Module:User:Surjection/urj-fin-pro-IPA
- This module lacks a documentation subpage. You may create it.
- Useful links: root page • root page’s subpages • links • transclusions • testcases • user page • user talk page • userspace
This is a private module sandbox of Surjection, for their own experimentation. Items in this module may be added and removed at Surjection's discretion; do not rely on this module's stability.
-- This is a toy not meant for serious use.
local export = {}
local langcode = "urj-fin-pro"
local LONG = "ː"
local SEMILONG = "ˑ"
local PRIMARY_STRESS = "ˈ"
local SECONDARY_STRESS = "ˌ"
local AUTO_STRESS = "ˌ"
local NONSYLLABIC = mw.ustring.char(0x032F)
local UNRELEASED = mw.ustring.char(0x031A)
local CENTRAL = mw.ustring.char(0x031E)
local GRAPHEME = ".[" .. mw.ustring.char(0x0300) .. "-" .. mw.ustring.char(0x036F) .. "]*"
local vowels = {
["a"] = "ɑ", ["e"] = "e", ["o"] = "o", ["u"] = "u",
["ä"] = "æ", ["ë"] = "ɤ", ["ö"] = "ø", ["ü"] = "y",
["i"] = "i",
}
local consonants = {
["k"] = "k", ["p"] = "p", ["t"] = "t",
["g"] = "ɣ", ["b"] = "β", ["d"] = "ð",
["s"] = "s", ["h"] = "h", ["v"] = "ʋ", ["r"] = "r", ["c"] = "ʦ",
["j"] = "j", ["l"] = "l", ["m"] = "m", ["n"] = "n",
}
local IPA_VOWELS = ""
local IPA_CONSONANTS = ""
for _, value in pairs(vowels) do IPA_VOWELS = IPA_VOWELS .. value end
for _, value in pairs(consonants) do IPA_CONSONANTS = IPA_CONSONANTS .. value end
function export.convert(text, is_phonetic)
local prefix = mw.ustring.find(text, "%-$")
local suffix = mw.ustring.find(text, "^%-")
if prefix then text = mw.ustring.gsub(text, "%-$", "") end
if suffix then text = mw.ustring.gsub(text, "^%-", "") end
text = mw.ustring.gsub(text, "([aeiouäëöy])%1", "%1" .. LONG)
text = mw.ustring.gsub(text, "([kptc])'", "%1" .. SEMILONG)
text = mw.ustring.gsub(text, "([kptcnmlrs])%1", "%1" .. LONG)
if not is_phonetic then
-- weak and semi-long consonants were probably allophones
text = mw.ustring.gsub(text, "[bdg]", {["b"] = "p", ["d"] = "t", ["g"] = "k"})
text = mw.ustring.gsub(text, SEMILONG, LONG)
end
text = mw.ustring.gsub(text, "([aeouäëu])i", "%1" .. "i" .. NONSYLLABIC)
text = mw.ustring.gsub(text, "([aeëio])u", "%1" .. "u" .. NONSYLLABIC)
text = mw.ustring.gsub(text, "([äeiö])ü", "%1" .. "ü" .. NONSYLLABIC)
text = mw.ustring.gsub(text, "n([kg])", "ŋ%1")
text = mw.ustring.gsub(text, "%-", SECONDARY_STRESS)
text = mw.ustring.gsub(text, "[aeiouäëöü]", vowels)
text = mw.ustring.gsub(text, "[bcdghjklmnprstv]", consonants)
if is_phonetic then
text = mw.ustring.gsub(text, "mβ", "mb")
text = mw.ustring.gsub(text, "nð", "nd")
text = mw.ustring.gsub(text, "ŋɣ", "ŋg")
text = mw.ustring.gsub(text, "k$", "k" .. UNRELEASED)
end
if suffix then
text = "-" .. text
else
text = PRIMARY_STRESS .. text
end
text = mw.ustring.gsub(text, " ", " " .. PRIMARY_STRESS)
if prefix then
text = text .. "-"
end
if is_phonetic then
-- automatic secondary stress
local old_text = text
text = ""
local IPA_VOWEL = "^[" .. IPA_VOWELS .. "]$"
local vowels_total = 0
local vowels_found = 0
local do_not_stress = {}
local distance = 0
for phone in mw.ustring.gmatch(old_text, GRAPHEME) do
if mw.ustring.match(phone, IPA_VOWEL) then
vowels_total = vowels_total + 1
elseif mw.ustring.match(phone, "[" .. PRIMARY_STRESS .. SECONDARY_STRESS .. "]") then
do_not_stress[vowels_total] = true
end
end
do_not_stress[vowels_total] = true
for phone in mw.ustring.gmatch(old_text, GRAPHEME) do
if mw.ustring.match(phone, IPA_VOWEL) then
vowels_found = vowels_found + 1
if not do_not_stress[vowels_found] then
if distance == 2 then
text = text .. AUTO_STRESS
distance = 0
else
distance = distance + 1
end
end
elseif mw.ustring.match(phone, "[" .. PRIMARY_STRESS .. SECONDARY_STRESS .. "]") then
distance = 0
end
text = text .. phone
end
if mw.ustring.match(text, "^" .. AUTO_STRESS, last_vowel) then
text = mw.ustring.sub(text, 1, last_vowel - 1) .. mw.ustring.sub(text, last_vowel + 1)
end
text = mw.ustring.gsub(text, "([" .. IPA_CONSONANTS .. "])" .. AUTO_STRESS, AUTO_STRESS .. "%1")
text = mw.ustring.gsub(text, "([eoɤø])", "%1" .. CENTRAL)
end
text = mw.ustring.gsub(text, "[gʦ]", { ["g"] = "ɡ", ["ʦ"] = "t͡s" } )
return text
end
local use_UPA_stress = true
local UPA_SHORT = mw.ustring.char(0x0306)
local UPA_LONG = mw.ustring.char(0x0304)
local UPA_DIPHTHONG = mw.ustring.char(0x0361)
local UPA_UNRELEASED = mw.ustring.char(0x2FE)
local UPA_vowels = {
["ë"] = "e̮",
}
local UPA_consonants = {
["g"] = "γ", ["b"] = "β", ["d"] = "δ", ["c"] = "ʦ",
}
function export.convert_UPA(text, is_phonetic)
local prefix = mw.ustring.find(text, "%-$")
local suffix = mw.ustring.find(text, "^%-")
if prefix then text = mw.ustring.gsub(text, "%-$", "") end
if suffix then text = mw.ustring.gsub(text, "^%-", "") end
text = mw.ustring.gsub(text, "([aeiouäëöy])%1", "%1" .. UPA_LONG)
text = mw.ustring.gsub(text, "([kptc])'", "%1" .. UPA_SHORT .. "%1")
if not is_phonetic then
-- weak and semi-long consonants were probably allophones
text = mw.ustring.gsub(text, "[bdg]", {["b"] = "p", ["d"] = "t", ["g"] = "k"})
text = mw.ustring.gsub(text, SEMILONG, LONG)
end
text = mw.ustring.gsub(text, "([aeouäëu])i", "%1" .. UPA_DIPHTHONG .. "i")
text = mw.ustring.gsub(text, "([aeëio])u", "%1" .. UPA_DIPHTHONG .. "u")
text = mw.ustring.gsub(text, "([äeiö])ü", "%1" .. UPA_DIPHTHONG .. "ü")
text = mw.ustring.gsub(text, "n([kg])", "ŋ%1")
text = mw.ustring.gsub(text, "%-", SECONDARY_STRESS)
text = mw.ustring.gsub(text, "[ë]", UPA_vowels)
text = mw.ustring.gsub(text, "[bcdg]", UPA_consonants)
if is_phonetic then
text = mw.ustring.gsub(text, "mβ", "mb")
text = mw.ustring.gsub(text, "nδ", "nd")
text = mw.ustring.gsub(text, "ŋγ", "ŋg")
text = mw.ustring.gsub(text, "k$", "k" .. UPA_UNRELEASED)
end
if suffix then
text = "-" .. text
else
text = PRIMARY_STRESS .. text
end
text = mw.ustring.gsub(text, " ", " " .. PRIMARY_STRESS)
if prefix then
text = text .. "-"
end
if is_phonetic then
-- automatic secondary stress
local old_text = text
text = ""
local UPA_VOWEL = "^[aeiouäöü]̮?$"
local vowels_total = 0
local vowels_found = 0
local do_not_stress = {}
local distance = 0
for phone in mw.ustring.gmatch(old_text, GRAPHEME) do
if mw.ustring.match(phone, UPA_VOWEL) then
vowels_total = vowels_total + 1
elseif mw.ustring.match(phone, "[" .. PRIMARY_STRESS .. SECONDARY_STRESS .. "]") then
do_not_stress[vowels_total] = true
end
end
do_not_stress[vowels_total] = true
for phone in mw.ustring.gmatch(old_text, GRAPHEME) do
if mw.ustring.match(phone, UPA_VOWEL) then
vowels_found = vowels_found + 1
if not do_not_stress[vowels_found] then
if distance == 2 then
text = text .. AUTO_STRESS
distance = 0
else
distance = distance + 1
end
end
elseif mw.ustring.match(phone, "[" .. PRIMARY_STRESS .. SECONDARY_STRESS .. "]") then
distance = 0
end
text = text .. phone
end
if mw.ustring.match(text, "^" .. AUTO_STRESS, last_vowel) then
text = mw.ustring.sub(text, 1, last_vowel - 1) .. mw.ustring.sub(text, last_vowel + 1)
end
text = mw.ustring.gsub(text, "([" .. IPA_CONSONANTS .. "γβδ])" .. AUTO_STRESS, AUTO_STRESS .. "%1")
end
text = mw.ustring.gsub(text, "[gʦ]", { ["g"] = "ɡ", ["ʦ"] = "t͡s" } )
if use_UPA_stress then
text = mw.ustring.gsub(text, "([ˈˌ])(.-)([aeiouäöü" .. mw.ustring.char(0x0300) .. "-" .. mw.ustring.char(0x036F) .. "]+)", "%2%3%1")
text = mw.ustring.gsub(text, "ˈ", "·")
text = mw.ustring.gsub(text, "ˌ", ":")
end
return text
end
function export.show(frame)
local title = mw.title.getCurrentTitle().text
if type(frame) == "table" then
title = frame:getParent().args[1] or mw.ustring.gsub(title, "^Proto-Finnic/", "")
end
local phonemic = export.convert(title, false)
local phonetic = export.convert(title, true)
return require "Module:IPA".format_IPA_full(
require("Module:languages").getByCode(langcode),
{
{pron = "*/" .. phonemic .. "/"},
{pron = "*[" .. phonetic .. "]"}
})
end
return export