nokogiri 1.10.10 → 1.14.3-aarch64-linux

data/lib/nokogiri/html5.rb

@@ -0,0 +1,389 @@
+# coding: utf-8
+# frozen_string_literal: true
+
+#
+#  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
+#
+#      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.
+#
+
+require_relative "html5/document"
+require_relative "html5/document_fragment"
+require_relative "html5/node"
+
+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)
+  end
+
+  # == Usage
+  #
+  # ⚠ HTML5 functionality is not available when running JRuby.
+  #
+  # Parse an HTML5 document:
+  #
+  #   doc = Nokogiri.HTML5(string)
+  #
+  # Parse an HTML5 fragment:
+  #
+  #   fragment = Nokogiri::HTML5.fragment(string)
+  #
+  # == Parsing options
+  #
+  # The document and fragment parsing methods support options that are different from Nokogiri's.
+  #
+  # - <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 three currently supported options are +:max_errors+, +:max_tree_depth+ and
+  # +:max_attributes+, described below.
+  #
+  # === Error reporting
+  #
+  # 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}.
+  #
+  # For example, this script:
+  #
+  #   doc = Nokogiri::HTML5.parse('<span/>Hi there!</span foo=bar />', max_errors: 10)
+  #   doc.errors.each do |err|
+  #     puts(err)
+  #   end
+  #
+  # Emits:
+  #
+  #   1:1: ERROR: Expected a doctype token
+  #   <span/>Hi there!</span foo=bar />
+  #   ^
+  #   1:1: ERROR: Start tag of nonvoid HTML element ends with '/>', use '>'.
+  #   <span/>Hi there!</span foo=bar />
+  #   ^
+  #   1:17: ERROR: End tag ends with '/>', use '>'.
+  #   <span/>Hi there!</span foo=bar />
+  #                   ^
+  #   1:17: ERROR: End tag contains attributes.
+  #   <span/>Hi there!</span foo=bar />
+  #                   ^
+  #
+  # 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 {https://html.spec.whatwg.org/multipage/parsing.html#parse-errors HTML standard} 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.
+  #
+  #   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
+  #   # => 1:1: generic-parser
+  #   #    1:1: non-void-html-element-start-tag-with-trailing-solidus
+  #   #    1:17: end-tag-with-trailing-solidus
+  #   #    1:17: end-tag-with-attributes
+  #
+  # Note that the first error is +generic-parser+ because it's an error from the tree construction
+  # stage and doesn't have a standardized error code.
+  #
+  # For the purposes of semantic versioning, the error messages, error locations, and error codes
+  # 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
+  #
+  # 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.
+  #
+  # 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>.
+  #
+  #   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
+  #
+  # 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.
+  #
+  # 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>.
+  #
+  #   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)
+  #
+  # == 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
+  # 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
+  # node. (This is the equivalent of JavaScript's +Element.innerHTML+.)
+  #
+  #   doc = Nokogiri::HTML5("<!DOCTYPE html><span>Hello world!</span>")
+  #   puts doc.serialize
+  #   # => <!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
+  # 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.
+  #
+  #   doc = Nokogiri::HTML5(<<-EOF)
+  #   <!DOCTYPE html>
+  #   <pre>
+  #   Content</pre>
+  #   EOF
+  #   puts doc.at('/html/body/pre').serialize
+  #   # => <pre>Content</pre>
+  #
+  # In this case, the original HTML is semantically equivalent to the serialized version. If the
+  # +pre+, +listing+, or +textarea+ content starts with two newlines, the first newline will be
+  # stripped on the first parse and the second newline will be stripped on the second, leading to
+  # semantically different DOMs. Passing the parameter <tt>preserve_newline: true</tt> will cause
+  # two or more newlines to be preserved. (A single leading newline will still be removed.)
+  #
+  #   doc = Nokogiri::HTML5(<<-EOF)
+  #   <!DOCTYPE html>
+  #   <listing>
+  #
+  #   Content</listing>
+  #   EOF
+  #   puts doc.at('/html/body/listing').serialize(preserve_newline: true)
+  #   # => <listing>
+  #   #
+  #   #    Content</listing>
+  #
+  # == Encodings
+  #
+  # Nokogiri always parses HTML5 using {https://en.wikipedia.org/wiki/UTF-8 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}.
+  #
+  #   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
+  # 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.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.
+  #
+  # * 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.
+  #
+  # 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)
+      end
+
+      # Parse a fragment from +string+. Convenience method for
+      # {Nokogiri::HTML5::DocumentFragment.parse}.
+      def fragment(string, encoding = nil, **options)
+        DocumentFragment.parse(string, encoding, options)
+      end
+
+      # Fetch and parse a HTML document from the web, following redirects,
+      # handling https, and determining the character encoding using HTML5
+      # rules.  +uri+ may be a +String+ or a +URI+.  +options+ contains
+      # http headers and special options.  Everything which is not a
+      # special option is considered a header.  Special options include:
+      #  * :follow_limit => number of redirects which are followed
+      #  * :basic_auth => [username, password]
+      def get(uri, options = {})
+        # TODO: deprecate
+        warn("Nokogiri::HTML5.get is deprecated and will be removed in a future version of Nokogiri.",
+          uplevel: 1, category: :deprecated)
+        get_impl(uri, options)
+      end
+
+      # :nodoc:
+      def read_and_encode(string, encoding)
+        # Read the string with the given encoding.
+        if string.respond_to?(:read)
+          string = if encoding.nil?
+            string.read
+          else
+            string.read(encoding: encoding)
+          end
+        else
+          # Otherwise the string has the given encoding.
+          string = string.to_s
+          if encoding
+            string = string.dup
+            string.force_encoding(encoding)
+          end
+        end
+
+        # convert to UTF-8
+        if string.encoding != Encoding::UTF_8
+          string = reencode(string)
+        end
+        string
+      end
+
+      private
+
+      def get_impl(uri, options = {})
+        headers = options.clone
+        headers = { follow_limit: headers } if Numeric === headers # deprecated
+        limit = headers[:follow_limit] ? headers.delete(:follow_limit).to_i : 10
+
+        require "net/http"
+        uri = URI(uri) unless URI === uri
+
+        http = Net::HTTP.new(uri.host, uri.port)
+
+        # TLS / SSL support
+        http.use_ssl = true if uri.scheme == "https"
+
+        # Pass through Net::HTTP override values, which currently include:
+        #   :ca_file, :ca_path, :cert, :cert_store, :ciphers,
+        #   :close_on_empty_response, :continue_timeout, :key, :open_timeout,
+        #   :read_timeout, :ssl_timeout, :ssl_version, :use_ssl,
+        #   :verify_callback, :verify_depth, :verify_mode
+        options.each do |key, _value|
+          http.send("#{key}=", headers.delete(key)) if http.respond_to?("#{key}=")
+        end
+
+        request = Net::HTTP::Get.new(uri.request_uri)
+
+        # basic authentication
+        auth = headers.delete(:basic_auth)
+        auth ||= [uri.user, uri.password] if uri.user && uri.password
+        request.basic_auth(auth.first, auth.last) if auth
+
+        # remaining options are treated as headers
+        headers.each { |key, value| request[key.to_s] = value.to_s }
+
+        response = http.request(request)
+
+        case response
+        when Net::HTTPSuccess
+          doc = parse(reencode(response.body, response["content-type"]), options)
+          doc.instance_variable_set(:@response, response)
+          doc.class.send(:attr_reader, :response)
+          doc
+        when Net::HTTPRedirection
+          response.value if limit <= 1
+          location = URI.join(uri, response["location"])
+          get_impl(location, options.merge(follow_limit: limit - 1))
+        else
+          response.value
+        end
+      end
+
+      # 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
+      # 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
+      # this lead, Nokogiri::HTML5 attempts to do likewise, while attempting to more closely follow
+      # the HTML5 standard.
+      #
+      # http://bugs.ruby-lang.org/issues/2567
+      # http://www.w3.org/TR/html5/syntax.html#determining-the-character-encoding
+      #
+      def reencode(body, content_type = nil)
+        if body.encoding == Encoding::ASCII_8BIT
+          encoding = nil
+
+          # look for a Byte Order Mark (BOM)
+          initial_bytes = body[0..2].bytes
+          if initial_bytes[0..2] == [0xEF, 0xBB, 0xBF]
+            encoding = Encoding::UTF_8
+          elsif initial_bytes[0..1] == [0xFE, 0xFF]
+            encoding = Encoding::UTF_16BE
+          elsif initial_bytes[0..1] == [0xFF, 0xFE]
+            encoding = Encoding::UTF_16LE
+          end
+
+          # look for a charset in a content-encoding header
+          if content_type
+            encoding ||= content_type[/charset=["']?(.*?)($|["';\s])/i, 1]
+          end
+
+          # look for a charset in a meta tag in the first 1024 bytes
+          unless encoding
+            data = body[0..1023].gsub(/<!--.*?(-->|\Z)/m, "")
+            data.scan(/<meta.*?>/im).each do |meta|
+              encoding ||= meta[/charset=["']?([^>]*?)($|["'\s>])/im, 1]
+            end
+          end
+
+          # if all else fails, default to the official default encoding for HTML
+          encoding ||= Encoding::ISO_8859_1
+
+          # change the encoding to match the detected or inferred encoding
+          body = body.dup
+          begin
+            body.force_encoding(encoding)
+          rescue ArgumentError
+            body.force_encoding(Encoding::ISO_8859_1)
+          end
+        end
+
+        body.encode(Encoding::UTF_8)
+      end
+    end
+  end
+end
+
+require_relative "gumbo"

data/lib/nokogiri/jruby/dependencies.rb

@@ -0,0 +1,3 @@
+# frozen_string_literal: true
+
+require_relative "nokogiri_jars"

data/lib/nokogiri/jruby/nokogiri_jars.rb

@@ -0,0 +1,43 @@
+# this is a generated file, to avoid over-writing it just delete this comment
+begin
+  require 'jar_dependencies'
+rescue LoadError
+  require 'xalan/xalan/2.7.2/xalan-2.7.2.jar'
+  require 'net/sourceforge/htmlunit/neko-htmlunit/2.63.0/neko-htmlunit-2.63.0.jar'
+  require 'nu/validator/jing/20200702VNU/jing-20200702VNU.jar'
+  require 'xerces/xercesImpl/2.12.2/xercesImpl-2.12.2.jar'
+  require 'org/nokogiri/nekodtd/0.1.11.noko1/nekodtd-0.1.11.noko1.jar'
+  require 'net/sf/saxon/Saxon-HE/9.6.0-4/Saxon-HE-9.6.0-4.jar'
+  require 'xml-apis/xml-apis/1.4.01/xml-apis-1.4.01.jar'
+  require 'xalan/serializer/2.7.2/serializer-2.7.2.jar'
+  require 'isorelax/isorelax/20030108/isorelax-20030108.jar'
+end
+
+if defined? Jars
+  require_jar 'xalan', 'xalan', '2.7.2'
+  require_jar 'net.sourceforge.htmlunit', 'neko-htmlunit', '2.63.0'
+  require_jar 'nu.validator', 'jing', '20200702VNU'
+  require_jar 'xerces', 'xercesImpl', '2.12.2'
+  require_jar 'org.nokogiri', 'nekodtd', '0.1.11.noko1'
+  require_jar 'net.sf.saxon', 'Saxon-HE', '9.6.0-4'
+  require_jar 'xml-apis', 'xml-apis', '1.4.01'
+  require_jar 'xalan', 'serializer', '2.7.2'
+  require_jar 'isorelax', 'isorelax', '20030108'
+end
+
+module Nokogiri
+  # generated by the :vendor_jars rake task
+  JAR_DEPENDENCIES = {
+    "isorelax:isorelax" => "20030108",
+    "net.sf.saxon:Saxon-HE" => "9.6.0-4",
+    "net.sourceforge.htmlunit:neko-htmlunit" => "2.63.0",
+    "nu.validator:jing" => "20200702VNU",
+    "org.nokogiri:nekodtd" => "0.1.11.noko1",
+    "xalan:serializer" => "2.7.2",
+    "xalan:xalan" => "2.7.2",
+    "xerces:xercesImpl" => "2.12.2",
+    "xml-apis:xml-apis" => "1.4.01",
+  }.freeze
+  XERCES_VERSION = JAR_DEPENDENCIES["xerces:xercesImpl"]
+  NEKO_VERSION = JAR_DEPENDENCIES["net.sourceforge.htmlunit:neko-htmlunit"]
+end

data/lib/nokogiri/syntax_error.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Nokogiri
   class SyntaxError < ::StandardError
   end

data/lib/nokogiri/version/constant.rb

@@ -0,0 +1,6 @@
+# frozen_string_literal: true
+
+module Nokogiri
+  # The version of Nokogiri you are using
+  VERSION = "1.14.3"
+end

data/lib/nokogiri/version/info.rb

@@ -0,0 +1,223 @@
+# frozen_string_literal: true
+
+require "singleton"
+require "shellwords"
+
+module Nokogiri
+  class VersionInfo # :nodoc:
+    include Singleton
+
+    def jruby?
+      ::JRUBY_VERSION if ::RUBY_PLATFORM == "java"
+    end
+
+    def windows?
+      ::RUBY_PLATFORM =~ /mingw|mswin/
+    end
+
+    def ruby_minor
+      Gem::Version.new(::RUBY_VERSION).segments[0..1].join(".")
+    end
+
+    def engine
+      defined?(::RUBY_ENGINE) ? ::RUBY_ENGINE : "mri"
+    end
+
+    def loaded_libxml_version
+      Gem::Version.new(Nokogiri::LIBXML_LOADED_VERSION
+        .scan(/^(\d+)(\d\d)(\d\d)(?!\d)/).first
+        .collect(&:to_i)
+        .join("."))
+    end
+
+    def compiled_libxml_version
+      Gem::Version.new(Nokogiri::LIBXML_COMPILED_VERSION)
+    end
+
+    def loaded_libxslt_version
+      Gem::Version.new(Nokogiri::LIBXSLT_LOADED_VERSION
+        .scan(/^(\d+)(\d\d)(\d\d)(?!\d)/).first
+        .collect(&:to_i)
+        .join("."))
+    end
+
+    def compiled_libxslt_version
+      Gem::Version.new(Nokogiri::LIBXSLT_COMPILED_VERSION)
+    end
+
+    def libxml2?
+      defined?(Nokogiri::LIBXML_COMPILED_VERSION)
+    end
+
+    def libxml2_has_iconv?
+      defined?(Nokogiri::LIBXML_ICONV_ENABLED) && Nokogiri::LIBXML_ICONV_ENABLED
+    end
+
+    def libxslt_has_datetime?
+      defined?(Nokogiri::LIBXSLT_DATETIME_ENABLED) && Nokogiri::LIBXSLT_DATETIME_ENABLED
+    end
+
+    def libxml2_using_packaged?
+      libxml2? && Nokogiri::PACKAGED_LIBRARIES
+    end
+
+    def libxml2_using_system?
+      libxml2? && !libxml2_using_packaged?
+    end
+
+    def libxml2_precompiled?
+      libxml2_using_packaged? && Nokogiri::PRECOMPILED_LIBRARIES
+    end
+
+    def warnings
+      warnings = []
+
+      if libxml2?
+        if compiled_libxml_version != loaded_libxml_version
+          warnings << "Nokogiri was built against libxml version #{compiled_libxml_version}, but has dynamically loaded #{loaded_libxml_version}"
+        end
+
+        if compiled_libxslt_version != loaded_libxslt_version
+          warnings << "Nokogiri was built against libxslt version #{compiled_libxslt_version}, but has dynamically loaded #{loaded_libxslt_version}"
+        end
+      end
+
+      warnings
+    end
+
+    def to_hash
+      header_directory = File.expand_path(File.join(File.dirname(__FILE__), "../../../ext/nokogiri"))
+
+      {}.tap do |vi|
+        vi["warnings"] = []
+        vi["nokogiri"] = {}.tap do |nokogiri|
+          nokogiri["version"] = Nokogiri::VERSION
+
+          unless jruby?
+            #  enable gems like nokogumbo to build with the following in their extconf.rb:
+            #
+            #    append_cflags(Nokogiri::VERSION_INFO["nokogiri"]["cppflags"])
+            #    append_ldflags(Nokogiri::VERSION_INFO["nokogiri"]["ldflags"])
+            #
+            cppflags = ["-I#{header_directory.shellescape}"]
+            ldflags = []
+
+            if libxml2_using_packaged?
+              cppflags << "-I#{File.join(header_directory, "include").shellescape}"
+              cppflags << "-I#{File.join(header_directory, "include/libxml2").shellescape}"
+            end
+
+            if windows?
+              # on windows, nokogumbo needs to link against nokogiri.so to resolve symbols. see #2167
+              lib_directory = File.expand_path(File.join(File.dirname(__FILE__), "../#{ruby_minor}"))
+              unless File.exist?(lib_directory)
+                lib_directory = File.expand_path(File.join(File.dirname(__FILE__), ".."))
+              end
+              ldflags << "-L#{lib_directory.shellescape}"
+              ldflags << "-l:nokogiri.so"
+            end
+
+            nokogiri["cppflags"] = cppflags
+            nokogiri["ldflags"] = ldflags
+          end
+        end
+        vi["ruby"] = {}.tap do |ruby|
+          ruby["version"] = ::RUBY_VERSION
+          ruby["platform"] = ::RUBY_PLATFORM
+          ruby["gem_platform"] = ::Gem::Platform.local.to_s
+          ruby["description"] = ::RUBY_DESCRIPTION
+          ruby["engine"] = engine
+          ruby["jruby"] = jruby? if jruby?
+        end
+
+        if libxml2?
+          vi["libxml"] = {}.tap do |libxml|
+            if libxml2_using_packaged?
+              libxml["source"] = "packaged"
+              libxml["precompiled"] = libxml2_precompiled?
+              libxml["patches"] = Nokogiri::LIBXML2_PATCHES
+
+              # this is for nokogumbo and shouldn't be forever
+              libxml["libxml2_path"] = header_directory
+            else
+              libxml["source"] = "system"
+            end
+            libxml["memory_management"] = Nokogiri::LIBXML_MEMORY_MANAGEMENT
+            libxml["iconv_enabled"] = libxml2_has_iconv?
+            libxml["compiled"] = compiled_libxml_version.to_s
+            libxml["loaded"] = loaded_libxml_version.to_s
+          end
+
+          vi["libxslt"] = {}.tap do |libxslt|
+            if libxml2_using_packaged?
+              libxslt["source"] = "packaged"
+              libxslt["precompiled"] = libxml2_precompiled?
+              libxslt["patches"] = Nokogiri::LIBXSLT_PATCHES
+            else
+              libxslt["source"] = "system"
+            end
+            libxslt["datetime_enabled"] = libxslt_has_datetime?
+            libxslt["compiled"] = compiled_libxslt_version.to_s
+            libxslt["loaded"] = loaded_libxslt_version.to_s
+          end
+
+          vi["warnings"] = warnings
+        end
+
+        if defined?(Nokogiri::OTHER_LIBRARY_VERSIONS)
+          # see extconf for how this string is assembled: "lib1name:lib1version,lib2name:lib2version"
+          vi["other_libraries"] = Hash[*Nokogiri::OTHER_LIBRARY_VERSIONS.split(/[,:]/)]
+        elsif jruby?
+          vi["other_libraries"] = {}.tap do |ol|
+            Nokogiri::JAR_DEPENDENCIES.each do |k, v|
+              ol[k] = v
+            end
+          end
+        end
+      end
+    end
+
+    def to_markdown
+      require "yaml"
+      "# Nokogiri (#{Nokogiri::VERSION})\n" +
+        YAML.dump(to_hash).each_line.map { |line| "    #{line}" }.join
+    end
+
+    instance.warnings.each do |warning|
+      warn "WARNING: #{warning}"
+    end
+  end
+
+  # :nodoc:
+  def self.uses_libxml?(requirement = nil)
+    return false unless VersionInfo.instance.libxml2?
+    return true unless requirement
+
+    Gem::Requirement.new(requirement).satisfied_by?(VersionInfo.instance.loaded_libxml_version)
+  end
+
+  # :nodoc:
+  def self.uses_gumbo?
+    uses_libxml? # TODO: replace with Gumbo functionality
+  end
+
+  # :nodoc:
+  def self.jruby?
+    VersionInfo.instance.jruby?
+  end
+
+  # :nodoc:
+  def self.libxml2_patches
+    if VersionInfo.instance.libxml2_using_packaged?
+      Nokogiri::VERSION_INFO["libxml"]["patches"]
+    else
+      []
+    end
+  end
+
+  require_relative "../jruby/dependencies" if Nokogiri.jruby?
+  require_relative "../extension"
+
+  # Detailed version info about Nokogiri and the installed extension dependencies.
+  VERSION_INFO = VersionInfo.instance.to_hash
+end