Module:vi-pron
- The following documentation is located at Module:vi-pron/documentation. [edit] Categories were auto-generated by Module:module categorization. [edit]
- Useful links: subpage list • links • transclusions • testcases • sandbox
Pronunciation module for Vietnamese.
local export = {}
local m_str_utils = require("Module:string utilities")
local IPA_module = "Module:IPA"
local parse_utilities_module = "Module:parse utilities"
local lang = require("Module:languages").getByCode("vi")
local ugcodepoint = m_str_utils.gcodepoint
local rsubn = m_str_utils.gsub
local rsplit = m_str_utils.split
local ulen = m_str_utils.len
local ulower = m_str_utils.lower
local rmatch = m_str_utils.match
local usub = m_str_utils.sub
local toNFC = mw.ustring.toNFC
local toNFD = mw.ustring.toNFD
local u = m_str_utils.char
local function rsub(str, from, to)
return (rsubn(str, from, to))
end
local function track(page)
require("Module:debug/track")("vi-pron/" .. page)
return true
end
local function split_on_comma(term)
if not term then
return nil
end
if term:find(",%s") then
return require(parse_utilities_module).split_on_comma(term)
elseif term:find(",") then
return rsplit(term, ",")
else
return {term}
end
end
--àằầèềìòồờùừỳ áắấéếíóốớúứý ảẳẩẻểỉỏổởủửỷ ãẵẫẽễĩõỗỡũữỹ ạặậẹệịọộợụựỵ
local tone_diacritics = {
[u(0x0300)] = 2, -- grave accent = ◌̀
[u(0x0301)] = 3, -- acute accent = ◌́
[u(0x0309)] = 4, -- hook above = ◌̉
[u(0x0303)] = 5, -- tilde = ◌̃
[u(0x0323)] = 6, -- dot under = ◌̣
}
local tone_contour = {
["hn"] = { [1] = "˧˧", [2] = "˨˩", ["3a"] = "˧˦", [3] = "˧˦", [4] = "˧˩", [5] = "˦ˀ˥", [6] = "˧˨ʔ" },
["hue"] = { [1] = "˧˧", [2] = "˦˩", ["3a"] = "˦˧˥", [3] = "˨˩˦", [4] = "˧˨", [5] = "˧˨", [6] = "˨˩ʔ" },
["hcmc"] = { [1] = "˧˧", [2] = "˨˩", ["3a"] = "˦˥", [3] = "˦˥", [4] = "˨˩˦", [5] = "˨˩˦", [6] = "˨˩˨" },
}
local initial_ipa = {
["b"] = { "ʔɓ", "ʔɓ", "ʔɓ" },
["c"] = { "k", "k", "k" },
["ch"] = { "t͡ɕ", "t͡ɕ", "c" },
["d"] = { "z", "j", "j" },
["đ"] = { "ʔɗ", "ʔɗ", "ʔɗ" },
["g"] = { "ɣ", "ɣ", "ɣ" },
["gh"] = { "ɣ", "ɣ", "ɣ" },
["gi"] = { "z", "j", "j" },
["gy"] = { "z", "j", "j" },
["h"] = { "h", "h", "h" },
["k"] = { "k", "k", "k" },
["kh"] = { "x", "kʰ", "kʰ" },
["l"] = { "l", "l", "l" },
["m"] = { "m", "m", "m" },
["n"] = { "n", "n", "n" },
["ng"] = { "ŋ", "ŋ", "ŋ" },
["ngh"] = { "ŋ", "ŋ", "ŋ" },
["nh"] = { "ɲ", "ɲ", "ɲ" },
["p"] = { "p", "p", "p" }, -- foreign
["ph"] = { "f", "f", "f" },
["q"] = { "k", "k", "k" },
["qu"] = { "kw", "kw", "w" },
["r"] = { "z", "ʐ", "ɹ" },
["ŕ"] = { "ɹ", "ɹ", "ɹ" },
["s"] = { "s", "ʂ", "ʂ" },
["t"] = { "t", "t", "t" },
["th"] = { "tʰ", "tʰ", "tʰ" },
["tr"] = { "t͡ɕ", "ʈ", "ʈ" },
["v"] = { "v", "v", "v" },
["x"] = { "s", "s", "s" },
["z"] = { "z", "z", "z" },
[""] = { "ʔ", "ʔ", "ʔ" },
["-"] = { "", "", "" },
}
local mvi_initial_ipa = {
["ꞗ"] = "β", ["Ꞗ"] = "β",
["b"] = "ɓ",
["c"] = "k", ["ch"] = "c",
["d"] = "ð", ["đ"] = "ɗ",
["g"] = "ɣ", ["gh"] = "ɣ", ["gi"] = "ʝ",
["h"] = "h",
["k"] = "k", ["kh"] = "kʰ",
["l"] = "l",
["m"] = "m",
["n"] = "n", ["ng"] = "ŋ", ["ngh"] = "ŋ", ["nh"] = "ɲ",
["p"] = "p", ["ph"] = "pʰ",
["r"] = "ɹ",
["s"] = "ʂ",
["t"] = "t", ["th"] = "tʰ", ["tr"] = "ʈ",
["v"] = "w",
["x"] = "ɕ",
}
local final_ipa = {
["a"] = { "aː", "aː", "aː" },
["ac"] = { "aːk̚", "aːk̚", "aːk̚" },
["ach"] = { "ajk̟̚", "at̚", "at̚" },
["ai"] = { "aːj", "aːj", "aːj" },
["am"] = { "aːm", "aːm", "aːm" },
["an"] = { "aːn", "aːŋ", "aːŋ" },
["ań"] = { "aːn", "aːn", "aːn" },
["ang"] = { "aːŋ", "aːŋ", "aːŋ" },
["anh"] = { "ajŋ̟", "ɛɲ", "an" },
["ao"] = { "aːw", "aːw", "aːw" },
["ao᷄"] = { "awŋ͡m", "", "" },
["ap"] = { "aːp̚", "aːp̚", "aːp̚" },
["at"] = { "aːt̚", "aːk̚", "aːk̚" },
["au"] = { "aw", "aw", "a(ː)w" },
["ay"] = { "aj", "aj", "a(ː)j" },
["ăc"] = { "ak̚", "ak̚", "ak̚" },
["ăm"] = { "am", "am", "am" },
["ăn"] = { "an", "aŋ", "aŋ" },
["ăng"] = { "aŋ", "aŋ", "aŋ" },
["ăp"] = { "ap̚", "ap̚", "ap̚" },
["ăt"] = { "at̚", "ak̚", "ak̚" },
["â"] = { "ə", "ə", "ə" },
["âc"] = { "ək̚", "ək̚", "ək̚" },
["âm"] = { "əm", "əm", "əm" },
["ân"] = { "ən", "əŋ", "əŋ" },
["âng"] = { "əŋ", "əŋ", "əŋ" },
["âp"] = { "əp̚", "əp̚", "əp̚" },
["ât"] = { "ət̚", "ək̚", "ək̚" },
["âu"] = { "əw", "əw", "əw" },
["ây"] = { "əj", "əj", "əj" },
["e"] = { "ɛ", "ɛ", "ɛ" },
["ec"] = { "ɛk̚", "ɛk̚", "ɛk̚" },
["em"] = { "ɛm", "ɛm", "ɛm" },
["en"] = { "ɛn", "ɛŋ", "ɛŋ" },
["eń"] = { "ɛn", "ɛn", "ɛn" },
["eng"] = { "ɛŋ", "ɛŋ", "ɛŋ" },
["eo"] = { "ɛw", "ɛw", "ɛw" },
["ep"] = { "ɛp̚", "ɛp̚", "ɛp̚" },
["et"] = { "ɛt̚", "ɛt̚", "ɛk̚" },
["ê"] = { "e", "ej", "ej" },
["êc"] = { "ek̚", "ek̚", "ek̚" },
["êch"] = { "əjk̟̚", "et̚", "əːt̚" },
["êm"] = { "em", "em", "em" },
["ên"] = { "en", "en", "əːn" },
["êng"] = { "eŋ", "eŋ", "eŋ" },
["ênh"] = { "əjŋ̟", "en", "əːn" },
["êp"] = { "ep̚", "ep̚", "ep̚" },
["êt"] = { "et̚", "et̚", "əːt̚" },
["êu"] = { "ew", "ew", "ew" },
["i"] = { "i", "ɪj", "ɪj" },
["ia"] = { "iə", "iə", "iə" },
["ic"] = { "ïk̟̚", "ïk̟̚", "ïk̟̚" },
["ich"] = { "ïk̟̚", "ɨt̚", "ɨt̚" },
["iêc"] = { "iək̚", "iək̚", "iək̚" },
["iêm"] = { "iəm", "iəm", "im" },
["iên"] = { "iən", "iəŋ", "iəŋ" },
["iêng"] = { "iəŋ", "iəŋ", "iəŋ" },
["iêp"] = { "iəp̚", "iəp̚", "ip̚" },
["iêt"] = { "iət̚", "iək̚", "iək̚" },
["iêu"] = { "iəw", "iw", "iw" },
["im"] = { "im", "im", "im" },
["in"] = { "in", "in", "ɨn" },
["inh"] = { "ïŋ", "ɨn", "ɨn" },
["ip"] = { "ip̚", "ip̚", "ip̚" },
["it"] = { "it̚", "it̚", "ɨt̚" },
["iu"] = { "iw", "iw", "iw" },
["o"] = { "ɔ", "ɔ", "ɔ" },
["oa"] = { "waː", "waː", "waː" },
["oac"] = { "waːk̚", "waːk̚", "waːk̚" },
["oach"] = { "wajk̟̚", "wat̚", "wat̚" },
["oai"] = { "waːj", "waːj", "waːj" },
["oam"] = { "waːm", "waːm", "waːm" },
["oan"] = { "waːn", "waːŋ", "waːŋ" },
["oang"] = { "waːŋ", "waːŋ", "waːŋ" },
["oanh"] = { "wajŋ̟", "wɛɲ", "wan" },
["oao"] = { "waːw", "waːw", "waːw" },
["oap"] = { "waːp̚", "waːp̚", "waːp̚" },
["oat"] = { "waːt̚", "waːk̚", "waːk̚" },
["oay"] = { "waj", "waj", "waj" },
["oă"] = { "wa", "wa", "wa" },
["oăc"] = { "wak̚", "wak̚", "wak̚" },
["oăm"] = { "wam", "wam", "wam" },
["oăn"] = { "wan", "waŋ", "waŋ" },
["oăng"] = { "waŋ", "waŋ", "waŋ" },
["oăt"] = { "wat̚", "wak̚", "wak̚" },
["oc"] = { "awk͡p̚", "awk͡p̚", "awk͡p̚" },
["oe"] = { "wɛ", "wɛ", "wɛ" },
["oem"] = { "wɛm", "wɛm", "wɛm" },
["oen"] = { "wɛn", "wɛŋ", "wɛŋ" },
["oeo"] = { "wɛw", "wɛw", "wɛw" },
["oet"] = { "wɛt̚", "wɛk̚", "wɛk̚" },
["oi"] = { "ɔj", "ɔj", "ɔj" },
["om"] = { "ɔm", "ɔm", "ɔm" },
["on"] = { "ɔn", "ɔŋ", "ɔŋ" },
["ong"] = { "awŋ͡m", "awŋ͡m", "awŋ͡m" },
["ooc"] = { "ɔk̚", "ɔk̚", "ɔk̚" },
["oong"] = { "ɔŋ", "ɔŋ͡m", "ɔŋ" },
["op"] = { "ɔp̚", "ɔp̚", "ɔp̚" },
["ot"] = { "ɔt̚", "ɔk̚", "ɔk̚" },
["ô"] = { "o", "ow", "ow" },
["ôc"] = { "əwk͡p̚", "əwk͡p̚", "əwk͡p̚" },
["ôi"] = { "oj", "oj", "oj" },
["ôm"] = { "om", "om", "om" },
["ôn"] = { "on", "oŋ", "oŋ" },
["ôń"] = { "on", "on", "on" },
["ông"] = { "əwŋ͡m", "əwŋ͡m", "əwŋ͡m" },
["ôôc"] = { "ok̚", "ok̚", "ok̚" },
["ôông"] = { "oŋ", "oŋ", "oŋ" },
["ôp"] = { "op̚", "op̚", "op̚" },
["ôt"] = { "ot̚", "ok̚", "ok̚" },
["ơ"] = { "əː", "əː", "əː" },
["ơi"] = { "əːj", "əːj", "əːj" },
["ơm"] = { "əːm", "əːm", "əːm" },
["ơn"] = { "əːn", "əːŋ", "əːŋ" },
["ơng"] = { "əːŋ", "əːŋ", "əːŋ" },
["ơp"] = { "əːp̚", "əːp̚", "əːp̚" },
["ơt"] = { "əːt̚", "əːk̚", "əːk̚" },
["u"] = { "u", "ʊw", "ʊw" },
["ua"] = { "uə", "uə", "uə" },
["uac"] = { "waːk̚", "waːk̚", "waːk̚" },
["uach"] = { "wajk̟̚", "wat̚", "wat̚" },
["uai"] = { "waːj", "waːj", "waːj" },
["uan"] = { "waːn", "waːŋ", "waːŋ" },
["uang"] = { "waːŋ", "waːŋ", "waːŋ" },
["uanh"] = { "wajŋ̟", "wɛɲ", "wan" },
["uao"] = { "waːw", "waːw", "waːw" },
["uap"] = { "waːp̚", "waːp̚", "waːp̚" },
["uat"] = { "waːt̚", "waːk̚", "waːk̚" },
["uau"] = { "waw", "waw", "wa(ː)w" },
["uay"] = { "waj", "waj", "waj" },
["uă"] = { "wa", "wa", "wa" },
["uăc"] = { "wak̚", "wak̚", "wak̚" },
["uăm"] = { "wam", "wam", "wam" },
["uăn"] = { "wan", "waŋ", "waŋ" },
["uăng"] = { "waŋ", "waŋ", "waŋ" },
["uăp"] = { "wap̚", "wap̚", "wap̚" },
["uăt"] = { "wat̚", "wak̚", "wak̚" },
["uâ"] = { "wə", "wə", "wə" },
["uâc"] = { "wək̚", "wək̚", "wək̚" },
["uân"] = { "wən", "wəŋ", "wəŋ" },
["uâng"] = { "wəŋ", "wəŋ", "wəŋ" },
["uât"] = { "wət̚", "wək̚", "wək̚" },
["uây"] = { "wəj", "wəj", "wəj" },
["uc"] = { "ʊwk͡p̚", "ʊwk͡p̚", "ʊwk͡p̚" },
["ue"] = { "wɛ", "wɛ", "wɛ" },
["uen"] = { "wɛn", "wɛŋ", "wɛŋ" },
["ueo"] = { "wɛw", "wɛw", "wɛw" },
["uep"] = { "wɛp̚", "wɛp̚", "wɛp̚" },
["uet"] = { "wɛt̚", "wɛt̚", "wɛt̚" },
["uê"] = { "we", "wej", "wej" },
["uêch"] = { "wəjk̟̚", "wet̚", "wəːt̚" },
["uên"] = { "wen", "wen", "wəːn" },
["uênh"] = { "wəjŋ̟", "wen", "wəːn" },
["uêt"] = { "wet̚", "wet̚", "wəːt̚" },
["uêu"] = { "weu", "weu", "wew" },
["ui"] = { "uj", "uj", "uj" },
["uin"] = { "win", "win", "wɨn" },
["uit"] = { "wit̚", "wit̚", "wit̚" },
["um"] = { "um", "um", "ʊm" },
["un"] = { "un", "un", "ʊwŋ͡m" },
["ung"] = { "ʊwŋ͡m", "ʊwŋ͡m", "ʊwŋ͡m" },
["unh"] = { "ujŋ̟", "un", "uwn" },
["uo"] = { "wɔ", "wɔ", "wɔ" },
["uô"] = { "uə", "uə", "uə" },
["uôc"] = { "uək̚", "uək̚", "uək̚" },
["uôi"] = { "uəj", "uj", "uj" },
["uôm"] = { "uəm", "uəm", "uəm" },
["uôn"] = { "uən", "uəŋ", "uəŋ" },
["uông"] = { "uəŋ", "uəŋ", "uəŋ" },
["uôt"] = { "uət̚", "uək̚", "uək̚" },
["uơ"] = { "wəː", "wəː", "wəː" },
["uơi"] = { "wəːj", "wəːj", "wəːj" },
["uơn"] = { "wəːn", "wəːŋ", "wəːŋ" },
["uơt"] = { "wəːt̚", "wəːk̚", "wəːk̚" },
["up"] = { "up̚", "up̚", "ʊp̚" },
["ut"] = { "ut̚", "ʊk̚", "ʊk͡p̚" },
["uy"] = { "wi", "wɪj", "wɪj" },
["uya"] = { "wiə", "wiə", "wiə" },
["uych"] = { "wïk̟̚", "wɨk̟̚", "wɨt̚" },
["uyn"] = { "win", "win", "wɨn" },
["uich"] = { "wïk̟̚", "wɨk̟̚", "wɨt̚" },
["uyê"] = { "wiə", "wiə", "wiə" },
["uyên"] = { "wiən", "wiəŋ", "wiəŋ" },
["uyênh"] = { "wiəŋ̟", "wiən", "wən" },
["uyêt"] = { "wiət̚", "wiək̚", "wiək̚" },
["uynh"] = { "wïŋ̟", "wɨn", "wɨn" },
["uyp"] = { "wip̚", "wip̚", "wip̚" },
["uyt"] = { "wit̚", "wɨt̚", "wɨt̚" },
["uyu"] = { "wiw", "wiw", "wiw" },
["ư"] = { "ɨ", "ɨ", "ɨ" },
["ưa"] = { "ɨə", "ɨə", "ɨə" },
["ưc"] = { "ɨk̚", "ɨk̚", "ɨk̚" },
["ưi"] = { "ɨj", "ɨj", "ɨj" },
["ưm"] = { "ɨm", "ɨm", "ɨm" },
["ưn"] = { "ɨn", "ɨŋ", "ɨŋ" },
["ưng"] = { "ɨŋ", "ɨŋ", "ɨŋ" },
["ươc"] = { "ɨək̚", "ɨək̚", "ɨək̚" },
["ươi"] = { "ɨəj", "ɨj", "ɨj" },
["ươm"] = { "ɨəm", "ɨəm", "ɨəm" },
["ươn"] = { "ɨən", "ɨəŋ", "ɨəŋ" },
["ương"] = { "ɨəŋ", "ɨəŋ", "ɨəŋ" },
["ươp"] = { "ɨəp̚", "ɨəp̚", "ɨəp̚" },
["ươt"] = { "ɨət̚", "ɨək̚", "ɨək̚" },
["ươu"] = { "iəw", "ɨəw", "ɨəw" },
["ưt"] = { "ɨt̚", "ɨk̚", "ɨk̚" },
["ưu"] = { "iw", "ɨw", "ɨw" },
["y"] = { "i", "ɪj", "ɪj" },
["yêc"] = { "iək̚", "iək̚", "iək̚" },
["yêm"] = { "iəm", "iəm", "iəm" },
["yên"] = { "iən", "iəŋ", "iəŋ" },
["yêng"] = { "iəŋ", "iəŋ", "iəŋ" },
["yêp"] = { "iəp̚", "iəp̚", "iəp̚" },
["yêt"] = { "iət̚", "iək̚", "iək̚" },
["yêu"] = { "iəw", "iw", "iw" },
}
local varieties = {
["hn"] = { "Hà Nội", 1 },
["hue"] = { "Huế", 2 },
["hcmc"] = { "Hồ Chí Minh City", 3 },
}
local hcmc_opt_w = {
["ch"] = true,
["d"] = true,
["l"] = true,
["s"] = true,
["t"] = true, ["th"] = true, ["tr"] = true,
["x"] = true,
}
local variations = {
["hn"] = { { "^ɹ", "z" }, { " ɹ", " z" } },
["hue"] = { { "z", "j" }, { "ʂ", "s" }, { "kʰ", "x" }, { "awŋ͡m", "ɔŋ" } },
["hcmc"] = { { "ʂ", "s" }, { "v", "j" }, { "kʰ", "x" }, { "z", "j" } },
}
function export.ipa(frame)
local respellings = {}
local variety_respellings = {}
local output = {}
for variety, _ in pairs(varieties) do
output[variety] = {}
end
local output_text = {}
local iparams = {
["mvi"] = {type = "boolean"},
}
local iargs = require("Module:parameters").process(frame.args, iparams)
local params = {
[1] = {list = true},
["hn"] = {},
["hue"] = {},
["hcmc"] = {},
["pagename"] = {}, -- for testing or documentation
}
local args = require("Module:parameters").process(frame:getParent().args, params)
local pagename = args.pagename or mw.loadData("Module:headword/data").pagename
local function canonicalize_respelling(respelling)
if respelling:find("^raw:") then
return {raw = (respelling:gsub("^raw:", ""))}
else
if respelling == "+" then
respelling = pagename
end
return {respelling = rsub(rsub(ulower(respelling), "%-", " "), ",", "")}
end
end
local mvi = iargs.mvi
local raw_respellings = args[1]
if not raw_respellings[1] then
raw_respellings = {"+"}
end
for _, raw_respelling in ipairs(raw_respellings) do
table.insert(respellings, canonicalize_respelling(raw_respelling))
end
for variety, _ in pairs(varieties) do
if args[variety] == "-" or (mvi and (variety == "hue" or variety == "hcmc")) then
variety_respellings[variety] = false
elseif args[variety] then
local variety_raw_respellings = split_on_comma(args[variety])
variety_respellings[variety] = {}
for _, raw_respelling in ipairs(variety_raw_respellings) do
table.insert(variety_respellings[variety], canonicalize_respelling(raw_respelling))
end
end
end
for variety, location in pairs(varieties) do
if variety_respellings[variety] == false then
-- skip variety
output[variety] = false
else
local var_respellings = variety_respellings[variety] or respellings
for i, spec in ipairs(var_respellings) do
local pronunciation = {}
if spec.raw then
table.insert(output[variety], spec.raw)
else
for syllable in mw.text.gsplit(spec.respelling, " ", true) do
local ipa = {}
local initial, final, tone = nil, nil, nil
tone = 1
syllable = toNFD(syllable)
syllable = rsub(syllable, "([nr]́)", toNFC)
for diac_pattern, tone_num in pairs(tone_diacritics) do
if rmatch(syllable, diac_pattern) then
tone = tone_num
break
end
end
syllable = toNFC(rsub(syllable, "[̣̀́̉̃]", ""))
if syllable == "gi" or syllable == "gin" then
syllable = rsub(syllable, "gi", "gii")
end
initial = rmatch(syllable, "^g[ꞗꞖbcdđgklmnpqrŕstvx]+") or rmatch(syllable, "^(g[hiy])[^cmnpt]")
or rmatch(syllable, "^g") or rmatch(syllable, "^[ꞗꞖbcdđghklmnpqrŕstvxz]+") or ""
initial = (rmatch(syllable, "^giê.") and syllable ~= "giên") and "d" or initial
initial = rmatch(syllable, "qu$") and "qu" or initial
final = usub(syllable, ulen(initial) + 1, -1)
local ipa, seq, detoned = {}, location[2], ""
if mvi then
if mvi_initial_ipa[initial] then
table.insert(ipa, mvi_initial_ipa[initial])
else
local initial_cluster = ""
for cc in ugcodepoint(initial) do
local ch = u(cc)
initial_cluster = initial_cluster .. mvi_initial_ipa[ch]
end
table.insert(ipa, initial_cluster)
end
elseif initial_ipa[initial] then
table.insert(ipa, initial_ipa[initial][seq])
else
local initial_cluster = ""
initial = rsub(initial, "r$", "ŕ")
for cc in ugcodepoint(initial) do
local ch = u(cc)
initial_cluster = initial_cluster .. initial_ipa[ch][seq]
end
initial_cluster = rsub(initial_cluster, "([cgknpt]h)", function(digraph)
return initial_ipa[digraph][seq] end)
table.insert(ipa, initial_cluster)
end
if final_ipa[final] then
detoned = rsub(final_ipa[final][seq], "^([wu].+)", function(nucleus)
if initial .. final == "qua" then
nucleus = final_ipa["oa"][seq]
elseif initial .. final == "qui" then
nucleus = final_ipa["uy"][seq]
end
if variety == "hcmc" then
if initial == "q" then
nucleus = rsub(nucleus, "^u", "w")
end
if hcmc_opt_w[initial] then
nucleus = rsub(nucleus, "^w", "⁽ʷ⁾")
end
end
return nucleus end)
table.insert(ipa, detoned)
else
error(("Unrecognised final: \"%s\""):format(final))
end
if tone == 3 and rmatch(final, "[chmngpt]") then
tone = "3a"
end
table.insert(ipa, tone_contour[variety][tone])
table.insert(pronunciation, table.concat(ipa, ""))
end
table.insert(output[variety], "[" .. table.concat(pronunciation, " ") .. "]")
end
end
end
end
for variety, location in pairs(varieties) do
if mvi and variety == "hn" then
location[1] = "Đông Kinh"
end
if output[variety] ~= false then
local ipa_items = {}
for i, out in ipairs(output[variety]) do
if variety == "hcmc" then
-- FIXME: Move this up to the pronunciation-computing loop.
out = rsub(out, "[hk]w", "w")
out = rsub(out, "ʔw", "(ʔ)w")
end
table.insert(ipa_items, {pron = out, separator = i == 1 and "" or ", "})
local alternative = out
for _, variation in ipairs(variations[variety]) do
alternative = rsub(alternative, variation[1], variation[2])
end
if alternative ~= out then
table.insert(ipa_items, {pron = alternative, separator = " ~ "})
end
end
table.insert(output_text, location[2], "\n* " .. require("Module:IPA").format_IPA_full {
lang = lang,
a = {location[1]},
items = ipa_items,
separator = "",
})
else
table.insert(output_text, location[2], "")
end
end
local saw_raw = false
local actual_respellings = {}
for _, spec in ipairs(respellings) do
if spec.raw then
saw_raw = true
break
else
table.insert(actual_respellings, spec.respelling)
end
end
if not saw_raw and table.concat(actual_respellings, "") ~= ulower(pagename) then
table.insert(output_text, #output_text + 1, "\n* ''Phonetic spelling'': " .. rsub(table.concat(actual_respellings, ", "), "ŕ", "R"))
end
return rsub(table.concat(output_text, ""), "^\n(.)", "%1")
end
return export