nokogiri 1.16.8-x86_64-linux → 1.17.0-x86_64-linux

data/lib/nokogiri/html5/document_fragment.rb

@@ -25,27 +25,145 @@ module Nokogiri
     #
     # 💡 HTML5 functionality is not available when running JRuby.
     class DocumentFragment < Nokogiri::HTML4::DocumentFragment
+      class << self
+        # :call-seq:
+        #   parse(input, **options) → HTML5::DocumentFragment
+        #
+        # Parse \HTML5 fragment input from a String, and return a new HTML5::DocumentFragment. This
+        # method creates a new, empty HTML5::Document to contain the fragment.
+        #
+        # [Parameters]
+        # - +input+ (String | IO) The HTML5 document fragment to parse.
+        #
+        # [Optional Keyword Arguments]
+        # - +encoding:+ (String | Encoding) The encoding, or name of the encoding, that should be
+        #   used when processing the document. When not provided, the encoding will be determined
+        #   based on the document content. Also see Nokogiri::HTML5 for a longer explanation of how
+        #   encoding is handled by the parser.
+        #
+        # - +context:+ (String | Nokogiri::XML::Node) The node, or the name of an HTML5 element, "in
+        #   context" of which to parse the document fragment. See below for more
+        #   information. (default +"body"+)
+        #
+        # - +max_errors:+ (Integer) The maximum number of parse errors to record. (default
+        #   +Nokogiri::Gumbo::DEFAULT_MAX_ERRORS+ which is currently 0)
+        #
+        # - +max_tree_depth:+ (Integer) The maximum depth of the parse tree. (default
+        #   +Nokogiri::Gumbo::DEFAULT_MAX_TREE_DEPTH+)
+        #
+        # - +max_attributes:+ (Integer) The maximum number of attributes allowed on an
+        #   element. (default +Nokogiri::Gumbo::DEFAULT_MAX_ATTRIBUTES+)
+        #
+        # - +parse_noscript_content_as_text:+ (Boolean) Whether to parse the content of +noscript+
+        #   elements as text. (default +false+)
+        #
+        # See rdoc-ref:HTML5@Parsing+options for a complete description of these parsing options.
+        #
+        # [Returns] Nokogiri::HTML5::DocumentFragment
+        #
+        # === Context \Node
+        #
+        # If a context node is specified using +context:+, then the parser will behave as if that
+        # Node, or a hypothetical tag named as specified, is the parent of the fragment subtree.
+        #
+        def parse(
+          input,
+          encoding_ = nil, positional_options_hash = nil,
+          encoding: encoding_, **options
+        )
+          unless positional_options_hash.nil? || positional_options_hash.empty?
+            options.merge!(positional_options_hash)
+          end
+
+          context = options.delete(:context)
+
+          document = HTML5::Document.new
+          document.encoding = "UTF-8"
+          input = HTML5.read_and_encode(input, encoding)
+
+          new(document, input, context, options)
+        end
+      end
+
       attr_accessor :document
       attr_accessor :errors
 
       # Get the parser's quirks mode value. See HTML5::QuirksMode.
       #
-      # This method returns `nil` if the parser was not invoked (e.g., `Nokogiri::HTML5::DocumentFragment.new(doc)`).
+      # This method returns `nil` if the parser was not invoked (e.g.,
+      # `Nokogiri::HTML5::DocumentFragment.new(doc)`).
       #
       # Since v1.14.0
       attr_reader :quirks_mode
 
-      # Create a document fragment.
-      def initialize(doc, tags = nil, ctx = nil, options = {}) # rubocop:disable Lint/MissingSuper
-        self.document = doc
-        self.errors = []
-        return self unless tags
-
-        max_attributes = options[:max_attributes] || Nokogiri::Gumbo::DEFAULT_MAX_ATTRIBUTES
-        max_errors = options[:max_errors] || Nokogiri::Gumbo::DEFAULT_MAX_ERRORS
-        max_depth = options[:max_tree_depth] || Nokogiri::Gumbo::DEFAULT_MAX_TREE_DEPTH
-        tags = Nokogiri::HTML5.read_and_encode(tags, nil)
-        Nokogiri::Gumbo.fragment(self, tags, ctx, max_attributes, max_errors, max_depth)
+      #
+      # :call-seq:
+      #   new(document, input, **options) → HTML5::DocumentFragment
+      #
+      # Parse \HTML5 fragment input from a String, and return a new HTML5::DocumentFragment.
+      #
+      # 💡 It's recommended to use either HTML5::DocumentFragment.parse or HTML5::Node#fragment
+      # rather than call this method directly.
+      #
+      # [Required Parameters]
+      # - +document+ (HTML5::Document) The parent document to associate the returned fragment with.
+      #
+      # [Optional Parameters]
+      # - +input+ (String) The content to be parsed.
+      #
+      # [Optional Keyword Arguments]
+      # - +encoding:+ (String | Encoding) The encoding, or name of the encoding, that should be
+      #   used when processing the document. When not provided, the encoding will be determined
+      #   based on the document content. Also see Nokogiri::HTML5 for a longer explanation of how
+      #   encoding is handled by the parser.
+      #
+      # - +context:+ (String | Nokogiri::XML::Node) The node, or the name of an HTML5 element, in
+      #   which to parse the document fragment. (default +"body"+)
+      #
+      # - +max_errors:+ (Integer) The maximum number of parse errors to record. (default
+      #   +Nokogiri::Gumbo::DEFAULT_MAX_ERRORS+ which is currently 0)
+      #
+      # - +max_tree_depth:+ (Integer) The maximum depth of the parse tree. (default
+      #   +Nokogiri::Gumbo::DEFAULT_MAX_TREE_DEPTH+)
+      #
+      # - +max_attributes:+ (Integer) The maximum number of attributes allowed on an
+      #   element. (default +Nokogiri::Gumbo::DEFAULT_MAX_ATTRIBUTES+)
+      #
+      # - +parse_noscript_content_as_text:+ (Boolean) Whether to parse the content of +noscript+
+      #   elements as text. (default +false+)
+      #
+      # See rdoc-ref:HTML5@Parsing+options for a complete description of these parsing options.
+      #
+      # [Returns] HTML5::DocumentFragment
+      #
+      # === Context \Node
+      #
+      # If a context node is specified using +context:+, then the parser will behave as if that
+      # Node, or a hypothetical tag named as specified, is the parent of the fragment subtree.
+      #
+      def initialize(
+        doc, input = nil,
+        context_ = nil, positional_options_hash = nil,
+        context: context_,
+        **options
+      ) # rubocop:disable Lint/MissingSuper
+        unless positional_options_hash.nil? || positional_options_hash.empty?
+          options.merge!(positional_options_hash)
+        end
+
+        @document = doc
+        @errors = []
+        return self unless input
+
+        input = Nokogiri::HTML5.read_and_encode(input, nil)
+
+        context = options.delete(:context) if options.key?(:context)
+
+        options[:max_attributes] ||= Nokogiri::Gumbo::DEFAULT_MAX_ATTRIBUTES
+        options[:max_errors] ||= options.delete(:max_parse_errors) || Nokogiri::Gumbo::DEFAULT_MAX_ERRORS
+        options[:max_tree_depth] ||= Nokogiri::Gumbo::DEFAULT_MAX_TREE_DEPTH
+
+        Nokogiri::Gumbo.fragment(self, input, context, **options)
       end
 
       def serialize(options = {}, &block) # :nodoc:
@@ -54,14 +172,6 @@ module Nokogiri
         XML::Node.instance_method(:serialize).bind_call(self, options, &block)
       end
 
-      # Parse a document fragment from +tags+, returning a Nodeset.
-      def self.parse(tags, encoding = nil, options = {})
-        doc = HTML5::Document.new
-        tags = HTML5.read_and_encode(tags, encoding)
-        doc.encoding = "UTF-8"
-        new(doc, tags, nil, options)
-      end
-
       def extract_params(params) # :nodoc:
         handler = params.find do |param|
           ![Hash, String, Symbol].include?(param.class)

data/lib/nokogiri/html5/node.rb

@@ -29,7 +29,7 @@ module Nokogiri
     # 💡 HTML5 functionality is not available when running JRuby.
     module Node
       def inner_html(options = {})
-        return super(options) unless document.is_a?(HTML5::Document)
+        return super unless document.is_a?(HTML5::Document)
 
         result = options[:preserve_newline] && prepend_newline? ? +"\n" : +""
         result << children.map { |child| child.to_html(options) }.join
@@ -37,7 +37,7 @@ module Nokogiri
       end
 
       def write_to(io, *options)
-        return super(io, *options) unless document.is_a?(HTML5::Document)
+        return super unless document.is_a?(HTML5::Document)
 
         options = options.first.is_a?(Hash) ? options.shift : {}
         encoding = options[:encoding] || options[0]
@@ -68,7 +68,7 @@ module Nokogiri
       end
 
       def fragment(tags)
-        return super(tags) unless document.is_a?(HTML5::Document)
+        return super unless document.is_a?(HTML5::Document)
 
         DocumentFragment.new(document, tags, self)
       end
@@ -81,7 +81,7 @@ module Nokogiri
       # annoying with attribute names like xml:lang since libxml2 will
       # actually create the xml namespace if it doesn't exist already.
       def add_child_node_and_reparent_attrs(node)
-        return super(node) unless document.is_a?(HTML5::Document)
+        return super unless document.is_a?(HTML5::Document)
 
         # I'm not sure what this method is supposed to do. Reparenting
         # namespaces is handled by libxml2, including child namespaces which

data/lib/nokogiri/html5.rb

@@ -1,66 +1,71 @@
 # coding: utf-8
 # frozen_string_literal: true
 
+# This file includes code from the Nokogumbo project, whose license follows.
 #
-#  Copyright 2013-2021 Sam Ruby, Stephen Checkoway
+#   Copyright 2013-2021 Sam Ruby, Stephen Checkoway
 #
-#  Licensed under the Apache License, Version 2.0 (the "License");
-#  you may not use this file except in compliance with the License.
-#  You may obtain a copy of the License at
+#   Licensed under the Apache License, Version 2.0 (the "License");
+#   you may not use this file except in compliance with the License.
+#   You may obtain a copy of the License at
 #
-#      http://www.apache.org/licenses/LICENSE-2.0
+#       http://www.apache.org/licenses/LICENSE-2.0
 #
-#  Unless required by applicable law or agreed to in writing, software
-#  distributed under the License is distributed on an "AS IS" BASIS,
-#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-#  See the License for the specific language governing permissions and
-#  limitations under the License.
+#   Unless required by applicable law or agreed to in writing, software
+#   distributed under the License is distributed on an "AS IS" BASIS,
+#   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#   See the License for the specific language governing permissions and
+#   limitations under the License.
 #
 
 require_relative "html5/document"
 require_relative "html5/document_fragment"
 require_relative "html5/node"
+require_relative "html5/builder"
 
 module Nokogiri
-  # Since v1.12.0
-  #
-  # ⚠ HTML5 functionality is not available when running JRuby.
-  #
-  # Parse an HTML5 document. Convenience method for {Nokogiri::HTML5::Document.parse}
-  def self.HTML5(input, url = nil, encoding = nil, **options, &block)
-    Nokogiri::HTML5::Document.parse(input, url, encoding, **options, &block)
+  # Convenience method for Nokogiri::HTML5::Document.parse
+  def self.HTML5(...)
+    Nokogiri::HTML5::Document.parse(...)
   end
 
   # == Usage
   #
-  # ⚠ HTML5 functionality is not available when running JRuby.
-  #
   # Parse an HTML5 document:
   #
-  #   doc = Nokogiri.HTML5(string)
+  #   doc = Nokogiri.HTML5(input)
   #
   # Parse an HTML5 fragment:
   #
-  #   fragment = Nokogiri::HTML5.fragment(string)
+  #   fragment = Nokogiri::HTML5.fragment(input)
+  #
+  # ⚠ HTML5 functionality is not available when running JRuby.
   #
   # == Parsing options
   #
-  # The document and fragment parsing methods support options that are different from Nokogiri's.
+  # The document and fragment parsing methods support options that are different from
+  # Nokogiri::HTML4::Document or Nokogiri::XML::Document.
+  #
+  # - <tt>Nokogiri.HTML5(input, url:, encoding:, **parse_options)</tt>
+  # - <tt>Nokogiri::HTML5.parse(input, url:, encoding:, **parse_options)</tt>
+  # - <tt>Nokogiri::HTML5::Document.parse(input, url:, encoding:, **parse_options)</tt>
+  # - <tt>Nokogiri::HTML5.fragment(input, encoding:, **parse_options)</tt>
+  # - <tt>Nokogiri::HTML5::DocumentFragment.parse(input, encoding:, **parse_options)</tt>
   #
-  # - <tt>Nokogiri.HTML5(html, url = nil, encoding = nil, options = {})</tt>
-  # - <tt>Nokogiri::HTML5.parse(html, url = nil, encoding = nil, options = {})</tt>
-  # - <tt>Nokogiri::HTML5::Document.parse(html, url = nil, encoding = nil, options = {})</tt>
-  # - <tt>Nokogiri::HTML5.fragment(html, encoding = nil, options = {})</tt>
-  # - <tt>Nokogiri::HTML5::DocumentFragment.parse(html, encoding = nil, options = {})</tt>
+  # The four currently supported parse options are
   #
-  # The three currently supported options are +:max_errors+, +:max_tree_depth+ and
-  # +:max_attributes+, described below.
+  # - +max_errors:+ (Integer, default 0) Maximum number of parse errors to report in HTML5::Document#errors.
+  # - +max_tree_depth:+ (Integer, default +Nokogiri::Gumbo::DEFAULT_MAX_TREE_DEPTH+) Maximum tree depth to parse.
+  # - +max_attributes:+ (Integer, default +Nokogiri::Gumbo::DEFAULT_MAX_ATTRIBUTES+) Maximum number of attributes to parse per element.
+  # - +parse_noscript_content_as_text:+ (Boolean, default false) When enabled, parse +noscript+ tag content as text, mimicking the behavior of web browsers.
   #
-  # === Error reporting
+  # These options are explained in the following sections.
+  #
+  # === Error reporting: +max_errors:+
   #
   # Nokogiri contains an experimental HTML5 parse error reporting facility. By default, no parse
   # errors are reported but this can be configured by passing the +:max_errors+ option to
-  # {HTML5.parse} or {HTML5.fragment}.
+  # HTML5.parse or HTML5.fragment.
   #
   # For example, this script:
   #
@@ -86,20 +91,21 @@ module Nokogiri
   #
   # Using <tt>max_errors: -1</tt> results in an unlimited number of errors being returned.
   #
-  # The errors returned by {HTML5::Document#errors} are instances of {Nokogiri::XML::SyntaxError}.
+  # The errors returned by HTML5::Document#errors are instances of Nokogiri::XML::SyntaxError.
   #
-  # The {https://html.spec.whatwg.org/multipage/parsing.html#parse-errors HTML standard} defines a
+  # The {HTML standard}[https://html.spec.whatwg.org/multipage/parsing.html#parse-errors] defines a
   # number of standard parse error codes. These error codes only cover the "tokenization" stage of
   # parsing HTML. The parse errors in the "tree construction" stage do not have standardized error
   # codes (yet).
   #
-  # As a convenience to Nokogiri users, the defined error codes are available via
-  # {Nokogiri::XML::SyntaxError#str1} method.
+  # As a convenience to Nokogiri users, the defined error codes are available
+  # via Nokogiri::XML::SyntaxError#str1 method.
   #
   #   doc = Nokogiri::HTML5.parse('<span/>Hi there!</span foo=bar />', max_errors: 10)
   #   doc.errors.each do |err|
   #     puts("#{err.line}:#{err.column}: #{err.str1}")
   #   end
+  #   doc = Nokogiri::HTML5.parse('<span/>Hi there!</span foo=bar />',
   #   # => 1:1: generic-parser
   #   #    1:1: non-void-html-element-start-tag-with-trailing-solidus
   #   #    1:17: end-tag-with-trailing-solidus
@@ -112,40 +118,75 @@ module Nokogiri
   # are not part of Nokogiri's public API. That is, these are subject to change without Nokogiri's
   # major version number changing. These may be stabilized in the future.
   #
-  # === Maximum tree depth
+  # === Maximum tree depth: +max_tree_depth:+
   #
   # The maximum depth of the DOM tree parsed by the various parsing methods is configurable by the
   # +:max_tree_depth+ option. If the depth of the tree would exceed this limit, then an
-  # {::ArgumentError} is thrown.
+  # +ArgumentError+ is thrown.
   #
-  # This limit (which defaults to <tt>Nokogiri::Gumbo::DEFAULT_MAX_TREE_DEPTH = 400</tt>) can be
-  # removed by giving the option <tt>max_tree_depth: -1</tt>.
+  # This limit (which defaults to +Nokogiri::Gumbo::DEFAULT_MAX_TREE_DEPTH+) can be removed by
+  # giving the option <tt>max_tree_depth: -1</tt>.
   #
   #   html = '<!DOCTYPE html>' + '<div>' * 1000
   #   doc = Nokogiri.HTML5(html)
   #   # raises ArgumentError: Document tree depth limit exceeded
   #   doc = Nokogiri.HTML5(html, max_tree_depth: -1)
   #
-  # === Attribute limit per element
+  # === Attribute limit per element: +max_attributes:+
   #
   # The maximum number of attributes per DOM element is configurable by the +:max_attributes+
-  # option. If a given element would exceed this limit, then an {::ArgumentError} is thrown.
+  # option. If a given element would exceed this limit, then an +ArgumentError+ is thrown.
   #
-  # This limit (which defaults to <tt>Nokogiri::Gumbo::DEFAULT_MAX_ATTRIBUTES = 400</tt>) can be
-  # removed by giving the option <tt>max_attributes: -1</tt>.
+  # This limit (which defaults to +Nokogiri::Gumbo::DEFAULT_MAX_ATTRIBUTES+) can be removed by
+  # giving the option <tt>max_attributes: -1</tt>.
   #
-  #   html = '<!DOCTYPE html><div ' + (1..1000).map { |x| "attr-#{x}" }.join(' ') + '>'
+  #   html = '<!DOCTYPE html><div ' + (1..1000).map { |x| "attr-#{x}" }.join(' # ') + '>'
   #   # "<!DOCTYPE html><div attr-1 attr-2 attr-3 ... attr-1000>"
   #   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: +parse_noscript_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 = "<!DOCTYPE html><noscript><meta charset='UTF-8'><link rel=stylesheet href=!></noscript>"
+  #   doc = Nokogiri::HTML5.parse(html, parse_noscript_content_as_text: true)
+  #   pp doc.at_xpath("/html/head/noscript")
+  #   # => #(Element:0x878c {
+  #   #        name = "noscript",
+  #   #        children = [ #(Text "<meta charset='UTF-8'><link rel=stylesheet href=!>")]
+  #   #      })
+  #
+  # In contrast, <tt>parse_noscript_content_as_text: false</tt> (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("<!DOCTYPE html><span>Hello world!</span>")
@@ -153,12 +194,12 @@ module Nokogiri
   #   # => <!DOCTYPE html><html><head></head><body><span>Hello world!</span></body></html>
   #
   # 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)
   #   <!DOCTYPE html>
@@ -187,56 +228,57 @@ module Nokogiri
   #
   # == 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('<span>아는 길도 물어가라</span>')
   #   html = frag.serialize(encoding: 'US-ASCII')
   #   puts html
   #   # => <span>&#xc544;&#xb294; &#xae38;&#xb3c4; &#xbb3c;&#xc5b4;&#xac00;&#xb77c;</span>
+  #
   #   frag = Nokogiri::HTML5.fragment(html)
   #   puts frag.serialize
   #   # => <span>아는 길도 물어가라</span>
   #
-  # (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 <tt>'ISO-2022-JP'</tt>. We recommend avoiding this
   # encoding.)
   #
   # == Notes
   #
-  # * 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.fragment function takes a String or IO and parses it as a HTML5 document
+  #   in a +body+ context. As a result, 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; but you can pass in a different context (e.g., "html" to
+  #   get +head+ and +body+ tags in the result).
   #
-  # * The {Nokogiri::HTML5.parse} function takes a string and passes it to the
-  #   <code>gumbo_parse_with_options</code> method, using the default options.
-  #   The resulting Gumbo parse tree is then walked.
+  # * The Nokogiri::HTML5.parse function takes a String or IO and passes it to the
+  #   <code>gumbo_parse_with_options</code> 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}
-      def parse(string, url = nil, encoding = nil, **options, &block)
-        Document.parse(string, url, encoding, **options, &block)
+      # Convenience method for Nokogiri::HTML5::Document.parse
+      def parse(...)
+        Document.parse(...)
       end
 
-      # Parse a fragment from +string+. Convenience method for
-      # {Nokogiri::HTML5::DocumentFragment.parse}.
-      def fragment(string, encoding = nil, **options)
-        DocumentFragment.parse(string, encoding, options)
+      # Convenience method for Nokogiri::HTML5::DocumentFragment.parse
+      def fragment(...)
+        DocumentFragment.parse(...)
       end
 
       # :nodoc:
@@ -267,11 +309,11 @@ module Nokogiri
       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.
       #

data/lib/nokogiri/version/constant.rb

@@ -2,5 +2,5 @@
 
 module Nokogiri
   # The version of Nokogiri you are using
-  VERSION = "1.16.8"
+  VERSION = "1.17.0"
 end

data/lib/nokogiri/xml/builder.rb

@@ -475,7 +475,14 @@ module Nokogiri
           if block
             old_parent = @doc_builder.parent
             @doc_builder.parent = @node
-            value = @doc_builder.instance_eval(&block)
+
+            arity = @doc_builder.arity || block.arity
+            value = if arity <= 0
+              @doc_builder.instance_eval(&block)
+            else
+              yield(@doc_builder)
+            end
+
             @doc_builder.parent = old_parent
             return value
           end