Merge branch 'cycles-html' into 'develop'

Recompilation speedup: Break out activity-specific HTML functions into Pleroma.Activity.HTML

See merge request pleroma/pleroma!3426
This commit is contained in:
feld 2021-05-29 21:19:25 +00:00
commit b5f3a5c979
4 changed files with 49 additions and 38 deletions

View file

@ -0,0 +1,45 @@
# Pleroma: A lightweight social networking server
# Copyright © 2017-2021 Pleroma Authors <https://pleroma.social/>
# 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

View file

@ -49,31 +49,6 @@ def filter_tags(html, scrubber) do
def filter_tags(html), do: filter_tags(html, nil) def filter_tags(html), do: filter_tags(html, nil)
def strip_tags(html), do: filter_tags(html, FastSanitize.Sanitizer.StripTags) 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( def ensure_scrubbed_html(
content, content,
scrubbers, scrubbers,
@ -92,16 +67,6 @@ def ensure_scrubbed_html(
end end
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) def extract_first_external_url_from_object(%{data: %{"content" => content}} = object)
when is_binary(content) do when is_binary(content) do
unless object.data["fake"] do unless object.data["fake"] do

View file

@ -260,7 +260,7 @@ def render("show.json", %{activity: %{data: %{"object" => _object}} = activity}
content_html = content_html =
content content
|> HTML.get_cached_scrubbed_html_for_activity( |> Activity.HTML.get_cached_scrubbed_html_for_activity(
User.html_filter_policy(opts[:for]), User.html_filter_policy(opts[:for]),
activity, activity,
"mastoapi:content" "mastoapi:content"
@ -268,7 +268,7 @@ def render("show.json", %{activity: %{data: %{"object" => _object}} = activity}
content_plaintext = content_plaintext =
content content
|> HTML.get_cached_stripped_html_for_activity( |> Activity.HTML.get_cached_stripped_html_for_activity(
activity, activity,
"mastoapi:content" "mastoapi:content"
) )

View file

@ -3,6 +3,7 @@
# SPDX-License-Identifier: AGPL-3.0-only # SPDX-License-Identifier: AGPL-3.0-only
defmodule Pleroma.Web.Metadata.Utils do defmodule Pleroma.Web.Metadata.Utils do
alias Pleroma.Activity
alias Pleroma.Emoji alias Pleroma.Emoji
alias Pleroma.Formatter alias Pleroma.Formatter
alias Pleroma.HTML 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 # html content comes from DB already encoded, decode first and scrub after
|> HtmlEntities.decode() |> HtmlEntities.decode()
|> String.replace(~r/<br\s?\/?>/, " ") |> String.replace(~r/<br\s?\/?>/, " ")
|> HTML.get_cached_stripped_html_for_activity(object, "metadata") |> Activity.HTML.get_cached_stripped_html_for_activity(object, "metadata")
|> Emoji.Formatter.demojify() |> Emoji.Formatter.demojify()
|> HtmlEntities.decode() |> HtmlEntities.decode()
|> Formatter.truncate() |> Formatter.truncate()