This module is used to retrieve and manage Wiktionary's various writing systems and the information associated with them. See Wiktionary:Scripts for more information.

The information itself is stored in Module:scripts/data. This module should not be used directly by any other module, the data should only be accessed through the functions provided by Module:scripts.

Finding and retrieving scripts

ସମ୍ପାଦନା

The module exports a number of functions that are used to find scripts.

getByCode(code)

Finds the script whose code matches the one provided. If it exists, it returns a Script object representing the script. Otherwise, it returns nil.

findBestScript(text, lang)

Given some text and a language object, this function iterates through the scripts of the given language and tries to find the script that best matches the text. It returns a Script object representing the script. If no match is found at all, it returns the None script object.

A Script object is returned from one of the functions above. It is a Lua representation of a script and the data associated with it. It has a number of methods that can be called on it, using the : syntax. For example:

local m_scripts = require("Module:scripts")
local sc = m_scripts.getByCode("Latn")
local name = sc:getCanonicalName()
-- "name" will now be "Latin"

:getCode()

Returns the script code of the language. Example: "Cyrl" for Cyrillic.

Script:getCanonicalName

ସମ୍ପାଦନା

:getCanonicalName()

Returns the canonical name of the script. This is the name used to represent that script on Wiktionary. Example: "Cyrillic" for Cyrillic.

Script:getAllNames

ସମ୍ପାଦନା

:getAllNames()

Returns a table of all names that the script is known by, including the canonical name. The names are not guaranteed to be unique, sometimes more than one script is known by the same name. Example: {"Latin", "Roman"} for the Latin script.

Script:countCharacters

ସମ୍ପାଦନା

:countCharacters(text)

Returns the number of characters in the text that are part of this script.

Note: You should never rely on text consisting entirely of the same script. Strings may contain spaces, punctuation and even wiki markup or HTML tags. HTML tags will skew the counts, as they contain Latin-script characters. So it's best to avoid them.

Script:getCategoryName

ସମ୍ପାଦନା

:getCategoryName()

Returns the name of the main category of that script. Example: "Cyrillic script" for Cyrillic, whose category is at Category:Cyrillic script.


local export = {}

local Script = {}


function Script:getCode()
	return self._code
end


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


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


--function Script:getAllNames()
--	return self._rawData.names
--end


function Script:getType()
	return "script"
end


function Script:getCategoryName()
	local name = self._rawData.canonicalName
	
	-- If the name already has "script" in it, don't add it.
	if name:find("[Ss]script$") then
		return name
	else
		return name .. " script"
	end
end


function Script:countCharacters(text)
	if not self._rawData.characters then
		return 0
	else
		local _, num = mw.ustring.gsub(text, "[" .. self._rawData.characters .. "]", "")
		return num
	end
end


function Script:getRawData()
	return self._rawData
end


function Script:toJSON()
	local ret = {
		canonicalName = self:getCanonicalName(),
		categoryName = self:getCategoryName(),
		code = self._code,
		otherNames = self:getOtherNames(),
		type = self:getType(),
		}
	
	return require("Module:JSON").toJSON(ret)
end


Script.__index = Script


function export.makeObject(code, data)
	return data and setmetatable({ _rawData = data, _code = code }, Script) or nil
end


function export.getByCode(code)
	if code == "IPAchar" then
		require("Module:debug").track("IPAchar")
	end
	return export.makeObject(code, mw.loadData("Module:scripts/data")[code])
end


-- Find the best script to use, based on the characters of a string.
function export.findBestScript(text, lang)
	if not text or not lang then
		return export.getByCode("None")
	end
	
	local scripts = lang:getScripts()
	
	-- Try to match every script against the text,
	-- and return the one with the most matching characters.
	local bestcount = 0
	local bestscript = nil
	
	for i, script in ipairs(scripts) do
		local count = script:countCharacters(text)
		
		if count > bestcount then
			bestcount = count
			bestscript = script
		end
	end
	
	if bestscript then
		return bestscript
	end
	
	-- No matching script was found. Return "None".
	return export.getByCode("None")
end

return export