Mòideal:Language/data/ISO 639 name to code/make
Coltas
(deasbaireachd⧼tpt-languages-separator⧽ ⧼tpt-languages-separator⧽eachdraidh⧼tpt-languages-separator⧽ceanglaichean⧼tpt-languages-separator⧽doc⧼tpt-languages-separator⧽bogsa-gainmhich⧼tpt-languages-separator⧽cùisean deuchainn)
This module is currently protected from editing. See the protection policy and protection log for more details. Please discuss any changes on the talk page; you may submit an edit request to ask an administrator to make an edit if it is uncontroversial or supported by consensus. You may also request that this page be unprotected. |
This module is subject to page protection. It is a highly visible module in use by a very large number of pages, or is substituted very frequently. Because vandalism or mistakes would affect many pages, and even trivial editing might cause substantial load on the servers, it is protected from editing. |
{{Module rating }}
Ùsaid - Usage
{{#invoke:Language/data/ISO 639 name to code|function_name}}
require('Module:No globals');
local temp = {};
--[[--------------------------< A D D _ L A N G >--------------------------------------------------------------
temp table is a table of tables where the key is the language name and the value is a 3-element table listing
the ISO 639 codes associated with that language name.
This function adds language name (as index) and its code (as a table element) to the appropriate place in the temp table.
lang is the language name from the source data
code is the associated ISO 639 code from the source data
part is 1 for ISO 639-1 language names and codes, 2 ..., 3 ..., 5 ... Note that part 5 codes go in index [4]
This function does not create alias entries in temp table for those language names that use characters with diacritics.
To do so risks conflict between names that do not use diacritics (Bari, code bfa) and names that do (Barí, code mot).
]]
local function lang_add (lang, code, part)
local count;
if 5 == part then
part = 4; -- there is no current 639-4 map part 5 codes into temp[lang][4]
end
lang = mw.ustring.lower (lang); -- convert to lowercase for use as table index
if not temp[lang] then -- when no entry for this language
temp[lang] = {'""', '""', '""', '""'}; -- make a blank entry
end
temp[lang][part] = table.concat ({'"', code, '"'}); -- add the code
end
--[[--------------------------< I S O 6 3 9 _ N A M E _ T O _ C O D E >----------------------------------------
read code-to-name source tables and convert to a name-to-code table.
]]
local function iso_639_name_to_code ()
local out = {};
local part1_data = mw.loadData ('Module:Language/data/iana languages'); -- used only for ISO 639-1 language codes / names
local part2_data = mw.loadData ('Module:Language/data/ISO 639-2'); -- ISO 639-2 language codes / names
local part3_data = mw.loadData ('Module:Language/data/ISO 639-3'); -- ISO 639-3 language codes / names
local part5_data = mw.loadData ('Module:Language/data/ISO 639-5'); -- ISO 639-5 language codes / names
for code, v in pairs (part3_data) do -- start with part 3 because it has the most codes
for _, lang in ipairs (v) do -- code can have multiple names so for each one
lang_add (lang, code, 3); -- create and / or add this name / code pair to the output
end
end
for code, v in pairs (part5_data) do -- now part 5
for _, lang in ipairs (v) do
lang_add (lang, code, 5);
end
end
for code, v in pairs (part2_data) do -- now part 2
for _, lang in ipairs (v) do
lang_add (lang, code, 2);
end
end
for code, v in pairs (part1_data) do -- now part 1
if 2 == #code then -- IANA source data includes a mix of 2- and 3-character codes; ISO 639-1 is the 2-character variety
for _, lang in ipairs (v) do
lang_add (lang, code, 1);
end
end
end
for lang, codes in pairs (temp) do
table.insert (out, table.concat ({'["', lang, '"] = {', table.concat (codes, ', '), '}'})); -- reformat
end
table.sort (out);
return table.concat ({"<pre>return {<br />	", table.concat (out, ',<br />	'), "<br />	}<br /></pre>"}); -- render
end
return {iso_639_name_to_code = iso_639_name_to_code}