From 3ff9c5e2a67ab83c2abdb14cd246dea059079e75 Mon Sep 17 00:00:00 2001 From: Alex Gleason Date: Sat, 22 May 2021 16:44:51 -0500 Subject: [PATCH] Break out activity-specific HTML functions into Pleroma.Activity.HTML Fixes cycles in lib/pleroma/ecto_type/activity_pub/object_validators/safe_text.ex --- lib/pleroma/activity/html.ex | 45 +++++++++++++++++++ lib/pleroma/html.ex | 35 --------------- .../web/mastodon_api/views/status_view.ex | 4 +- lib/pleroma/web/metadata/utils.ex | 3 +- 4 files changed, 49 insertions(+), 38 deletions(-) create mode 100644 lib/pleroma/activity/html.ex diff --git a/lib/pleroma/activity/html.ex b/lib/pleroma/activity/html.ex new file mode 100644 index 000000000..0bf393836 --- /dev/null +++ b/lib/pleroma/activity/html.ex @@ -0,0 +1,45 @@ +# Pleroma: A lightweight social networking server +# Copyright © 2017-2021 Pleroma Authors +# SPDX-License-Identifier: AGPL-3.0-only + +defmodule Pleroma.Activity.HTML do + alias Pleroma.HTML + alias Pleroma.Object + + @cachex Pleroma.Config.get([:cachex, :provider], Cachex) + + 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 = Object.normalize(activity, fetch: false) + HTML.ensure_scrubbed_html(content, scrubbers, object.data["fake"] || false, callback) + end) + end + + def get_cached_stripped_html_for_activity(content, activity, key) do + get_cached_scrubbed_html_for_activity( + content, + FastSanitize.Sanitizer.StripTags, + activity, + key, + &HtmlEntities.decode/1 + ) + 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 +end diff --git a/lib/pleroma/html.ex b/lib/pleroma/html.ex index 2dfdca693..bee66169d 100644 --- a/lib/pleroma/html.ex +++ b/lib/pleroma/html.ex @@ -49,31 +49,6 @@ def filter_tags(html, scrubber) do def filter_tags(html), do: filter_tags(html, nil) def strip_tags(html), do: filter_tags(html, FastSanitize.Sanitizer.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, fetch: false) - ensure_scrubbed_html(content, scrubbers, object.data["fake"] || false, callback) - end) - end - - def get_cached_stripped_html_for_activity(content, activity, key) do - get_cached_scrubbed_html_for_activity( - content, - FastSanitize.Sanitizer.StripTags, - activity, - key, - &HtmlEntities.decode/1 - ) - end - def ensure_scrubbed_html( content, scrubbers, @@ -92,16 +67,6 @@ def ensure_scrubbed_html( 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_from_object(%{data: %{"content" => content}} = object) when is_binary(content) do unless object.data["fake"] do diff --git a/lib/pleroma/web/mastodon_api/views/status_view.ex b/lib/pleroma/web/mastodon_api/views/status_view.ex index bac897a57..da2cf0f95 100644 --- a/lib/pleroma/web/mastodon_api/views/status_view.ex +++ b/lib/pleroma/web/mastodon_api/views/status_view.ex @@ -254,7 +254,7 @@ def render("show.json", %{activity: %{data: %{"object" => _object}} = activity} content_html = content - |> HTML.get_cached_scrubbed_html_for_activity( + |> Activity.HTML.get_cached_scrubbed_html_for_activity( User.html_filter_policy(opts[:for]), activity, "mastoapi:content" @@ -262,7 +262,7 @@ def render("show.json", %{activity: %{data: %{"object" => _object}} = activity} content_plaintext = content - |> HTML.get_cached_stripped_html_for_activity( + |> Activity.HTML.get_cached_stripped_html_for_activity( activity, "mastoapi:content" ) diff --git a/lib/pleroma/web/metadata/utils.ex b/lib/pleroma/web/metadata/utils.ex index de7195435..bc31d66b9 100644 --- a/lib/pleroma/web/metadata/utils.ex +++ b/lib/pleroma/web/metadata/utils.ex @@ -3,6 +3,7 @@ # SPDX-License-Identifier: AGPL-3.0-only defmodule Pleroma.Web.Metadata.Utils do + alias Pleroma.Activity alias Pleroma.Emoji alias Pleroma.Formatter alias Pleroma.HTML @@ -13,7 +14,7 @@ def scrub_html_and_truncate(%{data: %{"content" => content}} = object) do # html content comes from DB already encoded, decode first and scrub after |> HtmlEntities.decode() |> String.replace(~r//, " ") - |> HTML.get_cached_stripped_html_for_activity(object, "metadata") + |> Activity.HTML.get_cached_stripped_html_for_activity(object, "metadata") |> Emoji.Formatter.demojify() |> HtmlEntities.decode() |> Formatter.truncate()