nokogiri-backport 1.11.0

data/lib/nokogiri/html/sax/parser.rb

@@ -0,0 +1,63 @@
+# frozen_string_literal: true
+module Nokogiri
+  module HTML
+    ###
+    # Nokogiri lets you write a SAX parser to process HTML but get HTML
+    # correction features.
+    #
+    # See Nokogiri::HTML::SAX::Parser for a basic example of using a
+    # SAX parser with HTML.
+    #
+    # For more information on SAX parsers, see Nokogiri::XML::SAX
+    module SAX
+      ###
+      # This class lets you perform SAX style parsing on HTML with HTML
+      # error correction.
+      #
+      # Here is a basic usage example:
+      #
+      #   class MyDoc < Nokogiri::XML::SAX::Document
+      #     def start_element name, attributes = []
+      #       puts "found a #{name}"
+      #     end
+      #   end
+      #
+      #   parser = Nokogiri::HTML::SAX::Parser.new(MyDoc.new)
+      #   parser.parse(File.read(ARGV[0], mode: 'rb'))
+      #
+      # For more information on SAX parsers, see Nokogiri::XML::SAX
+      class Parser < Nokogiri::XML::SAX::Parser
+        ###
+        # Parse html stored in +data+ using +encoding+
+        def parse_memory data, encoding = 'UTF-8'
+          raise ArgumentError unless data
+          return unless data.length > 0
+          ctx = ParserContext.memory(data, encoding)
+          yield ctx if block_given?
+          ctx.parse_with self
+        end
+
+        ###
+        # Parse given +io+
+        def parse_io io, encoding = 'UTF-8'
+          check_encoding(encoding)
+          @encoding = encoding
+          ctx = ParserContext.io(io, ENCODINGS[encoding])
+          yield ctx if block_given?
+          ctx.parse_with self
+        end
+
+        ###
+        # Parse a file with +filename+
+        def parse_file filename, encoding = 'UTF-8'
+          raise ArgumentError unless filename
+          raise Errno::ENOENT unless File.exist?(filename)
+          raise Errno::EISDIR if File.directory?(filename)
+          ctx = ParserContext.file(filename, encoding)
+          yield ctx if block_given?
+          ctx.parse_with self
+        end
+      end
+    end
+  end
+end

data/lib/nokogiri/html/sax/parser_context.rb

@@ -0,0 +1,17 @@
+# frozen_string_literal: true
+module Nokogiri
+  module HTML
+    module SAX
+      ###
+      # Context for HTML SAX parsers.  This class is usually not instantiated
+      # by the user.  Instead, you should be looking at
+      # Nokogiri::HTML::SAX::Parser
+      class ParserContext < Nokogiri::XML::SAX::ParserContext
+        def self.new thing, encoding = 'UTF-8'
+          [:read, :close].all? { |x| thing.respond_to?(x) } ?  super :
+            memory(thing, encoding)
+        end
+      end
+    end
+  end
+end

data/lib/nokogiri/html/sax/push_parser.rb

@@ -0,0 +1,37 @@
+# frozen_string_literal: true
+module Nokogiri
+  module HTML
+    module SAX
+      class PushParser
+        
+        # The Nokogiri::HTML::SAX::Document on which the PushParser will be
+        # operating
+        attr_accessor :document
+        
+        def initialize(doc = HTML::SAX::Document.new, file_name = nil, encoding = 'UTF-8')
+          @document = doc
+          @encoding = encoding
+          @sax_parser = HTML::SAX::Parser.new(doc, @encoding)
+
+          ## Create our push parser context
+          initialize_native(@sax_parser, file_name, encoding)
+        end
+        
+        ###
+        # Write a +chunk+ of HTML to the PushParser.  Any callback methods
+        # that can be called will be called immediately.
+        def write chunk, last_chunk = false
+          native_write(chunk, last_chunk)
+        end
+        alias :<< :write
+
+        ###
+        # Finish the parsing.  This method is only necessary for
+        # Nokogiri::HTML::SAX::Document#end_document to be called.
+        def finish
+          write '', true
+        end
+      end
+    end
+  end
+end

data/lib/nokogiri/html.rb

@@ -0,0 +1,38 @@
+# frozen_string_literal: true
+require 'nokogiri/html/entity_lookup'
+require 'nokogiri/html/document'
+require 'nokogiri/html/document_fragment'
+require 'nokogiri/html/sax/parser_context'
+require 'nokogiri/html/sax/parser'
+require 'nokogiri/html/sax/push_parser'
+require 'nokogiri/html/element_description'
+require 'nokogiri/html/element_description_defaults'
+
+module Nokogiri
+  class << self
+    ###
+    # Parse HTML.  Convenience method for Nokogiri::HTML::Document.parse
+    def HTML thing, url = nil, encoding = nil, options = XML::ParseOptions::DEFAULT_HTML, &block
+      Nokogiri::HTML::Document.parse(thing, url, encoding, options, &block)
+    end
+  end
+
+  module HTML
+    class << self
+      ###
+      # Parse HTML.  Convenience method for Nokogiri::HTML::Document.parse
+      def parse thing, url = nil, encoding = nil, options = XML::ParseOptions::DEFAULT_HTML, &block
+        Document.parse(thing, url, encoding, options, &block)
+      end
+
+      ####
+      # Parse a fragment from +string+ in to a NodeSet.
+      def fragment string, encoding = nil
+        HTML::DocumentFragment.parse string, encoding
+      end
+    end
+
+    # Instance of Nokogiri::HTML::EntityLookup
+    NamedCharacters = EntityLookup.new
+  end
+end

data/lib/nokogiri/jruby/dependencies.rb

@@ -0,0 +1,20 @@
+# frozen_string_literal: true
+# The line below caused a problem on non-GAE rack environment.
+# unless defined?(JRuby::Rack::VERSION) || defined?(AppEngine::ApiProxy)
+#
+# However, simply cutting defined?(JRuby::Rack::VERSION) off resulted in
+# an unable-to-load-nokogiri problem. Thus, now, Nokogiri checks the presense
+# of appengine-rack.jar in $LOAD_PATH. If Nokogiri is on GAE, Nokogiri
+# should skip loading xml jars. This is because those are in WEB-INF/lib and
+# already set in the classpath.
+unless $LOAD_PATH.to_s.include?("appengine-rack")
+  require 'stringio'
+  require 'isorelax.jar'
+  require 'jing.jar'
+  require 'nekohtml.jar'
+  require 'nekodtd.jar'
+  require 'xercesImpl.jar'
+  require 'serializer.jar'
+  require 'xalan.jar'
+  require 'xml-apis.jar'
+end

data/lib/nokogiri/syntax_error.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+module Nokogiri
+  class SyntaxError < ::StandardError
+  end
+end

data/lib/nokogiri/version/constant.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+module Nokogiri
+  # The version of Nokogiri you are using
+  VERSION = "1.11.0"
+end

data/lib/nokogiri/version/info.rb

@@ -0,0 +1,182 @@
+# 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 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 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?
+            cppflags = ["-I#{header_directory.shellescape}"]
+            if libxml2_using_packaged?
+              cppflags << "-I#{File.join(header_directory, "include").shellescape}"
+              cppflags << "-I#{File.join(header_directory, "include/libxml2").shellescape}"
+            end
+            nokogiri["cppflags"] = cppflags
+          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["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["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|
+            ol["xerces"] = Nokogiri::XERCES_VERSION
+            ol["nekohtml"] = Nokogiri::NEKO_VERSION
+          end
+        end
+      end
+    end
+
+    def to_markdown
+      begin
+        require "psych"
+      rescue LoadError
+      end
+      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
+
+  def self.uses_libxml?(requirement = nil) # :nodoc:
+    return false unless VersionInfo.instance.libxml2?
+    return true unless requirement
+    Gem::Requirement.new(requirement).satisfied_by?(VersionInfo.instance.loaded_libxml_version)
+  end
+
+  def self.jruby? # :nodoc:
+    VersionInfo.instance.jruby?
+  end
+
+  # Ensure constants used in this file are loaded - see #1896
+  if Nokogiri.jruby?
+    require "nokogiri/jruby/dependencies"
+  end
+  begin
+    ::RUBY_VERSION =~ /(\d+\.\d+)/
+    require "nokogiri/#{Regexp.last_match(1)}/nokogiri"
+  rescue LoadError
+    require "nokogiri/nokogiri"
+  end
+
+  # More complete version information about libxml
+  VERSION_INFO = VersionInfo.instance.to_hash
+end

data/lib/nokogiri/version.rb

@@ -0,0 +1,3 @@
+# frozen_string_literal: true
+require_relative "version/constant"
+require_relative "version/info"

data/lib/nokogiri/xml/attr.rb

@@ -0,0 +1,15 @@
+# frozen_string_literal: true
+module Nokogiri
+  module XML
+    class Attr < Node
+      alias :value :content
+      alias :to_s :content
+      alias :content= :value=
+
+      private
+      def inspect_attributes
+        [:name, :namespace, :value]
+      end
+    end
+  end
+end

data/lib/nokogiri/xml/attribute_decl.rb

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+module Nokogiri
+  module XML
+    ###
+    # Represents an attribute declaration in a DTD
+    class AttributeDecl < Nokogiri::XML::Node
+      undef_method :attribute_nodes
+      undef_method :attributes
+      undef_method :content
+      undef_method :namespace
+      undef_method :namespace_definitions
+      undef_method :line if method_defined?(:line)
+
+      def inspect
+        "#<#{self.class.name}:#{sprintf("0x%x", object_id)} #{to_s.inspect}>"
+      end
+    end
+  end
+end