Difference between revisions 34822 and 35201 on mkwiktionary

< previous diff
Модул:languages
-- Module:languages
-- Imported from en.wiktionary
-- 2016-06-227-03 -- V2 -- last modified by DenisWasRight
-- Extended version for mk.wiktionary

local export = {}

local Language = {}


function Language:getCode()
	return self._code
end


function Language:getCanonicalName()
	return self._rawData.canonicalName
end


-- Commented out; I don't think anything uses this, the presence/absence of script errors should confirm
--function Language:getAllNames()
--	return self._rawData.names
--end


function Language:getOtherNames()
	return self._rawData.otherNames or {}
end


function Language:getType()
	return self._rawData.type or "regular"
end


function Language:getWikimediaLanguages()
	if not self._wikimediaLanguageObjects then
		local m_wikimedia_languages = require("Модул:wikimedia languages")
		self._wikimediaLanguageObjects = {}
		local wikimedia_codes = self._rawData.wikimedia_codes or {self._code}
		
		for _, wlangcode in ipairs(wikimedia_codes) do
			table.insert(self._wikimediaLanguageObjects, m_wikimedia_languages.getByCode(wlangcode))
		end
	end
	
	return self._wikimediaLanguageObjects
end


function Language:getWikipediaArticle()
	return self._rawData.wikipedia_article or self:getCategoryName()
end


function Language:getScripts()
	if not self._scriptObjects then
		local m_scripts = require("Модул:scripts")
		self._scriptObjects = {}
		
		for _, sc in ipairs(self._rawData.scripts or {"None"}) do
			table.insert(self._scriptObjects, m_scripts.getByCode(sc))
		end
	end
	
	return self._scriptObjects
end


function Language:getFamily()
	if self._rawData.family and not self._familyObject then
		self._familyObject = require("Модул:families").getByCode(self._rawData.family)
	end
	
	return self._familyObject
end


function Language:getAncestors()
	if not self._ancestorObjects then
		self._ancestorObjects = {}
		
		if self._rawData.ancestors then
			for _, ancestor in ipairs(self._rawData.ancestors) do
				table.insert(self._ancestorObjects, export.getByCode(ancestor) or require("Модул:etymology languages").getByCode(ancestor))
			end
		else
			local fam = self:getFamily()
			local protoLang = fam and fam:getProtoLanguage() or nil
			
			-- For the case where the current language is the proto-language
			-- of its family, we need to step up a level higher right from the start.
			if protoLang and protoLang:getCode() == self:getCode() then
				fam = fam:getFamily()
				protoLang = fam and fam:getProtoLanguage() or nil
			end
			
			while not protoLang and not (not fam or fam:getCode() == "qfa-not") do
				fam = fam:getFamily()
				protoLang = fam and fam:getProtoLanguage() or nil
			end
			
			table.insert(self._ancestorObjects, protoLang)
		end
	end
	
	return self._ancestorObjects
end

local function iterateOverAncestorTree(node, func)
	for _, ancestor in ipairs(node:getAncestors()) do
		if ancestor then
			local ret = func(ancestor) or iterateOverAncestorTree(ancestor, func)
			if ret then
				return ret
			end
		end
	end
end

function Language:getAncestorChain()
	if not self._ancestorChain then
		self._ancestorChain = {}
		local step = #self:getAncestors() == 1 and self:getAncestors()[1] or nil
		
		while step do
			table.insert(self._ancestorChain, 1, step)
			step = #step:getAncestors() == 1 and step:getAncestors()[1] or nil
		end
	end
	
	return self._ancestorChain
end


function Language:hasAncestor(otherlang)
	local function compare(ancestor)
		return ancestor:getCode() == otherlang:getCode()
	end
	return iterateOverAncestorTree(self, compare) or false
end


function Language:getCategoryName()
	local name = self._rawData.canonicalName
	
	-- If the name already has "language" in it, don't add it.
	if name:find("[Ll]anguageј]азик$") then
		return name
	else
		return name .. " languageјазик"
	end
end


function Language:getStandardCharacters()
	return self._rawData.standardChars
end


function Language:makeEntryName(text)
	text = mw.ustring.gsub(text, "^[¿¡]", "")
	text = mw.ustring.gsub(text, "(.)[؟?!;՛՜ ՞ ՟？！।॥။၊་།]$", "%1")
	
	if self._rawData.entry_name then
		for i, from in ipairs(self._rawData.entry_name.from) do
			local to = self._rawData.entry_name.to[i] or ""
			text = mw.ustring.gsub(text, from, to)
		end
	end
	
	return text
end


function Language:makeSortKey(name)
	name = mw.ustring.lower(name)
	
	-- Remove initial hyphens and *
	local hyphens_regex = "^[-־ـ*]+(.)"
	name = mw.ustring.gsub(name, hyphens_regex, "%1")

	-- Remove parentheses, as long as they are either preceded or followed by something
	name = mw.ustring.gsub(name, "(.)[()]+", "%1")
	name = mw.ustring.gsub(name, "[()]+(.)", "%1")
	
	-- If there are language-specific rules to generate the key, use those
	if self._rawData.sort_key then
		for i, from in ipairs(self._rawData.sort_key.from) do
			local to = self._rawData.sort_key.to[i] or ""
			name = mw.ustring.gsub(name, from, to)
		end
	end
	
	return mw.ustring.upper(name)
end


function Language:transliterate(text, sc, module_override)
	if not ((module_override or self._rawData.translit_module) and text) then
		return nil
	end
	
	if module_override then
		require("Модул:debug").track("module_override")
	end
	
	return require("Модул:" .. (module_override or self._rawData.translit_module)).tr(text, self:getCode(), sc and sc:getCode() or nil)
end


function Language:link_tr()
	return self._rawData.link_tr and true or false
end


function Language:toJSON()
	local entryNamePatterns = nil
	
	if self._rawData.entry_name then
		entryNamePatterns = {}
		
		for i, from in ipairs(self._rawData.entry_name.from) do
			local to = self._rawData.entry_name.to[i] or ""
			table.insert(entryNamePatterns, {from = from, to = to})
		end
	end
	
	local ret = {
		ancestors = self._rawData.ancestors,
		canonicalName = self:getCanonicalName(),
		categoryName = self:getCategoryName(),
		code = self._code,
		entryNamePatterns = entryNamePatterns,
		family = self._rawData.family,
		otherNames = self:getOtherNames(),
		scripts = self._rawData.scripts,
		type = self:getType(),
		wikimediaLanguages = self._rawData.wikimedia_codes,
		}
	
	return require("Модул:JSON").toJSON(ret)
end


-- Do NOT use this method!
-- All uses should be pre-approved on the talk page!
function Language:getRawData()
	return self._rawData
end

Language.__index = Language


function export.getDataModuleName(code)
	if code:find("^[a-z][a-z]$") then
		return "languages/data2"
	elseif code:find("^[a-z][a-z][a-z]$") then
		local prefix = code:sub(1, 1)
		return "languages/data3/" .. prefix
	elseif code:find("^[a-z-]+$") then
		return "languages/datax"
	else
		return nil
	end
end


local function getRawLanguageData(code)
	local modulename = export.getDataModuleName(code)
	return modulename and mw.loadData("Модул:" .. modulename)[code] or nil
end


function export.makeObject(code, data)
	if data and data.deprecated then
		require("Модул:debug").track("languages/deprecated")
		require("Модул:debug").track("languages/deprecated/" .. code)
	end
	
	return data and setmetatable({ _rawData = data, _code = code }, Language) or nil
end


function export.getByCode(code)
	return export.makeObject(code, getRawLanguageData(code))
end


function export.getByCanonicalName(name)
	local code = mw.loadData("Модул:languages/by name")[name]
	
	if not code then
		return nil
	end
	
	return export.makeObject(code, getRawLanguageData(code))
end


function export.iterateAll()
	mw.incrementExpensiveFunctionCount()
	local m_data = mw.loadData("Модул:languages/alldata")
	local func, t, var = pairs(m_data)
	
	return function()
		local code, data = func(t, var)
		return export.makeObject(code, data)
	end
end

return export