Módulo:generar-pron/sk
La documentación para este módulo puede ser creada en Módulo:generar-pron/sk/doc
local export = {}
local insert = table.insert
local concat = table.concat
local m_str = require("Módulo:String")
local U = m_str.char
local strlower = m_str.lower
local strsplit = m_str.split
local strlen = m_str.ulen
local substr = m_str.sub
local strfind = m_str.find
local strmatch = m_str.match
local strmatchit = m_str.gmatch
local strsubn = m_str.gsub
local strsubrep = m_str.gsub_rep
local strstrip = m_str.strip
local strnfd = m_str.toNFD
local strnfc = m_str.toNFC
local strhtml = m_str.encode_html
-- sustitución descartando todo salvo el string retornado
local function strsub(text, pattern, repl, n)
local t, _ = strsubn(text, pattern, repl, n)
return t
end
local PUNTUACION = "[%(%)%[%]%{%}¡!¿?.,;:–—]"
local PUNTUACION_EXTRA = "[%(%)%[%]%{%}¡!¿?.,;:–—\"“”„‟‘’«»»«‹››‹'´]"
local long = "ː"
local nonsyllabic = U(0x32F) -- inverted breve below
local syllabic = U(0x0329)
local tie = U(0x361) -- combining double inverted breve
local primary_stress = "ˈ"
local secondary_stress = "ˌ"
local data = {
["á"] = "a" .. long,
["ä"] = "ɛɐ" .. nonsyllabic,
["c"] = "t" .. tie .. "s",
["č"] = "t" .. tie .. "ʃ",
["ď"] = "ɟ",
["dz"] = "d" .. tie .. "z",
["dž"] = "d" .. tie .. "ʒ",
["é"] = "e" .. long,
["g"] = "ɡ",
["h"] = "ɦ",
["ch"] = "x",
["í"] = "i" .. long,
["ĺ"] = "l" .. syllabic .. long,
["ľ"] = "ʎ",
["ň"] = "ɲ",
["o"] = "ɔ",
["ó"] = "o" .. long,
["ô"] = "u" .. nonsyllabic .. "o",
["ö"] = "œ",
["q"] = "kv",
["ŕ"] = "r" .. syllabic .. long,
["š"] = "ʃ",
["ť"] = "c",
["ú"] = "u" .. long,
["ü"] = "y",
["w"] = "v",
["x"] = "ks",
["y"] = "i",
["ý"] = "i" .. long,
["ž"] = "ʒ",
["ia"] = "i" .. nonsyllabic .. "a",
["ie"] = "i" .. nonsyllabic .. "e",
["iu"] = "i" .. nonsyllabic .. "u",
["\""] = primary_stress,
["%"] = secondary_stress,
}
-- Add data["a"] = "a", data["b"] = "b", etc.
for character in strmatchit("abdefijklmnprstuvz ", ".") do
data[character] = character
end
--Define alveolars, front vowels, and palatalized consonants
local alveolars_ortho = { "t", "d", "n"}
local front_vowels_ortho = { "e", "é", "i", "í", "ie", "ia"}
local palatalized_ortho = {
["t"] = "ť",
["d"] = "ď",
["n"] = "ň",
}
local UTF8Char = "[\1-\127\194-\244][\128-\191]*"
local nonsyllabicDiacritics = U(0x311) .. U(0x32F)
local syllabicDiacritics = U(0x0329) .. U(0x030D)
local nonsyllabicDiacritic = "[" .. nonsyllabicDiacritics .. "]"
local syllabicDiacritic = "[" .. syllabicDiacritics .. "]"
local vowels_IPA = "iyɨʉɯuɪʏʊeøɘɵɤoəɚɛœɜɝɞʌɔæɐaɶɑɒäëïöüÿᵻᵿ" -- genérico, son las vocales fonéticas de todos los idiomas
local vowel_IPA = "["..vowels_IPA.."]"
local function getVowels(remainder)
if string.find(remainder, "^[%/%[]?%-") or string.find(remainder, "%-[%/%]]?$") then
return nil
end -- If a hyphen is at the beginning or end of the transcription, do not count syllables.
local count = 0
--local diphs = diphthongs[lang:getCode()] or {}
remainder = strnfd(remainder)
remainder = string.gsub(remainder, "%((.*)%)", "%1") -- Remove parentheses.
while remainder ~= "" do
-- Ignore nonsyllabic vowels
remainder = strsub(remainder, "^" .. vowel_IPA .. nonsyllabicDiacritic, "")
local m =
strmatch(remainder, "^." .. syllabicDiacritic) or -- Syllabic consonant
strmatch(remainder, "^" .. vowel_IPA .. tie .. vowel_IPA) -- Tie bar
-- Starts with a recognised diphthong?
--[=[
for _, diph in ipairs(diphs) do
if m then
break
end
m = m or mw.ustring.match(remainder, "^" .. diph)
end
--]=]
-- If we haven't found anything yet, just match on a single vowel
m = m or strmatch(remainder, "^" .. vowel_IPA)
if m then
-- Found a vowel, add it
count = count + 1
remainder = substr(remainder, #m + 1)
else
-- Found a non-vowel, skip it
remainder = substr(remainder, 2)
end
end
if count ~= 0 then return count end
return nil
end
local pron_abc = {
["A"] = {"á"},
["a"] = {"á"},
["Á"] = {"dlhé á"},
["á"] = {"dlhé á"},
["Ä"] = {"prehlasované á", "a s dvoma bodkami", "široké e"},
["ä"] = {"prehlasované á", "a s dvoma bodkami", "široké e"},
["B"] = {"bé"},
["b"] = {"bé"},
["C"] = {"cé"},
["c"] = {"cé"},
["Č"] = {"čé"},
["č"] = {"čé"},
["D"] = {"dé"},
["d"] = {"dé"},
["Ď"] = {"ďé", "mäkké dé"},
["ď"] = {"ďé", "mäkké dé"},
["Dz"] = {"dzé"},
["dz"] = {"dzé"},
["Dž"] = {"džé"},
["dž"] = {"džé"},
["E"] = {"é"},
["e"] = {"é"},
["É"] = {"dlhé é"},
["é"] = {"dlhé é"},
["F"] = {"ef"},
["f"] = {"ef"},
["G"] = {"gé"},
["g"] = {"gé"},
["H"] = {"há"},
["h"] = {"há"},
["Ch"] = {"chá"},
["ch"] = {"chá"},
["I"] = {"í"},
["i"] = {"í"},
["Í"] = {"dlhé í"},
["í"] = {"dlhé í"},
["J"] = {"jé"},
["j"] = {"jé"},
["K"] = {"ká"},
["k"] = {"ká"},
["L"] = {"el"},
["l"] = {"el"},
["Ĺ"] = {"dlhé el"},
["ĺ"] = {"dlhé el"},
["Ľ"] = {"eľ", "mäkké el"},
["ľ"] = {"eľ", "mäkké el"},
["M"] = {"em"},
["m"] = {"em"},
["N"] = {"en"},
["n"] = {"en"},
["Ň"] = {"eň"},
["ň"] = {"eň"},
["O"] = {"o"},
["o"] = {"o"},
["Ó"] = {"ó", "dlhé o"},
["ó"] = {"ó", "dlhé o"},
["Ô"] = {"ô"},
["ô"] = {"ô"},
["P"] = {"pé"},
["p"] = {"pé"},
["Q"] = {"kvé"},
["q"] = {"kvé"},
["R"] = {"er"},
["r"] = {"er"},
["Ŕ"] = {"dlhé er"},
["ŕ"] = {"dlhé er"},
["S"] = {"es"},
["s"] = {"es"},
["Š"] = {"eš"},
["š"] = {"eš"},
["T"] = {"té"},
["t"] = {"té"},
["Ť"] = {"ťé", "mäkké té"},
["ť"] = {"ťé", "mäkké té"},
["U"] = {"u"},
["u"] = {"u"},
["Ú"] = {"dlhé ú"},
["ú"] = {"dlhé ú"},
["V"] = {"vé"},
["v"] = {"vé"},
["W"] = {"dvojité vé"},
["w"] = {"dvojité vé"},
["X"] = {"iks"},
["x"] = {"iks"},
["Y"] = {"ypsilon", "i griego"},
["y"] = {"ypsilon", "i griego"},
["Ý"] = {"dlhý ypsilon", "dlhý i griego"},
["ý"] = {"dlhý ypsilon", "dlhý i griego"},
["Z"] = {"zet"},
["z"] = {"zet"},
["Ž"] = {"žet"},
["ž"] = {"žet"},
}
-- [==[ Phonological rules ]==]
--[[
This is used to replace multiple-character sounds
with numbers, which makes it easier to process them. ]]
local multiple_char = {
"t" .. tie .. "s", "t" .. tie .. "ʃ", "d" .. tie .. "z", "d" .. tie .. "ʒ",
}
local singlechar = {}
for number, character in pairs(multiple_char) do
singlechar[character] = tostring(number)
end
local voiceless = { "p", "t", "c", "k", "f", "s", "ʃ", "x", "1", "2", }
local voiced = { "b", "d", "ɟ", "ɡ", "v", "z", "ʒ", "ɦ", "3", "4", }
local sonorants = { "m", "n", "ɲ", "r", "l", "ʎ", "j", }
local features = {}
local indices = {}
for i, consonant in pairs(voiceless) do
if not features[consonant] then
features[consonant] = {}
end
features[consonant]["voicing"] = false
indices[consonant] = i
end
for i, consonant in pairs (voiced) do
if not features[consonant] then
features[consonant] = {}
end
features[consonant]["voicing"] = true
indices[consonant] = i
end
local function palatalize_orthography(term)
for _, alv in ipairs(alveolars_ortho) do
for _, vow in ipairs(front_vowels_ortho) do
local pattern = alv .. vow
local replacement = palatalized_ortho[alv] .. vow
term = strsub(term, pattern, replacement)
end
end
return term
end
local function devoice_finally(IPA)
local voiced_obstruent = "[" .. concat(voiced) .. "]"
local final_voiced_obstruent = strmatch(IPA, voiced_obstruent .. "+$") or strmatch(IPA, voiced_obstruent .. "+%s")
if final_voiced_obstruent then
local replacement = {}
local length = strlen(final_voiced_obstruent)
for i = 1, length do
local consonant = substr(final_voiced_obstruent, i, i)
local index = indices[consonant]
local devoiced = voiceless[index]
insert(replacement, devoiced)
end
local replacement_str = concat(replacement)
-- This will cause problems if the same consonant cluster occurs elsewhere in the term.
IPA = strsub(IPA, final_voiced_obstruent, replacement_str)
end
return IPA
end
local function syllabicize_sonorants(IPA)
local sonorant = strsub("[" .. concat(sonorants) .. "]", "[ɲʎj]", "") -- all except ɲ and ʎ and j
local obstruent = "[" .. concat(voiced) .. concat(voiceless) .. "]"
local consonant = "[" .. strsub(sonorant .. obstruent, "[%[%]]", "") .. "]"
-- between a consonant and an obstruent
IPA = strsub(IPA, "(" .. consonant .. sonorant .. ")(" .. obstruent .. ")", "%1" .. syllabic .. "%2")
-- at the beginning of a word before an obstruent
IPA = strsub(IPA, "^(" .. sonorant .. ")(" .. obstruent .. ")", "%1" .. syllabic .. "%2")
-- at the end of a word after an obstruent
IPA = strsub(IPA, "(" .. obstruent .. sonorant .. ")$", "%1" .. syllabic)
return IPA
end
local function add_stress(IPA)
local syllable_count = getVowels(IPA)
if not syllable_count then
-- words like “čln” or “v” contain no designated vowels, yet they are valid Slovak words
syllable_count = 1
end
if syllable_count > 1 and not strfind(IPA, " ") then
IPA = primary_stress .. IPA
end
return IPA
end
local function apply_rules(IPA)
-- Replace multiple-character units with numbers.
for sound, character in pairs(singlechar) do
IPA = strsub(IPA, sound, character)
end
IPA = devoice_finally(IPA)
IPA = syllabicize_sonorants(IPA)
IPA = add_stress(IPA)
-- Change double to single consonants.
local consonant = "[" .. concat(sonorants) .. concat(voiceless) .. concat(voiced) .. "]"
IPA = strsub(IPA, "(" .. consonant .. ")%1", "%1")
-- Replace numbers with multiple-character units.
for sound, character in pairs(singlechar) do
IPA = strsub(IPA, character, sound)
end
return IPA
end
local function normalizar(texto)
texto = strlower(texto)
texto = palatalize_orthography(texto)
texto = strsubrep(texto, PUNTUACION, " | ") -- convierto lo que delimite fragmentos a los IPA foot boundaries |
texto = strsubrep(texto, PUNTUACION_EXTRA, "") -- elimino la puntuación restante que haya quedado
texto = strsubrep(texto, "[%-‐]", " ") --los guiones pasan a ser espacios (austro-húngaro, franco-italiano)
texto = strsubrep(texto, "%s*|%s*|%s*", " | ") --finalmente, elimino las barras y espacios de más
texto = strsubrep(texto, "%s+", " ")
texto = strstrip(texto, "[%s|]+")
return texto
end
local function generar_pron(term)
term = normalizar(term)
local fragmentos_convertidos = {}
local fragmentos = strsplit(term, "%s*|%s*")
for _,fragmento in ipairs(fragmentos) do
local palabras = strsplit(fragmento, "%s")
local palabras_convertidas = {}
for debu,p in ipairs(palabras) do
local working_string = p
local convertido = ""
while strlen(working_string) > 0 do
local IPA_letter
local letter = substr(working_string, 1, 1)
local twoletters = substr(working_string, 1, 2) or ""
if data[twoletters] then
IPA_letter = data[twoletters]
working_string = substr(working_string, 3)
else
IPA_letter = data[letter] or error('The letter "' .. tostring(letter) .. '" is not a member of the Slovak alphabet.')
working_string = substr(working_string, 2)
end
convertido = convertido..IPA_letter
end
insert(palabras_convertidas, convertido)
end
insert(fragmentos_convertidos, concat(palabras_convertidas, " "))
end
local IPAstr = concat(fragmentos_convertidos, " | ")
IPAstr = apply_rules(IPAstr)
return {{strhtml(IPAstr)}}, {{strhtml(term)}}
end
function export.procesar_pron_args(titulo, args)
local tit = titulo
local vino_ayuda, x
if #args["ayuda"] < 1 then
args["ayuda"][1] = tit
else
vino_ayuda = true
end
if #args["fone"] < 1 and #args["fono"] < 1 then
x = pron_abc[args["ayuda"][1]]
if x then
args["ayuda"] = x
args["tl"] = x
end
local A = #args["ayuda"]
local j = 1 -- indice de la ayuda
local k = 1 -- cantidad de pronunciaciones insertadas (máximo 9)
while k <= 9 and j <= A do
local fono, fgraf = generar_pron(args["ayuda"][j])
for i,_ in ipairs(fono) do
insert(args["fono"], fono[i])
insert(args["fgraf"], fgraf[i])
k = k + 1
if k > 9 then
break
end
end
j = j + 1
end
end
local tiene_espacios = strfind(tit, "%s")
if args["fono"][1] and args["fono"][1][1] then
local rim = strsub(args["fono"][1][1], ".*%s([^%s]+)$", "%1") -- me quedo con la última palabra
rim = strsub(rim, "^.*"..primary_stress.."(.-)$", "%1")
args["rima"] = strsub(rim, ".-".."("..vowel_IPA..".*"..")".."$", "%1")
end
return args
end
return export