Module:zle-ort-translit
Appearance
- පහත දැක්වෙන උපදෙස්, Module:documentation/functions/translit මගින් ජනනය කොට ඇත. [සංස්කරණය කරන්න]
- ප්රයෝජනවත් සබැඳි: උප පිටු ලැයිස්තුව • සබැඳි • transclusions • testcases • sandbox (වෙනස)
This module will transliterate Old Ruthenian භාෂාව text.
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:zle-ort-translit/testcases.
Functions
[සංස්කරණය]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, returns
nil
.
local export = {}
local letters = {}
local digraphs = {}
local double_grave = mw.ustring.char(0x30F)
letters["Cyrs"] = {
-- main letters
["А"]='A', ["Б"]='B', ["В"]='V', ["Г"]='H', ["Д"]='D', ["Е"]='E', ["Ж"]='Ž', ["З"]='Z', ["Ї"]='I', ["И"]='I', ["Й"]='J',
["К"]='K', ["Л"]='L', ["М"]='M', ["Н"]='N', ["О"]='O', ["П"]='P', ["Р"]='R', ["С"]='S', ["Т"]='T', ["У"]='U', ["Ф"]='F',
["Х"]='X', ["Ѡ"]='O', ["Ѿ"]='Ot', ["Ц"]='C', ["Ч"]='Č', ["Ш"]='Š', ["Щ"]='Šč', ["Ъ"]='', ["Ы"]='Y', ["Ь"]='ʹ',
["Ѣ"]='Jě', ["Є"]='Je', ["Ю"]='Ju', ["Ꙗ"]='Ja', ["Ѧ"]='Ja',
["а"]='a', ["б"]='b', ["в"]='v', ["г"]='h', ["д"]='d', ["е"]='e', ["ж"]='ž', ["з"]='z', ["ї"]='i', ["и"]='i', ["й"]='j',
["к"]='k', ["л"]='l', ["м"]='m', ["н"]='n', ["о"]='o', ["п"]='p', ["р"]='r', ["с"]='s', ["т"]='t', ["у"]='u', ["ф"]='f',
["х"]='x', ["ѡ"]='o', ["ѿ"]='ot', ["ц"]='c', ["ч"]='č', ["ш"]='š', ["щ"]='šč', ["ъ"]='', ["ы"]='y', ["ь"]='ʹ',
["ѣ"]='jě', ["є"]='je', ["ю"]='ju', ["ꙗ"]='ja', ["ѧ"]='ja',
-- extended letters
["Ґ"]='G', ["Ѕ"]='Z', ["І"]='I', ["Ꙋ"]='U', ["Ѫ"]='U', ["Ѯ"]='Ks', ["Ѱ"]='Ps', ["Ѳ"]='F', ["Ѵ"]='I', ["Я"]='Ja',
["ґ"]='g', ["ѕ"]='z', ["і"]='i', ["ꙋ"]='u', ["ѫ"]='u', ["ѯ"]='ks', ["ѱ"]='ps', ["ѳ"]='f', ["ѵ"]='i', ["я"]='ja',
-- archaic letters & other
["Э"]='E', ["Ꙁ"]='Z', ["Ѻ"]='O', ["Ꙍ"]='O', ["Ѽ"]='O', ["Ꙑ"]='Y', ["Ꙓ"]='Jě', ["Ѥ"]='Je', ["Ѩ"]='Ja', ["Ѭ"]='Ju', ["Ѷ"]='I' .. double_grave,
["э"]='e', ["ꙁ"]='z', ["ѻ"]='o', ["ꙍ"]='o', ["ѽ"]='o', ["ꙑ"]='y', ["ꙓ"]='jě', ["ѥ"]='je', ["ѩ"]='ja', ["ѭ"]='ju', ["ѷ"]='i' .. double_grave, ["ⸯ"]='',
}
digraphs["Cyrs"] = {
["бѣлоу"]="bělou", ["бѣлоу́"]="běloú",
["О[УѴуѵ]"]="U", ["о[уѵ]"]="u", ["К[Гг]"]="G", ["кг"]="g", ["іа"]="ja",
["ъ([аеїиоуѡъыьѣєюꙗѧіꙋѫѵяэѻꙍѽꙑꙓѥѩѭѷ])"]="ʺ%1",
["([аеїиоуѡъыьѣєюꙗѧіꙋѫѵяэѻꙍѽꙑꙓѥѩѭѷАЕЇИОУѠЪЫЬѢЄЮꙖѦІꙊѪѴЯЭѺꙌѼꙐꙒѤѨѬѶ])е"]="%1je",
["([ъыіѵꙑ])и"]="%1j",
["([аеїиоуѡъыьѣєюꙗѧіꙋѫѵяэѻꙍѽꙑꙓѥѩѭѷАЕЇИОУѠЪЫЬѢЄЮꙖѦІꙊѪѴЯЭѺꙌѼꙐꙒѤѨѬѶ])ⸯ"]="%1j",
["([бвгджзйклмнпрстфхцчшщґѕѯѱѳꙁБBГДЖЗЙКЛМНПРСТФХЦЧШЩҐЅѮѰѲꙀ-])ѡ"]="%1ô",
["([бвгджзйклмнпрстфхцчшщґѕѯѱѳꙁБBГДЖЗЙКЛМНПРСТФХЦЧШЩҐЅѮѰѲꙀ-])ѣ"]="%1ě",
["([АаЯяꙖꙗѦѧѨѩ])ѵ"]="%1v", ["([АаЯяꙖꙗѦѧѨѩ])Ѵ"]="%1V",
["([оь])и"]="%1ʲi", ["цъ"]="cʹ",
["ї([оѡ])"]="j%1", ["Ї([оѡ])"]="J%1", ["и([оѡ])"]="j%1", ["И([оѡ])"]="J%1",
}
function export.tr(text, lang, sc)
if not sc then
sc = require("Module:languages").getByCode(lang):findBestScript(text):getCode()
end
-- Ѣ was pronounced differently in Old Ukrainian
if lang == "zle-ouk" then
letters["Cyrs"]["Ѣ"]='Ji'
letters["Cyrs"]["ѣ"]='ji'
digraphs["Cyrs"]["([бвгджзйклмнпрстфхцчшщґѕѯѱѳꙁБBГДЖЗЙКЛМНПРСТФХЦЧШЩҐЅѮѰѲꙀ-])ѣ"]='%1i'
else
letters["Cyrs"]["Ѣ"]='Jě'
letters["Cyrs"]["ѣ"]='jě'
digraphs["Cyrs"]["([бвгджзйклмнпрстфхцчшщґѕѯѱѳꙁБBГДЖЗЙКЛМНПРСТФХЦЧШЩҐЅѮѰѲꙀ-])ѣ"]='%1ě'
end
-- Transliterate the kamora as prime
text = string.gsub(text, "\210\132", "ʹ")
-- Transliterate the titlo as colon
text = string.gsub(text, mw.ustring.char(0x0483), ":")
if sc == "Cyrs" then
for key, repl in pairs(digraphs[sc]) do
text = mw.ustring.gsub(text, key, repl)
end
-- pattern for one non-ASCII character
text = string.gsub(text, '[\194-\244][\128-\191]+', letters[sc])
end
return text
end
return export