nokogiri 1.18.0.rc1-x86_64-linux-gnu

data/lib/nokogiri/xml/node_set.rb

@@ -0,0 +1,449 @@
+# coding: utf-8
+# frozen_string_literal: true
+
+module Nokogiri
+  module XML
+    ####
+    # A NodeSet is an Enumerable that contains a list of Nokogiri::XML::Node objects.
+    #
+    # Typically a NodeSet is returned as a result of searching a Document via
+    # Nokogiri::XML::Searchable#css or Nokogiri::XML::Searchable#xpath.
+    #
+    # Note that the `#dup` and `#clone` methods perform shallow copies; these methods do not copy
+    # the Nodes contained in the NodeSet (similar to how Array and other Enumerable classes work).
+    class NodeSet
+      include Nokogiri::XML::Searchable
+      include Enumerable
+
+      # The Document this NodeSet is associated with
+      attr_accessor :document
+
+      # Create a NodeSet with +document+ defaulting to +list+
+      def initialize(document, list = [])
+        @document = document
+        document.decorate(self)
+        list.each { |x| self << x }
+        yield self if block_given?
+      end
+
+      ###
+      # Get the first element of the NodeSet.
+      def first(n = nil)
+        return self[0] unless n
+
+        list = []
+        [n, length].min.times { |i| list << self[i] }
+        list
+      end
+
+      ###
+      # Get the last element of the NodeSet.
+      def last
+        self[-1]
+      end
+
+      ###
+      # Is this NodeSet empty?
+      def empty?
+        length == 0
+      end
+
+      ###
+      # Returns the index of the first node in self that is == to +node+ or meets the given block. Returns nil if no match is found.
+      def index(node = nil)
+        if node
+          warn("given block not used") if block_given?
+          each_with_index { |member, j| return j if member == node }
+        elsif block_given?
+          each_with_index { |member, j| return j if yield(member) }
+        end
+        nil
+      end
+
+      ###
+      # Insert +datum+ before the first Node in this NodeSet
+      def before(datum)
+        first.before(datum)
+      end
+
+      ###
+      # Insert +datum+ after the last Node in this NodeSet
+      def after(datum)
+        last.after(datum)
+      end
+
+      alias_method :<<, :push
+      alias_method :remove, :unlink
+
+      ###
+      # call-seq: css *rules, [namespace-bindings, custom-pseudo-class]
+      #
+      # Search this node set for CSS +rules+. +rules+ must be one or more CSS
+      # selectors. For example:
+      #
+      # For more information see Nokogiri::XML::Searchable#css
+      def css(*args)
+        rules, handler, ns, _ = extract_params(args)
+        paths = css_rules_to_xpath(rules, ns)
+
+        inject(NodeSet.new(document)) do |set, node|
+          set + xpath_internal(node, paths, handler, ns, nil)
+        end
+      end
+
+      ###
+      # call-seq: xpath *paths, [namespace-bindings, variable-bindings, custom-handler-class]
+      #
+      # Search this node set for XPath +paths+. +paths+ must be one or more XPath
+      # queries.
+      #
+      # For more information see Nokogiri::XML::Searchable#xpath
+      def xpath(*args)
+        paths, handler, ns, binds = extract_params(args)
+
+        inject(NodeSet.new(document)) do |set, node|
+          set + xpath_internal(node, paths, handler, ns, binds)
+        end
+      end
+
+      ###
+      # call-seq: search *paths, [namespace-bindings, xpath-variable-bindings, custom-handler-class]
+      #
+      # Search this object for +paths+, and return only the first
+      # result. +paths+ must be one or more XPath or CSS queries.
+      #
+      # See Searchable#search for more information.
+      #
+      # Or, if passed an integer, index into the NodeSet:
+      #
+      #   node_set.at(3) # same as node_set[3]
+      #
+      def at(*args)
+        if args.length == 1 && args.first.is_a?(Numeric)
+          return self[args.first]
+        end
+
+        super
+      end
+      alias_method :%, :at
+
+      ###
+      # Filter this list for nodes that match +expr+
+      def filter(expr)
+        find_all { |node| node.matches?(expr) }
+      end
+
+      ###
+      # Add the class attribute +name+ to all Node objects in the
+      # NodeSet.
+      #
+      # See Nokogiri::XML::Node#add_class for more information.
+      def add_class(name)
+        each do |el|
+          el.add_class(name)
+        end
+        self
+      end
+
+      ###
+      # Append the class attribute +name+ to all Node objects in the
+      # NodeSet.
+      #
+      # See Nokogiri::XML::Node#append_class for more information.
+      def append_class(name)
+        each do |el|
+          el.append_class(name)
+        end
+        self
+      end
+
+      ###
+      # Remove the class attribute +name+ from all Node objects in the
+      # NodeSet.
+      #
+      # See Nokogiri::XML::Node#remove_class for more information.
+      def remove_class(name = nil)
+        each do |el|
+          el.remove_class(name)
+        end
+        self
+      end
+
+      ###
+      # Set attributes on each Node in the NodeSet, or get an
+      # attribute from the first Node in the NodeSet.
+      #
+      # To get an attribute from the first Node in a NodeSet:
+      #
+      #   node_set.attr("href") # => "https://www.nokogiri.org"
+      #
+      # Note that an empty NodeSet will return nil when +#attr+ is called as a getter.
+      #
+      # To set an attribute on each node, +key+ can either be an
+      # attribute name, or a Hash of attribute names and values. When
+      # called as a setter, +#attr+ returns the NodeSet.
+      #
+      # If +key+ is an attribute name, then either +value+ or +block+
+      # must be passed.
+      #
+      # If +key+ is a Hash then attributes will be set for each
+      # key/value pair:
+      #
+      #   node_set.attr("href" => "https://www.nokogiri.org", "class" => "member")
+      #
+      # If +value+ is passed, it will be used as the attribute value
+      # for all nodes:
+      #
+      #   node_set.attr("href", "https://www.nokogiri.org")
+      #
+      # If +block+ is passed, it will be called on each Node object in
+      # the NodeSet and the return value used as the attribute value
+      # for that node:
+      #
+      #   node_set.attr("class") { |node| node.name }
+      #
+      def attr(key, value = nil, &block)
+        unless key.is_a?(Hash) || (key && (value || block))
+          return first&.attribute(key)
+        end
+
+        hash = key.is_a?(Hash) ? key : { key => value }
+
+        hash.each do |k, v|
+          each do |node|
+            node[k] = v || yield(node)
+          end
+        end
+
+        self
+      end
+      alias_method :set, :attr
+      alias_method :attribute, :attr
+
+      ###
+      # Remove the attributed named +name+ from all Node objects in the NodeSet
+      def remove_attr(name)
+        each { |el| el.delete(name) }
+        self
+      end
+      alias_method :remove_attribute, :remove_attr
+
+      ###
+      # Iterate over each node, yielding  to +block+
+      def each
+        return to_enum unless block_given?
+
+        0.upto(length - 1) do |x|
+          yield self[x]
+        end
+        self
+      end
+
+      ###
+      # Get the inner text of all contained Node objects
+      #
+      # Note: This joins the text of all Node objects in the NodeSet:
+      #
+      #    doc = Nokogiri::XML('<xml><a><d>foo</d><d>bar</d></a></xml>')
+      #    doc.css('d').text # => "foobar"
+      #
+      # Instead, if you want to return the text of all nodes in the NodeSet:
+      #
+      #    doc.css('d').map(&:text) # => ["foo", "bar"]
+      #
+      # See Nokogiri::XML::Node#content for more information.
+      def inner_text
+        collect(&:inner_text).join("")
+      end
+      alias_method :text, :inner_text
+
+      ###
+      # Get the inner html of all contained Node objects
+      def inner_html(*args)
+        collect { |j| j.inner_html(*args) }.join("")
+      end
+
+      # :call-seq:
+      #   wrap(markup) -> self
+      #   wrap(node) -> self
+      #
+      # Wrap each member of this NodeSet with the node parsed from +markup+ or a dup of the +node+.
+      #
+      # [Parameters]
+      # - *markup* (String)
+      #   Markup that is parsed, once per member of the NodeSet, and used as the wrapper. Each
+      #   node's parent, if it exists, is used as the context node for parsing; otherwise the
+      #   associated document is used. If the parsed fragment has multiple roots, the first root
+      #   node is used as the wrapper.
+      # - *node* (Nokogiri::XML::Node)
+      #   An element that is `#dup`ed and used as the wrapper.
+      #
+      # [Returns] +self+, to support chaining.
+      #
+      # ⚠ Note that if a +String+ is passed, the markup will be parsed <b>once per node</b> in the
+      # NodeSet. You can avoid this overhead in cases where you know exactly the wrapper you wish to
+      # use by passing a +Node+ instead.
+      #
+      # Also see Node#wrap
+      #
+      # *Example* with a +String+ argument:
+      #
+      #   doc = Nokogiri::HTML5(<<~HTML)
+      #     <html><body>
+      #       <a>a</a>
+      #       <a>b</a>
+      #       <a>c</a>
+      #       <a>d</a>
+      #     </body></html>
+      #   HTML
+      #   doc.css("a").wrap("<div></div>")
+      #   doc.to_html
+      #   # => <html><head></head><body>
+      #   #      <div><a>a</a></div>
+      #   #      <div><a>b</a></div>
+      #   #      <div><a>c</a></div>
+      #   #      <div><a>d</a></div>
+      #   #    </body></html>
+      #
+      # *Example* with a +Node+ argument
+      #
+      # 💡 Note that this is faster than the equivalent call passing a +String+ because it avoids
+      # having to reparse the wrapper markup for each node.
+      #
+      #   doc = Nokogiri::HTML5(<<~HTML)
+      #     <html><body>
+      #       <a>a</a>
+      #       <a>b</a>
+      #       <a>c</a>
+      #       <a>d</a>
+      #     </body></html>
+      #   HTML
+      #   doc.css("a").wrap(doc.create_element("div"))
+      #   doc.to_html
+      #   # => <html><head></head><body>
+      #   #      <div><a>a</a></div>
+      #   #      <div><a>b</a></div>
+      #   #      <div><a>c</a></div>
+      #   #      <div><a>d</a></div>
+      #   #    </body></html>
+      #
+      def wrap(node_or_tags)
+        map { |node| node.wrap(node_or_tags) }
+        self
+      end
+
+      ###
+      # Convert this NodeSet to a string.
+      def to_s
+        map(&:to_s).join
+      end
+
+      ###
+      # Convert this NodeSet to HTML
+      def to_html(*args)
+        if Nokogiri.jruby?
+          options = args.first.is_a?(Hash) ? args.shift : {}
+          options[:save_with] ||= Node::SaveOptions::DEFAULT_HTML
+          args.insert(0, options)
+        end
+        if empty?
+          encoding = (args.first.is_a?(Hash) ? args.first[:encoding] : nil)
+          encoding ||= document.encoding
+          encoding.nil? ? "" : "".encode(encoding)
+        else
+          map { |x| x.to_html(*args) }.join
+        end
+      end
+
+      ###
+      # Convert this NodeSet to XHTML
+      def to_xhtml(*args)
+        map { |x| x.to_xhtml(*args) }.join
+      end
+
+      ###
+      # Convert this NodeSet to XML
+      def to_xml(*args)
+        map { |x| x.to_xml(*args) }.join
+      end
+
+      alias_method :size, :length
+      alias_method :to_ary, :to_a
+
+      ###
+      # Removes the last element from set and returns it, or +nil+ if
+      # the set is empty
+      def pop
+        return if length == 0
+
+        delete(last)
+      end
+
+      ###
+      # Returns the first element of the NodeSet and removes it.  Returns
+      # +nil+ if the set is empty.
+      def shift
+        return if length == 0
+
+        delete(first)
+      end
+
+      ###
+      # Equality -- Two NodeSets are equal if the contain the same number
+      # of elements and if each element is equal to the corresponding
+      # element in the other NodeSet
+      def ==(other)
+        return false unless other.is_a?(Nokogiri::XML::NodeSet)
+        return false unless length == other.length
+
+        each_with_index do |node, i|
+          return false unless node == other[i]
+        end
+        true
+      end
+
+      ###
+      # Returns a new NodeSet containing all the children of all the nodes in
+      # the NodeSet
+      def children
+        node_set = NodeSet.new(document)
+        each do |node|
+          node.children.each { |n| node_set.push(n) }
+        end
+        node_set
+      end
+
+      ###
+      # Returns a new NodeSet containing all the nodes in the NodeSet
+      # in reverse order
+      def reverse
+        node_set = NodeSet.new(document)
+        (length - 1).downto(0) do |x|
+          node_set.push(self[x])
+        end
+        node_set
+      end
+
+      ###
+      # Return a nicely formatted string representation
+      def inspect
+        "[#{map(&:inspect).join(", ")}]"
+      end
+
+      alias_method :+, :|
+
+      #
+      #  :call-seq: deconstruct() → Array
+      #
+      #  Returns the members of this NodeSet as an array, to use in pattern matching.
+      #
+      #  Since v1.14.0
+      #
+      def deconstruct
+        to_a
+      end
+
+      IMPLIED_XPATH_CONTEXTS = [".//", "self::"].freeze # :nodoc:
+    end
+  end
+end

data/lib/nokogiri/xml/notation.rb

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+module Nokogiri
+  module XML
+    # Struct representing an {XML Schema Notation}[https://www.w3.org/TR/xml/#Notations]
+    class Notation < Struct.new(:name, :public_id, :system_id)
+      # dead comment to ensure rdoc processing
+
+      # :attr: name (String)
+      # The name for the element.
+
+      # :attr: public_id (String)
+      # The URI corresponding to the public identifier
+
+      # :attr: system_id (String,nil)
+      # The URI corresponding to the system identifier
+    end
+  end
+end

data/lib/nokogiri/xml/parse_options.rb

@@ -0,0 +1,213 @@
+# coding: utf-8
+# frozen_string_literal: true
+
+module Nokogiri
+  module XML
+    # Options that control the parsing behavior for XML::Document, XML::DocumentFragment,
+    # HTML4::Document, HTML4::DocumentFragment, XSLT::Stylesheet, and XML::Schema.
+    #
+    # These options directly expose libxml2's parse options, which are all boolean in the sense that
+    # an option is "on" or "off".
+    #
+    # 💡 Note that HTML5 parsing has a separate, orthogonal set of options due to the nature of the
+    # HTML5 specification. See Nokogiri::HTML5.
+    #
+    # ⚠ Not all parse options are supported on JRuby. Nokogiri will attempt to invoke the equivalent
+    # behavior in Xerces/NekoHTML on JRuby when it's possible.
+    #
+    # == Setting and unsetting parse options
+    #
+    # You can build your own combinations of parse options by using any of the following methods:
+    #
+    # [ParseOptions method chaining]
+    #
+    #   Every option has an equivalent method in lowercase. You can chain these methods together to
+    #   set various combinations.
+    #
+    #     # Set the HUGE & PEDANTIC options
+    #     po = Nokogiri::XML::ParseOptions.new.huge.pedantic
+    #     doc = Nokogiri::XML::Document.parse(xml, nil, nil, po)
+    #
+    #   Every option has an equivalent <code>no{option}</code> method in lowercase. You can call these
+    #   methods on an instance of ParseOptions to unset the option.
+    #
+    #     # Set the HUGE & PEDANTIC options
+    #     po = Nokogiri::XML::ParseOptions.new.huge.pedantic
+    #
+    #     # later we want to modify the options
+    #     po.nohuge # Unset the HUGE option
+    #     po.nopedantic # Unset the PEDANTIC option
+    #
+    #   💡 Note that some options begin with "no" leading to the logical but perhaps unintuitive
+    #   double negative:
+    #
+    #     po.nocdata # Set the NOCDATA parse option
+    #     po.nonocdata # Unset the NOCDATA parse option
+    #
+    #   💡 Note that negation is not available for STRICT, which is itself a negation of all other
+    #   features.
+    #
+    #
+    # [Using Ruby Blocks]
+    #
+    #   Most parsing methods will accept a block for configuration of parse options, and we
+    #   recommend chaining the setter methods:
+    #
+    #     doc = Nokogiri::XML::Document.parse(xml) { |config| config.huge.pedantic }
+    #
+    #
+    # [ParseOptions constants]
+    #
+    #   You can also use the constants declared under Nokogiri::XML::ParseOptions to set various
+    #   combinations. They are bits in a bitmask, and so can be combined with bitwise operators:
+    #
+    #     po = Nokogiri::XML::ParseOptions.new(Nokogiri::XML::ParseOptions::HUGE | Nokogiri::XML::ParseOptions::PEDANTIC)
+    #     doc = Nokogiri::XML::Document.parse(xml, nil, nil, po)
+    #
+    class ParseOptions
+      # Strict parsing
+      STRICT      = 0
+
+      # Recover from errors. On by default for XML::Document, XML::DocumentFragment,
+      # HTML4::Document, HTML4::DocumentFragment, XSLT::Stylesheet, and XML::Schema.
+      RECOVER     = 1 << 0
+
+      # Substitute entities. Off by default.
+      #
+      # ⚠ This option enables entity substitution, contrary to what the name implies.
+      #
+      # ⚠ <b>It is UNSAFE to set this option</b> when parsing untrusted documents.
+      NOENT       = 1 << 1
+
+      # Load external subsets. On by default for XSLT::Stylesheet.
+      #
+      # ⚠ <b>It is UNSAFE to set this option</b> when parsing untrusted documents.
+      DTDLOAD     = 1 << 2
+
+      # Default DTD attributes. On by default for XSLT::Stylesheet.
+      DTDATTR     = 1 << 3
+
+      # Validate with the DTD. Off by default.
+      DTDVALID    = 1 << 4
+
+      # Suppress error reports. On by default for HTML4::Document and HTML4::DocumentFragment
+      NOERROR     = 1 << 5
+
+      # Suppress warning reports. On by default for HTML4::Document and HTML4::DocumentFragment
+      NOWARNING   = 1 << 6
+
+      # Enable pedantic error reporting. Off by default.
+      PEDANTIC    = 1 << 7
+
+      # Remove blank nodes. Off by default.
+      NOBLANKS    = 1 << 8
+
+      # Use the SAX1 interface internally. Off by default.
+      SAX1        = 1 << 9
+
+      # Implement XInclude substitution. Off by default.
+      XINCLUDE    = 1 << 10
+
+      # Forbid network access. On by default for XML::Document, XML::DocumentFragment,
+      # HTML4::Document, HTML4::DocumentFragment, XSLT::Stylesheet, and XML::Schema.
+      #
+      # ⚠ <b>It is UNSAFE to unset this option</b> when parsing untrusted documents.
+      NONET       = 1 << 11
+
+      # Do not reuse the context dictionary. Off by default.
+      NODICT      = 1 << 12
+
+      # Remove redundant namespaces declarations. Off by default.
+      NSCLEAN     = 1 << 13
+
+      # Merge CDATA as text nodes. On by default for XSLT::Stylesheet.
+      NOCDATA     = 1 << 14
+
+      # Do not generate XInclude START/END nodes. Off by default.
+      NOXINCNODE  = 1 << 15
+
+      # Compact small text nodes. Off by default.
+      #
+      # ⚠ No modification of the DOM tree is allowed after parsing. libxml2 may crash if you try to
+      # modify the tree.
+      COMPACT     = 1 << 16
+
+      # Parse using XML-1.0 before update 5. Off by default
+      OLD10       = 1 << 17
+
+      # Do not fixup XInclude xml:base uris. Off by default
+      NOBASEFIX   = 1 << 18
+
+      # Relax any hardcoded limit from the parser. Off by default.
+      #
+      # ⚠ <b>It is UNSAFE to set this option</b> when parsing untrusted documents.
+      HUGE        = 1 << 19
+
+      # Support line numbers up to <code>long int</code> (default is a <code>short int</code>). On
+      # by default for for XML::Document, XML::DocumentFragment, HTML4::Document,
+      # HTML4::DocumentFragment, XSLT::Stylesheet, and XML::Schema.
+      BIG_LINES   = 1 << 22
+
+      # The options mask used by default for parsing XML::Document and XML::DocumentFragment
+      DEFAULT_XML  = RECOVER | NONET | BIG_LINES
+
+      # The options mask used by default used for parsing XSLT::Stylesheet
+      DEFAULT_XSLT = RECOVER | NONET | NOENT | DTDLOAD | DTDATTR | NOCDATA | BIG_LINES
+
+      # The options mask used by default used for parsing HTML4::Document and HTML4::DocumentFragment
+      DEFAULT_HTML = RECOVER | NOERROR | NOWARNING | NONET | BIG_LINES
+
+      # The options mask used by default used for parsing XML::Schema
+      DEFAULT_SCHEMA = NONET | BIG_LINES
+
+      attr_accessor :options
+
+      def initialize(options = STRICT)
+        @options = options
+      end
+
+      constants.each do |constant|
+        next if constant.to_sym == :STRICT
+
+        class_eval <<~RUBY, __FILE__, __LINE__ + 1
+          def #{constant.downcase}
+            @options |= #{constant}
+            self
+          end
+
+          def no#{constant.downcase}
+            @options &= ~#{constant}
+            self
+          end
+
+          def #{constant.downcase}?
+            #{constant} & @options == #{constant}
+          end
+        RUBY
+      end
+
+      def strict
+        @options &= ~RECOVER
+        self
+      end
+
+      def strict?
+        @options & RECOVER == STRICT
+      end
+
+      def ==(other)
+        other.to_i == to_i
+      end
+
+      alias_method :to_i, :options
+
+      def inspect
+        options = []
+        self.class.constants.each do |k|
+          options << k.downcase if send(:"#{k.downcase}?")
+        end
+        super.sub(/>$/, " " + options.join(", ") + ">")
+      end
+    end
+  end
+end

data/lib/nokogiri/xml/pp/character_data.rb

@@ -0,0 +1,21 @@
+# frozen_string_literal: true
+
+module Nokogiri
+  module XML
+    # :nodoc: all
+    module PP
+      module CharacterData
+        def pretty_print(pp)
+          nice_name = self.class.name.split("::").last
+          pp.group(2, "#(#{nice_name} ", ")") do
+            pp.pp(text)
+          end
+        end
+
+        def inspect
+          "#<#{self.class.name}:#{format("0x%x", object_id)} #{text.inspect}>"
+        end
+      end
+    end
+  end
+end