This module implements some methods and creates additional datastructured
from the big character table that we use for all kind of purposes:
We assume that at this point
This converts a string (if given) into a number.
--ldx]]-- local pattern = (P("0x") + P("U+")) * ((R("09","AF")^1 * P(-1)) / function(s) return tonumber(s,16) end) lpegpatterns.chartonumber = pattern local function chartonumber(k) if type(k) == "string" then local u = lpegmatch(pattern,k) if u then return utfbyte(u) else return utfbyte(k) or 0 end else return k or 0 end end local function charfromnumber(k) if type(k) == "number" then return utfchar(k) or "" else local u = lpegmatch(pattern,k) if u then return utfchar(u) else return k end end end --~ print(chartonumber(97), chartonumber("a"), chartonumber("0x61"), chartonumber("U+61")) characters.tonumber = chartonumber characters.fromnumber = charfromnumber local private = { description = "PRIVATE SLOT", } local ranges = allocate() characters.ranges = ranges setmetatableindex(data, function(t,k) local tk = type(k) if tk == "string" then k = lpegmatch(pattern,k) or utfbyte(k) if k then local v = rawget(t,k) if v then return v else tk = "number" -- fall through to range end else return private end end if tk == "number" and k < 0xF0000 then for r=1,#ranges do local rr = ranges[r] if k >= rr.first and k <= rr.last then local extender = rr.extender if extender then local v = extender(k,v) t[k] = v return v end end end end return private -- handy for when we loop over characters in fonts and check for a property end) local blocks = allocate { ["aegeannumbers"] = { first = 0x10100, last = 0x1013F, description = "Aegean Numbers" }, ["alchemicalsymbols"] = { first = 0x1F700, last = 0x1F77F, description = "Alchemical Symbols" }, ["alphabeticpresentationforms"] = { first = 0x0FB00, last = 0x0FB4F, otf="latn", description = "Alphabetic Presentation Forms" }, ["ancientgreekmusicalnotation"] = { first = 0x1D200, last = 0x1D24F, otf="grek", description = "Ancient Greek Musical Notation" }, ["ancientgreeknumbers"] = { first = 0x10140, last = 0x1018F, otf="grek", description = "Ancient Greek Numbers" }, ["ancientsymbols"] = { first = 0x10190, last = 0x101CF, otf="grek", description = "Ancient Symbols" }, ["arabic"] = { first = 0x00600, last = 0x006FF, otf="arab", description = "Arabic" }, ["arabicextendeda"] = { first = 0x008A0, last = 0x008FF, description = "Arabic Extended-A" }, ["arabicmathematicalalphabeticsymbols"] = { first = 0x1EE00, last = 0x1EEFF, description = "Arabic Mathematical Alphabetic Symbols" }, ["arabicpresentationformsa"] = { first = 0x0FB50, last = 0x0FDFF, otf="arab", description = "Arabic Presentation Forms-A" }, ["arabicpresentationformsb"] = { first = 0x0FE70, last = 0x0FEFF, otf="arab", description = "Arabic Presentation Forms-B" }, ["arabicsupplement"] = { first = 0x00750, last = 0x0077F, otf="arab", description = "Arabic Supplement" }, ["armenian"] = { first = 0x00530, last = 0x0058F, otf="armn", description = "Armenian" }, ["arrows"] = { first = 0x02190, last = 0x021FF, description = "Arrows" }, ["avestan"] = { first = 0x10B00, last = 0x10B3F, description = "Avestan" }, ["balinese"] = { first = 0x01B00, last = 0x01B7F, otf="bali", description = "Balinese" }, ["bamum"] = { first = 0x0A6A0, last = 0x0A6FF, description = "Bamum" }, ["bamumsupplement"] = { first = 0x16800, last = 0x16A3F, description = "Bamum Supplement" }, ["basiclatin"] = { first = 0x00000, last = 0x0007F, otf="latn", description = "Basic Latin" }, ["bassavah"] = { first = 0x16AD0, last = 0x16AFF, description = "Bassa Vah" }, ["batak"] = { first = 0x01BC0, last = 0x01BFF, description = "Batak" }, ["bengali"] = { first = 0x00980, last = 0x009FF, otf="beng", description = "Bengali" }, ["blockelements"] = { first = 0x02580, last = 0x0259F, otf="bopo", description = "Block Elements" }, ["bopomofo"] = { first = 0x03100, last = 0x0312F, otf="bopo", description = "Bopomofo" }, ["bopomofoextended"] = { first = 0x031A0, last = 0x031BF, otf="bopo", description = "Bopomofo Extended" }, ["boxdrawing"] = { first = 0x02500, last = 0x0257F, description = "Box Drawing" }, ["brahmi"] = { first = 0x11000, last = 0x1107F, description = "Brahmi" }, ["braillepatterns"] = { first = 0x02800, last = 0x028FF, otf="brai", description = "Braille Patterns" }, ["buginese"] = { first = 0x01A00, last = 0x01A1F, otf="bugi", description = "Buginese" }, ["buhid"] = { first = 0x01740, last = 0x0175F, otf="buhd", description = "Buhid" }, ["byzantinemusicalsymbols"] = { first = 0x1D000, last = 0x1D0FF, otf="byzm", description = "Byzantine Musical Symbols" }, ["carian"] = { first = 0x102A0, last = 0x102DF, description = "Carian" }, ["caucasianalbanian"] = { first = 0x10530, last = 0x1056F, description = "Caucasian Albanian" }, ["chakma"] = { first = 0x11100, last = 0x1114F, description = "Chakma" }, ["cham"] = { first = 0x0AA00, last = 0x0AA5F, description = "Cham" }, ["cherokee"] = { first = 0x013A0, last = 0x013FF, otf="cher", description = "Cherokee" }, ["cjkcompatibility"] = { first = 0x03300, last = 0x033FF, otf="hang", description = "CJK Compatibility" }, ["cjkcompatibilityforms"] = { first = 0x0FE30, last = 0x0FE4F, otf="hang", description = "CJK Compatibility Forms" }, ["cjkcompatibilityideographs"] = { first = 0x0F900, last = 0x0FAFF, otf="hang", description = "CJK Compatibility Ideographs" }, ["cjkcompatibilityideographssupplement"] = { first = 0x2F800, last = 0x2FA1F, otf="hang", description = "CJK Compatibility Ideographs Supplement" }, ["cjkradicalssupplement"] = { first = 0x02E80, last = 0x02EFF, otf="hang", description = "CJK Radicals Supplement" }, ["cjkstrokes"] = { first = 0x031C0, last = 0x031EF, otf="hang", description = "CJK Strokes" }, ["cjksymbolsandpunctuation"] = { first = 0x03000, last = 0x0303F, otf="hang", description = "CJK Symbols and Punctuation" }, ["cjkunifiedideographs"] = { first = 0x04E00, last = 0x09FFF, otf="hang", description = "CJK Unified Ideographs", catcode = "letter" }, ["cjkunifiedideographsextensiona"] = { first = 0x03400, last = 0x04DBF, otf="hang", description = "CJK Unified Ideographs Extension A" }, ["cjkunifiedideographsextensionb"] = { first = 0x20000, last = 0x2A6DF, otf="hang", description = "CJK Unified Ideographs Extension B" }, ["cjkunifiedideographsextensionc"] = { first = 0x2A700, last = 0x2B73F, description = "CJK Unified Ideographs Extension C" }, ["cjkunifiedideographsextensiond"] = { first = 0x2B740, last = 0x2B81F, description = "CJK Unified Ideographs Extension D" }, ["combiningdiacriticalmarks"] = { first = 0x00300, last = 0x0036F, description = "Combining Diacritical Marks" }, ["combiningdiacriticalmarksextended"] = { first = 0x01AB0, last = 0x01AFF, description = "Combining Diacritical Marks Extended" }, ["combiningdiacriticalmarksforsymbols"] = { first = 0x020D0, last = 0x020FF, description = "Combining Diacritical Marks for Symbols" }, ["combiningdiacriticalmarkssupplement"] = { first = 0x01DC0, last = 0x01DFF, description = "Combining Diacritical Marks Supplement" }, ["combininghalfmarks"] = { first = 0x0FE20, last = 0x0FE2F, description = "Combining Half Marks" }, ["commonindicnumberforms"] = { first = 0x0A830, last = 0x0A83F, description = "Common Indic Number Forms" }, ["controlpictures"] = { first = 0x02400, last = 0x0243F, description = "Control Pictures" }, ["coptic"] = { first = 0x02C80, last = 0x02CFF, otf="copt", description = "Coptic" }, ["copticepactnumbers"] = { first = 0x102E0, last = 0x102FF, description = "Coptic Epact Numbers" }, ["countingrodnumerals"] = { first = 0x1D360, last = 0x1D37F, description = "Counting Rod Numerals" }, ["cuneiform"] = { first = 0x12000, last = 0x123FF, otf="xsux", description = "Cuneiform" }, ["cuneiformnumbersandpunctuation"] = { first = 0x12400, last = 0x1247F, otf="xsux", description = "Cuneiform Numbers and Punctuation" }, ["currencysymbols"] = { first = 0x020A0, last = 0x020CF, description = "Currency Symbols" }, ["cypriotsyllabary"] = { first = 0x10800, last = 0x1083F, otf="cprt", description = "Cypriot Syllabary" }, ["cyrillic"] = { first = 0x00400, last = 0x004FF, otf="cyrl", description = "Cyrillic" }, ["cyrillicextendeda"] = { first = 0x02DE0, last = 0x02DFF, otf="cyrl", description = "Cyrillic Extended-A" }, ["cyrillicextendedb"] = { first = 0x0A640, last = 0x0A69F, otf="cyrl", description = "Cyrillic Extended-B" }, ["cyrillicsupplement"] = { first = 0x00500, last = 0x0052F, otf="cyrl", description = "Cyrillic Supplement" }, ["deseret"] = { first = 0x10400, last = 0x1044F, otf="dsrt", description = "Deseret" }, ["devanagari"] = { first = 0x00900, last = 0x0097F, otf="deva", description = "Devanagari" }, ["devanagariextended"] = { first = 0x0A8E0, last = 0x0A8FF, description = "Devanagari Extended" }, ["digitsarabicindic"] = { first = 0x00660, last = 0x00669, math = true }, -- ["digitsbengali"] = { first = 0x009E6, last = 0x009EF, math = true }, ["digitsbold"] = { first = 0x1D7CE, last = 0x1D7D8, math = true }, -- ["digitsdevanagari"] = { first = 0x00966, last = 0x0096F, math = true }, ["digitsdoublestruck"] = { first = 0x1D7D8, last = 0x1D7E2, math = true }, -- ["digitsethiopic"] = { first = 0x01369, last = 0x01371, math = true }, ["digitsextendedarabicindic"] = { first = 0x006F0, last = 0x006F9, math = true }, -- ["digitsgujarati"] = { first = 0x00AE6, last = 0x00AEF, math = true }, -- ["digitsgurmukhi"] = { first = 0x00A66, last = 0x00A6F, math = true }, -- ["digitskannada"] = { first = 0x00CE6, last = 0x00CEF, math = true }, -- ["digitskhmer"] = { first = 0x017E0, last = 0x017E9, math = true }, -- ["digitslao"] = { first = 0x00ED0, last = 0x00ED9, math = true }, ["digitslatin"] = { first = 0x00030, last = 0x00039, math = true }, -- ["digitsmalayalam"] = { first = 0x00D66, last = 0x00D6F, math = true }, -- ["digitsmongolian"] = { first = 0x01810, last = 0x01809, math = true }, ["digitsmonospace"] = { first = 0x1D7F6, last = 0x1D80F, math = true }, -- ["digitsmyanmar"] = { first = 0x01040, last = 0x01049, math = true }, ["digitsnormal"] = { first = 0x00030, last = 0x00039, math = true }, -- ["digitsoriya"] = { first = 0x00B66, last = 0x00B6F, math = true }, ["digitssansserifbold"] = { first = 0x1D7EC, last = 0x1D805, math = true }, ["digitssansserifnormal"] = { first = 0x1D7E2, last = 0x1D7EC, math = true }, -- ["digitstamil"] = { first = 0x00030, last = 0x00039, math = true }, -- no zero -- ["digitstelugu"] = { first = 0x00C66, last = 0x00C6F, math = true }, -- ["digitsthai"] = { first = 0x00E50, last = 0x00E59, math = true }, -- ["digitstibetan"] = { first = 0x00F20, last = 0x00F29, math = true }, ["dingbats"] = { first = 0x02700, last = 0x027BF, description = "Dingbats" }, ["dominotiles"] = { first = 0x1F030, last = 0x1F09F, description = "Domino Tiles" }, ["duployan"] = { first = 0x1BC00, last = 0x1BC9F, description = "Duployan" }, ["egyptianhieroglyphs"] = { first = 0x13000, last = 0x1342F, description = "Egyptian Hieroglyphs" }, ["elbasan"] = { first = 0x10500, last = 0x1052F, description = "Elbasan" }, ["emoticons"] = { first = 0x1F600, last = 0x1F64F, description = "Emoticons" }, ["enclosedalphanumerics"] = { first = 0x02460, last = 0x024FF, description = "Enclosed Alphanumerics" }, ["enclosedalphanumericsupplement"] = { first = 0x1F100, last = 0x1F1FF, description = "Enclosed Alphanumeric Supplement" }, ["enclosedcjklettersandmonths"] = { first = 0x03200, last = 0x032FF, description = "Enclosed CJK Letters and Months" }, ["enclosedideographicsupplement"] = { first = 0x1F200, last = 0x1F2FF, description = "Enclosed Ideographic Supplement" }, ["ethiopic"] = { first = 0x01200, last = 0x0137F, otf="ethi", description = "Ethiopic" }, ["ethiopicextended"] = { first = 0x02D80, last = 0x02DDF, otf="ethi", description = "Ethiopic Extended" }, ["ethiopicextendeda"] = { first = 0x0AB00, last = 0x0AB2F, description = "Ethiopic Extended-A" }, ["ethiopicsupplement"] = { first = 0x01380, last = 0x0139F, otf="ethi", description = "Ethiopic Supplement" }, ["generalpunctuation"] = { first = 0x02000, last = 0x0206F, description = "General Punctuation" }, ["geometricshapes"] = { first = 0x025A0, last = 0x025FF, description = "Geometric Shapes" }, ["geometricshapes"] = { first = 0x025A0, last = 0x025FF, math = true }, ["geometricshapesextended"] = { first = 0x1F780, last = 0x1F7FF, description = "Geometric Shapes Extended" }, ["georgian"] = { first = 0x010A0, last = 0x010FF, otf="geor", description = "Georgian" }, ["georgiansupplement"] = { first = 0x02D00, last = 0x02D2F, otf="geor", description = "Georgian Supplement" }, ["glagolitic"] = { first = 0x02C00, last = 0x02C5F, otf="glag", description = "Glagolitic" }, ["gothic"] = { first = 0x10330, last = 0x1034F, otf="goth", description = "Gothic" }, ["grantha"] = { first = 0x11300, last = 0x1137F, description = "Grantha" }, ["greekandcoptic"] = { first = 0x00370, last = 0x003FF, otf="grek", description = "Greek and Coptic" }, ["greekextended"] = { first = 0x01F00, last = 0x01FFF, otf="grek", description = "Greek Extended" }, ["gujarati"] = { first = 0x00A80, last = 0x00AFF, otf="gujr", description = "Gujarati" }, ["gurmukhi"] = { first = 0x00A00, last = 0x00A7F, otf="guru", description = "Gurmukhi" }, ["halfwidthandfullwidthforms"] = { first = 0x0FF00, last = 0x0FFEF, description = "Halfwidth and Fullwidth Forms" }, ["hangulcompatibilityjamo"] = { first = 0x03130, last = 0x0318F, otf="jamo", description = "Hangul Compatibility Jamo" }, ["hanguljamo"] = { first = 0x01100, last = 0x011FF, otf="jamo", description = "Hangul Jamo" }, ["hanguljamoextendeda"] = { first = 0x0A960, last = 0x0A97F, description = "Hangul Jamo Extended-A" }, ["hanguljamoextendedb"] = { first = 0x0D7B0, last = 0x0D7FF, description = "Hangul Jamo Extended-B" }, ["hangulsyllables"] = { first = 0x0AC00, last = 0x0D7AF, otf="hang", description = "Hangul Syllables" }, ["hanunoo"] = { first = 0x01720, last = 0x0173F, otf="hano", description = "Hanunoo" }, ["hebrew"] = { first = 0x00590, last = 0x005FF, otf="hebr", description = "Hebrew" }, ["highprivateusesurrogates"] = { first = 0x0DB80, last = 0x0DBFF, description = "High Private Use Surrogates" }, ["highsurrogates"] = { first = 0x0D800, last = 0x0DB7F, description = "High Surrogates" }, ["hiragana"] = { first = 0x03040, last = 0x0309F, otf="kana", description = "Hiragana" }, ["ideographicdescriptioncharacters"] = { first = 0x02FF0, last = 0x02FFF, description = "Ideographic Description Characters" }, ["imperialaramaic"] = { first = 0x10840, last = 0x1085F, description = "Imperial Aramaic" }, ["inscriptionalpahlavi"] = { first = 0x10B60, last = 0x10B7F, description = "Inscriptional Pahlavi" }, ["inscriptionalparthian"] = { first = 0x10B40, last = 0x10B5F, description = "Inscriptional Parthian" }, ["ipaextensions"] = { first = 0x00250, last = 0x002AF, description = "IPA Extensions" }, ["javanese"] = { first = 0x0A980, last = 0x0A9DF, description = "Javanese" }, ["kaithi"] = { first = 0x11080, last = 0x110CF, description = "Kaithi" }, ["kanasupplement"] = { first = 0x1B000, last = 0x1B0FF, description = "Kana Supplement" }, ["kanbun"] = { first = 0x03190, last = 0x0319F, description = "Kanbun" }, ["kangxiradicals"] = { first = 0x02F00, last = 0x02FDF, description = "Kangxi Radicals" }, ["kannada"] = { first = 0x00C80, last = 0x00CFF, otf="knda", description = "Kannada" }, ["katakana"] = { first = 0x030A0, last = 0x030FF, otf="kana", description = "Katakana" }, ["katakanaphoneticextensions"] = { first = 0x031F0, last = 0x031FF, otf="kana", description = "Katakana Phonetic Extensions" }, ["kayahli"] = { first = 0x0A900, last = 0x0A92F, description = "Kayah Li" }, ["kharoshthi"] = { first = 0x10A00, last = 0x10A5F, otf="khar", description = "Kharoshthi" }, ["khmer"] = { first = 0x01780, last = 0x017FF, otf="khmr", description = "Khmer" }, ["khmersymbols"] = { first = 0x019E0, last = 0x019FF, otf="khmr", description = "Khmer Symbols" }, ["khojki"] = { first = 0x11200, last = 0x1124F, description = "Khojki" }, ["khudawadi"] = { first = 0x112B0, last = 0x112FF, description = "Khudawadi" }, ["lao"] = { first = 0x00E80, last = 0x00EFF, otf="lao", description = "Lao" }, ["latinextendeda"] = { first = 0x00100, last = 0x0017F, otf="latn", description = "Latin Extended-A" }, ["latinextendedadditional"] = { first = 0x01E00, last = 0x01EFF, otf="latn", description = "Latin Extended Additional" }, ["latinextendedb"] = { first = 0x00180, last = 0x0024F, otf="latn", description = "Latin Extended-B" }, ["latinextendedc"] = { first = 0x02C60, last = 0x02C7F, otf="latn", description = "Latin Extended-C" }, ["latinextendedd"] = { first = 0x0A720, last = 0x0A7FF, otf="latn", description = "Latin Extended-D" }, ["latinextendede"] = { first = 0x0AB30, last = 0x0AB6F, description = "Latin Extended-E" }, ["latinsupplement"] = { first = 0x00080, last = 0x000FF, otf="latn", description = "Latin-1 Supplement" }, ["lepcha"] = { first = 0x01C00, last = 0x01C4F, description = "Lepcha" }, ["letterlikesymbols"] = { first = 0x02100, last = 0x0214F, description = "Letterlike Symbols" }, ["letterlikesymbols"] = { first = 0x02100, last = 0x0214F, math = true }, ["limbu"] = { first = 0x01900, last = 0x0194F, otf="limb", description = "Limbu" }, ["lineara"] = { first = 0x10600, last = 0x1077F, description = "Linear A" }, ["linearbideograms"] = { first = 0x10080, last = 0x100FF, otf="linb", description = "Linear B Ideograms" }, ["linearbsyllabary"] = { first = 0x10000, last = 0x1007F, otf="linb", description = "Linear B Syllabary" }, ["lisu"] = { first = 0x0A4D0, last = 0x0A4FF, description = "Lisu" }, ["lowercasebold"] = { first = 0x1D41A, last = 0x1D433, math = true }, ["lowercaseboldfraktur"] = { first = 0x1D586, last = 0x1D59F, math = true }, ["lowercasebolditalic"] = { first = 0x1D482, last = 0x1D49B, math = true }, ["lowercaseboldscript"] = { first = 0x1D4EA, last = 0x1D503, math = true }, ["lowercasedoublestruck"] = { first = 0x1D552, last = 0x1D56B, math = true }, ["lowercasefraktur"] = { first = 0x1D51E, last = 0x1D537, math = true }, ["lowercasegreekbold"] = { first = 0x1D6C2, last = 0x1D6DB, math = true }, ["lowercasegreekbolditalic"] = { first = 0x1D736, last = 0x1D74F, math = true }, ["lowercasegreekitalic"] = { first = 0x1D6FC, last = 0x1D715, math = true }, ["lowercasegreeknormal"] = { first = 0x003B1, last = 0x003CA, math = true }, ["lowercasegreeksansserifbold"] = { first = 0x1D770, last = 0x1D789, math = true }, ["lowercasegreeksansserifbolditalic"] = { first = 0x1D7AA, last = 0x1D7C3, math = true }, ["lowercaseitalic"] = { first = 0x1D44E, last = 0x1D467, math = true }, ["lowercasemonospace"] = { first = 0x1D68A, last = 0x1D6A3, math = true }, ["lowercasenormal"] = { first = 0x00061, last = 0x0007A, math = true }, ["lowercasesansserifbold"] = { first = 0x1D5EE, last = 0x1D607, math = true }, ["lowercasesansserifbolditalic"] = { first = 0x1D656, last = 0x1D66F, math = true }, ["lowercasesansserifitalic"] = { first = 0x1D622, last = 0x1D63B, math = true }, ["lowercasesansserifnormal"] = { first = 0x1D5BA, last = 0x1D5D3, math = true }, ["lowercasescript"] = { first = 0x1D4B6, last = 0x1D4CF, math = true }, ["lowsurrogates"] = { first = 0x0DC00, last = 0x0DFFF, description = "Low Surrogates" }, ["lycian"] = { first = 0x10280, last = 0x1029F, description = "Lycian" }, ["lydian"] = { first = 0x10920, last = 0x1093F, description = "Lydian" }, ["mahajani"] = { first = 0x11150, last = 0x1117F, description = "Mahajani" }, ["mahjongtiles"] = { first = 0x1F000, last = 0x1F02F, description = "Mahjong Tiles" }, ["malayalam"] = { first = 0x00D00, last = 0x00D7F, otf="mlym", description = "Malayalam" }, ["mandaic"] = { first = 0x00840, last = 0x0085F, otf="mand", description = "Mandaic" }, ["manichaean"] = { first = 0x10AC0, last = 0x10AFF, description = "Manichaean" }, ["mathematicalalphanumericsymbols"] = { first = 0x1D400, last = 0x1D7FF, math = true, description = "Mathematical Alphanumeric Symbols" }, ["mathematicaloperators"] = { first = 0x02200, last = 0x022FF, math = true, description = "Mathematical Operators" }, ["meeteimayek"] = { first = 0x0ABC0, last = 0x0ABFF, description = "Meetei Mayek" }, ["meeteimayekextensions"] = { first = 0x0AAE0, last = 0x0AAFF, description = "Meetei Mayek Extensions" }, ["mendekikakui"] = { first = 0x1E800, last = 0x1E8DF, description = "Mende Kikakui" }, ["meroiticcursive"] = { first = 0x109A0, last = 0x109FF, description = "Meroitic Cursive" }, ["meroitichieroglyphs"] = { first = 0x10980, last = 0x1099F, description = "Meroitic Hieroglyphs" }, ["miao"] = { first = 0x16F00, last = 0x16F9F, description = "Miao" }, ["miscellaneousmathematicalsymbolsa"] = { first = 0x027C0, last = 0x027EF, math = true, description = "Miscellaneous Mathematical Symbols-A" }, ["miscellaneousmathematicalsymbolsb"] = { first = 0x02980, last = 0x029FF, math = true, description = "Miscellaneous Mathematical Symbols-B" }, ["miscellaneoussymbols"] = { first = 0x02600, last = 0x026FF, math = true, description = "Miscellaneous Symbols" }, ["miscellaneoussymbolsandarrows"] = { first = 0x02B00, last = 0x02BFF, math = true, description = "Miscellaneous Symbols and Arrows" }, ["miscellaneoussymbolsandpictographs"] = { first = 0x1F300, last = 0x1F5FF, description = "Miscellaneous Symbols and Pictographs" }, ["miscellaneoustechnical"] = { first = 0x02300, last = 0x023FF, math = true, description = "Miscellaneous Technical" }, ["modi"] = { first = 0x11600, last = 0x1165F, description = "Modi" }, ["modifiertoneletters"] = { first = 0x0A700, last = 0x0A71F, description = "Modifier Tone Letters" }, ["mongolian"] = { first = 0x01800, last = 0x018AF, otf="mong", description = "Mongolian" }, ["mro"] = { first = 0x16A40, last = 0x16A6F, description = "Mro" }, ["musicalsymbols"] = { first = 0x1D100, last = 0x1D1FF, otf="musc", description = "Musical Symbols" }, ["myanmar"] = { first = 0x01000, last = 0x0109F, otf="mymr", description = "Myanmar" }, ["myanmarextendeda"] = { first = 0x0AA60, last = 0x0AA7F, description = "Myanmar Extended-A" }, ["myanmarextendedb"] = { first = 0x0A9E0, last = 0x0A9FF, description = "Myanmar Extended-B" }, ["nabataean"] = { first = 0x10880, last = 0x108AF, description = "Nabataean" }, ["newtailue"] = { first = 0x01980, last = 0x019DF, description = "New Tai Lue" }, ["nko"] = { first = 0x007C0, last = 0x007FF, otf="nko", description = "NKo" }, ["numberforms"] = { first = 0x02150, last = 0x0218F, description = "Number Forms" }, ["ogham"] = { first = 0x01680, last = 0x0169F, otf="ogam", description = "Ogham" }, ["olchiki"] = { first = 0x01C50, last = 0x01C7F, description = "Ol Chiki" }, ["olditalic"] = { first = 0x10300, last = 0x1032F, otf="ital", description = "Old Italic" }, ["oldnortharabian"] = { first = 0x10A80, last = 0x10A9F, description = "Old North Arabian" }, ["oldpermic"] = { first = 0x10350, last = 0x1037F, description = "Old Permic" }, ["oldpersian"] = { first = 0x103A0, last = 0x103DF, otf="xpeo", description = "Old Persian" }, ["oldsoutharabian"] = { first = 0x10A60, last = 0x10A7F, description = "Old South Arabian" }, ["oldturkic"] = { first = 0x10C00, last = 0x10C4F, description = "Old Turkic" }, ["opticalcharacterrecognition"] = { first = 0x02440, last = 0x0245F, description = "Optical Character Recognition" }, ["oriya"] = { first = 0x00B00, last = 0x00B7F, otf="orya", description = "Oriya" }, ["ornamentaldingbats"] = { first = 0x1F650, last = 0x1F67F, description = "Ornamental Dingbats" }, ["osmanya"] = { first = 0x10480, last = 0x104AF, otf="osma", description = "Osmanya" }, ["pahawhhmong"] = { first = 0x16B00, last = 0x16B8F, description = "Pahawh Hmong" }, ["palmyrene"] = { first = 0x10860, last = 0x1087F, description = "Palmyrene" }, ["paucinhau"] = { first = 0x11AC0, last = 0x11AFF, description = "Pau Cin Hau" }, ["phagspa"] = { first = 0x0A840, last = 0x0A87F, otf="phag", description = "Phags-pa" }, ["phaistosdisc"] = { first = 0x101D0, last = 0x101FF, description = "Phaistos Disc" }, ["phoenician"] = { first = 0x10900, last = 0x1091F, otf="phnx", description = "Phoenician" }, ["phoneticextensions"] = { first = 0x01D00, last = 0x01D7F, description = "Phonetic Extensions" }, ["phoneticextensionssupplement"] = { first = 0x01D80, last = 0x01DBF, description = "Phonetic Extensions Supplement" }, ["playingcards"] = { first = 0x1F0A0, last = 0x1F0FF, description = "Playing Cards" }, ["privateusearea"] = { first = 0x0E000, last = 0x0F8FF, description = "Private Use Area" }, ["psalterpahlavi"] = { first = 0x10B80, last = 0x10BAF, description = "Psalter Pahlavi" }, ["rejang"] = { first = 0x0A930, last = 0x0A95F, description = "Rejang" }, ["ruminumeralsymbols"] = { first = 0x10E60, last = 0x10E7F, description = "Rumi Numeral Symbols" }, ["runic"] = { first = 0x016A0, last = 0x016FF, otf="runr", description = "Runic" }, ["samaritan"] = { first = 0x00800, last = 0x0083F, description = "Samaritan" }, ["saurashtra"] = { first = 0x0A880, last = 0x0A8DF, description = "Saurashtra" }, ["sharada"] = { first = 0x11180, last = 0x111DF, description = "Sharada" }, ["shavian"] = { first = 0x10450, last = 0x1047F, otf="shaw", description = "Shavian" }, ["shorthandformatcontrols"] = { first = 0x1BCA0, last = 0x1BCAF, description = "Shorthand Format Controls" }, ["siddham"] = { first = 0x11580, last = 0x115FF, description = "Siddham" }, ["sinhala"] = { first = 0x00D80, last = 0x00DFF, otf="sinh", description = "Sinhala" }, ["sinhalaarchaicnumbers"] = { first = 0x111E0, last = 0x111FF, description = "Sinhala Archaic Numbers" }, ["smallformvariants"] = { first = 0x0FE50, last = 0x0FE6F, description = "Small Form Variants" }, ["sorasompeng"] = { first = 0x110D0, last = 0x110FF, description = "Sora Sompeng" }, ["spacingmodifierletters"] = { first = 0x002B0, last = 0x002FF, description = "Spacing Modifier Letters" }, ["specials"] = { first = 0x0FFF0, last = 0x0FFFF, description = "Specials" }, ["sundanese"] = { first = 0x01B80, last = 0x01BBF, description = "Sundanese" }, ["sundanesesupplement"] = { first = 0x01CC0, last = 0x01CCF, description = "Sundanese Supplement" }, ["superscriptsandsubscripts"] = { first = 0x02070, last = 0x0209F, description = "Superscripts and Subscripts" }, ["supplementalarrowsa"] = { first = 0x027F0, last = 0x027FF, math = true, description = "Supplemental Arrows-A" }, ["supplementalarrowsb"] = { first = 0x02900, last = 0x0297F, math = true, description = "Supplemental Arrows-B" }, ["supplementalarrowsc"] = { first = 0x1F800, last = 0x1F8FF, math = true, description = "Supplemental Arrows-C" }, ["supplementalmathematicaloperators"] = { first = 0x02A00, last = 0x02AFF, math = true, description = "Supplemental Mathematical Operators" }, ["supplementalpunctuation"] = { first = 0x02E00, last = 0x02E7F, description = "Supplemental Punctuation" }, ["supplementaryprivateuseareaa"] = { first = 0xF0000, last = 0xFFFFF, description = "Supplementary Private Use Area-A" }, ["supplementaryprivateuseareab"] = { first = 0x100000,last = 0x10FFFF, description = "Supplementary Private Use Area-B" }, ["sylotinagri"] = { first = 0x0A800, last = 0x0A82F, otf="sylo", description = "Syloti Nagri" }, ["syriac"] = { first = 0x00700, last = 0x0074F, otf="syrc", description = "Syriac" }, ["tagalog"] = { first = 0x01700, last = 0x0171F, otf="tglg", description = "Tagalog" }, ["tagbanwa"] = { first = 0x01760, last = 0x0177F, otf="tagb", description = "Tagbanwa" }, ["tags"] = { first = 0xE0000, last = 0xE007F, description = "Tags" }, ["taile"] = { first = 0x01950, last = 0x0197F, otf="tale", description = "Tai Le" }, ["taitham"] = { first = 0x01A20, last = 0x01AAF, description = "Tai Tham" }, ["taiviet"] = { first = 0x0AA80, last = 0x0AADF, description = "Tai Viet" }, ["taixuanjingsymbols"] = { first = 0x1D300, last = 0x1D35F, description = "Tai Xuan Jing Symbols" }, ["takri"] = { first = 0x11680, last = 0x116CF, description = "Takri" }, ["tamil"] = { first = 0x00B80, last = 0x00BFF, otf="taml", description = "Tamil" }, ["telugu"] = { first = 0x00C00, last = 0x00C7F, otf="telu", description = "Telugu" }, ["thaana"] = { first = 0x00780, last = 0x007BF, otf="thaa", description = "Thaana" }, ["thai"] = { first = 0x00E00, last = 0x00E7F, otf="thai", description = "Thai" }, ["tibetan"] = { first = 0x00F00, last = 0x00FFF, otf="tibt", description = "Tibetan" }, ["tifinagh"] = { first = 0x02D30, last = 0x02D7F, otf="tfng", description = "Tifinagh" }, ["tirhuta"] = { first = 0x11480, last = 0x114DF, description = "Tirhuta" }, ["transportandmapsymbols"] = { first = 0x1F680, last = 0x1F6FF, description = "Transport and Map Symbols" }, ["ugaritic"] = { first = 0x10380, last = 0x1039F, otf="ugar", description = "Ugaritic" }, ["unifiedcanadianaboriginalsyllabics"] = { first = 0x01400, last = 0x0167F, otf="cans", description = "Unified Canadian Aboriginal Syllabics" }, ["unifiedcanadianaboriginalsyllabicsextended"] = { first = 0x018B0, last = 0x018FF, description = "Unified Canadian Aboriginal Syllabics Extended" }, ["uppercasebold"] = { first = 0x1D400, last = 0x1D419, math = true }, ["uppercaseboldfraktur"] = { first = 0x1D56C, last = 0x1D585, math = true }, ["uppercasebolditalic"] = { first = 0x1D468, last = 0x1D481, math = true }, ["uppercaseboldscript"] = { first = 0x1D4D0, last = 0x1D4E9, math = true }, ["uppercasedoublestruck"] = { first = 0x1D538, last = 0x1D551, math = true }, ["uppercasefraktur"] = { first = 0x1D504, last = 0x1D51D, math = true }, ["uppercasegreekbold"] = { first = 0x1D6A8, last = 0x1D6C1, math = true }, ["uppercasegreekbolditalic"] = { first = 0x1D71C, last = 0x1D735, math = true }, ["uppercasegreekitalic"] = { first = 0x1D6E2, last = 0x1D6FB, math = true }, ["uppercasegreeknormal"] = { first = 0x00391, last = 0x003AA, math = true }, ["uppercasegreeksansserifbold"] = { first = 0x1D756, last = 0x1D76F, math = true }, ["uppercasegreeksansserifbolditalic"] = { first = 0x1D790, last = 0x1D7A9, math = true }, ["uppercaseitalic"] = { first = 0x1D434, last = 0x1D44D, math = true }, ["uppercasemonospace"] = { first = 0x1D670, last = 0x1D689, math = true }, ["uppercasenormal"] = { first = 0x00041, last = 0x0005A, math = true }, ["uppercasesansserifbold"] = { first = 0x1D5D4, last = 0x1D5ED, math = true }, ["uppercasesansserifbolditalic"] = { first = 0x1D63C, last = 0x1D655, math = true }, ["uppercasesansserifitalic"] = { first = 0x1D608, last = 0x1D621, math = true }, ["uppercasesansserifnormal"] = { first = 0x1D5A0, last = 0x1D5B9, math = true }, ["uppercasescript"] = { first = 0x1D49C, last = 0x1D4B5, math = true }, ["vai"] = { first = 0x0A500, last = 0x0A63F, description = "Vai" }, ["variationselectors"] = { first = 0x0FE00, last = 0x0FE0F, description = "Variation Selectors" }, ["variationselectorssupplement"] = { first = 0xE0100, last = 0xE01EF, description = "Variation Selectors Supplement" }, ["vedicextensions"] = { first = 0x01CD0, last = 0x01CFF, description = "Vedic Extensions" }, ["verticalforms"] = { first = 0x0FE10, last = 0x0FE1F, description = "Vertical Forms" }, ["warangciti"] = { first = 0x118A0, last = 0x118FF, description = "Warang Citi" }, ["yijinghexagramsymbols"] = { first = 0x04DC0, last = 0x04DFF, otf="yi", description = "Yijing Hexagram Symbols" }, ["yiradicals"] = { first = 0x0A490, last = 0x0A4CF, otf="yi", description = "Yi Radicals" }, ["yisyllables"] = { first = 0x0A000, last = 0x0A48F, otf="yi", description = "Yi Syllables" }, } characters.blocks = blocks function characters.blockrange(name) local b = blocks[name] if b then return b.first, b.last else return 0, 0 end end setmetatableindex(blocks, function(t,k) -- we could use an intermediate table if called often return k and rawget(t,lower(gsub(k,"[^a-zA-Z]",""))) end) local otfscripts = utilities.storage.allocate() characters.otfscripts = otfscripts setmetatableindex(otfscripts,function(t,unicode) for k, v in next, blocks do local first, last = v.first, v.last if unicode >= first and unicode <= last then local script = v.otf or "dflt" for u=first,last do t[u] = script end return script end end -- pretty slow when we're here t[unicode] = "dflt" return "dflt" end) local splitter = lpeg.splitat(S(":-")) function characters.getrange(name) -- used in font fallback definitions (name or range) local range = blocks[name] if range then return range.first, range.last, range.description, range.gaps end name = gsub(name,'"',"0x") -- goodie: tex hex notation local start, stop = lpegmatch(splitter,name) if start and stop then start, stop = tonumber(start,16) or tonumber(start), tonumber(stop,16) or tonumber(stop) if start and stop then return start, stop, nil end end local slot = tonumber(name,16) or tonumber(name) return slot, slot, nil end local categorytags = allocate { lu = "Letter Uppercase", ll = "Letter Lowercase", lt = "Letter Titlecase", lm = "Letter Modifier", lo = "Letter Other", mn = "Mark Nonspacing", mc = "Mark Spacing Combining", me = "Mark Enclosing", nd = "Number Decimal Digit", nl = "Number Letter", no = "Number Other", pc = "Punctuation Connector", pd = "Punctuation Dash", ps = "Punctuation Open", pe = "Punctuation Close", pi = "Punctuation Initial Quote", pf = "Punctuation Final Quote", po = "Punctuation Other", sm = "Symbol Math", sc = "Symbol Currency", sk = "Symbol Modifier", so = "Symbol Other", zs = "Separator Space", zl = "Separator Line", zp = "Separator Paragraph", cc = "Other Control", cf = "Other Format", cs = "Other Surrogate", co = "Other Private Use", cn = "Other Not Assigned", } local detailtags = allocate { sl = "small letter", bl = "big letter", im = "iteration mark", pm = "prolonged sound mark" } characters.categorytags = categorytags characters.detailtags = detailtags -- sounds : voiced unvoiced semivoiced --~ special : cf (softhyphen) zs (emspace) --~ characters: ll lm lo lt lu mn nl no pc pd pe pf pi po ps sc sk sm so local is_character = allocate ( tohash { "lu","ll","lt","lm","lo", "nd","nl","no", "mn", "nl","no", "pc","pd","ps","pe","pi","pf","po", "sm","sc","sk","so" } ) local is_letter = allocate ( tohash { "ll","lm","lo","lt","lu" } ) local is_command = allocate ( tohash { "cf","zs" } ) local is_spacing = allocate ( tohash { "zs", "zl","zp", } ) local is_mark = allocate ( tohash { "mn", "ms", } ) local is_punctuation = allocate ( tohash { "pc","pd","ps","pe","pi","pf","po", } ) -- to be redone: store checked characters characters.is_character = is_character characters.is_letter = is_letter characters.is_command = is_command characters.is_spacing = is_spacing characters.is_mark = is_mark characters.is_punctuation = is_punctuation local mti = function(t,k) if type(k) == "number" then local c = data[k].category return c and rawget(t,c) else -- avoid auto conversion in data.characters lookups end end setmetatableindex(characters.is_character, mti) setmetatableindex(characters.is_letter, mti) setmetatableindex(characters.is_command, mti) setmetatableindex(characters.is_spacing, mti) setmetatableindex(characters.is_punctuation,mti) -- todo: also define callers for the above -- linebreak: todo: hash -- -- normative : BK CR LF CM SG GL CB SP ZW NL WJ JL JV JT H2 H3 -- informative : XX OP CL CP QU NS EX SY IS PR PO NU AL ID IN HY BB BA SA AI B2 HL CJ RI -- -- comments taken from standard: characters.linebreaks = { -- non-tailorable line breaking classes ["bk"] = "mandatory break", -- nl, ps : cause a line break (after) ["cr"] = "carriage return", -- cr : cause a line break (after), except between cr and lf ["lf"] = "line feed", -- lf : cause a line break (after) ["cm"] = "combining mark", -- combining marks, control codes : prohibit a line break between the character and the preceding character ["nl"] = "next line", -- nel : cause a line break (after) ["sg"] = "surrogate", -- surrogates :do not occur in well-formed text ["wj"] = "word joiner", -- wj : prohibit line breaks before and after ["zw"] = "zero width space", -- zwsp : provide a break opportunity ["gl"] = "non-breaking (glue)", -- cgj, nbsp, zwnbsp : prohibit line breaks before and after ["sp"] = "space", -- space : enable indirect line breaks -- break opportunities ["b2"] = "break opportunity before and after", -- em dash : provide a line break opportunity before and after the character ["ba"] = "break after", -- spaces, hyphens : generally provide a line break opportunity after the character ["bb"] = "break before", -- punctuation used in dictionaries : generally provide a line break opportunity before the character ["hy"] = "hyphen", -- hyphen-minus : provide a line break opportunity after the character, except in numeric context ["cb"] = "contingent break opportunity", -- inline objects : provide a line break opportunity contingent on additional information -- characters prohibiting certain breaks ["cl"] = "close punctuation", -- “}”, “❳”, “⟫” etc. : prohibit line breaks before ["cp"] = "close parenthesis", -- “)”, “]” : prohibit line breaks before ["ex"] = "exclamation/interrogation", -- “!”, “?”, etc. : prohibit line breaks before ["in"] = "inseparable", -- leaders : allow only indirect line breaks between pairs ["ns"] = "nonstarter", -- “‼”, “‽”, “⁇”, “⁉”, etc. : allow only indirect line breaks before ["op"] = "open punctuation", -- “(“, “[“, “{“, etc. : prohibit line breaks after ["qu"] = "quotation", -- quotation marks : act like they are both opening and closing -- numeric context ["is"] = "infix numeric separator", -- . , : prevent breaks after any and before numeric ["nu"] = "numeric", -- digits : form numeric expressions for line breaking purposes ["po"] = "postfix numeric", -- %, ¢ : do not break following a numeric expression ["pr"] = "prefix numeric", -- $, £, ¥, etc. : do not break in front of a numeric expression ["sy"] = "symbols allowing break after", -- / : prevent a break before, and allow a break after -- other characters ["ai"] = "ambiguous (alphabetic or ideographic)", -- characters with ambiguous east asian width : act like al when the resolved eaw is n; otherwise, act as id ["al"] = "alphabetic", -- alphabets and regular symbols : are alphabetic characters or symbols that are used with alphabetic characters ["cj"] = "conditional japanese starter", -- small kana : treat as ns or id for strict or normal breaking. ["h2"] = "hangul lv syllable", -- hangul : form korean syllable blocks ["h3"] = "hangul lvt syllable", -- hangul : form korean syllable blocks ["hl"] = "hebrew letter", -- hebrew : do not break around a following hyphen; otherwise act as alphabetic ["id"] = "ideographic", -- ideographs : break before or after, except in some numeric context ["jl"] = "hangul l jamo", -- conjoining jamo : form korean syllable blocks ["jv"] = "hangul v jamo", -- conjoining jamo : form korean syllable blocks ["jt"] = "hangul t jamo", -- conjoining jamo : form korean syllable blocks ["ri"] = "regional indicator", -- regional indicator symbol letter a .. z : keep together, break before and after from others ["sa"] = "complex context dependent (south east asian)", -- south east asian: thai, lao, khmer : provide a line break opportunity contingent on additional, language-specific context analysis ["xx"] = "unknown", -- most unassigned, private-use : have as yet unknown line breaking behavior or unassigned code positions } -- east asian width: -- -- N A H W F Na characters.bidi = allocate { l = "Left-to-Right", lre = "Left-to-Right Embedding", lro = "Left-to-Right Override", r = "Right-to-Left", al = "Right-to-Left Arabic", rle = "Right-to-Left Embedding", rlo = "Right-to-Left Override", pdf = "Pop Directional Format", en = "European Number", es = "European Number Separator", et = "European Number Terminator", an = "Arabic Number", cs = "Common Number Separator", nsm = "Non-Spacing Mark", bn = "Boundary Neutral", b = "Paragraph Separator", s = "Segment Separator", ws = "Whitespace", on = "Other Neutrals", } --[[ldx--At this point we assume that the big data table is loaded. From this table we derive a few more.
--ldx]]-- if not characters.fallbacks then characters.fallbacks = { } -- not than many local fallbacks = characters.fallbacks for k, d in next, data do local specials = d.specials if specials and specials[1] == "compat" and specials[2] == 0x0020 then local s = specials[3] if s then fallbacks[k] = s fallbacks[s] = k end end end end if storage then storage.register("characters/fallbacks", characters.fallbacks, "characters.fallbacks") -- accents and such end characters.directions = { } setmetatableindex(characters.directions,function(t,k) local d = data[k] if d then local v = d.direction if v then t[k] = v return v end end t[k] = false -- maybe 'l' return v end) characters.mirrors = { } setmetatableindex(characters.mirrors,function(t,k) local d = data[k] if d then local v = d.mirror if v then t[k] = v return v end end t[k] = false return v end) characters.textclasses = { } setmetatableindex(characters.textclasses,function(t,k) local d = data[k] if d then local v = d.textclass if v then t[k] = v return v end end t[k] = false return v end) --[[ldx--Next comes a whole series of helper methods. These are (will be) part
of the official
Requesting lower and uppercase codes:
--ldx]]-- function characters.uccode(n) return uccodes[n] end -- obsolete function characters.lccode(n) return lccodes[n] end -- obsolete function characters.shape(n) local shcode = shcodes[n] if not shcode then return n, nil elseif type(shcode) == "table" then return shcode[1], shcode[#shcode] else return shcode, nil end end -- -- some day we might go this route, but it does not really save that much -- -- so not now (we can generate a lot using mtx-unicode that operates on the -- -- database) -- -- -- category cjkwd direction linebreak -- -- -- adobename comment contextcommand contextname description fallback lccode -- -- mathclass mathfiller mathname mathspec mathstretch mathsymbol mirror -- -- range shcode specials uccode uccodes unicodeslot -- -- local data = { -- ['one']={ -- common = { -- category="cc", -- direction="bn", -- linebreak="cm", -- }, -- vector = { -- [0x0000] = { -- description="NULL", -- group='one', -- unicodeslot=0x0000, -- }, -- { -- description="START OF HEADING", -- group='one', -- unicodeslot=0x0001, -- }, -- } -- } -- } -- -- local chardata, groupdata = { }, { } -- -- for group, gdata in next, data do -- local common, vector = { __index = gdata.common }, gdata.vector -- for character, cdata in next, vector do -- chardata[character] = cdata -- setmetatable(cdata,common) -- end -- groupdata[group] = gdata -- end -- characters.data, characters.groups = chardata, groupdata -- [0xF0000]={ -- category="co", -- cjkwd="a", -- description="