rexml 3.2.8 → 3.3.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: cef1cb55ed6a23bce0af7d46fce791961558ee885c57f1089207deb53e18ff95
-  data.tar.gz: 4fbe36d9e4422d266c2ffee71fab703e6408e9a2b5533ca0ae49411483f98368
+  metadata.gz: 70ccd1465a05dba3d53dcfc4a98e76dec865a4f6ac833b954aff4234bce6c255
+  data.tar.gz: 53f43fab8f531e0ba7461ce091e5eae6bec27b12e9139450c7b3e748b4eeacdc
 SHA512:
-  metadata.gz: 60da703f26ff7eaa6cf537634ad68e4c3246605c26c54ea96147fae59bb6c17eeab5c234e5e67301e342472ce8dd3cb671321168cddc212839b9347c8de62f91
-  data.tar.gz: 4d6eeaba460a22bcdc3512ac53504fe87f829cb783069fbebb989fb8f1585fbdfe9ed357c8fbda894fb68777d04f871b9073aa6d13c31eccc6b3b22db10c2ce1
+  metadata.gz: b46818d79ae57075c4e0bd620802e82c6958dddc7da1b182504c3fdc16685c887ac0ddd6a4838a080483abba330839e9ef4b2db22cc81b9eae3eac71ac14c965
+  data.tar.gz: 1e5205905eb435c02038dd0539de22472f5364ffc47635f13a1752cb79a423dcca558fb47394ac5d624b358e779b07cbcafedfd06b99742026856f9988109976

data/NEWS.md

@@ -1,5 +1,139 @@
 # News
 
+## 3.3.2 - 2024-07-16 {#version-3-3-2}
+
+### Improvements
+
+  * Improved parse performance.
+    * GH-160
+    * Patch by NAITOH Jun.
+
+  * Improved parse performance.
+    * GH-169
+    * GH-170
+    * GH-171
+    * GH-172
+    * GH-173
+    * GH-174
+    * Patch by Watson.
+
+  * Added support for raising a parse exception when an XML has extra
+    content after the root element.
+    * GH-161
+    * Patch by NAITOH Jun.
+
+  * Added support for raising a parse exception when an XML
+    declaration exists in wrong position.
+    * GH-162
+    * Patch by NAITOH Jun.
+
+  * Removed needless a space after XML declaration in pretty print mode.
+    * GH-164
+    * Patch by NAITOH Jun.
+
+  * Stopped to emit `:text` event after the root element.
+    * GH-167
+    * Patch by NAITOH Jun.
+
+### Fixes
+
+  * Fixed a bug that SAX2 parser doesn't expand predefined entities for
+    `characters` callback.
+    * GH-168
+    * Patch by NAITOH Jun.
+
+### Thanks
+
+  * NAITOH Jun
+
+  * Watson
+
+## 3.3.1 - 2024-06-25 {#version-3-3-1}
+
+### Improvements
+
+  * Added support for detecting malformed top-level comments.
+    * GH-145
+    * Patch by Hiroya Fujinami.
+
+  * Improved `REXML::Element#attribute` performance.
+    * GH-146
+    * Patch by Hiroya Fujinami.
+
+  * Added support for detecting malformed `<!-->` comments.
+    * GH-147
+    * Patch by Hiroya Fujinami.
+
+  * Added support for detecting unclosed `DOCTYPE`.
+    * GH-152
+    * Patch by Hiroya Fujinami.
+
+  * Added `changlog_uri` metadata to gemspec.
+    * GH-156
+    * Patch by fynsta.
+
+  * Improved parse performance.
+    * GH-157
+    * GH-158
+    * Patch by NAITOH Jun.
+
+### Fixes
+
+  * Fixed a bug that large XML can't be parsed.
+    * GH-154
+    * Patch by NAITOH Jun.
+
+  * Fixed a bug that private constants are visible.
+    * GH-155
+    * Patch by NAITOH Jun.
+
+### Thanks
+
+  * Hiroya Fujinami
+
+  * NAITOH Jun
+
+  * fynsta
+
+## 3.3.0 - 2024-06-11 {#version-3-3-0}
+
+### Improvements
+
+  * Added support for strscan 0.7.0 installed with Ruby 2.6.
+    * GH-142
+    * Reported by Fernando Trigoso.
+
+### Thanks
+
+  * Fernando Trigoso
+
+## 3.2.9 - 2024-06-09 {#version-3-2-9}
+
+### Improvements
+
+  * Added support for old strscan.
+    * GH-132
+    * Reported by Adam.
+
+  * Improved attribute value parse performance.
+    * GH-135
+    * Patch by NAITOH Jun.
+
+  * Improved `REXML::Node#each_recursive` performance.
+    * GH-134
+    * GH-139
+    * Patch by Hiroya Fujinami.
+
+  * Improved text parse performance.
+    * Reported by mprogrammer.
+
+### Thanks
+
+  * Adam
+  * NAITOH Jun
+  * Hiroya Fujinami
+  * mprogrammer
+
 ## 3.2.8 - 2024-05-16 {#version-3-2-8}
 
 ### Fixes
@@ -30,7 +164,7 @@
 
   * Improved parse performance when an attribute has many `<`s.
 
-    * GH-124
+    * GH-126
 
 ### Fixes
 
@@ -65,7 +199,6 @@
   * jcavalieri
   * DuKewu
 
-
 ## 3.2.6 - 2023-07-27 {#version-3-2-6}
 
 ### Improvements

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:
@@ -1284,16 +1276,11 @@ 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?

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/node.rb

@@ -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

data/lib/rexml/parsers/baseparser.rb

@@ -7,6 +7,17 @@ require "strscan"
 
 module REXML
   module Parsers
+    if StringScanner::Version < "3.0.8"
+      module StringScannerCaptures
+        refine StringScanner do
+          def captures
+            values_at(*(1...size))
+          end
+        end
+      end
+      using StringScannerCaptures
+    end
+
     # = Using the Pull Parser
     # <em>This API is experimental, and subject to change.</em>
     #  parser = PullParser.new( "<a>text<b att='val'/>txet</a>" )
@@ -113,6 +124,14 @@ module REXML
       }
 
       module Private
+        # Terminal requires two or more letters.
+        INSTRUCTION_TERM = "?>"
+        COMMENT_TERM = "-->"
+        CDATA_TERM = "]]>"
+        DOCTYPE_TERM = "]>"
+        # Read to the end of DOCTYPE because there is no proper ENTITY termination
+        ENTITY_TERM = DOCTYPE_TERM
+
         INSTRUCTION_END = /#{NAME}(\s+.*?)?\?>/um
         TAG_PATTERN = /((?>#{QNAME_STR}))\s*/um
         CLOSE_PATTERN = /(#{QNAME_STR})\s*>/um
@@ -121,13 +140,20 @@ module REXML
         GEDECL_PATTERN = "\\s+#{NAME}\\s+#{ENTITYDEF}\\s*>"
         PEDECL_PATTERN = "\\s+(%)\\s+#{NAME}\\s+#{PEDEF}\\s*>"
         ENTITYDECL_PATTERN = /(?:#{GEDECL_PATTERN})|(?:#{PEDECL_PATTERN})/um
+        CARRIAGE_RETURN_NEWLINE_PATTERN = /\r\n?/
+        CHARACTER_REFERENCES = /&#0*((?:\d+)|(?:x[a-fA-F0-9]+));/
+        DEFAULT_ENTITIES_PATTERNS = {}
+        default_entities = ['gt', 'lt', 'quot', 'apos', 'amp']
+        default_entities.each do |term|
+          DEFAULT_ENTITIES_PATTERNS[term] = /&#{term};/
+        end
       end
       private_constant :Private
-      include Private
 
       def initialize( source )
         self.stream = source
         @listeners = []
+        @prefixes = Set.new
       end
 
       def add_listener( listener )
@@ -139,6 +165,7 @@ module REXML
       def stream=( source )
         @source = SourceFactory.create_from( source )
         @closed = nil
+        @have_root = false
         @document_status = nil
         @tags = []
         @stack = []
@@ -193,6 +220,8 @@ module REXML
 
       # Returns the next event.  This is a +PullEvent+ object.
       def pull
+        @source.drop_parsed_content
+
         pull_event.tap do |event|
           @listeners.each do |listener|
             listener.receive event
@@ -205,7 +234,12 @@ module REXML
           x, @closed = @closed, nil
           return [ :end_element, x ]
         end
-        return [ :end_document ] if empty?
+        if empty?
+          if @document_status == :in_doctype
+            raise ParseException.new("Malformed DOCTYPE: unclosed", @source)
+          end
+          return [ :end_document ]
+        end
         return @stack.shift if @stack.size > 0
         #STDERR.puts @source.encoding
         #STDERR.puts "BUFFER = #{@source.buffer.inspect}"
@@ -217,7 +251,14 @@ module REXML
             return process_instruction(start_position)
           elsif @source.match("<!", true)
             if @source.match("--", true)
-              return [ :comment, @source.match(/(.*?)-->/um, true)[1] ]
+              md = @source.match(/(.*?)-->/um, true, term: Private::COMMENT_TERM)
+              if md.nil?
+                raise REXML::ParseException.new("Unclosed comment", @source)
+              end
+              if /--|-\z/.match?(md[1])
+                raise REXML::ParseException.new("Malformed comment", @source)
+              end
+              return [ :comment, md[1] ]
             elsif @source.match("DOCTYPE", true)
               base_error_message = "Malformed DOCTYPE"
               unless @source.match(/\s+/um, true)
@@ -229,7 +270,7 @@ module REXML
                 @source.position = start_position
                 raise REXML::ParseException.new(message, @source)
               end
-              @nsstack.unshift(curr_ns=Set.new)
+              @nsstack.unshift(Set.new)
               name = parse_name(base_error_message)
               if @source.match(/\s*\[/um, true)
                 id = [nil, nil, nil]
@@ -277,7 +318,7 @@ module REXML
               raise REXML::ParseException.new( "Bad ELEMENT declaration!", @source ) if md.nil?
               return [ :elementdecl, "<!ELEMENT" + md[1] ]
             elsif @source.match("ENTITY", true)
-              match = [:entitydecl, *@source.match(ENTITYDECL_PATTERN, true).captures.compact]
+              match = [:entitydecl, *@source.match(Private::ENTITYDECL_PATTERN, true, term: Private::ENTITY_TERM).captures.compact]
               ref = false
               if match[1] == '%'
                 ref = true
@@ -303,13 +344,13 @@ module REXML
               match << '%' if ref
               return match
             elsif @source.match("ATTLIST", true)
-              md = @source.match(ATTLISTDECL_END, true)
+              md = @source.match(Private::ATTLISTDECL_END, true)
               raise REXML::ParseException.new( "Bad ATTLIST declaration!", @source ) if md.nil?
               element = md[1]
               contents = md[0]
 
               pairs = {}
-              values = md[0].scan( ATTDEF_RE )
+              values = md[0].strip.scan( ATTDEF_RE )
               values.each do |attdef|
                 unless attdef[3] == "#IMPLIED"
                   attdef.compact!
@@ -342,19 +383,22 @@ module REXML
                 raise REXML::ParseException.new(message, @source)
               end
               return [:notationdecl, name, *id]
-            elsif md = @source.match(/--(.*?)-->/um, true)
+            elsif md = @source.match(/--(.*?)-->/um, true, term: Private::COMMENT_TERM)
               case md[1]
               when /--/, /-\z/
                 raise REXML::ParseException.new("Malformed comment", @source)
               end
               return [ :comment, md[1] ] if md
             end
-          elsif match = @source.match(/(%.*?;)\s*/um, true)
+          elsif match = @source.match(/(%.*?;)\s*/um, true, term: Private::DOCTYPE_TERM)
             return [ :externalentity, match[1] ]
           elsif @source.match(/\]\s*>/um, true)
             @document_status = :after_doctype
             return [ :end_doctype ]
           end
+          if @document_status == :in_doctype
+            raise ParseException.new("Malformed DOCTYPE: invalid declaration", @source)
+          end
         end
         if @document_status == :after_doctype
           @source.match(/\s*/um, true)
@@ -362,10 +406,14 @@ module REXML
         begin
           start_position = @source.position
           if @source.match("<", true)
+            # :text's read_until may remain only "<" in buffer. In the
+            # case, buffer is empty here. So we need to fill buffer
+            # here explicitly.
+            @source.ensure_buffer
             if @source.match("/", true)
               @nsstack.shift
               last_tag = @tags.pop
-              md = @source.match(CLOSE_PATTERN, true)
+              md = @source.match(Private::CLOSE_PATTERN, true)
               if md and !last_tag
                 message = "Unexpected top-level end tag (got '#{md[1]}')"
                 raise REXML::ParseException.new(message, @source)
@@ -382,16 +430,15 @@ module REXML
               #STDERR.puts "SOURCE BUFFER = #{source.buffer}, #{source.buffer.size}"
               raise REXML::ParseException.new("Malformed node", @source) unless md
               if md[0][0] == ?-
-                md = @source.match(/--(.*?)-->/um, true)
+                md = @source.match(/--(.*?)-->/um, true, term: Private::COMMENT_TERM)
 
-                case md[1]
-                when /--/, /-\z/
+                if md.nil? || /--|-\z/.match?(md[1])
                   raise REXML::ParseException.new("Malformed comment", @source)
                 end
 
-                return [ :comment, md[1] ] if md
+                return [ :comment, md[1] ]
               else
-                md = @source.match(/\[CDATA\[(.*?)\]\]>/um, true)
+                md = @source.match(/\[CDATA\[(.*?)\]\]>/um, true, term: Private::CDATA_TERM)
                 return [ :cdata, md[1] ] if md
               end
               raise REXML::ParseException.new( "Declarations can only occur "+
@@ -400,19 +447,19 @@ module REXML
               return process_instruction(start_position)
             else
               # Get the next tag
-              md = @source.match(TAG_PATTERN, true)
+              md = @source.match(Private::TAG_PATTERN, true)
               unless md
                 @source.position = start_position
                 raise REXML::ParseException.new("malformed XML: missing tag start", @source)
               end
               tag = md[1]
               @document_status = :in_element
-              prefixes = Set.new
-              prefixes << md[2] if md[2]
+              @prefixes.clear
+              @prefixes << md[2] if md[2]
               @nsstack.unshift(curr_ns=Set.new)
-              attributes, closed = parse_attributes(prefixes, curr_ns)
+              attributes, closed = parse_attributes(@prefixes, curr_ns)
               # Verify that all of the prefixes have been defined
-              for prefix in prefixes
+              for prefix in @prefixes
                 unless @nsstack.find{|k| k.member?(prefix)}
                   raise UndefinedNamespaceException.new(prefix,@source,self)
                 end
@@ -422,13 +469,25 @@ module REXML
                 @closed = tag
                 @nsstack.shift
               else
+                if @tags.empty? and @have_root
+                  raise ParseException.new("Malformed XML: Extra tag at the end of the document (got '<#{tag}')", @source)
+                end
                 @tags.push( tag )
               end
+              @have_root = true
               return [ :start_element, tag, attributes ]
             end
           else
-            md = @source.match(/([^<]*)/um, true)
-            text = md[1]
+            text = @source.read_until("<")
+            if text.chomp!("<")
+              @source.position -= "<".bytesize
+            end
+            if @tags.empty? and @have_root
+              unless /\A\s*\z/.match?(text)
+                raise ParseException.new("Malformed XML: Extra content at the end of the document (got '#{text}')", @source)
+              end
+              return pull_event
+            end
             return [ :text, text ]
           end
         rescue REXML::UndefinedNamespaceException
@@ -471,10 +530,14 @@ module REXML
 
       # Unescapes all possible entities
       def unnormalize( string, entities=nil, filter=nil )
-        rv = string.gsub( /\r\n?/, "\n" )
+        if string.include?("\r")
+          rv = string.gsub( Private::CARRIAGE_RETURN_NEWLINE_PATTERN, "\n" )
+        else
+          rv = string.dup
+        end
         matches = rv.scan( REFERENCE_RE )
         return rv if matches.size == 0
-        rv.gsub!( /&#0*((?:\d+)|(?:x[a-fA-F0-9]+));/ ) {
+        rv.gsub!( Private::CHARACTER_REFERENCES ) {
           m=$1
           m = "0#{m}" if m[0] == ?x
           [Integer(m)].pack('U*')
@@ -485,7 +548,7 @@ module REXML
             unless filter and filter.include?(entity_reference)
               entity_value = entity( entity_reference, entities )
               if entity_value
-                re = /&#{entity_reference};/
+                re = Private::DEFAULT_ENTITIES_PATTERNS[entity_reference] || /&#{entity_reference};/
                 rv.gsub!( re, entity_value )
               else
                 er = DEFAULT_ENTITIES[entity_reference]
@@ -493,7 +556,7 @@ module REXML
               end
             end
           end
-          rv.gsub!( /&amp;/, '&' )
+          rv.gsub!( Private::DEFAULT_ENTITIES_PATTERNS['amp'], '&' )
         end
         rv
       end
@@ -506,7 +569,7 @@ module REXML
       end
 
       def parse_name(base_error_message)
-        md = @source.match(NAME_PATTERN, true)
+        md = @source.match(Private::NAME_PATTERN, true)
         unless md
           if @source.match(/\s*\S/um)
             message = "#{base_error_message}: invalid name"
@@ -585,13 +648,16 @@ module REXML
       end
 
       def process_instruction(start_position)
-        match_data = @source.match(INSTRUCTION_END, true)
+        match_data = @source.match(Private::INSTRUCTION_END, true, term: Private::INSTRUCTION_TERM)
         unless match_data
           message = "Invalid processing instruction node"
           @source.position = start_position
           raise REXML::ParseException.new(message, @source)
         end
-        if @document_status.nil? and match_data[1] == "xml"
+        if match_data[1] == "xml"
+          if @document_status
+            raise ParseException.new("Malformed XML: XML declaration is not at the start", @source)
+          end
           content = match_data[2]
           version = VERSION.match(content)
           version = version[1] unless version.nil?
@@ -633,8 +699,10 @@ module REXML
               raise REXML::ParseException.new(message, @source)
             end
             quote = match[1]
+            start_position = @source.position
             value = @source.read_until(quote)
             unless value.chomp!(quote)
+              @source.position = start_position
               message = "Missing attribute value end quote: <#{name}>: <#{quote}>"
               raise REXML::ParseException.new(message, @source)
             end

data/lib/rexml/parsers/sax2parser.rb

@@ -157,25 +157,8 @@ module REXML
               end
             end
           when :text
-            #normalized = @parser.normalize( event[1] )
-            #handle( :characters, normalized )
-            copy = event[1].clone
-
-            esub = proc { |match|
-              if @entities.has_key?($1)
-                @entities[$1].gsub(Text::REFERENCE, &esub)
-              else
-                match
-              end
-            }
-
-            copy.gsub!( Text::REFERENCE, &esub )
-            copy.gsub!( Text::NUMERICENTITY ) {|m|
-              m=$1
-              m = "0#{m}" if m[0] == ?x
-              [Integer(m)].pack('U*')
-            }
-            handle( :characters, copy )
+            unnormalized = @parser.unnormalize( event[1], @entities )
+            handle( :characters, unnormalized )
           when :entitydecl
             handle_entitydecl( event )
           when :processing_instruction, :comment, :attlistdecl,

data/lib/rexml/parsers/streamparser.rb

@@ -36,8 +36,8 @@ module REXML
             @listener.tag_end( event[1] )
             @tag_stack.pop
           when :text
-            normalized = @parser.unnormalize( event[1] )
-            @listener.text( normalized )
+            unnormalized = @parser.unnormalize( event[1] )
+            @listener.text( unnormalized )
           when :processing_instruction
             @listener.instruction( *event[1,2] )
           when :start_doctype

data/lib/rexml/parsers/treeparser.rb

@@ -16,7 +16,6 @@ module REXML
 
       def parse
         tag_stack = []
-        in_doctype = false
         entities = nil
         begin
           while true
@@ -39,17 +38,15 @@ module REXML
               tag_stack.pop
               @build_context = @build_context.parent
             when :text
-              if not in_doctype
-                if @build_context[-1].instance_of? Text
-                  @build_context[-1] << event[1]
-                else
-                  @build_context.add(
-                    Text.new(event[1], @build_context.whitespace, nil, true)
-                  ) unless (
-                    @build_context.ignore_whitespace_nodes and
-                    event[1].strip.size==0
-                  )
-                end
+              if @build_context[-1].instance_of? Text
+                @build_context[-1] << event[1]
+              else
+                @build_context.add(
+                  Text.new(event[1], @build_context.whitespace, nil, true)
+                ) unless (
+                  @build_context.ignore_whitespace_nodes and
+                  event[1].strip.size==0
+                )
               end
             when :comment
               c = Comment.new( event[1] )
@@ -60,14 +57,12 @@ module REXML
             when :processing_instruction
               @build_context.add( Instruction.new( event[1], event[2] ) )
             when :end_doctype
-              in_doctype = false
               entities.each { |k,v| entities[k] = @build_context.entities[k].value }
               @build_context = @build_context.parent
             when :start_doctype
               doctype = DocType.new( event[1..-1], @build_context )
               @build_context = doctype
               entities = {}
-              in_doctype = true
             when :attlistdecl
               n = AttlistDecl.new( event[1..-1] )
               @build_context.add( n )

data/lib/rexml/rexml.rb

@@ -31,7 +31,7 @@
 module REXML
   COPYRIGHT = "Copyright © 2001-2008 Sean Russell <ser@germane-software.com>"
   DATE = "2008/019"
-  VERSION = "3.2.8"
+  VERSION = "3.3.2"
   REVISION = ""
 
   Copyright = COPYRIGHT

data/lib/rexml/source.rb

@@ -1,8 +1,28 @@
 # coding: US-ASCII
 # frozen_string_literal: false
+
+require "strscan"
+
 require_relative 'encoding'
 
 module REXML
+  if StringScanner::Version < "1.0.0"
+    module StringScannerCheckScanString
+      refine StringScanner do
+        def check(pattern)
+          pattern = /#{Regexp.escape(pattern)}/ if pattern.is_a?(String)
+          super(pattern)
+        end
+
+        def scan(pattern)
+          pattern = /#{Regexp.escape(pattern)}/ if pattern.is_a?(String)
+          super(pattern)
+        end
+      end
+    end
+    using StringScannerCheckScanString
+  end
+
   # Generates Source-s.  USE THIS CLASS.
   class SourceFactory
     # Generates a Source object
@@ -34,6 +54,16 @@ module REXML
     attr_reader :line
     attr_reader :encoding
 
+    module Private
+      SCANNER_RESET_SIZE = 100000
+      PRE_DEFINED_TERM_PATTERNS = {}
+      pre_defined_terms = ["'", '"', "<"]
+      pre_defined_terms.each do |term|
+        PRE_DEFINED_TERM_PATTERNS[term] = /#{Regexp.escape(term)}/
+      end
+    end
+    private_constant :Private
+
     # Constructor
     # @param arg must be a String, and should be a valid XML document
     # @param encoding if non-null, sets the encoding of the source to this
@@ -54,6 +84,12 @@ module REXML
       @scanner.rest
     end
 
+    def drop_parsed_content
+      if @scanner.pos > Private::SCANNER_RESET_SIZE
+        @scanner.string = @scanner.rest
+      end
+    end
+
     def buffer_encoding=(encoding)
       @scanner.string.force_encoding(encoding)
     end
@@ -69,13 +105,19 @@ module REXML
     end
 
     def read_until(term)
-      @scanner.scan_until(Regexp.union(term)) or @scanner.rest
+      pattern = Private::PRE_DEFINED_TERM_PATTERNS[term] || /#{Regexp.escape(term)}/
+      data = @scanner.scan_until(pattern)
+      unless data
+        data = @scanner.rest
+        @scanner.pos = @scanner.string.bytesize
+      end
+      data
     end
 
     def ensure_buffer
     end
 
-    def match(pattern, cons=false)
+    def match(pattern, cons=false, term: nil)
       if cons
         @scanner.scan(pattern).nil? ? nil : @scanner
       else
@@ -163,6 +205,7 @@ module REXML
     end
 
     def read(term = nil)
+      term = encode(term) if term
       begin
         @scanner << readline(term)
         true
@@ -173,16 +216,20 @@ module REXML
     end
 
     def read_until(term)
-      pattern = Regexp.union(term)
-      begin
-        until str = @scanner.scan_until(pattern)
-          @scanner << readline(term)
-        end
-      rescue EOFError
-        @scanner.rest
-      else
+      pattern = Private::PRE_DEFINED_TERM_PATTERNS[term] || /#{Regexp.escape(term)}/
+      term = encode(term)
+      until str = @scanner.scan_until(pattern)
+        break if @source.nil?
+        break if @source.eof?
+        @scanner << readline(term)
+      end
+      if str
         read if @scanner.eos? and !@source.eof?
         str
+      else
+        rest = @scanner.rest
+        @scanner.pos = @scanner.string.bytesize
+        rest
       end
     end
 
@@ -193,7 +240,7 @@ module REXML
     # Note: When specifying a string for 'pattern', it must not include '>' except in the following formats:
     # - ">"
     # - "XXX>" (X is any string excluding '>')
-    def match( pattern, cons=false )
+    def match( pattern, cons=false, term: nil )
       while true
         if cons
           md = @scanner.scan(pattern)
@@ -203,7 +250,7 @@ module REXML
         break if md
         return nil if pattern.is_a?(String)
         return nil if @source.nil?
-        return nil unless read
+        return nil unless read(term)
       end
 
       md.nil? ? nil : @scanner

data/lib/rexml/text.rb

@@ -151,25 +151,45 @@ module REXML
         end
       end
 
-      # context sensitive
-      string.scan(pattern) do
-        if $1[-1] != ?;
-          raise "Illegal character #{$1.inspect} in raw string #{string.inspect}"
-        elsif $1[0] == ?&
-          if $5 and $5[0] == ?#
-            case ($5[1] == ?x ? $5[2..-1].to_i(16) : $5[1..-1].to_i)
-            when *VALID_CHAR
+      pos = 0
+      while (index = string.index(/<|&/, pos))
+        if string[index] == "<"
+          raise "Illegal character \"#{string[index]}\" in raw string #{string.inspect}"
+        end
+
+        unless (end_index = string.index(/[^\s];/, index + 1))
+          raise "Illegal character \"#{string[index]}\" in raw string #{string.inspect}"
+        end
+
+        value = string[(index + 1)..end_index]
+        if /\s/.match?(value)
+          raise "Illegal character \"#{string[index]}\" in raw string #{string.inspect}"
+        end
+
+        if value[0] == "#"
+          character_reference = value[1..-1]
+
+          unless (/\A(\d+|x[0-9a-fA-F]+)\z/.match?(character_reference))
+            if character_reference[0] == "x" || character_reference[-1] == "x"
+              raise "Illegal character \"#{string[index]}\" in raw string #{string.inspect}"
             else
-              raise "Illegal character #{$1.inspect} in raw string #{string.inspect}"
+              raise "Illegal character #{string.inspect} in raw string #{string.inspect}"
             end
-          # FIXME: below can't work but this needs API change.
-          # elsif @parent and $3 and !SUBSTITUTES.include?($1)
-          #   if !doctype or !doctype.entities.has_key?($3)
-          #     raise "Undeclared entity '#{$1}' in raw string \"#{string}\""
-          #   end
           end
+
+          case (character_reference[0] == "x" ? character_reference[1..-1].to_i(16) : character_reference[0..-1].to_i)
+          when *VALID_CHAR
+          else
+            raise "Illegal character #{string.inspect} in raw string #{string.inspect}"
+          end
+        elsif !(/\A#{Entity::NAME}\z/um.match?(value))
+          raise "Illegal character \"#{string[index]}\" in raw string #{string.inspect}"
         end
+
+        pos = end_index + 1
       end
+
+      string
     end
 
     def node_type

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: rexml
 version: !ruby/object:Gem::Version
-  version: 3.2.8
+  version: 3.3.2
 platform: ruby
 authors:
 - Kouhei Sutou
 bindir: bin
 cert_chain: []
-date: 2024-05-16 00:00:00.000000000 Z
+date: 2024-07-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: strscan
@@ -15,14 +15,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 3.0.9
+        version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 3.0.9
+        version: '0'
 description: An XML toolkit for Ruby
 email:
 - kou@cozmixng.org
@@ -115,7 +115,8 @@ files:
 homepage: https://github.com/ruby/rexml
 licenses:
 - BSD-2-Clause
-metadata: {}
+metadata:
+  changelog_uri: https://github.com/ruby/rexml/releases/tag/v3.3.2
 rdoc_options:
 - "--main"
 - README.md