X-Git-Url: http://git.squeep.com/?a=blobdiff_plain;f=lib%2Fpleroma%2Fhtml.ex;h=d1da746de0c781d6bd08a386641cad36492c9fd4;hb=57d11ac9dbe4f3befd288cb0f59f368968474f93;hp=878fac28c00a60a91f1edd01cd2aa3b0814ea670;hpb=8ae9424edb753097f4c2093bbded946f938d99e7;p=akkoma diff --git a/lib/pleroma/html.ex b/lib/pleroma/html.ex index 878fac28c..d1da746de 100644 --- a/lib/pleroma/html.ex +++ b/lib/pleroma/html.ex @@ -1,32 +1,100 @@ +# 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 - @markup Application.get_env(:pleroma, :markup) - 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 - Keyword.get(@markup, :scrub_policy) + def get_scrubbers do + Pleroma.Config.get([:markup, :scrub_policy]) |> get_scrubbers 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_activity( + content, + scrubbers, + activity, + key \\ "", + callback \\ fn x -> x end + ) do + key = "#{key}#{generate_scrubber_signature(scrubbers)}|#{activity.id}" + + Cachex.fetch!(:scrubber_cache, key, fn _key -> + object = Pleroma.Object.normalize(activity) + ensure_scrubbed_html(content, scrubbers, object.data["fake"] || false, callback) + end) end - def filter_tags(html), do: filter_tags(html, nil) + def get_cached_stripped_html_for_activity(content, activity, key) do + get_cached_scrubbed_html_for_activity( + content, + HtmlSanitizeEx.Scrubber.StripTags, + activity, + key, + &HtmlEntities.decode/1 + ) + end - def strip_tags(html) do - html |> Scrubber.scrub(Scrubber.StripTags) + def ensure_scrubbed_html( + content, + scrubbers, + fake, + callback + ) do + 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.filter_out("a.mention") + |> Floki.attribute("a", "href") + |> Enum.at(0) + + {:commit, {:ok, result}} + end) end end @@ -36,16 +104,33 @@ defmodule Pleroma.HTML.Scrubber.TwitterText do paragraphs, breaks and links are allowed through the filter. """ + @markup Application.get_env(:pleroma, :markup) + @valid_schemes Pleroma.Config.get([:uri_schemes, :valid_schemes], []) + require HtmlSanitizeEx.Scrubber.Meta alias HtmlSanitizeEx.Scrubber.Meta - @valid_schemes ["http", "https"] - 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_this_attribute_values("a", "class", [ + "hashtag", + "u-url", + "mention", + "u-url mention", + "mention u-url" + ]) + + Meta.allow_tag_with_this_attribute_values("a", "rel", [ + "tag", + "nofollow", + "noopener", + "noreferrer" + ]) + Meta.allow_tag_with_these_attributes("a", ["name", "title"]) # paragraphs and linebreaks @@ -53,22 +138,26 @@ defmodule Pleroma.HTML.Scrubber.TwitterText do Meta.allow_tag_with_these_attributes("p", []) # microformats + Meta.allow_tag_with_this_attribute_values("span", "class", ["h-card"]) Meta.allow_tag_with_these_attributes("span", []) # allow inline images for custom emoji - @markup Application.get_env(:pleroma, :markup) @allow_inline_images Keyword.get(@markup, :allow_inline_images) if @allow_inline_images do - Meta.allow_tag_with_uri_attributes("img", ["src"], @valid_schemes) + # restrict img tags to http/https only, because of MediaProxy. + Meta.allow_tag_with_uri_attributes("img", ["src"], ["http", "https"]) Meta.allow_tag_with_these_attributes("img", [ "width", "height", + "class", "title", "alt" ]) end + + Meta.strip_everything_not_covered() end defmodule Pleroma.HTML.Scrubber.Default do @@ -76,15 +165,36 @@ defmodule Pleroma.HTML.Scrubber.Default do require HtmlSanitizeEx.Scrubber.Meta alias HtmlSanitizeEx.Scrubber.Meta + # credo:disable-for-previous-line + # No idea how to fix this one… - @valid_schemes ["http", "https"] + @markup Application.get_env(:pleroma, :markup) + @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"], @valid_schemes) + Meta.allow_tag_with_uri_attributes("a", ["href", "data-user", "data-tag"], @valid_schemes) + + Meta.allow_tag_with_this_attribute_values("a", "class", [ + "hashtag", + "u-url", + "mention", + "u-url mention", + "mention u-url" + ]) + + Meta.allow_tag_with_this_attribute_values("a", "rel", [ + "tag", + "nofollow", + "noopener", + "noreferrer" + ]) + Meta.allow_tag_with_these_attributes("a", ["name", "title"]) + Meta.allow_tag_with_these_attributes("abbr", ["title"]) + Meta.allow_tag_with_these_attributes("b", []) Meta.allow_tag_with_these_attributes("blockquote", []) Meta.allow_tag_with_these_attributes("br", []) @@ -96,20 +206,23 @@ 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("strong", []) Meta.allow_tag_with_these_attributes("u", []) Meta.allow_tag_with_these_attributes("ul", []) - @markup Application.get_env(:pleroma, :markup) + Meta.allow_tag_with_this_attribute_values("span", "class", ["h-card"]) + Meta.allow_tag_with_these_attributes("span", []) + @allow_inline_images Keyword.get(@markup, :allow_inline_images) if @allow_inline_images do - Meta.allow_tag_with_uri_attributes("img", ["src"], @valid_schemes) + # restrict img tags to http/https only, because of MediaProxy. + Meta.allow_tag_with_uri_attributes("img", ["src"], ["http", "https"]) Meta.allow_tag_with_these_attributes("img", [ "width", "height", + "class", "title", "alt" ]) @@ -160,7 +273,7 @@ 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 = @@ -171,7 +284,9 @@ defmodule Pleroma.HTML.Transform.MediaProxy do {"img", attributes, children} end + 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