2018-12-23 13:04:54 -07:00
|
|
|
# Pleroma: A lightweight social networking server
|
2020-03-01 22:08:45 -07:00
|
|
|
# Copyright © 2017-2020 Pleroma Authors <https://pleroma.social/>
|
2018-12-23 13:04:54 -07:00
|
|
|
# SPDX-License-Identifier: AGPL-3.0-only
|
|
|
|
|
2018-09-09 17:29:00 -06:00
|
|
|
defmodule Pleroma.HTML do
|
2019-12-08 09:42:40 -07:00
|
|
|
# Scrubbers are compiled on boot so they can be configured in OTP releases
|
|
|
|
# @on_load :compile_scrubbers
|
|
|
|
|
|
|
|
def compile_scrubbers do
|
|
|
|
dir = Path.join(:code.priv_dir(:pleroma), "scrubbers")
|
|
|
|
|
|
|
|
dir
|
2019-12-09 10:38:01 -07:00
|
|
|
|> Pleroma.Utils.compile_dir()
|
2019-12-08 09:42:40 -07:00
|
|
|
|> case do
|
|
|
|
{:error, _errors, _warnings} ->
|
|
|
|
raise "Compiling scrubbers failed"
|
|
|
|
|
|
|
|
{:ok, _modules, _warnings} ->
|
|
|
|
:ok
|
|
|
|
end
|
|
|
|
end
|
|
|
|
|
2018-09-15 20:07:01 -06:00
|
|
|
defp get_scrubbers(scrubber) when is_atom(scrubber), do: [scrubber]
|
|
|
|
defp get_scrubbers(scrubbers) when is_list(scrubbers), do: scrubbers
|
|
|
|
defp get_scrubbers(_), do: [Pleroma.HTML.Scrubber.Default]
|
|
|
|
|
2019-03-04 20:18:43 -07:00
|
|
|
def get_scrubbers do
|
2018-11-06 11:34:57 -07:00
|
|
|
Pleroma.Config.get([:markup, :scrub_policy])
|
2018-09-15 20:07:01 -06:00
|
|
|
|> get_scrubbers
|
|
|
|
end
|
|
|
|
|
2018-09-21 19:10:53 -06:00
|
|
|
def filter_tags(html, nil) do
|
2018-12-30 12:44:17 -07:00
|
|
|
filter_tags(html, get_scrubbers())
|
|
|
|
end
|
|
|
|
|
|
|
|
def filter_tags(html, scrubbers) when is_list(scrubbers) do
|
|
|
|
Enum.reduce(scrubbers, html, fn scrubber, html ->
|
2018-09-15 20:07:01 -06:00
|
|
|
filter_tags(html, scrubber)
|
|
|
|
end)
|
2018-09-09 17:29:00 -06:00
|
|
|
end
|
|
|
|
|
2019-10-28 16:18:08 -06:00
|
|
|
def filter_tags(html, scrubber) do
|
|
|
|
{:ok, content} = FastSanitize.Sanitizer.scrub(html, scrubber)
|
|
|
|
content
|
|
|
|
end
|
|
|
|
|
2018-09-21 19:10:53 -06:00
|
|
|
def filter_tags(html), do: filter_tags(html, nil)
|
2019-10-28 16:18:08 -06:00
|
|
|
def strip_tags(html), do: filter_tags(html, FastSanitize.Sanitizer.StripTags)
|
2018-12-31 00:19:48 -07:00
|
|
|
|
2019-04-30 13:52:17 -06:00
|
|
|
def get_cached_scrubbed_html_for_activity(
|
|
|
|
content,
|
|
|
|
scrubbers,
|
|
|
|
activity,
|
|
|
|
key \\ "",
|
|
|
|
callback \\ fn x -> x end
|
|
|
|
) do
|
2019-04-05 06:19:44 -06:00
|
|
|
key = "#{key}#{generate_scrubber_signature(scrubbers)}|#{activity.id}"
|
2019-10-29 11:58:54 -06:00
|
|
|
|
2019-04-01 02:55:59 -06:00
|
|
|
Cachex.fetch!(:scrubber_cache, key, fn _key ->
|
2019-04-17 03:22:32 -06:00
|
|
|
object = Pleroma.Object.normalize(activity)
|
2019-04-30 13:52:17 -06:00
|
|
|
ensure_scrubbed_html(content, scrubbers, object.data["fake"] || false, callback)
|
2019-04-01 02:55:59 -06:00
|
|
|
end)
|
2018-12-31 00:19:48 -07:00
|
|
|
end
|
|
|
|
|
2019-04-05 06:19:44 -06:00
|
|
|
def get_cached_stripped_html_for_activity(content, activity, key) do
|
|
|
|
get_cached_scrubbed_html_for_activity(
|
2019-01-04 16:25:31 -07:00
|
|
|
content,
|
2019-10-28 16:18:08 -06:00
|
|
|
FastSanitize.Sanitizer.StripTags,
|
2019-04-05 06:19:44 -06:00
|
|
|
activity,
|
2019-04-30 13:52:17 -06:00
|
|
|
key,
|
|
|
|
&HtmlEntities.decode/1
|
2019-01-04 16:25:31 -07:00
|
|
|
)
|
2018-09-21 19:10:53 -06:00
|
|
|
end
|
|
|
|
|
2018-12-31 00:19:48 -07:00
|
|
|
def ensure_scrubbed_html(
|
|
|
|
content,
|
2019-04-01 02:55:59 -06:00
|
|
|
scrubbers,
|
2019-04-30 13:52:17 -06:00
|
|
|
fake,
|
|
|
|
callback
|
2018-12-31 00:19:48 -07:00
|
|
|
) do
|
2019-04-30 13:52:17 -06:00
|
|
|
content =
|
|
|
|
content
|
|
|
|
|> filter_tags(scrubbers)
|
|
|
|
|> callback.()
|
|
|
|
|
|
|
|
if fake do
|
|
|
|
{:ignore, content}
|
|
|
|
else
|
|
|
|
{:commit, content}
|
|
|
|
end
|
2018-12-31 00:19:48 -07:00
|
|
|
end
|
|
|
|
|
|
|
|
defp generate_scrubber_signature(scrubber) when is_atom(scrubber) do
|
|
|
|
generate_scrubber_signature([scrubber])
|
|
|
|
end
|
|
|
|
|
|
|
|
defp generate_scrubber_signature(scrubbers) do
|
|
|
|
Enum.reduce(scrubbers, "", fn scrubber, signature ->
|
2019-01-04 16:19:46 -07:00
|
|
|
"#{signature}#{to_string(scrubber)}"
|
2018-12-31 00:19:48 -07:00
|
|
|
end)
|
|
|
|
end
|
2018-09-21 19:10:53 -06:00
|
|
|
|
2020-09-07 04:19:19 -06:00
|
|
|
def extract_first_external_url_from_object(%{data: %{"content" => content}} = object)
|
|
|
|
when is_binary(content) do
|
|
|
|
unless object.data["fake"] do
|
|
|
|
key = "URL|#{object.id}"
|
|
|
|
|
|
|
|
Cachex.fetch!(:scrubber_cache, key, fn _key ->
|
|
|
|
{:commit, {:ok, extract_first_external_url(content)}}
|
|
|
|
end)
|
|
|
|
else
|
|
|
|
{:ok, extract_first_external_url(content)}
|
|
|
|
end
|
|
|
|
end
|
2019-02-04 22:06:17 -07:00
|
|
|
|
2020-09-07 04:19:19 -06:00
|
|
|
def extract_first_external_url_from_object(_), do: {:error, :no_content}
|
2019-01-26 07:55:12 -07:00
|
|
|
|
2020-09-07 04:19:19 -06:00
|
|
|
def extract_first_external_url(content) do
|
|
|
|
content
|
|
|
|
|> Floki.parse_fragment!()
|
|
|
|
|> Floki.find("a:not(.mention,.hashtag,.attachment,[rel~=\"tag\"])")
|
|
|
|
|> Enum.take(1)
|
|
|
|
|> Floki.attribute("href")
|
|
|
|
|> Enum.at(0)
|
2018-09-09 17:29:00 -06:00
|
|
|
end
|
|
|
|
end
|