X-Git-Url: http://git.squeep.com/?a=blobdiff_plain;f=lib%2Fpleroma%2Fhtml.ex;h=7f1dbe28c81ce1e9a94cb43ae96bc0291d8cfb17;hb=9825a943917321204d26ca1b486491138c8c82da;hp=169394af9fd8c6d744198e00573222a4fd016ca2;hpb=19f9889fbe9d120acfaed2a5aedb4032d56eb217;p=akkoma
diff --git a/lib/pleroma/html.ex b/lib/pleroma/html.ex
index 169394af9..7f1dbe28c 100644
--- a/lib/pleroma/html.ex
+++ b/lib/pleroma/html.ex
@@ -1,10 +1,23 @@
# Pleroma: A lightweight social networking server
-# Copyright © 2017-2018 Pleroma Authors
+# Copyright © 2017-2019 Pleroma Authors
# SPDX-License-Identifier: AGPL-3.0-only
defmodule Pleroma.HTML do
alias HtmlSanitizeEx.Scrubber
+ 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)
@@ -14,6 +27,65 @@ defmodule Pleroma.HTML do
def filter_tags(html, scrubber), do: Scrubber.scrub(html, scrubber)
def filter_tags(html), do: filter_tags(html, nil)
def strip_tags(html), do: Scrubber.scrub(html, Scrubber.StripTags)
+
+ def get_cached_scrubbed_html_for_activity(content, scrubbers, activity, key \\ "") do
+ key = "#{key}#{generate_scrubber_signature(scrubbers)}|#{activity.id}"
+
+ Cachex.fetch!(:scrubber_cache, key, fn _key ->
+ ensure_scrubbed_html(content, scrubbers, activity.data["object"]["fake"] || false)
+ end)
+ end
+
+ def get_cached_stripped_html_for_activity(content, activity, key) do
+ get_cached_scrubbed_html_for_activity(
+ content,
+ HtmlSanitizeEx.Scrubber.StripTags,
+ activity,
+ key
+ )
+ end
+
+ def ensure_scrubbed_html(
+ content,
+ scrubbers,
+ false = _fake
+ ) do
+ {:commit, filter_tags(content, scrubbers)}
+ end
+
+ def ensure_scrubbed_html(
+ content,
+ scrubbers,
+ true = _fake
+ ) do
+ {:ignore, filter_tags(content, scrubbers)}
+ 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.filter_out("a.mention")
+ |> Floki.attribute("a", "href")
+ |> Enum.at(0)
+
+ {:commit, {:ok, result}}
+ end)
+ end
end
defmodule Pleroma.HTML.Scrubber.TwitterText do
@@ -23,29 +95,31 @@ defmodule Pleroma.HTML.Scrubber.TwitterText do
"""
@markup Application.get_env(:pleroma, :markup)
- @uri_schemes Application.get_env(:pleroma, :uri_schemes, [])
- @valid_schemes Keyword.get(@uri_schemes, :valid_schemes, [])
+ @valid_schemes Pleroma.Config.get([:uri_schemes, :valid_schemes], [])
require HtmlSanitizeEx.Scrubber.Meta
alias HtmlSanitizeEx.Scrubber.Meta
- def version do
- 0
- end
-
Meta.remove_cdata_sections_before_scrub()
Meta.strip_comments()
# links
Meta.allow_tag_with_uri_attributes("a", ["href", "data-user", "data-tag"], @valid_schemes)
- Meta.allow_tag_with_these_attributes("a", ["name", "title"])
+ Meta.allow_tag_with_these_attributes("a", ["name", "title", "class"])
+
+ Meta.allow_tag_with_this_attribute_values("a", "rel", [
+ "tag",
+ "nofollow",
+ "noopener",
+ "noreferrer"
+ ])
# paragraphs and linebreaks
Meta.allow_tag_with_these_attributes("br", [])
Meta.allow_tag_with_these_attributes("p", [])
# microformats
- Meta.allow_tag_with_these_attributes("span", [])
+ Meta.allow_tag_with_these_attributes("span", ["class"])
# allow inline images for custom emoji
@allow_inline_images Keyword.get(@markup, :allow_inline_images)
@@ -70,20 +144,24 @@ defmodule Pleroma.HTML.Scrubber.Default do
require HtmlSanitizeEx.Scrubber.Meta
alias HtmlSanitizeEx.Scrubber.Meta
-
- def version do
- 0
- end
+ # credo:disable-for-previous-line
+ # No idea how to fix this oneâ¦
@markup Application.get_env(:pleroma, :markup)
- @uri_schemes Application.get_env(:pleroma, :uri_schemes, [])
- @valid_schemes Keyword.get(@uri_schemes, :valid_schemes, [])
+ @valid_schemes Pleroma.Config.get([:uri_schemes, :valid_schemes], [])
Meta.remove_cdata_sections_before_scrub()
Meta.strip_comments()
Meta.allow_tag_with_uri_attributes("a", ["href", "data-user", "data-tag"], @valid_schemes)
- Meta.allow_tag_with_these_attributes("a", ["name", "title"])
+ Meta.allow_tag_with_these_attributes("a", ["name", "title", "class"])
+
+ Meta.allow_tag_with_this_attribute_values("a", "rel", [
+ "tag",
+ "nofollow",
+ "noopener",
+ "noreferrer"
+ ])
Meta.allow_tag_with_these_attributes("abbr", ["title"])
@@ -98,7 +176,7 @@ defmodule Pleroma.HTML.Scrubber.Default do
Meta.allow_tag_with_these_attributes("ol", [])
Meta.allow_tag_with_these_attributes("p", [])
Meta.allow_tag_with_these_attributes("pre", [])
- Meta.allow_tag_with_these_attributes("span", [])
+ Meta.allow_tag_with_these_attributes("span", ["class"])
Meta.allow_tag_with_these_attributes("strong", [])
Meta.allow_tag_with_these_attributes("u", [])
Meta.allow_tag_with_these_attributes("ul", [])
@@ -150,10 +228,6 @@ end
defmodule Pleroma.HTML.Transform.MediaProxy do
@moduledoc "Transforms inline image URIs to use MediaProxy."
- def version do
- 0
- end
-
alias Pleroma.Web.MediaProxy
def before_scrub(html), do: html