Module:Lang/data/sandbox
< Module:Lang | data
 | This is the module sandbox page for Module:Lang/data (diff). |
 | This Lua module is used on approximately 1,610,000 pages. To avoid major disruption and server load, any changes should be tested in the module's /sandbox or /testcases subpages, or in your own module sandbox. The tested changes can be added to this page in a single edit. Consider discussing changes on the talk page before implementing them. |
 | This module depends on the following other modules: |
This module holds various support tables used by Module:Lang
lang_name_table– this table provides language name data used in the creation of categories and, for the{{lang-??}}templates, the language name annotationoverride– this table overrides data inlang_name_table; commonly used when an en.wiki article title differs from the name for the standard's languagertl_scripts– a list of ISO 15924 scripts that are written right-to-left; data taken from the table at ISO 15924#List of codestranslit_title_table– a table of tables that is used in the creation of thetitle=attribute of the<i>...</i>tags that wrap transliterated text; data adapted from{{transliteration}}article_name– this table overrideslang_name_tableandoverridefor (typically) disambiguated en.wiki article names
--[[--------------------------< L A N G _ N A M E _ T A B L E >------------------------------------------------
primary table of tables that decode:
lang -> language tags and names
lang_dep -> deprecated language tags and names supported by iana (not a complete list of all deprecated ISO 639 tags)
script -> ISO 15924 script tags
region -> ISO 3166 region tags
variant -> iana registered variant tags
suppressed -> map of scripts tags and their associated language tags
all of these data come from separate modules that are derived from the IANA language-subtag-registry file
data_normalize() avoids the metatable trap and sets all keys in the subtables to lowercase. Many language codes
have multiple associated names; Module:lang is only concerned with the first name so data_normalize() only fetches
the first name.
TODO: instead of returning:
["key"] = {"name"}
where each table has only one name, return
["key"] = "name"
requires changes in Module:Lang.
]]
local function data_normalize (module, src_name)
local out = {};
local source = (('variants' == src_name) and require (module)) or mw.loadData (module); -- fetch data from this module; require() avoids metatable trap for variant data
if 'variants' == src_name then
for k, v in pairs (source) do
out[k:lower()] = v; -- for variant, everything is needed
end
elseif src_name then -- when src_name names a subtable in source
for k, v in pairs (source[src_name]) do
out[k:lower()] = {v[1]}; -- ignore multiple names; take first name only
end
else -- here when subtable not named
for k, v in pairs (source) do
out[k:lower()] = {v[1]}; -- ignore multiple names; take first name only
end
end
return out;
end
local lang_name_table = {
lang = data_normalize ('Module:Language/data/iana languages/sandbox', 'active'),
lang_dep = data_normalize ('Module:Language/data/iana languages/sandbox', 'deprecated'),
script = data_normalize ('Module:Language/data/iana scripts'), -- script keys are capitalized; set to lower
region = data_normalize ('Module:Language/data/iana regions'), -- region keys are uppercase; set to lower
variant = data_normalize ('Module:Language/data/iana variants', 'variants'),
suppressed = data_normalize ('Module:Language/data/iana suppressed scripts'), -- script keys are capitalized; set to lower
}
local override = data_normalize ('Module:Language/data/ISO_639_override/sandbox', 'override');
local article_name = data_normalize ('Module:Language/data/ISO_639_override/sandbox', 'article_name');
--[=[-------------------------< R T L _ S C R I P T S >--------------------------------------------------------
ISO 15924 scripts that are written right-to-left. Data in this table taken from [[ISO 15924#List of codes]]
last update to this list: 2017-12-24
]=]
local rtl_scripts = {
'adlm', 'arab', 'aran', 'armi', 'avst', 'cprt', 'egyd', 'egyh', 'hatr', 'hebr',
'hung', 'inds', 'khar', 'lydi', 'mand', 'mani', 'mend', 'merc', 'mero', 'narb',
'nbat', 'nkoo', 'orkh', 'palm', 'phli', 'phlp', 'phlv', 'phnx', 'prti', 'rohg',
'samr', 'sarb', 'sogd', 'sogo', 'syrc', 'syre', 'syrj', 'syrn', 'thaa', 'wole',
};
--[[--------------------------< T R A N S L I T T I T L E S >------------------------------------------------
This is a table of tables of transliteration standards and the language codes or language scripts that apply to
those standards. This table is used to create the tool-tip text associated with the transliterated text displayed
by some of the {{lang-??}} templates.
These tables are more-or-less copied directly from {{transl}}. The standard 'NO_STD' is a construct to allow for
the cases when no |std= parameter value is provided.
]]
local translit_title_table = {
['ahl'] = {
['default'] = 'Academy of the Hebrew Language transliteration',
},
['ala'] = {
['default'] = 'American Library Association – Library of Congress transliteration',
},
['ala-lc'] = {
['default'] = 'American Library Association – Library of Congress transliteration',
},
['batr'] = {
['default'] = 'Bikdash Arabic Transliteration Rules',
},
['bgn/pcgn'] = {
['default'] = 'Board on Geographic Names / Permanent Committee on Geographical Names transliteration',
},
['din'] = {
['ar'] = 'DIN 31635 Arabic',
['fa'] = 'DIN 31635 Arabic',
['ku'] = 'DIN 31635 Arabic',
['ps'] = 'DIN 31635 Arabic',
['tg'] = 'DIN 31635 Arabic',
['ug'] = 'DIN 31635 Arabic',
['ur'] = 'DIN 31635 Arabic',
['arab'] = 'DIN 31635 Arabic',
['default'] = 'DIN transliteration',
},
['eae'] = {
['default'] = 'Encyclopaedia Aethiopica transliteration',
},
['hepburn'] = {
['default'] = 'Hepburn transliteration',
},
['hunterian'] = {
['default'] = 'Hunterian transliteration',
},
['iast'] = {
['default'] = 'International Alphabet of Sanskrit transliteration',
},
['iso'] = { -- when a transliteration standard is supplied
['ab'] = 'ISO 9 Cyrillic',
['ba'] = 'ISO 9 Cyrillic',
['be'] = 'ISO 9 Cyrillic',
['bg'] = 'ISO 9 Cyrillic',
['kk'] = 'ISO 9 Cyrillic',
['ky'] = 'ISO 9 Cyrillic',
['mn'] = 'ISO 9 Cyrillic',
['ru'] = 'ISO 9 Cyrillic',
['tg'] = 'ISO 9 Cyrillic',
['uk'] = 'ISO 9 Cyrillic',
['bua'] = 'ISO 9 Cyrillic',
['sah'] = 'ISO 9 Cyrillic',
['tut'] = 'ISO 9 Cyrillic',
['xal'] = 'ISO 9 Cyrillic',
['cyrl'] = 'ISO 9 Cyrillic',
['ar'] = 'ISO 233 Arabic',
['ku'] = 'ISO 233 Arabic',
['ps'] = 'ISO 233 Arabic',
['ug'] = 'ISO 233 Arabic',
['ur'] = 'ISO 233 Arabic',
['arab'] = 'ISO 233 Arabic',
['he'] = 'ISO 259 Hebrew',
['yi'] = 'ISO 259 Hebrew',
['hebr'] = 'ISO 259 Hebrew',
['el'] = 'ISO 843 Greek',
['grc'] = 'ISO 843 Greek',
['ja'] = 'ISO 3602 Japanese',
['hira'] = 'ISO 3602 Japanese',
['hrkt'] = 'ISO 3602 Japanese',
['jpan'] = 'ISO 3602 Japanese',
['kana'] = 'ISO 3602 Japanese',
['zh'] = 'ISO 7098 Chinese',
['chi'] = 'ISO 7098 Chinese',
['pny'] = 'ISO 7098 Chinese',
['zho'] = 'ISO 7098 Chinese',
-- ['han'] = 'ISO 7098 Chinese', -- unicode alias of Hani? doesn't belong here? should be Hani?
['hans'] = 'ISO 7098 Chinese',
['hant'] = 'ISO 7098 Chinese',
['ka'] = 'ISO 9984 Georgian',
['kat'] = 'ISO 9984 Georgian',
['arm'] = 'ISO 9985 Armenian',
['hy'] = 'ISO 9985 Armenian',
['th'] = 'ISO 11940 Thai',
['tha'] = 'ISO 11940 Thai',
['ko'] = 'ISO 11941 Korean',
['kor'] = 'ISO 11941 Korean',
['awa'] = 'ISO 15919 Indic',
['bho'] = 'ISO 15919 Indic',
['bn'] = 'ISO 15919 Indic',
['bra'] = 'ISO 15919 Indic',
['doi'] = 'ISO 15919 Indic',
['dra'] = 'ISO 15919 Indic',
['gon'] = 'ISO 15919 Indic',
['gu'] = 'ISO 15919 Indic',
['hi'] = 'ISO 15919 Indic',
['inc'] = 'ISO 15919 Indic',
['kn'] = 'ISO 15919 Indic',
['kok'] = 'ISO 15919 Indic',
['ks'] = 'ISO 15919 Indic',
['mag'] = 'ISO 15919 Indic',
['mai'] = 'ISO 15919 Indic',
['ml'] = 'ISO 15919 Indic',
['mr'] = 'ISO 15919 Indic',
['ne'] = 'ISO 15919 Indic',
['new'] = 'ISO 15919 Indic',
['or'] = 'ISO 15919 Indic',
['pa'] = 'ISO 15919 Indic',
['raj'] = 'ISO 15919 Indic',
['sa'] = 'ISO 15919 Indic',
['sat'] = 'ISO 15919 Indic',
['sd'] = 'ISO 15919 Indic',
['si'] = 'ISO 15919 Indic',
['ta'] = 'ISO 15919 Indic',
['tcy'] = 'ISO 15919 Indic',
['te'] = 'ISO 15919 Indic',
['beng'] = 'ISO 15919 Indic',
['brah'] = 'ISO 15919 Indic',
['deva'] = 'ISO 15919 Indic',
['gujr'] = 'ISO 15919 Indic',
['guru'] = 'ISO 15919 Indic',
['knda'] = 'ISO 15919 Indic',
['mlym'] = 'ISO 15919 Indic',
['orya'] = 'ISO 15919 Indic',
['sinh'] = 'ISO 15919 Indic',
['taml'] = 'ISO 15919 Indic',
['telu'] = 'ISO 15919 Indic',
['default'] = 'ISO transliteration',
},
['jyutping'] = {
['default'] = 'Jyutping transliteration',
},
['mr'] = {
['default'] = 'McCune–Reischauer transliteration',
},
['nihon-shiki'] = {
['default'] = 'Nihon-shiki transliteration',
},
['no_std'] = { -- when no transliteration standard is supplied
['akk'] = 'Semitic transliteration',
['sem'] = 'Semitic transliteration',
['phnx'] = 'Semitic transliteration',
['xsux'] = 'Cuneiform transliteration',
},
['pinyin'] = {
['default'] = 'Pinyin transliteration',
},
['rr'] = {
['default'] = 'Revised Romanization of Korean transliteration',
},
['rtgs'] = {
['default'] = 'Royal Thai General System of Transcription',
},
['satts'] = {
['default'] = 'Standard Arabic Technical Transliteration System transliteration',
},
['ungegn'] = {
['default'] = 'United Nations Group of Experts on Geographical Names transliteration',
},
['wadegile'] = {
['default'] = 'Wade–Giles transliteration',
},
['wehr'] = {
['default'] = 'Hans Wehr transliteration',
},
};
return
{
article_name = article_name,
lang_name_table = lang_name_table,
override = override,
rtl_scripts = rtl_scripts,
translit_title_table = translit_title_table,
};