X-Git-Url: http://git.squeep.com/?a=blobdiff_plain;f=lib%2Fpleroma%2Fhtml.ex;h=fb602d6b6186335f1b4174f59fd6e70de9036648;hb=e91f867cc9f372da2262a3ac95a23bc12266595a;hp=107784e70496219156c616e17561e0285a94fd3d;hpb=358f88e10a7d3de0481309287b4b756087490dfc;p=akkoma diff --git a/lib/pleroma/html.ex b/lib/pleroma/html.ex index 107784e70..fb602d6b6 100644 --- a/lib/pleroma/html.ex +++ b/lib/pleroma/html.ex @@ -1,15 +1,76 @@ +# 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 + 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) + end) + end + + 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 filter_tags(html) do - scrubber = Keyword.get(@markup, :scrub_policy) - html |> Scrubber.scrub(scrubber) + 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 strip_tags(html) do - html |> Scrubber.scrub(Scrubber.StripTags) + 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, result} + end) end end @@ -19,31 +80,33 @@ defmodule Pleroma.HTML.Scrubber.TwitterText do paragraphs, breaks and links are allowed through the filter. """ + @markup Application.get_env(:pleroma, :markup) + @uri_schemes Application.get_env(:pleroma, :uri_schemes, []) + @valid_schemes Keyword.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_these_attributes("a", ["name", "title"]) + Meta.allow_tag_with_uri_attributes("a", ["href", "data-user", "data-tag"], @valid_schemes) + 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 - @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", @@ -52,6 +115,8 @@ defmodule Pleroma.HTML.Scrubber.TwitterText do "alt" ]) end + + Meta.strip_everything_not_covered() end defmodule Pleroma.HTML.Scrubber.Default do @@ -60,13 +125,17 @@ defmodule Pleroma.HTML.Scrubber.Default do require HtmlSanitizeEx.Scrubber.Meta alias HtmlSanitizeEx.Scrubber.Meta - @valid_schemes ["http", "https"] + @markup Application.get_env(:pleroma, :markup) + @uri_schemes Application.get_env(:pleroma, :uri_schemes, []) + @valid_schemes Keyword.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_these_attributes("a", ["name", "title"]) + Meta.allow_tag_with_uri_attributes("a", ["href", "data-user", "data-tag"], @valid_schemes) + Meta.allow_tag_with_these_attributes("a", ["name", "title", "class"]) + + Meta.allow_tag_with_these_attributes("abbr", ["title"]) Meta.allow_tag_with_these_attributes("b", []) Meta.allow_tag_with_these_attributes("blockquote", []) @@ -79,16 +148,16 @@ 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", []) - @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", @@ -127,3 +196,36 @@ defmodule Pleroma.HTML.Scrubber.Default do Meta.strip_everything_not_covered() end + +defmodule Pleroma.HTML.Transform.MediaProxy do + @moduledoc "Transforms inline image URIs to use MediaProxy." + + alias Pleroma.Web.MediaProxy + + def before_scrub(html), do: html + + def scrub_attribute("img", {"src", "http" <> target}) do + media_url = + ("http" <> target) + |> MediaProxy.url() + + {"src", media_url} + end + + def scrub_attribute(_tag, attribute), do: attribute + + def scrub({"img", attributes, children}) do + attributes = + attributes + |> Enum.map(fn attr -> scrub_attribute("img", attr) end) + |> Enum.reject(&is_nil(&1)) + + {"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(text), do: text +end