X-Git-Url: http://git.squeep.com/?a=blobdiff_plain;f=lib%2Fpleroma%2Fhtml.ex;h=2fae7281c46c30134ec89edf4adc10267539cd9f;hb=5329e84d62bbdf87a4b66e2ba9302a840802416f;hp=eb31f131eadfa6ba56ecac7f5573c6bed1e5e7ca;hpb=7e09c2bd7d4e22eff75037d8ac1252347a404aea;p=akkoma
diff --git a/lib/pleroma/html.ex b/lib/pleroma/html.ex
index eb31f131e..2fae7281c 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
@@ -28,20 +28,47 @@ defmodule Pleroma.HTML do
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) do
- key = "#{generate_scrubber_signature(scrubbers)}|#{object.id}"
- Cachex.fetch!(:scrubber_cache, key, fn _key -> ensure_scrubbed_html(content, scrubbers) end)
+ 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_object(content, object) do
- get_cached_scrubbed_html_for_object(content, HtmlSanitizeEx.Scrubber.StripTags, object)
+ 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
+ scrubbers,
+ fake,
+ callback
) do
- {:commit, 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
@@ -50,15 +77,23 @@ defmodule Pleroma.HTML do
defp generate_scrubber_signature(scrubbers) do
Enum.reduce(scrubbers, "", fn scrubber, signature ->
- # If a scrubber does not have a version(e.g HtmlSanitizeEx.Scrubber.StripTags) it is assumed it is always 0)
- version =
- if Kernel.function_exported?(scrubber, :version, 0) do
- scrubber.version
- else
- 0
- end
-
- "#{signature}#{to_string(scrubber)}#{version}"
+ "#{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
@@ -69,22 +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
@@ -92,18 +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"
])
@@ -117,19 +162,31 @@ defmodule Pleroma.HTML.Scrubber.Default do
require HtmlSanitizeEx.Scrubber.Meta
alias HtmlSanitizeEx.Scrubber.Meta
+ # credo:disable-for-previous-line
+ # No idea how to fix this oneâ¦
- 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, [])
+ @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"])
@@ -145,12 +202,14 @@ 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", [])
- @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.
@@ -159,14 +218,13 @@ 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", [])
@@ -175,9 +233,7 @@ 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", [])
@@ -185,9 +241,7 @@ 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
@@ -199,10 +253,6 @@ 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