વિભાગ:લિપિઓ

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:લિપિઓ/આંકડા. 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

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

getByCode

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

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.

Script objects

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:લિપિઓ")
local sc = m_scripts.getByCode("ગુજ")
local name = sc:getCanonicalName()
-- "નામ" હવે "ગુજરાતી" હશે

Script:getCode

:getCode()

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

Script:getCanonicalName

: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

: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

: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

: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:getRawData()
	return self._rawData
end

function Script:getCode()
	return self._code
end

function Script:getCanonicalName()
	return self._rawData.names[1]
end

function Script:getAllNames()
	return self._rawData.names
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:getCategoryName()
	local name = self._rawData.names[1]
	
	-- If the name already has "script" in it, don't add it.
	if name:find("લિપિ$") then
		return name
	else
		return name .. " લિપિ"
	end
end

Script.__index = Script

-- The object cache implements memoisation, and is used to avoid duplication
-- of objects. If you request the same script code twice, you should also get
-- the same object twice, not two different objects with identical data.
-- It might also speed things up a bit.
local object_cache = {}

function export.getByCode(code)
	if object_cache[code] then
		return object_cache[code]
	end
	
	local rawData = mw.loadData("Module:લિપિઓ/આંકડા")[code]
	
	if not rawData then
		return nil
	end
	
	local object = setmetatable({ _rawData = rawData, _code = code }, Script)
	object_cache[code] = object
	return object
end

function export.getScriptByCode(code)
	require("Module:ભૂલકાઢ").track("getScriptByCode")
	return export.getByCode(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("કંઈ નહિં")
	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("કંઈ નહિં")
end

return export