'
+ # html = '
'
# # "
"
# doc = Nokogiri.HTML5(html)
# # raises ArgumentError: Attributes per element limit exceeded
+ #
# doc = Nokogiri.HTML5(html, max_attributes: -1)
+ # # parses successfully
+ #
+ # === Parse +noscript+ elements' content as text
+ #
+ # By default, the content of +noscript+ elements is parsed as HTML elements. Browsers that
+ # support scripting parse the content of +noscript+ elements as raw text.
+ #
+ # The +:parse_noscript_content_as_text+ option causes Nokogiri to parse the content of +noscript+
+ # elements as a single text node.
+ #
+ # html = ""
+ # doc = Nokogiri::HTML5.parse(html, parse_noscript_content_as_text: true)
+ # pp doc.at_xpath("/html/head/noscript")
+ # # => #(Element:0x878c {
+ # # name = "noscript",
+ # # children = [ #(Text "")]
+ # # })
+ #
+ # In contrast, parse_noscript_content_as_text: false (the default) causes the +noscript+
+ # element in the previous example to have two children, a +meta+ element and a +link+ element.
+ #
+ # doc = Nokogiri::HTML5.parse(html)
+ # puts doc.at_xpath("/html/head/noscript")
+ # # => #(Element:0x96b4 {
+ # # name = "noscript",
+ # # children = [
+ # # #(Element:0x97e0 { name = "meta", attribute_nodes = [ #(Attr:0x990c { name = "charset", value = "UTF-8" })] }),
+ # # #(Element:0x9b00 {
+ # # name = "link",
+ # # attribute_nodes = [
+ # # #(Attr:0x9c2c { name = "rel", value = "stylesheet" }),
+ # # #(Attr:0x9dd0 { name = "href", value = "!" })]
+ # # })]
+ # # })
#
# == HTML Serialization
#
- # After parsing HTML, it may be serialized using any of the {Nokogiri::XML::Node} serialization
- # methods. In particular, {XML::Node#serialize}, {XML::Node#to_html}, and {XML::Node#to_s} will
+ # After parsing HTML, it may be serialized using any of the Nokogiri::XML::Node serialization
+ # methods. In particular, XML::Node#serialize, XML::Node#to_html, and XML::Node#to_s will
# serialize a given node and its children. (This is the equivalent of JavaScript's
- # +Element.outerHTML+.) Similarly, {XML::Node#inner_html} will serialize the children of a given
+ # +Element.outerHTML+.) Similarly, XML::Node#inner_html will serialize the children of a given
# node. (This is the equivalent of JavaScript's +Element.innerHTML+.)
#
# doc = Nokogiri::HTML5("Hello world!")
@@ -154,12 +190,12 @@ def self.HTML5(input, url = nil, encoding = nil, **options, &block)
# # => Hello world!
#
# Due to quirks in how HTML is parsed and serialized, it's possible for a DOM tree to be
- # serialized and then re-parsed, resulting in a different DOM. Mostly, this happens with DOMs
+ # serialized and then re-parsed, resulting in a different DOM. Mostly, this happens with DOMs
# produced from invalid HTML. Unfortunately, even valid HTML may not survive serialization and
# re-parsing.
#
- # In particular, a newline at the start of +pre+, +listing+, and +textarea+ elements is ignored by
- # the parser.
+ # In particular, a newline at the start of +pre+, +listing+, and +textarea+
+ # elements is ignored by the parser.
#
# doc = Nokogiri::HTML5(<<-EOF)
#
@@ -188,54 +224,54 @@ def self.HTML5(input, url = nil, encoding = nil, **options, &block)
#
# == Encodings
#
- # Nokogiri always parses HTML5 using {https://en.wikipedia.org/wiki/UTF-8 UTF-8}; however, the
+ # Nokogiri always parses HTML5 using {UTF-8}[https://en.wikipedia.org/wiki/UTF-8]; however, the
# encoding of the input can be explicitly selected via the optional +encoding+ parameter. This is
# most useful when the input comes not from a string but from an IO object.
#
# When serializing a document or node, the encoding of the output string can be specified via the
# +:encoding+ options. Characters that cannot be encoded in the selected encoding will be encoded
- # as {https://en.wikipedia.org/wiki/List_of_XML_and_HTML_character_entity_references HTML numeric
- # entities}.
+ # as {HTML numeric
+ # entities}[https://en.wikipedia.org/wiki/List_of_XML_and_HTML_character_entity_references].
#
# frag = Nokogiri::HTML5.fragment('아는 길도 물어가라')
# html = frag.serialize(encoding: 'US-ASCII')
# puts html
# # => 아는 길도 물어가라
+ #
# frag = Nokogiri::HTML5.fragment(html)
# puts frag.serialize
# # => 아는 길도 물어가라
#
- # (There's a {https://bugs.ruby-lang.org/issues/15033 bug} in all current versions of Ruby that
+ # (There's a {bug}[https://bugs.ruby-lang.org/issues/15033] in all current versions of Ruby that
# can cause the entity encoding to fail. Of the mandated supported encodings for HTML, the only
# encoding I'm aware of that has this bug is 'ISO-2022-JP'. We recommend avoiding this
# encoding.)
#
# == Notes
#
- # * The {Nokogiri::HTML5.fragment} function takes a string and parses it
- # as a HTML5 document. The ++, ++, and ++ elements are
- # removed from this document, and any children of these elements that remain
- # are returned as a {Nokogiri::HTML5::DocumentFragment}.
+ # * The Nokogiri::HTML5.fragment function takes a string and parses it as a HTML5 document. The
+ # +html+, +head+, and +body+ elements are removed from this document, and any children of these
+ # elements that remain are returned as a Nokogiri::HTML5::DocumentFragment.
#
- # * The {Nokogiri::HTML5.parse} function takes a string and passes it to the
- # ![]()
isn't allowed in noscript so the noscript element is popped off
+ # the stack of open elements and the token is reprocessed in `head`
+ # which causes the `head` element to be popped off the stack of open
+ # elements and a `body` element to be inserted. Then the `img` element is
+ # inserted in the body.
+ html = "
"
+ doc = Nokogiri::HTML5(html, parse_noscript_content_as_text: false, max_errors: 100)
+ noscript = doc.at("/html/head/noscript")
+ assert_equal(3, doc.errors.length, doc.errors.join("\n"))
+ # Start tag 'img' isn't allowed here
+ # End tag 'noscript' isn't allowed here
+ # End tag head isn't allowed here
+ assert_empty(noscript.children)
+ img = doc.at("/html/body/img")
+ refute_nil(img)
+ end
+
+ def test_parse_noscript_as_text_in_head
+ # In contrast to the previous test, when the scripting flag is enabled, the content
+ # of the noscript element is parsed as raw text.
+ html = ""
+ doc = Nokogiri::HTML5(html, parse_noscript_content_as_text: true, max_errors: 100)
+ noscript = doc.at("/html/head/noscript")
+ assert_empty(doc.errors)
+ assert_equal(1, noscript.children.length)
+ assert_kind_of(Nokogiri::XML::Text, noscript.children.first)
+ end
+
+ def test_parse_noscript_as_elements_in_body
+ html = ""
+ doc = Nokogiri::HTML5(html, parse_noscript_content_as_text: false, max_errors: 100)
+ assert_empty(doc.errors)
+ img = doc.at("/html/body/noscript/img")
+ refute_nil(img)
+ end
+
+ def test_parse_noscript_as_text_in_body
+ html = ""
+ doc = Nokogiri::HTML5(html, parse_noscript_content_as_text: true, max_errors: 100)
+ noscript = doc.at("/html/body/noscript")
+ assert_empty(doc.errors, doc.errors.join("\n"))
+ assert_equal(1, noscript.children.length)
+ assert_kind_of(Nokogiri::XML::Text, noscript.children.first)
+ end
+
+ def test_parse_noscript_fragment_as_elements
+ html = ""
+ frag = Nokogiri::HTML5::DocumentFragment.new(Nokogiri::HTML5::Document.new, html, "noscript", parse_noscript_content_as_text: false, max_errors: 100)
+ assert_empty(frag.errors)
+ assert_equal(2, frag.children.length)
+ end
+
+ def test_parse_noscript_fragment_as_text
+ html = ""
+ frag = Nokogiri::HTML5::DocumentFragment.new(Nokogiri::HTML5::Document.new, html, "noscript", parse_noscript_content_as_text: true, max_errors: 100)
+ assert_empty(frag.errors)
+ assert_equal(1, frag.children.length)
+ assert_kind_of(Nokogiri::XML::Text, frag.children.first)
+ end
+
+ def test_parse_noscript_content_default
+ html = ""
+ doc = Nokogiri::HTML5(html, max_errors: 100)
+ assert_empty(doc.errors)
+ img = doc.at("/html/body/noscript/img")
+ refute_nil(img)
+ end
+
["pre", "listing", "textarea"].each do |tag|
define_method("test_serialize_preserve_newline_#{tag}".to_sym) do
doc = Nokogiri::HTML5("<#{tag}>\n\nContent")
diff --git a/test/html5/test_tree_construction.rb b/test/html5/test_tree_construction.rb
index 7e01be866c8..1e321b3ecaa 100644
--- a/test/html5/test_tree_construction.rb
+++ b/test/html5/test_tree_construction.rb
@@ -70,6 +70,11 @@ def compare_nodes(node, ng_node)
end
def run_test
+ options = {
+ max_errors: -1,
+ parse_noscript_content_as_text: @test[:script] == :on,
+ }
+
if @test[:context]
# this is a fragment test
if @test_context_node
@@ -85,15 +90,15 @@ def run_test
doc = Nokogiri::HTML5::Document.new
context_node = doc.create_element(@test[:context].first)
end
- doc = Nokogiri::HTML5::DocumentFragment.new(doc, @test[:data], context_node, max_errors: @test[:errors].length + 10)
+ doc = Nokogiri::HTML5::DocumentFragment.new(doc, @test[:data], context_node, **options)
else
# run the test using a tag name
ctx = @test[:context].join(":")
doc = Nokogiri::HTML5::Document.new
- doc = Nokogiri::HTML5::DocumentFragment.new(doc, @test[:data], ctx, max_errors: @test[:errors].length + 10)
+ doc = Nokogiri::HTML5::DocumentFragment.new(doc, @test[:data], ctx, **options)
end
else
- doc = Nokogiri::HTML5.parse(@test[:data], max_errors: @test[:errors].length + 10)
+ doc = Nokogiri::HTML5.parse(@test[:data], **options)
end
# Walk the tree.
exp_nodes = [@test[:document]]
@@ -161,7 +166,7 @@ module Html5libTestCaseParser
class BadHtml5libFormat < RuntimeError; end
def self.parse_test(test_data)
- test = { script: :both }
+ test = { script: :off }
index = /(?:^#errors\n|\n#errors\n)/ =~ test_data
raise(BadHtml5libFormat, "Expected #errors in\n#{test_data}") if index.nil?
@@ -323,8 +328,6 @@ def self.generate_tests
klass = Class.new(TestHtml5TreeConstructionBase) do
tests.each_with_index do |test, index|
- next if test[:script] == :on
-
define_method "test_#{index}" do
@test = test
@index = index
gumbo_parse_with_options method, using the default options.
- # The resulting Gumbo parse tree is then walked.
+ # * The Nokogiri::HTML5.parse function takes a string and passes it to the
+ # gumbo_parse_with_options method, using the default options. The resulting Gumbo
+ # parse tree is then walked.
#
# * Instead of uppercase element names, lowercase element names are produced.
#
- # * Instead of returning +unknown+ as the element name for unknown tags, the
- # original tag name is returned verbatim.
+ # * Instead of returning +unknown+ as the element name for unknown tags, the original tag name is
+ # returned verbatim.
#
# Since v1.12.0
module HTML5
class << self
- # Parse an HTML 5 document. Convenience method for {Nokogiri::HTML5::Document.parse}
+ # Parse an HTML 5 document. Convenience method for Nokogiri::HTML5::Document.parse
def parse(string, url = nil, encoding = nil, **options, &block)
Document.parse(string, url, encoding, **options, &block)
end
# Parse a fragment from +string+. Convenience method for
- # {Nokogiri::HTML5::DocumentFragment.parse}.
+ # Nokogiri::HTML5::DocumentFragment.parse.
def fragment(string, encoding = nil, **options)
DocumentFragment.parse(string, encoding, options)
end
@@ -268,11 +304,11 @@ def read_and_encode(string, encoding)
private
# Charset sniffing is a complex and controversial topic that understandably isn't done _by
- # default_ by the Ruby Net::HTTP library. This being said, it is a very real problem for
+ # default_ by the Ruby Net::HTTP library. This being said, it is a very real problem for
# consumers of HTML as the default for HTML is iso-8859-1, most "good" producers use utf-8, and
# the Gumbo parser *only* supports utf-8.
#
- # Accordingly, Nokogiri::HTML4::Document.parse provides limited encoding detection. Following
+ # Accordingly, Nokogiri::HTML4::Document.parse provides limited encoding detection. Following
# this lead, Nokogiri::HTML5 attempts to do likewise, while attempting to more closely follow
# the HTML5 standard.
#
diff --git a/test/html5/test_api.rb b/test/html5/test_api.rb
index 926fa8a4dc0..93c5fb7783e 100644
--- a/test/html5/test_api.rb
+++ b/test/html5/test_api.rb
@@ -104,6 +104,75 @@ def test_serialization_encoding
assert_match("ฉันไม่พูดภาษาไทย", html2)
end
+ def test_parse_noscript_as_elements_in_head
+ #