Module:Sort title/sandbox: Difference between revisions

Module documentation[view] [edit] [history] [purge]

Module:Sort title is used to create sortkeys for pages.

What it does

The module preforms the following checks:

• If the first word of the title is an article, it moves it to the end of the title. For example: The Avengers will have a sortkey of Avengers, The.
• If the title is disambiguated and the first word of the disambiguation is an article, it moves it to the end of the disambiguation. For example: Pilot (The Flash) will have a sortkey of Pilot (Flash, The).
• If the title is disambiguated and the first word of the title and the disambiguation is an article, both of the above changes will occur. For example: The End (A Series of Unfortunate Events) will have a sortkey of End, The (Series of Unfortunate Events, A).
• If the title is a number which is separated by a commas, it removes the commas. For example: 4,722 Hours will have a sortkey of 4722 Hours.

Usage

From template:

• {{#invoke:Sort title|getSortKey}}
• {{#invoke:Sort title|getDefaultSort}}

From module:

local sortkeyModule = require('Module:Sort title')
local sortkey = sortkeyModule._getSortKey()

Function list

Function	Explanation
getSortKey	Returns a sortkey
getDefaultSort	Returns a DEFAULTSORT string

The above documentation is transcluded from Module:Sort title/doc. (edit | history)
Editors can experiment in this module's sandbox (edit | diff) and testcases (edit | run) pages.
Add categories to the /doc subpage. Subpages of this module.

local match = require("Module:String")._match

local p = {}

--[[
Local function which is used to return a title without its first word.
--]]
local function getTitleWithoutFirstWord(title)
	return mw.ustring.gsub(title, "^[^%s]*%s*", "")
end

--[[
Local function which is used to check if the word is an article.
Returns true if it is, false if it isn't.
--]]
local function isFirstWordAnArticle(word)
	word = string.lower(word)
	if (word == "a" or word == "an" or word == "the") then
		return true
	else
		return false
	end
end

--[[
Local function which is used to return a sort key for a specific part.
--]]
local function getSortKey(title, firstWord)
	local sortKey = title
	if (isFirstWordAnArticle(firstWord) and firstWord ~= title) then
		title = getTitleWithoutFirstWord(title)
		sortKey = title .. ", " .. firstWord
	end
	
	return sortKey
end

--TODO: DOC
local function convertRomanNumerals(romanNumerals)
	local convertModule = require('Module:ConvertNumeric').roman_to_numeral
	return tonumber(convertModule(romanNumerals))
end

--TODO: DOC
local function checkForRomanNumerals(title)
	if (title) then
		return mw.ustring.match(title, "[IVXLCDM]+")
	else
		return nil
	end
end

--[[
Local function which is used to return the last word from a title.
--]]
local function getLastWord(title)
	return string.match(title, "%s(%S+)$")
end

--[[
Local function which is used to return the first word from a title.
--]]
local function getFirstWord(title)
	return match(title, "^[^%s]*", 1, 1, false, "")
end

--[[
Local function which is used to return a number without commas.
For example: 4,722 will become 4722.
--]]
local function cleanNumberFromCommas(title)
	return string.gsub(title, "(%d+)(,+)", "%1")
end

local function getTitlePartSortKey(title)
	title = cleanNumberFromCommas(title)
	local firstWord = getFirstWord(title)
	local lastWord = getLastWord(title)
	local romanNumerals = checkForRomanNumerals(title)
	if (romanNumerals) then
		local lastWordModified = convertRomanNumerals(romanNumerals)
		title = string.gsub(title, lastWord, lastWordModified)
	end
	local sortKey = getSortKey(title, firstWord)
end

--[[
Local function which is used to return the disambiguation sort key.
--]]
local function getDisambiguationSortKey(disambiguation)
	if (disambiguation == "") then
		return ""
	end

	return "(" .. getTitlePartSortKey(disambiguation) .. ")"
end

--[[
Local function which is used to return the title without its disambiguation.
--]]
local function getTitleWithoutDisambiguation(title, disambiguation)
	local newTitle = string.gsub(title, "%(".. disambiguation .. "%)", "")
	return mw.text.trim(newTitle)
end

--[[
Local function which is used to return the disambiguation from a title.
--]]
local function getDisambiguation(title)
	local disambiguation = match(title, "%s%((.-)%)", 1, -1, false, "")
	if (disambiguation == "") then
		return ""
	else
		return disambiguation
	end
end

--[[
The main function.
--]]
local function _main(title)
	if (not title) then
		title = mw.title.getCurrentTitle().text
	end

	local disambiguation = getDisambiguation(title)
	local disambiguationSortKey = getDisambiguationSortKey(disambiguation)
	
	title = getTitleWithoutDisambiguation(title, disambiguation)
	title = getTitlePartSortKey(title)

	local sortKey = title .. " " .. disambiguationSortKey
	return mw.text.trim(sortKey)
end

--[[
Public function which allows modules to retrieve a sort key.
--]]
function p._getSortKey()
	return _main(nil)
end

--[[
Public function which allows templates to retrieve a sort key.
--]]
function p.getSortKey(frame)
	return p._main(nil) 
end

--[[
Public function which allows templates to retrieve the sort key inside a DEFAULTSORT.
--]]
function p.getDefaultSort(frame)
	local sortKey = p._main(nil)
	return frame:preprocess{text = "{{DEFAULTSORT:" .. sortKey .. "}}"} 
end

--[[
Public function which is used for testing various names and not the current page name.
--]]
function p.testcases(frame)
	local getArgs = require('Module:Arguments').getArgs
	local args = getArgs(frame)
	return _main(args[1])
end

return p