Description
Thesystem.unicode table is a virtual table that provides information about Unicode characters and their properties(https://unicode-org.github.io/icu/userguide/strings/properties.html). This table is generated on-the-fly.
The property names of Unicode code points from ICU are converted to snake_case for use as column names.
Columns
code_point(String) — The Unicode code point represented as U+XXXX.code_point_value(Int32) — The integer value of the Unicode code point.notation(String) — The character notation (visual representation of the code point).alphabetic(Bool)ascii_hex_digit(Bool)bidi_control(Bool)bidi_mirrored(Bool)dash(Bool)default_ignorable_code_point(Bool)deprecated(Bool)diacritic(Bool)extender(Bool)full_composition_exclusion(Bool)grapheme_base(Bool)grapheme_extend(Bool)grapheme_link(Bool)hex_digit(Bool)hyphen(Bool)id_continue(Bool)id_start(Bool)ideographic(Bool)ids_binary_operator(Bool)ids_trinary_operator(Bool)join_control(Bool)logical_order_exception(Bool)lowercase(Bool)math(Bool)noncharacter_code_point(Bool)quotation_mark(Bool)radical(Bool)soft_dotted(Bool)terminal_punctuation(Bool)unified_ideograph(Bool)uppercase(Bool)white_space(Bool)xid_continue(Bool)xid_start(Bool)case_sensitive(Bool)sentence_terminal(Bool)variation_selector(Bool)nfd_inert(Bool)nfkd_inert(Bool)nfc_inert(Bool)nfkc_inert(Bool)segment_starter(Bool)pattern_syntax(Bool)pattern_white_space(Bool)alnum(Bool)blank(Bool)graph(Bool)print(Bool)xdigit(Bool)cased(Bool)case_ignorable(Bool)changes_when_lowercased(Bool)changes_when_uppercased(Bool)changes_when_titlecased(Bool)changes_when_casefolded(Bool)changes_when_casemapped(Bool)changes_when_nfkc_casefolded(Bool)emoji(Bool)emoji_presentation(Bool)emoji_modifier(Bool)emoji_modifier_base(Bool)emoji_component(Bool)regional_indicator(Bool)prepended_concatenation_mark(Bool)extended_pictographic(Bool)basic_emoji(Bool)emoji_keycap_sequence(Bool)rgi_emoji_modifier_sequence(Bool)rgi_emoji_flag_sequence(Bool)rgi_emoji_tag_sequence(Bool)rgi_emoji_zwj_sequence(Bool)rgi_emoji(Bool)ids_unary_operator(Bool)id_compat_math_start(Bool)id_compat_math_continue(Bool)bidi_class(Enum8(‘Left_To_Right’ = 0, ‘Right_To_Left’ = 1, ‘European_Number’ = 2, ‘European_Separator’ = 3, ‘European_Terminator’ = 4, ‘Arabic_Number’ = 5, ‘Common_Separator’ = 6, ‘Paragraph_Separator’ = 7, ‘Segment_Separator’ = 8, ‘White_Space’ = 9, ‘Other_Neutral’ = 10, ‘Left_To_Right_Embedding’ = 11, ‘Left_To_Right_Override’ = 12, ‘Arabic_Letter’ = 13, ‘Right_To_Left_Embedding’ = 14, ‘Right_To_Left_Override’ = 15, ‘Pop_Directional_Format’ = 16, ‘Nonspacing_Mark’ = 17, ‘Boundary_Neutral’ = 18, ‘First_Strong_Isolate’ = 19, ‘Left_To_Right_Isolate’ = 20, ‘Right_To_Left_Isolate’ = 21, ‘Pop_Directional_Isolate’ = 22))block(Enum16(‘No_Block’ = 0, ‘Basic_Latin’ = 1, ‘Latin_1_Supplement’ = 2, ‘Latin_Extended_A’ = 3, ‘Latin_Extended_B’ = 4, ‘IPA_Extensions’ = 5, ‘Spacing_Modifier_Letters’ = 6, ‘Combining_Diacritical_Marks’ = 7, ‘Greek_And_Coptic’ = 8, ‘Cyrillic’ = 9, ‘Armenian’ = 10, ‘Hebrew’ = 11, ‘Arabic’ = 12, ‘Syriac’ = 13, ‘Thaana’ = 14, ‘Devanagari’ = 15, ‘Bengali’ = 16, ‘Gurmukhi’ = 17, ‘Gujarati’ = 18, ‘Oriya’ = 19, ‘Tamil’ = 20, ‘Telugu’ = 21, ‘Kannada’ = 22, ‘Malayalam’ = 23, ‘Sinhala’ = 24, ‘Thai’ = 25, ‘Lao’ = 26, ‘Tibetan’ = 27, ‘Myanmar’ = 28, ‘Georgian’ = 29, ‘Hangul_Jamo’ = 30, ‘Ethiopic’ = 31, ‘Cherokee’ = 32, ‘Unified_Canadian_Aboriginal_Syllabics’ = 33, ‘Ogham’ = 34, ‘Runic’ = 35, ‘Khmer’ = 36, ‘Mongolian’ = 37, ‘Latin_Extended_Additional’ = 38, ‘Greek_Extended’ = 39, ‘General_Punctuation’ = 40, ‘Superscripts_And_Subscripts’ = 41, ‘Currency_Symbols’ = 42, ‘Combining_Diacritical_Marks_For_Symbols’ = 43, ‘Letterlike_Symbols’ = 44, ‘Number_Forms’ = 45, ‘Arrows’ = 46, ‘Mathematical_Operators’ = 47, ‘Miscellaneous_Technical’ = 48, ‘Control_Pictures’ = 49, ‘Optical_Character_Recognition’ = 50, ‘Enclosed_Alphanumerics’ = 51, ‘Box_Drawing’ = 52, ‘Block_Elements’ = 53, ‘Geometric_Shapes’ = 54, ‘Miscellaneous_Symbols’ = 55, ‘Dingbats’ = 56, ‘Braille_Patterns’ = 57, ‘CJK_Radicals_Supplement’ = 58, ‘Kangxi_Radicals’ = 59, ‘Ideographic_Description_Characters’ = 60, ‘CJK_Symbols_And_Punctuation’ = 61, ‘Hiragana’ = 62, ‘Katakana’ = 63, ‘Bopomofo’ = 64, ‘Hangul_Compatibility_Jamo’ = 65, ‘Kanbun’ = 66, ‘Bopomofo_Extended’ = 67, ‘Enclosed_CJK_Letters_And_Months’ = 68, ‘CJK_Compatibility’ = 69, ‘CJK_Unified_Ideographs_Extension_A’ = 70, ‘CJK_Unified_Ideographs’ = 71, ‘Yi_Syllables’ = 72, ‘Yi_Radicals’ = 73, ‘Hangul_Syllables’ = 74, ‘High_Surrogates’ = 75, ‘High_Private_Use_Surrogates’ = 76, ‘Low_Surrogates’ = 77, ‘Private_Use_Area’ = 78, ‘CJK_Compatibility_Ideographs’ = 79, ‘Alphabetic_Presentation_Forms’ = 80, ‘Arabic_Presentation_Forms_A’ = 81, ‘Combining_Half_Marks’ = 82, ‘CJK_Compatibility_Forms’ = 83, ‘Small_Form_Variants’ = 84, ‘Arabic_Presentation_Forms_B’ = 85, ‘Specials’ = 86, ‘Halfwidth_And_Fullwidth_Forms’ = 87, ‘Old_Italic’ = 88, ‘Gothic’ = 89, ‘Deseret’ = 90, ‘Byzantine_Musical_Symbols’ = 91, ‘Musical_Symbols’ = 92, ‘Mathematical_Alphanumeric_Symbols’ = 93, ‘CJK_Unified_Ideographs_Extension_B’ = 94, ‘CJK_Compatibility_Ideographs_Supplement’ = 95, ‘Tags’ = 96, ‘Cyrillic_Supplement’ = 97, ‘Tagalog’ = 98, ‘Hanunoo’ = 99, ‘Buhid’ = 100, ‘Tagbanwa’ = 101, ‘Miscellaneous_Mathematical_Symbols_A’ = 102, ‘Supplemental_Arrows_A’ = 103, ‘Supplemental_Arrows_B’ = 104, ‘Miscellaneous_Mathematical_Symbols_B’ = 105, ‘Supplemental_Mathematical_Operators’ = 106, ‘Katakana_Phonetic_Extensions’ = 107, ‘Variation_Selectors’ = 108, ‘Supplementary_Private_Use_Area_A’ = 109, ‘Supplementary_Private_Use_Area_B’ = 110, ‘Limbu’ = 111, ‘Tai_Le’ = 112, ‘Khmer_Symbols’ = 113, ‘Phonetic_Extensions’ = 114, ‘Miscellaneous_Symbols_And_Arrows’ = 115, ‘Yijing_Hexagram_Symbols’ = 116, ‘Linear_B_Syllabary’ = 117, ‘Linear_B_Ideograms’ = 118, ‘Aegean_Numbers’ = 119, ‘Ugaritic’ = 120, ‘Shavian’ = 121, ‘Osmanya’ = 122, ‘Cypriot_Syllabary’ = 123, ‘Tai_Xuan_Jing_Symbols’ = 124, ‘Variation_Selectors_Supplement’ = 125, ‘Ancient_Greek_Musical_Notation’ = 126, ‘Ancient_Greek_Numbers’ = 127, ‘Arabic_Supplement’ = 128, ‘Buginese’ = 129, ‘CJK_Strokes’ = 130, ‘Combining_Diacritical_Marks_Supplement’ = 131, ‘Coptic’ = 132, ‘Ethiopic_Extended’ = 133, ‘Ethiopic_Supplement’ = 134, ‘Georgian_Supplement’ = 135, ‘Glagolitic’ = 136, ‘Kharoshthi’ = 137, ‘Modifier_Tone_Letters’ = 138, ‘New_Tai_Lue’ = 139, ‘Old_Persian’ = 140, ‘Phonetic_Extensions_Supplement’ = 141, ‘Supplemental_Punctuation’ = 142, ‘Syloti_Nagri’ = 143, ‘Tifinagh’ = 144, ‘Vertical_Forms’ = 145, ‘NKo’ = 146, ‘Balinese’ = 147, ‘Latin_Extended_C’ = 148, ‘Latin_Extended_D’ = 149, ‘Phags_Pa’ = 150, ‘Phoenician’ = 151, ‘Cuneiform’ = 152, ‘Cuneiform_Numbers_And_Punctuation’ = 153, ‘Counting_Rod_Numerals’ = 154, ‘Sundanese’ = 155, ‘Lepcha’ = 156, ‘Ol_Chiki’ = 157, ‘Cyrillic_Extended_A’ = 158, ‘Vai’ = 159, ‘Cyrillic_Extended_B’ = 160, ‘Saurashtra’ = 161, ‘Kayah_Li’ = 162, ‘Rejang’ = 163, ‘Cham’ = 164, ‘Ancient_Symbols’ = 165, ‘Phaistos_Disc’ = 166, ‘Lycian’ = 167, ‘Carian’ = 168, ‘Lydian’ = 169, ‘Mahjong_Tiles’ = 170, ‘Domino_Tiles’ = 171, ‘Samaritan’ = 172, ‘Unified_Canadian_Aboriginal_Syllabics_Extended’ = 173, ‘Tai_Tham’ = 174, ‘Vedic_Extensions’ = 175, ‘Lisu’ = 176, ‘Bamum’ = 177, ‘Common_Indic_Number_Forms’ = 178, ‘Devanagari_Extended’ = 179, ‘Hangul_Jamo_Extended_A’ = 180, ‘Javanese’ = 181, ‘Myanmar_Extended_A’ = 182, ‘Tai_Viet’ = 183, ‘Meetei_Mayek’ = 184, ‘Hangul_Jamo_Extended_B’ = 185, ‘Imperial_Aramaic’ = 186, ‘Old_South_Arabian’ = 187, ‘Avestan’ = 188, ‘Inscriptional_Parthian’ = 189, ‘Inscriptional_Pahlavi’ = 190, ‘Old_Turkic’ = 191, ‘Rumi_Numeral_Symbols’ = 192, ‘Kaithi’ = 193, ‘Egyptian_Hieroglyphs’ = 194, ‘Enclosed_Alphanumeric_Supplement’ = 195, ‘Enclosed_Ideographic_Supplement’ = 196, ‘CJK_Unified_Ideographs_Extension_C’ = 197, ‘Mandaic’ = 198, ‘Batak’ = 199, ‘Ethiopic_Extended_A’ = 200, ‘Brahmi’ = 201, ‘Bamum_Supplement’ = 202, ‘Kana_Supplement’ = 203, ‘Playing_Cards’ = 204, ‘Miscellaneous_Symbols_And_Pictographs’ = 205, ‘Emoticons’ = 206, ‘Transport_And_Map_Symbols’ = 207, ‘Alchemical_Symbols’ = 208, ‘CJK_Unified_Ideographs_Extension_D’ = 209, ‘Arabic_Extended_A’ = 210, ‘Arabic_Mathematical_Alphabetic_Symbols’ = 211, ‘Chakma’ = 212, ‘Meetei_Mayek_Extensions’ = 213, ‘Meroitic_Cursive’ = 214, ‘Meroitic_Hieroglyphs’ = 215, ‘Miao’ = 216, ‘Sharada’ = 217, ‘Sora_Sompeng’ = 218, ‘Sundanese_Supplement’ = 219, ‘Takri’ = 220, ‘Bassa_Vah’ = 221, ‘Caucasian_Albanian’ = 222, ‘Coptic_Epact_Numbers’ = 223, ‘Combining_Diacritical_Marks_Extended’ = 224, ‘Duployan’ = 225, ‘Elbasan’ = 226, ‘Geometric_Shapes_Extended’ = 227, ‘Grantha’ = 228, ‘Khojki’ = 229, ‘Khudawadi’ = 230, ‘Latin_Extended_E’ = 231, ‘Linear_A’ = 232, ‘Mahajani’ = 233, ‘Manichaean’ = 234, ‘Mende_Kikakui’ = 235, ‘Modi’ = 236, ‘Mro’ = 237, ‘Myanmar_Extended_B’ = 238, ‘Nabataean’ = 239, ‘Old_North_Arabian’ = 240, ‘Old_Permic’ = 241, ‘Ornamental_Dingbats’ = 242, ‘Pahawh_Hmong’ = 243, ‘Palmyrene’ = 244, ‘Pau_Cin_Hau’ = 245, ‘Psalter_Pahlavi’ = 246, ‘Shorthand_Format_Controls’ = 247, ‘Siddham’ = 248, ‘Sinhala_Archaic_Numbers’ = 249, ‘Supplemental_Arrows_C’ = 250, ‘Tirhuta’ = 251, ‘Warang_Citi’ = 252, ‘Ahom’ = 253, ‘Anatolian_Hieroglyphs’ = 254, ‘Cherokee_Supplement’ = 255, ‘CJK_Unified_Ideographs_Extension_E’ = 256, ‘Early_Dynastic_Cuneiform’ = 257, ‘Hatran’ = 258, ‘Multani’ = 259, ‘Old_Hungarian’ = 260, ‘Supplemental_Symbols_And_Pictographs’ = 261, ‘Sutton_SignWriting’ = 262, ‘Adlam’ = 263, ‘Bhaiksuki’ = 264, ‘Cyrillic_Extended_C’ = 265, ‘Glagolitic_Supplement’ = 266, ‘Ideographic_Symbols_And_Punctuation’ = 267, ‘Marchen’ = 268, ‘Mongolian_Supplement’ = 269, ‘Newa’ = 270, ‘Osage’ = 271, ‘Tangut’ = 272, ‘Tangut_Components’ = 273, ‘CJK_Unified_Ideographs_Extension_F’ = 274, ‘Kana_Extended_A’ = 275, ‘Masaram_Gondi’ = 276, ‘Nushu’ = 277, ‘Soyombo’ = 278, ‘Syriac_Supplement’ = 279, ‘Zanabazar_Square’ = 280, ‘Chess_Symbols’ = 281, ‘Dogra’ = 282, ‘Georgian_Extended’ = 283, ‘Gunjala_Gondi’ = 284, ‘Hanifi_Rohingya’ = 285, ‘Indic_Siyaq_Numbers’ = 286, ‘Makasar’ = 287, ‘Mayan_Numerals’ = 288, ‘Medefaidrin’ = 289, ‘Old_Sogdian’ = 290, ‘Sogdian’ = 291, ‘Egyptian_Hieroglyph_Format_Controls’ = 292, ‘Elymaic’ = 293, ‘Nandinagari’ = 294, ‘Nyiakeng_Puachue_Hmong’ = 295, ‘Ottoman_Siyaq_Numbers’ = 296, ‘Small_Kana_Extension’ = 297, ‘Symbols_And_Pictographs_Extended_A’ = 298, ‘Tamil_Supplement’ = 299, ‘Wancho’ = 300, ‘Chorasmian’ = 301, ‘CJK_Unified_Ideographs_Extension_G’ = 302, ‘Dives_Akuru’ = 303, ‘Khitan_Small_Script’ = 304, ‘Lisu_Supplement’ = 305, ‘Symbols_For_Legacy_Computing’ = 306, ‘Tangut_Supplement’ = 307, ‘Yezidi’ = 308, ‘Arabic_Extended_B’ = 309, ‘Cypro_Minoan’ = 310, ‘Ethiopic_Extended_B’ = 311, ‘Kana_Extended_B’ = 312, ‘Latin_Extended_F’ = 313, ‘Latin_Extended_G’ = 314, ‘Old_Uyghur’ = 315, ‘Tangsa’ = 316, ‘Toto’ = 317, ‘Unified_Canadian_Aboriginal_Syllabics_Extended_A’ = 318, ‘Vithkuqi’ = 319, ‘Znamenny_Musical_Notation’ = 320, ‘Arabic_Extended_C’ = 321, ‘CJK_Unified_Ideographs_Extension_H’ = 322, ‘Cyrillic_Extended_D’ = 323, ‘Devanagari_Extended_A’ = 324, ‘Kaktovik_Numerals’ = 325, ‘Kawi’ = 326, ‘Nag_Mundari’ = 327, ‘CJK_Unified_Ideographs_Extension_I’ = 328, ‘Egyptian_Hieroglyphs_Extended_A’ = 329, ‘Garay’ = 330, ‘Gurung_Khema’ = 331, ‘Kirat_Rai’ = 332, ‘Myanmar_Extended_C’ = 333, ‘Ol_Onal’ = 334, ‘Sunuwar’ = 335, ‘Symbols_For_Legacy_Computing_Supplement’ = 336, ‘Todhri’ = 337, ‘Tulu_Tigalari’ = 338, ‘Beria_Erfe’ = 339, ‘CJK_Unified_Ideographs_Extension_J’ = 340, ‘Miscellaneous_Symbols_Supplement’ = 341, ‘Sharada_Supplement’ = 342, ‘Sidetic’ = 343, ‘Tai_Yo’ = 344, ‘Tangut_Components_Supplement’ = 345, ‘Tolong_Siki’ = 346))canonical_combining_class(Enum16(‘Not_Reordered’ = 0, ‘Overlay’ = 1, ‘Han_Reading’ = 6, ‘Nukta’ = 7, ‘Kana_Voicing’ = 8, ‘Virama’ = 9, ‘CCC10’ = 10, ‘CCC11’ = 11, ‘CCC12’ = 12, ‘CCC13’ = 13, ‘CCC14’ = 14, ‘CCC15’ = 15, ‘CCC16’ = 16, ‘CCC17’ = 17, ‘CCC18’ = 18, ‘CCC19’ = 19, ‘CCC20’ = 20, ‘CCC21’ = 21, ‘CCC22’ = 22, ‘CCC23’ = 23, ‘CCC24’ = 24, ‘CCC25’ = 25, ‘CCC26’ = 26, ‘CCC27’ = 27, ‘CCC28’ = 28, ‘CCC29’ = 29, ‘CCC30’ = 30, ‘CCC31’ = 31, ‘CCC32’ = 32, ‘CCC33’ = 33, ‘CCC34’ = 34, ‘CCC35’ = 35, ‘CCC36’ = 36, ‘CCC84’ = 84, ‘CCC91’ = 91, ‘CCC103’ = 103, ‘CCC107’ = 107, ‘CCC118’ = 118, ‘CCC122’ = 122, ‘CCC129’ = 129, ‘CCC130’ = 130, ‘CCC132’ = 132, ‘CCC133’ = 133, ‘Attached_Below_Left’ = 200, ‘Attached_Below’ = 202, ‘Attached_Above’ = 214, ‘Attached_Above_Right’ = 216, ‘Below_Left’ = 218, ‘Below’ = 220, ‘Below_Right’ = 222, ‘Left’ = 224, ‘Right’ = 226, ‘Above_Left’ = 228, ‘Above’ = 230, ‘Above_Right’ = 232, ‘Double_Below’ = 233, ‘Double_Above’ = 234, ‘Iota_Subscript’ = 240))decomposition_type(Enum8(‘None’ = 0, ‘Canonical’ = 1, ‘Compat’ = 2, ‘Circle’ = 3, ‘Final’ = 4, ‘Font’ = 5, ‘Fraction’ = 6, ‘Initial’ = 7, ‘Isolated’ = 8, ‘Medial’ = 9, ‘Narrow’ = 10, ‘Nobreak’ = 11, ‘Small’ = 12, ‘Square’ = 13, ‘Sub’ = 14, ‘Super’ = 15, ‘Vertical’ = 16, ‘Wide’ = 17))east_asian_width(Enum8(‘Neutral’ = 0, ‘Ambiguous’ = 1, ‘Halfwidth’ = 2, ‘Fullwidth’ = 3, ‘Narrow’ = 4, ‘Wide’ = 5))general_category(Enum8(‘Unassigned’ = 0, ‘Uppercase_Letter’ = 1, ‘Lowercase_Letter’ = 2, ‘Titlecase_Letter’ = 3, ‘Modifier_Letter’ = 4, ‘Other_Letter’ = 5, ‘Nonspacing_Mark’ = 6, ‘Enclosing_Mark’ = 7, ‘Spacing_Mark’ = 8, ‘Decimal_Number’ = 9, ‘Letter_Number’ = 10, ‘Other_Number’ = 11, ‘Space_Separator’ = 12, ‘Line_Separator’ = 13, ‘Paragraph_Separator’ = 14, ‘Control’ = 15, ‘Format’ = 16, ‘Private_Use’ = 17, ‘Surrogate’ = 18, ‘Dash_Punctuation’ = 19, ‘Open_Punctuation’ = 20, ‘Close_Punctuation’ = 21, ‘Connector_Punctuation’ = 22, ‘Other_Punctuation’ = 23, ‘Math_Symbol’ = 24, ‘Currency_Symbol’ = 25, ‘Modifier_Symbol’ = 26, ‘Other_Symbol’ = 27, ‘Initial_Punctuation’ = 28, ‘Final_Punctuation’ = 29))joining_group(Enum8(‘No_Joining_Group’ = 0, ‘Ain’ = 1, ‘Alaph’ = 2, ‘Alef’ = 3, ‘Beh’ = 4, ‘Beth’ = 5, ‘Dal’ = 6, ‘Dalath_Rish’ = 7, ‘E’ = 8, ‘Feh’ = 9, ‘Final_Semkath’ = 10, ‘Gaf’ = 11, ‘Gamal’ = 12, ‘Hah’ = 13, ‘Teh_Marbuta_Goal’ = 14, ‘He’ = 15, ‘Heh’ = 16, ‘Heh_Goal’ = 17, ‘Heth’ = 18, ‘Kaf’ = 19, ‘Kaph’ = 20, ‘Knotted_Heh’ = 21, ‘Lam’ = 22, ‘Lamadh’ = 23, ‘Meem’ = 24, ‘Mim’ = 25, ‘Noon’ = 26, ‘Nun’ = 27, ‘Pe’ = 28, ‘Qaf’ = 29, ‘Qaph’ = 30, ‘Reh’ = 31, ‘Reversed_Pe’ = 32, ‘Sad’ = 33, ‘Sadhe’ = 34, ‘Seen’ = 35, ‘Semkath’ = 36, ‘Shin’ = 37, ‘Swash_Kaf’ = 38, ‘Syriac_Waw’ = 39, ‘Tah’ = 40, ‘Taw’ = 41, ‘Teh_Marbuta’ = 42, ‘Teth’ = 43, ‘Waw’ = 44, ‘Yeh’ = 45, ‘Yeh_Barree’ = 46, ‘Yeh_With_Tail’ = 47, ‘Yudh’ = 48, ‘Yudh_He’ = 49, ‘Zain’ = 50, ‘Fe’ = 51, ‘Khaph’ = 52, ‘Zhain’ = 53, ‘Burushaski_Yeh_Barree’ = 54, ‘Farsi_Yeh’ = 55, ‘Nya’ = 56, ‘Rohingya_Yeh’ = 57, ‘Manichaean_Aleph’ = 58, ‘Manichaean_Ayin’ = 59, ‘Manichaean_Beth’ = 60, ‘Manichaean_Daleth’ = 61, ‘Manichaean_Dhamedh’ = 62, ‘Manichaean_Five’ = 63, ‘Manichaean_Gimel’ = 64, ‘Manichaean_Heth’ = 65, ‘Manichaean_Hundred’ = 66, ‘Manichaean_Kaph’ = 67, ‘Manichaean_Lamedh’ = 68, ‘Manichaean_Mem’ = 69, ‘Manichaean_Nun’ = 70, ‘Manichaean_One’ = 71, ‘Manichaean_Pe’ = 72, ‘Manichaean_Qoph’ = 73, ‘Manichaean_Resh’ = 74, ‘Manichaean_Sadhe’ = 75, ‘Manichaean_Samekh’ = 76, ‘Manichaean_Taw’ = 77, ‘Manichaean_Ten’ = 78, ‘Manichaean_Teth’ = 79, ‘Manichaean_Thamedh’ = 80, ‘Manichaean_Twenty’ = 81, ‘Manichaean_Waw’ = 82, ‘Manichaean_Yodh’ = 83, ‘Manichaean_Zayin’ = 84, ‘Straight_Waw’ = 85, ‘African_Feh’ = 86, ‘African_Noon’ = 87, ‘African_Qaf’ = 88, ‘Malayalam_Bha’ = 89, ‘Malayalam_Ja’ = 90, ‘Malayalam_Lla’ = 91, ‘Malayalam_Llla’ = 92, ‘Malayalam_Nga’ = 93, ‘Malayalam_Nna’ = 94, ‘Malayalam_Nnna’ = 95, ‘Malayalam_Nya’ = 96, ‘Malayalam_Ra’ = 97, ‘Malayalam_Ssa’ = 98, ‘Malayalam_Tta’ = 99, ‘Hanifi_Rohingya_Kinna_Ya’ = 100, ‘Hanifi_Rohingya_Pa’ = 101, ‘Thin_Yeh’ = 102, ‘Vertical_Tail’ = 103, ‘Kashmiri_Yeh’ = 104, ‘Thin_Noon’ = 105))joining_type(Enum8(‘Non_Joining’ = 0, ‘Join_Causing’ = 1, ‘Dual_Joining’ = 2, ‘Left_Joining’ = 3, ‘Right_Joining’ = 4, ‘Transparent’ = 5))line_break(Enum8(‘Unknown’ = 0, ‘Ambiguous’ = 1, ‘Alphabetic’ = 2, ‘Break_Both’ = 3, ‘Break_After’ = 4, ‘Break_Before’ = 5, ‘Mandatory_Break’ = 6, ‘Contingent_Break’ = 7, ‘Close_Punctuation’ = 8, ‘Combining_Mark’ = 9, ‘Carriage_Return’ = 10, ‘Exclamation’ = 11, ‘Glue’ = 12, ‘Hyphen’ = 13, ‘Ideographic’ = 14, ‘Inseparable’ = 15, ‘Infix_Numeric’ = 16, ‘Line_Feed’ = 17, ‘Nonstarter’ = 18, ‘Numeric’ = 19, ‘Open_Punctuation’ = 20, ‘Postfix_Numeric’ = 21, ‘Prefix_Numeric’ = 22, ‘Quotation’ = 23, ‘Complex_Context’ = 24, ‘Surrogate’ = 25, ‘Space’ = 26, ‘Break_Symbols’ = 27, ‘ZWSpace’ = 28, ‘Next_Line’ = 29, ‘Word_Joiner’ = 30, ‘H2’ = 31, ‘H3’ = 32, ‘JL’ = 33, ‘JT’ = 34, ‘JV’ = 35, ‘Close_Parenthesis’ = 36, ‘Conditional_Japanese_Starter’ = 37, ‘Hebrew_Letter’ = 38, ‘Regional_Indicator’ = 39, ‘E_Base’ = 40, ‘E_Modifier’ = 41, ‘ZWJ’ = 42, ‘Aksara’ = 43, ‘Aksara_Prebase’ = 44, ‘Aksara_Start’ = 45, ‘Virama_Final’ = 46, ‘Virama’ = 47, ‘Unambiguous_Hyphen’ = 48))numeric_type(Enum8(‘None’ = 0, ‘Decimal’ = 1, ‘Digit’ = 2, ‘Numeric’ = 3))script(Enum16(‘Common’ = 0, ‘Inherited’ = 1, ‘Arabic’ = 2, ‘Armenian’ = 3, ‘Bengali’ = 4, ‘Bopomofo’ = 5, ‘Cherokee’ = 6, ‘Coptic’ = 7, ‘Cyrillic’ = 8, ‘Deseret’ = 9, ‘Devanagari’ = 10, ‘Ethiopic’ = 11, ‘Georgian’ = 12, ‘Gothic’ = 13, ‘Greek’ = 14, ‘Gujarati’ = 15, ‘Gurmukhi’ = 16, ‘Han’ = 17, ‘Hangul’ = 18, ‘Hebrew’ = 19, ‘Hiragana’ = 20, ‘Kannada’ = 21, ‘Katakana’ = 22, ‘Khmer’ = 23, ‘Lao’ = 24, ‘Latin’ = 25, ‘Malayalam’ = 26, ‘Mongolian’ = 27, ‘Myanmar’ = 28, ‘Ogham’ = 29, ‘Old_Italic’ = 30, ‘Oriya’ = 31, ‘Runic’ = 32, ‘Sinhala’ = 33, ‘Syriac’ = 34, ‘Tamil’ = 35, ‘Telugu’ = 36, ‘Thaana’ = 37, ‘Thai’ = 38, ‘Tibetan’ = 39, ‘Canadian_Aboriginal’ = 40, ‘Yi’ = 41, ‘Tagalog’ = 42, ‘Hanunoo’ = 43, ‘Buhid’ = 44, ‘Tagbanwa’ = 45, ‘Braille’ = 46, ‘Cypriot’ = 47, ‘Limbu’ = 48, ‘Linear_B’ = 49, ‘Osmanya’ = 50, ‘Shavian’ = 51, ‘Tai_Le’ = 52, ‘Ugaritic’ = 53, ‘Katakana_Or_Hiragana’ = 54, ‘Buginese’ = 55, ‘Glagolitic’ = 56, ‘Kharoshthi’ = 57, ‘Syloti_Nagri’ = 58, ‘New_Tai_Lue’ = 59, ‘Tifinagh’ = 60, ‘Old_Persian’ = 61, ‘Balinese’ = 62, ‘Batak’ = 63, ‘Blis’ = 64, ‘Brahmi’ = 65, ‘Cham’ = 66, ‘Cirt’ = 67, ‘Cyrs’ = 68, ‘Egyd’ = 69, ‘Egyh’ = 70, ‘Egyptian_Hieroglyphs’ = 71, ‘Geok’ = 72, ‘Hans’ = 73, ‘Hant’ = 74, ‘Pahawh_Hmong’ = 75, ‘Old_Hungarian’ = 76, ‘Inds’ = 77, ‘Javanese’ = 78, ‘Kayah_Li’ = 79, ‘Latf’ = 80, ‘Latg’ = 81, ‘Lepcha’ = 82, ‘Linear_A’ = 83, ‘Mandaic’ = 84, ‘Maya’ = 85, ‘Meroitic_Hieroglyphs’ = 86, ‘Nko’ = 87, ‘Old_Turkic’ = 88, ‘Old_Permic’ = 89, ‘Phags_Pa’ = 90, ‘Phoenician’ = 91, ‘Miao’ = 92, ‘Roro’ = 93, ‘Sara’ = 94, ‘Syre’ = 95, ‘Syrj’ = 96, ‘Syrn’ = 97, ‘Teng’ = 98, ‘Vai’ = 99, ‘Visp’ = 100, ‘Cuneiform’ = 101, ‘Zxxx’ = 102, ‘Unknown’ = 103, ‘Carian’ = 104, ‘Jpan’ = 105, ‘Tai_Tham’ = 106, ‘Lycian’ = 107, ‘Lydian’ = 108, ‘Ol_Chiki’ = 109, ‘Rejang’ = 110, ‘Saurashtra’ = 111, ‘SignWriting’ = 112, ‘Sundanese’ = 113, ‘Moon’ = 114, ‘Meetei_Mayek’ = 115, ‘Imperial_Aramaic’ = 116, ‘Avestan’ = 117, ‘Chakma’ = 118, ‘Kore’ = 119, ‘Kaithi’ = 120, ‘Manichaean’ = 121, ‘Inscriptional_Pahlavi’ = 122, ‘Psalter_Pahlavi’ = 123, ‘Phlv’ = 124, ‘Inscriptional_Parthian’ = 125, ‘Samaritan’ = 126, ‘Tai_Viet’ = 127, ‘Zmth’ = 128, ‘Zsym’ = 129, ‘Bamum’ = 130, ‘Lisu’ = 131, ‘Nkgb’ = 132, ‘Old_South_Arabian’ = 133, ‘Bassa_Vah’ = 134, ‘Duployan’ = 135, ‘Elbasan’ = 136, ‘Grantha’ = 137, ‘Kpel’ = 138, ‘Loma’ = 139, ‘Mende_Kikakui’ = 140, ‘Meroitic_Cursive’ = 141, ‘Old_North_Arabian’ = 142, ‘Nabataean’ = 143, ‘Palmyrene’ = 144, ‘Khudawadi’ = 145, ‘Warang_Citi’ = 146, ‘Afak’ = 147, ‘Jurc’ = 148, ‘Mro’ = 149, ‘Nushu’ = 150, ‘Sharada’ = 151, ‘Sora_Sompeng’ = 152, ‘Takri’ = 153, ‘Tangut’ = 154, ‘Wole’ = 155, ‘Anatolian_Hieroglyphs’ = 156, ‘Khojki’ = 157, ‘Tirhuta’ = 158, ‘Caucasian_Albanian’ = 159, ‘Mahajani’ = 160, ‘Ahom’ = 161, ‘Hatran’ = 162, ‘Modi’ = 163, ‘Multani’ = 164, ‘Pau_Cin_Hau’ = 165, ‘Siddham’ = 166, ‘Adlam’ = 167, ‘Bhaiksuki’ = 168, ‘Marchen’ = 169, ‘Newa’ = 170, ‘Osage’ = 171, ‘Hanb’ = 172, ‘Jamo’ = 173, ‘Zsye’ = 174, ‘Masaram_Gondi’ = 175, ‘Soyombo’ = 176, ‘Zanabazar_Square’ = 177, ‘Dogra’ = 178, ‘Gunjala_Gondi’ = 179, ‘Makasar’ = 180, ‘Medefaidrin’ = 181, ‘Hanifi_Rohingya’ = 182, ‘Sogdian’ = 183, ‘Old_Sogdian’ = 184, ‘Elymaic’ = 185, ‘Nyiakeng_Puachue_Hmong’ = 186, ‘Nandinagari’ = 187, ‘Wancho’ = 188, ‘Chorasmian’ = 189, ‘Dives_Akuru’ = 190, ‘Khitan_Small_Script’ = 191, ‘Yezidi’ = 192, ‘Cypro_Minoan’ = 193, ‘Old_Uyghur’ = 194, ‘Tangsa’ = 195, ‘Toto’ = 196, ‘Vithkuqi’ = 197, ‘Kawi’ = 198, ‘Nag_Mundari’ = 199, ‘Aran’ = 200, ‘Garay’ = 201, ‘Gurung_Khema’ = 202, ‘Kirat_Rai’ = 203, ‘Ol_Onal’ = 204, ‘Sunuwar’ = 205, ‘Todhri’ = 206, ‘Tulu_Tigalari’ = 207, ‘Beria_Erfe’ = 208, ‘Sidetic’ = 209, ‘Tai_Yo’ = 210, ‘Tolong_Siki’ = 211, ‘Hntl’ = 212))hangul_syllable_type(Enum8(‘Not_Applicable’ = 0, ‘Leading_Jamo’ = 1, ‘Vowel_Jamo’ = 2, ‘Trailing_Jamo’ = 3, ‘LV_Syllable’ = 4, ‘LVT_Syllable’ = 5))nfd_quick_check(Enum8(‘No’ = 0, ‘Yes’ = 1))nfkd_quick_check(Enum8(‘No’ = 0, ‘Yes’ = 1))nfc_quick_check(Enum8(‘No’ = 0, ‘Yes’ = 1, ‘Maybe’ = 2))nfkc_quick_check(Enum8(‘No’ = 0, ‘Yes’ = 1, ‘Maybe’ = 2))lead_canonical_combining_class(Enum16(‘Not_Reordered’ = 0, ‘Overlay’ = 1, ‘Han_Reading’ = 6, ‘Nukta’ = 7, ‘Kana_Voicing’ = 8, ‘Virama’ = 9, ‘CCC10’ = 10, ‘CCC11’ = 11, ‘CCC12’ = 12, ‘CCC13’ = 13, ‘CCC14’ = 14, ‘CCC15’ = 15, ‘CCC16’ = 16, ‘CCC17’ = 17, ‘CCC18’ = 18, ‘CCC19’ = 19, ‘CCC20’ = 20, ‘CCC21’ = 21, ‘CCC22’ = 22, ‘CCC23’ = 23, ‘CCC24’ = 24, ‘CCC25’ = 25, ‘CCC26’ = 26, ‘CCC27’ = 27, ‘CCC28’ = 28, ‘CCC29’ = 29, ‘CCC30’ = 30, ‘CCC31’ = 31, ‘CCC32’ = 32, ‘CCC33’ = 33, ‘CCC34’ = 34, ‘CCC35’ = 35, ‘CCC36’ = 36, ‘CCC84’ = 84, ‘CCC91’ = 91, ‘CCC103’ = 103, ‘CCC107’ = 107, ‘CCC118’ = 118, ‘CCC122’ = 122, ‘CCC129’ = 129, ‘CCC130’ = 130, ‘CCC132’ = 132, ‘CCC133’ = 133, ‘Attached_Below_Left’ = 200, ‘Attached_Below’ = 202, ‘Attached_Above’ = 214, ‘Attached_Above_Right’ = 216, ‘Below_Left’ = 218, ‘Below’ = 220, ‘Below_Right’ = 222, ‘Left’ = 224, ‘Right’ = 226, ‘Above_Left’ = 228, ‘Above’ = 230, ‘Above_Right’ = 232, ‘Double_Below’ = 233, ‘Double_Above’ = 234, ‘Iota_Subscript’ = 240))trail_canonical_combining_class(Enum16(‘Not_Reordered’ = 0, ‘Overlay’ = 1, ‘Han_Reading’ = 6, ‘Nukta’ = 7, ‘Kana_Voicing’ = 8, ‘Virama’ = 9, ‘CCC10’ = 10, ‘CCC11’ = 11, ‘CCC12’ = 12, ‘CCC13’ = 13, ‘CCC14’ = 14, ‘CCC15’ = 15, ‘CCC16’ = 16, ‘CCC17’ = 17, ‘CCC18’ = 18, ‘CCC19’ = 19, ‘CCC20’ = 20, ‘CCC21’ = 21, ‘CCC22’ = 22, ‘CCC23’ = 23, ‘CCC24’ = 24, ‘CCC25’ = 25, ‘CCC26’ = 26, ‘CCC27’ = 27, ‘CCC28’ = 28, ‘CCC29’ = 29, ‘CCC30’ = 30, ‘CCC31’ = 31, ‘CCC32’ = 32, ‘CCC33’ = 33, ‘CCC34’ = 34, ‘CCC35’ = 35, ‘CCC36’ = 36, ‘CCC84’ = 84, ‘CCC91’ = 91, ‘CCC103’ = 103, ‘CCC107’ = 107, ‘CCC118’ = 118, ‘CCC122’ = 122, ‘CCC129’ = 129, ‘CCC130’ = 130, ‘CCC132’ = 132, ‘CCC133’ = 133, ‘Attached_Below_Left’ = 200, ‘Attached_Below’ = 202, ‘Attached_Above’ = 214, ‘Attached_Above_Right’ = 216, ‘Below_Left’ = 218, ‘Below’ = 220, ‘Below_Right’ = 222, ‘Left’ = 224, ‘Right’ = 226, ‘Above_Left’ = 228, ‘Above’ = 230, ‘Above_Right’ = 232, ‘Double_Below’ = 233, ‘Double_Above’ = 234, ‘Iota_Subscript’ = 240))grapheme_cluster_break(Enum8(‘Other’ = 0, ‘Control’ = 1, ‘CR’ = 2, ‘Extend’ = 3, ‘L’ = 4, ‘LF’ = 5, ‘LV’ = 6, ‘LVT’ = 7, ‘T’ = 8, ‘V’ = 9, ‘SpacingMark’ = 10, ‘Prepend’ = 11, ‘Regional_Indicator’ = 12, ‘E_Base’ = 13, ‘E_Base_GAZ’ = 14, ‘E_Modifier’ = 15, ‘Glue_After_Zwj’ = 16, ‘ZWJ’ = 17))sentence_break(Enum8(‘Other’ = 0, ‘ATerm’ = 1, ‘Close’ = 2, ‘Format’ = 3, ‘Lower’ = 4, ‘Numeric’ = 5, ‘OLetter’ = 6, ‘Sep’ = 7, ‘Sp’ = 8, ‘STerm’ = 9, ‘Upper’ = 10, ‘CR’ = 11, ‘Extend’ = 12, ‘LF’ = 13, ‘SContinue’ = 14))word_break(Enum8(‘Other’ = 0, ‘ALetter’ = 1, ‘Format’ = 2, ‘Katakana’ = 3, ‘MidLetter’ = 4, ‘MidNum’ = 5, ‘Numeric’ = 6, ‘ExtendNumLet’ = 7, ‘CR’ = 8, ‘Extend’ = 9, ‘LF’ = 10, ‘MidNumLet’ = 11, ‘Newline’ = 12, ‘Regional_Indicator’ = 13, ‘Hebrew_Letter’ = 14, ‘Single_Quote’ = 15, ‘Double_Quote’ = 16, ‘E_Base’ = 17, ‘E_Base_GAZ’ = 18, ‘E_Modifier’ = 19, ‘Glue_After_Zwj’ = 20, ‘ZWJ’ = 21, ‘WSegSpace’ = 22))bidi_paired_bracket_type(Enum8(‘None’ = 0, ‘Open’ = 1, ‘Close’ = 2))indic_positional_category(Enum8(‘Not_Applicable’ = 0, ‘Bottom’ = 1, ‘Bottom_And_Left’ = 2, ‘Bottom_And_Right’ = 3, ‘Left’ = 4, ‘Left_And_Right’ = 5, ‘Overstruck’ = 6, ‘Right’ = 7, ‘Top’ = 8, ‘Top_And_Bottom’ = 9, ‘Top_And_Bottom_And_Right’ = 10, ‘Top_And_Left’ = 11, ‘Top_And_Left_And_Right’ = 12, ‘Top_And_Right’ = 13, ‘Visual_Order_Left’ = 14, ‘Top_And_Bottom_And_Left’ = 15))indic_syllabic_category(Enum8(‘Other’ = 0, ‘Avagraha’ = 1, ‘Bindu’ = 2, ‘Brahmi_Joining_Number’ = 3, ‘Cantillation_Mark’ = 4, ‘Consonant’ = 5, ‘Consonant_Dead’ = 6, ‘Consonant_Final’ = 7, ‘Consonant_Head_Letter’ = 8, ‘Consonant_Initial_Postfixed’ = 9, ‘Consonant_Killer’ = 10, ‘Consonant_Medial’ = 11, ‘Consonant_Placeholder’ = 12, ‘Consonant_Preceding_Repha’ = 13, ‘Consonant_Prefixed’ = 14, ‘Consonant_Subjoined’ = 15, ‘Consonant_Succeeding_Repha’ = 16, ‘Consonant_With_Stacker’ = 17, ‘Gemination_Mark’ = 18, ‘Invisible_Stacker’ = 19, ‘Joiner’ = 20, ‘Modifying_Letter’ = 21, ‘Non_Joiner’ = 22, ‘Nukta’ = 23, ‘Number’ = 24, ‘Number_Joiner’ = 25, ‘Pure_Killer’ = 26, ‘Register_Shifter’ = 27, ‘Syllable_Modifier’ = 28, ‘Tone_Letter’ = 29, ‘Tone_Mark’ = 30, ‘Virama’ = 31, ‘Visarga’ = 32, ‘Vowel’ = 33, ‘Vowel_Dependent’ = 34, ‘Vowel_Independent’ = 35, ‘Reordering_Killer’ = 36))vertical_orientation(Enum8(‘Rotated’ = 0, ‘Transformed_Rotated’ = 1, ‘Transformed_Upright’ = 2, ‘Upright’ = 3))identifier_status(Enum8(‘Restricted’ = 0, ‘Allowed’ = 1))general_category_mask(Int32)numeric_value(Float64)age(String)bidi_mirroring_glyph(String)case_folding(String)lowercase_mapping(String)name(String)simple_case_folding(String)simple_lowercase_mapping(String)simple_titlecase_mapping(String)simple_uppercase_mapping(String)titlecase_mapping(String)uppercase_mapping(String)bidi_paired_bracket(String)script_extensions(Array(LowCardinality(String)))identifier_type(Array(LowCardinality(String)))