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 \\ "") do
+ 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 ->
- ensure_scrubbed_html(content, scrubbers, activity.data["object"]["fake"] || false)
+ object = Pleroma.Object.normalize(activity)
+ ensure_scrubbed_html(content, scrubbers, object.data["fake"] || false, callback)
end)
end
content,
HtmlSanitizeEx.Scrubber.StripTags,
activity,
- key
+ key,
+ &HtmlEntities.decode/1
)
end
def ensure_scrubbed_html(
content,
scrubbers,
- false = _fake
+ fake,
+ callback
) do
- {:commit, filter_tags(content, scrubbers)}
- end
-
- def ensure_scrubbed_html(
- content,
- scrubbers,
- true = _fake
- ) do
- {:ignore, filter_tags(content, scrubbers)}
+ 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
Cachex.fetch!(:scrubber_cache, key, fn _key ->
result =
content
- |> Floki.filter_out("a.mention")
+ |> Floki.filter_out("a.mention,a.hashtag,a[rel~=\"tag\"]")
|> Floki.attribute("a", "href")
|> Enum.at(0)
paragraphs, breaks and links are allowed through the filter.
"""
- @markup Application.get_env(:pleroma, :markup)
@valid_schemes Pleroma.Config.get([:uri_schemes, :valid_schemes], [])
require HtmlSanitizeEx.Scrubber.Meta
# links
Meta.allow_tag_with_uri_attributes("a", ["href", "data-user", "data-tag"], @valid_schemes)
- Meta.allow_tag_with_these_attributes("a", ["name", "title", "class"])
+
+ 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",
"noreferrer"
])
+ Meta.allow_tag_with_these_attributes("a", ["name", "title"])
+
# 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", ["class"])
+ Meta.allow_tag_with_this_attribute_values("span", "class", ["h-card"])
+ Meta.allow_tag_with_these_attributes("span", [])
# allow inline images for custom emoji
- @allow_inline_images Keyword.get(@markup, :allow_inline_images)
-
- if @allow_inline_images do
+ if Pleroma.Config.get([:markup, :allow_inline_images]) do
# restrict img tags to http/https only, because of MediaProxy.
Meta.allow_tag_with_uri_attributes("img", ["src"], ["http", "https"])
Meta.allow_tag_with_these_attributes("img", [
"width",
"height",
+ "class",
"title",
"alt"
])
# credo:disable-for-previous-line
# No idea how to fix this oneā¦
- @markup Application.get_env(:pleroma, :markup)
@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", "class"])
+
+ 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",
"noreferrer"
])
+ Meta.allow_tag_with_these_attributes("a", ["name", "title"])
+
Meta.allow_tag_with_these_attributes("abbr", ["title"])
Meta.allow_tag_with_these_attributes("b", [])
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", ["class"])
Meta.allow_tag_with_these_attributes("strong", [])
+ Meta.allow_tag_with_these_attributes("sub", [])
+ Meta.allow_tag_with_these_attributes("sup", [])
Meta.allow_tag_with_these_attributes("u", [])
Meta.allow_tag_with_these_attributes("ul", [])
- @allow_inline_images Keyword.get(@markup, :allow_inline_images)
+ Meta.allow_tag_with_this_attribute_values("span", "class", ["h-card"])
+ Meta.allow_tag_with_these_attributes("span", [])
+
+ @allow_inline_images Pleroma.Config.get([:markup, :allow_inline_images])
if @allow_inline_images do
# restrict img tags to http/https only, because of MediaProxy.
Meta.allow_tag_with_these_attributes("img", [
"width",
"height",
+ "class",
"title",
"alt"
])
end
- @allow_tables Keyword.get(@markup, :allow_tables)
-
- if @allow_tables do
+ if Pleroma.Config.get([:markup, :allow_tables]) do
Meta.allow_tag_with_these_attributes("table", [])
Meta.allow_tag_with_these_attributes("tbody", [])
Meta.allow_tag_with_these_attributes("td", [])
Meta.allow_tag_with_these_attributes("tr", [])
end
- @allow_headings Keyword.get(@markup, :allow_headings)
-
- if @allow_headings do
+ if Pleroma.Config.get([:markup, :allow_headings]) do
Meta.allow_tag_with_these_attributes("h1", [])
Meta.allow_tag_with_these_attributes("h2", [])
Meta.allow_tag_with_these_attributes("h3", [])
Meta.allow_tag_with_these_attributes("h5", [])
end
- @allow_fonts Keyword.get(@markup, :allow_fonts)
-
- if @allow_fonts do
+ if Pleroma.Config.get([:markup, :allow_fonts]) do
Meta.allow_tag_with_these_attributes("font", ["face"])
end
def scrub({_tag, children}), do: children
def scrub(text), do: text
end
+
+defmodule Pleroma.HTML.Scrubber.LinksOnly do
+ @moduledoc """
+ An HTML scrubbing policy which limits to links only.
+ """
+
+ @valid_schemes Pleroma.Config.get([:uri_schemes, :valid_schemes], [])
+
+ require HtmlSanitizeEx.Scrubber.Meta
+ alias HtmlSanitizeEx.Scrubber.Meta
+
+ Meta.remove_cdata_sections_before_scrub()
+ Meta.strip_comments()
+
+ # links
+ Meta.allow_tag_with_uri_attributes("a", ["href"], @valid_schemes)
+
+ Meta.allow_tag_with_this_attribute_values("a", "rel", [
+ "tag",
+ "nofollow",
+ "noopener",
+ "noreferrer",
+ "me"
+ ])
+
+ Meta.allow_tag_with_these_attributes("a", ["name", "title"])
+ Meta.strip_everything_not_covered()
+end