Modul:Unicode data
This module is used for accessing the Unicode character database, derived from files found in http://www.unicode.org/Public/UNIDATA/ .
Currently it exports two methods: lookup_name and template_lookup_name. Both, given a Unicode code point number, return the code point's name. The latter is suited for invocation through templates, while the former is intended to be used directly in Lua code.
User:Kephir/Unicode contains scripts which may be helpful in maintaining this database.
Subpage index[ännern]
- Unicode data
- /Doku
- /aliases
- /combining
- /control
- /names/000
- /names/000 nds n
- /names/001
- /names/001 nds n
- /names/002
- /names/002 nds n
- /names/003
- /names/004
- /names/00A
- /names/00D
- /names/00F
- /names/010
- /names/010 nds n
- /names/011
- /names/012
- /names/013
- /names/016
- /names/01B
- /names/01D
- /names/01E
- /names/01F
- /names/0E0
Copyright[ännern]
The Unicode database is released by Unicode Inc. under the following terms:
Copyright © 1991-2013 Unicode, Inc. All rights reserved. Distributed under the Terms of Use in http://www.unicode.org/copyright.html.
Permission is hereby granted, free of charge, to any person obtaining a copy of the Unicode data files and any associated documentation (the "Data Files") or Unicode software and any associated documentation (the "Software") to deal in the Data Files or Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, and/or sell copies of the Data Files or Software, and to permit persons to whom the Data Files or Software are furnished to do so, provided that (a) the above copyright notice(s) and this permission notice appear with all copies of the Data Files or Software, (b) both the above copyright notice(s) and this permission notice appear in associated documentation, and (c) there is clear notice in each modified Data File or in the Software as well as in the documentation associated with the Data File(s) or Software that the data or software has been modified.
THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THE DATA FILES OR SOFTWARE.
Except as contained in this notice, the name of a copyright holder shall not be used in advertising or otherwise to promote the sale, use or other dealings in these Data Files or Software without prior written authorization of the copyright holder.
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, 0x9fcc }] = "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
[{ 0x20000, 0x2a6d6 }] = "CJK UNIFIED IDEOGRAPH-%04X", -- CJK Ideograph Extension B
[{ 0x2a700, 0x2b734 }] = "CJK UNIFIED IDEOGRAPH-%04X", -- CJK Ideograph Extension C
[{ 0x2a740, 0x2b81d }] = "CJK UNIFIED IDEOGRAPH-%04X", -- CJK Ideograph Extension D
[{ 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
}
function export.lookup_name(codepoint)
if noncharacters[codepoint] then
return ("<noncharacter-%.4X>"):format(codepoint)
end
for key, hook in pairs(name_hooks) do
if (codepoint >= key[1]) and (codepoint <= key[2]) then
if type(hook) == "string" then
return hook:format(codepoint)
else
return hook(codepoint)
end
end
end
local success, data = pcall(mw.loadData,
('Module:Unicode data/names/%03X'):format(
math.floor(codepoint / 0x1000)
)
)
if success then
return data[codepoint] or ("<U-%06X>"):format(codepoint)
else
return ("<U-%06X>"):format(codepoint)
end
end
function export.lookup_name_nds_n(codepoint)
if noncharacters[codepoint] then
return ("<noncharacter-%.4X>"):format(codepoint)
end
for key, hook in pairs(name_hooks) do
if (codepoint >= key[1]) and (codepoint <= key[2]) then
if type(hook) == "string" then
return hook:format(codepoint)
else
return hook(codepoint)
end
end
end
local success, data = pcall(mw.loadData,
('Module:Unicode data/names/%03X nds n'):format(
math.floor(codepoint / 0x1000)
)
)
if success then
return data[codepoint] or ("<U-%06X>"):format(codepoint)
else
return ("<U-%06X>"):format(codepoint)
end
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 = {
["Basislatiensch" ] = { 0x000000, 0x00007f };
["Latiensch-1 Ergänzen" ] = { 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 };
["Greeksch un Koptsch" ] = { 0x000370, 0x0003ff };
["Kyrillsch" ] = { 0x000400, 0x0004ff };
["Kyrillsch Ergänzen" ] = { 0x000500, 0x00052f };
["Armeensch" ] = { 0x000530, 0x00058f };
["Hebrääsch" ] = { 0x000590, 0x0005ff };
["Araabsch" ] = { 0x000600, 0x0006ff };
["Syriac" ] = { 0x000700, 0x00074f };
["Araabsch Ergänzen" ] = { 0x000750, 0x00077f };
["Thaana" ] = { 0x000780, 0x0007bf };
["NKo" ] = { 0x0007c0, 0x0007ff };
["Samaritaansch" ] = { 0x000800, 0x00083f };
["Mandaic" ] = { 0x000840, 0x00085f };
["Arabic Extended-A" ] = { 0x0008a0, 0x0008ff };
["Devanagari" ] = { 0x000900, 0x00097f };
["Bengaalsch" ] = { 0x000980, 0x0009ff };
["Gurmukhi" ] = { 0x000a00, 0x000a7f };
["Gujarati" ] = { 0x000a80, 0x000aff };
["Oriya" ] = { 0x000b00, 0x000b7f };
["Tamiilsch" ] = { 0x000b80, 0x000bff };
["Telugu" ] = { 0x000c00, 0x000c7f };
["Kannada" ] = { 0x000c80, 0x000cff };
["Malayalam" ] = { 0x000d00, 0x000d7f };
["Sinhala" ] = { 0x000d80, 0x000dff };
["Thai" ] = { 0x000e00, 0x000e7f };
["Laootsch" ] = { 0x000e80, 0x000eff };
["Tibeetsch" ] = { 0x000f00, 0x000fff };
["Myanmar" ] = { 0x001000, 0x00109f };
["Georgsch" ] = { 0x0010a0, 0x0010ff };
["Hangul Jamo" ] = { 0x001100, 0x0011ff };
["Äthiopsch" ] = { 0x001200, 0x00137f };
["Äthiopsch Ergänzen" ] = { 0x001380, 0x00139f };
["Cherokee" ] = { 0x0013a0, 0x0013ff };
["Unified Canadian Aboriginal Syllabics" ] = { 0x001400, 0x00167f };
["Ogham" ] = { 0x001680, 0x00169f };
["Runsch" ] = { 0x0016a0, 0x0016ff };
["Tagalog" ] = { 0x001700, 0x00171f };
["Hanunoo" ] = { 0x001720, 0x00173f };
["Buhid" ] = { 0x001740, 0x00175f };
["Tagbanwa" ] = { 0x001760, 0x00177f };
["Khmer" ] = { 0x001780, 0x0017ff };
["Mongoolsch" ] = { 0x001800, 0x0018af };
["Unified Canadian Aboriginal Syllabics Extended" ] = { 0x0018b0, 0x0018ff };
["Limbu" ] = { 0x001900, 0x00194f };
["Tai Le" ] = { 0x001950, 0x00197f };
["New Tai Lue" ] = { 0x001980, 0x0019df };
["Khmer Symbolen" ] = { 0x0019e0, 0x0019ff };
["Bugineesch" ] = { 0x001a00, 0x001a1f };
["Tai Tham" ] = { 0x001a20, 0x001aaf };
["Combining Diacritical Marks Extended" ] = { 0x001ab0, 0x001aff };
["Balineesch" ] = { 0x001b00, 0x001b7f };
["Sundaneesch" ] = { 0x001b80, 0x001bbf };
["Batak" ] = { 0x001bc0, 0x001bff };
["Lepcha" ] = { 0x001c00, 0x001c4f };
["Ol Chiki" ] = { 0x001c50, 0x001c7f };
["Sundaneesch Ergänzen" ] = { 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 };
["Koptsch" ] = { 0x002c80, 0x002cff };
["Georgsch Ergänzen" ] = { 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 };
["Javaneesch" ] = { 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 };
["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 Sülvenschrift" ] = { 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 };
["Oolditalsch" ] = { 0x010300, 0x01032f };
["Gootsch" ] = { 0x010330, 0x01034f };
["Old Permic" ] = { 0x010350, 0x01037f };
["Ugaritic" ] = { 0x010380, 0x01039f };
["Ooldpers'sch" ] = { 0x0103a0, 0x0103df };
["Deseret" ] = { 0x010400, 0x01044f };
["Shavian" ] = { 0x010450, 0x01047f };
["Osmanya" ] = { 0x010480, 0x0104af };
["Elbasan" ] = { 0x010500, 0x01052f };
["Caucasian Albanian" ] = { 0x010530, 0x01056f };
["Linear A" ] = { 0x010600, 0x01077f };
["Cypriot Syllabary" ] = { 0x010800, 0x01083f };
["Rieksaramääsch" ] = { 0x010840, 0x01085f };
["Palmyrene" ] = { 0x010860, 0x01087f };
["Nabataean" ] = { 0x010880, 0x0108af };
["Phoenician" ] = { 0x010900, 0x01091f };
["Lydian" ] = { 0x010920, 0x01093f };
["Meroitsch Hieroglyphen" ] = { 0x010980, 0x01099f };
["Meroitsch Kursiv" ] = { 0x0109a0, 0x0109ff };
["Kharoshthi" ] = { 0x010a00, 0x010a5f };
["Ooldsüüdaraabsch" ] = { 0x010a60, 0x010a7f };
["Ooldnoordaraabsch" ] = { 0x010a80, 0x010a9f };
["Manichaean" ] = { 0x010ac0, 0x010aff };
["Avestan" ] = { 0x010b00, 0x010b3f };
["Inscriptional Parthian" ] = { 0x010b40, 0x010b5f };
["Inscriptional Pahlavi" ] = { 0x010b60, 0x010b7f };
["Psalter Pahlavi" ] = { 0x010b80, 0x010baf };
["Ooldtörksch" ] = { 0x010c00, 0x010c4f };
["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 };
["Khudawadi" ] = { 0x0112b0, 0x0112ff };
["Grantha" ] = { 0x011300, 0x01137f };
["Tirhuta" ] = { 0x011480, 0x0114df };
["Siddham" ] = { 0x011580, 0x0115ff };
["Modi" ] = { 0x011600, 0x01165f };
["Takri" ] = { 0x011680, 0x0116cf };
["Warang Citi" ] = { 0x0118a0, 0x0118ff };
["Pau Cin Hau" ] = { 0x011ac0, 0x011aff };
["Cuneiform" ] = { 0x012000, 0x0123ff };
["Cuneiform Numbers and Punctuation" ] = { 0x012400, 0x01247f };
["Ägyptsch Hieroglyphen" ] = { 0x013000, 0x01342f };
["Bamum Supplement" ] = { 0x016800, 0x016a3f };
["Mro" ] = { 0x016a40, 0x016a6f };
["Bassa Vah" ] = { 0x016ad0, 0x016aff };
["Pahawh Hmong" ] = { 0x016b00, 0x016b8f };
["Miao" ] = { 0x016f00, 0x016f9f };
["Kana Ergänzen" ] = { 0x01b000, 0x01b0ff };
["Duployan" ] = { 0x01bc00, 0x01bc9f };
["Shorthand Format Controls" ] = { 0x01bca0, 0x01bcaf };
["Byzantiinsch Musiksymbolen" ] = { 0x01d000, 0x01d0ff };
["Musiksymbolen" ] = { 0x01d100, 0x01d1ff };
["Ancient Greek Musical Notation" ] = { 0x01d200, 0x01d24f };
["Tai Xuan Jing Symbols" ] = { 0x01d300, 0x01d35f };
["Counting Rod Numerals" ] = { 0x01d360, 0x01d37f };
["Mathematical Alphanumeric Symbols" ] = { 0x01d400, 0x01d7ff };
["Mende Kikakui" ] = { 0x01e800, 0x01e8df };
["Arabic Mathematical Alphabetic Symbols" ] = { 0x01ee00, 0x01eeff };
["Mahjongstenen" ] = { 0x01f000, 0x01f02f };
["Dominostenen" ] = { 0x01f030, 0x01f09f };
["Speelkoorten" ] = { 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- un Koortensymbolen" ] = { 0x01f680, 0x01f6ff };
["Alchemiesymbolen" ] = { 0x01f700, 0x01f77f };
["Geometric Shapes Extended" ] = { 0x01f780, 0x01f7ff };
["Supplemental Arrows-C" ] = { 0x01f800, 0x01f8ff };
["CJK Unified Ideographs Extension B" ] = { 0x020000, 0x02a6df };
["CJK Unified Ideographs Extension C" ] = { 0x02a700, 0x02b73f };
["CJK Unified Ideographs Extension D" ] = { 0x02b740, 0x02b81f };
["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)
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
if not export.is_printable(cp) then
return false
end
end
return true
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) ~= "unassigned"
end
function export.is_printable(codepoint)
local result = lookup_control(codepoint)
return (result == "assigned"), result
end
return export