Mòdul:ca-general/proves
La documentació d'ús d'aquest mòdul es pot crear a Mòdul:ca-general/proves/ús
-- Funcions generals per català.
local p = {}
-- Clau d'ordenació per a categories en català
local senseDiacritics = {
["À"] = "A", ["à"] = "a",
["È"] = "E", ["è"] = "e", ["É"] = "E", ["é"] = "e",
["Í"] = "I", ["í"] = "i", ["Ï"] = "I", ["ï"] = "i",
["Ò"] = "O", ["ò"] = "o", ["Ó"] = "O", ["ó"] = "o",
["Ú"] = "U", ["ú"] = "u", ["Ü"] = "U", ["ü"] = "u",
["Ç"] = "C", ["ç"] = "c",
["·"] = ""}
local senseSignes = {
["/"] = "",
["-"] = "",
["."] = "",
-- l'espai en blanc és anterior a "!"
-- el guió baix és posterior a A-Z i al final el Mediawiki ho converteix a majúscules
[" "] = "&",
["'"] = "&"}
local ordreAccents = { -- ordre eéè simulat amb ordre Unicode eèéê
["è"] = "ê",
["ò"] = "ô"}
function p.ordena(mot)
if type(mot) == "table" then mot = mot.args[1] end -- des de plantilles via invoke o des de mòduls via require
if mot == "" or mot == nil then
mot = mw.title.getCurrentTitle().text
end
local clau -- format complet: "clau1!clau2!clau3!mot"
local clau1 -- clau primària: en minúscules i sense diacrítics ni signes
local clau2 -- clau secundària: prioritat dels diacrítics eéè
local clau3 -- clau terciària: prioritat minúscules > majúscules
-- clau quaternària: prioritat sense signes > amb signes
local motSenseSignes = mw.ustring.gsub(mot, ".", senseSignes)
local motLower = mw.ustring.lower(mw.text.trim(motSenseSignes))
clau1 = mw.ustring.gsub(motLower, ".", senseDiacritics)
if clau1 == mot then
return clau1
end
clau2 = mw.ustring.gsub(motLower, ".", ordreAccents)
clau3 = mw.ustring.gsub(motSenseSignes, ".", senseDiacritics)
if clau1 == motLower then
clau = clau1 .. "!"
else
clau = clau1 .. "!" .. clau2
end
if clau3 ~= clau1 then
clau = clau .. "!" .. clau3
elseif motSenseSignes ~= mot then
clau = clau .. "!"
end
if motSenseSignes ~= mot then
clau = clau .."!" .. mot
end
return clau
end
function p.cat_ortografia(frame)
-- categorització per característiques ortogràfiques: invers, palíndroms, eles geminades
local pagename = mw.title.getCurrentTitle().text
local namespace = mw.title.getCurrentTitle().nsText
local ret = ""
if namespace == "" then
if not (pagename:find("^-") or pagename:find("-$")) then -- sense afixos
local motNet = mw.ustring.lower(mw.ustring.gsub(pagename, ".", senseSignes))
motNet = string.gsub(motNet, " ", "")
motNet = mw.ustring.gsub(motNet, ".", senseDiacritics)
local motInvers = motNet:reverse()
if not pagename:find("[ '.]") then -- sense locucions ni abreviatures
ret = "[[Categoria:Diccionari invers en català|" .. motInvers .. "]]"
if mw.ustring.find(pagename, "l·l") then
ret = ret .. "[[Categoria:Mots en català amb eles geminades|" .. motNet .. "]]"
end
end
-- palímdroms traslladat a [[Mòdul:palíndroms]
--if motInvers == motNet and string.len(motNet) > 1 and not pagename:find("%.") then
-- ret = ret .. "[[Categoria:Palíndroms en català" .. (motNet == pagename and "" or "|" .. motNet) .. "]]"
--end
end
end
return ret
end
--[[
Sil·labificació
marcatge intern: vocals 0, obertures 1, codes 2
síl·laba: ·(1*)0(2*)·
]]
function p.sil(mot)
if type(mot) == "table" then mot = mot.args[1] end -- des de plantilles via invoke o des de mòduls via require
if mot == "" or mot == nil then
mot = mw.title.getCurrentTitle().text
end
local sil = mw.ustring.lower(mot)
-- Prefixos que trenquen regles
local initial = string.sub(mot, 1, 1)
if initial == "a" then
sil = string.gsub(sil, "^anae", "0200") -- an-
sil = string.gsub(sil, "^anafro", "020110")
sil = mw.ustring.gsub(sil, "^an[aà]l[fg]", "02021")
sil = mw.ustring.gsub(sil, "^an[aà]r([cq])", "0202%1")
sil = mw.ustring.gsub(sil, "^anè", "020")
sil = string.gsub(sil, "^ane([nprs])", "020%1")
sil = mw.ustring.gsub(sil, "^an[uú]r", "020r")
sil = string.gsub(sil, "^autoi([mn])", "02100%1") -- auto-
elseif initial == "b" then
sil = mw.ustring.gsub(sil, "^bena(%l+è)", "1010%1")
sil = string.gsub(sil, "^bena(%l)", "1020%1") -- ben-
sil = string.gsub(sil, "^bene([ns]%l)", "1020%1")
sil = mw.ustring.gsub(sil, "^bes[aà]v", "10201") -- bes-
sil = string.gsub(sil, "^beson", "10202")
sil = string.gsub(sil, "^bisan", "10202") -- bis-
elseif initial == "c" then
sil = string.gsub(sil, "^coin", "1002") -- co-
sil = string.gsub(sil, "^con[ou][nr]", "10202") -- con-
sil = string.gsub(sil, "^contrai", "1021100") -- contra-
elseif initial == "d" then
sil = mw.ustring.gsub(sil, "^des([aeiouú])", "102%1") -- des- amb excepcions pendents
elseif initial == "e" then
sil = string.gsub(sil, "^enanti", "010210") -- enantio-
sil = mw.ustring.gsub(sil, "^en[oò]([flt])", "010%1") -- eno-
sil = string.gsub(sil, "^enorm", "01021") --
sil = mw.ustring.gsub(sil, "^en[aoò]", "020") -- en-, excepte anteriors
sil = string.gsub(sil, "^exa([bclnrs])", "020%1") -- ex-
sil = string.gsub(sil, "^exo([rs][^cdrpqt])", "020%1")
elseif initial == "h" then
sil = string.gsub(sil, "^hiper[ae]", "101020") -- hiper-
elseif initial == "i" then
sil = string.gsub(sil, "^inani[ct]", "010101")
sil = string.gsub(sil, "^inefa", "01010")
sil = mw.ustring.gsub(sil, "^in[eè]p", "0102")
sil = mw.ustring.gsub(sil, "^in[eè]r([^ru])", "0102%1")
sil = string.gsub(sil, "^ino[cs][ei]", "01010")
sil = mw.ustring.gsub(sil, "^in[aeèoò]", "020") -- in-, excepte anteriors
sil = string.gsub(sil, "^ini([gmn])", "020%1")
sil = mw.ustring.gsub(sil, "^in[uú]([rst])", "020%1")
sil = string.gsub(sil, "^infra[iu]", "021100") -- infra-
sil = string.gsub(sil, "^inter[ao]([^p])", "021020%1") -- inter
sil = string.gsub(sil, "^interest", "02102021")
sil = string.gsub(sil, "^intra[iu]", "021100") -- intra-
elseif initial == "m" then
sil = string.gsub(sil, "^m[ai]cro[iu]", "101100") -- macro-, micro-
elseif initial == "n" then
sil = string.gsub(sil, "^nosal", "10202")
elseif initial == "p" then
sil = string.gsub(sil, "^pana([frt][rate][^a])", "1020%1") -- pan-
sil = string.gsub(sil, "^panamer", "1020101")
sil = string.gsub(sil, "^panisl", "102021")
sil = mw.ustring.gsub(sil, "^panòpt", "102021")
sil = string.gsub(sil, "^posta[bcl]([^$])", "102202%1") -- post-
sil = string.gsub(sil, "^postes([^$])", "102202%1")
sil = string.gsub(sil, "^post[io][mp]", "102202")
sil = mw.ustring.gsub(sil, "^post[^aàeèéioòóu]", "10221")
sil = string.gsub(sil, "^pr[eo]i([^x])", "1100%1") -- pre-, pro-
elseif initial == "r" then
sil = string.gsub(sil, "^rein[ae]", "10210")
sil = string.gsub(sil, "^rei([^aegx])", "100%1") -- re-
sil = string.gsub(sil, "^reun", "1001")
elseif initial == "s" then
sil = string.gsub(sil, "^sots[ai]", "10220") -- sots-
sil = mw.ustring.gsub(sil, "^sub([aàíour])", "102%1") -- sub-
sil = mw.ustring.gsub(sil, "^sub[eè]([^r])", "1020%1")
sil = string.gsub(sil, "^subl[iu][nt]", "102101")
elseif initial == "t" then
sil = string.gsub(sil, "^trans[aeou]", "110220") -- trans-
elseif initial == "u" then
sil = string.gsub(sil, "^ultra[iu]", "021100") -- ultra-
elseif initial == "v" then
sil = string.gsub(sil, "^vosal", "10202")
end
-- Diftongs creixents
sil = mw.ustring.gsub(sil, "[qg][uü][aàeèéiíïoòóuúü]", "110")
sil = mw.ustring.gsub(sil, "[aàeèéiíïoòóuúü][iu][aàeèéiíïoòóuúü]", "010")
sil = mw.ustring.gsub(sil, "^i[oò]ni(.)", "0010%1") -- excepció pels derivant de ió
sil = mw.ustring.gsub(sil, "^(h?)[iu][aàeèéioòóu]", "%110")
-- Sufixos i desinències amb estalvi de dièresi
sil = string.gsub(sil, "[aeou]ir$", "002") -- infinitius -ir
sil = string.gsub(sil, "[aeou]int$", "0022") -- gerundis
sil = mw.ustring.gsub(sil, "[aeou]ir[éà]$", "0010") -- futur
sil = mw.ustring.gsub(sil, "[aeou]iràs$", "00102") -- futur
sil = string.gsub(sil, "[aeou]ire[mu]$", "00102") -- futur
sil = string.gsub(sil, "[aeou]iran$", "00102") -- futur
sil = string.gsub(sil, "[aeou]iria$", "00100") -- condicional
sil = string.gsub(sil, "[aeou]irie[sn]$", "001002") -- condicional
sil = string.gsub(sil, "[0iu]um(s?)$", "002%1") -- llatinismes
sil = string.gsub(sil, "[0aeiou]isme(s?)$", "00210%1") -- -isme
sil = string.gsub(sil, "[0aeiou]ist([ae]s?)$", "0021%1") -- -ista
-- Diftongs decreixents
sil = mw.ustring.gsub(sil, "[0aàeèéioòóu][u]", "02") -- inclou triftongs: creixent 10 + decreixent 2
sil = mw.ustring.gsub(sil, "[0aàeèéoòóuúü][i]", "02")
sil = string.gsub(sil, "ii$", "02") -- només final de mot, no amb prefix
-- Nuclis vocàlics
sil = mw.ustring.gsub(sil, "[aàeèéiíïoòóuúü]", "0")
-- Codes finals
sil = string.gsub(sil, "%l$", "2")
sil = string.gsub(sil, "%l2$", "22")
sil = string.gsub(sil, "%l22$", "222")
-- Obertures
sil = string.gsub(sil, "^%l", "1")
sil = string.gsub(sil, "^1%l", "11")
sil = string.gsub(sil, "^11%l", "111")
sil = string.gsub(sil, "ll0", "110")
sil = string.gsub(sil, "ny0", "110")
sil = string.gsub(sil, "[ptcfbdg]r", "11")
sil = string.gsub(sil, "[pcfbg]l", "11")
sil = string.gsub(sil, "%l0", "10")
sil = mw.ustring.gsub(sil, "[çñ]0", "10") -- %l (all ASCII lowercase letters) no inclou ç, ñ
-- Codes interiors
sil = string.gsub(sil, "[ps][%l1]", "21")
sil = string.gsub(sil, "%l([12])", "2%1")
-- Separació de síl·labes
local anterior = ""
local mot_sep = {}
for i = 1, mw.ustring.len(mot) do
actual = mw.ustring.sub(sil, i, i)
if (actual == "0" or actual == "1") and (anterior == "0" or anterior == "2") then
table.insert(mot_sep, "·")
end
table.insert(mot_sep, mw.ustring.sub(mot, i, i))
anterior = actual
end
return table.concat(mot_sep)
end
function p.sil_template(frame)
local word = frame:getParent().args[1] or mw.title.getCurrentTitle().text
if mw.ustring.find(word, "[^ ]+ [^ ]+") then
return
end
word = string.gsub(word, "-", "·")
local sil = p.sil(word)
local num_sil = mw.text.split(sil, '·')
return sil .. ' (' .. #num_sil .. ')'
end
return p