
+ {2028, "ebcdic-cp-us"},
+ {2028, "ebcdic-cp-wt"},
+ {2029, "IBM038"},
+ {2029, "EBCDIC-INT"},
+ {2029, "cp038"},
+ {2029, "csIBM038"},
+ {2030, "IBM273"},
+ {2030, "CP273"},
+ {2030, "csIBM273"},
+ {2031, "IBM274"},
+ {2031, "CP274"},
+ {2031, "EBCDIC-BE"},
+ {2031, "csIBM274"},
+ {2032, "IBM275"},
+ {2032, "EBCDIC-BR"},
+ {2032, "cp275"},
+ {2032, "csIBM275"},
+ {2033, "IBM277"},
+ {2033, "EBCDIC-CP-DK"},
+ {2033, "EBCDIC-CP-NO"},
+ {2033, "csIBM277"},
+ {2034, "IBM278"},
+ {2034, "CP278"},
+ {2034, "csIBM278"},
+ {2034, "ebcdic-cp-fi"},
+ {2034, "ebcdic-cp-se"},
+ {2035, "IBM280"},
+ {2035, "CP280"},
+ {2035, "csIBM280"},
+ {2035, "ebcdic-cp-it"},
+ {2036, "IBM281"},
+ {2036, "EBCDIC-JP-E"},
+ {2036, "cp281"},
+ {2036, "csIBM281"},
+ {2037, "IBM284"},
+ {2037, "CP284"},
+ {2037, "csIBM284"},
+ {2037, "ebcdic-cp-es"},
+ {2038, "IBM285"},
+ {2038, "CP285"},
+ {2038, "csIBM285"},
+ {2038, "ebcdic-cp-gb"},
+ {2039, "IBM290"},
+ {2039, "EBCDIC-JP-kana"},
+ {2039, "cp290"},
+ {2039, "csIBM290"},
+ {2040, "IBM297"},
+ {2040, "cp297"},
+ {2040, "csIBM297"},
+ {2040, "ebcdic-cp-fr"},
+ {2041, "IBM420"},
+ {2041, "cp420"},
+ {2041, "csIBM420"},
+ {2041, "ebcdic-cp-ar1"},
+ {2042, "IBM423"},
+ {2042, "cp423"},
+ {2042, "csIBM423"},
+ {2042, "ebcdic-cp-gr"},
+ {2043, "IBM424"},
+ {2043, "cp424"},
+ {2043, "csIBM424"},
+ {2043, "ebcdic-cp-he"},
+ {2044, "IBM500"},
+ {2044, "CP500"},
+ {2044, "csIBM500"},
+ {2044, "ebcdic-cp-be"},
+ {2044, "ebcdic-cp-ch"},
+ {2045, "IBM851"},
+ {2045, "851"},
+ {2045, "cp851"},
+ {2045, "csIBM851"},
+ {2046, "IBM855"},
+ {2046, "855"},
+ {2046, "cp855"},
+ {2046, "csIBM855"},
+ {2047, "IBM857"},
+ {2047, "857"},
+ {2047, "cp857"},
+ {2047, "csIBM857"},
+ {2048, "IBM860"},
+ {2048, "860"},
+ {2048, "cp860"},
+ {2048, "csIBM860"},
+ {2049, "IBM861"},
+ {2049, "861"},
+ {2049, "cp-is"},
+ {2049, "cp861"},
+ {2049, "csIBM861"},
+ {2050, "IBM863"},
+ {2050, "863"},
+ {2050, "cp863"},
+ {2050, "csIBM863"},
+ {2051, "IBM864"},
+ {2051, "cp864"},
+ {2051, "csIBM864"},
+ {2052, "IBM865"},
+ {2052, "865"},
+ {2052, "cp865"},
+ {2052, "csIBM865"},
+ {2053, "IBM868"},
+ {2053, "CP868"},
+ {2053, "cp-ar"},
+ {2053, "csIBM868"},
+ {2054, "IBM869"},
+ {2054, "869"},
+ {2054, "cp-gr"},
+ {2054, "cp869"},
+ {2054, "csIBM869"},
+ {2055, "IBM870"},
+ {2055, "CP870"},
+ {2055, "csIBM870"},
+ {2055, "ebcdic-cp-roece"},
+ {2055, "ebcdic-cp-yu"},
+ {2056, "IBM871"},
+ {2056, "CP871"},
+ {2056, "csIBM871"},
+ {2056, "ebcdic-cp-is"},
+ {2057, "IBM880"},
+ {2057, "EBCDIC-Cyrillic"},
+ {2057, "cp880"},
+ {2057, "csIBM880"},
+ {2058, "IBM891"},
+ {2058, "cp891"},
+ {2058, "csIBM891"},
+ {2059, "IBM903"},
+ {2059, "cp903"},
+ {2059, "csIBM903"},
+ {2060, "IBM904"},
+ {2060, "904"},
+ {2060, "cp904"},
+ {2060, "csIBBM904"},
+ {2061, "IBM905"},
+ {2061, "CP905"},
+ {2061, "csIBM905"},
+ {2061, "ebcdic-cp-tr"},
+ {2062, "IBM918"},
+ {2062, "CP918"},
+ {2062, "csIBM918"},
+ {2062, "ebcdic-cp-ar2"},
+ {2063, "IBM1026"},
+ {2063, "CP1026"},
+ {2063, "csIBM1026"},
+ {2064, "EBCDIC-AT-DE"},
+ {2064, "csIBMEBCDICATDE"},
+ {2065, "EBCDIC-AT-DE-A"},
+ {2065, "csEBCDICATDEA"},
+ {2066, "EBCDIC-CA-FR"},
+ {2066, "csEBCDICCAFR"},
+ {2067, "EBCDIC-DK-NO"},
+ {2067, "csEBCDICDKNO"},
+ {2068, "EBCDIC-DK-NO-A"},
+ {2068, "csEBCDICDKNOA"},
+ {2069, "EBCDIC-FI-SE"},
+ {2069, "csEBCDICFISE"},
+ {2070, "EBCDIC-FI-SE-A"},
+ {2070, "csEBCDICFISEA"},
+ {2071, "EBCDIC-FR"},
+ {2071, "csEBCDICFR"},
+ {2072, "EBCDIC-IT"},
+ {2072, "csEBCDICIT"},
+ {2073, "EBCDIC-PT"},
+ {2073, "csEBCDICPT"},
+ {2074, "EBCDIC-ES"},
+ {2074, "csEBCDICES"},
+ {2075, "EBCDIC-ES-A"},
+ {2075, "csEBCDICESA"},
+ {2076, "EBCDIC-ES-S"},
+ {2076, "csEBCDICESS"},
+ {2077, "EBCDIC-UK"},
+ {2077, "csEBCDICUK"},
+ {2078, "EBCDIC-US"},
+ {2078, "csEBCDICUS"},
+ {2079, "UNKNOWN-8BIT"},
+ {2079, "csUnknown8BiT"},
+ {2080, "MNEMONIC"},
+ {2080, "csMnemonic"},
+ {2081, "MNEM"},
+ {2081, "csMnem"},
+ {2082, "VISCII"},
+ {2082, "csVISCII"},
+ {2083, "VIQR"},
+ {2083, "csVIQR"},
+ {2084, "KOI8-R"},
+ {2084, "csKOI8R"},
+ {2085, "HZ-GB-2312"},
+ {2086, "IBM866"},
+ {2086, "866"},
+ {2086, "cp866"},
+ {2086, "csIBM866"},
+ {2087, "IBM775"},
+ {2087, "cp775"},
+ {2087, "csPC775Baltic"},
+ {2088, "KOI8-U"},
+ {2088, "csKOI8U"},
+ {2089, "IBM00858"},
+ {2089, "CCSID00858"},
+ {2089, "CP00858"},
+ {2089, "PC-Multilingual-850+euro"},
+ {2089, "csIBM00858"},
+ {2090, "IBM00924"},
+ {2090, "CCSID00924"},
+ {2090, "CP00924"},
+ {2090, "csIBM00924"},
+ {2090, "ebcdic-Latin9--euro"},
+ {2091, "IBM01140"},
+ {2091, "CCSID01140"},
+ {2091, "CP01140"},
+ {2091, "csIBM01140"},
+ {2091, "ebcdic-us-37+euro"},
+ {2092, "IBM01141"},
+ {2092, "CCSID01141"},
+ {2092, "CP01141"},
+ {2092, "csIBM01141"},
+ {2092, "ebcdic-de-273+euro"},
+ {2093, "IBM01142"},
+ {2093, "CCSID01142"},
+ {2093, "CP01142"},
+ {2093, "csIBM01142"},
+ {2093, "ebcdic-dk-277+euro"},
+ {2093, "ebcdic-no-277+euro"},
+ {2094, "IBM01143"},
+ {2094, "CCSID01143"},
+ {2094, "CP01143"},
+ {2094, "csIBM01143"},
+ {2094, "ebcdic-fi-278+euro"},
+ {2094, "ebcdic-se-278+euro"},
+ {2095, "IBM01144"},
+ {2095, "CCSID01144"},
+ {2095, "CP01144"},
+ {2095, "csIBM01144"},
+ {2095, "ebcdic-it-280+euro"},
+ {2096, "IBM01145"},
+ {2096, "CCSID01145"},
+ {2096, "CP01145"},
+ {2096, "csIBM01145"},
+ {2096, "ebcdic-es-284+euro"},
+ {2097, "IBM01146"},
+ {2097, "CCSID01146"},
+ {2097, "CP01146"},
+ {2097, "csIBM01146"},
+ {2097, "ebcdic-gb-285+euro"},
+ {2098, "IBM01147"},
+ {2098, "CCSID01147"},
+ {2098, "CP01147"},
+ {2098, "csIBM01147"},
+ {2098, "ebcdic-fr-297+euro"},
+ {2099, "IBM01148"},
+ {2099, "CCSID01148"},
+ {2099, "CP01148"},
+ {2099, "csIBM01148"},
+ {2099, "ebcdic-international-500+euro"},
+ {2100, "IBM01149"},
+ {2100, "CCSID01149"},
+ {2100, "CP01149"},
+ {2100, "csIBM01149"},
+ {2100, "ebcdic-is-871+euro"},
+ {2101, "Big5-HKSCS"},
+ {2101, "csBig5HKSCS"},
+ {2102, "IBM1047"},
+ {2102, "IBM-1047"},
+ {2102, "csIBM1047"},
+ {2103, "PTCP154"},
+ {2103, "CP154"},
+ {2103, "Cyrillic-Asian"},
+ {2103, "PT154"},
+ {2103, "csPTCP154"},
+ {2104, "Amiga-1251"},
+ {2104, "Ami-1251"},
+ {2104, "Ami1251"},
+ {2104, "Amiga1251"},
+ {2104, "csAmiga1251"},
+ {2105, "KOI7-switched"},
+ {2105, "csKOI7switched"},
+ {2106, "BRF"},
+ {2106, "csBRF"},
+ {2107, "TSCII"},
+ {2107, "csTSCII"},
+ {2108, "CP51932"},
+ {2108, "csCP51932"},
+ {2109, "windows-874"},
+ {2109, "cswindows874"},
+ {2250, "windows-1250"},
+ {2250, "cswindows1250"},
+ {2251, "windows-1251"},
+ {2251, "cswindows1251"},
+ {2252, "windows-1252"},
+ {2252, "cswindows1252"},
+ {2253, "windows-1253"},
+ {2253, "cswindows1253"},
+ {2254, "windows-1254"},
+ {2254, "cswindows1254"},
+ {2255, "windows-1255"},
+ {2255, "cswindows1255"},
+ {2256, "windows-1256"},
+ {2256, "cswindows1256"},
+ {2257, "windows-1257"},
+ {2257, "cswindows1257"},
+ {2258, "windows-1258"},
+ {2258, "cswindows1258"},
+ {2259, "TIS-620"},
+ {2259, "ISO-8859-11"},
+ {2259, "csTIS620"},
+ {2260, "CP50220"},
+ {2260, "csCP50220"},
+ {0, nullptr} // sentinel
+ };
+
+ const __encoding_data* __encoding_rep_ = __text_encoding_data + 1;
+ char __name_[max_name_length + 1] = {0};
+};
+
+template <>
+struct hash<text_encoding> {
+ size_t operator()(const text_encoding& __enc) const noexcept { return std::hash<text_encoding::id>()(__enc.mib()); }
+};
+
+namespace ranges {
+
+template <>
+inline constexpr bool enable_borrowed_range<text_encoding::aliases_view> = true;
+
+} // namespace ranges
+
+_LIBCPP_END_NAMESPACE_STD
+
+#endif // _LIBCPP_STD_VER >= 26
+
+_LIBCPP_POP_MACROS
+
+#endif // _LIBCPP_HAS_LOCALIZATION
+
+#endif // _LIBCPP___TEXT_ENCODING_TEXT_ENCODING_H
diff --git a/libcxx/include/module.modulemap.in b/libcxx/include/module.modulemap.in
index 7f625cefed1c2..a347538620f4d 100644
--- a/libcxx/include/module.modulemap.in
+++ b/libcxx/include/module.modulemap.in
@@ -2056,6 +2056,13 @@ module std [system] {
export *
}
+ module text_encoding {
+ module text_encoding { header "__text_encoding/text_encoding.h" }
+
+ header "text_encoding"
+ export *
+ }
+
module thread {
module formatter { header "__thread/formatter.h" }
module id { header "__thread/id.h" }
diff --git a/libcxx/include/text_encoding b/libcxx/include/text_encoding
new file mode 100644
index 0000000000000..579608e4f939d
--- /dev/null
+++ b/libcxx/include/text_encoding
@@ -0,0 +1,68 @@
+// -*- C++ -*-
+//===----------------------------------------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef _LIBCPP_TEXT_ENCODING
+#define _LIBCPP_TEXT_ENCODING
+
+/* text_encoding synopsis
+namespace std {
+
+struct text_encoding;
+
+// [text.encoding.hash], hash support
+template<class T> struct hash;
+template<> struct hash<text_encoding>;
+
+struct text_encoding
+{
+ static constexpr size_t max_name_length = 63;
+
+ // [text.encoding.id], enumeration text_encoding::id
+ enum class id : int_least32_t {
+ see below
+ };
+ using enum id;
+
+ constexpr text_encoding() = default;
+ constexpr explicit text_encoding(string_view enc) noexcept;
+ constexpr text_encoding(id i) noexcept;
+
+ constexpr id mib() const noexcept;
+ constexpr const char* name() const noexcept;
+
+ // [text.encoding.aliases], class text_encoding::aliases_view
+ struct aliases_view;
+ constexpr aliases_view aliases() const noexcept;
+
+ friend constexpr bool operator==(const text_encoding& a,
+ const text_encoding& b) noexcept;
+ friend constexpr bool operator==(const text_encoding& encoding, id i) noexcept;
+
+ static consteval text_encoding literal() noexcept;
+ static text_encoding environment();
+ template<id i> static bool environment_is();
+
+ private:
+ id mib_ = id::unknown; // exposition only
+ char name_[max_name_length + 1] = {0}; // exposition only
+ static constexpr bool comp-name(string_view a, string_view b); // exposition only
+};
+}
+
+*/
+
+#include <__config>
+
+#if _LIBCPP_STD_VER >= 26
+# include <__text_encoding/text_encoding.h>
+#endif // _LIBCPP_STD_VER >= 26
+
+#include <version>
+
+#endif // _LIBCPP_TEXT_ENCODING
diff --git a/libcxx/include/version b/libcxx/include/version
index 77d97b93adc6c..3079feac1ed54 100644
--- a/libcxx/include/version
+++ b/libcxx/include/version
@@ -592,7 +592,7 @@ __cpp_lib_void_t 201411L <type_traits>
# undef __cpp_lib_string_view
# define __cpp_lib_string_view 202403L
// # define __cpp_lib_submdspan 202306L
-// # define __cpp_lib_text_encoding 202306L
+# define __cpp_lib_text_encoding 202306L
# undef __cpp_lib_to_chars
// # define __cpp_lib_to_chars 202306L
// # define __cpp_lib_to_string 202306L
diff --git a/libcxx/modules/std.compat.cppm.in b/libcxx/modules/std.compat.cppm.in
index 95931447ccdc6..ce9b8bb5ec279 100644
--- a/libcxx/modules/std.compat.cppm.in
+++ b/libcxx/modules/std.compat.cppm.in
@@ -77,9 +77,6 @@ module;
# if __has_include(<stdfloat>)
# error "please update the header information for <stdfloat> in headers_not_available in utils/libcxx/header_information.py"
# endif // __has_include(<stdfloat>)
-# if __has_include(<text_encoding>)
-# error "please update the header information for <text_encoding> in headers_not_available in utils/libcxx/header_information.py"
-# endif // __has_include(<text_encoding>)
#endif // _WIN32
export module std.compat;
diff --git a/libcxx/modules/std.cppm.in b/libcxx/modules/std.cppm.in
index 5c523691bff4e..6f396e9ccdd90 100644
--- a/libcxx/modules/std.cppm.in
+++ b/libcxx/modules/std.cppm.in
@@ -138,6 +138,9 @@ module;
# include <syncstream>
#endif
#include <system_error>
+#if _LIBCPP_HAS_LOCALIZATION
+# include <text_encoding>
+#endif
#include <thread>
#include <tuple>
#include <type_traits>
@@ -187,9 +190,6 @@ module;
# if __has_include(<stdfloat>)
# error "please update the header information for <stdfloat> in headers_not_available in utils/libcxx/header_information.py"
# endif // __has_include(<stdfloat>)
-# if __has_include(<text_encoding>)
-# error "please update the header information for <text_encoding> in headers_not_available in utils/libcxx/header_information.py"
-# endif // __has_include(<text_encoding>)
#endif // _WIN32
export module std;
diff --git a/libcxx/modules/std/text_encoding.inc b/libcxx/modules/std/text_encoding.inc
index 6d5e3f1d68c60..23dd71965414c 100644
--- a/libcxx/modules/std/text_encoding.inc
+++ b/libcxx/modules/std/text_encoding.inc
@@ -8,12 +8,9 @@
//===----------------------------------------------------------------------===//
export namespace std {
-#if 0
-# if _LIBCPP_STD_VER >= 23
+#if _LIBCPP_STD_VER >= 26
+ using ::std::hash;
using std::text_encoding;
-
- // hash support
- using std::hash;
-# endif // _LIBCPP_STD_VER >= 23
+ using ::std::ranges::enable_borrowed_range;
#endif
} // namespace std
diff --git a/libcxx/src/CMakeLists.txt b/libcxx/src/CMakeLists.txt
index 4e9bf900af4c5..1a98812894896 100644
--- a/libcxx/src/CMakeLists.txt
+++ b/libcxx/src/CMakeLists.txt
@@ -92,6 +92,7 @@ if (LIBCXX_ENABLE_LOCALIZATION)
ostream.cpp
regex.cpp
strstream.cpp
+ text_encoding.cpp
)
endif()
diff --git a/libcxx/src/locale.cpp b/libcxx/src/locale.cpp
index d981d137cf1ba..6d8dababb84ce 100644
--- a/libcxx/src/locale.cpp
+++ b/libcxx/src/locale.cpp
@@ -558,6 +558,19 @@ locale::locale(const locale& other, const locale& one, category c)
string locale::name() const { return __locale_->name(); }
+# if _LIBCPP_STD_VER >= 26 && __CHAR_BIT__ == 8
+ text_encoding locale::encoding() const {
+ std::string __name = this->name();
+ if(__name.size() == 1){
+ if(__name[0] == 'C')
+ return std::text_encoding(text_encoding::id::ASCII);
+ if(__name[0] == '*')
+ return std::text_encoding();
+ }
+ return std::text_encoding(__name);
+ }
+# endif // _LIBCPP_STD_VER >= 26
+
void locale::__install_ctor(const locale& other, facet* f, long facet_id) {
if (f)
__locale_ = new __imp(*other.__locale_, f, facet_id);
diff --git a/libcxx/src/text_encoding.cpp b/libcxx/src/text_encoding.cpp
new file mode 100644
index 0000000000000..42812aaed49c7
--- /dev/null
+++ b/libcxx/src/text_encoding.cpp
@@ -0,0 +1,49 @@
+//===----------------------------------------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+#include <__config>
+
+#if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
+# pragma GCC system_header
+#endif
+
+#include <__locale_dir/locale_base_api.h>
+
+#include <text_encoding>
+
+#if __has_include(<langinfo.h>)
+# include <langinfo.h>
+#endif
+
+#if _LIBCPP_STD_VER >= 26
+
+_LIBCPP_BEGIN_NAMESPACE_STD
+#if __CHAR_BIT__ == 8
+
+text_encoding text_encoding::environment() {
+ auto __make_locale = [](const char* __name) {
+ text_encoding __enc{};
+ if (auto __loc = __locale::__newlocale(LC_CTYPE_MASK, __name, static_cast<locale_t>(0))) {
+ if (const char* __codeset = nl_langinfo_l(CODESET, __loc)) {
+ string_view __s(__codeset);
+ if (__s.size() < max_name_length)
+ __enc = text_encoding(__s);
+ }
+ __locale::__freelocale(__loc);
+ }
+ return __enc;
+ };
+
+ return __make_locale("");
+ }
+
+# endif // __CHAR_BIT__ == 8
+
+_LIBCPP_END_NAMESPACE_STD
+
+#endif // _LIBCPP_STD_VER > 26
diff --git a/libcxx/test/libcxx/transitive_includes/cxx26.csv b/libcxx/test/libcxx/transitive_includes/cxx26.csv
index ce8f0261f2b27..24e57ab696857 100644
--- a/libcxx/test/libcxx/transitive_includes/cxx26.csv
+++ b/libcxx/test/libcxx/transitive_includes/cxx26.csv
@@ -1065,6 +1065,21 @@ system_error string
system_error string_view
system_error tuple
system_error version
+text_encoding cctype
+text_encoding clocale
+text_encoding compare
+text_encoding cstdint
+text_encoding cstdio
+text_encoding cstdlib
+text_encoding cstring
+text_encoding cwchar
+text_encoding cwctype
+text_encoding initializer_list
+text_encoding iosfwd
+text_encoding limits
+text_encoding stdexcept
+text_encoding string_view
+text_encoding version
thread array
thread atomic
thread bitset
diff --git a/libcxx/test/std/language.support/support.limits/support.limits.general/text_encoding.version.compile.pass.cpp b/libcxx/test/std/language.support/support.limits/support.limits.general/text_encoding.version.compile.pass.cpp
new file mode 100644
index 0000000000000..817b0f0d655db
--- /dev/null
+++ b/libcxx/test/std/language.support/support.limits/support.limits.general/text_encoding.version.compile.pass.cpp
@@ -0,0 +1,63 @@
+//===----------------------------------------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+// WARNING: This test was generated by generate_feature_test_macro_components.py
+// and should not be edited manually.
+
+// <text_encoding>
+
+// Test the feature test macros defined by <text_encoding>
+
+// clang-format off
+
+#include <text_encoding>
+#include "test_macros.h"
+
+#if TEST_STD_VER < 14
+
+# ifdef __cpp_lib_text_encoding
+# error "__cpp_lib_text_encoding should not be defined before c++26"
+# endif
+
+#elif TEST_STD_VER == 14
+
+# ifdef __cpp_lib_text_encoding
+# error "__cpp_lib_text_encoding should not be defined before c++26"
+# endif
+
+#elif TEST_STD_VER == 17
+
+# ifdef __cpp_lib_text_encoding
+# error "__cpp_lib_text_encoding should not be defined before c++26"
+# endif
+
+#elif TEST_STD_VER == 20
+
+# ifdef __cpp_lib_text_encoding
+# error "__cpp_lib_text_encoding should not be defined before c++26"
+# endif
+
+#elif TEST_STD_VER == 23
+
+# ifdef __cpp_lib_text_encoding
+# error "__cpp_lib_text_encoding should not be defined before c++26"
+# endif
+
+#elif TEST_STD_VER > 23
+
+# ifndef __cpp_lib_text_encoding
+# error "__cpp_lib_text_encoding should be defined in c++26"
+# endif
+# if __cpp_lib_text_encoding != 202306L
+# error "__cpp_lib_text_encoding should have the value 202306L in c++26"
+# endif
+
+#endif // TEST_STD_VER > 23
+
+// clang-format on
+
diff --git a/libcxx/test/std/language.support/support.limits/support.limits.general/version.version.compile.pass.cpp b/libcxx/test/std/language.support/support.limits/support.limits.general/version.version.compile.pass.cpp
index aa33a2788f1eb..ffcaeb4904b60 100644
--- a/libcxx/test/std/language.support/support.limits/support.limits.general/version.version.compile.pass.cpp
+++ b/libcxx/test/std/language.support/support.limits/support.limits.general/version.version.compile.pass.cpp
@@ -7852,17 +7852,11 @@
# endif
# endif
-# if !defined(_LIBCPP_VERSION)
-# ifndef __cpp_lib_text_encoding
-# error "__cpp_lib_text_encoding should be defined in c++26"
-# endif
-# if __cpp_lib_text_encoding != 202306L
-# error "__cpp_lib_text_encoding should have the value 202306L in c++26"
-# endif
-# else
-# ifdef __cpp_lib_text_encoding
-# error "__cpp_lib_text_encoding should not be defined because it is unimplemented in libc++!"
-# endif
+# ifndef __cpp_lib_text_encoding
+# error "__cpp_lib_text_encoding should be defined in c++26"
+# endif
+# if __cpp_lib_text_encoding != 202306L
+# error "__cpp_lib_text_encoding should have the value 202306L in c++26"
# endif
# ifndef __cpp_lib_three_way_comparison
diff --git a/libcxx/test/std/localization/locales/locale/locale.members/encoding.pass.cpp b/libcxx/test/std/localization/locales/locale/locale.members/encoding.pass.cpp
new file mode 100644
index 0000000000000..7ebfb5a0b4f74
--- /dev/null
+++ b/libcxx/test/std/localization/locales/locale/locale.members/encoding.pass.cpp
@@ -0,0 +1,56 @@
+
+//===----------------------------------------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+// <text_encoding>
+
+// libc++ not built with C++26 yet
+// XFAIL: *
+// REQUIRES: std-at-least-c++26
+// REQUIRES: locale.en_US.UTF-8
+// UNSUPPORTED: no-localization
+
+// class locale
+
+// text_encoding encoding() const
+
+// Concerns:
+// 1. Default locale returns a text_encoding representing "ASCII"
+// 2. Locale built with en_US.UTF-8 returns text_encoding representing "UTF-8"
+
+#include <cassert>
+#include <locale>
+#include <text_encoding>
+
+#include "test_macros.h"
+#include "platform_support.h"
+
+using id = std::text_encoding::id;
+
+int main() {
+
+ {
+ std::locale loc;
+
+ auto te = loc.encoding();
+ auto classicTE = std::text_encoding(id::ASCII);
+ assert(te == id::ASCII);
+ assert(te == classicTE);
+ }
+
+ {
+ std::locale utf8Locale(LOCALE_en_US_UTF_8);
+
+ auto te = utf8Locale.encoding();
+ auto utf8TE = std::text_encoding(id::UTF8);
+ assert(te == id::UTF8);
+ assert(te == utf8TE);
+ }
+
+ return 0;
+}
diff --git a/libcxx/test/std/utilities/text_encoding/text_encoding.ctor/default.pass.cpp b/libcxx/test/std/utilities/text_encoding/text_encoding.ctor/default.pass.cpp
new file mode 100644
index 0000000000000..62c30d7295491
--- /dev/null
+++ b/libcxx/test/std/utilities/text_encoding/text_encoding.ctor/default.pass.cpp
@@ -0,0 +1,39 @@
+//===----------------------------------------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+// <text_encoding>
+
+// REQUIRES: std-at-least-c++26
+
+// UNSUPPORTED: no-localization
+
+// class text_encoding
+
+// text_encoding::text_encoding() noexcept
+
+// Concerns:
+// 1. Default constructor must be nothrow
+// 2. Default constructing a text_encoding object makes it so that mib() == id::unknown, and its name is empty
+
+#include <cassert>
+#include <cstring>
+#include <text_encoding>
+#include <type_traits>
+
+int main(int, char**) {
+ {
+ static_assert(
+ std::is_nothrow_default_constructible<std::text_encoding>::value, "Must be nothrow default constructible");
+ }
+
+ {
+ auto te = std::text_encoding();
+ assert(te.mib() == std::text_encoding::id::unknown);
+ assert(strcmp(te.name(), "") == 0);
+ }
+}
diff --git a/libcxx/test/std/utilities/text_encoding/text_encoding.ctor/id.pass.cpp b/libcxx/test/std/utilities/text_encoding/text_encoding.ctor/id.pass.cpp
new file mode 100644
index 0000000000000..6562971c73dbb
--- /dev/null
+++ b/libcxx/test/std/utilities/text_encoding/text_encoding.ctor/id.pass.cpp
@@ -0,0 +1,56 @@
+//===----------------------------------------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+// <text_encoding>
+
+// REQUIRES: std-at-least-c++26
+
+// UNSUPPORTED: no-localization
+
+// class text_encoding
+
+// text_encoding::text_encoding(id) noexcept
+
+// Concerns:
+// 1. text_encoding(id) must be nothrow
+// 2. Constructing an object with a valid id must set mib() and the name to the corresponding value.
+// 3. Constructing an object using id::unknown must set mib() to id::unknown and the name to an empty string.
+// 4. Constructing an object using id::other must set mib() to id::other and the name to an empty string.
+
+#include "test_text_encoding.h"
+#include <cassert>
+#include <string_view>
+#include <text_encoding>
+#include <type_traits>
+
+using te_id = std::text_encoding::id;
+
+constexpr void test_ctor(te_id i, te_id expect_id, std::string_view expect_name) {
+ auto te = std::text_encoding(i);
+ assert(te.mib() == expect_id);
+ assert(expect_name.compare(te.name()) == 0);
+}
+
+int main() {
+ {
+ static_assert(std::is_nothrow_constructible<std::text_encoding, std::text_encoding::id>::value,
+ "Must be nothrow constructible with id");
+ }
+
+ {
+ for (auto pair : unique_encoding_data){
+ test_ctor(te_id{pair.mib}, te_id{pair.mib}, pair.name);
+ }
+ }
+
+ {
+ for(int i = 2261; i < 2300; i++){ // test out of range id values
+ test_ctor(te_id{i}, te_id::unknown, "");
+ }
+ }
+}
diff --git a/libcxx/test/std/utilities/text_encoding/text_encoding.ctor/string_view.pass.cpp b/libcxx/test/std/utilities/text_encoding/text_encoding.ctor/string_view.pass.cpp
new file mode 100644
index 0000000000000..b72adf0274cb2
--- /dev/null
+++ b/libcxx/test/std/utilities/text_encoding/text_encoding.ctor/string_view.pass.cpp
@@ -0,0 +1,73 @@
+//===----------------------------------------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+// <text_encoding>
+
+// REQUIRES: std-at-least-c++26
+
+// UNSUPPORTED: no-localization
+
+// class text_encoding
+
+// text_encoding::text_encoding(string_view) noexcept
+
+#include "test_macros.h"
+#include "test_text_encoding.h"
+#include <cassert>
+#include <cstring>
+#include <string_view>
+#include <text_encoding>
+#include <type_traits>
+
+constexpr void test_ctor(std::string_view str, std::string_view expect, std::text_encoding::id expect_id) {
+ auto te = std::text_encoding(str);
+ assert(te.mib() == expect_id);
+ assert(expect.compare(te.name()) == 0);
+}
+
+void test_correct_encoding_spellings() {
+ for (auto pair : unique_encoding_data) {
+ test_ctor(pair.name, pair.name, std::text_encoding::id{pair.mib});
+ }
+}
+
+int main() {
+ {
+ static_assert(std::is_nothrow_constructible<std::text_encoding, std::string_view>::value,
+ "Must be nothrow constructible with string_view");
+ }
+
+ // happy paths
+ {
+ test_correct_encoding_spellings();
+ }
+
+ {
+ test_ctor("U_T_F-8", "U_T_F-8", std::text_encoding::UTF8);
+ }
+
+ {
+ test_ctor("utf8", "utf8", std::text_encoding::UTF8);
+ }
+
+ {
+ test_ctor("u.t.f-008", "u.t.f-008", std::text_encoding::UTF8);
+ }
+
+ {
+ test_ctor("utf-80", "utf-80", std::text_encoding::other);
+ }
+
+ {
+ test_ctor("iso885931988", "iso885931988", std::text_encoding::ISOLatin3);
+ }
+
+ {
+ test_ctor("iso00885931988", "iso00885931988", std::text_encoding::ISOLatin3);
+ }
+}
diff --git a/libcxx/test/std/utilities/text_encoding/text_encoding.eq/equal.id.pass.cpp b/libcxx/test/std/utilities/text_encoding/text_encoding.eq/equal.id.pass.cpp
new file mode 100644
index 0000000000000..30ce1badec1d7
--- /dev/null
+++ b/libcxx/test/std/utilities/text_encoding/text_encoding.eq/equal.id.pass.cpp
@@ -0,0 +1,69 @@
+//===----------------------------------------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+// <text_encoding>
+
+// REQUIRES: std-at-least-c++26
+
+// UNSUPPORTED: no-localization
+
+// class text_encoding
+
+// text_encoding operator==(const text_encoding&, id) _NOEXCEPT
+
+// Concerns:
+// 1. operator==(const text_encoding&, id) must be noexcept
+// 2. operator==(const text_encoding&, id) returns true if mib() is equal to the id
+// 3. operator==(const text_encoding&, id) returns false if mib() is not equal to the id
+
+#include <cassert>
+#include <text_encoding>
+#include <type_traits>
+
+#include "test_macros.h"
+#include "test_text_encoding.h"
+
+using id = std::text_encoding::id;
+
+int main() {
+
+ { // 1
+ auto te = std::text_encoding();
+ ASSERT_NOEXCEPT(te == id::UTF8);
+ }
+
+ { // 2
+ auto te = std::text_encoding(id::UTF8);
+ assert(te == id::UTF8);
+ }
+
+ { // 2.0.1
+ constexpr auto te = std::text_encoding();
+ static_assert(te == id::unknown);
+ }
+
+ { // 2.1
+ auto te = std::text_encoding(id::other);
+ assert(te == id::other);
+ }
+
+ { // 2.1.1
+ constexpr auto te = std::text_encoding(id::other);
+ static_assert(te == id::other);
+ }
+
+ { // 3
+ auto te = std::text_encoding(id::UTF8);
+ assert(!(te == id::UTF16));
+ }
+
+ { // 3
+ constexpr auto te = std::text_encoding(id::UTF8);
+ static_assert(!(te == id::UTF16));
+ }
+}
diff --git a/libcxx/test/std/utilities/text_encoding/text_encoding.eq/equal.pass.cpp b/libcxx/test/std/utilities/text_encoding/text_encoding.eq/equal.pass.cpp
new file mode 100644
index 0000000000000..81fdb0a681143
--- /dev/null
+++ b/libcxx/test/std/utilities/text_encoding/text_encoding.eq/equal.pass.cpp
@@ -0,0 +1,66 @@
+//===----------------------------------------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+// <text_encoding>
+
+// REQUIRES: std-at-least-c++26
+
+// UNSUPPORTED: no-localization
+
+// class text_encoding
+
+// text_encoding operator==(const text_encoding&, const text_encoding&) _NOEXCEPT
+
+// Concerns:
+// 1. operator==(const text_encoding&, const text_encoding&) must be noexcept
+// 2. operator==(const text_encoding&, const text_encoding&) returns true if both text_encoding ids are equal
+// 3. operator==(const text_encoding&, const text_encoding&) for text_encodings with ids of "other" return true if the names are equal
+// 4. operator==(const text_encoding&, const text_encoding&) returns false when comparingtext_encodings with different ids
+// 5. operator==(const text_encoding&, const text_encoding&) for text_encodings with ids of "other" returns false if the names are not equal
+
+#include <cassert>
+#include <text_encoding>
+#include <type_traits>
+
+#include "test_macros.h"
+#include "test_text_encoding.h"
+
+using id = std::text_encoding::id;
+
+int main(){
+
+ { // 1
+ auto te1 = std::text_encoding();
+ auto te2 = std::text_encoding();
+ ASSERT_NOEXCEPT(te1 == te2);
+ }
+
+ { // 2
+ auto te1 = std::text_encoding(id::UTF8);
+ auto te2 = std::text_encoding(id::UTF8);
+ assert(te1 == te2);
+ }
+
+ { // 3
+ auto other_te1 = std::text_encoding("foo");
+ auto other_te2 = std::text_encoding("foo");
+ assert(other_te1 == other_te2);
+ }
+
+ { // 4
+ auto te1 = std::text_encoding(id::UTF8);
+ auto te2 = std::text_encoding(id::UTF16);
+ assert(!(te1 == te2));
+ }
+
+ { // 5
+ auto other_te1 = std::text_encoding("foo");
+ auto other_te2 = std::text_encoding("bar");
+ assert(!(other_te1 == other_te2));
+ }
+}
diff --git a/libcxx/test/std/utilities/text_encoding/text_encoding.members/aliases.pass.cpp b/libcxx/test/std/utilities/text_encoding/text_encoding.members/aliases.pass.cpp
new file mode 100644
index 0000000000000..345438d6a1ecb
--- /dev/null
+++ b/libcxx/test/std/utilities/text_encoding/text_encoding.members/aliases.pass.cpp
@@ -0,0 +1,37 @@
+//===----------------------------------------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+// <text_encoding>
+
+// REQUIRES: std-at-least-c++26
+// UNSUPPORTED: no-localization
+
+// class text_encoding
+
+// text_encoding text_encoding::environment();
+
+// Concerns:
+// 1. Verify that text_encoding::aliases_view satisfies ranges::forward_range, copyable, view,
+// ranges::random_access_range and ranges::borrowed_range
+
+#include <concepts>
+#include <ranges>
+#include <text_encoding>
+#include <type_traits>
+
+#include "platform_support.h"
+#include "test_macros.h"
+#include "test_text_encoding.h"
+
+int main(){
+ static_assert(std::ranges::forward_range<std::text_encoding::aliases_view>);
+ static_assert(std::copyable<std::text_encoding::aliases_view>);
+ static_assert(std::ranges::view<std::text_encoding::aliases_view>);
+ static_assert(std::ranges::random_access_range<std::text_encoding::aliases_view>);
+ static_assert(std::ranges::borrowed_range<std::text_encoding::aliases_view>);
+}
diff --git a/libcxx/test/std/utilities/text_encoding/text_encoding.members/environment.pass.cpp b/libcxx/test/std/utilities/text_encoding/text_encoding.members/environment.pass.cpp
new file mode 100644
index 0000000000000..c0412d4d39ee1
--- /dev/null
+++ b/libcxx/test/std/utilities/text_encoding/text_encoding.members/environment.pass.cpp
@@ -0,0 +1,83 @@
+//===----------------------------------------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+// <text_encoding>
+
+// REQUIRES: std-at-least-c++26
+// REQUIRES: locale.en_US.UTF-8
+
+// UNSUPPORTED: no-localization
+// UNSUPPORTED: windows
+
+// libc++ is not built with C++26, and the implementation for this function is in a source file.
+// XFAIL: *
+
+// class text_encoding
+
+// text_encoding text_encoding::environment();
+
+// Concerns:
+// 1. text_encoding::environment() returns the encoding for the "C" locale, which should be the default for any C++ program.
+// 2. text_encoding::environment() still returns the "C" locale encoding when the locale is set to "en_US.UTF-8".
+// 3. text_encoding::environment() is affected by changes to the "LANG" environment variable.
+
+// The current implementation of text_encoding::environment() while conformant,
+// is unfortunately affected by changes to the "LANG" environment variable.
+
+#include <cassert>
+#include <clocale>
+#include <cstdlib>
+#include <string_view>
+#include <text_encoding>
+
+#include "platform_support.h"
+#include "test_macros.h"
+#include "test_text_encoding.h"
+
+int main() {
+
+ { // 1
+ auto te = std::text_encoding::environment();
+
+ assert(te == std::text_encoding::environment());
+ assert(te.mib() == std::text_encoding::id::ASCII);
+ assert(te == std::text_encoding::id::ASCII);
+ assert(std::string_view(te.name()) == "ANSI_X3.4-1968");
+ assert(te == std::text_encoding("ANSI_X3.4-1968"));
+
+ assert(std::text_encoding::environment_is<std::text_encoding::id::ASCII>());
+ }
+
+ { // 2
+ std::setlocale(LC_ALL, "en_US.UTF-8");
+
+ auto te = std::text_encoding::environment();
+
+ assert(te == std::text_encoding::environment());
+ assert(te.mib() == std::text_encoding::id::ASCII);
+ assert(std::string_view(te.name()) == "ANSI_X3.4-1968");
+ assert(te == std::text_encoding("ANSI_X3.4-1968"));
+
+ assert(std::text_encoding::environment_is<std::text_encoding::id::ASCII>());
+ }
+
+ { // 3
+ setenv("LANG", LOCALE_en_US_UTF_8, 1);
+
+ auto te = std::text_encoding::environment();
+
+ assert(te == std::text_encoding::environment());
+ assert(te.mib() == std::text_encoding::id::UTF8);
+ assert(std::string_view(te.name()) == "UTF-8");
+ assert(te == std::text_encoding("UTF-8"));
+
+ assert(std::text_encoding::environment_is<std::text_encoding::id::UTF8>());
+ }
+
+ return 0;
+}
diff --git a/libcxx/test/std/utilities/text_encoding/text_encoding.members/literal.pass.cpp b/libcxx/test/std/utilities/text_encoding/text_encoding.members/literal.pass.cpp
new file mode 100644
index 0000000000000..200f9630de580
--- /dev/null
+++ b/libcxx/test/std/utilities/text_encoding/text_encoding.members/literal.pass.cpp
@@ -0,0 +1,49 @@
+
+//===----------------------------------------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+// <text_encoding>
+
+// REQUIRES: std-at-least-c++26
+
+// UNSUPPORTED: no-localization
+
+// class text_encoding
+
+// text_encoding text_encoding::literal() noexcept;
+
+// Concerns:
+// 1. text_encoding::literal() returns the proper encoding depending on the compiler, else unknown.
+
+#include <cassert>
+#include <text_encoding>
+#include <type_traits>
+#include <string_view>
+
+#include "test_macros.h"
+#include "test_text_encoding.h"
+
+int main() {
+#if __CHAR_BIT__ == 8
+
+ {
+ auto te = std::text_encoding::literal();
+# ifdef __GNUC_EXECUTION_CHARSET_NAME
+ assert(std::string_view(te.name()) == std::string_view(__GNUC_EXECUTION_CHARSET_NAME));
+# elif defined(__clang_literal_encoding__)
+ assert(std::string_view(te.name()) == std::string_view(__clang_literal_encoding__));
+# elif defined(__clang__)
+ assert(std::string_view(te.name()) == "UTF-8");
+ assert(te.mib() == std::text_encoding::id::UTF8);
+# else
+ assert(te.mib() = std::text_encoding::id::unknown);
+# endif
+ }
+
+#endif // if __CHAR_BIT__ == 8
+}
diff --git a/libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/begin.pass.cpp b/libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/begin.pass.cpp
new file mode 100644
index 0000000000000..61c148f854813
--- /dev/null
+++ b/libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/begin.pass.cpp
@@ -0,0 +1,66 @@
+//===----------------------------------------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+// <text_encoding>
+
+// REQUIRES: std-at-least-c++26
+
+// UNSUPPORTED: no-localization
+
+// class text_encoding
+
+// text_encoding text_encoding::environment();
+
+// Concerns:
+// 1. begin() of an aliases_view() from a single text_encoding object are the same.
+// 2. begin() of aliases_views of two text_encoding objects that represent the same ID but hold different names are the same.
+// 3. begin() of aliases_views of two text_encoding objects that represent different IDs are different.
+
+#include <cassert>
+#include <cstdlib>
+#include <text_encoding>
+#include <ranges>
+
+#include "platform_support.h"
+#include "test_macros.h"
+#include "test_text_encoding.h"
+
+using id = std::text_encoding::id;
+
+int main() {
+
+ {
+ auto te = std::text_encoding(id::UTF8);
+ auto view1 = te.aliases();
+ auto view2 = te.aliases();
+
+ assert(std::ranges::begin(view1) == std::ranges::begin(view2));
+ }
+
+ {
+ auto te1 = std::text_encoding("ANSI_X3.4-1968");
+ auto te2 = std::text_encoding("ANSI_X3.4-1986");
+
+ auto view1 = te1.aliases();
+ auto view2 = te2.aliases();
+
+ assert(std::ranges::begin(view1) == std::ranges::begin(view2));
+ }
+
+ {
+
+ auto te1 = std::text_encoding(id::UTF8);
+ auto te2 = std::text_encoding(id::ASCII);
+
+ auto view1 = te1.aliases();
+ auto view2 = te2.aliases();
+
+ assert(!(std::ranges::begin(view1) == std::ranges::begin(view2)));
+ }
+
+}
diff --git a/libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/empty.pass.cpp b/libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/empty.pass.cpp
new file mode 100644
index 0000000000000..253a060dc0961
--- /dev/null
+++ b/libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/empty.pass.cpp
@@ -0,0 +1,64 @@
+//===----------------------------------------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+// <text_encoding>
+
+// REQUIRES: std-at-least-c++26
+
+// UNSUPPORTED: no-localization
+
+// class text_encoding
+
+// text_encoding text_encoding::environment();
+
+// Concerns:
+// 1. An alias_view of a text_encoding object for "other" is empty
+// 2. An alias_view of a text_encoding object for "unknown" is empty
+// 3. An alias_view of a text_encoding object for a known encoding e.g. "UTF-8" is not empty
+
+#include <cassert>
+#include <cstdlib>
+#include <ranges>
+#include <text_encoding>
+
+#include "platform_support.h"
+#include "test_macros.h"
+#include "test_text_encoding.h"
+
+using id = std::text_encoding::id;
+
+int main(){
+
+ {
+ auto te = std::text_encoding(id::other);
+ auto empty_range = te.aliases();
+
+ assert(std::ranges::empty(empty_range));
+ assert(empty_range.empty());
+ assert(!bool(empty_range));
+ }
+
+ {
+ auto te = std::text_encoding(id::unknown);
+ auto empty_range = te.aliases();
+
+ assert(std::ranges::empty(empty_range));
+ assert(empty_range.empty());
+ assert(!bool(empty_range));
+ }
+
+ {
+ auto te = std::text_encoding(id::UTF8);
+ auto range = te.aliases();
+
+ assert(!std::ranges::empty(range));
+ assert(!range.empty());
+ assert(bool(range));
+ }
+
+}
diff --git a/libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/front.pass.cpp b/libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/front.pass.cpp
new file mode 100644
index 0000000000000..fb9f80247b1ac
--- /dev/null
+++ b/libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/front.pass.cpp
@@ -0,0 +1,66 @@
+//===----------------------------------------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+// <text_encoding>
+
+// REQUIRES: std-at-least-c++26
+
+// UNSUPPORTED: no-localization
+
+// class text_encoding
+
+// text_encoding text_encoding::environment();
+
+// Concerns:
+// 1. An aliases_view from a single text_encoding object returns the same front()
+// 2. An aliases_views of two text_encoding objects that represent the same ID but hold different names return the same front()
+// 3. An aliases_views of two text_encoding objects that represent different IDs return different front()
+
+#include <cassert>
+#include <cstdlib>
+#include <text_encoding>
+
+#include "platform_support.h"
+#include "test_macros.h"
+#include "test_text_encoding.h"
+
+using id = std::text_encoding::id;
+
+int main() {
+
+ {
+ auto te = std::text_encoding(id::UTF8);
+
+ auto view1 = te.aliases();
+ auto view2 = te.aliases();
+
+ assert(view1.front() == view2.front());
+ }
+
+ {
+ auto te1 = std::text_encoding("ANSI_X3.4-1968");
+ auto te2 = std::text_encoding("ANSI_X3.4-1986");
+
+ auto view1 = te1.aliases();
+ auto view2 = te2.aliases();
+
+ assert(view1.front() == view2.front());
+ }
+
+ {
+
+ auto te1 = std::text_encoding(id::UTF8);
+ auto te2 = std::text_encoding(id::ASCII);
+
+ auto view1 = te1.aliases();
+ auto view2 = te2.aliases();
+
+ assert(!(view1.front() == view2.front()));
+ }
+
+}
diff --git a/libcxx/test/support/test_text_encoding.h b/libcxx/test/support/test_text_encoding.h
new file mode 100644
index 0000000000000..460a259722f0d
--- /dev/null
+++ b/libcxx/test/support/test_text_encoding.h
@@ -0,0 +1,1173 @@
+//===----------------------------------------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef SUPPORT_TEST_TEXT_ENCODING_H
+#define SUPPORT_TEST_TEXT_ENCODING_H
+
+#include "test_macros.h"
+#include <cstdint>
+
+struct encoding_pair {
+ int_least32_t mib;
+ const char* name;
+};
+
+constexpr encoding_pair all_encoding_data[] = {
+ {1, ""},
+ {2, ""},
+ {3, "ANSI_X3.4-1968"},
+ {3, "ANSI_X3.4-1986"},
+ {3, "IBM367"},
+ {3, "ISO646-US"},
+ {3, "ISO_646.irv:1991"},
+ {3, "cp367"},
+ {3, "csASCII"},
+ {3, "iso-ir-6"},
+ {3, "us"},
+ {4, "ISO-8859-1"},
+ {4, "ISO_8859-1:1987"},
+ {4, "CP819"},
+ {4, "IBM819"},
+ {4, "ISO_8859-1"},
+ {4, "csISOLatin1"},
+ {4, "iso-ir-100"},
+ {4, "l1"},
+ {4, "latin1"},
+ {5, "ISO-8859-2"},
+ {5, "ISO_8859-2:1987"},
+ {5, "ISO_8859-2"},
+ {5, "csISOLatin2"},
+ {5, "iso-ir-101"},
+ {5, "l2"},
+ {5, "latin2"},
+ {6, "ISO-8859-3"},
+ {6, "ISO_8859-3:1988"},
+ {6, "ISO_8859-3"},
+ {6, "csISOLatin3"},
+ {6, "iso-ir-109"},
+ {6, "l3"},
+ {6, "latin3"},
+ {7, "ISO-8859-4"},
+ {7, "ISO_8859-4:1988"},
+ {7, "ISO_8859-4"},
+ {7, "csISOLatin4"},
+ {7, "iso-ir-110"},
+ {7, "l4"},
+ {7, "latin4"},
+ {8, "ISO-8859-5"},
+ {8, "ISO_8859-5:1988"},
+ {8, "ISO_8859-5"},
+ {8, "csISOLatinCyrillic"},
+ {8, "cyrillic"},
+ {8, "iso-ir-144"},
+ {9, "ISO-8859-6"},
+ {9, "ISO_8859-6:1987"},
+ {9, "ASMO-708"},
+ {9, "ECMA-114"},
+ {9, "ISO_8859-6"},
+ {9, "arabic"},
+ {9, "csISOLatinArabic"},
+ {9, "iso-ir-127"},
+ {10, "ISO-8859-7"},
+ {10, "ISO_8859-7:1987"},
+ {10, "ECMA-118"},
+ {10, "ELOT_928"},
+ {10, "ISO_8859-7"},
+ {10, "csISOLatinGreek"},
+ {10, "greek"},
+ {10, "greek8"},
+ {10, "iso-ir-126"},
+ {11, "ISO-8859-8"},
+ {11, "ISO_8859-8:1988"},
+ {11, "ISO_8859-8"},
+ {11, "csISOLatinHebrew"},
+ {11, "hebrew"},
+ {11, "iso-ir-138"},
+ {12, "ISO-8859-9"},
+ {12, "ISO_8859-9:1989"},
+ {12, "ISO_8859-9"},
+ {12, "csISOLatin5"},
+ {12, "iso-ir-148"},
+ {12, "l5"},
+ {12, "latin5"},
+ {13, "ISO-8859-10"},
+ {13, "ISO_8859-10:1992"},
+ {13, "csISOLatin6"},
+ {13, "iso-ir-157"},
+ {13, "l6"},
+ {13, "latin6"},
+ {14, "ISO_6937-2-add"},
+ {14, "csISOTextComm"},
+ {14, "iso-ir-142"},
+ {15, "JIS_X0201"},
+ {15, "X0201"},
+ {15, "csHalfWidthKatakana"},
+ {16, "JIS_Encoding"},
+ {16, "csJISEncoding"},
+ {17, "Shift_JIS"},
+ {17, "MS_Kanji"},
+ {17, "csShiftJIS"},
+ {18, "EUC-JP"},
+ {18, "Extended_UNIX_Code_Packed_Format_for_Japanese"},
+ {18, "csEUCPkdFmtJapanese"},
+ {19, "Extended_UNIX_Code_Fixed_Width_for_Japanese"},
+ {19, "csEUCFixWidJapanese"},
+ {20, "BS_4730"},
+ {20, "ISO646-GB"},
+ {20, "csISO4UnitedKingdom"},
+ {20, "gb"},
+ {20, "iso-ir-4"},
+ {20, "uk"},
+ {21, "SEN_850200_C"},
+ {21, "ISO646-SE2"},
+ {21, "csISO11SwedishForNames"},
+ {21, "iso-ir-11"},
+ {21, "se2"},
+ {22, "IT"},
+ {22, "ISO646-IT"},
+ {22, "csISO15Italian"},
+ {22, "iso-ir-15"},
+ {23, "ES"},
+ {23, "ISO646-ES"},
+ {23, "csISO17Spanish"},
+ {23, "iso-ir-17"},
+ {24, "DIN_66003"},
+ {24, "ISO646-DE"},
+ {24, "csISO21German"},
+ {24, "de"},
+ {24, "iso-ir-21"},
+ {25, "NS_4551-1"},
+ {25, "ISO646-NO"},
+ {25, "csISO60DanishNorwegian"},
+ {25, "csISO60Norwegian1"},
+ {25, "iso-ir-60"},
+ {25, "no"},
+ {26, "NF_Z_62-010"},
+ {26, "ISO646-FR"},
+ {26, "csISO69French"},
+ {26, "fr"},
+ {26, "iso-ir-69"},
+ {27, "ISO-10646-UTF-1"},
+ {27, "csISO10646UTF1"},
+ {28, "ISO_646.basic:1983"},
+ {28, "csISO646basic1983"},
+ {28, "ref"},
+ {29, "INVARIANT"},
+ {29, "csINVARIANT"},
+ {30, "ISO_646.irv:1983"},
+ {30, "csISO2IntlRefVersion"},
+ {30, "irv"},
+ {30, "iso-ir-2"},
+ {31, "NATS-SEFI"},
+ {31, "csNATSSEFI"},
+ {31, "iso-ir-8-1"},
+ {32, "NATS-SEFI-ADD"},
+ {32, "csNATSSEFIADD"},
+ {32, "iso-ir-8-2"},
+ {33, "NATS-DANO"},
+ {33, "csNATSDANO"},
+ {33, "iso-ir-9-1"},
+ {34, "NATS-DANO-ADD"},
+ {34, "csNATSDANOADD"},
+ {34, "iso-ir-9-2"},
+ {35, "SEN_850200_B"},
+ {35, "FI"},
+ {35, "ISO646-FI"},
+ {35, "ISO646-SE"},
+ {35, "csISO10Swedish"},
+ {35, "iso-ir-10"},
+ {35, "se"},
+ {36, "KS_C_5601-1987"},
+ {36, "KSC_5601"},
+ {36, "KS_C_5601-1989"},
+ {36, "csKSC56011987"},
+ {36, "iso-ir-149"},
+ {36, "korean"},
+ {37, "ISO-2022-KR"},
+ {37, "csISO2022KR"},
+ {38, "EUC-KR"},
+ {38, "csEUCKR"},
+ {39, "ISO-2022-JP"},
+ {39, "csISO2022JP"},
+ {40, "ISO-2022-JP-2"},
+ {40, "csISO2022JP2"},
+ {41, "JIS_C6220-1969-jp"},
+ {41, "JIS_C6220-1969"},
+ {41, "csISO13JISC6220jp"},
+ {41, "iso-ir-13"},
+ {41, "katakana"},
+ {41, "x0201-7"},
+ {42, "JIS_C6220-1969-ro"},
+ {42, "ISO646-JP"},
+ {42, "csISO14JISC6220ro"},
+ {42, "iso-ir-14"},
+ {42, "jp"},
+ {43, "PT"},
+ {43, "ISO646-PT"},
+ {43, "csISO16Portuguese"},
+ {43, "iso-ir-16"},
+ {44, "greek7-old"},
+ {44, "csISO18Greek7Old"},
+ {44, "iso-ir-18"},
+ {45, "latin-greek"},
+ {45, "csISO19LatinGreek"},
+ {45, "iso-ir-19"},
+ {46, "NF_Z_62-010_(1973)"},
+ {46, "ISO646-FR1"},
+ {46, "csISO25French"},
+ {46, "iso-ir-25"},
+ {47, "Latin-greek-1"},
+ {47, "csISO27LatinGreek1"},
+ {47, "iso-ir-27"},
+ {48, "ISO_5427"},
+ {48, "csISO5427Cyrillic"},
+ {48, "iso-ir-37"},
+ {49, "JIS_C6226-1978"},
+ {49, "csISO42JISC62261978"},
+ {49, "iso-ir-42"},
+ {50, "BS_viewdata"},
+ {50, "csISO47BSViewdata"},
+ {50, "iso-ir-47"},
+ {51, "INIS"},
+ {51, "csISO49INIS"},
+ {51, "iso-ir-49"},
+ {52, "INIS-8"},
+ {52, "csISO50INIS8"},
+ {52, "iso-ir-50"},
+ {53, "INIS-cyrillic"},
+ {53, "csISO51INISCyrillic"},
+ {53, "iso-ir-51"},
+ {54, "ISO_5427:1981"},
+ {54, "ISO5427Cyrillic1981"},
+ {54, "csISO54271981"},
+ {54, "iso-ir-54"},
+ {55, "ISO_5428:1980"},
+ {55, "csISO5428Greek"},
+ {55, "iso-ir-55"},
+ {56, "GB_1988-80"},
+ {56, "ISO646-CN"},
+ {56, "cn"},
+ {56, "csISO57GB1988"},
+ {56, "iso-ir-57"},
+ {57, "GB_2312-80"},
+ {57, "chinese"},
+ {57, "csISO58GB231280"},
+ {57, "iso-ir-58"},
+ {58, "NS_4551-2"},
+ {58, "ISO646-NO2"},
+ {58, "csISO61Norwegian2"},
+ {58, "iso-ir-61"},
+ {58, "no2"},
+ {59, "videotex-suppl"},
+ {59, "csISO70VideotexSupp1"},
+ {59, "iso-ir-70"},
+ {60, "PT2"},
+ {60, "ISO646-PT2"},
+ {60, "csISO84Portuguese2"},
+ {60, "iso-ir-84"},
+ {61, "ES2"},
+ {61, "ISO646-ES2"},
+ {61, "csISO85Spanish2"},
+ {61, "iso-ir-85"},
+ {62, "MSZ_7795.3"},
+ {62, "ISO646-HU"},
+ {62, "csISO86Hungarian"},
+ {62, "hu"},
+ {62, "iso-ir-86"},
+ {63, "JIS_C6226-1983"},
+ {63, "JIS_X0208-1983"},
+ {63, "csISO87JISX0208"},
+ {63, "iso-ir-87"},
+ {63, "x0208"},
+ {64, "greek7"},
+ {64, "csISO88Greek7"},
+ {64, "iso-ir-88"},
+ {65, "ASMO_449"},
+ {65, "ISO_9036"},
+ {65, "arabic7"},
+ {65, "csISO89ASMO449"},
+ {65, "iso-ir-89"},
+ {66, "iso-ir-90"},
+ {66, "csISO90"},
+ {67, "JIS_C6229-1984-a"},
+ {67, "csISO91JISC62291984a"},
+ {67, "iso-ir-91"},
+ {67, "jp-ocr-a"},
+ {68, "JIS_C6229-1984-b"},
+ {68, "ISO646-JP-OCR-B"},
+ {68, "csISO92JISC62991984b"},
+ {68, "iso-ir-92"},
+ {68, "jp-ocr-b"},
+ {69, "JIS_C6229-1984-b-add"},
+ {69, "csISO93JIS62291984badd"},
+ {69, "iso-ir-93"},
+ {69, "jp-ocr-b-add"},
+ {70, "JIS_C6229-1984-hand"},
+ {70, "csISO94JIS62291984hand"},
+ {70, "iso-ir-94"},
+ {70, "jp-ocr-hand"},
+ {71, "JIS_C6229-1984-hand-add"},
+ {71, "csISO95JIS62291984handadd"},
+ {71, "iso-ir-95"},
+ {71, "jp-ocr-hand-add"},
+ {72, "JIS_C6229-1984-kana"},
+ {72, "csISO96JISC62291984kana"},
+ {72, "iso-ir-96"},
+ {73, "ISO_2033-1983"},
+ {73, "csISO2033"},
+ {73, "e13b"},
+ {73, "iso-ir-98"},
+ {74, "ANSI_X3.110-1983"},
+ {74, "CSA_T500-1983"},
+ {74, "NAPLPS"},
+ {74, "csISO99NAPLPS"},
+ {74, "iso-ir-99"},
+ {75, "T.61-7bit"},
+ {75, "csISO102T617bit"},
+ {75, "iso-ir-102"},
+ {76, "T.61-8bit"},
+ {76, "T.61"},
+ {76, "csISO103T618bit"},
+ {76, "iso-ir-103"},
+ {77, "ECMA-cyrillic"},
+ {77, "KOI8-E"},
+ {77, "csISO111ECMACyrillic"},
+ {77, "iso-ir-111"},
+ {78, "CSA_Z243.4-1985-1"},
+ {78, "ISO646-CA"},
+ {78, "ca"},
+ {78, "csISO121Canadian1"},
+ {78, "csa7-1"},
+ {78, "csa71"},
+ {78, "iso-ir-121"},
+ {79, "CSA_Z243.4-1985-2"},
+ {79, "ISO646-CA2"},
+ {79, "csISO122Canadian2"},
+ {79, "csa7-2"},
+ {79, "csa72"},
+ {79, "iso-ir-122"},
+ {80, "CSA_Z243.4-1985-gr"},
+ {80, "csISO123CSAZ24341985gr"},
+ {80, "iso-ir-123"},
+ {81, "ISO-8859-6-E"},
+ {81, "ISO_8859-6-E"},
+ {81, "csISO88596E"},
+ {82, "ISO-8859-6-I"},
+ {82, "ISO_8859-6-I"},
+ {82, "csISO88596I"},
+ {83, "T.101-G2"},
+ {83, "csISO128T101G2"},
+ {83, "iso-ir-128"},
+ {84, "ISO-8859-8-E"},
+ {84, "ISO_8859-8-E"},
+ {84, "csISO88598E"},
+ {85, "ISO-8859-8-I"},
+ {85, "ISO_8859-8-I"},
+ {85, "csISO88598I"},
+ {86, "CSN_369103"},
+ {86, "csISO139CSN369103"},
+ {86, "iso-ir-139"},
+ {87, "JUS_I.B1.002"},
+ {87, "ISO646-YU"},
+ {87, "csISO141JUSIB1002"},
+ {87, "iso-ir-141"},
+ {87, "js"},
+ {87, "yu"},
+ {88, "IEC_P27-1"},
+ {88, "csISO143IECP271"},
+ {88, "iso-ir-143"},
+ {89, "JUS_I.B1.003-serb"},
+ {89, "csISO146Serbian"},
+ {89, "iso-ir-146"},
+ {89, "serbian"},
+ {90, "JUS_I.B1.003-mac"},
+ {90, "csISO147Macedonian"},
+ {90, "iso-ir-147"},
+ {90, "macedonian"},
+ {91, "greek-ccitt"},
+ {91, "csISO150"},
+ {91, "csISO150GreekCCITT"},
+ {91, "iso-ir-150"},
+ {92, "NC_NC00-10:81"},
+ {92, "ISO646-CU"},
+ {92, "csISO151Cuba"},
+ {92, "cuba"},
+ {92, "iso-ir-151"},
+ {93, "ISO_6937-2-25"},
+ {93, "csISO6937Add"},
+ {93, "iso-ir-152"},
+ {94, "GOST_19768-74"},
+ {94, "ST_SEV_358-88"},
+ {94, "csISO153GOST1976874"},
+ {94, "iso-ir-153"},
+ {95, "ISO_8859-supp"},
+ {95, "csISO8859Supp"},
+ {95, "iso-ir-154"},
+ {95, "latin1-2-5"},
+ {96, "ISO_10367-box"},
+ {96, "csISO10367Box"},
+ {96, "iso-ir-155"},
+ {97, "latin-lap"},
+ {97, "csISO158Lap"},
+ {97, "iso-ir-158"},
+ {97, "lap"},
+ {98, "JIS_X0212-1990"},
+ {98, "csISO159JISX02121990"},
+ {98, "iso-ir-159"},
+ {98, "x0212"},
+ {99, "DS_2089"},
+ {99, "DS2089"},
+ {99, "ISO646-DK"},
+ {99, "csISO646Danish"},
+ {99, "dk"},
+ {100, "us-dk"},
+ {100, "csUSDK"},
+ {101, "dk-us"},
+ {101, "csDKUS"},
+ {102, "KSC5636"},
+ {102, "ISO646-KR"},
+ {102, "csKSC5636"},
+ {103, "UNICODE-1-1-UTF-7"},
+ {103, "csUnicode11UTF7"},
+ {104, "ISO-2022-CN"},
+ {104, "csISO2022CN"},
+ {105, "ISO-2022-CN-EXT"},
+ {105, "csISO2022CNEXT"},
+ {106, "UTF-8"},
+ {106, "csUTF8"},
+ {109, "ISO-8859-13"},
+ {109, "csISO885913"},
+ {110, "ISO-8859-14"},
+ {110, "ISO_8859-14"},
+ {110, "ISO_8859-14:1998"},
+ {110, "csISO885914"},
+ {110, "iso-celtic"},
+ {110, "iso-ir-199"},
+ {110, "l8"},
+ {110, "latin8"},
+ {111, "ISO-8859-15"},
+ {111, "ISO_8859-15"},
+ {111, "Latin-9"},
+ {111, "csISO885915"},
+ {112, "ISO-8859-16"},
+ {112, "ISO_8859-16"},
+ {112, "ISO_8859-16:2001"},
+ {112, "csISO885916"},
+ {112, "iso-ir-226"},
+ {112, "l10"},
+ {112, "latin10"},
+ {113, "GBK"},
+ {113, "CP936"},
+ {113, "MS936"},
+ {113, "csGBK"},
+ {113, "windows-936"},
+ {114, "GB18030"},
+ {114, "csGB18030"},
+ {115, "OSD_EBCDIC_DF04_15"},
+ {115, "csOSDEBCDICDF0415"},
+ {116, "OSD_EBCDIC_DF03_IRV"},
+ {116, "csOSDEBCDICDF03IRV"},
+ {117, "OSD_EBCDIC_DF04_1"},
+ {117, "csOSDEBCDICDF041"},
+ {118, "ISO-11548-1"},
+ {118, "ISO_11548-1"},
+ {118, "ISO_TR_11548-1"},
+ {118, "csISO115481"},
+ {119, "KZ-1048"},
+ {119, "RK1048"},
+ {119, "STRK1048-2002"},
+ {119, "csKZ1048"},
+ {1000, "ISO-10646-UCS-2"},
+ {1000, "csUnicode"},
+ {1001, "ISO-10646-UCS-4"},
+ {1001, "csUCS4"},
+ {1002, "ISO-10646-UCS-Basic"},
+ {1002, "csUnicodeASCII"},
+ {1003, "ISO-10646-Unicode-Latin1"},
+ {1003, "ISO-10646"},
+ {1003, "csUnicodeLatin1"},
+ {1004, "ISO-10646-J-1"},
+ {1004, "csUnicodeJapanese"},
+ {1005, "ISO-Unicode-IBM-1261"},
+ {1005, "csUnicodeIBM1261"},
+ {1006, "ISO-Unicode-IBM-1268"},
+ {1006, "csUnicodeIBM1268"},
+ {1007, "ISO-Unicode-IBM-1276"},
+ {1007, "csUnicodeIBM1276"},
+ {1008, "ISO-Unicode-IBM-1264"},
+ {1008, "csUnicodeIBM1264"},
+ {1009, "ISO-Unicode-IBM-1265"},
+ {1009, "csUnicodeIBM1265"},
+ {1010, "UNICODE-1-1"},
+ {1010, "csUnicode11"},
+ {1011, "SCSU"},
+ {1011, "csSCSU"},
+ {1012, "UTF-7"},
+ {1012, "csUTF7"},
+ {1013, "UTF-16BE"},
+ {1013, "csUTF16BE"},
+ {1014, "UTF-16LE"},
+ {1014, "csUTF16LE"},
+ {1015, "UTF-16"},
+ {1015, "csUTF16"},
+ {1016, "CESU-8"},
+ {1016, "csCESU-8"},
+ {1016, "csCESU8"},
+ {1017, "UTF-32"},
+ {1017, "csUTF32"},
+ {1018, "UTF-32BE"},
+ {1018, "csUTF32BE"},
+ {1019, "UTF-32LE"},
+ {1019, "csUTF32LE"},
+ {1020, "BOCU-1"},
+ {1020, "csBOCU-1"},
+ {1020, "csBOCU1"},
+ {1021, "UTF-7-IMAP"},
+ {1021, "csUTF7IMAP"},
+ {2000, "ISO-8859-1-Windows-3.0-Latin-1"},
+ {2000, "csWindows30Latin1"},
+ {2001, "ISO-8859-1-Windows-3.1-Latin-1"},
+ {2001, "csWindows31Latin1"},
+ {2002, "ISO-8859-2-Windows-Latin-2"},
+ {2002, "csWindows31Latin2"},
+ {2003, "ISO-8859-9-Windows-Latin-5"},
+ {2003, "csWindows31Latin5"},
+ {2004, "hp-roman8"},
+ {2004, "csHPRoman8"},
+ {2004, "r8"},
+ {2004, "roman8"},
+ {2005, "Adobe-Standard-Encoding"},
+ {2005, "csAdobeStandardEncoding"},
+ {2006, "Ventura-US"},
+ {2006, "csVenturaUS"},
+ {2007, "Ventura-International"},
+ {2007, "csVenturaInternational"},
+ {2008, "DEC-MCS"},
+ {2008, "csDECMCS"},
+ {2008, "dec"},
+ {2009, "IBM850"},
+ {2009, "850"},
+ {2009, "cp850"},
+ {2009, "csPC850Multilingual"},
+ {2010, "IBM852"},
+ {2010, "852"},
+ {2010, "cp852"},
+ {2010, "csPCp852"},
+ {2011, "IBM437"},
+ {2011, "437"},
+ {2011, "cp437"},
+ {2011, "csPC8CodePage437"},
+ {2012, "PC8-Danish-Norwegian"},
+ {2012, "csPC8DanishNorwegian"},
+ {2013, "IBM862"},
+ {2013, "862"},
+ {2013, "cp862"},
+ {2013, "csPC862LatinHebrew"},
+ {2014, "PC8-Turkish"},
+ {2014, "csPC8Turkish"},
+ {2015, "IBM-Symbols"},
+ {2015, "csIBMSymbols"},
+ {2016, "IBM-Thai"},
+ {2016, "csIBMThai"},
+ {2017, "HP-Legal"},
+ {2017, "csHPLegal"},
+ {2018, "HP-Pi-font"},
+ {2018, "csHPPiFont"},
+ {2019, "HP-Math8"},
+ {2019, "csHPMath8"},
+ {2020, "Adobe-Symbol-Encoding"},
+ {2020, "csHPPSMath"},
+ {2021, "HP-DeskTop"},
+ {2021, "csHPDesktop"},
+ {2022, "Ventura-Math"},
+ {2022, "csVenturaMath"},
+ {2023, "Microsoft-Publishing"},
+ {2023, "csMicrosoftPublishing"},
+ {2024, "Windows-31J"},
+ {2024, "csWindows31J"},
+ {2025, "GB2312"},
+ {2025, "csGB2312"},
+ {2026, "Big5"},
+ {2026, "csBig5"},
+ {2027, "macintosh"},
+ {2027, "csMacintosh"},
+ {2027, "mac"},
+ {2028, "IBM037"},
+ {2028, "cp037"},
+ {2028, "csIBM037"},
+ {2028, "ebcdic-cp-ca"},
+ {2028, "ebcdic-cp-nl"},
+ {2028, "ebcdic-cp-us"},
+ {2028, "ebcdic-cp-wt"},
+ {2029, "IBM038"},
+ {2029, "EBCDIC-INT"},
+ {2029, "cp038"},
+ {2029, "csIBM038"},
+ {2030, "IBM273"},
+ {2030, "CP273"},
+ {2030, "csIBM273"},
+ {2031, "IBM274"},
+ {2031, "CP274"},
+ {2031, "EBCDIC-BE"},
+ {2031, "csIBM274"},
+ {2032, "IBM275"},
+ {2032, "EBCDIC-BR"},
+ {2032, "cp275"},
+ {2032, "csIBM275"},
+ {2033, "IBM277"},
+ {2033, "EBCDIC-CP-DK"},
+ {2033, "EBCDIC-CP-NO"},
+ {2033, "csIBM277"},
+ {2034, "IBM278"},
+ {2034, "CP278"},
+ {2034, "csIBM278"},
+ {2034, "ebcdic-cp-fi"},
+ {2034, "ebcdic-cp-se"},
+ {2035, "IBM280"},
+ {2035, "CP280"},
+ {2035, "csIBM280"},
+ {2035, "ebcdic-cp-it"},
+ {2036, "IBM281"},
+ {2036, "EBCDIC-JP-E"},
+ {2036, "cp281"},
+ {2036, "csIBM281"},
+ {2037, "IBM284"},
+ {2037, "CP284"},
+ {2037, "csIBM284"},
+ {2037, "ebcdic-cp-es"},
+ {2038, "IBM285"},
+ {2038, "CP285"},
+ {2038, "csIBM285"},
+ {2038, "ebcdic-cp-gb"},
+ {2039, "IBM290"},
+ {2039, "EBCDIC-JP-kana"},
+ {2039, "cp290"},
+ {2039, "csIBM290"},
+ {2040, "IBM297"},
+ {2040, "cp297"},
+ {2040, "csIBM297"},
+ {2040, "ebcdic-cp-fr"},
+ {2041, "IBM420"},
+ {2041, "cp420"},
+ {2041, "csIBM420"},
+ {2041, "ebcdic-cp-ar1"},
+ {2042, "IBM423"},
+ {2042, "cp423"},
+ {2042, "csIBM423"},
+ {2042, "ebcdic-cp-gr"},
+ {2043, "IBM424"},
+ {2043, "cp424"},
+ {2043, "csIBM424"},
+ {2043, "ebcdic-cp-he"},
+ {2044, "IBM500"},
+ {2044, "CP500"},
+ {2044, "csIBM500"},
+ {2044, "ebcdic-cp-be"},
+ {2044, "ebcdic-cp-ch"},
+ {2045, "IBM851"},
+ {2045, "851"},
+ {2045, "cp851"},
+ {2045, "csIBM851"},
+ {2046, "IBM855"},
+ {2046, "855"},
+ {2046, "cp855"},
+ {2046, "csIBM855"},
+ {2047, "IBM857"},
+ {2047, "857"},
+ {2047, "cp857"},
+ {2047, "csIBM857"},
+ {2048, "IBM860"},
+ {2048, "860"},
+ {2048, "cp860"},
+ {2048, "csIBM860"},
+ {2049, "IBM861"},
+ {2049, "861"},
+ {2049, "cp-is"},
+ {2049, "cp861"},
+ {2049, "csIBM861"},
+ {2050, "IBM863"},
+ {2050, "863"},
+ {2050, "cp863"},
+ {2050, "csIBM863"},
+ {2051, "IBM864"},
+ {2051, "cp864"},
+ {2051, "csIBM864"},
+ {2052, "IBM865"},
+ {2052, "865"},
+ {2052, "cp865"},
+ {2052, "csIBM865"},
+ {2053, "IBM868"},
+ {2053, "CP868"},
+ {2053, "cp-ar"},
+ {2053, "csIBM868"},
+ {2054, "IBM869"},
+ {2054, "869"},
+ {2054, "cp-gr"},
+ {2054, "cp869"},
+ {2054, "csIBM869"},
+ {2055, "IBM870"},
+ {2055, "CP870"},
+ {2055, "csIBM870"},
+ {2055, "ebcdic-cp-roece"},
+ {2055, "ebcdic-cp-yu"},
+ {2056, "IBM871"},
+ {2056, "CP871"},
+ {2056, "csIBM871"},
+ {2056, "ebcdic-cp-is"},
+ {2057, "IBM880"},
+ {2057, "EBCDIC-Cyrillic"},
+ {2057, "cp880"},
+ {2057, "csIBM880"},
+ {2058, "IBM891"},
+ {2058, "cp891"},
+ {2058, "csIBM891"},
+ {2059, "IBM903"},
+ {2059, "cp903"},
+ {2059, "csIBM903"},
+ {2060, "IBM904"},
+ {2060, "904"},
+ {2060, "cp904"},
+ {2060, "csIBBM904"},
+ {2061, "IBM905"},
+ {2061, "CP905"},
+ {2061, "csIBM905"},
+ {2061, "ebcdic-cp-tr"},
+ {2062, "IBM918"},
+ {2062, "CP918"},
+ {2062, "csIBM918"},
+ {2062, "ebcdic-cp-ar2"},
+ {2063, "IBM1026"},
+ {2063, "CP1026"},
+ {2063, "csIBM1026"},
+ {2064, "EBCDIC-AT-DE"},
+ {2064, "csIBMEBCDICATDE"},
+ {2065, "EBCDIC-AT-DE-A"},
+ {2065, "csEBCDICATDEA"},
+ {2066, "EBCDIC-CA-FR"},
+ {2066, "csEBCDICCAFR"},
+ {2067, "EBCDIC-DK-NO"},
+ {2067, "csEBCDICDKNO"},
+ {2068, "EBCDIC-DK-NO-A"},
+ {2068, "csEBCDICDKNOA"},
+ {2069, "EBCDIC-FI-SE"},
+ {2069, "csEBCDICFISE"},
+ {2070, "EBCDIC-FI-SE-A"},
+ {2070, "csEBCDICFISEA"},
+ {2071, "EBCDIC-FR"},
+ {2071, "csEBCDICFR"},
+ {2072, "EBCDIC-IT"},
+ {2072, "csEBCDICIT"},
+ {2073, "EBCDIC-PT"},
+ {2073, "csEBCDICPT"},
+ {2074, "EBCDIC-ES"},
+ {2074, "csEBCDICES"},
+ {2075, "EBCDIC-ES-A"},
+ {2075, "csEBCDICESA"},
+ {2076, "EBCDIC-ES-S"},
+ {2076, "csEBCDICESS"},
+ {2077, "EBCDIC-UK"},
+ {2077, "csEBCDICUK"},
+ {2078, "EBCDIC-US"},
+ {2078, "csEBCDICUS"},
+ {2079, "UNKNOWN-8BIT"},
+ {2079, "csUnknown8BiT"},
+ {2080, "MNEMONIC"},
+ {2080, "csMnemonic"},
+ {2081, "MNEM"},
+ {2081, "csMnem"},
+ {2082, "VISCII"},
+ {2082, "csVISCII"},
+ {2083, "VIQR"},
+ {2083, "csVIQR"},
+ {2084, "KOI8-R"},
+ {2084, "csKOI8R"},
+ {2085, "HZ-GB-2312"},
+ {2086, "IBM866"},
+ {2086, "866"},
+ {2086, "cp866"},
+ {2086, "csIBM866"},
+ {2087, "IBM775"},
+ {2087, "cp775"},
+ {2087, "csPC775Baltic"},
+ {2088, "KOI8-U"},
+ {2088, "csKOI8U"},
+ {2089, "IBM00858"},
+ {2089, "CCSID00858"},
+ {2089, "CP00858"},
+ {2089, "PC-Multilingual-850+euro"},
+ {2089, "csIBM00858"},
+ {2090, "IBM00924"},
+ {2090, "CCSID00924"},
+ {2090, "CP00924"},
+ {2090, "csIBM00924"},
+ {2090, "ebcdic-Latin9--euro"},
+ {2091, "IBM01140"},
+ {2091, "CCSID01140"},
+ {2091, "CP01140"},
+ {2091, "csIBM01140"},
+ {2091, "ebcdic-us-37+euro"},
+ {2092, "IBM01141"},
+ {2092, "CCSID01141"},
+ {2092, "CP01141"},
+ {2092, "csIBM01141"},
+ {2092, "ebcdic-de-273+euro"},
+ {2093, "IBM01142"},
+ {2093, "CCSID01142"},
+ {2093, "CP01142"},
+ {2093, "csIBM01142"},
+ {2093, "ebcdic-dk-277+euro"},
+ {2093, "ebcdic-no-277+euro"},
+ {2094, "IBM01143"},
+ {2094, "CCSID01143"},
+ {2094, "CP01143"},
+ {2094, "csIBM01143"},
+ {2094, "ebcdic-fi-278+euro"},
+ {2094, "ebcdic-se-278+euro"},
+ {2095, "IBM01144"},
+ {2095, "CCSID01144"},
+ {2095, "CP01144"},
+ {2095, "csIBM01144"},
+ {2095, "ebcdic-it-280+euro"},
+ {2096, "IBM01145"},
+ {2096, "CCSID01145"},
+ {2096, "CP01145"},
+ {2096, "csIBM01145"},
+ {2096, "ebcdic-es-284+euro"},
+ {2097, "IBM01146"},
+ {2097, "CCSID01146"},
+ {2097, "CP01146"},
+ {2097, "csIBM01146"},
+ {2097, "ebcdic-gb-285+euro"},
+ {2098, "IBM01147"},
+ {2098, "CCSID01147"},
+ {2098, "CP01147"},
+ {2098, "csIBM01147"},
+ {2098, "ebcdic-fr-297+euro"},
+ {2099, "IBM01148"},
+ {2099, "CCSID01148"},
+ {2099, "CP01148"},
+ {2099, "csIBM01148"},
+ {2099, "ebcdic-international-500+euro"},
+ {2100, "IBM01149"},
+ {2100, "CCSID01149"},
+ {2100, "CP01149"},
+ {2100, "csIBM01149"},
+ {2100, "ebcdic-is-871+euro"},
+ {2101, "Big5-HKSCS"},
+ {2101, "csBig5HKSCS"},
+ {2102, "IBM1047"},
+ {2102, "IBM-1047"},
+ {2102, "csIBM1047"},
+ {2103, "PTCP154"},
+ {2103, "CP154"},
+ {2103, "Cyrillic-Asian"},
+ {2103, "PT154"},
+ {2103, "csPTCP154"},
+ {2104, "Amiga-1251"},
+ {2104, "Ami-1251"},
+ {2104, "Ami1251"},
+ {2104, "Amiga1251"},
+ {2104, "csAmiga1251"},
+ {2105, "KOI7-switched"},
+ {2105, "csKOI7switched"},
+ {2106, "BRF"},
+ {2106, "csBRF"},
+ {2107, "TSCII"},
+ {2107, "csTSCII"},
+ {2108, "CP51932"},
+ {2108, "csCP51932"},
+ {2109, "windows-874"},
+ {2109, "cswindows874"},
+ {2250, "windows-1250"},
+ {2250, "cswindows1250"},
+ {2251, "windows-1251"},
+ {2251, "cswindows1251"},
+ {2252, "windows-1252"},
+ {2252, "cswindows1252"},
+ {2253, "windows-1253"},
+ {2253, "cswindows1253"},
+ {2254, "windows-1254"},
+ {2254, "cswindows1254"},
+ {2255, "windows-1255"},
+ {2255, "cswindows1255"},
+ {2256, "windows-1256"},
+ {2256, "cswindows1256"},
+ {2257, "windows-1257"},
+ {2257, "cswindows1257"},
+ {2258, "windows-1258"},
+ {2258, "cswindows1258"},
+ {2259, "TIS-620"},
+ {2259, "ISO-8859-11"},
+ {2259, "csTIS620"},
+ {2260, "CP50220"},
+ {2260, "csCP50220"},
+ {0, nullptr} // sentinel
+};
+
+constexpr encoding_pair unique_encoding_data[] = {
+ {3, "ANSI_X3.4-1968"},
+ {4, "ISO-8859-1"},
+ {5, "ISO-8859-2"},
+ {6, "ISO-8859-3"},
+ {7, "ISO-8859-4"},
+ {8, "ISO-8859-5"},
+ {9, "ISO-8859-6"},
+ {10, "ISO-8859-7"},
+ {11, "ISO-8859-8"},
+ {12, "ISO-8859-9"},
+ {13, "ISO-8859-10"},
+ {14, "ISO_6937-2-add"},
+ {15, "JIS_X0201"},
+ {16, "JIS_Encoding"},
+ {17, "Shift_JIS"},
+ {18, "EUC-JP"},
+ {19, "Extended_UNIX_Code_Fixed_Width_for_Japanese"},
+ {20, "BS_4730"},
+ {21, "SEN_850200_C"},
+ {22, "IT"},
+ {23, "ES"},
+ {24, "DIN_66003"},
+ {25, "NS_4551-1"},
+ {26, "NF_Z_62-010"},
+ {27, "ISO-10646-UTF-1"},
+ {28, "ISO_646.basic:1983"},
+ {29, "INVARIANT"},
+ {30, "ISO_646.irv:1983"},
+ {31, "NATS-SEFI"},
+ {32, "NATS-SEFI-ADD"},
+ {33, "NATS-DANO"},
+ {34, "NATS-DANO-ADD"},
+ {35, "SEN_850200_B"},
+ {36, "KS_C_5601-1987"},
+ {37, "ISO-2022-KR"},
+ {38, "EUC-KR"},
+ {39, "ISO-2022-JP"},
+ {40, "ISO-2022-JP-2"},
+ {41, "JIS_C6220-1969-jp"},
+ {42, "JIS_C6220-1969-ro"},
+ {43, "PT"},
+ {44, "greek7-old"},
+ {45, "latin-greek"},
+ {46, "NF_Z_62-010_(1973)"},
+ {47, "Latin-greek-1"},
+ {48, "ISO_5427"},
+ {49, "JIS_C6226-1978"},
+ {50, "BS_viewdata"},
+ {51, "INIS"},
+ {52, "INIS-8"},
+ {53, "INIS-cyrillic"},
+ {54, "ISO_5427:1981"},
+ {55, "ISO_5428:1980"},
+ {56, "GB_1988-80"},
+ {57, "GB_2312-80"},
+ {58, "NS_4551-2"},
+ {59, "videotex-suppl"},
+ {60, "PT2"},
+ {61, "ES2"},
+ {62, "MSZ_7795.3"},
+ {63, "JIS_C6226-1983"},
+ {64, "greek7"},
+ {65, "ASMO_449"},
+ {66, "iso-ir-90"},
+ {67, "JIS_C6229-1984-a"},
+ {68, "JIS_C6229-1984-b"},
+ {69, "JIS_C6229-1984-b-add"},
+ {70, "JIS_C6229-1984-hand"},
+ {71, "JIS_C6229-1984-hand-add"},
+ {72, "JIS_C6229-1984-kana"},
+ {73, "ISO_2033-1983"},
+ {74, "ANSI_X3.110-1983"},
+ {75, "T.61-7bit"},
+ {76, "T.61-8bit"},
+ {77, "ECMA-cyrillic"},
+ {78, "CSA_Z243.4-1985-1"},
+ {79, "CSA_Z243.4-1985-2"},
+ {80, "CSA_Z243.4-1985-gr"},
+ {81, "ISO-8859-6-E"},
+ {82, "ISO-8859-6-I"},
+ {83, "T.101-G2"},
+ {84, "ISO-8859-8-E"},
+ {85, "ISO-8859-8-I"},
+ {86, "CSN_369103"},
+ {87, "JUS_I.B1.002"},
+ {88, "IEC_P27-1"},
+ {89, "JUS_I.B1.003-serb"},
+ {90, "JUS_I.B1.003-mac"},
+ {91, "greek-ccitt"},
+ {92, "NC_NC00-10:81"},
+ {93, "ISO_6937-2-25"},
+ {94, "GOST_19768-74"},
+ {95, "ISO_8859-supp"},
+ {96, "ISO_10367-box"},
+ {97, "latin-lap"},
+ {98, "JIS_X0212-1990"},
+ {99, "DS_2089"},
+ {100, "us-dk"},
+ {101, "dk-us"},
+ {102, "KSC5636"},
+ {103, "UNICODE-1-1-UTF-7"},
+ {104, "ISO-2022-CN"},
+ {105, "ISO-2022-CN-EXT"},
+ {106, "UTF-8"},
+ {109, "ISO-8859-13"},
+ {110, "ISO-8859-14"},
+ {111, "ISO-8859-15"},
+ {112, "ISO-8859-16"},
+ {113, "GBK"},
+ {114, "GB18030"},
+ {115, "OSD_EBCDIC_DF04_15"},
+ {116, "OSD_EBCDIC_DF03_IRV"},
+ {117, "OSD_EBCDIC_DF04_1"},
+ {118, "ISO-11548-1"},
+ {119, "KZ-1048"},
+ {1000, "ISO-10646-UCS-2"},
+ {1001, "ISO-10646-UCS-4"},
+ {1002, "ISO-10646-UCS-Basic"},
+ {1003, "ISO-10646-Unicode-Latin1"},
+ {1004, "ISO-10646-J-1"},
+ {1005, "ISO-Unicode-IBM-1261"},
+ {1006, "ISO-Unicode-IBM-1268"},
+ {1007, "ISO-Unicode-IBM-1276"},
+ {1008, "ISO-Unicode-IBM-1264"},
+ {1009, "ISO-Unicode-IBM-1265"},
+ {1010, "UNICODE-1-1"},
+ {1011, "SCSU"},
+ {1012, "UTF-7"},
+ {1013, "UTF-16BE"},
+ {1014, "UTF-16LE"},
+ {1015, "UTF-16"},
+ {1016, "CESU-8"},
+ {1017, "UTF-32"},
+ {1018, "UTF-32BE"},
+ {1019, "UTF-32LE"},
+ {1020, "BOCU-1"},
+ {1021, "UTF-7-IMAP"},
+ {2000, "ISO-8859-1-Windows-3.0-Latin-1"},
+ {2001, "ISO-8859-1-Windows-3.1-Latin-1"},
+ {2002, "ISO-8859-2-Windows-Latin-2"},
+ {2003, "ISO-8859-9-Windows-Latin-5"},
+ {2004, "hp-roman8"},
+ {2005, "Adobe-Standard-Encoding"},
+ {2006, "Ventura-US"},
+ {2007, "Ventura-International"},
+ {2008, "DEC-MCS"},
+ {2009, "IBM850"},
+ {2010, "IBM852"},
+ {2011, "IBM437"},
+ {2012, "PC8-Danish-Norwegian"},
+ {2013, "IBM862"},
+ {2014, "PC8-Turkish"},
+ {2015, "IBM-Symbols"},
+ {2016, "IBM-Thai"},
+ {2017, "HP-Legal"},
+ {2018, "HP-Pi-font"},
+ {2019, "HP-Math8"},
+ {2020, "Adobe-Symbol-Encoding"},
+ {2021, "HP-DeskTop"},
+ {2022, "Ventura-Math"},
+ {2023, "Microsoft-Publishing"},
+ {2024, "Windows-31J"},
+ {2025, "GB2312"},
+ {2026, "Big5"},
+ {2027, "macintosh"},
+ {2028, "IBM037"},
+ {2029, "IBM038"},
+ {2030, "IBM273"},
+ {2031, "IBM274"},
+ {2032, "IBM275"},
+ {2033, "IBM277"},
+ {2034, "IBM278"},
+ {2035, "IBM280"},
+ {2036, "IBM281"},
+ {2037, "IBM284"},
+ {2038, "IBM285"},
+ {2039, "IBM290"},
+ {2040, "IBM297"},
+ {2041, "IBM420"},
+ {2042, "IBM423"},
+ {2043, "IBM424"},
+ {2044, "IBM500"},
+ {2045, "IBM851"},
+ {2046, "IBM855"},
+ {2047, "IBM857"},
+ {2048, "IBM860"},
+ {2049, "IBM861"},
+ {2050, "IBM863"},
+ {2051, "IBM864"},
+ {2052, "IBM865"},
+ {2053, "IBM868"},
+ {2054, "IBM869"},
+ {2055, "IBM870"},
+ {2056, "IBM871"},
+ {2057, "IBM880"},
+ {2058, "IBM891"},
+ {2059, "IBM903"},
+ {2060, "IBM904"},
+ {2061, "IBM905"},
+ {2062, "IBM918"},
+ {2063, "IBM1026"},
+ {2064, "EBCDIC-AT-DE"},
+ {2065, "EBCDIC-AT-DE-A"},
+ {2066, "EBCDIC-CA-FR"},
+ {2067, "EBCDIC-DK-NO"},
+ {2068, "EBCDIC-DK-NO-A"},
+ {2069, "EBCDIC-FI-SE"},
+ {2070, "EBCDIC-FI-SE-A"},
+ {2071, "EBCDIC-FR"},
+ {2072, "EBCDIC-IT"},
+ {2073, "EBCDIC-PT"},
+ {2074, "EBCDIC-ES"},
+ {2075, "EBCDIC-ES-A"},
+ {2076, "EBCDIC-ES-S"},
+ {2077, "EBCDIC-UK"},
+ {2078, "EBCDIC-US"},
+ {2079, "UNKNOWN-8BIT"},
+ {2080, "MNEMONIC"},
+ {2081, "MNEM"},
+ {2082, "VISCII"},
+ {2083, "VIQR"},
+ {2084, "KOI8-R"},
+ {2085, "HZ-GB-2312"},
+ {2086, "IBM866"},
+ {2087, "IBM775"},
+ {2088, "KOI8-U"},
+ {2089, "IBM00858"},
+ {2090, "IBM00924"},
+ {2091, "IBM01140"},
+ {2092, "IBM01141"},
+ {2093, "IBM01142"},
+ {2094, "IBM01143"},
+ {2095, "IBM01144"},
+ {2096, "IBM01145"},
+ {2097, "IBM01146"},
+ {2098, "IBM01147"},
+ {2099, "IBM01148"},
+ {2100, "IBM01149"},
+ {2101, "Big5-HKSCS"},
+ {2102, "IBM1047"},
+ {2103, "PTCP154"},
+ {2104, "Amiga-1251"},
+ {2105, "KOI7-switched"},
+ {2106, "BRF"},
+ {2107, "TSCII"},
+ {2108, "CP51932"},
+ {2109, "windows-874"},
+ {2250, "windows-1250"},
+ {2251, "windows-1251"},
+ {2252, "windows-1252"},
+ {2253, "windows-1253"},
+ {2254, "windows-1254"},
+ {2255, "windows-1255"},
+ {2256, "windows-1256"},
+ {2257, "windows-1257"},
+ {2258, "windows-1258"},
+ {2259, "TIS-620"},
+ {2260, "CP50220"},
+};
+
+#endif // SUPPORT_TEST_TEXT_ENCODING_H
diff --git a/libcxx/utils/generate_feature_test_macro_components.py b/libcxx/utils/generate_feature_test_macro_components.py
index 2b7f6fa8a48a9..fc3294c4bba76 100755
--- a/libcxx/utils/generate_feature_test_macro_components.py
+++ b/libcxx/utils/generate_feature_test_macro_components.py
@@ -1346,7 +1346,6 @@ def add_version_header(tc):
"c++26": 202306 # P1885R12 Naming Text Encodings to Demystify Them
},
"headers": ["text_encoding"],
- "unimplemented": True,
},
{
"name": "__cpp_lib_three_way_comparison",
diff --git a/libcxx/utils/libcxx/header_information.py b/libcxx/utils/libcxx/header_information.py
index a505d37b65b81..55b01f9eae44e 100644
--- a/libcxx/utils/libcxx/header_information.py
+++ b/libcxx/utils/libcxx/header_information.py
@@ -172,7 +172,6 @@ def __hash__(self) -> int:
"spanstream",
"stacktrace",
"stdfloat",
- "text_encoding",
]))
header_restrictions = {
@@ -196,6 +195,7 @@ def __hash__(self) -> int:
"streambuf": "_LIBCPP_HAS_LOCALIZATION",
"strstream": "_LIBCPP_HAS_LOCALIZATION",
"syncstream": "_LIBCPP_HAS_LOCALIZATION",
+ "text_encoding": "_LIBCPP_HAS_LOCALIZATION",
}
lit_header_restrictions = {
@@ -231,6 +231,7 @@ def __hash__(self) -> int:
"streambuf": "// UNSUPPORTED: no-localization",
"strstream": "// UNSUPPORTED: no-localization",
"syncstream": "// UNSUPPORTED: no-localization",
+ "text_encoding": "// UNSUPPORTED: no-localization",
"thread": "// UNSUPPORTED: no-threads, c++03",
"wchar.h": "// UNSUPPORTED: no-wide-characters",
"wctype.h": "// UNSUPPORTED: no-wide-characters",
>From 46758a78a3d4293911a90b5468c61258490ad4bf Mon Sep 17 00:00:00 2001
From: William Tran-Viet <wtranviet at proton.me>
Date: Fri, 23 May 2025 22:58:03 -0400
Subject: [PATCH 2/3] Clang-Format
---
libcxx/include/__locale | 4 +-
.../include/__text_encoding/text_encoding.h | 47 +++++++++----------
libcxx/include/text_encoding | 10 ++--
libcxx/src/locale.cpp | 22 ++++-----
libcxx/src/text_encoding.cpp | 36 +++++++-------
.../text_encoding.ctor/id.pass.cpp | 6 +--
.../text_encoding.eq/equal.id.pass.cpp | 3 +-
.../text_encoding.eq/equal.pass.cpp | 5 +-
.../text_encoding.members/aliases.pass.cpp | 8 ++--
.../environment.pass.cpp | 17 ++++---
.../text_encoding.members/literal.pass.cpp | 2 +-
.../text_encoding.aliases_view/begin.pass.cpp | 19 ++++----
.../text_encoding.aliases_view/empty.pass.cpp | 16 +++----
.../text_encoding.aliases_view/front.pass.cpp | 17 +++----
14 files changed, 100 insertions(+), 112 deletions(-)
diff --git a/libcxx/include/__locale b/libcxx/include/__locale
index 4da3f38ac408f..6f6091d08026f 100644
--- a/libcxx/include/__locale
+++ b/libcxx/include/__locale
@@ -103,9 +103,9 @@ public:
// locale operations:
string name() const;
-
+
# if _LIBCPP_STD_VER >= 26 && __CHAR_BIT__ == 8
- text_encoding encoding() const;
+ text_encoding encoding() const;
# endif // _LIBCPP_STD_VER >= 26
bool operator==(const locale&) const;
diff --git a/libcxx/include/__text_encoding/text_encoding.h b/libcxx/include/__text_encoding/text_encoding.h
index 93d0ae2ab6b89..5edc631f7acfd 100644
--- a/libcxx/include/__text_encoding/text_encoding.h
+++ b/libcxx/include/__text_encoding/text_encoding.h
@@ -18,22 +18,22 @@
#if _LIBCPP_HAS_LOCALIZATION
-#include <__algorithm/copy_n.h>
-#include <__algorithm/lower_bound.h>
-#include <__algorithm/min.h>
-#include <__functional/hash.h>
-#include <__iterator/iterator_traits.h>
-#include <__locale_dir/locale_base_api.h>
-#include <__ranges/view_interface.h>
-#include <__string/char_traits.h>
-#include <__utility/unreachable.h>
-#include <cstdint>
-#include <string_view>
+# include <__algorithm/copy_n.h>
+# include <__algorithm/lower_bound.h>
+# include <__algorithm/min.h>
+# include <__functional/hash.h>
+# include <__iterator/iterator_traits.h>
+# include <__locale_dir/locale_base_api.h>
+# include <__ranges/view_interface.h>
+# include <__string/char_traits.h>
+# include <__utility/unreachable.h>
+# include <cstdint>
+# include <string_view>
_LIBCPP_PUSH_MACROS
-#include <__undef_macros>
+# include <__undef_macros>
-#if _LIBCPP_STD_VER >= 26
+# if _LIBCPP_STD_VER >= 26
_LIBCPP_BEGIN_NAMESPACE_STD
struct _LIBCPP_EXPORTED_FROM_ABI text_encoding {
@@ -340,12 +340,12 @@ struct _LIBCPP_EXPORTED_FROM_ABI text_encoding {
constexpr aliases_view(const __encoding_data* __d) : __view_data_(__d) {}
struct __end_sentinel {};
struct __iterator {
- using value_type = const char*;
- using reference = const char*;
- using difference_type = ptrdiff_t;
+ using value_type = const char*;
+ using reference = const char*;
+ using difference_type = ptrdiff_t;
+
+ _LIBCPP_HIDE_FROM_ABI constexpr __iterator() noexcept = default;
- _LIBCPP_HIDE_FROM_ABI constexpr __iterator() noexcept = default;
-
_LIBCPP_HIDE_FROM_ABI constexpr value_type operator*() const {
if (__can_dereference())
return __data_->__name;
@@ -368,19 +368,18 @@ struct _LIBCPP_EXPORTED_FROM_ABI text_encoding {
}
_LIBCPP_HIDE_FROM_ABI friend constexpr __iterator operator-(__iterator __it, difference_type __n) {
- __it -= __n;
+ __it -= __n;
return __it;
}
- _LIBCPP_HIDE_FROM_ABI constexpr difference_type operator-(const __iterator& __other) const
- {
- if(__other.__mib_rep_ == __mib_rep_)
+ _LIBCPP_HIDE_FROM_ABI constexpr difference_type operator-(const __iterator& __other) const {
+ if (__other.__mib_rep_ == __mib_rep_)
return __mib_rep_ - __other.__mib_rep_;
std::unreachable();
}
_LIBCPP_HIDE_FROM_ABI friend constexpr __iterator operator-(difference_type __n, __iterator& __it) {
- __it -= __n;
+ __it -= __n;
return __it;
}
@@ -1474,7 +1473,7 @@ inline constexpr bool enable_borrowed_range<text_encoding::aliases_view> = true;
_LIBCPP_END_NAMESPACE_STD
-#endif // _LIBCPP_STD_VER >= 26
+# endif // _LIBCPP_STD_VER >= 26
_LIBCPP_POP_MACROS
diff --git a/libcxx/include/text_encoding b/libcxx/include/text_encoding
index 579608e4f939d..b312e5ac1b9fb 100644
--- a/libcxx/include/text_encoding
+++ b/libcxx/include/text_encoding
@@ -10,7 +10,7 @@
#ifndef _LIBCPP_TEXT_ENCODING
#define _LIBCPP_TEXT_ENCODING
-/* text_encoding synopsis
+/* text_encoding synopsis
namespace std {
struct text_encoding;
@@ -19,7 +19,7 @@ struct text_encoding;
template<class T> struct hash;
template<> struct hash<text_encoding>;
-struct text_encoding
+struct text_encoding
{
static constexpr size_t max_name_length = 63;
@@ -60,9 +60,9 @@ struct text_encoding
#include <__config>
#if _LIBCPP_STD_VER >= 26
-# include <__text_encoding/text_encoding.h>
+# include <__text_encoding/text_encoding.h>
#endif // _LIBCPP_STD_VER >= 26
-#include <version>
+#include <version>
-#endif // _LIBCPP_TEXT_ENCODING
+#endif // _LIBCPP_TEXT_ENCODING
diff --git a/libcxx/src/locale.cpp b/libcxx/src/locale.cpp
index 6d8dababb84ce..21c93e0939910 100644
--- a/libcxx/src/locale.cpp
+++ b/libcxx/src/locale.cpp
@@ -558,18 +558,18 @@ locale::locale(const locale& other, const locale& one, category c)
string locale::name() const { return __locale_->name(); }
-# if _LIBCPP_STD_VER >= 26 && __CHAR_BIT__ == 8
- text_encoding locale::encoding() const {
- std::string __name = this->name();
- if(__name.size() == 1){
- if(__name[0] == 'C')
- return std::text_encoding(text_encoding::id::ASCII);
- if(__name[0] == '*')
- return std::text_encoding();
- }
- return std::text_encoding(__name);
+#if _LIBCPP_STD_VER >= 26 && __CHAR_BIT__ == 8
+text_encoding locale::encoding() const {
+ std::string __name = this->name();
+ if (__name.size() == 1) {
+ if (__name[0] == 'C')
+ return std::text_encoding(text_encoding::id::ASCII);
+ if (__name[0] == '*')
+ return std::text_encoding();
}
-# endif // _LIBCPP_STD_VER >= 26
+ return std::text_encoding(__name);
+}
+#endif // _LIBCPP_STD_VER >= 26
void locale::__install_ctor(const locale& other, facet* f, long facet_id) {
if (f)
diff --git a/libcxx/src/text_encoding.cpp b/libcxx/src/text_encoding.cpp
index 42812aaed49c7..95b0020ba7690 100644
--- a/libcxx/src/text_encoding.cpp
+++ b/libcxx/src/text_encoding.cpp
@@ -6,7 +6,7 @@
//
//===----------------------------------------------------------------------===//
-#include <__config>
+#include <__config>
#if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
# pragma GCC system_header
@@ -14,35 +14,35 @@
#include <__locale_dir/locale_base_api.h>
-#include <text_encoding>
+#include <text_encoding>
#if __has_include(<langinfo.h>)
# include <langinfo.h>
#endif
-#if _LIBCPP_STD_VER >= 26
+#if _LIBCPP_STD_VER >= 26
_LIBCPP_BEGIN_NAMESPACE_STD
-#if __CHAR_BIT__ == 8
+# if __CHAR_BIT__ == 8
text_encoding text_encoding::environment() {
- auto __make_locale = [](const char* __name) {
- text_encoding __enc{};
- if (auto __loc = __locale::__newlocale(LC_CTYPE_MASK, __name, static_cast<locale_t>(0))) {
- if (const char* __codeset = nl_langinfo_l(CODESET, __loc)) {
- string_view __s(__codeset);
- if (__s.size() < max_name_length)
- __enc = text_encoding(__s);
- }
- __locale::__freelocale(__loc);
+ auto __make_locale = [](const char* __name) {
+ text_encoding __enc{};
+ if (auto __loc = __locale::__newlocale(LC_CTYPE_MASK, __name, static_cast<locale_t>(0))) {
+ if (const char* __codeset = nl_langinfo_l(CODESET, __loc)) {
+ string_view __s(__codeset);
+ if (__s.size() < max_name_length)
+ __enc = text_encoding(__s);
}
- return __enc;
- };
+ __locale::__freelocale(__loc);
+ }
+ return __enc;
+ };
- return __make_locale("");
- }
+ return __make_locale("");
+}
-# endif // __CHAR_BIT__ == 8
+# endif // __CHAR_BIT__ == 8
_LIBCPP_END_NAMESPACE_STD
diff --git a/libcxx/test/std/utilities/text_encoding/text_encoding.ctor/id.pass.cpp b/libcxx/test/std/utilities/text_encoding/text_encoding.ctor/id.pass.cpp
index 6562971c73dbb..f01c3956e4736 100644
--- a/libcxx/test/std/utilities/text_encoding/text_encoding.ctor/id.pass.cpp
+++ b/libcxx/test/std/utilities/text_encoding/text_encoding.ctor/id.pass.cpp
@@ -41,15 +41,15 @@ int main() {
static_assert(std::is_nothrow_constructible<std::text_encoding, std::text_encoding::id>::value,
"Must be nothrow constructible with id");
}
-
+
{
- for (auto pair : unique_encoding_data){
+ for (auto pair : unique_encoding_data) {
test_ctor(te_id{pair.mib}, te_id{pair.mib}, pair.name);
}
}
{
- for(int i = 2261; i < 2300; i++){ // test out of range id values
+ for (int i = 2261; i < 2300; i++) { // test out of range id values
test_ctor(te_id{i}, te_id::unknown, "");
}
}
diff --git a/libcxx/test/std/utilities/text_encoding/text_encoding.eq/equal.id.pass.cpp b/libcxx/test/std/utilities/text_encoding/text_encoding.eq/equal.id.pass.cpp
index 30ce1badec1d7..bf0c75a3ebbb5 100644
--- a/libcxx/test/std/utilities/text_encoding/text_encoding.eq/equal.id.pass.cpp
+++ b/libcxx/test/std/utilities/text_encoding/text_encoding.eq/equal.id.pass.cpp
@@ -14,7 +14,7 @@
// class text_encoding
-// text_encoding operator==(const text_encoding&, id) _NOEXCEPT
+// text_encoding operator==(const text_encoding&, id) _NOEXCEPT
// Concerns:
// 1. operator==(const text_encoding&, id) must be noexcept
@@ -31,7 +31,6 @@
using id = std::text_encoding::id;
int main() {
-
{ // 1
auto te = std::text_encoding();
ASSERT_NOEXCEPT(te == id::UTF8);
diff --git a/libcxx/test/std/utilities/text_encoding/text_encoding.eq/equal.pass.cpp b/libcxx/test/std/utilities/text_encoding/text_encoding.eq/equal.pass.cpp
index 81fdb0a681143..27cd9bdff08a5 100644
--- a/libcxx/test/std/utilities/text_encoding/text_encoding.eq/equal.pass.cpp
+++ b/libcxx/test/std/utilities/text_encoding/text_encoding.eq/equal.pass.cpp
@@ -14,7 +14,7 @@
// class text_encoding
-// text_encoding operator==(const text_encoding&, const text_encoding&) _NOEXCEPT
+// text_encoding operator==(const text_encoding&, const text_encoding&) _NOEXCEPT
// Concerns:
// 1. operator==(const text_encoding&, const text_encoding&) must be noexcept
@@ -32,8 +32,7 @@
using id = std::text_encoding::id;
-int main(){
-
+int main() {
{ // 1
auto te1 = std::text_encoding();
auto te2 = std::text_encoding();
diff --git a/libcxx/test/std/utilities/text_encoding/text_encoding.members/aliases.pass.cpp b/libcxx/test/std/utilities/text_encoding/text_encoding.members/aliases.pass.cpp
index 345438d6a1ecb..6b363ef7555e6 100644
--- a/libcxx/test/std/utilities/text_encoding/text_encoding.members/aliases.pass.cpp
+++ b/libcxx/test/std/utilities/text_encoding/text_encoding.members/aliases.pass.cpp
@@ -13,10 +13,10 @@
// class text_encoding
-// text_encoding text_encoding::environment();
+// text_encoding text_encoding::environment();
// Concerns:
-// 1. Verify that text_encoding::aliases_view satisfies ranges::forward_range, copyable, view,
+// 1. Verify that text_encoding::aliases_view satisfies ranges::forward_range, copyable, view,
// ranges::random_access_range and ranges::borrowed_range
#include <concepts>
@@ -24,11 +24,11 @@
#include <text_encoding>
#include <type_traits>
-#include "platform_support.h"
+#include "platform_support.h"
#include "test_macros.h"
#include "test_text_encoding.h"
-int main(){
+int main() {
static_assert(std::ranges::forward_range<std::text_encoding::aliases_view>);
static_assert(std::copyable<std::text_encoding::aliases_view>);
static_assert(std::ranges::view<std::text_encoding::aliases_view>);
diff --git a/libcxx/test/std/utilities/text_encoding/text_encoding.members/environment.pass.cpp b/libcxx/test/std/utilities/text_encoding/text_encoding.members/environment.pass.cpp
index c0412d4d39ee1..cba72e45f0666 100644
--- a/libcxx/test/std/utilities/text_encoding/text_encoding.members/environment.pass.cpp
+++ b/libcxx/test/std/utilities/text_encoding/text_encoding.members/environment.pass.cpp
@@ -15,18 +15,18 @@
// UNSUPPORTED: windows
// libc++ is not built with C++26, and the implementation for this function is in a source file.
-// XFAIL: *
+// XFAIL: *
// class text_encoding
-// text_encoding text_encoding::environment();
+// text_encoding text_encoding::environment();
// Concerns:
// 1. text_encoding::environment() returns the encoding for the "C" locale, which should be the default for any C++ program.
// 2. text_encoding::environment() still returns the "C" locale encoding when the locale is set to "en_US.UTF-8".
-// 3. text_encoding::environment() is affected by changes to the "LANG" environment variable.
+// 3. text_encoding::environment() is affected by changes to the "LANG" environment variable.
-// The current implementation of text_encoding::environment() while conformant,
+// The current implementation of text_encoding::environment() while conformant,
// is unfortunately affected by changes to the "LANG" environment variable.
#include <cassert>
@@ -35,14 +35,13 @@
#include <string_view>
#include <text_encoding>
-#include "platform_support.h"
+#include "platform_support.h"
#include "test_macros.h"
#include "test_text_encoding.h"
int main() {
-
{ // 1
- auto te = std::text_encoding::environment();
+ auto te = std::text_encoding::environment();
assert(te == std::text_encoding::environment());
assert(te.mib() == std::text_encoding::id::ASCII);
@@ -68,7 +67,7 @@ int main() {
{ // 3
setenv("LANG", LOCALE_en_US_UTF_8, 1);
-
+
auto te = std::text_encoding::environment();
assert(te == std::text_encoding::environment());
@@ -78,6 +77,6 @@ int main() {
assert(std::text_encoding::environment_is<std::text_encoding::id::UTF8>());
}
-
+
return 0;
}
diff --git a/libcxx/test/std/utilities/text_encoding/text_encoding.members/literal.pass.cpp b/libcxx/test/std/utilities/text_encoding/text_encoding.members/literal.pass.cpp
index 200f9630de580..4aa6d793000b3 100644
--- a/libcxx/test/std/utilities/text_encoding/text_encoding.members/literal.pass.cpp
+++ b/libcxx/test/std/utilities/text_encoding/text_encoding.members/literal.pass.cpp
@@ -30,7 +30,7 @@
int main() {
#if __CHAR_BIT__ == 8
-
+
{
auto te = std::text_encoding::literal();
# ifdef __GNUC_EXECUTION_CHARSET_NAME
diff --git a/libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/begin.pass.cpp b/libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/begin.pass.cpp
index 61c148f854813..ecb98403fc821 100644
--- a/libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/begin.pass.cpp
+++ b/libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/begin.pass.cpp
@@ -14,53 +14,50 @@
// class text_encoding
-// text_encoding text_encoding::environment();
+// text_encoding text_encoding::environment();
// Concerns:
// 1. begin() of an aliases_view() from a single text_encoding object are the same.
// 2. begin() of aliases_views of two text_encoding objects that represent the same ID but hold different names are the same.
-// 3. begin() of aliases_views of two text_encoding objects that represent different IDs are different.
+// 3. begin() of aliases_views of two text_encoding objects that represent different IDs are different.
#include <cassert>
#include <cstdlib>
#include <text_encoding>
#include <ranges>
-#include "platform_support.h"
+#include "platform_support.h"
#include "test_macros.h"
#include "test_text_encoding.h"
using id = std::text_encoding::id;
int main() {
-
{
- auto te = std::text_encoding(id::UTF8);
+ auto te = std::text_encoding(id::UTF8);
auto view1 = te.aliases();
auto view2 = te.aliases();
-
- assert(std::ranges::begin(view1) == std::ranges::begin(view2));
+
+ assert(std::ranges::begin(view1) == std::ranges::begin(view2));
}
{
auto te1 = std::text_encoding("ANSI_X3.4-1968");
auto te2 = std::text_encoding("ANSI_X3.4-1986");
- auto view1 = te1.aliases();
+ auto view1 = te1.aliases();
auto view2 = te2.aliases();
assert(std::ranges::begin(view1) == std::ranges::begin(view2));
}
{
-
auto te1 = std::text_encoding(id::UTF8);
auto te2 = std::text_encoding(id::ASCII);
-
+
auto view1 = te1.aliases();
auto view2 = te2.aliases();
assert(!(std::ranges::begin(view1) == std::ranges::begin(view2)));
}
-
}
diff --git a/libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/empty.pass.cpp b/libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/empty.pass.cpp
index 253a060dc0961..6105655351675 100644
--- a/libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/empty.pass.cpp
+++ b/libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/empty.pass.cpp
@@ -14,7 +14,7 @@
// class text_encoding
-// text_encoding text_encoding::environment();
+// text_encoding text_encoding::environment();
// Concerns:
// 1. An alias_view of a text_encoding object for "other" is empty
@@ -26,25 +26,24 @@
#include <ranges>
#include <text_encoding>
-#include "platform_support.h"
+#include "platform_support.h"
#include "test_macros.h"
#include "test_text_encoding.h"
using id = std::text_encoding::id;
-int main(){
-
+int main() {
{
- auto te = std::text_encoding(id::other);
+ auto te = std::text_encoding(id::other);
auto empty_range = te.aliases();
-
+
assert(std::ranges::empty(empty_range));
assert(empty_range.empty());
assert(!bool(empty_range));
}
{
- auto te = std::text_encoding(id::unknown);
+ auto te = std::text_encoding(id::unknown);
auto empty_range = te.aliases();
assert(std::ranges::empty(empty_range));
@@ -53,12 +52,11 @@ int main(){
}
{
- auto te = std::text_encoding(id::UTF8);
+ auto te = std::text_encoding(id::UTF8);
auto range = te.aliases();
assert(!std::ranges::empty(range));
assert(!range.empty());
assert(bool(range));
}
-
}
diff --git a/libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/front.pass.cpp b/libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/front.pass.cpp
index fb9f80247b1ac..9066e1e9f8da9 100644
--- a/libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/front.pass.cpp
+++ b/libcxx/test/std/utilities/text_encoding/text_encoding.members/text_encoding.aliases_view/front.pass.cpp
@@ -14,31 +14,30 @@
// class text_encoding
-// text_encoding text_encoding::environment();
+// text_encoding text_encoding::environment();
// Concerns:
// 1. An aliases_view from a single text_encoding object returns the same front()
// 2. An aliases_views of two text_encoding objects that represent the same ID but hold different names return the same front()
-// 3. An aliases_views of two text_encoding objects that represent different IDs return different front()
+// 3. An aliases_views of two text_encoding objects that represent different IDs return different front()
#include <cassert>
#include <cstdlib>
#include <text_encoding>
-#include "platform_support.h"
+#include "platform_support.h"
#include "test_macros.h"
#include "test_text_encoding.h"
using id = std::text_encoding::id;
int main() {
-
{
auto te = std::text_encoding(id::UTF8);
-
+
auto view1 = te.aliases();
auto view2 = te.aliases();
-
+
assert(view1.front() == view2.front());
}
@@ -46,21 +45,19 @@ int main() {
auto te1 = std::text_encoding("ANSI_X3.4-1968");
auto te2 = std::text_encoding("ANSI_X3.4-1986");
- auto view1 = te1.aliases();
+ auto view1 = te1.aliases();
auto view2 = te2.aliases();
assert(view1.front() == view2.front());
}
{
-
auto te1 = std::text_encoding(id::UTF8);
auto te2 = std::text_encoding(id::ASCII);
-
+
auto view1 = te1.aliases();
auto view2 = te2.aliases();
assert(!(view1.front() == view2.front()));
}
-
}
>From 38c97df18df0be1fc7859f7cef79ada14b4c928e Mon Sep 17 00:00:00 2001
From: William Tran-Viet <wtranviet at proton.me>
Date: Fri, 23 May 2025 23:20:55 -0400
Subject: [PATCH 3/3] Fix most causes of failing CI
---
libcxx/include/text_encoding | 12 +++++++-----
libcxx/test/libcxx/transitive_includes/cxx26.csv | 1 -
2 files changed, 7 insertions(+), 6 deletions(-)
diff --git a/libcxx/include/text_encoding b/libcxx/include/text_encoding
index b312e5ac1b9fb..b41913a57bd72 100644
--- a/libcxx/include/text_encoding
+++ b/libcxx/include/text_encoding
@@ -23,7 +23,7 @@ struct text_encoding
{
static constexpr size_t max_name_length = 63;
- // [text.encoding.id], enumeration text_encoding::id
+ // [text.encoding.id], enumeration text_encoding::id
enum class id : int_least32_t {
see below
};
@@ -36,8 +36,8 @@ struct text_encoding
constexpr id mib() const noexcept;
constexpr const char* name() const noexcept;
- // [text.encoding.aliases], class text_encoding::aliases_view
- struct aliases_view;
+ // [text.encoding.aliases], class text_encoding::aliases_view
+ // struct aliases_view;
constexpr aliases_view aliases() const noexcept;
friend constexpr bool operator==(const text_encoding& a,
@@ -59,10 +59,12 @@ struct text_encoding
#include <__config>
+#if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
+# pragma GCC system_header
+#endif
+
#if _LIBCPP_STD_VER >= 26
# include <__text_encoding/text_encoding.h>
#endif // _LIBCPP_STD_VER >= 26
-#include <version>
-
#endif // _LIBCPP_TEXT_ENCODING
diff --git a/libcxx/test/libcxx/transitive_includes/cxx26.csv b/libcxx/test/libcxx/transitive_includes/cxx26.csv
index 24e57ab696857..a795b872a6646 100644
--- a/libcxx/test/libcxx/transitive_includes/cxx26.csv
+++ b/libcxx/test/libcxx/transitive_includes/cxx26.csv
@@ -1066,7 +1066,6 @@ system_error string_view
system_error tuple
system_error version
text_encoding cctype
-text_encoding clocale
text_encoding compare
text_encoding cstdint
text_encoding cstdio
More information about the libcxx-commits
mailing list