182
edits
No edit summary |
No edit summary |
||
| (45 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
-- apologies to anyone horrified by my primitive coding ability | |||
local export = {} | local export = {} | ||
| Line 4: | Line 6: | ||
local word = type(frame) == "table" and frame.args[1] or frame | local word = type(frame) == "table" and frame.args[1] or frame | ||
-- go from orthography to one-to-one | -- go from orthography to a one-to-one phonemic map | ||
word = string.gsub(word, "mb", "B") | word = string.gsub(word, "aa", "ā") | ||
word = string.gsub(word, "áa", "â") | |||
word = string.gsub(word, "aá", "ǎ") | |||
word = string.gsub(word, "aai", "Ā") | |||
word = string.gsub(word, "áai", "Â") | |||
word = string.gsub(word, "aái", "Ǎ") | |||
word = string.gsub(word, "ai", "A") | |||
word = string.gsub(word, "ái", "Á") | |||
word = string.gsub(word, "^mb", "B") | |||
word = string.gsub(word, "ei", "ē") | |||
word = string.gsub(word, "éi", "ê") | |||
word = string.gsub(word, "eí", "ě") | |||
word = string.gsub(word, "nd", "D") | word = string.gsub(word, "nd", "D") | ||
word = string.gsub(word, "ng", "G") | word = string.gsub(word, "ng", "G") | ||
word = string.gsub(word, "ḫ", "H") | word = string.gsub(word, "ḫ", "H") | ||
word = string.gsub(word, "ii", "ī") | word = string.gsub(word, "ii", "ī") | ||
word = string.gsub(word, "íi", "î") | word = string.gsub(word, "íi", "î") | ||
word = string.gsub(word, "ií", "ǐ") | word = string.gsub(word, "ií", "ǐ") | ||
word = string.gsub(word, " | word = string.gsub(word, "oi", "I") | ||
word = string.gsub(word, " | word = string.gsub(word, "ói", "Í") | ||
word = string.gsub(word, " | word = string.gsub(word, "jh", "J") | ||
word = string.gsub(word, "nkk", "Kk") | |||
word = string.gsub(word, "ou", "ō") | word = string.gsub(word, "ou", "ō") | ||
word = string.gsub(word, "óu", "ô") | word = string.gsub(word, "óu", "ô") | ||
word = string.gsub(word, "oú", "ǒ") | word = string.gsub(word, "oú", "ǒ") | ||
word = string.gsub(word, "aao", "Ō") | word = string.gsub(word, "aao", "Ō") | ||
word = string.gsub(word, "áao", "Ô") | word = string.gsub(word, "áao", "Ô") | ||
| Line 34: | Line 37: | ||
word = string.gsub(word, "ao", "O") | word = string.gsub(word, "ao", "O") | ||
word = string.gsub(word, "áo", "Ó") | word = string.gsub(word, "áo", "Ó") | ||
word = string.gsub(word, " | word = string.gsub(word, "mp", "P") | ||
word = string.gsub(word, " | word = string.gsub(word, "ntt", "Tt") | ||
word = mw.text.split(word, "", true) | word = mw.text.split(word, "", true) | ||
| Line 85: | Line 87: | ||
-- isolate syllable boundary marks | -- isolate syllable boundary marks | ||
stresses = string.gsub(table.concat(result), "[^%.ˈ]", "") | |||
stresses = mw.text.split(stresses, "", true) | stresses = mw.text.split(stresses, "", true) | ||
-- compute position of stress | -- compute position of stress | ||
syllables = 0 | |||
pos = 0 | pos = 0 | ||
for i,val in | for i,val in ipairs(stresses) do | ||
if | syllables = syllables + 1 | ||
if val == "ˈ" then | |||
pos = i | pos = i | ||
end | end | ||
| Line 101: | Line 103: | ||
-- mark secondary stress | -- mark secondary stress | ||
for i,val in stresses do | for i,val in ipairs(stresses) do | ||
if | if val == "." and (i ~= syllables) then | ||
if (i - pos) % 2 == 0 then | if (i - pos) % 2 == 0 then | ||
table.insert(newStresses, "ˌ") | table.insert(newStresses, "ˌ") | ||
else | else | ||
table.insert(newStresses, ".") | |||
end | end | ||
else | else | ||
| Line 115: | Line 115: | ||
end | end | ||
newWord = {} | newWord = {} | ||
index = 1 | index = 1 | ||
for val in | for i,val in ipairs(result) do | ||
if | -- look through word and replace the correct .'s with ˌ's | ||
if (i == 1) and val == "." and newStresses[1] == "." then | |||
index = index + 1 | |||
elseif val == "." or val == "ˈ" then | |||
table.insert(newWord, newStresses[index]) | table.insert(newWord, newStresses[index]) | ||
index = index + 1 | index = index + 1 | ||
-- allophonic rules, i.e., from a one-to-one phonemic map to a one-to- | |||
-- one phonetic map: vowels first | |||
elseif val == "a" then | |||
if newStresses[index-1] == "." then | |||
table.insert(newWord, "w") | |||
else | |||
table.insert(newWord, "a") | |||
end | |||
elseif val == "A" then | |||
if newStresses[index-1] == "." then | |||
table.insert(newWord, "W") | |||
else | |||
table.insert(newWord, "A") | |||
end | |||
elseif val == "O" then | |||
if newStresses[index-1] == "." then | |||
table.insert(newWord, "x") | |||
else | |||
table.insert(newWord, "O") | |||
end | |||
elseif val == "e" then | |||
if newStresses[index-1] == "." then | |||
if result[i+1] ~= nil then | |||
if mw.ustring.match(result[i+1], "[ntzdr]") then | |||
table.insert(newWord, "3") | |||
elseif result[i+2] ~= nil then | |||
if mw.ustring.match(result[i+1], "[%.ˌˈ]") and mw.ustring.match(result[i+2], "[ntzdr]") then | |||
table.insert(newWord, "3") | |||
else | |||
table.insert(newWord, "e") | |||
end | |||
else | |||
table.insert(newWord, "e") | |||
end | |||
else | |||
table.insert(newWord, "e") | |||
end | |||
else | |||
table.insert(newWord, "e") | |||
end | |||
elseif val == "i" then | |||
if newStresses[index-1] == "." then | |||
if result[i+1] == "H" then | |||
table.insert(newWord, "1") | |||
elseif ((result[i+1] == ".") or (result[i+1] == "ˌ") or (result[i+1] == "ˈ")) and (result[i+2] == "H") then | |||
table.insert(newWord, "1") | |||
elseif ((result[i-1] == "m") or (result[i-1] == "n") or (result[i-1] == "j")) and (result[i+1] ~= nil) then | |||
if mw.ustring.match(result[i+1], "[mnjPTt]") then | |||
table.insert(newWord, "6") | |||
elseif (result[i+1] == "k") or (result[i+1] == "K") then | |||
table.insert(newWord, "7") | |||
elseif mw.ustring.match(result[i+1], "[%.ˌˈ]") then | |||
if mw.ustring.match(result[i+2], "[mnjt]") then | |||
table.insert(newWord, "6") | |||
elseif (result[i+2] == "k") or (result[i+2] == "kK") then | |||
table.insert(newWord, "7") | |||
else | |||
table.insert(newWord, "i") | |||
end | |||
else | |||
table.insert(newWord, "i") | |||
end | |||
else | |||
table.insert(newWord, "i") | |||
end | |||
else | |||
if result[i+1] == "H" then | |||
table.insert(newWord, "u") | |||
elseif ((result[i+1] == ".") or (result[i+1] == "ˌ") or (result[i+1] == "ˈ")) and (result[i+2] == "H") then | |||
table.insert(newWord, "u") | |||
else | |||
table.insert(newWord, "i") | |||
end | |||
end | |||
elseif val == "í" then | |||
if result[i+1] == "H" then | |||
table.insert(newWord, "ú") | |||
elseif ((result[i+1] == ".") or (result[i+1] == "ˌ") or (result[i+1] == "ˈ")) and (result[i+2] == "H") then | |||
table.insert(newWord, "ú") | |||
else | |||
table.insert(newWord, "í") | |||
end | |||
elseif val == "ī" then | |||
if result[i+1] == "H" then | |||
table.insert(newWord, "ū") | |||
elseif ((result[i+1] == ".") or (result[i+1] == "ˌ") or (result[i+1] == "ˈ")) and (result[i+2] == "H") then | |||
table.insert(newWord, "ū") | |||
else | |||
table.insert(newWord, "ī") | |||
end | |||
elseif val == "î" then | |||
if result[i+1] == "H" then | |||
table.insert(newWord, "û") | |||
elseif ((result[i+1] == ".") or (result[i+1] == "ˌ") or (result[i+1] == "ˈ")) and (result[i+2] == "H") then | |||
table.insert(newWord, "û") | |||
else | |||
table.insert(newWord, "î") | |||
end | |||
elseif val == "ǐ" then | |||
if result[i+1] == "H" then | |||
table.insert(newWord, "ǔ") | |||
elseif ((result[i+1] == ".") or (result[i+1] == "ˌ") or (result[i+1] == "ˈ")) and (result[i+2] == "H") then | |||
table.insert(newWord, "ǔ") | |||
else | |||
table.insert(newWord, "ǐ") | |||
end | |||
elseif val == "ó" then | |||
if (result[i-1] == "m") or (result[i-1] == "p") or (result[i-1] == "B") then | |||
table.insert(newWord, "Ú") | |||
else | |||
table.insert(newWord, "ó") | |||
end | |||
elseif val == "ô" then | |||
if (result[i-1] == "m") or (result[i-1] == "p") or (result[i-1] == "B") then | |||
table.insert(newWord, "Û") | |||
else | |||
table.insert(newWord, "ô") | |||
end | |||
elseif val == "ǒ" then | |||
if (result[i-1] == "m") or (result[i-1] == "p") or (result[i-1] == "B") then | |||
table.insert(newWord, "Ǔ") | |||
else | |||
table.insert(newWord, "ǒ") | |||
end | |||
elseif val == "ó" then | |||
if (result[i-1] == "m") or (result[i-1] == "p") or (result[i-1] == "B") then | |||
table.insert(newWord, "Ú") | |||
else | |||
table.insert(newWord, "ó") | |||
end | |||
elseif val == "Í" then | |||
if (result[i-1] == "m") or (result[i-1] == "p") or (result[i-1] == "B") then | |||
table.insert(newWord, "X") | |||
else | |||
table.insert(newWord, "Í") | |||
end | |||
-- now let's do consonants | |||
elseif val == "n" then | |||
if ((result[i+1] == ".") or (result[i+1] == "ˌ") or (result[i+1] == "ˈ")) and (result[i+2] == "j") then | |||
table.insert(newWord, "j") | |||
elseif ((result[i+1] == ".") or (result[i+1] == "ˌ") or (result[i+1] == "ˈ")) and (result[i+2] == "k") then | |||
table.insert(newWord, "N") | |||
else | |||
table.insert(newWord, "n") | |||
end | |||
elseif val == "j" then | |||
if result[i-1] == "ˈ" then | |||
if result[i-2] == nil then | |||
table.insert(newWord, "Z") | |||
elseif mw.ustring.match(result[i-2], "[iīeēoōIaāAĀOŌ]") then | |||
table.insert(newWord, "Z") | |||
else | |||
table.insert(newWord, "j") | |||
end | |||
else | |||
table.insert(newWord, "j") | |||
end | |||
elseif val == "t" then | |||
if ((result[i-1] == ".") or (result[i-1] == "ˌ") or (result[i-1] == "ˈ")) and (result[i-2] == "n") then | |||
table.insert(newWord, "2") | |||
else | |||
table.insert(newWord, "t") | |||
end | |||
elseif val == "k" then | |||
if ((result[i-1] == ".") or (result[i-1] == "ˌ") or (result[i-1] == "ˈ")) and (result[i-2] == "n") then | |||
table.insert(newWord, "4") | |||
else | |||
table.insert(newWord, "k") | |||
end | |||
elseif val == "b" then | |||
if ((result[i-1] == ".") or (result[i-1] == "ˌ") or (result[i-1] == "ˈ")) and (result[i-2] == "m") then | |||
table.insert(newWord, "8") | |||
elseif result[i+1] == nil then | |||
table.insert(newWord, "v") | |||
else | |||
table.insert(newWord, "b") | |||
end | |||
else | else | ||
table.insert(newWord, val) | table.insert(newWord, val) | ||
| Line 129: | Line 308: | ||
word = table.concat(newWord) | word = table.concat(newWord) | ||
-- go from one-to-one | word = string.gsub(word, "x", "ɐɔ̯") | ||
-- go from one-to-one phonetic map to IPA | |||
word = string.gsub(word, "ā", "aː") | |||
word = string.gsub(word, "â", "âː") | |||
word = string.gsub(word, "ǎ", "ǎː") | |||
word = string.gsub(word, "A", "aɪ̯") | |||
word = string.gsub(word, "Á", "áɪ̯") | |||
word = string.gsub(word, "Ā", "aːɪ̯") | |||
word = string.gsub(word, "Â", "âːɪ̯") | |||
word = string.gsub(word, "Ǎ", "ǎːɪ̯") | |||
word = string.gsub(word, "b", "β") | |||
word = string.gsub(word, "B", "ᵐb") | word = string.gsub(word, "B", "ᵐb") | ||
word = string.gsub(word, "D", " | word = string.gsub(word, "d", "ð") | ||
word = string.gsub(word, " | word = string.gsub(word, "D", "ⁿd̪") | ||
word = string.gsub(word, "ē", "eːɪ̯") | |||
word = string.gsub(word, "ê", "êːɪ̯") | |||
word = string.gsub(word, "ě", "ěːɪ̯") | |||
word = string.gsub(word, "G", "ᵑg") | word = string.gsub(word, "G", "ᵑg") | ||
word = string.gsub(word, " | word = string.gsub(word, "h", "ɦ") | ||
word = string.gsub(word, "H", "x") | word = string.gsub(word, "H", "x") | ||
word = string.gsub(word, "ī", "iː") | word = string.gsub(word, "ī", "iː") | ||
word = string.gsub(word, "î", "îː") | word = string.gsub(word, "î", "îː") | ||
word = string.gsub(word, "ǐ", "ǐː") | word = string.gsub(word, "ǐ", "ǐː") | ||
word = string.gsub(word, " | word = string.gsub(word, "I", "ɔɪ̯") | ||
word = string.gsub(word, " | word = string.gsub(word, "Í", "ɔ́ɪ̯") | ||
word = string.gsub(word, " | word = string.gsub(word, "j", "ȵ") | ||
word = string.gsub(word, "J", "ʑ") | |||
word = string.gsub(word, "K", "ŋk") | |||
word = string.gsub(word, "n", "n̪") | |||
word = string.gsub(word, "N", "ŋ") | |||
word = string.gsub(word, "o", "ɔ") | word = string.gsub(word, "o", "ɔ") | ||
word = string.gsub(word, "ó", "ɔ́") | word = string.gsub(word, "ó", "ɔ́") | ||
| Line 157: | Line 343: | ||
word = string.gsub(word, "ô", "ɔ̂ːʊ̯") | word = string.gsub(word, "ô", "ɔ̂ːʊ̯") | ||
word = string.gsub(word, "ǒ", "ɔ̌ːʊ̯") | word = string.gsub(word, "ǒ", "ɔ̌ːʊ̯") | ||
word = string.gsub(word, "O", "aɔ̯") | word = string.gsub(word, "O", "aɔ̯") | ||
word = string.gsub(word, "Ó", "áɔ̯") | word = string.gsub(word, "Ó", "áɔ̯") | ||
| Line 172: | Line 348: | ||
word = string.gsub(word, "Ô", "âːɔ̯") | word = string.gsub(word, "Ô", "âːɔ̯") | ||
word = string.gsub(word, "Ǒ", "ǎːɔ̯") | word = string.gsub(word, "Ǒ", "ǎːɔ̯") | ||
word = string.gsub(word, "P", "mp") | |||
word = string.gsub(word, "r", "ɺ") | |||
word = string.gsub(word, "s", "ɕ") | |||
word = string.gsub(word, "t", "t̪") | |||
word = string.gsub(word, "T", "n̪t̪") | |||
word = string.gsub(word, "u", "ʲɪ") | |||
word = string.gsub(word, "ú", "íɪ̯") | |||
word = string.gsub(word, "ū", "iːɪ̯") | |||
word = string.gsub(word, "û", "îːɪ̯") | |||
word = string.gsub(word, "ǔ", "ǐːɪ̯") | |||
word = string.gsub(word, "Ú", "ʊ̯ɔ́") | |||
word = string.gsub(word, "Û", "ʊ̯ɔ̂ːʊ̯") | |||
word = string.gsub(word, "Ǔ", "ʊ̯ɔ̌ːʊ̯") | |||
word = string.gsub(word, "v", "v") | |||
word = string.gsub(word, "w", "ɐ") | |||
word = string.gsub(word, "W", "ɐɪ̯") | |||
word = string.gsub(word, "X", "ʊ̯ɔ́ɪ̯") | |||
word = string.gsub(word, "y", "j") | |||
word = string.gsub(word, "z", "θ̱") | |||
word = string.gsub(word, "Z", "ᶮȡ") | |||
word = string.gsub(word, "1", "ɪ") | |||
word = string.gsub(word, "2", "d̪") | |||
word = string.gsub(word, "3", "ɛ") | |||
word = string.gsub(word, "4", "g") | |||
word = string.gsub(word, "6", "ȵ̩") | |||
word = string.gsub(word, "7", "ŋ̩ʲ") | |||
word = string.gsub(word, "8", "b") | |||
return " | return "[" .. word .. "]" | ||
end | end | ||
return export | return export | ||
edits