update to unicode 14.0

This commit is contained in:
Yao Wei (魏銘廷) 2021-10-31 23:24:18 +08:00
parent 563730f8ce
commit 390640a357
No known key found for this signature in database
GPG Key ID: 9757B044D3444C33
5 changed files with 745 additions and 606 deletions

View File

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

View File

@ -4,9 +4,9 @@
# Source: https://unicode.org/Public/UNIDATA/ScriptExtensions.txt # Source: https://unicode.org/Public/UNIDATA/ScriptExtensions.txt
# License: http://unicode.org/copyright.html#License # License: http://unicode.org/copyright.html#License
# #
# ScriptExtensions-13.0.0.txt # ScriptExtensions-14.0.0.txt
# Date: 2020-01-22, 00:07:43 GMT # Date: 2021-06-04, 02:19:38 GMT
# © 2020 Unicode®, Inc. # © 2021 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # 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 # For terms of use, see http://www.unicode.org/terms_of_use.html
# #
@ -17,10 +17,10 @@
# with more than one script, but with a limited number of scripts. # with more than one script, but with a limited number of scripts.
# For each code point, there is one or more property values. Each such value is a Script property value. # For each code point, there is one or more property values. Each such value is a Script property value.
# For more information, see: # For more information, see:
# UAX #24, Unicode Script Property: http://www.unicode.org/reports/tr24/ # UAX #24, Unicode Script Property: https://www.unicode.org/reports/tr24/
# Especially the sections: # Especially the sections:
# http://www.unicode.org/reports/tr24/#Assignment_Script_Values # https://www.unicode.org/reports/tr24/#Assignment_Script_Values
# http://www.unicode.org/reports/tr24/#Assignment_ScriptX_Values # https://www.unicode.org/reports/tr24/#Assignment_ScriptX_Values
# #
# Each Script_Extensions value in this file consists of a set # Each Script_Extensions value in this file consists of a set
# of one or more abbreviated Script property values. The ordering of the # of one or more abbreviated Script property values. The ordering of the
@ -53,14 +53,14 @@ RANGES = [
0x0485, # .. 0x0486 ; {'Cyrl', 'Latn'} 0x0485, # .. 0x0486 ; {'Cyrl', 'Latn'}
0x0487, # .. 0x0487 ; {'Cyrl', 'Glag'} 0x0487, # .. 0x0487 ; {'Cyrl', 'Glag'}
0x0488, # .. 0x060B ; None 0x0488, # .. 0x060B ; None
0x060C, # .. 0x060C ; {'Arab', 'Rohg', 'Syrc', 'Thaa', 'Yezi'} 0x060C, # .. 0x060C ; {'Arab', 'Nkoo', 'Rohg', 'Syrc', 'Thaa', 'Yezi'}
0x060D, # .. 0x061A ; None 0x060D, # .. 0x061A ; None
0x061B, # .. 0x061B ; {'Arab', 'Rohg', 'Syrc', 'Thaa', 'Yezi'} 0x061B, # .. 0x061B ; {'Arab', 'Nkoo', 'Rohg', 'Syrc', 'Thaa', 'Yezi'}
0x061C, # .. 0x061C ; {'Arab', 'Syrc', 'Thaa'} 0x061C, # .. 0x061C ; {'Arab', 'Syrc', 'Thaa'}
0x061D, # .. 0x061E ; None 0x061D, # .. 0x061E ; None
0x061F, # .. 0x061F ; {'Arab', 'Rohg', 'Syrc', 'Thaa', 'Yezi'} 0x061F, # .. 0x061F ; {'Adlm', 'Arab', 'Nkoo', 'Rohg', 'Syrc', 'Thaa', 'Yezi'}
0x0620, # .. 0x063F ; None 0x0620, # .. 0x063F ; None
0x0640, # .. 0x0640 ; {'Adlm', 'Arab', 'Mand', 'Mani', 'Phlp', 'Rohg', 'Sogd', 'Syrc'} 0x0640, # .. 0x0640 ; {'Adlm', 'Arab', 'Mand', 'Mani', 'Ougr', 'Phlp', 'Rohg', 'Sogd', 'Syrc'}
0x0641, # .. 0x064A ; None 0x0641, # .. 0x064A ; None
0x064B, # .. 0x0655 ; {'Arab', 'Syrc'} 0x064B, # .. 0x0655 ; {'Arab', 'Syrc'}
0x0656, # .. 0x065F ; None 0x0656, # .. 0x065F ; None
@ -129,7 +129,9 @@ RANGES = [
0x1DC0, # .. 0x1DC1 ; {'Grek'} 0x1DC0, # .. 0x1DC1 ; {'Grek'}
0x1DC2, # .. 0x1DF7 ; None 0x1DC2, # .. 0x1DF7 ; None
0x1DF8, # .. 0x1DF8 ; {'Cyrl', 'Syrc'} 0x1DF8, # .. 0x1DF8 ; {'Cyrl', 'Syrc'}
0x1DF9, # .. 0x202E ; None 0x1DF9, # .. 0x1DF9 ; None
0x1DFA, # .. 0x1DFA ; {'Syrc'}
0x1DFB, # .. 0x202E ; None
0x202F, # .. 0x202F ; {'Latn', 'Mong'} 0x202F, # .. 0x202F ; {'Latn', 'Mong'}
0x2030, # .. 0x20EF ; None 0x2030, # .. 0x20EF ; None
0x20F0, # .. 0x20F0 ; {'Deva', 'Gran', 'Latn'} 0x20F0, # .. 0x20F0 ; {'Deva', 'Gran', 'Latn'}
@ -197,7 +199,9 @@ RANGES = [
0xA92E, # .. 0xA92E ; {'Kali', 'Latn', 'Mymr'} 0xA92E, # .. 0xA92E ; {'Kali', 'Latn', 'Mymr'}
0xA92F, # .. 0xA9CE ; None 0xA92F, # .. 0xA9CE ; None
0xA9CF, # .. 0xA9CF ; {'Bugi', 'Java'} 0xA9CF, # .. 0xA9CF ; {'Bugi', 'Java'}
0xA9D0, # .. 0xFDF1 ; None 0xA9D0, # .. 0xFD3D ; None
0xFD3E, # .. 0xFD3F ; {'Arab', 'Nkoo'}
0xFD40, # .. 0xFDF1 ; None
0xFDF2, # .. 0xFDF2 ; {'Arab', 'Thaa'} 0xFDF2, # .. 0xFDF2 ; {'Arab', 'Thaa'}
0xFDF3, # .. 0xFDFC ; None 0xFDF3, # .. 0xFDFC ; None
0xFDFD, # .. 0xFDFD ; {'Arab', 'Thaa'} 0xFDFD, # .. 0xFDFD ; {'Arab', 'Thaa'}
@ -210,14 +214,17 @@ RANGES = [
0xFF71, # .. 0xFF9D ; None 0xFF71, # .. 0xFF9D ; None
0xFF9E, # .. 0xFF9F ; {'Hira', 'Kana'} 0xFF9E, # .. 0xFF9F ; {'Hira', 'Kana'}
0xFFA0, # .. 0x100FF ; None 0xFFA0, # .. 0x100FF ; None
0x10100, # .. 0x10102 ; {'Cprt', 'Linb'} 0x10100, # .. 0x10101 ; {'Cpmn', 'Cprt', 'Linb'}
0x10102, # .. 0x10102 ; {'Cprt', 'Linb'}
0x10103, # .. 0x10106 ; None 0x10103, # .. 0x10106 ; None
0x10107, # .. 0x10133 ; {'Cprt', 'Lina', 'Linb'} 0x10107, # .. 0x10133 ; {'Cprt', 'Lina', 'Linb'}
0x10134, # .. 0x10136 ; None 0x10134, # .. 0x10136 ; None
0x10137, # .. 0x1013F ; {'Cprt', 'Linb'} 0x10137, # .. 0x1013F ; {'Cprt', 'Linb'}
0x10140, # .. 0x102DF ; None 0x10140, # .. 0x102DF ; None
0x102E0, # .. 0x102FB ; {'Arab', 'Copt'} 0x102E0, # .. 0x102FB ; {'Arab', 'Copt'}
0x102FC, # .. 0x11300 ; None 0x102FC, # .. 0x10AF1 ; None
0x10AF2, # .. 0x10AF2 ; {'Mani', 'Ougr'}
0x10AF3, # .. 0x11300 ; None
0x11301, # .. 0x11301 ; {'Gran', 'Taml'} 0x11301, # .. 0x11301 ; {'Gran', 'Taml'}
0x11302, # .. 0x11302 ; None 0x11302, # .. 0x11302 ; None
0x11303, # .. 0x11303 ; {'Gran', 'Taml'} 0x11303, # .. 0x11303 ; {'Gran', 'Taml'}
@ -249,14 +256,14 @@ VALUES = [
{'Cyrl', 'Latn'}, # 0485..0486 {'Cyrl', 'Latn'}, # 0485..0486
{'Cyrl', 'Glag'}, # 0487..0487 {'Cyrl', 'Glag'}, # 0487..0487
None, # 0488..060B None, # 0488..060B
{'Arab', 'Rohg', 'Syrc', 'Thaa', 'Yezi'}, # 060C..060C {'Arab', 'Nkoo', 'Rohg', 'Syrc', 'Thaa', 'Yezi'}, # 060C..060C
None, # 060D..061A None, # 060D..061A
{'Arab', 'Rohg', 'Syrc', 'Thaa', 'Yezi'}, # 061B..061B {'Arab', 'Nkoo', 'Rohg', 'Syrc', 'Thaa', 'Yezi'}, # 061B..061B
{'Arab', 'Syrc', 'Thaa'}, # 061C..061C {'Arab', 'Syrc', 'Thaa'}, # 061C..061C
None, # 061D..061E None, # 061D..061E
{'Arab', 'Rohg', 'Syrc', 'Thaa', 'Yezi'}, # 061F..061F {'Adlm', 'Arab', 'Nkoo', 'Rohg', 'Syrc', 'Thaa', 'Yezi'}, # 061F..061F
None, # 0620..063F None, # 0620..063F
{'Adlm', 'Arab', 'Mand', 'Mani', 'Phlp', 'Rohg', 'Sogd', 'Syrc'}, # 0640..0640 {'Adlm', 'Arab', 'Mand', 'Mani', 'Ougr', 'Phlp', 'Rohg', 'Sogd', 'Syrc'}, # 0640..0640
None, # 0641..064A None, # 0641..064A
{'Arab', 'Syrc'}, # 064B..0655 {'Arab', 'Syrc'}, # 064B..0655
None, # 0656..065F None, # 0656..065F
@ -325,7 +332,9 @@ VALUES = [
{'Grek'}, # 1DC0..1DC1 {'Grek'}, # 1DC0..1DC1
None, # 1DC2..1DF7 None, # 1DC2..1DF7
{'Cyrl', 'Syrc'}, # 1DF8..1DF8 {'Cyrl', 'Syrc'}, # 1DF8..1DF8
None, # 1DF9..202E None, # 1DF9..1DF9
{'Syrc'}, # 1DFA..1DFA
None, # 1DFB..202E
{'Latn', 'Mong'}, # 202F..202F {'Latn', 'Mong'}, # 202F..202F
None, # 2030..20EF None, # 2030..20EF
{'Deva', 'Gran', 'Latn'}, # 20F0..20F0 {'Deva', 'Gran', 'Latn'}, # 20F0..20F0
@ -393,7 +402,9 @@ VALUES = [
{'Kali', 'Latn', 'Mymr'}, # A92E..A92E {'Kali', 'Latn', 'Mymr'}, # A92E..A92E
None, # A92F..A9CE None, # A92F..A9CE
{'Bugi', 'Java'}, # A9CF..A9CF {'Bugi', 'Java'}, # A9CF..A9CF
None, # A9D0..FDF1 None, # A9D0..FD3D
{'Arab', 'Nkoo'}, # FD3E..FD3F
None, # FD40..FDF1
{'Arab', 'Thaa'}, # FDF2..FDF2 {'Arab', 'Thaa'}, # FDF2..FDF2
None, # FDF3..FDFC None, # FDF3..FDFC
{'Arab', 'Thaa'}, # FDFD..FDFD {'Arab', 'Thaa'}, # FDFD..FDFD
@ -406,14 +417,17 @@ VALUES = [
None, # FF71..FF9D None, # FF71..FF9D
{'Hira', 'Kana'}, # FF9E..FF9F {'Hira', 'Kana'}, # FF9E..FF9F
None, # FFA0..100FF None, # FFA0..100FF
{'Cprt', 'Linb'}, # 10100..10102 {'Cpmn', 'Cprt', 'Linb'}, # 10100..10101
{'Cprt', 'Linb'}, # 10102..10102
None, # 10103..10106 None, # 10103..10106
{'Cprt', 'Lina', 'Linb'}, # 10107..10133 {'Cprt', 'Lina', 'Linb'}, # 10107..10133
None, # 10134..10136 None, # 10134..10136
{'Cprt', 'Linb'}, # 10137..1013F {'Cprt', 'Linb'}, # 10137..1013F
None, # 10140..102DF None, # 10140..102DF
{'Arab', 'Copt'}, # 102E0..102FB {'Arab', 'Copt'}, # 102E0..102FB
None, # 102FC..11300 None, # 102FC..10AF1
{'Mani', 'Ougr'}, # 10AF2..10AF2
None, # 10AF3..11300
{'Gran', 'Taml'}, # 11301..11301 {'Gran', 'Taml'}, # 11301..11301
None, # 11302..11302 None, # 11302..11302
{'Gran', 'Taml'}, # 11303..11303 {'Gran', 'Taml'}, # 11303..11303

View File

@ -4,19 +4,19 @@
# Source: https://unicode.org/Public/UNIDATA/Scripts.txt # Source: https://unicode.org/Public/UNIDATA/Scripts.txt
# License: http://unicode.org/copyright.html#License # License: http://unicode.org/copyright.html#License
# #
# Scripts-13.0.0.txt # Scripts-14.0.0.txt
# Date: 2020-01-22, 00:07:43 GMT # Date: 2021-07-10, 00:35:31 GMT
# © 2020 Unicode®, Inc. # © 2021 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. # 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 # For terms of use, see http://www.unicode.org/terms_of_use.html
# #
# Unicode Character Database # Unicode Character Database
# For documentation, see http://www.unicode.org/reports/tr44/ # For documentation, see http://www.unicode.org/reports/tr44/
# For more information, see: # For more information, see:
# UAX #24, Unicode Script Property: http://www.unicode.org/reports/tr24/ # UAX #24, Unicode Script Property: https://www.unicode.org/reports/tr24/
# Especially the sections: # Especially the sections:
# http://www.unicode.org/reports/tr24/#Assignment_Script_Values # https://www.unicode.org/reports/tr24/#Assignment_Script_Values
# http://www.unicode.org/reports/tr24/#Assignment_ScriptX_Values # https://www.unicode.org/reports/tr24/#Assignment_ScriptX_Values
# #
@ -84,9 +84,7 @@ RANGES = [
0x060C, # .. 0x060C ; Common 0x060C, # .. 0x060C ; Common
0x060D, # .. 0x061A ; Arabic 0x060D, # .. 0x061A ; Arabic
0x061B, # .. 0x061B ; Common 0x061B, # .. 0x061B ; Common
0x061C, # .. 0x061C ; Arabic 0x061C, # .. 0x061E ; Arabic
0x061D, # .. 0x061D ; Unknown
0x061E, # .. 0x061E ; Arabic
0x061F, # .. 0x061F ; Common 0x061F, # .. 0x061F ; Common
0x0620, # .. 0x063F ; Arabic 0x0620, # .. 0x063F ; Arabic
0x0640, # .. 0x0640 ; Common 0x0640, # .. 0x0640 ; Common
@ -117,12 +115,12 @@ RANGES = [
0x085E, # .. 0x085E ; Mandaic 0x085E, # .. 0x085E ; Mandaic
0x085F, # .. 0x085F ; Unknown 0x085F, # .. 0x085F ; Unknown
0x0860, # .. 0x086A ; Syriac 0x0860, # .. 0x086A ; Syriac
0x086B, # .. 0x089F ; Unknown 0x086B, # .. 0x086F ; Unknown
0x08A0, # .. 0x08B4 ; Arabic 0x0870, # .. 0x088E ; Arabic
0x08B5, # .. 0x08B5 ; Unknown 0x088F, # .. 0x088F ; Unknown
0x08B6, # .. 0x08C7 ; Arabic 0x0890, # .. 0x0891 ; Arabic
0x08C8, # .. 0x08D2 ; Unknown 0x0892, # .. 0x0897 ; Unknown
0x08D3, # .. 0x08E1 ; Arabic 0x0898, # .. 0x08E1 ; Arabic
0x08E2, # .. 0x08E2 ; Common 0x08E2, # .. 0x08E2 ; Common
0x08E3, # .. 0x08FF ; Arabic 0x08E3, # .. 0x08FF ; Arabic
0x0900, # .. 0x0950 ; Devanagari 0x0900, # .. 0x0950 ; Devanagari
@ -285,8 +283,8 @@ RANGES = [
0x0C12, # .. 0x0C28 ; Telugu 0x0C12, # .. 0x0C28 ; Telugu
0x0C29, # .. 0x0C29 ; Unknown 0x0C29, # .. 0x0C29 ; Unknown
0x0C2A, # .. 0x0C39 ; Telugu 0x0C2A, # .. 0x0C39 ; Telugu
0x0C3A, # .. 0x0C3C ; Unknown 0x0C3A, # .. 0x0C3B ; Unknown
0x0C3D, # .. 0x0C44 ; Telugu 0x0C3C, # .. 0x0C44 ; Telugu
0x0C45, # .. 0x0C45 ; Unknown 0x0C45, # .. 0x0C45 ; Unknown
0x0C46, # .. 0x0C48 ; Telugu 0x0C46, # .. 0x0C48 ; Telugu
0x0C49, # .. 0x0C49 ; Unknown 0x0C49, # .. 0x0C49 ; Unknown
@ -295,7 +293,9 @@ RANGES = [
0x0C55, # .. 0x0C56 ; Telugu 0x0C55, # .. 0x0C56 ; Telugu
0x0C57, # .. 0x0C57 ; Unknown 0x0C57, # .. 0x0C57 ; Unknown
0x0C58, # .. 0x0C5A ; Telugu 0x0C58, # .. 0x0C5A ; Telugu
0x0C5B, # .. 0x0C5F ; Unknown 0x0C5B, # .. 0x0C5C ; Unknown
0x0C5D, # .. 0x0C5D ; Telugu
0x0C5E, # .. 0x0C5F ; Unknown
0x0C60, # .. 0x0C63 ; Telugu 0x0C60, # .. 0x0C63 ; Telugu
0x0C64, # .. 0x0C65 ; Unknown 0x0C64, # .. 0x0C65 ; Unknown
0x0C66, # .. 0x0C6F ; Telugu 0x0C66, # .. 0x0C6F ; Telugu
@ -318,8 +318,8 @@ RANGES = [
0x0CCA, # .. 0x0CCD ; Kannada 0x0CCA, # .. 0x0CCD ; Kannada
0x0CCE, # .. 0x0CD4 ; Unknown 0x0CCE, # .. 0x0CD4 ; Unknown
0x0CD5, # .. 0x0CD6 ; Kannada 0x0CD5, # .. 0x0CD6 ; Kannada
0x0CD7, # .. 0x0CDD ; Unknown 0x0CD7, # .. 0x0CDC ; Unknown
0x0CDE, # .. 0x0CDE ; Kannada 0x0CDD, # .. 0x0CDE ; Kannada
0x0CDF, # .. 0x0CDF ; Unknown 0x0CDF, # .. 0x0CDF ; Unknown
0x0CE0, # .. 0x0CE3 ; Kannada 0x0CE0, # .. 0x0CE3 ; Kannada
0x0CE4, # .. 0x0CE5 ; Unknown 0x0CE4, # .. 0x0CE5 ; Unknown
@ -464,10 +464,9 @@ RANGES = [
0x16EB, # .. 0x16ED ; Common 0x16EB, # .. 0x16ED ; Common
0x16EE, # .. 0x16F8 ; Runic 0x16EE, # .. 0x16F8 ; Runic
0x16F9, # .. 0x16FF ; Unknown 0x16F9, # .. 0x16FF ; Unknown
0x1700, # .. 0x170C ; Tagalog 0x1700, # .. 0x1715 ; Tagalog
0x170D, # .. 0x170D ; Unknown 0x1716, # .. 0x171E ; Unknown
0x170E, # .. 0x1714 ; Tagalog 0x171F, # .. 0x171F ; Tagalog
0x1715, # .. 0x171F ; Unknown
0x1720, # .. 0x1734 ; Hanunoo 0x1720, # .. 0x1734 ; Hanunoo
0x1735, # .. 0x1736 ; Common 0x1735, # .. 0x1736 ; Common
0x1737, # .. 0x173F ; Unknown 0x1737, # .. 0x173F ; Unknown
@ -489,9 +488,7 @@ RANGES = [
0x1802, # .. 0x1803 ; Common 0x1802, # .. 0x1803 ; Common
0x1804, # .. 0x1804 ; Mongolian 0x1804, # .. 0x1804 ; Mongolian
0x1805, # .. 0x1805 ; Common 0x1805, # .. 0x1805 ; Common
0x1806, # .. 0x180E ; Mongolian 0x1806, # .. 0x1819 ; Mongolian
0x180F, # .. 0x180F ; Unknown
0x1810, # .. 0x1819 ; Mongolian
0x181A, # .. 0x181F ; Unknown 0x181A, # .. 0x181F ; Unknown
0x1820, # .. 0x1878 ; Mongolian 0x1820, # .. 0x1878 ; Mongolian
0x1879, # .. 0x187F ; Unknown 0x1879, # .. 0x187F ; Unknown
@ -533,12 +530,12 @@ RANGES = [
0x1A9A, # .. 0x1A9F ; Unknown 0x1A9A, # .. 0x1A9F ; Unknown
0x1AA0, # .. 0x1AAD ; Tai_Tham 0x1AA0, # .. 0x1AAD ; Tai_Tham
0x1AAE, # .. 0x1AAF ; Unknown 0x1AAE, # .. 0x1AAF ; Unknown
0x1AB0, # .. 0x1AC0 ; Inherited 0x1AB0, # .. 0x1ACE ; Inherited
0x1AC1, # .. 0x1AFF ; Unknown 0x1ACF, # .. 0x1AFF ; Unknown
0x1B00, # .. 0x1B4B ; Balinese 0x1B00, # .. 0x1B4C ; Balinese
0x1B4C, # .. 0x1B4F ; Unknown 0x1B4D, # .. 0x1B4F ; Unknown
0x1B50, # .. 0x1B7C ; Balinese 0x1B50, # .. 0x1B7E ; Balinese
0x1B7D, # .. 0x1B7F ; Unknown 0x1B7F, # .. 0x1B7F ; Unknown
0x1B80, # .. 0x1BBF ; Sundanese 0x1B80, # .. 0x1BBF ; Sundanese
0x1BC0, # .. 0x1BF3 ; Batak 0x1BC0, # .. 0x1BF3 ; Batak
0x1BF4, # .. 0x1BFB ; Unknown 0x1BF4, # .. 0x1BFB ; Unknown
@ -580,9 +577,7 @@ RANGES = [
0x1D78, # .. 0x1D78 ; Cyrillic 0x1D78, # .. 0x1D78 ; Cyrillic
0x1D79, # .. 0x1DBE ; Latin 0x1D79, # .. 0x1DBE ; Latin
0x1DBF, # .. 0x1DBF ; Greek 0x1DBF, # .. 0x1DBF ; Greek
0x1DC0, # .. 0x1DF9 ; Inherited 0x1DC0, # .. 0x1DFF ; Inherited
0x1DFA, # .. 0x1DFA ; Unknown
0x1DFB, # .. 0x1DFF ; Inherited
0x1E00, # .. 0x1EFF ; Latin 0x1E00, # .. 0x1EFF ; Latin
0x1F00, # .. 0x1F15 ; Greek 0x1F00, # .. 0x1F15 ; Greek
0x1F16, # .. 0x1F17 ; Unknown 0x1F16, # .. 0x1F17 ; Unknown
@ -629,8 +624,8 @@ RANGES = [
0x208F, # .. 0x208F ; Unknown 0x208F, # .. 0x208F ; Unknown
0x2090, # .. 0x209C ; Latin 0x2090, # .. 0x209C ; Latin
0x209D, # .. 0x209F ; Unknown 0x209D, # .. 0x209F ; Unknown
0x20A0, # .. 0x20BF ; Common 0x20A0, # .. 0x20C0 ; Common
0x20C0, # .. 0x20CF ; Unknown 0x20C1, # .. 0x20CF ; Unknown
0x20D0, # .. 0x20F0 ; Inherited 0x20D0, # .. 0x20F0 ; Inherited
0x20F1, # .. 0x20FF ; Unknown 0x20F1, # .. 0x20FF ; Unknown
0x2100, # .. 0x2125 ; Common 0x2100, # .. 0x2125 ; Common
@ -656,10 +651,7 @@ RANGES = [
0x2B76, # .. 0x2B95 ; Common 0x2B76, # .. 0x2B95 ; Common
0x2B96, # .. 0x2B96 ; Unknown 0x2B96, # .. 0x2B96 ; Unknown
0x2B97, # .. 0x2BFF ; Common 0x2B97, # .. 0x2BFF ; Common
0x2C00, # .. 0x2C2E ; Glagolitic 0x2C00, # .. 0x2C5F ; Glagolitic
0x2C2F, # .. 0x2C2F ; Unknown
0x2C30, # .. 0x2C5E ; Glagolitic
0x2C5F, # .. 0x2C5F ; Unknown
0x2C60, # .. 0x2C7F ; Latin 0x2C60, # .. 0x2C7F ; Latin
0x2C80, # .. 0x2CF3 ; Coptic 0x2C80, # .. 0x2CF3 ; Coptic
0x2CF4, # .. 0x2CF8 ; Unknown 0x2CF4, # .. 0x2CF8 ; Unknown
@ -694,8 +686,8 @@ RANGES = [
0x2DD8, # .. 0x2DDE ; Ethiopic 0x2DD8, # .. 0x2DDE ; Ethiopic
0x2DDF, # .. 0x2DDF ; Unknown 0x2DDF, # .. 0x2DDF ; Unknown
0x2DE0, # .. 0x2DFF ; Cyrillic 0x2DE0, # .. 0x2DFF ; Cyrillic
0x2E00, # .. 0x2E52 ; Common 0x2E00, # .. 0x2E5D ; Common
0x2E53, # .. 0x2E7F ; Unknown 0x2E5E, # .. 0x2E7F ; Unknown
0x2E80, # .. 0x2E99 ; Han 0x2E80, # .. 0x2E99 ; Han
0x2E9A, # .. 0x2E9A ; Unknown 0x2E9A, # .. 0x2E9A ; Unknown
0x2E9B, # .. 0x2EF3 ; Han 0x2E9B, # .. 0x2EF3 ; Han
@ -746,8 +738,7 @@ RANGES = [
0x3358, # .. 0x33FF ; Common 0x3358, # .. 0x33FF ; Common
0x3400, # .. 0x4DBF ; Han 0x3400, # .. 0x4DBF ; Han
0x4DC0, # .. 0x4DFF ; Common 0x4DC0, # .. 0x4DFF ; Common
0x4E00, # .. 0x9FFC ; Han 0x4E00, # .. 0x9FFF ; Han
0x9FFD, # .. 0x9FFF ; Unknown
0xA000, # .. 0xA48C ; Yi 0xA000, # .. 0xA48C ; Yi
0xA48D, # .. 0xA48F ; Unknown 0xA48D, # .. 0xA48F ; Unknown
0xA490, # .. 0xA4C6 ; Yi 0xA490, # .. 0xA4C6 ; Yi
@ -761,11 +752,15 @@ RANGES = [
0xA700, # .. 0xA721 ; Common 0xA700, # .. 0xA721 ; Common
0xA722, # .. 0xA787 ; Latin 0xA722, # .. 0xA787 ; Latin
0xA788, # .. 0xA78A ; Common 0xA788, # .. 0xA78A ; Common
0xA78B, # .. 0xA7BF ; Latin 0xA78B, # .. 0xA7CA ; Latin
0xA7C0, # .. 0xA7C1 ; Unknown 0xA7CB, # .. 0xA7CF ; Unknown
0xA7C2, # .. 0xA7CA ; Latin 0xA7D0, # .. 0xA7D1 ; Latin
0xA7CB, # .. 0xA7F4 ; Unknown 0xA7D2, # .. 0xA7D2 ; Unknown
0xA7F5, # .. 0xA7FF ; Latin 0xA7D3, # .. 0xA7D3 ; Latin
0xA7D4, # .. 0xA7D4 ; Unknown
0xA7D5, # .. 0xA7D9 ; Latin
0xA7DA, # .. 0xA7F1 ; Unknown
0xA7F2, # .. 0xA7FF ; Latin
0xA800, # .. 0xA82C ; Syloti_Nagri 0xA800, # .. 0xA82C ; Syloti_Nagri
0xA82D, # .. 0xA82F ; Unknown 0xA82D, # .. 0xA82F ; Unknown
0xA830, # .. 0xA839 ; Common 0xA830, # .. 0xA839 ; Common
@ -853,17 +848,17 @@ RANGES = [
0xFB43, # .. 0xFB44 ; Hebrew 0xFB43, # .. 0xFB44 ; Hebrew
0xFB45, # .. 0xFB45 ; Unknown 0xFB45, # .. 0xFB45 ; Unknown
0xFB46, # .. 0xFB4F ; Hebrew 0xFB46, # .. 0xFB4F ; Hebrew
0xFB50, # .. 0xFBC1 ; Arabic 0xFB50, # .. 0xFBC2 ; Arabic
0xFBC2, # .. 0xFBD2 ; Unknown 0xFBC3, # .. 0xFBD2 ; Unknown
0xFBD3, # .. 0xFD3D ; Arabic 0xFBD3, # .. 0xFD3D ; Arabic
0xFD3E, # .. 0xFD3F ; Common 0xFD3E, # .. 0xFD3F ; Common
0xFD40, # .. 0xFD4F ; Unknown 0xFD40, # .. 0xFD8F ; Arabic
0xFD50, # .. 0xFD8F ; Arabic
0xFD90, # .. 0xFD91 ; Unknown 0xFD90, # .. 0xFD91 ; Unknown
0xFD92, # .. 0xFDC7 ; Arabic 0xFD92, # .. 0xFDC7 ; Arabic
0xFDC8, # .. 0xFDEF ; Unknown 0xFDC8, # .. 0xFDCE ; Unknown
0xFDF0, # .. 0xFDFD ; Arabic 0xFDCF, # .. 0xFDCF ; Arabic
0xFDFE, # .. 0xFDFF ; Unknown 0xFDD0, # .. 0xFDEF ; Unknown
0xFDF0, # .. 0xFDFF ; Arabic
0xFE00, # .. 0xFE0F ; Inherited 0xFE00, # .. 0xFE0F ; Inherited
0xFE10, # .. 0xFE19 ; Common 0xFE10, # .. 0xFE19 ; Common
0xFE1A, # .. 0xFE1F ; Unknown 0xFE1A, # .. 0xFE1F ; Unknown
@ -970,13 +965,34 @@ RANGES = [
0x10530, # .. 0x10563 ; Caucasian_Albanian 0x10530, # .. 0x10563 ; Caucasian_Albanian
0x10564, # .. 0x1056E ; Unknown 0x10564, # .. 0x1056E ; Unknown
0x1056F, # .. 0x1056F ; Caucasian_Albanian 0x1056F, # .. 0x1056F ; Caucasian_Albanian
0x10570, # .. 0x105FF ; Unknown 0x10570, # .. 0x1057A ; Vithkuqi
0x1057B, # .. 0x1057B ; Unknown
0x1057C, # .. 0x1058A ; Vithkuqi
0x1058B, # .. 0x1058B ; Unknown
0x1058C, # .. 0x10592 ; Vithkuqi
0x10593, # .. 0x10593 ; Unknown
0x10594, # .. 0x10595 ; Vithkuqi
0x10596, # .. 0x10596 ; Unknown
0x10597, # .. 0x105A1 ; Vithkuqi
0x105A2, # .. 0x105A2 ; Unknown
0x105A3, # .. 0x105B1 ; Vithkuqi
0x105B2, # .. 0x105B2 ; Unknown
0x105B3, # .. 0x105B9 ; Vithkuqi
0x105BA, # .. 0x105BA ; Unknown
0x105BB, # .. 0x105BC ; Vithkuqi
0x105BD, # .. 0x105FF ; Unknown
0x10600, # .. 0x10736 ; Linear_A 0x10600, # .. 0x10736 ; Linear_A
0x10737, # .. 0x1073F ; Unknown 0x10737, # .. 0x1073F ; Unknown
0x10740, # .. 0x10755 ; Linear_A 0x10740, # .. 0x10755 ; Linear_A
0x10756, # .. 0x1075F ; Unknown 0x10756, # .. 0x1075F ; Unknown
0x10760, # .. 0x10767 ; Linear_A 0x10760, # .. 0x10767 ; Linear_A
0x10768, # .. 0x107FF ; Unknown 0x10768, # .. 0x1077F ; Unknown
0x10780, # .. 0x10785 ; Latin
0x10786, # .. 0x10786 ; Unknown
0x10787, # .. 0x107B0 ; Latin
0x107B1, # .. 0x107B1 ; Unknown
0x107B2, # .. 0x107BA ; Latin
0x107BB, # .. 0x107FF ; Unknown
0x10800, # .. 0x10805 ; Cypriot 0x10800, # .. 0x10805 ; Cypriot
0x10806, # .. 0x10807 ; Unknown 0x10806, # .. 0x10807 ; Unknown
0x10808, # .. 0x10808 ; Cypriot 0x10808, # .. 0x10808 ; Cypriot
@ -1074,18 +1090,20 @@ RANGES = [
0x10F00, # .. 0x10F27 ; Old_Sogdian 0x10F00, # .. 0x10F27 ; Old_Sogdian
0x10F28, # .. 0x10F2F ; Unknown 0x10F28, # .. 0x10F2F ; Unknown
0x10F30, # .. 0x10F59 ; Sogdian 0x10F30, # .. 0x10F59 ; Sogdian
0x10F5A, # .. 0x10FAF ; Unknown 0x10F5A, # .. 0x10F6F ; Unknown
0x10F70, # .. 0x10F89 ; Old_Uyghur
0x10F8A, # .. 0x10FAF ; Unknown
0x10FB0, # .. 0x10FCB ; Chorasmian 0x10FB0, # .. 0x10FCB ; Chorasmian
0x10FCC, # .. 0x10FDF ; Unknown 0x10FCC, # .. 0x10FDF ; Unknown
0x10FE0, # .. 0x10FF6 ; Elymaic 0x10FE0, # .. 0x10FF6 ; Elymaic
0x10FF7, # .. 0x10FFF ; Unknown 0x10FF7, # .. 0x10FFF ; Unknown
0x11000, # .. 0x1104D ; Brahmi 0x11000, # .. 0x1104D ; Brahmi
0x1104E, # .. 0x11051 ; Unknown 0x1104E, # .. 0x11051 ; Unknown
0x11052, # .. 0x1106F ; Brahmi 0x11052, # .. 0x11075 ; Brahmi
0x11070, # .. 0x1107E ; Unknown 0x11076, # .. 0x1107E ; Unknown
0x1107F, # .. 0x1107F ; Brahmi 0x1107F, # .. 0x1107F ; Brahmi
0x11080, # .. 0x110C1 ; Kaithi 0x11080, # .. 0x110C2 ; Kaithi
0x110C2, # .. 0x110CC ; Unknown 0x110C3, # .. 0x110CC ; Unknown
0x110CD, # .. 0x110CD ; Kaithi 0x110CD, # .. 0x110CD ; Kaithi
0x110CE, # .. 0x110CF ; Unknown 0x110CE, # .. 0x110CF ; Unknown
0x110D0, # .. 0x110E8 ; Sora_Sompeng 0x110D0, # .. 0x110E8 ; Sora_Sompeng
@ -1169,16 +1187,16 @@ RANGES = [
0x1165A, # .. 0x1165F ; Unknown 0x1165A, # .. 0x1165F ; Unknown
0x11660, # .. 0x1166C ; Mongolian 0x11660, # .. 0x1166C ; Mongolian
0x1166D, # .. 0x1167F ; Unknown 0x1166D, # .. 0x1167F ; Unknown
0x11680, # .. 0x116B8 ; Takri 0x11680, # .. 0x116B9 ; Takri
0x116B9, # .. 0x116BF ; Unknown 0x116BA, # .. 0x116BF ; Unknown
0x116C0, # .. 0x116C9 ; Takri 0x116C0, # .. 0x116C9 ; Takri
0x116CA, # .. 0x116FF ; Unknown 0x116CA, # .. 0x116FF ; Unknown
0x11700, # .. 0x1171A ; Ahom 0x11700, # .. 0x1171A ; Ahom
0x1171B, # .. 0x1171C ; Unknown 0x1171B, # .. 0x1171C ; Unknown
0x1171D, # .. 0x1172B ; Ahom 0x1171D, # .. 0x1172B ; Ahom
0x1172C, # .. 0x1172F ; Unknown 0x1172C, # .. 0x1172F ; Unknown
0x11730, # .. 0x1173F ; Ahom 0x11730, # .. 0x11746 ; Ahom
0x11740, # .. 0x117FF ; Unknown 0x11747, # .. 0x117FF ; Unknown
0x11800, # .. 0x1183B ; Dogra 0x11800, # .. 0x1183B ; Dogra
0x1183C, # .. 0x1189F ; Unknown 0x1183C, # .. 0x1189F ; Unknown
0x118A0, # .. 0x118F2 ; Warang_Citi 0x118A0, # .. 0x118F2 ; Warang_Citi
@ -1209,7 +1227,8 @@ RANGES = [
0x11A00, # .. 0x11A47 ; Zanabazar_Square 0x11A00, # .. 0x11A47 ; Zanabazar_Square
0x11A48, # .. 0x11A4F ; Unknown 0x11A48, # .. 0x11A4F ; Unknown
0x11A50, # .. 0x11AA2 ; Soyombo 0x11A50, # .. 0x11AA2 ; Soyombo
0x11AA3, # .. 0x11ABF ; Unknown 0x11AA3, # .. 0x11AAF ; Unknown
0x11AB0, # .. 0x11ABF ; Canadian_Aboriginal
0x11AC0, # .. 0x11AF8 ; Pau_Cin_Hau 0x11AC0, # .. 0x11AF8 ; Pau_Cin_Hau
0x11AF9, # .. 0x11BFF ; Unknown 0x11AF9, # .. 0x11BFF ; Unknown
0x11C00, # .. 0x11C08 ; Bhaiksuki 0x11C00, # .. 0x11C08 ; Bhaiksuki
@ -1266,7 +1285,9 @@ RANGES = [
0x12470, # .. 0x12474 ; Cuneiform 0x12470, # .. 0x12474 ; Cuneiform
0x12475, # .. 0x1247F ; Unknown 0x12475, # .. 0x1247F ; Unknown
0x12480, # .. 0x12543 ; Cuneiform 0x12480, # .. 0x12543 ; Cuneiform
0x12544, # .. 0x12FFF ; Unknown 0x12544, # .. 0x12F8F ; Unknown
0x12F90, # .. 0x12FF2 ; Cypro_Minoan
0x12FF3, # .. 0x12FFF ; Unknown
0x13000, # .. 0x1342E ; Egyptian_Hieroglyphs 0x13000, # .. 0x1342E ; Egyptian_Hieroglyphs
0x1342F, # .. 0x1342F ; Unknown 0x1342F, # .. 0x1342F ; Unknown
0x13430, # .. 0x13438 ; Egyptian_Hieroglyphs 0x13430, # .. 0x13438 ; Egyptian_Hieroglyphs
@ -1280,7 +1301,10 @@ RANGES = [
0x16A60, # .. 0x16A69 ; Mro 0x16A60, # .. 0x16A69 ; Mro
0x16A6A, # .. 0x16A6D ; Unknown 0x16A6A, # .. 0x16A6D ; Unknown
0x16A6E, # .. 0x16A6F ; Mro 0x16A6E, # .. 0x16A6F ; Mro
0x16A70, # .. 0x16ACF ; Unknown 0x16A70, # .. 0x16ABE ; Tangsa
0x16ABF, # .. 0x16ABF ; Unknown
0x16AC0, # .. 0x16AC9 ; Tangsa
0x16ACA, # .. 0x16ACF ; Unknown
0x16AD0, # .. 0x16AED ; Bassa_Vah 0x16AD0, # .. 0x16AED ; Bassa_Vah
0x16AEE, # .. 0x16AEF ; Unknown 0x16AEE, # .. 0x16AEF ; Unknown
0x16AF0, # .. 0x16AF5 ; Bassa_Vah 0x16AF0, # .. 0x16AF5 ; Bassa_Vah
@ -1305,7 +1329,7 @@ RANGES = [
0x16FA0, # .. 0x16FDF ; Unknown 0x16FA0, # .. 0x16FDF ; Unknown
0x16FE0, # .. 0x16FE0 ; Tangut 0x16FE0, # .. 0x16FE0 ; Tangut
0x16FE1, # .. 0x16FE1 ; Nushu 0x16FE1, # .. 0x16FE1 ; Nushu
0x16FE2, # .. 0x16FE3 ; Common 0x16FE2, # .. 0x16FE3 ; Han
0x16FE4, # .. 0x16FE4 ; Khitan_Small_Script 0x16FE4, # .. 0x16FE4 ; Khitan_Small_Script
0x16FE5, # .. 0x16FEF ; Unknown 0x16FE5, # .. 0x16FEF ; Unknown
0x16FF0, # .. 0x16FF1 ; Han 0x16FF0, # .. 0x16FF1 ; Han
@ -1316,10 +1340,17 @@ RANGES = [
0x18B00, # .. 0x18CD5 ; Khitan_Small_Script 0x18B00, # .. 0x18CD5 ; Khitan_Small_Script
0x18CD6, # .. 0x18CFF ; Unknown 0x18CD6, # .. 0x18CFF ; Unknown
0x18D00, # .. 0x18D08 ; Tangut 0x18D00, # .. 0x18D08 ; Tangut
0x18D09, # .. 0x1AFFF ; Unknown 0x18D09, # .. 0x1AFEF ; Unknown
0x1AFF0, # .. 0x1AFF3 ; Katakana
0x1AFF4, # .. 0x1AFF4 ; Unknown
0x1AFF5, # .. 0x1AFFB ; Katakana
0x1AFFC, # .. 0x1AFFC ; Unknown
0x1AFFD, # .. 0x1AFFE ; Katakana
0x1AFFF, # .. 0x1AFFF ; Unknown
0x1B000, # .. 0x1B000 ; Katakana 0x1B000, # .. 0x1B000 ; Katakana
0x1B001, # .. 0x1B11E ; Hiragana 0x1B001, # .. 0x1B11F ; Hiragana
0x1B11F, # .. 0x1B14F ; Unknown 0x1B120, # .. 0x1B122 ; Katakana
0x1B123, # .. 0x1B14F ; Unknown
0x1B150, # .. 0x1B152 ; Hiragana 0x1B150, # .. 0x1B152 ; Hiragana
0x1B153, # .. 0x1B163 ; Unknown 0x1B153, # .. 0x1B163 ; Unknown
0x1B164, # .. 0x1B167 ; Katakana 0x1B164, # .. 0x1B167 ; Katakana
@ -1336,7 +1367,13 @@ RANGES = [
0x1BC9A, # .. 0x1BC9B ; Unknown 0x1BC9A, # .. 0x1BC9B ; Unknown
0x1BC9C, # .. 0x1BC9F ; Duployan 0x1BC9C, # .. 0x1BC9F ; Duployan
0x1BCA0, # .. 0x1BCA3 ; Common 0x1BCA0, # .. 0x1BCA3 ; Common
0x1BCA4, # .. 0x1CFFF ; Unknown 0x1BCA4, # .. 0x1CEFF ; Unknown
0x1CF00, # .. 0x1CF2D ; Inherited
0x1CF2E, # .. 0x1CF2F ; Unknown
0x1CF30, # .. 0x1CF46 ; Inherited
0x1CF47, # .. 0x1CF4F ; Unknown
0x1CF50, # .. 0x1CFC3 ; Common
0x1CFC4, # .. 0x1CFFF ; Unknown
0x1D000, # .. 0x1D0F5 ; Common 0x1D000, # .. 0x1D0F5 ; Common
0x1D0F6, # .. 0x1D0FF ; Unknown 0x1D0F6, # .. 0x1D0FF ; Unknown
0x1D100, # .. 0x1D126 ; Common 0x1D100, # .. 0x1D126 ; Common
@ -1349,8 +1386,8 @@ RANGES = [
0x1D185, # .. 0x1D18B ; Inherited 0x1D185, # .. 0x1D18B ; Inherited
0x1D18C, # .. 0x1D1A9 ; Common 0x1D18C, # .. 0x1D1A9 ; Common
0x1D1AA, # .. 0x1D1AD ; Inherited 0x1D1AA, # .. 0x1D1AD ; Inherited
0x1D1AE, # .. 0x1D1E8 ; Common 0x1D1AE, # .. 0x1D1EA ; Common
0x1D1E9, # .. 0x1D1FF ; Unknown 0x1D1EB, # .. 0x1D1FF ; Unknown
0x1D200, # .. 0x1D245 ; Greek 0x1D200, # .. 0x1D245 ; Greek
0x1D246, # .. 0x1D2DF ; Unknown 0x1D246, # .. 0x1D2DF ; Unknown
0x1D2E0, # .. 0x1D2F3 ; Common 0x1D2E0, # .. 0x1D2F3 ; Common
@ -1405,7 +1442,9 @@ RANGES = [
0x1DA9B, # .. 0x1DA9F ; SignWriting 0x1DA9B, # .. 0x1DA9F ; SignWriting
0x1DAA0, # .. 0x1DAA0 ; Unknown 0x1DAA0, # .. 0x1DAA0 ; Unknown
0x1DAA1, # .. 0x1DAAF ; SignWriting 0x1DAA1, # .. 0x1DAAF ; SignWriting
0x1DAB0, # .. 0x1DFFF ; Unknown 0x1DAB0, # .. 0x1DEFF ; Unknown
0x1DF00, # .. 0x1DF1E ; Latin
0x1DF1F, # .. 0x1DFFF ; Unknown
0x1E000, # .. 0x1E006 ; Glagolitic 0x1E000, # .. 0x1E006 ; Glagolitic
0x1E007, # .. 0x1E007 ; Unknown 0x1E007, # .. 0x1E007 ; Unknown
0x1E008, # .. 0x1E018 ; Glagolitic 0x1E008, # .. 0x1E018 ; Glagolitic
@ -1423,11 +1462,21 @@ RANGES = [
0x1E140, # .. 0x1E149 ; Nyiakeng_Puachue_Hmong 0x1E140, # .. 0x1E149 ; Nyiakeng_Puachue_Hmong
0x1E14A, # .. 0x1E14D ; Unknown 0x1E14A, # .. 0x1E14D ; Unknown
0x1E14E, # .. 0x1E14F ; Nyiakeng_Puachue_Hmong 0x1E14E, # .. 0x1E14F ; Nyiakeng_Puachue_Hmong
0x1E150, # .. 0x1E2BF ; Unknown 0x1E150, # .. 0x1E28F ; Unknown
0x1E290, # .. 0x1E2AE ; Toto
0x1E2AF, # .. 0x1E2BF ; Unknown
0x1E2C0, # .. 0x1E2F9 ; Wancho 0x1E2C0, # .. 0x1E2F9 ; Wancho
0x1E2FA, # .. 0x1E2FE ; Unknown 0x1E2FA, # .. 0x1E2FE ; Unknown
0x1E2FF, # .. 0x1E2FF ; Wancho 0x1E2FF, # .. 0x1E2FF ; Wancho
0x1E300, # .. 0x1E7FF ; Unknown 0x1E300, # .. 0x1E7DF ; Unknown
0x1E7E0, # .. 0x1E7E6 ; Ethiopic
0x1E7E7, # .. 0x1E7E7 ; Unknown
0x1E7E8, # .. 0x1E7EB ; Ethiopic
0x1E7EC, # .. 0x1E7EC ; Unknown
0x1E7ED, # .. 0x1E7EE ; Ethiopic
0x1E7EF, # .. 0x1E7EF ; Unknown
0x1E7F0, # .. 0x1E7FE ; Ethiopic
0x1E7FF, # .. 0x1E7FF ; Unknown
0x1E800, # .. 0x1E8C4 ; Mende_Kikakui 0x1E800, # .. 0x1E8C4 ; Mende_Kikakui
0x1E8C5, # .. 0x1E8C6 ; Unknown 0x1E8C5, # .. 0x1E8C6 ; Unknown
0x1E8C7, # .. 0x1E8D6 ; Mende_Kikakui 0x1E8C7, # .. 0x1E8D6 ; Mende_Kikakui
@ -1537,8 +1586,8 @@ RANGES = [
0x1F260, # .. 0x1F265 ; Common 0x1F260, # .. 0x1F265 ; Common
0x1F266, # .. 0x1F2FF ; Unknown 0x1F266, # .. 0x1F2FF ; Unknown
0x1F300, # .. 0x1F6D7 ; Common 0x1F300, # .. 0x1F6D7 ; Common
0x1F6D8, # .. 0x1F6DF ; Unknown 0x1F6D8, # .. 0x1F6DC ; Unknown
0x1F6E0, # .. 0x1F6EC ; Common 0x1F6DD, # .. 0x1F6EC ; Common
0x1F6ED, # .. 0x1F6EF ; Unknown 0x1F6ED, # .. 0x1F6EF ; Unknown
0x1F6F0, # .. 0x1F6FC ; Common 0x1F6F0, # .. 0x1F6FC ; Common
0x1F6FD, # .. 0x1F6FF ; Unknown 0x1F6FD, # .. 0x1F6FF ; Unknown
@ -1547,7 +1596,9 @@ RANGES = [
0x1F780, # .. 0x1F7D8 ; Common 0x1F780, # .. 0x1F7D8 ; Common
0x1F7D9, # .. 0x1F7DF ; Unknown 0x1F7D9, # .. 0x1F7DF ; Unknown
0x1F7E0, # .. 0x1F7EB ; Common 0x1F7E0, # .. 0x1F7EB ; Common
0x1F7EC, # .. 0x1F7FF ; Unknown 0x1F7EC, # .. 0x1F7EF ; Unknown
0x1F7F0, # .. 0x1F7F0 ; Common
0x1F7F1, # .. 0x1F7FF ; Unknown
0x1F800, # .. 0x1F80B ; Common 0x1F800, # .. 0x1F80B ; Common
0x1F80C, # .. 0x1F80F ; Unknown 0x1F80C, # .. 0x1F80F ; Unknown
0x1F810, # .. 0x1F847 ; Common 0x1F810, # .. 0x1F847 ; Common
@ -1560,38 +1611,38 @@ RANGES = [
0x1F8AE, # .. 0x1F8AF ; Unknown 0x1F8AE, # .. 0x1F8AF ; Unknown
0x1F8B0, # .. 0x1F8B1 ; Common 0x1F8B0, # .. 0x1F8B1 ; Common
0x1F8B2, # .. 0x1F8FF ; Unknown 0x1F8B2, # .. 0x1F8FF ; Unknown
0x1F900, # .. 0x1F978 ; Common 0x1F900, # .. 0x1FA53 ; Common
0x1F979, # .. 0x1F979 ; Unknown
0x1F97A, # .. 0x1F9CB ; Common
0x1F9CC, # .. 0x1F9CC ; Unknown
0x1F9CD, # .. 0x1FA53 ; Common
0x1FA54, # .. 0x1FA5F ; Unknown 0x1FA54, # .. 0x1FA5F ; Unknown
0x1FA60, # .. 0x1FA6D ; Common 0x1FA60, # .. 0x1FA6D ; Common
0x1FA6E, # .. 0x1FA6F ; Unknown 0x1FA6E, # .. 0x1FA6F ; Unknown
0x1FA70, # .. 0x1FA74 ; Common 0x1FA70, # .. 0x1FA74 ; Common
0x1FA75, # .. 0x1FA77 ; Unknown 0x1FA75, # .. 0x1FA77 ; Unknown
0x1FA78, # .. 0x1FA7A ; Common 0x1FA78, # .. 0x1FA7C ; Common
0x1FA7B, # .. 0x1FA7F ; Unknown 0x1FA7D, # .. 0x1FA7F ; Unknown
0x1FA80, # .. 0x1FA86 ; Common 0x1FA80, # .. 0x1FA86 ; Common
0x1FA87, # .. 0x1FA8F ; Unknown 0x1FA87, # .. 0x1FA8F ; Unknown
0x1FA90, # .. 0x1FAA8 ; Common 0x1FA90, # .. 0x1FAAC ; Common
0x1FAA9, # .. 0x1FAAF ; Unknown 0x1FAAD, # .. 0x1FAAF ; Unknown
0x1FAB0, # .. 0x1FAB6 ; Common 0x1FAB0, # .. 0x1FABA ; Common
0x1FAB7, # .. 0x1FABF ; Unknown 0x1FABB, # .. 0x1FABF ; Unknown
0x1FAC0, # .. 0x1FAC2 ; Common 0x1FAC0, # .. 0x1FAC5 ; Common
0x1FAC3, # .. 0x1FACF ; Unknown 0x1FAC6, # .. 0x1FACF ; Unknown
0x1FAD0, # .. 0x1FAD6 ; Common 0x1FAD0, # .. 0x1FAD9 ; Common
0x1FAD7, # .. 0x1FAFF ; Unknown 0x1FADA, # .. 0x1FADF ; Unknown
0x1FAE0, # .. 0x1FAE7 ; Common
0x1FAE8, # .. 0x1FAEF ; Unknown
0x1FAF0, # .. 0x1FAF6 ; Common
0x1FAF7, # .. 0x1FAFF ; Unknown
0x1FB00, # .. 0x1FB92 ; Common 0x1FB00, # .. 0x1FB92 ; Common
0x1FB93, # .. 0x1FB93 ; Unknown 0x1FB93, # .. 0x1FB93 ; Unknown
0x1FB94, # .. 0x1FBCA ; Common 0x1FB94, # .. 0x1FBCA ; Common
0x1FBCB, # .. 0x1FBEF ; Unknown 0x1FBCB, # .. 0x1FBEF ; Unknown
0x1FBF0, # .. 0x1FBF9 ; Common 0x1FBF0, # .. 0x1FBF9 ; Common
0x1FBFA, # .. 0x1FFFF ; Unknown 0x1FBFA, # .. 0x1FFFF ; Unknown
0x20000, # .. 0x2A6DD ; Han 0x20000, # .. 0x2A6DF ; Han
0x2A6DE, # .. 0x2A6FF ; Unknown 0x2A6E0, # .. 0x2A6FF ; Unknown
0x2A700, # .. 0x2B734 ; Han 0x2A700, # .. 0x2B738 ; Han
0x2B735, # .. 0x2B73F ; Unknown 0x2B739, # .. 0x2B73F ; Unknown
0x2B740, # .. 0x2B81D ; Han 0x2B740, # .. 0x2B81D ; Han
0x2B81E, # .. 0x2B81F ; Unknown 0x2B81E, # .. 0x2B81F ; Unknown
0x2B820, # .. 0x2CEA1 ; Han 0x2B820, # .. 0x2CEA1 ; Han
@ -1674,9 +1725,7 @@ VALUES = [
'Zyyy', # 060C..060C ; Common 'Zyyy', # 060C..060C ; Common
'Arab', # 060D..061A ; Arabic 'Arab', # 060D..061A ; Arabic
'Zyyy', # 061B..061B ; Common 'Zyyy', # 061B..061B ; Common
'Arab', # 061C..061C ; Arabic 'Arab', # 061C..061E ; Arabic
'Zzzz', # 061D..061D ; Unknown
'Arab', # 061E..061E ; Arabic
'Zyyy', # 061F..061F ; Common 'Zyyy', # 061F..061F ; Common
'Arab', # 0620..063F ; Arabic 'Arab', # 0620..063F ; Arabic
'Zyyy', # 0640..0640 ; Common 'Zyyy', # 0640..0640 ; Common
@ -1707,12 +1756,12 @@ VALUES = [
'Mand', # 085E..085E ; Mandaic 'Mand', # 085E..085E ; Mandaic
'Zzzz', # 085F..085F ; Unknown 'Zzzz', # 085F..085F ; Unknown
'Syrc', # 0860..086A ; Syriac 'Syrc', # 0860..086A ; Syriac
'Zzzz', # 086B..089F ; Unknown 'Zzzz', # 086B..086F ; Unknown
'Arab', # 08A0..08B4 ; Arabic 'Arab', # 0870..088E ; Arabic
'Zzzz', # 08B5..08B5 ; Unknown 'Zzzz', # 088F..088F ; Unknown
'Arab', # 08B6..08C7 ; Arabic 'Arab', # 0890..0891 ; Arabic
'Zzzz', # 08C8..08D2 ; Unknown 'Zzzz', # 0892..0897 ; Unknown
'Arab', # 08D3..08E1 ; Arabic 'Arab', # 0898..08E1 ; Arabic
'Zyyy', # 08E2..08E2 ; Common 'Zyyy', # 08E2..08E2 ; Common
'Arab', # 08E3..08FF ; Arabic 'Arab', # 08E3..08FF ; Arabic
'Deva', # 0900..0950 ; Devanagari 'Deva', # 0900..0950 ; Devanagari
@ -1875,8 +1924,8 @@ VALUES = [
'Telu', # 0C12..0C28 ; Telugu 'Telu', # 0C12..0C28 ; Telugu
'Zzzz', # 0C29..0C29 ; Unknown 'Zzzz', # 0C29..0C29 ; Unknown
'Telu', # 0C2A..0C39 ; Telugu 'Telu', # 0C2A..0C39 ; Telugu
'Zzzz', # 0C3A..0C3C ; Unknown 'Zzzz', # 0C3A..0C3B ; Unknown
'Telu', # 0C3D..0C44 ; Telugu 'Telu', # 0C3C..0C44 ; Telugu
'Zzzz', # 0C45..0C45 ; Unknown 'Zzzz', # 0C45..0C45 ; Unknown
'Telu', # 0C46..0C48 ; Telugu 'Telu', # 0C46..0C48 ; Telugu
'Zzzz', # 0C49..0C49 ; Unknown 'Zzzz', # 0C49..0C49 ; Unknown
@ -1885,7 +1934,9 @@ VALUES = [
'Telu', # 0C55..0C56 ; Telugu 'Telu', # 0C55..0C56 ; Telugu
'Zzzz', # 0C57..0C57 ; Unknown 'Zzzz', # 0C57..0C57 ; Unknown
'Telu', # 0C58..0C5A ; Telugu 'Telu', # 0C58..0C5A ; Telugu
'Zzzz', # 0C5B..0C5F ; Unknown 'Zzzz', # 0C5B..0C5C ; Unknown
'Telu', # 0C5D..0C5D ; Telugu
'Zzzz', # 0C5E..0C5F ; Unknown
'Telu', # 0C60..0C63 ; Telugu 'Telu', # 0C60..0C63 ; Telugu
'Zzzz', # 0C64..0C65 ; Unknown 'Zzzz', # 0C64..0C65 ; Unknown
'Telu', # 0C66..0C6F ; Telugu 'Telu', # 0C66..0C6F ; Telugu
@ -1908,8 +1959,8 @@ VALUES = [
'Knda', # 0CCA..0CCD ; Kannada 'Knda', # 0CCA..0CCD ; Kannada
'Zzzz', # 0CCE..0CD4 ; Unknown 'Zzzz', # 0CCE..0CD4 ; Unknown
'Knda', # 0CD5..0CD6 ; Kannada 'Knda', # 0CD5..0CD6 ; Kannada
'Zzzz', # 0CD7..0CDD ; Unknown 'Zzzz', # 0CD7..0CDC ; Unknown
'Knda', # 0CDE..0CDE ; Kannada 'Knda', # 0CDD..0CDE ; Kannada
'Zzzz', # 0CDF..0CDF ; Unknown 'Zzzz', # 0CDF..0CDF ; Unknown
'Knda', # 0CE0..0CE3 ; Kannada 'Knda', # 0CE0..0CE3 ; Kannada
'Zzzz', # 0CE4..0CE5 ; Unknown 'Zzzz', # 0CE4..0CE5 ; Unknown
@ -2054,10 +2105,9 @@ VALUES = [
'Zyyy', # 16EB..16ED ; Common 'Zyyy', # 16EB..16ED ; Common
'Runr', # 16EE..16F8 ; Runic 'Runr', # 16EE..16F8 ; Runic
'Zzzz', # 16F9..16FF ; Unknown 'Zzzz', # 16F9..16FF ; Unknown
'Tglg', # 1700..170C ; Tagalog 'Tglg', # 1700..1715 ; Tagalog
'Zzzz', # 170D..170D ; Unknown 'Zzzz', # 1716..171E ; Unknown
'Tglg', # 170E..1714 ; Tagalog 'Tglg', # 171F..171F ; Tagalog
'Zzzz', # 1715..171F ; Unknown
'Hano', # 1720..1734 ; Hanunoo 'Hano', # 1720..1734 ; Hanunoo
'Zyyy', # 1735..1736 ; Common 'Zyyy', # 1735..1736 ; Common
'Zzzz', # 1737..173F ; Unknown 'Zzzz', # 1737..173F ; Unknown
@ -2079,9 +2129,7 @@ VALUES = [
'Zyyy', # 1802..1803 ; Common 'Zyyy', # 1802..1803 ; Common
'Mong', # 1804..1804 ; Mongolian 'Mong', # 1804..1804 ; Mongolian
'Zyyy', # 1805..1805 ; Common 'Zyyy', # 1805..1805 ; Common
'Mong', # 1806..180E ; Mongolian 'Mong', # 1806..1819 ; Mongolian
'Zzzz', # 180F..180F ; Unknown
'Mong', # 1810..1819 ; Mongolian
'Zzzz', # 181A..181F ; Unknown 'Zzzz', # 181A..181F ; Unknown
'Mong', # 1820..1878 ; Mongolian 'Mong', # 1820..1878 ; Mongolian
'Zzzz', # 1879..187F ; Unknown 'Zzzz', # 1879..187F ; Unknown
@ -2123,12 +2171,12 @@ VALUES = [
'Zzzz', # 1A9A..1A9F ; Unknown 'Zzzz', # 1A9A..1A9F ; Unknown
'Lana', # 1AA0..1AAD ; Tai_Tham 'Lana', # 1AA0..1AAD ; Tai_Tham
'Zzzz', # 1AAE..1AAF ; Unknown 'Zzzz', # 1AAE..1AAF ; Unknown
'Zinh', # 1AB0..1AC0 ; Inherited 'Zinh', # 1AB0..1ACE ; Inherited
'Zzzz', # 1AC1..1AFF ; Unknown 'Zzzz', # 1ACF..1AFF ; Unknown
'Bali', # 1B00..1B4B ; Balinese 'Bali', # 1B00..1B4C ; Balinese
'Zzzz', # 1B4C..1B4F ; Unknown 'Zzzz', # 1B4D..1B4F ; Unknown
'Bali', # 1B50..1B7C ; Balinese 'Bali', # 1B50..1B7E ; Balinese
'Zzzz', # 1B7D..1B7F ; Unknown 'Zzzz', # 1B7F..1B7F ; Unknown
'Sund', # 1B80..1BBF ; Sundanese 'Sund', # 1B80..1BBF ; Sundanese
'Batk', # 1BC0..1BF3 ; Batak 'Batk', # 1BC0..1BF3 ; Batak
'Zzzz', # 1BF4..1BFB ; Unknown 'Zzzz', # 1BF4..1BFB ; Unknown
@ -2170,9 +2218,7 @@ VALUES = [
'Cyrl', # 1D78..1D78 ; Cyrillic 'Cyrl', # 1D78..1D78 ; Cyrillic
'Latn', # 1D79..1DBE ; Latin 'Latn', # 1D79..1DBE ; Latin
'Grek', # 1DBF..1DBF ; Greek 'Grek', # 1DBF..1DBF ; Greek
'Zinh', # 1DC0..1DF9 ; Inherited 'Zinh', # 1DC0..1DFF ; Inherited
'Zzzz', # 1DFA..1DFA ; Unknown
'Zinh', # 1DFB..1DFF ; Inherited
'Latn', # 1E00..1EFF ; Latin 'Latn', # 1E00..1EFF ; Latin
'Grek', # 1F00..1F15 ; Greek 'Grek', # 1F00..1F15 ; Greek
'Zzzz', # 1F16..1F17 ; Unknown 'Zzzz', # 1F16..1F17 ; Unknown
@ -2219,8 +2265,8 @@ VALUES = [
'Zzzz', # 208F..208F ; Unknown 'Zzzz', # 208F..208F ; Unknown
'Latn', # 2090..209C ; Latin 'Latn', # 2090..209C ; Latin
'Zzzz', # 209D..209F ; Unknown 'Zzzz', # 209D..209F ; Unknown
'Zyyy', # 20A0..20BF ; Common 'Zyyy', # 20A0..20C0 ; Common
'Zzzz', # 20C0..20CF ; Unknown 'Zzzz', # 20C1..20CF ; Unknown
'Zinh', # 20D0..20F0 ; Inherited 'Zinh', # 20D0..20F0 ; Inherited
'Zzzz', # 20F1..20FF ; Unknown 'Zzzz', # 20F1..20FF ; Unknown
'Zyyy', # 2100..2125 ; Common 'Zyyy', # 2100..2125 ; Common
@ -2246,10 +2292,7 @@ VALUES = [
'Zyyy', # 2B76..2B95 ; Common 'Zyyy', # 2B76..2B95 ; Common
'Zzzz', # 2B96..2B96 ; Unknown 'Zzzz', # 2B96..2B96 ; Unknown
'Zyyy', # 2B97..2BFF ; Common 'Zyyy', # 2B97..2BFF ; Common
'Glag', # 2C00..2C2E ; Glagolitic 'Glag', # 2C00..2C5F ; Glagolitic
'Zzzz', # 2C2F..2C2F ; Unknown
'Glag', # 2C30..2C5E ; Glagolitic
'Zzzz', # 2C5F..2C5F ; Unknown
'Latn', # 2C60..2C7F ; Latin 'Latn', # 2C60..2C7F ; Latin
'Copt', # 2C80..2CF3 ; Coptic 'Copt', # 2C80..2CF3 ; Coptic
'Zzzz', # 2CF4..2CF8 ; Unknown 'Zzzz', # 2CF4..2CF8 ; Unknown
@ -2284,8 +2327,8 @@ VALUES = [
'Ethi', # 2DD8..2DDE ; Ethiopic 'Ethi', # 2DD8..2DDE ; Ethiopic
'Zzzz', # 2DDF..2DDF ; Unknown 'Zzzz', # 2DDF..2DDF ; Unknown
'Cyrl', # 2DE0..2DFF ; Cyrillic 'Cyrl', # 2DE0..2DFF ; Cyrillic
'Zyyy', # 2E00..2E52 ; Common 'Zyyy', # 2E00..2E5D ; Common
'Zzzz', # 2E53..2E7F ; Unknown 'Zzzz', # 2E5E..2E7F ; Unknown
'Hani', # 2E80..2E99 ; Han 'Hani', # 2E80..2E99 ; Han
'Zzzz', # 2E9A..2E9A ; Unknown 'Zzzz', # 2E9A..2E9A ; Unknown
'Hani', # 2E9B..2EF3 ; Han 'Hani', # 2E9B..2EF3 ; Han
@ -2336,8 +2379,7 @@ VALUES = [
'Zyyy', # 3358..33FF ; Common 'Zyyy', # 3358..33FF ; Common
'Hani', # 3400..4DBF ; Han 'Hani', # 3400..4DBF ; Han
'Zyyy', # 4DC0..4DFF ; Common 'Zyyy', # 4DC0..4DFF ; Common
'Hani', # 4E00..9FFC ; Han 'Hani', # 4E00..9FFF ; Han
'Zzzz', # 9FFD..9FFF ; Unknown
'Yiii', # A000..A48C ; Yi 'Yiii', # A000..A48C ; Yi
'Zzzz', # A48D..A48F ; Unknown 'Zzzz', # A48D..A48F ; Unknown
'Yiii', # A490..A4C6 ; Yi 'Yiii', # A490..A4C6 ; Yi
@ -2351,11 +2393,15 @@ VALUES = [
'Zyyy', # A700..A721 ; Common 'Zyyy', # A700..A721 ; Common
'Latn', # A722..A787 ; Latin 'Latn', # A722..A787 ; Latin
'Zyyy', # A788..A78A ; Common 'Zyyy', # A788..A78A ; Common
'Latn', # A78B..A7BF ; Latin 'Latn', # A78B..A7CA ; Latin
'Zzzz', # A7C0..A7C1 ; Unknown 'Zzzz', # A7CB..A7CF ; Unknown
'Latn', # A7C2..A7CA ; Latin 'Latn', # A7D0..A7D1 ; Latin
'Zzzz', # A7CB..A7F4 ; Unknown 'Zzzz', # A7D2..A7D2 ; Unknown
'Latn', # A7F5..A7FF ; Latin 'Latn', # A7D3..A7D3 ; Latin
'Zzzz', # A7D4..A7D4 ; Unknown
'Latn', # A7D5..A7D9 ; Latin
'Zzzz', # A7DA..A7F1 ; Unknown
'Latn', # A7F2..A7FF ; Latin
'Sylo', # A800..A82C ; Syloti_Nagri 'Sylo', # A800..A82C ; Syloti_Nagri
'Zzzz', # A82D..A82F ; Unknown 'Zzzz', # A82D..A82F ; Unknown
'Zyyy', # A830..A839 ; Common 'Zyyy', # A830..A839 ; Common
@ -2443,17 +2489,17 @@ VALUES = [
'Hebr', # FB43..FB44 ; Hebrew 'Hebr', # FB43..FB44 ; Hebrew
'Zzzz', # FB45..FB45 ; Unknown 'Zzzz', # FB45..FB45 ; Unknown
'Hebr', # FB46..FB4F ; Hebrew 'Hebr', # FB46..FB4F ; Hebrew
'Arab', # FB50..FBC1 ; Arabic 'Arab', # FB50..FBC2 ; Arabic
'Zzzz', # FBC2..FBD2 ; Unknown 'Zzzz', # FBC3..FBD2 ; Unknown
'Arab', # FBD3..FD3D ; Arabic 'Arab', # FBD3..FD3D ; Arabic
'Zyyy', # FD3E..FD3F ; Common 'Zyyy', # FD3E..FD3F ; Common
'Zzzz', # FD40..FD4F ; Unknown 'Arab', # FD40..FD8F ; Arabic
'Arab', # FD50..FD8F ; Arabic
'Zzzz', # FD90..FD91 ; Unknown 'Zzzz', # FD90..FD91 ; Unknown
'Arab', # FD92..FDC7 ; Arabic 'Arab', # FD92..FDC7 ; Arabic
'Zzzz', # FDC8..FDEF ; Unknown 'Zzzz', # FDC8..FDCE ; Unknown
'Arab', # FDF0..FDFD ; Arabic 'Arab', # FDCF..FDCF ; Arabic
'Zzzz', # FDFE..FDFF ; Unknown 'Zzzz', # FDD0..FDEF ; Unknown
'Arab', # FDF0..FDFF ; Arabic
'Zinh', # FE00..FE0F ; Inherited 'Zinh', # FE00..FE0F ; Inherited
'Zyyy', # FE10..FE19 ; Common 'Zyyy', # FE10..FE19 ; Common
'Zzzz', # FE1A..FE1F ; Unknown 'Zzzz', # FE1A..FE1F ; Unknown
@ -2560,13 +2606,34 @@ VALUES = [
'Aghb', # 10530..10563 ; Caucasian_Albanian 'Aghb', # 10530..10563 ; Caucasian_Albanian
'Zzzz', # 10564..1056E ; Unknown 'Zzzz', # 10564..1056E ; Unknown
'Aghb', # 1056F..1056F ; Caucasian_Albanian 'Aghb', # 1056F..1056F ; Caucasian_Albanian
'Zzzz', # 10570..105FF ; Unknown 'Vith', # 10570..1057A ; Vithkuqi
'Zzzz', # 1057B..1057B ; Unknown
'Vith', # 1057C..1058A ; Vithkuqi
'Zzzz', # 1058B..1058B ; Unknown
'Vith', # 1058C..10592 ; Vithkuqi
'Zzzz', # 10593..10593 ; Unknown
'Vith', # 10594..10595 ; Vithkuqi
'Zzzz', # 10596..10596 ; Unknown
'Vith', # 10597..105A1 ; Vithkuqi
'Zzzz', # 105A2..105A2 ; Unknown
'Vith', # 105A3..105B1 ; Vithkuqi
'Zzzz', # 105B2..105B2 ; Unknown
'Vith', # 105B3..105B9 ; Vithkuqi
'Zzzz', # 105BA..105BA ; Unknown
'Vith', # 105BB..105BC ; Vithkuqi
'Zzzz', # 105BD..105FF ; Unknown
'Lina', # 10600..10736 ; Linear_A 'Lina', # 10600..10736 ; Linear_A
'Zzzz', # 10737..1073F ; Unknown 'Zzzz', # 10737..1073F ; Unknown
'Lina', # 10740..10755 ; Linear_A 'Lina', # 10740..10755 ; Linear_A
'Zzzz', # 10756..1075F ; Unknown 'Zzzz', # 10756..1075F ; Unknown
'Lina', # 10760..10767 ; Linear_A 'Lina', # 10760..10767 ; Linear_A
'Zzzz', # 10768..107FF ; Unknown 'Zzzz', # 10768..1077F ; Unknown
'Latn', # 10780..10785 ; Latin
'Zzzz', # 10786..10786 ; Unknown
'Latn', # 10787..107B0 ; Latin
'Zzzz', # 107B1..107B1 ; Unknown
'Latn', # 107B2..107BA ; Latin
'Zzzz', # 107BB..107FF ; Unknown
'Cprt', # 10800..10805 ; Cypriot 'Cprt', # 10800..10805 ; Cypriot
'Zzzz', # 10806..10807 ; Unknown 'Zzzz', # 10806..10807 ; Unknown
'Cprt', # 10808..10808 ; Cypriot 'Cprt', # 10808..10808 ; Cypriot
@ -2664,18 +2731,20 @@ VALUES = [
'Sogo', # 10F00..10F27 ; Old_Sogdian 'Sogo', # 10F00..10F27 ; Old_Sogdian
'Zzzz', # 10F28..10F2F ; Unknown 'Zzzz', # 10F28..10F2F ; Unknown
'Sogd', # 10F30..10F59 ; Sogdian 'Sogd', # 10F30..10F59 ; Sogdian
'Zzzz', # 10F5A..10FAF ; Unknown 'Zzzz', # 10F5A..10F6F ; Unknown
'Ougr', # 10F70..10F89 ; Old_Uyghur
'Zzzz', # 10F8A..10FAF ; Unknown
'Chrs', # 10FB0..10FCB ; Chorasmian 'Chrs', # 10FB0..10FCB ; Chorasmian
'Zzzz', # 10FCC..10FDF ; Unknown 'Zzzz', # 10FCC..10FDF ; Unknown
'Elym', # 10FE0..10FF6 ; Elymaic 'Elym', # 10FE0..10FF6 ; Elymaic
'Zzzz', # 10FF7..10FFF ; Unknown 'Zzzz', # 10FF7..10FFF ; Unknown
'Brah', # 11000..1104D ; Brahmi 'Brah', # 11000..1104D ; Brahmi
'Zzzz', # 1104E..11051 ; Unknown 'Zzzz', # 1104E..11051 ; Unknown
'Brah', # 11052..1106F ; Brahmi 'Brah', # 11052..11075 ; Brahmi
'Zzzz', # 11070..1107E ; Unknown 'Zzzz', # 11076..1107E ; Unknown
'Brah', # 1107F..1107F ; Brahmi 'Brah', # 1107F..1107F ; Brahmi
'Kthi', # 11080..110C1 ; Kaithi 'Kthi', # 11080..110C2 ; Kaithi
'Zzzz', # 110C2..110CC ; Unknown 'Zzzz', # 110C3..110CC ; Unknown
'Kthi', # 110CD..110CD ; Kaithi 'Kthi', # 110CD..110CD ; Kaithi
'Zzzz', # 110CE..110CF ; Unknown 'Zzzz', # 110CE..110CF ; Unknown
'Sora', # 110D0..110E8 ; Sora_Sompeng 'Sora', # 110D0..110E8 ; Sora_Sompeng
@ -2759,16 +2828,16 @@ VALUES = [
'Zzzz', # 1165A..1165F ; Unknown 'Zzzz', # 1165A..1165F ; Unknown
'Mong', # 11660..1166C ; Mongolian 'Mong', # 11660..1166C ; Mongolian
'Zzzz', # 1166D..1167F ; Unknown 'Zzzz', # 1166D..1167F ; Unknown
'Takr', # 11680..116B8 ; Takri 'Takr', # 11680..116B9 ; Takri
'Zzzz', # 116B9..116BF ; Unknown 'Zzzz', # 116BA..116BF ; Unknown
'Takr', # 116C0..116C9 ; Takri 'Takr', # 116C0..116C9 ; Takri
'Zzzz', # 116CA..116FF ; Unknown 'Zzzz', # 116CA..116FF ; Unknown
'Ahom', # 11700..1171A ; Ahom 'Ahom', # 11700..1171A ; Ahom
'Zzzz', # 1171B..1171C ; Unknown 'Zzzz', # 1171B..1171C ; Unknown
'Ahom', # 1171D..1172B ; Ahom 'Ahom', # 1171D..1172B ; Ahom
'Zzzz', # 1172C..1172F ; Unknown 'Zzzz', # 1172C..1172F ; Unknown
'Ahom', # 11730..1173F ; Ahom 'Ahom', # 11730..11746 ; Ahom
'Zzzz', # 11740..117FF ; Unknown 'Zzzz', # 11747..117FF ; Unknown
'Dogr', # 11800..1183B ; Dogra 'Dogr', # 11800..1183B ; Dogra
'Zzzz', # 1183C..1189F ; Unknown 'Zzzz', # 1183C..1189F ; Unknown
'Wara', # 118A0..118F2 ; Warang_Citi 'Wara', # 118A0..118F2 ; Warang_Citi
@ -2799,7 +2868,8 @@ VALUES = [
'Zanb', # 11A00..11A47 ; Zanabazar_Square 'Zanb', # 11A00..11A47 ; Zanabazar_Square
'Zzzz', # 11A48..11A4F ; Unknown 'Zzzz', # 11A48..11A4F ; Unknown
'Soyo', # 11A50..11AA2 ; Soyombo 'Soyo', # 11A50..11AA2 ; Soyombo
'Zzzz', # 11AA3..11ABF ; Unknown 'Zzzz', # 11AA3..11AAF ; Unknown
'Cans', # 11AB0..11ABF ; Canadian_Aboriginal
'Pauc', # 11AC0..11AF8 ; Pau_Cin_Hau 'Pauc', # 11AC0..11AF8 ; Pau_Cin_Hau
'Zzzz', # 11AF9..11BFF ; Unknown 'Zzzz', # 11AF9..11BFF ; Unknown
'Bhks', # 11C00..11C08 ; Bhaiksuki 'Bhks', # 11C00..11C08 ; Bhaiksuki
@ -2856,7 +2926,9 @@ VALUES = [
'Xsux', # 12470..12474 ; Cuneiform 'Xsux', # 12470..12474 ; Cuneiform
'Zzzz', # 12475..1247F ; Unknown 'Zzzz', # 12475..1247F ; Unknown
'Xsux', # 12480..12543 ; Cuneiform 'Xsux', # 12480..12543 ; Cuneiform
'Zzzz', # 12544..12FFF ; Unknown 'Zzzz', # 12544..12F8F ; Unknown
'Cpmn', # 12F90..12FF2 ; Cypro_Minoan
'Zzzz', # 12FF3..12FFF ; Unknown
'Egyp', # 13000..1342E ; Egyptian_Hieroglyphs 'Egyp', # 13000..1342E ; Egyptian_Hieroglyphs
'Zzzz', # 1342F..1342F ; Unknown 'Zzzz', # 1342F..1342F ; Unknown
'Egyp', # 13430..13438 ; Egyptian_Hieroglyphs 'Egyp', # 13430..13438 ; Egyptian_Hieroglyphs
@ -2870,7 +2942,10 @@ VALUES = [
'Mroo', # 16A60..16A69 ; Mro 'Mroo', # 16A60..16A69 ; Mro
'Zzzz', # 16A6A..16A6D ; Unknown 'Zzzz', # 16A6A..16A6D ; Unknown
'Mroo', # 16A6E..16A6F ; Mro 'Mroo', # 16A6E..16A6F ; Mro
'Zzzz', # 16A70..16ACF ; Unknown 'Tnsa', # 16A70..16ABE ; Tangsa
'Zzzz', # 16ABF..16ABF ; Unknown
'Tnsa', # 16AC0..16AC9 ; Tangsa
'Zzzz', # 16ACA..16ACF ; Unknown
'Bass', # 16AD0..16AED ; Bassa_Vah 'Bass', # 16AD0..16AED ; Bassa_Vah
'Zzzz', # 16AEE..16AEF ; Unknown 'Zzzz', # 16AEE..16AEF ; Unknown
'Bass', # 16AF0..16AF5 ; Bassa_Vah 'Bass', # 16AF0..16AF5 ; Bassa_Vah
@ -2895,7 +2970,7 @@ VALUES = [
'Zzzz', # 16FA0..16FDF ; Unknown 'Zzzz', # 16FA0..16FDF ; Unknown
'Tang', # 16FE0..16FE0 ; Tangut 'Tang', # 16FE0..16FE0 ; Tangut
'Nshu', # 16FE1..16FE1 ; Nushu 'Nshu', # 16FE1..16FE1 ; Nushu
'Zyyy', # 16FE2..16FE3 ; Common 'Hani', # 16FE2..16FE3 ; Han
'Kits', # 16FE4..16FE4 ; Khitan_Small_Script 'Kits', # 16FE4..16FE4 ; Khitan_Small_Script
'Zzzz', # 16FE5..16FEF ; Unknown 'Zzzz', # 16FE5..16FEF ; Unknown
'Hani', # 16FF0..16FF1 ; Han 'Hani', # 16FF0..16FF1 ; Han
@ -2906,10 +2981,17 @@ VALUES = [
'Kits', # 18B00..18CD5 ; Khitan_Small_Script 'Kits', # 18B00..18CD5 ; Khitan_Small_Script
'Zzzz', # 18CD6..18CFF ; Unknown 'Zzzz', # 18CD6..18CFF ; Unknown
'Tang', # 18D00..18D08 ; Tangut 'Tang', # 18D00..18D08 ; Tangut
'Zzzz', # 18D09..1AFFF ; Unknown 'Zzzz', # 18D09..1AFEF ; Unknown
'Kana', # 1AFF0..1AFF3 ; Katakana
'Zzzz', # 1AFF4..1AFF4 ; Unknown
'Kana', # 1AFF5..1AFFB ; Katakana
'Zzzz', # 1AFFC..1AFFC ; Unknown
'Kana', # 1AFFD..1AFFE ; Katakana
'Zzzz', # 1AFFF..1AFFF ; Unknown
'Kana', # 1B000..1B000 ; Katakana 'Kana', # 1B000..1B000 ; Katakana
'Hira', # 1B001..1B11E ; Hiragana 'Hira', # 1B001..1B11F ; Hiragana
'Zzzz', # 1B11F..1B14F ; Unknown 'Kana', # 1B120..1B122 ; Katakana
'Zzzz', # 1B123..1B14F ; Unknown
'Hira', # 1B150..1B152 ; Hiragana 'Hira', # 1B150..1B152 ; Hiragana
'Zzzz', # 1B153..1B163 ; Unknown 'Zzzz', # 1B153..1B163 ; Unknown
'Kana', # 1B164..1B167 ; Katakana 'Kana', # 1B164..1B167 ; Katakana
@ -2926,7 +3008,13 @@ VALUES = [
'Zzzz', # 1BC9A..1BC9B ; Unknown 'Zzzz', # 1BC9A..1BC9B ; Unknown
'Dupl', # 1BC9C..1BC9F ; Duployan 'Dupl', # 1BC9C..1BC9F ; Duployan
'Zyyy', # 1BCA0..1BCA3 ; Common 'Zyyy', # 1BCA0..1BCA3 ; Common
'Zzzz', # 1BCA4..1CFFF ; Unknown 'Zzzz', # 1BCA4..1CEFF ; Unknown
'Zinh', # 1CF00..1CF2D ; Inherited
'Zzzz', # 1CF2E..1CF2F ; Unknown
'Zinh', # 1CF30..1CF46 ; Inherited
'Zzzz', # 1CF47..1CF4F ; Unknown
'Zyyy', # 1CF50..1CFC3 ; Common
'Zzzz', # 1CFC4..1CFFF ; Unknown
'Zyyy', # 1D000..1D0F5 ; Common 'Zyyy', # 1D000..1D0F5 ; Common
'Zzzz', # 1D0F6..1D0FF ; Unknown 'Zzzz', # 1D0F6..1D0FF ; Unknown
'Zyyy', # 1D100..1D126 ; Common 'Zyyy', # 1D100..1D126 ; Common
@ -2939,8 +3027,8 @@ VALUES = [
'Zinh', # 1D185..1D18B ; Inherited 'Zinh', # 1D185..1D18B ; Inherited
'Zyyy', # 1D18C..1D1A9 ; Common 'Zyyy', # 1D18C..1D1A9 ; Common
'Zinh', # 1D1AA..1D1AD ; Inherited 'Zinh', # 1D1AA..1D1AD ; Inherited
'Zyyy', # 1D1AE..1D1E8 ; Common 'Zyyy', # 1D1AE..1D1EA ; Common
'Zzzz', # 1D1E9..1D1FF ; Unknown 'Zzzz', # 1D1EB..1D1FF ; Unknown
'Grek', # 1D200..1D245 ; Greek 'Grek', # 1D200..1D245 ; Greek
'Zzzz', # 1D246..1D2DF ; Unknown 'Zzzz', # 1D246..1D2DF ; Unknown
'Zyyy', # 1D2E0..1D2F3 ; Common 'Zyyy', # 1D2E0..1D2F3 ; Common
@ -2995,7 +3083,9 @@ VALUES = [
'Sgnw', # 1DA9B..1DA9F ; SignWriting 'Sgnw', # 1DA9B..1DA9F ; SignWriting
'Zzzz', # 1DAA0..1DAA0 ; Unknown 'Zzzz', # 1DAA0..1DAA0 ; Unknown
'Sgnw', # 1DAA1..1DAAF ; SignWriting 'Sgnw', # 1DAA1..1DAAF ; SignWriting
'Zzzz', # 1DAB0..1DFFF ; Unknown 'Zzzz', # 1DAB0..1DEFF ; Unknown
'Latn', # 1DF00..1DF1E ; Latin
'Zzzz', # 1DF1F..1DFFF ; Unknown
'Glag', # 1E000..1E006 ; Glagolitic 'Glag', # 1E000..1E006 ; Glagolitic
'Zzzz', # 1E007..1E007 ; Unknown 'Zzzz', # 1E007..1E007 ; Unknown
'Glag', # 1E008..1E018 ; Glagolitic 'Glag', # 1E008..1E018 ; Glagolitic
@ -3013,11 +3103,21 @@ VALUES = [
'Hmnp', # 1E140..1E149 ; Nyiakeng_Puachue_Hmong 'Hmnp', # 1E140..1E149 ; Nyiakeng_Puachue_Hmong
'Zzzz', # 1E14A..1E14D ; Unknown 'Zzzz', # 1E14A..1E14D ; Unknown
'Hmnp', # 1E14E..1E14F ; Nyiakeng_Puachue_Hmong 'Hmnp', # 1E14E..1E14F ; Nyiakeng_Puachue_Hmong
'Zzzz', # 1E150..1E2BF ; Unknown 'Zzzz', # 1E150..1E28F ; Unknown
'Toto', # 1E290..1E2AE ; Toto
'Zzzz', # 1E2AF..1E2BF ; Unknown
'Wcho', # 1E2C0..1E2F9 ; Wancho 'Wcho', # 1E2C0..1E2F9 ; Wancho
'Zzzz', # 1E2FA..1E2FE ; Unknown 'Zzzz', # 1E2FA..1E2FE ; Unknown
'Wcho', # 1E2FF..1E2FF ; Wancho 'Wcho', # 1E2FF..1E2FF ; Wancho
'Zzzz', # 1E300..1E7FF ; Unknown 'Zzzz', # 1E300..1E7DF ; Unknown
'Ethi', # 1E7E0..1E7E6 ; Ethiopic
'Zzzz', # 1E7E7..1E7E7 ; Unknown
'Ethi', # 1E7E8..1E7EB ; Ethiopic
'Zzzz', # 1E7EC..1E7EC ; Unknown
'Ethi', # 1E7ED..1E7EE ; Ethiopic
'Zzzz', # 1E7EF..1E7EF ; Unknown
'Ethi', # 1E7F0..1E7FE ; Ethiopic
'Zzzz', # 1E7FF..1E7FF ; Unknown
'Mend', # 1E800..1E8C4 ; Mende_Kikakui 'Mend', # 1E800..1E8C4 ; Mende_Kikakui
'Zzzz', # 1E8C5..1E8C6 ; Unknown 'Zzzz', # 1E8C5..1E8C6 ; Unknown
'Mend', # 1E8C7..1E8D6 ; Mende_Kikakui 'Mend', # 1E8C7..1E8D6 ; Mende_Kikakui
@ -3127,8 +3227,8 @@ VALUES = [
'Zyyy', # 1F260..1F265 ; Common 'Zyyy', # 1F260..1F265 ; Common
'Zzzz', # 1F266..1F2FF ; Unknown 'Zzzz', # 1F266..1F2FF ; Unknown
'Zyyy', # 1F300..1F6D7 ; Common 'Zyyy', # 1F300..1F6D7 ; Common
'Zzzz', # 1F6D8..1F6DF ; Unknown 'Zzzz', # 1F6D8..1F6DC ; Unknown
'Zyyy', # 1F6E0..1F6EC ; Common 'Zyyy', # 1F6DD..1F6EC ; Common
'Zzzz', # 1F6ED..1F6EF ; Unknown 'Zzzz', # 1F6ED..1F6EF ; Unknown
'Zyyy', # 1F6F0..1F6FC ; Common 'Zyyy', # 1F6F0..1F6FC ; Common
'Zzzz', # 1F6FD..1F6FF ; Unknown 'Zzzz', # 1F6FD..1F6FF ; Unknown
@ -3137,7 +3237,9 @@ VALUES = [
'Zyyy', # 1F780..1F7D8 ; Common 'Zyyy', # 1F780..1F7D8 ; Common
'Zzzz', # 1F7D9..1F7DF ; Unknown 'Zzzz', # 1F7D9..1F7DF ; Unknown
'Zyyy', # 1F7E0..1F7EB ; Common 'Zyyy', # 1F7E0..1F7EB ; Common
'Zzzz', # 1F7EC..1F7FF ; Unknown 'Zzzz', # 1F7EC..1F7EF ; Unknown
'Zyyy', # 1F7F0..1F7F0 ; Common
'Zzzz', # 1F7F1..1F7FF ; Unknown
'Zyyy', # 1F800..1F80B ; Common 'Zyyy', # 1F800..1F80B ; Common
'Zzzz', # 1F80C..1F80F ; Unknown 'Zzzz', # 1F80C..1F80F ; Unknown
'Zyyy', # 1F810..1F847 ; Common 'Zyyy', # 1F810..1F847 ; Common
@ -3150,38 +3252,38 @@ VALUES = [
'Zzzz', # 1F8AE..1F8AF ; Unknown 'Zzzz', # 1F8AE..1F8AF ; Unknown
'Zyyy', # 1F8B0..1F8B1 ; Common 'Zyyy', # 1F8B0..1F8B1 ; Common
'Zzzz', # 1F8B2..1F8FF ; Unknown 'Zzzz', # 1F8B2..1F8FF ; Unknown
'Zyyy', # 1F900..1F978 ; Common 'Zyyy', # 1F900..1FA53 ; Common
'Zzzz', # 1F979..1F979 ; Unknown
'Zyyy', # 1F97A..1F9CB ; Common
'Zzzz', # 1F9CC..1F9CC ; Unknown
'Zyyy', # 1F9CD..1FA53 ; Common
'Zzzz', # 1FA54..1FA5F ; Unknown 'Zzzz', # 1FA54..1FA5F ; Unknown
'Zyyy', # 1FA60..1FA6D ; Common 'Zyyy', # 1FA60..1FA6D ; Common
'Zzzz', # 1FA6E..1FA6F ; Unknown 'Zzzz', # 1FA6E..1FA6F ; Unknown
'Zyyy', # 1FA70..1FA74 ; Common 'Zyyy', # 1FA70..1FA74 ; Common
'Zzzz', # 1FA75..1FA77 ; Unknown 'Zzzz', # 1FA75..1FA77 ; Unknown
'Zyyy', # 1FA78..1FA7A ; Common 'Zyyy', # 1FA78..1FA7C ; Common
'Zzzz', # 1FA7B..1FA7F ; Unknown 'Zzzz', # 1FA7D..1FA7F ; Unknown
'Zyyy', # 1FA80..1FA86 ; Common 'Zyyy', # 1FA80..1FA86 ; Common
'Zzzz', # 1FA87..1FA8F ; Unknown 'Zzzz', # 1FA87..1FA8F ; Unknown
'Zyyy', # 1FA90..1FAA8 ; Common 'Zyyy', # 1FA90..1FAAC ; Common
'Zzzz', # 1FAA9..1FAAF ; Unknown 'Zzzz', # 1FAAD..1FAAF ; Unknown
'Zyyy', # 1FAB0..1FAB6 ; Common 'Zyyy', # 1FAB0..1FABA ; Common
'Zzzz', # 1FAB7..1FABF ; Unknown 'Zzzz', # 1FABB..1FABF ; Unknown
'Zyyy', # 1FAC0..1FAC2 ; Common 'Zyyy', # 1FAC0..1FAC5 ; Common
'Zzzz', # 1FAC3..1FACF ; Unknown 'Zzzz', # 1FAC6..1FACF ; Unknown
'Zyyy', # 1FAD0..1FAD6 ; Common 'Zyyy', # 1FAD0..1FAD9 ; Common
'Zzzz', # 1FAD7..1FAFF ; Unknown 'Zzzz', # 1FADA..1FADF ; Unknown
'Zyyy', # 1FAE0..1FAE7 ; Common
'Zzzz', # 1FAE8..1FAEF ; Unknown
'Zyyy', # 1FAF0..1FAF6 ; Common
'Zzzz', # 1FAF7..1FAFF ; Unknown
'Zyyy', # 1FB00..1FB92 ; Common 'Zyyy', # 1FB00..1FB92 ; Common
'Zzzz', # 1FB93..1FB93 ; Unknown 'Zzzz', # 1FB93..1FB93 ; Unknown
'Zyyy', # 1FB94..1FBCA ; Common 'Zyyy', # 1FB94..1FBCA ; Common
'Zzzz', # 1FBCB..1FBEF ; Unknown 'Zzzz', # 1FBCB..1FBEF ; Unknown
'Zyyy', # 1FBF0..1FBF9 ; Common 'Zyyy', # 1FBF0..1FBF9 ; Common
'Zzzz', # 1FBFA..1FFFF ; Unknown 'Zzzz', # 1FBFA..1FFFF ; Unknown
'Hani', # 20000..2A6DD ; Han 'Hani', # 20000..2A6DF ; Han
'Zzzz', # 2A6DE..2A6FF ; Unknown 'Zzzz', # 2A6E0..2A6FF ; Unknown
'Hani', # 2A700..2B734 ; Han 'Hani', # 2A700..2B738 ; Han
'Zzzz', # 2B735..2B73F ; Unknown 'Zzzz', # 2B739..2B73F ; Unknown
'Hani', # 2B740..2B81D ; Han 'Hani', # 2B740..2B81D ; Han
'Zzzz', # 2B81E..2B81F ; Unknown 'Zzzz', # 2B81E..2B81F ; Unknown
'Hani', # 2B820..2CEA1 ; Han 'Hani', # 2B820..2CEA1 ; Han
@ -3226,6 +3328,7 @@ NAMES = {
'Cher': 'Cherokee', 'Cher': 'Cherokee',
'Chrs': 'Chorasmian', 'Chrs': 'Chorasmian',
'Copt': 'Coptic', 'Copt': 'Coptic',
'Cpmn': 'Cypro_Minoan',
'Cprt': 'Cypriot', 'Cprt': 'Cypriot',
'Cyrl': 'Cyrillic', 'Cyrl': 'Cyrillic',
'Deva': 'Devanagari', 'Deva': 'Devanagari',
@ -3305,6 +3408,7 @@ NAMES = {
'Orya': 'Oriya', 'Orya': 'Oriya',
'Osge': 'Osage', 'Osge': 'Osage',
'Osma': 'Osmanya', 'Osma': 'Osmanya',
'Ougr': 'Old_Uyghur',
'Palm': 'Palmyrene', 'Palm': 'Palmyrene',
'Pauc': 'Pau_Cin_Hau', 'Pauc': 'Pau_Cin_Hau',
'Perm': 'Old_Permic', 'Perm': 'Old_Permic',
@ -3347,8 +3451,11 @@ NAMES = {
'Thai': 'Thai', 'Thai': 'Thai',
'Tibt': 'Tibetan', 'Tibt': 'Tibetan',
'Tirh': 'Tirhuta', 'Tirh': 'Tirhuta',
'Tnsa': 'Tangsa',
'Toto': 'Toto',
'Ugar': 'Ugaritic', 'Ugar': 'Ugaritic',
'Vaii': 'Vai', 'Vaii': 'Vai',
'Vith': 'Vithkuqi',
'Wara': 'Warang_Citi', 'Wara': 'Warang_Citi',
'Wcho': 'Wancho', 'Wcho': 'Wancho',
'Xpeo': 'Old_Persian', 'Xpeo': 'Old_Persian',

View File

@ -73,7 +73,7 @@ def script_extension(char):
>>> script_extension("a") == {'Latn'} >>> script_extension("a") == {'Latn'}
True True
>>> script_extension(chr(0x060C)) == {'Rohg', 'Syrc', 'Yezi', 'Arab', 'Thaa'} >>> script_extension(chr(0x060C)) == {'Rohg', 'Syrc', 'Yezi', 'Arab', 'Thaa', 'Nkoo'}
True True
>>> script_extension(chr(0x10FFFF)) == {'Zzzz'} >>> script_extension(chr(0x10FFFF)) == {'Zzzz'}
True True

View File

@ -198,7 +198,7 @@ def test_block():
assert unicodedata.block("\x7F") == "Basic Latin" assert unicodedata.block("\x7F") == "Basic Latin"
assert unicodedata.block("\x80") == "Latin-1 Supplement" assert unicodedata.block("\x80") == "Latin-1 Supplement"
assert unicodedata.block("\u1c90") == "Georgian Extended" assert unicodedata.block("\u1c90") == "Georgian Extended"
assert unicodedata.block("\u0870") == "No_Block" assert unicodedata.block("\u0870") == "Arabic Extended-B"
def test_ot_tags_from_script(): def test_ot_tags_from_script():