rexml 3.2.5 → 3.4.4

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
@@ -121,36 +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
-      if @value
-        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
-        return rv
-      end
-      nil
-    end
   end
 
   # This is a set of entity constants -- the ones defined in the XML

data/lib/rexml/formatters/pretty.rb

@@ -1,4 +1,4 @@
-# frozen_string_literal: false
+# frozen_string_literal: true
 require_relative 'default'
 
 module REXML
@@ -58,7 +58,7 @@ module REXML
           skip = false
           if compact
             if node.children.inject(true) {|s,c| s & c.kind_of?(Text)}
-              string = ""
+              string = +""
               old_level = @level
               @level = 0
               node.children.each { |child| write( child, string ) }
@@ -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

@@ -1,4 +1,4 @@
-# frozen_string_literal: false
+# frozen_string_literal: true
 
 require_relative 'xmltokens'
 
@@ -10,13 +10,17 @@ module REXML
     # The expanded name of the object, valid if name is set
     attr_accessor :prefix
     include XMLTokens
+    NAME_WITHOUT_NAMESPACE = /\A#{NCNAME_STR}\z/
     NAMESPLIT = /^(?:(#{NCNAME_STR}):)?(#{NCNAME_STR})/u
 
     # Sets the name and the expanded name
     def name=( name )
       @expanded_name = name
-      case name
-      when NAMESPLIT
+      if name.match?(NAME_WITHOUT_NAMESPACE)
+        @prefix = ""
+        @namespace = ""
+        @name = name
+      elsif name =~ NAMESPLIT
         if $1
           @prefix = $1
         else
@@ -24,7 +28,7 @@ module REXML
           @namespace = ""
         end
         @name = $2
-      when ""
+      elsif name == ""
         @prefix = nil
         @namespace = nil
         @name = nil
@@ -38,11 +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
 
@@ -53,7 +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