RubyGems - nokogiri - Versions diffs - 1.18.0-aarch64-linux-musl - Mend

nokogiri 1.18.0-aarch64-linux-musl

Files changed (203) hide show

checksums.yaml +7 -0
data/Gemfile +39 -0
data/LICENSE-DEPENDENCIES.md +2224 -0
data/LICENSE.md +9 -0
data/README.md +293 -0
data/bin/nokogiri +131 -0
data/dependencies.yml +42 -0
data/ext/nokogiri/depend +38 -0
data/ext/nokogiri/extconf.rb +1173 -0
data/ext/nokogiri/gumbo.c +610 -0
data/ext/nokogiri/html4_document.c +171 -0
data/ext/nokogiri/html4_element_description.c +299 -0
data/ext/nokogiri/html4_entity_lookup.c +37 -0
data/ext/nokogiri/html4_sax_parser.c +40 -0
data/ext/nokogiri/html4_sax_parser_context.c +98 -0
data/ext/nokogiri/html4_sax_push_parser.c +96 -0
data/ext/nokogiri/include/libexslt/exslt.h +108 -0
data/ext/nokogiri/include/libexslt/exsltconfig.h +70 -0
data/ext/nokogiri/include/libexslt/exsltexports.h +63 -0
data/ext/nokogiri/include/libxml2/libxml/HTMLparser.h +336 -0
data/ext/nokogiri/include/libxml2/libxml/HTMLtree.h +147 -0
data/ext/nokogiri/include/libxml2/libxml/SAX.h +202 -0
data/ext/nokogiri/include/libxml2/libxml/SAX2.h +171 -0
data/ext/nokogiri/include/libxml2/libxml/c14n.h +115 -0
data/ext/nokogiri/include/libxml2/libxml/catalog.h +182 -0
data/ext/nokogiri/include/libxml2/libxml/chvalid.h +230 -0
data/ext/nokogiri/include/libxml2/libxml/debugXML.h +217 -0
data/ext/nokogiri/include/libxml2/libxml/dict.h +82 -0
data/ext/nokogiri/include/libxml2/libxml/encoding.h +244 -0
data/ext/nokogiri/include/libxml2/libxml/entities.h +166 -0
data/ext/nokogiri/include/libxml2/libxml/globals.h +41 -0
data/ext/nokogiri/include/libxml2/libxml/hash.h +251 -0
data/ext/nokogiri/include/libxml2/libxml/list.h +137 -0
data/ext/nokogiri/include/libxml2/libxml/nanoftp.h +186 -0
data/ext/nokogiri/include/libxml2/libxml/nanohttp.h +98 -0
data/ext/nokogiri/include/libxml2/libxml/parser.h +1390 -0
data/ext/nokogiri/include/libxml2/libxml/parserInternals.h +671 -0
data/ext/nokogiri/include/libxml2/libxml/pattern.h +106 -0
data/ext/nokogiri/include/libxml2/libxml/relaxng.h +219 -0
data/ext/nokogiri/include/libxml2/libxml/schemasInternals.h +959 -0
data/ext/nokogiri/include/libxml2/libxml/schematron.h +143 -0
data/ext/nokogiri/include/libxml2/libxml/threads.h +87 -0
data/ext/nokogiri/include/libxml2/libxml/tree.h +1382 -0
data/ext/nokogiri/include/libxml2/libxml/uri.h +106 -0
data/ext/nokogiri/include/libxml2/libxml/valid.h +477 -0
data/ext/nokogiri/include/libxml2/libxml/xinclude.h +136 -0
data/ext/nokogiri/include/libxml2/libxml/xlink.h +189 -0
data/ext/nokogiri/include/libxml2/libxml/xmlIO.h +438 -0
data/ext/nokogiri/include/libxml2/libxml/xmlautomata.h +146 -0
data/ext/nokogiri/include/libxml2/libxml/xmlerror.h +962 -0
data/ext/nokogiri/include/libxml2/libxml/xmlexports.h +146 -0
data/ext/nokogiri/include/libxml2/libxml/xmlmemory.h +188 -0
data/ext/nokogiri/include/libxml2/libxml/xmlmodule.h +57 -0
data/ext/nokogiri/include/libxml2/libxml/xmlreader.h +436 -0
data/ext/nokogiri/include/libxml2/libxml/xmlregexp.h +215 -0
data/ext/nokogiri/include/libxml2/libxml/xmlsave.h +102 -0
data/ext/nokogiri/include/libxml2/libxml/xmlschemas.h +249 -0
data/ext/nokogiri/include/libxml2/libxml/xmlschemastypes.h +152 -0
data/ext/nokogiri/include/libxml2/libxml/xmlstring.h +140 -0
data/ext/nokogiri/include/libxml2/libxml/xmlunicode.h +366 -0
data/ext/nokogiri/include/libxml2/libxml/xmlversion.h +347 -0
data/ext/nokogiri/include/libxml2/libxml/xmlwriter.h +489 -0
data/ext/nokogiri/include/libxml2/libxml/xpath.h +579 -0
data/ext/nokogiri/include/libxml2/libxml/xpathInternals.h +633 -0
data/ext/nokogiri/include/libxml2/libxml/xpointer.h +138 -0
data/ext/nokogiri/include/libxslt/attributes.h +39 -0
data/ext/nokogiri/include/libxslt/documents.h +93 -0
data/ext/nokogiri/include/libxslt/extensions.h +262 -0
data/ext/nokogiri/include/libxslt/extra.h +72 -0
data/ext/nokogiri/include/libxslt/functions.h +78 -0
data/ext/nokogiri/include/libxslt/imports.h +75 -0
data/ext/nokogiri/include/libxslt/keys.h +53 -0
data/ext/nokogiri/include/libxslt/namespaces.h +68 -0
data/ext/nokogiri/include/libxslt/numbersInternals.h +73 -0
data/ext/nokogiri/include/libxslt/pattern.h +84 -0
data/ext/nokogiri/include/libxslt/preproc.h +43 -0
data/ext/nokogiri/include/libxslt/security.h +104 -0
data/ext/nokogiri/include/libxslt/templates.h +77 -0
data/ext/nokogiri/include/libxslt/transform.h +207 -0
data/ext/nokogiri/include/libxslt/variables.h +118 -0
data/ext/nokogiri/include/libxslt/xslt.h +110 -0
data/ext/nokogiri/include/libxslt/xsltInternals.h +1995 -0
data/ext/nokogiri/include/libxslt/xsltconfig.h +146 -0
data/ext/nokogiri/include/libxslt/xsltexports.h +64 -0
data/ext/nokogiri/include/libxslt/xsltlocale.h +44 -0
data/ext/nokogiri/include/libxslt/xsltutils.h +343 -0
data/ext/nokogiri/libxml2_polyfill.c +114 -0
data/ext/nokogiri/nokogiri.c +294 -0
data/ext/nokogiri/nokogiri.h +238 -0
data/ext/nokogiri/test_global_handlers.c +40 -0
data/ext/nokogiri/xml_attr.c +103 -0
data/ext/nokogiri/xml_attribute_decl.c +70 -0
data/ext/nokogiri/xml_cdata.c +62 -0
data/ext/nokogiri/xml_comment.c +57 -0
data/ext/nokogiri/xml_document.c +784 -0
data/ext/nokogiri/xml_document_fragment.c +29 -0
data/ext/nokogiri/xml_dtd.c +208 -0
data/ext/nokogiri/xml_element_content.c +131 -0
data/ext/nokogiri/xml_element_decl.c +69 -0
data/ext/nokogiri/xml_encoding_handler.c +112 -0
data/ext/nokogiri/xml_entity_decl.c +112 -0
data/ext/nokogiri/xml_entity_reference.c +50 -0
data/ext/nokogiri/xml_namespace.c +181 -0
data/ext/nokogiri/xml_node.c +2459 -0
data/ext/nokogiri/xml_node_set.c +518 -0
data/ext/nokogiri/xml_processing_instruction.c +54 -0
data/ext/nokogiri/xml_reader.c +777 -0
data/ext/nokogiri/xml_relax_ng.c +149 -0
data/ext/nokogiri/xml_sax_parser.c +403 -0
data/ext/nokogiri/xml_sax_parser_context.c +390 -0
data/ext/nokogiri/xml_sax_push_parser.c +206 -0
data/ext/nokogiri/xml_schema.c +226 -0
data/ext/nokogiri/xml_syntax_error.c +93 -0
data/ext/nokogiri/xml_text.c +59 -0
data/ext/nokogiri/xml_xpath_context.c +486 -0
data/ext/nokogiri/xslt_stylesheet.c +421 -0
data/gumbo-parser/CHANGES.md +63 -0
data/gumbo-parser/Makefile +129 -0
data/gumbo-parser/THANKS +27 -0
data/lib/nokogiri/3.1/nokogiri.so +0 -0
data/lib/nokogiri/3.2/nokogiri.so +0 -0
data/lib/nokogiri/3.3/nokogiri.so +0 -0
data/lib/nokogiri/3.4/nokogiri.so +0 -0
data/lib/nokogiri/class_resolver.rb +67 -0
data/lib/nokogiri/css/node.rb +58 -0
data/lib/nokogiri/css/parser.rb +772 -0
data/lib/nokogiri/css/parser.y +277 -0
data/lib/nokogiri/css/parser_extras.rb +36 -0
data/lib/nokogiri/css/selector_cache.rb +38 -0
data/lib/nokogiri/css/syntax_error.rb +9 -0
data/lib/nokogiri/css/tokenizer.rb +155 -0
data/lib/nokogiri/css/tokenizer.rex +57 -0
data/lib/nokogiri/css/xpath_visitor.rb +375 -0
data/lib/nokogiri/css.rb +132 -0
data/lib/nokogiri/decorators/slop.rb +42 -0
data/lib/nokogiri/encoding_handler.rb +57 -0
data/lib/nokogiri/extension.rb +32 -0
data/lib/nokogiri/gumbo.rb +15 -0
data/lib/nokogiri/html.rb +48 -0
data/lib/nokogiri/html4/builder.rb +37 -0
data/lib/nokogiri/html4/document.rb +235 -0
data/lib/nokogiri/html4/document_fragment.rb +166 -0
data/lib/nokogiri/html4/element_description.rb +25 -0
data/lib/nokogiri/html4/element_description_defaults.rb +2040 -0
data/lib/nokogiri/html4/encoding_reader.rb +121 -0
data/lib/nokogiri/html4/entity_lookup.rb +15 -0
data/lib/nokogiri/html4/sax/parser.rb +48 -0
data/lib/nokogiri/html4/sax/parser_context.rb +15 -0
data/lib/nokogiri/html4/sax/push_parser.rb +37 -0
data/lib/nokogiri/html4.rb +42 -0
data/lib/nokogiri/html5/builder.rb +40 -0
data/lib/nokogiri/html5/document.rb +199 -0
data/lib/nokogiri/html5/document_fragment.rb +200 -0
data/lib/nokogiri/html5/node.rb +103 -0
data/lib/nokogiri/html5.rb +368 -0
data/lib/nokogiri/jruby/dependencies.rb +3 -0
data/lib/nokogiri/jruby/nokogiri_jars.rb +43 -0
data/lib/nokogiri/syntax_error.rb +6 -0
data/lib/nokogiri/version/constant.rb +6 -0
data/lib/nokogiri/version/info.rb +224 -0
data/lib/nokogiri/version.rb +4 -0
data/lib/nokogiri/xml/attr.rb +66 -0
data/lib/nokogiri/xml/attribute_decl.rb +22 -0
data/lib/nokogiri/xml/builder.rb +494 -0
data/lib/nokogiri/xml/cdata.rb +13 -0
data/lib/nokogiri/xml/character_data.rb +9 -0
data/lib/nokogiri/xml/document.rb +514 -0
data/lib/nokogiri/xml/document_fragment.rb +276 -0
data/lib/nokogiri/xml/dtd.rb +34 -0
data/lib/nokogiri/xml/element_content.rb +46 -0
data/lib/nokogiri/xml/element_decl.rb +17 -0
data/lib/nokogiri/xml/entity_decl.rb +23 -0
data/lib/nokogiri/xml/entity_reference.rb +20 -0
data/lib/nokogiri/xml/namespace.rb +57 -0
data/lib/nokogiri/xml/node/save_options.rb +76 -0
data/lib/nokogiri/xml/node.rb +1650 -0
data/lib/nokogiri/xml/node_set.rb +449 -0
data/lib/nokogiri/xml/notation.rb +19 -0
data/lib/nokogiri/xml/parse_options.rb +213 -0
data/lib/nokogiri/xml/pp/character_data.rb +21 -0
data/lib/nokogiri/xml/pp/node.rb +73 -0
data/lib/nokogiri/xml/pp.rb +4 -0
data/lib/nokogiri/xml/processing_instruction.rb +11 -0
data/lib/nokogiri/xml/reader.rb +139 -0
data/lib/nokogiri/xml/relax_ng.rb +75 -0
data/lib/nokogiri/xml/sax/document.rb +258 -0
data/lib/nokogiri/xml/sax/parser.rb +199 -0
data/lib/nokogiri/xml/sax/parser_context.rb +129 -0
data/lib/nokogiri/xml/sax/push_parser.rb +64 -0
data/lib/nokogiri/xml/sax.rb +54 -0
data/lib/nokogiri/xml/schema.rb +140 -0
data/lib/nokogiri/xml/searchable.rb +274 -0
data/lib/nokogiri/xml/syntax_error.rb +94 -0
data/lib/nokogiri/xml/text.rb +11 -0
data/lib/nokogiri/xml/xpath/syntax_error.rb +13 -0
data/lib/nokogiri/xml/xpath.rb +21 -0
data/lib/nokogiri/xml/xpath_context.rb +27 -0
data/lib/nokogiri/xml.rb +65 -0
data/lib/nokogiri/xslt/stylesheet.rb +49 -0
data/lib/nokogiri/xslt.rb +129 -0
data/lib/nokogiri.rb +128 -0
data/lib/xsd/xmlparser/nokogiri.rb +105 -0
metadata +321 -0

data/lib/nokogiri/html.rb ADDED Viewed

@@ -0,0 +1,48 @@
+# coding: utf-8
+# frozen_string_literal: true
+require_relative "html4"
+module Nokogiri
+  # Alias for Nokogiri::HTML4
+  HTML = Nokogiri::HTML4
+  # :singleton-method: HTML
+  # :call-seq: HTML(input, url = nil, encoding = nil, options = XML::ParseOptions::DEFAULT_HTML, &block) → Nokogiri::HTML4::Document
+  #
+  # Parse HTML. Convenience method for Nokogiri::HTML4::Document.parse
+  # :nodoc:
+  define_singleton_method(:HTML, Nokogiri.method(:HTML4))
+  # 💡 This module/namespace is an alias for Nokogiri::HTML4 as of v1.12.0. Before v1.12.0,
+  #   Nokogiri::HTML4 did not exist, and this was the module/namespace for all HTML-related
+  #   classes.
+  module HTML
+    # 💡 This class is an alias for Nokogiri::HTML4::Document as of v1.12.0.
+    class Document < Nokogiri::XML::Document
+    end
+    # 💡 This class is an alias for Nokogiri::HTML4::DocumentFragment as of v1.12.0.
+    class DocumentFragment < Nokogiri::XML::DocumentFragment
+    end
+    # 💡 This class is an alias for Nokogiri::HTML4::Builder as of v1.12.0.
+    class Builder < Nokogiri::XML::Builder
+    end
+    module SAX
+      # 💡 This class is an alias for Nokogiri::HTML4::SAX::Parser as of v1.12.0.
+      class Parser < Nokogiri::XML::SAX::Parser
+      end
+      # 💡 This class is an alias for Nokogiri::HTML4::SAX::ParserContext as of v1.12.0.
+      class ParserContext < Nokogiri::XML::SAX::ParserContext
+      end
+      # 💡 This class is an alias for Nokogiri::HTML4::SAX::PushParser as of v1.12.0.
+      class PushParser
+      end
+    end
+  end
+end

data/lib/nokogiri/html4/builder.rb ADDED Viewed

@@ -0,0 +1,37 @@
+# frozen_string_literal: true
+module Nokogiri
+  module HTML4
+    ###
+    # Nokogiri HTML builder is used for building HTML documents.  It is very
+    # similar to the Nokogiri::XML::Builder.  In fact, you should go read the
+    # documentation for Nokogiri::XML::Builder before reading this
+    # documentation.
+    #
+    # == Synopsis:
+    #
+    # Create an HTML document with a body that has an onload attribute, and a
+    # span tag with a class of "bold" that has content of "Hello world".
+    #
+    #   builder = Nokogiri::HTML4::Builder.new do |doc|
+    #     doc.html {
+    #       doc.body(:onload => 'some_func();') {
+    #         doc.span.bold {
+    #           doc.text "Hello world"
+    #         }
+    #       }
+    #     }
+    #   end
+    #   puts builder.to_html
+    #
+    # The HTML builder inherits from the XML builder, so make sure to read the
+    # Nokogiri::XML::Builder documentation.
+    class Builder < Nokogiri::XML::Builder
+      ###
+      # Convert the builder to HTML
+      def to_html
+        @doc.to_html
+      end
+    end
+  end
+end

data/lib/nokogiri/html4/document.rb ADDED Viewed

@@ -0,0 +1,235 @@
+# coding: utf-8
+# frozen_string_literal: true
+require "pathname"
+module Nokogiri
+  module HTML4
+    class Document < Nokogiri::XML::Document
+      ###
+      # Get the meta tag encoding for this document.  If there is no meta tag,
+      # then nil is returned.
+      def meta_encoding
+        if (meta = at_xpath("//meta[@charset]"))
+          meta[:charset]
+        elsif (meta = meta_content_type)
+          meta["content"][/charset\s*=\s*([\w-]+)/i, 1]
+        end
+      end
+      ###
+      # Set the meta tag encoding for this document.
+      #
+      # If an meta encoding tag is already present, its content is
+      # replaced with the given text.
+      #
+      # Otherwise, this method tries to create one at an appropriate
+      # place supplying head and/or html elements as necessary, which
+      # is inside a head element if any, and before any text node or
+      # content element (typically <body>) if any.
+      #
+      # The result when trying to set an encoding that is different
+      # from the document encoding is undefined.
+      #
+      # Beware in CRuby, that libxml2 automatically inserts a meta tag
+      # into a head element.
+      def meta_encoding=(encoding)
+        if (meta = meta_content_type)
+          meta["content"] = format("text/html; charset=%s", encoding)
+          encoding
+        elsif (meta = at_xpath("//meta[@charset]"))
+          meta["charset"] = encoding
+        else
+          meta = XML::Node.new("meta", self)
+          if (dtd = internal_subset) && dtd.html5_dtd?
+            meta["charset"] = encoding
+          else
+            meta["http-equiv"] = "Content-Type"
+            meta["content"] = format("text/html; charset=%s", encoding)
+          end
+          if (head = at_xpath("//head"))
+            head.prepend_child(meta)
+          else
+            set_metadata_element(meta)
+          end
+          encoding
+        end
+      end
+      def meta_content_type
+        xpath("//meta[@http-equiv and boolean(@content)]").find do |node|
+          node["http-equiv"] =~ /\AContent-Type\z/i
+        end
+      end
+      private :meta_content_type
+      ###
+      # Get the title string of this document.  Return nil if there is
+      # no title tag.
+      def title
+        (title = at_xpath("//title")) && title.inner_text
+      end
+      ###
+      # Set the title string of this document.
+      #
+      # If a title element is already present, its content is replaced
+      # with the given text.
+      #
+      # Otherwise, this method tries to create one at an appropriate
+      # place supplying head and/or html elements as necessary, which
+      # is inside a head element if any, right after a meta
+      # encoding/charset tag if any, and before any text node or
+      # content element (typically <body>) if any.
+      def title=(text)
+        tnode = XML::Text.new(text, self)
+        if (title = at_xpath("//title"))
+          title.children = tnode
+          return text
+        end
+        title = XML::Node.new("title", self) << tnode
+        if (head = at_xpath("//head"))
+          head << title
+        elsif (meta = at_xpath("//meta[@charset]") || meta_content_type)
+          # better put after charset declaration
+          meta.add_next_sibling(title)
+        else
+          set_metadata_element(title)
+        end
+      end
+      def set_metadata_element(element) # rubocop:disable Naming/AccessorMethodName
+        if (head = at_xpath("//head"))
+          head << element
+        elsif (html = at_xpath("//html"))
+          head = html.prepend_child(XML::Node.new("head", self))
+          head.prepend_child(element)
+        elsif (first = children.find do |node|
+                 case node
+                 when XML::Element, XML::Text
+                   true
+                 end
+               end)
+          # We reach here only if the underlying document model
+          # allows <html>/<head> elements to be omitted and does not
+          # automatically supply them.
+          first.add_previous_sibling(element)
+        else
+          html = add_child(XML::Node.new("html", self))
+          head = html.add_child(XML::Node.new("head", self))
+          head.prepend_child(element)
+        end
+      end
+      private :set_metadata_element
+      ####
+      # Serialize Node using +options+. Save options can also be set using a block.
+      #
+      # See also Nokogiri::XML::Node::SaveOptions and Node@Serialization+and+Generating+Output.
+      #
+      # These two statements are equivalent:
+      #
+      #  node.serialize(:encoding => 'UTF-8', :save_with => FORMAT | AS_XML)
+      #
+      # or
+      #
+      #   node.serialize(:encoding => 'UTF-8') do |config|
+      #     config.format.as_xml
+      #   end
+      #
+      def serialize(options = {})
+        options[:save_with] ||= XML::Node::SaveOptions::DEFAULT_HTML
+        super
+      end
+      ####
+      # Create a Nokogiri::XML::DocumentFragment from +tags+
+      def fragment(tags = nil)
+        DocumentFragment.new(self, tags, root)
+      end
+      # :call-seq:
+      #   xpath_doctype() → Nokogiri::CSS::XPathVisitor::DoctypeConfig
+      #
+      # [Returns] The document type which determines CSS-to-XPath translation.
+      #
+      # See XPathVisitor for more information.
+      def xpath_doctype
+        Nokogiri::CSS::XPathVisitor::DoctypeConfig::HTML4
+      end
+      class << self
+        # :call-seq:
+        #   parse(input) { |options| ... } => Nokogiri::HTML4::Document
+        #   parse(input, url:, encoding:, options:) => Nokogiri::HTML4::Document
+        #
+        # Parse \HTML4 input from a String or IO object, and return a new HTML4::Document.
+        #
+        # [Required Parameters]
+        # - +input+ (String | IO) The content to be parsed.
+        #
+        # [Optional Keyword Arguments]
+        # - +url:+ (String) The base URI for this document.
+        #
+        # - +encoding:+ (String) The 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.
+        #
+        # - +options:+ (Nokogiri::XML::ParseOptions) Configuration object that determines some
+        #   behaviors during parsing. See ParseOptions for more information. The default value is
+        #   +ParseOptions::DEFAULT_HTML+.
+        #
+        # [Yields]
+        #   If a block is given, a Nokogiri::XML::ParseOptions object is yielded to the block which
+        #   can be configured before parsing. See Nokogiri::XML::ParseOptions for more information.
+        #
+        # [Returns] Nokogiri::HTML4::Document
+        def parse(
+          input,
+          url_ = nil, encoding_ = nil, options_ = XML::ParseOptions::DEFAULT_HTML,
+          url: url_, encoding: encoding_, options: options_
+        )
+          options = Nokogiri::XML::ParseOptions.new(options) if Integer === options
+          yield options if block_given?
+          url ||= input.respond_to?(:path) ? input.path : nil
+          if input.respond_to?(:encoding)
+            unless input.encoding == Encoding::ASCII_8BIT
+              encoding ||= input.encoding.name
+            end
+          end
+          if input.respond_to?(:read)
+            if input.is_a?(Pathname)
+              # resolve the Pathname to the file and open it as an IO object, see #2110
+              input = input.expand_path.open
+              url ||= input.path
+            end
+            unless encoding
+              input = EncodingReader.new(input)
+              begin
+                return read_io(input, url, encoding, options.to_i)
+              rescue EncodingReader::EncodingFound => e
+                encoding = e.found_encoding
+              end
+            end
+            return read_io(input, url, encoding, options.to_i)
+          end
+          # read_memory pukes on empty docs
+          if input.nil? || input.empty?
+            return encoding ? new.tap { |i| i.encoding = encoding } : new
+          end
+          encoding ||= EncodingReader.detect_encoding(input)
+          read_memory(input, url, encoding, options.to_i)
+        end
+      end
+    end
+  end
+end

data/lib/nokogiri/html4/document_fragment.rb ADDED Viewed

@@ -0,0 +1,166 @@
+# frozen_string_literal: true
+module Nokogiri
+  module HTML4
+    class DocumentFragment < Nokogiri::XML::DocumentFragment
+      #
+      # :call-seq:
+      #   parse(input) { |options| ... } → HTML4::DocumentFragment
+      #   parse(input, encoding:, options:) { |options| ... } → HTML4::DocumentFragment
+      #
+      # Parse \HTML4 fragment input from a String, and return a new HTML4::DocumentFragment. This
+      # method creates a new, empty HTML4::Document to contain the fragment.
+      #
+      # [Required Parameters]
+      # - +input+ (String | IO) The content to be parsed.
+      #
+      # [Optional Keyword Arguments]
+      # - +encoding:+ (String) The 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.
+      #
+      # - +options:+ (Nokogiri::XML::ParseOptions) Configuration object that determines some
+      #   behaviors during parsing. See ParseOptions for more information. The default value is
+      #   +ParseOptions::DEFAULT_HTML+.
+      #
+      # [Yields]
+      #   If a block is given, a Nokogiri::XML::ParseOptions object is yielded to the block which
+      #   can be configured before parsing. See ParseOptions for more information.
+      #
+      # [Returns] HTML4::DocumentFragment
+      #
+      # *Example:* Parsing a string
+      #
+      #   fragment = HTML4::DocumentFragment.parse("<div>Hello World</div>")
+      #
+      # *Example:* Parsing an IO
+      #
+      #   fragment = File.open("fragment.html") do |file|
+      #     HTML4::DocumentFragment.parse(file)
+      #   end
+      #
+      # *Example:* Specifying encoding
+      #
+      #   fragment = HTML4::DocumentFragment.parse(input, encoding: "EUC-JP")
+      #
+      # *Example:* Setting parse options dynamically
+      #
+      #   HTML4::DocumentFragment.parse("<div>Hello World") do |options|
+      #     options.huge.pedantic
+      #   end
+      #
+      def self.parse(
+        input,
+        encoding_ = nil, options_ = XML::ParseOptions::DEFAULT_HTML,
+        encoding: encoding_, options: options_,
+        &block
+      )
+        # TODO: this method should take a context node.
+        doc = HTML4::Document.new
+        if input.respond_to?(:read)
+          # Handle IO-like objects (IO, File, StringIO, etc.)
+          # The _read_ method of these objects doesn't accept an +encoding+ parameter.
+          # Encoding is usually set when the IO object is created or opened,
+          # or by using the _set_encoding_ method.
+          #
+          # 1. If +encoding+ is provided and the object supports _set_encoding_,
+          #    set the encoding before reading.
+          # 2. Read the content from the IO-like object.
+          #
+          # Note: After reading, the content's encoding will be:
+          # - The encoding set by _set_encoding_ if it was called
+          # - The default encoding of the IO object otherwise
+          #
+          # For StringIO specifically, _set_encoding_ affects only the internal string,
+          # not how the data is read out.
+          input.set_encoding(encoding) if encoding && input.respond_to?(:set_encoding)
+          input = input.read
+        end
+        encoding ||= if input.respond_to?(:encoding)
+          encoding = input.encoding
+          if encoding == ::Encoding::ASCII_8BIT
+            "UTF-8"
+          else
+            encoding.name
+          end
+        else
+          "UTF-8"
+        end
+        doc.encoding = encoding
+        new(doc, input, options: options, &block)
+      end
+      #
+      # :call-seq:
+      #   new(document) { |options| ... } → HTML4::DocumentFragment
+      #   new(document, input) { |options| ... } → HTML4::DocumentFragment
+      #   new(document, input, context:, options:) { |options| ... } → HTML4::DocumentFragment
+      #
+      # Parse \HTML4 fragment input from a String, and return a new HTML4::DocumentFragment.
+      #
+      # 💡 It's recommended to use either HTML4::DocumentFragment.parse or XML::Node#parse rather
+      # than call this method directly.
+      #
+      # [Required Parameters]
+      # - +document+ (HTML4::Document) The parent document to associate the returned fragment with.
+      #
+      # [Optional Parameters]
+      # - +input+ (String) The content to be parsed.
+      #
+      # [Optional Keyword Arguments]
+      # - +context:+ (Nokogiri::XML::Node) The <b>context node</b> for the subtree created. See
+      #   below for more information.
+      #
+      # - +options:+ (Nokogiri::XML::ParseOptions) Configuration object that determines some
+      #   behaviors during parsing. See ParseOptions for more information. The default value is
+      #   +ParseOptions::DEFAULT_HTML+.
+      #
+      # [Yields]
+      #   If a block is given, a Nokogiri::XML::ParseOptions object is yielded to the block which
+      #   can be configured before parsing. See ParseOptions for more information.
+      #
+      # [Returns] HTML4::DocumentFragment
+      #
+      # === Context \Node
+      #
+      # If a context node is specified using +context:+, then the fragment will be created by
+      # calling XML::Node#parse on that node, so the parser will behave as if that Node is the
+      # parent of the fragment subtree.
+      #
+      def initialize(
+        document, input = nil,
+        context_ = nil, options_ = XML::ParseOptions::DEFAULT_HTML,
+        context: context_, options: options_
+      ) # rubocop:disable Lint/MissingSuper
+        return self unless input
+        options = Nokogiri::XML::ParseOptions.new(options) if Integer === options
+        @parse_options = options
+        yield options if block_given?
+        if context
+          preexisting_errors = document.errors.dup
+          node_set = context.parse("<div>#{input}</div>", options)
+          node_set.first.children.each { |child| child.parent = self } unless node_set.empty?
+          self.errors = document.errors - preexisting_errors
+        else
+          # This is a horrible hack, but I don't care
+          path = if /^\s*?<body/i.match?(input)
+            "/html/body"
+          else
+            "/html/body/node()"
+          end
+          temp_doc = HTML4::Document.parse("<html><body>#{input}", nil, document.encoding, options)
+          temp_doc.xpath(path).each { |child| child.parent = self }
+          self.errors = temp_doc.errors
+        end
+        children
+      end
+    end
+  end
+end

data/lib/nokogiri/html4/element_description.rb ADDED Viewed

@@ -0,0 +1,25 @@
+# frozen_string_literal: true
+module Nokogiri
+  module HTML4
+    class ElementDescription
+      ###
+      # Is this element a block element?
+      def block?
+        !inline?
+      end
+      ###
+      # Convert this description to a string
+      def to_s
+        "#{name}: #{description}"
+      end
+      ###
+      # Inspection information
+      def inspect
+        "#<#{self.class.name}: #{name} #{description}>"
+      end
+    end
+  end
+end