view mod_measure_message_length/mod_measure_message_length.lua @ 4651:8231774f5bfd

mod_cloud_notify_encrypted: Ensure body substring remains valid UTF-8 The `body:sub()` call risks splitting the string in the middle of a multi-byte UTF-8 sequence. This should have been caught by util.stanza validation, but that would have caused some havoc, at the very least causing the notification to not be sent. There have been no reports of this happening. Likely because this module isn't widely deployed among users with languages that use many longer UTF-8 sequences. The util.encodings.utf8.valid() function is O(n) where only the last sequence really needs to be checked, but it's in C and expected to be fast.
author Kim Alvefur <zash@zash.se>
date Sun, 22 Aug 2021 13:22:59 +0200
parents 6e70d354b7d8
children
line wrap: on
line source

local bytes = module:measure("bytes", "sizes");
local lines = module:measure("lines", "distribution");
local words = module:measure("words", "distribution");

local function measure_length(event)
	local body = event.stanza:get_child_text("body");
	if body then
		bytes(#body);
		lines(select(2, body:gsub("[^\n]+","")));
		words(select(2, body:gsub("%S+","")));
	end
end

module:hook("message/full", measure_length);
module:hook("message/bare", measure_length);
module:hook("message/host", measure_length);

module:hook("pre-message/full", measure_length);
module:hook("pre-message/bare", measure_length);
module:hook("pre-message/host", measure_length);