X-Git-Url: http://git.squeep.com/?a=blobdiff_plain;f=lib%2Fpleroma%2Fhtml.ex;h=d1da746de0c781d6bd08a386641cad36492c9fd4;hb=57d11ac9dbe4f3befd288cb0f59f368968474f93;hp=5e1f5bf96f469c002ca866ba087baaf97440f957;hpb=dec23500d8988c22a99f049ef1d1e49328ba075a;p=akkoma
diff --git a/lib/pleroma/html.ex b/lib/pleroma/html.ex
index 5e1f5bf96..d1da746de 100644
--- a/lib/pleroma/html.ex
+++ b/lib/pleroma/html.ex
@@ -1,5 +1,5 @@
# Pleroma: A lightweight social networking server
-# Copyright © 2017-2018 Pleroma Authors
+# Copyright © 2017-2019 Pleroma Authors
# SPDX-License-Identifier: AGPL-3.0-only
defmodule Pleroma.HTML do
@@ -9,7 +9,7 @@ defmodule Pleroma.HTML do
defp get_scrubbers(scrubbers) when is_list(scrubbers), do: scrubbers
defp get_scrubbers(_), do: [Pleroma.HTML.Scrubber.Default]
- def get_scrubbers() do
+ def get_scrubbers do
Pleroma.Config.get([:markup, :scrub_policy])
|> get_scrubbers
end
@@ -27,6 +27,75 @@ defmodule Pleroma.HTML do
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 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 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
defmodule Pleroma.HTML.Scrubber.TwitterText do
@@ -36,21 +105,32 @@ defmodule Pleroma.HTML.Scrubber.TwitterText do
"""
@markup Application.get_env(:pleroma, :markup)
- @uri_schemes Application.get_env(:pleroma, :uri_schemes, [])
- @valid_schemes Keyword.get(@uri_schemes, :valid_schemes, [])
+ @valid_schemes Pleroma.Config.get([:uri_schemes, :valid_schemes], [])
require HtmlSanitizeEx.Scrubber.Meta
alias HtmlSanitizeEx.Scrubber.Meta
- def version do
- 0
- end
-
Meta.remove_cdata_sections_before_scrub()
Meta.strip_comments()
# links
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
@@ -58,6 +138,7 @@ 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
@@ -70,6 +151,7 @@ defmodule Pleroma.HTML.Scrubber.TwitterText do
Meta.allow_tag_with_these_attributes("img", [
"width",
"height",
+ "class",
"title",
"alt"
])
@@ -83,19 +165,32 @@ defmodule Pleroma.HTML.Scrubber.Default do
require HtmlSanitizeEx.Scrubber.Meta
alias HtmlSanitizeEx.Scrubber.Meta
-
- def version do
- 0
- end
+ # credo:disable-for-previous-line
+ # No idea how to fix this oneâ¦
@markup Application.get_env(:pleroma, :markup)
- @uri_schemes Application.get_env(:pleroma, :uri_schemes, [])
- @valid_schemes Keyword.get(@uri_schemes, :valid_schemes, [])
+ @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", "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"])
@@ -111,11 +206,13 @@ 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", [])
+ 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
@@ -125,6 +222,7 @@ defmodule Pleroma.HTML.Scrubber.Default do
Meta.allow_tag_with_these_attributes("img", [
"width",
"height",
+ "class",
"title",
"alt"
])
@@ -165,10 +263,6 @@ defmodule Pleroma.HTML.Transform.MediaProxy do
alias Pleroma.Web.MediaProxy
- def version do
- 0
- end
-
def before_scrub(html), do: html
def scrub_attribute("img", {"src", "http" <> target}) do