rexml 3.2.6 → 3.3.9

data/lib/rexml/parsers/pullparser.rb

@@ -47,6 +47,18 @@ module REXML
         @listeners << listener
       end
 
+      def entity_expansion_count
+        @parser.entity_expansion_count
+      end
+
+      def entity_expansion_limit=( limit )
+        @parser.entity_expansion_limit = limit
+      end
+
+      def entity_expansion_text_limit=( limit )
+        @parser.entity_expansion_text_limit = limit
+      end
+
       def each
         while has_next?
           yield self.pull

data/lib/rexml/parsers/sax2parser.rb

@@ -22,6 +22,18 @@ module REXML
         @parser.source
       end
 
+      def entity_expansion_count
+        @parser.entity_expansion_count
+      end
+
+      def entity_expansion_limit=( limit )
+        @parser.entity_expansion_limit = limit
+      end
+
+      def entity_expansion_text_limit=( limit )
+        @parser.entity_expansion_text_limit = limit
+      end
+
       def add_listener( listener )
         @parser.add_listener( listener )
       end
@@ -157,25 +169,8 @@ 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,
@@ -264,6 +259,8 @@ module REXML
       end
 
       def get_namespace( prefix )
+        return nil if @namespace_stack.empty?
+
         uris = (@namespace_stack.find_all { |ns| not ns[prefix].nil? }) ||
           (@namespace_stack.find { |ns| not ns[nil].nil? })
         uris[-1][prefix] unless uris.nil? or 0 == uris.size

data/lib/rexml/parsers/streamparser.rb

@@ -7,37 +7,42 @@ module REXML
       def initialize source, listener
         @listener = listener
         @parser = BaseParser.new( source )
-        @tag_stack = []
+        @entities = {}
       end
 
       def add_listener( listener )
         @parser.add_listener( listener )
       end
 
+      def entity_expansion_count
+        @parser.entity_expansion_count
+      end
+
+      def entity_expansion_limit=( limit )
+        @parser.entity_expansion_limit = limit
+      end
+
+      def entity_expansion_text_limit=( limit )
+        @parser.entity_expansion_text_limit = limit
+      end
+
       def parse
         # entity string
         while true
           event = @parser.pull
           case event[0]
           when :end_document
-            unless @tag_stack.empty?
-              tag_path = "/" + @tag_stack.join("/")
-              raise ParseException.new("Missing end tag for '#{tag_path}'",
-                                       @parser.source)
-            end
             return
           when :start_element
-            @tag_stack << event[1]
             attrs = event[2].each do |n, v|
               event[2][n] = @parser.unnormalize( v )
             end
             @listener.tag_start( event[1], attrs )
           when :end_element
             @listener.tag_end( event[1] )
-            @tag_stack.pop
           when :text
-            normalized = @parser.unnormalize( event[1] )
-            @listener.text( normalized )
+            unnormalized = @parser.unnormalize( event[1], @entities )
+            @listener.text( unnormalized )
           when :processing_instruction
             @listener.instruction( *event[1,2] )
           when :start_doctype
@@ -48,6 +53,7 @@ module REXML
           when :comment, :attlistdecl, :cdata, :xmldecl, :elementdecl
             @listener.send( event[0].to_s, *event[1..-1] )
           when :entitydecl, :notationdecl
+            @entities[ event[1] ] = event[2] if event.size == 3
             @listener.send( event[0].to_s, event[1..-1] )
           when :externalentity
             entity_reference = event[1]

data/lib/rexml/parsers/treeparser.rb

@@ -15,8 +15,6 @@ module REXML
       end
 
       def parse
-        tag_stack = []
-        in_doctype = false
         entities = nil
         begin
           while true
@@ -24,32 +22,24 @@ module REXML
             #STDERR.puts "TREEPARSER GOT #{event.inspect}"
             case event[0]
             when :end_document
-              unless tag_stack.empty?
-                raise ParseException.new("No close tag for #{@build_context.xpath}",
-                                         @parser.source, @parser)
-              end
               return
             when :start_element
-              tag_stack.push(event[1])
               el = @build_context = @build_context.add_element( event[1] )
               event[2].each do |key, value|
                 el.attributes[key]=Attribute.new(key,value,self)
               end
             when :end_element
-              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 +50,12 @@ 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 = "3.2.6"
+  VERSION = "3.3.9"
   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
@@ -30,26 +50,50 @@ module REXML
   # objects and provides consumption of text
   class Source
     include Encoding
-    # The current buffer (what we're going to read next)
-    attr_reader :buffer
     # The line number of the last consumed text
     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
     # value, overriding all encoding detection
     def initialize(arg, encoding=nil)
-      @orig = @buffer = arg
+      @orig = arg
+      @scanner = StringScanner.new(@orig)
       if encoding
         self.encoding = encoding
       else
         detect_encoding
       end
       @line = 0
+      @term_encord = {}
     end
 
+    # The current buffer (what we're going to read next)
+    def buffer
+      @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
 
     # Inherited from Encoding
     # Overridden to support optimized en/decoding
@@ -58,98 +102,78 @@ module REXML
       encoding_updated
     end
 
-    # Scans the source for a given pattern.  Note, that this is not your
-    # usual scan() method.  For one thing, the pattern argument has some
-    # requirements; for another, the source can be consumed.  You can easily
-    # confuse this method.  Originally, the patterns were easier
-    # to construct and this method more robust, because this method
-    # generated search regexps on the fly; however, this was
-    # computationally expensive and slowed down the entire REXML package
-    # considerably, since this is by far the most commonly called method.
-    # @param pattern must be a Regexp, and must be in the form of
-    # /^\s*(#{your pattern, with no groups})(.*)/.  The first group
-    # will be returned; the second group is used if the consume flag is
-    # set.
-    # @param consume if true, the pattern returned will be consumed, leaving
-    # everything after it in the Source.
-    # @return the pattern, if found, or nil if the Source is empty or the
-    # pattern is not found.
-    def scan(pattern, cons=false)
-      return nil if @buffer.nil?
-      rv = @buffer.scan(pattern)
-      @buffer = $' if cons and rv.size>0
-      rv
+    def read(term = nil)
     end
 
-    def read
+    def read_until(term)
+      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 consume( pattern )
-      @buffer = $' if pattern.match( @buffer )
+    def ensure_buffer
     end
 
-    def match_to( char, pattern )
-      return pattern.match(@buffer)
+    def match(pattern, cons=false)
+      if cons
+        @scanner.scan(pattern).nil? ? nil : @scanner
+      else
+        @scanner.check(pattern).nil? ? nil : @scanner
+      end
     end
 
-    def match_to_consume( char, pattern )
-      md = pattern.match(@buffer)
-      @buffer = $'
-      return md
+    def position
+      @scanner.pos
     end
 
-    def match(pattern, cons=false)
-      md = pattern.match(@buffer)
-      @buffer = $' if cons and md
-      return md
+    def position=(pos)
+      @scanner.pos = pos
     end
 
     # @return true if the Source is exhausted
     def empty?
-      @buffer == ""
-    end
-
-    def position
-      @orig.index( @buffer )
+      @scanner.eos?
     end
 
     # @return the current line in the source
     def current_line
       lines = @orig.split
-      res = lines.grep @buffer[0..30]
+      res = lines.grep @scanner.rest[0..30]
       res = res[-1] if res.kind_of? Array
       lines.index( res ) if res
     end
 
     private
+
     def detect_encoding
-      buffer_encoding = @buffer.encoding
+      scanner_encoding = @scanner.rest.encoding
       detected_encoding = "UTF-8"
       begin
-        @buffer.force_encoding("ASCII-8BIT")
-        if @buffer[0, 2] == "\xfe\xff"
-          @buffer[0, 2] = ""
+        @scanner.string.force_encoding("ASCII-8BIT")
+        if @scanner.scan(/\xfe\xff/n)
           detected_encoding = "UTF-16BE"
-        elsif @buffer[0, 2] == "\xff\xfe"
-          @buffer[0, 2] = ""
+        elsif @scanner.scan(/\xff\xfe/n)
           detected_encoding = "UTF-16LE"
-        elsif @buffer[0, 3] == "\xef\xbb\xbf"
-          @buffer[0, 3] = ""
+        elsif @scanner.scan(/\xef\xbb\xbf/n)
           detected_encoding = "UTF-8"
         end
       ensure
-        @buffer.force_encoding(buffer_encoding)
+        @scanner.string.force_encoding(scanner_encoding)
       end
       self.encoding = detected_encoding
     end
 
     def encoding_updated
       if @encoding != 'UTF-8'
-        @buffer = decode(@buffer)
+        @scanner.string = decode(@scanner.rest)
         @to_utf = true
       else
         @to_utf = false
-        @buffer.force_encoding ::Encoding::UTF_8
+        @scanner.string.force_encoding(::Encoding::UTF_8)
       end
     end
   end
@@ -172,7 +196,7 @@ module REXML
       end
 
       if !@to_utf and
-          @buffer.respond_to?(:force_encoding) and
+          @orig.respond_to?(:force_encoding) and
           @source.respond_to?(:external_encoding) and
           @source.external_encoding != ::Encoding::UTF_8
         @force_utf8 = true
@@ -181,65 +205,72 @@ module REXML
       end
     end
 
-    def scan(pattern, cons=false)
-      rv = super
-      # You'll notice that this next section is very similar to the same
-      # section in match(), but just a liiittle different.  This is
-      # because it is a touch faster to do it this way with scan()
-      # than the way match() does it; enough faster to warrant duplicating
-      # some code
-      if rv.size == 0
-        until @buffer =~ pattern or @source.nil?
-          begin
-            @buffer << readline
-          rescue Iconv::IllegalSequence
-            raise
-          rescue
-            @source = nil
+    def read(term = nil, min_bytes = 1)
+      term = encode(term) if term
+      begin
+        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
-        rv = super
+        true
+      rescue Exception, NameError
+        @source = nil
+        false
       end
-      rv.taint if RUBY_VERSION < '2.7'
-      rv
     end
 
-    def read
-      begin
-        @buffer << readline
-      rescue Exception, NameError
-        @source = nil
+    def read_until(term)
+      pattern = Private::PRE_DEFINED_TERM_PATTERNS[term] || /#{Regexp.escape(term)}/
+      term = @term_encord[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
 
-    def consume( pattern )
-      match( pattern, true )
+    def ensure_buffer
+      read if @scanner.eos? && @source
     end
 
     def match( pattern, cons=false )
-      rv = pattern.match(@buffer)
-      @buffer = $' if cons and rv
-      while !rv and @source
-        begin
-          @buffer << readline
-          rv = pattern.match(@buffer)
-          @buffer = $' if cons and rv
-        rescue
-          @source = nil
+      # To avoid performance issue, we need to increase bytes to read per scan
+      min_bytes = 1
+      while true
+        if cons
+          md = @scanner.scan(pattern)
+        else
+          md = @scanner.check(pattern)
         end
+        break if md
+        return nil if pattern.is_a?(String)
+        return nil if @source.nil?
+        return nil unless read(nil, min_bytes)
+        min_bytes *= 2
       end
-      rv.taint if RUBY_VERSION < '2.7'
-      rv
+
+      md.nil? ? nil : @scanner
     end
 
     def empty?
       super and ( @source.nil? || @source.eof? )
     end
 
-    def position
-      @er_source.pos rescue 0
-    end
-
     # @return the current line in the source
     def current_line
       begin
@@ -263,15 +294,20 @@ module REXML
     end
 
     private
-    def readline
-      str = @source.readline(@line_break)
+    def readline(term = nil)
       if @pending_buffer
+        begin
+          str = @source.readline(term || @line_break)
+        rescue IOError
+        end
         if str.nil?
           str = @pending_buffer
         else
           str = @pending_buffer + str
         end
         @pending_buffer = nil
+      else
+        str = @source.readline(term || @line_break)
       end
       return nil if str.nil?
 
@@ -290,7 +326,7 @@ module REXML
         @source.set_encoding(@encoding, @encoding)
       end
       @line_break = encode(">")
-      @pending_buffer, @buffer = @buffer, ""
+      @pending_buffer, @scanner.string = @scanner.rest, ""
       @pending_buffer.force_encoding(@encoding)
       super
     end

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
@@ -248,7 +268,8 @@ module REXML
     #   u = Text.new( "sean russell", false, nil, true )
     #   u.value   #-> "sean russell"
     def value
-      @unnormalized ||= Text::unnormalize( @string, doctype )
+      @unnormalized ||= Text::unnormalize(@string, doctype,
+                                          entity_expansion_text_limit: document&.entity_expansion_text_limit)
     end
 
     # Sets the contents of this text node.  This expects the text to be
@@ -391,11 +412,12 @@ module REXML
     end
 
     # Unescapes all possible entities
-    def Text::unnormalize( string, doctype=nil, filter=nil, illegal=nil )
+    def Text::unnormalize( string, doctype=nil, filter=nil, illegal=nil, entity_expansion_text_limit: nil )
+      entity_expansion_text_limit ||= Security.entity_expansion_text_limit
       sum = 0
       string.gsub( /\r\n?/, "\n" ).gsub( REFERENCE ) {
         s = Text.expand($&, doctype, filter)
-        if sum + s.bytesize > Security.entity_expansion_text_limit
+        if sum + s.bytesize > entity_expansion_text_limit
           raise "entity expansion has grown too large"
         else
           sum += s.bytesize