Module:string/removeComments

local concat = table.concat
local find = string.find
local sub = string.sub

local function remove_comments(str, pre)
	local pos1 = find(str, "<!--", nil, true)
	if not pos1 then
		return str
	end
	local pos2 = find(str, "-->", pos1 + 4, true)
	if not pos2 then
		return pre and sub(str, 1, pos1 - 1) or str
	end
	local ret = sub(str, 1, pos1 - 1)
	pos1 = pos2 + 3
	pos2 = find(str, "<!--", pos1, true)
	if not pos2 then
		return ret .. sub(str, pos1)
	end
	local pos3 = find(str, "-->", pos2 + 4, true)
	if not pos3 then
		return ret .. sub(str, pos1, pre and pos2 - 1 or nil)
	end
	ret = {ret, sub(str, pos1, pos2 - 1)}
	local n = 2
	while true do
		pos1 = pos3 + 3
		pos2 = find(str, "<!--", pos1, true)
		if not pos2 then
			return concat(ret) .. sub(str, pos1)
		end
		pos3 = find(str, "-->", pos2 + 4, true)
		if not pos3 then
			return concat(ret) .. sub(str, pos1, pre and pos2 - 1 or nil)
		end
		n = n + 1
		ret = sub(str, pos1, pos2 - 1)
	end
end

--[==[Removes any HTML comments from the input text. `stage` can be one of three options:
* {"PRE"} (default) applies the method used by MediaWiki's preprocessor: all {{code|html|<nowiki><!-- ... --></nowiki>}} pairs are removed, as well as any text after an unclosed {{code|html|<nowiki><!--</nowiki>}}. This is generally suitable when parsing raw template or ] code. (Note, however, that the actual method used by the preprocessor is considerably more complex and differs under certain conditions (e.g. comments inside nowiki tags); if full accuracy is absolutely necessary, use ] instead).
* {"POST"} applies the method used to generate the final page output once all templates have been expanded: it loops over the text, removing any {{code|html|<nowiki><!-- ... --></nowiki>}} pairs until no more are found (e.g. {{code|html|<nowiki><!-<!-- ... -->- ... --></nowiki>}} would be fully removed), but any unclosed {{code|html|<nowiki><!--</nowiki>}} is ignored. This is suitable for handling links embedded in template inputs, where the {"PRE"} method will have already been applied by the native parser.
* {"BOTH"} applies {"PRE"} then {"POST"}.]==]
return function(str, stage)
	if stage == nil or stage == "PRE" then
		return remove_comments(str, true)
	elseif stage == "BOTH" then
		str = remove_comments(str, true)
	elseif stage ~= "POST" then
		error("bad argument #2 to 'remove_comments' (expected PRE, POST, or BOTH)", 2)
	end
	while true do
		local processed = remove_comments(str)
		if processed == str then
			return str
		end
		str = processed
	end
end