Pleroma/lib/pleroma/html.ex

120 lines
3.0 KiB
Elixir
Raw Normal View History

# Pleroma: A lightweight social networking server
2018-12-31 16:41:47 +01:00
# Copyright © 2017-2019 Pleroma Authors <https://pleroma.social/>
# SPDX-License-Identifier: AGPL-3.0-only
defmodule Pleroma.HTML do
# 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
|> Pleroma.Utils.compile_dir()
|> case do
{:error, _errors, _warnings} ->
raise "Compiling scrubbers failed"
{:ok, _modules, _warnings} ->
:ok
end
end
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]
def get_scrubbers do
Pleroma.Config.get([:markup, :scrub_policy])
|> get_scrubbers
end
def filter_tags(html, nil) do
filter_tags(html, get_scrubbers())
end
def filter_tags(html, scrubbers) when is_list(scrubbers) do
Enum.reduce(scrubbers, html, fn scrubber, html ->
filter_tags(html, scrubber)
end)
end
def filter_tags(html, scrubber) do
{:ok, content} = FastSanitize.Sanitizer.scrub(html, scrubber)
content
end
def filter_tags(html), do: filter_tags(html, nil)
def strip_tags(html), do: filter_tags(html, FastSanitize.Sanitizer.StripTags)
2019-04-30 21:52:17 +02:00
def get_cached_scrubbed_html_for_activity(
content,
scrubbers,
activity,
key \\ "",
callback \\ fn x -> x end
) do
key = "#{key}#{generate_scrubber_signature(scrubbers)}|#{activity.id}"
2019-10-29 18:58:54 +01:00
2019-04-01 10:55:59 +02:00
Cachex.fetch!(:scrubber_cache, key, fn _key ->
object = Pleroma.Object.normalize(activity)
2019-04-30 21:52:17 +02:00
ensure_scrubbed_html(content, scrubbers, object.data["fake"] || false, callback)
2019-04-01 10:55:59 +02:00
end)
end
def get_cached_stripped_html_for_activity(content, activity, key) do
get_cached_scrubbed_html_for_activity(
2019-01-05 00:25:31 +01:00
content,
FastSanitize.Sanitizer.StripTags,
activity,
2019-04-30 21:52:17 +02:00
key,
&HtmlEntities.decode/1
2019-01-05 00:25:31 +01:00
)
end
def ensure_scrubbed_html(
content,
2019-04-01 10:55:59 +02:00
scrubbers,
2019-04-30 21:52:17 +02:00
fake,
callback
) do
2019-04-30 21:52:17 +02:00
content =
content
|> filter_tags(scrubbers)
|> callback.()
if fake do
{:ignore, content}
else
{:commit, content}
end
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 ->
"#{signature}#{to_string(scrubber)}"
end)
end
def extract_first_external_url(_, nil), do: {:error, "No content"}
def extract_first_external_url(object, content) do
key = "URL|#{object.id}"
Cachex.fetch!(:scrubber_cache, key, fn _key ->
result =
content
|> Floki.parse_fragment!()
|> Floki.filter_out("a.mention,a.hashtag,a[rel~=\"tag\"]")
|> Floki.attribute("a", "href")
|> Enum.at(0)
2019-01-28 21:55:33 +01:00
{:commit, {:ok, result}}
end)
end
end