မော်ဂျူး:ja-pron
Documentation for this module may be created at မော်ဂျူး:ja-pron/doc
local export = {}
local gsub = mw.ustring.gsub
local match = mw.ustring.match
local sub = mw.ustring.sub
local len = mw.ustring.len
local lang = require("Module:languages").getByCode("ja")
local m_ja = require("Module:ja")
local m_accent = require("Module:accent qualifier")
-- also [[Module:qualifier]]
local PAGENAME = mw.title.getCurrentTitle().text
local function quote(text)
return "“" .. text .. "”"
end
function export.show(frame)
local params = {
[1] = {default = PAGENAME, list = true},
["y"] = {alias_of = "yomi"},
["yomi"] = {},
["accent"] = {list = true},
["accent=_loc"] = {list = true},
["accent=_ref"] = {list = true},
["accent=_note"] = {list = true},
["acc"] = {alias_of = "accent", list = true},
["acc=_loc"] = {alias_of = "accent_loc", list = true}, -- using "accent=_loc" (etc.) doesn't work
["acc=_ref"] = {alias_of = "accent_ref", list = true},
["acc=_note"] = {alias_of = "accent_note", list = true},
["dev"] = {},
["dev2"] = {},
["devm"] = {},
["noipa"] = {},
["a"] = {alias_of = "audio"},
["audio"] = {}
}
local args = require("Module:parameters").process(frame:getParent().args, params)
local yomi, au = args.yomi, args.audio
local dev, dev2, devm = args.dev, args.dev2, args.devm
local maxindex = table.getn(args[1])
local result = ""
local text
local yomi_types = {
o = "on", on = "on",
go = "goon", goon = "goon",
ko = "kanon", kan = "kanon", kanon = "kanon",
to = "toon", toon = "toon",
ky = "kanyoon", kanyo = "kanyoon", kanyoon = "kanyoon",
k = "kun", kun = "kun",
j = "ju", ju = "ju",
y = "yu", yu = "yu",
i = "irregular", irr = "irregular", irreg = "irregular", irregular = "irregular",
}
local yomi_text = {
on = "[[:en:音読み#ဂျပန်|အွန်ယိုမီ]]",
goon = "[[:en:音読み#ဂျပန်|အွန်ယိုမီ]]: [[:en:呉音#ဂျပန်|ဂိုးအွန်]]",
kanon = "[[:en:音読み#ဂျပန်|အွန်ယိုမီ]]: [[:en:漢音#ဂျပန်|ကန်အွန်]]",
toon = "[[:en:音読み#Japanese|အွန်ယိုမီ]]: [[:en:唐音#ဂျပန်|တိုးအွန်]]",
kanyoon = "[[:en:慣用読み#ဂျပန်|ကန်ယိုးယိုမီ]]",
kun = "[[:en:訓読み#ဂျပန်|ကုန်ယိုမီ]]",
ju = "[[:en:重箱読み#ဂျပန်|ဂျူးဘာကိုယိုမီ]]",
yu = "[[:en:湯桶読み#ဂျပန်|ယုတိုးယိုမီ]]",
irregular = require("Module:qualifier").format_qualifier("ပုံမှန်မဟုတ်သော ဖတ်ပုံများ")
}
-- Deals with the yomi
if yomi then
if yomi_types[yomi] then
yomi = yomi_types[yomi]
else
error("The yomi type " .. quote(yomi) .. " is not recognized. See Template:ja-pron/documentation for recognized types")
end
local kanji = mw.ustring.gsub(PAGENAME, "[^" .. require("Module:scripts").getByCode("Hani"):getCharacters() .. "]+", "")
if mw.ustring.len(kanji) ~= 2 and (yomi == "ju" or yomi == "yu") then
require("Module:debug").track("ja-pron/incorrect yutou or juubako")
end
result = "* " .. yomi_text[yomi]
end
-- Deals with the accents
local a, al, ar, an = args.accent, args.accent_loc, args.accent_ref, args.accent_note
for i, position in ipairs(a) do
text = args[1][math.min(maxindex,i)]
if yomi then result = result .. "\n**" else result = result .. "\n*"
end
if not al[i] then
al[i] = "[[w:တိုကျိုမြို့|တိုကျို]]"
end
result = result .. m_accent.show({al[i]}) .. " "
result = result .. export.accent(text, position, dev, dev2, devm)
if ar[i] then
result = result .. frame:expandTemplate{title = "ja-pron/acc-ref", args = {ar[i]}}
end
result = result .. (an[i] and (" " .. an[i]) or "")
end
-- Deals with the IPA
if not noipa then
local m_IPA = require("Module:IPA")
for i, text in ipairs(args[1]) do
local sortkey = m_ja.jsort(text)
result = result .. (yomi and "\n**" or "\n*")
result = result .. m_IPA.format_IPA_full(lang, {{ pron = "[" .. export.ipa(text, dev, dev2, devm) .. "]" }}, nil, nil, sortkey)
end
end
-- Deals with the audio
if au then
sortkey = m_ja.jsort(args[1][1])
if yomi then result = result .. "\n**" else result = result .. "\n*"
end
result = result .. ' <table class="audiotable" style="vertical-align: top; display:inline-block; list-style:none;line-height: 1em;"><tr><td class="unicode audiolink">အသံ</td><td class="audiofile">[[Image:' .. au .. '|noicon|175px]]</td><td class="audiometa" style="font-size: 80%;">([[:Image:' .. au ..'|file]])</td></tr></table>[[ကဏ္ဍ:အသံလင့်ခ်များ ပါဝင်သော ဂျပန် ဝေါဟာရများ|' .. sortkey .. ']]'
end
return result
end
function export.ipa(text, dev, dev2, devm)
if type(text) == "table" then
text, dev, dev2, devm = text.args[1], text.args["dev"], text.args["dev2"], text:getParent().args["devm"] end
dev = dev or ""
dev2 = dev2 or ""
devm = devm or ""
if dev2 ~= "" then error('Please remove parameter dev2 and change parameter dev to \"dev=' .. dev .. ',' .. dev2 .. '"') end
local position_kana = {}
local position_mora = {}
for i=1,mw.ustring.len(text) do
if sub(text,i,i) ~= ' ' then
table.insert(position_kana, i)
if not mw.ustring.match(sub(text,i,i), "[ァィゥェォャュョヮぁぃぅぇぉゃゅょゎ]") then
table.insert(position_mora, i)
end
end
end
if dev ~= "" then
for position in mw.text.gsplit(dev,",") do
position = position_kana[tonumber(position)]
text = sub(text, 1, position) .. "̥" .. sub(text, position + 1, -1)
for i=position+1,table.getn(position_kana) do
position_kana[i] = position_kana[i] + 1
end
end
end
if devm ~= "" then
for position in mw.text.gsplit(devm,",") do
position = tonumber(position)
if #position_mora == position then
text = text .. "̥"
else
position = position_mora[tonumber(position)+1]
text = sub(text, 1, position-1) .. "̥" .. sub(text, position, -1)
end
for i=position+1,table.getn(position_mora) do
position_mora[i] = position_mora[i] + 1
end
end
end
text = m_ja.kana_to_romaji(text, { keep_period = true })
text = gsub(text, "'", "ʔ")
text = gsub(text, "[ptkbjgzsdr][ptckbjgzsdr][hs]?", {
["pp"] = "p̚p", ["tch"] = "t̚ch", ["kk"] = "k̚k", ["bb"] = "b̚b̥", ["jj"] = "d̚j",
["dd"] = "d̚d̥", ["gg"] = "g̚g̊", ["zz"] = "d̚z", ["tt"] = "t̚t", ["tts"] = "t̚ts",
["rr"] = "r̚r", ["ssh"] = "ɕː" })
text = gsub(text, "ei", "ē")
text = gsub(text, "[āēīōūfvjryz]", {
["ā"] = "aː", ["ē"] = "eː", ["ī"] = "iː", ["ō"] = "oː", ["ū"] = "uː",
["f"] = "ɸ", ["v"] = "b", ["j"] = "d͡ʑ", ["r"] = "ɾ", ["y"] = "j", ["z"] = "d͡z" })
text = gsub(text, "[sct][hs]", {
["sh"] = "ɕ",
["ch"] = "t͡ɕ",
["ts"] = "t͡s" })
text = gsub(text, "([aeiouː̥])d͡([zʑ])", "%1%2")
text = gsub(text, "([pbtdkgnmɸszɾ][̥̊]?)i", "%1ʲi")
text = gsub(text, "([pbtdkgnmɸszɾ][̥̊]?)j", "%1ʲ")
text = gsub(text, "nʲ", "ɲ̟")
text = gsub(text, "([^ ː])(ː?)n([^aeou])", "%1̃%2n%3")
for i, args in pairs{
{ "(ː?)n$", "̃%1ɴ" },
{ "n( ?)([pbm])", "m%1%2" },
{ "n( ?)(.͡[ɕʑ])", "ɲ̟%1%2" },
{ "n( ?)ɲ̟", "ɲ̟%1ɲ̟" },
{ "n( ?)([kg])(ʲ?)", "ŋ%1%3%2%3" },
{ "n( ?)([ɸszɕhjw])", "ɰ̃%1%2" },
{ "n'", "ɰ̃" },
{ "n ([aeiou])", "ɰ̃ %1" },
} do
text = gsub(text, args[1], args[2])
end
text = gsub(text, "h[iju]", {
["hi"] = "çi", ["hj"] = "ç",
["hu"] = "ɸu" })
text = gsub(text, "h([çɸ])", "%1%1")
text = gsub(text, "([snhçɸmɾjw])%1", "%1ː")
text = gsub(text, "ːʲ", "ʲː")
text = gsub(text, "̚(.[̥̊]?)ʲ", "̚ʲ%1ʲ")
text = gsub(text, "[aeiouw]", {
["a"] = "a̠",
["e"] = "e̞",
["o"] = "o̞",
["u"] = "ɯ̟ᵝ",
["w"] = "ɰᵝ"})
text = gsub(text, "([szɕʑɲçʲ])ɯ̟", "%1ɨ")
text = gsub(text, "ᵝ̥", "̥ᵝ")
text = gsub(text, "ᵝ̃", "̃ᵝ")
text = gsub(text, "̠[̥̃][̥̃]", "̥̃˗")
text = gsub(text, "̞[̥̃][̥̃]", "̥̃˕")
text = gsub(text, "̟[̥̃][̥̃]", "̥̃˖")
text = gsub(text, "([̠̞̟])̥", "%1̊")
text = gsub(text, "%.", "")
text = gsub(text, "'", ".")
text = gsub(text, "g", "ɡ")
return text
end
function export.rise_and_fall(word, rftype)
word = gsub(word, "([おこごそぞとどのほぼぽもよろぉょオコゴソゾトドノホボポモヨロォョ])([うウ])", "%1.%2")
word = gsub(word, "([えけげせぜてでねへべぺめれゑぇエケゲセゼテデネヘベペメレェ])([いイ])", "%1.%2")
word = m_ja.kana_to_romaji(word)
if rftype == "rise" then
word = gsub(word, ".", {
["a"] = "á", ["e"] = "é", ["i"] = "í", ["o"] = "ó", ["u"] = "ú",
["ā"] = "áá", ["ē"] = "éé", ["ī"] = "íí", ["ō"] = "óó", ["ū"] = "úú" })
word = gsub(gsub(word, "n([bcdfghjkmnprstvw%'z ])", "ń%1"), "n$", "ń")
elseif rftype == "fall" then
word = gsub(word, ".", {
["a"] = "à", ["e"] = "è", ["i"] = "ì", ["o"] = "ò", ["u"] = "ù",
["ā"] = "àà", ["ē"] = "èè", ["ī"] = "ìì", ["ō"] = "òò", ["ū"] = "ùù" })
word = gsub(gsub(word, "n([bcdfghjkmnprstvw%'z ])", "ǹ%1"), "n$", "ǹ")
else
return error("Type not recognised.")
end
return word
end
function export.accent(text, class, dev, dev2, devm)
if(type(text)) == "table" then text, class, dev, dev2, devm = text.args[1], text.args[2], text.args["dev"], text.args["dev2"], text.args["devm"] end
text = gsub(text, "([おこごそぞとどのほぼぽもよろぉょオコゴソゾトドノホボポモヨロォョ])[うウ]", "%1ー")
text = gsub(text, "([えけげせぜてでねへべぺめれゑぇエケゲセゼテデネヘベペメレェ])[いイ]", "%1ー")
text = gsub(text, "%.", "")
if dev == "" then dev = false end
if dev2 == "" then dev2 = false end
if devm == "" then devm = false end
local down_first = "<span style=\"border-top:1px solid black;position:relative;padding:1px;\">"
local down_last = "<span style=\"position:absolute;top:0;bottom:67%;right:0%;border-right:1px solid black;\">​</span></span>"
local high_first = "<span style=\"border-top:1px solid black\">"
local start = "<span lang=\"ja\" class=\"Jpan\">"
local romaji_start = " <span class=\"Latn\"><samp>["
local romaji_last = "]</samp></span> "
local last = "</span>"
local position_kana = {} --position of each kana (ぁ counted), text without space
local position_mora = {} --position of each mora (ぁ not counted), text without space
local position_mora_space = {} --position of each mora (ぁ not counted), text with space
for i=1,mw.ustring.len(text) do
if not mw.ustring.match(sub(text,i,i), "[ァィゥェォャュョヮぁぃぅぇぉゃゅょゎ ]") then
local extra = mw.ustring.len(mw.ustring.match(sub(text,i+1), "^[ァィゥェォャュョヮぁぃぅぇぉゃゅょゎ]*"))
table.insert(position_mora_space, i+extra)
end
end
local space_removed = mw.ustring.gsub(text," ","")
for i=1,mw.ustring.len(space_removed) do
table.insert(position_kana, i)
if not mw.ustring.match(sub(space_removed,i,i), "[ァィゥェォャュョヮぁぃぅぇぉゃゅょゎ]") then
local extra = mw.ustring.len(mw.ustring.match(sub(space_removed,i+1), "^[ァィゥェォャュョヮぁぃぅぇぉゃゅょゎ]*"))
table.insert(position_mora, i+extra)
end
end
if match(class, "^[h0]$") then
acc_type, acc_number = "h", 0
elseif match(class, "^[a1]$") then
acc_type, acc_number = "a", 1
elseif match(class, "^o$") then
acc_type = "o"
end
if match(class, "^[0-9]+$") and not match(class,"^[01]$") then
class = gsub(class, "[on]", "")
acc_number = tonumber(class)
morae_count = len(gsub(text, "[ァィゥェォャュョヮぁぃぅぇぉゃゅょゎ ]", ""))
if morae_count == acc_number then
acc_type = "o"
elseif morae_count < acc_number then
return error("Mora count is smaller than position of downstep mora.")
else
acc_type = "n"
end
elseif not acc_number then
acc_number = class
end
local start_index = 1
while match(sub(text, start_index+1, start_index+1), "[ァィゥェォャュョヮぁぃぅぇぉゃゅょゎ]") do
start_index = start_index + 1
end
local kanas = mw.text.split(gsub(text, " ", ""), "")
local function kana_devoice(text)
return '<span style="border:1px dotted gray; border-radius:50%;">' .. text .. "</span>"
end
if dev then
for position in mw.text.gsplit(dev, ",") do
position = tonumber(position)
kanas[position] = kana_devoice(kanas[position])
end
end
if devm then
for position in mw.text.gsplit(devm, ",") do
position = position_mora[tonumber(position)]
kanas[position] = kana_devoice(kanas[position])
end
end
romaji_text = gsub(text, "([おこそとのほもよろをごぞどぼぽょぉオコソトノホモヨロヲゴゾドボポョォ])ー", "%1お")
romaji_text = gsub(romaji_text, "([えけせてねへめれゑげぜでべぺぇエケセテネヘメレヱゲゼデベペェ])ー", "%1え")
romaji_text = gsub(romaji_text, "([うくすつぬふむゆるぐずづぶぷゅうウクスツヌフムユルグズヅブプュゥゔヴ])ー", "%1う")
romaji_text = gsub(romaji_text, "([いきしちにひみりゐぎじぢびぴぃイキシチニヒミリヰギジヂビピィ])ー", "%1い")
romaji_text = gsub(romaji_text, "([あかさたなはまやらわんがざだばぱゃぁアカサタナハマヤラワンガザダバパャァ])ー", "%1あ")
local romajis = mw.text.split(romaji_text, "")
local function count_nspaces(text, index)
local i, sample, nspaces = 0, "", 0
while len(sample) < index do
i = i + 1
sample, nspaces = gsub(sub(text, 1, i), " ", "")
end
return nspaces
end
local function romaji_devoice(text)
return text .. "̥"
end
if dev then
for position in mw.text.gsplit(dev,",") do
position = tonumber(position)
romajis[position] = romaji_devoice(romajis[position])
end
end
if devm then
for position in mw.text.gsplit(devm,",") do
position = position_mora_space[tonumber(position)]
romajis[position] = romaji_devoice(romajis[position])
end
end
if acc_type == "n" then
r_start_index = start_index + count_nspaces(romaji_text, start_index)
local r_index = position_mora_space[acc_number]
local k_index = position_mora[acc_number]
r_parts = {
[1] = table.concat(romajis, "", 1, r_start_index),
[2] = table.concat(romajis, "", r_start_index + 1, r_index),
[3] = table.concat(romajis, "", r_index + 1, #romajis)
}
k_parts = {
[1] = table.concat(kanas, "", 1, start_index),
[2] = table.concat(kanas, "", start_index + 1, k_index),
[3] = table.concat(kanas, "", k_index + 1, #kanas)
}
result = start ..
k_parts[1] ..
down_first ..
k_parts[2] ..
down_last ..
k_parts[3] ..
last ..
romaji_start ..
export.rise_and_fall(r_parts[1], "fall") ..
export.rise_and_fall(r_parts[2], "rise") ..
"ꜜ" ..
export.rise_and_fall(r_parts[3], "fall") ..
romaji_last ..
"([[:en:中高型|နာကာဒါကာ]] – [" .. acc_number .. "])"
else
r_start_index = start_index + count_nspaces(romaji_text, start_index)
r_parts = {
[1] = table.concat(romajis, "", 1, r_start_index),
[2] = table.concat(romajis, "", r_start_index + 1, #romajis)
}
k_parts = {
[1] = table.concat(kanas, "", 1, start_index),
[2] = table.concat(kanas, "", start_index + 1, #kanas)
}
if acc_type == "h" then
result = start ..
k_parts[1] ..
high_first ..
k_parts[2] ..
last ..
last ..
romaji_start ..
export.rise_and_fall(r_parts[1], "fall") ..
export.rise_and_fall(r_parts[2], "rise") ..
romaji_last ..
"([[:en:平板型|ဟေးဘန်]] – [" .. acc_number .. "])"
elseif acc_type == "a" then
result = start ..
down_first ..
k_parts[1] ..
down_last ..
k_parts[2] ..
last ..
romaji_start ..
export.rise_and_fall(r_parts[1], "rise") ..
"ꜜ" ..
export.rise_and_fall(r_parts[2], "fall") ..
romaji_last ..
"([[:en:頭高型|အာတာမာဒါကာ]] – [" .. acc_number .. "])"
elseif acc_type == "o" then
result = start ..
k_parts[1] ..
down_first ..
k_parts[2] ..
down_last ..
last ..
romaji_start ..
export.rise_and_fall(r_parts[1], "fall") ..
export.rise_and_fall(r_parts[2], "rise") ..
"ꜜ" ..
romaji_last ..
"([[:en:尾高型|အိုဒါကာ]] – [" .. acc_number .. "])"
else
return error("Accent type not recognised.")
end
end
result = gsub(result, "(.)̥", "<del>%1</del>") .. (dev and "[[Category:Kenny's testing category]]" or "")
return result
end
return export