မဝ်ဂျူ:th-pron
Documentation for this module may be created at မဝ်ဂျူ:th-pron/doc
local export = {}
local gsub = mw.ustring.gsub
local sub = mw.ustring.sub
local match = mw.ustring.match
local find = mw.ustring.find
local failed_cat = "[[Category:Entries with failed Thai transliterations]]"
local namespace = mw.title.getCurrentTitle().nsText
local thai_range = "[ก-๛̄]"
local categories = {}
local systems = {
["paiboon"] = 1,
["royin"] = 2,
["ipa"] = 3,
["charPhon"] = 4,
["homophone"] = 5,
["file"] = 6
}
local initial = {
["ก"] = { "g", "k", "k", class = "mid" },
["จ"] = { "j", "ch", "t͡ɕ", class = "mid" },
["ด"] = { "d", "d", "d", class = "mid" },
["ฎ"] = { "d", "d", "d", class = "mid" },
["ฏ"] = { "dt", "t", "t", class = "mid" },
["ต"] = { "dt", "t", "t", class = "mid" },
["บ"] = { "b", "b", "b", class = "mid" },
["ป"] = { "bp", "p", "p", class = "mid" },
["อ"] = { "", "@", "ʔ", class = "mid" },
["ง"] = { "ng", "$ng", "ŋ", class = "low" },
["ณ"] = { "n", "n", "n", class = "low" },
["น"] = { "n", "n", "n", class = "low" },
["ม"] = { "m", "m", "m", class = "low" },
["ญ"] = { "y", "y", "j", class = "low" },
["ย"] = { "y", "y", "j", class = "low" },
["ร"] = { "r", "r", "r", class = "low" },
["ล"] = { "l", "l", "l", class = "low" },
["ฬ"] = { "l", "l", "l", class = "low" },
["ว"] = { "w", "w", "w", class = "low" },
["ค"] = { "k", "kh", "kʰ", class = "low" },
["ฅ"] = { "k", "kh", "kʰ", class = "low" },
["ฆ"] = { "k", "kh", "kʰ", class = "low" },
["ข"] = { "k", "kh", "kʰ", class = "high" },
["ฃ"] = { "k", "kh", "kʰ", class = "high" },
["ช"] = { "ch", "ch", "t͡ɕʰ", class = "low" },
["ฌ"] = { "ch", "ch", "t͡ɕʰ", class = "low" },
["ฉ"] = { "ch", "ch", "t͡ɕʰ", class = "high" },
["ฑ"] = { "t", "th", "tʰ", class = "low" },
["ฒ"] = { "t", "th", "tʰ", class = "low" },
["ท"] = { "t", "th", "tʰ", class = "low" },
["ธ"] = { "t", "th", "tʰ", class = "low" },
["ฐ"] = { "t", "th", "tʰ", class = "high" },
["ถ"] = { "t", "th", "tʰ", class = "high" },
["พ"] = { "p", "ph", "pʰ", class = "low" },
["ภ"] = { "p", "ph", "pʰ", class = "low" },
["ผ"] = { "p", "ph", "pʰ", class = "high" },
["ฟ"] = { "f", "f", "f", class = "low" },
["ฝ"] = { "f", "f", "f", class = "high" },
["ซ"] = { "s", "s", "s", class = "low" },
["ศ"] = { "s", "s", "s", class = "high" },
["ษ"] = { "s", "s", "s", class = "high" },
["ส"] = { "s", "s", "s", class = "high" },
["ฮ"] = { "h", "h", "h", class = "low" },
["ห"] = { "h", "h", "h", class = "high" },
["หง"] = { "ng", "$ng", "ŋ", class = "high" },
["หน"] = { "n", "n", "n", class = "high" },
["หม"] = { "m", "m", "m", class = "high" },
["หญ"] = { "y", "y", "j", class = "high" },
["หย"] = { "y", "y", "j", class = "high" },
["หร"] = { "r", "r", "r", class = "high" },
["หล"] = { "l", "l", "l", class = "high" },
["หว"] = { "w", "w", "w", class = "high" },
["…"] = { "…", "…", "…", class = "" },
[""] = { failed_cat, failed_cat, "", class = "" },
}
local vowel = {
["open"] = {
["ะ"] = { "a", "a", "a" },
[""] = { "a", "a", "a" },
["ิ"] = { "i", "i", "i" },
["ึ"] = { "ʉ", "ue", "ɯ" },
["ุ"] = { "u", "u", "u" },
["เะ"] = { "e", "e", "eʔ" },
["แะ"] = { "ɛ", "ae", "ɛʔ" },
["โะ"] = { "o", "o", "oʔ" },
["เาะ"] = { "ɔ", "o", "ɔʔ" },
["็"] = { "ɔ", "o", "ɔ" },
["เิ"] = { "ə", "oe", "ɤ" },
["เอะ"] = { "ə", "oe", "ɤʔ" },
["า"] = { "aa", "a", "aː" },
["ี"] = { "ii", "i", "iː" },
["ู"] = { "uu", "u", "uː" },
["ือ"] = { "ʉʉ", "ue", "ɯː" },
["เ"] = { "ee", "e", "eː" },
["แ"] = { "ɛɛ", "ae", "ɛː" },
["โ"] = { "oo", "o", "oː" },
["อ"] = { "ɔɔ", "o", "ɔː" },
["ร"] = { "ɔɔn", "on", "ɔːn" },
["เอ"] = { "əə", "oe", "ɤː" },
["เียะ"] = { "ia", "ia", "ia̯ʔ" },
["เือะ"] = { "ʉa", "uea", "ɯa̯ʔ" },
["ัวะ"] = { "ua", "ua", "ua̯ʔ" },
["เีย"] = { "iia", "ia", "ia̯" },
["เือ"] = { "ʉʉa", "uea", "ɯa̯" },
["ัว"] = { "uua", "ua", "ua̯" },
["ิว"] = { "iu", "io", "iw" },
["ีว"] = { "iiu", "io", "iːw" },
["เ็ว"] = { "eo", "eo", "ew" },
["แ็ว"] = { "ɛo", "aeo", "ɛw" },
["เา"] = { "ao", "ao", "aw" },
["เว"] = { "eeo", "eo", "eːw" },
["แว"] = { "ɛɛo", "aeo", "ɛːw" },
["าว"] = { "aao", "ao", "aːw" },
["เอว"] = { "əəo", "oeu", "ɤːw" }, --royin inferred
["โว"] = { "oow", "ou", "oːw" }, --royin inferred
["เียว"] = { "iao", "iao", "ia̯w" },
["ัย"] = { "ai", "ai", "aj" },
["ใ"] = { "ai", "ai", "aj" },
["ไ"] = { "ai", "ai", "aj" },
["ไย"] = { "ai", "ai", "aj" },
["ึย"] = { "ʉi", "uei", "ɯj" },
["็อย"] = { "ɔi", "oi", "ɔj" },
["เิ็ย"] = { "əi", "oei", "ɤj" },
["ุย"] = { "ui", "ui", "uj" },
["าย"] = { "aai", "ai", "aːj" },
["อย"] = { "ɔɔi", "oi", "ɔːj" },
["โย"] = { "ooi", "oi", "oːj" },
["เย"] = { "əəi", "oei", "ɤːj" },
["ูย"] = { "uui", "ui", "uːj" },
["วย"] = { "uai", "uai", "ua̯j" },
["เือย"] = { "ʉai", "ueai", "ɯa̯j" },
["ำ"] = { "am", "am", "am" },
},
["closed"] = {
["ั"] = { "a", "a", "a" },
["รร"] = { "a", "a", "a" },
["ิ"] = { "i", "i", "i" },
["ึ"] = { "ʉ", "ue", "ɯ" },
["ุ"] = { "u", "u", "u" },
["เ"] = { "ee", "e", "eː" },
["เ็"] = { "e", "e", "e" },
["แ็"] = { "ɛ", "ae", "ɛ" },
["แ"] = { "ɛɛ", "ae", "ɛː" },
[""] = { "o", "o", "o" },
["็อ"] = { "ɔ", "o", "ɔ" },
["เิ็"] = { "ə", "oe", "ɤ" },
["า"] = { "aa", "a", "aː" },
["ี"] = { "ii", "i", "iː" },
["ื"] = { "ʉʉ", "ue", "ɯː" },
["ู"] = { "uu", "u", "uː" },
["โ"] = { "oo", "o", "oː" },
["อ"] = { "ɔɔ", "o", "ɔː" },
["เิ"] = { "əə", "oe", "ɤː" },
["เอ"] = { "əə", "oe", "ɤː" },
["เีย"] = { "iia", "ia", "ia̯" },
["เือ"] = { "ʉʉa", "uea", "ɯa̯" },
["ว"] = { "uua", "ua", "ua̯" },
["ไ"] = { "ai", "ai", "aj" },
["เา"] = { "ao", "ao", "aw" },
["็อย"] = { "ɔi", "oi", "ɔj" },
}
}
local unromLong = {
["เีย"] = true, ["เือ"] = true, ["ัว"] = true, ["ว"] = true,
["เือย"] = true, ["วาย"] = true, ["เอว"] = true,
["เียว"] = true,
}
local liveExc = {
["ัย"] = true, ["ใ"] = true, ["ไ"] = true, ["ไย"] = true,
["ุย"] = true, ["วย"] = true, ["็อย"] = true, ["เิ็ย"] = true,
["เา"] = true, ["ิว"] = true, ["เ็ว"] = true, ["แ็ว"] = true,
["ำ"] = true,
}
-- ย,ว are not included.
-- ช,ซ,ส,ฟ,ล are changed for loanwords.
-- ห,อ,ฮ can never be codas.
-- ฯ (ʔ) is for Arabic loanwords.
local coda = {
["ก"] = { "k", "k", "k̚" },
["ข"] = { "k", "k", "k̚" },
["ฃ"] = { "k", "k", "k̚" },
["ค"] = { "k", "k", "k̚" },
["ฅ"] = { "k", "k", "k̚" },
["ฆ"] = { "k", "k", "k̚" },
["จ"] = { "t", "t", "t̚" },
["ฉ"] = { "t", "t", "t̚" },
["ช"] = { "ch", "ch", "t͡ɕʰ" },
["ซ"] = { "s", "s", "s" },
["ฌ"] = { "t", "t", "t̚" },
["ฎ"] = { "t", "t", "t̚" },
["ฏ"] = { "t", "t", "t̚" },
["ฐ"] = { "t", "t", "t̚" },
["ฑ"] = { "t", "t", "t̚" },
["ฒ"] = { "t", "t", "t̚" },
["ด"] = { "t", "t", "t̚" },
["ต"] = { "t", "t", "t̚" },
["ถ"] = { "t", "t", "t̚" },
["ท"] = { "t", "t", "t̚" },
["ธ"] = { "t", "t", "t̚" },
["ศ"] = { "t", "t", "t̚" },
["ษ"] = { "t", "t", "t̚" },
["ส"] = { "s", "s", "s" },
["บ"] = { "p", "p", "p̚" },
["ป"] = { "p", "p", "p̚" },
["ผ"] = { "p", "p", "p̚" },
["ฝ"] = { "p", "p", "p̚" },
["พ"] = { "p", "p", "p̚" },
["ฟ"] = { "f", "f", "f" },
["ภ"] = { "p", "p", "p̚" },
["ง"] = { "ng", "ng$", "ŋ" },
["ญ"] = { "n", "n", "n" },
["ณ"] = { "n", "n", "n" },
["น"] = { "n", "n", "n" },
["ร"] = { "n", "n", "n" },
["ล"] = { "l", "l", "l" },
["ฬ"] = { "n", "n", "n" },
["ม"] = { "m", "m", "m" },
["ฯ"] = { "ʔ", "ʔ", "ʔ" },
}
local tFromMark = {
-- common
["่"] = { ["high"] = "low", ["mid"] = "low", ["low"] = "falling" },
["้"] = { ["high"] = "falling", ["mid"] = "falling", ["low"] = "high" },
["๊"] = { ["high"] = "high", ["mid"] = "high", ["low"] = "high" },
["๋"] = { ["high"] = "rising", ["mid"] = "rising", ["low"] = "rising" },
-- forced mid tone
["̄"] = { ["high"] = "mid", ["mid"] = "mid", ["low"] = "mid" },
}
local tNoMark = {
["dead-short"] = { ["high"] = "low", ["mid"] = "low", ["low"] = "high" },
["dead-long"] = { ["high"] = "low", ["mid"] = "low", ["low"] = "falling" },
["live"] = { ["high"] = "rising", ["mid"] = "mid", ["low"] = "mid" },
}
local tRomMarks = {
["high"] = "́", ["mid"] = "", ["low"] = "̀",
["rising"] = "̌", ["falling"] = "̂",
}
local tLevels = {
["high"] = "˦˥", ["mid"] = "˧", ["low"] = "˨˩",
["rising"] = "˩˩˦", ["falling"] = "˥˩",
}
local symbols = {
["๐"] = 0, ["๑"] = 1, ["๒"] = 2, ["๓"] = 3, ["๔"] = 4,
["๕"] = 5, ["๖"] = 6, ["๗"] = 7, ["๘"] = 8, ["๙"] = 9,
}
local permitted_cluster = {
["ks"] = 1, ["ms"] = 1, ["ns"] = 1, ["ps"] = 1, ["ts"] = 1,
}
-- modified ISO 11940 (to make sound values are more apparent), uses spacing marks for signs
local char_table = {
["ก"] = "k", ["ข"] = "kʰ", ["ฃ"] = "x", ["ค"] = "g", ["ฅ"] = "ɣ", ["ฆ"] = "gʰ", ["ง"] = "ŋ",
["จ"] = "t͡ɕ", ["ฉ"] = "t͡ɕʰ", ["ช"] = "d͡ʑ", ["ซ"] = "z", ["ฌ"] = "d͡ʑʰ", ["ญ"] = "ɲ",
["ฎ"] = "ᶑ", ["ฏ"] = "ʈ", ["ฐ"] = "ʈʰ", ["ฑ"] = "ɖ", ["ฒ"] = "ɖʰ", ["ณ"] = "ɳ",
["ด"] = "ɗ", ["ต"] = "t", ["ถ"] = "tʰ", ["ท"] = "d", ["ธ"] = "dʰ", ["น"] = "n",
["บ"] = "ɓ", ["ป"] = "p", ["ผ"] = "pʰ", ["ฝ"] = "v", ["พ"] = "b", ["ฟ"] = "f", ["ภ"] = "bʰ", ["ม"] = "m",
["ย"] = "y", ["ร"] = "r", ["ฤ"] = "ṛ", ["ล"] = "l", ["ฦ"] = "ḷ", ["ว"] = "w",
["ศ"] = "ɕ", ["ษ"] = "ʂ", ["ส"] = "s", ["ห"] = "h", ["ฬ"] = "ɭ", ["อ"] = "ɒ", ["ฮ"] = "ɦ",
["ะ"] = "a", ["ั"] = "ạ", ["า"] = "ā", ["ำ"] = "å", ["ิ"] = "i", ["ี"] = "ī",
["ึ"] = "ụ", ["ื"] = "ụ̄", ["ุ"] = "u", ["ู"] = "ū", ["ๅ"] = "ɨ", ["ฺ"] = "̥", ["฿"] = "฿",
["เ"] = "e", ["แ"] = "æ", ["โ"] = "o", ["ใ"] = "au", ["ไ"] = "ai",
["่"] = "ˋ", ["้"] = "ˆ", ["๊"] = "ˊ", ["๋"] = "ˇ",
["ฯ"] = "ǂ", ["ๆ"] = "«", ["็"] = "˘",
["์"] = "ʻ", ["ํ"] = "˚", ["๎"] = "~", ["๏"] = "§",
["๚"] = "ǁ", ["๛"] = "»",
["๐"] = "0", ["๑"] = "1", ["๒"] = "2", ["๓"] = "3", ["๔"] = "4",
["๕"] = "5", ["๖"] = "6", ["๗"] = "7", ["๘"] = "8", ["๙"] = "9",
[" "] = " ", ["-"] = "–", ["…"] = "…",
}
local mgvc_pattern = "^([รลว]?)([ิึุ็ีืัำู]?[าอรยว]?[วยร]?ะ?)([คฅฆกขฃพฟภบปชฌฑฒทธจฎฏดตฐถศษสมญณนรลฬงฯ]?)$"
local full_pattern = "^([เแโใไ]?)(หฺ[ก-รลว-ฮ])(ฺ?[รลว]?)([ิึุ็ีืัู]?็?[่้๊๋̄]?[าอรยวำ]?[วยร]?ะ?)([คฅฆกขฃพฟภบปชฌฑฒทธจฎฏดตฐถศษสมญณนรลฬงฯ]?[คฅฆกขฃพฟภบปชฌฑฒทธจฎฏดตฐถศษสมญณนรลฬงฯ]?)$"
local partial_pattern = "^([เแโใไ]?)([ก-รลว-ฮ])(ฺ?[รลว]?)([ิึุ็ีืัู]?็?[่้๊๋̄]?[าอรยวำ]?[วยร]?ะ?)([คฅฆกขฃพฟภบปชฌฑฒทธจฎฏดตฐถศษสมญณนรลฬงฯ]?[คฅฆกขฃพฟภบปชฌฑฒทธจฎฏดตฐถศษสมญณนรลฬงฯ]?)$"
function export.translit(text, lang, sc, mode, source)
local seq = systems[mode]
for word in mw.ustring.gmatch(text, thai_range .. "+") do
local orig_word = word
if match(word, "[่้๊๋̄].?[่้๊๋̄]") then
return nil
end
local function c2_decomp(c2_char, seq, source)
local converted_c2 = {}
for character in mw.text.gsplit(c2_char, "") do
table.insert(converted_c2, coda[character] and coda[character][seq] or nil)
end
local cluster = table.concat(converted_c2)
if source == "translit-module" and not permitted_cluster[gsub(cluster, "̚", "")] then
return c2_char
else
return cluster
end
end
local tone
local function syllable(v1, c1, g, v2, c2)
local tMark = match(v2, "[่้๊๋̄]")
v2 = gsub(v2, "[่้๊๋̄]", "")
if match(c1, "^ห.$") then
if match(sub(c1, 2, 2) .. g .. v2 .. c2, mgvc_pattern) then
c1, g, v2, c2 = "ห", match(sub(c1, 2, 2) .. g .. v2 .. c2, mgvc_pattern)
if g ~= "" and not v2 == "ย" then c1, g = c1 .. g, "" end
end
end
if g == "ล" and v2 .. c2 == "" then
c2 = g
g = ""
end
local openness = c2 ~= "" and "closed" or "open"
if source == "pron-module"
and (mw.ustring.len(c1) > 1 or match(g, "[รล]"))
and not match(c1 .. g, "ฺ") then
error("Please replace " .. c1 .. g .. " in the respelling with " ..
sub(c1, 1, 1) .. "ฺ" .. (sub(c1, 2, -1) or "") .. g .. ".")
end
local orig_v, v
if vowel[openness][v1 .. g .. v2] then
orig_v = v1 .. g .. v2
v, g = vowel[openness][v1 .. g .. v2][seq], ""
else
orig_v = v1 .. v2
v = vowel[openness][v1 .. v2] and vowel[openness][v1 .. v2][seq] or (v1 .. v2)
g = (initial[gsub(g, "ฺ", "")] or initial[""])[seq]
end
c1 = gsub(c1, "ฺ", "")
local ini, class = "", ""
if initial[c1] then
ini, class = initial[c1][seq], initial[c1].class
else
return nil
end
local length = (match(v, "([aiʉueɛoɔə])%1") or match(v, "ː") or unromLong[orig_v]) and "long" or "short"
local life = (match(c2, "[มญณนรลฬง]") or (match(orig_v, "ย$") and match(v, "i$")) or
c2..length == "long" or liveExc[orig_v]) and "live" or "dead"
c2 = coda[c2] and coda[c2][seq] or c2_decomp(c2, seq, source)
-- note: not add tone for royin
tone = tMark and tFromMark[tMark][class] or (tNoMark[life.."-"..length] or tNoMark[life])[class]
if mode == "paiboon" then
v = gsub(v, "^([^aiʉueɛoɔə]*)([aiʉueɛoɔə])", "%1%2" .. tRomMarks[tone])
elseif mode == "ipa" then
c2 = c2 .. tLevels[tone]
end
return ini .. g .. v .. c2
end
word = gsub(word, full_pattern, syllable)
word = gsub(word, partial_pattern, syllable)
text = gsub(text, orig_word, word, 1)
end
text = gsub(text, "[๐-๙]", symbols)
-- postprocessing
if mode == "royin" then
-- initial อ
text = gsub(text, "^@", "")
text = gsub(text, "([%s%p])@", "%1")
text = gsub(text, "@", "-")
-- initial ง
text = gsub(text, "^%$ng", "ng")
text = gsub(text, "([%s%p])%$ng", "%1ng")
text = gsub(text, "([aeiou])%$ng", "%1-ng")
text = gsub(text, "%$ng", "ng")
-- final ง
text = gsub(text, "ng%$$", "ng")
text = gsub(text, "ng%$([%s%p])", "ng%1") -- includes hyphen
text = gsub(text, "ng%$", "ng")
end
local count_syl = 0
if mode == "ipa" then
text, count_syl = gsub(text, "[ %-–]", ".") -- space, common hyphen, en dash
if not match(text, "%.$") then
count_syl = count_syl + 1
end
text = gsub(text, "([aiɯu])([˥-˩]+)$", "%1ʔ%2") -- add ʔ if last syllable ends with [aiɯu]
end
if match(text, thai_range) then
if source == "translit-module" or namespace ~= "" then
return nil
else
return failed_cat
end
else
table.insert(categories, count_syl > 0 and
"[[Category:ဝေါဟာသေံဝဏ္ဏ " .. require("မဝ်ဂျူ:mnw-utilities").arabic_digit_to_mon(count_syl) .. " မ-ဂမၠိုင်]]" or "")
return mw.ustring.toNFC(text)
end
end
local function annotate(c1_text, annotation)
if not annotation then return c1_text end
return tostring( mw.html.create( "span" )
:css( "border-bottom", "1px dotted #000" )
:css( "cursor", "help" )
:attr( "title", annotation )
:wikitext( c1_text ))
end
local front_v = "[เแโใไ]"
local char_annotation = {
["์"] = "CANCEL"
}
function export.getCharSeqTbl(text)
local result = {}
for character in mw.text.gsplit(text, "") do
local charDetail = char_table[character] or nil
if find(character, front_v) then
table.insert(result, tostring( mw.html.create( "span" )
:css( "border", "1px dotted gray" )
:css( "border-radius", "50%" )
:css( "cursor", "help" )
:attr( "title", "Vowel sign appearing in front of the initial consonant." )
:wikitext( charDetail )))
else
table.insert(result, annotate(charDetail, char_annotation[character]))
end
end
return result
end
local function getCharSeq(text)
return "<br><small>" ..
table.concat(export.getCharSeqTbl(text), " ") ..
"</small>"
end
local note_set = {
["aaw"] = annotate(
"-ɔɔ r-",
"In this word, the double consonant combinations กร, ทร, ธร, มร and หร are pronounced 'gaaw ra', two times 'thaaw ra', 'maaw ra' and 'haaw ra', respectively."
),
["redup"] = annotate(
"Reduplication",
"This word exhibits reduplication in pronunciation, i.e. one written consonant is used as the final consonant of a syllable as well as the initial consonant of the next syllable."
),
["short"] = annotate(
"Short",
"The vowel in this word is pronounced irregularly short."
),
["unorthographical"] = annotate(
"Unorthographical",
"This phonetic respelling violates Thai alphabet rules to indicate an irregular pronunciation."
),
}
local function getRhymeFromIPA(ipa)
return match(ipa, "([a̯iɯueɛoɔɤː]+[ʔk̚ŋtnpmjwfls]-)[˥-˩]+$")
end
function export.show(frame)
local lang, sc = "th", "Thai" -- it's script code
local args = frame:getParent().args
local pagename = args.pagename or mw.title.getCurrentTitle().text
local p, note = {}, {}
if args["note"] then
for ind_note in mw.text.gsplit(args["note"], ",") do
table.insert(note, note_set[ind_note])
end
end
if args[1] then
for index, item in ipairs(args) do
table.insert(p, (item ~= "") and item or nil)
end
else
table.insert(p, pagename)
end
local p_concatenated = table.concat(p, "/")
if match(p_concatenated, "็" .. thai_range .. "*[่้๊๋̄]")
or match(p_concatenated, "[่้๊๋̄]" .. thai_range .. "*็")
or match(p_concatenated, "ิ็") then
table.insert(note, note_set["unorthographical"])
if not match(args["note"] or "", "short") then
table.insert(note, note_set["short"])
end
elseif match(p_concatenated, "็")
and not match(pagename, "็")
and not match(args["note"] or "", "short") then
table.insert(note, note_set["short"])
end
homEdit = tostring( mw.html.create( "div" )
:css( "float", "right" )
:css( "clear", "right" )
:css( "font-size", "60%" )
:wikitext( tostring( mw.html.create( "span" )
:attr( "class", "plainlinks" )
:wikitext( "[" .. tostring( mw.uri.fullUrl(
"Module:th-hom/data",
{ ["action"] = "edit" }
)) .." edit]" ))))
function formatThai(text, pron, qualifiers)
local readclass = ''
if pron == true then
readclass = 'th-reading'
end
return ((qualifiers and table.concat(qualifiers) ~= "")
and '<span style="background-color:var(--wikt-palette-lightyellow,#ffffe0);color:inherit"><small>[' ..
table.concat(qualifiers, ", ") .. ']</small></span><br>'
or '') .. '<span lang="th" class="Thai ' .. readclass .. '">' .. text .. '</span>'
end
local result = {
["charPhon"] = {},
["paiboon"] = {},
["royin"] = {},
["ipa"] = {},
["homophone"] = {},
["file"] = {}
}
table.insert(categories, "[[Category:ဝေါဟာသေံရမ္သာင်IPAဂမၠိုင်]]")
local m_hom_data = require("Module:th-hom/data")
local m_hom = require("Module:th-hom").makeList
local m_fileData = require("Module:th-pron/files")
local qualifiers = {}
for system, _ in pairs(systems) do
local function f(text, system)
if system == "paiboon" or system == "royin" then
return '<span class="tr">' .. text .. '</span>'
elseif system == "ipa" then
rhyme = getRhymeFromIPA(text)
return '<span class="IPA">/' .. text .. '/</span>' ..
(rhyme and ("<sup>([[:Category:ကာရန်:သေံ/" .. rhyme .. "|ဗှ်]])</sup>[[Category:ကာရန်:သေံ/" .. rhyme .. "]]") or "")
elseif system == "file" then
local length = ((mw.ustring.len(gsub(text, "[^ %-]", "")) + 1) * 25 + 50)
if m_fileData[text] then
table.insert(categories, "[[Category:ဝေါဟာ သေံနွံရမျာင်လေန်ဂမၠိုင်]]")
return "[[File:" ..
m_fileData[text] ..
"|" .. (length > 200 and 200 or length) ..
"px|center]]"
else
return ""
end
else
return m_hom_data[text]
and (#m_hom_data[text] > 3
and tostring( mw.html.create( "div" )
:attr {
["class"] = "vsSwitcher",
["data-toggle-category"] = "homophones",
}
:wikitext(
tostring( mw.html.create( "span" )
:attr( "class", "vsToggleElement" )
:wikitext( " " )) ..
tostring( mw.html.create( "div" )
:attr( "class", "vsShow" )
:css( "display", "none" )) ..
tostring( mw.html.create( "div" )
:attr( "class", "vsHide" )
:wikitext(( gsub(m_hom(text), ", ", "<br>" ))))))
or gsub(m_hom(text), ", ", "<br>"))
or ""
end
end
for i, spelling in ipairs(p) do
if system == "charPhon" then
qualifiers = {}
if match(spelling, "%:") then
table.insert(qualifiers, match(spelling, "%:(.+)"))
spelling = match(spelling, "([^%:]+)")
end
if match(spelling, "-$") then
table.insert(qualifiers, "ဗီုပြၚ်ဂြဲဖျပ်")
table.insert(categories, "[[Category:Thai prefixes]]")
end
else
spelling = match(spelling, "([^%:]+)")
end
table.insert(result[system], tostring( mw.html.create( "td" )
:css( "border-right", i < #p and "1px solid lightgray" or "0px" )
:wikitext(
(system == "charPhon"
and tostring( mw.html.create( "div" )
:attr("class","th-reading")
:wikitext( formatThai(spelling, false, qualifiers) .. getCharSeq(spelling) ) )
or f(find(system, "^[pri]")
and export.translit(spelling, lang, sc, system, "pron-module")
or spelling, system)))))
end
end
has_hom = match(table.concat(result["homophone"]), "Thai") or false
has_file = match(table.concat(result["file"]), "File") or false
notes = (#note > 0 and "<br><small>{" .. table.concat(note, "; ") .. "}</small>" or "")
local function row(a, b, o)
return ((o and o["pr"]) and "" or "\n<tr>") ..
tostring( mw.html.create( "td" )
:attr( (o and o["rom"]) and "rowspan" or "colspan", (o and o["pr"]) and 1 or 2 )
:css( "background-color", "var(--wikt-palette-paleblue,#f8f9fa)" )
:css( "color", "inherit" )
:css( "border-bottom", (o and o["bt"]) and "0px" or "1px solid lightgray" )
:css( "border-right", "1px solid lightgray" )
:css( "font-weight", "bold" )
:wikitext(a)) ..
((o and o["rom"]) and "" or
((o and o["ortho"])
and tostring(mw.html.create( "td" )
:attr( "colspan", #p )
:css( "border-bottom", "1px solid lightgray" )
:wikitext(b))
or b) ..
"</tr>")
end
if find(pagename, "ทร") and find(table.concat(result["charPhon"]), "ซ") then
table.insert(categories, "[[Category:Thai terms spelled with ทร read as ซ]]")
end
return
'<table cellpadding=10 style="border-spacing: 2px; border: 1px solid darkgray; text-align:center">' ..
((namespace ~= "" and not args.pagename)
and row(
"''[[:en:w:Thai alphabet|ပါ်ခြာပ္တိတ်ရမျာင်]]''" .. notes,
table.concat(result["charPhon"]))
or (pagename == table.concat(p)
and row(
"''[[:en:w:Thai alphabet|ထ္ဍုတ်ဗီုအခဝ်ရဝ်မာန်]]''",
formatThai(pagename,true) .. getCharSeq(pagename),
{ ["ortho"] = true })
or row(
"''[[:en:w:Thai alphabet|ဗီုနဲအခဝ်]]''",
formatThai(pagename,true) .. getCharSeq(pagename),
{ ["ortho"] = true }) ..
row(
"''[[:en:w:Thai alphabet|အတိုင်ရမျာင်]]''" .. notes,
table.concat(result["charPhon"])))) ..
row("''[[:en:Wiktionary:Thai romanization|ဗီုအခဝ်ရဝ်မာန်]]''", nil, { ["rom"] = true }) ..
row(
"''[[:en:Wiktionary:Thai romanization|ဖါဲပေန်]]''",
table.concat(result["paiboon"]),
{ ["pr"] = true }) ..
row(
"''[[:en:Wiktionary:Thai romanization|တန်က္ဍိုင်ကၟုကဆံၚ်သၠုင်]]''",
table.concat(result["royin"]),
{ ["pr"] = true }) ..
row(
"(''[[:en:w:Standard Thai|တင်မကၞာတ်လဝ်]]'') " ..
"[[ရီု:IPA-Mon|IPA]]" ..
"<sup>([[:en:Appendix:Thai pronunciation|key]])</sup>",
table.concat(result["ipa"]),
{ ["bt"] = not has_hom and not has_file }) ..
(has_hom
and row(
"''ဗွဟ်ရမျာင်''" .. homEdit,
table.concat(result["homophone"]) or "",
{ ["bt"] = not has_file })
or "") ..
(has_file
and row(
"''ရမျာၚ်''",
table.concat(result["file"]) or "",
{ ["bt"] = true })
or "") ..
"\n</table>" .. (namespace == "" and table.concat(categories) or "")
end
return export