This module will transliterate Kuvi language text. It is also used to transliterate Kui (India), Manda (India), and Pengo.
The module should preferably not be called directly from templates or other modules.
To use it from a template, use {{xlit}}
.
Within a module, use Module:languages#Language:transliterate.
For testcases, see Module:kxv-translit/testcases.
tr(text, lang, sc)
text
written in the script specified by the code sc
, and language specified by the code lang
.nil
.All tests passed. (refresh)
Text | Expected | Actual | Comments | |
---|---|---|---|---|
ଅଡୁ | oḍu | oḍu | independent ଅ is o | |
ଓଡୁ | oḍu | oḍu | independent ଓ is o | |
ଅ୕ଡୁ | ōḍu | ōḍu | independent ଅ୕ is ō | |
ଓଓଡୁ | ōḍu | ōḍu | independent ଓଓ is ō | |
ଆକୁ | aku | aku | independent ଆ is a | |
ଆ୕କୁ | āku | āku | independent ଆ୕ is ā | |
ଆଆକୁ | āku | āku | independent ଆଆ is ā | |
ଏସ୍କି | eski | eski | independent ଏ is e | |
ଏ୕ସ୍କି | ēski | ēski | independent ଏ୕ is ē | |
ଏଏସ୍କି | ēski | ēski | independent ଏଏ is ē | |
କଡି | koḍi | koḍi | dependent ଅ/ଓ is o | |
କ୕ଡି | kōḍi | kōḍi | dependent ଅ୕ is ō | |
କୋଓଡି | kōḍi | kōḍi | dependent ଓଓ is ō | |
ବାଲା | bala | bala | dependent ଆ is a | |
ବା୕ଲା | bāla | bāla | dependent ଆ୕ is ā | |
ବଆଲା | bāla | bāla | dependent ଆଆ is ā | |
ମେଣ୍ଡା | meṇḍa | meṇḍa | dependent ଏ is e | |
ମେ୕ଣ୍ଡା | mēṇḍa | mēṇḍa | dependent ଏ୕ is ē | |
ମେଏଣ୍ଡା | mēṇḍa | mēṇḍa | dependent ଏଏ is ē | |
ଇଇ | ī | ī | independent ଇଇ is ī | |
ଉଉ | ū | ū | independent ଉଉ is ū | |
କିଇ | kī | kī | dependent ଇଇ is ī | |
କୁଉ | kū | kū | dependent ଉଉ is ū | |
କୁଃଏ | kuʔe | kuʔe | glottal stop ʔ | |
ବିସେୟିଁ | biseyĩ | biseyĩ | chandrabindu |
local export = {}
local gsub = mw.ustring.gsub
local consonants = {
--common
="k", ="kh", ="g", ="gh", ="ṅ",
="c", ="ch", ="j", ="jh", ="ñ",
="ṭ", ="ṭh", ="ḍ", ="ḍh", ="ṇ",
="t", ="th", ="d", ="dh", ="n",
="p", ="ph", ="b", ="bh", ="m",
="j", ="y", ="r", ="l", ="ḷ",
="v", ="w", ="ś", ="ṣ", ="s", ="h",
--nuktas
="q", ="x", ="ġ", ="z", ="ź",
="ṛ", ="ṛh", ="f",
}
local diacritics = {
="a", ="i", ="ī", ="u", ="ū", ="ru", ="rū",
="lu", ="lū", ="e", ="oi", ="oi", ="o", ="ou", ="ou",
="",
}
local tt = {
-- vowels
="o", ="a", ="i", ="ī", ="u", ="ū", ="ru", ="rū",
="lu", ="lū", ="e", ="oi", ="o", ="ou",
-- chandrabindu
="̃", --until a better method is found
-- anusvara
="ṁ", --until a better method is found
-- visarga
="ʔ",
-- avagraha
="’",
--numerals
="0", ="1", ="2", ="3", ="4", ="5", ="6", ="7", ="8", ="9",
="¼", ="½", ="¾", ="¹⁄₁₆", ="⅛", ="³⁄₁₆",
--punctuation
=".", --danda
}
function export.tr(text, lang, sc)
text = gsub(
text,
"(଼?)"..
"(?)",
function(c, d)
if not consonants then
return c
end
if d == "" then
return consonants .. "o"
else
return consonants .. diacritics
end
end)
text = mw.ustring.gsub(text, ".", tt)
-- anusvara
text = gsub(text, 'ṁ()', 'ṅ%1')
text = gsub(text, 'ṁ()', 'ñ%1')
text = gsub(text, 'ṁ()', 'ṇ%1')
text = gsub(text, 'ṁ()', 'n%1')
text = gsub(text, 'ṁ()', 'm%1')
-- long vowels
text = gsub(text, '()%1', '%1̄') -- VV → V̄
text = gsub(text, '()୕', '%1̄')
text = gsub(text, 'oa', 'ā')
text = gsub(text, 'aā', 'ā')
return mw.ustring.toNFC(text)
end
return export