Linguifex

Module:xchc-pron: Difference between revisions

← Older edit
No edit summary
No edit summary
 
(28 intermediate revisions by the same user not shown)
Line 7: Line 7:
local split = mw.text.split
local split = mw.text.split
local gsplit = mw.text.gsplit
local gsplit = mw.text.gsplit
local M = u(0x0304) -- COMBINING MACRON
local B = u(0x0306) -- COMBINING BREVE
local D = u(0x0308) -- COMBINING DIAERESIS


local lang = require("Module:languages").getByCode("xchc")
local lang = require("Module:languages").getByCode("xchc")
local c = require("Module:languages/data").chars
local m_IPA = require("Module:IPA")
local m_IPA = require("Module:IPA")


local consonants = "[mnŋɲptbdkɡfvszʃʒxɣhʧʦʤʣlrɾʎ]"
local M = c.macron
local B = c.breve
local D = c.diaer
local nb_cons = "mnŋɲptbdkɡfvszʃʒxɣhʧʦʤʣlrɾʎ"
local consonants = "[" .. nb_cons .. "]"
 
local consonantsAsIs = "[мньӈбдгвзжғлрйпткфсшӀчц]"
local vowels = "[ыиэеаяүөуюоёӯӣɜɔ]"


local export = {}
local export = {}
local function laxen(v)
local otc = {}
local switch = {["e"] = "ɛ", ["i"] = "ɪ", ["o"] = "ɔ", ["u"] = "ʊ"}
for vc in gmatch(v, ".") do
if switch[vc] then vc = gsub(vc, vc, switch[vc]) end
table.insert(otc, vc)
end
return table.concat(otc)
end
local function same(foo, bar)
foo, bar = mw.ustring.toNFD(foo), mw.ustring.toNFD(bar) -- decompose diacritics
foo, bar = match(foo, "^."), match(bar, "^.") -- sort out the letter
return foo == bar and true or false
end


local first_rules = {
local first_rules = {
{M, "ː"}, {"ː([" .. M .. D .. B .. "])", "%1ː"},
{"%-", ""}, {M, "ː"}, {"ː([" .. M .. D .. B .. "])", "%1ː"},
{"е" .. D, "ьo"}, {"о" .. B, "ɔ"}, {"э" .. B, "ɛ"},
{"е" .. D, "ьo"}, {"о" .. B, "ɔ"}, {"э" .. B, "ɛ"}, {"и" .. B, "j"},
{"а", "a"},
{"а", "a"},
Line 65: Line 52:
{"ү", "y"},
{"ү", "y"},
{"ф", "f"},
{"ф", "f"},
{"хӀ", "h"}, {"х", "x"},
{"[хx]ӏ", "h"}, {"х", "x"},
{"ц", "ʦ"},
{"ц", "ʦ"},
{"ч", "ʧ"},
{"ч", "ʧ"},
Line 76: Line 63:
{"l[ьі]", "ʎ"}, {"n[ьі]", "ɲ"}, {"[ьі]", "j"},
{"l[ьі]", "ʎ"}, {"n[ьі]", "ɲ"}, {"[ьі]", "j"},
{"(" .. consonants .. ")(" .. consonants .. ")", function(c1,c2) return same(c1, c2) and c1 .. "ː" or c1 .. c2 end}
{"(" .. consonants .. ")%1", "%1ː"},
{"r$", "ɾ"}, {"([ŋkɡxɣh])a", "%1ɑ"}, {"a(ː?[ŋkɡxɣh])", "ɑ%1"}
}
}


Line 85: Line 73:
{"ʧ", "t͡ʃ"},
{"ʧ", "t͡ʃ"},
}
}
local wnc = "([iyueøoɛɔœʌ]ː?)"
local western_rules = {
    {wnc .. "f$", "%1p̪͡f"},
    {wnc .. "v$", "%1b̪͡v"},
{wnc .. "s$", "%1t͡s"},
    {wnc .. "z$", "%1d͡z"},
    {wnc .. "ʃ$", "%1t͡ʃ"},
    {wnc .. "ʒ$", "%1d͡ʒ"},
    {wnc .. "x$", "%1k͡x"},
    {wnc .. "ɣ$", "%1ɡ͡ɣ"},
    {wnc .. "h$", "%1ʔ͡h"},
    {wnc .. "p$", "%1ɸ"}, {wnc .. "b$", "%1β"}, {wnc .. "t$", "%1s"},
    {wnc .. "d$", "%1z"}, {wnc .. "k$", "%1x"}, {wnc .. "ɡ$", "%1ɣ"},
}
local surgut_rules = {
{"ɲ", "nʲ"}, {"ʎ", "lʲ"},
{"(" .. consonants .. ")([iyeø])", "%1ʲ%2"},
}
-- Remove diacritics for module calculations based on vowels
function export.simplify(term)
term = mw.ustring.toNFD(term):gsub(c.macron, "") -- vowel length
term = term:gsub("э" .. c.breve, "ɛ"); term = term:gsub("о" .. c.breve, "ɔ")
term = mw.ustring.toNFC(term):gsub("ё", "о"); term = term:gsub("е" .. c.diaer, "о")
return term
end


function export.crux(term)
function export.crux(term)
term = mw.ustring.lower(mw.ustring.toNFD(term))
for _, rule in ipairs(first_rules) do
for _, rule in ipairs(first_rules) do
term = gsub(term, rule[1], rule[2])
term = gsub(term, rule[1], rule[2])
Line 99: Line 114:
return term
return term
end
end
function export.harmony(term)
term = export.simplify(term)
local termR, termB = term, term
local unrounded = "[ыиӣеэ]"; local rounded = "[үөуӯюоё]"; local neutralR = "[ɛɔая]"
local front = "ɛ"; local back = "ɔ"; local neutralB = "[ыиӣеэүөуӯюоёая]"
-- for words that violate vowel harmony (compounds and loanwords)
local exception = (term:match(unrounded) and term:match(rounded)) or (term:match(front) and term:match(back))
if exception then
termR = term:gsub(neutralR, ""); termB = term:gsub(neutralB, "")
termR = termR:match("(".. vowels .. consonantsAsIs .. "*)$") or termR; termB = termB:match("(" .. vowels .. consonants .. "*)$") or termB
end
local ret = {
["roundness"] = termR:match(unrounded) and "u" or termR:match(rounded) and "r" or "ar",
["backness"] = termB:match(front) and "f" or termB:match(back) and "b" or "ab",
}
return ret
end


function separate_word(term)
function separate_word(term)
Line 104: Line 141:
for word in gsplit(term, " ") do
for word in gsplit(term, " ") do
table.insert(result, export.crux(word))
local ipa = export.crux(word)
if export.harmony(word).backness == "b" then ipa = ipa:gsub("a", "ɑ") end
if export.harmony(word).roundness == "r" then ipa = ipa:gsub("ɛ", "œ") end
if export.harmony(word).roundness == "u" then ipa = ipa:gsub("ɔ", "ʌ") end
table.insert(result, ipa)
end
end
Line 116: Line 159:
}
}
local args = require("Module:parameters").process(parent_args, params)
local args = require("Module:parameters").process(parent_args, params)
local term = args[1]
local term = mw.ustring.lower(mw.ustring.toNFD(args[1]))


local IPA_args = {}
local IPA_args = {}
local phonetic = separate_word(term)
local phonetic = separate_word(term)
table.insert(IPA_args, {pron = '[' .. phonetic .. ']'})
local western = phonetic
for _, rule in ipairs(western_rules) do
western = gsub(western, rule[1], rule[2])
end
local ipa1 = (western ~= phonetic) and "\n** " .. m_IPA.format_IPA_multiple(lang, {{pron='[' .. western .. ']', q={"Western"}}}) or ""
local surgut = phonetic
for _, rule in ipairs(surgut_rules) do
surgut = gsub(surgut, rule[1], rule[2])
end
local ipa2 = (surgut ~= phonetic) and "\n** " .. m_IPA.format_IPA_multiple(lang, {{pron='[' .. surgut .. ']', q={"Surgut"}}}) or ""


return "* " .. m_IPA.format_IPA_full(lang, IPA_args)
return "* " .. m_IPA.format_IPA_full{lang = lang, items = {{pron='[' .. phonetic .. ']'}}} .. ipa1 .. ipa2
end
end


return export
return export
Retrieved from "https://duo.linguifex.com/wiki/Module:xchc-pron"