From d4ead771b48095b3889d0c5694dc6152e6d58359 Mon Sep 17 00:00:00 2001 From: Mischa POSLAWSKY Date: Mon, 27 Mar 2017 21:51:42 +0200 Subject: [PATCH] charset: common unicode cell formatting function Convert data to generic [size, class, name, title] to allow different layouts without hardcoded table properties, while simplifying entry and automating styling of continued rows. --- base.css | 2 +- charset-unicode.inc.pl | 854 ++++++++++++++++++++--------------------- charset.plp | 43 ++- 3 files changed, 457 insertions(+), 442 deletions(-) diff --git a/base.css b/base.css index 179b2ec..50b92d8 100644 --- a/base.css +++ b/base.css @@ -235,7 +235,7 @@ td.joinl { font-size: 200%; } .glyphs .glyphs { - margin: 0.5ex 0; + margin: 0.5ex 0; /* nested in legend */ } .glyphs .glyphs td { font-size: 100%; diff --git a/charset-unicode.inc.pl b/charset-unicode.inc.pl index a0717a7..6709e84 100644 --- a/charset-unicode.inc.pl +++ b/charset-unicode.inc.pl @@ -1,444 +1,418 @@ use utf8; -my %uniblock = ( ++{ # bmp - 0x000, 'control', - 0x002, 'comn', - 0x004, 'basic latin', - 0x008, 'control', - 0x00A, 'comn', - 0x00C, 'latin1', - 0x010, 'latin extended-A', - 0x018, 'latin extended-B', - 0x020, 'latin ext-B', - 0x025, 'IPA', - 0x02B, 'spacing modifier', - 0x030, 'diacritics', - 0x038, 'greek', - 0x040, 'cyrillic', - 0x050, 'cyrillic+', - 0x053, 'armenian', - 0x058, 'hebrew', - 0x060, 'arabic', - 0x070, 'syriac', - 0x075, 'arabic+', - 0x078, 'thaana', - 0x07C, 'n\'ko', - 0x080, 'samaritan', - 0x084, 'manda', - 0x086, 'syr', - 0x087, 'reserved', - 0x08A, 'arabic ext-A', - 0x090, 'devanagari', - 0x098, 'bengali', - 0x0A0, 'gurmukhi', - 0x0A8, 'gujarati', - 0x0B0, 'oriya', - 0x0B8, 'tamil', - 0x0C0, 'telugu', - 0x0C8, 'kannada', - 0x0D0, 'malayalam', - 0x0D8, 'sinhala', - 0x0E0, 'thai', - 0x0E8, 'lao', - 0x0F0, 'tibetan', - 0x100, 'myanmar', - 0x10A, 'georgian', - 0x110, 'hangeul jamo', - 0x120, 'ethiopic', - 0x130, 'ethiopic', - 0x138, 'eth+', - 0x13A, 'cherokee', - 0x140, 'unified canadian aboriginal syllabics', - 0x160, 'unified canadian syllabics', - 0x168, 'ogham', - 0x16A, 'runic', - 0x170, 'tagalog', - 0x172, 'hanun', - 0x174, 'buhid', - 0x176, 'tagb', - 0x178, 'khmer', - 0x180, 'mongolian', - 0x18B, 'canadian+', - 0x190, 'limbu', - 0x195, 'tai le', - 0x198, 'new tai lue', - 0x19E, 'khmer', - 0x1A0, 'lontara', - 0x1A2, 'tai tham', - 0x1AB, 'diacritics+', - 0x1B0, 'balinese', - 0x1B8, 'sundanese', - 0x1BC, 'batak', - 0x1C0, 'lepcha', - 0x1C5, 'ol chiki', - 0x1C8, 'cyr', - 0x1C9, 'georg+', - 0x1CC, 'sn', - 0x1CD, 'vedic', - 0x1D0, 'phonetic', - 0x1D8, 'phonetic+', - 0x1DC, 'diacritics+', - 0x1E0, 'latin extended additional', - 0x1F0, 'greek+', - 0x200, 'general punctuation', - 0x207, 'suþscript', # suth now means "sub and/or sup" - 0x20A, 'currency', - 0x20D, 'overlay', - 0x210, 'letterlike', - 0x215, 'number', - 0x219, 'arrows', - 0x220, 'mathematical symbols', - 0x230, 'miscellaneous technical', - 0x240, 'control', - 0x244, 'OCR', - 0x246, 'enclosed alphanumerics', - 0x250, 'box drawing', - 0x258, 'blocks', - 0x25A, 'geometric shapes', - 0x260, 'miscellaneous symbols', - 0x270, 'dingbats', - 0x27C, 'maths-A', - 0x27F, 'arr', - 0x280, 'braille', - 0x290, 'supplemental arrows-B', - 0x298, 'mathematical symbols-B', - 0x2A0, 'supplemental mathematical operators', - 0x2B0, 'miscellaneous symbols and arrows', - 0x2C0, 'glagolitic', - 0x2C6, 'latin-C', - 0x2C8, 'coptic', - 0x2D0, 'georgian+', - 0x2D3, 'tifinagh', #TODO: proto-canaanite - 0x2D8, 'ethiopic+', - 0x2DE, 'cyrl-A', - 0x2E0, 'punctuation+', - 0x2E8, 'cjk radicals', - 0x2F0, 'kangxi radicals', - 0x2FE, '', - 0x2FF, 'idc', - 0x300, 'cjk misc', - 0x304, 'hiragana', - 0x30A, 'katakana', - 0x310, 'bopomofo', - 0x313, 'hangeul compat', - 0x319, 'kbn', - 0x31A, 'bpmf', - 0x31C, 'strokes', - 0x31F, 'k+', - 0x320, 'enclosed cjk characters', - 0x330, 'cjk compatibility', - 0x340, 'cjk unified ideographs extension A', - 0x4D0, 'cjk unified ideographs extension A', - 0x4DC, 'hexagrams', - 0x4E0, 'cjk unified ideographs', - 0xA00, 'yi', - 0xA40, 'yi', - 0xA49, 'yi radicals', - 0xA4D, 'lisu', - 0xA50, 'vai', - 0xA60, 'vai', - 0xA64, 'cyrillic extended-B', - 0xA6A, 'bamum', - 0xA70, 'tones', - 0xA72, 'latin extended-D', - 0xA80, 'sylheti', - 0xA83, 'in', - 0xA84, 'phags-pa', - 0xA88, 'saurashtra', - 0xA8E, 'deva+', - 0xA90, 'kayah li', - 0xA93, 'rejang', - 0xA96, 'jamo-A', - 0xA98, 'javanese', - 0xA9E, 'mm-B', - 0xAA0, 'cham', - 0xAA6, 'mm-A', - 0xAA8, 'tai viet', - 0xAAE, 'mtei+', - 0xAB0, 'ethiopic-A', - 0xAB3, 'latin ext-E', - 0xAB7, 'cherokee+', - 0xABC, 'meithei', - 0xAC0, 'hangeul syllables', - 0xD70, 'hangeul syllables', - 0xD7B, 'haungeul jamo-B', - 0xD80, 'high surrogates', - 0xDC0, 'low surrogates', - 0xE00, 'private use', - 0xF90, 'cjk compatibility ideographs', - 0xFB0, 'presentation', - 0xFB5, '', - 0xFC0, 'arabic presentation forms A', - 0xFD0, '', - 0xFDD, '?', - 0xFDF, '', - 0xFE0, 'var', - 0xFE1, 'ver', - 0xFE2, '½', - 0xFE3, 'comp', - 0xFE5, 'small', - 0xFE7, 'arabic presentation B', - 0xFF0, 'halfwidth & fullwidth forms', - 0xFFF, '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, 'linear B syllabary', - 0x1008, 'linear B ideograms', - 0x1010, 'aegean num', - 0x1014, 'greek numbers', - 0x1019, 'ancient sym', - 0x101D, 'phaistos', - 0x1020, 'iberian', - 0x1024, 'reserved', - 0x1028, 'lycian', - 0x102A, 'carian', - 0x102E, 'coptic', - 0x1030, 'italic', - 0x1033, 'gothic', - 0x1035, 'permic', - 0x1038, 'ugarit', - 0x103A, 'old persian', - 0x103E, 'sh.qs', - 0x1040, 'deseret', - 0x1045, 'shavian', - 0x1048, 'osmanya', - 0x104B, 'osage', - 0x1050, 'elbasan', - 0x1053, 'c albanian', - 0x1057, 'vithkuqi', - 0x105C, 'todhri', - 0x1060, 'linear A', - 0x1070, 'linear A', - 0x1078, 'cypro-minoan', - 0x1080, 'cypriot', - 0x1084, 'aram', - 0x1086, 'palmr', - 0x1088, 'nabataean', - 0x108A, 'res', - 0x108C, 'numid', - 0x108E, 'hatr', - 0x1090, 'phoen', - 0x1092, 'lydian', - 0x1094, 'reserved', - 0x1098, 'mero h', - 0x109A, 'meroitic cursive', - 0x10A0, 'kharoshthi', - 0x10A6, 's arab', - 0x10A8, 'n arab', - 0x10AA, 'balti', - 0x10AC, 'manichaean', - 0x10B0, 'avestan', - 0x10B4, 'parth', - 0x10B6, 'pahlav', - 0x10B8, 'psalt pahl', - 0x10BB, 'book pahl', - 0x10BE, 'babur', - 0x10C0, 'old turkic', - 0x10C5, 'reserved', - 0x10C8, 'old hungarian', - 0x10D0, 'rohingya', - 0x10D4, 'garay', - 0x10D8, 'byblos', - 0x10E0, 'reserved', - 0x10E6, 'rumi', - 0x10E8, 'reserved', - 0x10EE, 'elym', - 0x10F0, 'old sog', - 0x10F3, 'sogdian', - 0x10F7, 'res', - 0x10F8, 'uyghur', - 0x1100, 'brahmi', - 0x1108, 'kaithi', - 0x110D, 'sora som', - 0x1110, 'chakma', - 0x1115, 'mahajani', - 0x1118, 'sharada', - 0x111E, 'sinhal', - 0x1120, 'khojki', - 0x1125, 'landa', - 0x1128, 'multani', - 0x112B, 'khudabadi', - 0x1130, 'grantha', - 0x1138, 'tulu', - 0x113E, 'shar+', - 0x1140, 'newar', - 0x1148, 'tirhuta', - 0x114E, 'tani', - 0x1150, 'ranjana', - 0x1158, 'siddham', - 0x1160, 'modi', - 0x1166, 'mong', - 0x1168, 'takri', - 0x116D, 'jenticha', - 0x1170, 'ahom', - 0x1174, 'zou', - 0x117A, 'pyu', - 0x1180, 'dogra', - 0x1185, 'sirmauri', - 0x1189, 'res', - 0x118A, 'warang citi', - 0x1190, 'tolong siki', - 0x1194, 'tikamuli', - 0x1198, 'khambu rai', - 0x119C, 'kirat rai', - 0x11A0, 'zanabazar square', - 0x11A5, 'soyombo', - 0x11AB, 'res', - 0x11AC, 'pau cin hau', - 0x11B0, 'dhives akuru', - 0x11B5, 'leke', - 0x11B9, 'nandinagari', - 0x11BF, 'res', - 0x11C0, 'bhaiksuki', - 0x11C7, 'marchen', - 0x11CC, 'balti B', - 0x11D0, 'masaram gondi', - 0x11D6, 'gunjala gondi', - 0x11DB, 'kawi', - 0x11E0, 'tocharian', - 0x11E7, 'khotanese', - 0x11ED, 'res', - 0x11EE, 'makas', - 0x11F0, 'vatteluttu', - 0x11F4, 'res', - 0x11F6, 'chola', - 0x11FC, 'tamil+', - 0x1200, 'cuneiform', - 0x1240, 'cuneiform numbers', - 0x1248, 'early dynastic cuneiform', - 0x1250, 'e. dyn. cuneiform', - 0x1255, 'reserved', - 0x1260, 'proto-cuneiform', - 0x12E0, 'indus', - 0x12F0, 'indus', - 0x12F9, 'reserved', - 0x1300, 'egyptian hieroglyphs', - 0x1340, 'egyptian', - 0x1343, 'eg.c', - 0x1344, '', - 0x1350, 'egyptian hieroglyphs extended-A', - 0x1440, 'anatolian hieroglyphs', - 0x1460, 'anatolian', - 0x1468, '', - 0x1470, 'egyptian hieroglyphs extended-B', - 0x1500, 'lampung', - 0x1504, 'kerinci', - 0x1507, 'res', - 0x1508, '', - 0x1510, 'mandombe', - 0x1550, 'maya hieroglyphs', - 0x15A0, 'reserved', - 0x15C0, 'aztec pictograms', - 0x1600, 'cirth', - 0x1608, 'tengwar', - 0x1610, 'khema', - 0x1614, 'khe prih', - 0x1618, 'res', - 0x161A, 'moon', - 0x1620, 'blissymbols', - 0x1670, 'bagam', - 0x167B, 'iban', - 0x1680, 'bamum supplement', - 0x16A0, 'bamum+', - 0x16A4, 'mro', - 0x16A7, 'mossang tangsa', - 0x16AD, 'bassa vah', - 0x16B0, 'pahawh hmong', - 0x16B9, 'woleai', - 0x16C0, 'kpelle', - 0x16C8, 'afaka', - 0x16CD, 'lk tangsa', - 0x16D0, 'reserved', - 0x16DD, 'kulitan', - 0x16E0, 'mwangwego', - 0x16E4, 'medefaidrin', - 0x16EA, 'lontara+', - 0x16F0, 'miao', - 0x16FA, 'lontara b-b', - 0x16FE, 'ideo', - 0x1700, 'tangut ideographs', - 0x1880, 'tangut components', - 0x18B0, 'khitan small', - 0x18D0, 'khitan ideographs', - 0x1960, 'jurchen', - 0x19B0, 'jurchen', - 0x19B6, 'jurchen rad', - 0x19BA, 'reserved', - 0x19C0, 'reserved', - 0x19E0, 'pau cin hau syllabary', - 0x1A30, 'eskaya', - 0x1A80, 'naxi geba', - 0x1AA0, 'naxi geba', - 0x1AAB, 'res', - 0x1AAC, '', - 0x1AB0, 'naxi dongba', - 0x1B00, 'kana supplement', - 0x1B10, 'kana+A', - 0x1B13, 'kaidā', - 0x1B17, '', - 0x1B20, 'nushu', - 0x1B30, 'shuishu', - 0x1B50, 'proto-elamite', - 0x1BC0, 'duployan', - 0x1BCA, 'sh', - 0x1BCB, 'pitman', - 0x1BD0, 'shorthands?', - 0x1C00, 'micmac hieroglyphs', - 0x1CB0, 'rongorongo', - 0x1CE0, 'reserved', - 0x1D00, 'byzantine musical', - 0x1D10, 'musical symbols', - 0x1D20, 'anc greek music', - 0x1D25, 'reserved', - 0x1D2E, 'mayan', - 0x1D30, 'tai xuan jing', - 0x1D36, 'rod', - 0x1D38, 'mathematical alphanumeric+', - 0x1D40, 'mathematical alphanumeric', - 0x1D80, 'sutton', - 0x1DA0, '', - 0x1DAB, 'reserved', - 0x1DB0, 'reserved', - 0x1E00, 'glagol+', - 0x1E03, 'pallava', - 0x1E08, 'chalukya', - 0x1E0E, 'res', - 0x1E10, 'eebee hmong', - 0x1E1B, 'cher vang hmong', - 0x1E20, 'western cham', - 0x1E27, 'beria', - 0x1E2A, 'reserved', - 0x1E30, 'loma', - 0x1E50, 'reserved', - 0x1E80, 'mende kikakui', - 0x1E8E, 'res', - 0x1E90, 'adlam', - 0x1E96, 'reserved', - 0x1EA0, 'reserved', - 0x1EC0, 'persian siyaq', - 0x1EC7, 'indic siyaq', - 0x1ECC, 'diwani siyaq', - 0x1ED0, 'ottoman siyaq', - 0x1ED5, 'reserved', - 0x1EE0, 'arabic mathematical alphabetic', # Sm - 0x1EF0, 'reserved', - 0x1F00, 'mahjong', - 0x1F03, 'domino tiles', - 0x1F0A, 'playing cards', - 0x1F10, 'enclosed alphanumeric supplement', # So - 0x1F20, 'enclosed ideographic supplement', # So - 0x1F30, 'miscellaneous symbols and pictographs', - 0x1F60, 'emoticons', - 0x1F65, 'ornament', - 0x1F68, 'transport', - 0x1F70, 'alchemical', - 0x1F78, 'geometric shapes ext', - 0x1F80, 'supplemental arrows-C', - 0x1F90, 'supplemental symbols and pictographs', - 0x1FA0, '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], +}; diff --git a/charset.plp b/charset.plp index 402d839..e55e771 100644 --- a/charset.plp +++ b/charset.plp @@ -101,6 +101,43 @@ for my $cp437 (grep {$request[$_]->{set} eq 'cp437'} 0 .. $#request) { ); } +sub range_cell { + my ($table, $offset) = @_; + my $def = $table->{$offset} or return; + my ($len, $class, $name, $title) = @{$def}; + + my $attr = ''; + $name //= $len <= 2 ? 'res' : 'reserved'; + + if (my $part = $offset % 16) { + # continued row + my $cols = 16 - $part; # remaining + $cols = $len if $len < $cols; #TODO: optimise + if ($len -= $cols) { + # continued on new row + $table->{$offset + $cols} = [$len, "$class joinu", $name, $title]; + $name = ''; + $class .= ' joind'; + } + $len = $cols; + } + elsif (my $rows = $len >> 4) { + # multiple full rows + if ($len -= $rows << 4) { + # partial row remains + $table->{$offset + $rows * 16} = [$len, "$class joinu", '', $title]; + $class .= ' joind'; + } + $attr .= sprintf ' rowspan=%d', $rows; + $len = 16; + } + + $attr .= sprintf ' colspan=%d', $len unless $len == 1; + $attr .= sprintf ' class="%s"', $class if $class; + $attr .= sprintf ' title="%s"', EscapeHTML($title) if $title; + return "$name"; +} + for my $row (@request) { printf '
', !$row->{cell} && ' charmap'; printf '', $row->{set}; @@ -116,7 +153,11 @@ for my $row (@request) { for my $lsb (0 .. $#nibble) { my $val = ( ($msb<<4) + $lsb ) * $nibsize; if ($row->{cell}) { - print $row->{cell}->($val); + if (ref $row->{cell} eq 'CODE') { + print $row->{cell}->($val); + next; + } + print range_cell($row->{cell}, $val); next; } -- 2.30.0
%s