X-Git-Url: http://git.squeep.com/?a=blobdiff_plain;f=lib%2Fpleroma%2Fhtml.ex;h=bf5daa9482bdb1da279502b5a8c5b937f805d5fc;hb=7e384a2425b5188ca76aad4b97172b553ca9b640;hp=583f05aebc0d33535c1c788ca5dc486582efd35d;hpb=cc6689cc203d44e19e9aa14c2ef3a3dad823ef88;p=akkoma diff --git a/lib/pleroma/html.ex b/lib/pleroma/html.ex index 583f05aeb..bf5daa948 100644 --- a/lib/pleroma/html.ex +++ b/lib/pleroma/html.ex @@ -1,3 +1,7 @@ +# Pleroma: A lightweight social networking server +# Copyright © 2017-2019 Pleroma Authors +# SPDX-License-Identifier: AGPL-3.0-only + defmodule Pleroma.HTML do alias HtmlSanitizeEx.Scrubber @@ -11,8 +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 @@ -20,6 +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 @@ -40,14 +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) @@ -81,7 +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"]) @@ -96,7 +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", [])