Модуль:Unicode data
Бул модулда http://www.unicode.org/Public/UNIDATA/ табылган материалдар алынган Юникод эмес тамга базасын, жетүү үчүн колдонулат.
Азыркы учурда бул эки ыкманы экспорттойт: lookup_name жана template_lookup_name. Да, бир Юникод коду пункту номери берилет, коду баллдардын наамын кайтарып. мурдагы Lua кодексине түздөн-түз пайдалануу үчүн арналган, ал эми экинчиси, шаблонла аркылуу дубасы басууга болот.
User:Kephir/Unicode бул маалымат базасын жүргүзүү боюнча пайдалуу болушу мүмкүн скрипттерди камтыйт.
Subpage index[түзөтүү]
Copyright[түзөтүү]
Юникод эмес маалымат базасы төмөнкү шарттарда Unicode Inc. тарабынан бошотулат:
Copyright © 1991-2016 Unicode, Inc. Бардык укуктар корголгон. Колдонуу шарттары боюнча таратылган http://www.unicode.org/copyright.html.
Уруксат тутушуп, акысыз, Юникод эмес маалыматтарды көчүрмөсүн алуу ар бир адам жана ага байланыштуу документтер үчүн ("маалыматтар билэ") же Unicode программалык жана ага байланыштуу документтерин ("Программа") маалыматтар билэ мамиле болуп саналат же пайдаланууга, көчүрмөсүн укугун, өзгөртүү, бириктирилген жарыялоо, чеги жок, чектөө жок таратууга программа, жана / же маалыматтар билэ же Программанын көчүрмөсүн сатып, маалыматтар билэ же программасы төшөлгөн болуп кимге эмне үчүн адамдарды уруксат берүү ошондуктан, (а) жогоруда көрсөтүлгөн укук кабарлоо (лор) жана бул уруксат билдирүү маалыматтарды же Программанын бардык көчүрмөлөрү менен пайда болот, (б) жогоруда көрсөтүлгөн укук кабарлоо (лор) жана бул уруксат кабарлоо байланышкан документтерди пайда, ал эми берилген (с) ар бир барак маалыматтар билэ же программа ачык эскертүү болуп саналат, ошондой эле, маалымат же программа өзгөртүлдү маалыматтар билэ (тер) же аны менен байланышкан документтерди жок.
Бул кабарлоодо камтылган учурларды кошпогондо, укук ээсинин аты-жөнү жарнамалык же Эгерде соода-сатык жайылтуу үчүн колдонулушу мүмкүн эмес, пайдалануу же укук ээси алдын ала кат жүзүндөгү уруксаты болмоюнча, бул маалыматтарды же Программанын башка мамиле.
local export = {}
-- http://www.unicode.org/Public/UNIDATA/Jamo.txt
local hangul_leads = {
[0] = "G", "GG", "N", "D", "DD", "R", "M", "B", "BB", "S", "SS",
"", "J", "JJ", "C", "K", "T", "P", "H"
}
local hangul_vowels = {
[0] = "A", "AE", "YA", "YAE", "EO", "E", "YEO", "YE", "O", "WA",
"WAE", "OE", "YO", "U", "WEO", "WE", "WI", "YU", "EU", "YI",
"I"
}
local hangul_trails = {
[0] = "", "G", "GG", "GS", "N", "NJ", "NH", "D", "L", "LG", "LM", "LB",
"LS", "LT", "LP", "LH", "M", "B", "BS", "S", "SS", "NG", "J", "C", "K",
"T", "P", "H"
}
local name_hooks = {
{ 0x00, 0x1f, "<control-%04X>" }, -- C0 control characters
{ 0x80, 0x9f, "<control-%04X>" }, -- C1 control characters
{ 0x3400, 0x4db5, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph Extension A
{ 0x4e00, 0x9fd5, "CJK UNIFIED IDEOGRAPH-%04X" }, -- CJK Ideograph
{ 0xac00, 0xd7a3, function (codepoint)
local m_hangul = require('Module:ko-hangul')
local li, vi, ti = m_hangul.syllableIndex2JamoIndices(
codepoint - 0xac00
)
return ("HANGUL SYLLABLE %s%s%s"):format(
hangul_leads[li], -- I hate one-based indexing
hangul_vowels[vi],
hangul_trails[ti] -- never mind, I can live with it
)
end },
{ 0xd800, 0xdb7f, "<surrogate-%04X>" }, -- Non Private Use High Surrogate
{ 0xdb80, 0xdbff, "<surrogate-%04X>" }, -- Private Use High Surrogate
{ 0xdc00, 0xdfff, "<surrogate-%04X>" }, -- Low Surrogate
{ 0xe000, 0xf8ff, "<private-use-%04X>" }, -- Private Use
{ 0x17000, 0x187ec, "TANGUT IDEOGRAPH-%05X" }, -- Tangut
{ 0x20000, 0x2a6d6, "CJK UNIFIED IDEOGRAPH-%05X" }, -- CJK Ideograph Extension B
{ 0x2a700, 0x2b734, "CJK UNIFIED IDEOGRAPH-%05X" }, -- CJK Ideograph Extension C
{ 0x2a740, 0x2b81d, "CJK UNIFIED IDEOGRAPH-%05X" }, -- CJK Ideograph Extension D
{ 0x2b820, 0x2cea1, "CJK UNIFIED IDEOGRAPH-%05X" }, -- CJK Ideograph Extension E
{ 0x2f800, 0x2fa1d, "CJK COMPATIBILITY IDEOGRAPH-%05X" }, -- CJK Compatibility Ideographs Supplement (Supplementary Ideographic Plane)
{ 0xf0000, 0xffffd, "<private-use-%05X>" }, -- Plane 15 Private Use
{ 0x100000, 0x10fffd, "<private-use-%06X>" } -- Plane 16 Private Use
}
local noncharacters = {
[ 0xfdd0] = true, [ 0xfdd1] = true,
[ 0xfdd2] = true, [ 0xfdd3] = true,
[ 0xfdd4] = true, [ 0xfdd5] = true,
[ 0xfdd6] = true, [ 0xfdd7] = true,
[ 0xfdd8] = true, [ 0xfdd9] = true,
[ 0xfdda] = true, [ 0xfddb] = true,
[ 0xfddc] = true, [ 0xfddd] = true,
[ 0xfdde] = true, [ 0xfddf] = true,
[ 0xfde0] = true, [ 0xfde1] = true,
[ 0xfde2] = true, [ 0xfde3] = true,
[ 0xfde4] = true, [ 0xfde5] = true,
[ 0xfde6] = true, [ 0xfde7] = true,
[ 0xfde8] = true, [ 0xfde9] = true,
[ 0xfdea] = true, [ 0xfdeb] = true,
[ 0xfdec] = true, [ 0xfded] = true,
[ 0xfdee] = true, [ 0xfdef] = true,
[ 0xfffe] = true, [ 0xffff] = true,
[ 0x1fffe] = true, [ 0x1ffff] = true,
[ 0x2fffe] = true, [ 0x2ffff] = true,
[ 0x3fffe] = true, [ 0x3ffff] = true,
[ 0x4fffe] = true, [ 0x4ffff] = true,
[ 0x5fffe] = true, [ 0x5ffff] = true,
[ 0x6fffe] = true, [ 0x6ffff] = true,
[ 0x7fffe] = true, [ 0x7ffff] = true,
[ 0x8fffe] = true, [ 0x8ffff] = true,
[ 0x9fffe] = true, [ 0x9ffff] = true,
[ 0xafffe] = true, [ 0xaffff] = true,
[ 0xbfffe] = true, [ 0xbffff] = true,
[ 0xcfffe] = true, [ 0xcffff] = true,
[ 0xdfffe] = true, [ 0xdffff] = true,
[ 0xefffe] = true, [ 0xeffff] = true,
[ 0xffffe] = true, [ 0xfffff] = true,
[0x10fffe] = true, [0x10ffff] = true
}
local name_range_cache
function export.lookup_name(codepoint)
if noncharacters[codepoint] then
return ("<noncharacter-%.4X>"):format(codepoint)
end
if name_range_cache then
if (codepoint >= name_range_cache[1]) and (codepoint <= name_range_cache[2]) then
if type(name_range_cache[3]) == "string" then
return name_range_cache[3]:format(codepoint)
else
return name_range_cache[3](codepoint)
end
end
end
for _, item in ipairs(name_hooks) do
if (codepoint >= item[1]) and (codepoint <= item[2]) then
name_range_cache = item
if type(item[3]) == "string" then
return item[3]:format(codepoint)
else
return item[3](codepoint)
end
elseif codepoint < item[1] then
break
end
end
local success, data = pcall(mw.loadData,
('Module:Unicode data/names/%03X'):format(
math.floor(codepoint / 0x1000)
)
)
return (success and data[codepoint]) or ("<U-%06X>"):format(codepoint)
end
function export.template_lookup_name(frame)
local codepoint = tonumber(frame.args[1] or frame:getParent().args[1])
local name = export.lookup_name(codepoint)
return name:gsub("<", "<")
end
local planes = {
[ 0] = "Basic Multilingual Plane";
[ 1] = "Supplementary Multilingual Plane";
[ 2] = "Supplementary Ideographic Plane";
[13] = "Supplementary Special-purpose Plane";
[14] = "Supplementary Private Use Area-A";
[15] = "Supplementary Private Use Area-B";
}
-- http://www.unicode.org/Public/UNIDATA/Blocks.txt
local blocks = {
["Basic Latin" ] = { 0x000000, 0x00007f };
["Latin-1 Supplement" ] = { 0x000080, 0x0000ff };
["Latin Extended-A" ] = { 0x000100, 0x00017f };
["Latin Extended-B" ] = { 0x000180, 0x00024f };
["IPA Extensions" ] = { 0x000250, 0x0002af };
["Spacing Modifier Letters" ] = { 0x0002b0, 0x0002ff };
["Combining Diacritical Marks" ] = { 0x000300, 0x00036f };
["Greek and Coptic" ] = { 0x000370, 0x0003ff };
["Cyrillic" ] = { 0x000400, 0x0004ff };
["Cyrillic Supplement" ] = { 0x000500, 0x00052f };
["Armenian" ] = { 0x000530, 0x00058f };
["Hebrew" ] = { 0x000590, 0x0005ff };
["Arabic" ] = { 0x000600, 0x0006ff };
["Syriac" ] = { 0x000700, 0x00074f };
["Arabic Supplement" ] = { 0x000750, 0x00077f };
["Thaana" ] = { 0x000780, 0x0007bf };
["NKo" ] = { 0x0007c0, 0x0007ff };
["Samaritan" ] = { 0x000800, 0x00083f };
["Mandaic" ] = { 0x000840, 0x00085f };
["Arabic Extended-A" ] = { 0x0008a0, 0x0008ff };
["Devanagari" ] = { 0x000900, 0x00097f };
["Bengali" ] = { 0x000980, 0x0009ff };
["Gurmukhi" ] = { 0x000a00, 0x000a7f };
["Gujarati" ] = { 0x000a80, 0x000aff };
["Oriya" ] = { 0x000b00, 0x000b7f };
["Tamil" ] = { 0x000b80, 0x000bff };
["Telugu" ] = { 0x000c00, 0x000c7f };
["Kannada" ] = { 0x000c80, 0x000cff };
["Malayalam" ] = { 0x000d00, 0x000d7f };
["Sinhala" ] = { 0x000d80, 0x000dff };
["សៀម" ] = { 0x000e00, 0x000e7f };
["Lao" ] = { 0x000e80, 0x000eff };
["Tibetan" ] = { 0x000f00, 0x000fff };
["Myanmar" ] = { 0x001000, 0x00109f };
["Georgian" ] = { 0x0010a0, 0x0010ff };
["Hangul Jamo" ] = { 0x001100, 0x0011ff };
["Ethiopic" ] = { 0x001200, 0x00137f };
["Ethiopic Supplement" ] = { 0x001380, 0x00139f };
["Cherokee" ] = { 0x0013a0, 0x0013ff };
["Unified Canadian Aboriginal Syllabics" ] = { 0x001400, 0x00167f };
["Ogham" ] = { 0x001680, 0x00169f };
["Runic" ] = { 0x0016a0, 0x0016ff };
["Tagalog" ] = { 0x001700, 0x00171f };
["Hanunoo" ] = { 0x001720, 0x00173f };
["Buhid" ] = { 0x001740, 0x00175f };
["Tagbanwa" ] = { 0x001760, 0x00177f };
["ខ្មែរ" ] = { 0x001780, 0x0017ff };
["Mongolian" ] = { 0x001800, 0x0018af };
["Unified Canadian Aboriginal Syllabics Extended" ] = { 0x0018b0, 0x0018ff };
["Limbu" ] = { 0x001900, 0x00194f };
["Tai Le" ] = { 0x001950, 0x00197f };
["New Tai Lue" ] = { 0x001980, 0x0019df };
["Khmer Symbols" ] = { 0x0019e0, 0x0019ff };
["Buginese" ] = { 0x001a00, 0x001a1f };
["Tai Tham" ] = { 0x001a20, 0x001aaf };
["Combining Diacritical Marks Extended" ] = { 0x001ab0, 0x001aff };
["Balinese" ] = { 0x001b00, 0x001b7f };
["Sundanese" ] = { 0x001b80, 0x001bbf };
["Batak" ] = { 0x001bc0, 0x001bff };
["Lepcha" ] = { 0x001c00, 0x001c4f };
["Ol Chiki" ] = { 0x001c50, 0x001c7f };
["Cyrillic Extended-C" ] = { 0x001c80, 0x001c8f };
["Sundanese Supplement" ] = { 0x001cc0, 0x001ccf };
["Vedic Extensions" ] = { 0x001cd0, 0x001cff };
["Phonetic Extensions" ] = { 0x001d00, 0x001d7f };
["Phonetic Extensions Supplement" ] = { 0x001d80, 0x001dbf };
["Combining Diacritical Marks Supplement" ] = { 0x001dc0, 0x001dff };
["Latin Extended Additional" ] = { 0x001e00, 0x001eff };
["Greek Extended" ] = { 0x001f00, 0x001fff };
["General Punctuation" ] = { 0x002000, 0x00206f };
["Superscripts and Subscripts" ] = { 0x002070, 0x00209f };
["Currency Symbols" ] = { 0x0020a0, 0x0020cf };
["Combining Diacritical Marks for Symbols" ] = { 0x0020d0, 0x0020ff };
["Letterlike Symbols" ] = { 0x002100, 0x00214f };
["Number Forms" ] = { 0x002150, 0x00218f };
["Arrows" ] = { 0x002190, 0x0021ff };
["Mathematical Operators" ] = { 0x002200, 0x0022ff };
["Miscellaneous Technical" ] = { 0x002300, 0x0023ff };
["Control Pictures" ] = { 0x002400, 0x00243f };
["Optical Character Recognition" ] = { 0x002440, 0x00245f };
["Enclosed Alphanumerics" ] = { 0x002460, 0x0024ff };
["Box Drawing" ] = { 0x002500, 0x00257f };
["Block Elements" ] = { 0x002580, 0x00259f };
["Geometric Shapes" ] = { 0x0025a0, 0x0025ff };
["Miscellaneous Symbols" ] = { 0x002600, 0x0026ff };
["Dingbats" ] = { 0x002700, 0x0027bf };
["Miscellaneous Mathematical Symbols-A" ] = { 0x0027c0, 0x0027ef };
["Supplemental Arrows-A" ] = { 0x0027f0, 0x0027ff };
["Braille Patterns" ] = { 0x002800, 0x0028ff };
["Supplemental Arrows-B" ] = { 0x002900, 0x00297f };
["Miscellaneous Mathematical Symbols-B" ] = { 0x002980, 0x0029ff };
["Supplemental Mathematical Operators" ] = { 0x002a00, 0x002aff };
["Miscellaneous Symbols and Arrows" ] = { 0x002b00, 0x002bff };
["Glagolitic" ] = { 0x002c00, 0x002c5f };
["Latin Extended-C" ] = { 0x002c60, 0x002c7f };
["Coptic" ] = { 0x002c80, 0x002cff };
["Georgian Supplement" ] = { 0x002d00, 0x002d2f };
["Tifinagh" ] = { 0x002d30, 0x002d7f };
["Ethiopic Extended" ] = { 0x002d80, 0x002ddf };
["Cyrillic Extended-A" ] = { 0x002de0, 0x002dff };
["Supplemental Punctuation" ] = { 0x002e00, 0x002e7f };
["CJK Radicals Supplement" ] = { 0x002e80, 0x002eff };
["Kangxi Radicals" ] = { 0x002f00, 0x002fdf };
["Ideographic Description Characters" ] = { 0x002ff0, 0x002fff };
["CJK Symbols and Punctuation" ] = { 0x003000, 0x00303f };
["Hiragana" ] = { 0x003040, 0x00309f };
["Katakana" ] = { 0x0030a0, 0x0030ff };
["Bopomofo" ] = { 0x003100, 0x00312f };
["Hangul Compatibility Jamo" ] = { 0x003130, 0x00318f };
["Kanbun" ] = { 0x003190, 0x00319f };
["Bopomofo Extended" ] = { 0x0031a0, 0x0031bf };
["CJK Strokes" ] = { 0x0031c0, 0x0031ef };
["Katakana Phonetic Extensions" ] = { 0x0031f0, 0x0031ff };
["Enclosed CJK Letters and Months" ] = { 0x003200, 0x0032ff };
["CJK Compatibility" ] = { 0x003300, 0x0033ff };
["CJK Unified Ideographs Extension A" ] = { 0x003400, 0x004dbf };
["Yijing Hexagram Symbols" ] = { 0x004dc0, 0x004dff };
["CJK Unified Ideographs" ] = { 0x004e00, 0x009fff };
["Yi Syllables" ] = { 0x00a000, 0x00a48f };
["Yi Radicals" ] = { 0x00a490, 0x00a4cf };
["Lisu" ] = { 0x00a4d0, 0x00a4ff };
["Vai" ] = { 0x00a500, 0x00a63f };
["Cyrillic Extended-B" ] = { 0x00a640, 0x00a69f };
["Bamum" ] = { 0x00a6a0, 0x00a6ff };
["Modifier Tone Letters" ] = { 0x00a700, 0x00a71f };
["Latin Extended-D" ] = { 0x00a720, 0x00a7ff };
["Syloti Nagri" ] = { 0x00a800, 0x00a82f };
["Common Indic Number Forms" ] = { 0x00a830, 0x00a83f };
["Phags-pa" ] = { 0x00a840, 0x00a87f };
["Saurashtra" ] = { 0x00a880, 0x00a8df };
["Devanagari Extended" ] = { 0x00a8e0, 0x00a8ff };
["Kayah Li" ] = { 0x00a900, 0x00a92f };
["Rejang" ] = { 0x00a930, 0x00a95f };
["Hangul Jamo Extended-A" ] = { 0x00a960, 0x00a97f };
["Javanese" ] = { 0x00a980, 0x00a9df };
["Myanmar Extended-B" ] = { 0x00a9e0, 0x00a9ff };
["Cham" ] = { 0x00aa00, 0x00aa5f };
["Myanmar Extended-A" ] = { 0x00aa60, 0x00aa7f };
["Tai Viet" ] = { 0x00aa80, 0x00aadf };
["Meetei Mayek Extensions" ] = { 0x00aae0, 0x00aaff };
["Ethiopic Extended-A" ] = { 0x00ab00, 0x00ab2f };
["Latin Extended-E" ] = { 0x00ab30, 0x00ab6f };
["Cherokee Supplement" ] = { 0x00ab70, 0x00abbf };
["Meetei Mayek" ] = { 0x00abc0, 0x00abff };
["Hangul Syllables" ] = { 0x00ac00, 0x00d7af };
["Hangul Jamo Extended-B" ] = { 0x00d7b0, 0x00d7ff };
["High Surrogates" ] = { 0x00d800, 0x00db7f };
["High Private Use Surrogates" ] = { 0x00db80, 0x00dbff };
["Low Surrogates" ] = { 0x00dc00, 0x00dfff };
["Private Use Area" ] = { 0x00e000, 0x00f8ff };
["CJK Compatibility Ideographs" ] = { 0x00f900, 0x00faff };
["Alphabetic Presentation Forms" ] = { 0x00fb00, 0x00fb4f };
["Arabic Presentation Forms-A" ] = { 0x00fb50, 0x00fdff };
["Variation Selectors" ] = { 0x00fe00, 0x00fe0f };
["Vertical Forms" ] = { 0x00fe10, 0x00fe1f };
["Combining Half Marks" ] = { 0x00fe20, 0x00fe2f };
["CJK Compatibility Forms" ] = { 0x00fe30, 0x00fe4f };
["Small Form Variants" ] = { 0x00fe50, 0x00fe6f };
["Arabic Presentation Forms-B" ] = { 0x00fe70, 0x00feff };
["Halfwidth and Fullwidth Forms" ] = { 0x00ff00, 0x00ffef };
["Specials" ] = { 0x00fff0, 0x00ffff };
["Linear B Syllabary" ] = { 0x010000, 0x01007f };
["Linear B Ideograms" ] = { 0x010080, 0x0100ff };
["Aegean Numbers" ] = { 0x010100, 0x01013f };
["Ancient Greek Numbers" ] = { 0x010140, 0x01018f };
["Ancient Symbols" ] = { 0x010190, 0x0101cf };
["Phaistos Disc" ] = { 0x0101d0, 0x0101ff };
["Lycian" ] = { 0x010280, 0x01029f };
["Carian" ] = { 0x0102a0, 0x0102df };
["Coptic Epact Numbers" ] = { 0x0102e0, 0x0102ff };
["Old Italic" ] = { 0x010300, 0x01032f };
["Gothic" ] = { 0x010330, 0x01034f };
["Old Permic" ] = { 0x010350, 0x01037f };
["Ugaritic" ] = { 0x010380, 0x01039f };
["Old Persian" ] = { 0x0103a0, 0x0103df };
["Deseret" ] = { 0x010400, 0x01044f };
["Shavian" ] = { 0x010450, 0x01047f };
["Osmanya" ] = { 0x010480, 0x0104af };
["Osage" ] = { 0x0104b0, 0x0104ff };
["Elbasan" ] = { 0x010500, 0x01052f };
["Caucasian Albanian" ] = { 0x010530, 0x01056f };
["Linear A" ] = { 0x010600, 0x01077f };
["Cypriot Syllabary" ] = { 0x010800, 0x01083f };
["Imperial Aramaic" ] = { 0x010840, 0x01085f };
["Palmyrene" ] = { 0x010860, 0x01087f };
["Nabataean" ] = { 0x010880, 0x0108af };
["Hatran" ] = { 0x0108e0, 0x0108ff };
["Phoenician" ] = { 0x010900, 0x01091f };
["Lydian" ] = { 0x010920, 0x01093f };
["Meroitic Hieroglyphs" ] = { 0x010980, 0x01099f };
["Meroitic Cursive" ] = { 0x0109a0, 0x0109ff };
["Kharoshthi" ] = { 0x010a00, 0x010a5f };
["Old South Arabian" ] = { 0x010a60, 0x010a7f };
["Old North Arabian" ] = { 0x010a80, 0x010a9f };
["Manichaean" ] = { 0x010ac0, 0x010aff };
["Avestan" ] = { 0x010b00, 0x010b3f };
["Inscriptional Parthian" ] = { 0x010b40, 0x010b5f };
["Inscriptional Pahlavi" ] = { 0x010b60, 0x010b7f };
["Psalter Pahlavi" ] = { 0x010b80, 0x010baf };
["Old Turkic" ] = { 0x010c00, 0x010c4f };
["Old Hungarian" ] = { 0x010c80, 0x010cff };
["Rumi Numeral Symbols" ] = { 0x010e60, 0x010e7f };
["Brahmi" ] = { 0x011000, 0x01107f };
["Kaithi" ] = { 0x011080, 0x0110cf };
["Sora Sompeng" ] = { 0x0110d0, 0x0110ff };
["Chakma" ] = { 0x011100, 0x01114f };
["Mahajani" ] = { 0x011150, 0x01117f };
["Sharada" ] = { 0x011180, 0x0111df };
["Sinhala Archaic Numbers" ] = { 0x0111e0, 0x0111ff };
["Khojki" ] = { 0x011200, 0x01124f };
["Multani" ] = { 0x011280, 0x0112af };
["Khudawadi" ] = { 0x0112b0, 0x0112ff };
["Grantha" ] = { 0x011300, 0x01137f };
["Newa" ] = { 0x011400, 0x01147f };
["Tirhuta" ] = { 0x011480, 0x0114df };
["Siddham" ] = { 0x011580, 0x0115ff };
["Modi" ] = { 0x011600, 0x01165f };
["Mongolian Supplement" ] = { 0x011660, 0x01167f };
["Takri" ] = { 0x011680, 0x0116cf };
["Ahom" ] = { 0x011700, 0x01173f };
["Warang Citi" ] = { 0x0118a0, 0x0118ff };
["Pau Cin Hau" ] = { 0x011ac0, 0x011aff };
["Bhaiksuki" ] = { 0x011c00, 0x011c6f };
["Marchen" ] = { 0x011c70, 0x011cbf };
["Cuneiform" ] = { 0x012000, 0x0123ff };
["Cuneiform Numbers and Punctuation" ] = { 0x012400, 0x01247f };
["Early Dynastic Cuneiform" ] = { 0x012480, 0x01254f };
["Egyptian Hieroglyphs" ] = { 0x013000, 0x01342f };
["Anatolian Hieroglyphs" ] = { 0x014400, 0x01467f };
["Bamum Supplement" ] = { 0x016800, 0x016a3f };
["Mro" ] = { 0x016a40, 0x016a6f };
["Bassa Vah" ] = { 0x016ad0, 0x016aff };
["Pahawh Hmong" ] = { 0x016b00, 0x016b8f };
["Miao" ] = { 0x016f00, 0x016f9f };
["Ideographic Symbols and Punctuation" ] = { 0x016fe0, 0x016fff };
["Tangut" ] = { 0x017000, 0x0187ec };
["Tangut Components" ] = { 0x018800, 0x018aff };
["Kana Supplement" ] = { 0x01b000, 0x01b0ff };
["Duployan" ] = { 0x01bc00, 0x01bc9f };
["Shorthand Format Controls" ] = { 0x01bca0, 0x01bcaf };
["Byzantine Musical Symbols" ] = { 0x01d000, 0x01d0ff };
["Musical Symbols" ] = { 0x01d100, 0x01d1ff };
["Ancient Greek Musical Notation" ] = { 0x01d200, 0x01d24f };
["Tai Xuan Jing Symbols" ] = { 0x01d300, 0x01d35f };
["Counting Rod Numerals" ] = { 0x01d360, 0x01d37f };
["Mathematical Alphanumeric Symbols" ] = { 0x01d400, 0x01d7ff };
["Sutton SignWriting" ] = { 0x01d800, 0x01daaf };
["Glagolitic Supplement" ] = { 0x01e000, 0x01e02f };
["Mende Kikakui" ] = { 0x01e800, 0x01e8df };
["Adlam" ] = { 0x01e900, 0x01e95f };
["Arabic Mathematical Alphabetic Symbols" ] = { 0x01ee00, 0x01eeff };
["Mahjong Tiles" ] = { 0x01f000, 0x01f02f };
["Domino Tiles" ] = { 0x01f030, 0x01f09f };
["Playing Cards" ] = { 0x01f0a0, 0x01f0ff };
["Enclosed Alphanumeric Supplement" ] = { 0x01f100, 0x01f1ff };
["Enclosed Ideographic Supplement" ] = { 0x01f200, 0x01f2ff };
["Miscellaneous Symbols and Pictographs" ] = { 0x01f300, 0x01f5ff };
["Emoticons" ] = { 0x01f600, 0x01f64f };
["Ornamental Dingbats" ] = { 0x01f650, 0x01f67f };
["Transport and Map Symbols" ] = { 0x01f680, 0x01f6ff };
["Alchemical Symbols" ] = { 0x01f700, 0x01f77f };
["Geometric Shapes Extended" ] = { 0x01f780, 0x01f7ff };
["Supplemental Arrows-C" ] = { 0x01f800, 0x01f8ff };
["Supplemental Symbols and Pictographs" ] = { 0x01f900, 0x01f9ff };
["CJK Unified Ideographs Extension B" ] = { 0x020000, 0x02a6df };
["CJK Unified Ideographs Extension C" ] = { 0x02a700, 0x02b73f };
["CJK Unified Ideographs Extension D" ] = { 0x02b740, 0x02b81f };
["CJK Unified Ideographs Extension E" ] = { 0x02b820, 0x02ceaf };
["CJK Compatibility Ideographs Supplement" ] = { 0x02f800, 0x02fa1f };
["Tags" ] = { 0x0e0000, 0x0e007f };
["Variation Selectors Supplement" ] = { 0x0e0100, 0x0e01ef };
["Supplementary Private Use Area-A" ] = { 0x0f0000, 0x0fffff };
["Supplementary Private Use Area-B" ] = { 0x100000, 0x10ffff };
}
function export.enum_blocks()
local list = {}
for name, range in pairs(blocks) do
table.insert(list, { name, range[1], range[2] })
end
table.sort(list, function (apple, orange)
return apple[2] < orange[2]
end)
return function (list, i)
local data = list[i + 1]
if not data then
return nil
end
return i + 1, data[1], data[2], data[3]
end, list, 0
end
function export.lookup_plane(codepoint)
local i = math.floor(codepoint / 0x10000)
return planes[i] or ("Plane %u"):format(i)
end
function export.lookup_block(codepoint)
for name, range in pairs(blocks) do
if (codepoint >= range[1]) and (codepoint <= range[2]) then
return name
end
end
end
function export.get_block_range(name)
local range = blocks[name]
if range then
return range[1], range[2]
end
end
function export.is_valid_pagename(pagename)
local has_nonws = false
for cp in mw.ustring.gcodepoint(pagename) do
if false
or (cp == 0x0023) -- #
or (cp == 0x005b) -- [
or (cp == 0x005d) -- ]
or (cp == 0x007b) -- {
or (cp == 0x007c) -- |
or (cp == 0x007d) -- }
or (cp == 0x180e) -- MONGOLIAN VOWEL SEPARATOR
or ((cp >= 0x2000) and (cp <= 0x200a))
or (cp == 0xfffd) -- REPLACEMENT CHARACTER
then
return false
end
local printable, result = export.is_printable(cp)
if not printable then
return false
end
if result ~= "space-separator" then
has_nonws = true
end
end
return has_nonws
end
local function manual_unpack(what, from)
local result = {}
from = from or 1
for i, item in ipairs(what) do
if i >= from then
table.insert(result, item)
end
end
return unpack(result)
end
local function memo_lookup(loader, match_func, ...)
local dots = { ... }
local cache = {}
local singles, ranges
return function (codepoint)
if not singles then
singles, ranges = loader()
end
if singles[codepoint] then
return match_func(codepoint, singles[codepoint])
end
local lastlast = -1
for _, range in pairs(cache) do
if (range[1] <= codepoint) and (codepoint <= range[2]) then
return match_func(codepoint, unpack(range, 3))
end
end
for _, range in pairs(ranges) do
if (range[1] <= codepoint) and (codepoint <= range[2]) then
table.insert(cache, { manual_unpack(range) })
return match_func(codepoint, manual_unpack(range, 3))
elseif codepoint < range[1] then
table.insert(cache, { lastlast + 1, range[1] - 1, unpack(dots) })
return match_func(codepoint, unpack(dots))
else
lastlast = range[2]
end
end
return match_func(codepoint)
end
end
export.is_combining = memo_lookup(function ()
local m_comb = mw.loadData('Module:Unicode data/combining')
return m_comb.single, m_comb.ranges
end, function (codepoint, cc)
return cc and (cc ~= 0)
end, 0)
local lookup_control = memo_lookup(function ()
local m_cc = mw.loadData('Module:Unicode data/control')
return m_cc.single, m_cc.ranges
end, function (codepoint, ccc)
return ccc or "assigned"
end, "assigned")
function export.is_assigned(codepoint)
return lookup_control(codepoint) ~= "មិនទាន់ចែង"
end
function export.is_printable(codepoint)
local result = lookup_control(codepoint)
return (result == "assigned") or (result == "space-separator"), result
end
function export.is_whitespace(codepoint)
local result = lookup_control(codepoint)
return (result == "space-separator"), result
end
-- to be used in language-neutral context only (e.g. character lists)
local script_pats
local script_blacklist = {
["Latf"] = true;
["Hans"] = true;
["Hant"] = true;
["Kore"] = true;
["Jpan"] = true;
}
local script_cache = {}
function export.get_script(codepoint)
local text = mw.ustring.char(codepoint)
for pat, sc in pairs(script_cache) do
if mw.ustring.match(text, pat) then
return sc
end
end
if not script_pats then
local m_scripts = mw.loadData("Module:scripts/data")
script_pats = {}
for sc, info in pairs(m_scripts) do
if info.characters and not script_blacklist[sc] then
script_pats[sc] = "[" .. info.characters .. "]"
end
end
end
for sc, pat in pairs(script_pats) do
if mw.ustring.match(text, pat) then
script_cache[pat] = sc
return sc
end
end
return "Zyyy"
end
local unsupported_title = {
[0x0020] = "Unsupported titles/Space";
[0x0023] = "Unsupported titles/Number sign";
[0x002e] = "Unsupported titles/Full stop";
[0x003a] = "Unsupported titles/Colon";
[0x003c] = "Unsupported titles/Less than";
[0x003e] = "Unsupported titles/Greater than";
[0x005b] = "Unsupported titles/Left square bracket";
[0x005d] = "Unsupported titles/Right square bracket";
[0x005f] = "Unsupported titles/Low line";
[0x007b] = "Unsupported titles/Left curly bracket";
[0x007c] = "Unsupported titles/Vertical line";
[0x007d] = "Unsupported titles/Right curly bracket";
[0x1680] = "Unsupported titles/Ogham space";
[0xfffd] = "Unsupported titles/Replacement character";
}
function export.get_entry_title(codepoint)
if unsupported_title[codepoint] then
return unsupported_title[codepoint]
end
if lookup_control(codepoint) ~= "assigned" then
return nil
end
return mw.ustring.char(codepoint)
end
return export