# # Copyright (c), 2018-2026, SISSA (International School for Advanced Studies). # All rights reserved. # This file is distributed under the terms of the MIT License. # See the file 'LICENSE' in the root directory of the present # distribution, or https://opensource.org/licenses/MIT. # # @author Davide Brunato # # --- Auto-generated code: don't edit this file --- # UNICODE_BLOCKS_VER_2_0_0 = { 'Basic Latin': '\u0000-\u007F', 'Latin-1 Supplement': '\u0080-\u00FF', 'Latin Extended-A': '\u0100-\u017F', 'Latin Extended-B': '\u0180-\u024F', 'IPA Extensions': '\u0250-\u02AF', 'Spacing Modifier Letters': '\u02B0-\u02FF', 'Combining Diacritical Marks': '\u0300-\u036F', 'Greek': '\u0370-\u03FF', 'Cyrillic': '\u0400-\u04FF', 'Armenian': '\u0530-\u058F', 'Hebrew': '\u0590-\u05FF', 'Arabic': '\u0600-\u06FF', 'Devanagari': '\u0900-\u097F', 'Bengali': '\u0980-\u09FF', 'Gurmukhi': '\u0A00-\u0A7F', 'Gujarati': '\u0A80-\u0AFF', 'Oriya': '\u0B00-\u0B7F', 'Tamil': '\u0B80-\u0BFF', 'Telugu': '\u0C00-\u0C7F', 'Kannada': '\u0C80-\u0CFF', 'Malayalam': '\u0D00-\u0D7F', 'Thai': '\u0E00-\u0E7F', 'Lao': '\u0E80-\u0EFF', 'Tibetan': '\u0F00-\u0FBF', 'Georgian': '\u10A0-\u10FF', 'Hangul Jamo': '\u1100-\u11FF', 'Latin Extended Additional': '\u1E00-\u1EFF', 'Greek Extended': '\u1F00-\u1FFF', 'General Punctuation': '\u2000-\u206F', 'Superscripts and Subscripts': '\u2070-\u209F', 'Currency Symbols': '\u20A0-\u20CF', 'Combining Marks for Symbols': '\u20D0-\u20FF', 'Letterlike Symbols': '\u2100-\u214F', 'Number Forms': '\u2150-\u218F', 'Arrows': '\u2190-\u21FF', 'Mathematical Operators': '\u2200-\u22FF', 'Miscellaneous Technical': '\u2300-\u23FF', 'Control Pictures': '\u2400-\u243F', 'Optical Character Recognition': '\u2440-\u245F', 'Enclosed Alphanumerics': '\u2460-\u24FF', 'Box Drawing': '\u2500-\u257F', 'Block Elements': '\u2580-\u259F', 'Geometric Shapes': '\u25A0-\u25FF', 'Miscellaneous Symbols': '\u2600-\u26FF', 'Dingbats': '\u2700-\u27BF', 'CJK Symbols and Punctuation': '\u3000-\u303F', 'Hiragana': '\u3040-\u309F', 'Katakana': '\u30A0-\u30FF', 'Bopomofo': '\u3100-\u312F', 'Hangul Compatibility Jamo': '\u3130-\u318F', 'Kanbun': '\u3190-\u319F', 'Enclosed CJK Letters and Months': '\u3200-\u32FF', 'CJK Compatibility': '\u3300-\u33FF', 'CJK Unified Ideographs': '\u4E00-\u9FFF', 'Hangul Syllables': '\uAC00-\uD7A3', 'High Surrogates': '\uD800-\uDB7F', 'High Private Use Surrogates': '\uDB80-\uDBFF', 'Low Surrogates': '\uDC00-\uDFFF', 'Private Use': '\uE000-\uF8FF', 'CJK Compatibility Ideographs': '\uF900-\uFAFF', 'Alphabetic Presentation Forms': '\uFB00-\uFB4F', 'Arabic Presentation Forms-A': '\uFB50-\uFDFF', 'Combining Half Marks': '\uFE20-\uFE2F', 'CJK Compatibility Forms': '\uFE30-\uFE4F', 'Small Form Variants': '\uFE50-\uFE6F', 'Arabic Presentation Forms-B': '\uFE70-\uFEFF', 'Halfwidth and Fullwidth Forms': '\uFF00-\uFFEF', 'Specials': '\uFEFF-\uFEFF\uFFF0-\uFFFF' } UPDATE_BLOCKS_VER_2_1_9 = { 'Arabic Presentation Forms-B': '\uFE70-\uFEFE', 'Specials': '\uFEFF-\uFEFF\uFFF0-\uFFFD' } UPDATE_BLOCKS_VER_3_0_0 = { 'Syriac': '\u0700-\u074F', 'Thaana': '\u0780-\u07BF', 'Sinhala': '\u0D80-\u0DFF', 'Tibetan': '\u0F00-\u0FFF', 'Myanmar': '\u1000-\u109F', 'Ethiopic': '\u1200-\u137F', 'Cherokee': '\u13A0-\u13FF', 'Unified Canadian Aboriginal Syllabics': '\u1400-\u167F', 'Ogham': '\u1680-\u169F', 'Runic': '\u16A0-\u16FF', 'Khmer': '\u1780-\u17FF', 'Mongolian': '\u1800-\u18AF', 'Braille Patterns': '\u2800-\u28FF', 'CJK Radicals Supplement': '\u2E80-\u2EFF', 'Kangxi Radicals': '\u2F00-\u2FDF', 'Ideographic Description Characters': '\u2FF0-\u2FFF', 'Bopomofo Extended': '\u31A0-\u31BF', 'CJK Unified Ideographs Extension A': '\u3400-\u4DB5', 'Yi Syllables': '\uA000-\uA48F', 'Yi Radicals': '\uA490-\uA4CF' } UPDATE_BLOCKS_VER_3_1_0 = { 'Private Use': '\uE000-\uF8FF\U000F0000-\U000FFFFD\U00100000-\U0010FFFD', 'Old Italic': '\U00010300-\U0001032F', 'Gothic': '\U00010330-\U0001034F', 'Deseret': '\U00010400-\U0001044F', 'Byzantine Musical Symbols': '\U0001D000-\U0001D0FF', 'Musical Symbols': '\U0001D100-\U0001D1FF', 'Mathematical Alphanumeric Symbols': '\U0001D400-\U0001D7FF', 'CJK Unified Ideographs Extension B': '\U00020000-\U0002A6D6', 'CJK Compatibility Ideographs Supplement': '\U0002F800-\U0002FA1F', 'Tags': '\U000E0000-\U000E007F' } REMOVED_BLOCKS_VER_3_1_1 = [ 'Greek', 'Combining Marks for Symbols', 'Private Use' ] UPDATE_BLOCKS_VER_3_1_1 = { 'Greek and Coptic': '\u0370-\u03FF', 'Cyrillic Supplementary': '\u0500-\u052F', 'Tagalog': '\u1700-\u171F', 'Hanunoo': '\u1720-\u173F', 'Buhid': '\u1740-\u175F', 'Tagbanwa': '\u1760-\u177F', 'Combining Diacritical Marks for Symbols': '\u20D0-\u20FF', 'Miscellaneous Mathematical Symbols-A': '\u27C0-\u27EF', 'Supplemental Arrows-A': '\u27F0-\u27FF', 'Supplemental Arrows-B': '\u2900-\u297F', 'Miscellaneous Mathematical Symbols-B': '\u2980-\u29FF', 'Supplemental Mathematical Operators': '\u2A00-\u2AFF', 'Katakana Phonetic Extensions': '\u31F0-\u31FF', 'CJK Unified Ideographs Extension A': '\u3400-\u4DBF', 'Hangul Syllables': '\uAC00-\uD7AF', 'Private Use Area': '\uE000-\uF8FF', 'Variation Selectors': '\uFE00-\uFE0F', 'Arabic Presentation Forms-B': '\uFE70-\uFEFF', 'Specials': '\uFFF0-\uFFFF', 'CJK Unified Ideographs Extension B': '\U00020000-\U0002A6DF', 'Supplementary Private Use Area-A': '\U000F0000-\U000FFFFF', 'Supplementary Private Use Area-B': '\U00100000-\U0010FFFF' } UPDATE_BLOCKS_VER_4_0_0 = { 'Limbu': '\u1900-\u194F', 'Tai Le': '\u1950-\u197F', 'Khmer Symbols': '\u19E0-\u19FF', 'Phonetic Extensions': '\u1D00-\u1D7F', 'Miscellaneous Symbols and Arrows': '\u2B00-\u2BFF', 'Yijing Hexagram Symbols': '\u4DC0-\u4DFF', 'Linear B Syllabary': '\U00010000-\U0001007F', 'Linear B Ideograms': '\U00010080-\U000100FF', 'Aegean Numbers': '\U00010100-\U0001013F', 'Ugaritic': '\U00010380-\U0001039F', 'Shavian': '\U00010450-\U0001047F', 'Osmanya': '\U00010480-\U000104AF', 'Cypriot Syllabary': '\U00010800-\U0001083F', 'Tai Xuan Jing Symbols': '\U0001D300-\U0001D35F', 'Variation Selectors Supplement': '\U000E0100-\U000E01EF' } REMOVED_BLOCKS_VER_4_0_1 = [ 'Cyrillic Supplementary' ] UPDATE_BLOCKS_VER_4_0_1 = { 'Cyrillic Supplement': '\u0500-\u052F' } UPDATE_BLOCKS_VER_4_1_0 = { 'Arabic Supplement': '\u0750-\u077F', 'Ethiopic Supplement': '\u1380-\u139F', 'New Tai Lue': '\u1980-\u19DF', 'Buginese': '\u1A00-\u1A1F', 'Phonetic Extensions Supplement': '\u1D80-\u1DBF', 'Combining Diacritical Marks Supplement': '\u1DC0-\u1DFF', 'Glagolitic': '\u2C00-\u2C5F', 'Coptic': '\u2C80-\u2CFF', 'Georgian Supplement': '\u2D00-\u2D2F', 'Tifinagh': '\u2D30-\u2D7F', 'Ethiopic Extended': '\u2D80-\u2DDF', 'Supplemental Punctuation': '\u2E00-\u2E7F', 'CJK Strokes': '\u31C0-\u31EF', 'Modifier Tone Letters': '\uA700-\uA71F', 'Syloti Nagri': '\uA800-\uA82F', 'Vertical Forms': '\uFE10-\uFE1F', 'Ancient Greek Numbers': '\U00010140-\U0001018F', 'Old Persian': '\U000103A0-\U000103DF', 'Kharoshthi': '\U00010A00-\U00010A5F', 'Ancient Greek Musical Notation': '\U0001D200-\U0001D24F' } UPDATE_BLOCKS_VER_5_0_0 = { 'NKo': '\u07C0-\u07FF', 'Balinese': '\u1B00-\u1B7F', 'Latin Extended-C': '\u2C60-\u2C7F', 'Latin Extended-D': '\uA720-\uA7FF', 'Phags-pa': '\uA840-\uA87F', 'Phoenician': '\U00010900-\U0001091F', 'Cuneiform': '\U00012000-\U000123FF', 'Cuneiform Numbers and Punctuation': '\U00012400-\U0001247F', 'Counting Rod Numerals': '\U0001D360-\U0001D37F' } UPDATE_BLOCKS_VER_5_1_0 = { 'Sundanese': '\u1B80-\u1BBF', 'Lepcha': '\u1C00-\u1C4F', 'Ol Chiki': '\u1C50-\u1C7F', 'Cyrillic Extended-A': '\u2DE0-\u2DFF', 'Vai': '\uA500-\uA63F', 'Cyrillic Extended-B': '\uA640-\uA69F', 'Saurashtra': '\uA880-\uA8DF', 'Kayah Li': '\uA900-\uA92F', 'Rejang': '\uA930-\uA95F', 'Cham': '\uAA00-\uAA5F', 'Ancient Symbols': '\U00010190-\U000101CF', 'Phaistos Disc': '\U000101D0-\U000101FF', 'Lycian': '\U00010280-\U0001029F', 'Carian': '\U000102A0-\U000102DF', 'Lydian': '\U00010920-\U0001093F', 'Mahjong Tiles': '\U0001F000-\U0001F02F', 'Domino Tiles': '\U0001F030-\U0001F09F' } UPDATE_BLOCKS_VER_5_2_0 = { 'Samaritan': '\u0800-\u083F', 'Unified Canadian Aboriginal Syllabics Extended': '\u18B0-\u18FF', 'Tai Tham': '\u1A20-\u1AAF', 'Vedic Extensions': '\u1CD0-\u1CFF', 'Lisu': '\uA4D0-\uA4FF', 'Bamum': '\uA6A0-\uA6FF', 'Common Indic Number Forms': '\uA830-\uA83F', 'Devanagari Extended': '\uA8E0-\uA8FF', 'Hangul Jamo Extended-A': '\uA960-\uA97F', 'Javanese': '\uA980-\uA9DF', 'Myanmar Extended-A': '\uAA60-\uAA7F', 'Tai Viet': '\uAA80-\uAADF', 'Meetei Mayek': '\uABC0-\uABFF', 'Hangul Jamo Extended-B': '\uD7B0-\uD7FF', 'Imperial Aramaic': '\U00010840-\U0001085F', 'Old South Arabian': '\U00010A60-\U00010A7F', 'Avestan': '\U00010B00-\U00010B3F', 'Inscriptional Parthian': '\U00010B40-\U00010B5F', 'Inscriptional Pahlavi': '\U00010B60-\U00010B7F', 'Old Turkic': '\U00010C00-\U00010C4F', 'Rumi Numeral Symbols': '\U00010E60-\U00010E7F', 'Kaithi': '\U00011080-\U000110CF', 'Egyptian Hieroglyphs': '\U00013000-\U0001342F', 'Enclosed Alphanumeric Supplement': '\U0001F100-\U0001F1FF', 'Enclosed Ideographic Supplement': '\U0001F200-\U0001F2FF', 'CJK Unified Ideographs Extension C': '\U0002A700-\U0002B73F' } UPDATE_BLOCKS_VER_6_0_0 = { 'Mandaic': '\u0840-\u085F', 'Batak': '\u1BC0-\u1BFF', 'Ethiopic Extended-A': '\uAB00-\uAB2F', 'Brahmi': '\U00011000-\U0001107F', 'Bamum Supplement': '\U00016800-\U00016A3F', 'Kana Supplement': '\U0001B000-\U0001B0FF', 'Playing Cards': '\U0001F0A0-\U0001F0FF', 'Miscellaneous Symbols And Pictographs': '\U0001F300-\U0001F5FF', 'Emoticons': '\U0001F600-\U0001F64F', 'Transport And Map Symbols': '\U0001F680-\U0001F6FF', 'Alchemical Symbols': '\U0001F700-\U0001F77F', 'CJK Unified Ideographs Extension D': '\U0002B740-\U0002B81F' } UPDATE_BLOCKS_VER_6_1_0 = { 'Arabic Extended-A': '\u08A0-\u08FF', 'Sundanese Supplement': '\u1CC0-\u1CCF', 'Meetei Mayek Extensions': '\uAAE0-\uAAFF', 'Meroitic Hieroglyphs': '\U00010980-\U0001099F', 'Meroitic Cursive': '\U000109A0-\U000109FF', 'Sora Sompeng': '\U000110D0-\U000110FF', 'Chakma': '\U00011100-\U0001114F', 'Sharada': '\U00011180-\U000111DF', 'Takri': '\U00011680-\U000116CF', 'Miao': '\U00016F00-\U00016F9F', 'Arabic Mathematical Alphabetic Symbols': '\U0001EE00-\U0001EEFF' } REMOVED_BLOCKS_VER_7_0_0 = [ 'Miscellaneous Symbols And Pictographs', 'Transport And Map Symbols' ] UPDATE_BLOCKS_VER_7_0_0 = { 'Combining Diacritical Marks Extended': '\u1AB0-\u1AFF', 'Myanmar Extended-B': '\uA9E0-\uA9FF', 'Latin Extended-E': '\uAB30-\uAB6F', 'Coptic Epact Numbers': '\U000102E0-\U000102FF', 'Old Permic': '\U00010350-\U0001037F', 'Elbasan': '\U00010500-\U0001052F', 'Caucasian Albanian': '\U00010530-\U0001056F', 'Linear A': '\U00010600-\U0001077F', 'Palmyrene': '\U00010860-\U0001087F', 'Nabataean': '\U00010880-\U000108AF', 'Old North Arabian': '\U00010A80-\U00010A9F', 'Manichaean': '\U00010AC0-\U00010AFF', 'Psalter Pahlavi': '\U00010B80-\U00010BAF', 'Mahajani': '\U00011150-\U0001117F', 'Sinhala Archaic Numbers': '\U000111E0-\U000111FF', 'Khojki': '\U00011200-\U0001124F', 'Khudawadi': '\U000112B0-\U000112FF', 'Grantha': '\U00011300-\U0001137F', 'Tirhuta': '\U00011480-\U000114DF', 'Siddham': '\U00011580-\U000115FF', 'Modi': '\U00011600-\U0001165F', 'Warang Citi': '\U000118A0-\U000118FF', 'Pau Cin Hau': '\U00011AC0-\U00011AFF', 'Mro': '\U00016A40-\U00016A6F', 'Bassa Vah': '\U00016AD0-\U00016AFF', 'Pahawh Hmong': '\U00016B00-\U00016B8F', 'Duployan': '\U0001BC00-\U0001BC9F', 'Shorthand Format Controls': '\U0001BCA0-\U0001BCAF', 'Mende Kikakui': '\U0001E800-\U0001E8DF', 'Miscellaneous Symbols and Pictographs': '\U0001F300-\U0001F5FF', 'Ornamental Dingbats': '\U0001F650-\U0001F67F', 'Transport and Map Symbols': '\U0001F680-\U0001F6FF', 'Geometric Shapes Extended': '\U0001F780-\U0001F7FF', 'Supplemental Arrows-C': '\U0001F800-\U0001F8FF' } UPDATE_BLOCKS_VER_8_0_0 = { 'Cherokee Supplement': '\uAB70-\uABBF', 'Hatran': '\U000108E0-\U000108FF', 'Old Hungarian': '\U00010C80-\U00010CFF', 'Multani': '\U00011280-\U000112AF', 'Ahom': '\U00011700-\U0001173F', 'Early Dynastic Cuneiform': '\U00012480-\U0001254F', 'Anatolian Hieroglyphs': '\U00014400-\U0001467F', 'Sutton SignWriting': '\U0001D800-\U0001DAAF', 'Supplemental Symbols and Pictographs': '\U0001F900-\U0001F9FF', 'CJK Unified Ideographs Extension E': '\U0002B820-\U0002CEAF' } UPDATE_BLOCKS_VER_9_0_0 = { 'Cyrillic Extended-C': '\u1C80-\u1C8F', 'Osage': '\U000104B0-\U000104FF', 'Newa': '\U00011400-\U0001147F', 'Mongolian Supplement': '\U00011660-\U0001167F', 'Bhaiksuki': '\U00011C00-\U00011C6F', 'Marchen': '\U00011C70-\U00011CBF', 'Ideographic Symbols and Punctuation': '\U00016FE0-\U00016FFF', 'Tangut': '\U00017000-\U000187FF', 'Tangut Components': '\U00018800-\U00018AFF', 'Glagolitic Supplement': '\U0001E000-\U0001E02F', 'Adlam': '\U0001E900-\U0001E95F' } UPDATE_BLOCKS_VER_10_0_0 = { 'Syriac Supplement': '\u0860-\u086F', 'Zanabazar Square': '\U00011A00-\U00011A4F', 'Soyombo': '\U00011A50-\U00011AAF', 'Masaram Gondi': '\U00011D00-\U00011D5F', 'Kana Extended-A': '\U0001B100-\U0001B12F', 'Nushu': '\U0001B170-\U0001B2FF', 'CJK Unified Ideographs Extension F': '\U0002CEB0-\U0002EBEF' } UPDATE_BLOCKS_VER_11_0_0 = { 'Georgian Extended': '\u1C90-\u1CBF', 'Hanifi Rohingya': '\U00010D00-\U00010D3F', 'Old Sogdian': '\U00010F00-\U00010F2F', 'Sogdian': '\U00010F30-\U00010F6F', 'Dogra': '\U00011800-\U0001184F', 'Gunjala Gondi': '\U00011D60-\U00011DAF', 'Makasar': '\U00011EE0-\U00011EFF', 'Medefaidrin': '\U00016E40-\U00016E9F', 'Mayan Numerals': '\U0001D2E0-\U0001D2FF', 'Indic Siyaq Numbers': '\U0001EC70-\U0001ECBF', 'Chess Symbols': '\U0001FA00-\U0001FA6F' } UPDATE_BLOCKS_VER_12_0_0 = { 'Elymaic': '\U00010FE0-\U00010FFF', 'Nandinagari': '\U000119A0-\U000119FF', 'Tamil Supplement': '\U00011FC0-\U00011FFF', 'Egyptian Hieroglyph Format Controls': '\U00013430-\U0001343F', 'Small Kana Extension': '\U0001B130-\U0001B16F', 'Nyiakeng Puachue Hmong': '\U0001E100-\U0001E14F', 'Wancho': '\U0001E2C0-\U0001E2FF', 'Ottoman Siyaq Numbers': '\U0001ED00-\U0001ED4F', 'Symbols and Pictographs Extended-A': '\U0001FA70-\U0001FAFF' } UPDATE_BLOCKS_VER_13_0_0 = { 'Yezidi': '\U00010E80-\U00010EBF', 'Chorasmian': '\U00010FB0-\U00010FDF', 'Dives Akuru': '\U00011900-\U0001195F', 'Lisu Supplement': '\U00011FB0-\U00011FBF', 'Khitan Small Script': '\U00018B00-\U00018CFF', 'Tangut Supplement': '\U00018D00-\U00018D8F', 'Symbols for Legacy Computing': '\U0001FB00-\U0001FBFF', 'CJK Unified Ideographs Extension G': '\U00030000-\U0003134F' } UPDATE_BLOCKS_VER_14_0_0 = { 'Arabic Extended-B': '\u0870-\u089F', 'Vithkuqi': '\U00010570-\U000105BF', 'Latin Extended-F': '\U00010780-\U000107BF', 'Old Uyghur': '\U00010F70-\U00010FAF', 'Ahom': '\U00011700-\U0001174F', 'Unified Canadian Aboriginal Syllabics Extended-A': '\U00011AB0-\U00011ABF', 'Cypro-Minoan': '\U00012F90-\U00012FFF', 'Tangsa': '\U00016A70-\U00016ACF', 'Tangut Supplement': '\U00018D00-\U00018D7F', 'Kana Extended-B': '\U0001AFF0-\U0001AFFF', 'Znamenny Musical Notation': '\U0001CF00-\U0001CFCF', 'Latin Extended-G': '\U0001DF00-\U0001DFFF', 'Toto': '\U0001E290-\U0001E2BF', 'Ethiopic Extended-B': '\U0001E7E0-\U0001E7FF' } UPDATE_BLOCKS_VER_15_0_0 = { 'Arabic Extended-C': '\U00010EC0-\U00010EFF', 'Devanagari Extended-A': '\U00011B00-\U00011B5F', 'Kawi': '\U00011F00-\U00011F5F', 'Egyptian Hieroglyph Format Controls': '\U00013430-\U0001345F', 'Kaktovik Numerals': '\U0001D2C0-\U0001D2DF', 'Cyrillic Extended-D': '\U0001E030-\U0001E08F', 'Nag Mundari': '\U0001E4D0-\U0001E4FF', 'CJK Unified Ideographs Extension H': '\U00031350-\U000323AF' } UPDATE_BLOCKS_VER_15_1_0 = { 'CJK Unified Ideographs Extension I': '\U0002EBF0-\U0002EE5F' } UPDATE_BLOCKS_VER_16_0_0 = { 'Todhri': '\U000105C0-\U000105FF', 'Garay': '\U00010D40-\U00010D8F', 'Tulu-Tigalari': '\U00011380-\U000113FF', 'Myanmar Extended-C': '\U000116D0-\U000116FF', 'Sunuwar': '\U00011BC0-\U00011BFF', 'Egyptian Hieroglyphs Extended-A': '\U00013460-\U000143FF', 'Gurung Khema': '\U00016100-\U0001613F', 'Kirat Rai': '\U00016D40-\U00016D7F', 'Symbols for Legacy Computing Supplement': '\U0001CC00-\U0001CEBF', 'Ol Onal': '\U0001E5D0-\U0001E5FF' } UPDATE_BLOCKS_VER_17_0_0 = { 'Sidetic': '\U00010940-\U0001095F', 'Sharada Supplement': '\U00011B60-\U00011B7F', 'Tolong Siki': '\U00011DB0-\U00011DEF', 'Beria Erfe': '\U00016EA0-\U00016EDF', 'Tangut Components Supplement': '\U00018D80-\U00018DFF', 'Miscellaneous Symbols Supplement': '\U0001CEC0-\U0001CEFF', 'Tai Yo': '\U0001E6C0-\U0001E6FF', 'CJK Unified Ideographs Extension J': '\U000323B0-\U0003347F' }