X-Git-Url: https://git.squeep.com/?a=blobdiff_plain;f=lib%2Fpleroma%2Fhtml.ex;h=2dfdca6930bd2c147dccd09941cca62bf6054a9e;hb=2217b35bd40593f5dcfdba4c13dd7b7bded018f3;hp=05946aa966a829deea50a8b33d54310f287c484e;hpb=226f4d5ef93805e2ff93f00d443238ab7afeb3e6;p=akkoma diff --git a/lib/pleroma/html.ex b/lib/pleroma/html.ex index 05946aa96..2dfdca693 100644 --- a/lib/pleroma/html.ex +++ b/lib/pleroma/html.ex @@ -1,11 +1,13 @@ # Pleroma: A lightweight social networking server -# Copyright © 2017-2019 Pleroma Authors +# Copyright © 2017-2021 Pleroma Authors # SPDX-License-Identifier: AGPL-3.0-only defmodule Pleroma.HTML do # Scrubbers are compiled on boot so they can be configured in OTP releases # @on_load :compile_scrubbers + @cachex Pleroma.Config.get([:cachex, :provider], Cachex) + def compile_scrubbers do dir = Path.join(:code.priv_dir(:pleroma), "scrubbers") @@ -56,8 +58,8 @@ defmodule Pleroma.HTML do ) do key = "#{key}#{generate_scrubber_signature(scrubbers)}|#{activity.id}" - Cachex.fetch!(:scrubber_cache, key, fn _key -> - object = Pleroma.Object.normalize(activity) + @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 @@ -100,20 +102,27 @@ defmodule Pleroma.HTML do end) end - def extract_first_external_url(_, nil), do: {:error, "No content"} + def extract_first_external_url_from_object(%{data: %{"content" => content}} = object) + when is_binary(content) do + unless object.data["fake"] do + key = "URL|#{object.id}" - def extract_first_external_url(object, content) do - key = "URL|#{object.id}" + @cachex.fetch!(:scrubber_cache, key, fn _key -> + {:commit, {:ok, extract_first_external_url(content)}} + end) + else + {:ok, extract_first_external_url(content)} + end + end - Cachex.fetch!(:scrubber_cache, key, fn _key -> - result = - content - |> Floki.parse_fragment!() - |> Floki.filter_out("a.mention,a.hashtag,a[rel~=\"tag\"]") - |> Floki.attribute("a", "href") - |> Enum.at(0) + def extract_first_external_url_from_object(_), do: {:error, :no_content} - {:commit, {:ok, result}} - end) + def extract_first_external_url(content) do + content + |> Floki.parse_fragment!() + |> Floki.find("a:not(.mention,.hashtag,.attachment,[rel~=\"tag\"])") + |> Enum.take(1) + |> Floki.attribute("href") + |> Enum.at(0) end end