Sware: 1 revision imported

2026-04-21T12:00:36Z

1 revision imported

← Older revision	Revision as of 12:00, 21 April 2026
(No difference)

wikt>Sbb1413 at 13:34, 26 April 2023

2023-04-26T13:34:39Z

New page

-- Transliteration for Middle Bengali

local export = {}
local gsub = mw.ustring.gsub
local match = mw.ustring.match

local char = {
-- consonants
["ক"] = "k", ["খ"] = "kh", ["গ"] = "g", ["ঘ"] = "gh", ["ঙ"] = "ṅ",
["চ"] = "c", ["ছ"] = "ch", ["জ"] = "j", ["ঝ"] = "jh", ["ঞ"] = "ñ",
["ট"] = "ṭ", ["ঠ"] = "ṭh", ["ড"] = "ḍ", ["ঢ"] = "ḍh", ["ণ"] = "ṇ",
["ত"] = "t", ["থ"] = "th", ["দ"] = "d", ["ধ"] = "dh", ["ন"] = "n",
["প"] = "p", ["ফ"] = "ph", ["ব"] = "b", ["ভ"] = "bh", ["ম"] = "m",
["য"] = "j", ["র"] = "r", ["ল"] = "l",
["শ"] = "ś", ["ষ"] = "ṣ", ["স"] = "s", ["হ"] = "h",
["য়"] = "ẏ", ["ড়"] = "ṛ", ["ঢ়"] = "ṛh",

-- vowel diacritics
["ি"] = "i", ["ু"] = "u",
["ৃ"] = "ri", ["ে"] = "e", ["ো"] = "ō",
["া"] = "a", ["ী"] = "i", ["ূ"] = "u", ["ৈ"] = "ōi", ["ৌ"] = "ōu",

-- archaic vowel diacritics
["ৄ"] = "ri", ["ৢ"] = "li", ["ৣ"] = "li",

-- visarga
["ঃ"] = "ḥ",

-- vowel signs
["অ"] = "o", ["ই"] = "i", ["উ"] = "u",
["ঋ"] = "ri", ["এ"] = "e", ["ও"] = "ō",
["আ"] = "a", ["ঈ"] = "i", ["ঊ"] = "u", ["ঐ"] = "ōi", ["ঔ"] = "ōu",

-- archaic vowel signs
["ৠ"] = "ri", ["ঌ"] = "li", ["ৡ"] = "li",

--virama
["্"] = "",

-- chandrabindu
["ঁ"] = "̃",

-- avagraha
['ঽ']='’',

-- anusvara
["ং"] = "ṅ",

-- khandata,
["ৎ"] = "t",

-- numerals
["০"] = "0", ["১"] = "1", ["২"] = "2", ["৩"] = "3", ["৪"] = "4",
["৫"] = "5", ["৬"] = "6", ["৭"] = "7", ["৮"] = "8", ["৯"] = "9",

-- punctuation
["।"] = ".", -- dãri
}

local consonant, vowel, vowel_sign = "ক-হড়-য়", "oা-ৌ’", "অ-ঔ"
local c = "[" .. consonant .. "]"
local cc = "়?" .. c
local v = "[" .. vowel .. vowel_sign .. "o]"
local syncope_pattern = "(" .. v .. cc .. v .. cc .. ")o(" .. cc .. "ঁ?" .. v .. ")"

local function rev_string(text)
local result, length = "", mw.ustring.len(text)
for i = 1, length do
result = result .. mw.ustring.sub(text, length - i + 1, length - i + 1)
end
return result
end

function export.tr(text, lang, sc, override)
text = gsub(text, "(" .. c .. ")ও", "%1্ও")
text = gsub(text, "^(" .. c .. ")্ও", "%1ও")

text = gsub(text, "([কখগঘ])([গচছট-ধস])", "%1্%2")
text = gsub(text, "^([কখগঘ])্([গচছট-ধস])", "%1%2")
text = gsub(text, "([কখগঘ])্([ড়ঢ়])", "%1%2")

text = gsub(text, "কব", "ক্b")
text = gsub(text, "^ক্b", "কb")

text = gsub(text, "(" .. c .. ")্‌(" .. c .. ")$", "%1্%2্")
text = gsub(text, "(" .. c .. ")্‌(" .. c .. ") ", "%1্%2্ ")

text = gsub(text, "([ট-ধ])([ক-ঘ])(" .. v .. ")", "%1্%2%3")
text = gsub(text, "^([ট-ধ])্([ক-ঘ])(" .. v .. ")", "%1%2%3")
text = gsub(text, " ^([ট-ধ])্([ক-ঘ])(" .. v .. ")", " %1%2%3")

text = gsub(text, "ন([চ-ঝট-ঢশ-হ])", "ন্%1")
text = gsub(text, "^ন্([চ-ঝট-ঢশ-হ])", "ন%1")
text = gsub(text, " ন্([চ-ঝট-ঢশ-হ])", " ন%1")

text = gsub(text, "প([ঙঞণনম])", "প্%1")
text = gsub(text, "^প্([ঙঞণনম])", "প%1")
text = gsub(text, "ফ([ঙঞণত-নমরল])", "ফ্%1")
text = gsub(text, "^ফ্([ঙঞণত-নমরল])", "ফ%1")

text = gsub(text, "(" .. v .. ")ঞ(" .. v .. ")", "%1̃%2")

text = gsub(text, "(" .. c .. "়?)([" .. vowel .. "’?্]?)", function(a, b)
return a .. (b == "" and "o" or b) end)

for word in mw.ustring.gmatch(text, "[ঁ-৽o’]+") do
local orig_word = word
word = rev_string(word)
word = gsub(word, "^o(়?" .. c .. ")(ঁ?" .. v .. ")", "%1%2")
while match(word, syncope_pattern) do
word = gsub(word, syncope_pattern, "%1%2")
end
text = gsub(text, orig_word, rev_string(word))
end

text = gsub(text, "্ম", "ṃ")
text = gsub(text, "্য", "y")
text = gsub(text, "্ব", "v")

text = gsub(text, "িত$", "ito")
text = gsub(text, "িত ", "ito ")

text = gsub(text, "ৃত$", "rito")
text = gsub(text, "ৃত ", "rito ")

text = gsub(text, "ছিল$", "chilo")
text = gsub(text, "ছিল ", "chilo ")

text = gsub(text, ".[়’]?", char)
text = gsub(text, ".", char)

local v_Latn = "[oaiueō]"
local c_Latn = "[bcdḍghjklmṃnṇprsśṣtṭvẇyẏ]"
local consonants_no_h = "[bcdgjklmnpsśtṭḍ]"

-- inherent vowel deletion
text = gsub(text, "(".. v_Latn .. ")bo([bnp])(".. v_Latn .. ")", "%1b%2%3")
text = gsub(text, "(".. v_Latn .. ")do([bp])(".. v_Latn .. ")", "%1d%2%3")
text = gsub(text, "(".. v_Latn .. ")dho([bp])(".. v_Latn .. ")", "%1dh%2%3")
text = gsub(text, "(".. v_Latn .. ")lo([bp])(".. v_Latn .. ")", "%1l%2%3")
text = gsub(text, "(".. v_Latn .. ")mo([bkprṛ])(".. v_Latn .. ")", "%1m%2%3")
text = gsub(text, "(".. v_Latn .. ")ro([bcghjpsś]h?)(".. v_Latn .. ")", "%1r%2%3")
text = gsub(text, "goñjo$", "gonj") -- exceptional
text = gsub(text, "goñjo ", "gonj ") -- exceptional

-- Cv
text = gsub(text, "([bgmr])v", "%1b")
text = gsub(text, "hv", "hb")
text = gsub(text, "udv", "udb")
text = gsub(text, "ttv", "tt")
text = gsub(text, "^sv", "ś") -- initial
text = gsub(text, "([sś])v", "śś") -- medial

text = gsub(text, "^(" .. consonants_no_h .. "h?)v", "%1") -- initial
text = gsub(text, "(" .. consonants_no_h .. ")v", "%1%1") -- medial
text = gsub(text, "(" .. consonants_no_h .. ")hv", "%1%1h") -- medial_h

--ahb, ihb
text = gsub(text, "ahb", "aōbh")
text = gsub(text, "ihb", "iubh")

-- kṣ
text = gsub(text, "^kṣ", "kh") -- initial
text = gsub(text, "kṣ", "kkh") -- medial
text = gsub(text, "okkhṃ", "okkh") -- medial_m

-- sm
text = gsub(text, "^([ṣs])ṃ(" .. v_Latn .. ")", "ś%2̃") -- initial
text = gsub(text, "([ṣs])ṃ(" .. v_Latn .. ")", "śś%2̃") -- medial

-- tm
text = gsub(text, "^tṃ", "t") -- initial
text = gsub(text, "tṃ", "tt") -- medial

text = gsub(text, "ṃ", "m")
text = gsub(text, "ṣ", "ś")

-- rules for changing s to ś (applicable for native words only)
text = gsub(text, "s(".. v_Latn .. ")$", "ś%1")
text = gsub(text, "s(".. v_Latn .. ") ", "ś%1 ")
text = gsub(text, "s([oō])", "ś%1")
text = gsub(text, "os$", "oś")
text = gsub(text, "os ", "oś ")

text = gsub(text, "śl", "sl")
text = gsub(text, "śr", "sr")
text = gsub(text, "sp", "śp")
text = gsub(text, "^śp", "sp")
text = gsub(text, " śp", " sp")

-- visarga deletion
text = gsub(text, "ḥkh", "kkh")

-- jñ
text = gsub(text, "jñ", "gy")

text = gsub(text, "ñ", "n")

text = gsub(text, "nḍo$", "nḍ")
text = gsub(text, "nḍo ", "nḍ ")

text = gsub(text, "rko$", "rk")
text = gsub(text, "rko ", "rk ")

text = gsub(text, "(" .. v_Latn .. ")h$", "%1ho")
text = gsub(text, "(" .. v_Latn .. ")h ", "%1ho ")

text = gsub(text, "([glś])aho$", "%1ah")
text = gsub(text, "([glś])aho ", "%1ah ")

text = gsub(text, "ṇn", "ṇon")
text = gsub(text, "ṇ", "n")

text = gsub(text, "^ek", "êk")
text = gsub(text, "^oya", "ê")
text = gsub(text, "^eya", "ê")

text = gsub(text, "^(" .. consonants_no_h .. "h?)ya", "%1ê") -- initial
text = gsub(text, " (" .. consonants_no_h .. "h?)ya", " %1ê") -- initial
text = gsub(text, "^hya", "hê") -- h_initial
text = gsub(text, "gya", "ggê") -- g_medial
text = gsub(text, "yal$", "êl") -- final_l

text = gsub(text, "yanḍ", "ênḍ")

-- Cy
text = gsub(text, "^(" .. consonants_no_h .. "h?)y", "%1") -- initial
text = gsub(text, "(" .. consonants_no_h .. ")y", "%1%1") -- medial
text = gsub(text, "(" .. consonants_no_h .. ")hy", "%1%1h") -- medial_h
text = gsub(text, "^hy", "jh") -- h_initial
text = gsub(text, "hy", "jjh") -- h_medial
text = gsub(text, "ry", "rj")

text = gsub(text, "ẏo([gklmn])([aeiīōuū])", "ẏ%1%2")
text = gsub(text, "ẏoō", "ẏō")
text = gsub(text, "oō$", "ō")

text = gsub(text, "([ei])ẏ([" .. consonant .. "])", "%1ẏo%2")
text = gsub(text, "([ei])ẏ$", "%1ẏo")

text = gsub(text, "śṭh$", "śṭho")

text = gsub(text, "^([kg]h?)([dḍtṭ])", "%1o%2")
text = gsub(text, "([au])b$", "%1bo")
text = gsub(text, "([au])b ", "%1bo ")

text = gsub(text, "([tb]h?)ob$", "%1obo") -- exceptional
text = gsub(text, "([tb]h?)ob ", "%1obo ") -- exceptional

text = gsub(text, "([au])bh$", "%1bho")
text = gsub(text, "([au])bh ", "%1bho ")
text = gsub(text, "^l([au])bho$", "l%1bh")
text = gsub(text, "^l([au])bho ", "l%1bh ")

text = gsub(text, "lona$", "lna")
text = gsub(text, "nola$", "nla")

text = gsub(text, "ōẏ", "ōẇ")
text = gsub(text, "ō̃ẏ", "ō̃ẇ")

text = gsub(text, "oo", "o")

if match(text, "[ঁ-৽]") and mode ~= "debug" then
return nil
else
return mw.ustring.toNFC(text)
end
end

return export

Module:inc-mbn-translit - Revision history

Sware: 1 revision imported

wikt>Sbb1413 at 13:34, 26 April 2023