Module:ábḫ-ipa: Difference between revisions
Jump to navigation
Jump to search
No edit summary |
No edit summary |
||
Line 4: | Line 4: | ||
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, "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, "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 35: | ||
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 93: | Line 93: | ||
for i,val in ipairs(stresses) do | for i,val in ipairs(stresses) do | ||
syllables = syllables + 1 | syllables = syllables + 1 | ||
if | if val == "ˈ" then | ||
pos = i | pos = i | ||
end | end | ||
Line 102: | Line 102: | ||
-- mark secondary stress | -- mark secondary stress | ||
for i,val in ipairs(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, | table.insert(newStresses, ".") | ||
end | end | ||
else | else | ||
Line 119: | Line 119: | ||
if (i == 1) and val == "." and newStresses[1] == "." then | if (i == 1) and val == "." and newStresses[1] == "." then | ||
index = index + 1 | index = index + 1 | ||
elseif | elseif val == "." or val == "ˈ" then | ||
table.insert(newWord, newStresses[index]) | table.insert(newWord, newStresses[index]) | ||
index = index + 1 | index = index + 1 | ||
Line 130: | Line 130: | ||
newWord = {} | newWord = {} | ||
-- allophonic rules | -- allophonic rules, i.e., from a one-to-one phonemic map to a one-to one | ||
-- phonetic map | |||
for i,val in ipairs(word) do | for i,val in ipairs(word) do | ||
if val == "a" then | if val == "a" then | ||
if word[i-1] == nil then | if word[i-1] == nil then | ||
table.insert(newWord, "w") | table.insert(newWord, "w") | ||
elseif word[i-1] == "ˌ" then | |||
table.insert(newWord, "a") | |||
elseif word[i-1] == "." then | |||
table.insert(newWord, "w") | |||
elseif word[i-2] == nil then | |||
table.insert(newWord, "w") | |||
elseif word[i-2] == "ˌ" then | |||
table.insert(newWord, "a") | |||
else | else | ||
table.insert(newWord, | table.insert(newWord, "w") | ||
end | end | ||
else | else | ||
Line 146: | Line 154: | ||
word = table.concat(newWord) | word = table.concat(newWord) | ||
-- go from one-to-one | -- go from one-to-one phonetic map to IPA | ||
word = string.gsub(word, "ā", "aː") | word = string.gsub(word, "ā", "aː") | ||
word = string.gsub(word, "â", "âː") | word = string.gsub(word, "â", "âː") |
Revision as of 02:36, 28 February 2020
- The following documentation is located at Module:ábḫ-ipa/doc.[edit]
- Useful links: subpage list • links • transclusions • testcases • sandbox
local export = {}
function export.convert(frame)
local word = type(frame) == "table" and frame.args[1] or frame
-- go from orthography to a one-to-one phonemic map
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, "ng", "G")
word = string.gsub(word, "ḫ", "H")
word = string.gsub(word, "ii", "ī")
word = string.gsub(word, "íi", "î")
word = string.gsub(word, "ií", "ǐ")
word = string.gsub(word, "oi", "I")
word = string.gsub(word, "ói", "Í")
word = string.gsub(word, "jh", "J")
word = string.gsub(word, "nkk", "Kk")
word = string.gsub(word, "ou", "ō")
word = string.gsub(word, "óu", "ô")
word = string.gsub(word, "oú", "ǒ")
word = string.gsub(word, "aao", "Ō")
word = string.gsub(word, "áao", "Ô")
word = string.gsub(word, "aáo", "Ǒ")
word = string.gsub(word, "ao", "O")
word = string.gsub(word, "áo", "Ó")
word = string.gsub(word, "mp", "P")
word = string.gsub(word, "ntt", "Tt")
word = mw.text.split(word, "", true)
result = {}
-- put in syllable boundary marks
for i,val in ipairs(word) do
if word[i-1] == nil then
if mw.ustring.match(word[i], "[íîǐéêěóôǒÍáâǎÁÂǍÓÔǑ]") then
table.insert(result, "ˈ")
table.insert(result, val)
elseif mw.ustring.match(word[i], "[mnjBDGPpTtKkbzdsJHhry]") and mw.ustring.match(word[i+1], "[íîǐéêěóôǒÍáâǎÁÂǍÓÔǑ]") then
table.insert(result, "ˈ")
table.insert(result, val)
else
table.insert(result, ".")
table.insert(result, val)
end
elseif mw.ustring.match(word[i], "[iīeēoōIaāAĀOŌ]") then
if mw.ustring.match(word[i-1], "[iīeēoōIaāAĀOŌíîǐéêěóôǒÍáâǎÁÂǍÓÔǑ]") then
table.insert(result, ".")
table.insert(result, val)
else
table.insert(result, val)
end
elseif mw.ustring.match(word[i], "[íîǐéêěóôǒÍáâǎÁÂǍÓÔǑ]") then
if mw.ustring.match(word[i-1], "[iīeēoōIaāAĀOŌíîǐéêěóôǒÍáâǎÁÂǍÓÔǑ]") then
table.insert(result, "ˈ")
table.insert(result, val)
else
table.insert(result, val)
end
else
if word[i+1] == nil then
table.insert(result, val)
elseif mw.ustring.match(word[i+1], "[iīeēoōIaāAĀOŌ]") then
table.insert(result, ".")
table.insert(result, val)
elseif mw.ustring.match(word[i+1], "[íîǐéêěóôǒÍáâǎÁÂǍÓÔǑ]") then
table.insert(result, "ˈ")
table.insert(result, val)
else
table.insert(result, val)
end
end
end
-- isolate syllable boundary marks
stresses = string.gsub(table.concat(result), "[^%.ˈ]", "")
stresses = mw.text.split(stresses, "", true)
-- compute position of stress
syllables = 0
pos = 0
for i,val in ipairs(stresses) do
syllables = syllables + 1
if val == "ˈ" then
pos = i
end
end
newStresses = {}
-- mark secondary stress
for i,val in ipairs(stresses) do
if val == "." and (i ~= syllables) then
if (i - pos) % 2 == 0 then
table.insert(newStresses, "ˌ")
else
table.insert(newStresses, ".")
end
else
table.insert(newStresses, val)
end
end
-- look through word and replace the correct .'s with ˌ's
newWord = {}
index = 1
for i,val in ipairs(result) do
if (i == 1) and val == "." and newStresses[1] == "." then
index = index + 1
elseif val == "." or val == "ˈ" then
table.insert(newWord, newStresses[index])
index = index + 1
else
table.insert(newWord, val)
end
end
word = newWord
newWord = {}
-- allophonic rules, i.e., from a one-to-one phonemic map to a one-to one
-- phonetic map
for i,val in ipairs(word) do
if val == "a" then
if word[i-1] == nil then
table.insert(newWord, "w")
elseif word[i-1] == "ˌ" then
table.insert(newWord, "a")
elseif word[i-1] == "." then
table.insert(newWord, "w")
elseif word[i-2] == nil then
table.insert(newWord, "w")
elseif word[i-2] == "ˌ" then
table.insert(newWord, "a")
else
table.insert(newWord, "w")
end
else
table.insert(newWord, val)
end
end
word = table.concat(newWord)
-- 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, "d", "ð")
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, "h", "ɦ")
word = string.gsub(word, "H", "x")
word = string.gsub(word, "ī", "iː")
word = string.gsub(word, "î", "îː")
word = string.gsub(word, "ǐ", "ǐː")
word = string.gsub(word, "I", "ɔɪ̯")
word = string.gsub(word, "Í", "ɔ́ɪ̯")
word = string.gsub(word, "j", "ɲ̟")
word = string.gsub(word, "J", "ʑ")
word = string.gsub(word, "K", "ŋk")
word = string.gsub(word, "n", "n̪")
word = string.gsub(word, "o", "ɔ")
word = string.gsub(word, "ó", "ɔ́")
word = string.gsub(word, "ō", "ɔːʊ̯")
word = string.gsub(word, "ô", "ɔ̂ːʊ̯")
word = string.gsub(word, "ǒ", "ɔ̌ːʊ̯")
word = string.gsub(word, "O", "aɔ̯")
word = string.gsub(word, "Ó", "áɔ̯")
word = string.gsub(word, "Ō", "aːɔ̯")
word = string.gsub(word, "Ô", "âːɔ̯")
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, "w", "ɐ")
word = string.gsub(word, "y", "j")
word = string.gsub(word, "z", "θ̱")
return "/" .. word .. "/"
end
return export