diff options
| author | dcc <dcc@logografos.com> | 2023-09-02 00:52:52 -0700 |
|---|---|---|
| committer | dcc <dcc@logografos.com> | 2023-09-02 00:52:52 -0700 |
| commit | 3a4773c3c2bd0bbef244eb519b07208da9108e49 (patch) | |
| tree | 973567a6f3abb37bfb0f785b1cad14ed55840ef5 /priv/scrubbers | |
| download | anni-3a4773c3c2bd0bbef244eb519b07208da9108e49.tar.gz anni-3a4773c3c2bd0bbef244eb519b07208da9108e49.tar.bz2 anni-3a4773c3c2bd0bbef244eb519b07208da9108e49.zip | |
First
Diffstat (limited to 'priv/scrubbers')
| -rw-r--r-- | priv/scrubbers/default.ex | 106 | ||||
| -rw-r--r-- | priv/scrubbers/links_only.ex | 31 | ||||
| -rw-r--r-- | priv/scrubbers/media_proxy.ex | 36 | ||||
| -rw-r--r-- | priv/scrubbers/twitter_text.ex | 62 |
4 files changed, 235 insertions, 0 deletions
diff --git a/priv/scrubbers/default.ex b/priv/scrubbers/default.ex new file mode 100644 index 0000000..e10e3ec --- /dev/null +++ b/priv/scrubbers/default.ex @@ -0,0 +1,106 @@ +# Pleroma: A lightweight social networking server +# Copyright © 2017-2022 Pleroma Authors <https://pleroma.social/> +# SPDX-License-Identifier: AGPL-3.0-only + +defmodule Pleroma.HTML.Scrubber.Default do + @doc "The default HTML scrubbing policy: no " + + require FastSanitize.Sanitizer.Meta + alias FastSanitize.Sanitizer.Meta + + # credo:disable-for-previous-line + # No idea how to fix this one… + + @valid_schemes Pleroma.Config.get([:uri_schemes, :valid_schemes], []) + + 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"]) + + Meta.allow_tag_with_these_attributes(:b, []) + Meta.allow_tag_with_these_attributes(:blockquote, []) + Meta.allow_tag_with_these_attributes(:br, []) + Meta.allow_tag_with_these_attributes(:code, []) + Meta.allow_tag_with_these_attributes(:del, []) + Meta.allow_tag_with_these_attributes(:em, []) + Meta.allow_tag_with_these_attributes(:hr, []) + Meta.allow_tag_with_these_attributes(:i, []) + Meta.allow_tag_with_these_attributes(:li, []) + 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(:strong, []) + Meta.allow_tag_with_these_attributes(:sub, []) + Meta.allow_tag_with_these_attributes(:sup, []) + Meta.allow_tag_with_these_attributes(:ruby, []) + Meta.allow_tag_with_these_attributes(:rb, []) + Meta.allow_tag_with_these_attributes(:rp, []) + Meta.allow_tag_with_these_attributes(:rt, []) + Meta.allow_tag_with_these_attributes(:rtc, []) + 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", "recipients-inline"]) + Meta.allow_tag_with_these_attributes(:span, []) + + Meta.allow_tag_with_this_attribute_values(:code, "class", ["inline"]) + + @allow_inline_images Pleroma.Config.get([:markup, :allow_inline_images]) + + if @allow_inline_images do + Meta.allow_tag_with_this_attribute_values(:img, "class", ["emoji"]) + + # 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", + "title", + "alt" + ]) + end + + 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(:th, []) + Meta.allow_tag_with_these_attributes(:thead, []) + Meta.allow_tag_with_these_attributes(:tr, []) + end + + 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(:h4, []) + Meta.allow_tag_with_these_attributes(:h5, []) + end + + if Pleroma.Config.get([:markup, :allow_fonts]) do + Meta.allow_tag_with_these_attributes(:font, ["face"]) + end + + Meta.strip_everything_not_covered() +end diff --git a/priv/scrubbers/links_only.ex b/priv/scrubbers/links_only.ex new file mode 100644 index 0000000..7f434fb --- /dev/null +++ b/priv/scrubbers/links_only.ex @@ -0,0 +1,31 @@ +# Pleroma: A lightweight social networking server +# Copyright © 2017-2022 Pleroma Authors <https://pleroma.social/> +# SPDX-License-Identifier: AGPL-3.0-only + +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 FastSanitize.Sanitizer.Meta + alias FastSanitize.Sanitizer.Meta + + 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 diff --git a/priv/scrubbers/media_proxy.ex b/priv/scrubbers/media_proxy.ex new file mode 100644 index 0000000..9935b38 --- /dev/null +++ b/priv/scrubbers/media_proxy.ex @@ -0,0 +1,36 @@ +# Pleroma: A lightweight social networking server +# Copyright © 2017-2022 Pleroma Authors <https://pleroma.social/> +# SPDX-License-Identifier: AGPL-3.0-only + +defmodule Pleroma.HTML.Transform.MediaProxy do + @moduledoc "Transforms inline image URIs to use MediaProxy." + + alias Pleroma.Web.MediaProxy + + def before_scrub(html), do: html + + def scrub_attribute(:img, {"src", "http" <> target}) do + media_url = + ("http" <> target) + |> MediaProxy.url() + + {"src", media_url} + end + + def scrub_attribute(_tag, attribute), do: attribute + + def scrub({:img, attributes, children}) do + attributes = + attributes + |> Enum.map(fn attr -> scrub_attribute(:img, attr) end) + |> Enum.reject(&is_nil(&1)) + + {:img, attributes, children} + end + + def scrub({:comment, _text, _children}), do: "" + + def scrub({tag, attributes, children}), do: {tag, attributes, children} + def scrub({_tag, children}), do: children + def scrub(text), do: text +end diff --git a/priv/scrubbers/twitter_text.ex b/priv/scrubbers/twitter_text.ex new file mode 100644 index 0000000..6e23b3e --- /dev/null +++ b/priv/scrubbers/twitter_text.ex @@ -0,0 +1,62 @@ +# Pleroma: A lightweight social networking server +# Copyright © 2017-2022 Pleroma Authors <https://pleroma.social/> +# SPDX-License-Identifier: AGPL-3.0-only + +defmodule Pleroma.HTML.Scrubber.TwitterText do + @moduledoc """ + An HTML scrubbing policy which limits to twitter-style text. Only + paragraphs, breaks and links are allowed through the filter. + """ + + @valid_schemes Pleroma.Config.get([:uri_schemes, :valid_schemes], []) + + require FastSanitize.Sanitizer.Meta + alias FastSanitize.Sanitizer.Meta + + 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 + Meta.allow_tag_with_these_attributes(:br, []) + 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 + if Pleroma.Config.get([:markup, :allow_inline_images]) do + Meta.allow_tag_with_this_attribute_values(:img, "class", ["emoji"]) + + # 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", + "title", + "alt" + ]) + end + + Meta.strip_everything_not_covered() +end |
