rexml 3.2.6 → 3.4.2

data/lib/rexml/element.rb

@@ -7,14 +7,6 @@ require_relative "xpath"
 require_relative "parseexception"
 
 module REXML
-  # An implementation note about namespaces:
-  # As we parse, when we find namespaces we put them in a hash and assign
-  # them a unique ID.  We then convert the namespace prefix for the node
-  # to the unique ID.  This makes namespace lookup much faster for the
-  # cost of extra memory use.  We save the namespace prefix for the
-  # context node and convert it back when we write it.
-  @@namespaces = {}
-
   # An \REXML::Element object represents an XML element.
   #
   # An element:
@@ -449,9 +441,14 @@ module REXML
     # Related: #root_node, #document.
     #
     def root
-      return elements[1] if self.kind_of? Document
-      return self if parent.kind_of? Document or parent.nil?
-      return parent.root
+      target = self
+      while target
+        return target.elements[1] if target.kind_of? Document
+        parent = target.parent
+        return target if parent.kind_of? Document or parent.nil?
+        target = parent
+      end
+      nil
     end
 
     # :call-seq:
@@ -476,8 +473,7 @@ module REXML
     # Related: #root, #root_node.
     #
     def document
-      rt = root
-      rt.parent if rt
+      root&.parent
     end
 
     # :call-seq:
@@ -569,7 +565,7 @@ module REXML
       prefixes = []
       prefixes = parent.prefixes if parent
       prefixes |= attributes.prefixes
-      return prefixes
+      prefixes
     end
 
     # :call-seq:
@@ -592,10 +588,12 @@ module REXML
     #   d.elements['//c'].namespaces # => {"x"=>"1", "y"=>"2", "z"=>"3"}
     #
     def namespaces
-      namespaces = {}
-      namespaces = parent.namespaces if parent
-      namespaces = namespaces.merge( attributes.namespaces )
-      return namespaces
+      namespaces_cache = document&.__send__(:namespaces_cache)
+      if namespaces_cache
+        namespaces_cache[self] ||= calculate_namespaces
+      else
+        calculate_namespaces
+      end
     end
 
     # :call-seq:
@@ -622,15 +620,11 @@ module REXML
       if prefix.nil?
         prefix = prefix()
       end
-      if prefix == ''
-        prefix = "xmlns"
-      else
-        prefix = "xmlns:#{prefix}" unless prefix[0,5] == 'xmlns'
-      end
-      ns = attributes[ prefix ]
-      ns = parent.namespace(prefix) if ns.nil? and parent
+      prefix = (prefix == '') ? 'xmlns' : prefix.delete_prefix("xmlns:")
+      ns = namespaces[prefix]
+
       ns = '' if ns.nil? and prefix == 'xmlns'
-      return ns
+      ns
     end
 
     # :call-seq:
@@ -962,7 +956,7 @@ module REXML
     def next_element
       element = next_sibling
       element = element.next_sibling until element.nil? or element.kind_of? Element
-      return element
+      element
     end
 
     # :call-seq:
@@ -978,7 +972,7 @@ module REXML
     def previous_element
       element = previous_sibling
       element = element.previous_sibling until element.nil? or element.kind_of? Element
-      return element
+      element
     end
 
 
@@ -1028,8 +1022,7 @@ module REXML
     #
     def text( path = nil )
       rv = get_text(path)
-      return rv.value unless rv.nil?
-      nil
+      rv&.value
     end
 
     # :call-seq:
@@ -1057,7 +1050,7 @@ module REXML
       else
         rv = @children.find { |node| node.kind_of? Text }
       end
-      return rv
+      rv
     end
 
     # :call-seq:
@@ -1101,7 +1094,7 @@ module REXML
           old_text.replace_with( text )
         end
       end
-      return self
+      self
     end
 
     # :call-seq:
@@ -1152,7 +1145,7 @@ module REXML
         text = Text.new( text, whitespace(), nil, raw() )
       end
       self << text unless text.nil?
-      return self
+      self
     end
 
     # :call-seq:
@@ -1196,7 +1189,7 @@ module REXML
         cur = cur.parent
         path_elements << __to_xpath_helper( cur )
       end
-      return path_elements.reverse.join( "/" )
+      path_elements.reverse.join( "/" )
     end
 
     #################################################
@@ -1284,16 +1277,11 @@ module REXML
     #   document.root.attribute("x", "a") # => a:x='a:x'
     #
     def attribute( name, namespace=nil )
-      prefix = nil
-      if namespaces.respond_to? :key
-        prefix = namespaces.key(namespace) if namespace
-      else
-        prefix = namespaces.index(namespace) if namespace
-      end
+      prefix = namespaces.key(namespace) if namespace
       prefix = nil if prefix == 'xmlns'
 
       ret_val =
-        attributes.get_attribute( "#{prefix ? prefix + ':' : ''}#{name}" )
+        attributes.get_attribute( prefix ? "#{prefix}:#{name}" : name )
 
       return ret_val unless ret_val.nil?
       return nil if prefix.nil?
@@ -1303,7 +1291,6 @@ module REXML
       return nil unless ( namespaces[ prefix ] == namespaces[ 'xmlns' ] )
 
       attributes.get_attribute( name )
-
     end
 
     # :call-seq:
@@ -1317,7 +1304,7 @@ module REXML
     #   b.has_attributes? # => false
     #
     def has_attributes?
-      return !@attributes.empty?
+      !@attributes.empty?
     end
 
     # :call-seq:
@@ -1506,7 +1493,7 @@ module REXML
     #  doc.write( out )     #-> doc is written to the string 'out'
     #  doc.write( $stdout ) #-> doc written to the console
     def write(output=$stdout, indent=-1, transitive=false, ie_hack=false)
-      Kernel.warn("#{self.class.name}.write is deprecated.  See REXML::Formatters", uplevel: 1)
+      Kernel.warn("#{self.class.name}#write is deprecated.  See REXML::Formatters", uplevel: 1)
       formatter = if indent > -1
           if transitive
             require_relative "formatters/transitive"
@@ -1520,8 +1507,15 @@ module REXML
       formatter.write( self, output )
     end
 
-
     private
+    def calculate_namespaces
+      if parent
+        parent.namespaces.merge(attributes.namespaces)
+      else
+        attributes.namespaces
+      end
+    end
+
     def __to_xpath_helper node
       rv = node.expanded_name.clone
       if node.parent
@@ -1688,11 +1682,7 @@ module REXML
           (num += 1) == index
         }
       else
-        return XPath::first( @element, index )
-        #{ |element|
-        #       return element if element.kind_of? Element
-        #}
-        #return nil
+        XPath::first( @element, index )
       end
     end
 
@@ -1739,7 +1729,7 @@ module REXML
       else
         previous.replace_with element
       end
-      return previous
+      previous
     end
 
     # :call-seq:
@@ -1778,7 +1768,7 @@ module REXML
         child == element
       end
       return rv if found == element
-      return -1
+      -1
     end
 
     # :call-seq:
@@ -1857,7 +1847,7 @@ module REXML
         @element.delete element
         element.remove
       end
-      return rv
+      rv
     end
 
     # :call-seq:
@@ -2184,8 +2174,7 @@ module REXML
     #
     def [](name)
       attr = get_attribute(name)
-      return attr.value unless attr.nil?
-      return nil
+      attr&.value
     end
 
     # :call-seq:
@@ -2328,11 +2317,11 @@ module REXML
             return attr
           end
         end
-        element_document = @element.document
-        if element_document and element_document.doctype
+        doctype = @element.document&.doctype
+        if doctype
           expn = @element.expanded_name
-          expn = element_document.doctype.name if expn.size == 0
-          attr_val = element_document.doctype.attribute_of(expn, name)
+          expn = doctype.name if expn.size == 0
+          attr_val = doctype.attribute_of(expn, name)
           return Attribute.new( name, attr_val ) if attr_val
         end
         return nil
@@ -2340,7 +2329,7 @@ module REXML
       if attr.kind_of? Hash
         attr = attr[ @element.prefix ]
       end
-      return attr
+      attr
     end
 
     # :call-seq:
@@ -2374,8 +2363,9 @@ module REXML
       end
 
       unless value.kind_of? Attribute
-        if @element.document and @element.document.doctype
-          value = Text::normalize( value, @element.document.doctype )
+        doctype = @element.document&.doctype
+        if doctype
+          value = Text::normalize( value, doctype )
         else
           value = Text::normalize( value, nil )
         end
@@ -2388,23 +2378,12 @@ module REXML
       elsif old_attr.kind_of? Hash
         old_attr[value.prefix] = value
       elsif old_attr.prefix != value.prefix
-        # Check for conflicting namespaces
-        if value.prefix != "xmlns" and old_attr.prefix != "xmlns"
-          old_namespace = old_attr.namespace
-          new_namespace = value.namespace
-          if old_namespace == new_namespace
-            raise ParseException.new(
-                    "Namespace conflict in adding attribute \"#{value.name}\": "+
-                    "Prefix \"#{old_attr.prefix}\" = \"#{old_namespace}\" and "+
-                    "prefix \"#{value.prefix}\" = \"#{new_namespace}\"")
-          end
-        end
         store value.name, {old_attr.prefix => old_attr,
                            value.prefix    => value}
       else
         store value.name, value
       end
-      return @element
+      @element
     end
 
     # :call-seq:
@@ -2423,10 +2402,11 @@ module REXML
       each_attribute do |attribute|
         ns << attribute.name if attribute.prefix == 'xmlns'
       end
-      if @element.document and @element.document.doctype
+      doctype = @element.document&.doctype
+      if doctype
         expn = @element.expanded_name
-        expn = @element.document.doctype.name if expn.size == 0
-        @element.document.doctype.attributes_of(expn).each {
+        expn = doctype.name if expn.size == 0
+        doctype.attributes_of(expn).each {
           |attribute|
           ns << attribute.name if attribute.prefix == 'xmlns'
         }
@@ -2448,10 +2428,11 @@ module REXML
       each_attribute do |attribute|
         namespaces[attribute.name] = attribute.value if attribute.prefix == 'xmlns' or attribute.name == 'xmlns'
       end
-      if @element.document and @element.document.doctype
+      doctype = @element.document&.doctype
+      if doctype
         expn = @element.expanded_name
-        expn = @element.document.doctype.name if expn.size == 0
-        @element.document.doctype.attributes_of(expn).each {
+        expn = doctype.name if expn.size == 0
+        doctype.attributes_of(expn).each {
           |attribute|
           namespaces[attribute.name] = attribute.value if attribute.prefix == 'xmlns' or attribute.name == 'xmlns'
         }
@@ -2506,9 +2487,7 @@ module REXML
           old.each_value{|v| repl = v}
           store name, repl
         end
-      elsif old.nil?
-        return @element
-      else # the supplied attribute is a top-level one
+      elsif old # the supplied attribute is a top-level one
         super(name)
       end
       @element
@@ -2562,7 +2541,7 @@ module REXML
         rv << attribute if attribute.expanded_name == name
       }
       rv.each{ |attr| attr.remove }
-      return rv
+      rv
     end
 
     # :call-seq:

data/lib/rexml/encoding.rb

@@ -5,7 +5,7 @@ module REXML
     # ID ---> Encoding name
     attr_reader :encoding
     def encoding=(encoding)
-      encoding = encoding.name if encoding.is_a?(Encoding)
+      encoding = encoding.name if encoding.is_a?(::Encoding)
       if encoding.is_a?(String)
         original_encoding = encoding
         encoding = find_encoding(encoding)
@@ -13,12 +13,9 @@ module REXML
           raise ArgumentError, "Bad encoding name #{original_encoding}"
         end
       end
+      encoding = encoding.upcase if encoding
       return false if defined?(@encoding) and encoding == @encoding
-      if encoding
-        @encoding = encoding.upcase
-      else
-        @encoding = 'UTF-8'
-      end
+      @encoding = encoding || "UTF-8"
       true
     end
 

data/lib/rexml/entity.rb

@@ -12,6 +12,7 @@ module REXML
     EXTERNALID = "(?:(?:(SYSTEM)\\s+#{SYSTEMLITERAL})|(?:(PUBLIC)\\s+#{PUBIDLITERAL}\\s+#{SYSTEMLITERAL}))"
     NDATADECL = "\\s+NDATA\\s+#{NAME}"
     PEREFERENCE = "%#{NAME};"
+    PEREFERENCE_RE = /#{PEREFERENCE}/um
     ENTITYVALUE = %Q{((?:"(?:[^%&"]|#{PEREFERENCE}|#{REFERENCE})*")|(?:'([^%&']|#{PEREFERENCE}|#{REFERENCE})*'))}
     PEDEF = "(?:#{ENTITYVALUE}|#{EXTERNALID})"
     ENTITYDEF = "(?:#{ENTITYVALUE}|(?:#{EXTERNALID}(#{NDATADECL})?))"
@@ -19,7 +20,7 @@ module REXML
     GEDECL = "<!ENTITY\\s+#{NAME}\\s+#{ENTITYDEF}\\s*>"
     ENTITYDECL = /\s*(?:#{GEDECL})|(?:#{PEDECL})/um
 
-    attr_reader :name, :external, :ref, :ndata, :pubid
+    attr_reader :name, :external, :ref, :ndata, :pubid, :value
 
     # Create a new entity.  Simple entities can be constructed by passing a
     # name, value to the constructor; this creates a generic, plain entity
@@ -68,14 +69,14 @@ module REXML
     end
 
     # Evaluates to the unnormalized value of this entity; that is, replacing
-    # all entities -- both %ent; and &ent; entities.  This differs from
-    # +value()+ in that +value+ only replaces %ent; entities.
+    # &ent; entities.
     def unnormalized
-      document.record_entity_expansion unless document.nil?
-      v = value()
-      return nil if v.nil?
-      @unnormalized = Text::unnormalize(v, parent)
-      @unnormalized
+      document&.record_entity_expansion
+
+      return nil if @value.nil?
+
+      @unnormalized = Text::unnormalize(@value, parent,
+                                        entity_expansion_text_limit: document&.entity_expansion_text_limit)
     end
 
     #once :unnormalized
@@ -121,46 +122,6 @@ module REXML
       write rv
       rv
     end
-
-    PEREFERENCE_RE = /#{PEREFERENCE}/um
-    # Returns the value of this entity.  At the moment, only internal entities
-    # are processed.  If the value contains internal references (IE,
-    # %blah;), those are replaced with their values.  IE, if the doctype
-    # contains:
-    #  <!ENTITY % foo "bar">
-    #  <!ENTITY yada "nanoo %foo; nanoo>
-    # then:
-    #  doctype.entity('yada').value   #-> "nanoo bar nanoo"
-    def value
-      @resolved_value ||= resolve_value
-    end
-
-    def parent=(other)
-      @resolved_value = nil
-      super
-    end
-
-    private
-    def resolve_value
-      return nil if @value.nil?
-      return @value unless @value.match?(PEREFERENCE_RE)
-
-      matches = @value.scan(PEREFERENCE_RE)
-      rv = @value.clone
-      if @parent
-        sum = 0
-        matches.each do |entity_reference|
-          entity_value = @parent.entity( entity_reference[0] )
-          if sum + entity_value.bytesize > Security.entity_expansion_text_limit
-            raise "entity expansion has grown too large"
-          else
-            sum += entity_value.bytesize
-          end
-          rv.gsub!( /%#{entity_reference.join};/um, entity_value )
-        end
-      end
-      rv
-    end
   end
 
   # This is a set of entity constants -- the ones defined in the XML

data/lib/rexml/formatters/pretty.rb

@@ -111,7 +111,7 @@ module REXML
         # itself, then we don't need a carriage return... which makes this
         # logic more complex.
         node.children.each { |child|
-          next if child == node.children[-1] and child.instance_of?(Text)
+          next if child.instance_of?(Text)
           unless child == node.children[0] or child.instance_of?(Text) or
             (child == node.children[1] and !node.children[0].writethis)
             output << "\n"

data/lib/rexml/functions.rb

@@ -39,11 +39,11 @@ module REXML
 
     def Functions::text( )
       if @@context[:node].node_type == :element
-        return @@context[:node].find_all{|n| n.node_type == :text}.collect{|n| n.value}
+        @@context[:node].find_all{|n| n.node_type == :text}.collect{|n| n.value}
       elsif @@context[:node].node_type == :text
-        return @@context[:node].value
+        @@context[:node].value
       else
-        return false
+        false
       end
     end
 
@@ -262,11 +262,10 @@ module REXML
       string(string).length
     end
 
-    # UNTESTED
     def Functions::normalize_space( string=nil )
       string = string(@@context[:node]) if string.nil?
       if string.kind_of? Array
-        string.collect{|x| string.to_s.strip.gsub(/\s+/um, ' ') if string}
+        string.collect{|x| x.to_s.strip.gsub(/\s+/um, ' ') if x}
       else
         string.to_s.strip.gsub(/\s+/um, ' ')
       end

data/lib/rexml/instruction.rb

@@ -49,7 +49,7 @@ module REXML
     # See the rexml/formatters package
     #
     def write writer, indent=-1, transitive=false, ie_hack=false
-      Kernel.warn( "#{self.class.name}.write is deprecated", uplevel: 1)
+      Kernel.warn( "#{self.class.name}#write is deprecated", uplevel: 1)
       indent(writer, indent)
       writer << START
       writer << @target

data/lib/rexml/namespace.rb

@@ -42,11 +42,11 @@ module REXML
     # Compares names optionally WITH namespaces
     def has_name?( other, ns=nil )
       if ns
-        return (namespace() == ns and name() == other)
+        namespace() == ns and name() == other
       elsif other.include? ":"
-        return fully_expanded_name == other
+        fully_expanded_name == other
       else
-        return name == other
+        name == other
       end
     end
 
@@ -57,7 +57,7 @@ module REXML
     def fully_expanded_name
       ns = prefix
       return "#{ns}:#@name" if ns.size > 0
-      return @name
+      @name
     end
   end
 end

data/lib/rexml/node.rb

@@ -26,7 +26,7 @@ module REXML
     #   REXML::Formatters package for changing the output style.
     def to_s indent=nil
       unless indent.nil?
-        Kernel.warn( "#{self.class.name}.to_s(indent) parameter is deprecated", uplevel: 1)
+        Kernel.warn( "#{self.class.name}#to_s(indent) parameter is deprecated", uplevel: 1)
         f = REXML::Formatters::Pretty.new( indent )
         f.write( self, rv = "" )
       else
@@ -52,10 +52,14 @@ module REXML
 
     # Visit all subnodes of +self+ recursively
     def each_recursive(&block) # :yields: node
-      self.elements.each {|node|
-        block.call(node)
-        node.each_recursive(&block)
-      }
+      stack = []
+      each { |child| stack.unshift child if child.node_type == :element }
+      until stack.empty?
+        child = stack.pop
+        yield child
+        n = stack.size
+        child.each { |grandchild| stack.insert n, grandchild if grandchild.node_type == :element }
+      end
     end
 
     # Find (and return) first subnode (recursively) for which the block
@@ -64,7 +68,7 @@ module REXML
       each_recursive {|node|
         return node if block.call(node)
       }
-      return nil
+      nil
     end
 
     # Returns the position that +self+ holds in its parent's array, indexed

data/lib/rexml/parseexception.rb

@@ -29,6 +29,7 @@ module REXML
         err << "\nLine: #{line}\n"
         err << "Position: #{position}\n"
         err << "Last 80 unconsumed characters:\n"
+        err.force_encoding("ASCII-8BIT")
         err << @source.buffer[0..80].force_encoding("ASCII-8BIT").gsub(/\n/, ' ')
       end