rexml 3.3.1 → 3.3.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: afaa8e7d5241253a1c36a218f94eeff525cc19378d2ed104f738abfc01693889
-  data.tar.gz: 665e18c0db75cce5e3db16c674c02e986ff9141df54fd7ff3da704b4403a928d
+  metadata.gz: 5e5e2317fb4a12cc855de221be85a9d62c2966c4997ead5a4ede3600561d5ede
+  data.tar.gz: a2b8f326e706211d00a9a8446b84ebd658c9cb82a4f7c98e5760ed2b10d8866c
 SHA512:
-  metadata.gz: 86ea7a0ce4847b320f297b1eb03158003c2931847c07ea118f0a7413f476660dcf40baec8b59a92a2e7096eb665ace359b04c5d8e82617b7162305465472c88d
-  data.tar.gz: ae248f28516ab6c76170623bcc5e5a30389596823133fd0a13cb74235d6101dd469235bab8b1e15bcbd7a7795f04b44e4674dfdcb1712109dce58001cea01648
+  metadata.gz: 2d26167dc282f9ff928b263927a9f003bddb6591a938b43dfddcd8a2fe2c1ddb4f931f09ec52dd3bf1912953365dcaafafb359bdd6dba1f9ca33a55bbc62ec5b
+  data.tar.gz: b3216114c5978079b102a6492cd0d8afde5eaf0af5ebc803873dc7a9ad4dc9afa785000c923f296b88c3b5c663a543348f65a3734801149f792518a1bcb5844c

data/NEWS.md

@@ -1,5 +1,90 @@
 # News
 
+## 3.3.3 - 2024-08-01 {#version-3-3-3}
+
+### Improvements
+
+  * Added support for detecting invalid XML that has unsupported
+    content before root element
+    * GH-184
+    * Patch by NAITOH Jun.
+
+  * Added support for `REXML::Security.entity_expansion_limit=` and
+    `REXML::Security.entity_expansion_text_limit=` in SAX2 and pull
+    parsers
+    * GH-187
+    * Patch by NAITOH Jun.
+
+  * Added more tests for invalid XMLs.
+    * GH-183
+    * Patch by Watson.
+
+  * Added more performance tests.
+    * Patch by Watson.
+
+  * Improved parse performance.
+    * GH-186
+    * Patch by tomoya ishida.
+
+### Thanks
+
+  * NAITOH Jun
+
+  * Watson
+
+  * tomoya ishida
+
+## 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
+    * GH-175
+    * GH-176
+    * GH-177
+    * 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

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/parsers/baseparser.rb

@@ -124,11 +124,10 @@ module REXML
       }
 
       module Private
-        INSTRUCTION_END = /#{NAME}(\s+.*?)?\?>/um
         TAG_PATTERN = /((?>#{QNAME_STR}))\s*/um
         CLOSE_PATTERN = /(#{QNAME_STR})\s*>/um
         ATTLISTDECL_END = /\s+#{NAME}(?:#{ATTDEF})*\s*>/um
-        NAME_PATTERN = /\s*#{NAME}/um
+        NAME_PATTERN = /#{NAME}/um
         GEDECL_PATTERN = "\\s+#{NAME}\\s+#{ENTITYDEF}\\s*>"
         PEDECL_PATTERN = "\\s+(%)\\s+#{NAME}\\s+#{PEDEF}\\s*>"
         ENTITYDECL_PATTERN = /(?:#{GEDECL_PATTERN})|(?:#{PEDECL_PATTERN})/um
@@ -146,6 +145,7 @@ module REXML
         self.stream = source
         @listeners = []
         @prefixes = Set.new
+        @entity_expansion_count = 0
       end
 
       def add_listener( listener )
@@ -153,10 +153,12 @@ module REXML
       end
 
       attr_reader :source
+      attr_reader :entity_expansion_count
 
       def stream=( source )
         @source = SourceFactory.create_from( source )
         @closed = nil
+        @have_root = false
         @document_status = nil
         @tags = []
         @stack = []
@@ -239,7 +241,7 @@ module REXML
         if @document_status == nil
           start_position = @source.position
           if @source.match("<?", true)
-            return process_instruction(start_position)
+            return process_instruction
           elsif @source.match("<!", true)
             if @source.match("--", true)
               md = @source.match(/(.*?)-->/um, true)
@@ -309,7 +311,11 @@ 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(Private::ENTITYDECL_PATTERN, true).captures.compact]
+              match_data = @source.match(Private::ENTITYDECL_PATTERN, true)
+              unless match_data
+                raise REXML::ParseException.new("Malformed entity declaration", @source)
+              end
+              match = [:entitydecl, *match_data.captures.compact]
               ref = false
               if match[1] == '%'
                 ref = true
@@ -341,7 +347,7 @@ module REXML
               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!
@@ -435,7 +441,7 @@ module REXML
               raise REXML::ParseException.new( "Declarations can only occur "+
                 "in the doctype declaration.", @source)
             elsif @source.match("?", true)
-              return process_instruction(start_position)
+              return process_instruction
             else
               # Get the next tag
               md = @source.match(Private::TAG_PATTERN, true)
@@ -460,8 +466,12 @@ 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
@@ -469,6 +479,16 @@ module REXML
             if text.chomp!("<")
               @source.position -= "<".bytesize
             end
+            if @tags.empty?
+              unless /\A\s*\z/.match?(text)
+                if @have_root
+                  raise ParseException.new("Malformed XML: Extra content at the end of the document (got '#{text}')", @source)
+                else
+                  raise ParseException.new("Malformed XML: Content at the start of the document (got '#{text}')", @source)
+                end
+              end
+              return pull_event if @have_root
+            end
             return [ :text, text ]
           end
         rescue REXML::UndefinedNamespaceException
@@ -486,7 +506,9 @@ module REXML
       def entity( reference, entities )
         value = nil
         value = entities[ reference ] if entities
-        if not value
+        if value
+          record_entity_expansion
+        else
           value = DEFAULT_ENTITIES[ reference ]
           value = value[2] if value
         end
@@ -511,7 +533,11 @@ module REXML
 
       # Unescapes all possible entities
       def unnormalize( string, entities=nil, filter=nil )
-        rv = string.gsub( Private::CARRIAGE_RETURN_NEWLINE_PATTERN, "\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!( Private::CHARACTER_REFERENCES ) {
@@ -521,12 +547,17 @@ module REXML
         }
         matches.collect!{|x|x[0]}.compact!
         if matches.size > 0
+          sum = 0
           matches.each do |entity_reference|
             unless filter and filter.include?(entity_reference)
               entity_value = entity( entity_reference, entities )
               if entity_value
                 re = Private::DEFAULT_ENTITIES_PATTERNS[entity_reference] || /&#{entity_reference};/
                 rv.gsub!( re, entity_value )
+                sum += rv.bytesize
+                if sum > Security.entity_expansion_text_limit
+                  raise "entity expansion has grown too large"
+                end
               else
                 er = DEFAULT_ENTITIES[entity_reference]
                 rv.gsub!( er[0], er[2] ) if er
@@ -539,6 +570,14 @@ module REXML
       end
 
       private
+
+      def record_entity_expansion
+        @entity_expansion_count += 1
+        if @entity_expansion_count > Security.entity_expansion_limit
+          raise "number of entity expansions exceeded, processing aborted."
+        end
+      end
+
       def need_source_encoding_update?(xml_declaration_encoding)
         return false if xml_declaration_encoding.nil?
         return false if /\AUTF-16\z/i =~ xml_declaration_encoding
@@ -548,14 +587,14 @@ module REXML
       def parse_name(base_error_message)
         md = @source.match(Private::NAME_PATTERN, true)
         unless md
-          if @source.match(/\s*\S/um)
+          if @source.match(/\S/um)
             message = "#{base_error_message}: invalid name"
           else
             message = "#{base_error_message}: name is missing"
           end
           raise REXML::ParseException.new(message, @source)
         end
-        md[1]
+        md[0]
       end
 
       def parse_id(base_error_message,
@@ -624,15 +663,24 @@ module REXML
         end
       end
 
-      def process_instruction(start_position)
-        match_data = @source.match(Private::INSTRUCTION_END, true)
-        unless match_data
-          message = "Invalid processing instruction node"
-          @source.position = start_position
-          raise REXML::ParseException.new(message, @source)
+      def process_instruction
+        name = parse_name("Malformed XML: Invalid processing instruction node")
+        if @source.match(/\s+/um, true)
+          match_data = @source.match(/(.*?)\?>/um, true)
+          unless match_data
+            raise ParseException.new("Malformed XML: Unclosed processing instruction", @source)
+          end
+          content = match_data[1]
+        else
+          content = nil
+          unless @source.match("?>", true)
+            raise ParseException.new("Malformed XML: Unclosed processing instruction", @source)
+          end
         end
-        if @document_status.nil? and match_data[1] == "xml"
-          content = match_data[2]
+        if name == "xml"
+          if @document_status
+            raise ParseException.new("Malformed XML: XML declaration is not at the start", @source)
+          end
           version = VERSION.match(content)
           version = version[1] unless version.nil?
           encoding = ENCODING.match(content)
@@ -647,7 +695,7 @@ module REXML
           standalone = standalone[1] unless standalone.nil?
           return [ :xmldecl, version, encoding, standalone ]
         end
-        [:processing_instruction, match_data[1], match_data[2]]
+        [:processing_instruction, name, content]
       end
 
       def parse_attributes(prefixes, curr_ns)

data/lib/rexml/parsers/pullparser.rb

@@ -47,6 +47,10 @@ module REXML
         @listeners << listener
       end
 
+      def entity_expansion_count
+        @parser.entity_expansion_count
+      end
+
       def each
         while has_next?
           yield self.pull

data/lib/rexml/parsers/sax2parser.rb

@@ -22,6 +22,10 @@ module REXML
         @parser.source
       end
 
+      def entity_expansion_count
+        @parser.entity_expansion_count
+      end
+
       def add_listener( listener )
         @parser.add_listener( listener )
       end
@@ -157,25 +161,8 @@ 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/rexml.rb

@@ -31,7 +31,7 @@
 module REXML
   COPYRIGHT = "Copyright © 2001-2008 Sean Russell <ser@germane-software.com>"
   DATE = "2008/019"
-  VERSION = "3.3.1"
+  VERSION = "3.3.3"
   REVISION = ""
 
   Copyright = COPYRIGHT

data/lib/rexml/source.rb

@@ -204,10 +204,20 @@ module REXML
       end
     end
 
-    def read(term = nil)
+    def read(term = nil, min_bytes = 1)
       term = encode(term) if term
       begin
-        @scanner << readline(term)
+        str = readline(term)
+        @scanner << str
+        read_bytes = str.bytesize
+        begin
+          while read_bytes < min_bytes
+            str = readline(term)
+            @scanner << str
+            read_bytes += str.bytesize
+          end
+        rescue IOError
+        end
         true
       rescue Exception, NameError
         @source = nil
@@ -237,10 +247,9 @@ module REXML
       read if @scanner.eos? && @source
     end
 
-    # 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 )
+      # To avoid performance issue, we need to increase bytes to read per scan
+      min_bytes = 1
       while true
         if cons
           md = @scanner.scan(pattern)
@@ -250,7 +259,8 @@ 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(nil, min_bytes)
+        min_bytes *= 2
       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: 3.3.1
+  version: 3.3.3
 platform: ruby
 authors:
 - Kouhei Sutou
 bindir: bin
 cert_chain: []
-date: 2024-06-25 00:00:00.000000000 Z
+date: 2024-08-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: strscan
@@ -116,7 +116,7 @@ homepage: https://github.com/ruby/rexml
 licenses:
 - BSD-2-Clause
 metadata:
-  changelog_uri: https://github.com/ruby/rexml/releases/tag/v3.3.1
+  changelog_uri: https://github.com/ruby/rexml/releases/tag/v3.3.3
 rdoc_options:
 - "--main"
 - README.md