imported>Trappist the monk at 19:14, 1 October 2020

2020-10-01T19:14:55Z

New page

p={}
-- crude comparison between the various ISO 639 parts data and iana 2020-09-17
function p.comp ()
local iana = mw.loadData ('Module:Language/data/iana languages/sandbox');
local iso2 = mw.loadData ('Module:Language/data/ISO 639-2')
local iso2B = mw.loadData ('Module:Language/data/ISO 639-2B')
local iso3 = mw.loadData ('Module:Language/data/ISO 639-3');
local dep3 = mw.loadData ('Module:Language/data/ISO 639-3 (dep)');
local iso5 = mw.loadData ('Module:Language/data/ISO 639-5');
local syn = mw.loadData ('Module:Lang/ISO 639 synonyms');
local wp_lang = mw.loadData ('Module:Language/data/wp languages');
local override = mw.loadData ('Module:Lang/data/sandbox').override;

local iso2_not_in_iana = {} -- ISO 639-1 synonymous codes not in iana
local iso2B_not_in_iana = {} -- none of the ISO 639-2B codes in iana
local iso3_not_in_iana = {} -- ISO 639-1 synonymous codes and hbs (Serbo Croatian) not in iana
local dep3_not_in_iana = {} -- none of the deprecated ISO 639-3 codes in iana
local iso5_not_in_iana = {} -- ISO 639-1 synonymous codes not in iana (bih)
local wp_lang_not_in_override = {}

local iana_not_in_iso3 = {}
local iana_dep_not_in_dep3 = {}

for k, v in pairs (iso2) do
if not iana.active[k] then
if not syn[k] then
table.insert (iso2_not_in_iana, k);
end
end
end

for k, v in pairs (iso2B) do
if not iana.active[k] then
table.insert (iso2B_not_in_iana, k);
end
end

for k, v in pairs (iso3) do
if not iana.active[k] then
if not syn[k] then
table.insert (iso3_not_in_iana, k);
end
end
end

for k, v in pairs (dep3) do
if not iana.deprecated[k] then
table.insert (dep3_not_in_iana, k)
end
end

for k, v in pairs (iana.deprecated) do
if not dep3[k] then
table.insert (iana_dep_not_in_dep3, k)
end
end

for k, v in pairs (iso5) do
if not iana.active[k] then
table.insert (iso5_not_in_iana, k);
end
end

for k, v in pairs (iana.active) do
if (3 == k:len()) and not iso3[k] then
table.insert (iana_not_in_iso3, k);
end
end

for k, v in pairs (wp_lang) do
k = k:lower()
--error (mw.dumpObject (iana[k][1]))
if not override[k] then
if iana.active[k] then
table.insert (wp_lang_not_in_override, table.concat ({
k,
': ',
v[1],
'; iana: ',
iana.active[k][1],
}));
else
table.insert (wp_lang_not_in_override, table.concat ({
k,
': ',
v[1],
'; not in iana',
}));
end
-- table.insert (wp_lang_not_in_override, k);
end
end
table.sort (wp_lang_not_in_override)
table.sort (iso2B_not_in_iana)
table.sort (iso3_not_in_iana)
table.sort (dep3_not_in_iana)
table.sort (iana_dep_not_in_dep3)

return 'iso2_not_in_iana:\n' .. mw.dumpObject (iso2_not_in_iana) ..
'\n\niso2B_not_in_iana:\n' .. mw.dumpObject (iso2B_not_in_iana) ..
'\n\niso3_not_in_iana:\n' .. mw.dumpObject (iso3_not_in_iana) ..
'\n\niso5_not_in_iana:\n' .. mw.dumpObject (iso5_not_in_iana) ..
'\n\dep3_not_in_iana:\n' .. mw.dumpObject (dep3_not_in_iana) ..
'\n\iana_dep_not_in_dep3:\n' .. mw.dumpObject (iana_dep_not_in_dep3) ..
'\n\wp_lang_not_in_override:\n' .. mw.dumpObject (wp_lang_not_in_override)
-- return #dep3_not_in_iana, 'dep3_not_in_iana:\n' .. mw.dumpObject (dep3_not_in_iana)

-- return mw.dumpObject (iana_not_in_iso3)
end

----------------------------------------------------

function p.test ()
local langs = mw.language.fetchLanguageNames('en', 'all');
local iws = mw.site.interwikiMap ('local');
local lang_not_in_iw = {};
local iw_is_lang = {}
local iw_is_not_lang = {}
local iw_is_extra_lang = {}

for code, language in pairs (langs) do
if not iws[code] then
lang_not_in_iw[code] = language;
end
end

for k, v in pairs (iws) do
if langs[v["prefix"]] then
iw_is_lang[v["prefix"]] = langs[v["prefix"]];
elseif v.isExtraLanguageLink then
iw_is_extra_lang[v["prefix"]] = v['url'];
else
if v['url']:match ('%.wikipedia%.org') then
iw_is_not_lang[v["prefix"]] = v['url'];
end
end
end

--[[
these are wikipedia language prefixes that seem to be redirects; these do not add to the languages link-list
["cmn"] = "https://zh.wikipedia.org/wiki/$1", -- Mandarin Chinese (ISO 639-3 code)
["cz"] = "https://cs.wikipedia.org/wiki/$1", -- Czech (ISO 3166 country code)
["dk"] = "https://da.wikipedia.org/wiki/$1", -- Danish (ISO 3166 country code)
["epo"] = "https://eo.wikipedia.org/wiki/$1", -- Esperanto (ISO 639-3 code)
["jp"] = "https://ja.wikipedia.org/wiki/$1", -- Japanese (ISO 3166 country code)
["minnan"] = "https://zh-min-nan.wikipedia.org/wiki/$1",
["zh-cfr"] = "https://zh-min-nan.wikipedia.org/wiki/$1",

these are not wikipedia language codes:
["nost"] = "https://nostalgia.wikipedia.org/wiki/$1",
["nostalgia"] = "https://nostalgia.wikipedia.org/wiki/$1",
["sep11"] = "https://sep11.wikipedia.org/wiki/$1",
["tenwiki"] = "https://ten.wikipedia.org/wiki/$1",
["test2wiki"] = "https://test2.wikipedia.org/wiki/$1",
["testwiki"] = "https://test.wikipedia.org/wiki/$1",
["w"] = "https://en.wikipedia.org/wiki/$1",
["wg"] = "https://wg-en.wikipedia.org/wiki/$1",
["wikipedia"] = "https://en.wikipedia.org/wiki/$1",
["wikipediawikipedia"] = "https://en.wikipedia.org/wiki/Wikipedia:$1",
]]

-- return mw.dumpObject (lang_not_in_iw); -- list of lang codes that are not prefixes (there are a lot)
return mw.dumpObject (iw_is_lang); -- list of prefixes that match supported language codes (use this list)
-- return mw.dumpObject (iw_is_not_lang); -- list of prefixes that have wikipedia.org url but prefix isn't found in the langs list
-- return mw.dumpObject (iw_is_extra_lang); -- none are marked with ["isExtraLanguageLink"] = true,
end

function p.format (text)
local str = text:gsub ('%s*=%s*', '='):gsub('%s*|%s*', ' |'); -- uniform spacing
str = str:gsub ('accessdate', 'access-date'):gsub ('archivedate', 'archive-date'); -- hyphenated version
str = str:gsub ('(%a)url', '%1-url'); -- archive, dead, chapter, etc urls to hyphenated versions
str = str:gsub ('|[%a%-]+= +', ''); -- remove empty parameters
str = str:gsub (' +|[%a%-]+=}', '}'); -- remove empty parameter at end of template
str = str:gsub('{%s+', '{'):gsub('%s+}', '}'); -- no spacing
return str;

end

function p.eq (frame)
local ref = frame[1];
local test = frame[2];

if ref == test then
return 'ref == test'
end

local msg;

if ref:len() == test:len() then
msg = 'same length; ';
else
msg = 'diff length; ';
end

local i=1;
while (1) do
local r, t;
r = mw.ustring.codepoint(ref, i);
t = mw.ustring.codepoint(test, i);

if r == t then
i=i+1;
else
return msg .. 'diff @ char: ' .. i .. '; ref: ' .. mw.ustring.char (r) .. '; test: ' .. mw.ustring.char (t);
end
end
return i;
end
return p;

Module:Sandbox/trappist the monk/bob - Revision history

imported>Trappist the monk at 19:14, 1 October 2020