Pleroma/lib/pleroma/html.ex

186 lines
5.3 KiB
Elixir
Raw Normal View History

# Pleroma: A lightweight social networking server
# Copyright © 2017-2018 Pleroma Authors <https://pleroma.social/>
# SPDX-License-Identifier: AGPL-3.0-only
defmodule Pleroma.HTML do
alias HtmlSanitizeEx.Scrubber
def filter_tags(html, scrubbers) when is_list(scrubbers) do
Enum.reduce(scrubbers, html, fn scrubber, html ->
filter_tags(html, scrubber)
end)
end
2018-12-14 10:41:55 +01:00
def filter_tags(html, scrubber), do: Scrubber.scrub(html, scrubber)
def filter_tags(html), do: filter_tags(html, nil)
2018-12-14 10:41:55 +01:00
def strip_tags(html), do: Scrubber.scrub(html, Scrubber.StripTags)
end
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.
"""
@markup Application.get_env(:pleroma, :markup)
@uri_schemes Application.get_env(:pleroma, :uri_schemes, [])
@valid_schemes Keyword.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
2018-12-05 21:44:56 +01:00
Meta.allow_tag_with_uri_attributes("a", ["href", "data-user", "data-tag"], @valid_schemes)
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", [])
# allow inline images for custom emoji
@allow_inline_images Keyword.get(@markup, :allow_inline_images)
if @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",
"title",
"alt"
])
end
Meta.strip_everything_not_covered()
end
defmodule Pleroma.HTML.Scrubber.Default do
@doc "The default HTML scrubbing policy: no "
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, [])
Meta.remove_cdata_sections_before_scrub()
Meta.strip_comments()
2018-12-05 20:35:41 +01:00
Meta.allow_tag_with_uri_attributes("a", ["href", "data-user", "data-tag"], @valid_schemes)
Meta.allow_tag_with_these_attributes("a", ["name", "title"])
2018-10-30 22:40:06 +01:00
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("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("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)
if @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",
"title",
"alt"
])
end
@allow_tables Keyword.get(@markup, :allow_tables)
if @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
@allow_headings Keyword.get(@markup, :allow_headings)
if @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
@allow_fonts Keyword.get(@markup, :allow_fonts)
if @allow_fonts do
Meta.allow_tag_with_these_attributes("font", ["face"])
end
Meta.strip_everything_not_covered()
end
defmodule Pleroma.HTML.Transform.MediaProxy do
@moduledoc "Transforms inline image URIs to use MediaProxy."
def version do
0
end
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
2018-12-09 10:12:48 +01:00
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
2018-12-09 10:12:48 +01:00
def scrub({:comment, _children}), do: ""
def scrub({tag, attributes, children}), do: {tag, attributes, children}
2018-12-09 10:12:48 +01:00
def scrub({_tag, children}), do: children
def scrub(text), do: text
end