rexml 3.2.9 → 3.3.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ed57404d6f519cb196d671fd629380f5b08a50cf649ae99a71432edceaf15014
-  data.tar.gz: 9097f235049d98aa743998da10724fd6ff5f6cd0cb4f230c59290af4a75e2134
+  metadata.gz: afaa8e7d5241253a1c36a218f94eeff525cc19378d2ed104f738abfc01693889
+  data.tar.gz: 665e18c0db75cce5e3db16c674c02e986ff9141df54fd7ff3da704b4403a928d
 SHA512:
-  metadata.gz: 0d7a0be04c12fcd88c64dd2962d4db49f57ed02c08e3f4628e8e546aea135c672839a19a950423afa72d0cf25af0554558f2261b6b5f2b23637f4ca47d43bd73
-  data.tar.gz: 28479b3b11de58e84f57dc88057f185eb2365998f7fbc9f0df78d5899bb9b241c6bb93d26a57ca1b54d8a058b743daa78a8df52c4ddbfbb5f7c94aeb97724808
+  metadata.gz: 86ea7a0ce4847b320f297b1eb03158003c2931847c07ea118f0a7413f476660dcf40baec8b59a92a2e7096eb665ace359b04c5d8e82617b7162305465472c88d
+  data.tar.gz: ae248f28516ab6c76170623bcc5e5a30389596823133fd0a13cb74235d6101dd469235bab8b1e15bcbd7a7795f04b44e4674dfdcb1712109dce58001cea01648

data/NEWS.md

@@ -1,12 +1,71 @@
 # News
 
-## 3.2.9 - 2024-06-19 {#version-3-2-9}
+## 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
+    * Reported by Adam.
 
   * Improved attribute value parse performance.
     * GH-135

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/parsers/baseparser.rb

@@ -132,13 +132,20 @@ 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 )
@@ -204,6 +211,8 @@ 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
@@ -216,7 +225,12 @@ 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}"
@@ -228,7 +242,14 @@ 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)
+              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)
@@ -240,7 +261,7 @@ 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]
@@ -288,7 +309,7 @@ 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).captures.compact]
               ref = false
               if match[1] == '%'
                 ref = true
@@ -314,7 +335,7 @@ 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]
@@ -366,6 +387,9 @@ module REXML
             @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)
@@ -380,7 +404,7 @@ module REXML
             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)
@@ -399,12 +423,11 @@ module REXML
               if md[0][0] == ?-
                 md = @source.match(/--(.*?)-->/um, true)
 
-                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)
                 return [ :cdata, md[1] ] if md
@@ -415,19 +438,19 @@ 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
@@ -488,10 +511,10 @@ module REXML
 
       # Unescapes all possible entities
       def unnormalize( string, entities=nil, filter=nil )
-        rv = string.gsub( /\r\n?/, "\n" )
+        rv = string.gsub( Private::CARRIAGE_RETURN_NEWLINE_PATTERN, "\n" )
         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*')
@@ -502,7 +525,7 @@ 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]
@@ -510,7 +533,7 @@ module REXML
               end
             end
           end
-          rv.gsub!( /&amp;/, '&' )
+          rv.gsub!( Private::DEFAULT_ENTITIES_PATTERNS['amp'], '&' )
         end
         rv
       end
@@ -523,7 +546,7 @@ 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"
@@ -602,7 +625,7 @@ module REXML
       end
 
       def process_instruction(start_position)
-        match_data = @source.match(INSTRUCTION_END, true)
+        match_data = @source.match(Private::INSTRUCTION_END, true)
         unless match_data
           message = "Invalid processing instruction node"
           @source.position = start_position

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 = "3.2.9"
+  VERSION = "3.3.1"
   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
@@ -35,6 +55,7 @@ module REXML
     attr_reader :encoding
 
     module Private
+      SCANNER_RESET_SIZE = 100000
       PRE_DEFINED_TERM_PATTERNS = {}
       pre_defined_terms = ["'", '"', "<"]
       pre_defined_terms.each do |term|
@@ -42,7 +63,6 @@ module REXML
       end
     end
     private_constant :Private
-    include Private
 
     # Constructor
     # @param arg must be a String, and should be a valid XML document
@@ -64,6 +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

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: rexml
 version: !ruby/object:Gem::Version
-  version: 3.2.9
+  version: 3.3.1
 platform: ruby
 authors:
 - Kouhei Sutou
 bindir: bin
 cert_chain: []
-date: 2024-06-09 00:00:00.000000000 Z
+date: 2024-06-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: strscan
@@ -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/v3.3.1
 rdoc_options:
 - "--main"
 - README.md