Module:siwa-pron: Difference between revisions

no edit summary
No edit summary
No edit summary
Line 38: Line 38:
end
end


local function open_to_closed(v, a)
local function open_to_closed(v, w)
local otc = {}
local otc = {}
local switch = {["ɑ"] = "a", ["e"] = "ɛ", ["i"] = "ɪ", ["ɔ"] = "ɔ", ["u"] = "ʊ", ["y"] = "œ",
local switch = {["ɑ"] = "a", ["e"] = "ɛ", ["i"] = "ɪ", ["ɔ"] = "ɔ", ["u"] = "ʊ", ["y"] = "œ",
["ø"] = function(s1)
["ø"] = w and "ɤ" or "œ"}
if(a=="w") then s1="ɤ"
else s1="œ" end
return s1 end,}


for vc in gmatch(v, ".") do
for vc in gmatch(v, ".") do
Line 52: Line 49:
return table.concat(otc)
return table.concat(otc)
end
end
local rules = {
{ --ligatures and ł
["t[ṡɕ]"] = "ʨ", ["ṡ"] = "ɕ", ["į"] = "j", ["dj"] = "ʥ",
["ḍ"] = "ð", ["dl"] = "ł", ["kj"] = "c", ["ḥ"] = "ʔ",
["nj"] = "ɲ", ["ġ"] = "x", ["ts"] = "ʦ", ["g"] = "ɡ", -- IPA g
},
{ --long consonants
["mm"] = "mː", ["bb"] = "pː", ["vv"] = "wː", ["nn"] = "nː",
["dʥ"] = "ʥː", ["dd"] = "tː", ["ðð"] = "ðː", ["ss"] = "sː",
["ɕɕ"] = "ɕː", ["rr"] = "rː", ["ll"] = "lː", ["ɡɡ"] = "kː",
["xx"] = "xː", ["nɡ"] = "ŋː", ["hh"] = "hː", ["ʔʔ"] = "ʔː",
["nɲ"] = "ɲː", ["hl"] = "ɬː",
},
{ --[[default all consonants to unstressed. [] with stroke and ꬶ (U+AB36)
to tell apart natural and stress-borne]]
["p"] = "ƀ", ["d"] = "ꝺ", ["t"] = "đ",
["ɡ"] = "ɣ", ["k"] = "ꬶ",
},
{ --default all vowels as open (open-closed distinctions are computed later)
["a"] = "ɑ", ["ả"] = "æː",
["ę"] = "æ",
["ẻ"] = "eː",
["ỉ"] = "iː",
["o"] = "ɔ", ["ỏ"] = "ʊː",
["ủ"] = "uː",
["ỷ"] = "yː",
["ů"] = "ø", ["ẻu"] = "øː",
["õ"] = "ɔ̃", ["õu"] = "ɔ̃ː̃",
},
{
["^(ˈ)ꬶ([" .. front_vowel .. "])"] = "%1c%2", --word-initial [k] palatalizes before front-vowels
["^(ˈ[ƀđꬶc])"] = "%1ʰ", --voiceless stops word-initially become aspirated
["^(.*·ˈ[ƀđꬶc])"] = "%1⁽ʰ⁾",
["^(ˈ)ɣj([" .. front_vowel .. "])"] = "%1ʣ%2", --<gį> word-initially and before front vowels is pronounced [d͡z]
["^(ˈ)ɣj([" .. back_vowel .. "])"] = "%1ɟ%2",
["^(ˈ)ɣ([" .. front_vowel .. "])"] = "%1ɟ%2",
},
{
["ˈƀ"] = "ˈp", ["ˈđ"] = "ˈt", ["ˈꬶ"] = "ˈk", ["ˈꝺ"] = "ˈd",
["đi"] = "ʨi", ["ꝺi"] = "ʥi", ["ɣi"] = "ɉi", ["ɣj"] = "jː", ["ɣjː"] = "ɟː",
},
{
[spat1] = "%1ʔ%3", [spat2] = "%1k%3", [spat3] = "%1p%3", [spat4] = "%1t%3", [spat5] = "%1ð%3"
},
{
["ƀƀ"] = "ʔp", ["pƀ"] = "ʔp",
["đđ"] = "ʔt", ["tđ"] = "ʔt",
["ꬶꬶ"] = "ʔk", ["kꬶ"] = "ʔk",
["bm"] = "ʔp̚m", ["ꝺn"] = "ʔt̚n", ["ꬶn"] = "ʔk̚ŋ",
["mn"] = "mnː", ["mʔk"] = "mkː",
["(p[msɕ])"] = "%1ː", ["pr"] = "px",
["b([sɕ])"] = "p%1",
["nꬶ"] = "ŋk", ["([ðđʦłɕꬶ])v"] = "%1wː",
["đn"] = "tnː", ["đr"] = "tx", ["đꬶv"] = "tkwː",
["(ʦ[đlmn])"] = "%1ː", ["ʦꬶv"] = "ʦkwː",
["ʦxv"] = "ʦxw", ["đx"] = "tːx",
["(ð[mꬶ])"] = "%1ː",
["ꝺx"] = "ðx",
["(sk[l])"] = "%1ː", ["sʔk"] = "skː", ["sxv"] = "sxwː",
["([lr])ʔ([ptk])"] = "%1%2ː", ["rv"] = "rwː",
["lʦ(x?)v"] = "ɬʦ%1w", ["lʦx"] = "ɬʦx",
["(ł[mnꬶ])"] = "%1ː",
["(ꬶ[msɕl])"] = "%1ː",
["ꬶsꬶ"] = "kskː", ["ꬶsl"] = "ksł",
["ɣ([mn])"] = "ŋ%1ː", ["ɣ([vsl])"] = "kv",
},
{
["(" .. vowel .. "*)(" .. consonant .. consonant .. ")"] = function(s1, s2) return open_to_closed(s1) .. s2 end,
["(" .. vowel .. "*)(" .. consonant .. ")$"] = function(s1, s2) return open_to_closed(s1) .. s2 end,
["ɑ$"] = "a",
},
{
["į"] = "j", ["l(ʦx)v"] = "ɬ%1w",
["(" .. vowel .. ")đ$"] = "%1ʔ%1", -- -Vt becomes -VʔV (or -Vht, not considered)
},
{ --undo ligatures
["ʨ"] = "t͡ɕ", ["ʥ"] = "d͡ʑ", ["ł"] = "tɬ", ["ʣ"] = "d͡z", ["ʦ"] = "t͡s",
["ƀ"] = "p", ["ꝺ"] = "d", ["đ"] = "t", ["ꬶ"] = "ɡ", ["ɉ"] = "ɟ"
},
{
["·"] = "", --remove morpheme separator
},
}
local wrules = {
{ --ligatures and ł
["t[ṡɕ]"] = "ʨ", ["ṡ"] = "ɕ", ["į"] = "j", ["dj"] = "ʥ",
["ḍ"] = "ð", ["dl"] = "ł", ["kj"] = "c", ["ḥ"] = "ʔ",
["nj"] = "ɲ", ["ġ"] = "x", ["ts"] = "ʦ", ["g"] = "ɡ", -- IPA g
},
{ --long consonants
["mm"] = "mː", ["bb"] = "pː", ["vv"] = "wː", ["nn"] = "nː",
["dʥ"] = "ʥː", ["dd"] = "tː", ["ðð"] = "ðː", ["ss"] = "sː",
["ɕɕ"] = "ɕː", ["rr"] = "rː", ["ll"] = "lː", ["ɡɡ"] = "kː",
["xx"] = "xː", ["nɡ"] = "ŋː", ["hh"] = "hː", ["ʔʔ"] = "ʔː",
["nɲ"] = "ɲː", ["hl"] = "ɬː",
},
{ --[[default all consonants to unstressed. [] with stroke and ꬶ (U+AB36)
to tell apart natural and stress-borne]]
["p"] = "ƀ", ["d"] = "ꝺ", ["t"] = "đ",
["ɡ"] = "ɣ", ["k"] = "ꬶ",
},
{ --default all vowels as open (open-closed distinctions are computed later)
["a"] = "ɑ", ["ả"] = "æː",
["ę"] = "æ",
["ẻ"] = "eː",
["ỉ"] = "iː",
["o"] = "ɔ", ["ỏ"] = "ʊː",
["ủ"] = "uː",
["ỷ"] = "yː",
["ů"] = "ø", ["ẻu"] = "øː",
["õ"] = "ɔ̃", ["õu"] = "ɔ̃ː̃",
},
{
["^(ˈ)ꬶ([" .. front_vowel .. "])"] = "%1c%2", --word-initial [k] palatalizes before front-vowels
["^(ˈ[ƀđꬶc])"] = "%1ʰ", --voiceless stops word-initially become aspirated
["^(.*·ˈ[ƀđꬶc])"] = "%1⁽ʰ⁾",
["^(ˈ)ɣj([" .. front_vowel .. "])"] = "%1ʣ%2", --<gį> word-initially and before front vowels is pronounced [d͡z]
["^(ˈ)ɣj([" .. back_vowel .. "])"] = "%1ɟ%2",
["^(ˈ)ɣ([" .. front_vowel .. "])"] = "%1ɟ%2",
},
{
["ˈƀ"] = "ˈp", ["ˈđ"] = "ˈt", ["ˈꬶ"] = "ˈk", ["ˈꝺ"] = "ˈd",
["đi"] = "ʨi", ["ꝺi"] = "ʥi", ["ɣi"] = "ɉi", ["ɣj"] = "jː", ["ɣjː"] = "ɟː",
},
{
[spat1] = "%1ʔ%3", [spat2] = "%1k%3", [spat3] = "%1p%3", [spat4] = "%1t%3", [spat5] = "%1ð%3"
},
{
["ƀƀ"] = "ʔp", ["pƀ"] = "ʔp",
["đđ"] = "ʔt", ["tđ"] = "ʔt",
["ꬶꬶ"] = "ʔk", ["kꬶ"] = "ʔk",
["bm"] = "ʔp̚m", ["ꝺn"] = "ʔt̚n", ["ꬶn"] = "ʔk̚ŋ",
["mn"] = "mnː", ["mʔk"] = "mkː",
["(p[msɕ])"] = "%1ː", ["pr"] = "px",
["b([sɕ])"] = "p%1",
["nꬶ"] = "ŋk", ["([ðđʦłɕꬶ])v"] = "%1wː",
["đn"] = "tnː", ["đr"] = "tx", ["đꬶv"] = "tkwː",
["(ʦ[đlmn])"] = "%1ː", ["ʦꬶv"] = "ʦkwː",
["ʦxv"] = "ʦxw", ["đx"] = "tːx",
["(ð[mꬶ])"] = "%1ː",
["ꝺx"] = "ðx",
["(sk[l])"] = "%1ː", ["sʔk"] = "skː", ["sxv"] = "sxwː",
["([lr])ʔ([ptk])"] = "%1%2ː", ["rv"] = "rwː",
["lʦ(x?)v"] = "ɬʦ%1w", ["lʦx"] = "ɬʦx",
["(ł[mnꬶ])"] = "%1ː",
["(ꬶ[msɕl])"] = "%1ː",
["ꬶsꬶ"] = "kskː", ["ꬶsl"] = "ksł",
["ɣ([mn])"] = "ŋ%1ː", ["ɣ([vsl])"] = "kv",
},
{
["(" .. vowel .. "*)(" .. consonant .. consonant .. ")"] = function(s1, s2) return open_to_closed(s1,"w") .. s2 end,
["(" .. vowel .. "*)(" .. consonant .. ")$"] = function(s1, s2) return open_to_closed(s1,"w") .. s2 end,
["ɑ$"] = "a",
},
{
["į"] = "j", ["l(ʦx)v"] = "ɬ%1w",
["(" .. vowel .. ")đ$"] = "%1ʔ%1", -- -Vt becomes -VʔV (or -Vht, not considered)
},
{ --undo ligatures
["ʨ"] = "t͡ɕ", ["ʥ"] = "d͡ʑ", ["ł"] = "tɬ", ["ʣ"] = "d͡z", ["ʦ"] = "t͡s",
["ƀ"] = "p", ["ꝺ"] = "d", ["đ"] = "t", ["ꬶ"] = "ɡ", ["ɉ"] = "ɟ"
},
{
["·"] = "", --remove morpheme separator
},
}


function export.morphemes(word)
function export.morphemes(word)
Line 241: Line 70:


function export.crux(term, e, w)
function export.crux(term, e, w)
term=mw.ustring.lower(term)
term=mw.ustring.lower(term)
term=export.morphemes(term)
term=export.morphemes(term)
local rules = {
{".", {
["ḍ"] = "ð", ["ṡ"] = "ɕ",
["ḥ"] = "ʔ", ["į"] = "j",
["ġ"] = "x", ["g"] = "ɡ", -- IPA g
}},
{"t[ṡɕ]", "ʨ"}, {"dj", "ʥ"}, {"dl", "ł"}, {"kj", "c"}, {"nj", "ɲ"},  {"ts", "ʦ"},
-- long consonants
{"mm", "mː"}, {"bb", "pː"}, {"vv", "wː"}, {"nn", "nː"},
{"dʥ", "ʥː"}, {"dd", "tː"}, {"ðð", "ðː"}, {"ss", "sː"},
{"ɕɕ", "ɕː"}, {"rr", "rː"}, {"ll", "lː"}, {"ɡɡ", "kː"},
{"xx", "xː"}, {"nɡ", "ŋː"}, {"hh", "hː"}, {"ʔʔ", "ʔː"},
{"nɲ", "ɲː"}, {"hl", "ɬː"},
-- default all consonants to unstressed. [] with stroke and ꬶ (U+AB36) to tell apart natural and stress-borne
{"p", "ƀ"}, {"d", "ꝺ"}, {"t", "đ"}, {"ɡ", "ɣ"}, {"k", "ꬶ"},
-- default all vowels to open (open-closed distinctions are computed later); long vowels don't have closed counterparts
{"a", "ɑ"}, {"ę", "æ"}, {"o", "ɔ"}, {"ů", "ø"}, {"õ", "ɔ̃"},
{"ả", "æː"}, {"ẻ", "eː"}, {"ỉ", "iː"}, {"ỏ", "ʊː"}, {"ủ", "uː"}, {"ỷ", "yː"}, {"ẻu", "øː"}, {"õu", "ɔ̃ː̃"},
{"^(ˈ)ꬶ([" .. front_vowel .. "])", "%1c%2"}, -- word-initial [k] palatalizes before front-vowels
{"^(ˈ[ƀđꬶc])", "%1ʰ"}, -- voiceless stops word-initially become aspirated
{"^(.*·ˈ[ƀđꬶc])", "%1⁽ʰ⁾"}, -- although after a prefix they may or may not be
{"^(ˈ)ɣj([" .. front_vowel .. "])", "%1ʣ%2"}, -- <gį> word-initially and before front vowels is pronounced [d͡z]
{"^(ˈ)ɣj([" .. back_vowel .. "])", "%1ɟ%2"}, -- and [ɟ] before back vowels
{"^(ˈ)ɣ([" .. front_vowel .. "])", "%1ɟ%2"}, -- ɣ > ɟ / #_[+back]
-- other stem- and/or word-initial configurations
{"đi", "ʨi"}, {"ꝺi", "ʥi"}, {"ɣi", "ɉi"}, {"ɣj", "jː"}, {"ɣjː", "ɟː"},
{"ˈƀ", "ˈp"}, {"ˈđ", "ˈt"}, {"ˈꬶ", "ˈk"}, {"ˈꝺ", "ˈd"},
-- stressed consonants (coda of stressed syllables without long vowels, diphthongs, or triphthongs)
{spat1, "%1ʔ%3"}, {spat2, "%1k%3"}, {spat3, "%1p%3"}, {spat4, "%1t%3"}, {spat5, "%1ð%3"},
-- internal consonant clusters
{"ƀƀ", "ʔp"}, {"pƀ", "ʔp"},
{"đđ", "ʔt"}, {"tđ", "ʔt"},
{"ꬶꬶ", "ʔk"}, {"kꬶ", "ʔk"},
{"bm", "ʔp̚m"}, {"ꝺn", "ʔt̚n"}, {"ꬶn", "ʔk̚ŋ"},
{"mn", "mnː"}, {"mʔk", "mkː"},
{"(p[msɕ])", "%1ː"}, {"pr", "px"},
{"b([sɕ])", "p%1"},
{"nꬶ", "ŋk"}, {"([ðđʦłɕꬶr])v", "%1wː"},
{"đn", "tnː"}, {"đr", "tx"}, {"đꬶv", "tkwː"},
{"(ʦ[đlmn])", "%1ː"}, {"ʦꬶv", "ʦkwː"},
{"ʦxv", "ʦxw"}, {"đx", "tːx"},
{"(ð[mꬶ])", "%1ː"},
{"ꝺx", "ðx"},
{"(skl)", "%1ː"}, {"sʔk", "skː"}, {"sxv", "sxwː"},
{"([lr])ʔ([ptk])", "%1%2ː"},
{"lʦ(x?)v", "ɬʦ%1w"}, {"lʦx", "ɬʦx"},
{"(ł[mnꬶ])", "%1ː"},
{"(ꬶ[msɕ])", "%1ː"}, {"ꬶl", "ʔł", {"w"}}, {"ꬶl", "klː"},
{"ꬶsꬶ", "kskː"}, {"ꬶsl", "ksł"},
{"ɣ([mn])", "ŋ%1ː"}, {"ɣ([vsl])", "k%1"},
-- closed vowels
{"(" .. vowel .. "*)(" .. consonant .. consonant .. ")", function(s1, s2) return open_to_closed(s1, w) .. s2 end, {"w"}},
{"(" .. vowel .. "*)(" .. consonant .. consonant .. ")", function(s1, s2) return open_to_closed(s1) .. s2 end},
{"(" .. vowel .. "*)(" .. consonant .. ")$", function(s1, s2) return open_to_closed(s1, w) .. s2 end, {"w"}},
{"(" .. vowel .. "*)(" .. consonant .. ")$", function(s1, s2) return open_to_closed(s1) .. s2 end},
{"ɑ$", "a"},
{"(" .. vowel .. ")đ$", "%1ʔ%1"}, -- -Vt becomes -VʔV (or -Vht, not considered)
--undo ligatures
{"ʨ", "t͡ɕ"}, {"ʥ", "d͡ʑ"}, {"ł", "tɬ"}, {"ʣ", "d͡z"}, {"ʦ", "t͡s"},
{"ƀ", "p"}, {"ꝺ", "d"}, {"đ", "t"}, {"ꬶ", "ɡ"}, {"ɉ", "ɟ"},
-- remove morpheme separator and possible double long vowel markers
{"·", ""}, {"ːː", "ː"},
}
for _, rule in ipairs(rules) do
for _, rule in ipairs(rules) do
for regex, replacement in pairs(rule) do
local fordialect = rule[3]
term = gsub(term, regex, replacement)
if not fordialect or m_table.contains(fordialect, "w") then
word = rsub(word, rule[1], rule[2])
end
end
end
end