Editing Module:Category handler

--[=[ <pre>
-- Implements [Template:Ctg]
-- Sorts pages into a category more appropriately than pagename alone
-- Default and custom rules are outlined at [[Template:Category handler/doc]]
--]=]

local p = {}

local ucf = require('Module:Paramtest').ucfirst

local curpage = mw.title.getCurrentTitle()

function p.main(frame)
	local ns = curpage.namespace

	-- Just don't bother unless we're in content namespaces
	if not (ns == 0 or ns == 120 or ns == 116) then
		return ''
	end

	local args = frame:getParent().args 
	local cats = {}

	for _, v in ipairs(args) do
		local cat_x = {}

		-- Replace underscores with spaces
		-- Condense and trim white-space; remove new lines (just in case)
		v = mw.text.trim(v)
			:gsub('[_%s]+',' ')
			:gsub('\n','')

		-- Snip category name now, up to the index of the first set of two colons
		-- If no colons, just use the whole string
		local cat_n = (v:match('^([^:]+)::') or v)
				:gsub('[Cc]ategory:%s*','')

		-- Set category name to the name just snipped
		cat_x.name = cat_n

		-- Page title includes matched text
		-- Matched text is defined by ::ifmatches[text]
		-- or if empty, defaults to category name
		if v:find('::ifmatches') then
			-- Look for brackets used as delimiters and capture them all
			local match_set = v:match('::ifmatches(%[[^:]+%])')

			-- If none are found, use the pagename
			if not match_set then
				cat_x.ifmatch = {cat_n}
			else
				cat_x.ifmatch = {}
				-- Split match into table, delimited by brackets
				match_set = mw.text.split(match_set,'[%]%[]+')

				-- Add to match table; only if not blank
				-- An empty string is created by "[" at the beginning
				for _, w in ipairs(match_set) do
					if w:find('%S') then
						table.insert(cat_x.ifmatch,w)
					end
				end
			end

			-- Iterate through and escape all metacharacters
			-- Prevents errors when they're passed to string.match() below
			-- Make everything lowercase
			for i, w in ipairs(cat_x.ifmatch) do
				cat_x.ifmatch[i] = w:gsub(
						-- Chars: - ^ $ * ( ) + ?
						'([%-^$*()+?])',
						'%%%1'):lower()
			end
		end

		-- Text to strip from the front of the sort
		-- Can be user defined with ::remove[text]
		-- Defaults to category name exactly
		-- Escape metacharacters to prevent errors when they're passed to string.match() below
		cat_x.trim = string.gsub(
				v:match('::remove%[%s*([^]:]+)%s*%]') or
					cat_n,
					-- Chars: - ^ $ * ( ) + ?
					'([%-^$*()+?])',
					'%%%1')

		-- Add category and its rules into the list
		table.insert(cats,cat_x)
	end

	return p._main(cats)
end

function p._main(cat_list)
	-- Pagename, exactly, in all lowercase, and escaped (used for matching)
	local pagename = curpage.text
	local pagelc = pagename:lower()
	local pageesc = pagelc:gsub(
				-- Chars: - ^ $ * ( ) + ?
				'([%-^$*()+?])',
				'%%%1')
	-- Return table
	local ctg = {}

	for _, v in ipairs(cat_list) do
		-- Category name and in lowercase
		local cn = v.name
		local cnl = cn:lower()
		-- Text to remove
		local rmv = v.trim:lower()

		-- Little thing that checks pagename against everything in the matches table
		-- If there's no table, keep as false (it won't matter)
		local pagematches = false
		if v.ifmatch then
			for _, w in ipairs(v.ifmatch) do
				-- Look for exact match, and with faux-singular too
				if pagelc:find(w) or
				(w:find('s$') and 
					pagelc:find(w:match('(.*)s$')))
				then
					pagematches = true
				end
			end
		end

		-- Create a second string that counts as the singular of the text to remove
		-- If it works as a singular, and the page name is singular, then use it too
		-- Otherwise, just make it the same as rmv
		local rmvpl = rmv
		if rmv:find('s$') then
			rmvpl = rmv:match('(.*)s$')
			if pagelc:find('^'..rmvpl) and
			(not pagelc:find('^'..rmv))
			then
				-- Nothing
			else
				rmvpl = rmv
			end
		end

		-- If v.ifmatch is not specified or
		-- It is and the pattern matches any part of the pagename
		-- Continue to add categories
		if (not v.ifmatch) or
			(v.ifmatch and pagematches)
		then
			-- If the pagename matches category name exactly
			-- Or either is a simple plural of the other
			-- Or the text to remove exactly
			-- Sort to front
			if pagelc:find('^'..cnl..'$') or
				cnl:find('^'..pageesc..'s$') or
				pagelc:find('^'..cnl..'s$') or
				pagelc:find('^'..rmv..'$')
			then
				table.insert(ctg,string.format('[[Category:%s| ]]',cn))

			-- If the pagename begins with the category name
			-- Sort with beginning remove
			elseif pagelc:find('^'..rmv) or 
				pagelc:find('^'..rmvpl)
			then
				-- Offset by an extra character if it's not plural
				-- Or the page starts with plural
				if rmvpl == rmv then
					offset = 1
				else
					offset = 0
				end

				-- Unescape metacharacters for proper length
				local key = pagename:sub( #(rmv:gsub('%%','')) + offset )

				key = ucf(mw.text.trim(key))

				-- Remove punctuation from start if leftover
				-- Such as "/" leftover on subpages
				-- Or "(" for disambiguated pages
				if key:find('^%p') then
					key = ucf(key:sub(2))
				-- Just in case, remove "s" preceding punctuation
				elseif key:find('^S%p') then
					key = ucf(key:sub(3))
				end

				table.insert(ctg,string.format('[[Category:%s|%s]]',cn,key))

			-- Everything else just gets the category added plainly
			else
				table.insert(ctg,string.format('[[Category:%s]]',cn))
			end
		end
	end

	return table.concat(ctg)
end

return p