diff options
Diffstat (limited to 'Lib/fontTools/unicodedata/Blocks.py')
| -rw-r--r-- | Lib/fontTools/unicodedata/Blocks.py | 778 |
1 files changed, 398 insertions, 380 deletions
diff --git a/Lib/fontTools/unicodedata/Blocks.py b/Lib/fontTools/unicodedata/Blocks.py index 0755074b..2b30be67 100644 --- a/Lib/fontTools/unicodedata/Blocks.py +++ b/Lib/fontTools/unicodedata/Blocks.py @@ -4,9 +4,9 @@ # Source: https://unicode.org/Public/UNIDATA/Blocks.txt # License: http://unicode.org/copyright.html#License # -# Blocks-13.0.0.txt -# Date: 2019-07-10, 19:06:00 GMT [KW] -# © 2019 Unicode®, Inc. +# Blocks-14.0.0.txt +# Date: 2021-01-22, 23:29:00 GMT [KW] +# © 2021 Unicode®, Inc. # For terms of use, see http://www.unicode.org/terms_of_use.html # # Unicode Character Database @@ -37,7 +37,7 @@ RANGES = [ 0x0800, # .. 0x083F ; Samaritan 0x0840, # .. 0x085F ; Mandaic 0x0860, # .. 0x086F ; Syriac Supplement - 0x0870, # .. 0x089F ; No_Block + 0x0870, # .. 0x089F ; Arabic Extended-B 0x08A0, # .. 0x08FF ; Arabic Extended-A 0x0900, # .. 0x097F ; Devanagari 0x0980, # .. 0x09FF ; Bengali @@ -204,9 +204,11 @@ RANGES = [ 0x104B0, # .. 0x104FF ; Osage 0x10500, # .. 0x1052F ; Elbasan 0x10530, # .. 0x1056F ; Caucasian Albanian - 0x10570, # .. 0x105FF ; No_Block + 0x10570, # .. 0x105BF ; Vithkuqi + 0x105C0, # .. 0x105FF ; No_Block 0x10600, # .. 0x1077F ; Linear A - 0x10780, # .. 0x107FF ; No_Block + 0x10780, # .. 0x107BF ; Latin Extended-F + 0x107C0, # .. 0x107FF ; No_Block 0x10800, # .. 0x1083F ; Cypriot Syllabary 0x10840, # .. 0x1085F ; Imperial Aramaic 0x10860, # .. 0x1087F ; Palmyrene @@ -238,7 +240,7 @@ RANGES = [ 0x10EC0, # .. 0x10EFF ; No_Block 0x10F00, # .. 0x10F2F ; Old Sogdian 0x10F30, # .. 0x10F6F ; Sogdian - 0x10F70, # .. 0x10FAF ; No_Block + 0x10F70, # .. 0x10FAF ; Old Uyghur 0x10FB0, # .. 0x10FDF ; Chorasmian 0x10FE0, # .. 0x10FFF ; Elymaic 0x11000, # .. 0x1107F ; Brahmi @@ -262,8 +264,8 @@ RANGES = [ 0x11660, # .. 0x1167F ; Mongolian Supplement 0x11680, # .. 0x116CF ; Takri 0x116D0, # .. 0x116FF ; No_Block - 0x11700, # .. 0x1173F ; Ahom - 0x11740, # .. 0x117FF ; No_Block + 0x11700, # .. 0x1174F ; Ahom + 0x11750, # .. 0x117FF ; No_Block 0x11800, # .. 0x1184F ; Dogra 0x11850, # .. 0x1189F ; No_Block 0x118A0, # .. 0x118FF ; Warang Citi @@ -272,7 +274,7 @@ RANGES = [ 0x119A0, # .. 0x119FF ; Nandinagari 0x11A00, # .. 0x11A4F ; Zanabazar Square 0x11A50, # .. 0x11AAF ; Soyombo - 0x11AB0, # .. 0x11ABF ; No_Block + 0x11AB0, # .. 0x11ABF ; Unified Canadian Aboriginal Syllabics Extended-A 0x11AC0, # .. 0x11AFF ; Pau Cin Hau 0x11B00, # .. 0x11BFF ; No_Block 0x11C00, # .. 0x11C6F ; Bhaiksuki @@ -288,7 +290,8 @@ RANGES = [ 0x12000, # .. 0x123FF ; Cuneiform 0x12400, # .. 0x1247F ; Cuneiform Numbers and Punctuation 0x12480, # .. 0x1254F ; Early Dynastic Cuneiform - 0x12550, # .. 0x12FFF ; No_Block + 0x12550, # .. 0x12F8F ; No_Block + 0x12F90, # .. 0x12FFF ; Cypro-Minoan 0x13000, # .. 0x1342F ; Egyptian Hieroglyphs 0x13430, # .. 0x1343F ; Egyptian Hieroglyph Format Controls 0x13440, # .. 0x143FF ; No_Block @@ -296,7 +299,7 @@ RANGES = [ 0x14680, # .. 0x167FF ; No_Block 0x16800, # .. 0x16A3F ; Bamum Supplement 0x16A40, # .. 0x16A6F ; Mro - 0x16A70, # .. 0x16ACF ; No_Block + 0x16A70, # .. 0x16ACF ; Tangsa 0x16AD0, # .. 0x16AFF ; Bassa Vah 0x16B00, # .. 0x16B8F ; Pahawh Hmong 0x16B90, # .. 0x16E3F ; No_Block @@ -308,8 +311,9 @@ RANGES = [ 0x17000, # .. 0x187FF ; Tangut 0x18800, # .. 0x18AFF ; Tangut Components 0x18B00, # .. 0x18CFF ; Khitan Small Script - 0x18D00, # .. 0x18D8F ; Tangut Supplement - 0x18D90, # .. 0x1AFFF ; No_Block + 0x18D00, # .. 0x18D7F ; Tangut Supplement + 0x18D80, # .. 0x1AFEF ; No_Block + 0x1AFF0, # .. 0x1AFFF ; Kana Extended-B 0x1B000, # .. 0x1B0FF ; Kana Supplement 0x1B100, # .. 0x1B12F ; Kana Extended-A 0x1B130, # .. 0x1B16F ; Small Kana Extension @@ -317,7 +321,9 @@ RANGES = [ 0x1B300, # .. 0x1BBFF ; No_Block 0x1BC00, # .. 0x1BC9F ; Duployan 0x1BCA0, # .. 0x1BCAF ; Shorthand Format Controls - 0x1BCB0, # .. 0x1CFFF ; No_Block + 0x1BCB0, # .. 0x1CEFF ; No_Block + 0x1CF00, # .. 0x1CFCF ; Znamenny Musical Notation + 0x1CFD0, # .. 0x1CFFF ; No_Block 0x1D000, # .. 0x1D0FF ; Byzantine Musical Symbols 0x1D100, # .. 0x1D1FF ; Musical Symbols 0x1D200, # .. 0x1D24F ; Ancient Greek Musical Notation @@ -328,13 +334,16 @@ RANGES = [ 0x1D380, # .. 0x1D3FF ; No_Block 0x1D400, # .. 0x1D7FF ; Mathematical Alphanumeric Symbols 0x1D800, # .. 0x1DAAF ; Sutton SignWriting - 0x1DAB0, # .. 0x1DFFF ; No_Block + 0x1DAB0, # .. 0x1DEFF ; No_Block + 0x1DF00, # .. 0x1DFFF ; Latin Extended-G 0x1E000, # .. 0x1E02F ; Glagolitic Supplement 0x1E030, # .. 0x1E0FF ; No_Block 0x1E100, # .. 0x1E14F ; Nyiakeng Puachue Hmong - 0x1E150, # .. 0x1E2BF ; No_Block + 0x1E150, # .. 0x1E28F ; No_Block + 0x1E290, # .. 0x1E2BF ; Toto 0x1E2C0, # .. 0x1E2FF ; Wancho - 0x1E300, # .. 0x1E7FF ; No_Block + 0x1E300, # .. 0x1E7DF ; No_Block + 0x1E7E0, # .. 0x1E7FF ; Ethiopic Extended-B 0x1E800, # .. 0x1E8DF ; Mende Kikakui 0x1E8E0, # .. 0x1E8FF ; No_Block 0x1E900, # .. 0x1E95F ; Adlam @@ -382,366 +391,375 @@ RANGES = [ ] VALUES = [ - 'Basic Latin', # 0000..007F - 'Latin-1 Supplement', # 0080..00FF - 'Latin Extended-A', # 0100..017F - 'Latin Extended-B', # 0180..024F - 'IPA Extensions', # 0250..02AF - 'Spacing Modifier Letters', # 02B0..02FF - 'Combining Diacritical Marks', # 0300..036F - 'Greek and Coptic', # 0370..03FF - 'Cyrillic', # 0400..04FF - 'Cyrillic Supplement', # 0500..052F - 'Armenian', # 0530..058F - 'Hebrew', # 0590..05FF - 'Arabic', # 0600..06FF - 'Syriac', # 0700..074F - 'Arabic Supplement', # 0750..077F - 'Thaana', # 0780..07BF - 'NKo', # 07C0..07FF - 'Samaritan', # 0800..083F - 'Mandaic', # 0840..085F - 'Syriac Supplement', # 0860..086F - 'No_Block', # 0870..089F - 'Arabic Extended-A', # 08A0..08FF - 'Devanagari', # 0900..097F - 'Bengali', # 0980..09FF - 'Gurmukhi', # 0A00..0A7F - 'Gujarati', # 0A80..0AFF - 'Oriya', # 0B00..0B7F - 'Tamil', # 0B80..0BFF - 'Telugu', # 0C00..0C7F - 'Kannada', # 0C80..0CFF - 'Malayalam', # 0D00..0D7F - 'Sinhala', # 0D80..0DFF - 'Thai', # 0E00..0E7F - 'Lao', # 0E80..0EFF - 'Tibetan', # 0F00..0FFF - 'Myanmar', # 1000..109F - 'Georgian', # 10A0..10FF - 'Hangul Jamo', # 1100..11FF - 'Ethiopic', # 1200..137F - 'Ethiopic Supplement', # 1380..139F - 'Cherokee', # 13A0..13FF - 'Unified Canadian Aboriginal Syllabics', # 1400..167F - 'Ogham', # 1680..169F - 'Runic', # 16A0..16FF - 'Tagalog', # 1700..171F - 'Hanunoo', # 1720..173F - 'Buhid', # 1740..175F - 'Tagbanwa', # 1760..177F - 'Khmer', # 1780..17FF - 'Mongolian', # 1800..18AF - 'Unified Canadian Aboriginal Syllabics Extended', # 18B0..18FF - 'Limbu', # 1900..194F - 'Tai Le', # 1950..197F - 'New Tai Lue', # 1980..19DF - 'Khmer Symbols', # 19E0..19FF - 'Buginese', # 1A00..1A1F - 'Tai Tham', # 1A20..1AAF - 'Combining Diacritical Marks Extended', # 1AB0..1AFF - 'Balinese', # 1B00..1B7F - 'Sundanese', # 1B80..1BBF - 'Batak', # 1BC0..1BFF - 'Lepcha', # 1C00..1C4F - 'Ol Chiki', # 1C50..1C7F - 'Cyrillic Extended-C', # 1C80..1C8F - 'Georgian Extended', # 1C90..1CBF - 'Sundanese Supplement', # 1CC0..1CCF - 'Vedic Extensions', # 1CD0..1CFF - 'Phonetic Extensions', # 1D00..1D7F - 'Phonetic Extensions Supplement', # 1D80..1DBF - 'Combining Diacritical Marks Supplement', # 1DC0..1DFF - 'Latin Extended Additional', # 1E00..1EFF - 'Greek Extended', # 1F00..1FFF - 'General Punctuation', # 2000..206F - 'Superscripts and Subscripts', # 2070..209F - 'Currency Symbols', # 20A0..20CF - 'Combining Diacritical Marks for Symbols', # 20D0..20FF - 'Letterlike Symbols', # 2100..214F - 'Number Forms', # 2150..218F - 'Arrows', # 2190..21FF - 'Mathematical Operators', # 2200..22FF - 'Miscellaneous Technical', # 2300..23FF - 'Control Pictures', # 2400..243F - 'Optical Character Recognition', # 2440..245F - 'Enclosed Alphanumerics', # 2460..24FF - 'Box Drawing', # 2500..257F - 'Block Elements', # 2580..259F - 'Geometric Shapes', # 25A0..25FF - 'Miscellaneous Symbols', # 2600..26FF - 'Dingbats', # 2700..27BF - 'Miscellaneous Mathematical Symbols-A', # 27C0..27EF - 'Supplemental Arrows-A', # 27F0..27FF - 'Braille Patterns', # 2800..28FF - 'Supplemental Arrows-B', # 2900..297F - 'Miscellaneous Mathematical Symbols-B', # 2980..29FF - 'Supplemental Mathematical Operators', # 2A00..2AFF - 'Miscellaneous Symbols and Arrows', # 2B00..2BFF - 'Glagolitic', # 2C00..2C5F - 'Latin Extended-C', # 2C60..2C7F - 'Coptic', # 2C80..2CFF - 'Georgian Supplement', # 2D00..2D2F - 'Tifinagh', # 2D30..2D7F - 'Ethiopic Extended', # 2D80..2DDF - 'Cyrillic Extended-A', # 2DE0..2DFF - 'Supplemental Punctuation', # 2E00..2E7F - 'CJK Radicals Supplement', # 2E80..2EFF - 'Kangxi Radicals', # 2F00..2FDF - 'No_Block', # 2FE0..2FEF - 'Ideographic Description Characters', # 2FF0..2FFF - 'CJK Symbols and Punctuation', # 3000..303F - 'Hiragana', # 3040..309F - 'Katakana', # 30A0..30FF - 'Bopomofo', # 3100..312F - 'Hangul Compatibility Jamo', # 3130..318F - 'Kanbun', # 3190..319F - 'Bopomofo Extended', # 31A0..31BF - 'CJK Strokes', # 31C0..31EF - 'Katakana Phonetic Extensions', # 31F0..31FF - 'Enclosed CJK Letters and Months', # 3200..32FF - 'CJK Compatibility', # 3300..33FF - 'CJK Unified Ideographs Extension A', # 3400..4DBF - 'Yijing Hexagram Symbols', # 4DC0..4DFF - 'CJK Unified Ideographs', # 4E00..9FFF - 'Yi Syllables', # A000..A48F - 'Yi Radicals', # A490..A4CF - 'Lisu', # A4D0..A4FF - 'Vai', # A500..A63F - 'Cyrillic Extended-B', # A640..A69F - 'Bamum', # A6A0..A6FF - 'Modifier Tone Letters', # A700..A71F - 'Latin Extended-D', # A720..A7FF - 'Syloti Nagri', # A800..A82F - 'Common Indic Number Forms', # A830..A83F - 'Phags-pa', # A840..A87F - 'Saurashtra', # A880..A8DF - 'Devanagari Extended', # A8E0..A8FF - 'Kayah Li', # A900..A92F - 'Rejang', # A930..A95F - 'Hangul Jamo Extended-A', # A960..A97F - 'Javanese', # A980..A9DF - 'Myanmar Extended-B', # A9E0..A9FF - 'Cham', # AA00..AA5F - 'Myanmar Extended-A', # AA60..AA7F - 'Tai Viet', # AA80..AADF - 'Meetei Mayek Extensions', # AAE0..AAFF - 'Ethiopic Extended-A', # AB00..AB2F - 'Latin Extended-E', # AB30..AB6F - 'Cherokee Supplement', # AB70..ABBF - 'Meetei Mayek', # ABC0..ABFF - 'Hangul Syllables', # AC00..D7AF - 'Hangul Jamo Extended-B', # D7B0..D7FF - 'High Surrogates', # D800..DB7F - 'High Private Use Surrogates', # DB80..DBFF - 'Low Surrogates', # DC00..DFFF - 'Private Use Area', # E000..F8FF - 'CJK Compatibility Ideographs', # F900..FAFF - 'Alphabetic Presentation Forms', # FB00..FB4F - 'Arabic Presentation Forms-A', # FB50..FDFF - 'Variation Selectors', # FE00..FE0F - 'Vertical Forms', # FE10..FE1F - 'Combining Half Marks', # FE20..FE2F - 'CJK Compatibility Forms', # FE30..FE4F - 'Small Form Variants', # FE50..FE6F - 'Arabic Presentation Forms-B', # FE70..FEFF - 'Halfwidth and Fullwidth Forms', # FF00..FFEF - 'Specials', # FFF0..FFFF - 'Linear B Syllabary', # 10000..1007F - 'Linear B Ideograms', # 10080..100FF - 'Aegean Numbers', # 10100..1013F - 'Ancient Greek Numbers', # 10140..1018F - 'Ancient Symbols', # 10190..101CF - 'Phaistos Disc', # 101D0..101FF - 'No_Block', # 10200..1027F - 'Lycian', # 10280..1029F - 'Carian', # 102A0..102DF - 'Coptic Epact Numbers', # 102E0..102FF - 'Old Italic', # 10300..1032F - 'Gothic', # 10330..1034F - 'Old Permic', # 10350..1037F - 'Ugaritic', # 10380..1039F - 'Old Persian', # 103A0..103DF - 'No_Block', # 103E0..103FF - 'Deseret', # 10400..1044F - 'Shavian', # 10450..1047F - 'Osmanya', # 10480..104AF - 'Osage', # 104B0..104FF - 'Elbasan', # 10500..1052F - 'Caucasian Albanian', # 10530..1056F - 'No_Block', # 10570..105FF - 'Linear A', # 10600..1077F - 'No_Block', # 10780..107FF - 'Cypriot Syllabary', # 10800..1083F - 'Imperial Aramaic', # 10840..1085F - 'Palmyrene', # 10860..1087F - 'Nabataean', # 10880..108AF - 'No_Block', # 108B0..108DF - 'Hatran', # 108E0..108FF - 'Phoenician', # 10900..1091F - 'Lydian', # 10920..1093F - 'No_Block', # 10940..1097F - 'Meroitic Hieroglyphs', # 10980..1099F - 'Meroitic Cursive', # 109A0..109FF - 'Kharoshthi', # 10A00..10A5F - 'Old South Arabian', # 10A60..10A7F - 'Old North Arabian', # 10A80..10A9F - 'No_Block', # 10AA0..10ABF - 'Manichaean', # 10AC0..10AFF - 'Avestan', # 10B00..10B3F - 'Inscriptional Parthian', # 10B40..10B5F - 'Inscriptional Pahlavi', # 10B60..10B7F - 'Psalter Pahlavi', # 10B80..10BAF - 'No_Block', # 10BB0..10BFF - 'Old Turkic', # 10C00..10C4F - 'No_Block', # 10C50..10C7F - 'Old Hungarian', # 10C80..10CFF - 'Hanifi Rohingya', # 10D00..10D3F - 'No_Block', # 10D40..10E5F - 'Rumi Numeral Symbols', # 10E60..10E7F - 'Yezidi', # 10E80..10EBF - 'No_Block', # 10EC0..10EFF - 'Old Sogdian', # 10F00..10F2F - 'Sogdian', # 10F30..10F6F - 'No_Block', # 10F70..10FAF - 'Chorasmian', # 10FB0..10FDF - 'Elymaic', # 10FE0..10FFF - 'Brahmi', # 11000..1107F - 'Kaithi', # 11080..110CF - 'Sora Sompeng', # 110D0..110FF - 'Chakma', # 11100..1114F - 'Mahajani', # 11150..1117F - 'Sharada', # 11180..111DF - 'Sinhala Archaic Numbers', # 111E0..111FF - 'Khojki', # 11200..1124F - 'No_Block', # 11250..1127F - 'Multani', # 11280..112AF - 'Khudawadi', # 112B0..112FF - 'Grantha', # 11300..1137F - 'No_Block', # 11380..113FF - 'Newa', # 11400..1147F - 'Tirhuta', # 11480..114DF - 'No_Block', # 114E0..1157F - 'Siddham', # 11580..115FF - 'Modi', # 11600..1165F - 'Mongolian Supplement', # 11660..1167F - 'Takri', # 11680..116CF - 'No_Block', # 116D0..116FF - 'Ahom', # 11700..1173F - 'No_Block', # 11740..117FF - 'Dogra', # 11800..1184F - 'No_Block', # 11850..1189F - 'Warang Citi', # 118A0..118FF - 'Dives Akuru', # 11900..1195F - 'No_Block', # 11960..1199F - 'Nandinagari', # 119A0..119FF - 'Zanabazar Square', # 11A00..11A4F - 'Soyombo', # 11A50..11AAF - 'No_Block', # 11AB0..11ABF - 'Pau Cin Hau', # 11AC0..11AFF - 'No_Block', # 11B00..11BFF - 'Bhaiksuki', # 11C00..11C6F - 'Marchen', # 11C70..11CBF - 'No_Block', # 11CC0..11CFF - 'Masaram Gondi', # 11D00..11D5F - 'Gunjala Gondi', # 11D60..11DAF - 'No_Block', # 11DB0..11EDF - 'Makasar', # 11EE0..11EFF - 'No_Block', # 11F00..11FAF - 'Lisu Supplement', # 11FB0..11FBF - 'Tamil Supplement', # 11FC0..11FFF - 'Cuneiform', # 12000..123FF - 'Cuneiform Numbers and Punctuation', # 12400..1247F - 'Early Dynastic Cuneiform', # 12480..1254F - 'No_Block', # 12550..12FFF - 'Egyptian Hieroglyphs', # 13000..1342F - 'Egyptian Hieroglyph Format Controls', # 13430..1343F - 'No_Block', # 13440..143FF - 'Anatolian Hieroglyphs', # 14400..1467F - 'No_Block', # 14680..167FF - 'Bamum Supplement', # 16800..16A3F - 'Mro', # 16A40..16A6F - 'No_Block', # 16A70..16ACF - 'Bassa Vah', # 16AD0..16AFF - 'Pahawh Hmong', # 16B00..16B8F - 'No_Block', # 16B90..16E3F - 'Medefaidrin', # 16E40..16E9F - 'No_Block', # 16EA0..16EFF - 'Miao', # 16F00..16F9F - 'No_Block', # 16FA0..16FDF - 'Ideographic Symbols and Punctuation', # 16FE0..16FFF - 'Tangut', # 17000..187FF - 'Tangut Components', # 18800..18AFF - 'Khitan Small Script', # 18B00..18CFF - 'Tangut Supplement', # 18D00..18D8F - 'No_Block', # 18D90..1AFFF - 'Kana Supplement', # 1B000..1B0FF - 'Kana Extended-A', # 1B100..1B12F - 'Small Kana Extension', # 1B130..1B16F - 'Nushu', # 1B170..1B2FF - 'No_Block', # 1B300..1BBFF - 'Duployan', # 1BC00..1BC9F - 'Shorthand Format Controls', # 1BCA0..1BCAF - 'No_Block', # 1BCB0..1CFFF - 'Byzantine Musical Symbols', # 1D000..1D0FF - 'Musical Symbols', # 1D100..1D1FF - 'Ancient Greek Musical Notation', # 1D200..1D24F - 'No_Block', # 1D250..1D2DF - 'Mayan Numerals', # 1D2E0..1D2FF - 'Tai Xuan Jing Symbols', # 1D300..1D35F - 'Counting Rod Numerals', # 1D360..1D37F - 'No_Block', # 1D380..1D3FF - 'Mathematical Alphanumeric Symbols', # 1D400..1D7FF - 'Sutton SignWriting', # 1D800..1DAAF - 'No_Block', # 1DAB0..1DFFF - 'Glagolitic Supplement', # 1E000..1E02F - 'No_Block', # 1E030..1E0FF - 'Nyiakeng Puachue Hmong', # 1E100..1E14F - 'No_Block', # 1E150..1E2BF - 'Wancho', # 1E2C0..1E2FF - 'No_Block', # 1E300..1E7FF - 'Mende Kikakui', # 1E800..1E8DF - 'No_Block', # 1E8E0..1E8FF - 'Adlam', # 1E900..1E95F - 'No_Block', # 1E960..1EC6F - 'Indic Siyaq Numbers', # 1EC70..1ECBF - 'No_Block', # 1ECC0..1ECFF - 'Ottoman Siyaq Numbers', # 1ED00..1ED4F - 'No_Block', # 1ED50..1EDFF - 'Arabic Mathematical Alphabetic Symbols', # 1EE00..1EEFF - 'No_Block', # 1EF00..1EFFF - 'Mahjong Tiles', # 1F000..1F02F - 'Domino Tiles', # 1F030..1F09F - 'Playing Cards', # 1F0A0..1F0FF - 'Enclosed Alphanumeric Supplement', # 1F100..1F1FF - 'Enclosed Ideographic Supplement', # 1F200..1F2FF - 'Miscellaneous Symbols and Pictographs', # 1F300..1F5FF - 'Emoticons', # 1F600..1F64F - 'Ornamental Dingbats', # 1F650..1F67F - 'Transport and Map Symbols', # 1F680..1F6FF - 'Alchemical Symbols', # 1F700..1F77F - 'Geometric Shapes Extended', # 1F780..1F7FF - 'Supplemental Arrows-C', # 1F800..1F8FF - 'Supplemental Symbols and Pictographs', # 1F900..1F9FF - 'Chess Symbols', # 1FA00..1FA6F - 'Symbols and Pictographs Extended-A', # 1FA70..1FAFF - 'Symbols for Legacy Computing', # 1FB00..1FBFF - 'No_Block', # 1FC00..1FFFF - 'CJK Unified Ideographs Extension B', # 20000..2A6DF - 'No_Block', # 2A6E0..2A6FF - 'CJK Unified Ideographs Extension C', # 2A700..2B73F - 'CJK Unified Ideographs Extension D', # 2B740..2B81F - 'CJK Unified Ideographs Extension E', # 2B820..2CEAF - 'CJK Unified Ideographs Extension F', # 2CEB0..2EBEF - 'No_Block', # 2EBF0..2F7FF - 'CJK Compatibility Ideographs Supplement', # 2F800..2FA1F - 'No_Block', # 2FA20..2FFFF - 'CJK Unified Ideographs Extension G', # 30000..3134F - 'No_Block', # 31350..DFFFF - 'Tags', # E0000..E007F - 'No_Block', # E0080..E00FF - 'Variation Selectors Supplement', # E0100..E01EF - 'No_Block', # E01F0..EFFFF - 'Supplementary Private Use Area-A', # F0000..FFFFF - 'Supplementary Private Use Area-B', # 100000..10FFFF + 'Basic Latin', # 0000..007F + 'Latin-1 Supplement', # 0080..00FF + 'Latin Extended-A', # 0100..017F + 'Latin Extended-B', # 0180..024F + 'IPA Extensions', # 0250..02AF + 'Spacing Modifier Letters', # 02B0..02FF + 'Combining Diacritical Marks', # 0300..036F + 'Greek and Coptic', # 0370..03FF + 'Cyrillic', # 0400..04FF + 'Cyrillic Supplement', # 0500..052F + 'Armenian', # 0530..058F + 'Hebrew', # 0590..05FF + 'Arabic', # 0600..06FF + 'Syriac', # 0700..074F + 'Arabic Supplement', # 0750..077F + 'Thaana', # 0780..07BF + 'NKo', # 07C0..07FF + 'Samaritan', # 0800..083F + 'Mandaic', # 0840..085F + 'Syriac Supplement', # 0860..086F + 'Arabic Extended-B', # 0870..089F + 'Arabic Extended-A', # 08A0..08FF + 'Devanagari', # 0900..097F + 'Bengali', # 0980..09FF + 'Gurmukhi', # 0A00..0A7F + 'Gujarati', # 0A80..0AFF + 'Oriya', # 0B00..0B7F + 'Tamil', # 0B80..0BFF + 'Telugu', # 0C00..0C7F + 'Kannada', # 0C80..0CFF + 'Malayalam', # 0D00..0D7F + 'Sinhala', # 0D80..0DFF + 'Thai', # 0E00..0E7F + 'Lao', # 0E80..0EFF + 'Tibetan', # 0F00..0FFF + 'Myanmar', # 1000..109F + 'Georgian', # 10A0..10FF + 'Hangul Jamo', # 1100..11FF + 'Ethiopic', # 1200..137F + 'Ethiopic Supplement', # 1380..139F + 'Cherokee', # 13A0..13FF + 'Unified Canadian Aboriginal Syllabics', # 1400..167F + 'Ogham', # 1680..169F + 'Runic', # 16A0..16FF + 'Tagalog', # 1700..171F + 'Hanunoo', # 1720..173F + 'Buhid', # 1740..175F + 'Tagbanwa', # 1760..177F + 'Khmer', # 1780..17FF + 'Mongolian', # 1800..18AF + 'Unified Canadian Aboriginal Syllabics Extended', # 18B0..18FF + 'Limbu', # 1900..194F + 'Tai Le', # 1950..197F + 'New Tai Lue', # 1980..19DF + 'Khmer Symbols', # 19E0..19FF + 'Buginese', # 1A00..1A1F + 'Tai Tham', # 1A20..1AAF + 'Combining Diacritical Marks Extended', # 1AB0..1AFF + 'Balinese', # 1B00..1B7F + 'Sundanese', # 1B80..1BBF + 'Batak', # 1BC0..1BFF + 'Lepcha', # 1C00..1C4F + 'Ol Chiki', # 1C50..1C7F + 'Cyrillic Extended-C', # 1C80..1C8F + 'Georgian Extended', # 1C90..1CBF + 'Sundanese Supplement', # 1CC0..1CCF + 'Vedic Extensions', # 1CD0..1CFF + 'Phonetic Extensions', # 1D00..1D7F + 'Phonetic Extensions Supplement', # 1D80..1DBF + 'Combining Diacritical Marks Supplement', # 1DC0..1DFF + 'Latin Extended Additional', # 1E00..1EFF + 'Greek Extended', # 1F00..1FFF + 'General Punctuation', # 2000..206F + 'Superscripts and Subscripts', # 2070..209F + 'Currency Symbols', # 20A0..20CF + 'Combining Diacritical Marks for Symbols', # 20D0..20FF + 'Letterlike Symbols', # 2100..214F + 'Number Forms', # 2150..218F + 'Arrows', # 2190..21FF + 'Mathematical Operators', # 2200..22FF + 'Miscellaneous Technical', # 2300..23FF + 'Control Pictures', # 2400..243F + 'Optical Character Recognition', # 2440..245F + 'Enclosed Alphanumerics', # 2460..24FF + 'Box Drawing', # 2500..257F + 'Block Elements', # 2580..259F + 'Geometric Shapes', # 25A0..25FF + 'Miscellaneous Symbols', # 2600..26FF + 'Dingbats', # 2700..27BF + 'Miscellaneous Mathematical Symbols-A', # 27C0..27EF + 'Supplemental Arrows-A', # 27F0..27FF + 'Braille Patterns', # 2800..28FF + 'Supplemental Arrows-B', # 2900..297F + 'Miscellaneous Mathematical Symbols-B', # 2980..29FF + 'Supplemental Mathematical Operators', # 2A00..2AFF + 'Miscellaneous Symbols and Arrows', # 2B00..2BFF + 'Glagolitic', # 2C00..2C5F + 'Latin Extended-C', # 2C60..2C7F + 'Coptic', # 2C80..2CFF + 'Georgian Supplement', # 2D00..2D2F + 'Tifinagh', # 2D30..2D7F + 'Ethiopic Extended', # 2D80..2DDF + 'Cyrillic Extended-A', # 2DE0..2DFF + 'Supplemental Punctuation', # 2E00..2E7F + 'CJK Radicals Supplement', # 2E80..2EFF + 'Kangxi Radicals', # 2F00..2FDF + 'No_Block', # 2FE0..2FEF + 'Ideographic Description Characters', # 2FF0..2FFF + 'CJK Symbols and Punctuation', # 3000..303F + 'Hiragana', # 3040..309F + 'Katakana', # 30A0..30FF + 'Bopomofo', # 3100..312F + 'Hangul Compatibility Jamo', # 3130..318F + 'Kanbun', # 3190..319F + 'Bopomofo Extended', # 31A0..31BF + 'CJK Strokes', # 31C0..31EF + 'Katakana Phonetic Extensions', # 31F0..31FF + 'Enclosed CJK Letters and Months', # 3200..32FF + 'CJK Compatibility', # 3300..33FF + 'CJK Unified Ideographs Extension A', # 3400..4DBF + 'Yijing Hexagram Symbols', # 4DC0..4DFF + 'CJK Unified Ideographs', # 4E00..9FFF + 'Yi Syllables', # A000..A48F + 'Yi Radicals', # A490..A4CF + 'Lisu', # A4D0..A4FF + 'Vai', # A500..A63F + 'Cyrillic Extended-B', # A640..A69F + 'Bamum', # A6A0..A6FF + 'Modifier Tone Letters', # A700..A71F + 'Latin Extended-D', # A720..A7FF + 'Syloti Nagri', # A800..A82F + 'Common Indic Number Forms', # A830..A83F + 'Phags-pa', # A840..A87F + 'Saurashtra', # A880..A8DF + 'Devanagari Extended', # A8E0..A8FF + 'Kayah Li', # A900..A92F + 'Rejang', # A930..A95F + 'Hangul Jamo Extended-A', # A960..A97F + 'Javanese', # A980..A9DF + 'Myanmar Extended-B', # A9E0..A9FF + 'Cham', # AA00..AA5F + 'Myanmar Extended-A', # AA60..AA7F + 'Tai Viet', # AA80..AADF + 'Meetei Mayek Extensions', # AAE0..AAFF + 'Ethiopic Extended-A', # AB00..AB2F + 'Latin Extended-E', # AB30..AB6F + 'Cherokee Supplement', # AB70..ABBF + 'Meetei Mayek', # ABC0..ABFF + 'Hangul Syllables', # AC00..D7AF + 'Hangul Jamo Extended-B', # D7B0..D7FF + 'High Surrogates', # D800..DB7F + 'High Private Use Surrogates', # DB80..DBFF + 'Low Surrogates', # DC00..DFFF + 'Private Use Area', # E000..F8FF + 'CJK Compatibility Ideographs', # F900..FAFF + 'Alphabetic Presentation Forms', # FB00..FB4F + 'Arabic Presentation Forms-A', # FB50..FDFF + 'Variation Selectors', # FE00..FE0F + 'Vertical Forms', # FE10..FE1F + 'Combining Half Marks', # FE20..FE2F + 'CJK Compatibility Forms', # FE30..FE4F + 'Small Form Variants', # FE50..FE6F + 'Arabic Presentation Forms-B', # FE70..FEFF + 'Halfwidth and Fullwidth Forms', # FF00..FFEF + 'Specials', # FFF0..FFFF + 'Linear B Syllabary', # 10000..1007F + 'Linear B Ideograms', # 10080..100FF + 'Aegean Numbers', # 10100..1013F + 'Ancient Greek Numbers', # 10140..1018F + 'Ancient Symbols', # 10190..101CF + 'Phaistos Disc', # 101D0..101FF + 'No_Block', # 10200..1027F + 'Lycian', # 10280..1029F + 'Carian', # 102A0..102DF + 'Coptic Epact Numbers', # 102E0..102FF + 'Old Italic', # 10300..1032F + 'Gothic', # 10330..1034F + 'Old Permic', # 10350..1037F + 'Ugaritic', # 10380..1039F + 'Old Persian', # 103A0..103DF + 'No_Block', # 103E0..103FF + 'Deseret', # 10400..1044F + 'Shavian', # 10450..1047F + 'Osmanya', # 10480..104AF + 'Osage', # 104B0..104FF + 'Elbasan', # 10500..1052F + 'Caucasian Albanian', # 10530..1056F + 'Vithkuqi', # 10570..105BF + 'No_Block', # 105C0..105FF + 'Linear A', # 10600..1077F + 'Latin Extended-F', # 10780..107BF + 'No_Block', # 107C0..107FF + 'Cypriot Syllabary', # 10800..1083F + 'Imperial Aramaic', # 10840..1085F + 'Palmyrene', # 10860..1087F + 'Nabataean', # 10880..108AF + 'No_Block', # 108B0..108DF + 'Hatran', # 108E0..108FF + 'Phoenician', # 10900..1091F + 'Lydian', # 10920..1093F + 'No_Block', # 10940..1097F + 'Meroitic Hieroglyphs', # 10980..1099F + 'Meroitic Cursive', # 109A0..109FF + 'Kharoshthi', # 10A00..10A5F + 'Old South Arabian', # 10A60..10A7F + 'Old North Arabian', # 10A80..10A9F + 'No_Block', # 10AA0..10ABF + 'Manichaean', # 10AC0..10AFF + 'Avestan', # 10B00..10B3F + 'Inscriptional Parthian', # 10B40..10B5F + 'Inscriptional Pahlavi', # 10B60..10B7F + 'Psalter Pahlavi', # 10B80..10BAF + 'No_Block', # 10BB0..10BFF + 'Old Turkic', # 10C00..10C4F + 'No_Block', # 10C50..10C7F + 'Old Hungarian', # 10C80..10CFF + 'Hanifi Rohingya', # 10D00..10D3F + 'No_Block', # 10D40..10E5F + 'Rumi Numeral Symbols', # 10E60..10E7F + 'Yezidi', # 10E80..10EBF + 'No_Block', # 10EC0..10EFF + 'Old Sogdian', # 10F00..10F2F + 'Sogdian', # 10F30..10F6F + 'Old Uyghur', # 10F70..10FAF + 'Chorasmian', # 10FB0..10FDF + 'Elymaic', # 10FE0..10FFF + 'Brahmi', # 11000..1107F + 'Kaithi', # 11080..110CF + 'Sora Sompeng', # 110D0..110FF + 'Chakma', # 11100..1114F + 'Mahajani', # 11150..1117F + 'Sharada', # 11180..111DF + 'Sinhala Archaic Numbers', # 111E0..111FF + 'Khojki', # 11200..1124F + 'No_Block', # 11250..1127F + 'Multani', # 11280..112AF + 'Khudawadi', # 112B0..112FF + 'Grantha', # 11300..1137F + 'No_Block', # 11380..113FF + 'Newa', # 11400..1147F + 'Tirhuta', # 11480..114DF + 'No_Block', # 114E0..1157F + 'Siddham', # 11580..115FF + 'Modi', # 11600..1165F + 'Mongolian Supplement', # 11660..1167F + 'Takri', # 11680..116CF + 'No_Block', # 116D0..116FF + 'Ahom', # 11700..1174F + 'No_Block', # 11750..117FF + 'Dogra', # 11800..1184F + 'No_Block', # 11850..1189F + 'Warang Citi', # 118A0..118FF + 'Dives Akuru', # 11900..1195F + 'No_Block', # 11960..1199F + 'Nandinagari', # 119A0..119FF + 'Zanabazar Square', # 11A00..11A4F + 'Soyombo', # 11A50..11AAF + 'Unified Canadian Aboriginal Syllabics Extended-A', # 11AB0..11ABF + 'Pau Cin Hau', # 11AC0..11AFF + 'No_Block', # 11B00..11BFF + 'Bhaiksuki', # 11C00..11C6F + 'Marchen', # 11C70..11CBF + 'No_Block', # 11CC0..11CFF + 'Masaram Gondi', # 11D00..11D5F + 'Gunjala Gondi', # 11D60..11DAF + 'No_Block', # 11DB0..11EDF + 'Makasar', # 11EE0..11EFF + 'No_Block', # 11F00..11FAF + 'Lisu Supplement', # 11FB0..11FBF + 'Tamil Supplement', # 11FC0..11FFF + 'Cuneiform', # 12000..123FF + 'Cuneiform Numbers and Punctuation', # 12400..1247F + 'Early Dynastic Cuneiform', # 12480..1254F + 'No_Block', # 12550..12F8F + 'Cypro-Minoan', # 12F90..12FFF + 'Egyptian Hieroglyphs', # 13000..1342F + 'Egyptian Hieroglyph Format Controls', # 13430..1343F + 'No_Block', # 13440..143FF + 'Anatolian Hieroglyphs', # 14400..1467F + 'No_Block', # 14680..167FF + 'Bamum Supplement', # 16800..16A3F + 'Mro', # 16A40..16A6F + 'Tangsa', # 16A70..16ACF + 'Bassa Vah', # 16AD0..16AFF + 'Pahawh Hmong', # 16B00..16B8F + 'No_Block', # 16B90..16E3F + 'Medefaidrin', # 16E40..16E9F + 'No_Block', # 16EA0..16EFF + 'Miao', # 16F00..16F9F + 'No_Block', # 16FA0..16FDF + 'Ideographic Symbols and Punctuation', # 16FE0..16FFF + 'Tangut', # 17000..187FF + 'Tangut Components', # 18800..18AFF + 'Khitan Small Script', # 18B00..18CFF + 'Tangut Supplement', # 18D00..18D7F + 'No_Block', # 18D80..1AFEF + 'Kana Extended-B', # 1AFF0..1AFFF + 'Kana Supplement', # 1B000..1B0FF + 'Kana Extended-A', # 1B100..1B12F + 'Small Kana Extension', # 1B130..1B16F + 'Nushu', # 1B170..1B2FF + 'No_Block', # 1B300..1BBFF + 'Duployan', # 1BC00..1BC9F + 'Shorthand Format Controls', # 1BCA0..1BCAF + 'No_Block', # 1BCB0..1CEFF + 'Znamenny Musical Notation', # 1CF00..1CFCF + 'No_Block', # 1CFD0..1CFFF + 'Byzantine Musical Symbols', # 1D000..1D0FF + 'Musical Symbols', # 1D100..1D1FF + 'Ancient Greek Musical Notation', # 1D200..1D24F + 'No_Block', # 1D250..1D2DF + 'Mayan Numerals', # 1D2E0..1D2FF + 'Tai Xuan Jing Symbols', # 1D300..1D35F + 'Counting Rod Numerals', # 1D360..1D37F + 'No_Block', # 1D380..1D3FF + 'Mathematical Alphanumeric Symbols', # 1D400..1D7FF + 'Sutton SignWriting', # 1D800..1DAAF + 'No_Block', # 1DAB0..1DEFF + 'Latin Extended-G', # 1DF00..1DFFF + 'Glagolitic Supplement', # 1E000..1E02F + 'No_Block', # 1E030..1E0FF + 'Nyiakeng Puachue Hmong', # 1E100..1E14F + 'No_Block', # 1E150..1E28F + 'Toto', # 1E290..1E2BF + 'Wancho', # 1E2C0..1E2FF + 'No_Block', # 1E300..1E7DF + 'Ethiopic Extended-B', # 1E7E0..1E7FF + 'Mende Kikakui', # 1E800..1E8DF + 'No_Block', # 1E8E0..1E8FF + 'Adlam', # 1E900..1E95F + 'No_Block', # 1E960..1EC6F + 'Indic Siyaq Numbers', # 1EC70..1ECBF + 'No_Block', # 1ECC0..1ECFF + 'Ottoman Siyaq Numbers', # 1ED00..1ED4F + 'No_Block', # 1ED50..1EDFF + 'Arabic Mathematical Alphabetic Symbols', # 1EE00..1EEFF + 'No_Block', # 1EF00..1EFFF + 'Mahjong Tiles', # 1F000..1F02F + 'Domino Tiles', # 1F030..1F09F + 'Playing Cards', # 1F0A0..1F0FF + 'Enclosed Alphanumeric Supplement', # 1F100..1F1FF + 'Enclosed Ideographic Supplement', # 1F200..1F2FF + 'Miscellaneous Symbols and Pictographs', # 1F300..1F5FF + 'Emoticons', # 1F600..1F64F + 'Ornamental Dingbats', # 1F650..1F67F + 'Transport and Map Symbols', # 1F680..1F6FF + 'Alchemical Symbols', # 1F700..1F77F + 'Geometric Shapes Extended', # 1F780..1F7FF + 'Supplemental Arrows-C', # 1F800..1F8FF + 'Supplemental Symbols and Pictographs', # 1F900..1F9FF + 'Chess Symbols', # 1FA00..1FA6F + 'Symbols and Pictographs Extended-A', # 1FA70..1FAFF + 'Symbols for Legacy Computing', # 1FB00..1FBFF + 'No_Block', # 1FC00..1FFFF + 'CJK Unified Ideographs Extension B', # 20000..2A6DF + 'No_Block', # 2A6E0..2A6FF + 'CJK Unified Ideographs Extension C', # 2A700..2B73F + 'CJK Unified Ideographs Extension D', # 2B740..2B81F + 'CJK Unified Ideographs Extension E', # 2B820..2CEAF + 'CJK Unified Ideographs Extension F', # 2CEB0..2EBEF + 'No_Block', # 2EBF0..2F7FF + 'CJK Compatibility Ideographs Supplement', # 2F800..2FA1F + 'No_Block', # 2FA20..2FFFF + 'CJK Unified Ideographs Extension G', # 30000..3134F + 'No_Block', # 31350..DFFFF + 'Tags', # E0000..E007F + 'No_Block', # E0080..E00FF + 'Variation Selectors Supplement', # E0100..E01EF + 'No_Block', # E01F0..EFFFF + 'Supplementary Private Use Area-A', # F0000..FFFFF + 'Supplementary Private Use Area-B', # 100000..10FFFF ] |