# Pleroma: A lightweight social networking server
-# Copyright © 2017-2018 Pleroma Authors <https://pleroma.social/>
+# Copyright © 2017-2019 Pleroma Authors <https://pleroma.social/>
# SPDX-License-Identifier: AGPL-3.0-only
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
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 get_cached_stripped_html_for_object(content, object, module) do
+ get_cached_scrubbed_html_for_object(
+ content,
+ HtmlSanitizeEx.Scrubber.StripTags,
+ object,
+ module
+ )
+ end
+
+ 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(_, 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
"""
@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_these_attributes("a", ["name", "title"])
+ 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
@allow_inline_images Keyword.get(@markup, :allow_inline_images)
require HtmlSanitizeEx.Scrubber.Meta
alias HtmlSanitizeEx.Scrubber.Meta
-
- def version do
- 0
- end
+ # credo:disable-for-previous-line
+ # No idea how to fix this one…
@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_these_attributes("a", ["name", "title"])
+ Meta.allow_tag_with_these_attributes("a", ["name", "title", "class"])
Meta.allow_tag_with_these_attributes("abbr", ["title"])
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", [])
alias Pleroma.Web.MediaProxy
- def version do
- 0
- end
-
def before_scrub(html), do: html
def scrub_attribute("img", {"src", "http" <> target}) do