Module:ta-translit
Itsura
- The following documentation is generated by Module:documentation/functions/translit. [edit]
- Useful links: subpage list • links • transclusions • testcases • sandbox
This module will transliterate Wikang Tamil text. It is also used to transliterate Irula, Kota (India), Mannan, at Betta Kurumba.
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:ta-translit/testcases.
Functions
[baguhin]tr(text, lang, sc)- Transliterates a given piece of
textwritten in the script specified by the codesc, and language specified by the codelang. - When the transliteration fails, returns
nil.
local export = {}
local consonants = {
['க']='k' , ['ங']='ṅ' , ['ச']='c' , ['ஞ']='ñ' , ['ட']='ṭ' , ['ண']='ṇ' , ['த']='t' ,
['ந']='n' , ['ப']='p', ['ம']='m' , ['ய']='y' , ['ர']='r' , ['ல']='l' , ['வ']='v' ,
['ழ']='ḻ' , ['ள']='ḷ' , ['ற']='ṟ' , ['ன']='ṉ' , ['ஶ']='ś' , ['ஜ']='j' , ['ஷ']='ṣ' ,
['ஸ']='s' , ['ஹ']='h' , ['ஃப']='f' , ['ஃஜ']='z', ['ஃஸ']='ks' , ['ஃக ']='x',
['ஃ']='ḥ' , ['ௐ']='о̄m',
}
local diacritics = {
['ா']= 'ā' , ['ி']='i' , ['ீ']='ī' , ['ு']='u' , ['ூ']='ū' , ['ெ']='e' ,
['ே']='ē' , ['ை']='ai' , ['ொ']='o' , ['ோ']='ō' , ['ௌ']='au',
['்']='', --halant, supresses the inherent vowel "a"
-- no diacritic
[''] = 'a',
}
local nonconsonants = {
-- vowels
['அ']='’a' , ['ஆ']='’ā' , ['இ']='’i' , ['ஈ']='’ī' , ['உ']='’u' , ['ஊ']='’ū' ,
['எ']='’e' , ['ஏ']='’ē' , ['ஐ']='’ai' , ['ஒ']='’o' , ['ஓ']='’ō' , ['ஔ']='’au' , ['ௐ']='о̄m',
-- other symbols
-- ['ஃ']='' , ['ௐ']='о̄m',
}
-- translit any words or phrases
function export.tr(text, lang, sc)
text = mw.ustring.gsub(
text,
'(ஃ?)([க-ஹ])([ா-்]?)',
function(h, c, d)
return (consonants[h..c] or consonants[h] .. (consonants[c] or c)) .. diacritics[d]
end)
text = mw.ustring.gsub(text, '[அ-ஔ]', nonconsonants)
text = mw.ustring.gsub(text, '^’', '')
text = mw.ustring.gsub(text, '([%s%p])’', '%1')
return text
end
return export