From 8e59b16eb2df75251db45eafbe460d5cfd8b407c Mon Sep 17 00:00:00 2001 From: Jessica James Date: Sat, 27 Nov 2021 23:45:53 -0600 Subject: [PATCH] Add various string helpers to unicode.hpp & appropriate tests; fix a bug with word_split --- src/common/unicode.cpp | 253 +++++ src/include/jessilib/unicode.hpp | 374 +++++- src/include/jessilib/word_split.hpp | 2 +- src/test/CMakeLists.txt | 5 + src/test/data/CaseFolding.txt | 1624 +++++++++++++++++++++++++++ src/test/unicode.cpp | 351 ++++++ 6 files changed, 2603 insertions(+), 6 deletions(-) create mode 100644 src/test/data/CaseFolding.txt diff --git a/src/common/unicode.cpp b/src/common/unicode.cpp index 636c1ee..3ba1790 100644 --- a/src/common/unicode.cpp +++ b/src/common/unicode.cpp @@ -266,4 +266,257 @@ get_endpoint_result decode_surrogate_pair(char16_t in_high_surrogate, char16_t i return { 0, 0 }; } +/** + * Codepoint folding (case-insensitive character comparisons) + */ + +// describes a range +struct folding_set { + enum class mode_type { + constant, + alternating, + single + } mode = mode_type::single; + + uint32_t range_start; // inclusive + uint32_t range_end; // inclusive + int64_t diff; // difference between two codepoints + + uint32_t fold(uint32_t in_codepoint) const { + if (mode != mode_type::alternating // Constant & single types immediately apply diff and return + || (in_codepoint % 2) == (range_start % 2)) { // Alternating type apply diff only if matches range type + return static_cast(in_codepoint + diff); + } + + return in_codepoint; + } +}; + +bool operator<(const folding_set& in_lhs, const uint32_t in_rhs) { + return in_rhs > in_lhs.range_end; +} + +bool operator<(const uint32_t in_lhs, const folding_set& in_rhs) { + return in_lhs < in_rhs.range_start; +} + +char32_t fold(char32_t in_codepoint) { + // Break this up? The most common case is going to be points < 0x80, but even without breaking this up we'll only + // perform at most like 8+1 integer comparisons, which is hardly a major constraint + static constexpr folding_set s_folding_sets[]{ + { folding_set::mode_type::constant, 0x0041, 0x005A, 32 }, + { folding_set::mode_type::single, 0x00B5, 0x00B5, 775 }, + { folding_set::mode_type::constant, 0x00C0, 0x00D6, 32 }, + { folding_set::mode_type::constant, 0x00D8, 0x00DE, 32 }, + { folding_set::mode_type::alternating, 0x0100, 0x012E, 1 }, + { folding_set::mode_type::alternating, 0x0132, 0x0136, 1 }, + { folding_set::mode_type::alternating, 0x0139, 0x0147, 1 }, + { folding_set::mode_type::alternating, 0x014A, 0x0176, 1 }, + { folding_set::mode_type::single, 0x0178, 0x0178, -121 }, + { folding_set::mode_type::alternating, 0x0179, 0x017D, 1 }, + { folding_set::mode_type::single, 0x017F, 0x017F, -268 }, + { folding_set::mode_type::single, 0x0181, 0x0181, 210 }, + { folding_set::mode_type::alternating, 0x0182, 0x0184, 1 }, + { folding_set::mode_type::single, 0x0186, 0x0186, 206 }, + { folding_set::mode_type::single, 0x0187, 0x0187, 1 }, + { folding_set::mode_type::constant, 0x0189, 0x018A, 205 }, + { folding_set::mode_type::single, 0x018B, 0x018B, 1 }, + { folding_set::mode_type::single, 0x018E, 0x018E, 79 }, + { folding_set::mode_type::single, 0x018F, 0x018F, 202 }, + { folding_set::mode_type::single, 0x0190, 0x0190, 203 }, + { folding_set::mode_type::single, 0x0191, 0x0191, 1 }, + { folding_set::mode_type::single, 0x0193, 0x0193, 205 }, + { folding_set::mode_type::single, 0x0194, 0x0194, 207 }, + { folding_set::mode_type::single, 0x0196, 0x0196, 211 }, + { folding_set::mode_type::single, 0x0197, 0x0197, 209 }, + { folding_set::mode_type::single, 0x0198, 0x0198, 1 }, + { folding_set::mode_type::single, 0x019C, 0x019C, 211 }, + { folding_set::mode_type::single, 0x019D, 0x019D, 213 }, + { folding_set::mode_type::single, 0x019F, 0x019F, 214 }, + { folding_set::mode_type::alternating, 0x01A0, 0x01A4, 1 }, + { folding_set::mode_type::single, 0x01A6, 0x01A6, 218 }, + { folding_set::mode_type::single, 0x01A7, 0x01A7, 1 }, + { folding_set::mode_type::single, 0x01A9, 0x01A9, 218 }, + { folding_set::mode_type::single, 0x01AC, 0x01AC, 1 }, + { folding_set::mode_type::single, 0x01AE, 0x01AE, 218 }, + { folding_set::mode_type::single, 0x01AF, 0x01AF, 1 }, + { folding_set::mode_type::constant, 0x01B1, 0x01B2, 217 }, + { folding_set::mode_type::alternating, 0x01B3, 0x01B5, 1 }, + { folding_set::mode_type::single, 0x01B7, 0x01B7, 219 }, + { folding_set::mode_type::single, 0x01B8, 0x01B8, 1 }, + { folding_set::mode_type::single, 0x01BC, 0x01BC, 1 }, + { folding_set::mode_type::single, 0x01C4, 0x01C4, 2 }, + { folding_set::mode_type::single, 0x01C5, 0x01C5, 1 }, + { folding_set::mode_type::single, 0x01C7, 0x01C7, 2 }, + { folding_set::mode_type::single, 0x01C8, 0x01C8, 1 }, + { folding_set::mode_type::single, 0x01CA, 0x01CA, 2 }, + { folding_set::mode_type::alternating, 0x01CB, 0x01DB, 1 }, + { folding_set::mode_type::alternating, 0x01DE, 0x01EE, 1 }, + { folding_set::mode_type::single, 0x01F1, 0x01F1, 2 }, + { folding_set::mode_type::alternating, 0x01F2, 0x01F4, 1 }, + { folding_set::mode_type::single, 0x01F6, 0x01F6, -97 }, + { folding_set::mode_type::single, 0x01F7, 0x01F7, -56 }, + { folding_set::mode_type::alternating, 0x01F8, 0x021E, 1 }, + { folding_set::mode_type::single, 0x0220, 0x0220, -130 }, + { folding_set::mode_type::alternating, 0x0222, 0x0232, 1 }, + { folding_set::mode_type::single, 0x023A, 0x023A, 10795 }, + { folding_set::mode_type::single, 0x023B, 0x023B, 1 }, + { folding_set::mode_type::single, 0x023D, 0x023D, -163 }, + { folding_set::mode_type::single, 0x023E, 0x023E, 10792 }, + { folding_set::mode_type::single, 0x0241, 0x0241, 1 }, + { folding_set::mode_type::single, 0x0243, 0x0243, -195 }, + { folding_set::mode_type::single, 0x0244, 0x0244, 69 }, + { folding_set::mode_type::single, 0x0245, 0x0245, 71 }, + { folding_set::mode_type::alternating, 0x0246, 0x024E, 1 }, + { folding_set::mode_type::single, 0x0345, 0x0345, 116 }, + { folding_set::mode_type::alternating, 0x0370, 0x0372, 1 }, + { folding_set::mode_type::single, 0x0376, 0x0376, 1 }, + { folding_set::mode_type::single, 0x037F, 0x037F, 116 }, + { folding_set::mode_type::single, 0x0386, 0x0386, 38 }, + { folding_set::mode_type::constant, 0x0388, 0x038A, 37 }, + { folding_set::mode_type::single, 0x038C, 0x038C, 64 }, + { folding_set::mode_type::constant, 0x038E, 0x038F, 63 }, + { folding_set::mode_type::constant, 0x0391, 0x03A1, 32 }, + { folding_set::mode_type::constant, 0x03A3, 0x03AB, 32 }, + { folding_set::mode_type::single, 0x03C2, 0x03C2, 1 }, + { folding_set::mode_type::single, 0x03CF, 0x03CF, 8 }, + { folding_set::mode_type::single, 0x03D0, 0x03D0, -30 }, + { folding_set::mode_type::single, 0x03D1, 0x03D1, -25 }, + { folding_set::mode_type::single, 0x03D5, 0x03D5, -15 }, + { folding_set::mode_type::single, 0x03D6, 0x03D6, -22 }, + { folding_set::mode_type::alternating, 0x03D8, 0x03EE, 1 }, + { folding_set::mode_type::single, 0x03F0, 0x03F0, -54 }, + { folding_set::mode_type::single, 0x03F1, 0x03F1, -48 }, + { folding_set::mode_type::single, 0x03F4, 0x03F4, -60 }, + { folding_set::mode_type::single, 0x03F5, 0x03F5, -64 }, + { folding_set::mode_type::single, 0x03F7, 0x03F7, 1 }, + { folding_set::mode_type::single, 0x03F9, 0x03F9, -7 }, + { folding_set::mode_type::single, 0x03FA, 0x03FA, 1 }, + { folding_set::mode_type::constant, 0x03FD, 0x03FF, -130 }, + { folding_set::mode_type::constant, 0x0400, 0x040F, 80 }, + { folding_set::mode_type::constant, 0x0410, 0x042F, 32 }, + { folding_set::mode_type::alternating, 0x0460, 0x0480, 1 }, + { folding_set::mode_type::alternating, 0x048A, 0x04BE, 1 }, + { folding_set::mode_type::single, 0x04C0, 0x04C0, 15 }, + { folding_set::mode_type::alternating, 0x04C1, 0x04CD, 1 }, + { folding_set::mode_type::alternating, 0x04D0, 0x052E, 1 }, + { folding_set::mode_type::constant, 0x0531, 0x0556, 48 }, + { folding_set::mode_type::constant, 0x10A0, 0x10C5, 7264 }, + { folding_set::mode_type::single, 0x10C7, 0x10C7, 7264 }, + { folding_set::mode_type::single, 0x10CD, 0x10CD, 7264 }, + { folding_set::mode_type::constant, 0x13F8, 0x13FD, -8 }, + { folding_set::mode_type::single, 0x1C80, 0x1C80, -6222 }, + { folding_set::mode_type::single, 0x1C81, 0x1C81, -6221 }, + { folding_set::mode_type::single, 0x1C82, 0x1C82, -6212 }, + { folding_set::mode_type::constant, 0x1C83, 0x1C84, -6210 }, + { folding_set::mode_type::single, 0x1C85, 0x1C85, -6211 }, + { folding_set::mode_type::single, 0x1C86, 0x1C86, -6204 }, + { folding_set::mode_type::single, 0x1C87, 0x1C87, -6180 }, + { folding_set::mode_type::single, 0x1C88, 0x1C88, 35267 }, + { folding_set::mode_type::constant, 0x1C90, 0x1CBA, -3008 }, + { folding_set::mode_type::constant, 0x1CBD, 0x1CBF, -3008 }, + { folding_set::mode_type::alternating, 0x1E00, 0x1E94, 1 }, + { folding_set::mode_type::single, 0x1E9B, 0x1E9B, -58 }, + { folding_set::mode_type::single, 0x1E9E, 0x1E9E, -7615 }, + { folding_set::mode_type::alternating, 0x1EA0, 0x1EFE, 1 }, + { folding_set::mode_type::constant, 0x1F08, 0x1F0F, -8 }, + { folding_set::mode_type::constant, 0x1F18, 0x1F1D, -8 }, + { folding_set::mode_type::constant, 0x1F28, 0x1F2F, -8 }, + { folding_set::mode_type::constant, 0x1F38, 0x1F3F, -8 }, + { folding_set::mode_type::constant, 0x1F48, 0x1F4D, -8 }, + { folding_set::mode_type::alternating, 0x1F59, 0x1F5F, -8 }, + { folding_set::mode_type::constant, 0x1F68, 0x1F6F, -8 }, + { folding_set::mode_type::constant, 0x1F88, 0x1F8F, -8 }, + { folding_set::mode_type::constant, 0x1F98, 0x1F9F, -8 }, + { folding_set::mode_type::constant, 0x1FA8, 0x1FAF, -8 }, + { folding_set::mode_type::constant, 0x1FB8, 0x1FB9, -8 }, + { folding_set::mode_type::constant, 0x1FBA, 0x1FBB, -74 }, + { folding_set::mode_type::single, 0x1FBC, 0x1FBC, -9 }, + { folding_set::mode_type::single, 0x1FBE, 0x1FBE, -7173 }, + { folding_set::mode_type::constant, 0x1FC8, 0x1FCB, -86 }, + { folding_set::mode_type::single, 0x1FCC, 0x1FCC, -9 }, + { folding_set::mode_type::constant, 0x1FD8, 0x1FD9, -8 }, + { folding_set::mode_type::constant, 0x1FDA, 0x1FDB, -100 }, + { folding_set::mode_type::constant, 0x1FE8, 0x1FE9, -8 }, + { folding_set::mode_type::constant, 0x1FEA, 0x1FEB, -112 }, + { folding_set::mode_type::single, 0x1FEC, 0x1FEC, -7 }, + { folding_set::mode_type::constant, 0x1FF8, 0x1FF9, -128 }, + { folding_set::mode_type::constant, 0x1FFA, 0x1FFB, -126 }, + { folding_set::mode_type::single, 0x1FFC, 0x1FFC, -9 }, + { folding_set::mode_type::single, 0x2126, 0x2126, -7517 }, + { folding_set::mode_type::single, 0x212A, 0x212A, -8383 }, + { folding_set::mode_type::single, 0x212B, 0x212B, -8262 }, + { folding_set::mode_type::single, 0x2132, 0x2132, 28 }, + { folding_set::mode_type::constant, 0x2160, 0x216F, 16 }, + { folding_set::mode_type::single, 0x2183, 0x2183, 1 }, + { folding_set::mode_type::constant, 0x24B6, 0x24CF, 26 }, + { folding_set::mode_type::constant, 0x2C00, 0x2C2F, 48 }, + { folding_set::mode_type::single, 0x2C60, 0x2C60, 1 }, + { folding_set::mode_type::single, 0x2C62, 0x2C62, -10743 }, + { folding_set::mode_type::single, 0x2C63, 0x2C63, -3814 }, + { folding_set::mode_type::single, 0x2C64, 0x2C64, -10727 }, + { folding_set::mode_type::alternating, 0x2C67, 0x2C6B, 1 }, + { folding_set::mode_type::single, 0x2C6D, 0x2C6D, -10780 }, + { folding_set::mode_type::single, 0x2C6E, 0x2C6E, -10749 }, + { folding_set::mode_type::single, 0x2C6F, 0x2C6F, -10783 }, + { folding_set::mode_type::single, 0x2C70, 0x2C70, -10782 }, + { folding_set::mode_type::single, 0x2C72, 0x2C72, 1 }, + { folding_set::mode_type::single, 0x2C75, 0x2C75, 1 }, + { folding_set::mode_type::constant, 0x2C7E, 0x2C7F, -10815 }, + { folding_set::mode_type::alternating, 0x2C80, 0x2CE2, 1 }, + { folding_set::mode_type::alternating, 0x2CEB, 0x2CED, 1 }, + { folding_set::mode_type::single, 0x2CF2, 0x2CF2, 1 }, + { folding_set::mode_type::alternating, 0xA640, 0xA66C, 1 }, + { folding_set::mode_type::alternating, 0xA680, 0xA69A, 1 }, + { folding_set::mode_type::alternating, 0xA722, 0xA72E, 1 }, + { folding_set::mode_type::alternating, 0xA732, 0xA76E, 1 }, + { folding_set::mode_type::alternating, 0xA779, 0xA77B, 1 }, + { folding_set::mode_type::single, 0xA77D, 0xA77D, -35332 }, + { folding_set::mode_type::alternating, 0xA77E, 0xA786, 1 }, + { folding_set::mode_type::single, 0xA78B, 0xA78B, 1 }, + { folding_set::mode_type::single, 0xA78D, 0xA78D, -42280 }, + { folding_set::mode_type::alternating, 0xA790, 0xA792, 1 }, + { folding_set::mode_type::alternating, 0xA796, 0xA7A8, 1 }, + { folding_set::mode_type::single, 0xA7AA, 0xA7AA, -42308 }, + { folding_set::mode_type::single, 0xA7AB, 0xA7AB, -42319 }, + { folding_set::mode_type::single, 0xA7AC, 0xA7AC, -42315 }, + { folding_set::mode_type::single, 0xA7AD, 0xA7AD, -42305 }, + { folding_set::mode_type::single, 0xA7AE, 0xA7AE, -42308 }, + { folding_set::mode_type::single, 0xA7B0, 0xA7B0, -42258 }, + { folding_set::mode_type::single, 0xA7B1, 0xA7B1, -42282 }, + { folding_set::mode_type::single, 0xA7B2, 0xA7B2, -42261 }, + { folding_set::mode_type::single, 0xA7B3, 0xA7B3, 928 }, + { folding_set::mode_type::alternating, 0xA7B4, 0xA7C2, 1 }, + { folding_set::mode_type::single, 0xA7C4, 0xA7C4, -48 }, + { folding_set::mode_type::single, 0xA7C5, 0xA7C5, -42307 }, + { folding_set::mode_type::single, 0xA7C6, 0xA7C6, -35384 }, + { folding_set::mode_type::alternating, 0xA7C7, 0xA7C9, 1 }, + { folding_set::mode_type::single, 0xA7D0, 0xA7D0, 1 }, + { folding_set::mode_type::alternating, 0xA7D6, 0xA7D8, 1 }, + { folding_set::mode_type::single, 0xA7F5, 0xA7F5, 1 }, + { folding_set::mode_type::constant, 0xAB70, 0xABBF, -38864 }, + { folding_set::mode_type::constant, 0xFF21, 0xFF3A, 32 }, + { folding_set::mode_type::constant, 0x10400, 0x10427, 40 }, + { folding_set::mode_type::constant, 0x104B0, 0x104D3, 40 }, + { folding_set::mode_type::constant, 0x10570, 0x1057A, 39 }, + { folding_set::mode_type::constant, 0x1057C, 0x1058A, 39 }, + { folding_set::mode_type::constant, 0x1058C, 0x10592, 39 }, + { folding_set::mode_type::constant, 0x10594, 0x10595, 39 }, + { folding_set::mode_type::constant, 0x10C80, 0x10CB2, 64 }, + { folding_set::mode_type::constant, 0x118A0, 0x118BF, 32 }, + { folding_set::mode_type::constant, 0x16E40, 0x16E5F, 32 }, + { folding_set::mode_type::constant, 0x1E900, 0x1E921, 34 }, + }; + + const folding_set* folding_sets_end = std::end(s_folding_sets); + auto match = std::lower_bound(s_folding_sets, folding_sets_end, in_codepoint); + if (match == folding_sets_end + || in_codepoint < *match) { + // in_codepoint doesn't fit into any set; + return in_codepoint; + } + + return match->fold(in_codepoint); +} + } // namespace jessilib diff --git a/src/include/jessilib/unicode.hpp b/src/include/jessilib/unicode.hpp index f457d6f..9c11957 100644 --- a/src/include/jessilib/unicode.hpp +++ b/src/include/jessilib/unicode.hpp @@ -26,14 +26,36 @@ namespace jessilib { /** encode_codepoint */ -size_t encode_codepoint(std::string& out_string, char32_t in_codepoint); // ASSUMES UTF-8 +/** + * Encodes a codepoint, and appends it to an output string + * + * @param out_string String to append + * @param in_codepoint Codepoint to encode + * @return Number of data elements appended to out_string + */ +size_t encode_codepoint(std::string& out_string, char32_t in_codepoint); // DEPRECATED: ASSUMES UTF-8 size_t encode_codepoint(std::u8string& out_string, char32_t in_codepoint); size_t encode_codepoint(std::u16string& out_string, char32_t in_codepoint); size_t encode_codepoint(std::u32string& out_string, char32_t in_codepoint); -size_t encode_codepoint(std::basic_ostream& out_stream, char32_t in_codepoint); // ASSUMES UTF-8 + +/** + * Encodes a codepoint to an output stream + * + * @param out_stream Stream to write codepoint to + * @param in_codepoint Codepoint to encode + * @return Number of data elements appending to out_stream + */ +size_t encode_codepoint(std::basic_ostream& out_stream, char32_t in_codepoint); // DEPRECATED: ASSUMES UTF-8 size_t encode_codepoint(std::basic_ostream& out_stream, char32_t in_codepoint); size_t encode_codepoint(std::basic_ostream& out_stream, char32_t in_codepoint); size_t encode_codepoint(std::basic_ostream& out_stream, char32_t in_codepoint); + +/** + * Encodes a codepoint and returns it as a string + * + * @param in_codepoint Codepoint to encode + * @return A string containing the codepoint encoded to the appropriate underlying CharT type + */ std::u8string encode_codepoint_u8(char32_t in_codepoint); std::u16string encode_codepoint_u16(char32_t in_codepoint); std::u32string encode_codepoint_u32(char32_t in_codepoint); @@ -41,11 +63,17 @@ std::u32string encode_codepoint_u32(char32_t in_codepoint); /** decode_codepoint */ struct get_endpoint_result { - char32_t codepoint{}; - size_t units{}; + char32_t codepoint{}; // Codepoint + size_t units{}; // Number of data units codepoint was represented by, or 0 }; -get_endpoint_result decode_codepoint(const std::string_view& in_string); // ASSUMES UTF-8 +/** + * Decodes the front codepoint in a string + * + * @param in_string String to decode a codepoint from + * @return A struct containing a valid codepoint and the number of representative data units on success, zero otherwise. + */ +get_endpoint_result decode_codepoint(const std::string_view& in_string); // DEPRECATED: ASSUMES UTF-8 get_endpoint_result decode_codepoint(const std::u8string_view& in_string); // UTF-8 get_endpoint_result decode_codepoint(const std::u16string_view& in_string); // UTF-16 get_endpoint_result decode_codepoint(const std::u32string_view& in_string); // UTF-32 @@ -79,4 +107,340 @@ bool is_high_surrogate(char32_t in_codepoint); bool is_low_surrogate(char32_t in_codepoint); get_endpoint_result decode_surrogate_pair(char16_t in_high_surrogate, char16_t in_low_surrogate); +/** Utilities */ + +template +bool is_valid(const InT& in_string) { + using InCharT = typename InT::value_type; + using InViewT = std::basic_string_view; + + InViewT in_string_view = static_cast(in_string); + while (!in_string_view.empty()) { + get_endpoint_result string_front = decode_codepoint(in_string_view); + if (string_front.units == 0) { + return false; + } + in_string_view.remove_prefix(string_front.units); + } + + return true; +} + +/** + * Interprets one string type as another (i.e: reading from a I/O stream or buffer, char -> whatever) + * NOTE: THIS DOES NOT GUARANTEE THE RESULTING VIEW IS SANE, ONLY THAT IT'S A TECHNICALLY VALID SEQUENCE + * + * @tparam OutCharT Output view character type + * @tparam InT Input string type + * @param in_string Container holding string data + * @return A valid view into in_string on success, an empty string_view otherwise + */ +template +std::basic_string_view string_view_cast(const InT& in_string) { + using InCharT = typename InT::value_type; + size_t in_string_bytes = in_string.size() * sizeof(InCharT); + if constexpr (sizeof(OutCharT) > sizeof(InCharT)) { + // The output type is larger than the input type; verify no partial codepoints + if (in_string_bytes % sizeof(OutCharT) != 0) { + // This cannot be used to produce a valid result + return {}; + } + } + + size_t out_string_units = in_string_bytes / sizeof(OutCharT); + const OutCharT* data_begin = reinterpret_cast(in_string.data()); + std::basic_string_view result{ data_begin, out_string_units }; + + if (!is_valid(result)) { + // Result isn't valid; discard and return empty + return {}; + } + + return result; +} + +template +std::basic_string string_cast(const InT& in_string) { + using InCharT = typename InT::value_type; + using InViewT = std::basic_string_view; + std::basic_string result; + + // Just do a dumb copy when same type & valid; should be slightly faster than re-encoding + if constexpr (std::is_same_v) { + if (is_valid(in_string)) { + result = in_string; + } + + return result; + } + + InViewT in_string_view = static_cast(in_string); + if constexpr (sizeof(InCharT) <= sizeof(OutCharT)) { + // When copying to a larger type, we will need _at most_ as many elements as the smaller storage type + result.reserve(in_string_view.size()); + } + else { + result.reserve(in_string_view.size() * (sizeof(OutCharT) / sizeof(InCharT))); + } + + while (!in_string_view.empty()) { + get_endpoint_result string_front = decode_codepoint(in_string_view); + if (string_front.units == 0) { + return {}; + } + in_string_view.remove_prefix(string_front.units); + + encode_codepoint(result, string_front.codepoint); + } + + return result; +} + +/** single-unit case folding utilities */ +char32_t fold(char32_t in_codepoint); // Folds codepoint for case insensitive checks (not for human output) + +/** + * Checks if two codepoints are equal to eachother (case insensitive) + * + * @param lhs First codepoint to compare + * @param rhs Second codepoint to compare + * @return True if the characters are equal, false otherwise + */ +inline bool equalsi(char32_t lhs, char32_t rhs) { + return lhs == rhs + || fold(lhs) == fold(rhs); +} + +// Should just make these methods container-type agnostic rather than this mess... +#define ADAPT_BASIC_STRING(method) \ + template \ + auto method(const std::basic_string& lhs, std::basic_string_view rhs) { \ + return method(static_cast>(lhs), rhs); } \ + template \ + bool method(std::basic_string_view lhs, const std::basic_string& rhs) { \ + return method(lhs, static_cast>(rhs)); } \ + template \ + bool method(const std::basic_string& lhs, const std::basic_string& rhs) { \ + return method(static_cast>(lhs), static_cast>(rhs)); } + +/** + * Checks if two strings are equal + * + * @tparam LhsCharT Unicode codepoint container type for left-hand parameter + * @tparam RhsCharT Unicode codepoint container type for right-hand parameter + * @param lhs First string to compare + * @param rhs Second string to compare against + * @return True if the strings are equal, false otherwise + */ +template +bool equals(std::basic_string_view lhs, std::basic_string_view rhs) { + // If lhs and rhs are the same type, compare their sizes and quickly return if not same + if constexpr (std::is_same_v) { + return lhs == rhs; + } + + while (!lhs.empty() && !rhs.empty()) { + auto lhs_front = decode_codepoint(lhs); + auto rhs_front = decode_codepoint(rhs); + + if (lhs_front.units == 0 + || rhs_front.units == 0) { + // Failed to decode front codepoint; bad unicode sequence + return false; + } + + if (lhs_front.codepoint != rhs_front.codepoint) { + // Codepoints aren't the same + return false; + } + + // Codepoints are equal; trim off the fronts and continue + lhs.remove_prefix(lhs_front.units); + rhs.remove_prefix(rhs_front.units); + } + + return lhs.empty() && rhs.empty(); +} + +ADAPT_BASIC_STRING(equals) + +/** + * Checks if two strings are equal (case insensitive) + * + * @tparam LhsCharT Unicode codepoint container type for left-hand parameter + * @tparam RhsCharT Unicode codepoint container type for right-hand parameter + * @param lhs First string to compare + * @param rhs Second string to compare against + * @return True if the strings are equal, false otherwise + */ +template +bool equalsi(std::basic_string_view lhs, std::basic_string_view rhs) { + // If lhs and rhs are the same type, compare their sizes and quickly return if not same + if constexpr (std::is_same_v) { + if (lhs.size() != rhs.size()) { + return false; + } + } + + while (!lhs.empty() && !rhs.empty()) { + auto lhs_front = decode_codepoint(lhs); + auto rhs_front = decode_codepoint(rhs); + + if (lhs_front.units == 0 + || rhs_front.units == 0) { + // Failed to decode front codepoint; bad unicode sequence + return false; + } + + if (!equalsi(lhs_front.codepoint, rhs_front.codepoint)) { + // Codepoints don't fold to same value + return false; + } + + // Codepoints are equal; trim off the fronts and continue + lhs.remove_prefix(lhs_front.units); + rhs.remove_prefix(rhs_front.units); + } + + return lhs.empty() && rhs.empty(); +} + +ADAPT_BASIC_STRING(equalsi) + +/** + * Checks if a string starts with a substring + * + * @tparam LhsCharT Unicode codepoint container type for underlying string + * @tparam RhsCharT Unicode codepoint container type for prefix string + * @param in_string String to check for prefix + * @param in_prefix Substring prefix to check for + * @return Data length of in_prefix in terms of LhsCharT if in_string starts with in_prefix, 0 otherwise + */ +template +size_t starts_with_length(std::basic_string_view in_string, std::basic_string_view in_prefix) { + // If in_string and in_prefix are the same type, compare their sizes and quickly return if in_string is too small + if constexpr (std::is_same_v) { + if (in_string.size() < in_prefix.size()) { + return 0; + } + } + + size_t codepoints_removed{}; + while (!in_string.empty() && !in_prefix.empty()) { + get_endpoint_result string_front = decode_codepoint(in_string); + get_endpoint_result prefix_front = decode_codepoint(in_prefix); + + if (string_front.units == 0 + || prefix_front.units == 0) { + // Failed to decode front codepoint; bad unicode sequence + return 0; + } + + if (string_front.codepoint != prefix_front.codepoint) { + // Codepoints aren't the same + return 0; + } + + // Codepoints are equal; trim off the fronts and continue + in_string.remove_prefix(string_front.units); + in_prefix.remove_prefix(prefix_front.units); + codepoints_removed += string_front.units; + } + + if (!in_prefix.empty()) { + // We reached end of in_string before end of prefix + return 0; + } + + return codepoints_removed; +} + +ADAPT_BASIC_STRING(starts_with_length) + +/** + * Checks if a string starts with a substring (case insensitive) + * + * @tparam LhsCharT Unicode codepoint container type for underlying string + * @tparam RhsCharT Unicode codepoint container type for prefix string + * @param in_string String to check for prefix + * @param in_prefix Substring prefix to check for + * @return Data length of in_prefix in terms of LhsCharT if in_string starts with in_prefix, 0 otherwise + */ +template +size_t starts_with_lengthi(std::basic_string_view in_string, std::basic_string_view in_prefix) { + // If in_string and in_prefix are the same type, compare their sizes and quickly return if in_string is too small + if constexpr (std::is_same_v) { + if (in_string.size() < in_prefix.size()) { + return 0; + } + } + + size_t codepoints_removed{}; + while (!in_string.empty() && !in_prefix.empty()) { + get_endpoint_result string_front = decode_codepoint(in_string); + get_endpoint_result prefix_front = decode_codepoint(in_prefix); + + if (string_front.units == 0 + || prefix_front.units == 0) { + // Failed to decode front codepoint; bad unicode sequence + return 0; + } + + if (!equalsi(string_front.codepoint, prefix_front.codepoint)) { + // Codepoints don't fold to same value + return 0; + } + + // Codepoints are equal; trim off the fronts and continue + in_string.remove_prefix(string_front.units); + in_prefix.remove_prefix(prefix_front.units); + codepoints_removed += string_front.units; + } + + if (!in_prefix.empty()) { + // We reached end of in_string before end of prefix + return 0; + } + + return codepoints_removed; +} + +ADAPT_BASIC_STRING(starts_with_lengthi) + +/** + * Checks if a string starts with a substring + * + * @tparam LhsCharT Unicode codepoint container type for underlying string + * @tparam RhsCharT Unicode codepoint container type for prefix string + * @param in_string String to check for prefix + * @param in_prefix Prefix to check for + * @return True if both strings are valid and in_string starts with in_prefix, false otherwise + */ +template +bool starts_with(std::basic_string_view in_string, std::basic_string_view in_prefix) { + return starts_with_length(in_string, in_prefix) != 0; +} + +ADAPT_BASIC_STRING(starts_with) + +/** + * Checks if a string starts with a substring (case insensitive) + * + * @tparam LhsCharT Unicode codepoint container type for underlying string + * @tparam RhsCharT Unicode codepoint container type for prefix string + * @param in_string String to check for prefix + * @param in_prefix Prefix to check for + * @return True if both strings are valid and in_string starts with in_prefix, false otherwise + */ +template +bool starts_withi(std::basic_string_view in_string, std::basic_string_view in_prefix) { + return starts_with_lengthi(in_string, in_prefix) != 0; +} + +ADAPT_BASIC_STRING(starts_withi) + +/** to_lower / to_upper */ +//char32_t to_lower(char32_t in_chr); // TODO: implement +//char32_t to_upper(char32_t in_chr); // TODO: implement + } // namespace jessilib diff --git a/src/include/jessilib/word_split.hpp b/src/include/jessilib/word_split.hpp index c756a8f..7a4e5e3 100644 --- a/src/include/jessilib/word_split.hpp +++ b/src/include/jessilib/word_split.hpp @@ -301,7 +301,7 @@ constexpr auto word_split_once(ItrT begin, EndT end, SpaceItrT in_whitespace_beg } for (auto itr = begin; itr < end;) { - if (is_whitespace(itr)) { + if (is_whitespace(*itr)) { // in_whitespace found; word_split upon it result.first = make_word_split_member(begin, itr); diff --git a/src/test/CMakeLists.txt b/src/test/CMakeLists.txt index 54c966a..3c0ccdf 100644 --- a/src/test/CMakeLists.txt +++ b/src/test/CMakeLists.txt @@ -16,3 +16,8 @@ target_include_directories(jessilib_tests PRIVATE .) # Link with gtest target_link_libraries(jessilib_tests gtest gtest_main jessilib) + +# Also ensure JESSITEST_SRC_DIR is defined +target_compile_definitions(jessilib_tests PRIVATE + JESSITEST_SRC_DIR="${CMAKE_CURRENT_SOURCE_DIR}/" + JESSITEST_DATA_DIR="${CMAKE_CURRENT_SOURCE_DIR}/data/") diff --git a/src/test/data/CaseFolding.txt b/src/test/data/CaseFolding.txt new file mode 100644 index 0000000..932ace2 --- /dev/null +++ b/src/test/data/CaseFolding.txt @@ -0,0 +1,1624 @@ +# CaseFolding-14.0.0.txt +# Date: 2021-03-08, 19:35:41 GMT +# © 2021 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ +# +# Case Folding Properties +# +# This file is a supplement to the UnicodeData file. +# It provides a case folding mapping generated from the Unicode Character Database. +# If all characters are mapped according to the full mapping below, then +# case differences (according to UnicodeData.txt and SpecialCasing.txt) +# are eliminated. +# +# The data supports both implementations that require simple case foldings +# (where string lengths don't change), and implementations that allow full case folding +# (where string lengths may grow). Note that where they can be supported, the +# full case foldings are superior: for example, they allow "MASSE" and "Maße" to match. +# +# All code points not listed in this file map to themselves. +# +# NOTE: case folding does not preserve normalization formats! +# +# For information on case folding, including how to have case folding +# preserve normalization formats, see Section 3.13 Default Case Algorithms in +# The Unicode Standard. +# +# ================================================================================ +# Format +# ================================================================================ +# The entries in this file are in the following machine-readable format: +# +# ; ; ; # +# +# The status field is: +# C: common case folding, common mappings shared by both simple and full mappings. +# F: full case folding, mappings that cause strings to grow in length. Multiple characters are separated by spaces. +# S: simple case folding, mappings to single characters where different from F. +# T: special case for uppercase I and dotted uppercase I +# - For non-Turkic languages, this mapping is normally not used. +# - For Turkic languages (tr, az), this mapping can be used instead of the normal mapping for these characters. +# Note that the Turkic mappings do not maintain canonical equivalence without additional processing. +# See the discussions of case mapping in the Unicode Standard for more information. +# +# Usage: +# A. To do a simple case folding, use the mappings with status C + S. +# B. To do a full case folding, use the mappings with status C + F. +# +# The mappings with status T can be used or omitted depending on the desired case-folding +# behavior. (The default option is to exclude them.) +# +# ================================================================= + +# Property: Case_Folding + +# All code points not explicitly listed for Case_Folding +# have the value C for the status field, and the code point itself for the mapping field. + +# ================================================================= +0041; C; 0061; # LATIN CAPITAL LETTER A +0042; C; 0062; # LATIN CAPITAL LETTER B +0043; C; 0063; # LATIN CAPITAL LETTER C +0044; C; 0064; # LATIN CAPITAL LETTER D +0045; C; 0065; # LATIN CAPITAL LETTER E +0046; C; 0066; # LATIN CAPITAL LETTER F +0047; C; 0067; # LATIN CAPITAL LETTER G +0048; C; 0068; # LATIN CAPITAL LETTER H +0049; C; 0069; # LATIN CAPITAL LETTER I +0049; T; 0131; # LATIN CAPITAL LETTER I +004A; C; 006A; # LATIN CAPITAL LETTER J +004B; C; 006B; # LATIN CAPITAL LETTER K +004C; C; 006C; # LATIN CAPITAL LETTER L +004D; C; 006D; # LATIN CAPITAL LETTER M +004E; C; 006E; # LATIN CAPITAL LETTER N +004F; C; 006F; # LATIN CAPITAL LETTER O +0050; C; 0070; # LATIN CAPITAL LETTER P +0051; C; 0071; # LATIN CAPITAL LETTER Q +0052; C; 0072; # LATIN CAPITAL LETTER R +0053; C; 0073; # LATIN CAPITAL LETTER S +0054; C; 0074; # LATIN CAPITAL LETTER T +0055; C; 0075; # LATIN CAPITAL LETTER U +0056; C; 0076; # LATIN CAPITAL LETTER V +0057; C; 0077; # LATIN CAPITAL LETTER W +0058; C; 0078; # LATIN CAPITAL LETTER X +0059; C; 0079; # LATIN CAPITAL LETTER Y +005A; C; 007A; # LATIN CAPITAL LETTER Z +00B5; C; 03BC; # MICRO SIGN +00C0; C; 00E0; # LATIN CAPITAL LETTER A WITH GRAVE +00C1; C; 00E1; # LATIN CAPITAL LETTER A WITH ACUTE +00C2; C; 00E2; # LATIN CAPITAL LETTER A WITH CIRCUMFLEX +00C3; C; 00E3; # LATIN CAPITAL LETTER A WITH TILDE +00C4; C; 00E4; # LATIN CAPITAL LETTER A WITH DIAERESIS +00C5; C; 00E5; # LATIN CAPITAL LETTER A WITH RING ABOVE +00C6; C; 00E6; # LATIN CAPITAL LETTER AE +00C7; C; 00E7; # LATIN CAPITAL LETTER C WITH CEDILLA +00C8; C; 00E8; # LATIN CAPITAL LETTER E WITH GRAVE +00C9; C; 00E9; # LATIN CAPITAL LETTER E WITH ACUTE +00CA; C; 00EA; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX +00CB; C; 00EB; # LATIN CAPITAL LETTER E WITH DIAERESIS +00CC; C; 00EC; # LATIN CAPITAL LETTER I WITH GRAVE +00CD; C; 00ED; # LATIN CAPITAL LETTER I WITH ACUTE +00CE; C; 00EE; # LATIN CAPITAL LETTER I WITH CIRCUMFLEX +00CF; C; 00EF; # LATIN CAPITAL LETTER I WITH DIAERESIS +00D0; C; 00F0; # LATIN CAPITAL LETTER ETH +00D1; C; 00F1; # LATIN CAPITAL LETTER N WITH TILDE +00D2; C; 00F2; # LATIN CAPITAL LETTER O WITH GRAVE +00D3; C; 00F3; # LATIN CAPITAL LETTER O WITH ACUTE +00D4; C; 00F4; # LATIN CAPITAL LETTER O WITH CIRCUMFLEX +00D5; C; 00F5; # LATIN CAPITAL LETTER O WITH TILDE +00D6; C; 00F6; # LATIN CAPITAL LETTER O WITH DIAERESIS +00D8; C; 00F8; # LATIN CAPITAL LETTER O WITH STROKE +00D9; C; 00F9; # LATIN CAPITAL LETTER U WITH GRAVE +00DA; C; 00FA; # LATIN CAPITAL LETTER U WITH ACUTE +00DB; C; 00FB; # LATIN CAPITAL LETTER U WITH CIRCUMFLEX +00DC; C; 00FC; # LATIN CAPITAL LETTER U WITH DIAERESIS +00DD; C; 00FD; # LATIN CAPITAL LETTER Y WITH ACUTE +00DE; C; 00FE; # LATIN CAPITAL LETTER THORN +00DF; F; 0073 0073; # LATIN SMALL LETTER SHARP S +0100; C; 0101; # LATIN CAPITAL LETTER A WITH MACRON +0102; C; 0103; # LATIN CAPITAL LETTER A WITH BREVE +0104; C; 0105; # LATIN CAPITAL LETTER A WITH OGONEK +0106; C; 0107; # LATIN CAPITAL LETTER C WITH ACUTE +0108; C; 0109; # LATIN CAPITAL LETTER C WITH CIRCUMFLEX +010A; C; 010B; # LATIN CAPITAL LETTER C WITH DOT ABOVE +010C; C; 010D; # LATIN CAPITAL LETTER C WITH CARON +010E; C; 010F; # LATIN CAPITAL LETTER D WITH CARON +0110; C; 0111; # LATIN CAPITAL LETTER D WITH STROKE +0112; C; 0113; # LATIN CAPITAL LETTER E WITH MACRON +0114; C; 0115; # LATIN CAPITAL LETTER E WITH BREVE +0116; C; 0117; # LATIN CAPITAL LETTER E WITH DOT ABOVE +0118; C; 0119; # LATIN CAPITAL LETTER E WITH OGONEK +011A; C; 011B; # LATIN CAPITAL LETTER E WITH CARON +011C; C; 011D; # LATIN CAPITAL LETTER G WITH CIRCUMFLEX +011E; C; 011F; # LATIN CAPITAL LETTER G WITH BREVE +0120; C; 0121; # LATIN CAPITAL LETTER G WITH DOT ABOVE +0122; C; 0123; # LATIN CAPITAL LETTER G WITH CEDILLA +0124; C; 0125; # LATIN CAPITAL LETTER H WITH CIRCUMFLEX +0126; C; 0127; # LATIN CAPITAL LETTER H WITH STROKE +0128; C; 0129; # LATIN CAPITAL LETTER I WITH TILDE +012A; C; 012B; # LATIN CAPITAL LETTER I WITH MACRON +012C; C; 012D; # LATIN CAPITAL LETTER I WITH BREVE +012E; C; 012F; # LATIN CAPITAL LETTER I WITH OGONEK +0130; F; 0069 0307; # LATIN CAPITAL LETTER I WITH DOT ABOVE +0130; T; 0069; # LATIN CAPITAL LETTER I WITH DOT ABOVE +0132; C; 0133; # LATIN CAPITAL LIGATURE IJ +0134; C; 0135; # LATIN CAPITAL LETTER J WITH CIRCUMFLEX +0136; C; 0137; # LATIN CAPITAL LETTER K WITH CEDILLA +0139; C; 013A; # LATIN CAPITAL LETTER L WITH ACUTE +013B; C; 013C; # LATIN CAPITAL LETTER L WITH CEDILLA +013D; C; 013E; # LATIN CAPITAL LETTER L WITH CARON +013F; C; 0140; # LATIN CAPITAL LETTER L WITH MIDDLE DOT +0141; C; 0142; # LATIN CAPITAL LETTER L WITH STROKE +0143; C; 0144; # LATIN CAPITAL LETTER N WITH ACUTE +0145; C; 0146; # LATIN CAPITAL LETTER N WITH CEDILLA +0147; C; 0148; # LATIN CAPITAL LETTER N WITH CARON +0149; F; 02BC 006E; # LATIN SMALL LETTER N PRECEDED BY APOSTROPHE +014A; C; 014B; # LATIN CAPITAL LETTER ENG +014C; C; 014D; # LATIN CAPITAL LETTER O WITH MACRON +014E; C; 014F; # LATIN CAPITAL LETTER O WITH BREVE +0150; C; 0151; # LATIN CAPITAL LETTER O WITH DOUBLE ACUTE +0152; C; 0153; # LATIN CAPITAL LIGATURE OE +0154; C; 0155; # LATIN CAPITAL LETTER R WITH ACUTE +0156; C; 0157; # LATIN CAPITAL LETTER R WITH CEDILLA +0158; C; 0159; # LATIN CAPITAL LETTER R WITH CARON +015A; C; 015B; # LATIN CAPITAL LETTER S WITH ACUTE +015C; C; 015D; # LATIN CAPITAL LETTER S WITH CIRCUMFLEX +015E; C; 015F; # LATIN CAPITAL LETTER S WITH CEDILLA +0160; C; 0161; # LATIN CAPITAL LETTER S WITH CARON +0162; C; 0163; # LATIN CAPITAL LETTER T WITH CEDILLA +0164; C; 0165; # LATIN CAPITAL LETTER T WITH CARON +0166; C; 0167; # LATIN CAPITAL LETTER T WITH STROKE +0168; C; 0169; # LATIN CAPITAL LETTER U WITH TILDE +016A; C; 016B; # LATIN CAPITAL LETTER U WITH MACRON +016C; C; 016D; # LATIN CAPITAL LETTER U WITH BREVE +016E; C; 016F; # LATIN CAPITAL LETTER U WITH RING ABOVE +0170; C; 0171; # LATIN CAPITAL LETTER U WITH DOUBLE ACUTE +0172; C; 0173; # LATIN CAPITAL LETTER U WITH OGONEK +0174; C; 0175; # LATIN CAPITAL LETTER W WITH CIRCUMFLEX +0176; C; 0177; # LATIN CAPITAL LETTER Y WITH CIRCUMFLEX +0178; C; 00FF; # LATIN CAPITAL LETTER Y WITH DIAERESIS +0179; C; 017A; # LATIN CAPITAL LETTER Z WITH ACUTE +017B; C; 017C; # LATIN CAPITAL LETTER Z WITH DOT ABOVE +017D; C; 017E; # LATIN CAPITAL LETTER Z WITH CARON +017F; C; 0073; # LATIN SMALL LETTER LONG S +0181; C; 0253; # LATIN CAPITAL LETTER B WITH HOOK +0182; C; 0183; # LATIN CAPITAL LETTER B WITH TOPBAR +0184; C; 0185; # LATIN CAPITAL LETTER TONE SIX +0186; C; 0254; # LATIN CAPITAL LETTER OPEN O +0187; C; 0188; # LATIN CAPITAL LETTER C WITH HOOK +0189; C; 0256; # LATIN CAPITAL LETTER AFRICAN D +018A; C; 0257; # LATIN CAPITAL LETTER D WITH HOOK +018B; C; 018C; # LATIN CAPITAL LETTER D WITH TOPBAR +018E; C; 01DD; # LATIN CAPITAL LETTER REVERSED E +018F; C; 0259; # LATIN CAPITAL LETTER SCHWA +0190; C; 025B; # LATIN CAPITAL LETTER OPEN E +0191; C; 0192; # LATIN CAPITAL LETTER F WITH HOOK +0193; C; 0260; # LATIN CAPITAL LETTER G WITH HOOK +0194; C; 0263; # LATIN CAPITAL LETTER GAMMA +0196; C; 0269; # LATIN CAPITAL LETTER IOTA +0197; C; 0268; # LATIN CAPITAL LETTER I WITH STROKE +0198; C; 0199; # LATIN CAPITAL LETTER K WITH HOOK +019C; C; 026F; # LATIN CAPITAL LETTER TURNED M +019D; C; 0272; # LATIN CAPITAL LETTER N WITH LEFT HOOK +019F; C; 0275; # LATIN CAPITAL LETTER O WITH MIDDLE TILDE +01A0; C; 01A1; # LATIN CAPITAL LETTER O WITH HORN +01A2; C; 01A3; # LATIN CAPITAL LETTER OI +01A4; C; 01A5; # LATIN CAPITAL LETTER P WITH HOOK +01A6; C; 0280; # LATIN LETTER YR +01A7; C; 01A8; # LATIN CAPITAL LETTER TONE TWO +01A9; C; 0283; # LATIN CAPITAL LETTER ESH +01AC; C; 01AD; # LATIN CAPITAL LETTER T WITH HOOK +01AE; C; 0288; # LATIN CAPITAL LETTER T WITH RETROFLEX HOOK +01AF; C; 01B0; # LATIN CAPITAL LETTER U WITH HORN +01B1; C; 028A; # LATIN CAPITAL LETTER UPSILON +01B2; C; 028B; # LATIN CAPITAL LETTER V WITH HOOK +01B3; C; 01B4; # LATIN CAPITAL LETTER Y WITH HOOK +01B5; C; 01B6; # LATIN CAPITAL LETTER Z WITH STROKE +01B7; C; 0292; # LATIN CAPITAL LETTER EZH +01B8; C; 01B9; # LATIN CAPITAL LETTER EZH REVERSED +01BC; C; 01BD; # LATIN CAPITAL LETTER TONE FIVE +01C4; C; 01C6; # LATIN CAPITAL LETTER DZ WITH CARON +01C5; C; 01C6; # LATIN CAPITAL LETTER D WITH SMALL LETTER Z WITH CARON +01C7; C; 01C9; # LATIN CAPITAL LETTER LJ +01C8; C; 01C9; # LATIN CAPITAL LETTER L WITH SMALL LETTER J +01CA; C; 01CC; # LATIN CAPITAL LETTER NJ +01CB; C; 01CC; # LATIN CAPITAL LETTER N WITH SMALL LETTER J +01CD; C; 01CE; # LATIN CAPITAL LETTER A WITH CARON +01CF; C; 01D0; # LATIN CAPITAL LETTER I WITH CARON +01D1; C; 01D2; # LATIN CAPITAL LETTER O WITH CARON +01D3; C; 01D4; # LATIN CAPITAL LETTER U WITH CARON +01D5; C; 01D6; # LATIN CAPITAL LETTER U WITH DIAERESIS AND MACRON +01D7; C; 01D8; # LATIN CAPITAL LETTER U WITH DIAERESIS AND ACUTE +01D9; C; 01DA; # LATIN CAPITAL LETTER U WITH DIAERESIS AND CARON +01DB; C; 01DC; # LATIN CAPITAL LETTER U WITH DIAERESIS AND GRAVE +01DE; C; 01DF; # LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON +01E0; C; 01E1; # LATIN CAPITAL LETTER A WITH DOT ABOVE AND MACRON +01E2; C; 01E3; # LATIN CAPITAL LETTER AE WITH MACRON +01E4; C; 01E5; # LATIN CAPITAL LETTER G WITH STROKE +01E6; C; 01E7; # LATIN CAPITAL LETTER G WITH CARON +01E8; C; 01E9; # LATIN CAPITAL LETTER K WITH CARON +01EA; C; 01EB; # LATIN CAPITAL LETTER O WITH OGONEK +01EC; C; 01ED; # LATIN CAPITAL LETTER O WITH OGONEK AND MACRON +01EE; C; 01EF; # LATIN CAPITAL LETTER EZH WITH CARON +01F0; F; 006A 030C; # LATIN SMALL LETTER J WITH CARON +01F1; C; 01F3; # LATIN CAPITAL LETTER DZ +01F2; C; 01F3; # LATIN CAPITAL LETTER D WITH SMALL LETTER Z +01F4; C; 01F5; # LATIN CAPITAL LETTER G WITH ACUTE +01F6; C; 0195; # LATIN CAPITAL LETTER HWAIR +01F7; C; 01BF; # LATIN CAPITAL LETTER WYNN +01F8; C; 01F9; # LATIN CAPITAL LETTER N WITH GRAVE +01FA; C; 01FB; # LATIN CAPITAL LETTER A WITH RING ABOVE AND ACUTE +01FC; C; 01FD; # LATIN CAPITAL LETTER AE WITH ACUTE +01FE; C; 01FF; # LATIN CAPITAL LETTER O WITH STROKE AND ACUTE +0200; C; 0201; # LATIN CAPITAL LETTER A WITH DOUBLE GRAVE +0202; C; 0203; # LATIN CAPITAL LETTER A WITH INVERTED BREVE +0204; C; 0205; # LATIN CAPITAL LETTER E WITH DOUBLE GRAVE +0206; C; 0207; # LATIN CAPITAL LETTER E WITH INVERTED BREVE +0208; C; 0209; # LATIN CAPITAL LETTER I WITH DOUBLE GRAVE +020A; C; 020B; # LATIN CAPITAL LETTER I WITH INVERTED BREVE +020C; C; 020D; # LATIN CAPITAL LETTER O WITH DOUBLE GRAVE +020E; C; 020F; # LATIN CAPITAL LETTER O WITH INVERTED BREVE +0210; C; 0211; # LATIN CAPITAL LETTER R WITH DOUBLE GRAVE +0212; C; 0213; # LATIN CAPITAL LETTER R WITH INVERTED BREVE +0214; C; 0215; # LATIN CAPITAL LETTER U WITH DOUBLE GRAVE +0216; C; 0217; # LATIN CAPITAL LETTER U WITH INVERTED BREVE +0218; C; 0219; # LATIN CAPITAL LETTER S WITH COMMA BELOW +021A; C; 021B; # LATIN CAPITAL LETTER T WITH COMMA BELOW +021C; C; 021D; # LATIN CAPITAL LETTER YOGH +021E; C; 021F; # LATIN CAPITAL LETTER H WITH CARON +0220; C; 019E; # LATIN CAPITAL LETTER N WITH LONG RIGHT LEG +0222; C; 0223; # LATIN CAPITAL LETTER OU +0224; C; 0225; # LATIN CAPITAL LETTER Z WITH HOOK +0226; C; 0227; # LATIN CAPITAL LETTER A WITH DOT ABOVE +0228; C; 0229; # LATIN CAPITAL LETTER E WITH CEDILLA +022A; C; 022B; # LATIN CAPITAL LETTER O WITH DIAERESIS AND MACRON +022C; C; 022D; # LATIN CAPITAL LETTER O WITH TILDE AND MACRON +022E; C; 022F; # LATIN CAPITAL LETTER O WITH DOT ABOVE +0230; C; 0231; # LATIN CAPITAL LETTER O WITH DOT ABOVE AND MACRON +0232; C; 0233; # LATIN CAPITAL LETTER Y WITH MACRON +023A; C; 2C65; # LATIN CAPITAL LETTER A WITH STROKE +023B; C; 023C; # LATIN CAPITAL LETTER C WITH STROKE +023D; C; 019A; # LATIN CAPITAL LETTER L WITH BAR +023E; C; 2C66; # LATIN CAPITAL LETTER T WITH DIAGONAL STROKE +0241; C; 0242; # LATIN CAPITAL LETTER GLOTTAL STOP +0243; C; 0180; # LATIN CAPITAL LETTER B WITH STROKE +0244; C; 0289; # LATIN CAPITAL LETTER U BAR +0245; C; 028C; # LATIN CAPITAL LETTER TURNED V +0246; C; 0247; # LATIN CAPITAL LETTER E WITH STROKE +0248; C; 0249; # LATIN CAPITAL LETTER J WITH STROKE +024A; C; 024B; # LATIN CAPITAL LETTER SMALL Q WITH HOOK TAIL +024C; C; 024D; # LATIN CAPITAL LETTER R WITH STROKE +024E; C; 024F; # LATIN CAPITAL LETTER Y WITH STROKE +0345; C; 03B9; # COMBINING GREEK YPOGEGRAMMENI +0370; C; 0371; # GREEK CAPITAL LETTER HETA +0372; C; 0373; # GREEK CAPITAL LETTER ARCHAIC SAMPI +0376; C; 0377; # GREEK CAPITAL LETTER PAMPHYLIAN DIGAMMA +037F; C; 03F3; # GREEK CAPITAL LETTER YOT +0386; C; 03AC; # GREEK CAPITAL LETTER ALPHA WITH TONOS +0388; C; 03AD; # GREEK CAPITAL LETTER EPSILON WITH TONOS +0389; C; 03AE; # GREEK CAPITAL LETTER ETA WITH TONOS +038A; C; 03AF; # GREEK CAPITAL LETTER IOTA WITH TONOS +038C; C; 03CC; # GREEK CAPITAL LETTER OMICRON WITH TONOS +038E; C; 03CD; # GREEK CAPITAL LETTER UPSILON WITH TONOS +038F; C; 03CE; # GREEK CAPITAL LETTER OMEGA WITH TONOS +0390; F; 03B9 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS +0391; C; 03B1; # GREEK CAPITAL LETTER ALPHA +0392; C; 03B2; # GREEK CAPITAL LETTER BETA +0393; C; 03B3; # GREEK CAPITAL LETTER GAMMA +0394; C; 03B4; # GREEK CAPITAL LETTER DELTA +0395; C; 03B5; # GREEK CAPITAL LETTER EPSILON +0396; C; 03B6; # GREEK CAPITAL LETTER ZETA +0397; C; 03B7; # GREEK CAPITAL LETTER ETA +0398; C; 03B8; # GREEK CAPITAL LETTER THETA +0399; C; 03B9; # GREEK CAPITAL LETTER IOTA +039A; C; 03BA; # GREEK CAPITAL LETTER KAPPA +039B; C; 03BB; # GREEK CAPITAL LETTER LAMDA +039C; C; 03BC; # GREEK CAPITAL LETTER MU +039D; C; 03BD; # GREEK CAPITAL LETTER NU +039E; C; 03BE; # GREEK CAPITAL LETTER XI +039F; C; 03BF; # GREEK CAPITAL LETTER OMICRON +03A0; C; 03C0; # GREEK CAPITAL LETTER PI +03A1; C; 03C1; # GREEK CAPITAL LETTER RHO +03A3; C; 03C3; # GREEK CAPITAL LETTER SIGMA +03A4; C; 03C4; # GREEK CAPITAL LETTER TAU +03A5; C; 03C5; # GREEK CAPITAL LETTER UPSILON +03A6; C; 03C6; # GREEK CAPITAL LETTER PHI +03A7; C; 03C7; # GREEK CAPITAL LETTER CHI +03A8; C; 03C8; # GREEK CAPITAL LETTER PSI +03A9; C; 03C9; # GREEK CAPITAL LETTER OMEGA +03AA; C; 03CA; # GREEK CAPITAL LETTER IOTA WITH DIALYTIKA +03AB; C; 03CB; # GREEK CAPITAL LETTER UPSILON WITH DIALYTIKA +03B0; F; 03C5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS +03C2; C; 03C3; # GREEK SMALL LETTER FINAL SIGMA +03CF; C; 03D7; # GREEK CAPITAL KAI SYMBOL +03D0; C; 03B2; # GREEK BETA SYMBOL +03D1; C; 03B8; # GREEK THETA SYMBOL +03D5; C; 03C6; # GREEK PHI SYMBOL +03D6; C; 03C0; # GREEK PI SYMBOL +03D8; C; 03D9; # GREEK LETTER ARCHAIC KOPPA +03DA; C; 03DB; # GREEK LETTER STIGMA +03DC; C; 03DD; # GREEK LETTER DIGAMMA +03DE; C; 03DF; # GREEK LETTER KOPPA +03E0; C; 03E1; # GREEK LETTER SAMPI +03E2; C; 03E3; # COPTIC CAPITAL LETTER SHEI +03E4; C; 03E5; # COPTIC CAPITAL LETTER FEI +03E6; C; 03E7; # COPTIC CAPITAL LETTER KHEI +03E8; C; 03E9; # COPTIC CAPITAL LETTER HORI +03EA; C; 03EB; # COPTIC CAPITAL LETTER GANGIA +03EC; C; 03ED; # COPTIC CAPITAL LETTER SHIMA +03EE; C; 03EF; # COPTIC CAPITAL LETTER DEI +03F0; C; 03BA; # GREEK KAPPA SYMBOL +03F1; C; 03C1; # GREEK RHO SYMBOL +03F4; C; 03B8; # GREEK CAPITAL THETA SYMBOL +03F5; C; 03B5; # GREEK LUNATE EPSILON SYMBOL +03F7; C; 03F8; # GREEK CAPITAL LETTER SHO +03F9; C; 03F2; # GREEK CAPITAL LUNATE SIGMA SYMBOL +03FA; C; 03FB; # GREEK CAPITAL LETTER SAN +03FD; C; 037B; # GREEK CAPITAL REVERSED LUNATE SIGMA SYMBOL +03FE; C; 037C; # GREEK CAPITAL DOTTED LUNATE SIGMA SYMBOL +03FF; C; 037D; # GREEK CAPITAL REVERSED DOTTED LUNATE SIGMA SYMBOL +0400; C; 0450; # CYRILLIC CAPITAL LETTER IE WITH GRAVE +0401; C; 0451; # CYRILLIC CAPITAL LETTER IO +0402; C; 0452; # CYRILLIC CAPITAL LETTER DJE +0403; C; 0453; # CYRILLIC CAPITAL LETTER GJE +0404; C; 0454; # CYRILLIC CAPITAL LETTER UKRAINIAN IE +0405; C; 0455; # CYRILLIC CAPITAL LETTER DZE +0406; C; 0456; # CYRILLIC CAPITAL LETTER BYELORUSSIAN-UKRAINIAN I +0407; C; 0457; # CYRILLIC CAPITAL LETTER YI +0408; C; 0458; # CYRILLIC CAPITAL LETTER JE +0409; C; 0459; # CYRILLIC CAPITAL LETTER LJE +040A; C; 045A; # CYRILLIC CAPITAL LETTER NJE +040B; C; 045B; # CYRILLIC CAPITAL LETTER TSHE +040C; C; 045C; # CYRILLIC CAPITAL LETTER KJE +040D; C; 045D; # CYRILLIC CAPITAL LETTER I WITH GRAVE +040E; C; 045E; # CYRILLIC CAPITAL LETTER SHORT U +040F; C; 045F; # CYRILLIC CAPITAL LETTER DZHE +0410; C; 0430; # CYRILLIC CAPITAL LETTER A +0411; C; 0431; # CYRILLIC CAPITAL LETTER BE +0412; C; 0432; # CYRILLIC CAPITAL LETTER VE +0413; C; 0433; # CYRILLIC CAPITAL LETTER GHE +0414; C; 0434; # CYRILLIC CAPITAL LETTER DE +0415; C; 0435; # CYRILLIC CAPITAL LETTER IE +0416; C; 0436; # CYRILLIC CAPITAL LETTER ZHE +0417; C; 0437; # CYRILLIC CAPITAL LETTER ZE +0418; C; 0438; # CYRILLIC CAPITAL LETTER I +0419; C; 0439; # CYRILLIC CAPITAL LETTER SHORT I +041A; C; 043A; # CYRILLIC CAPITAL LETTER KA +041B; C; 043B; # CYRILLIC CAPITAL LETTER EL +041C; C; 043C; # CYRILLIC CAPITAL LETTER EM +041D; C; 043D; # CYRILLIC CAPITAL LETTER EN +041E; C; 043E; # CYRILLIC CAPITAL LETTER O +041F; C; 043F; # CYRILLIC CAPITAL LETTER PE +0420; C; 0440; # CYRILLIC CAPITAL LETTER ER +0421; C; 0441; # CYRILLIC CAPITAL LETTER ES +0422; C; 0442; # CYRILLIC CAPITAL LETTER TE +0423; C; 0443; # CYRILLIC CAPITAL LETTER U +0424; C; 0444; # CYRILLIC CAPITAL LETTER EF +0425; C; 0445; # CYRILLIC CAPITAL LETTER HA +0426; C; 0446; # CYRILLIC CAPITAL LETTER TSE +0427; C; 0447; # CYRILLIC CAPITAL LETTER CHE +0428; C; 0448; # CYRILLIC CAPITAL LETTER SHA +0429; C; 0449; # CYRILLIC CAPITAL LETTER SHCHA +042A; C; 044A; # CYRILLIC CAPITAL LETTER HARD SIGN +042B; C; 044B; # CYRILLIC CAPITAL LETTER YERU +042C; C; 044C; # CYRILLIC CAPITAL LETTER SOFT SIGN +042D; C; 044D; # CYRILLIC CAPITAL LETTER E +042E; C; 044E; # CYRILLIC CAPITAL LETTER YU +042F; C; 044F; # CYRILLIC CAPITAL LETTER YA +0460; C; 0461; # CYRILLIC CAPITAL LETTER OMEGA +0462; C; 0463; # CYRILLIC CAPITAL LETTER YAT +0464; C; 0465; # CYRILLIC CAPITAL LETTER IOTIFIED E +0466; C; 0467; # CYRILLIC CAPITAL LETTER LITTLE YUS +0468; C; 0469; # CYRILLIC CAPITAL LETTER IOTIFIED LITTLE YUS +046A; C; 046B; # CYRILLIC CAPITAL LETTER BIG YUS +046C; C; 046D; # CYRILLIC CAPITAL LETTER IOTIFIED BIG YUS +046E; C; 046F; # CYRILLIC CAPITAL LETTER KSI +0470; C; 0471; # CYRILLIC CAPITAL LETTER PSI +0472; C; 0473; # CYRILLIC CAPITAL LETTER FITA +0474; C; 0475; # CYRILLIC CAPITAL LETTER IZHITSA +0476; C; 0477; # CYRILLIC CAPITAL LETTER IZHITSA WITH DOUBLE GRAVE ACCENT +0478; C; 0479; # CYRILLIC CAPITAL LETTER UK +047A; C; 047B; # CYRILLIC CAPITAL LETTER ROUND OMEGA +047C; C; 047D; # CYRILLIC CAPITAL LETTER OMEGA WITH TITLO +047E; C; 047F; # CYRILLIC CAPITAL LETTER OT +0480; C; 0481; # CYRILLIC CAPITAL LETTER KOPPA +048A; C; 048B; # CYRILLIC CAPITAL LETTER SHORT I WITH TAIL +048C; C; 048D; # CYRILLIC CAPITAL LETTER SEMISOFT SIGN +048E; C; 048F; # CYRILLIC CAPITAL LETTER ER WITH TICK +0490; C; 0491; # CYRILLIC CAPITAL LETTER GHE WITH UPTURN +0492; C; 0493; # CYRILLIC CAPITAL LETTER GHE WITH STROKE +0494; C; 0495; # CYRILLIC CAPITAL LETTER GHE WITH MIDDLE HOOK +0496; C; 0497; # CYRILLIC CAPITAL LETTER ZHE WITH DESCENDER +0498; C; 0499; # CYRILLIC CAPITAL LETTER ZE WITH DESCENDER +049A; C; 049B; # CYRILLIC CAPITAL LETTER KA WITH DESCENDER +049C; C; 049D; # CYRILLIC CAPITAL LETTER KA WITH VERTICAL STROKE +049E; C; 049F; # CYRILLIC CAPITAL LETTER KA WITH STROKE +04A0; C; 04A1; # CYRILLIC CAPITAL LETTER BASHKIR KA +04A2; C; 04A3; # CYRILLIC CAPITAL LETTER EN WITH DESCENDER +04A4; C; 04A5; # CYRILLIC CAPITAL LIGATURE EN GHE +04A6; C; 04A7; # CYRILLIC CAPITAL LETTER PE WITH MIDDLE HOOK +04A8; C; 04A9; # CYRILLIC CAPITAL LETTER ABKHASIAN HA +04AA; C; 04AB; # CYRILLIC CAPITAL LETTER ES WITH DESCENDER +04AC; C; 04AD; # CYRILLIC CAPITAL LETTER TE WITH DESCENDER +04AE; C; 04AF; # CYRILLIC CAPITAL LETTER STRAIGHT U +04B0; C; 04B1; # CYRILLIC CAPITAL LETTER STRAIGHT U WITH STROKE +04B2; C; 04B3; # CYRILLIC CAPITAL LETTER HA WITH DESCENDER +04B4; C; 04B5; # CYRILLIC CAPITAL LIGATURE TE TSE +04B6; C; 04B7; # CYRILLIC CAPITAL LETTER CHE WITH DESCENDER +04B8; C; 04B9; # CYRILLIC CAPITAL LETTER CHE WITH VERTICAL STROKE +04BA; C; 04BB; # CYRILLIC CAPITAL LETTER SHHA +04BC; C; 04BD; # CYRILLIC CAPITAL LETTER ABKHASIAN CHE +04BE; C; 04BF; # CYRILLIC CAPITAL LETTER ABKHASIAN CHE WITH DESCENDER +04C0; C; 04CF; # CYRILLIC LETTER PALOCHKA +04C1; C; 04C2; # CYRILLIC CAPITAL LETTER ZHE WITH BREVE +04C3; C; 04C4; # CYRILLIC CAPITAL LETTER KA WITH HOOK +04C5; C; 04C6; # CYRILLIC CAPITAL LETTER EL WITH TAIL +04C7; C; 04C8; # CYRILLIC CAPITAL LETTER EN WITH HOOK +04C9; C; 04CA; # CYRILLIC CAPITAL LETTER EN WITH TAIL +04CB; C; 04CC; # CYRILLIC CAPITAL LETTER KHAKASSIAN CHE +04CD; C; 04CE; # CYRILLIC CAPITAL LETTER EM WITH TAIL +04D0; C; 04D1; # CYRILLIC CAPITAL LETTER A WITH BREVE +04D2; C; 04D3; # CYRILLIC CAPITAL LETTER A WITH DIAERESIS +04D4; C; 04D5; # CYRILLIC CAPITAL LIGATURE A IE +04D6; C; 04D7; # CYRILLIC CAPITAL LETTER IE WITH BREVE +04D8; C; 04D9; # CYRILLIC CAPITAL LETTER SCHWA +04DA; C; 04DB; # CYRILLIC CAPITAL LETTER SCHWA WITH DIAERESIS +04DC; C; 04DD; # CYRILLIC CAPITAL LETTER ZHE WITH DIAERESIS +04DE; C; 04DF; # CYRILLIC CAPITAL LETTER ZE WITH DIAERESIS +04E0; C; 04E1; # CYRILLIC CAPITAL LETTER ABKHASIAN DZE +04E2; C; 04E3; # CYRILLIC CAPITAL LETTER I WITH MACRON +04E4; C; 04E5; # CYRILLIC CAPITAL LETTER I WITH DIAERESIS +04E6; C; 04E7; # CYRILLIC CAPITAL LETTER O WITH DIAERESIS +04E8; C; 04E9; # CYRILLIC CAPITAL LETTER BARRED O +04EA; C; 04EB; # CYRILLIC CAPITAL LETTER BARRED O WITH DIAERESIS +04EC; C; 04ED; # CYRILLIC CAPITAL LETTER E WITH DIAERESIS +04EE; C; 04EF; # CYRILLIC CAPITAL LETTER U WITH MACRON +04F0; C; 04F1; # CYRILLIC CAPITAL LETTER U WITH DIAERESIS +04F2; C; 04F3; # CYRILLIC CAPITAL LETTER U WITH DOUBLE ACUTE +04F4; C; 04F5; # CYRILLIC CAPITAL LETTER CHE WITH DIAERESIS +04F6; C; 04F7; # CYRILLIC CAPITAL LETTER GHE WITH DESCENDER +04F8; C; 04F9; # CYRILLIC CAPITAL LETTER YERU WITH DIAERESIS +04FA; C; 04FB; # CYRILLIC CAPITAL LETTER GHE WITH STROKE AND HOOK +04FC; C; 04FD; # CYRILLIC CAPITAL LETTER HA WITH HOOK +04FE; C; 04FF; # CYRILLIC CAPITAL LETTER HA WITH STROKE +0500; C; 0501; # CYRILLIC CAPITAL LETTER KOMI DE +0502; C; 0503; # CYRILLIC CAPITAL LETTER KOMI DJE +0504; C; 0505; # CYRILLIC CAPITAL LETTER KOMI ZJE +0506; C; 0507; # CYRILLIC CAPITAL LETTER KOMI DZJE +0508; C; 0509; # CYRILLIC CAPITAL LETTER KOMI LJE +050A; C; 050B; # CYRILLIC CAPITAL LETTER KOMI NJE +050C; C; 050D; # CYRILLIC CAPITAL LETTER KOMI SJE +050E; C; 050F; # CYRILLIC CAPITAL LETTER KOMI TJE +0510; C; 0511; # CYRILLIC CAPITAL LETTER REVERSED ZE +0512; C; 0513; # CYRILLIC CAPITAL LETTER EL WITH HOOK +0514; C; 0515; # CYRILLIC CAPITAL LETTER LHA +0516; C; 0517; # CYRILLIC CAPITAL LETTER RHA +0518; C; 0519; # CYRILLIC CAPITAL LETTER YAE +051A; C; 051B; # CYRILLIC CAPITAL LETTER QA +051C; C; 051D; # CYRILLIC CAPITAL LETTER WE +051E; C; 051F; # CYRILLIC CAPITAL LETTER ALEUT KA +0520; C; 0521; # CYRILLIC CAPITAL LETTER EL WITH MIDDLE HOOK +0522; C; 0523; # CYRILLIC CAPITAL LETTER EN WITH MIDDLE HOOK +0524; C; 0525; # CYRILLIC CAPITAL LETTER PE WITH DESCENDER +0526; C; 0527; # CYRILLIC CAPITAL LETTER SHHA WITH DESCENDER +0528; C; 0529; # CYRILLIC CAPITAL LETTER EN WITH LEFT HOOK +052A; C; 052B; # CYRILLIC CAPITAL LETTER DZZHE +052C; C; 052D; # CYRILLIC CAPITAL LETTER DCHE +052E; C; 052F; # CYRILLIC CAPITAL LETTER EL WITH DESCENDER +0531; C; 0561; # ARMENIAN CAPITAL LETTER AYB +0532; C; 0562; # ARMENIAN CAPITAL LETTER BEN +0533; C; 0563; # ARMENIAN CAPITAL LETTER GIM +0534; C; 0564; # ARMENIAN CAPITAL LETTER DA +0535; C; 0565; # ARMENIAN CAPITAL LETTER ECH +0536; C; 0566; # ARMENIAN CAPITAL LETTER ZA +0537; C; 0567; # ARMENIAN CAPITAL LETTER EH +0538; C; 0568; # ARMENIAN CAPITAL LETTER ET +0539; C; 0569; # ARMENIAN CAPITAL LETTER TO +053A; C; 056A; # ARMENIAN CAPITAL LETTER ZHE +053B; C; 056B; # ARMENIAN CAPITAL LETTER INI +053C; C; 056C; # ARMENIAN CAPITAL LETTER LIWN +053D; C; 056D; # ARMENIAN CAPITAL LETTER XEH +053E; C; 056E; # ARMENIAN CAPITAL LETTER CA +053F; C; 056F; # ARMENIAN CAPITAL LETTER KEN +0540; C; 0570; # ARMENIAN CAPITAL LETTER HO +0541; C; 0571; # ARMENIAN CAPITAL LETTER JA +0542; C; 0572; # ARMENIAN CAPITAL LETTER GHAD +0543; C; 0573; # ARMENIAN CAPITAL LETTER CHEH +0544; C; 0574; # ARMENIAN CAPITAL LETTER MEN +0545; C; 0575; # ARMENIAN CAPITAL LETTER YI +0546; C; 0576; # ARMENIAN CAPITAL LETTER NOW +0547; C; 0577; # ARMENIAN CAPITAL LETTER SHA +0548; C; 0578; # ARMENIAN CAPITAL LETTER VO +0549; C; 0579; # ARMENIAN CAPITAL LETTER CHA +054A; C; 057A; # ARMENIAN CAPITAL LETTER PEH +054B; C; 057B; # ARMENIAN CAPITAL LETTER JHEH +054C; C; 057C; # ARMENIAN CAPITAL LETTER RA +054D; C; 057D; # ARMENIAN CAPITAL LETTER SEH +054E; C; 057E; # ARMENIAN CAPITAL LETTER VEW +054F; C; 057F; # ARMENIAN CAPITAL LETTER TIWN +0550; C; 0580; # ARMENIAN CAPITAL LETTER REH +0551; C; 0581; # ARMENIAN CAPITAL LETTER CO +0552; C; 0582; # ARMENIAN CAPITAL LETTER YIWN +0553; C; 0583; # ARMENIAN CAPITAL LETTER PIWR +0554; C; 0584; # ARMENIAN CAPITAL LETTER KEH +0555; C; 0585; # ARMENIAN CAPITAL LETTER OH +0556; C; 0586; # ARMENIAN CAPITAL LETTER FEH +0587; F; 0565 0582; # ARMENIAN SMALL LIGATURE ECH YIWN +10A0; C; 2D00; # GEORGIAN CAPITAL LETTER AN +10A1; C; 2D01; # GEORGIAN CAPITAL LETTER BAN +10A2; C; 2D02; # GEORGIAN CAPITAL LETTER GAN +10A3; C; 2D03; # GEORGIAN CAPITAL LETTER DON +10A4; C; 2D04; # GEORGIAN CAPITAL LETTER EN +10A5; C; 2D05; # GEORGIAN CAPITAL LETTER VIN +10A6; C; 2D06; # GEORGIAN CAPITAL LETTER ZEN +10A7; C; 2D07; # GEORGIAN CAPITAL LETTER TAN +10A8; C; 2D08; # GEORGIAN CAPITAL LETTER IN +10A9; C; 2D09; # GEORGIAN CAPITAL LETTER KAN +10AA; C; 2D0A; # GEORGIAN CAPITAL LETTER LAS +10AB; C; 2D0B; # GEORGIAN CAPITAL LETTER MAN +10AC; C; 2D0C; # GEORGIAN CAPITAL LETTER NAR +10AD; C; 2D0D; # GEORGIAN CAPITAL LETTER ON +10AE; C; 2D0E; # GEORGIAN CAPITAL LETTER PAR +10AF; C; 2D0F; # GEORGIAN CAPITAL LETTER ZHAR +10B0; C; 2D10; # GEORGIAN CAPITAL LETTER RAE +10B1; C; 2D11; # GEORGIAN CAPITAL LETTER SAN +10B2; C; 2D12; # GEORGIAN CAPITAL LETTER TAR +10B3; C; 2D13; # GEORGIAN CAPITAL LETTER UN +10B4; C; 2D14; # GEORGIAN CAPITAL LETTER PHAR +10B5; C; 2D15; # GEORGIAN CAPITAL LETTER KHAR +10B6; C; 2D16; # GEORGIAN CAPITAL LETTER GHAN +10B7; C; 2D17; # GEORGIAN CAPITAL LETTER QAR +10B8; C; 2D18; # GEORGIAN CAPITAL LETTER SHIN +10B9; C; 2D19; # GEORGIAN CAPITAL LETTER CHIN +10BA; C; 2D1A; # GEORGIAN CAPITAL LETTER CAN +10BB; C; 2D1B; # GEORGIAN CAPITAL LETTER JIL +10BC; C; 2D1C; # GEORGIAN CAPITAL LETTER CIL +10BD; C; 2D1D; # GEORGIAN CAPITAL LETTER CHAR +10BE; C; 2D1E; # GEORGIAN CAPITAL LETTER XAN +10BF; C; 2D1F; # GEORGIAN CAPITAL LETTER JHAN +10C0; C; 2D20; # GEORGIAN CAPITAL LETTER HAE +10C1; C; 2D21; # GEORGIAN CAPITAL LETTER HE +10C2; C; 2D22; # GEORGIAN CAPITAL LETTER HIE +10C3; C; 2D23; # GEORGIAN CAPITAL LETTER WE +10C4; C; 2D24; # GEORGIAN CAPITAL LETTER HAR +10C5; C; 2D25; # GEORGIAN CAPITAL LETTER HOE +10C7; C; 2D27; # GEORGIAN CAPITAL LETTER YN +10CD; C; 2D2D; # GEORGIAN CAPITAL LETTER AEN +13F8; C; 13F0; # CHEROKEE SMALL LETTER YE +13F9; C; 13F1; # CHEROKEE SMALL LETTER YI +13FA; C; 13F2; # CHEROKEE SMALL LETTER YO +13FB; C; 13F3; # CHEROKEE SMALL LETTER YU +13FC; C; 13F4; # CHEROKEE SMALL LETTER YV +13FD; C; 13F5; # CHEROKEE SMALL LETTER MV +1C80; C; 0432; # CYRILLIC SMALL LETTER ROUNDED VE +1C81; C; 0434; # CYRILLIC SMALL LETTER LONG-LEGGED DE +1C82; C; 043E; # CYRILLIC SMALL LETTER NARROW O +1C83; C; 0441; # CYRILLIC SMALL LETTER WIDE ES +1C84; C; 0442; # CYRILLIC SMALL LETTER TALL TE +1C85; C; 0442; # CYRILLIC SMALL LETTER THREE-LEGGED TE +1C86; C; 044A; # CYRILLIC SMALL LETTER TALL HARD SIGN +1C87; C; 0463; # CYRILLIC SMALL LETTER TALL YAT +1C88; C; A64B; # CYRILLIC SMALL LETTER UNBLENDED UK +1C90; C; 10D0; # GEORGIAN MTAVRULI CAPITAL LETTER AN +1C91; C; 10D1; # GEORGIAN MTAVRULI CAPITAL LETTER BAN +1C92; C; 10D2; # GEORGIAN MTAVRULI CAPITAL LETTER GAN +1C93; C; 10D3; # GEORGIAN MTAVRULI CAPITAL LETTER DON +1C94; C; 10D4; # GEORGIAN MTAVRULI CAPITAL LETTER EN +1C95; C; 10D5; # GEORGIAN MTAVRULI CAPITAL LETTER VIN +1C96; C; 10D6; # GEORGIAN MTAVRULI CAPITAL LETTER ZEN +1C97; C; 10D7; # GEORGIAN MTAVRULI CAPITAL LETTER TAN +1C98; C; 10D8; # GEORGIAN MTAVRULI CAPITAL LETTER IN +1C99; C; 10D9; # GEORGIAN MTAVRULI CAPITAL LETTER KAN +1C9A; C; 10DA; # GEORGIAN MTAVRULI CAPITAL LETTER LAS +1C9B; C; 10DB; # GEORGIAN MTAVRULI CAPITAL LETTER MAN +1C9C; C; 10DC; # GEORGIAN MTAVRULI CAPITAL LETTER NAR +1C9D; C; 10DD; # GEORGIAN MTAVRULI CAPITAL LETTER ON +1C9E; C; 10DE; # GEORGIAN MTAVRULI CAPITAL LETTER PAR +1C9F; C; 10DF; # GEORGIAN MTAVRULI CAPITAL LETTER ZHAR +1CA0; C; 10E0; # GEORGIAN MTAVRULI CAPITAL LETTER RAE +1CA1; C; 10E1; # GEORGIAN MTAVRULI CAPITAL LETTER SAN +1CA2; C; 10E2; # GEORGIAN MTAVRULI CAPITAL LETTER TAR +1CA3; C; 10E3; # GEORGIAN MTAVRULI CAPITAL LETTER UN +1CA4; C; 10E4; # GEORGIAN MTAVRULI CAPITAL LETTER PHAR +1CA5; C; 10E5; # GEORGIAN MTAVRULI CAPITAL LETTER KHAR +1CA6; C; 10E6; # GEORGIAN MTAVRULI CAPITAL LETTER GHAN +1CA7; C; 10E7; # GEORGIAN MTAVRULI CAPITAL LETTER QAR +1CA8; C; 10E8; # GEORGIAN MTAVRULI CAPITAL LETTER SHIN +1CA9; C; 10E9; # GEORGIAN MTAVRULI CAPITAL LETTER CHIN +1CAA; C; 10EA; # GEORGIAN MTAVRULI CAPITAL LETTER CAN +1CAB; C; 10EB; # GEORGIAN MTAVRULI CAPITAL LETTER JIL +1CAC; C; 10EC; # GEORGIAN MTAVRULI CAPITAL LETTER CIL +1CAD; C; 10ED; # GEORGIAN MTAVRULI CAPITAL LETTER CHAR +1CAE; C; 10EE; # GEORGIAN MTAVRULI CAPITAL LETTER XAN +1CAF; C; 10EF; # GEORGIAN MTAVRULI CAPITAL LETTER JHAN +1CB0; C; 10F0; # GEORGIAN MTAVRULI CAPITAL LETTER HAE +1CB1; C; 10F1; # GEORGIAN MTAVRULI CAPITAL LETTER HE +1CB2; C; 10F2; # GEORGIAN MTAVRULI CAPITAL LETTER HIE +1CB3; C; 10F3; # GEORGIAN MTAVRULI CAPITAL LETTER WE +1CB4; C; 10F4; # GEORGIAN MTAVRULI CAPITAL LETTER HAR +1CB5; C; 10F5; # GEORGIAN MTAVRULI CAPITAL LETTER HOE +1CB6; C; 10F6; # GEORGIAN MTAVRULI CAPITAL LETTER FI +1CB7; C; 10F7; # GEORGIAN MTAVRULI CAPITAL LETTER YN +1CB8; C; 10F8; # GEORGIAN MTAVRULI CAPITAL LETTER ELIFI +1CB9; C; 10F9; # GEORGIAN MTAVRULI CAPITAL LETTER TURNED GAN +1CBA; C; 10FA; # GEORGIAN MTAVRULI CAPITAL LETTER AIN +1CBD; C; 10FD; # GEORGIAN MTAVRULI CAPITAL LETTER AEN +1CBE; C; 10FE; # GEORGIAN MTAVRULI CAPITAL LETTER HARD SIGN +1CBF; C; 10FF; # GEORGIAN MTAVRULI CAPITAL LETTER LABIAL SIGN +1E00; C; 1E01; # LATIN CAPITAL LETTER A WITH RING BELOW +1E02; C; 1E03; # LATIN CAPITAL LETTER B WITH DOT ABOVE +1E04; C; 1E05; # LATIN CAPITAL LETTER B WITH DOT BELOW +1E06; C; 1E07; # LATIN CAPITAL LETTER B WITH LINE BELOW +1E08; C; 1E09; # LATIN CAPITAL LETTER C WITH CEDILLA AND ACUTE +1E0A; C; 1E0B; # LATIN CAPITAL LETTER D WITH DOT ABOVE +1E0C; C; 1E0D; # LATIN CAPITAL LETTER D WITH DOT BELOW +1E0E; C; 1E0F; # LATIN CAPITAL LETTER D WITH LINE BELOW +1E10; C; 1E11; # LATIN CAPITAL LETTER D WITH CEDILLA +1E12; C; 1E13; # LATIN CAPITAL LETTER D WITH CIRCUMFLEX BELOW +1E14; C; 1E15; # LATIN CAPITAL LETTER E WITH MACRON AND GRAVE +1E16; C; 1E17; # LATIN CAPITAL LETTER E WITH MACRON AND ACUTE +1E18; C; 1E19; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX BELOW +1E1A; C; 1E1B; # LATIN CAPITAL LETTER E WITH TILDE BELOW +1E1C; C; 1E1D; # LATIN CAPITAL LETTER E WITH CEDILLA AND BREVE +1E1E; C; 1E1F; # LATIN CAPITAL LETTER F WITH DOT ABOVE +1E20; C; 1E21; # LATIN CAPITAL LETTER G WITH MACRON +1E22; C; 1E23; # LATIN CAPITAL LETTER H WITH DOT ABOVE +1E24; C; 1E25; # LATIN CAPITAL LETTER H WITH DOT BELOW +1E26; C; 1E27; # LATIN CAPITAL LETTER H WITH DIAERESIS +1E28; C; 1E29; # LATIN CAPITAL LETTER H WITH CEDILLA +1E2A; C; 1E2B; # LATIN CAPITAL LETTER H WITH BREVE BELOW +1E2C; C; 1E2D; # LATIN CAPITAL LETTER I WITH TILDE BELOW +1E2E; C; 1E2F; # LATIN CAPITAL LETTER I WITH DIAERESIS AND ACUTE +1E30; C; 1E31; # LATIN CAPITAL LETTER K WITH ACUTE +1E32; C; 1E33; # LATIN CAPITAL LETTER K WITH DOT BELOW +1E34; C; 1E35; # LATIN CAPITAL LETTER K WITH LINE BELOW +1E36; C; 1E37; # LATIN CAPITAL LETTER L WITH DOT BELOW +1E38; C; 1E39; # LATIN CAPITAL LETTER L WITH DOT BELOW AND MACRON +1E3A; C; 1E3B; # LATIN CAPITAL LETTER L WITH LINE BELOW +1E3C; C; 1E3D; # LATIN CAPITAL LETTER L WITH CIRCUMFLEX BELOW +1E3E; C; 1E3F; # LATIN CAPITAL LETTER M WITH ACUTE +1E40; C; 1E41; # LATIN CAPITAL LETTER M WITH DOT ABOVE +1E42; C; 1E43; # LATIN CAPITAL LETTER M WITH DOT BELOW +1E44; C; 1E45; # LATIN CAPITAL LETTER N WITH DOT ABOVE +1E46; C; 1E47; # LATIN CAPITAL LETTER N WITH DOT BELOW +1E48; C; 1E49; # LATIN CAPITAL LETTER N WITH LINE BELOW +1E4A; C; 1E4B; # LATIN CAPITAL LETTER N WITH CIRCUMFLEX BELOW +1E4C; C; 1E4D; # LATIN CAPITAL LETTER O WITH TILDE AND ACUTE +1E4E; C; 1E4F; # LATIN CAPITAL LETTER O WITH TILDE AND DIAERESIS +1E50; C; 1E51; # LATIN CAPITAL LETTER O WITH MACRON AND GRAVE +1E52; C; 1E53; # LATIN CAPITAL LETTER O WITH MACRON AND ACUTE +1E54; C; 1E55; # LATIN CAPITAL LETTER P WITH ACUTE +1E56; C; 1E57; # LATIN CAPITAL LETTER P WITH DOT ABOVE +1E58; C; 1E59; # LATIN CAPITAL LETTER R WITH DOT ABOVE +1E5A; C; 1E5B; # LATIN CAPITAL LETTER R WITH DOT BELOW +1E5C; C; 1E5D; # LATIN CAPITAL LETTER R WITH DOT BELOW AND MACRON +1E5E; C; 1E5F; # LATIN CAPITAL LETTER R WITH LINE BELOW +1E60; C; 1E61; # LATIN CAPITAL LETTER S WITH DOT ABOVE +1E62; C; 1E63; # LATIN CAPITAL LETTER S WITH DOT BELOW +1E64; C; 1E65; # LATIN CAPITAL LETTER S WITH ACUTE AND DOT ABOVE +1E66; C; 1E67; # LATIN CAPITAL LETTER S WITH CARON AND DOT ABOVE +1E68; C; 1E69; # LATIN CAPITAL LETTER S WITH DOT BELOW AND DOT ABOVE +1E6A; C; 1E6B; # LATIN CAPITAL LETTER T WITH DOT ABOVE +1E6C; C; 1E6D; # LATIN CAPITAL LETTER T WITH DOT BELOW +1E6E; C; 1E6F; # LATIN CAPITAL LETTER T WITH LINE BELOW +1E70; C; 1E71; # LATIN CAPITAL LETTER T WITH CIRCUMFLEX BELOW +1E72; C; 1E73; # LATIN CAPITAL LETTER U WITH DIAERESIS BELOW +1E74; C; 1E75; # LATIN CAPITAL LETTER U WITH TILDE BELOW +1E76; C; 1E77; # LATIN CAPITAL LETTER U WITH CIRCUMFLEX BELOW +1E78; C; 1E79; # LATIN CAPITAL LETTER U WITH TILDE AND ACUTE +1E7A; C; 1E7B; # LATIN CAPITAL LETTER U WITH MACRON AND DIAERESIS +1E7C; C; 1E7D; # LATIN CAPITAL LETTER V WITH TILDE +1E7E; C; 1E7F; # LATIN CAPITAL LETTER V WITH DOT BELOW +1E80; C; 1E81; # LATIN CAPITAL LETTER W WITH GRAVE +1E82; C; 1E83; # LATIN CAPITAL LETTER W WITH ACUTE +1E84; C; 1E85; # LATIN CAPITAL LETTER W WITH DIAERESIS +1E86; C; 1E87; # LATIN CAPITAL LETTER W WITH DOT ABOVE +1E88; C; 1E89; # LATIN CAPITAL LETTER W WITH DOT BELOW +1E8A; C; 1E8B; # LATIN CAPITAL LETTER X WITH DOT ABOVE +1E8C; C; 1E8D; # LATIN CAPITAL LETTER X WITH DIAERESIS +1E8E; C; 1E8F; # LATIN CAPITAL LETTER Y WITH DOT ABOVE +1E90; C; 1E91; # LATIN CAPITAL LETTER Z WITH CIRCUMFLEX +1E92; C; 1E93; # LATIN CAPITAL LETTER Z WITH DOT BELOW +1E94; C; 1E95; # LATIN CAPITAL LETTER Z WITH LINE BELOW +1E96; F; 0068 0331; # LATIN SMALL LETTER H WITH LINE BELOW +1E97; F; 0074 0308; # LATIN SMALL LETTER T WITH DIAERESIS +1E98; F; 0077 030A; # LATIN SMALL LETTER W WITH RING ABOVE +1E99; F; 0079 030A; # LATIN SMALL LETTER Y WITH RING ABOVE +1E9A; F; 0061 02BE; # LATIN SMALL LETTER A WITH RIGHT HALF RING +1E9B; C; 1E61; # LATIN SMALL LETTER LONG S WITH DOT ABOVE +1E9E; F; 0073 0073; # LATIN CAPITAL LETTER SHARP S +1E9E; S; 00DF; # LATIN CAPITAL LETTER SHARP S +1EA0; C; 1EA1; # LATIN CAPITAL LETTER A WITH DOT BELOW +1EA2; C; 1EA3; # LATIN CAPITAL LETTER A WITH HOOK ABOVE +1EA4; C; 1EA5; # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND ACUTE +1EA6; C; 1EA7; # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND GRAVE +1EA8; C; 1EA9; # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND HOOK ABOVE +1EAA; C; 1EAB; # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND TILDE +1EAC; C; 1EAD; # LATIN CAPITAL LETTER A WITH CIRCUMFLEX AND DOT BELOW +1EAE; C; 1EAF; # LATIN CAPITAL LETTER A WITH BREVE AND ACUTE +1EB0; C; 1EB1; # LATIN CAPITAL LETTER A WITH BREVE AND GRAVE +1EB2; C; 1EB3; # LATIN CAPITAL LETTER A WITH BREVE AND HOOK ABOVE +1EB4; C; 1EB5; # LATIN CAPITAL LETTER A WITH BREVE AND TILDE +1EB6; C; 1EB7; # LATIN CAPITAL LETTER A WITH BREVE AND DOT BELOW +1EB8; C; 1EB9; # LATIN CAPITAL LETTER E WITH DOT BELOW +1EBA; C; 1EBB; # LATIN CAPITAL LETTER E WITH HOOK ABOVE +1EBC; C; 1EBD; # LATIN CAPITAL LETTER E WITH TILDE +1EBE; C; 1EBF; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND ACUTE +1EC0; C; 1EC1; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND GRAVE +1EC2; C; 1EC3; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND HOOK ABOVE +1EC4; C; 1EC5; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND TILDE +1EC6; C; 1EC7; # LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND DOT BELOW +1EC8; C; 1EC9; # LATIN CAPITAL LETTER I WITH HOOK ABOVE +1ECA; C; 1ECB; # LATIN CAPITAL LETTER I WITH DOT BELOW +1ECC; C; 1ECD; # LATIN CAPITAL LETTER O WITH DOT BELOW +1ECE; C; 1ECF; # LATIN CAPITAL LETTER O WITH HOOK ABOVE +1ED0; C; 1ED1; # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND ACUTE +1ED2; C; 1ED3; # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND GRAVE +1ED4; C; 1ED5; # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND HOOK ABOVE +1ED6; C; 1ED7; # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND TILDE +1ED8; C; 1ED9; # LATIN CAPITAL LETTER O WITH CIRCUMFLEX AND DOT BELOW +1EDA; C; 1EDB; # LATIN CAPITAL LETTER O WITH HORN AND ACUTE +1EDC; C; 1EDD; # LATIN CAPITAL LETTER O WITH HORN AND GRAVE +1EDE; C; 1EDF; # LATIN CAPITAL LETTER O WITH HORN AND HOOK ABOVE +1EE0; C; 1EE1; # LATIN CAPITAL LETTER O WITH HORN AND TILDE +1EE2; C; 1EE3; # LATIN CAPITAL LETTER O WITH HORN AND DOT BELOW +1EE4; C; 1EE5; # LATIN CAPITAL LETTER U WITH DOT BELOW +1EE6; C; 1EE7; # LATIN CAPITAL LETTER U WITH HOOK ABOVE +1EE8; C; 1EE9; # LATIN CAPITAL LETTER U WITH HORN AND ACUTE +1EEA; C; 1EEB; # LATIN CAPITAL LETTER U WITH HORN AND GRAVE +1EEC; C; 1EED; # LATIN CAPITAL LETTER U WITH HORN AND HOOK ABOVE +1EEE; C; 1EEF; # LATIN CAPITAL LETTER U WITH HORN AND TILDE +1EF0; C; 1EF1; # LATIN CAPITAL LETTER U WITH HORN AND DOT BELOW +1EF2; C; 1EF3; # LATIN CAPITAL LETTER Y WITH GRAVE +1EF4; C; 1EF5; # LATIN CAPITAL LETTER Y WITH DOT BELOW +1EF6; C; 1EF7; # LATIN CAPITAL LETTER Y WITH HOOK ABOVE +1EF8; C; 1EF9; # LATIN CAPITAL LETTER Y WITH TILDE +1EFA; C; 1EFB; # LATIN CAPITAL LETTER MIDDLE-WELSH LL +1EFC; C; 1EFD; # LATIN CAPITAL LETTER MIDDLE-WELSH V +1EFE; C; 1EFF; # LATIN CAPITAL LETTER Y WITH LOOP +1F08; C; 1F00; # GREEK CAPITAL LETTER ALPHA WITH PSILI +1F09; C; 1F01; # GREEK CAPITAL LETTER ALPHA WITH DASIA +1F0A; C; 1F02; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA +1F0B; C; 1F03; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA +1F0C; C; 1F04; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA +1F0D; C; 1F05; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA +1F0E; C; 1F06; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI +1F0F; C; 1F07; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI +1F18; C; 1F10; # GREEK CAPITAL LETTER EPSILON WITH PSILI +1F19; C; 1F11; # GREEK CAPITAL LETTER EPSILON WITH DASIA +1F1A; C; 1F12; # GREEK CAPITAL LETTER EPSILON WITH PSILI AND VARIA +1F1B; C; 1F13; # GREEK CAPITAL LETTER EPSILON WITH DASIA AND VARIA +1F1C; C; 1F14; # GREEK CAPITAL LETTER EPSILON WITH PSILI AND OXIA +1F1D; C; 1F15; # GREEK CAPITAL LETTER EPSILON WITH DASIA AND OXIA +1F28; C; 1F20; # GREEK CAPITAL LETTER ETA WITH PSILI +1F29; C; 1F21; # GREEK CAPITAL LETTER ETA WITH DASIA +1F2A; C; 1F22; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA +1F2B; C; 1F23; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA +1F2C; C; 1F24; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA +1F2D; C; 1F25; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA +1F2E; C; 1F26; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI +1F2F; C; 1F27; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI +1F38; C; 1F30; # GREEK CAPITAL LETTER IOTA WITH PSILI +1F39; C; 1F31; # GREEK CAPITAL LETTER IOTA WITH DASIA +1F3A; C; 1F32; # GREEK CAPITAL LETTER IOTA WITH PSILI AND VARIA +1F3B; C; 1F33; # GREEK CAPITAL LETTER IOTA WITH DASIA AND VARIA +1F3C; C; 1F34; # GREEK CAPITAL LETTER IOTA WITH PSILI AND OXIA +1F3D; C; 1F35; # GREEK CAPITAL LETTER IOTA WITH DASIA AND OXIA +1F3E; C; 1F36; # GREEK CAPITAL LETTER IOTA WITH PSILI AND PERISPOMENI +1F3F; C; 1F37; # GREEK CAPITAL LETTER IOTA WITH DASIA AND PERISPOMENI +1F48; C; 1F40; # GREEK CAPITAL LETTER OMICRON WITH PSILI +1F49; C; 1F41; # GREEK CAPITAL LETTER OMICRON WITH DASIA +1F4A; C; 1F42; # GREEK CAPITAL LETTER OMICRON WITH PSILI AND VARIA +1F4B; C; 1F43; # GREEK CAPITAL LETTER OMICRON WITH DASIA AND VARIA +1F4C; C; 1F44; # GREEK CAPITAL LETTER OMICRON WITH PSILI AND OXIA +1F4D; C; 1F45; # GREEK CAPITAL LETTER OMICRON WITH DASIA AND OXIA +1F50; F; 03C5 0313; # GREEK SMALL LETTER UPSILON WITH PSILI +1F52; F; 03C5 0313 0300; # GREEK SMALL LETTER UPSILON WITH PSILI AND VARIA +1F54; F; 03C5 0313 0301; # GREEK SMALL LETTER UPSILON WITH PSILI AND OXIA +1F56; F; 03C5 0313 0342; # GREEK SMALL LETTER UPSILON WITH PSILI AND PERISPOMENI +1F59; C; 1F51; # GREEK CAPITAL LETTER UPSILON WITH DASIA +1F5B; C; 1F53; # GREEK CAPITAL LETTER UPSILON WITH DASIA AND VARIA +1F5D; C; 1F55; # GREEK CAPITAL LETTER UPSILON WITH DASIA AND OXIA +1F5F; C; 1F57; # GREEK CAPITAL LETTER UPSILON WITH DASIA AND PERISPOMENI +1F68; C; 1F60; # GREEK CAPITAL LETTER OMEGA WITH PSILI +1F69; C; 1F61; # GREEK CAPITAL LETTER OMEGA WITH DASIA +1F6A; C; 1F62; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA +1F6B; C; 1F63; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA +1F6C; C; 1F64; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA +1F6D; C; 1F65; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA +1F6E; C; 1F66; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI +1F6F; C; 1F67; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI +1F80; F; 1F00 03B9; # GREEK SMALL LETTER ALPHA WITH PSILI AND YPOGEGRAMMENI +1F81; F; 1F01 03B9; # GREEK SMALL LETTER ALPHA WITH DASIA AND YPOGEGRAMMENI +1F82; F; 1F02 03B9; # GREEK SMALL LETTER ALPHA WITH PSILI AND VARIA AND YPOGEGRAMMENI +1F83; F; 1F03 03B9; # GREEK SMALL LETTER ALPHA WITH DASIA AND VARIA AND YPOGEGRAMMENI +1F84; F; 1F04 03B9; # GREEK SMALL LETTER ALPHA WITH PSILI AND OXIA AND YPOGEGRAMMENI +1F85; F; 1F05 03B9; # GREEK SMALL LETTER ALPHA WITH DASIA AND OXIA AND YPOGEGRAMMENI +1F86; F; 1F06 03B9; # GREEK SMALL LETTER ALPHA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI +1F87; F; 1F07 03B9; # GREEK SMALL LETTER ALPHA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI +1F88; F; 1F00 03B9; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI +1F88; S; 1F80; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PROSGEGRAMMENI +1F89; F; 1F01 03B9; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI +1F89; S; 1F81; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PROSGEGRAMMENI +1F8A; F; 1F02 03B9; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI +1F8A; S; 1F82; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND VARIA AND PROSGEGRAMMENI +1F8B; F; 1F03 03B9; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI +1F8B; S; 1F83; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND VARIA AND PROSGEGRAMMENI +1F8C; F; 1F04 03B9; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI +1F8C; S; 1F84; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND OXIA AND PROSGEGRAMMENI +1F8D; F; 1F05 03B9; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA AND PROSGEGRAMMENI +1F8D; S; 1F85; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND OXIA AND PROSGEGRAMMENI +1F8E; F; 1F06 03B9; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI +1F8E; S; 1F86; # GREEK CAPITAL LETTER ALPHA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI +1F8F; F; 1F07 03B9; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI +1F8F; S; 1F87; # GREEK CAPITAL LETTER ALPHA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI +1F90; F; 1F20 03B9; # GREEK SMALL LETTER ETA WITH PSILI AND YPOGEGRAMMENI +1F91; F; 1F21 03B9; # GREEK SMALL LETTER ETA WITH DASIA AND YPOGEGRAMMENI +1F92; F; 1F22 03B9; # GREEK SMALL LETTER ETA WITH PSILI AND VARIA AND YPOGEGRAMMENI +1F93; F; 1F23 03B9; # GREEK SMALL LETTER ETA WITH DASIA AND VARIA AND YPOGEGRAMMENI +1F94; F; 1F24 03B9; # GREEK SMALL LETTER ETA WITH PSILI AND OXIA AND YPOGEGRAMMENI +1F95; F; 1F25 03B9; # GREEK SMALL LETTER ETA WITH DASIA AND OXIA AND YPOGEGRAMMENI +1F96; F; 1F26 03B9; # GREEK SMALL LETTER ETA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI +1F97; F; 1F27 03B9; # GREEK SMALL LETTER ETA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI +1F98; F; 1F20 03B9; # GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI +1F98; S; 1F90; # GREEK CAPITAL LETTER ETA WITH PSILI AND PROSGEGRAMMENI +1F99; F; 1F21 03B9; # GREEK CAPITAL LETTER ETA WITH DASIA AND PROSGEGRAMMENI +1F99; S; 1F91; # GREEK CAPITAL LETTER ETA WITH DASIA AND PROSGEGRAMMENI +1F9A; F; 1F22 03B9; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA AND PROSGEGRAMMENI +1F9A; S; 1F92; # GREEK CAPITAL LETTER ETA WITH PSILI AND VARIA AND PROSGEGRAMMENI +1F9B; F; 1F23 03B9; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA AND PROSGEGRAMMENI +1F9B; S; 1F93; # GREEK CAPITAL LETTER ETA WITH DASIA AND VARIA AND PROSGEGRAMMENI +1F9C; F; 1F24 03B9; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA AND PROSGEGRAMMENI +1F9C; S; 1F94; # GREEK CAPITAL LETTER ETA WITH PSILI AND OXIA AND PROSGEGRAMMENI +1F9D; F; 1F25 03B9; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA AND PROSGEGRAMMENI +1F9D; S; 1F95; # GREEK CAPITAL LETTER ETA WITH DASIA AND OXIA AND PROSGEGRAMMENI +1F9E; F; 1F26 03B9; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI +1F9E; S; 1F96; # GREEK CAPITAL LETTER ETA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI +1F9F; F; 1F27 03B9; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI +1F9F; S; 1F97; # GREEK CAPITAL LETTER ETA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI +1FA0; F; 1F60 03B9; # GREEK SMALL LETTER OMEGA WITH PSILI AND YPOGEGRAMMENI +1FA1; F; 1F61 03B9; # GREEK SMALL LETTER OMEGA WITH DASIA AND YPOGEGRAMMENI +1FA2; F; 1F62 03B9; # GREEK SMALL LETTER OMEGA WITH PSILI AND VARIA AND YPOGEGRAMMENI +1FA3; F; 1F63 03B9; # GREEK SMALL LETTER OMEGA WITH DASIA AND VARIA AND YPOGEGRAMMENI +1FA4; F; 1F64 03B9; # GREEK SMALL LETTER OMEGA WITH PSILI AND OXIA AND YPOGEGRAMMENI +1FA5; F; 1F65 03B9; # GREEK SMALL LETTER OMEGA WITH DASIA AND OXIA AND YPOGEGRAMMENI +1FA6; F; 1F66 03B9; # GREEK SMALL LETTER OMEGA WITH PSILI AND PERISPOMENI AND YPOGEGRAMMENI +1FA7; F; 1F67 03B9; # GREEK SMALL LETTER OMEGA WITH DASIA AND PERISPOMENI AND YPOGEGRAMMENI +1FA8; F; 1F60 03B9; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI +1FA8; S; 1FA0; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PROSGEGRAMMENI +1FA9; F; 1F61 03B9; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PROSGEGRAMMENI +1FA9; S; 1FA1; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PROSGEGRAMMENI +1FAA; F; 1F62 03B9; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA AND PROSGEGRAMMENI +1FAA; S; 1FA2; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND VARIA AND PROSGEGRAMMENI +1FAB; F; 1F63 03B9; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA AND PROSGEGRAMMENI +1FAB; S; 1FA3; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND VARIA AND PROSGEGRAMMENI +1FAC; F; 1F64 03B9; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA AND PROSGEGRAMMENI +1FAC; S; 1FA4; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND OXIA AND PROSGEGRAMMENI +1FAD; F; 1F65 03B9; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA AND PROSGEGRAMMENI +1FAD; S; 1FA5; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND OXIA AND PROSGEGRAMMENI +1FAE; F; 1F66 03B9; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI +1FAE; S; 1FA6; # GREEK CAPITAL LETTER OMEGA WITH PSILI AND PERISPOMENI AND PROSGEGRAMMENI +1FAF; F; 1F67 03B9; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI +1FAF; S; 1FA7; # GREEK CAPITAL LETTER OMEGA WITH DASIA AND PERISPOMENI AND PROSGEGRAMMENI +1FB2; F; 1F70 03B9; # GREEK SMALL LETTER ALPHA WITH VARIA AND YPOGEGRAMMENI +1FB3; F; 03B1 03B9; # GREEK SMALL LETTER ALPHA WITH YPOGEGRAMMENI +1FB4; F; 03AC 03B9; # GREEK SMALL LETTER ALPHA WITH OXIA AND YPOGEGRAMMENI +1FB6; F; 03B1 0342; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI +1FB7; F; 03B1 0342 03B9; # GREEK SMALL LETTER ALPHA WITH PERISPOMENI AND YPOGEGRAMMENI +1FB8; C; 1FB0; # GREEK CAPITAL LETTER ALPHA WITH VRACHY +1FB9; C; 1FB1; # GREEK CAPITAL LETTER ALPHA WITH MACRON +1FBA; C; 1F70; # GREEK CAPITAL LETTER ALPHA WITH VARIA +1FBB; C; 1F71; # GREEK CAPITAL LETTER ALPHA WITH OXIA +1FBC; F; 03B1 03B9; # GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI +1FBC; S; 1FB3; # GREEK CAPITAL LETTER ALPHA WITH PROSGEGRAMMENI +1FBE; C; 03B9; # GREEK PROSGEGRAMMENI +1FC2; F; 1F74 03B9; # GREEK SMALL LETTER ETA WITH VARIA AND YPOGEGRAMMENI +1FC3; F; 03B7 03B9; # GREEK SMALL LETTER ETA WITH YPOGEGRAMMENI +1FC4; F; 03AE 03B9; # GREEK SMALL LETTER ETA WITH OXIA AND YPOGEGRAMMENI +1FC6; F; 03B7 0342; # GREEK SMALL LETTER ETA WITH PERISPOMENI +1FC7; F; 03B7 0342 03B9; # GREEK SMALL LETTER ETA WITH PERISPOMENI AND YPOGEGRAMMENI +1FC8; C; 1F72; # GREEK CAPITAL LETTER EPSILON WITH VARIA +1FC9; C; 1F73; # GREEK CAPITAL LETTER EPSILON WITH OXIA +1FCA; C; 1F74; # GREEK CAPITAL LETTER ETA WITH VARIA +1FCB; C; 1F75; # GREEK CAPITAL LETTER ETA WITH OXIA +1FCC; F; 03B7 03B9; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI +1FCC; S; 1FC3; # GREEK CAPITAL LETTER ETA WITH PROSGEGRAMMENI +1FD2; F; 03B9 0308 0300; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND VARIA +1FD3; F; 03B9 0308 0301; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA +1FD6; F; 03B9 0342; # GREEK SMALL LETTER IOTA WITH PERISPOMENI +1FD7; F; 03B9 0308 0342; # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND PERISPOMENI +1FD8; C; 1FD0; # GREEK CAPITAL LETTER IOTA WITH VRACHY +1FD9; C; 1FD1; # GREEK CAPITAL LETTER IOTA WITH MACRON +1FDA; C; 1F76; # GREEK CAPITAL LETTER IOTA WITH VARIA +1FDB; C; 1F77; # GREEK CAPITAL LETTER IOTA WITH OXIA +1FE2; F; 03C5 0308 0300; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND VARIA +1FE3; F; 03C5 0308 0301; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA +1FE4; F; 03C1 0313; # GREEK SMALL LETTER RHO WITH PSILI +1FE6; F; 03C5 0342; # GREEK SMALL LETTER UPSILON WITH PERISPOMENI +1FE7; F; 03C5 0308 0342; # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND PERISPOMENI +1FE8; C; 1FE0; # GREEK CAPITAL LETTER UPSILON WITH VRACHY +1FE9; C; 1FE1; # GREEK CAPITAL LETTER UPSILON WITH MACRON +1FEA; C; 1F7A; # GREEK CAPITAL LETTER UPSILON WITH VARIA +1FEB; C; 1F7B; # GREEK CAPITAL LETTER UPSILON WITH OXIA +1FEC; C; 1FE5; # GREEK CAPITAL LETTER RHO WITH DASIA +1FF2; F; 1F7C 03B9; # GREEK SMALL LETTER OMEGA WITH VARIA AND YPOGEGRAMMENI +1FF3; F; 03C9 03B9; # GREEK SMALL LETTER OMEGA WITH YPOGEGRAMMENI +1FF4; F; 03CE 03B9; # GREEK SMALL LETTER OMEGA WITH OXIA AND YPOGEGRAMMENI +1FF6; F; 03C9 0342; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI +1FF7; F; 03C9 0342 03B9; # GREEK SMALL LETTER OMEGA WITH PERISPOMENI AND YPOGEGRAMMENI +1FF8; C; 1F78; # GREEK CAPITAL LETTER OMICRON WITH VARIA +1FF9; C; 1F79; # GREEK CAPITAL LETTER OMICRON WITH OXIA +1FFA; C; 1F7C; # GREEK CAPITAL LETTER OMEGA WITH VARIA +1FFB; C; 1F7D; # GREEK CAPITAL LETTER OMEGA WITH OXIA +1FFC; F; 03C9 03B9; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI +1FFC; S; 1FF3; # GREEK CAPITAL LETTER OMEGA WITH PROSGEGRAMMENI +2126; C; 03C9; # OHM SIGN +212A; C; 006B; # KELVIN SIGN +212B; C; 00E5; # ANGSTROM SIGN +2132; C; 214E; # TURNED CAPITAL F +2160; C; 2170; # ROMAN NUMERAL ONE +2161; C; 2171; # ROMAN NUMERAL TWO +2162; C; 2172; # ROMAN NUMERAL THREE +2163; C; 2173; # ROMAN NUMERAL FOUR +2164; C; 2174; # ROMAN NUMERAL FIVE +2165; C; 2175; # ROMAN NUMERAL SIX +2166; C; 2176; # ROMAN NUMERAL SEVEN +2167; C; 2177; # ROMAN NUMERAL EIGHT +2168; C; 2178; # ROMAN NUMERAL NINE +2169; C; 2179; # ROMAN NUMERAL TEN +216A; C; 217A; # ROMAN NUMERAL ELEVEN +216B; C; 217B; # ROMAN NUMERAL TWELVE +216C; C; 217C; # ROMAN NUMERAL FIFTY +216D; C; 217D; # ROMAN NUMERAL ONE HUNDRED +216E; C; 217E; # ROMAN NUMERAL FIVE HUNDRED +216F; C; 217F; # ROMAN NUMERAL ONE THOUSAND +2183; C; 2184; # ROMAN NUMERAL REVERSED ONE HUNDRED +24B6; C; 24D0; # CIRCLED LATIN CAPITAL LETTER A +24B7; C; 24D1; # CIRCLED LATIN CAPITAL LETTER B +24B8; C; 24D2; # CIRCLED LATIN CAPITAL LETTER C +24B9; C; 24D3; # CIRCLED LATIN CAPITAL LETTER D +24BA; C; 24D4; # CIRCLED LATIN CAPITAL LETTER E +24BB; C; 24D5; # CIRCLED LATIN CAPITAL LETTER F +24BC; C; 24D6; # CIRCLED LATIN CAPITAL LETTER G +24BD; C; 24D7; # CIRCLED LATIN CAPITAL LETTER H +24BE; C; 24D8; # CIRCLED LATIN CAPITAL LETTER I +24BF; C; 24D9; # CIRCLED LATIN CAPITAL LETTER J +24C0; C; 24DA; # CIRCLED LATIN CAPITAL LETTER K +24C1; C; 24DB; # CIRCLED LATIN CAPITAL LETTER L +24C2; C; 24DC; # CIRCLED LATIN CAPITAL LETTER M +24C3; C; 24DD; # CIRCLED LATIN CAPITAL LETTER N +24C4; C; 24DE; # CIRCLED LATIN CAPITAL LETTER O +24C5; C; 24DF; # CIRCLED LATIN CAPITAL LETTER P +24C6; C; 24E0; # CIRCLED LATIN CAPITAL LETTER Q +24C7; C; 24E1; # CIRCLED LATIN CAPITAL LETTER R +24C8; C; 24E2; # CIRCLED LATIN CAPITAL LETTER S +24C9; C; 24E3; # CIRCLED LATIN CAPITAL LETTER T +24CA; C; 24E4; # CIRCLED LATIN CAPITAL LETTER U +24CB; C; 24E5; # CIRCLED LATIN CAPITAL LETTER V +24CC; C; 24E6; # CIRCLED LATIN CAPITAL LETTER W +24CD; C; 24E7; # CIRCLED LATIN CAPITAL LETTER X +24CE; C; 24E8; # CIRCLED LATIN CAPITAL LETTER Y +24CF; C; 24E9; # CIRCLED LATIN CAPITAL LETTER Z +2C00; C; 2C30; # GLAGOLITIC CAPITAL LETTER AZU +2C01; C; 2C31; # GLAGOLITIC CAPITAL LETTER BUKY +2C02; C; 2C32; # GLAGOLITIC CAPITAL LETTER VEDE +2C03; C; 2C33; # GLAGOLITIC CAPITAL LETTER GLAGOLI +2C04; C; 2C34; # GLAGOLITIC CAPITAL LETTER DOBRO +2C05; C; 2C35; # GLAGOLITIC CAPITAL LETTER YESTU +2C06; C; 2C36; # GLAGOLITIC CAPITAL LETTER ZHIVETE +2C07; C; 2C37; # GLAGOLITIC CAPITAL LETTER DZELO +2C08; C; 2C38; # GLAGOLITIC CAPITAL LETTER ZEMLJA +2C09; C; 2C39; # GLAGOLITIC CAPITAL LETTER IZHE +2C0A; C; 2C3A; # GLAGOLITIC CAPITAL LETTER INITIAL IZHE +2C0B; C; 2C3B; # GLAGOLITIC CAPITAL LETTER I +2C0C; C; 2C3C; # GLAGOLITIC CAPITAL LETTER DJERVI +2C0D; C; 2C3D; # GLAGOLITIC CAPITAL LETTER KAKO +2C0E; C; 2C3E; # GLAGOLITIC CAPITAL LETTER LJUDIJE +2C0F; C; 2C3F; # GLAGOLITIC CAPITAL LETTER MYSLITE +2C10; C; 2C40; # GLAGOLITIC CAPITAL LETTER NASHI +2C11; C; 2C41; # GLAGOLITIC CAPITAL LETTER ONU +2C12; C; 2C42; # GLAGOLITIC CAPITAL LETTER POKOJI +2C13; C; 2C43; # GLAGOLITIC CAPITAL LETTER RITSI +2C14; C; 2C44; # GLAGOLITIC CAPITAL LETTER SLOVO +2C15; C; 2C45; # GLAGOLITIC CAPITAL LETTER TVRIDO +2C16; C; 2C46; # GLAGOLITIC CAPITAL LETTER UKU +2C17; C; 2C47; # GLAGOLITIC CAPITAL LETTER FRITU +2C18; C; 2C48; # GLAGOLITIC CAPITAL LETTER HERU +2C19; C; 2C49; # GLAGOLITIC CAPITAL LETTER OTU +2C1A; C; 2C4A; # GLAGOLITIC CAPITAL LETTER PE +2C1B; C; 2C4B; # GLAGOLITIC CAPITAL LETTER SHTA +2C1C; C; 2C4C; # GLAGOLITIC CAPITAL LETTER TSI +2C1D; C; 2C4D; # GLAGOLITIC CAPITAL LETTER CHRIVI +2C1E; C; 2C4E; # GLAGOLITIC CAPITAL LETTER SHA +2C1F; C; 2C4F; # GLAGOLITIC CAPITAL LETTER YERU +2C20; C; 2C50; # GLAGOLITIC CAPITAL LETTER YERI +2C21; C; 2C51; # GLAGOLITIC CAPITAL LETTER YATI +2C22; C; 2C52; # GLAGOLITIC CAPITAL LETTER SPIDERY HA +2C23; C; 2C53; # GLAGOLITIC CAPITAL LETTER YU +2C24; C; 2C54; # GLAGOLITIC CAPITAL LETTER SMALL YUS +2C25; C; 2C55; # GLAGOLITIC CAPITAL LETTER SMALL YUS WITH TAIL +2C26; C; 2C56; # GLAGOLITIC CAPITAL LETTER YO +2C27; C; 2C57; # GLAGOLITIC CAPITAL LETTER IOTATED SMALL YUS +2C28; C; 2C58; # GLAGOLITIC CAPITAL LETTER BIG YUS +2C29; C; 2C59; # GLAGOLITIC CAPITAL LETTER IOTATED BIG YUS +2C2A; C; 2C5A; # GLAGOLITIC CAPITAL LETTER FITA +2C2B; C; 2C5B; # GLAGOLITIC CAPITAL LETTER IZHITSA +2C2C; C; 2C5C; # GLAGOLITIC CAPITAL LETTER SHTAPIC +2C2D; C; 2C5D; # GLAGOLITIC CAPITAL LETTER TROKUTASTI A +2C2E; C; 2C5E; # GLAGOLITIC CAPITAL LETTER LATINATE MYSLITE +2C2F; C; 2C5F; # GLAGOLITIC CAPITAL LETTER CAUDATE CHRIVI +2C60; C; 2C61; # LATIN CAPITAL LETTER L WITH DOUBLE BAR +2C62; C; 026B; # LATIN CAPITAL LETTER L WITH MIDDLE TILDE +2C63; C; 1D7D; # LATIN CAPITAL LETTER P WITH STROKE +2C64; C; 027D; # LATIN CAPITAL LETTER R WITH TAIL +2C67; C; 2C68; # LATIN CAPITAL LETTER H WITH DESCENDER +2C69; C; 2C6A; # LATIN CAPITAL LETTER K WITH DESCENDER +2C6B; C; 2C6C; # LATIN CAPITAL LETTER Z WITH DESCENDER +2C6D; C; 0251; # LATIN CAPITAL LETTER ALPHA +2C6E; C; 0271; # LATIN CAPITAL LETTER M WITH HOOK +2C6F; C; 0250; # LATIN CAPITAL LETTER TURNED A +2C70; C; 0252; # LATIN CAPITAL LETTER TURNED ALPHA +2C72; C; 2C73; # LATIN CAPITAL LETTER W WITH HOOK +2C75; C; 2C76; # LATIN CAPITAL LETTER HALF H +2C7E; C; 023F; # LATIN CAPITAL LETTER S WITH SWASH TAIL +2C7F; C; 0240; # LATIN CAPITAL LETTER Z WITH SWASH TAIL +2C80; C; 2C81; # COPTIC CAPITAL LETTER ALFA +2C82; C; 2C83; # COPTIC CAPITAL LETTER VIDA +2C84; C; 2C85; # COPTIC CAPITAL LETTER GAMMA +2C86; C; 2C87; # COPTIC CAPITAL LETTER DALDA +2C88; C; 2C89; # COPTIC CAPITAL LETTER EIE +2C8A; C; 2C8B; # COPTIC CAPITAL LETTER SOU +2C8C; C; 2C8D; # COPTIC CAPITAL LETTER ZATA +2C8E; C; 2C8F; # COPTIC CAPITAL LETTER HATE +2C90; C; 2C91; # COPTIC CAPITAL LETTER THETHE +2C92; C; 2C93; # COPTIC CAPITAL LETTER IAUDA +2C94; C; 2C95; # COPTIC CAPITAL LETTER KAPA +2C96; C; 2C97; # COPTIC CAPITAL LETTER LAULA +2C98; C; 2C99; # COPTIC CAPITAL LETTER MI +2C9A; C; 2C9B; # COPTIC CAPITAL LETTER NI +2C9C; C; 2C9D; # COPTIC CAPITAL LETTER KSI +2C9E; C; 2C9F; # COPTIC CAPITAL LETTER O +2CA0; C; 2CA1; # COPTIC CAPITAL LETTER PI +2CA2; C; 2CA3; # COPTIC CAPITAL LETTER RO +2CA4; C; 2CA5; # COPTIC CAPITAL LETTER SIMA +2CA6; C; 2CA7; # COPTIC CAPITAL LETTER TAU +2CA8; C; 2CA9; # COPTIC CAPITAL LETTER UA +2CAA; C; 2CAB; # COPTIC CAPITAL LETTER FI +2CAC; C; 2CAD; # COPTIC CAPITAL LETTER KHI +2CAE; C; 2CAF; # COPTIC CAPITAL LETTER PSI +2CB0; C; 2CB1; # COPTIC CAPITAL LETTER OOU +2CB2; C; 2CB3; # COPTIC CAPITAL LETTER DIALECT-P ALEF +2CB4; C; 2CB5; # COPTIC CAPITAL LETTER OLD COPTIC AIN +2CB6; C; 2CB7; # COPTIC CAPITAL LETTER CRYPTOGRAMMIC EIE +2CB8; C; 2CB9; # COPTIC CAPITAL LETTER DIALECT-P KAPA +2CBA; C; 2CBB; # COPTIC CAPITAL LETTER DIALECT-P NI +2CBC; C; 2CBD; # COPTIC CAPITAL LETTER CRYPTOGRAMMIC NI +2CBE; C; 2CBF; # COPTIC CAPITAL LETTER OLD COPTIC OOU +2CC0; C; 2CC1; # COPTIC CAPITAL LETTER SAMPI +2CC2; C; 2CC3; # COPTIC CAPITAL LETTER CROSSED SHEI +2CC4; C; 2CC5; # COPTIC CAPITAL LETTER OLD COPTIC SHEI +2CC6; C; 2CC7; # COPTIC CAPITAL LETTER OLD COPTIC ESH +2CC8; C; 2CC9; # COPTIC CAPITAL LETTER AKHMIMIC KHEI +2CCA; C; 2CCB; # COPTIC CAPITAL LETTER DIALECT-P HORI +2CCC; C; 2CCD; # COPTIC CAPITAL LETTER OLD COPTIC HORI +2CCE; C; 2CCF; # COPTIC CAPITAL LETTER OLD COPTIC HA +2CD0; C; 2CD1; # COPTIC CAPITAL LETTER L-SHAPED HA +2CD2; C; 2CD3; # COPTIC CAPITAL LETTER OLD COPTIC HEI +2CD4; C; 2CD5; # COPTIC CAPITAL LETTER OLD COPTIC HAT +2CD6; C; 2CD7; # COPTIC CAPITAL LETTER OLD COPTIC GANGIA +2CD8; C; 2CD9; # COPTIC CAPITAL LETTER OLD COPTIC DJA +2CDA; C; 2CDB; # COPTIC CAPITAL LETTER OLD COPTIC SHIMA +2CDC; C; 2CDD; # COPTIC CAPITAL LETTER OLD NUBIAN SHIMA +2CDE; C; 2CDF; # COPTIC CAPITAL LETTER OLD NUBIAN NGI +2CE0; C; 2CE1; # COPTIC CAPITAL LETTER OLD NUBIAN NYI +2CE2; C; 2CE3; # COPTIC CAPITAL LETTER OLD NUBIAN WAU +2CEB; C; 2CEC; # COPTIC CAPITAL LETTER CRYPTOGRAMMIC SHEI +2CED; C; 2CEE; # COPTIC CAPITAL LETTER CRYPTOGRAMMIC GANGIA +2CF2; C; 2CF3; # COPTIC CAPITAL LETTER BOHAIRIC KHEI +A640; C; A641; # CYRILLIC CAPITAL LETTER ZEMLYA +A642; C; A643; # CYRILLIC CAPITAL LETTER DZELO +A644; C; A645; # CYRILLIC CAPITAL LETTER REVERSED DZE +A646; C; A647; # CYRILLIC CAPITAL LETTER IOTA +A648; C; A649; # CYRILLIC CAPITAL LETTER DJERV +A64A; C; A64B; # CYRILLIC CAPITAL LETTER MONOGRAPH UK +A64C; C; A64D; # CYRILLIC CAPITAL LETTER BROAD OMEGA +A64E; C; A64F; # CYRILLIC CAPITAL LETTER NEUTRAL YER +A650; C; A651; # CYRILLIC CAPITAL LETTER YERU WITH BACK YER +A652; C; A653; # CYRILLIC CAPITAL LETTER IOTIFIED YAT +A654; C; A655; # CYRILLIC CAPITAL LETTER REVERSED YU +A656; C; A657; # CYRILLIC CAPITAL LETTER IOTIFIED A +A658; C; A659; # CYRILLIC CAPITAL LETTER CLOSED LITTLE YUS +A65A; C; A65B; # CYRILLIC CAPITAL LETTER BLENDED YUS +A65C; C; A65D; # CYRILLIC CAPITAL LETTER IOTIFIED CLOSED LITTLE YUS +A65E; C; A65F; # CYRILLIC CAPITAL LETTER YN +A660; C; A661; # CYRILLIC CAPITAL LETTER REVERSED TSE +A662; C; A663; # CYRILLIC CAPITAL LETTER SOFT DE +A664; C; A665; # CYRILLIC CAPITAL LETTER SOFT EL +A666; C; A667; # CYRILLIC CAPITAL LETTER SOFT EM +A668; C; A669; # CYRILLIC CAPITAL LETTER MONOCULAR O +A66A; C; A66B; # CYRILLIC CAPITAL LETTER BINOCULAR O +A66C; C; A66D; # CYRILLIC CAPITAL LETTER DOUBLE MONOCULAR O +A680; C; A681; # CYRILLIC CAPITAL LETTER DWE +A682; C; A683; # CYRILLIC CAPITAL LETTER DZWE +A684; C; A685; # CYRILLIC CAPITAL LETTER ZHWE +A686; C; A687; # CYRILLIC CAPITAL LETTER CCHE +A688; C; A689; # CYRILLIC CAPITAL LETTER DZZE +A68A; C; A68B; # CYRILLIC CAPITAL LETTER TE WITH MIDDLE HOOK +A68C; C; A68D; # CYRILLIC CAPITAL LETTER TWE +A68E; C; A68F; # CYRILLIC CAPITAL LETTER TSWE +A690; C; A691; # CYRILLIC CAPITAL LETTER TSSE +A692; C; A693; # CYRILLIC CAPITAL LETTER TCHE +A694; C; A695; # CYRILLIC CAPITAL LETTER HWE +A696; C; A697; # CYRILLIC CAPITAL LETTER SHWE +A698; C; A699; # CYRILLIC CAPITAL LETTER DOUBLE O +A69A; C; A69B; # CYRILLIC CAPITAL LETTER CROSSED O +A722; C; A723; # LATIN CAPITAL LETTER EGYPTOLOGICAL ALEF +A724; C; A725; # LATIN CAPITAL LETTER EGYPTOLOGICAL AIN +A726; C; A727; # LATIN CAPITAL LETTER HENG +A728; C; A729; # LATIN CAPITAL LETTER TZ +A72A; C; A72B; # LATIN CAPITAL LETTER TRESILLO +A72C; C; A72D; # LATIN CAPITAL LETTER CUATRILLO +A72E; C; A72F; # LATIN CAPITAL LETTER CUATRILLO WITH COMMA +A732; C; A733; # LATIN CAPITAL LETTER AA +A734; C; A735; # LATIN CAPITAL LETTER AO +A736; C; A737; # LATIN CAPITAL LETTER AU +A738; C; A739; # LATIN CAPITAL LETTER AV +A73A; C; A73B; # LATIN CAPITAL LETTER AV WITH HORIZONTAL BAR +A73C; C; A73D; # LATIN CAPITAL LETTER AY +A73E; C; A73F; # LATIN CAPITAL LETTER REVERSED C WITH DOT +A740; C; A741; # LATIN CAPITAL LETTER K WITH STROKE +A742; C; A743; # LATIN CAPITAL LETTER K WITH DIAGONAL STROKE +A744; C; A745; # LATIN CAPITAL LETTER K WITH STROKE AND DIAGONAL STROKE +A746; C; A747; # LATIN CAPITAL LETTER BROKEN L +A748; C; A749; # LATIN CAPITAL LETTER L WITH HIGH STROKE +A74A; C; A74B; # LATIN CAPITAL LETTER O WITH LONG STROKE OVERLAY +A74C; C; A74D; # LATIN CAPITAL LETTER O WITH LOOP +A74E; C; A74F; # LATIN CAPITAL LETTER OO +A750; C; A751; # LATIN CAPITAL LETTER P WITH STROKE THROUGH DESCENDER +A752; C; A753; # LATIN CAPITAL LETTER P WITH FLOURISH +A754; C; A755; # LATIN CAPITAL LETTER P WITH SQUIRREL TAIL +A756; C; A757; # LATIN CAPITAL LETTER Q WITH STROKE THROUGH DESCENDER +A758; C; A759; # LATIN CAPITAL LETTER Q WITH DIAGONAL STROKE +A75A; C; A75B; # LATIN CAPITAL LETTER R ROTUNDA +A75C; C; A75D; # LATIN CAPITAL LETTER RUM ROTUNDA +A75E; C; A75F; # LATIN CAPITAL LETTER V WITH DIAGONAL STROKE +A760; C; A761; # LATIN CAPITAL LETTER VY +A762; C; A763; # LATIN CAPITAL LETTER VISIGOTHIC Z +A764; C; A765; # LATIN CAPITAL LETTER THORN WITH STROKE +A766; C; A767; # LATIN CAPITAL LETTER THORN WITH STROKE THROUGH DESCENDER +A768; C; A769; # LATIN CAPITAL LETTER VEND +A76A; C; A76B; # LATIN CAPITAL LETTER ET +A76C; C; A76D; # LATIN CAPITAL LETTER IS +A76E; C; A76F; # LATIN CAPITAL LETTER CON +A779; C; A77A; # LATIN CAPITAL LETTER INSULAR D +A77B; C; A77C; # LATIN CAPITAL LETTER INSULAR F +A77D; C; 1D79; # LATIN CAPITAL LETTER INSULAR G +A77E; C; A77F; # LATIN CAPITAL LETTER TURNED INSULAR G +A780; C; A781; # LATIN CAPITAL LETTER TURNED L +A782; C; A783; # LATIN CAPITAL LETTER INSULAR R +A784; C; A785; # LATIN CAPITAL LETTER INSULAR S +A786; C; A787; # LATIN CAPITAL LETTER INSULAR T +A78B; C; A78C; # LATIN CAPITAL LETTER SALTILLO +A78D; C; 0265; # LATIN CAPITAL LETTER TURNED H +A790; C; A791; # LATIN CAPITAL LETTER N WITH DESCENDER +A792; C; A793; # LATIN CAPITAL LETTER C WITH BAR +A796; C; A797; # LATIN CAPITAL LETTER B WITH FLOURISH +A798; C; A799; # LATIN CAPITAL LETTER F WITH STROKE +A79A; C; A79B; # LATIN CAPITAL LETTER VOLAPUK AE +A79C; C; A79D; # LATIN CAPITAL LETTER VOLAPUK OE +A79E; C; A79F; # LATIN CAPITAL LETTER VOLAPUK UE +A7A0; C; A7A1; # LATIN CAPITAL LETTER G WITH OBLIQUE STROKE +A7A2; C; A7A3; # LATIN CAPITAL LETTER K WITH OBLIQUE STROKE +A7A4; C; A7A5; # LATIN CAPITAL LETTER N WITH OBLIQUE STROKE +A7A6; C; A7A7; # LATIN CAPITAL LETTER R WITH OBLIQUE STROKE +A7A8; C; A7A9; # LATIN CAPITAL LETTER S WITH OBLIQUE STROKE +A7AA; C; 0266; # LATIN CAPITAL LETTER H WITH HOOK +A7AB; C; 025C; # LATIN CAPITAL LETTER REVERSED OPEN E +A7AC; C; 0261; # LATIN CAPITAL LETTER SCRIPT G +A7AD; C; 026C; # LATIN CAPITAL LETTER L WITH BELT +A7AE; C; 026A; # LATIN CAPITAL LETTER SMALL CAPITAL I +A7B0; C; 029E; # LATIN CAPITAL LETTER TURNED K +A7B1; C; 0287; # LATIN CAPITAL LETTER TURNED T +A7B2; C; 029D; # LATIN CAPITAL LETTER J WITH CROSSED-TAIL +A7B3; C; AB53; # LATIN CAPITAL LETTER CHI +A7B4; C; A7B5; # LATIN CAPITAL LETTER BETA +A7B6; C; A7B7; # LATIN CAPITAL LETTER OMEGA +A7B8; C; A7B9; # LATIN CAPITAL LETTER U WITH STROKE +A7BA; C; A7BB; # LATIN CAPITAL LETTER GLOTTAL A +A7BC; C; A7BD; # LATIN CAPITAL LETTER GLOTTAL I +A7BE; C; A7BF; # LATIN CAPITAL LETTER GLOTTAL U +A7C0; C; A7C1; # LATIN CAPITAL LETTER OLD POLISH O +A7C2; C; A7C3; # LATIN CAPITAL LETTER ANGLICANA W +A7C4; C; A794; # LATIN CAPITAL LETTER C WITH PALATAL HOOK +A7C5; C; 0282; # LATIN CAPITAL LETTER S WITH HOOK +A7C6; C; 1D8E; # LATIN CAPITAL LETTER Z WITH PALATAL HOOK +A7C7; C; A7C8; # LATIN CAPITAL LETTER D WITH SHORT STROKE OVERLAY +A7C9; C; A7CA; # LATIN CAPITAL LETTER S WITH SHORT STROKE OVERLAY +A7D0; C; A7D1; # LATIN CAPITAL LETTER CLOSED INSULAR G +A7D6; C; A7D7; # LATIN CAPITAL LETTER MIDDLE SCOTS S +A7D8; C; A7D9; # LATIN CAPITAL LETTER SIGMOID S +A7F5; C; A7F6; # LATIN CAPITAL LETTER REVERSED HALF H +AB70; C; 13A0; # CHEROKEE SMALL LETTER A +AB71; C; 13A1; # CHEROKEE SMALL LETTER E +AB72; C; 13A2; # CHEROKEE SMALL LETTER I +AB73; C; 13A3; # CHEROKEE SMALL LETTER O +AB74; C; 13A4; # CHEROKEE SMALL LETTER U +AB75; C; 13A5; # CHEROKEE SMALL LETTER V +AB76; C; 13A6; # CHEROKEE SMALL LETTER GA +AB77; C; 13A7; # CHEROKEE SMALL LETTER KA +AB78; C; 13A8; # CHEROKEE SMALL LETTER GE +AB79; C; 13A9; # CHEROKEE SMALL LETTER GI +AB7A; C; 13AA; # CHEROKEE SMALL LETTER GO +AB7B; C; 13AB; # CHEROKEE SMALL LETTER GU +AB7C; C; 13AC; # CHEROKEE SMALL LETTER GV +AB7D; C; 13AD; # CHEROKEE SMALL LETTER HA +AB7E; C; 13AE; # CHEROKEE SMALL LETTER HE +AB7F; C; 13AF; # CHEROKEE SMALL LETTER HI +AB80; C; 13B0; # CHEROKEE SMALL LETTER HO +AB81; C; 13B1; # CHEROKEE SMALL LETTER HU +AB82; C; 13B2; # CHEROKEE SMALL LETTER HV +AB83; C; 13B3; # CHEROKEE SMALL LETTER LA +AB84; C; 13B4; # CHEROKEE SMALL LETTER LE +AB85; C; 13B5; # CHEROKEE SMALL LETTER LI +AB86; C; 13B6; # CHEROKEE SMALL LETTER LO +AB87; C; 13B7; # CHEROKEE SMALL LETTER LU +AB88; C; 13B8; # CHEROKEE SMALL LETTER LV +AB89; C; 13B9; # CHEROKEE SMALL LETTER MA +AB8A; C; 13BA; # CHEROKEE SMALL LETTER ME +AB8B; C; 13BB; # CHEROKEE SMALL LETTER MI +AB8C; C; 13BC; # CHEROKEE SMALL LETTER MO +AB8D; C; 13BD; # CHEROKEE SMALL LETTER MU +AB8E; C; 13BE; # CHEROKEE SMALL LETTER NA +AB8F; C; 13BF; # CHEROKEE SMALL LETTER HNA +AB90; C; 13C0; # CHEROKEE SMALL LETTER NAH +AB91; C; 13C1; # CHEROKEE SMALL LETTER NE +AB92; C; 13C2; # CHEROKEE SMALL LETTER NI +AB93; C; 13C3; # CHEROKEE SMALL LETTER NO +AB94; C; 13C4; # CHEROKEE SMALL LETTER NU +AB95; C; 13C5; # CHEROKEE SMALL LETTER NV +AB96; C; 13C6; # CHEROKEE SMALL LETTER QUA +AB97; C; 13C7; # CHEROKEE SMALL LETTER QUE +AB98; C; 13C8; # CHEROKEE SMALL LETTER QUI +AB99; C; 13C9; # CHEROKEE SMALL LETTER QUO +AB9A; C; 13CA; # CHEROKEE SMALL LETTER QUU +AB9B; C; 13CB; # CHEROKEE SMALL LETTER QUV +AB9C; C; 13CC; # CHEROKEE SMALL LETTER SA +AB9D; C; 13CD; # CHEROKEE SMALL LETTER S +AB9E; C; 13CE; # CHEROKEE SMALL LETTER SE +AB9F; C; 13CF; # CHEROKEE SMALL LETTER SI +ABA0; C; 13D0; # CHEROKEE SMALL LETTER SO +ABA1; C; 13D1; # CHEROKEE SMALL LETTER SU +ABA2; C; 13D2; # CHEROKEE SMALL LETTER SV +ABA3; C; 13D3; # CHEROKEE SMALL LETTER DA +ABA4; C; 13D4; # CHEROKEE SMALL LETTER TA +ABA5; C; 13D5; # CHEROKEE SMALL LETTER DE +ABA6; C; 13D6; # CHEROKEE SMALL LETTER TE +ABA7; C; 13D7; # CHEROKEE SMALL LETTER DI +ABA8; C; 13D8; # CHEROKEE SMALL LETTER TI +ABA9; C; 13D9; # CHEROKEE SMALL LETTER DO +ABAA; C; 13DA; # CHEROKEE SMALL LETTER DU +ABAB; C; 13DB; # CHEROKEE SMALL LETTER DV +ABAC; C; 13DC; # CHEROKEE SMALL LETTER DLA +ABAD; C; 13DD; # CHEROKEE SMALL LETTER TLA +ABAE; C; 13DE; # CHEROKEE SMALL LETTER TLE +ABAF; C; 13DF; # CHEROKEE SMALL LETTER TLI +ABB0; C; 13E0; # CHEROKEE SMALL LETTER TLO +ABB1; C; 13E1; # CHEROKEE SMALL LETTER TLU +ABB2; C; 13E2; # CHEROKEE SMALL LETTER TLV +ABB3; C; 13E3; # CHEROKEE SMALL LETTER TSA +ABB4; C; 13E4; # CHEROKEE SMALL LETTER TSE +ABB5; C; 13E5; # CHEROKEE SMALL LETTER TSI +ABB6; C; 13E6; # CHEROKEE SMALL LETTER TSO +ABB7; C; 13E7; # CHEROKEE SMALL LETTER TSU +ABB8; C; 13E8; # CHEROKEE SMALL LETTER TSV +ABB9; C; 13E9; # CHEROKEE SMALL LETTER WA +ABBA; C; 13EA; # CHEROKEE SMALL LETTER WE +ABBB; C; 13EB; # CHEROKEE SMALL LETTER WI +ABBC; C; 13EC; # CHEROKEE SMALL LETTER WO +ABBD; C; 13ED; # CHEROKEE SMALL LETTER WU +ABBE; C; 13EE; # CHEROKEE SMALL LETTER WV +ABBF; C; 13EF; # CHEROKEE SMALL LETTER YA +FB00; F; 0066 0066; # LATIN SMALL LIGATURE FF +FB01; F; 0066 0069; # LATIN SMALL LIGATURE FI +FB02; F; 0066 006C; # LATIN SMALL LIGATURE FL +FB03; F; 0066 0066 0069; # LATIN SMALL LIGATURE FFI +FB04; F; 0066 0066 006C; # LATIN SMALL LIGATURE FFL +FB05; F; 0073 0074; # LATIN SMALL LIGATURE LONG S T +FB06; F; 0073 0074; # LATIN SMALL LIGATURE ST +FB13; F; 0574 0576; # ARMENIAN SMALL LIGATURE MEN NOW +FB14; F; 0574 0565; # ARMENIAN SMALL LIGATURE MEN ECH +FB15; F; 0574 056B; # ARMENIAN SMALL LIGATURE MEN INI +FB16; F; 057E 0576; # ARMENIAN SMALL LIGATURE VEW NOW +FB17; F; 0574 056D; # ARMENIAN SMALL LIGATURE MEN XEH +FF21; C; FF41; # FULLWIDTH LATIN CAPITAL LETTER A +FF22; C; FF42; # FULLWIDTH LATIN CAPITAL LETTER B +FF23; C; FF43; # FULLWIDTH LATIN CAPITAL LETTER C +FF24; C; FF44; # FULLWIDTH LATIN CAPITAL LETTER D +FF25; C; FF45; # FULLWIDTH LATIN CAPITAL LETTER E +FF26; C; FF46; # FULLWIDTH LATIN CAPITAL LETTER F +FF27; C; FF47; # FULLWIDTH LATIN CAPITAL LETTER G +FF28; C; FF48; # FULLWIDTH LATIN CAPITAL LETTER H +FF29; C; FF49; # FULLWIDTH LATIN CAPITAL LETTER I +FF2A; C; FF4A; # FULLWIDTH LATIN CAPITAL LETTER J +FF2B; C; FF4B; # FULLWIDTH LATIN CAPITAL LETTER K +FF2C; C; FF4C; # FULLWIDTH LATIN CAPITAL LETTER L +FF2D; C; FF4D; # FULLWIDTH LATIN CAPITAL LETTER M +FF2E; C; FF4E; # FULLWIDTH LATIN CAPITAL LETTER N +FF2F; C; FF4F; # FULLWIDTH LATIN CAPITAL LETTER O +FF30; C; FF50; # FULLWIDTH LATIN CAPITAL LETTER P +FF31; C; FF51; # FULLWIDTH LATIN CAPITAL LETTER Q +FF32; C; FF52; # FULLWIDTH LATIN CAPITAL LETTER R +FF33; C; FF53; # FULLWIDTH LATIN CAPITAL LETTER S +FF34; C; FF54; # FULLWIDTH LATIN CAPITAL LETTER T +FF35; C; FF55; # FULLWIDTH LATIN CAPITAL LETTER U +FF36; C; FF56; # FULLWIDTH LATIN CAPITAL LETTER V +FF37; C; FF57; # FULLWIDTH LATIN CAPITAL LETTER W +FF38; C; FF58; # FULLWIDTH LATIN CAPITAL LETTER X +FF39; C; FF59; # FULLWIDTH LATIN CAPITAL LETTER Y +FF3A; C; FF5A; # FULLWIDTH LATIN CAPITAL LETTER Z +10400; C; 10428; # DESERET CAPITAL LETTER LONG I +10401; C; 10429; # DESERET CAPITAL LETTER LONG E +10402; C; 1042A; # DESERET CAPITAL LETTER LONG A +10403; C; 1042B; # DESERET CAPITAL LETTER LONG AH +10404; C; 1042C; # DESERET CAPITAL LETTER LONG O +10405; C; 1042D; # DESERET CAPITAL LETTER LONG OO +10406; C; 1042E; # DESERET CAPITAL LETTER SHORT I +10407; C; 1042F; # DESERET CAPITAL LETTER SHORT E +10408; C; 10430; # DESERET CAPITAL LETTER SHORT A +10409; C; 10431; # DESERET CAPITAL LETTER SHORT AH +1040A; C; 10432; # DESERET CAPITAL LETTER SHORT O +1040B; C; 10433; # DESERET CAPITAL LETTER SHORT OO +1040C; C; 10434; # DESERET CAPITAL LETTER AY +1040D; C; 10435; # DESERET CAPITAL LETTER OW +1040E; C; 10436; # DESERET CAPITAL LETTER WU +1040F; C; 10437; # DESERET CAPITAL LETTER YEE +10410; C; 10438; # DESERET CAPITAL LETTER H +10411; C; 10439; # DESERET CAPITAL LETTER PEE +10412; C; 1043A; # DESERET CAPITAL LETTER BEE +10413; C; 1043B; # DESERET CAPITAL LETTER TEE +10414; C; 1043C; # DESERET CAPITAL LETTER DEE +10415; C; 1043D; # DESERET CAPITAL LETTER CHEE +10416; C; 1043E; # DESERET CAPITAL LETTER JEE +10417; C; 1043F; # DESERET CAPITAL LETTER KAY +10418; C; 10440; # DESERET CAPITAL LETTER GAY +10419; C; 10441; # DESERET CAPITAL LETTER EF +1041A; C; 10442; # DESERET CAPITAL LETTER VEE +1041B; C; 10443; # DESERET CAPITAL LETTER ETH +1041C; C; 10444; # DESERET CAPITAL LETTER THEE +1041D; C; 10445; # DESERET CAPITAL LETTER ES +1041E; C; 10446; # DESERET CAPITAL LETTER ZEE +1041F; C; 10447; # DESERET CAPITAL LETTER ESH +10420; C; 10448; # DESERET CAPITAL LETTER ZHEE +10421; C; 10449; # DESERET CAPITAL LETTER ER +10422; C; 1044A; # DESERET CAPITAL LETTER EL +10423; C; 1044B; # DESERET CAPITAL LETTER EM +10424; C; 1044C; # DESERET CAPITAL LETTER EN +10425; C; 1044D; # DESERET CAPITAL LETTER ENG +10426; C; 1044E; # DESERET CAPITAL LETTER OI +10427; C; 1044F; # DESERET CAPITAL LETTER EW +104B0; C; 104D8; # OSAGE CAPITAL LETTER A +104B1; C; 104D9; # OSAGE CAPITAL LETTER AI +104B2; C; 104DA; # OSAGE CAPITAL LETTER AIN +104B3; C; 104DB; # OSAGE CAPITAL LETTER AH +104B4; C; 104DC; # OSAGE CAPITAL LETTER BRA +104B5; C; 104DD; # OSAGE CAPITAL LETTER CHA +104B6; C; 104DE; # OSAGE CAPITAL LETTER EHCHA +104B7; C; 104DF; # OSAGE CAPITAL LETTER E +104B8; C; 104E0; # OSAGE CAPITAL LETTER EIN +104B9; C; 104E1; # OSAGE CAPITAL LETTER HA +104BA; C; 104E2; # OSAGE CAPITAL LETTER HYA +104BB; C; 104E3; # OSAGE CAPITAL LETTER I +104BC; C; 104E4; # OSAGE CAPITAL LETTER KA +104BD; C; 104E5; # OSAGE CAPITAL LETTER EHKA +104BE; C; 104E6; # OSAGE CAPITAL LETTER KYA +104BF; C; 104E7; # OSAGE CAPITAL LETTER LA +104C0; C; 104E8; # OSAGE CAPITAL LETTER MA +104C1; C; 104E9; # OSAGE CAPITAL LETTER NA +104C2; C; 104EA; # OSAGE CAPITAL LETTER O +104C3; C; 104EB; # OSAGE CAPITAL LETTER OIN +104C4; C; 104EC; # OSAGE CAPITAL LETTER PA +104C5; C; 104ED; # OSAGE CAPITAL LETTER EHPA +104C6; C; 104EE; # OSAGE CAPITAL LETTER SA +104C7; C; 104EF; # OSAGE CAPITAL LETTER SHA +104C8; C; 104F0; # OSAGE CAPITAL LETTER TA +104C9; C; 104F1; # OSAGE CAPITAL LETTER EHTA +104CA; C; 104F2; # OSAGE CAPITAL LETTER TSA +104CB; C; 104F3; # OSAGE CAPITAL LETTER EHTSA +104CC; C; 104F4; # OSAGE CAPITAL LETTER TSHA +104CD; C; 104F5; # OSAGE CAPITAL LETTER DHA +104CE; C; 104F6; # OSAGE CAPITAL LETTER U +104CF; C; 104F7; # OSAGE CAPITAL LETTER WA +104D0; C; 104F8; # OSAGE CAPITAL LETTER KHA +104D1; C; 104F9; # OSAGE CAPITAL LETTER GHA +104D2; C; 104FA; # OSAGE CAPITAL LETTER ZA +104D3; C; 104FB; # OSAGE CAPITAL LETTER ZHA +10570; C; 10597; # VITHKUQI CAPITAL LETTER A +10571; C; 10598; # VITHKUQI CAPITAL LETTER BBE +10572; C; 10599; # VITHKUQI CAPITAL LETTER BE +10573; C; 1059A; # VITHKUQI CAPITAL LETTER CE +10574; C; 1059B; # VITHKUQI CAPITAL LETTER CHE +10575; C; 1059C; # VITHKUQI CAPITAL LETTER DE +10576; C; 1059D; # VITHKUQI CAPITAL LETTER DHE +10577; C; 1059E; # VITHKUQI CAPITAL LETTER EI +10578; C; 1059F; # VITHKUQI CAPITAL LETTER E +10579; C; 105A0; # VITHKUQI CAPITAL LETTER FE +1057A; C; 105A1; # VITHKUQI CAPITAL LETTER GA +1057C; C; 105A3; # VITHKUQI CAPITAL LETTER HA +1057D; C; 105A4; # VITHKUQI CAPITAL LETTER HHA +1057E; C; 105A5; # VITHKUQI CAPITAL LETTER I +1057F; C; 105A6; # VITHKUQI CAPITAL LETTER IJE +10580; C; 105A7; # VITHKUQI CAPITAL LETTER JE +10581; C; 105A8; # VITHKUQI CAPITAL LETTER KA +10582; C; 105A9; # VITHKUQI CAPITAL LETTER LA +10583; C; 105AA; # VITHKUQI CAPITAL LETTER LLA +10584; C; 105AB; # VITHKUQI CAPITAL LETTER ME +10585; C; 105AC; # VITHKUQI CAPITAL LETTER NE +10586; C; 105AD; # VITHKUQI CAPITAL LETTER NJE +10587; C; 105AE; # VITHKUQI CAPITAL LETTER O +10588; C; 105AF; # VITHKUQI CAPITAL LETTER PE +10589; C; 105B0; # VITHKUQI CAPITAL LETTER QA +1058A; C; 105B1; # VITHKUQI CAPITAL LETTER RE +1058C; C; 105B3; # VITHKUQI CAPITAL LETTER SE +1058D; C; 105B4; # VITHKUQI CAPITAL LETTER SHE +1058E; C; 105B5; # VITHKUQI CAPITAL LETTER TE +1058F; C; 105B6; # VITHKUQI CAPITAL LETTER THE +10590; C; 105B7; # VITHKUQI CAPITAL LETTER U +10591; C; 105B8; # VITHKUQI CAPITAL LETTER VE +10592; C; 105B9; # VITHKUQI CAPITAL LETTER XE +10594; C; 105BB; # VITHKUQI CAPITAL LETTER Y +10595; C; 105BC; # VITHKUQI CAPITAL LETTER ZE +10C80; C; 10CC0; # OLD HUNGARIAN CAPITAL LETTER A +10C81; C; 10CC1; # OLD HUNGARIAN CAPITAL LETTER AA +10C82; C; 10CC2; # OLD HUNGARIAN CAPITAL LETTER EB +10C83; C; 10CC3; # OLD HUNGARIAN CAPITAL LETTER AMB +10C84; C; 10CC4; # OLD HUNGARIAN CAPITAL LETTER EC +10C85; C; 10CC5; # OLD HUNGARIAN CAPITAL LETTER ENC +10C86; C; 10CC6; # OLD HUNGARIAN CAPITAL LETTER ECS +10C87; C; 10CC7; # OLD HUNGARIAN CAPITAL LETTER ED +10C88; C; 10CC8; # OLD HUNGARIAN CAPITAL LETTER AND +10C89; C; 10CC9; # OLD HUNGARIAN CAPITAL LETTER E +10C8A; C; 10CCA; # OLD HUNGARIAN CAPITAL LETTER CLOSE E +10C8B; C; 10CCB; # OLD HUNGARIAN CAPITAL LETTER EE +10C8C; C; 10CCC; # OLD HUNGARIAN CAPITAL LETTER EF +10C8D; C; 10CCD; # OLD HUNGARIAN CAPITAL LETTER EG +10C8E; C; 10CCE; # OLD HUNGARIAN CAPITAL LETTER EGY +10C8F; C; 10CCF; # OLD HUNGARIAN CAPITAL LETTER EH +10C90; C; 10CD0; # OLD HUNGARIAN CAPITAL LETTER I +10C91; C; 10CD1; # OLD HUNGARIAN CAPITAL LETTER II +10C92; C; 10CD2; # OLD HUNGARIAN CAPITAL LETTER EJ +10C93; C; 10CD3; # OLD HUNGARIAN CAPITAL LETTER EK +10C94; C; 10CD4; # OLD HUNGARIAN CAPITAL LETTER AK +10C95; C; 10CD5; # OLD HUNGARIAN CAPITAL LETTER UNK +10C96; C; 10CD6; # OLD HUNGARIAN CAPITAL LETTER EL +10C97; C; 10CD7; # OLD HUNGARIAN CAPITAL LETTER ELY +10C98; C; 10CD8; # OLD HUNGARIAN CAPITAL LETTER EM +10C99; C; 10CD9; # OLD HUNGARIAN CAPITAL LETTER EN +10C9A; C; 10CDA; # OLD HUNGARIAN CAPITAL LETTER ENY +10C9B; C; 10CDB; # OLD HUNGARIAN CAPITAL LETTER O +10C9C; C; 10CDC; # OLD HUNGARIAN CAPITAL LETTER OO +10C9D; C; 10CDD; # OLD HUNGARIAN CAPITAL LETTER NIKOLSBURG OE +10C9E; C; 10CDE; # OLD HUNGARIAN CAPITAL LETTER RUDIMENTA OE +10C9F; C; 10CDF; # OLD HUNGARIAN CAPITAL LETTER OEE +10CA0; C; 10CE0; # OLD HUNGARIAN CAPITAL LETTER EP +10CA1; C; 10CE1; # OLD HUNGARIAN CAPITAL LETTER EMP +10CA2; C; 10CE2; # OLD HUNGARIAN CAPITAL LETTER ER +10CA3; C; 10CE3; # OLD HUNGARIAN CAPITAL LETTER SHORT ER +10CA4; C; 10CE4; # OLD HUNGARIAN CAPITAL LETTER ES +10CA5; C; 10CE5; # OLD HUNGARIAN CAPITAL LETTER ESZ +10CA6; C; 10CE6; # OLD HUNGARIAN CAPITAL LETTER ET +10CA7; C; 10CE7; # OLD HUNGARIAN CAPITAL LETTER ENT +10CA8; C; 10CE8; # OLD HUNGARIAN CAPITAL LETTER ETY +10CA9; C; 10CE9; # OLD HUNGARIAN CAPITAL LETTER ECH +10CAA; C; 10CEA; # OLD HUNGARIAN CAPITAL LETTER U +10CAB; C; 10CEB; # OLD HUNGARIAN CAPITAL LETTER UU +10CAC; C; 10CEC; # OLD HUNGARIAN CAPITAL LETTER NIKOLSBURG UE +10CAD; C; 10CED; # OLD HUNGARIAN CAPITAL LETTER RUDIMENTA UE +10CAE; C; 10CEE; # OLD HUNGARIAN CAPITAL LETTER EV +10CAF; C; 10CEF; # OLD HUNGARIAN CAPITAL LETTER EZ +10CB0; C; 10CF0; # OLD HUNGARIAN CAPITAL LETTER EZS +10CB1; C; 10CF1; # OLD HUNGARIAN CAPITAL LETTER ENT-SHAPED SIGN +10CB2; C; 10CF2; # OLD HUNGARIAN CAPITAL LETTER US +118A0; C; 118C0; # WARANG CITI CAPITAL LETTER NGAA +118A1; C; 118C1; # WARANG CITI CAPITAL LETTER A +118A2; C; 118C2; # WARANG CITI CAPITAL LETTER WI +118A3; C; 118C3; # WARANG CITI CAPITAL LETTER YU +118A4; C; 118C4; # WARANG CITI CAPITAL LETTER YA +118A5; C; 118C5; # WARANG CITI CAPITAL LETTER YO +118A6; C; 118C6; # WARANG CITI CAPITAL LETTER II +118A7; C; 118C7; # WARANG CITI CAPITAL LETTER UU +118A8; C; 118C8; # WARANG CITI CAPITAL LETTER E +118A9; C; 118C9; # WARANG CITI CAPITAL LETTER O +118AA; C; 118CA; # WARANG CITI CAPITAL LETTER ANG +118AB; C; 118CB; # WARANG CITI CAPITAL LETTER GA +118AC; C; 118CC; # WARANG CITI CAPITAL LETTER KO +118AD; C; 118CD; # WARANG CITI CAPITAL LETTER ENY +118AE; C; 118CE; # WARANG CITI CAPITAL LETTER YUJ +118AF; C; 118CF; # WARANG CITI CAPITAL LETTER UC +118B0; C; 118D0; # WARANG CITI CAPITAL LETTER ENN +118B1; C; 118D1; # WARANG CITI CAPITAL LETTER ODD +118B2; C; 118D2; # WARANG CITI CAPITAL LETTER TTE +118B3; C; 118D3; # WARANG CITI CAPITAL LETTER NUNG +118B4; C; 118D4; # WARANG CITI CAPITAL LETTER DA +118B5; C; 118D5; # WARANG CITI CAPITAL LETTER AT +118B6; C; 118D6; # WARANG CITI CAPITAL LETTER AM +118B7; C; 118D7; # WARANG CITI CAPITAL LETTER BU +118B8; C; 118D8; # WARANG CITI CAPITAL LETTER PU +118B9; C; 118D9; # WARANG CITI CAPITAL LETTER HIYO +118BA; C; 118DA; # WARANG CITI CAPITAL LETTER HOLO +118BB; C; 118DB; # WARANG CITI CAPITAL LETTER HORR +118BC; C; 118DC; # WARANG CITI CAPITAL LETTER HAR +118BD; C; 118DD; # WARANG CITI CAPITAL LETTER SSUU +118BE; C; 118DE; # WARANG CITI CAPITAL LETTER SII +118BF; C; 118DF; # WARANG CITI CAPITAL LETTER VIYO +16E40; C; 16E60; # MEDEFAIDRIN CAPITAL LETTER M +16E41; C; 16E61; # MEDEFAIDRIN CAPITAL LETTER S +16E42; C; 16E62; # MEDEFAIDRIN CAPITAL LETTER V +16E43; C; 16E63; # MEDEFAIDRIN CAPITAL LETTER W +16E44; C; 16E64; # MEDEFAIDRIN CAPITAL LETTER ATIU +16E45; C; 16E65; # MEDEFAIDRIN CAPITAL LETTER Z +16E46; C; 16E66; # MEDEFAIDRIN CAPITAL LETTER KP +16E47; C; 16E67; # MEDEFAIDRIN CAPITAL LETTER P +16E48; C; 16E68; # MEDEFAIDRIN CAPITAL LETTER T +16E49; C; 16E69; # MEDEFAIDRIN CAPITAL LETTER G +16E4A; C; 16E6A; # MEDEFAIDRIN CAPITAL LETTER F +16E4B; C; 16E6B; # MEDEFAIDRIN CAPITAL LETTER I +16E4C; C; 16E6C; # MEDEFAIDRIN CAPITAL LETTER K +16E4D; C; 16E6D; # MEDEFAIDRIN CAPITAL LETTER A +16E4E; C; 16E6E; # MEDEFAIDRIN CAPITAL LETTER J +16E4F; C; 16E6F; # MEDEFAIDRIN CAPITAL LETTER E +16E50; C; 16E70; # MEDEFAIDRIN CAPITAL LETTER B +16E51; C; 16E71; # MEDEFAIDRIN CAPITAL LETTER C +16E52; C; 16E72; # MEDEFAIDRIN CAPITAL LETTER U +16E53; C; 16E73; # MEDEFAIDRIN CAPITAL LETTER YU +16E54; C; 16E74; # MEDEFAIDRIN CAPITAL LETTER L +16E55; C; 16E75; # MEDEFAIDRIN CAPITAL LETTER Q +16E56; C; 16E76; # MEDEFAIDRIN CAPITAL LETTER HP +16E57; C; 16E77; # MEDEFAIDRIN CAPITAL LETTER NY +16E58; C; 16E78; # MEDEFAIDRIN CAPITAL LETTER X +16E59; C; 16E79; # MEDEFAIDRIN CAPITAL LETTER D +16E5A; C; 16E7A; # MEDEFAIDRIN CAPITAL LETTER OE +16E5B; C; 16E7B; # MEDEFAIDRIN CAPITAL LETTER N +16E5C; C; 16E7C; # MEDEFAIDRIN CAPITAL LETTER R +16E5D; C; 16E7D; # MEDEFAIDRIN CAPITAL LETTER O +16E5E; C; 16E7E; # MEDEFAIDRIN CAPITAL LETTER AI +16E5F; C; 16E7F; # MEDEFAIDRIN CAPITAL LETTER Y +1E900; C; 1E922; # ADLAM CAPITAL LETTER ALIF +1E901; C; 1E923; # ADLAM CAPITAL LETTER DAALI +1E902; C; 1E924; # ADLAM CAPITAL LETTER LAAM +1E903; C; 1E925; # ADLAM CAPITAL LETTER MIIM +1E904; C; 1E926; # ADLAM CAPITAL LETTER BA +1E905; C; 1E927; # ADLAM CAPITAL LETTER SINNYIIYHE +1E906; C; 1E928; # ADLAM CAPITAL LETTER PE +1E907; C; 1E929; # ADLAM CAPITAL LETTER BHE +1E908; C; 1E92A; # ADLAM CAPITAL LETTER RA +1E909; C; 1E92B; # ADLAM CAPITAL LETTER E +1E90A; C; 1E92C; # ADLAM CAPITAL LETTER FA +1E90B; C; 1E92D; # ADLAM CAPITAL LETTER I +1E90C; C; 1E92E; # ADLAM CAPITAL LETTER O +1E90D; C; 1E92F; # ADLAM CAPITAL LETTER DHA +1E90E; C; 1E930; # ADLAM CAPITAL LETTER YHE +1E90F; C; 1E931; # ADLAM CAPITAL LETTER WAW +1E910; C; 1E932; # ADLAM CAPITAL LETTER NUN +1E911; C; 1E933; # ADLAM CAPITAL LETTER KAF +1E912; C; 1E934; # ADLAM CAPITAL LETTER YA +1E913; C; 1E935; # ADLAM CAPITAL LETTER U +1E914; C; 1E936; # ADLAM CAPITAL LETTER JIIM +1E915; C; 1E937; # ADLAM CAPITAL LETTER CHI +1E916; C; 1E938; # ADLAM CAPITAL LETTER HA +1E917; C; 1E939; # ADLAM CAPITAL LETTER QAAF +1E918; C; 1E93A; # ADLAM CAPITAL LETTER GA +1E919; C; 1E93B; # ADLAM CAPITAL LETTER NYA +1E91A; C; 1E93C; # ADLAM CAPITAL LETTER TU +1E91B; C; 1E93D; # ADLAM CAPITAL LETTER NHA +1E91C; C; 1E93E; # ADLAM CAPITAL LETTER VA +1E91D; C; 1E93F; # ADLAM CAPITAL LETTER KHA +1E91E; C; 1E940; # ADLAM CAPITAL LETTER GBE +1E91F; C; 1E941; # ADLAM CAPITAL LETTER ZAL +1E920; C; 1E942; # ADLAM CAPITAL LETTER KPO +1E921; C; 1E943; # ADLAM CAPITAL LETTER SHA +# +# EOF diff --git a/src/test/unicode.cpp b/src/test/unicode.cpp index d200b79..b08745a 100644 --- a/src/test/unicode.cpp +++ b/src/test/unicode.cpp @@ -17,6 +17,9 @@ */ #include "jessilib/unicode.hpp" +#include +#include +#include "jessilib/split.hpp" #include "test.hpp" using namespace jessilib; @@ -118,3 +121,351 @@ TEST(UTF32Test, decode_codepoint) { DECODE_CODEPOINT_TEST(U"\U0010FFFF"sv, U'\U0010FFFF', 1U); DECODE_CODEPOINT_TEST(U"\U0001F604"sv, U'\U0001F604', 1U); } + +using char_types = ::testing::Types; +using char_type_combos = ::testing::Types< + std::pair, std::pair, std::pair, std::pair, + std::pair, std::pair, std::pair, std::pair, + std::pair, std::pair, std::pair, std::pair, + std::pair, std::pair, std::pair, std::pair>; + +template +class UnicodeAbcdTest : public ::testing::Test { +public: +}; +TYPED_TEST_SUITE(UnicodeAbcdTest, char_type_combos); + +template +std::basic_string make_str(const char32_t (&in_str)[InLength]) { + std::basic_string result; + auto in_str_end = std::end(in_str) - 1; // ignore null terminator + for (auto itr = std::begin(in_str); itr != in_str_end; ++itr) { + jessilib::encode_codepoint(result, *itr); + } + return result; +} + +/** string_cast */ + +TYPED_TEST(UnicodeAbcdTest, string_cast) { + auto abcd_str = make_str(U"ABCD"); + std::basic_string_view abcd_string_view = abcd_str; + + EXPECT_TRUE(equals(abcd_str, + string_cast(abcd_str))); + EXPECT_TRUE(is_valid(abcd_str)); + + EXPECT_TRUE(equals(abcd_string_view, + string_cast(abcd_string_view))); + EXPECT_TRUE(is_valid(abcd_string_view)); +} + +TEST(UTF8Test, string_view_cast) { + auto abcd_str = make_str(U"ABCD"); + auto view = string_view_cast(abcd_str); + EXPECT_TRUE(equals(view, abcd_str)); +} + +/** equals */ + +TYPED_TEST(UnicodeAbcdTest, equals) { + // TypeParam::first_type == TypeParam::second_type + EXPECT_TRUE(equals(make_str(U"ABCD"), + make_str(U"ABCD"))); + EXPECT_TRUE(equals(make_str(U"abcd"), + make_str(U"abcd"))); + EXPECT_FALSE(equals(make_str(U"ABCD"), + make_str(U"abcd"))); + EXPECT_FALSE(equals(make_str(U"abcd"), + make_str(U"ABCD"))); + EXPECT_FALSE(equals(make_str(U"ABcd"), + make_str(U"abCD"))); +} + +/** equalsi */ + +TYPED_TEST(UnicodeAbcdTest, equalsi) { + // TypeParam::first_type == TypeParam::second_type + EXPECT_TRUE(equalsi(make_str(U"ABCD"), + make_str(U"ABCD"))); + EXPECT_TRUE(equalsi(make_str(U"abcd"), + make_str(U"abcd"))); + EXPECT_TRUE(equalsi(make_str(U"ABCD"), + make_str(U"abcd"))); + EXPECT_TRUE(equalsi(make_str(U"abcd"), + make_str(U"ABCD"))); + EXPECT_TRUE(equalsi(make_str(U"ABcd"), + make_str(U"abCD"))); +} + +/** starts_with */ + +TYPED_TEST(UnicodeAbcdTest, starts_with) { + // TypeParam::first_type == TypeParam::second_type + EXPECT_TRUE(starts_with(make_str(U"ABCD"), + make_str(U"ABCD"))); + EXPECT_TRUE(starts_with(make_str(U"abcd"), + make_str(U"abcd"))); + EXPECT_FALSE(starts_with(make_str(U"ABCD"), + make_str(U"abcd"))); + EXPECT_FALSE(starts_with(make_str(U"abcd"), + make_str(U"ABCD"))); + EXPECT_FALSE(starts_with(make_str(U"ABcd"), + make_str(U"abCD"))); + + // TypeParam::first_type starts_with TypeParam::second_type... (always false) + EXPECT_FALSE(starts_with(make_str(U"ABCD"), + make_str(U"ABCDzz"))); + EXPECT_FALSE(starts_with(make_str(U"abcd"), + make_str(U"abcdzz"))); + EXPECT_FALSE(starts_with(make_str(U"ABCD"), + make_str(U"abcdzz"))); + EXPECT_FALSE(starts_with(make_str(U"abcd"), + make_str(U"ABCDzz"))); + EXPECT_FALSE(starts_with(make_str(U"ABcd"), + make_str(U"abCDzz"))); + + // TypeParam::first_type... starts_with TypeParam::second_type (always same results as first) + EXPECT_TRUE(starts_with(make_str(U"ABCDzz"), + make_str(U"ABCD"))); + EXPECT_TRUE(starts_with(make_str(U"abcdzz"), + make_str(U"abcd"))); + EXPECT_FALSE(starts_with(make_str(U"ABCDzz"), + make_str(U"abcd"))); + EXPECT_FALSE(starts_with(make_str(U"abcdzz"), + make_str(U"ABCD"))); + EXPECT_FALSE(starts_with(make_str(U"ABcdzz"), + make_str(U"abCD"))); +} + +/** starts_withi */ + +TYPED_TEST(UnicodeAbcdTest, starts_withi) { + // TypeParam::first_type == TypeParam::second_type + EXPECT_TRUE(starts_withi(make_str(U"ABCD"), + make_str(U"ABCD"))); + EXPECT_TRUE(starts_withi(make_str(U"abcd"), + make_str(U"abcd"))); + EXPECT_TRUE(starts_withi(make_str(U"ABCD"), + make_str(U"abcd"))); + EXPECT_TRUE(starts_withi(make_str(U"abcd"), + make_str(U"ABCD"))); + EXPECT_TRUE(starts_withi(make_str(U"ABcd"), + make_str(U"abCD"))); + + // TypeParam::first_type starts_with TypeParam::second_type... (always false) + EXPECT_FALSE(starts_withi(make_str(U"ABCD"), + make_str(U"ABCDzz"))); + EXPECT_FALSE(starts_withi(make_str(U"abcd"), + make_str(U"abcdzz"))); + EXPECT_FALSE(starts_withi(make_str(U"ABCD"), + make_str(U"abcdzz"))); + EXPECT_FALSE(starts_withi(make_str(U"abcd"), + make_str(U"ABCDzz"))); + EXPECT_FALSE(starts_withi(make_str(U"ABcd"), + make_str(U"abCDzz"))); + + // TypeParam::first_type... starts_with TypeParam::second_type (always same results as first) + EXPECT_TRUE(starts_withi(make_str(U"ABCDzz"), + make_str(U"ABCD"))); + EXPECT_TRUE(starts_withi(make_str(U"abcdzz"), + make_str(U"abcd"))); + EXPECT_TRUE(starts_withi(make_str(U"ABCDzz"), + make_str(U"abcd"))); + EXPECT_TRUE(starts_withi(make_str(U"abcdzz"), + make_str(U"ABCD"))); + EXPECT_TRUE(starts_withi(make_str(U"ABcdzz"), + make_str(U"abCD"))); + + EXPECT_TRUE(starts_withi(make_str(U"Les Bean del Dallas"), + make_str(U"les"))); + EXPECT_TRUE(starts_withi(make_str(U"Les Bean del Dallas"), + make_str(U"les Bean"))); + EXPECT_FALSE(starts_withi(make_str(U"Les Bean del Dallas"), + make_str(U"del"))); +} + + +/** + * Folding test + */ + +struct folding_info { + uint32_t in_codepoint; + uint32_t out_codepoint; +}; + +constexpr bool operator<(const folding_info& lhs, uint32_t rhs) { + return lhs.in_codepoint < rhs; +} + +constexpr bool operator<(uint32_t lhs, const folding_info& rhs) { + return lhs < rhs.in_codepoint; +} + +// TODO: make this just download from unicode.org (https://www.unicode.org/Public/UCD/latest/ucd/CaseFolding.txt) +std::vector read_CaseFolding_txt(const char* filename = JESSITEST_DATA_DIR "CaseFolding.txt") { + std::vector result; + std::ifstream file{ filename }; + + while (file.good() && !file.eof()) { + std::string line; + std::getline(file, line); + auto split_line = jessilib::split(line, "; "sv); + if (split_line.size() < 3) { + continue; + } + + // From CaseFolding.txt usage; we're doing simple case folding: + // "A. To do a simple case folding, use the mappings with status C + S." + // "B. To do a full case folding, use the mappings with status C + F." + if (split_line[1] == "C" || split_line[1] == "S") { + folding_info info; + std::from_chars(split_line[0].data(), split_line[0].data() + split_line[0].size(), info.in_codepoint, 16); + std::from_chars(split_line[2].data(), split_line[2].data() + split_line[2].size(), info.out_codepoint, 16); + result.push_back(info); + } + //else { + // std::cout << "ignoring: " << line << std::endl; + //} + } + + return result; +} + +// describes a range +struct folding_set { + enum class mode_type { + constant, + alternating, + single + } mode = mode_type::single; + + uint32_t range_start; // inclusive + uint32_t range_end; // inclusive + int64_t diff; // difference between two codepoints + + const char* type() const { + switch (mode) { + case mode_type::constant: + return "constant"; + case mode_type::alternating: + return "alternating"; + case mode_type::single: + return "single"; + default: + break; + } + + return nullptr; + } +}; + +std::vector folding_sets_from_folding_info(const std::vector& in_info) { + std::vector result; + + folding_set current{}; + uint32_t last_match; + for (auto& info : in_info) { + int64_t diff = static_cast(info.out_codepoint) - static_cast(info.in_codepoint); + + if (current.diff == 0) { + // this is a new set; set range_start and diff + current.range_start = info.in_codepoint; + current.diff = diff; + last_match = info.in_codepoint; + continue; + } + + if (current.mode == folding_set::mode_type::single) { + // We don't know what mode we are yet; check if this is constant + if (diff == current.diff + && info.in_codepoint == last_match + 1) { + // diff is same for range_start + 1; must be a constant-diff continuous set + current.mode = folding_set::mode_type::constant; + last_match = info.in_codepoint; + continue; + } + + // Either one-off fold, or alternating set. Check if in_codepoint is last_match + 2 + if (diff == current.diff + && info.in_codepoint == last_match + 2) { + // Looks like an alternating set + current.mode = folding_set::mode_type::alternating; + last_match = info.in_codepoint; + continue; + } + } + + if (current.mode == folding_set::mode_type::constant // For constant offset diffs to continue... + && current.diff == diff // Diff must be the same + && last_match + 1 == info.in_codepoint) { // And current codepoint must be 1 higher than previous + // This matches the current range pattern; just update last_match and carry on + last_match = info.in_codepoint; + continue; + } + + if (current.mode == folding_set::mode_type::alternating // For alternating sets to continue... + && current.diff == diff // Diff must be same + && last_match + 2 == info.in_codepoint) { // And current codepoint must be 2 higher than previous + last_match = info.in_codepoint; + continue; + } + + // This isn't a continuation of the current set; push current and start a new set + current.range_end = last_match; + result.push_back(current); + + current = folding_set{}; + current.range_start = info.in_codepoint; + current.diff = diff; + last_match = info.in_codepoint; + } + + // Push final range + if (current.diff != 0) { + current.range_end = last_match; + result.push_back(current); + } + + return result; +} + +TEST(jess, unicode_case_folding_txt) { + auto folded_codepoints = read_CaseFolding_txt(); + ASSERT_FALSE(folded_codepoints.empty()); + + // Test that every folded codepoint is equal to its folded equivalent + for (auto& folded_codepoint : folded_codepoints) { + EXPECT_EQ(jessilib::fold(folded_codepoint.in_codepoint), folded_codepoint.out_codepoint) + << std::hex << std::uppercase << "lhs: " << std::setw(4) << folded_codepoint.in_codepoint << "; rhs: " << std::setw(8) << folded_codepoint.out_codepoint; + EXPECT_TRUE(jessilib::equalsi(folded_codepoint.in_codepoint, folded_codepoint.out_codepoint)); + } + + // If the above failed, print out what the fold table needs to be replaced with + if (::testing::Test::HasFailure()) { + auto folding_sets = folding_sets_from_folding_info(folded_codepoints); + ASSERT_FALSE(folding_sets.empty()); + for (auto& set : folding_sets) { + // Generate code in the format: { folding_set::mode_type::constant, 0x1234, 0x2345, 1 }, + std::cout << std::hex << std::uppercase << std::setfill('0') << "{ " + << "folding_set::mode_type::" << set.type() + << ", " + << "0x" << std::setw(4) << set.range_start << ", " + << "0x" << std::setw(4) << set.range_end << ", " + << std::dec << set.diff + << " }," << std::endl; + } + + std::cout << "folded_codepoints.size(): " << folded_codepoints.size() << "; folding_sets.size(): " << folding_sets.size() << std::endl; + } + + // Test that every non-folded codepoint in [0, 0xFFFF] is equal to itself; we already tested folded ones above + for (char32_t codepoint = 0; codepoint != 0x10000; ++codepoint) { + bool is_folded = std::binary_search(folded_codepoints.begin(), folded_codepoints.end(), codepoint); + if (!is_folded) { + EXPECT_EQ(codepoint, jessilib::fold(codepoint)); + EXPECT_TRUE(jessilib::equalsi(codepoint, codepoint)); + } + } +}