tags
# span2div = Loofah::Scrubber.new do |node|
# node.name = "div" if node.name == "span"
# end
#
# Alternatively, this scrubber could have been implemented as:
#
# class Span2Div < Loofah::Scrubber
# def scrub(node)
# node.name = "div" if node.name == "span"
# end
# end
# span2div = Span2Div.new
#
# This can then be run on a document:
#
# Loofah.fragment("
foobar
").scrub!(span2div).to_s
# # => "
foo
bar
"
#
# Scrubbers can be run on a document in either a top-down traversal (the
# default) or bottom-up. Top-down scrubbers can optionally return
# Scrubber::STOP to terminate the traversal of a subtree.
#
# source://loofah//lib/loofah/scrubber.rb#34
class Loofah::Scrubber
# Options may include
# :direction => :top_down (the default)
# or
# :direction => :bottom_up
#
# For top_down traversals, if the block returns
# Loofah::Scrubber::STOP, then the traversal will be terminated
# for the current node's subtree.
#
# Alternatively, a Scrubber may inherit from Loofah::Scrubber,
# and implement +scrub+, which is slightly faster than using a
# block.
#
# @return [Scrubber] a new instance of Scrubber
#
# source://loofah//lib/loofah/scrubber.rb#65
def initialize(options = T.unsafe(nil), &block); end
# If the attribute is not set, add it
# If the attribute is set, don't overwrite the existing value
#
# source://loofah//lib/loofah/scrubber.rb#94
def append_attribute(node, attribute, value); end
# When a scrubber is initialized, the optional block is saved as
# :block. Note that, if no block is passed, then the +scrub+
# method is assumed to have been implemented.
#
# source://loofah//lib/loofah/scrubber.rb#49
def block; end
# When a scrubber is initialized, the :direction may be specified
# as :top_down (the default) or :bottom_up.
#
# source://loofah//lib/loofah/scrubber.rb#44
def direction; end
# When +new+ is not passed a block, the class may implement
# +scrub+, which will be called for each document node.
#
# @raise [ScrubberNotFound]
#
# source://loofah//lib/loofah/scrubber.rb#86
def scrub(node); end
# Calling +traverse+ will cause the document to be traversed by
# either the lambda passed to the initializer or the +scrub+
# method, in the direction specified at +new+ time.
#
# source://loofah//lib/loofah/scrubber.rb#78
def traverse(node); end
private
# source://loofah//lib/loofah/scrubber.rb#103
def html5lib_sanitize(node); end
# source://loofah//lib/loofah/scrubber.rb#129
def traverse_conditionally_bottom_up(node); end
# source://loofah//lib/loofah/scrubber.rb#120
def traverse_conditionally_top_down(node); end
end
# Top-down Scrubbers may return CONTINUE to indicate that the subtree should be traversed.
#
# source://loofah//lib/loofah/scrubber.rb#37
Loofah::Scrubber::CONTINUE = T.let(T.unsafe(nil), Object)
# Top-down Scrubbers may return STOP to indicate that the subtree should not be traversed.
#
# source://loofah//lib/loofah/scrubber.rb#40
Loofah::Scrubber::STOP = T.let(T.unsafe(nil), Object)
# A RuntimeError raised when Loofah could not find an appropriate scrubber.
#
# source://loofah//lib/loofah/scrubber.rb#6
class Loofah::ScrubberNotFound < ::RuntimeError; end
# Loofah provides some built-in scrubbers for sanitizing with
# HTML5lib's safelist and for accomplishing some common
# transformation tasks.
#
#
# === Loofah::Scrubbers::Strip / scrub!(:strip)
#
# +:strip+ removes unknown/unsafe tags, but leaves behind the pristine contents:
#
# unsafe_html = "ohai!
div is safe
but foo is not"
# Loofah.fragment(unsafe_html).scrub!(:strip)
# => "ohai!
div is safe
but foo is
not"
#
#
# === Loofah::Scrubbers::Prune / scrub!(:prune)
#
# +:prune+ removes unknown/unsafe tags and their contents (including their subtrees):
#
# unsafe_html = "ohai!
div is safe
but foo is not"
# Loofah.fragment(unsafe_html).scrub!(:prune)
# => "ohai!
div is safe
"
#
#
# === Loofah::Scrubbers::Escape / scrub!(:escape)
#
# +:escape+ performs HTML entity escaping on the unknown/unsafe tags:
#
# unsafe_html = "ohai!
div is safe
but foo is not"
# Loofah.fragment(unsafe_html).scrub!(:escape)
# => "ohai!
div is safe
<foo>but foo is <b>not</b></foo>"
#
#
# === Loofah::Scrubbers::Whitewash / scrub!(:whitewash)
#
# +:whitewash+ removes all comments, styling and attributes in
# addition to doing markup-fixer-uppery and pruning unsafe tags. I
# like to call this "whitewashing", since it's like putting a new
# layer of paint on top of the HTML input to make it look nice.
#
# messy_markup = "ohai!
div with attributes
"
# Loofah.fragment(messy_markup).scrub!(:whitewash)
# => "ohai!
div with attributes
"
#
# One use case for this scrubber is to clean up HTML that was
# cut-and-pasted from Microsoft Word into a WYSIWYG editor or a
# rich text editor. Microsoft's software is famous for injecting
# all kinds of cruft into its HTML output. Who needs that crap?
# Certainly not me.
#
#
# === Loofah::Scrubbers::NoFollow / scrub!(:nofollow)
#
# +:nofollow+ adds a rel="nofollow" attribute to all links
#
# link_farmers_markup = "ohai!
I like your blog post"
# Loofah.fragment(link_farmers_markup).scrub!(:nofollow)
# => "ohai!
I like your blog post"
#
#
# === Loofah::Scrubbers::NoOpener / scrub!(:noopener)
#
# +:noopener+ adds a rel="noopener" attribute to all links
#
# link_farmers_markup = "ohai!
I like your blog post"
# Loofah.fragment(link_farmers_markup).scrub!(:noopener)
# => "ohai!
I like your blog post"
#
#
# === Loofah::Scrubbers::Unprintable / scrub!(:unprintable)
#
# +:unprintable+ removes unprintable Unicode characters.
#
# markup = "
Some text with an unprintable character at the end\u2028
"
# Loofah.fragment(markup).scrub!(:unprintable)
# => "
Some text with an unprintable character at the end
"
#
# You may not be able to see the unprintable character in the above example, but there is a
# U+2028 character right before the closing tag. These characters can cause issues if
# the content is ever parsed by JavaScript - more information here:
#
# http://timelessrepo.com/json-isnt-a-javascript-subset
#
# source://loofah//lib/loofah/scrubbers.rb#86
module Loofah::Scrubbers
class << self
# Returns an array of symbols representing the built-in scrubbers
#
# source://loofah//lib/loofah/scrubbers.rb#295
def scrubber_symbols; end
end
end
# === scrub!(:escape)
#
# +:escape+ performs HTML entity escaping on the unknown/unsafe tags:
#
# unsafe_html = "ohai!
div is safe
but foo is not"
# Loofah.fragment(unsafe_html).scrub!(:escape)
# => "ohai!
div is safe
<foo>but foo is <b>not</b></foo>"
#
# source://loofah//lib/loofah/scrubbers.rb#139
class Loofah::Scrubbers::Escape < ::Loofah::Scrubber
# @return [Escape] a new instance of Escape
#
# source://loofah//lib/loofah/scrubbers.rb#140
def initialize; end
# source://loofah//lib/loofah/scrubbers.rb#144
def scrub(node); end
end
# A hash that maps a symbol (like +:prune+) to the appropriate Scrubber (Loofah::Scrubbers::Prune).
#
# source://loofah//lib/loofah/scrubbers.rb#281
Loofah::Scrubbers::MAP = T.let(T.unsafe(nil), Hash)
# This class probably isn't useful publicly, but is used for #to_text's current implemention
#
# source://loofah//lib/loofah/scrubbers.rb#233
class Loofah::Scrubbers::NewlineBlockElements < ::Loofah::Scrubber
# @return [NewlineBlockElements] a new instance of NewlineBlockElements
#
# source://loofah//lib/loofah/scrubbers.rb#234
def initialize; end
# source://loofah//lib/loofah/scrubbers.rb#238
def scrub(node); end
end
# === scrub!(:nofollow)
#
# +:nofollow+ adds a rel="nofollow" attribute to all links
#
# link_farmers_markup = "ohai!
I like your blog post"
# Loofah.fragment(link_farmers_markup).scrub!(:nofollow)
# => "ohai!
I like your blog post"
#
# source://loofah//lib/loofah/scrubbers.rb#199
class Loofah::Scrubbers::NoFollow < ::Loofah::Scrubber
# @return [NoFollow] a new instance of NoFollow
#
# source://loofah//lib/loofah/scrubbers.rb#200
def initialize; end
# source://loofah//lib/loofah/scrubbers.rb#204
def scrub(node); end
end
# === scrub!(:noopener)
#
# +:noopener+ adds a rel="noopener" attribute to all links
#
# link_farmers_markup = "ohai!
I like your blog post"
# Loofah.fragment(link_farmers_markup).scrub!(:noopener)
# => "ohai!
I like your blog post"
#
# source://loofah//lib/loofah/scrubbers.rb#220
class Loofah::Scrubbers::NoOpener < ::Loofah::Scrubber
# @return [NoOpener] a new instance of NoOpener
#
# source://loofah//lib/loofah/scrubbers.rb#221
def initialize; end
# source://loofah//lib/loofah/scrubbers.rb#225
def scrub(node); end
end
# === scrub!(:prune)
#
# +:prune+ removes unknown/unsafe tags and their contents (including their subtrees):
#
# unsafe_html = "ohai!
div is safe
but foo is not"
# Loofah.fragment(unsafe_html).scrub!(:prune)
# => "ohai!
div is safe
"
#
# source://loofah//lib/loofah/scrubbers.rb#118
class Loofah::Scrubbers::Prune < ::Loofah::Scrubber
# @return [Prune] a new instance of Prune
#
# source://loofah//lib/loofah/scrubbers.rb#119
def initialize; end
# source://loofah//lib/loofah/scrubbers.rb#123
def scrub(node); end
end
# === scrub!(:strip)
#
# +:strip+ removes unknown/unsafe tags, but leaves behind the pristine contents:
#
# unsafe_html = "ohai!
div is safe
but foo is not"
# Loofah.fragment(unsafe_html).scrub!(:strip)
# => "ohai!
div is safe
but foo is
not"
#
# source://loofah//lib/loofah/scrubbers.rb#96
class Loofah::Scrubbers::Strip < ::Loofah::Scrubber
# @return [Strip] a new instance of Strip
#
# source://loofah//lib/loofah/scrubbers.rb#97
def initialize; end
# source://loofah//lib/loofah/scrubbers.rb#101
def scrub(node); end
end
# === scrub!(:unprintable)
#
# +:unprintable+ removes unprintable Unicode characters.
#
# markup = "
Some text with an unprintable character at the end\u2028
"
# Loofah.fragment(markup).scrub!(:unprintable)
# => "
Some text with an unprintable character at the end
"
#
# You may not be able to see the unprintable character in the above example, but there is a
# U+2028 character right before the closing tag. These characters can cause issues if
# the content is ever parsed by JavaScript - more information here:
#
# http://timelessrepo.com/json-isnt-a-javascript-subset
#
# source://loofah//lib/loofah/scrubbers.rb#265
class Loofah::Scrubbers::Unprintable < ::Loofah::Scrubber
# @return [Unprintable] a new instance of Unprintable
#
# source://loofah//lib/loofah/scrubbers.rb#266
def initialize; end
# source://loofah//lib/loofah/scrubbers.rb#270
def scrub(node); end
end
# === scrub!(:whitewash)
#
# +:whitewash+ removes all comments, styling and attributes in
# addition to doing markup-fixer-uppery and pruning unsafe tags. I
# like to call this "whitewashing", since it's like putting a new
# layer of paint on top of the HTML input to make it look nice.
#
# messy_markup = "ohai!
div with attributes
"
# Loofah.fragment(messy_markup).scrub!(:whitewash)
# => "ohai!
div with attributes
"
#
# One use case for this scrubber is to clean up HTML that was
# cut-and-pasted from Microsoft Word into a WYSIWYG editor or a
# rich text editor. Microsoft's software is famous for injecting
# all kinds of cruft into its HTML output. Who needs that crap?
# Certainly not me.
#
# source://loofah//lib/loofah/scrubbers.rb#170
class Loofah::Scrubbers::Whitewash < ::Loofah::Scrubber
# @return [Whitewash] a new instance of Whitewash
#
# source://loofah//lib/loofah/scrubbers.rb#171
def initialize; end
# source://loofah//lib/loofah/scrubbers.rb#175
def scrub(node); end
end
# Overrides +text+ in HTML::Document and HTML::DocumentFragment,
# and mixes in +to_text+.
#
# source://loofah//lib/loofah/instance_methods.rb#73
module Loofah::TextBehavior
# Returns a plain-text version of the markup contained by the document,
# with HTML entities encoded.
#
# This method is significantly faster than #to_text, but isn't
# clever about whitespace around block elements.
#
# Loofah.document("
Title
Content
").text
# # => "TitleContent"
#
# By default, the returned text will have HTML entities
# escaped. If you want unescaped entities, and you understand
# that the result is unsafe to render in a browser, then you
# can pass an argument as shown:
#
# frag = Loofah.fragment("<script>alert('EVIL');</script>")
# # ok for browser:
# frag.text # => "<script>alert('EVIL');</script>"
# # decidedly not ok for browser:
# frag.text(:encode_special_chars => false) # => ""
#
# source://loofah//lib/loofah/instance_methods.rb#95
def inner_text(options = T.unsafe(nil)); end
# Returns a plain-text version of the markup contained by the document,
# with HTML entities encoded.
#
# This method is significantly faster than #to_text, but isn't
# clever about whitespace around block elements.
#
# Loofah.document("
Title
Content
").text
# # => "TitleContent"
#
# By default, the returned text will have HTML entities
# escaped. If you want unescaped entities, and you understand
# that the result is unsafe to render in a browser, then you
# can pass an argument as shown:
#
# frag = Loofah.fragment("<script>alert('EVIL');</script>")
# # ok for browser:
# frag.text # => "<script>alert('EVIL');</script>"
# # decidedly not ok for browser:
# frag.text(:encode_special_chars => false) # => ""
#
# source://loofah//lib/loofah/instance_methods.rb#95
def text(options = T.unsafe(nil)); end
# Returns a plain-text version of the markup contained by the document,
# with HTML entities encoded.
#
# This method is significantly faster than #to_text, but isn't
# clever about whitespace around block elements.
#
# Loofah.document("
Title
Content
").text
# # => "TitleContent"
#
# By default, the returned text will have HTML entities
# escaped. If you want unescaped entities, and you understand
# that the result is unsafe to render in a browser, then you
# can pass an argument as shown:
#
# frag = Loofah.fragment("<script>alert('EVIL');</script>")
# # ok for browser:
# frag.text # => "<script>alert('EVIL');</script>"
# # decidedly not ok for browser:
# frag.text(:encode_special_chars => false) # => ""
#
# source://loofah//lib/loofah/instance_methods.rb#95
def to_str(options = T.unsafe(nil)); end
# Returns a plain-text version of the markup contained by the
# fragment, with HTML entities encoded.
#
# This method is slower than #text, but is clever about
# whitespace around block elements and line break elements.
#
# Loofah.document("
Title
Content
Next line
").to_text
# # => "\nTitle\n\nContent\nNext line\n"
#
# source://loofah//lib/loofah/instance_methods.rb#121
def to_text(options = T.unsafe(nil)); end
end
# The version of Loofah you are using
#
# source://loofah//lib/loofah/version.rb#4
Loofah::VERSION = T.let(T.unsafe(nil), String)
# source://loofah//lib/loofah/xml/document.rb#3
module Loofah::XML; end
# Subclass of Nokogiri::XML::Document.
#
# See Loofah::ScrubBehavior and Loofah::DocumentDecorator for additional methods.
#
# source://loofah//lib/loofah/xml/document.rb#9
class Loofah::XML::Document < ::Nokogiri::XML::Document
include ::Loofah::ScrubBehavior::Node
include ::Loofah::DocumentDecorator
end
# Subclass of Nokogiri::XML::DocumentFragment.
#
# See Loofah::ScrubBehavior for additional methods.
#
# source://loofah//lib/loofah/xml/document_fragment.rb#9
class Loofah::XML::DocumentFragment < ::Nokogiri::XML::DocumentFragment
class << self
# Overridden Nokogiri::XML::DocumentFragment
# constructor. Applications should use Loofah.fragment to
# parse a fragment.
#
# source://loofah//lib/loofah/xml/document_fragment.rb#16
def parse(tags); end
end
end