[libcxx-commits] [libcxx] [llvm] [libc++] Implement P1885R12: `<text_encoding>` (PR #141312)
Louis Dionne via libcxx-commits
libcxx-commits at lists.llvm.org
Wed Apr 8 14:04:33 PDT 2026
================
@@ -0,0 +1,1691 @@
+// -*- 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
+};
+}
+
+*/
+
+#if __cplusplus < 201103L && defined(_LIBCPP_USE_FROZEN_CXX03_HEADERS)
+# include <__cxx03/__config>
+#else
+# include <__config>
+
+# if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
+# pragma GCC system_header
+# endif
+
+# if _LIBCPP_STD_VER >= 26
+
+# include <__algorithm/find_if.h>
+# include <__algorithm/lower_bound.h>
+# include <__cstddef/ptrdiff_t.h>
+# include <__functional/hash.h>
+# include <__iterator/iterator_traits.h>
+# include <__ranges/enable_borrowed_range.h>
+# include <__ranges/view_interface.h>
+# include <cstdint>
+# include <string_view>
+# include <version>
+
+_LIBCPP_BEGIN_NAMESPACE_STD
+struct text_encoding;
+
+_LIBCPP_AVAILABILITY_TE_ENVIRONMENT _LIBCPP_EXPORTED_FROM_ABI text_encoding __get_locale_encoding(const char* __name);
+
+struct text_encoding {
+ enum class id : int_least32_t {
+ 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, // NATS-DANO (33) and NATS-DANO-ADD (34) are omitted by the standard.
+ 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,
+ IBM904 = 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
+ };
+
+private:
+ static constexpr int __NATS_DANO_ = 33;
+ static constexpr int __NATS_DANO_ADD_ = 34;
+
+ // A __te_data structure stores:
+ // Index into a table of offsets in the giant aliases string
+ // The MIB of that text encoding
+ // Number of aliases the current MIB holds
+ struct __te_data {
+ unsigned short __first_alias_index_;
+ unsigned short __mib_rep_;
+ unsigned char __num_aliases_;
+
+ _LIBCPP_HIDE_FROM_ABI friend constexpr bool operator<(const __te_data& __enc, id __i) noexcept {
+ return __enc.__mib_rep_ < static_cast<unsigned short>(__i);
+ }
+ };
+
+ _LIBCPP_HIDE_FROM_ABI static constexpr bool __comp_name(string_view __a, string_view __b) noexcept {
+ 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 {
+ if (__n == '0') {
+ return __in_number ? '0' : 255;
+ }
+ __in_number = __n >= '1' && __n <= '9';
+
+ if ((__n >= '1' && __n <= '9') || (__n >= 'a' && __n <= 'z')) {
+ return __n;
+ }
+ if (__n >= 'A' && __n <= 'Z') {
+ return __n + ('a' - 'A'); // tolower
+ }
+
+ return 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_ptr != __a.end() && (__a_val = __map_char(*__a_ptr, __a_in_number)) == 255)
+ __a_ptr++;
+ while (__b_ptr != __b.end() && (__b_val = __map_char(*__b_ptr, __b_in_number)) == 255)
+ __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 unsigned short __find_data_idx(string_view __a) noexcept {
+ _LIBCPP_ASSERT_ARGUMENT_WITHIN_DOMAIN(__a.size() <= max_name_length, "input string_view must have size <= 63");
+ _LIBCPP_ASSERT_ARGUMENT_WITHIN_DOMAIN(!__a.contains('\0'), "input string_view must not contain '\\0'");
+
+ auto __pred = [&__a](const __te_data& __entry) -> bool {
+ // Search aliases of text encoding for string
+ aliases_view __aliases(__entry);
+ return std::find_if(__aliases.begin(), __aliases.end(), [&__a](auto __alias) {
+ return __comp_name(__a, __alias);
+ }) != __aliases.end();
+ };
+
+ const __te_data* __found = std::find_if(__entries + 2, std::end(__entries), __pred);
+ if (__found == std::end(__entries)) {
+ return __other_idx_; // other
+ }
+
+ return __found - __entries;
+ }
+
+ _LIBCPP_HIDE_FROM_ABI static constexpr unsigned short __find_data_idx_by_id(id __i) noexcept {
+ _LIBCPP_ASSERT_ARGUMENT_WITHIN_DOMAIN(__i >= id::other, "invalid text_encoding::id passed");
+ _LIBCPP_ASSERT_ARGUMENT_WITHIN_DOMAIN(__i <= id::CP50220, "invalid text_encoding::id passed");
+ _LIBCPP_ASSERT_ARGUMENT_WITHIN_DOMAIN(int_least32_t(__i) != __NATS_DANO_, "Mib for NATS-DANO used");
+ _LIBCPP_ASSERT_ARGUMENT_WITHIN_DOMAIN(int_least32_t(__i) != __NATS_DANO_ADD_, "Mib for NATS-DANO-ADD used");
+ auto __found = std::lower_bound(std::begin(__entries), std::end(__entries), __i);
+
+ if (__found == std::end(__entries)) {
+ return __unknown_idx_; // unknown
+ }
+
+ return __found - __entries;
+ }
+
+public:
+ using enum id;
+ static constexpr size_t max_name_length = 63;
+
+ // [text.encoding.aliases], class text_encoding::aliases_view
+ struct aliases_view : ranges::view_interface<aliases_view> {
+ struct __iterator {
+ using iterator_concept = random_access_iterator_tag;
+ using iterator_category = random_access_iterator_tag;
+ using value_type = const char*;
+ using reference = const char*;
+ using difference_type = decltype(static_cast<unsigned short>(1) - static_cast<unsigned short>(1));
+
+ constexpr __iterator() noexcept = default;
+
+ _LIBCPP_HIDE_FROM_ABI constexpr reference operator*() const noexcept {
+ return __get_alias_from_idx_table_idx(__current_idx_);
+ }
+
+ _LIBCPP_HIDE_FROM_ABI constexpr reference operator[](difference_type __n) const noexcept {
+ auto __it = *this;
+ return *(__it + __n);
+ }
+
+ _LIBCPP_HIDE_FROM_ABI constexpr decltype(auto) operator->() = delete;
+
+ _LIBCPP_HIDE_FROM_ABI friend constexpr __iterator operator+(__iterator __it, difference_type __n) noexcept {
+ __it += __n;
+ return __it;
+ }
+
+ _LIBCPP_HIDE_FROM_ABI friend constexpr __iterator operator+(difference_type __n, __iterator __it) noexcept {
+ __it += __n;
+ return __it;
+ }
+
+ _LIBCPP_HIDE_FROM_ABI friend constexpr __iterator operator-(__iterator __it, difference_type __n) noexcept {
+ __it -= __n;
+ return __it;
+ }
+
+ _LIBCPP_HIDE_FROM_ABI constexpr difference_type operator-(const __iterator& __other) const noexcept {
+ return __current_idx_ - __other.__current_idx_;
+ }
+
+ _LIBCPP_HIDE_FROM_ABI constexpr __iterator& operator++() noexcept {
+ __current_idx_++;
+ return *this;
+ }
+
+ _LIBCPP_HIDE_FROM_ABI constexpr __iterator operator++(int) noexcept {
+ auto __old = *this;
+ __current_idx_++;
+ return __old;
+ }
+
+ _LIBCPP_HIDE_FROM_ABI constexpr __iterator& operator--() noexcept {
+ __current_idx_--;
+ return *this;
+ }
+
+ _LIBCPP_HIDE_FROM_ABI constexpr __iterator operator--(int) noexcept {
+ auto __old = *this;
+ __current_idx_--;
+ return __old;
+ }
+
+ _LIBCPP_HIDE_FROM_ABI constexpr __iterator& operator+=(difference_type __n) noexcept {
+ __current_idx_ += __n;
+ return *this;
+ }
+
+ _LIBCPP_HIDE_FROM_ABI constexpr __iterator& operator-=(difference_type __n) noexcept { return (*this += -__n); }
+
+ _LIBCPP_HIDE_FROM_ABI friend constexpr auto
+ operator<=>(const __iterator& __it, const __iterator& __it2) noexcept = default;
+
+ private:
+ friend struct aliases_view;
+
+ _LIBCPP_HIDE_FROM_ABI constexpr __iterator(unsigned short __enc_d) noexcept : __current_idx_(__enc_d) {}
+
+ unsigned short __current_idx_;
+ }; // __iterator
+
+ _LIBCPP_HIDE_FROM_ABI constexpr __iterator begin() const noexcept { return __iterator(__first_idx_); }
+
+ _LIBCPP_HIDE_FROM_ABI constexpr __iterator end() const noexcept { return __iterator(__last_idx_); }
+
+ private:
+ friend struct text_encoding;
+
+ _LIBCPP_HIDE_FROM_ABI constexpr aliases_view(const __te_data& __d)
+ : __first_idx_(__d.__first_alias_index_), __last_idx_(__d.__first_alias_index_ + __d.__num_aliases_) {}
+
+ unsigned short __first_idx_;
+ unsigned short __last_idx_;
+ }; // aliases_view
+
+ _LIBCPP_HIDE_FROM_ABI constexpr text_encoding() = default;
+
+ _LIBCPP_HIDE_FROM_ABI constexpr explicit text_encoding(string_view __enc) noexcept
+ : __encoding_idx_(__find_data_idx(__enc)) {
+ __enc.copy(__name_, max_name_length, 0);
+ }
+
+ _LIBCPP_HIDE_FROM_ABI constexpr text_encoding(id __i) noexcept : __encoding_idx_(__find_data_idx_by_id(__i)) {
+ const char* __alias = __get_alias_from_idx_table_idx(__get().__first_alias_index_);
+ if (__alias[0] != '\0') {
+ string_view(__alias).copy(__name_, max_name_length);
+ }
+ }
+
+ [[nodiscard]] _LIBCPP_HIDE_FROM_ABI constexpr id mib() const noexcept { return id(__get().__mib_rep_); }
+
+ [[nodiscard]] _LIBCPP_HIDE_FROM_ABI constexpr const char* name() const noexcept { return __name_; }
+
+ [[nodiscard]] _LIBCPP_HIDE_FROM_ABI constexpr aliases_view aliases() const noexcept { return aliases_view(__get()); }
+
+ _LIBCPP_HIDE_FROM_ABI friend constexpr bool operator==(const text_encoding& __a, const text_encoding& __b) noexcept {
+ return __a.mib() == id::other && __b.mib() == id::other
+ ? __comp_name(__a.__name_, __b.__name_)
+ : __a.mib() == __b.mib();
+ }
+
+ _LIBCPP_HIDE_FROM_ABI friend constexpr bool operator==(const text_encoding& __encoding, id __i) noexcept {
+ return __encoding.mib() == __i;
+ }
+
+ [[nodiscard]] _LIBCPP_HIDE_FROM_ABI static consteval text_encoding literal() noexcept {
+ // TODO: Remove this branch once we have __GNUC_EXECUTION_CHARSET_NAME or __clang_literal_encoding__ unconditionally
+# ifdef __GNUC_EXECUTION_CHARSET_NAME
+ return text_encoding(__GNUC_EXECUTION_CHARSET_NAME);
+# elif defined(__clang_literal_encoding__)
+ return text_encoding(__clang_literal_encoding__);
+# else
+ return text_encoding();
+# endif
+ }
+
+# if _LIBCPP_HAS_LOCALIZATION
+ [[nodiscard]] _LIBCPP_AVAILABILITY_TE_ENVIRONMENT _LIBCPP_HIDE_FROM_ABI static text_encoding environment() {
+# if defined(_LIBCPP_WIN32API)
+ return __get_locale_encoding(nullptr);
+# else
+ return __get_locale_encoding("");
+# endif
+ }
+
+ template <id _Id>
+ [[nodiscard]] _LIBCPP_AVAILABILITY_TE_ENVIRONMENT _LIBCPP_HIDE_FROM_ABI static bool environment_is() {
+ // TODO: It may be worthwhile to implement an optimization for popular encodings, e.g. UTF-8,
+ // to allow checking the environment text encoding without needing to use the data tables.
+
+# if defined(__ANDROID__)
+ return _Id == std::text_encoding::id::UTF8;
+# else
+ return environment() == _Id;
+# endif
+ }
+# else
+ static text_encoding environment() = delete;
+
+ template <id _Id>
+ static bool environment_is() = delete;
+# endif
+
+private:
+ _LIBCPP_HIDE_FROM_ABI constexpr const __te_data& __get() const { return __entries[__encoding_idx_]; }
+
+ _LIBCPP_HIDE_FROM_ABI static constexpr char const* __get_alias_from_idx_table_idx(unsigned short __idx) {
+ return __aliases_string + __alias_index_table_[__idx];
+ }
+
+ static constexpr auto __other_idx_ = 0u;
+ static constexpr auto __unknown_idx_ = 1u;
+
+ unsigned short __encoding_idx_{1u};
+ char __name_[max_name_length + 1]{};
+
+ // Structuring the text encoding data and the table in this manner has a few benefits:
+ // Smaller footprint: We only need 6 bytes for the information we need.
+ // Smaller total table: We only need one entry per Mib.
+ // Easier aliases_view: We know the begin, and end of each range of aliases, which makes iterator
+ // implementation simple.
+
+ static constexpr __te_data __entries[] = {
+ {0, 1, 0}, {1, 2, 0}, {2, 3, 11}, {13, 4, 9}, {22, 5, 7}, {29, 6, 7}, {36, 7, 7},
+ {43, 8, 6}, {49, 9, 8}, {57, 10, 9}, {66, 11, 6}, {72, 12, 7}, {79, 13, 6}, {85, 14, 3},
+ {88, 15, 3}, {91, 16, 2}, {93, 17, 3}, {96, 18, 3}, {99, 19, 2}, {101, 20, 6}, {107, 21, 5},
+ {112, 22, 4}, {116, 23, 4}, {120, 24, 5}, {125, 25, 6}, {131, 26, 5}, {136, 27, 2}, {138, 28, 3},
+ {141, 29, 2}, {143, 30, 4}, {147, 31, 3}, {150, 32, 3}, {153, 35, 7}, {160, 36, 6}, {166, 37, 2},
+ {168, 38, 2}, {170, 39, 2}, {172, 40, 2}, {174, 41, 6}, {180, 42, 5}, {185, 43, 4}, {189, 44, 3},
+ {192, 45, 3}, {195, 46, 4}, {199, 47, 3}, {202, 48, 3}, {205, 49, 3}, {208, 50, 3}, {211, 51, 3},
+ {214, 52, 3}, {217, 53, 3}, {220, 54, 4}, {224, 55, 3}, {227, 56, 5}, {232, 57, 4}, {236, 58, 5},
+ {241, 59, 3}, {244, 60, 4}, {248, 61, 4}, {252, 62, 5}, {257, 63, 5}, {262, 64, 3}, {265, 65, 5},
+ {270, 66, 2}, {272, 67, 4}, {276, 68, 5}, {281, 69, 4}, {285, 70, 4}, {289, 71, 4}, {293, 72, 3},
+ {296, 73, 4}, {300, 74, 5}, {305, 75, 3}, {308, 76, 4}, {312, 77, 4}, {316, 78, 7}, {323, 79, 6},
+ {329, 80, 3}, {332, 81, 3}, {335, 82, 3}, {338, 83, 3}, {341, 84, 3}, {344, 85, 3}, {347, 86, 3},
+ {350, 87, 6}, {356, 88, 3}, {359, 89, 4}, {363, 90, 4}, {367, 91, 4}, {371, 92, 5}, {376, 93, 3},
+ {379, 94, 4}, {383, 95, 4}, {387, 96, 3}, {390, 97, 4}, {394, 98, 4}, {398, 99, 5}, {403, 100, 2},
+ {405, 101, 2}, {407, 102, 3}, {410, 103, 2}, {412, 104, 2}, {414, 105, 2}, {416, 106, 2}, {418, 109, 2},
+ {420, 110, 8}, {428, 111, 4}, {432, 112, 7}, {439, 113, 5}, {444, 114, 2}, {446, 115, 2}, {448, 116, 2},
+ {450, 117, 2}, {452, 118, 4}, {456, 119, 4}, {460, 1000, 2}, {462, 1001, 2}, {464, 1002, 2}, {466, 1003, 3},
+ {469, 1004, 2}, {471, 1005, 2}, {473, 1006, 2}, {475, 1007, 2}, {477, 1008, 2}, {479, 1009, 2}, {481, 1010, 2},
+ {483, 1011, 2}, {485, 1012, 2}, {487, 1013, 2}, {489, 1014, 2}, {491, 1015, 2}, {493, 1016, 3}, {496, 1017, 2},
+ {498, 1018, 2}, {500, 1019, 2}, {502, 1020, 3}, {505, 1021, 2}, {507, 2000, 2}, {509, 2001, 2}, {511, 2002, 2},
+ {513, 2003, 2}, {515, 2004, 4}, {519, 2005, 2}, {521, 2006, 2}, {523, 2007, 2}, {525, 2008, 3}, {528, 2009, 4},
+ {532, 2010, 4}, {536, 2011, 4}, {540, 2012, 2}, {542, 2013, 4}, {546, 2014, 2}, {548, 2015, 2}, {550, 2016, 2},
+ {552, 2017, 2}, {554, 2018, 2}, {556, 2019, 2}, {558, 2020, 2}, {560, 2021, 2}, {562, 2022, 2}, {564, 2023, 2},
+ {566, 2024, 2}, {568, 2025, 2}, {570, 2026, 2}, {572, 2027, 3}, {575, 2028, 7}, {582, 2029, 4}, {586, 2030, 3},
+ {589, 2031, 4}, {593, 2032, 4}, {597, 2033, 4}, {601, 2034, 5}, {606, 2035, 4}, {610, 2036, 4}, {614, 2037, 4},
+ {618, 2038, 4}, {622, 2039, 4}, {626, 2040, 4}, {630, 2041, 4}, {634, 2042, 4}, {638, 2043, 4}, {642, 2044, 5},
+ {647, 2045, 4}, {651, 2046, 4}, {655, 2047, 4}, {659, 2048, 4}, {663, 2049, 5}, {668, 2050, 4}, {672, 2051, 3},
+ {675, 2052, 4}, {679, 2053, 4}, {683, 2054, 5}, {688, 2055, 5}, {693, 2056, 4}, {697, 2057, 4}, {701, 2058, 3},
+ {704, 2059, 3}, {707, 2060, 4}, {711, 2061, 4}, {715, 2062, 4}, {719, 2063, 3}, {722, 2064, 2}, {724, 2065, 2},
+ {726, 2066, 2}, {728, 2067, 2}, {730, 2068, 2}, {732, 2069, 2}, {734, 2070, 2}, {736, 2071, 2}, {738, 2072, 2},
+ {740, 2073, 2}, {742, 2074, 2}, {744, 2075, 2}, {746, 2076, 2}, {748, 2077, 2}, {750, 2078, 2}, {752, 2079, 2},
+ {754, 2080, 2}, {756, 2081, 2}, {758, 2082, 2}, {760, 2083, 2}, {762, 2084, 2}, {764, 2085, 1}, {765, 2086, 4},
+ {769, 2087, 3}, {772, 2088, 2}, {774, 2089, 5}, {779, 2090, 5}, {784, 2091, 5}, {789, 2092, 5}, {794, 2093, 6},
+ {800, 2094, 6}, {806, 2095, 5}, {811, 2096, 5}, {816, 2097, 5}, {821, 2098, 5}, {826, 2099, 5}, {831, 2100, 5},
+ {836, 2101, 2}, {838, 2102, 3}, {841, 2103, 5}, {846, 2104, 5}, {851, 2105, 2}, {853, 2106, 2}, {855, 2107, 2},
+ {857, 2108, 2}, {859, 2109, 2}, {861, 2250, 2}, {863, 2251, 2}, {865, 2252, 2}, {867, 2253, 2}, {869, 2254, 2},
+ {871, 2255, 2}, {873, 2256, 2}, {875, 2257, 2}, {877, 2258, 2}, {879, 2259, 3}, {882, 2260, 2}};
+
+ // We're saving space by storing a giant string and a table of indexes vs storing an array of const char*
+ // because we know ahead of time the offset can fit into 2 bytes.
+
+ static constexpr char __aliases_string[] =
+ "US-ASCII\0iso-ir-6\0ANSI_X3.4-1968\0ANSI_X3.4-1986\0ISO_646.irv:1991\0ISO646-"
+ "US\0us\0IBM367\0cp367\0csASCII\0ASCII\0ISO_8859-1:1987\0iso-ir-100\0ISO_8859-1\0ISO-8859-"
+ "1\0latin1\0l1\0IBM819\0CP819\0csISOLatin1\0ISO_8859-2:1987\0iso-ir-101\0ISO_8859-2\0ISO-8859-"
+ "2\0latin2\0l2\0csISOLatin2\0ISO_8859-3:1988\0iso-ir-109\0ISO_8859-3\0ISO-8859-3\0latin3\0l3\0csISOLatin3\0ISO_"
+ "8859-4:1988\0iso-ir-110\0ISO_8859-4\0ISO-8859-4\0latin4\0l4\0csISOLatin4\0ISO_8859-5:1988\0iso-ir-144\0ISO_8859-"
+ "5\0ISO-8859-5\0cyrillic\0csISOLatinCyrillic\0ISO_8859-6:1987\0iso-ir-127\0ISO_8859-6\0ISO-8859-6\0ECMA-"
+ "114\0ASMO-708\0arabic\0csISOLatinArabic\0ISO_8859-7:1987\0iso-ir-126\0ISO_8859-7\0ISO-8859-7\0ELOT_928\0ECMA-"
+ "118\0greek\0greek8\0csISOLatinGreek\0ISO_8859-8:1988\0iso-ir-138\0ISO_8859-8\0ISO-8859-"
+ "8\0hebrew\0csISOLatinHebrew\0ISO_8859-9:1989\0iso-ir-148\0ISO_8859-9\0ISO-8859-9\0latin5\0l5\0csISOLatin5\0ISO-"
+ "8859-10\0iso-ir-157\0l6\0ISO_8859-10:1992\0csISOLatin6\0latin6\0ISO_6937-2-add\0iso-ir-142\0csISOTextComm\0JIS_"
+ "X0201\0X0201\0csHalfWidthKatakana\0JIS_Encoding\0csJISEncoding\0Shift_JIS\0MS_Kanji\0csShiftJIS\0Extended_UNIX_"
+ "Code_Packed_Format_for_Japanese\0csEUCPkdFmtJapanese\0EUC-JP\0Extended_UNIX_Code_Fixed_Width_for_"
+ "Japanese\0csEUCFixWidJapanese\0BS_4730\0iso-ir-4\0ISO646-GB\0gb\0uk\0csISO4UnitedKingdom\0SEN_850200_C\0iso-ir-"
+ "11\0ISO646-SE2\0se2\0csISO11SwedishForNames\0IT\0iso-ir-15\0ISO646-IT\0csISO15Italian\0ES\0iso-ir-17\0ISO646-"
+ "ES\0csISO17Spanish\0DIN_66003\0iso-ir-21\0de\0ISO646-DE\0csISO21German\0NS_4551-1\0iso-ir-60\0ISO646-"
+ "NO\0no\0csISO60DanishNorwegian\0csISO60Norwegian1\0NF_Z_62-010\0iso-ir-69\0ISO646-FR\0fr\0csISO69French\0ISO-"
+ "10646-UTF-1\0csISO10646UTF1\0ISO_646.basic:1983\0ref\0csISO646basic1983\0INVARIANT\0csINVARIANT\0ISO_646.irv:"
+ "1983\0iso-ir-2\0irv\0csISO2IntlRefVersion\0NATS-SEFI\0iso-ir-8-1\0csNATSSEFI\0NATS-SEFI-ADD\0iso-ir-8-"
+ "2\0csNATSSEFIADD\0SEN_850200_B\0iso-ir-10\0FI\0ISO646-FI\0ISO646-SE\0se\0csISO10Swedish\0KS_C_5601-1987\0iso-ir-"
+ "149\0KS_C_5601-1989\0KSC_5601\0korean\0csKSC56011987\0ISO-2022-KR\0csISO2022KR\0EUC-KR\0csEUCKR\0ISO-2022-"
+ "JP\0csISO2022JP\0ISO-2022-JP-2\0csISO2022JP2\0JIS_C6220-1969-jp\0JIS_C6220-1969\0iso-ir-13\0katakana\0x0201-"
+ "7\0csISO13JISC6220jp\0JIS_C6220-1969-ro\0iso-ir-14\0jp\0ISO646-JP\0csISO14JISC6220ro\0PT\0iso-ir-16\0ISO646-"
+ "PT\0csISO16Portuguese\0greek7-old\0iso-ir-18\0csISO18Greek7Old\0latin-greek\0iso-ir-19\0csISO19LatinGreek\0NF_Z_"
+ "62-010_(1973)\0iso-ir-25\0ISO646-FR1\0csISO25French\0Latin-greek-1\0iso-ir-27\0csISO27LatinGreek1\0ISO_"
+ "5427\0iso-ir-37\0csISO5427Cyrillic\0JIS_C6226-1978\0iso-ir-42\0csISO42JISC62261978\0BS_viewdata\0iso-ir-"
+ "47\0csISO47BSViewdata\0INIS\0iso-ir-49\0csISO49INIS\0INIS-8\0iso-ir-50\0csISO50INIS8\0INIS-cyrillic\0iso-ir-"
+ "51\0csISO51INISCyrillic\0ISO_5427:1981\0iso-ir-54\0ISO5427Cyrillic1981\0csISO54271981\0ISO_5428:1980\0iso-ir-"
+ "55\0csISO5428Greek\0GB_1988-80\0iso-ir-57\0cn\0ISO646-CN\0csISO57GB1988\0GB_2312-80\0iso-ir-"
+ "58\0chinese\0csISO58GB231280\0NS_4551-2\0ISO646-NO2\0iso-ir-61\0no2\0csISO61Norwegian2\0videotex-suppl\0iso-ir-"
+ "70\0csISO70VideotexSupp1\0PT2\0iso-ir-84\0ISO646-PT2\0csISO84Portuguese2\0ES2\0iso-ir-85\0ISO646-"
+ "ES2\0csISO85Spanish2\0MSZ_7795.3\0iso-ir-86\0ISO646-HU\0hu\0csISO86Hungarian\0JIS_C6226-1983\0iso-ir-"
+ "87\0x0208\0JIS_X0208-1983\0csISO87JISX0208\0greek7\0iso-ir-88\0csISO88Greek7\0ASMO_449\0ISO_9036\0arabic7\0iso-"
+ "ir-89\0csISO89ASMO449\0iso-ir-90\0csISO90\0JIS_C6229-1984-a\0iso-ir-91\0jp-ocr-a\0csISO91JISC62291984a\0JIS_"
+ "C6229-1984-b\0iso-ir-92\0ISO646-JP-OCR-B\0jp-ocr-b\0csISO92JISC62991984b\0JIS_C6229-1984-b-add\0iso-ir-93\0jp-"
+ "ocr-b-add\0csISO93JIS62291984badd\0JIS_C6229-1984-hand\0iso-ir-94\0jp-ocr-hand\0csISO94JIS62291984hand\0JIS_"
+ "C6229-1984-hand-add\0iso-ir-95\0jp-ocr-hand-add\0csISO95JIS62291984handadd\0JIS_C6229-1984-kana\0iso-ir-"
+ "96\0csISO96JISC62291984kana\0ISO_2033-1983\0iso-ir-98\0e13b\0csISO2033\0ANSI_X3.110-1983\0iso-ir-99\0CSA_T500-"
+ "1983\0NAPLPS\0csISO99NAPLPS\0T.61-7bit\0iso-ir-102\0csISO102T617bit\0T.61-8bit\0T.61\0iso-ir-"
+ "103\0csISO103T618bit\0ECMA-cyrillic\0iso-ir-111\0KOI8-E\0csISO111ECMACyrillic\0CSA_Z243.4-1985-1\0iso-ir-"
+ "121\0ISO646-CA\0csa7-1\0csa71\0ca\0csISO121Canadian1\0CSA_Z243.4-1985-2\0iso-ir-122\0ISO646-CA2\0csa7-"
+ "2\0csa72\0csISO122Canadian2\0CSA_Z243.4-1985-gr\0iso-ir-123\0csISO123CSAZ24341985gr\0ISO_8859-6-"
+ "E\0csISO88596E\0ISO-8859-6-E\0ISO_8859-6-I\0csISO88596I\0ISO-8859-6-I\0T.101-G2\0iso-ir-"
+ "128\0csISO128T101G2\0ISO_8859-8-E\0csISO88598E\0ISO-8859-8-E\0ISO_8859-8-I\0csISO88598I\0ISO-8859-8-I\0CSN_"
+ "369103\0iso-ir-139\0csISO139CSN369103\0JUS_I.B1.002\0iso-ir-141\0ISO646-YU\0js\0yu\0csISO141JUSIB1002\0IEC_P27-"
+ "1\0iso-ir-143\0csISO143IECP271\0JUS_I.B1.003-serb\0iso-ir-146\0serbian\0csISO146Serbian\0JUS_I.B1.003-"
+ "mac\0macedonian\0iso-ir-147\0csISO147Macedonian\0greek-ccitt\0iso-ir-150\0csISO150\0csISO150GreekCCITT\0NC_NC00-"
+ "10:81\0cuba\0iso-ir-151\0ISO646-CU\0csISO151Cuba\0ISO_6937-2-25\0iso-ir-152\0csISO6937Add\0GOST_19768-74\0ST_"
+ "SEV_358-88\0iso-ir-153\0csISO153GOST1976874\0ISO_8859-supp\0iso-ir-154\0latin1-2-5\0csISO8859Supp\0ISO_10367-"
+ "box\0iso-ir-155\0csISO10367Box\0latin-lap\0lap\0iso-ir-158\0csISO158Lap\0JIS_X0212-1990\0x0212\0iso-ir-"
+ "159\0csISO159JISX02121990\0DS_2089\0DS2089\0ISO646-DK\0dk\0csISO646Danish\0us-dk\0csUSDK\0dk-"
+ "us\0csDKUS\0KSC5636\0ISO646-KR\0csKSC5636\0UNICODE-1-1-UTF-7\0csUnicode11UTF7\0ISO-2022-CN\0csISO2022CN\0ISO-"
+ "2022-CN-EXT\0csISO2022CNEXT\0UTF-8\0csUTF8\0ISO-8859-13\0csISO885913\0ISO-8859-14\0iso-ir-199\0ISO_8859-14:"
+ "1998\0ISO_8859-14\0latin8\0iso-celtic\0l8\0csISO885914\0ISO-8859-15\0ISO_8859-15\0Latin-9\0csISO885915\0ISO-"
+ "8859-16\0iso-ir-226\0ISO_8859-16:2001\0ISO_8859-16\0latin10\0l10\0csISO885916\0GBK\0CP936\0MS936\0windows-"
+ "936\0csGBK\0GB18030\0csGB18030\0OSD_EBCDIC_DF04_15\0csOSDEBCDICDF0415\0OSD_EBCDIC_DF03_"
+ "IRV\0csOSDEBCDICDF03IRV\0OSD_EBCDIC_DF04_1\0csOSDEBCDICDF041\0ISO-11548-1\0ISO_11548-1\0ISO_TR_11548-"
+ "1\0csISO115481\0KZ-1048\0STRK1048-2002\0RK1048\0csKZ1048\0ISO-10646-UCS-2\0csUnicode\0ISO-10646-UCS-"
+ "4\0csUCS4\0ISO-10646-UCS-Basic\0csUnicodeASCII\0ISO-10646-Unicode-Latin1\0csUnicodeLatin1\0ISO-10646\0ISO-10646-"
+ "J-1\0csUnicodeJapanese\0ISO-Unicode-IBM-1261\0csUnicodeIBM1261\0ISO-Unicode-IBM-1268\0csUnicodeIBM1268\0ISO-"
+ "Unicode-IBM-1276\0csUnicodeIBM1276\0ISO-Unicode-IBM-1264\0csUnicodeIBM1264\0ISO-Unicode-IBM-"
+ "1265\0csUnicodeIBM1265\0UNICODE-1-1\0csUnicode11\0SCSU\0csSCSU\0UTF-7\0csUTF7\0UTF-16BE\0csUTF16BE\0UTF-"
+ "16LE\0csUTF16LE\0UTF-16\0csUTF16\0CESU-8\0csCESU8\0csCESU-8\0UTF-32\0csUTF32\0UTF-32BE\0csUTF32BE\0UTF-"
+ "32LE\0csUTF32LE\0BOCU-1\0csBOCU1\0csBOCU-1\0UTF-7-IMAP\0csUTF7IMAP\0ISO-8859-1-Windows-3.0-Latin-"
+ "1\0csWindows30Latin1\0ISO-8859-1-Windows-3.1-Latin-1\0csWindows31Latin1\0ISO-8859-2-Windows-Latin-"
+ "2\0csWindows31Latin2\0ISO-8859-9-Windows-Latin-5\0csWindows31Latin5\0hp-roman8\0roman8\0r8\0csHPRoman8\0Adobe-"
+ "Standard-Encoding\0csAdobeStandardEncoding\0Ventura-US\0csVenturaUS\0Ventura-"
+ "International\0csVenturaInternational\0DEC-"
+ "MCS\0dec\0csDECMCS\0IBM850\0cp850\0850\0csPC850Multilingual\0IBM852\0cp852\0852\0csPCp852\0IBM437\0cp437\0"
+ "437\0csPC8CodePage437\0PC8-Danish-Norwegian\0csPC8DanishNorwegian\0IBM862\0cp862\0862\0csPC862LatinHebrew\0PC8-"
+ "Turkish\0csPC8Turkish\0IBM-Symbols\0csIBMSymbols\0IBM-Thai\0csIBMThai\0HP-Legal\0csHPLegal\0HP-Pi-"
+ "font\0csHPPiFont\0HP-Math8\0csHPMath8\0Adobe-Symbol-Encoding\0csHPPSMath\0HP-DeskTop\0csHPDesktop\0Ventura-"
+ "Math\0csVenturaMath\0Microsoft-Publishing\0csMicrosoftPublishing\0Windows-"
+ "31J\0csWindows31J\0GB2312\0csGB2312\0Big5\0csBig5\0macintosh\0mac\0csMacintosh\0IBM037\0cp037\0ebcdic-cp-"
+ "us\0ebcdic-cp-ca\0ebcdic-cp-wt\0ebcdic-cp-nl\0csIBM037\0IBM038\0EBCDIC-"
+ "INT\0cp038\0csIBM038\0IBM273\0CP273\0csIBM273\0IBM274\0EBCDIC-BE\0CP274\0csIBM274\0IBM275\0EBCDIC-"
+ "BR\0cp275\0csIBM275\0IBM277\0EBCDIC-CP-DK\0EBCDIC-CP-NO\0csIBM277\0IBM278\0CP278\0ebcdic-cp-fi\0ebcdic-cp-"
+ "se\0csIBM278\0IBM280\0CP280\0ebcdic-cp-it\0csIBM280\0IBM281\0EBCDIC-JP-"
+ "E\0cp281\0csIBM281\0IBM284\0CP284\0ebcdic-cp-es\0csIBM284\0IBM285\0CP285\0ebcdic-cp-"
+ "gb\0csIBM285\0IBM290\0cp290\0EBCDIC-JP-kana\0csIBM290\0IBM297\0cp297\0ebcdic-cp-"
+ "fr\0csIBM297\0IBM420\0cp420\0ebcdic-cp-ar1\0csIBM420\0IBM423\0cp423\0ebcdic-cp-"
+ "gr\0csIBM423\0IBM424\0cp424\0ebcdic-cp-he\0csIBM424\0IBM500\0CP500\0ebcdic-cp-be\0ebcdic-cp-"
+ "ch\0csIBM500\0IBM851\0cp851\0851\0csIBM851\0IBM855\0cp855\0855\0csIBM855\0IBM857\0cp857\0857\0csIBM857\0IBM860\0"
+ "cp860\0860\0csIBM860\0IBM861\0cp861\0861\0cp-"
+ "is\0csIBM861\0IBM863\0cp863\0863\0csIBM863\0IBM864\0cp864\0csIBM864\0IBM865\0cp865\0865\0csIBM865\0IBM868\0CP868"
+ "\0cp-ar\0csIBM868\0IBM869\0cp869\0869\0cp-gr\0csIBM869\0IBM870\0CP870\0ebcdic-cp-roece\0ebcdic-cp-"
+ "yu\0csIBM870\0IBM871\0CP871\0ebcdic-cp-is\0csIBM871\0IBM880\0cp880\0EBCDIC-"
+ "Cyrillic\0csIBM880\0IBM891\0cp891\0csIBM891\0IBM903\0cp903\0csIBM903\0IBM904\0cp904\0904\0csIBBM904\0IBM905\0CP9"
+ "05\0ebcdic-cp-tr\0csIBM905\0IBM918\0CP918\0ebcdic-cp-ar2\0csIBM918\0IBM1026\0CP1026\0csIBM1026\0EBCDIC-AT-"
+ "DE\0csIBMEBCDICATDE\0EBCDIC-AT-DE-A\0csEBCDICATDEA\0EBCDIC-CA-FR\0csEBCDICCAFR\0EBCDIC-DK-"
+ "NO\0csEBCDICDKNO\0EBCDIC-DK-NO-A\0csEBCDICDKNOA\0EBCDIC-FI-SE\0csEBCDICFISE\0EBCDIC-FI-SE-"
+ "A\0csEBCDICFISEA\0EBCDIC-FR\0csEBCDICFR\0EBCDIC-IT\0csEBCDICIT\0EBCDIC-PT\0csEBCDICPT\0EBCDIC-"
+ "ES\0csEBCDICES\0EBCDIC-ES-A\0csEBCDICESA\0EBCDIC-ES-S\0csEBCDICESS\0EBCDIC-UK\0csEBCDICUK\0EBCDIC-"
+ "US\0csEBCDICUS\0UNKNOWN-"
+ "8BIT\0csUnknown8BiT\0MNEMONIC\0csMnemonic\0MNEM\0csMnem\0VISCII\0csVISCII\0VIQR\0csVIQR\0KOI8-R\0csKOI8R\0HZ-GB-"
+ "2312\0IBM866\0cp866\0866\0csIBM866\0IBM775\0cp775\0csPC775Baltic\0KOI8-"
+ "U\0csKOI8U\0IBM00858\0CCSID00858\0CP00858\0PC-Multilingual-850+"
+ "euro\0csIBM00858\0IBM00924\0CCSID00924\0CP00924\0ebcdic-Latin9--"
+ "euro\0csIBM00924\0IBM01140\0CCSID01140\0CP01140\0ebcdic-us-37+"
+ "euro\0csIBM01140\0IBM01141\0CCSID01141\0CP01141\0ebcdic-de-273+"
+ "euro\0csIBM01141\0IBM01142\0CCSID01142\0CP01142\0ebcdic-dk-277+euro\0ebcdic-no-277+"
+ "euro\0csIBM01142\0IBM01143\0CCSID01143\0CP01143\0ebcdic-fi-278+euro\0ebcdic-se-278+"
+ "euro\0csIBM01143\0IBM01144\0CCSID01144\0CP01144\0ebcdic-it-280+"
+ "euro\0csIBM01144\0IBM01145\0CCSID01145\0CP01145\0ebcdic-es-284+"
+ "euro\0csIBM01145\0IBM01146\0CCSID01146\0CP01146\0ebcdic-gb-285+"
+ "euro\0csIBM01146\0IBM01147\0CCSID01147\0CP01147\0ebcdic-fr-297+"
+ "euro\0csIBM01147\0IBM01148\0CCSID01148\0CP01148\0ebcdic-international-500+"
+ "euro\0csIBM01148\0IBM01149\0CCSID01149\0CP01149\0ebcdic-is-871+euro\0csIBM01149\0Big5-"
+ "HKSCS\0csBig5HKSCS\0IBM1047\0IBM-1047\0csIBM1047\0PTCP154\0csPTCP154\0PT154\0CP154\0Cyrillic-Asian\0Amiga-"
+ "1251\0Ami1251\0Amiga1251\0Ami-1251\0csAmiga1251\0KOI7-"
+ "switched\0csKOI7switched\0BRF\0csBRF\0TSCII\0csTSCII\0CP51932\0csCP51932\0windows-874\0cswindows874\0windows-"
+ "1250\0cswindows1250\0windows-1251\0cswindows1251\0windows-1252\0cswindows1252\0windows-"
+ "1253\0cswindows1253\0windows-1254\0cswindows1254\0windows-1255\0cswindows1255\0windows-"
+ "1256\0cswindows1256\0windows-1257\0cswindows1257\0windows-1258\0cswindows1258\0TIS-620\0csTIS620\0ISO-8859-"
+ "11\0CP50220\0csCP50220\0";
+
+ static constexpr unsigned short __alias_index_table_[] = {
----------------
ldionne wrote:
If we get any of these numbers wrong or out of sync, it's going to be really painful. Instead, I would suggest populating this using a constexpr computation, something like this:
```
struct _AliasIndexTable {
unsigned short __values[std::__count(__aliases_string, '\0')]; // double-check probably off-by-at-least-one
};
static constexpr _AliasIndexTable __alias_index_table = [] {
_AliasIndexTable __result;
// constexpr computation here to build up __result
return __result;
}();
```
Notes: not including `<array>` so we can make a meaningful comparison of the include times between status quo and this suggestion.
If the difference is negligible, the constexpr computation provides a large maintenance benefit.
https://github.com/llvm/llvm-project/pull/141312
More information about the libcxx-commits
mailing list