Module:rad-stem: Difference between revisions
Jump to navigation
Jump to search
TheNightAvl (talk | contribs) mNo edit summary |
TheNightAvl (talk | contribs) No edit summary |
||
(119 intermediate revisions by the same user not shown) | |||
Line 1: | Line 1: | ||
local export = {} | local export = {} | ||
local getArgs = require( | local getArgs = require("Module:Arguments").getArgs | ||
local m_table = require("Module:table") | |||
local | |||
local V = "aáàâảeéèiíìỉoóòøuúùûūủyýỳỷ" | local V = "aáàâảeéèiíìỉoóòøuúùûūủyýỳỷ" | ||
Line 18: | Line 14: | ||
stem_data = { | stem_data = { | ||
-- heavy stems -- | |||
["b"] = "C", | |||
["c"] = "C", | |||
["d"] = "C", | |||
["ð"] = "C", | |||
["dz"] = "C", | |||
["f"] = "C", | |||
["g"] = "C", | |||
["h"] = "C", | |||
["ħ"] = "C", | |||
["j"] = "C", | |||
["k"] = "C", | |||
["ķ"] = "C", | |||
["l"] = "C", | |||
["m"] = "C", | |||
["n"] = "C", | |||
["ņ"] = "C", | |||
["p"] = "C", | |||
["r"] = "C", | |||
["s"] = "C", | |||
["ș"] = "C", | |||
["t"] = "C", | |||
["v"] = "C", | |||
["x"] = "C", | |||
["z"] = "C", | |||
["þ"] = "C", | |||
-- heavy spirants -- | |||
["bH"] = "CH", | |||
["cH"] = "CH", | |||
["dH"] = "CH", | |||
["ðH"] = "CH", | |||
["dzH"] = "CH", | |||
["fH"] = "CH", | |||
["gH"] = "CH", | |||
["jH"] = "CH", | |||
["kH"] = "CH", | |||
["lḤ"] = "CH", | |||
["mḤ"] = "CH", | |||
["nḤ"] = "CH", | |||
["ņḤ"] = "CH", | |||
["pH"] = "CH", | |||
["rḤ"] = "CH", | |||
["sH"] = "CH", | |||
["șH"] = "CH", | |||
["tH"] = "CH", | |||
["vH"] = "CH", | |||
["xH"] = "CH", | |||
["zH"] = "CH", | |||
["þH"] = "CH", | |||
-- semi-light -- | |||
["a^eG"] = "G", | |||
["a^oG"] = "G", | |||
["eG"] = "G", | |||
["G"] = "G", | |||
["ieG"] = "G", | |||
["iG"] = "G", | |||
["oG"] = "G", | |||
["øG"] = "G", | |||
["uG"] = "G", | |||
["yG"] = "G", | |||
["yeG"] = "G", | |||
-- light -- | |||
["a"] = "V", | |||
["a^e"] = "V", | |||
["a^o"] = "V", | |||
["ai"] = "V", | |||
["au"] = "V", | |||
["e"] = "V", | |||
["i"] = "V", | |||
["ie"] = "V", | |||
["iè"] = "V", | |||
["nj^e"] = "V", | |||
["o"] = "V", | |||
["o*"] = "V", | |||
["ø"] = "V", | |||
["t^o"] = "V", | |||
["ķ^o"] = "V", | |||
["u"] = "V", | |||
["ù"] = "V", | |||
["y"] = "V", | |||
-- light spirant -- | |||
["H"] = "VH", | |||
["HH"] = "VH", | |||
["Ḥ"] = "VH", | |||
["ḤḤ"] = "VH" | |||
} | } | ||
light_noun_data = { | light_noun_data = { | ||
-- NOM, V, ^V, dat, acc, ins, pl, voc | |||
["a"] = {"a", "a", "a", "an", "ast"}, | |||
["a^e"] = {"Ra", "a", "e", "an", "ast"}, | |||
["a^o"] = {"Ra", "a", "u", "an", "ast"}, | |||
["ai"] = {"ai", "ai"}, | |||
["áj"] = {"áj", "áj"}, | |||
["au"] = {"au", "au"}, | |||
["e"] = {"Ra", "e", "=i"}, | |||
["i"] = {"Re", "=i"}, | |||
["ie"] = {"íRa", "ie"}, | |||
["iè"] = {"ia", "iè"}, | |||
["o"] = {"Ra", "o", "u", "un", "ust"}, | |||
["o*"] = {"o*", "o", "o*", "on*", "ost*"}, | |||
["ø"] = {"Ra", "ø", "y"}, | |||
["u"] = {"Re", "u"}, | |||
["ù"] = {"ù", "ù"}, | |||
["y"] = {"Re", "y"}, | |||
["a^eG"] = {"ár", "í", "á", "ád", "aúr", "ai", "áse"}, | |||
["a^oG"] = {"ár", "ív", "á", "ád", "aúr", "ai", "áse"}, | |||
["eG"] = {"ír", "í", "ea", "íd", "eúr", "í", "íse"}, | |||
["iG"] = {"ír", "í", "ea", "íd", "iúr", "í", "íse"}, | |||
["ieG"] = {"ỉr", "ỉ", "iea", "ỉd", "ieúr", "ỉ", "ỉse"}, | |||
["oG"] = {"úr", "ív", "oa", "úd", "oúr", "í", "úse"}, | |||
["øG"] = {"ýr", "ýj", "øa", "ýd", "øúr", "ý", "ýse"}, | |||
["uG"] = {"úr", "ív", "oa", "úd", "ủr", "í", "úse"}, | |||
["yG"] = {"ýr", "ýj", "øa", "ýd", "yúr", "ý", "ýse"}, | |||
["yeG"] = {"ỷr", "ỷ", "yea", "ỷd", "yeúr", "ỷ", "ỷse"}, | |||
["G"] = {"jr", "j", "a", "x", "úr", "j", "șe"} | |||
} | } | ||
pos_data = { "noun", "verb" } | pos_data = {"noun", "verb"} | ||
function | -- this function resolves all consonant clashes | ||
function resolve_ending(resolution) | |||
local function resolve(to_Match, to_Replace) | |||
if mw.ustring.find(resolution, to_Match) then | |||
resolution = mw.ustring.gsub(resolution, to_Match, to_Replace) | |||
-- mw.log( "/" .. to_Match .. "/ → " .. to_Replace .. " : " .. resolution ) | |||
end | |||
end | end | ||
-- resolve heavy spirant stems -- | |||
resolve("", "") | |||
resolve("([^Ḥ])Ḥ%=e", "%1ge") | |||
resolve("(ỉ[HḤ][HḤ]?%=e)$", "ỉè") | |||
resolve("(ie[HḤ][HḤ]?%=e)$", "íe") | |||
resolve("(ye[HḤ][HḤ]?%=e)$", "ýe") | |||
resolve("(a[HḤ][HḤ]?%=e)$", "ai") | |||
resolve("(e[HḤ][HḤ]?%=e)$", "ei") | |||
resolve("(ø[HḤ][HḤ]?%=e)$", "øi") | |||
resolve("(i[HḤ][HḤ]?%=e)$", "iè") | |||
resolve("(y[HḤ][HḤ]?%=e)$", "yè") | |||
resolve("(â[HḤ][HḤ]%=e)$", "âi") | |||
resolve("(ỉH%=i%=s)", "ỉes") | |||
resolve("(ieH%=i%=s)", "ies") | |||
resolve("(ieH%=i)", "eí") | |||
resolve("([ei][HḤ]%=i)", "=í") | |||
resolve("([íỉ][HḤ]%=i)", "ỉ") | |||
resolve("([øy][HḤ]%=i)", "=ý") | |||
resolve("(ý[HḤ]%=i)", "ỷ") | |||
resolve("([ouû]H%=[ei])", "ui") | |||
resolve("([ouû]H%=se)", "ûse") | |||
resolve("(aH%=[ei])", "ai") | |||
resolve("([" .. V .. "])H%=[ei]", "%1j=e") | |||
resolve("ieH%=([aú])", "eív=%1") | |||
resolve("([" .. V .. "])H%=([aú])", "%1v=%2") | |||
-- resolve semi-light and light spirant stems | |||
resolve("(%=ý%=s)$", "yes") | |||
resolve("(%=ú%=s)$", "uos") | |||
resolve("(%=ỉ%=s)$", "ỉes") | |||
resolve("([" .. C .. "][" .. C .. "])%=í%=s$", "%1ies") | |||
resolve("([jșķx])%=í%=s$", "%1ies") | |||
resolve("(%=í%=s)$", "jes") | |||
-- resolve light stems | |||
resolve("%=tr", "t=s") | |||
resolve("%=njr", "nj=s") | |||
resolve("aij%=R([ae])$", "aí%1") | |||
resolve("([^a])uv%=R([ae])$", "%1ú=%2") | |||
resolve("([^au])ov%=R([ae])$", "%1ú=%2") | |||
resolve("^[ou]v%=R([ae])$", "ú=%1") | |||
resolve("[ùò]v%=R([ae])$", "ú%1") | |||
resolve("uav%=Ra$", "uò=Ra") | |||
resolve("([^eoø])av%=Ra$", "%1o=Ra") | |||
resolve("uav%=(R?e)$", "uò=%1") | |||
resolve("([^eoø])av%=(R?e)$", "%1o=%2") | |||
resolve("([oò])%=Ra$", "%1à") | |||
-- resolve spirants | |||
resolve("ḤḤ%=g", "=k") | |||
resolve("ḤḤ%=d", "=t") | |||
resolve("ḤḤ%=s", "=s") | |||
resolve("ḤḤ%=a", "=à") | |||
resolve("ḤḤ%=úr", "úr") | |||
resolve("ḤḤ%=e", "=e") | |||
resolve("ḤḤ%=i", "=șe") | |||
resolve("HH%=g", "=ak") | |||
resolve("HH%=d", "=at") | |||
resolve("HH%=s", "=as") | |||
resolve("HH%=a", "=à") | |||
resolve("HH%=úr", "úr") | |||
resolve("HH%=e", "=e") | |||
resolve("HH%=i", "=așe") | |||
resolve("y%=à$", "ya") | |||
resolve("y%=a$", "øa") | |||
resolve("i%=à$", "ia") | |||
resolve("i%=a$", "ea") | |||
resolve("u%=à$", "ua") | |||
resolve("u%=a$", "oa") | |||
resolve("[aà]%=[aà]", "á") | |||
resolve("[áả]%=[aà]", "ả") | |||
resolve("â%=([aàáả])", "o%1") | |||
resolve("kH%=g", "k") | |||
resolve("kH%=d", "kt") | |||
resolve("[ḤH]%=g", "g") | |||
resolve("[ḤH]%=([ds])", "=%1") | |||
resolve("Ḥ%=i", "j=i") | |||
resolve("H%=i", "ș=i") | |||
resolve("Ḥ%=([" .. V .. "])", "g%1") | |||
-- resolve =g/=d | |||
resolve("([rvħh])%=g", "%1=u") | |||
resolve("(j%=g)", "j") | |||
resolve("(j%=d)", "x") | |||
resolve("([pf]%=g)", "f") | |||
resolve("([pf]%=d)", "f=t") | |||
resolve("(g%=g)", "g") | |||
resolve("(k%=g)", "k") | |||
resolve("(k%=d)", "t") | |||
resolve("(m%=g)", "n=g") | |||
resolve("b%=([gd])", "v=%1") | |||
resolve("(j[ctþ]%=g)", "ș=k") | |||
resolve("(j[ctþ]%=d)", "ș=t") | |||
resolve("j[dð]%=([gd])", "x=%1") | |||
resolve("jdz%=([gd])", "x=%1") | |||
resolve("([sș]?[șķ]%=g)", "ș=k") | |||
resolve("([sș]?[șķ]%=d)", "ș=t") | |||
resolve("[zx]?d?x%=([gd])", "x=%1") | |||
resolve("(s?[cstþ]%=g)", "s=k") | |||
resolve("(s?[cstþ]%=d)", "s=t") | |||
resolve("z?[zdð]%=([gd])", "z=%1") | |||
resolve("z?dz%=([gd])", "z=%1") | |||
resolve("([" .. C .. "])[mnņ]%=([gd])", "%1=%2") | |||
-- resolve =s | |||
resolve("([^a])u([sș])%=se", "%1û%2e") | |||
resolve("([sș])%=s", "%1") | |||
resolve("j%=s", "ș") | |||
-- resolve VvC | |||
resolve("([^eoø])av%=([^" .. V .. "])", "%1au=%2") | |||
resolve("^av%=([^" .. V .. "])", "au=%1") | |||
resolve("(àv%=)", "au=") | |||
resolve("([^a])uv%=([^" .. V .. "])", "%1ú=%2") | |||
resolve("([^au])ov%=([^" .. V .. "])", "%1ú=%2") | |||
resolve("^[ou]v%=([^" .. V .. "])", "ú=%1") | |||
resolve("([òù]v%=)", "ú=") | |||
resolve("([^iy])ev%=([^" .. V .. "])", "%1ø=%2") | |||
resolve("^ev%=([^" .. V .. "])", "ø=%1") | |||
resolve("(èv%=)", "ø=") | |||
resolve("([^aeuøuâ])iv%=([^" .. V .. "])", "%1y=%2") | |||
resolve("^iv%=([^" .. V .. "])", "y=%1") | |||
resolve("(ìv%=)", "y=") | |||
-- resolve CvC | |||
-- resolve("mv%=([" .. C .. "])","nu=%1") | |||
resolve("([" .. C .. "])v%=([" .. C .. "])", "%1u=%2") | |||
resolve("vv%=([aiuú])", "v=%1") | |||
resolve("([" .. C .. "])v%=R?e$", "%1u=i") | |||
resolve("([" .. C .. "])v%=Ra$", "%1u=a") | |||
-- resolve -ûve → -úe | |||
resolve("ûv%=R?e", "ú=e") | |||
resolve("ûv%=R?e", "ú=e") | |||
-- resolve aja, ava | |||
resolve("([^eoø])a[vj]%=a", "%1á") | |||
resolve("(à[vj]%=a)", "á") | |||
-- resolve f/þ~v/ð | |||
resolve("([" .. V .. O .. L .. J .. "])f%=([" .. V .. J .. "])", "%1v=%2") | |||
resolve("([" .. V .. O .. L .. J .. "])þ%=([" .. V .. J .. "])", "%1ð=%2") | |||
-- resolve k/g + front vowel | |||
resolve("k%=([ie])", "c=%1") | |||
resolve("g%=([ie])", "dz=%1") | |||
-- resolve palatal + i | |||
resolve("([jșxķ])%=i", "%1=e") | |||
-- resolve misc. | |||
resolve("(v%=g)", "v") | |||
resolve("[HḤ][HḤ]%=", "=") | |||
resolve("[HḤ]%=", "=") | |||
resolve("au°?%=R?a", "o=à") | |||
resolve("au°?%=R?([" .. V .. "])", "o=%1") | |||
resolve("%=(%S*)R", "=%1") | |||
resolve("(%=)", "") | |||
resolve("(°)", "") | |||
return resolution | |||
end | end | ||
-- | function export.getNounStem(args) -- rad-inflection|pos|principle_part| 3 | 4 | 5, outputs table of principle parts | ||
local principle_parts = { | |||
["nom"] = "", | |||
["voc"] = "", | |||
["gen"] = "", | |||
["dat"] = "", | |||
["acc"] = "", | |||
["ins"] = "", | |||
["nompl"] = "", | |||
["genpl"] = "", | |||
["genpl_short"] = "", | |||
["anim"] = "" | |||
} | |||
local stem = "" | |||
local stem_broken = "" | |||
local stem_broken_e = "" | |||
local stem_raised = "" | |||
local ending = "" | |||
-- create stem and ending parameters -- | |||
--mw.log("Parameters:") | |||
if stem_data[args[4]] or stem_data[args[5]] or stem_data[args[6]] then | |||
local v_index = 4 -- max nucleus position | |||
while true do | |||
if mw.ustring.find(args[v_index], "([%^%~])") and args[v_index + 1] ~= nil then | |||
if mw.ustring.find(args[v_index], "([%^])") then | |||
stem = mw.ustring.match(args[v_index], "([^%^]+)%^") or "" | |||
stem_raised = mw.ustring.match(args[v_index], "%^([^%^]+)") | |||
else | |||
stem = args[v_index] | |||
stem_raised = args[v_index] | |||
end | |||
if mw.ustring.find(stem, "([%~])") then | |||
stem_broken = mw.ustring.match(stem, "%~([^%~%^]+)") | |||
stem = mw.ustring.match(stem, "([^%~]+)%~") | |||
if stem_raised == args[v_index] then | |||
stem_raised = stem | |||
end | |||
else | |||
stem_broken = stem | |||
end | |||
break | |||
else | |||
if mw.ustring.find(V, mw.ustring.sub(args[v_index], -1)) and args[v_index + 1] ~= nil then | |||
stem = args[v_index] | |||
stem_raised = stem | |||
stem_broken = stem | |||
break | |||
elseif v_index == 3 then | |||
stem = args[3] | |||
stem_raised = stem | |||
stem_broken = stem | |||
break | |||
else | |||
v_index = 3 | |||
end | |||
end | |||
end | |||
if stem_broken == "u" then | |||
stem_broken_e = "û" | |||
else | |||
stem_broken_e = stem_broken | |||
end | |||
if v_index > 3 then | |||
stem = args[v_index - 1] .. stem | |||
stem_broken = args[v_index - 1] .. stem_broken | |||
stem_broken_e = args[v_index - 1] .. stem_broken_e | |||
stem_raised = args[v_index - 1] .. stem_raised | |||
end | |||
if args[v_index + 2] ~= nil then | |||
ending = args[v_index + 2] | |||
stem = stem .. args[v_index + 1] | |||
stem_broken = stem_broken .. args[v_index + 1] | |||
stem_broken_e = stem_broken_e .. args[v_index + 1] | |||
stem_raised = stem_raised .. args[v_index + 1] | |||
elseif args[v_index + 1] ~= nil then | |||
ending = args[v_index + 1] | |||
elseif stem_data[args[v_index]] then | |||
ending = args[v_index] | |||
stem = "" | |||
stem_broken = "" | |||
stem_broken_e = "" | |||
stem_raised = "" | |||
else | |||
error("No valid ending detected") | |||
end | |||
elseif stem_data[args[3]] then | |||
ending = args[3] | |||
stem = "" | |||
stem_broken = "" | |||
stem_broken_e = "" | |||
stem_raised = "" | |||
else | |||
error("Invalid format: Please format the arguments as hv|o~u^u|þ, dv|a^u|n|þ, he|rḤ or lorál|eH") | |||
end | |||
if stem_data[ending] == "C" or stem_data[ending] == "CH" or stem_data[ending] == "VH" then | |||
stem = stem .. ending | |||
stem_broken = stem_broken .. ending | |||
stem_broken_e = stem_broken_e .. ending | |||
stem_raised = stem_raised .. ending | |||
end | |||
-- | |||
--[[ | |||
mw.log("Stem: " .. stem) | mw.log("Stem: " .. stem) | ||
if stem_broken then mw.log("Broken stem: " .. stem_broken ) end | if stem_broken then mw.log("Broken stem: " .. stem_broken ) end | ||
Line 352: | Line 441: | ||
if stem_raised then mw.log("Raised stem: " .. stem_raised ) end | if stem_raised then mw.log("Raised stem: " .. stem_raised ) end | ||
mw.log("Ending: " .. ending) | mw.log("Ending: " .. ending) | ||
]] -- generate endings from declension type -- | |||
-- HEAVY AND HEAVY SPIRANT -- | |||
if stem_data[ending] == "C" or stem_data[ending] == "CH" or stem_data[ending] == "VH" then | |||
-- LIGHT -- | |||
if | |||
ending == "j" and | |||
not (mw.ustring.sub(stem, -2) == "oj" and mw.ustring.sub(stem, -3) ~= "aoj" and | |||
mw.ustring.sub(stem, -3) ~= "uoj") | |||
then | |||
principle_parts["nom"] = stem .. "=s" | |||
principle_parts["acc"] = stem .. "=d" | |||
principle_parts["voc"] = stem .. "=se" | |||
else | |||
principle_parts["nom"] = stem_broken .. "=s" | |||
principle_parts["acc"] = stem_broken .. "=d" | |||
principle_parts["voc"] = stem_broken .. "=se" | |||
end | |||
if (ending == "v" or ending == "r") and stem_raised == stem then | |||
principle_parts["gen"] = stem .. "=g" | |||
elseif stem_raised ~= stem then | |||
principle_parts["gen"] = stem_raised .. "=g" | |||
else | |||
principle_parts["gen"] = stem_broken .. "=g" | |||
end | |||
principle_parts["dat"] = stem .. "=a" | |||
principle_parts["ins"] = stem .. "=úr" | |||
principle_parts["nompl"] = stem_broken_e .. "=e" | |||
principle_parts["genpl"] = stem .. "=i" | |||
principle_parts["genpl_short"] = principle_parts["genpl"] .. "=s" | |||
principle_parts["anim"] = stem --for adjs only | |||
elseif ending == "nj^e" then | |||
principle_parts["nom"] = stem_broken .. "nș" | |||
principle_parts["voc"] = stem_broken .. "nșe" | |||
principle_parts["gen"] = stem_broken_e .. "njesk" | |||
principle_parts["dat"] = stem_broken_e .. "=" .. "nja" | |||
principle_parts["acc"] = stem_broken .. "nșt" | |||
principle_parts["ins"] = stem .. "nivúr" | |||
principle_parts["nompl"] = stem_broken .. "nxe" | |||
principle_parts["genpl"] = stem_broken_e .. "nje" | |||
principle_parts["genpl_short"] = stem_broken_e .. "nje=s" | |||
elseif mw.ustring.match(ending, "^[tķ]%^o$") then | |||
local temp_stem = mw.ustring.match(ending, "^([tķ])%^o$") | |||
principle_parts["nom"] = stem_broken .. temp_stem .. "s" | |||
principle_parts["voc"] = stem_broken .. temp_stem .. "se" | |||
principle_parts["gen"] = stem .. temp_stem .. "usk" | |||
principle_parts["dat"] = stem .. temp_stem .. "a" | |||
principle_parts["acc"] = stem_broken .. temp_stem .. "st" | |||
principle_parts["ins"] = stem_broken .. temp_stem .. "vúr" | |||
principle_parts["nompl"] = stem_broken .. temp_stem .. "se" | |||
principle_parts["genpl"] = stem_broken .. temp_stem .. "s" | |||
principle_parts["genpl_short"] = stem .. temp_stem .. "u=s" | |||
elseif stem_data[ending] == "V" then | |||
-- SEMI-LIGHT | |||
principle_parts["nom"] = stem_broken_e .. "=" .. light_noun_data[ending][1] | |||
principle_parts["voc"] = stem .. light_noun_data[ending][2] .. "se" | |||
principle_parts["gen"] = stem .. (light_noun_data[ending][3] or light_noun_data[ending][2]) .. "sk" | |||
principle_parts["dat"] = stem .. (light_noun_data[ending][4] or (light_noun_data[ending][2] .. "n")) | |||
principle_parts["acc"] = stem .. (light_noun_data[ending][5] or (light_noun_data[ending][2] .. "st")) | |||
principle_parts["ins"] = stem .. (light_noun_data[ending][6] or (light_noun_data[ending][2] .. "vúr")) | |||
principle_parts["nompl"] = stem .. light_noun_data[ending][2] .. "re" | |||
principle_parts["genpl"] = stem .. light_noun_data[ending][2] | |||
principle_parts["genpl_short"] = stem .. (light_noun_data[ending][3] or light_noun_data[ending][2]) .. "=s" | |||
elseif stem_data[ending] == "G" then | |||
principle_parts["nom"] = stem_broken .. light_noun_data[ending][1] | |||
principle_parts["voc"] = stem .. light_noun_data[ending][7] | |||
principle_parts["gen"] = stem_broken .. light_noun_data[ending][2] | |||
principle_parts["dat"] = stem .. light_noun_data[ending][3] | |||
principle_parts["acc"] = stem .. light_noun_data[ending][4] | |||
principle_parts["ins"] = stem .. light_noun_data[ending][5] | |||
principle_parts["nompl"] = stem_broken .. light_noun_data[ending][6] .. "re" | |||
principle_parts["genpl"] = stem_broken .. light_noun_data[ending][6] | |||
principle_parts["genpl_short"] = stem_broken .. "=" .. light_noun_data[ending][6] .. "=s" | |||
end | |||
--mw.log("——— Resolving ———") | |||
for part, infl in pairs(principle_parts) do | |||
principle_parts[part] = resolve_ending(infl) | |||
end | |||
principle_parts["type"] = stem_data[ending] | |||
--mw.logObject(principle_parts) | |||
return principle_parts | |||
end | end | ||
--[[ | function export.getVerbStem(args) -- outputs table of principle parts | ||
if args["pre"] then | |||
for arg, value in pairs(args) do | |||
if arg ~= "pre" and arg ~= "t" and arg ~= "vstem" and not mw.ustring.match(arg, "note$") then | |||
args[arg] = args["pre"] .. value | |||
end | |||
end | |||
end | |||
local principle_parts = { | |||
["inf"] = args[1], | |||
["2s"] = args[2], | |||
["pst"] = args[3], | |||
["prespart"] = args[4], | |||
["pspart"] = args[5], | |||
["passinf"] = args[6], | |||
["passprespart"] = args[7] or args[6] | |||
} | |||
if args["vstem"] then | |||
if args.vstem == "true" then | |||
principle_parts["vstem"] = true | |||
elseif args.vstem == "false" then | |||
principle_parts["vstem"] = false | |||
end | |||
elseif | |||
mw.ustring.match(principle_parts["2s"], "[^n]v$") and not mw.ustring.match(principle_parts["inf"], "ft$") and | |||
not mw.ustring.match(principle_parts["inf"], "aut$") | |||
then | |||
principle_parts["vstem"] = true | |||
else | |||
principle_parts["vstem"] = false | |||
end | |||
-- non-finite parameters | |||
if principle_parts.vstem then | |||
principle_parts["vnoun"] = args["vnoun"] or mw.ustring.gsub(principle_parts["2s"], "v$", "nș") | |||
else | |||
principle_parts["vnoun"] = args["vnoun"] or (mw.ustring.gsub(principle_parts["pspart"] .. "aș", "âaș$", "oàș")) | |||
end | |||
if mw.ustring.match(principle_parts["pspart"], "ru$") then | |||
principle_parts["pspart"] = mw.ustring.gsub(principle_parts["pspart"], "ru$", "rủ") | |||
else | |||
principle_parts["pspart"] = mw.ustring.gsub(principle_parts["pspart"] .. "ú", "[uú]ú$", "ủ") | |||
end | |||
-- nonpast parameters | |||
if args["1s"] then | |||
principle_parts["1s"] = args["1s"] | |||
else | |||
if principle_parts["vstem"] then | |||
principle_parts["1s"] = mw.ustring.gsub(principle_parts["2s"], "v$", "") .. "e" | |||
else | |||
principle_parts["1s"] = principle_parts["2s"] .. "e" | |||
end | |||
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "([âø])e$", "%1i") | |||
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "([^eoø])ae$", "%1ai") | |||
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "([^i])ee$", "%1ei") | |||
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "([^aeuøâ])ie$", "%1iè") | |||
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "ye$", "yè") | |||
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "([^au])oe$", "%1ui") | |||
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "([^a])ue$", "%1ui") | |||
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "uave$", "uòe") | |||
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "([^eøo])ave$", "%1oe") | |||
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "iee$", "íe") | |||
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "yee$", "ýe") | |||
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "uoe$", "úe") | |||
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "aoe$", "aoi") | |||
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "nve$", "nui") | |||
end | |||
if args["3s"] then | |||
principle_parts["3s"] = args["3s"] | |||
else | |||
principle_parts["3s"] = principle_parts["2s"] .. "ș" | |||
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "([^eoø])aș$", "%1áș") | |||
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "áș$", "ảș") | |||
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "([^aeuøâ])iș$", "%1eaș") | |||
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "([^i])eș$", "%1eaș") | |||
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "([^a])uș$", "%1oaș") | |||
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "([^au])oș$", "%1oaș") | |||
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "aoș$", "aôș") | |||
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "[øy]ș$", "øaș") | |||
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "âș$", "oaș") | |||
if principle_parts["vstem"] then | |||
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "vș$", "ș") | |||
end | |||
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "[sș]ș$", "ș") | |||
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "nvș$", "mș") | |||
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "([^eoø])avș$", "%1auș") | |||
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "([nņlr])gș$", "%1ș") | |||
end | |||
principle_parts["pl"] = args["pl"] | |||
principle_parts["a"] = args["a"] or mw.ustring.gsub(principle_parts["2s"] .. "a", "([eoø])a$", "%1à") | |||
principle_parts["a"] = mw.ustring.gsub(principle_parts["a"], "aa$", "á") | |||
principle_parts["a"] = mw.ustring.gsub(principle_parts["a"], "áa$", "ả") | |||
principle_parts["a"] = mw.ustring.gsub(principle_parts["a"], "âa$", "oà") | |||
if principle_parts["vstem"] then | |||
principle_parts["a"] = mw.ustring.gsub(principle_parts["a"], "ava$", "á") | |||
end | |||
--principle_parts["aa"] = args["aa"] --or mw.ustring.gsub(principle_parts["2s"] .. "á", "([^eoø])avá$", "%1áva") | |||
--principle_parts["ai"] = args["ai"] --or mw.ustring.gsub(principle_parts["2s"] .. "ai", "([^eoø])avai$", "%1áe") | |||
if principle_parts["vstem"] then | |||
principle_parts["depers"] = args["depers"] or mw.ustring.gsub(principle_parts["2s"], "v$", "") | |||
else | |||
principle_parts["depers"] = args["depers"] | |||
if principle_parts["depers"] then | |||
principle_parts["depers"] = mw.ustring.gsub(principle_parts["depers"], "([^eoø])av$", "%1au") | |||
end | |||
end | |||
--principle_parts["o"] = mw.ustring.gsub(principle_parts["2s"] .. "o", "([au])o$", "%1ò") | |||
local imp_temp = args["depers"] | |||
if imp_temp then | |||
if mw.ustring.match(imp_temp, "au$") then | |||
imp_temp = nil | |||
elseif mw.ustring.find(imp_temp, "[uú]$") then | |||
imp_temp = imp_temp .. "a" | |||
else | |||
imp_temp = principle_parts["2s"] .. "a" | |||
end | |||
end | |||
if principle_parts["vstem"] then | |||
principle_parts["imp"] = args["imp"] or mw.ustring.gsub(principle_parts["2s"], "v$", "ja") | |||
else | |||
principle_parts["imp"] = args["imp"] or imp_temp or nil | |||
end | |||
if args["r"] then | |||
principle_parts["r"] = args["r"] | |||
else | |||
principle_parts["r"] = (principle_parts["depers"] or principle_parts["2s"]) .. "r" | |||
if principle_parts["vstem"] then | |||
principle_parts["r"] = mw.ustring.gsub(principle_parts["r"], "vr$", "r") | |||
end | |||
principle_parts["r"] = mw.ustring.gsub(principle_parts["r"], "([sș])r$", "%1tr") | |||
principle_parts["r"] = mw.ustring.gsub(principle_parts["r"], "([zx])r$", "%1dr") | |||
principle_parts["r"] = mw.ustring.gsub(principle_parts["r"], "rr$", "r") | |||
principle_parts["r"] = mw.ustring.gsub(principle_parts["r"], "nr$", "rr") | |||
principle_parts["r"] = mw.ustring.gsub(principle_parts["r"], "mr$", "mbr") | |||
principle_parts["r"] = mw.ustring.gsub(principle_parts["r"], "ņr$", "ņgr") | |||
principle_parts["r"] = mw.ustring.gsub(principle_parts["r"], "nvr$", "nur") | |||
end | |||
-- past parameters | |||
principle_parts["apst"] = args["apst"] or mw.ustring.gsub(principle_parts["pst"] .. "a", "([eoø])a$", "%1à") | |||
principle_parts["apst"] = mw.ustring.gsub(principle_parts["apst"], "aa$", "á") | |||
principle_parts["apst"] = mw.ustring.gsub(principle_parts["apst"], "áa$", "ả") | |||
principle_parts["apst"] = mw.ustring.gsub(principle_parts["apst"], "âa$", "oà") | |||
-- principle_parts["aipst"] = args["aipst"] | |||
principle_parts["epst"] = args["epst"] | |||
if args["rpst"] then | |||
principle_parts["rpst"] = args["rpst"] | |||
else | |||
principle_parts["rpst"] = principle_parts["pst"] .. "r" | |||
principle_parts["rpst"] = mw.ustring.gsub(principle_parts["rpst"], "([sș])r$", "%1tr") | |||
principle_parts["rpst"] = mw.ustring.gsub(principle_parts["rpst"], "([zx])r$", "%1dr") | |||
principle_parts["rpst"] = mw.ustring.gsub(principle_parts["rpst"], "rr$", "r") | |||
principle_parts["rpst"] = mw.ustring.gsub(principle_parts["rpst"], "nr$", "rr") | |||
principle_parts["rpst"] = mw.ustring.gsub(principle_parts["rpst"], "mr$", "mbr") | |||
principle_parts["rpst"] = mw.ustring.gsub(principle_parts["rpst"], "ņr$", "ņgr") | |||
end | |||
return principle_parts | |||
end | end | ||
function export.getStem(frame) | function export.getStem(frame) | ||
local args = getArgs(frame) | |||
local word = mw.title.getCurrentTitle().subpageText | |||
local to_Return = "" | |||
if args[1] ~= nil and m_table.contains(pos_data, args[1]) then | |||
local pos = args[1] | |||
else | |||
local error_text = "Parameter 1 must be:" | |||
for i, _ in pairs(data) do | |||
error_text = error_text .. " [" .. i .. "]" | |||
end | |||
error(error_text) | |||
end | |||
if args[1] == "noun" then | |||
to_Return = export.getNounStem(args)[args[2]] | |||
elseif args[1] == "verb" then | |||
to_Return = export.getVerbStem(args)[args[2]] | |||
end | |||
return to_Return | |||
end | end | ||
Latest revision as of 10:59, 7 October 2024
local export = {}
local getArgs = require("Module:Arguments").getArgs
local m_table = require("Module:table")
local V = "aáàâảeéèiíìỉoóòøuúùûūủyýỳỷ"
local C = "bcdðfghħjĵkķlmnņpqrsștvwxzþ°"
local O_voiced = "bdðgħvxz"
local O_unvoiced = "cfhkķpqsștþ"
local O = O_voiced .. O_unvoiced
local N = "mnņ"
local L = "lr"
local R = L .. N
local J = "jĵw"
stem_data = {
-- heavy stems --
["b"] = "C",
["c"] = "C",
["d"] = "C",
["ð"] = "C",
["dz"] = "C",
["f"] = "C",
["g"] = "C",
["h"] = "C",
["ħ"] = "C",
["j"] = "C",
["k"] = "C",
["ķ"] = "C",
["l"] = "C",
["m"] = "C",
["n"] = "C",
["ņ"] = "C",
["p"] = "C",
["r"] = "C",
["s"] = "C",
["ș"] = "C",
["t"] = "C",
["v"] = "C",
["x"] = "C",
["z"] = "C",
["þ"] = "C",
-- heavy spirants --
["bH"] = "CH",
["cH"] = "CH",
["dH"] = "CH",
["ðH"] = "CH",
["dzH"] = "CH",
["fH"] = "CH",
["gH"] = "CH",
["jH"] = "CH",
["kH"] = "CH",
["lḤ"] = "CH",
["mḤ"] = "CH",
["nḤ"] = "CH",
["ņḤ"] = "CH",
["pH"] = "CH",
["rḤ"] = "CH",
["sH"] = "CH",
["șH"] = "CH",
["tH"] = "CH",
["vH"] = "CH",
["xH"] = "CH",
["zH"] = "CH",
["þH"] = "CH",
-- semi-light --
["a^eG"] = "G",
["a^oG"] = "G",
["eG"] = "G",
["G"] = "G",
["ieG"] = "G",
["iG"] = "G",
["oG"] = "G",
["øG"] = "G",
["uG"] = "G",
["yG"] = "G",
["yeG"] = "G",
-- light --
["a"] = "V",
["a^e"] = "V",
["a^o"] = "V",
["ai"] = "V",
["au"] = "V",
["e"] = "V",
["i"] = "V",
["ie"] = "V",
["iè"] = "V",
["nj^e"] = "V",
["o"] = "V",
["o*"] = "V",
["ø"] = "V",
["t^o"] = "V",
["ķ^o"] = "V",
["u"] = "V",
["ù"] = "V",
["y"] = "V",
-- light spirant --
["H"] = "VH",
["HH"] = "VH",
["Ḥ"] = "VH",
["ḤḤ"] = "VH"
}
light_noun_data = {
-- NOM, V, ^V, dat, acc, ins, pl, voc
["a"] = {"a", "a", "a", "an", "ast"},
["a^e"] = {"Ra", "a", "e", "an", "ast"},
["a^o"] = {"Ra", "a", "u", "an", "ast"},
["ai"] = {"ai", "ai"},
["áj"] = {"áj", "áj"},
["au"] = {"au", "au"},
["e"] = {"Ra", "e", "=i"},
["i"] = {"Re", "=i"},
["ie"] = {"íRa", "ie"},
["iè"] = {"ia", "iè"},
["o"] = {"Ra", "o", "u", "un", "ust"},
["o*"] = {"o*", "o", "o*", "on*", "ost*"},
["ø"] = {"Ra", "ø", "y"},
["u"] = {"Re", "u"},
["ù"] = {"ù", "ù"},
["y"] = {"Re", "y"},
["a^eG"] = {"ár", "í", "á", "ád", "aúr", "ai", "áse"},
["a^oG"] = {"ár", "ív", "á", "ád", "aúr", "ai", "áse"},
["eG"] = {"ír", "í", "ea", "íd", "eúr", "í", "íse"},
["iG"] = {"ír", "í", "ea", "íd", "iúr", "í", "íse"},
["ieG"] = {"ỉr", "ỉ", "iea", "ỉd", "ieúr", "ỉ", "ỉse"},
["oG"] = {"úr", "ív", "oa", "úd", "oúr", "í", "úse"},
["øG"] = {"ýr", "ýj", "øa", "ýd", "øúr", "ý", "ýse"},
["uG"] = {"úr", "ív", "oa", "úd", "ủr", "í", "úse"},
["yG"] = {"ýr", "ýj", "øa", "ýd", "yúr", "ý", "ýse"},
["yeG"] = {"ỷr", "ỷ", "yea", "ỷd", "yeúr", "ỷ", "ỷse"},
["G"] = {"jr", "j", "a", "x", "úr", "j", "șe"}
}
pos_data = {"noun", "verb"}
-- this function resolves all consonant clashes
function resolve_ending(resolution)
local function resolve(to_Match, to_Replace)
if mw.ustring.find(resolution, to_Match) then
resolution = mw.ustring.gsub(resolution, to_Match, to_Replace)
-- mw.log( "/" .. to_Match .. "/ → " .. to_Replace .. " : " .. resolution )
end
end
-- resolve heavy spirant stems --
resolve("", "")
resolve("([^Ḥ])Ḥ%=e", "%1ge")
resolve("(ỉ[HḤ][HḤ]?%=e)$", "ỉè")
resolve("(ie[HḤ][HḤ]?%=e)$", "íe")
resolve("(ye[HḤ][HḤ]?%=e)$", "ýe")
resolve("(a[HḤ][HḤ]?%=e)$", "ai")
resolve("(e[HḤ][HḤ]?%=e)$", "ei")
resolve("(ø[HḤ][HḤ]?%=e)$", "øi")
resolve("(i[HḤ][HḤ]?%=e)$", "iè")
resolve("(y[HḤ][HḤ]?%=e)$", "yè")
resolve("(â[HḤ][HḤ]%=e)$", "âi")
resolve("(ỉH%=i%=s)", "ỉes")
resolve("(ieH%=i%=s)", "ies")
resolve("(ieH%=i)", "eí")
resolve("([ei][HḤ]%=i)", "=í")
resolve("([íỉ][HḤ]%=i)", "ỉ")
resolve("([øy][HḤ]%=i)", "=ý")
resolve("(ý[HḤ]%=i)", "ỷ")
resolve("([ouû]H%=[ei])", "ui")
resolve("([ouû]H%=se)", "ûse")
resolve("(aH%=[ei])", "ai")
resolve("([" .. V .. "])H%=[ei]", "%1j=e")
resolve("ieH%=([aú])", "eív=%1")
resolve("([" .. V .. "])H%=([aú])", "%1v=%2")
-- resolve semi-light and light spirant stems
resolve("(%=ý%=s)$", "yes")
resolve("(%=ú%=s)$", "uos")
resolve("(%=ỉ%=s)$", "ỉes")
resolve("([" .. C .. "][" .. C .. "])%=í%=s$", "%1ies")
resolve("([jșķx])%=í%=s$", "%1ies")
resolve("(%=í%=s)$", "jes")
-- resolve light stems
resolve("%=tr", "t=s")
resolve("%=njr", "nj=s")
resolve("aij%=R([ae])$", "aí%1")
resolve("([^a])uv%=R([ae])$", "%1ú=%2")
resolve("([^au])ov%=R([ae])$", "%1ú=%2")
resolve("^[ou]v%=R([ae])$", "ú=%1")
resolve("[ùò]v%=R([ae])$", "ú%1")
resolve("uav%=Ra$", "uò=Ra")
resolve("([^eoø])av%=Ra$", "%1o=Ra")
resolve("uav%=(R?e)$", "uò=%1")
resolve("([^eoø])av%=(R?e)$", "%1o=%2")
resolve("([oò])%=Ra$", "%1à")
-- resolve spirants
resolve("ḤḤ%=g", "=k")
resolve("ḤḤ%=d", "=t")
resolve("ḤḤ%=s", "=s")
resolve("ḤḤ%=a", "=à")
resolve("ḤḤ%=úr", "úr")
resolve("ḤḤ%=e", "=e")
resolve("ḤḤ%=i", "=șe")
resolve("HH%=g", "=ak")
resolve("HH%=d", "=at")
resolve("HH%=s", "=as")
resolve("HH%=a", "=à")
resolve("HH%=úr", "úr")
resolve("HH%=e", "=e")
resolve("HH%=i", "=așe")
resolve("y%=à$", "ya")
resolve("y%=a$", "øa")
resolve("i%=à$", "ia")
resolve("i%=a$", "ea")
resolve("u%=à$", "ua")
resolve("u%=a$", "oa")
resolve("[aà]%=[aà]", "á")
resolve("[áả]%=[aà]", "ả")
resolve("â%=([aàáả])", "o%1")
resolve("kH%=g", "k")
resolve("kH%=d", "kt")
resolve("[ḤH]%=g", "g")
resolve("[ḤH]%=([ds])", "=%1")
resolve("Ḥ%=i", "j=i")
resolve("H%=i", "ș=i")
resolve("Ḥ%=([" .. V .. "])", "g%1")
-- resolve =g/=d
resolve("([rvħh])%=g", "%1=u")
resolve("(j%=g)", "j")
resolve("(j%=d)", "x")
resolve("([pf]%=g)", "f")
resolve("([pf]%=d)", "f=t")
resolve("(g%=g)", "g")
resolve("(k%=g)", "k")
resolve("(k%=d)", "t")
resolve("(m%=g)", "n=g")
resolve("b%=([gd])", "v=%1")
resolve("(j[ctþ]%=g)", "ș=k")
resolve("(j[ctþ]%=d)", "ș=t")
resolve("j[dð]%=([gd])", "x=%1")
resolve("jdz%=([gd])", "x=%1")
resolve("([sș]?[șķ]%=g)", "ș=k")
resolve("([sș]?[șķ]%=d)", "ș=t")
resolve("[zx]?d?x%=([gd])", "x=%1")
resolve("(s?[cstþ]%=g)", "s=k")
resolve("(s?[cstþ]%=d)", "s=t")
resolve("z?[zdð]%=([gd])", "z=%1")
resolve("z?dz%=([gd])", "z=%1")
resolve("([" .. C .. "])[mnņ]%=([gd])", "%1=%2")
-- resolve =s
resolve("([^a])u([sș])%=se", "%1û%2e")
resolve("([sș])%=s", "%1")
resolve("j%=s", "ș")
-- resolve VvC
resolve("([^eoø])av%=([^" .. V .. "])", "%1au=%2")
resolve("^av%=([^" .. V .. "])", "au=%1")
resolve("(àv%=)", "au=")
resolve("([^a])uv%=([^" .. V .. "])", "%1ú=%2")
resolve("([^au])ov%=([^" .. V .. "])", "%1ú=%2")
resolve("^[ou]v%=([^" .. V .. "])", "ú=%1")
resolve("([òù]v%=)", "ú=")
resolve("([^iy])ev%=([^" .. V .. "])", "%1ø=%2")
resolve("^ev%=([^" .. V .. "])", "ø=%1")
resolve("(èv%=)", "ø=")
resolve("([^aeuøuâ])iv%=([^" .. V .. "])", "%1y=%2")
resolve("^iv%=([^" .. V .. "])", "y=%1")
resolve("(ìv%=)", "y=")
-- resolve CvC
-- resolve("mv%=([" .. C .. "])","nu=%1")
resolve("([" .. C .. "])v%=([" .. C .. "])", "%1u=%2")
resolve("vv%=([aiuú])", "v=%1")
resolve("([" .. C .. "])v%=R?e$", "%1u=i")
resolve("([" .. C .. "])v%=Ra$", "%1u=a")
-- resolve -ûve → -úe
resolve("ûv%=R?e", "ú=e")
resolve("ûv%=R?e", "ú=e")
-- resolve aja, ava
resolve("([^eoø])a[vj]%=a", "%1á")
resolve("(à[vj]%=a)", "á")
-- resolve f/þ~v/ð
resolve("([" .. V .. O .. L .. J .. "])f%=([" .. V .. J .. "])", "%1v=%2")
resolve("([" .. V .. O .. L .. J .. "])þ%=([" .. V .. J .. "])", "%1ð=%2")
-- resolve k/g + front vowel
resolve("k%=([ie])", "c=%1")
resolve("g%=([ie])", "dz=%1")
-- resolve palatal + i
resolve("([jșxķ])%=i", "%1=e")
-- resolve misc.
resolve("(v%=g)", "v")
resolve("[HḤ][HḤ]%=", "=")
resolve("[HḤ]%=", "=")
resolve("au°?%=R?a", "o=à")
resolve("au°?%=R?([" .. V .. "])", "o=%1")
resolve("%=(%S*)R", "=%1")
resolve("(%=)", "")
resolve("(°)", "")
return resolution
end
function export.getNounStem(args) -- rad-inflection|pos|principle_part| 3 | 4 | 5, outputs table of principle parts
local principle_parts = {
["nom"] = "",
["voc"] = "",
["gen"] = "",
["dat"] = "",
["acc"] = "",
["ins"] = "",
["nompl"] = "",
["genpl"] = "",
["genpl_short"] = "",
["anim"] = ""
}
local stem = ""
local stem_broken = ""
local stem_broken_e = ""
local stem_raised = ""
local ending = ""
-- create stem and ending parameters --
--mw.log("Parameters:")
if stem_data[args[4]] or stem_data[args[5]] or stem_data[args[6]] then
local v_index = 4 -- max nucleus position
while true do
if mw.ustring.find(args[v_index], "([%^%~])") and args[v_index + 1] ~= nil then
if mw.ustring.find(args[v_index], "([%^])") then
stem = mw.ustring.match(args[v_index], "([^%^]+)%^") or ""
stem_raised = mw.ustring.match(args[v_index], "%^([^%^]+)")
else
stem = args[v_index]
stem_raised = args[v_index]
end
if mw.ustring.find(stem, "([%~])") then
stem_broken = mw.ustring.match(stem, "%~([^%~%^]+)")
stem = mw.ustring.match(stem, "([^%~]+)%~")
if stem_raised == args[v_index] then
stem_raised = stem
end
else
stem_broken = stem
end
break
else
if mw.ustring.find(V, mw.ustring.sub(args[v_index], -1)) and args[v_index + 1] ~= nil then
stem = args[v_index]
stem_raised = stem
stem_broken = stem
break
elseif v_index == 3 then
stem = args[3]
stem_raised = stem
stem_broken = stem
break
else
v_index = 3
end
end
end
if stem_broken == "u" then
stem_broken_e = "û"
else
stem_broken_e = stem_broken
end
if v_index > 3 then
stem = args[v_index - 1] .. stem
stem_broken = args[v_index - 1] .. stem_broken
stem_broken_e = args[v_index - 1] .. stem_broken_e
stem_raised = args[v_index - 1] .. stem_raised
end
if args[v_index + 2] ~= nil then
ending = args[v_index + 2]
stem = stem .. args[v_index + 1]
stem_broken = stem_broken .. args[v_index + 1]
stem_broken_e = stem_broken_e .. args[v_index + 1]
stem_raised = stem_raised .. args[v_index + 1]
elseif args[v_index + 1] ~= nil then
ending = args[v_index + 1]
elseif stem_data[args[v_index]] then
ending = args[v_index]
stem = ""
stem_broken = ""
stem_broken_e = ""
stem_raised = ""
else
error("No valid ending detected")
end
elseif stem_data[args[3]] then
ending = args[3]
stem = ""
stem_broken = ""
stem_broken_e = ""
stem_raised = ""
else
error("Invalid format: Please format the arguments as hv|o~u^u|þ, dv|a^u|n|þ, he|rḤ or lorál|eH")
end
if stem_data[ending] == "C" or stem_data[ending] == "CH" or stem_data[ending] == "VH" then
stem = stem .. ending
stem_broken = stem_broken .. ending
stem_broken_e = stem_broken_e .. ending
stem_raised = stem_raised .. ending
end
--
--[[
mw.log("Stem: " .. stem)
if stem_broken then mw.log("Broken stem: " .. stem_broken ) end
if stem_broken_e then mw.log("Broken stem (û): " .. stem_broken_e ) end
if stem_raised then mw.log("Raised stem: " .. stem_raised ) end
mw.log("Ending: " .. ending)
]] -- generate endings from declension type --
-- HEAVY AND HEAVY SPIRANT --
if stem_data[ending] == "C" or stem_data[ending] == "CH" or stem_data[ending] == "VH" then
-- LIGHT --
if
ending == "j" and
not (mw.ustring.sub(stem, -2) == "oj" and mw.ustring.sub(stem, -3) ~= "aoj" and
mw.ustring.sub(stem, -3) ~= "uoj")
then
principle_parts["nom"] = stem .. "=s"
principle_parts["acc"] = stem .. "=d"
principle_parts["voc"] = stem .. "=se"
else
principle_parts["nom"] = stem_broken .. "=s"
principle_parts["acc"] = stem_broken .. "=d"
principle_parts["voc"] = stem_broken .. "=se"
end
if (ending == "v" or ending == "r") and stem_raised == stem then
principle_parts["gen"] = stem .. "=g"
elseif stem_raised ~= stem then
principle_parts["gen"] = stem_raised .. "=g"
else
principle_parts["gen"] = stem_broken .. "=g"
end
principle_parts["dat"] = stem .. "=a"
principle_parts["ins"] = stem .. "=úr"
principle_parts["nompl"] = stem_broken_e .. "=e"
principle_parts["genpl"] = stem .. "=i"
principle_parts["genpl_short"] = principle_parts["genpl"] .. "=s"
principle_parts["anim"] = stem --for adjs only
elseif ending == "nj^e" then
principle_parts["nom"] = stem_broken .. "nș"
principle_parts["voc"] = stem_broken .. "nșe"
principle_parts["gen"] = stem_broken_e .. "njesk"
principle_parts["dat"] = stem_broken_e .. "=" .. "nja"
principle_parts["acc"] = stem_broken .. "nșt"
principle_parts["ins"] = stem .. "nivúr"
principle_parts["nompl"] = stem_broken .. "nxe"
principle_parts["genpl"] = stem_broken_e .. "nje"
principle_parts["genpl_short"] = stem_broken_e .. "nje=s"
elseif mw.ustring.match(ending, "^[tķ]%^o$") then
local temp_stem = mw.ustring.match(ending, "^([tķ])%^o$")
principle_parts["nom"] = stem_broken .. temp_stem .. "s"
principle_parts["voc"] = stem_broken .. temp_stem .. "se"
principle_parts["gen"] = stem .. temp_stem .. "usk"
principle_parts["dat"] = stem .. temp_stem .. "a"
principle_parts["acc"] = stem_broken .. temp_stem .. "st"
principle_parts["ins"] = stem_broken .. temp_stem .. "vúr"
principle_parts["nompl"] = stem_broken .. temp_stem .. "se"
principle_parts["genpl"] = stem_broken .. temp_stem .. "s"
principle_parts["genpl_short"] = stem .. temp_stem .. "u=s"
elseif stem_data[ending] == "V" then
-- SEMI-LIGHT
principle_parts["nom"] = stem_broken_e .. "=" .. light_noun_data[ending][1]
principle_parts["voc"] = stem .. light_noun_data[ending][2] .. "se"
principle_parts["gen"] = stem .. (light_noun_data[ending][3] or light_noun_data[ending][2]) .. "sk"
principle_parts["dat"] = stem .. (light_noun_data[ending][4] or (light_noun_data[ending][2] .. "n"))
principle_parts["acc"] = stem .. (light_noun_data[ending][5] or (light_noun_data[ending][2] .. "st"))
principle_parts["ins"] = stem .. (light_noun_data[ending][6] or (light_noun_data[ending][2] .. "vúr"))
principle_parts["nompl"] = stem .. light_noun_data[ending][2] .. "re"
principle_parts["genpl"] = stem .. light_noun_data[ending][2]
principle_parts["genpl_short"] = stem .. (light_noun_data[ending][3] or light_noun_data[ending][2]) .. "=s"
elseif stem_data[ending] == "G" then
principle_parts["nom"] = stem_broken .. light_noun_data[ending][1]
principle_parts["voc"] = stem .. light_noun_data[ending][7]
principle_parts["gen"] = stem_broken .. light_noun_data[ending][2]
principle_parts["dat"] = stem .. light_noun_data[ending][3]
principle_parts["acc"] = stem .. light_noun_data[ending][4]
principle_parts["ins"] = stem .. light_noun_data[ending][5]
principle_parts["nompl"] = stem_broken .. light_noun_data[ending][6] .. "re"
principle_parts["genpl"] = stem_broken .. light_noun_data[ending][6]
principle_parts["genpl_short"] = stem_broken .. "=" .. light_noun_data[ending][6] .. "=s"
end
--mw.log("——— Resolving ———")
for part, infl in pairs(principle_parts) do
principle_parts[part] = resolve_ending(infl)
end
principle_parts["type"] = stem_data[ending]
--mw.logObject(principle_parts)
return principle_parts
end
function export.getVerbStem(args) -- outputs table of principle parts
if args["pre"] then
for arg, value in pairs(args) do
if arg ~= "pre" and arg ~= "t" and arg ~= "vstem" and not mw.ustring.match(arg, "note$") then
args[arg] = args["pre"] .. value
end
end
end
local principle_parts = {
["inf"] = args[1],
["2s"] = args[2],
["pst"] = args[3],
["prespart"] = args[4],
["pspart"] = args[5],
["passinf"] = args[6],
["passprespart"] = args[7] or args[6]
}
if args["vstem"] then
if args.vstem == "true" then
principle_parts["vstem"] = true
elseif args.vstem == "false" then
principle_parts["vstem"] = false
end
elseif
mw.ustring.match(principle_parts["2s"], "[^n]v$") and not mw.ustring.match(principle_parts["inf"], "ft$") and
not mw.ustring.match(principle_parts["inf"], "aut$")
then
principle_parts["vstem"] = true
else
principle_parts["vstem"] = false
end
-- non-finite parameters
if principle_parts.vstem then
principle_parts["vnoun"] = args["vnoun"] or mw.ustring.gsub(principle_parts["2s"], "v$", "nș")
else
principle_parts["vnoun"] = args["vnoun"] or (mw.ustring.gsub(principle_parts["pspart"] .. "aș", "âaș$", "oàș"))
end
if mw.ustring.match(principle_parts["pspart"], "ru$") then
principle_parts["pspart"] = mw.ustring.gsub(principle_parts["pspart"], "ru$", "rủ")
else
principle_parts["pspart"] = mw.ustring.gsub(principle_parts["pspart"] .. "ú", "[uú]ú$", "ủ")
end
-- nonpast parameters
if args["1s"] then
principle_parts["1s"] = args["1s"]
else
if principle_parts["vstem"] then
principle_parts["1s"] = mw.ustring.gsub(principle_parts["2s"], "v$", "") .. "e"
else
principle_parts["1s"] = principle_parts["2s"] .. "e"
end
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "([âø])e$", "%1i")
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "([^eoø])ae$", "%1ai")
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "([^i])ee$", "%1ei")
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "([^aeuøâ])ie$", "%1iè")
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "ye$", "yè")
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "([^au])oe$", "%1ui")
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "([^a])ue$", "%1ui")
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "uave$", "uòe")
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "([^eøo])ave$", "%1oe")
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "iee$", "íe")
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "yee$", "ýe")
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "uoe$", "úe")
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "aoe$", "aoi")
principle_parts["1s"] = mw.ustring.gsub(principle_parts["1s"], "nve$", "nui")
end
if args["3s"] then
principle_parts["3s"] = args["3s"]
else
principle_parts["3s"] = principle_parts["2s"] .. "ș"
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "([^eoø])aș$", "%1áș")
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "áș$", "ảș")
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "([^aeuøâ])iș$", "%1eaș")
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "([^i])eș$", "%1eaș")
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "([^a])uș$", "%1oaș")
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "([^au])oș$", "%1oaș")
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "aoș$", "aôș")
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "[øy]ș$", "øaș")
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "âș$", "oaș")
if principle_parts["vstem"] then
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "vș$", "ș")
end
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "[sș]ș$", "ș")
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "nvș$", "mș")
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "([^eoø])avș$", "%1auș")
principle_parts["3s"] = mw.ustring.gsub(principle_parts["3s"], "([nņlr])gș$", "%1ș")
end
principle_parts["pl"] = args["pl"]
principle_parts["a"] = args["a"] or mw.ustring.gsub(principle_parts["2s"] .. "a", "([eoø])a$", "%1à")
principle_parts["a"] = mw.ustring.gsub(principle_parts["a"], "aa$", "á")
principle_parts["a"] = mw.ustring.gsub(principle_parts["a"], "áa$", "ả")
principle_parts["a"] = mw.ustring.gsub(principle_parts["a"], "âa$", "oà")
if principle_parts["vstem"] then
principle_parts["a"] = mw.ustring.gsub(principle_parts["a"], "ava$", "á")
end
--principle_parts["aa"] = args["aa"] --or mw.ustring.gsub(principle_parts["2s"] .. "á", "([^eoø])avá$", "%1áva")
--principle_parts["ai"] = args["ai"] --or mw.ustring.gsub(principle_parts["2s"] .. "ai", "([^eoø])avai$", "%1áe")
if principle_parts["vstem"] then
principle_parts["depers"] = args["depers"] or mw.ustring.gsub(principle_parts["2s"], "v$", "")
else
principle_parts["depers"] = args["depers"]
if principle_parts["depers"] then
principle_parts["depers"] = mw.ustring.gsub(principle_parts["depers"], "([^eoø])av$", "%1au")
end
end
--principle_parts["o"] = mw.ustring.gsub(principle_parts["2s"] .. "o", "([au])o$", "%1ò")
local imp_temp = args["depers"]
if imp_temp then
if mw.ustring.match(imp_temp, "au$") then
imp_temp = nil
elseif mw.ustring.find(imp_temp, "[uú]$") then
imp_temp = imp_temp .. "a"
else
imp_temp = principle_parts["2s"] .. "a"
end
end
if principle_parts["vstem"] then
principle_parts["imp"] = args["imp"] or mw.ustring.gsub(principle_parts["2s"], "v$", "ja")
else
principle_parts["imp"] = args["imp"] or imp_temp or nil
end
if args["r"] then
principle_parts["r"] = args["r"]
else
principle_parts["r"] = (principle_parts["depers"] or principle_parts["2s"]) .. "r"
if principle_parts["vstem"] then
principle_parts["r"] = mw.ustring.gsub(principle_parts["r"], "vr$", "r")
end
principle_parts["r"] = mw.ustring.gsub(principle_parts["r"], "([sș])r$", "%1tr")
principle_parts["r"] = mw.ustring.gsub(principle_parts["r"], "([zx])r$", "%1dr")
principle_parts["r"] = mw.ustring.gsub(principle_parts["r"], "rr$", "r")
principle_parts["r"] = mw.ustring.gsub(principle_parts["r"], "nr$", "rr")
principle_parts["r"] = mw.ustring.gsub(principle_parts["r"], "mr$", "mbr")
principle_parts["r"] = mw.ustring.gsub(principle_parts["r"], "ņr$", "ņgr")
principle_parts["r"] = mw.ustring.gsub(principle_parts["r"], "nvr$", "nur")
end
-- past parameters
principle_parts["apst"] = args["apst"] or mw.ustring.gsub(principle_parts["pst"] .. "a", "([eoø])a$", "%1à")
principle_parts["apst"] = mw.ustring.gsub(principle_parts["apst"], "aa$", "á")
principle_parts["apst"] = mw.ustring.gsub(principle_parts["apst"], "áa$", "ả")
principle_parts["apst"] = mw.ustring.gsub(principle_parts["apst"], "âa$", "oà")
-- principle_parts["aipst"] = args["aipst"]
principle_parts["epst"] = args["epst"]
if args["rpst"] then
principle_parts["rpst"] = args["rpst"]
else
principle_parts["rpst"] = principle_parts["pst"] .. "r"
principle_parts["rpst"] = mw.ustring.gsub(principle_parts["rpst"], "([sș])r$", "%1tr")
principle_parts["rpst"] = mw.ustring.gsub(principle_parts["rpst"], "([zx])r$", "%1dr")
principle_parts["rpst"] = mw.ustring.gsub(principle_parts["rpst"], "rr$", "r")
principle_parts["rpst"] = mw.ustring.gsub(principle_parts["rpst"], "nr$", "rr")
principle_parts["rpst"] = mw.ustring.gsub(principle_parts["rpst"], "mr$", "mbr")
principle_parts["rpst"] = mw.ustring.gsub(principle_parts["rpst"], "ņr$", "ņgr")
end
return principle_parts
end
function export.getStem(frame)
local args = getArgs(frame)
local word = mw.title.getCurrentTitle().subpageText
local to_Return = ""
if args[1] ~= nil and m_table.contains(pos_data, args[1]) then
local pos = args[1]
else
local error_text = "Parameter 1 must be:"
for i, _ in pairs(data) do
error_text = error_text .. " [" .. i .. "]"
end
error(error_text)
end
if args[1] == "noun" then
to_Return = export.getNounStem(args)[args[2]]
elseif args[1] == "verb" then
to_Return = export.getVerbStem(args)[args[2]]
end
return to_Return
end
return export
--[[
Debug console test string:
=p.getStem(mw.getCurrentFrame():newChild{title="whatever",args={"noun", "nom", "dv", "a^u", "n", "þ"}})
]]--