X-Git-Url: http://git.squeep.com/?a=blobdiff_plain;f=lib%2Fpleroma%2Fhtml.ex;h=71db516e699bda753ca8a5d0ee83147c786c9e80;hb=9ef664ffceed15727fd185c4c119025d0ee21e30;hp=1b920d7fd5cf95781bbaa08d6d5f9107ad810658;hpb=b451a92d78b184dda63e6647f815f89c0e37fd98;p=akkoma diff --git a/lib/pleroma/html.ex b/lib/pleroma/html.ex index 1b920d7fd..71db516e6 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 @@ -11,20 +15,51 @@ 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 - def filter_tags(html, scrubber) do - html |> Scrubber.scrub(scrubber) + 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) do + key = "#{generate_scrubber_signature(scrubbers)}|#{object.id}" + Cachex.fetch!(:scrubber_cache, key, fn _key -> ensure_scrubbed_html(content, scrubbers) end) end - def filter_tags(html), do: filter_tags(html, nil) + def get_cached_stripped_html_for_object(content, object) do + get_cached_scrubbed_html_for_object(content, HtmlSanitizeEx.Scrubber.StripTags, object) + end + + def ensure_scrubbed_html( + content, + scrubbers + ) do + {:commit, filter_tags(content, scrubbers)} + end - def strip_tags(html) do - html |> Scrubber.scrub(Scrubber.StripTags) + 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 -> + # If a scrubber does not have a version(e.g HtmlSanitizeEx.Scrubber.StripTags) it is assumed it is always 0) + version = + if Kernel.function_exported?(scrubber, :version, 0) do + scrubber.version + else + 0 + end + + "#{signature}#{to_string(scrubber)}#{version}" + end) end end @@ -41,11 +76,15 @@ defmodule Pleroma.HTML.Scrubber.TwitterText do 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"], @valid_schemes) + Meta.allow_tag_with_uri_attributes("a", ["href", "data-user", "data-tag"], @valid_schemes) Meta.allow_tag_with_these_attributes("a", ["name", "title"]) # paragraphs and linebreaks @@ -79,6 +118,10 @@ defmodule Pleroma.HTML.Scrubber.Default do require HtmlSanitizeEx.Scrubber.Meta alias HtmlSanitizeEx.Scrubber.Meta + def version do + 0 + end + @markup Application.get_env(:pleroma, :markup) @uri_schemes Application.get_env(:pleroma, :uri_schemes, []) @valid_schemes Keyword.get(@uri_schemes, :valid_schemes, []) @@ -86,7 +129,7 @@ defmodule Pleroma.HTML.Scrubber.Default do Meta.remove_cdata_sections_before_scrub() Meta.strip_comments() - Meta.allow_tag_with_uri_attributes("a", ["href"], @valid_schemes) + 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("abbr", ["title"]) @@ -156,6 +199,10 @@ defmodule Pleroma.HTML.Transform.MediaProxy do alias Pleroma.Web.MediaProxy + def version do + 0 + end + def before_scrub(html), do: html def scrub_attribute("img", {"src", "http" <> target}) do @@ -166,7 +213,7 @@ defmodule Pleroma.HTML.Transform.MediaProxy do {"src", media_url} end - def scrub_attribute(tag, attribute), do: attribute + def scrub_attribute(_tag, attribute), do: attribute def scrub({"img", attributes, children}) do attributes = @@ -177,9 +224,9 @@ defmodule Pleroma.HTML.Transform.MediaProxy do {"img", attributes, children} end - def scrub({:comment, children}), do: "" + def scrub({:comment, _children}), do: "" def scrub({tag, attributes, children}), do: {tag, attributes, children} - def scrub({tag, children}), do: children + def scrub({_tag, children}), do: children def scrub(text), do: text end