X-Git-Url: http://git.squeep.com/?a=blobdiff_plain;f=lib%2Fpleroma%2Fhtml.ex;h=bf5daa9482bdb1da279502b5a8c5b937f805d5fc;hb=8180de951e2ac1efc6cfb9f64d078d6a1b7d0c0e;hp=a0473676b936821136d29ea12ce9cec40fe25205;hpb=89fbed88212657e3dcd4bbcb2c0718b07802037f;p=akkoma
diff --git a/lib/pleroma/html.ex b/lib/pleroma/html.ex
index a0473676b..bf5daa948 100644
--- a/lib/pleroma/html.ex
+++ b/lib/pleroma/html.ex
@@ -1,5 +1,5 @@
# 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
@@ -15,8 +15,11 @@ defmodule Pleroma.HTML do
end
def filter_tags(html, nil) do
- get_scrubbers()
- |> Enum.reduce(html, fn scrubber, html ->
+ 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
@@ -24,6 +27,51 @@ 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_object(content, scrubbers, object, module) do
+ key = "#{module}#{generate_scrubber_signature(scrubbers)}|#{object.id}"
+ Cachex.fetch!(:scrubber_cache, key, fn _key -> ensure_scrubbed_html(content, scrubbers) end)
+ end
+
+ def get_cached_stripped_html_for_object(content, object, module) do
+ get_cached_scrubbed_html_for_object(
+ content,
+ HtmlSanitizeEx.Scrubber.StripTags,
+ object,
+ module
+ )
+ end
+
+ def ensure_scrubbed_html(
+ content,
+ scrubbers
+ ) do
+ {:commit, 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(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
@@ -44,14 +92,14 @@ defmodule Pleroma.HTML.Scrubber.TwitterText do
# 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"])
# 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)
@@ -85,7 +133,7 @@ defmodule Pleroma.HTML.Scrubber.Default do
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_these_attributes("abbr", ["title"])
@@ -100,7 +148,7 @@ 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", [])