Module:ar-translit: Difference between revisions

local export = {}

-- assigned below

end

local alif_madda = U(0x622)

local alif_hamza_below = U(0x625)

local dagger_alif = U(0x670)

local alif_waSl = U(0x671)

local tt = {

["ب"]="b", ["ت"]="t", ["ث"]="ṯ", ["ج"]="j", ["ح"]="ḥ", ["خ"]="ḵ",

["د"]="d", ["ذ"]="ḏ", ["ر"]="r", ["ز"]="z", ["س"]="s", ["ش"]="š",

["ف"]="f", ["ق"]="q", ["ك"]="k", ["ڪ"]="k", ["ل"]="l", ["م"]="m", ["ن"]="n",

["ه"]="h",

-- [zwj]="", -- ZWJ (zero-width joiner)

-- rare letters

-- semivowels or long vowels, alif, hamza, special letters

["ا"]="ā", -- ʾalif

-- hamzated letters

-- long vowels

[waaw]="w", --"ū" after ḍamma (u) and not before diacritic

[yaa]="y", --"ī" after kasra (i) and not before diacritic

[alif_maqSuura]="ā", -- ʾalif maqṣūra

[alif_waSl]= "", -- hamzatu l-waṣl

[dagger_alif] = "ā", -- ʾalif xanjariyya = dagger ʾalif (Koranic diacritic)

local sun_letters_tr = table.concat(ttsun3, "")

-- consonants on the right side; includes alif madda

local rconsonants = consonants_needing_vowels .. "ويآ"

local before_diacritic_checking_subs = {

------------ transformations prior to checking for diacritics --------------

-- convert llh for allāh into ll+shadda+dagger-alif+h

{"لله", "للّٰه"},

-- transliteration process inconvenient, so undo it.

{"([" .. fatHataan .. Dammataan .. kasrataan .. fatHa .. Damma .. kasra .. dagger_alif .. "])" .. shadda, shadda .. "%1"},

-- ignore alif jamīla (otiose alif in 3pl verb forms)

--    #1: handle ḍamma + wāw + alif (final -ū)

{alif_waSl .. fatHa .. "?" .. laam, "l-"},

-- special casing if the l in al- has a shadda on it (as in الَّذِي "that"),

-- implement assimilation of sun letters

{"l%-[" .. sun_letters .. "]", ttsun2},

if not force_translit and not has_diacritics(text) then

return nil

end

-- Otherwise, no if word ends in a/i/u, yes if ends in an/in/un.

text = rsub(text, "^(a?l%-[^%s]+)" .. taa_marbuuTa .. "([" .. fatHataan .. Dammataan .. kasrataan .. fatHa .. Damma .. kasra .. "])",

text = rsub(text, "(" .. space_like_class .. "a?l%-[^%s]+)" .. taa_marbuuTa .. "([" .. fatHataan .. Dammataan .. kasrataan .. fatHa .. Damma .. kasra .. "])",

text = rsub(text, taa_marbuuTa .. "([" .. fatHa .. Damma .. kasra .. "])", "t%1")

text = rsub(text, taa_marbuuTa .. "([" .. fatHataan .. Dammataan .. kasrataan .. "])",

text = rsub(text, ".", {

})

text = rsub(text, "([" .. fatHa .. Damma .. kasra .. "])(" .. space_like_class .. ")",

function(vowel, space)

vowel_repl = {

}

return vowel_repl[vowel] .. space

)

text = rsub(text, "[" .. fatHa .. Damma .. kasra .. "]$", {

})

elseif omit_i3raab then -- omit ʾiʿrāb in transliteration

text = rsub(text, "[" .. fatHataan .. Dammataan .. kasrataan .. "]", "")

text = rsub(text, "aā", "ā")

-- Implement elision of al- after a final vowel. We do this

-- than elision in other cases of hamzat al-waṣl (e.g. form-I imperatives

-- or form-VII and above verbal nouns) partly because elision in

-- elision in case of words written with initial bare alif instead of

-- properly with hamzated alif. Possibly we should reconsider.

"%1%2")

if gray_i3raab then

"%1%2")

end

text = rsub(text, "^(a?)l%-lāh", "%1llāh")

text = rsub(text, "(" .. space_like_class .. "a?)l%-lāh", "%1llāh")

return text

-- If you want to catch places without iʿrāb, comment out the next two lines.

{"[" .. lconsonants .. "]$", ""},

-- remove consonants (or alif) when followed by diacritics

-- must go after removing shadda

-- declared as local above

function has_diacritics(text)

local count

text, count = rsubn(text, "[" .. lrm .. rlm .. "]", "")

for _, sub in ipairs(has_diacritics_subs) do

text = rsub(text, unpack(sub))

end

return #text == 0

return export