模組:Kham-translit
這個模組會將加馬爾卡姆語未確定的文字拉丁化。
最好不要直接從模板或其他模組調用此模組。要從模板中使用它,請以{{xlit}}
做為替代;若要在模組中使用,則以Module:languages#Language:transliterate替代。
關於測試用例,請參閱Module:Kham-translit/testcases。
函數
编辑tr(text, lang, sc)
- Transliterates a given piece of
text
written in the script specified by the codesc
, and language specified by the codelang
. When the transliteration fails, returnsnil
.
local export = {}
local gsub = mw.ustring.gsub
local match = mw.ustring.match
local conv = {
-- consonants
['क'] = 'k', ['ख'] = 'kh', ['ग'] = 'g', ['घ'] = 'gh', ['ङ'] = 'ṅ',
['च'] = 'c', ['छ'] = 'ch', ['ज'] = 'j', ['झ'] = 'jh', ['ञ'] = 'ñ',
['ट'] = 'ṭ', ['ठ'] = 'ṭh', ['ड'] = 'ḍ', ['ढ'] = 'ḍh', ['ण'] = 'ṇ',
['त'] = 't', ['थ'] = 'th', ['द'] = 'd', ['ध'] = 'dh', ['न'] = 'n',
['प'] = 'p', ['फ'] = 'ph', ['ब'] = 'b', ['भ'] = 'bh', ['म'] = 'm',
['य'] = 'y', ['र'] = 'r', ['ल'] = 'l', ['व'] = 'w', ['ळ'] = 'ḷ',
['श'] = 'ś', ['ष'] = 'ṣ', ['स'] = 's', ['ह'] = 'h', ['ज़'] = 'z',
['झ़'] = 'zh', ['व़'] = 'ẏ',
--
['क़'] = 'q', ['ख़'] = 'x', ['ग़'] = 'ġ',
['ऴ'] = 'ḻ', ['ड़'] = 'ṛ', ['ढ़'] = 'ṛh',
['फ़'] = 'f', ['थ़'] = 'θ',['द़'] = 'ð',
['ऩ'] = 'ṉ', ['ऱ'] = 'ṟ', ['स़'] = 'z',
['च़'] = 'c', ['छ़'] = 'ch', ['ॹ'] = 'ž',
['श़'] = 'ž',
-- vowel diacritics
['ि'] = 'i', ['ु'] = 'u', ['े'] = 'e', ['ो'] = 'o', ['ा'] = 'ā', ['ी'] = 'ī', ['ू'] = 'ū', ['ृ'] = 'r̥', ['ॄ'] = 'r̥̄', ['ॢ'] = 'l̥', ['ॣ'] = 'l̥̄', ['ै'] = 'ai', ['ौ'] = 'au', ['ॉ'] = 'ŏ', ['ॅ'] = 'ĕ', ['ॆ'] = 'e', ['ॊ'] = 'o',
-- vowel signs
['अ'] = 'a', ['इ'] = 'i', ['इ़'] = 'ü', ['उ'] = 'u', ['उ़'] = 'ï', ['ए'] = 'e', ['ए़'] = 'ø', ['ओ'] = 'o', ['आ'] = 'ā', ['ई'] = 'ī', ['ऊ'] = 'ū', ['ऋ'] = 'r̥', ['ॠ'] = 'r̥̄', ['ऌ'] = 'l̥', ['ॡ'] = 'l̥̄', ['ऐ'] = 'ai', ['औ'] = 'au', ['ऑ'] = 'ŏ', ['ॲ'] = 'ĕ', ['ऍ'] = 'ĕ', ['ऎ'] = 'e', ['ऒ'] = 'o',
-- chandrabindu
['ँ'] = '̃',
-- anusvara
['ं'] = '̃',
-- visarga
['ः'] = 'ḥ',
-- virama
['्'] = '',
-- glottal stop
['ॽ'] = "’",
-- high spacing dot
['ॱ'] = "'",
-- avagraha
['ऽ'] = "'",
--- dot
['.'] = "'",
--
['°'] = "'",
-- numerals
['०'] = '0', ['१'] = '1', ['२'] = '2', ['३'] = '3', ['४'] = '4', ['५'] = '5', ['६'] = '6', ['७'] = '7', ['८'] = '8', ['९'] = '9',
-- punctuation
['।'] = '.', -- danda
['॥'] = '.', -- double danda
['+'] = '', -- compound separator
-- abbreviation sign
['॰'] = '.',
}
local all_cons, special_cons = 'कखगघङचछजझञटठडढणतथदधनपफबभमयरलवसशषह', 'कखगघचछजझटठडढणतथदधनपफबभमयरलवशषसह'
local vowel, vowel_sign = 'aिुृेोाीूैौॉॅॆॊॄॢॣॆॊ', 'अइउएओआईऊऋॠॡऌऐऔऎऒए़इ़ऑऍ'
local function rev_string(text)
local result, length = {}, mw.ustring.len(text)
for i = length, 1, -1 do
table.insert(result, mw.ustring.sub(text, i, i))
end
return table.concat(result)
end
function export.tr(text, lang, sc)
text = gsub(text, '([' .. all_cons .. ']़?)([' .. vowel .. '्]?)', function(c, d)
return c .. (d == "" and 'a' or d) end)
for word in mw.ustring.gmatch(text, "[ऀ-ॿa]+") do
local orig_word = word
word = rev_string(word)
word = gsub(word, '^a(़?)([' .. all_cons .. '])(.)(.?)', function(opt, first, second, third)
return (((match(first, '[' .. special_cons .. ']') and match(second, 'ं')
or match(first, '[' .. special_cons .. ']') and match(second, '्') and not perm_cl[first..second..third])
or match(first .. second, 'य[aिुृेोाीूैौॉॅॆॊआईउऊइएऐओऔ]') or match(first .. second, 'ह[अaिुृेोाीूैौॉॅॆॊआईउऊइएऐओऔ]'))
and 'a' or "") .. opt .. first .. second .. third end)
local escaped_orig_word = gsub(orig_word, "%+", "") text = gsub(text, orig_word, rev_string(word))
text = gsub(text, 'ज्ञ', 'gy')
text = gsub(text, "ॱ([" .. all_cons .. "])(़?)(्?)([वयरल]?)(़?)([" .. vowel .. "]?)([ँँं]?)(ः?)", "%1%2%3%4%5%6%7%8'") end
text = gsub(text, '.़?', conv)
text = gsub(text, 'a([iu])̃', 'a͠%1')
text = gsub(text, 'rh̥', 'hr̥')
text = gsub(text, "[<>]", "")
return mw.ustring.toNFC(text)
end
return export