Module:rki-pron
Jump to navigation
Jump to search
- The following documentation is located at Module:rki-pron/documentation. [edit] Categories were auto-generated by Module:module categorization. [edit]
- Useful links: subpage list • links • transclusions • testcases • sandbox
Rakhine (Arakanese) pronunciation and romanisation module. See {{rki-IPA}}.
Testcases
[edit]See Module:rki-pron/testcases.
local export = {}
local gsub = mw.ustring.gsub
local sub = mw.ustring.sub
local match = mw.ustring.match
local system_list = {
{ 1, ["type"] = "phonetic", ["name"] = "IPA" },
{ 2, ["type"] = "orthographic", ["name"] = "MLCTS" },
{ 3, ["type"] = "orthographic", ["name"] = "ALA-LC" },
}
local initial_table = {
["က"] = { "k", "k", "k" },
["ကျ"] = { "t͡ɕ", "ky", "ky" },
["ကြ"] = { "kɹ", "kr", "kr" },
["ကျွ"] = { "t͡ɕw", "kyw", "kyv" },
["ကြွ"] = { "kɹw", "krw", "krv" },
["ကွ"] = { "kw", "kw", "kv" },
["ခ"] = { "kʰ", "hk", "kh" },
["ချ"] = { "t͡ɕʰ", "hky", "khy" },
["*ချ"] = { "ʃ", "hkr", "khr" },
["ခြ"] = { "t͡ɕʰ", "hkr", "khr" },
["*ခြ"] = { "ʃ", "hkr", "khr" },
["ချွ"] = { "t͡ɕʰw", "hkyw", "khyv" },
["ခြွ"] = { "kʰɹw", "hkrw", "khrv" },
["ခွ"] = { "kʰw", "hkw", "khv" },
["ဂ"] = { "ɡ", "g", "g" },
["ဂျ"] = { "d͡ʑ", "gy", "gy" },
["ဂြ"] = { "gɹ", "gr", "gr" },
["ဂျွ"] = { "d͡ʑw", "gyw", "gyv" },
["ဂွ"] = { "ɡw", "gw", "gv" },
["ဃ"] = { "ɡ", "gh", "gh" },
["င"] = { "ŋ", "ng", "ṅ" },
["ငှ"] = { "ŋ̊", "hng", "ṅh" },
["ငြ"] = { "ɲ", "ngr", "ṅr" },
["ငြှ"] = { "ɲ̊", "hngr", "ṅrh" },
["ငွ"] = { "ŋw", "ngw", "ṅv" },
["ငွှ"] = { "ŋ̊w", "hngw", "ṅvh" },
["စ"] = { "s", "c", "c" },
["စွ"] = { "sw", "cw", "cv" },
["ဆ"] = { "sʰ", "hc", "ch" },
["ဆွ"] = { "sʰw", "hcw", "chv" },
["ဇ"] = { "z", "j", "j" },
["ဇွ"] = { "zw", "jw", "jv" },
["ဈ"] = { "z", "jh", "jh" },
["ဉ"] = { "ɲ", "ny", "ñ" },
["ည"] = { "ɲ", "ny", "ññ" },
["ဉှ"] = { "ɲ̊", "hny", "ñh" },
["ညှ"] = { "ɲ̊", "hny", "ññh" },
["ညွ"] = { "ɲw", "nyw", "ñv" },
["ညွှ"] = { "ɲ̊w", "hnyw", "ñvh" },
["ဋ"] = { "t", "t", "ṭ" },
["ဌ"] = { "tʰ", "ht", "ṭh" },
["ဍ"] = { "d", "d", "ḍ" },
["ဎ"] = { "d", "dh", "ḍh" },
["ဏ"] = { "n", "n", "ṇ" },
["ဏှ"] = { "n̥", "hn", "ṇh" },
["တ"] = { "t", "t", "t" },
["တျ"] = { "tj", "ty", "ty" },
["တြ"] = { "tɹ", "tr", "tr" },
["တွ"] = { "tw", "tw", "tv" },
["ထ"] = { "tʰ", "ht", "th" },
["ထွ"] = { "tʰw", "htw", "thv" },
["ဒ"] = { "d", "d", "d" },
["ဒျ"] = { "dj", "dy", "dy" },
["ဒြ"] = { "dɹ", "dr", "dr" },
["ဒွ"] = { "dw", "dw", "dv" },
["ဓ"] = { "d", "dh", "dh" },
["န"] = { "n", "n", "n" },
["နှ"] = { "n̥", "hn", "nh" },
["နျ"] = { "nj", "ny", "ny" },
["နွ"] = { "nw", "nw", "nv" },
["နွှ"] = { "n̥w", "hnw", "nvh" },
["ပ"] = { "p", "p", "p" },
["ပျ"] = { "pj", "py", "py" },
["ပြ"] = { "pɹ", "pr", "pr" },
["ပြွ"] = { "pw", "prw", "prv" },
["ပွ"] = { "pw", "pw", "pv" },
["ဖ"] = { "pʰ", "hp", "ph" },
["ဖျ"] = { "pʰj", "hpy", "phy" },
["ဖြ"] = { "pʰɹ", "hpr", "phr" },
["ဖွ"] = { "pʰw", "hpw", "phv" },
["ဗ"] = { "b", "b", "b" },
["ဗျ"] = { "bj", "by", "by" },
["ဗြ"] = { "bɹ", "br", "br" },
["ဗွ"] = { "bw", "bw", "bv" },
["ဘ"] = { "b", "bh", "bh" },
["-ဘ"] = { "pʰ", "bh", "bh" },
["ဘွ"] = { "bw", "bhw", "bhv" },
["-ဘွ"] = { "pʰw", "bhw", "bhw" },
["မ"] = { "m", "m", "m" },
["မှ"] = { "m̥", "hm", "mh" },
["မျ"] = { "mj", "my", "my" },
["မျှ"] = { "m̥j", "hmy", "myh" },
["မြ"] = { "mɹ", "mr", "mr" },
["မြှ"] = { "m̥ɹ", "hmr", "mrh" },
["မြွ"] = { "mɹw", "mrw", "mrv" },
["မြွှ"] = { "m̥w", "hmrw", "mrvh" },
["မွ"] = { "mw", "mw", "mv" },
["မွှ"] = { "m̥w", "hmw", "mvh" },
["ယ"] = { "j", "y", "y" },
["ယှ"] = { "ʃ", "hy", "yh" },
["သျှ"] = { "ʃ", "hsy", "syh" },
["ယွ"] = { "jw", "yw", "yv" },
["ရ"] = { "ɹ", "r", "r" },
["ရှ"] = { "hɹ", "hr", "rh" },
["*ရှ"] = { "ʃ", "hr", "rh" },
["ရွ"] = { "ɹw", "rw", "rv" },
["ရွှ"] = { "hɹw", "hrw", "rvh" },
["လ"] = { "l", "l", "l" },
["လှ"] = { "l̥", "hl", "lh" },
["လျ"] = { "j", "ly", "ly" },
["+သျှ"]= { "j", "hsy", "syh" },
["*လျ"]= { "lj", "ly", "ly" },
["လျှ"] = { "ʃ", "hly", "lyh" },
["*လျှ"]= { "l̥j", "hly", "lyh" },
["လွ"] = { "lw", "lw", "lv" },
["လွှ"] = { "l̥w", "hlw", "lvh" },
["ဝ"] = { "w", "w", "v" },
["ဝှ"] = { "ʍ", "hw", "vh" },
["သ"] = { "θ", "s", "s" },
["+သ"] = { "ð", "s", "s" },
["သွ"] = { "θw", "sw", "sv" },
["+သွ"] = { "ðw", "sw", "sw" },
["ဟ"] = { "h", "h", "h" },
["ဟွ"] = { "hw", "hw", "hv" },
["ဠ"] = { "l", "l", "ḷ" },
["အ"] = { "ʔ", "", "ʼ" },
-- only appears after a vowel in the same word
["ဿ"] = { "ʔθ", "ss", "ss" },
[""] = { "ʔ", "", "" },
["-"] = { "", "", "" },
["ျ"] = { nil, "y", "y" },
["ြ"] = { nil, "r", "r" },
["ွ"] = { nil, "w", "w" },
}
local initial_voicing = {
["+က"] = "ဂ",
["+ခ"] = "ဂ",
["+စ"] = "ဇ",
["+ဆ"] = "ဇ",
["+ဋ"] = "ဍ",
["+ဌ"] = "ဍ",
["+တ"] = "ဒ",
["+ထ"] = "ဒ",
["+ပ"] = "ဗ",
["+ဖ"] = "ဗ",
["-ဘ"] = "ဖ",
}
local final_table = {
[""] = { "a̰", "a.", "a" },
["က်"] = { "ɔʔ", "ak", "akʻ" },
["င်"] = { "ɔ̀ɴ", "ang", "aṅʻ" },
["စ်"] = { "aɪʔ", "ac", "acʻ" },
["ည်"] = { "è", "any", "aññʻ" },
["ည်2"] = { "ì", "any", "aññʻ" },
["ည်3"] = { "ɛ̀", "any", "aññʻ" },
["ဉ်"] = { "aɪ̀ɴ", "any", "añʻ" },
["တ်"] = { "ɛʔ", "at", "atʻ" },
["န်"] = { "ɛ̀ɴ", "an", "anʻ" },
["ပ်"] = { "ɛʔ", "ap", "apʻ" },
["မ်"] = { "ɛ̀ɴ", "am", "amʻ" },
["ယ်"] = { "è", "ai", "ayʻ" },
["ံ"] = { "ɛ̀ɴ", "am", "aṃ" },
["ာ"] = { "à", "a", "ā" },
["ါ"] = { "à", "a", "ā" },
["ိ"] = { "ḭ", "i.", "i" },
["ိတ်"] = { "eɪʔ", "it", "itʻ" },
["ိန်"] = { "èɪɴ", "in", "inʻ" },
["ိပ်"] = { "eɪʔ", "ip", "ipʻ" },
["ိမ်"] = { "èɪɴ", "im", "imʻ" },
["ိံ"] = { "èɪɴ", "im", "iṃ" },
["ီ"] = { "ì", "i", "ī" },
["ု"] = { "ṵ", "u.", "u" },
["ုတ်"] = { "oʊʔ", "ut", "utʻ" },
["ုန်"] = { "òʊɴ", "un", "unʻ" },
["ုပ်"] = { "oʊʔ", "up", "upʻ" },
["ုမ်"] = { "òʊɴ", "um", "umʻ" },
["ုံ"] = { "òʊɴ", "um", "uṃ" },
["ူ"] = { "ù", "u", "ū" },
["ေ"] = { "ì", "e", "e" },
["ေ2"] = { "è", "e", "e" },
["ဲ"] = { "é", "ai:", "ai" },
["ော"] = { "ɔ́", "au:", "o" },
["ောက်"] = { "aʊʔ", "auk", "okʻ" },
["ောင်"] = { "àʊɴ", "aung", "oṅʻ" },
["ော်"] = { "ɔ̀", "au", "oʻ" },
["ို"] = { "ò", "ui", "ui" },
["ိုက်"] = { "aɪʔ", "uik", "uikʻ" },
["ိုင်"] = { "àɪɴ", "uing", "uiṅʻ" },
["ွတ်"] = { "wɛʔ", "wat", "vatʻ" },
["ွန်"] = { "wɛ̀ɴ", "wan", "vanʻ" },
["ွပ်"] = { "wɛ̀ʔ", "wap", "vapʻ" },
["ွမ်"] = { "wɛ̀ɴ", "wam", "vamʻ" },
["ွံ"] = { "wɛ̀ɴ", "wam", "vaṃ" },
["'"] = { "ə", "a", "a" },
["်"] = { "", "", "ʻ" },
}
local nucleus_table = {
[""] = { "à", "a", "a" },
["ိ"] = { "ì", "i", "i" },
["ု"] = { "ù", "u", "u" },
["ော"] = { "ɔ̀", "au", "o" },
["ေါ"] = { "ɔ̀", "au", "o" },
["ွ"] = { "ʊ̀", "wa", "va" },
}
local indep_letter_table = {
["ဣ"] = { "ḭ", "i.", "i" },
["ဤ"] = { "ì", "i", "ī" },
["ဥ"] = { "ṵ", "u.", "u" },
["ဦ"] = { "ù", "u", "ū" },
["ဧ"] = { "ì", "e", "e" },
["၏"] = { "ḭ", "e", "e*" },
["ဩ"] = { "ɔ́", "au:", "o" },
["ဪ"] = { "ɔ̀", "au", "oʻ" },
["၌"] = { "n̥aɪʔ", "hnai.", "n*" },
["၍"] = { "ɹwḭ", "rwe", "r*" },
}
local tone_table = {
["း"] = { "́", ":", "ʺ" },
["့"] = { "̰", ".", "ʹ" },
}
local ambig_intersyl = {
[1] = {
},
[2] = {
["ky"] = 1, ["kr"] = 1, ["kw"] = 1,
["gy"] = 1, ["gr"] = 1, ["gw"] = 1,
["ng"] = 1, ["ny"] = 1,
["cw"] = 1, ["tw"] = 1, ["nw"] = 1,
["py"] = 1, ["pr"] = 1, ["pw"] = 1,
["my"] = 1, ["mr"] = 1, ["mw"] = 1,
},
[3] = {
},
[4] = {
["ky"] = 1, ["kr"] = 1, ["kw"] = 1,
["gy"] = 1, ["gr"] = 1, ["gw"] = 1,
["ng"] = 1, ["ny"] = 1,
["cw"] = 1, ["tw"] = 1, ["nw"] = 1,
["tr"] = 1, ["tw"] = 1,
["py"] = 1, ["pr"] = 1, ["pw"] = 1,
["my"] = 1, ["mr"] = 1, ["mw"] = 1,
},
[5] = {
["ou"] = 1,
},
}
local reverse_table = {
["hm"] = "မှ", ["m"] = "မ",
["hn"] = "နှ", ["n"] = "န",
["hny"] = "ညှ", ["ny"] = "ည",
["hng"] = "ငှ", ["ng"] = "င",
["p"] = "ပ", ["hp"] = "ဖ", ["b"] = "ဗ",
["t"] = "တ", ["ht"] = "ထ", ["d"] = "ဒ",
["c"] = "ကျ", ["hc"] = "ချ", ["j"] = "ဂျ",
["k"] = "က", ["hk"] = "ခ", ["g"] = "ဂ",
[""] = "အ",
["th"] = "သ", ["+th"] = "+သ",
["s"] = "စ", ["hs"] = "ဆ", ["z"] = "ဇ",
["hr"] = "ရှ",
["h"] = "ဟ",
["r"] = "ရ",
["y"] = "ယ",
["hw"] = "ဝှ", ["w"] = "ဝ",
["hl"] = "လှ", ["l"] = "လ",
["hmw"] = "မွှ", ["mw"] = "မွ", ["hmy"] = "မျှ", ["my"] = "မျ",
["hnw"] = "နွှ", ["nw"] = "နွ",
["hnyw"] = "ညွှ", ["nyw"] = "ညွ",
["hngw"] = "ငွှ", ["ngw"] = "ငွ",
["pw"] = "ပွ", ["hpw"] = "ဖွ", ["bw"] = "ဗွ",
["py"] = "ပျ", ["hpy"] = "ဖျ", ["by"] = "ဗျ",
["tw"] = "တွ", ["htw"] = "ထွ", ["dw"] = "ဒွ",
["cw"] = "ကျွ", ["hcw"] = "ချွ", ["jw"] = "ဂျွ",
["kw"] = "ကွ", ["hkw"] = "ခွ", ["gw"] = "ဂွ",
["thw"] = "သွ",
["sw"] = "စွ", ["hsw"] = "ဆွ", ["zw"] = "ဇွ",
["hrw"] = "ရွှ",
["hw"] = "ဟွ",
["yw"] = "ယွ",
["hlw"] = "လွှ", ["lw"] = "လွ", ["hly"] = "*လျှ", ["ly"] = "*လျ",
["i"] = "ီ", ["i\\"] = "ီး", ["i/"] = "ိ", ["i?"] = "စ်",
["i~"] = "င်", ["i\\~"] = "င်း", ["i/~"] = "င့်",
["ei"] = "ေ", ["ei\\"] = "ေး", ["ei/"] = "ေ့", ["ei?"] = "ိတ်",
["ei~"] = "ိန်", ["ei\\~"] = "ိန်း", ["ei/~"] = "ိန့်",
["e"] = "ယ်", ["e\\"] = "ဲ", ["e/"] = "ယ့်", ["e?"] = "က်",
["ai~"] = "ိုင်", ["ai\\~"] = "ိုင်း", ["ai/~"] = "ိုင့်",
["ai?"] = "ိုက်",
["a"] = "ာ", ["a\\"] = "ား", ["a/"] = "", ["a?"] = "တ်",
["a~"] = "န်", ["a\\~"] = "န်း", ["a/~"] = "န့်",
["o"] = "ော်", ["o\\"] = "ော", ["o/"] = "ော့", ["au?"] = "ောက်",
["au~"] = "ောင်", ["au\\~"] = "ောင်း", ["au/~"] = "ောင့်",
["ou"] = "ို", ["ou\\"] = "ိုး", ["ou/"] = "ို့", ["ou?"] = "ုပ်",
["ou~"] = "ုန်", ["ou\\~"] = "ုန်း", ["ou/~"] = "ုန့်",
["u"] = "ူ", ["u\\"] = "ူး", ["u/"] = "ု", ["u?"] = "ွတ်",
["u~"] = "ွန်", ["u\\~"] = "ွန်း", ["u/~"] = "ွန့်",
["a'"] = "'",
}
local repl_string = "([ကခဂဃငစဆဇဈဉညဋဌဍဎဏတထဒဓနပဖဗဘမယရလဝသဟဠအဿ][ျြွှ]*[ံ့းွာါါိီုူေဲ]*)([ကခဂဃငစဆဇဈဉညဋဌဍဎဏတထဒဓနပဖဗဘမယရလဝသဟဠအဿ][့]?[^့်္])"
function syllabify(text)
text = gsub(text, "('?)([%+%-%*]*)", function(a, b)
if a .. b ~= "" then return a .. " " .. b end
end)
text = gsub(text, "([ဣဤဥဦဧဩဪ၏၌၍][့း်]?)(.?)(.?)", function(a, b, c)
return (c == "္" and " "..a..b.." "..c or (c == "်" and " "..a..b..c or " "..a.." "..b..c))
end) .. " "
text = gsub(text, "(်း?'?)", "%1 ")
text = gsub(text, "([း့])([ကခဂဃငစဆဇဈဉညဋဌဍဎဏတထဒဓနပဖဗဘမယရလဝသဟဠအ]်)", "%2%1")
while match(text, repl_string) do
text = gsub(text, repl_string, "%1 %2")
end
text = gsub(text, "္", " , ")
text = gsub(text, " +", " ")
text = gsub(text, "^ ?(.*[^ ]) ?$", "%1")
text = gsub(text, " , ", " ")
text = gsub(text, " ([23])", "%1")
return text
end
function initial_by_char(initial_string, system_index, ref_table)
local initial_set = {}
for character in mw.text.gsplit(initial_string, "") do
local temp_initial = ref_table[character] or error("Initial data not found.")
table.insert(initial_set, temp_initial[system_index] or temp_initial)
end
return table.concat(initial_set)
end
function generate_respelling(text)
text = gsub(text, " ", " ")
text = gsub(text, "ါ", "ာ")
if match(text, "[က-႟ꩠ-ꩻ]") then return text end
text = gsub(text, "(%+?)([^%?%+'/\\~aeiou ]*)(/?)([%?'/\\~aeiou]+)", function(voicing_mark, latin_initial, opt_sep, latin_final)
return
voicing_mark ..
(reverse_table[latin_initial] or initial_by_char(latin_initial, nil, reverse_table)) ..
opt_sep ..
reverse_table[latin_final]
end)
return text
end
function process(initial, final, tone, schwa, system, system_index)
if match(initial .. final, "ွှ?[တနပမံ]") and system["type"] == "phonetic" then
initial = gsub(initial, "[ွ/]", "")
final = "ွ" .. final
else
initial = gsub(initial, "/", "")
end
initial_new = system["type"] == "phonetic" and gsub(initial, "%+.", initial_voicing) or initial
if indep_letter_table[initial_new] then
initial_new = match(initial_new, "[၌၍]") and "-" or ""
final = initial .. final
end
if initial_new == "မြွ" then require('Module:debug').track('rki-pron/mrw') end
initial_data =
initial_table[initial_new]
or initial_table[gsub(initial_new, "[%+%-%*]", "")]
or (system["type"] == "orthographic"
and initial_by_char(initial_new, system_index, initial_table)
or error("Initial data not found."))
initial_value = initial_data[system_index] or initial_data
if match(initial, "^%+") and system_index == 5 then
initial_value = initial_table[gsub(initial, "%+", "")][system_index]
initial_value = gsub(initial_value, "^([^rwy]+)", "<u>%1</u>")
end
final_data =
final_table[system["type"] .. schwa == "phonetic'" and schwa or final]
or (system["type"] == "phonetic"
and (final_table[final .. "်"] or indep_letter_table[final])
or indep_letter_table[final])
or gsub(final, "^([^်]*)([^်])(်?)$", function(first, second, third)
first_data = nucleus_table[first] or final_table[first] or indep_letter_table[first] or first
second_data = initial_table[second] or second
first = first_data ~= first and first_data[system_index] or first
second = second_data ~= second
and second_data[system_index] .. ((system_index == 3 and third ~= "") and "ʻ" or "")
or second
return (gsub(first .. second, "([%.:])(.*)", "%2"))
end)
final_value = type(final_data) == "table" and final_data[system_index] or final_data
final_value = mw.ustring.toNFD(final_value)
if tone == "" then
tone_value = ""
else
if system_index ~= 4 then final_value = gsub(final_value, "̀", "") end
final_value = gsub(final_value, "[́:%.]", "")
if system["type"] .. schwa == "phonetic'" then
tone_value = ""
else
tone_data = tone_table[tone] or error("Tone data not found.")
tone_value = tone_data[system_index]
end
end
if system_index == 1 then
final_value = gsub(final_value, "^([aeəɛiɪoɔuʊ])", "%1" .. tone_value)
elseif system_index == 5 then
final_value = gsub(final_value, "([aeiou])([^aeiou]*)$", "%1" .. tone_value .. "%2")
else
final_value = final_value .. tone_value
end
return mw.ustring.toNFC(initial_value .. final_value)
end
function remove_wide_space(text)
return (gsub(text, " ", ""))
end
function concatenate(set, system_index)
if system_index == 1 then return remove_wide_space(table.concat(set)) end
result_text = remove_wide_space(table.concat(set, " "))
for count = 1, 3 do
result_text = gsub(result_text, "(.) (.)([^ ]?)",
function(previous, next, after_next)
if ambig_intersyl[system_index][previous .. next]
or ((system_index == 2 or system_index == 4)
and (match(previous .. " " .. next, "[ptkgmngy] [aeiou]")
or (match(previous .. next .. after_next, "[aeiou][ptkmn][rwyg]") and not match(after_next, "[aeiou]")))) then
return previous .. "-" .. next .. after_next
else
return previous .. next .. after_next
end
end)
end
return result_text
end
function export.get_romanisation(word, pronunciations, system, system_index, mode)
local sentences = {}
word = gsub(word, " ", "|")
if system["type"] == "phonetic" then
word = gsub(word, "ဿ", "တ်သ")
end
word = syllabify(word)
word = gsub(word, "ါ", "ာ")
if system["type"] == "phonetic" then
word = gsub(word, "ဝ([တနပမံ])", "ဝွ%1")
end
for phrase in mw.text.gsplit(word, "|", true) do
local temp = {}
local syllable = mw.text.split(phrase, " ", true)
for syllable_index = 1, #syllable do
syllable[syllable_index] = gsub(syllable[syllable_index], "([း့])(်)", "%2%1")
temp[syllable_index] = gsub(
syllable[syllable_index],
"^([%+%-%*]*[ကခဂဃငစဆဇဈဉညဋဌဍဎဏတထဒဓနပဖဗဘမယရလဝသဟဠအဣဤဥဦဧဩဪ၏၌၍ဿ][ျြ]?ွ?ှ?/?)([^း့']*)([း့]?)('?)$",
function(initial, final, tone, schwa)
return process(initial, final, tone, schwa, system, system_index)
end)
end
table.insert(sentences, concatenate(temp, system_index))
end
if mode == "translit_module" then return table.concat(sentences, " ") end
table.insert(pronunciations[system_index], table.concat(sentences, " "))
return pronunciations[system_index]
end
function respelling_format(phonetic, page_title)
local page_title_set = mw.text.split(syllabify(page_title), " ")
local new_respellings = {}
for _, respelling in ipairs(phonetic) do
local respelling_set = mw.text.split(syllabify(respelling), " ")
if gsub(table.concat(respelling_set), "[%+%-%*']", "") == (gsub(table.concat(page_title_set), "ါ", "ာ")) then
for index, element in ipairs(respelling_set) do
if element ~= page_title_set[index] then
respelling_set[index] = '<span style="font-size:110%; color:#A32214; font-weight: bold">' .. element .. '</span>'
end
end
end
table.insert(new_respellings, table.concat(respelling_set))
end
text = table.concat(new_respellings, ", ")
text = remove_wide_space(text)
text = gsub(text, "[%+%-].", initial_voicing)
text = gsub(text, "([ခဂငဒပဝ]ေ?)ာ", "%1ါ")
return text
end
function export.generate_tests(word, respelling)
respelling, word = generate_respelling(respelling), generate_respelling(word)
local pronunciations = {
[1] = {},
[2] = {},
[3] = {},
[4] = {},
[5] = {},
}
local p, result = { ["orthographic"] = word, ["phonetic"] = respelling or word }, {}
table.sort(system_list, function(first, second) return first[1] < second[1] end)
for system_index, system in ipairs(system_list) do
pronunciations[system_index] = export.get_romanisation(p[system["type"]], pronunciations, system, system_index)
end
for system_index = 1, 5 do
table.insert(result, table.concat(pronunciations[system_index]))
end
return (gsub(gsub(table.concat(result, " | "), "<u>", "("), "</u>", ")"))
end
function export.make(frame)
local args = frame:getParent().args
local page_title = mw.title.getCurrentTitle().text
local title = generate_respelling(args["word"] or page_title)
local p, result = { ["orthographic"] = { title }, ["phonetic"] = {} }, {}
local pronunciations = {
[1] = {},
[2] = {},
[3] = {},
[4] = {},
[5] = {},
}
if not args[1] then args = { title } end
for index, item in ipairs(args) do
table.insert(p["phonetic"], (item ~= "") and generate_respelling(item) or nil)
end
table.sort(system_list, function(first, second) return first[1] < second[1] end)
for system_index, system in ipairs(system_list) do
for _, word in ipairs(p[system["type"]]) do
pronunciations[system_index] = export.get_romanisation(word, pronunciations, system, system_index)
end
end
if title ~= table.concat(args) then
table.insert(result,
"* Phonetic respelling" .. (#p["phonetic"] > 1 and "s" or "") .. ": " ..
tostring( mw.html.create( "span" )
:attr( "lang", "rki" )
:attr( "class", "Mymr" )
:wikitext( respelling_format( p["phonetic"], page_title ))) .. "\n" )
end
table.insert(result,
'* [[Wiktionary:International Phonetic Alphabet|IPA]]' ..
'<sup>([[Appendix:Burmese pronunciation|key]])</sup>: ' ..
(tostring( mw.html.create( "span" )
:attr( "class", "IPA" )
:wikitext( "/" .. gsub(table.concat(pronunciations[1], "/, /"), "ʔʔ", "ʔ.ʔ") .. "/" ))) ..
'\n* [[Wiktionary:Burmese transliteration|Romanization:]] ')
for system_index = 2, 5 do
table.insert(result,
(system_index ~= 2 and " • " or "") ..
"''" .. system_list[system_index]["name"] .. ":'' " ..
table.concat(pronunciations[system_index], "/"))
end
return table.concat(result)
end
return export