rexml 3.3.8 → 3.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 84b42219a4278ab15e7ee7627951d0b94dddc707cbf9563799b3266d02ed32db
-  data.tar.gz: 4895e6f04d100a2affc8d5c6af4c6dfec5ec4d0d863f8d22de1c66da1d253c61
+  metadata.gz: 582bb5339257c81f2ce9c076155c01d7adfe8fb169c09bc7f5f489f6a76bca80
+  data.tar.gz: 160de8899d8d1f995bafca23631e9e4ab928ebbffa21684e3b61dad805a6187b
 SHA512:
-  metadata.gz: 7729c31da310e2fb7c96cc3a5bd5b981fefdcdae6fe545bf2d113d91af5862fbb51789e9289b91e4247963169900b0cdccc373ffeea6ca3f935b2e32bab1e2e4
-  data.tar.gz: 542f689b7cd27b5c71aeb6845e5af2ac28186e31a98af8c45e984ce6ca563192b2a74e50b6acd95f1fde49ed6289bf9024bfd6612608455038a22e66c6b3a75b
+  metadata.gz: e2b095792523f54301e8a6af2f1682a9ad24d92cdd5d94c9e6088b27520e3c03b68fe06061b6ff2fd96b001b9cb947c57e4095244d83206a83fc2a1829dd4243
+  data.tar.gz: 4f335d2b1e58c1da233c3f0a0588def502c8cb2660633e0e06b4d0930bbcedcaae36b52dc550923704b4525d94a1011f4b5f4e87a81e5d689cce24ee89210a23

data/NEWS.md

@@ -1,5 +1,55 @@
 # News
 
+## 3.4.0 - 2024-12-15 {#version-3-4-0}
+
+### Improvement
+
+  * Improved performance.
+    * GH-216
+    * Patch by NAITOH Jun
+
+  * JRuby: Improved parse performance.
+    * GH-219
+    * Patch by João Duarte
+
+  * Added support for reusing pull parser.
+    * GH-214
+    * GH-220
+    * Patch by Dmitry Pogrebnoy
+
+  * Improved error handling when source is `IO`.
+    * GH-221
+    * Patch by NAITOH Jun
+
+### Thanks
+
+  * NAITOH Jun
+
+  * João Duarte
+
+  * Dmitry Pogrebnoy
+
+## 3.3.9 - 2024-10-24 {#version-3-3-9}
+
+### Improvements
+
+  * Improved performance.
+    * GH-210
+    * Patch by NAITOH Jun.
+
+### Fixes
+
+  * Fixed a parse bug for text only invalid XML.
+    * GH-215
+    * Patch by NAITOH Jun.
+
+  * Fixed a parse bug that `&#0x...;` is accepted as a character
+    reference.
+
+### Thanks
+
+  * NAITOH Jun
+
 ## 3.3.8 - 2024-09-29 {#version-3-3-8}
 
 ### Improvements

data/lib/rexml/parsers/baseparser.rb

@@ -150,7 +150,7 @@ module REXML
         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]+));/
+        CHARACTER_REFERENCES = /&#((?:\d+)|(?:x[a-fA-F0-9]+));/
         DEFAULT_ENTITIES_PATTERNS = {}
         default_entities = ['gt', 'lt', 'quot', 'apos', 'amp']
         default_entities.each do |term|
@@ -167,6 +167,7 @@ module REXML
         @entity_expansion_count = 0
         @entity_expansion_limit = Security.entity_expansion_limit
         @entity_expansion_text_limit = Security.entity_expansion_text_limit
+        @source.ensure_buffer
       end
 
       def add_listener( listener )
@@ -180,6 +181,10 @@ module REXML
 
       def stream=( source )
         @source = SourceFactory.create_from( source )
+        reset
+      end
+
+      def reset
         @closed = nil
         @have_root = false
         @document_status = nil
@@ -268,10 +273,10 @@ module REXML
         @source.ensure_buffer
         if @document_status == nil
           start_position = @source.position
-          if @source.match("<?", true)
+          if @source.match?("<?", true)
             return process_instruction
-          elsif @source.match("<!", true)
-            if @source.match("--", true)
+          elsif @source.match?("<!", true)
+            if @source.match?("--", true)
               md = @source.match(/(.*?)-->/um, true)
               if md.nil?
                 raise REXML::ParseException.new("Unclosed comment", @source)
@@ -280,10 +285,10 @@ module REXML
                 raise REXML::ParseException.new("Malformed comment", @source)
               end
               return [ :comment, md[1] ]
-            elsif @source.match("DOCTYPE", true)
+            elsif @source.match?("DOCTYPE", true)
               base_error_message = "Malformed DOCTYPE"
-              unless @source.match(/\s+/um, true)
-                if @source.match(">")
+              unless @source.match?(/\s+/um, true)
+                if @source.match?(">")
                   message = "#{base_error_message}: name is missing"
                 else
                   message = "#{base_error_message}: invalid name"
@@ -292,10 +297,10 @@ module REXML
                 raise REXML::ParseException.new(message, @source)
               end
               name = parse_name(base_error_message)
-              if @source.match(/\s*\[/um, true)
+              if @source.match?(/\s*\[/um, true)
                 id = [nil, nil, nil]
                 @document_status = :in_doctype
-              elsif @source.match(/\s*>/um, true)
+              elsif @source.match?(/\s*>/um, true)
                 id = [nil, nil, nil]
                 @document_status = :after_doctype
                 @source.ensure_buffer
@@ -307,9 +312,9 @@ module REXML
                   # For backward compatibility
                   id[1], id[2] = id[2], nil
                 end
-                if @source.match(/\s*\[/um, true)
+                if @source.match?(/\s*\[/um, true)
                   @document_status = :in_doctype
-                elsif @source.match(/\s*>/um, true)
+                elsif @source.match?(/\s*>/um, true)
                   @document_status = :after_doctype
                   @source.ensure_buffer
                 else
@@ -319,7 +324,7 @@ module REXML
               end
               args = [:start_doctype, name, *id]
               if @document_status == :after_doctype
-                @source.match(/\s*/um, true)
+                @source.match?(/\s*/um, true)
                 @stack << [ :end_doctype ]
               end
               return args
@@ -330,14 +335,14 @@ module REXML
           end
         end
         if @document_status == :in_doctype
-          @source.match(/\s*/um, true) # skip spaces
+          @source.match?(/\s*/um, true) # skip spaces
           start_position = @source.position
-          if @source.match("<!", true)
-            if @source.match("ELEMENT", true)
+          if @source.match?("<!", true)
+            if @source.match?("ELEMENT", true)
               md = @source.match(/(.*?)>/um, true)
               raise REXML::ParseException.new( "Bad ELEMENT declaration!", @source ) if md.nil?
               return [ :elementdecl, "<!ELEMENT" + md[1] ]
-            elsif @source.match("ENTITY", true)
+            elsif @source.match?("ENTITY", true)
               match_data = @source.match(Private::ENTITYDECL_PATTERN, true)
               unless match_data
                 raise REXML::ParseException.new("Malformed entity declaration", @source)
@@ -369,7 +374,7 @@ module REXML
               end
               match << '%' if ref
               return match
-            elsif @source.match("ATTLIST", true)
+            elsif @source.match?("ATTLIST", true)
               md = @source.match(Private::ATTLISTDECL_END, true)
               raise REXML::ParseException.new( "Bad ATTLIST declaration!", @source ) if md.nil?
               element = md[1]
@@ -389,10 +394,10 @@ module REXML
                 end
               end
               return [ :attlistdecl, element, pairs, contents ]
-            elsif @source.match("NOTATION", true)
+            elsif @source.match?("NOTATION", true)
               base_error_message = "Malformed notation declaration"
-              unless @source.match(/\s+/um, true)
-                if @source.match(">")
+              unless @source.match?(/\s+/um, true)
+                if @source.match?(">")
                   message = "#{base_error_message}: name is missing"
                 else
                   message = "#{base_error_message}: invalid name"
@@ -404,7 +409,7 @@ module REXML
               id = parse_id(base_error_message,
                             accept_external_id: true,
                             accept_public_id: true)
-              unless @source.match(/\s*>/um, true)
+              unless @source.match?(/\s*>/um, true)
                 message = "#{base_error_message}: garbage before end >"
                 raise REXML::ParseException.new(message, @source)
               end
@@ -418,7 +423,7 @@ module REXML
             end
           elsif match = @source.match(/(%.*?;)\s*/um, true)
             return [ :externalentity, match[1] ]
-          elsif @source.match(/\]\s*>/um, true)
+          elsif @source.match?(/\]\s*>/um, true)
             @document_status = :after_doctype
             return [ :end_doctype ]
           end
@@ -427,16 +432,16 @@ module REXML
           end
         end
         if @document_status == :after_doctype
-          @source.match(/\s*/um, true)
+          @source.match?(/\s*/um, true)
         end
         begin
           start_position = @source.position
-          if @source.match("<", true)
+          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)
+            if @source.match?("/", true)
               @namespaces_restore_stack.pop
               last_tag = @tags.pop
               md = @source.match(Private::CLOSE_PATTERN, true)
@@ -451,7 +456,7 @@ module REXML
                 raise REXML::ParseException.new(message, @source)
               end
               return [ :end_element, last_tag ]
-            elsif @source.match("!", true)
+            elsif @source.match?("!", true)
               md = @source.match(/([^>]*>)/um)
               #STDERR.puts "SOURCE BUFFER = #{source.buffer}, #{source.buffer.size}"
               raise REXML::ParseException.new("Malformed node", @source) unless md
@@ -469,7 +474,7 @@ module REXML
               end
               raise REXML::ParseException.new( "Declarations can only occur "+
                 "in the doctype declaration.", @source)
-            elsif @source.match("?", true)
+            elsif @source.match?("?", true)
               return process_instruction
             else
               # Get the next tag
@@ -569,8 +574,12 @@ module REXML
         return rv if matches.size == 0
         rv.gsub!( Private::CHARACTER_REFERENCES ) {
           m=$1
-          m = "0#{m}" if m[0] == ?x
-          [Integer(m)].pack('U*')
+          if m.start_with?("x")
+            code_point = Integer(m[1..-1], 16)
+          else
+            code_point = Integer(m, 10)
+          end
+          [code_point].pack('U*')
         }
         matches.collect!{|x|x[0]}.compact!
         if filter
@@ -646,7 +655,7 @@ module REXML
       def parse_name(base_error_message)
         md = @source.match(Private::NAME_PATTERN, true)
         unless md
-          if @source.match(/\S/um)
+          if @source.match?(/\S/um)
             message = "#{base_error_message}: invalid name"
           else
             message = "#{base_error_message}: name is missing"
@@ -688,34 +697,34 @@ module REXML
                                    accept_public_id:)
         public = /\A\s*PUBLIC/um
         system = /\A\s*SYSTEM/um
-        if (accept_external_id or accept_public_id) and @source.match(/#{public}/um)
-          if @source.match(/#{public}(?:\s+[^'"]|\s*[\[>])/um)
+        if (accept_external_id or accept_public_id) and @source.match?(/#{public}/um)
+          if @source.match?(/#{public}(?:\s+[^'"]|\s*[\[>])/um)
             return "public ID literal is missing"
           end
-          unless @source.match(/#{public}\s+#{PUBIDLITERAL}/um)
+          unless @source.match?(/#{public}\s+#{PUBIDLITERAL}/um)
             return "invalid public ID literal"
           end
           if accept_public_id
-            if @source.match(/#{public}\s+#{PUBIDLITERAL}\s+[^'"]/um)
+            if @source.match?(/#{public}\s+#{PUBIDLITERAL}\s+[^'"]/um)
               return "system ID literal is missing"
             end
-            unless @source.match(/#{public}\s+#{PUBIDLITERAL}\s+#{SYSTEMLITERAL}/um)
+            unless @source.match?(/#{public}\s+#{PUBIDLITERAL}\s+#{SYSTEMLITERAL}/um)
               return "invalid system literal"
             end
             "garbage after system literal"
           else
             "garbage after public ID literal"
           end
-        elsif accept_external_id and @source.match(/#{system}/um)
-          if @source.match(/#{system}(?:\s+[^'"]|\s*[\[>])/um)
+        elsif accept_external_id and @source.match?(/#{system}/um)
+          if @source.match?(/#{system}(?:\s+[^'"]|\s*[\[>])/um)
             return "system literal is missing"
           end
-          unless @source.match(/#{system}\s+#{SYSTEMLITERAL}/um)
+          unless @source.match?(/#{system}\s+#{SYSTEMLITERAL}/um)
             return "invalid system literal"
           end
           "garbage after system literal"
         else
-          unless @source.match(/\A\s*(?:PUBLIC|SYSTEM)\s/um)
+          unless @source.match?(/\A\s*(?:PUBLIC|SYSTEM)\s/um)
             return "invalid ID type"
           end
           "ID type is missing"
@@ -724,7 +733,7 @@ module REXML
 
       def process_instruction
         name = parse_name("Malformed XML: Invalid processing instruction node")
-        if @source.match(/\s+/um, true)
+        if @source.match?(/\s+/um, true)
           match_data = @source.match(/(.*?)\?>/um, true)
           unless match_data
             raise ParseException.new("Malformed XML: Unclosed processing instruction", @source)
@@ -732,7 +741,7 @@ module REXML
           content = match_data[1]
         else
           content = nil
-          unless @source.match("?>", true)
+          unless @source.match?("?>", true)
             raise ParseException.new("Malformed XML: Unclosed processing instruction", @source)
           end
         end
@@ -762,9 +771,9 @@ module REXML
         expanded_names = {}
         closed = false
         while true
-          if @source.match(">", true)
+          if @source.match?(">", true)
             return attributes, closed
-          elsif @source.match("/>", true)
+          elsif @source.match?("/>", true)
             closed = true
             return attributes, closed
           elsif match = @source.match(QNAME, true)
@@ -772,7 +781,7 @@ module REXML
             prefix = match[2]
             local_part = match[3]
 
-            unless @source.match(/\s*=\s*/um, true)
+            unless @source.match?(/\s*=\s*/um, true)
               message = "Missing attribute equal: <#{name}>"
               raise REXML::ParseException.new(message, @source)
             end
@@ -788,7 +797,7 @@ module REXML
               message = "Missing attribute value end quote: <#{name}>: <#{quote}>"
               raise REXML::ParseException.new(message, @source)
             end
-            @source.match(/\s*/um, true)
+            @source.match?(/\s*/um, true)
             if prefix == "xmlns"
               if local_part == "xml"
                 if value != Private::XML_PREFIXED_NAMESPACE

data/lib/rexml/parsers/pullparser.rb

@@ -93,6 +93,10 @@ module REXML
       def unshift token
         @my_stack.unshift token
       end
+
+      def reset
+        @parser.reset
+      end
     end
 
     # A parsing event.  The contents of the event are accessed as an +Array?,

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 = "3.3.8"
+  VERSION = "3.4.0"
   REVISION = ""
 
   Copyright = COPYRIGHT

data/lib/rexml/source.rb

@@ -1,6 +1,7 @@
 # coding: US-ASCII
 # frozen_string_literal: false
 
+require "stringio"
 require "strscan"
 
 require_relative 'encoding'
@@ -18,6 +19,16 @@ module REXML
           pattern = /#{Regexp.escape(pattern)}/ if pattern.is_a?(String)
           super(pattern)
         end
+
+        def match?(pattern)
+          pattern = /#{Regexp.escape(pattern)}/ if pattern.is_a?(String)
+          super(pattern)
+        end
+
+        def skip(pattern)
+          pattern = /#{Regexp.escape(pattern)}/ if pattern.is_a?(String)
+          super(pattern)
+        end
       end
     end
     using StringScannerCheckScanString
@@ -35,7 +46,6 @@ module REXML
           arg.respond_to? :eof?
         IOSource.new(arg)
       elsif arg.respond_to? :to_str
-        require 'stringio'
         IOSource.new(StringIO.new(arg))
       elsif arg.kind_of? Source
         arg
@@ -77,6 +87,7 @@ module REXML
         detect_encoding
       end
       @line = 0
+      @encoded_terms = {}
     end
 
     # The current buffer (what we're going to read next)
@@ -125,6 +136,14 @@ module REXML
       end
     end
 
+    def match?(pattern, cons=false)
+      if cons
+        !@scanner.skip(pattern).nil?
+      else
+        !@scanner.match?(pattern).nil?
+      end
+    end
+
     def position
       @scanner.pos
     end
@@ -227,7 +246,7 @@ module REXML
 
     def read_until(term)
       pattern = Private::PRE_DEFINED_TERM_PATTERNS[term] || /#{Regexp.escape(term)}/
-      term = encode(term)
+      term = @encoded_terms[term] ||= encode(term)
       until str = @scanner.scan_until(pattern)
         break if @source.nil?
         break if @source.eof?
@@ -266,6 +285,23 @@ module REXML
       md.nil? ? nil : @scanner
     end
 
+    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
+          n_matched_bytes = @scanner.skip(pattern)
+        else
+          n_matched_bytes = @scanner.match?(pattern)
+        end
+        return true if n_matched_bytes
+        return false if pattern.is_a?(String)
+        return false if @source.nil?
+        return false unless read(nil, min_bytes)
+        min_bytes *= 2
+      end
+    end
+
     def empty?
       super and ( @source.nil? || @source.eof? )
     end
@@ -285,7 +321,7 @@ module REXML
         rescue
         end
         @er_source.seek(pos)
-      rescue IOError
+      rescue IOError, SystemCallError
         pos = -1
         line = -1
       end
@@ -294,14 +330,19 @@ module REXML
 
     private
     def readline(term = nil)
-      str = @source.readline(term || @line_break)
       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?
 

data/lib/rexml/text.rb

@@ -29,31 +29,16 @@ module REXML
       (0x10000..0x10FFFF)
     ]
 
-    if String.method_defined? :encode
-      VALID_XML_CHARS = Regexp.new('^['+
-        VALID_CHAR.map { |item|
-          case item
-          when Integer
-            [item].pack('U').force_encoding('utf-8')
-          when Range
-            [item.first, '-'.ord, item.last].pack('UUU').force_encoding('utf-8')
-          end
-        }.join +
-      ']*$')
-    else
-      VALID_XML_CHARS = /^(
-           [\x09\x0A\x0D\x20-\x7E]            # ASCII
-         | [\xC2-\xDF][\x80-\xBF]             # non-overlong 2-byte
-         |  \xE0[\xA0-\xBF][\x80-\xBF]        # excluding overlongs
-         | [\xE1-\xEC\xEE][\x80-\xBF]{2}      # straight 3-byte
-         |  \xEF[\x80-\xBE]{2}                #
-         |  \xEF\xBF[\x80-\xBD]               # excluding U+fffe and U+ffff
-         |  \xED[\x80-\x9F][\x80-\xBF]        # excluding surrogates
-         |  \xF0[\x90-\xBF][\x80-\xBF]{2}     # planes 1-3
-         | [\xF1-\xF3][\x80-\xBF]{3}          # planes 4-15
-         |  \xF4[\x80-\x8F][\x80-\xBF]{2}     # plane 16
-       )*$/nx;
-    end
+    VALID_XML_CHARS = Regexp.new('^['+
+      VALID_CHAR.map { |item|
+        case item
+        when Integer
+          [item].pack('U').force_encoding('utf-8')
+        when Range
+          [item.first, '-'.ord, item.last].pack('UUU').force_encoding('utf-8')
+        end
+      }.join +
+    ']*$')
 
     # Constructor
     # +arg+ if a String, the content is set to the String.  If a Text,
@@ -132,21 +117,11 @@ module REXML
 
       # illegal anywhere
       if !string.match?(VALID_XML_CHARS)
-        if String.method_defined? :encode
-          string.chars.each do |c|
-            case c.ord
-            when *VALID_CHAR
-            else
-              raise "Illegal character #{c.inspect} in raw string #{string.inspect}"
-            end
-          end
-        else
-          string.scan(/[\x00-\x7F]|[\x80-\xBF][\xC0-\xF0]*|[\xC0-\xF0]/n) do |c|
-            case c.unpack('U')
-            when *VALID_CHAR
-            else
-              raise "Illegal character #{c.inspect} in raw string #{string.inspect}"
-            end
+        string.chars.each do |c|
+          case c.ord
+          when *VALID_CHAR
+          else
+            raise "Illegal character #{c.inspect} in raw string #{string.inspect}"
           end
         end
       end

metadata

@@ -1,13 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rexml
 version: !ruby/object:Gem::Version
-  version: 3.3.8
+  version: 3.4.0
 platform: ruby
 authors:
 - Kouhei Sutou
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-09-29 00:00:00.000000000 Z
+date: 2024-12-15 00:00:00.000000000 Z
 dependencies: []
 description: An XML toolkit for Ruby
 email:
@@ -102,7 +103,8 @@ homepage: https://github.com/ruby/rexml
 licenses:
 - BSD-2-Clause
 metadata:
-  changelog_uri: https://github.com/ruby/rexml/releases/tag/v3.3.8
+  changelog_uri: https://github.com/ruby/rexml/releases/tag/v3.4.0
+post_install_message:
 rdoc_options:
 - "--main"
 - README.md
@@ -119,7 +121,8 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.6.0.dev
+rubygems_version: 3.5.22
+signing_key:
 specification_version: 4
 summary: An XML toolkit for Ruby
 test_files: []