use utf8;
-my %uniblock = (
++{
# bmp
- 0x000, '<td colspan="2" class="X Cc joinr">control',
- 0x002, '<td colspan="2" class="X L Po joinl joinr">comn',
- 0x004, '<td colspan="4" class="X L Latin joinl">basic latin',
- 0x008, '<td colspan="2" class="X Cc joinr">control',
- 0x00A, '<td colspan="2" class="X L So joinl joinr">comn',
- 0x00C, '<td colspan="4" class="X L Latin joinl">latin1',
- 0x010, '<td colspan="8" class="X L Latin">latin extended-A',
- 0x018, '<td colspan="8" class="X L Latin">latin extended-B',
- 0x020, '<td colspan="5" class="X L Latin">latin ext-B',
- 0x025, '<td colspan="6" class="X L Latin">IPA',
- 0x02B, '<td colspan="5" class="X Sk">spacing modifier',
- 0x030, '<td colspan="8" class="X Mn">diacritics',
- 0x038, '<td colspan="8" class="X L Greek">greek',
- 0x040, '<td colspan="16" class="X L Cyrillic">cyrillic',
- 0x050, '<td colspan="3" class="X L Cyrillic">cyrillic+',
- 0x053, '<td colspan="5" class="X L Armenian">armenian',
- 0x058, '<td colspan="8" class="X L Hebrew">hebrew',
- 0x060, '<td colspan="16" class="X L Arabic">arabic',
- 0x070, '<td colspan="5" class="X L Aramaic">syriac',
- 0x075, '<td colspan="3" class="X L Arabic">arabic+',
- 0x078, '<td colspan="4" class="X L African">thaana',
- 0x07C, '<td colspan="4" class="X L African">n\'ko',
- 0x080, '<td colspan="4" class="X L Hebrew">samaritan',
- 0x084, '<td colspan="2" class="X L Aramaic">manda',
- 0x086, '<td colspan="1" class="X Xr L Aramaic">syr',
- 0x087, '<td colspan="3" class="">reserved',
- 0x08A, '<td colspan="6" class="X L Arabic">arabic ext-A',
- 0x090, '<td colspan="8" class="X L Brahmic">devanagari',
- 0x098, '<td colspan="8" class="X L Brahmic">bengali',
- 0x0A0, '<td colspan="8" class="X L Brahmic">gurmukhi',
- 0x0A8, '<td colspan="8" class="X L Brahmic">gujarati',
- 0x0B0, '<td colspan="8" class="X L Brahmic">oriya',
- 0x0B8, '<td colspan="8" class="X L Brahmic">tamil',
- 0x0C0, '<td colspan="8" class="X L Brahmic">telugu',
- 0x0C8, '<td colspan="8" class="X L Brahmic">kannada',
- 0x0D0, '<td colspan="8" class="X L Brahmic">malayalam',
- 0x0D8, '<td colspan="8" class="X L Brahmic">sinhala',
- 0x0E0, '<td colspan="8" class="X L Brahmic Khmer">thai',
- 0x0E8, '<td colspan="8" class="X L Brahmic Khmer">lao',
- 0x0F0, '<td colspan="16" class="X L Brahmic">tibetan',
- 0x100, '<td colspan="10" class="X L Brahmic">myanmar',
- 0x10A, '<td colspan="6" class="X L Aramaic">georgian',
- 0x110, '<td colspan="16" class="X L Hangul">hangeul jamo',
- 0x120, '<td colspan="16" class="X L African">ethiopic',
- 0x130, '<td colspan="8" class="X L African">ethiopic',
- 0x138, '<td colspan="2" class="X L African">eth+',
- 0x13A, '<td colspan="6" class="X L Syllabic">cherokee',
- 0x140, '<td colspan="16" rowspan="2" class="X L Syllabic">unified canadian aboriginal syllabics',
- 0x160, '<td colspan="8" class="X L Syllabic">unified canadian syllabics',
- 0x168, '<td colspan="2" class="X L Alpha">ogham',
- 0x16A, '<td colspan="6" class="X L Alpha">runic',
- 0x170, '<td colspan="2" class="X L Brahmic">tagalog',
- 0x172, '<td colspan="2" class="X L Brahmic">hanun',
- 0x174, '<td colspan="2" class="X L Brahmic">buhid',
- 0x176, '<td colspan="2" class="X L Brahmic" title="tagbanwa">tagb',
- 0x178, '<td colspan="8" class="X L Brahmic Khmer">khmer',
- 0x180, '<td colspan="11" class="X L Aramaic">mongolian',
- 0x18B, '<td colspan="5" class="X L Syllabic">canadian+',
- 0x190, '<td colspan="5" class="X L Brahmic">limbu',
- 0x195, '<td colspan="3" class="X L Brahmic">tai le',
- 0x198, '<td colspan="6" class="X L Brahmic">new tai lue',
- 0x19E, '<td colspan="2" class="X L Brahmic Khmer" title="khmer symbols">khmer',
- 0x1A0, '<td colspan="2" class="X L Brahmic">lontara',
- 0x1A2, '<td colspan="9" class="X L Brahmic">tai tham',
- 0x1AB, '<td colspan="5" class="X Mn">diacritics+',
- 0x1B0, '<td colspan="8" class="X L Brahmic">balinese',
- 0x1B8, '<td colspan="4" class="X L Brahmic">sundanese',
- 0x1BC, '<td colspan="4" class="X L Brahmic">batak',
- 0x1C0, '<td colspan="5" class="X L Brahmic">lepcha',
- 0x1C5, '<td colspan="3" class="X L Alpha">ol chiki',
- 0x1C8, '<td colspan="1" class="X L Cyrillic">cyr',
- 0x1C9, '<td colspan="3" class="X Xr L Aramaic">georg+',
- 0x1CC, '<td colspan="1" class="X L Brahmic">sn',
- 0x1CD, '<td colspan="3" class="X L Brahmic">vedic',
- 0x1D0, '<td colspan="8" class="X L Latin">phonetic',
- 0x1D8, '<td colspan="4" class="X L Latin">phonetic+',
- 0x1DC, '<td colspan="4" class="X Mn">diacritics+',
- 0x1E0, '<td colspan="16" class="X L Latin">latin extended additional',
- 0x1F0, '<td colspan="16" class="X L Greek">greek+',
- 0x200, '<td colspan="7" class="X Po">general punctuation',
- 0x207, '<td colspan="3" class="X L Latin">suþscript', # suth now means "sub and/or sup"
- 0x20A, '<td colspan="3" class="X Sc">currency',
- 0x20D, '<td colspan="3" class="X Mn">overlay',
- 0x210, '<td colspan="5" class="X So">letterlike',
- 0x215, '<td colspan="4" class="X Latin">number',
- 0x219, '<td colspan="7" class="X So">arrows',
- 0x220, '<td colspan="16" class="X Sm">mathematical symbols',
- 0x230, '<td colspan="16" class="X So">miscellaneous technical',
- 0x240, '<td colspan="4" class="X So">control',
- 0x244, '<td colspan="2" class="X So">OCR',
- 0x246, '<td colspan="10" class="X Latin">enclosed alphanumerics',
- 0x250, '<td colspan="8" class="X So">box drawing',
- 0x258, '<td colspan="2" class="X So">blocks',
- 0x25A, '<td colspan="6" class="X So">geometric shapes',
- 0x260, '<td colspan="16" class="X So">miscellaneous symbols',
- 0x270, '<td colspan="12" class="X So">dingbats',
- 0x27C, '<td colspan="3" class="X Sm">maths-A',
- 0x27F, '<td colspan="1" class="X So" title="supplemental arrows-A">arr',
- 0x280, '<td colspan="16" class="X L Alpha">braille',
- 0x290, '<td colspan="8" class="X So">supplemental arrows-B',
- 0x298, '<td colspan="8" class="X Sm">mathematical symbols-B',
- 0x2A0, '<td colspan="16" class="X Sm">supplemental mathematical operators',
- 0x2B0, '<td colspan="16" class="X So">miscellaneous symbols and arrows',
- 0x2C0, '<td colspan="6" class="X L Cyrillic">glagolitic',
- 0x2C6, '<td colspan="2" class="X L Latin">latin-C',
- 0x2C8, '<td colspan="8" class="X L Greek">coptic',
- 0x2D0, '<td colspan="3" class="X L Aramaic">georgian+',
- 0x2D3, '<td colspan="5" class="X L Alpha">tifinagh', #TODO: proto-canaanite
- 0x2D8, '<td colspan="6" class="X L African">ethiopic+',
- 0x2DE, '<td colspan="2" class="X L Cyrillic">cyrl-A',
- 0x2E0, '<td colspan="8" class="X Po">punctuation+',
- 0x2E8, '<td colspan="8" class="X L Han">cjk radicals',
- 0x2F0, '<td colspan="14" class="X L Han">kangxi radicals',
- 0x2FE, '<td colspan="1" class="">',
- 0x2FF, '<td colspan="1" class="X So Han">idc',
- 0x300, '<td colspan="4" class="X Po Han">cjk misc',
- 0x304, '<td colspan="6" class="X L Hiragana">hiragana',
- 0x30A, '<td colspan="6" class="X L Katakana">katakana',
- 0x310, '<td colspan="3" class="X L Bopomofo">bopomofo',
- 0x313, '<td colspan="6" class="X L Katakana">hangeul compat',
- 0x319, '<td colspan="1" class="X L Han" title="kanbun">kbn',
- 0x31A, '<td colspan="2" class="X L Bopomofo" title="bopomofo extended">bpmf',
- 0x31C, '<td colspan="3" class="X L Han" title="CJK strokes">strokes',
- 0x31F, '<td colspan="1" class="X L Katakana" title="katakana phonetic extensions">k+',
- 0x320, '<td colspan="16" class="X L Han">enclosed cjk characters',
- 0x330, '<td colspan="16" class="X Xd L Han">cjk compatibility',
- 0x340, '<td colspan="16" rowspan="25" class="X L Han">cjk unified ideographs extension A',
- 0x4D0, '<td colspan="12" class="X L Han joinu">cjk unified ideographs extension A',
- 0x4DC, '<td colspan="4" class="X So">hexagrams',
- 0x4E0, '<td colspan="16" rowspan="82" class="X L Han">cjk unified ideographs',
- 0xA00, '<td colspan="16" rowspan="4" class="X L Syllabic">yi',
- 0xA40, '<td colspan="9" class="X L Syllabic joinu">yi',
- 0xA49, '<td colspan="4" class="X L Syllabic">yi radicals',
- 0xA4D, '<td colspan="3" class="X L Latin">lisu',
- 0xA50, '<td colspan="16" class="X L Syllabic">vai',
- 0xA60, '<td colspan="4" class="X L Syllabic joinu">vai',
- 0xA64, '<td colspan="6" class="X L Cyrillic">cyrillic extended-B',
- 0xA6A, '<td colspan="6" class="X L Syllabic">bamum',
- 0xA70, '<td colspan="2" class="X L Mn">tones',
- 0xA72, '<td colspan="14" class="X L Latin">latin extended-D',
- 0xA80, '<td colspan="3" class="X L Brahmic">sylheti',
- 0xA83, '<td colspan="1" class="X No">in',
- 0xA84, '<td colspan="4" class="X L Brahmic">phags-pa',
- 0xA88, '<td colspan="6" class="X L Brahmic">saurashtra',
- 0xA8E, '<td colspan="2" class="X L Brahmic">deva+',
- 0xA90, '<td colspan="3" class="X L Brahmic">kayah li',
- 0xA93, '<td colspan="3" class="X L Brahmic">rejang',
- 0xA96, '<td colspan="2" class="X L Hangul">jamo-A',
- 0xA98, '<td colspan="6" class="X L Brahmic">javanese',
- 0xA9E, '<td colspan="2" class="X L Brahmic" title="myanmar extended-B">mm-B',
- 0xAA0, '<td colspan="6" class="X L Brahmic">cham',
- 0xAA6, '<td colspan="2" class="X L Brahmic" title="myanmar extended-A">mm-A',
- 0xAA8, '<td colspan="6" class="X L Brahmic Khmer">tai viet',
- 0xAAE, '<td colspan="2" class="X L Brahmic" title="meetei mayek extended">mtei+',
- 0xAB0, '<td colspan="3" class="X L African">ethiopic-A',
- 0xAB3, '<td colspan="4" class="X L Latin">latin ext-E',
- 0xAB7, '<td colspan="5" class="X L Syllabic">cherokee+',
- 0xABC, '<td colspan="4" class="X L Brahmic" title="meetai mayek">meithei',
- 0xAC0, '<td colspan="16" rowspan="43" class="X L Hangul">hangeul syllables',
- 0xD70, '<td colspan="11" class="X L Hangul joinu">hangeul syllables',
- 0xD7B, '<td colspan="5" class="X L Hangul">haungeul jamo-B',
- 0xD80, '<td colspan="16" rowspan="4" class="X Cs">high surrogates',
- 0xDC0, '<td colspan="16" rowspan="4" class="X Cs">low surrogates',
- 0xE00, '<td colspan="16" rowspan="25" class="X Co">private use',
- 0xF90, '<td colspan="16" rowspan="2" class="X L Han">cjk compatibility ideographs',
- 0xFB0, '<td colspan="5" class="X Xd L Alpha">presentation',
- 0xFB5, '<td colspan="11" class="X Xd L Arabic joind">',
- 0xFC0, '<td colspan="16" class="X Xd L Arabic joinu joind">arabic presentation forms A',
- 0xFD0, '<td colspan="13" class="X Xd L Arabic joinu">',
- 0xFDD, '<td colspan="2" class="Xi">?',
- 0xFDF, '<td colspan="1" class="X Xd L Arabic joinu">',
- 0xFE0, '<td colspan="1" class="X Cc">var',
- 0xFE1, '<td colspan="1" class="X L Pd">ver',
- 0xFE2, '<td colspan="1" class="X L Mn">½',
- 0xFE3, '<td colspan="2" class="X Xd Pd Han">comp',
- 0xFE5, '<td colspan="2" class="X Xd L Latin">small',
- 0xFE7, '<td colspan="9" class="X Xd L Arabic">arabic presentation B',
- 0xFF0, '<td colspan="15" class="X L Latin">halfwidth & fullwidth forms',
- 0xFFF, '<td colspan="1" class="X Cc">sp',
+ 0x0000 => [0x02, 'X Cc joinr', 'control'],
+ 0x0002 => [0x02, 'X L Po joinl joinr', 'comn'],
+ 0x0004 => [0x04, 'X L Latin joinl', 'basic latin'],
+ 0x0008 => [0x02, 'X Cc joinr', 'control'],
+ 0x000A => [0x02, 'X L So joinl joinr', 'comn'],
+ 0x000C => [0x04, 'X L Latin joinl', 'latin1'],
+ 0x0010 => [0x08, 'X L Latin', 'latin extended-A'],
+ 0x0018 => [0x08, 'X L Latin', 'latin extended-B'],
+ 0x0020 => [0x05, 'X L Latin', 'latin ext-B'],
+ 0x0025 => [0x06, 'X L Latin', 'IPA'],
+ 0x002B => [0x05, 'X Sk', 'spacing modifier'],
+ 0x0030 => [0x08, 'X Mn', 'diacritics'],
+ 0x0038 => [0x08, 'X L Greek', 'greek'],
+ 0x0040 => [0x10, 'X L Cyrillic', 'cyrillic'],
+ 0x0050 => [0x03, 'X L Cyrillic', 'cyrillic+'],
+ 0x0053 => [0x05, 'X L Armenian', 'armenian'],
+ 0x0058 => [0x08, 'X L Hebrew', 'hebrew'],
+ 0x0060 => [0x10, 'X L Arabic', 'arabic'],
+ 0x0070 => [0x05, 'X L Aramaic', 'syriac'],
+ 0x0075 => [0x03, 'X L Arabic', 'arabic+'],
+ 0x0078 => [0x04, 'X L African', 'thaana'],
+ 0x007C => [0x04, 'X L African', 'n\'ko'],
+ 0x0080 => [0x04, 'X L Hebrew', 'samaritan'],
+ 0x0084 => [0x02, 'X L Aramaic', 'manda'],
+ 0x0086 => [0x01, 'X Xr L Aramaic', 'syr'],
+ 0x0087 => [0x03],
+ 0x008A => [0x06, 'X L Arabic', 'arabic ext-A'],
+ 0x0090 => [0x08, 'X L Brahmic', 'devanagari'],
+ 0x0098 => [0x08, 'X L Brahmic', 'bengali'],
+ 0x00A0 => [0x08, 'X L Brahmic', 'gurmukhi'],
+ 0x00A8 => [0x08, 'X L Brahmic', 'gujarati'],
+ 0x00B0 => [0x08, 'X L Brahmic', 'oriya'],
+ 0x00B8 => [0x08, 'X L Brahmic', 'tamil'],
+ 0x00C0 => [0x08, 'X L Brahmic', 'telugu'],
+ 0x00C8 => [0x08, 'X L Brahmic', 'kannada'],
+ 0x00D0 => [0x08, 'X L Brahmic', 'malayalam'],
+ 0x00D8 => [0x08, 'X L Brahmic', 'sinhala'],
+ 0x00E0 => [0x08, 'X L Brahmic Khmer', 'thai'],
+ 0x00E8 => [0x08, 'X L Brahmic Khmer', 'lao'],
+ 0x00F0 => [0x10, 'X L Brahmic', 'tibetan'],
+ 0x0100 => [0x0A, 'X L Brahmic', 'myanmar'],
+ 0x010A => [0x06, 'X L Aramaic', 'georgian'],
+ 0x0110 => [0x10, 'X L Hangul', 'hangeul jamo'],
+ 0x0120 => [0x10, 'X L African', 'ethiopic'],
+ 0x0130 => [0x08, 'X L African', 'ethiopic'],
+ 0x0138 => [0x02, 'X L African', 'eth+'],
+ 0x013A => [0x06, 'X L Syllabic', 'cherokee'],
+ 0x0140 => [0x20, 'X L Syllabic', 'unified canadian aboriginal syllabics'],
+ 0x0160 => [0x08, 'X L Syllabic', 'unified canadian syllabics'],
+ 0x0168 => [0x02, 'X L Alpha', 'ogham'],
+ 0x016A => [0x06, 'X L Alpha', 'runic'],
+ 0x0170 => [0x02, 'X L Brahmic', 'tagalog'],
+ 0x0172 => [0x02, 'X L Brahmic', 'hanun'],
+ 0x0174 => [0x02, 'X L Brahmic', 'buhid'],
+ 0x0176 => [0x02, 'X L Brahmic', 'tagb', 'tagbanwa'],
+ 0x0178 => [0x08, 'X L Brahmic Khmer', 'khmer'],
+ 0x0180 => [0x0B, 'X L Aramaic', 'mongolian'],
+ 0x018B => [0x05, 'X L Syllabic', 'canadian+'],
+ 0x0190 => [0x05, 'X L Brahmic', 'limbu'],
+ 0x0195 => [0x03, 'X L Brahmic', 'tai le'],
+ 0x0198 => [0x06, 'X L Brahmic', 'new tai lue'],
+ 0x019E => [0x02, 'X L Brahmic Khmer', 'khmer', 'khmer symbols'],
+ 0x01A0 => [0x02, 'X L Brahmic', 'lontara'],
+ 0x01A2 => [0x09, 'X L Brahmic', 'tai tham'],
+ 0x01AB => [0x05, 'X Mn', 'diacritics+'],
+ 0x01B0 => [0x08, 'X L Brahmic', 'balinese'],
+ 0x01B8 => [0x04, 'X L Brahmic', 'sundanese'],
+ 0x01BC => [0x04, 'X L Brahmic', 'batak'],
+ 0x01C0 => [0x05, 'X L Brahmic', 'lepcha'],
+ 0x01C5 => [0x03, 'X L Alpha', 'ol chiki'],
+ 0x01C8 => [0x01, 'X L Cyrillic', 'cyr'],
+ 0x01C9 => [0x03, 'X Xr L Aramaic', 'georg+'],
+ 0x01CC => [0x01, 'X L Brahmic', 'sn'],
+ 0x01CD => [0x03, 'X L Brahmic', 'vedic'],
+ 0x01D0 => [0x08, 'X L Latin', 'phonetic'],
+ 0x01D8 => [0x04, 'X L Latin', 'phonetic+'],
+ 0x01DC => [0x04, 'X Mn', 'diacritics+'],
+ 0x01E0 => [0x10, 'X L Latin', 'latin extended additional'],
+ 0x01F0 => [0x10, 'X L Greek', 'greek+'],
+ 0x0200 => [0x07, 'X Po', 'general punctuation'],
+ 0x0207 => [0x03, 'X L Latin', 'suþscript'], # suth now means "sub and/or sup"
+ 0x020A => [0x03, 'X Sc', 'currency'],
+ 0x020D => [0x03, 'X Mn', 'overlay'],
+ 0x0210 => [0x05, 'X So', 'letterlike'],
+ 0x0215 => [0x04, 'X Latin', 'number'],
+ 0x0219 => [0x07, 'X So', 'arrows'],
+ 0x0220 => [0x10, 'X Sm', 'mathematical symbols'],
+ 0x0230 => [0x10, 'X So', 'miscellaneous technical'],
+ 0x0240 => [0x04, 'X So', 'control'],
+ 0x0244 => [0x02, 'X So', 'OCR'],
+ 0x0246 => [0x0A, 'X Latin', 'enclosed alphanumerics'],
+ 0x0250 => [0x08, 'X So', 'box drawing'],
+ 0x0258 => [0x02, 'X So', 'blocks'],
+ 0x025A => [0x06, 'X So', 'geometric shapes'],
+ 0x0260 => [0x10, 'X So', 'miscellaneous symbols'],
+ 0x0270 => [0x0C, 'X So', 'dingbats'],
+ 0x027C => [0x03, 'X Sm', 'maths-A'],
+ 0x027F => [0x01, 'X So', 'arr', 'supplemental arrows-A'],
+ 0x0280 => [0x10, 'X L Alpha', 'braille'],
+ 0x0290 => [0x08, 'X So', 'supplemental arrows-B'],
+ 0x0298 => [0x08, 'X Sm', 'mathematical symbols-B'],
+ 0x02A0 => [0x10, 'X Sm', 'supplemental mathematical operators'],
+ 0x02B0 => [0x10, 'X So', 'miscellaneous symbols and arrows'],
+ 0x02C0 => [0x06, 'X L Cyrillic', 'glagolitic'],
+ 0x02C6 => [0x02, 'X L Latin', 'latin-C'],
+ 0x02C8 => [0x08, 'X L Greek', 'coptic'],
+ 0x02D0 => [0x03, 'X L Aramaic', 'georgian+'],
+ 0x02D3 => [0x05, 'X L Alpha', 'tifinagh'], #TODO: proto-canaanite
+ 0x02D8 => [0x06, 'X L African', 'ethiopic+'],
+ 0x02DE => [0x02, 'X L Cyrillic', 'cyrl-A'],
+ 0x02E0 => [0x08, 'X Po', 'punctuation+'],
+ 0x02E8 => [0x08, 'X L Han', 'cjk radicals'],
+ 0x02F0 => [0x0E, 'X L Han', 'kangxi radicals'],
+ 0x02FE => [0x01],
+ 0x02FF => [0x01, 'X So Han', 'idc'],
+ 0x0300 => [0x04, 'X Po Han', 'cjk misc'],
+ 0x0304 => [0x06, 'X L Hiragana', 'hiragana'],
+ 0x030A => [0x06, 'X L Katakana', 'katakana'],
+ 0x0310 => [0x03, 'X L Bopomofo', 'bopomofo'],
+ 0x0313 => [0x06, 'X L Katakana', 'hangeul compat'],
+ 0x0319 => [0x01, 'X L Han', 'kbn', 'kanbun'],
+ 0x031A => [0x02, 'X L Bopomofo', 'bpmf', 'bopomofo extended'],
+ 0x031C => [0x03, 'X L Han', 'strokes', 'CJK strokes'],
+ 0x031F => [0x01, 'X L Katakana', 'k+', 'katakana phonetic extensions'],
+ 0x0320 => [0x10, 'X L Han', 'enclosed cjk characters'],
+ 0x0330 => [0x10, 'X Xd L Han', 'cjk compatibility'],
+ 0x0340 => [0x19C,'X L Han', 'cjk unified ideographs extension A'],
+ 0x04DC => [0x04, 'X So', 'hexagrams'],
+ 0x04E0 => [0x520,'X L Han', 'cjk unified ideographs'],
+ 0x0A00 => [0x49, 'X L Syllabic', 'yi'],
+ 0x0A49 => [0x04, 'X L Syllabic', 'yi radicals'],
+ 0x0A4D => [0x03, 'X L Latin', 'lisu'],
+ 0x0A50 => [0x14, 'X L Syllabic', 'vai'],
+ 0x0A64 => [0x06, 'X L Cyrillic', 'cyrillic extended-B'],
+ 0x0A6A => [0x06, 'X L Syllabic', 'bamum'],
+ 0x0A70 => [0x02, 'X L Mn', 'tones'],
+ 0x0A72 => [0x0E, 'X L Latin', 'latin extended-D'],
+ 0x0A80 => [0x03, 'X L Brahmic', 'sylheti'],
+ 0x0A83 => [0x01, 'X No', 'in'],
+ 0x0A84 => [0x04, 'X L Brahmic', 'phags-pa'],
+ 0x0A88 => [0x06, 'X L Brahmic', 'saurashtra'],
+ 0x0A8E => [0x02, 'X L Brahmic', 'deva+'],
+ 0x0A90 => [0x03, 'X L Brahmic', 'kayah li'],
+ 0x0A93 => [0x03, 'X L Brahmic', 'rejang'],
+ 0x0A96 => [0x02, 'X L Hangul', 'jamo-A'],
+ 0x0A98 => [0x06, 'X L Brahmic', 'javanese'],
+ 0x0A9E => [0x02, 'X L Brahmic', 'mm-B', 'myanmar extended-B'],
+ 0x0AA0 => [0x06, 'X L Brahmic', 'cham'],
+ 0x0AA6 => [0x02, 'X L Brahmic', 'mm-A', 'myanmar extended-A'],
+ 0x0AA8 => [0x06, 'X L Brahmic Khmer', 'tai viet'],
+ 0x0AAE => [0x02, 'X L Brahmic', 'mtei+', 'meetei mayek extended'],
+ 0x0AB0 => [0x03, 'X L African', 'ethiopic-A'],
+ 0x0AB3 => [0x04, 'X L Latin', 'latin ext-E'],
+ 0x0AB7 => [0x05, 'X L Syllabic', 'cherokee+'],
+ 0x0ABC => [0x04, 'X L Brahmic', 'meithei', 'meetai mayek'],
+ 0x0AC0 => [0x2BB,'X L Hangul', 'hangeul syllables'],
+ 0x0D7B => [0x05, 'X L Hangul', 'haungeul jamo-B'],
+ 0x0D80 => [0x40, 'X Cs', 'high surrogates'],
+ 0x0DC0 => [0x40, 'X Cs', 'low surrogates'],
+ 0x0E00 => [0x190,'X Co', 'private use'],
+ 0x0F90 => [0x20, 'X L Han', 'cjk compatibility ideographs'],
+ 0x0FB0 => [0x05, 'X Xd L Alpha', 'presentation'],
+ 0x0FB5 => [0x28, 'X Xd L Arabic', 'arabic presentation forms A'],
+ 0x0FDD => [0x02, 'Xi', '?'],
+ 0x0FDF => [0x01, 'X Xd L Arabic joinu', ''], # continue after brief intermission
+ 0x0FE0 => [0x01, 'X Cc', 'var'],
+ 0x0FE1 => [0x01, 'X L Pd', 'ver'],
+ 0x0FE2 => [0x01, 'X L Mn', '½'],
+ 0x0FE3 => [0x02, 'X Xd Pd Han', 'comp'],
+ 0x0FE5 => [0x02, 'X Xd L Latin', 'small'],
+ 0x0FE7 => [0x09, 'X Xd L Arabic', 'arabic presentation B'],
+ 0x0FF0 => [0x0F, 'X L Latin', 'halfwidth & fullwidth forms'],
+ 0x0FFF => [0x01, 'X Cc', 'sp'],
# smp
- 0x1000, '<td colspan="8" class="X L Syllabic">linear B syllabary',
- 0x1008, '<td colspan="8" class="X L Syllabic">linear B ideograms',
- 0x1010, '<td colspan="4" class="X No">aegean num',
- 0x1014, '<td colspan="5" class="X No">greek numbers',
- 0x1019, '<td colspan="4" class="X So">ancient sym',
- 0x101D, '<td colspan="3" class="X L Syllabic">phaistos',
- 0x1020, '<td colspan="4" class="X Xr L Greek">iberian',
- 0x1024, '<td colspan="4" class="">reserved',
- 0x1028, '<td colspan="2" class="X L Greek">lycian',
- 0x102A, '<td colspan="4" class="X L Greek">carian',
- 0x102E, '<td colspan="2" class="X L No">coptic',
- 0x1030, '<td colspan="3" class="X L Greek">italic',
- 0x1033, '<td colspan="2" class="X L Greek">gothic',
- 0x1035, '<td colspan="3" class="X L Cyrillic">permic',
- 0x1038, '<td colspan="2" class="X L Alpha">ugarit',
- 0x103A, '<td colspan="4" class="X L Alpha">old persian',
- 0x103E, '<td colspan="2" class="X Xr L Alpha">sh.qs',
- 0x1040, '<td colspan="5" class="X L Alpha">deseret',
- 0x1045, '<td colspan="3" class="X L Alpha">shavian',
- 0x1048, '<td colspan="3" class="X L Alpha">osmanya',
- 0x104B, '<td colspan="5" class="X L Alpha">osage',
- 0x1050, '<td colspan="3" class="X L Alpha">elbasan',
- 0x1053, '<td colspan="4" class="X L Alpha">c albanian',
- 0x1057, '<td colspan="5" class="X Xr L Alpha">vithkuqi',
- 0x105C, '<td colspan="4" class="X Xr L Alpha">todhri',
- 0x1060, '<td colspan="16" class="X L Syllabic">linear A',
- 0x1070, '<td colspan="8" class="X L Syllabic">linear A',
- 0x1078, '<td colspan="8" class="X Xr L Syllabic">cypro-minoan',
- 0x1080, '<td colspan="4" class="X L Syllabic">cypriot',
- 0x1084, '<td colspan="2" class="X L Aramaic">aram',
- 0x1086, '<td colspan="2" class="X L Aramaic">palmr',
- 0x1088, '<td colspan="3" class="X L Aramaic">nabataean',
- 0x108A, '<td colspan="1" class="">res',
- 0x108C, '<td colspan="2" class="X Xr L Alpha">numid',
- 0x108E, '<td colspan="2" class="X L Aramaic">hatr',
- 0x1090, '<td colspan="2" class="X L Aramaic">phoen',
- 0x1092, '<td colspan="2" class="X L Greek">lydian',
- 0x1094, '<td colspan="4" class="">reserved',
- 0x1098, '<td colspan="2" class="X L Alpha" title="meroitic hieroglyphs">mero h',
- 0x109A, '<td colspan="6" class="X L Alpha">meroitic cursive',
- 0x10A0, '<td colspan="6" class="X L Syllabic">kharoshthi',
- 0x10A6, '<td colspan="2" class="X L Aramaic">s arab',
- 0x10A8, '<td colspan="2" class="X L Aramaic">n arab',
- 0x10AA, '<td colspan="2" class="X Xr L Brahmic">balti',
- 0x10AC, '<td colspan="4" class="X L Aramaic">manichaean',
- 0x10B0, '<td colspan="4" class="X L Aramaic">avestan',
- 0x10B4, '<td colspan="2" class="X L Aramaic">parth',
- 0x10B6, '<td colspan="2" class="X L Aramaic" title="inscriptional pahlavi">pahlav',
- 0x10B8, '<td colspan="3" class="X L Aramaic" title="psalter pahlavi">psalt pahl',
- 0x10BB, '<td colspan="3" class="X Xr L Aramaic" title="book pahlavi">book pahl',
- 0x10BE, '<td colspan="2" class="X Xr L Alpha">babur',
- 0x10C0, '<td colspan="5" class="X L Aramaic">old turkic',
- 0x10C5, '<td colspan="3" class="">reserved',
- 0x10C8, '<td colspan="8" class="X L Aramaic">old hungarian',
- 0x10D0, '<td colspan="4" class="X Xr L Alpha">rohingya',
- 0x10D4, '<td colspan="4" class="X Xr L Alpha">garay',
- 0x10D8, '<td colspan="8" class="X Xr L Syllabic">byblos',
- 0x10E0, '<td colspan="6" class="">reserved',
- 0x10E6, '<td colspan="2" class="X No">rumi',
- 0x10E8, '<td colspan="6" class="">reserved',
- 0x10EE, '<td colspan="2" class="X Xr L Aramaic">elym',
- 0x10F0, '<td colspan="3" class="X Xr L Aramaic">old sog',
- 0x10F3, '<td colspan="4" class="X Xr L Aramaic">sogdian',
- 0x10F7, '<td colspan="1" class="">res',
- 0x10F8, '<td colspan="8" class="X Xr L Aramaic">uyghur',
- 0x1100, '<td colspan="8" class="X L Brahmic">brahmi',
- 0x1108, '<td colspan="5" class="X L Brahmic">kaithi',
- 0x110D, '<td colspan="3" class="X L Brahmic">sora som',
- 0x1110, '<td colspan="5" class="X L Brahmic">chakma',
- 0x1115, '<td colspan="3" class="X L Brahmic">mahajani',
- 0x1118, '<td colspan="6" class="X L Brahmic">sharada',
- 0x111E, '<td colspan="2" class="X No Brahmic">sinhal',
- 0x1120, '<td colspan="5" class="X L Brahmic">khojki',
- 0x1125, '<td colspan="3" class="X Xr L Brahmic">landa',
- 0x1128, '<td colspan="3" class="X L Brahmic">multani',
- 0x112B, '<td colspan="5" class="X L Brahmic">khudabadi',
- 0x1130, '<td colspan="8" class="X L Brahmic">grantha',
- 0x1138, '<td colspan="6" class="X Xr L Brahmic">tulu',
- 0x113E, '<td colspan="2" class="X Xr L Brahmic" title="sharada extension">shar+',
- 0x1140, '<td colspan="8" class="X L Brahmic">newar',
- 0x1148, '<td colspan="6" class="X L Brahmic">tirhuta',
- 0x114E, '<td colspan="2" class="X Xr L Alpha">tani',
- 0x1150, '<td colspan="8" class="X Xr L Brahmic">ranjana',
- 0x1158, '<td colspan="8" class="X L Brahmic">siddham',
- 0x1160, '<td colspan="6" class="X L Brahmic">modi',
- 0x1166, '<td colspan="2" class="X L Aramaic" title="mongolian extension">mong',
- 0x1168, '<td colspan="5" class="X L Brahmic">takri',
- 0x116D, '<td colspan="3" class="X Xr L Brahmic">jenticha',
- 0x1170, '<td colspan="4" class="X Xr L Brahmic">ahom',
- 0x1174, '<td colspan="6" class="X Xr L Alpha">zou',
- 0x117A, '<td colspan="6" class="X Xr L Brahmic">pyu',
- 0x1180, '<td colspan="5" class="X Xr L Brahmic">dogra',
- 0x1185, '<td colspan="4" class="X Xr L Brahmic">sirmauri',
- 0x1189, '<td colspan="1" class="">res',
- 0x118A, '<td colspan="6" class="X L Syllabic">warang citi',
- 0x1190, '<td colspan="4" class="X Xr L Brahmic">tolong siki',
- 0x1194, '<td colspan="4" class="X Xr L Brahmic">tikamuli',
- 0x1198, '<td colspan="4" class="X Xr L Brahmic">khambu rai',
- 0x119C, '<td colspan="4" class="X Xr L Brahmic">kirat rai',
- 0x11A0, '<td colspan="5" class="X Xr L Brahmic">zanabazar square',
- 0x11A5, '<td colspan="6" class="X Xr L Brahmic">soyombo',
- 0x11AB, '<td colspan="1" class="">res',
- 0x11AC, '<td colspan="4" class="X L Alpha">pau cin hau',
- 0x11B0, '<td colspan="5" class="X Xr L Brahmic">dhives akuru',
- 0x11B5, '<td colspan="4" class="X Xr L Brahmic">leke',
- 0x11B9, '<td colspan="6" class="X Xr L Brahmic">nandinagari',
- 0x11BF, '<td colspan="1" class="">res',
- 0x11C0, '<td colspan="7" class="X L Brahmic">bhaiksuki',
- 0x11C7, '<td colspan="5" class="X L Brahmic">marchen',
- 0x11CC, '<td colspan="4" class="X Xr L Brahmic">balti B',
- 0x11D0, '<td colspan="6" class="X Xr L Brahmic">masaram gondi',
- 0x11D6, '<td colspan="5" class="X Xr L Brahmic">gunjala gondi',
- 0x11DB, '<td colspan="5" class="X Xr L Brahmic">kawi',
- 0x11E0, '<td colspan="7" class="X Xr L Brahmic">tocharian',
- 0x11E7, '<td colspan="6" class="X Xr L Brahmic">khotanese',
- 0x11ED, '<td colspan="1" class="">res',
- 0x11EE, '<td colspan="2" class="X Xr L Brahmic" title="makasar">makas',
- 0x11F0, '<td colspan="4" class="X Xr L Brahmic">vatteluttu',
- 0x11F4, '<td colspan="2" class="">res',
- 0x11F6, '<td colspan="6" class="X Xr L Brahmic">chola',
- 0x11FC, '<td colspan="4" class="X Xr L Brahmic">tamil+',
- 0x1200, '<td colspan="16" rowspan="4" class="X L Syllabic">cuneiform',
- 0x1240, '<td colspan="8" class="X No">cuneiform numbers',
- 0x1248, '<td colspan="8" class="X L Syllabic">early dynastic cuneiform',
- 0x1250, '<td colspan="5" class="X L Syllabic">e. dyn. cuneiform',
- 0x1255, '<td colspan="11" class="">reserved',
- 0x1260, '<td colspan="16" rowspan="8" class="X Xr L Syllabic">proto-cuneiform',
- 0x12E0, '<td colspan="16" class="X Xr L Syllabic">indus',
- 0x12F0, '<td colspan="9" class="X Xr L Syllabic">indus',
- 0x12F9, '<td colspan="7" class="">reserved',
- 0x1300, '<td colspan="16" rowspan="4" class="X L Syllabic">egyptian hieroglyphs',
- 0x1340, '<td colspan="3" class="X L Syllabic">egyptian',
- 0x1343, '<td colspan="1" class="X Xr L Syllabic" title="Egyptian control characters">eg.c',
- 0x1344, '<td colspan="12" class="X Xr L Syllabic joind">',
- 0x1350, '<td colspan="16" rowspan="15" class="X Xr L Syllabic joinu">egyptian hieroglyphs extended-A',
- 0x1440, '<td colspan="16" rowspan="2" class="X L Syllabic joind">anatolian hieroglyphs',
- 0x1460, '<td colspan="8" class="X L Syllabic">anatolian',
- 0x1468, '<td colspan="8" class="X Xr L Syllabic joind">',
- 0x1470, '<td colspan="16" rowspan="9" class="X Xr L Syllabic joinu">egyptian hieroglyphs extended-B',
- 0x1500, '<td colspan="4" class="X Xr L Brahmic">lampung',
- 0x1504, '<td colspan="3" class="X Xr L Brahmic">kerinci',
- 0x1507, '<td colspan="1" class="">res',
- 0x1508, '<td colspan="8" class="X Xr L Syllabic joind">',
- 0x1510, '<td colspan="16" rowspan="4" class="X Xr L Syllabic joinu">mandombe',
- 0x1550, '<td colspan="16" rowspan="5" class="X Xr L Syllabic">maya hieroglyphs',
- 0x15A0, '<td colspan="16" rowspan="2" class="">reserved',
- 0x15C0, '<td colspan="16" rowspan="4" class="X Xr L Syllabic">aztec pictograms',
- 0x1600, '<td colspan="8" class="X Xr L Alpha">cirth',
- 0x1608, '<td colspan="8" class="X Xr L Alpha">tengwar',
- 0x1610, '<td colspan="4" class="X Xr L Brahmic">khema',
- 0x1614, '<td colspan="4" class="X Xr L Brahmic">khe prih',
- 0x1618, '<td colspan="2" class="">res',
- 0x161A, '<td colspan="6" class="X Xr L Alpha">moon',
- 0x1620, '<td colspan="16" rowspan="5" class="X Xr L Syllabic">blissymbols',
- 0x1670, '<td colspan="11" class="X Xr L Syllabic">bagam',
- 0x167B, '<td colspan="5" class="X Xr L Syllabic">iban',
- 0x1680, '<td colspan="16" rowspan="2" class="X L Syllabic">bamum supplement',
- 0x16A0, '<td colspan="4" class="X L Syllabic">bamum+',
- 0x16A4, '<td colspan="3" class="X L Alpha">mro',
- 0x16A7, '<td colspan="6" class="X Xr L Alpha">mossang tangsa',
- 0x16AD, '<td colspan="3" class="X L Alpha">bassa vah',
- 0x16B0, '<td colspan="9" class="X L Syllabic">pahawh hmong',
- 0x16B9, '<td colspan="7" class="X Xr L Syllabic">woleai',
- 0x16C0, '<td colspan="8" class="X Xr L Syllabic">kpelle',
- 0x16C8, '<td colspan="5" class="X Xr L Syllabic">afaka',
- 0x16CD, '<td colspan="3" class="X Xr L Syllabic" title="Latsam Khimhun Tangsa">lk tangsa',
- 0x16D0, '<td colspan="13" class="">reserved',
- 0x16DD, '<td colspan="3" class="X Xr L Brahmic">kulitan',
- 0x16E0, '<td colspan="4" class="X Xr L Alpha">mwangwego',
- 0x16E4, '<td colspan="6" class="X Xr L Alpha">medefaidrin',
- 0x16EA, '<td colspan="6" class="X Xr L Brahmic" title="buginese">lontara+',
- 0x16F0, '<td colspan="10" class="X L Syllabic">miao',
- 0x16FA, '<td colspan="4" class="X Xr L Brahmic">lontara b-b',
- 0x16FE, '<td colspan="2" class="X So" title="Ideographic Symbols and Punctuation">ideo',
- 0x1700, '<td colspan="16" rowspan="24" class="X L Syllabic">tangut ideographs',
- 0x1880, '<td colspan="16" rowspan="3" class="X L Syllabic">tangut components',
- 0x18B0, '<td colspan="16" rowspan="2" class="X Xr L Han">khitan small',
- 0x18D0, '<td colspan="16" rowspan="9" class="X Xr L Han">khitan ideographs',
- 0x1960, '<td colspan="16" rowspan="5" class="X Xr L Han">jurchen',
- 0x19B0, '<td colspan="6" class="X Xr L Han">jurchen',
- 0x19B6, '<td colspan="4" class="X Xr L Han">jurchen rad',
- 0x19BA, '<td colspan="6" class="">reserved',
- 0x19C0, '<td colspan="16" rowspan="2" class="">reserved',
- 0x19E0, '<td colspan="16" rowspan="5" class="X Xr L Syllabic">pau cin hau syllabary',
- 0x1A30, '<td colspan="16" rowspan="5" class="X Xr L Syllabic">eskaya',
- 0x1A80, '<td colspan="16" rowspan="2" class="X Xr L Syllabic">naxi geba',
- 0x1AA0, '<td colspan="11" class="X Xr L Syllabic">naxi geba',
- 0x1AAB, '<td colspan="1" class="">res',
- 0x1AAC, '<td colspan="4" class="X Xr L Syllabic joind">',
- 0x1AB0, '<td colspan="16" rowspan="5" class="X Xr L Syllabic joinu">naxi dongba',
- 0x1B00, '<td colspan="16" class="X L Hiragana">kana supplement',
- 0x1B10, '<td colspan="3" class="X Xr L Hiragana">kana+A',
- 0x1B13, '<td colspan="4" class="X Xr L Syllabic">kaidā',
- 0x1B17, '<td colspan="9" class="X Xr L Han joind">',
- 0x1B20, '<td colspan="16" class="X Xr L Han joinu">nushu',
- 0x1B30, '<td colspan="16" rowspan="2" class="X Xr L Han">shuishu',
- 0x1B50, '<td colspan="16" rowspan="7" class="X Xr L Syllabic">proto-elamite',
- 0x1BC0, '<td colspan="10" class="X L Alpha">duployan',
- 0x1BCA, '<td colspan="1" class="X L Cc" title="Shorthand Formatting">sh',
- 0x1BCB, '<td colspan="5" class="X Xr L Alpha">pitman',
- 0x1BD0, '<td colspan="16" rowspan="3" class="X Xr L Alpha">shorthands?',
- 0x1C00, '<td colspan="16" rowspan="11" class="X Xr L Alpha">micmac hieroglyphs',
- 0x1CB0, '<td colspan="16" rowspan="3" class="X Xr L Syllabic">rongorongo',
- 0x1CE0, '<td colspan="16" rowspan="2" class="">reserved',
- 0x1D00, '<td colspan="16" class="X So">byzantine musical',
- 0x1D10, '<td colspan="16" class="X So">musical symbols',
- 0x1D20, '<td colspan="5" class="X So">anc greek music',
- 0x1D25, '<td colspan="9" class="">reserved',
- 0x1D2E, '<td colspan="2" class="X Xr No" title="Mayan Numerals">mayan',
- 0x1D30, '<td colspan="6" class="X So" title="tetragrams">tai xuan jing',
- 0x1D36, '<td colspan="2" class="X No">rod',
- 0x1D38, '<td colspan="8" class="X Xr L Sm">mathematical alphanumeric+',
- 0x1D40, '<td colspan="16" rowspan="4" class="X L Sm">mathematical alphanumeric',
- 0x1D80, '<td colspan="16" rowspan="2" class="X L Alpha joind">sutton',
- 0x1DA0, '<td colspan="11" class="X L Alpha joinu">',
- 0x1DAB, '<td colspan="5" class="">reserved',
- 0x1DB0, '<td colspan="16" rowspan="5" class="">reserved',
- 0x1E00, '<td colspan="3" class="X L Cyrillic">glagol+',
- 0x1E03, '<td colspan="5" class="X Xr L Brahmic">pallava',
- 0x1E08, '<td colspan="6" class="X Xr L Brahmic">chalukya',
- 0x1E0E, '<td colspan="2" class="">res',
- 0x1E10, '<td colspan="11" class="X Xr L Alpha">eebee hmong',
- 0x1E1B, '<td colspan="5" class="X Xr L Alpha">cher vang hmong',
- 0x1E20, '<td colspan="6" class="X Xr L Brahmic">western cham',
- 0x1E27, '<td colspan="3" class="X Xr L Alpha" title="zaghawa">beria',
- 0x1E2A, '<td colspan="7" class="">reserved',
- 0x1E30, '<td colspan="16" rowspan="2" class="X Xr L Syllabic">loma',
- 0x1E50, '<td colspan="16" rowspan="3" class="">reserved',
- 0x1E80, '<td colspan="14" class="X L Syllabic">mende kikakui',
- 0x1E8E, '<td colspan="2" class="">res',
- 0x1E90, '<td colspan="6" class="X L Alpha">adlam',
- 0x1E96, '<td colspan="10" class="">reserved',
- 0x1EA0, '<td colspan="16" rowspan="2" class="">reserved',
- 0x1EC0, '<td colspan="7" class="X Xr No">persian siyaq',
- 0x1EC7, '<td colspan="5" class="X Xr No">indic siyaq',
- 0x1ECC, '<td colspan="4" class="X Xr No">diwani siyaq',
- 0x1ED0, '<td colspan="5" class="X Xr No">ottoman siyaq',
- 0x1ED5, '<td colspan="11" class="">reserved',
- 0x1EE0, '<td colspan="16" class="X L Arabic">arabic mathematical alphabetic', # Sm
- 0x1EF0, '<td colspan="16" class="">reserved',
- 0x1F00, '<td colspan="3" class="X So">mahjong',
- 0x1F03, '<td colspan="7" class="X So">domino tiles',
- 0x1F0A, '<td colspan="6" class="X So">playing cards',
- 0x1F10, '<td colspan="16" class="X L Latin">enclosed alphanumeric supplement', # So
- 0x1F20, '<td colspan="16" class="X L Han">enclosed ideographic supplement', # So
- 0x1F30, '<td colspan="16" rowspan="3" class="X So">miscellaneous symbols and pictographs',
- 0x1F60, '<td colspan="5" class="X So">emoticons',
- 0x1F65, '<td colspan="3" class="X So">ornament',
- 0x1F68, '<td colspan="8" class="X So">transport',
- 0x1F70, '<td colspan="8" class="X So">alchemical',
- 0x1F78, '<td colspan="8" class="X So">geometric shapes ext',
- 0x1F80, '<td colspan="16" class="X So">supplemental arrows-C',
- 0x1F90, '<td colspan="16" class="X So">supplemental symbols and pictographs',
- 0x1FA0, '<td colspan="16" rowspan="6" class="">reserved',
-);
-
-sub {
- return defined $uniblock{$_[0]} ? $uniblock{$_[0]} : ();
-}
-
+ 0x1000 => [0x08, 'X L Syllabic', 'linear B syllabary'],
+ 0x1008 => [0x08, 'X L Syllabic', 'linear B ideograms'],
+ 0x1010 => [0x04, 'X No', 'aegean num'],
+ 0x1014 => [0x05, 'X No', 'greek numbers'],
+ 0x1019 => [0x04, 'X So', 'ancient sym'],
+ 0x101D => [0x03, 'X L Syllabic', 'phaistos'],
+ 0x1020 => [0x04, 'X Xr L Greek', 'iberian'],
+ 0x1024 => [0x04],
+ 0x1028 => [0x02, 'X L Greek', 'lycian'],
+ 0x102A => [0x04, 'X L Greek', 'carian'],
+ 0x102E => [0x02, 'X L No', 'coptic'],
+ 0x1030 => [0x03, 'X L Greek', 'italic'],
+ 0x1033 => [0x02, 'X L Greek', 'gothic'],
+ 0x1035 => [0x03, 'X L Cyrillic', 'permic'],
+ 0x1038 => [0x02, 'X L Alpha', 'ugarit'],
+ 0x103A => [0x04, 'X L Alpha', 'old persian'],
+ 0x103E => [0x02, 'X Xr L Alpha', 'sh.qs'],
+ 0x1040 => [0x05, 'X L Alpha', 'deseret'],
+ 0x1045 => [0x03, 'X L Alpha', 'shavian'],
+ 0x1048 => [0x03, 'X L Alpha', 'osmanya'],
+ 0x104B => [0x05, 'X L Alpha', 'osage'],
+ 0x1050 => [0x03, 'X L Alpha', 'elbasan'],
+ 0x1053 => [0x04, 'X L Alpha', 'c albanian'],
+ 0x1057 => [0x05, 'X Xr L Alpha', 'vithkuqi'],
+ 0x105C => [0x04, 'X Xr L Alpha', 'todhri'],
+ 0x1060 => [0x18, 'X L Syllabic', 'linear A'],
+ 0x1078 => [0x08, 'X Xr L Syllabic', 'cypro-minoan'],
+ 0x1080 => [0x04, 'X L Syllabic', 'cypriot'],
+ 0x1084 => [0x02, 'X L Aramaic', 'aram'],
+ 0x1086 => [0x02, 'X L Aramaic', 'palmr'],
+ 0x1088 => [0x03, 'X L Aramaic', 'nabataean'],
+ 0x108A => [0x01],
+ 0x108C => [0x02, 'X Xr L Alpha', 'numid'],
+ 0x108E => [0x02, 'X L Aramaic', 'hatr'],
+ 0x1090 => [0x02, 'X L Aramaic', 'phoen'],
+ 0x1092 => [0x02, 'X L Greek', 'lydian'],
+ 0x1094 => [0x04],
+ 0x1098 => [0x02, 'X L Alpha', 'mero h', 'meroitic hieroglyphs'],
+ 0x109A => [0x06, 'X L Alpha', 'meroitic cursive'],
+ 0x10A0 => [0x06, 'X L Syllabic', 'kharoshthi'],
+ 0x10A6 => [0x02, 'X L Aramaic', 's arab'],
+ 0x10A8 => [0x02, 'X L Aramaic', 'n arab'],
+ 0x10AA => [0x02, 'X Xr L Brahmic', 'balti'],
+ 0x10AC => [0x04, 'X L Aramaic', 'manichaean'],
+ 0x10B0 => [0x04, 'X L Aramaic', 'avestan'],
+ 0x10B4 => [0x02, 'X L Aramaic', 'parth'],
+ 0x10B6 => [0x02, 'X L Aramaic', 'pahlav', 'inscriptional pahlavi'],
+ 0x10B8 => [0x03, 'X L Aramaic', 'psalt pahl', 'psalter pahlavi'],
+ 0x10BB => [0x03, 'X Xr L Aramaic', 'book pahl', 'book pahlavi'],
+ 0x10BE => [0x02, 'X Xr L Alpha', 'babur'],
+ 0x10C0 => [0x05, 'X L Aramaic', 'old turkic'],
+ 0x10C5 => [0x03],
+ 0x10C8 => [0x08, 'X L Aramaic', 'old hungarian'],
+ 0x10D0 => [0x04, 'X Xr L Alpha', 'rohingya'],
+ 0x10D4 => [0x04, 'X Xr L Alpha', 'garay'],
+ 0x10D8 => [0x08, 'X Xr L Syllabic', 'byblos'],
+ 0x10E0 => [0x06],
+ 0x10E6 => [0x02, 'X No', 'rumi'],
+ 0x10E8 => [0x06],
+ 0x10EE => [0x02, 'X Xr L Aramaic', 'elym'],
+ 0x10F0 => [0x03, 'X Xr L Aramaic', 'old sog'],
+ 0x10F3 => [0x04, 'X Xr L Aramaic', 'sogdian'],
+ 0x10F7 => [0x01],
+ 0x10F8 => [0x08, 'X Xr L Aramaic', 'uyghur'],
+ 0x1100 => [0x08, 'X L Brahmic', 'brahmi'],
+ 0x1108 => [0x05, 'X L Brahmic', 'kaithi'],
+ 0x110D => [0x03, 'X L Brahmic', 'sora som'],
+ 0x1110 => [0x05, 'X L Brahmic', 'chakma'],
+ 0x1115 => [0x03, 'X L Brahmic', 'mahajani'],
+ 0x1118 => [0x06, 'X L Brahmic', 'sharada'],
+ 0x111E => [0x02, 'X No Brahmic', 'sinhal'],
+ 0x1120 => [0x05, 'X L Brahmic', 'khojki'],
+ 0x1125 => [0x03, 'X Xr L Brahmic', 'landa'],
+ 0x1128 => [0x03, 'X L Brahmic', 'multani'],
+ 0x112B => [0x05, 'X L Brahmic', 'khudabadi'],
+ 0x1130 => [0x08, 'X L Brahmic', 'grantha'],
+ 0x1138 => [0x06, 'X Xr L Brahmic', 'tulu'],
+ 0x113E => [0x02, 'X Xr L Brahmic', 'shar+', 'sharada extension'],
+ 0x1140 => [0x08, 'X L Brahmic', 'newar'],
+ 0x1148 => [0x06, 'X L Brahmic', 'tirhuta'],
+ 0x114E => [0x02, 'X Xr L Alpha', 'tani'],
+ 0x1150 => [0x08, 'X Xr L Brahmic', 'ranjana'],
+ 0x1158 => [0x08, 'X L Brahmic', 'siddham'],
+ 0x1160 => [0x06, 'X L Brahmic', 'modi'],
+ 0x1166 => [0x02, 'X L Aramaic', 'mong', 'mongolian extension'],
+ 0x1168 => [0x05, 'X L Brahmic', 'takri'],
+ 0x116D => [0x03, 'X Xr L Brahmic', 'jenticha'],
+ 0x1170 => [0x04, 'X Xr L Brahmic', 'ahom'],
+ 0x1174 => [0x06, 'X Xr L Alpha', 'zou'],
+ 0x117A => [0x06, 'X Xr L Brahmic', 'pyu'],
+ 0x1180 => [0x05, 'X Xr L Brahmic', 'dogra'],
+ 0x1185 => [0x04, 'X Xr L Brahmic', 'sirmauri'],
+ 0x1189 => [0x01],
+ 0x118A => [0x06, 'X L Syllabic', 'warang citi'],
+ 0x1190 => [0x04, 'X Xr L Brahmic', 'tolong siki'],
+ 0x1194 => [0x04, 'X Xr L Brahmic', 'tikamuli'],
+ 0x1198 => [0x04, 'X Xr L Brahmic', 'khambu rai'],
+ 0x119C => [0x04, 'X Xr L Brahmic', 'kirat rai'],
+ 0x11A0 => [0x05, 'X Xr L Brahmic', 'zanabazar square'],
+ 0x11A5 => [0x06, 'X Xr L Brahmic', 'soyombo'],
+ 0x11AB => [0x01],
+ 0x11AC => [0x04, 'X L Alpha', 'pau cin hau'],
+ 0x11B0 => [0x05, 'X Xr L Brahmic', 'dhives akuru'],
+ 0x11B5 => [0x04, 'X Xr L Brahmic', 'leke'],
+ 0x11B9 => [0x06, 'X Xr L Brahmic', 'nandinagari'],
+ 0x11BF => [0x01],
+ 0x11C0 => [0x07, 'X L Brahmic', 'bhaiksuki'],
+ 0x11C7 => [0x05, 'X L Brahmic', 'marchen'],
+ 0x11CC => [0x04, 'X Xr L Brahmic', 'balti B'],
+ 0x11D0 => [0x06, 'X Xr L Brahmic', 'masaram gondi'],
+ 0x11D6 => [0x05, 'X Xr L Brahmic', 'gunjala gondi'],
+ 0x11DB => [0x05, 'X Xr L Brahmic', 'kawi'],
+ 0x11E0 => [0x07, 'X Xr L Brahmic', 'tocharian'],
+ 0x11E7 => [0x06, 'X Xr L Brahmic', 'khotanese'],
+ 0x11ED => [0x01],
+ 0x11EE => [0x02, 'X Xr L Brahmic', 'makas', 'makasar'],
+ 0x11F0 => [0x04, 'X Xr L Brahmic', 'vatteluttu'],
+ 0x11F4 => [0x02],
+ 0x11F6 => [0x06, 'X Xr L Brahmic', 'chola'],
+ 0x11FC => [0x04, 'X Xr L Brahmic', 'tamil+'],
+ 0x1200 => [0x40, 'X L Syllabic', 'cuneiform'],
+ 0x1240 => [0x08, 'X No', 'cuneiform numbers'],
+ 0x1248 => [0x08, 'X L Syllabic', 'early dynastic cuneiform'], #TODO: join bottom but title at top
+ 0x1250 => [0x05, 'X L Syllabic', 'e. dyn. cuneiform'],
+ 0x1255 => [0x0B],
+ 0x1260 => [0x80, 'X Xr L Syllabic', 'proto-cuneiform'],
+ 0x12E0 => [0x19, 'X Xr L Syllabic', 'indus'],
+ 0x12F9 => [0x07],
+ 0x1300 => [0x43, 'X L Syllabic', 'egyptian hieroglyphs'],
+ 0x1343 => [0x01, 'X Xr L Syllabic', 'eg.c', 'Egyptian control characters'],
+ 0x1344 => [0xFC, 'X Xr L Syllabic', 'egyptian hieroglyphs extended-A'],
+ 0x1440 => [0x28, 'X L Syllabic', 'anatolian hieroglyphs'],
+ 0x1468 => [0x98, 'X Xr L Syllabic', 'egyptian hieroglyphs extended-B'],
+ 0x1500 => [0x04, 'X Xr L Brahmic', 'lampung'],
+ 0x1504 => [0x03, 'X Xr L Brahmic', 'kerinci'],
+ 0x1507 => [0x01],
+ 0x1508 => [0x48, 'X Xr L Syllabic', 'mandombe'],
+ 0x1550 => [0x50, 'X Xr L Syllabic', 'maya hieroglyphs'],
+ 0x15A0 => [0x20],
+ 0x15C0 => [0x40, 'X Xr L Syllabic', 'aztec pictograms'],
+ 0x1600 => [0x08, 'X Xr L Alpha', 'cirth'],
+ 0x1608 => [0x08, 'X Xr L Alpha', 'tengwar'],
+ 0x1610 => [0x04, 'X Xr L Brahmic', 'khema'],
+ 0x1614 => [0x04, 'X Xr L Brahmic', 'khe prih'],
+ 0x1618 => [0x02],
+ 0x161A => [0x06, 'X Xr L Alpha', 'moon'],
+ 0x1620 => [0x50, 'X Xr L Syllabic', 'blissymbols'],
+ 0x1670 => [0x0B, 'X Xr L Syllabic', 'bagam'],
+ 0x167B => [0x05, 'X Xr L Syllabic', 'iban'],
+ 0x1680 => [0x24, 'X L Syllabic', 'bamum supplement'],
+ 0x16A4 => [0x03, 'X L Alpha', 'mro'],
+ 0x16A7 => [0x06, 'X Xr L Alpha', 'mossang tangsa'],
+ 0x16AD => [0x03, 'X L Alpha', 'bassa vah'],
+ 0x16B0 => [0x09, 'X L Syllabic', 'pahawh hmong'],
+ 0x16B9 => [0x07, 'X Xr L Syllabic', 'woleai'],
+ 0x16C0 => [0x08, 'X Xr L Syllabic', 'kpelle'],
+ 0x16C8 => [0x05, 'X Xr L Syllabic', 'afaka'],
+ 0x16CD => [0x03, 'X Xr L Syllabic', 'lk tangsa', 'Latsam Khimhun Tangsa'],
+ 0x16D0 => [0x0D],
+ 0x16DD => [0x03, 'X Xr L Brahmic', 'kulitan'],
+ 0x16E0 => [0x04, 'X Xr L Alpha', 'mwangwego'],
+ 0x16E4 => [0x06, 'X Xr L Alpha', 'medefaidrin'],
+ 0x16EA => [0x06, 'X Xr L Brahmic', 'lontara+', 'buginese'],
+ 0x16F0 => [0x0A, 'X L Syllabic', 'miao'],
+ 0x16FA => [0x04, 'X Xr L Brahmic', 'lontara b-b'],
+ 0x16FE => [0x02, 'X So', 'ideo', 'Ideographic Symbols and Punctuation'],
+ 0x1700 => [0x180,'X L Syllabic', 'tangut ideographs'],
+ 0x1880 => [0x30, 'X L Syllabic', 'tangut components'],
+ 0x18B0 => [0x20, 'X Xr L Han', 'khitan small'],
+ 0x18D0 => [0x90, 'X Xr L Han', 'khitan ideographs'],
+ 0x1960 => [0x56, 'X Xr L Han', 'jurchen'],
+ 0x19B6 => [0x04, 'X Xr L Han', 'jurchen rad'],
+ 0x19BA => [0x06],
+ 0x19C0 => [0x20],
+ 0x19E0 => [0x50, 'X Xr L Syllabic', 'pau cin hau syllabary'],
+ 0x1A30 => [0x50, 'X Xr L Syllabic', 'eskaya'],
+ 0x1A80 => [0x2B, 'X Xr L Syllabic', 'naxi geba'],
+ 0x1AAB => [0x01],
+ 0x1AAC => [0x54, 'X Xr L Syllabic', 'naxi dongba'],
+ 0x1B00 => [0x10, 'X L Hiragana', 'kana supplement'],
+ 0x1B10 => [0x03, 'X Xr L Hiragana', 'kana+A'],
+ 0x1B13 => [0x04, 'X Xr L Syllabic', 'kaidā'],
+ 0x1B17 => [0x19, 'X Xr L Han', 'nushu'],
+ 0x1B30 => [0x20, 'X Xr L Han', 'shuishu'],
+ 0x1B50 => [0x70, 'X Xr L Syllabic', 'proto-elamite'],
+ 0x1BC0 => [0x0A, 'X L Alpha', 'duployan'],
+ 0x1BCA => [0x01, 'X L Cc', 'sh', 'Shorthand Formatting'],
+ 0x1BCB => [0x05, 'X Xr L Alpha', 'pitman'],
+ 0x1BD0 => [0x30, 'X Xr L Alpha', 'shorthands?'],
+ 0x1C00 => [0xB0, 'X Xr L Alpha', 'micmac hieroglyphs'],
+ 0x1CB0 => [0x30, 'X Xr L Syllabic', 'rongorongo'],
+ 0x1CE0 => [0x20],
+ 0x1D00 => [0x10, 'X So', 'byzantine musical'],
+ 0x1D10 => [0x10, 'X So', 'musical symbols'],
+ 0x1D20 => [0x05, 'X So', 'anc greek music'],
+ 0x1D25 => [0x09],
+ 0x1D2E => [0x02, 'X Xr No', 'mayan', 'Mayan Numerals'],
+ 0x1D30 => [0x06, 'X So', 'tai xuan jing', 'tetragrams'],
+ 0x1D36 => [0x02, 'X No', 'rod'],
+ 0x1D38 => [0x08, 'X Xr L Sm', 'mathematical alphanumeric+'],
+ 0x1D40 => [0x40, 'X L Sm', 'mathematical alphanumeric'],
+ 0x1D80 => [0x2B, 'X L Alpha', 'sutton'],
+ 0x1DAB => [0x55],
+ 0x1E00 => [0x03, 'X L Cyrillic', 'glagol+'],
+ 0x1E03 => [0x05, 'X Xr L Brahmic', 'pallava'],
+ 0x1E08 => [0x06, 'X Xr L Brahmic', 'chalukya'],
+ 0x1E0E => [0x02],
+ 0x1E10 => [0x0B, 'X Xr L Alpha', 'eebee hmong'],
+ 0x1E1B => [0x05, 'X Xr L Alpha', 'cher vang hm.'],
+ 0x1E20 => [0x06, 'X Xr L Brahmic', 'western cham'],
+ 0x1E26 => [0x03, 'X Xr L Alpha', 'beria', 'zaghawa'],
+ 0x1E29 => [0x07],
+ 0x1E30 => [0x20, 'X Xr L Syllabic', 'loma'],
+ 0x1E50 => [0x30],
+ 0x1E80 => [0x0E, 'X L Syllabic', 'mende kikakui'],
+ 0x1E8E => [0x02],
+ 0x1E90 => [0x06, 'X L Alpha', 'adlam'],
+ 0x1E96 => [0x2A],
+ 0x1EC0 => [0x07, 'X Xr No', 'persian siyaq'],
+ 0x1EC7 => [0x05, 'X Xr No', 'indic siyaq'],
+ 0x1ECC => [0x04, 'X Xr No', 'diwani siyaq'],
+ 0x1ED0 => [0x05, 'X Xr No', 'ottoman siyaq'],
+ 0x1ED5 => [0x0B],
+ 0x1EE0 => [0x10, 'X L Arabic', 'arabic mathematical alphabetic'], # Sm
+ 0x1EF0 => [0x10],
+ 0x1F00 => [0x03, 'X So', 'mahjong'],
+ 0x1F03 => [0x07, 'X So', 'domino tiles'],
+ 0x1F0A => [0x06, 'X So', 'playing cards'],
+ 0x1F10 => [0x10, 'X L Latin', 'enclosed alphanumeric supplement'], # So
+ 0x1F20 => [0x10, 'X L Han', 'enclosed ideographic supplement'], # So
+ 0x1F30 => [0x30, 'X So', 'miscellaneous symbols and pictographs'],
+ 0x1F60 => [0x05, 'X So', 'emoticons'],
+ 0x1F65 => [0x03, 'X So', 'ornament'],
+ 0x1F68 => [0x08, 'X So', 'transport'],
+ 0x1F70 => [0x08, 'X So', 'alchemical'],
+ 0x1F78 => [0x08, 'X So', 'geometric shapes ext'],
+ 0x1F80 => [0x10, 'X So', 'supplemental arrows-C'],
+ 0x1F90 => [0x10, 'X So', 'supplemental symbols and pictographs'],
+ 0x1FA0 => [0x60],
+};
git.shiar.nl / sheet.git / commitdiff