local export = {}
local pos_functions = {}
local PAGENAME = mw.title.getCurrentTitle().text
local lang = require("Module:languages").getByCode("eo")
local except = require("Module:eo-headword/exceptions")
-- Verb stem must have at least two letters.
local participle_pattern = "..([aio]n?t[aeo]j?n?)$"
local function monosyllabic(word)
return select(2, mw.ustring.gsub(word, "[AEIOUaeiou]", "")) == 1
end
local function check(data, tracking_categories)
local catname = "Danh từ Quốc tế ngữ có liên kết đỏ trong dòng tiêu đề"
if data.pos_category == "Tính từ" or data.pos_category == "determiners" or data.pos_category == "adjectival participles" then
catname = "Tính từ Quốc tế ngữ có liên kết đỏ trong dòng tiêu đề"
end
for _, entry in ipairs(data.check) do
local t = mw.title.new(entry)
if t and not t.exists then
table.insert(tracking_categories, catname)
end
end
end
-- Determines which function in pos_functions should be used for a word in {{eo-head}}.
local function getPOS(word)
-- deal with some exceptions
if except[word] then
return except[word]
end
-- delete anything after "de"
word = mw.ustring.gsub(word, " de .+$", "")
if word:find(" ") then
if word:find("o%f[%z%s]") and word:find("a%f[%z%s]") then
return "Danh từ"
end
end
-- deal with letters
if mw.ustring.match(word,"^[aeiou]$") or mw.ustring.match(word,"^[bcĉdfgĝhĥjĵklmnprsŝtŭvz]o$") then
return "Danh từ"
end
-- deal with ordinals
if mw.ustring.match(word, "^[0-9]+%-?a$") then
return "Tính từ"
elseif mw.ustring.match(word, "^[0-9]+%-?aj?n?$") then
return "adjective forms"
end
-- Words with only one vowel are always irregular
if monosyllabic(word) then
return nil
elseif mw.ustring.find(word, participle_pattern) then -- detect this firstly
return "participles"
end
local ending = word:match("[aeiou][^aeiou]*$")
if ending == "a" then
return "Tính từ"
elseif ending == "aj" or ending == "an" or ending == "ajn" then
return "adjective forms"
elseif ending == "e" or ending == "en" then
return "adverbs"
elseif ending == "o" then
if mw.ustring.find(word, "^%u") then
return "Danh từ riêng"
else
return "Danh từ"
end
elseif ending == "oj" or ending == "on" or ending == "ojn" then
if mw.ustring.find(word, "^%u") then
return "proper noun forms"
else
return "noun forms"
end
elseif ending == "i" then
return "Động từ"
elseif ending:find("^[iaou]s$") or ending == "u" then
return "verb forms"
else
return nil
end
end
export.getPOS = getPOS
-- The main entry point
function export.show(frame)
local tracking_categories = {}
local parent_args = frame:getParent().args
local poscat = parent_args["pos"] or frame.args["poscat"] or getPOS(PAGENAME)
if not poscat then
if mw.title.getCurrentTitle().nsText == "Template" then
poscat = "Danh từ"
else
error("Part of speech of \"" .. PAGENAME .. "\" cannot be automatically determined.")
end
else
if poscat == "plurale tantum" then
poscat = "pluralia tantum"
elseif not (poscat == "pluralia tantum" or poscat:find("s$")) then
poscat = poscat .. "" -- Pluralize part of speech.
end
end
local params = {
["head"] = {list = true},
["pos"] = {},
["suff"] = {type = "boolean"},
}
if pos_functions[poscat] then
for key, val in pairs(pos_functions[poscat].params) do
params[key] = val
end
end
local args = require("Module:parameters").process(parent_args, params)
local data = {lang = lang, pos_category = poscat, categories = {}, heads = args["head"], genders = {}, inflections = {}, check = {}}
if pos_functions[poscat] then
pos_functions[poscat].func(args, data)
end
check(data, tracking_categories)
return require("Module:headword").full_headword(data) .. require("Module:utilities").format_categories(tracking_categories, lang)
end
pos_functions["Tính từ"] = {
params = {
},
func = function(args, data)
table.insert(data.inflections, {label = "[[accusative|acc.]] số ít", accel = {form = "acc|s"}, PAGENAME .. "n"})
table.insert(data.inflections, {label = "số nhiều", accel = {form = "p"}, PAGENAME .. "j"})
table.insert(data.inflections, {label = "[[accusative|acc.]] số nhiều", accel = {form = "acc|p"}, PAGENAME .. "jn"})
table.insert(data.check, PAGENAME .. "n")
table.insert(data.check, PAGENAME .. "j")
table.insert(data.check, PAGENAME .. "jn")
end
}
pos_functions["determiners"] = {
params = {
},
func = function(args, data)
table.insert(data.inflections, {label = "[[accusative|acc.]] số ít", accel = {form = "acc|s"}, PAGENAME .. "n"})
table.insert(data.inflections, {label = "số nhiều", accel = {form = "p"}, PAGENAME .. "j"})
table.insert(data.inflections, {label = "[[accusative|acc.]] số nhiều", accel = {form = "acc|p"}, PAGENAME .. "jn"})
table.insert(data.check, PAGENAME .. "n")
table.insert(data.check, PAGENAME .. "j")
table.insert(data.check, PAGENAME .. "jn")
end
}
pos_functions["Danh từ"] = {
params = {
[1] = {list = true, allow_holes = true},
},
func = function(args, data)
-- Get the parameters
local inflected_words_specified = false
local inflected_words = {}
for i = 1, args[1].maxindex do
local word = args[1][i]
if word == "+" or word == "-" then
word = nil
end
if word then
inflected_words[word] = true
inflected_words_specified = true
end
end
local pl = {}
local acc = {}
local acc_pl = {}
-- Split multi-word terms
for word in mw.text.gsplit(PAGENAME, " ", true) do
local pos = getPOS(word)
-- Inflect each word separately
if (not inflected_words_specified or inflected_words[word]) and (pos == "Tính từ" or pos == "Danh từ" or pos == "Danh từ riêng") then
local is_letter = ""
if mw.ustring.match(word,"^[aeiou]$") or mw.ustring.match(word,"^[bcĉdfgĝhĥjĵklmnprsŝtŭvz]o$")then
is_letter = "-o"
end
table.insert(acc, word .. is_letter .. "n")
table.insert(pl, word .. is_letter .. "j")
table.insert(acc_pl, word .. is_letter .. "jn")
else
table.insert(acc, word)
table.insert(pl, word)
table.insert(acc_pl, word)
end
end
-- Merge back together
acc = table.concat(acc, " ")
pl = table.concat(pl, " ")
acc_pl = table.concat(acc_pl, " ")
local acc2, pl2, acc_pl2
if PAGENAME == "sozo" then
acc2 = "sozo-on"
pl2 = "sozo-oj"
acc_pl2 = "sozo-ojn"
end
if args[1][1] == "-" then
table.insert(data.inflections, {label = "uncountable"})
table.insert(data.inflections, {label = "[[accusative|acc.]]", accel = {form = "acc"}, acc})
table.insert(data.categories, lang:getCanonicalName() .. " uncountable nouns")
table.insert(data.check, acc)
else
table.insert(data.inflections, {label = "[[accusative|acc.]] số ít", accel = {form = "acc|s"}, acc, acc2})
table.insert(data.inflections, {label = "số nhiều", accel = {form = "p"}, pl, pl2})
table.insert(data.inflections, {label = "[[accusative|acc.]] số nhiều", accel = {form = "acc|p"}, acc_pl, acc_pl2})
table.insert(data.check, acc)
table.insert(data.check, pl)
table.insert(data.check, acc_pl)
end
end
}
pos_functions["Danh từ riêng"] = {
params = {
[1] = {list = true, allow_holes = true},
},
func = function(args, data)
-- Get the parameters
local inflected_words_specified = false
local inflected_words = {}
for i = 1, args[1].maxindex do
local word = args[1][i]
if word == "+" or word == "-" then
word = nil
end
if word then
inflected_words[word] = true
inflected_words_specified = true
end
end
local acc = {}
local pl = {}
local acc_pl = {}
local de = false
-- Split multi-word terms
for word in mw.text.gsplit(PAGENAME, " ", true) do
local pos = getPOS(word)
if word == "de" then de = true end
-- Inflect each word separately
if (not inflected_words_specified or inflected_words[word]) and (pos == "Tính từ" or pos == "Danh từ" or pos == "Danh từ riêng" or mw.ustring.match(word,'[ao]j$') and not monosyllabic(word)) and not de then
table.insert(acc, word .. "n")
table.insert(pl, word .. "j")
table.insert(acc_pl, word .. "jn")
else
table.insert(acc, word)
table.insert(pl, word)
table.insert(acc_pl, word)
end
end
-- Merge back together
acc = table.concat(acc, " ")
pl = table.concat(pl, " ")
acc_pl = table.concat(acc_pl, " ")
if args[1][1] == "+" then
table.insert(data.inflections, {label = "[[accusative|acc.]] số ít", accel = {form = "acc|s"}, acc})
table.insert(data.inflections, {label = "số nhiều", accel = {form = "p"}, pl})
table.insert(data.inflections, {label = "[[accusative|acc.]] số nhiều", accel = {form = "acc|p"}, acc_pl})
table.insert(data.check, acc)
table.insert(data.check, pl)
table.insert(data.check, acc_pl)
else
table.insert(data.inflections, {label = "[[accusative|acc.]]", accel = {form = "acc"}, acc})
table.insert(data.check, acc)
end
end
}
pos_functions["Động từ"] = {
params = {
},
func = function(args, data)
local stem = PAGENAME:sub(1, -2)
table.insert(data.inflections, {label = "hiện tại", accel = {form = "pres"}, stem .. "as"})
table.insert(data.inflections, {label = "quá khứ", accel = {form = "past"}, stem .. "is"})
table.insert(data.inflections, {label = "tương lai", accel = {form = "futr"}, stem .. "os"})
table.insert(data.inflections, {label = "[[conditional|cond.]]", accel = {form = "cond"}, stem .. "us"})
table.insert(data.inflections, {label = "[[volitive|voli.]]", accel = {form = "voli"}, stem .. "u"})
end
}
pos_functions["noun forms"] = {
params = {
[1] = {},
},
func = function(args, data)
if args[1] == "p" or args[1] == "p+" then
table.insert(data.genders, "p")
data.categories = {"Esperanto nouns", "Esperanto pluralia tantum"}
table.insert(data.inflections, {label = "[[accusative|acc.]]", accel = {form = "acc"}, PAGENAME .. "n"})
table.insert(data.check, PAGENAME .. "n")
if args[1] == "p+" then
local singular = mw.ustring.gsub(PAGENAME, "j$", "")
table.insert(data.inflections, {label = "singular", singular})
table.insert(data.check, singular)
end
end
end
}
pos_functions["pluralia tantum"] = {
params = {
[1] = {},
},
func = function(args, data)
data.pos_category = "Danh từ"
table.insert(data.categories, 1, "Esperanto pluralia tantum")
table.insert(data.inflections, {label = "[[accusative|acc.]]", accel = {form = "acc"}, PAGENAME .. "n"})
table.insert(data.check, PAGENAME .. "n")
if args[1] == "+" then
local singular = mw.ustring.gsub(PAGENAME, "j$", "")
table.insert(data.inflections, {label = "singular", singular})
table.insert(data.check, singular)
end
end
}
pos_functions["participles"] = {
params = {
[1] = {}, [2] = {}, --these will be phased out
},
func = function(args, data)
local ending = mw.ustring.match(PAGENAME, participle_pattern)
if ending then
local vowel, consonant = ending:match("([aoe])(j?n?)$")
if consonant == "" then
if vowel == "a" or vowel == "o" then
table.insert(data.inflections, {label = "[[accusative|acc.]] số ít", accel = {form = ending .. "n"}, PAGENAME .. "n"})
table.insert(data.inflections, {label = "số nhiều", accel = {form = ending .. "j"}, PAGENAME .. "j"})
table.insert(data.inflections, {label = "[[accusative|acc.]] số nhiều", accel = {form = ending .. "jn"}, PAGENAME .. "jn"})
table.insert(data.check, PAGENAME .. "n")
table.insert(data.check, PAGENAME .. "j")
table.insert(data.check, PAGENAME .. "jn")
elseif vowel == "e" then
data.categories = {"Esperanto adverbial participles"}
end
elseif vowel == "e" then
error("-e" .. consonant .. " is not a valid participle ending!")
end
if vowel == "a" then
data.categories = {"Esperanto adjectival participles"}
elseif vowel == "o" then
data.categories = {"Esperanto nominal participles"}
end
else
error("This term is not a participle!")
end
end
}
return export
