မဝ်ဂျူ:az-headword
Documentation for this module may be created at မဝ်ဂျူ:az-headword/doc
local export = {}
local pos_functions = {}
local rfind = mw.ustring.find
local rmatch = mw.ustring.match
local rsubn = mw.ustring.gsub
local rsplit = mw.text.split
local lang = require("Module:languages").getByCode("az")
local m_scripts = require("Module:scripts")
local m_common = require("Module:az-common")
local suffix_categories = {["နာမဝိသေသန"] = true, ["နာမ်"] = true}
-- version of rsubn() that discards all but the first return value
local function rsub(term, foo, bar)
local retval = rsubn(term, foo, bar)
return retval
end
local function track(page)
require("Module:debug").track("az-headword/" .. page)
return true
end
local no_split_words = {["bə's"] = true}
local function add_space_word_links(space_word, split_dash)
local space_word_no_punct, punct = rmatch(space_word, "^(.*)([,;:?!])$")
space_word_no_punct = space_word_no_punct or space_word
punct = punct or ""
local words
-- don’t split prefixes and suffixes
if not split_dash or rfind(space_word_no_punct, "^%-") or
rfind(space_word_no_punct, "%-$") then
words = {space_word_no_punct}
else
words = rsplit(space_word_no_punct, "%-")
end
local linked_words = {}
for _, word in ipairs(words) do
if not no_split_words[word] and rfind(word, "'") then
word = rsub(word, "([^']+')", "[[%1]]")
word = rsub(word, "%]([^%[%]]*)$", "][[%1]]")
else
word = "[[" .. word .. "]]"
end
table.insert(linked_words, word)
end
return table.concat(linked_words, "-") .. punct
end
local function add_lemma_links(lemma, split_dash)
if not rfind(lemma, " ") then split_dash = true end
local words = rsplit(lemma, " ")
local linked_words = {}
for _, word in ipairs(words) do
table.insert(linked_words, add_space_word_links(word, split_dash))
end
local retval = table.concat(linked_words, " ")
-- If we ended up with a single link consisting of the entire lemma,
-- remove the link.
local unlinked_retval = rmatch(retval, "^%[%[([^%[%]]*)%]%]$")
return unlinked_retval or retval
end
-- The main entry point.
-- This is the only function that can be invoked from a template.
function export.show(frame)
local PAGENAME = mw.title.getCurrentTitle().text
local poscat = frame.args[1] or error(
"Part of speech has not been specified. Please pass parameter 1 to the module invocation.")
local params = {
["head"] = {list = true},
["suff"] = {type = "boolean"},
["splitdash"] = {alias_of = "splithyph", type = "boolean"},
["splithyph"] = {type = "boolean"},
["nolinkhead"] = {type = "boolean"}
}
if rfind(PAGENAME, " ") then track("space") end
if pos_functions[poscat] then
for key, val in pairs(pos_functions[poscat].params) do
params[key] = val
end
end
local parargs = frame:getParent().args
if parargs.splitdash then track("splitdash") end
local args = require("Module:parameters").process(parargs, params)
local heads = args["head"]
if pos_functions[poscat] and pos_functions[poscat].param1_is_head and
args[1] then table.insert(heads, 1, args[1]) end
if args.nolinkhead then
if #heads == 0 then heads = {PAGENAME} end
else
local auto_linked_head = add_lemma_links(PAGENAME, args["splithyph"])
if #heads == 0 then
heads = {auto_linked_head}
else
for _, head in ipairs(heads) do
if head == auto_linked_head then
track("redundant-head")
end
end
end
end
local data = {
lang = lang,
pos_category = poscat,
categories = {},
heads = heads,
genders = {},
inflections = {}
}
if args["suff"] then
if suffix_categories[poscat] then
local singular_poscat = poscat:gsub("s$", "")
table.insert(data.categories, lang:getCanonicalName() .. " " ..
singular_poscat .. "-forming suffixes")
else
error("No category exists for suffixes forming " .. poscat .. ".")
end
end
if pos_functions[poscat] then pos_functions[poscat].func(args, data) end
return require("Module:headword").full_headword(data)
end
local function do_adjective(pos)
return {
params = {
[1] = {} -- hyphen (-) if incomparable, intensive form otherwise
},
func = function(args, data)
local PAGENAME = mw.title.getCurrentTitle().text
local script = m_scripts.findBestScript(PAGENAME, lang):getCode()
local function comp()
if script == "Latn" then
return "[[daha]] "
elseif script == "Cyrl" then
return "[[даһа]] "
end
end
local function sup()
if script == "Latn" then
return "[[ən]] "
elseif script == "Cyrl" then
return "[[ән]] "
end
end
if args[1] == "-" then
table.insert(data.inflections, {label = "ပတုပ်ရံၚ်ဟွံမာန်"})
else
table.insert(data.inflections,
{label = "ပတုပ်ရံၚ်", comp() .. PAGENAME})
table.insert(data.inflections,
{label = "သဒ္ဒာ", sup() .. PAGENAME})
if args[1] then
table.insert(data.inflections, {label = "သ္ကာတ်မြဟ်လောန်", args1})
end
end
end
}
end
local function get_noun_pos(is_proper)
return {
params = {
[1] = {},
[2] = {},
["stem"] = {},
["broken"] = {},
["broken-v"] = {},
["nb"] = {},
["sing"] = {}
},
func = function(args, data)
local PAGENAME = mw.title.getCurrentTitle().text
local script = m_scripts.findBestScript(PAGENAME, lang):getCode()
local args1, args2 = m_common.getType(PAGENAME)
local function stemforacc()
if script == "Latn" then
if args2 == "q" then
return mw.ustring.sub(PAGENAME, 1, -2) .. 'ğ'
elseif args2 == "k" then
return mw.ustring.sub(PAGENAME, 1, -2) .. 'y'
else
return PAGENAME
end
elseif script == "Cyrl" then
if args2 == "г" then
return mw.ustring.sub(PAGENAME, 1, -2) .. 'ғ'
elseif args2 == "к" then
return mw.ustring.sub(PAGENAME, 1, -2) .. 'ј'
else
return PAGENAME
end
end
end
local function stemforpl()
if script == "Latn" then
if args2 == "cc" then
return mw.ustring.sub(PAGENAME, 1, -2)
else
return PAGENAME
end
elseif script == "Cyrl" then
if args2 == "cc" then
return mw.ustring.sub(PAGENAME, 1, -2)
else
return PAGENAME
end
end
end
local function azv1()
if script == "Latn" then
if rfind(args1, "[əeiöü]") then
return "i"
else
return "ı"
end
elseif script == "Cyrl" then
if rfind(args1, "[әеиөү]") then
return "и"
else
return "ы"
end
end
end
local function azv2()
if script == "Latn" then
if rfind(args1, "[əeiöü]") then
return "ə"
else
return "a"
end
elseif script == "Cyrl" then
if rfind(args1, "[әеиөү]") then
return "ә"
else
return "а"
end
end
end
local function azv3()
if script == "Latn" then
if rfind(args1, "[əei]") then
return "i"
elseif rfind(args1, "[öü]") then
return "ü"
elseif rfind(args1, "[aı]") then
return "ı"
else
return "u"
end
elseif script == "Cyrl" then
if rfind(args1, "[әеи]") then
return "и"
elseif rfind(args1, "[өү]") then
return "ү"
elseif rfind(args1, "[аы]") then
return "ы"
else
return "у"
end
end
end
local function n()
if script == "Latn" then
return "n"
elseif script == "Cyrl" then
return "н"
end
end
local function l()
if script == "Latn" then
return "l"
elseif script == "Cyrl" then
return "л"
end
end
local function r()
if script == "Latn" then
return "r"
elseif script == "Cyrl" then
return "р"
end
end
if args2 == "c" or args2 == "cc" or args2 == "q" or args2 == "k" then
if args["stem"] then
if args["sing"] == "no" then
if args["nb"] == "no" then
if args["broken"] then
table.insert(data.genders, {"p"})
else
table.insert("?")
end
else
table.insert(data.genders, {"p"})
if args["broken"] then
table.insert(data.inflections, {
label = "broken plural",
accel = {form = "nom|broken|plural"},
args["broken"]
})
end
end
else
if args["nb"] == "no" then
table.insert(data.inflections, {
label = "definite accusative",
accel = {form = "def|acc|s"},
args["stem"] .. azv3()
})
if args["broken"] then
table.insert(data.inflections, {
label = "broken plural",
accel = {form = "nom|broken|plural"},
args["broken"]
})
end
else
if args["broken"] then
table.insert(data.inflections, {
label = "definite accusative",
accel = {form = "def|acc|s"},
args["stem"] .. azv3()
})
table.insert(data.inflections, {
label = "sound plural",
accel = {form = "nom|sound|p"},
PAGENAME .. l() .. azv2() .. r()
})
table.insert(data.inflections, {
label = "broken plural",
accel = {form = "nom|broken|p"},
args["broken"]
})
else
table.insert(data.inflections, {
label = "definite accusative",
accel = {form = "def|acc|s"},
args["stem"] .. azv3()
})
table.insert(data.inflections, {
label = "ကိုန်ဗဟုဝစ်",
accel = {form = "nom|p"},
PAGENAME .. l() .. azv2() .. r()
})
end
end
end
else
if args["sing"] == "no" then
if args["nb"] == "no" then
if args["broken"] then
table.insert(data.genders, {"p"})
else
table.insert("?")
end
else
table.insert(data.genders, {"p"})
if args["broken"] then
table.insert(data.inflections, {
label = "broken plural",
accel = {form = "nom|broken|plural"},
args["broken"]
})
end
end
else
if args["nb"] == "no" then
table.insert(data.inflections, {
label = "definite accusative",
accel = {form = "def|acc|s"},
stemforacc() .. azv3()
})
if args["broken"] then
table.insert(data.inflections, {
label = "broken plural",
accel = {form = "nom|broken|plural"},
args["broken"]
})
end
else
if args["broken"] then
table.insert(data.inflections, {
label = "definite accusative",
accel = {form = "def|acc|s"},
stemforacc() .. azv3()
})
table.insert(data.inflections, {
label = "sound plural",
accel = {form = "nom|sound|p"},
stemforpl() .. l() .. azv2() .. r()
})
table.insert(data.inflections, {
label = "broken plural",
accel = {form = "nom|broken|p"},
args["broken"]
})
else
table.insert(data.inflections, {
label = "definite accusative",
accel = {form = "def|acc|s"},
stemforacc() .. azv3()
})
table.insert(data.inflections, {
label = "plural",
accel = {form = "nom|p"},
stemforpl() .. l() .. azv2() .. r()
})
end
end
end
end
else
if args["stem"] then
if args["sing"] == "no" then
if args["nb"] == "no" then
if args["broken"] then
table.insert(data.genders, {"p"})
else
table.insert("?")
end
else
table.insert(data.genders, {"p"})
if args["broken"] then
table.insert(data.inflections, {
label = "broken plural",
accel = {form = "nom|broken|plural"},
args["broken"]
})
end
end
else
if args["nb"] == "no" then
table.insert(data.inflections, {
label = "definite accusative",
accel = {form = "def|acc|s"},
args["stem"] .. azv3()
})
if args["broken"] then
table.insert(data.inflections, {
label = "broken plural",
accel = {form = "nom|broken|plural"},
args["broken"]
})
end
else
if args["broken"] then
table.insert(data.inflections, {
label = "definite accusative",
accel = {form = "def|acc|s"},
args["stem"] .. azv3()
})
table.insert(data.inflections, {
label = "sound plural",
accel = {form = "nom|sound|p"},
PAGENAME .. l() .. azv2() .. r()
})
table.insert(data.inflections, {
label = "broken plural",
accel = {form = "nom|broken|p"},
args["broken"]
})
else
table.insert(data.inflections, {
label = "definite accusative",
accel = {form = "def|acc|s"},
args["stem"] .. azv3()
})
table.insert(data.inflections, {
label = "plural",
accel = {form = "nom|p"},
PAGENAME .. l() .. azv2() .. r()
})
end
end
end
else
if args["sing"] == "no" then
if args["nb"] == "no" then
if args["broken"] then
table.insert(data.genders, {"p"})
else
table.insert("?")
end
else
table.insert(data.genders, {"p"})
if args["broken"] then
table.insert(data.inflections, {
label = "broken plural",
accel = {form = "nom|broken|plural"},
args["broken"]
})
end
end
else
if args["nb"] == "no" then
table.insert(data.inflections, {
label = "definite accusative",
accel = {form = "def|acc|s"},
PAGENAME .. n() .. azv3()
})
if args["broken"] then
table.insert(data.inflections, {
label = "broken plural",
accel = {form = "nom|broken|plural"},
args["broken"]
})
end
else
if args["broken"] then
table.insert(data.inflections, {
label = "definite accusative",
accel = {form = "def|acc|s"},
PAGENAME .. n() .. azv3()
})
table.insert(data.inflections, {
label = "sound plural",
accel = {form = "nom|sound|p"},
PAGENAME .. l() .. azv2() .. r()
})
table.insert(data.inflections, {
label = "broken plural",
accel = {form = "nom|broken|p"},
args["broken"]
})
else
table.insert(data.inflections, {
label = "definite accusative",
accel = {form = "def|acc|s"},
PAGENAME .. n() .. azv3()
})
table.insert(data.inflections, {
label = "plural",
accel = {form = "nom|p"},
PAGENAME .. l() .. azv2() .. r()
})
end
end
end
end
end
end
}
end
pos_functions["နာမ်"] = get_noun_pos(false)
pos_functions["proper nouns"] = get_noun_pos(true)
pos_functions["နာမဝိသေသန"] = do_adjective("adjectives")
return export