X-Git-Url: http://git.squeep.com/?a=blobdiff_plain;f=lib%2Fpleroma%2Fhtml.ex;h=937bafed53ac8a1a574c7ca6668a0b041a1ca8f0;hb=743b622b7b59148525d0f941de3a7c4af7825d22;hp=f363ed85c704ec82006db756ba4ad6e914f31a4b;hpb=62af23bd26d370ecc38159a8a3803562514596f4;p=akkoma
diff --git a/lib/pleroma/html.ex b/lib/pleroma/html.ex
index f363ed85c..937bafed5 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
@@ -9,14 +9,17 @@ 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, nil) do
- get_scrubbers()
- |> Enum.reduce(html, fn scrubber, html ->
+ filter_tags(html, get_scrubbers())
+ end
+
+ def filter_tags(html, scrubbers) when is_list(scrubbers) do
+ Enum.reduce(scrubbers, html, fn scrubber, html ->
filter_tags(html, scrubber)
end)
end
@@ -24,6 +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,a.hashtag,a[rel~=\"tag\"]")
+ |> Floki.attribute("a", "href")
+ |> Enum.at(0)
+
+ {:commit, {:ok, result}}
+ end)
+ end
end
defmodule Pleroma.HTML.Scrubber.TwitterText do
@@ -32,19 +104,32 @@ defmodule Pleroma.HTML.Scrubber.TwitterText do
paragraphs, breaks and links are allowed through the filter.
"""
- @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
@@ -52,18 +137,18 @@ 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
- @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"
])
@@ -77,15 +162,32 @@ defmodule Pleroma.HTML.Scrubber.Default do
require HtmlSanitizeEx.Scrubber.Meta
alias HtmlSanitizeEx.Scrubber.Meta
- def version do 0 end
- @markup Application.get_env(:pleroma, :markup)
- @uri_schemes Application.get_env(:pleroma, :uri_schemes, [])
- @valid_schemes Keyword.get(@uri_schemes, :valid_schemes, [])
+ # credo:disable-for-previous-line
+ # No idea how to fix this oneâ¦
+
+ @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",
+ "ugc"
+ ])
+
Meta.allow_tag_with_these_attributes("a", ["name", "title"])
Meta.allow_tag_with_these_attributes("abbr", ["title"])
@@ -101,12 +203,16 @@ 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("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.
@@ -115,14 +221,13 @@ defmodule Pleroma.HTML.Scrubber.Default do
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", [])
@@ -131,9 +236,7 @@ defmodule Pleroma.HTML.Scrubber.Default do
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", [])
@@ -141,9 +244,7 @@ defmodule Pleroma.HTML.Scrubber.Default do
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
@@ -154,8 +255,7 @@ defmodule Pleroma.HTML.Transform.MediaProxy do
@moduledoc "Transforms inline image URIs to use MediaProxy."
alias Pleroma.Web.MediaProxy
-
- def version do 0 end
+
def before_scrub(html), do: html
def scrub_attribute("img", {"src", "http" <> target}) do
@@ -183,3 +283,32 @@ defmodule Pleroma.HTML.Transform.MediaProxy do
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",
+ "ugc"
+ ])
+
+ Meta.allow_tag_with_these_attributes("a", ["name", "title"])
+ Meta.strip_everything_not_covered()
+end