Modulo:łéngua
La documentazione per questo modulo può essere creata in Modulo:łéngua/man
--DA CA.WIKT--
local p = {}
local tola = mw.loadData("Module:łéngua/toła")
local function isSet( var )
return not (var == nil or var == '')
end
--[[extracts and returns IETF language tag parts:
primary language subtag (required) - 2 or 3 character IANA language code
script subtag - four character IANA script code
region subtag - two-letter or three digit IANA region code
variant subtag - four digit or 5-8 alnum variant code; only one variant subtag supported
private subtag - x- followed by 1-8 alnum private code; only supported with the primary language tag
in any one of these forms
lang lang-variant
lang-script lang-script-variant
lang-region lang-region-variant
lang-script-region lang-script-region-variant
lang-x-private
each of lang, script, region, variant, and private, when used, must be valid
Languages with both two- and three-character code synonyms are promoted to the two-character synonym because
the IANA registry file omits the synonymous three-character code; we cannot depend on browsers understanding
the synonymous three-character codes in the lang= attribute.
returns six values; all lower case. Valid parts are returned as themselves; omitted parts are returned as empty strings, invalid
parts are returned as nil; the sixth returned item is an error message (if an error detected) or nil.
see http://www.rfc-editor.org/rfc/bcp/bcp47.txt section 2.1
]]
local function get_ietf_parts(source, args_script, args_region, args_variant)
local code, script, region, variant, private -- ietf tag parts
if not isSet(source) then
return nil, nil, nil, nil, nil, 'missing language tag'
end
local pattern = { -- table of tables holding acceptibe ietf tag patterns and short names of the ietf part captured by the pattern
{'^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)%-(%d%d%d%d)$', 's', 'r', 'v'}, -- 1 - ll-Ssss-RR-variant (where variant is 4 digits)
{'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)%-(%d%d%d%d)$', 's', 'r', 'v'}, -- 2 - ll-Ssss-DDD-variant (where region is 3 digits; variant is 4 digits)
{'^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)%-(%w%w%w%w%w%w?%w?%w?)$', 's', 'r', 'v'}, -- 3 - ll-Ssss-RR-variant (where variant is 5-8 alnum characters)
{'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)%-(%w%w%w%w%w%w?%w?%w?)$', 's', 'r', 'v'}, -- 4 - ll-Ssss-DDD-variant (where region is 3 digits; variant is 5-8 alnum characters)
{'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d%d)$', 's', 'v'}, -- 5 - ll-Ssss-variant (where variant is 4 digits)
{'^(%a%a%a?)%-(%a%a%a%a)%-(%w%w%w%w%w%w?%w?%w?)$', 's', 'v'}, -- 6 - ll-Ssss-variant (where variant is 5-8 alnum characters)
{'^(%a%a%a?)%-(%a%a)%-(%d%d%d%d)$', 'r', 'v'}, -- 7 - ll-RR-variant (where variant is 4 digits)
{'^(%a%a%a?)%-(%d%d%d)%-(%d%d%d%d)$', 'r', 'v'}, -- 8 - ll-DDD-variant (where region is 3 digits; variant is 4 digits)
{'^(%a%a%a?)%-(%a%a)%-(%w%w%w%w%w%w?%w?%w?)$', 'r', 'v'}, -- 9 - ll-RR-variant (where variant is 5-8 alnum characters)
{'^(%a%a%a?)%-(%d%d%d)%-(%w%w%w%w%w%w?%w?%w?)$', 'r', 'v'}, -- 10 - ll-DDD-variant (where region is 3 digits; variant is 5-8 alnum characters)
{'^(%a%a%a?)%-(%d%d%d%d)$', 'v'}, -- 11 - ll-variant (where variant is 4 digits)
{'^(%a%a%a?)%-(%w%w%w%w%w%w?%w?%w?)$', 'v'}, -- 12 - ll-variant (where variant is 5-8 alnum characters)
{'^(%a%a%a?)%-(%a%a%a%a)%-(%a%a)$', 's', 'r'}, -- 13 - ll-Ssss-RR
{'^(%a%a%a?)%-(%a%a%a%a)%-(%d%d%d)$', 's', 'r'}, -- 14 - ll-Ssss-DDD (region is 3 digits)
{'^(%a%a%a?)%-(%a%a%a%a)$', 's'}, -- 15 - ll-Ssss
{'^(%a%a%a?)[%-_](%a%a)$', 'r'}, -- 16 - ll-RR
{'^(%a%a%a?)%-(%d%d%d)$', 'r'}, -- 17 - ll-DDD (region is 3 digits)
{'^(%a%a%a?)$'}, -- 18 - ll
{'^(%a%a%a?)%-x%-(%w%w?%w?%w?%w?%w?%w?%w?)$', 'p'}, -- 19 - ll-x-pppppppp (private is 1-8 alnum characters)
}
local t = {} -- table of captures; serves as a translator between captured ietf tag parts and named variables
for i, v in ipairs(pattern) do -- spin through the pattern table looking for a match
local c1, c2, c3, c4 -- captures in the 'pattern' from the pattern table go here
c1, c2, c3, c4 = source:match(pattern[i][1]) -- one or more captures set if source matches pattern[i])
if c1 then -- c1 always set on match
code = c1 -- first capture is always code
t = {
[pattern[i][2] or 'x'] = c2, -- fill the table of captures with the rest of the captures
[pattern[i][3] or 'x'] = c3, -- take index names from pattern table and assign sequential captures
[pattern[i][4] or 'x'] = c4, -- index name may be nil in pattern[i] table so "or 'x'" spoofs a name for this index in this table
}
script = t.s or '' -- translate table contents to named variables;
region = t.r or '' -- absent table entries are nil so set named ietf parts to empty string for concatenation
variant= t.v or ''
private = t.p or ''
break -- and done
end
end
if not code then
return nil, nil, nil, nil, nil, table.concat ({'unrecognized language tag: ', source}) -- don't know what we got but it is malformed
end
code = code:lower() -- ensure that we use and return lower case version of this
--if synonyms[code] then -- if 639-2/639-2T code has a 639-1 synonym
-- code = synonyms[code] -- use the synonym
--end
if tola[code] == nil and mw.language.fetchLanguageName(code, 'vec') == '' then
return nil, nil, nil, nil, nil, table.concat({'unrecognized language code: ', code}) -- invalid language code, don't know about the others (don't care?)
end
if not isSet(script) then
script = args_script or '' -- use args.script if provided
end
if isSet(script) then
script = string.sub(script, 1, 1):upper() .. string.sub(script, 2):lower()
--if not scripts[script] then
-- return code, nil, nil, nil, nil, table.concat({'unrecognized script: ', script, ' for code: ', code}); -- language code ok, invalid script, don't know about the others (don't care?)
--end
end
if not isSet(region) then
region = args_region or '' -- use args.region if provided
end
region = region:upper()
if not isSet(variant) then
variant = args_variant or '' -- use args.variant if provided
end
variant = variant:lower() -- ensure that we use and return lower case version of this
if isSet(private) then
private = private:lower() -- ensure that we use and return lower case version of this
end
return code, script, region, variant, private, nil -- return the good bits; make sure that msg is nil
end
-- Cerca el nom de lengua definit a /tola o en la llibreria de MediaWiki
local function language_name_get(code)
if not code then return end
local name
if tola[code] then
name = tola[code].nom
end
if name == nil then
name = mw.language.new('vec'):lcfirst(mw.language.fetchLanguageName(code, 'vec'))
end
if not isSet(name) then
return
end
return name
end
-- Cerca el nom de lengua definit a /tola o en la llibreria de MediaWiki
function p.nom(codaze)
if type(codaze) == "table" then codaze = codaze.args[1] end -- des de plantilles via invoke o des de mòduls via require
if codaze == nil then
return 'Nisun còdaze'
end
local nom
local lang, script = get_ietf_parts(codaze)
if lang and isSet(script) then
nom = language_name_get(lang)
end
if not nom then
nom = language_name_get(codaze)
end
return nom or codaze
end
-- Retorna la direcció d'escriptura, ltr o rtl
function p.dir(codaze)
if type(codaze) == "table" then codaze = codaze.args[1] end -- des de plantilles via invoke o des de mòduls via require
if codaze == nil then
return 'Nisun còdaze'
end
local scriptRtl = {["Arab"]=true, ["fa-Arab"]=true, ["ks-Arab"]=true, ["ota-Arab"]=true,
["ps-Arab"]=true, ["ug-Arab"]=true, ["ur-Arab"]=true, ["Avst"]=true, ["Hebr"]=true,
["Nkoo"]=true, ["Phli"]=true, ["Phnx"]=true, ["Syrc"]=true, ["Thaa"]=true}
local alfabet = p.script(codaze)
if scriptRtl[alfabet] then
return 'rtl'
end
local dir = mw.getLanguage(codaze):getDir()
if (dir ~= nil and dir ~= '') then
return dir
end
return 'ltr'
end
-- Retorna el sistema d'escriptura, Latn per defecte
function p.script(codaze)
if type(codaze) == "table" then codaze = codaze.args[1] end -- des de plantilles via invoke o des de mòduls via require
if codaze == nil then
return 'Nisun còdaze'
end
local script
if tola[codaze] then
script = tola[codaze].script
end
if not script then
_, script = get_ietf_parts(codaze)
end
return isSet(script) and script or 'Latn'
end
-- Retorna el subdomini Wikimedia o "" (buit) si no existeix
function p.wikimedia(codaze)
if type(codaze) == "table" then codaze = codaze.args[1] end -- des de plantilles via invoke o des de mòduls via require
if codaze == nil then
return 'Nisun còdaze'
end
local lenguatola = tola[codaze]
local codazeWM = nil
if lenguatola then
codazeWM = lenguatola.wikimedia
end
if codazeWM ~= nil then
return codazeWM
elseif mw.language.isSupportedLanguage(codaze) then
return codaze
end
return ''
end
-- A Wikimedia project exists if its Main page is linked at d:Q5296
function p.wmproject(codaze)
if type(codaze) == "table" then codaze = codaze.args[1] end -- via invoke o via require
if codaze == nil then return end
local lengua_tola = tola[codaze]
local codaze_wikimedia = codaze
if lengua_tola then
codaze_wikimedia = lengua_tola.wikimedia or codaze
end
local codaze_wikidata = string.gsub(codaze_wikimedia, '-', '_')
local main_page = mw.wikibase.getEntity('Q5296')
if main_page.sitelinks[codaze_wikidata .. 'wiktionary'] then
return codaze_wikimedia
end
return
end
-- Existeix el codaze?
function p.existeix(codaze)
--if tola[codaze] or mw.language.isSupportedLanguage(codaze) then
-- return true
--end
-- Comprovació alternativa, les llengües suportades pel Mediawiki són limitades
if type(codaze) == "table" then codaze = codaze.args[1] end -- des de plantilles via invoke o des de mòduls via require
if p.nom(codaze) == codaze then
return false
end
return true
end
--[=[
Funció auxiliar per l’apostrofació de l’article masculí, retorna true o false
Limitacions, en general no necessàries per noms de lengua:
els casos previstos de h consonant són limitats
no analitza el cas l’s+consonant
no preveu si hi ha caràcters de puntuació inicial (l’«apòstrof», l’[[enllaç]])
no apostrofa davant números (l’1, l’11) ni sigles (l’FMI)
--]=]
local apostrofa = {
["hakk"]=false, -- h consonant (hakka)
["hawa"]=false, -- h consonant (hawaià)
["hia"]=false, ["hie"]=false, ["hio"]=false, ["hui"]=false, -- vocal consonant
["uix"]=true, -- excepció per u vocal
["ha"]=true, ["he"]=true, ["hi"]=true, ["hí"]=true, ["ho"]=true, ["hu"]=true, ["hy"]=true, -- excepte anteriors
["ia"]=false, ["ià"]=false, ["ie"]=false, ["io"]=false, ["iu"]=false, -- i consonant
["ua"]=false, ["ue"]=false, ["ui"]=false, ["uí"]=false, ["uï"]=false, ["uo"]=false, -- u consonant
["ya"]=false, ["ye"]=false, ["yi"]=false, ["yo"]=false, ["yu"]=false, -- y consonant
["a"]=true, ["à"]=true, ["e"]=true, ["è"]=true, ["é"]=true,
["i"]=true, ["í"]=true, ["ï"]=true, ["y"]=true,
["o"]=true, ["ò"]=true, ["ó"]=true, ["u"]=true, ["ú"]=true, ["ü"]=true -- excepte anteriors
}
local function sapostrofa(text)
local elText = mw.ustring.lower(text)
for i=4,1,-1 do
lletres = mw.ustring.sub(elText, 1, i)
apo = apostrofa[lletres]
if apo ~= nil then
return apo
end
end
return false
end
-- Retorna "del nom" o "de l'nom"
function p.del_nom(frame)
local nom = p.nom(frame)
if nom == "preromà" then
return "d'un preromà"
end
if sapostrofa(nom) then
return "de l'" .. nom
end
return "del " .. nom
end
-- Retorna "al nom" o "a l'nom"
function p.al_nom(frame)
local nom = p.nom(frame)
if sapostrofa(nom) then
return "a l'" .. nom
end
return "al " .. nom
end
-- Retorna "el nom" o "l'nom"
-- TODO: unificar funcions d'apostrofació en base a paràmetre de partícula
function p.el_nom(codaze)
local nom = p.nom(codaze)
if sapostrofa(nom) then
return "l'" .. nom
end
return "el " .. nom
end
-- transcripció, si existeix el mòdul per la lengua amb la funció tr
function p.trans(lang, text)
local trans
if lang and text then
local m_trans = tola[lang]
if m_trans and m_trans.trans_module then
trans = require("Module:" .. m_trans.trans_module).tr(text)
end
end
return trans
end
return p