rexml 3.2.6 → 3.2.9

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2583ae302aa5e698f0887a689c416e5debe0533ac472a9f96fce6a8912040fd8
-  data.tar.gz: b0ffa6301fd899969a78e060ccaeafebfc2169e3c63ff499ebc6170468866475
+  metadata.gz: ed57404d6f519cb196d671fd629380f5b08a50cf649ae99a71432edceaf15014
+  data.tar.gz: 9097f235049d98aa743998da10724fd6ff5f6cd0cb4f230c59290af4a75e2134
 SHA512:
-  metadata.gz: f63fb0b84ef51e790cc6310244f2106d8c47ec9a00687c58c743afda82b60be9986d503c6f56f947db06f6758707facccd03405c4d1009376e856080aa26d0e4
-  data.tar.gz: db62bea7391837a7ab4cfc5cb5a412ed4deb8d232653ca66d93a323a5a76383eed520cd4ced5b20204f29b04e84678791cd6f807195868f5d4a5e519a73d2aaf
+  metadata.gz: 0d7a0be04c12fcd88c64dd2962d4db49f57ed02c08e3f4628e8e546aea135c672839a19a950423afa72d0cf25af0554558f2261b6b5f2b23637f4ca47d43bd73
+  data.tar.gz: 28479b3b11de58e84f57dc88057f185eb2365998f7fbc9f0df78d5899bb9b241c6bb93d26a57ca1b54d8a058b743daa78a8df52c4ddbfbb5f7c94aeb97724808

data/NEWS.md

@@ -1,5 +1,97 @@
 # News
 
+## 3.2.9 - 2024-06-19 {#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
+
+  * Suppressed a warning
+
+## 3.2.7 - 2024-05-16 {#version-3-2-7}
+
+### Improvements
+
+  * Improve parse performance by using `StringScanner`.
+
+    * GH-106
+    * GH-107
+    * GH-108
+    * GH-109
+    * GH-112
+    * GH-113
+    * GH-114
+    * GH-115
+    * GH-116
+    * GH-117
+    * GH-118
+    * GH-119
+    * GH-121
+
+    * Patch by NAITOH Jun.
+
+  * Improved parse performance when an attribute has many `<`s.
+
+    * GH-126
+
+### Fixes
+
+  * XPath: Fixed a bug of `normalize_space(array)`.
+
+    * GH-110
+    * GH-111
+
+    * Patch by flatisland.
+
+  * XPath: Fixed a bug that wrong position is used with nested path.
+
+    * GH-110
+    * GH-122
+
+    * Reported by jcavalieri.
+    * Patch by NAITOH Jun.
+
+  * Fixed a bug that an exception message can't be generated for
+    invalid encoding XML.
+
+    * GH-29
+    * GH-123
+
+    * Reported by DuKewu.
+    * Patch by NAITOH Jun.
+
+### Thanks
+
+  * NAITOH Jun
+  * flatisland
+  * jcavalieri
+  * DuKewu
+
 ## 3.2.6 - 2023-07-27 {#version-3-2-6}
 
 ### Improvements

data/lib/rexml/functions.rb

@@ -262,11 +262,10 @@ module REXML
       string(string).length
     end
 
-    # UNTESTED
     def Functions::normalize_space( string=nil )
       string = string(@@context[:node]) if string.nil?
       if string.kind_of? Array
-        string.collect{|x| string.to_s.strip.gsub(/\s+/um, ' ') if string}
+        string.collect{|x| x.to_s.strip.gsub(/\s+/um, ' ') if x}
       else
         string.to_s.strip.gsub(/\s+/um, ' ')
       end

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/parseexception.rb

@@ -29,6 +29,7 @@ module REXML
         err << "\nLine: #{line}\n"
         err << "Position: #{position}\n"
         err << "Last 80 unconsumed characters:\n"
+        err.force_encoding("ASCII-8BIT")
         err << @source.buffer[0..80].force_encoding("ASCII-8BIT").gsub(/\n/, ' ')
       end
 

data/lib/rexml/parsers/baseparser.rb

@@ -1,4 +1,4 @@
-# frozen_string_literal: false
+# frozen_string_literal: true
 require_relative '../parseexception'
 require_relative '../undefinednamespaceexception'
 require_relative '../source'
@@ -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>" )
@@ -96,7 +107,7 @@ module REXML
       ENTITYDEF = "(?:#{ENTITYVALUE}|(?:#{EXTERNALID}(#{NDATADECL})?))"
       PEDECL = "<!ENTITY\\s+(%)\\s+#{NAME}\\s+#{PEDEF}\\s*>"
       GEDECL = "<!ENTITY\\s+#{NAME}\\s+#{ENTITYDEF}\\s*>"
-      ENTITYDECL = /\s*(?:#{GEDECL})|(?:#{PEDECL})/um
+      ENTITYDECL = /\s*(?:#{GEDECL})|\s*(?:#{PEDECL})/um
 
       NOTATIONDECL_START = /\A\s*<!NOTATION/um
       EXTERNAL_ID_PUBLIC = /\A\s*PUBLIC\s+#{PUBIDLITERAL}\s+#{SYSTEMLITERAL}\s*/um
@@ -112,6 +123,19 @@ module REXML
         "apos" => [/&apos;/, "&apos;", "'", /'/]
       }
 
+      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
+        GEDECL_PATTERN = "\\s+#{NAME}\\s+#{ENTITYDEF}\\s*>"
+        PEDECL_PATTERN = "\\s+(%)\\s+#{NAME}\\s+#{PEDEF}\\s*>"
+        ENTITYDECL_PATTERN = /(?:#{GEDECL_PATTERN})|(?:#{PEDECL_PATTERN})/um
+      end
+      private_constant :Private
+      include Private
+
       def initialize( source )
         self.stream = source
         @listeners = []
@@ -196,181 +220,184 @@ module REXML
         return @stack.shift if @stack.size > 0
         #STDERR.puts @source.encoding
         #STDERR.puts "BUFFER = #{@source.buffer.inspect}"
+
+        @source.ensure_buffer
         if @document_status == nil
-          word = @source.match( /\A((?:\s+)|(?:<[^>]*>))/um )
-          word = word[1] unless word.nil?
-          #STDERR.puts "WORD = #{word.inspect}"
-          case word
-          when COMMENT_START
-            return [ :comment, @source.match( COMMENT_PATTERN, true )[1] ]
-          when XMLDECL_START
-            #STDERR.puts "XMLDECL"
-            results = @source.match( XMLDECL_PATTERN, true )[1]
-            version = VERSION.match( results )
-            version = version[1] unless version.nil?
-            encoding = ENCODING.match(results)
-            encoding = encoding[1] unless encoding.nil?
-            if need_source_encoding_update?(encoding)
-              @source.encoding = encoding
-            end
-            if encoding.nil? and /\AUTF-16(?:BE|LE)\z/i =~ @source.encoding
-              encoding = "UTF-16"
-            end
-            standalone = STANDALONE.match(results)
-            standalone = standalone[1] unless standalone.nil?
-            return [ :xmldecl, version, encoding, standalone ]
-          when INSTRUCTION_START
-            return process_instruction
-          when DOCTYPE_START
-            base_error_message = "Malformed DOCTYPE"
-            @source.match(DOCTYPE_START, true)
-            @nsstack.unshift(curr_ns=Set.new)
-            name = parse_name(base_error_message)
-            if @source.match(/\A\s*\[/um, true)
-              id = [nil, nil, nil]
-              @document_status = :in_doctype
-            elsif @source.match(/\A\s*>/um, true)
-              id = [nil, nil, nil]
-              @document_status = :after_doctype
-            else
-              id = parse_id(base_error_message,
-                            accept_external_id: true,
-                            accept_public_id: false)
-              if id[0] == "SYSTEM"
-                # For backward compatibility
-                id[1], id[2] = id[2], nil
+          start_position = @source.position
+          if @source.match("<?", true)
+            return process_instruction(start_position)
+          elsif @source.match("<!", true)
+            if @source.match("--", true)
+              return [ :comment, @source.match(/(.*?)-->/um, true)[1] ]
+            elsif @source.match("DOCTYPE", true)
+              base_error_message = "Malformed DOCTYPE"
+              unless @source.match(/\s+/um, true)
+                if @source.match(">")
+                  message = "#{base_error_message}: name is missing"
+                else
+                  message = "#{base_error_message}: invalid name"
+                end
+                @source.position = start_position
+                raise REXML::ParseException.new(message, @source)
               end
-              if @source.match(/\A\s*\[/um, true)
+              @nsstack.unshift(curr_ns=Set.new)
+              name = parse_name(base_error_message)
+              if @source.match(/\s*\[/um, true)
+                id = [nil, nil, nil]
                 @document_status = :in_doctype
-              elsif @source.match(/\A\s*>/um, true)
+              elsif @source.match(/\s*>/um, true)
+                id = [nil, nil, nil]
                 @document_status = :after_doctype
+                @source.ensure_buffer
               else
-                message = "#{base_error_message}: garbage after external ID"
-                raise REXML::ParseException.new(message, @source)
+                id = parse_id(base_error_message,
+                              accept_external_id: true,
+                              accept_public_id: false)
+                if id[0] == "SYSTEM"
+                  # For backward compatibility
+                  id[1], id[2] = id[2], nil
+                end
+                if @source.match(/\s*\[/um, true)
+                  @document_status = :in_doctype
+                elsif @source.match(/\s*>/um, true)
+                  @document_status = :after_doctype
+                  @source.ensure_buffer
+                else
+                  message = "#{base_error_message}: garbage after external ID"
+                  raise REXML::ParseException.new(message, @source)
+                end
               end
-            end
-            args = [:start_doctype, name, *id]
-            if @document_status == :after_doctype
-              @source.match(/\A\s*/um, true)
-              @stack << [ :end_doctype ]
-            end
-            return args
-          when /\A\s+/
-          else
-            @document_status = :after_doctype
-            if @source.encoding == "UTF-8"
-              @source.buffer.force_encoding(::Encoding::UTF_8)
+              args = [:start_doctype, name, *id]
+              if @document_status == :after_doctype
+                @source.match(/\s*/um, true)
+                @stack << [ :end_doctype ]
+              end
+              return args
+            else
+              message = "Invalid XML"
+              raise REXML::ParseException.new(message, @source)
             end
           end
         end
         if @document_status == :in_doctype
-          md = @source.match(/\A\s*(.*?>)/um)
-          case md[1]
-          when SYSTEMENTITY
-            match = @source.match( SYSTEMENTITY, true )[1]
-            return [ :externalentity, match ]
-
-          when ELEMENTDECL_START
-            return [ :elementdecl, @source.match( ELEMENTDECL_PATTERN, true )[1] ]
-
-          when ENTITY_START
-            match = @source.match( ENTITYDECL, true ).to_a.compact
-            match[0] = :entitydecl
-            ref = false
-            if match[1] == '%'
-              ref = true
-              match.delete_at 1
-            end
-            # Now we have to sort out what kind of entity reference this is
-            if match[2] == 'SYSTEM'
-              # External reference
-              match[3] = match[3][1..-2] # PUBID
-              match.delete_at(4) if match.size > 4 # Chop out NDATA decl
-              # match is [ :entity, name, SYSTEM, pubid(, ndata)? ]
-            elsif match[2] == 'PUBLIC'
-              # External reference
-              match[3] = match[3][1..-2] # PUBID
-              match[4] = match[4][1..-2] # HREF
-              match.delete_at(5) if match.size > 5 # Chop out NDATA decl
-              # match is [ :entity, name, PUBLIC, pubid, href(, ndata)? ]
-            else
-              match[2] = match[2][1..-2]
-              match.pop if match.size == 4
-              # match is [ :entity, name, value ]
-            end
-            match << '%' if ref
-            return match
-          when ATTLISTDECL_START
-            md = @source.match( ATTLISTDECL_PATTERN, 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.each do |attdef|
-              unless attdef[3] == "#IMPLIED"
-                attdef.compact!
-                val = attdef[3]
-                val = attdef[4] if val == "#FIXED "
-                pairs[attdef[0]] = val
-                if attdef[0] =~ /^xmlns:(.*)/
-                  @nsstack[0] << $1
-                end
+          @source.match(/\s*/um, true) # skip spaces
+          start_position = @source.position
+          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)
+              match = [:entitydecl, *@source.match(ENTITYDECL_PATTERN, true).captures.compact]
+              ref = false
+              if match[1] == '%'
+                ref = true
+                match.delete_at 1
               end
-            end
-            return [ :attlistdecl, element, pairs, contents ]
-          when NOTATIONDECL_START
-            base_error_message = "Malformed notation declaration"
-            unless @source.match(/\A\s*<!NOTATION\s+/um, true)
-              if @source.match(/\A\s*<!NOTATION\s*>/um)
-                message = "#{base_error_message}: name is missing"
+              # Now we have to sort out what kind of entity reference this is
+              if match[2] == 'SYSTEM'
+                # External reference
+                match[3] = match[3][1..-2] # PUBID
+                match.delete_at(4) if match.size > 4 # Chop out NDATA decl
+                # match is [ :entity, name, SYSTEM, pubid(, ndata)? ]
+              elsif match[2] == 'PUBLIC'
+                # External reference
+                match[3] = match[3][1..-2] # PUBID
+                match[4] = match[4][1..-2] # HREF
+                match.delete_at(5) if match.size > 5 # Chop out NDATA decl
+                # match is [ :entity, name, PUBLIC, pubid, href(, ndata)? ]
               else
-                message = "#{base_error_message}: invalid declaration name"
+                match[2] = match[2][1..-2]
+                match.pop if match.size == 4
+                # match is [ :entity, name, value ]
               end
-              raise REXML::ParseException.new(message, @source)
-            end
-            name = parse_name(base_error_message)
-            id = parse_id(base_error_message,
-                          accept_external_id: true,
-                          accept_public_id: true)
-            unless @source.match(/\A\s*>/um, true)
-              message = "#{base_error_message}: garbage before end >"
-              raise REXML::ParseException.new(message, @source)
+              match << '%' if ref
+              return match
+            elsif @source.match("ATTLIST", true)
+              md = @source.match(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.each do |attdef|
+                unless attdef[3] == "#IMPLIED"
+                  attdef.compact!
+                  val = attdef[3]
+                  val = attdef[4] if val == "#FIXED "
+                  pairs[attdef[0]] = val
+                  if attdef[0] =~ /^xmlns:(.*)/
+                    @nsstack[0] << $1
+                  end
+                end
+              end
+              return [ :attlistdecl, element, pairs, contents ]
+            elsif @source.match("NOTATION", true)
+              base_error_message = "Malformed notation declaration"
+              unless @source.match(/\s+/um, true)
+                if @source.match(">")
+                  message = "#{base_error_message}: name is missing"
+                else
+                  message = "#{base_error_message}: invalid name"
+                end
+                @source.position = start_position
+                raise REXML::ParseException.new(message, @source)
+              end
+              name = parse_name(base_error_message)
+              id = parse_id(base_error_message,
+                            accept_external_id: true,
+                            accept_public_id: true)
+              unless @source.match(/\s*>/um, true)
+                message = "#{base_error_message}: garbage before end >"
+                raise REXML::ParseException.new(message, @source)
+              end
+              return [:notationdecl, name, *id]
+            elsif md = @source.match(/--(.*?)-->/um, true)
+              case md[1]
+              when /--/, /-\z/
+                raise REXML::ParseException.new("Malformed comment", @source)
+              end
+              return [ :comment, md[1] ] if md
             end
-            return [:notationdecl, name, *id]
-          when DOCTYPE_END
+          elsif match = @source.match(/(%.*?;)\s*/um, true)
+            return [ :externalentity, match[1] ]
+          elsif @source.match(/\]\s*>/um, true)
             @document_status = :after_doctype
-            @source.match( DOCTYPE_END, true )
             return [ :end_doctype ]
           end
         end
         if @document_status == :after_doctype
-          @source.match(/\A\s*/um, true)
+          @source.match(/\s*/um, true)
         end
         begin
-          @source.read if @source.buffer.size<2
-          if @source.buffer[0] == ?<
-            if @source.buffer[1] == ?/
+          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_MATCH, true )
+              md = @source.match(CLOSE_PATTERN, true)
               if md and !last_tag
                 message = "Unexpected top-level end tag (got '#{md[1]}')"
                 raise REXML::ParseException.new(message, @source)
               end
               if md.nil? or last_tag != md[1]
                 message = "Missing end tag for '#{last_tag}'"
-                message << " (got '#{md[1]}')" if md
+                message += " (got '#{md[1]}')" if md
+                @source.position = start_position if md.nil?
                 raise REXML::ParseException.new(message, @source)
               end
               return [ :end_element, last_tag ]
-            elsif @source.buffer[1] == ?!
-              md = @source.match(/\A(\s*[^>]*>)/um)
+            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
-              if md[0][2] == ?-
-                md = @source.match( COMMENT_PATTERN, true )
+              if md[0][0] == ?-
+                md = @source.match(/--(.*?)-->/um, true)
 
                 case md[1]
                 when /--/, /-\z/
@@ -379,19 +406,21 @@ module REXML
 
                 return [ :comment, md[1] ] if md
               else
-                md = @source.match( CDATA_PATTERN, true )
+                md = @source.match(/\[CDATA\[(.*?)\]\]>/um, true)
                 return [ :cdata, md[1] ] if md
               end
               raise REXML::ParseException.new( "Declarations can only occur "+
                 "in the doctype declaration.", @source)
-            elsif @source.buffer[1] == ??
-              return process_instruction
+            elsif @source.match("?", true)
+              return process_instruction(start_position)
             else
               # Get the next tag
-              md = @source.match(TAG_MATCH, true)
+              md = @source.match(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]
@@ -405,23 +434,19 @@ module REXML
               end
 
               if closed
-                @closed = md[1]
+                @closed = tag
                 @nsstack.shift
               else
-                @tags.push( md[1] )
+                @tags.push( tag )
               end
-              return [ :start_element, md[1], attributes ]
+              return [ :start_element, tag, attributes ]
             end
           else
-            md = @source.match( TEXT_PATTERN, true )
-            if md[0].length == 0
-              @source.match( /(\s+)/, true )
+            text = @source.read_until("<")
+            if text.chomp!("<")
+              @source.position -= "<".bytesize
             end
-            #STDERR.puts "GOT #{md[1].inspect}" unless md[0].length == 0
-            #return [ :text, "" ] if md[0].length == 0
-            # unnormalized = Text::unnormalize( md[1], self )
-            # return PullEvent.new( :text, md[1], unnormalized )
-            return [ :text, md[1] ]
+            return [ :text, text ]
           end
         rescue REXML::UndefinedNamespaceException
           raise
@@ -463,8 +488,7 @@ module REXML
 
       # Unescapes all possible entities
       def unnormalize( string, entities=nil, filter=nil )
-        rv = string.clone
-        rv.gsub!( /\r\n?/, "\n" )
+        rv = string.gsub( /\r\n?/, "\n" )
         matches = rv.scan( REFERENCE_RE )
         return rv if matches.size == 0
         rv.gsub!( /&#0*((?:\d+)|(?:x[a-fA-F0-9]+));/ ) {
@@ -499,9 +523,9 @@ module REXML
       end
 
       def parse_name(base_error_message)
-        md = @source.match(/\A\s*#{NAME}/um, true)
+        md = @source.match(NAME_PATTERN, true)
         unless md
-          if @source.match(/\A\s*\S/um)
+          if @source.match(/\s*\S/um)
             message = "#{base_error_message}: invalid name"
           else
             message = "#{base_error_message}: name is missing"
@@ -577,97 +601,91 @@ module REXML
         end
       end
 
-      def process_instruction
-        match_data = @source.match(INSTRUCTION_PATTERN, true)
+      def process_instruction(start_position)
+        match_data = @source.match(INSTRUCTION_END, true)
         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"
+          content = match_data[2]
+          version = VERSION.match(content)
+          version = version[1] unless version.nil?
+          encoding = ENCODING.match(content)
+          encoding = encoding[1] unless encoding.nil?
+          if need_source_encoding_update?(encoding)
+            @source.encoding = encoding
+          end
+          if encoding.nil? and /\AUTF-16(?:BE|LE)\z/i =~ @source.encoding
+            encoding = "UTF-16"
+          end
+          standalone = STANDALONE.match(content)
+          standalone = standalone[1] unless standalone.nil?
+          return [ :xmldecl, version, encoding, standalone ]
+        end
         [:processing_instruction, match_data[1], match_data[2]]
       end
 
       def parse_attributes(prefixes, curr_ns)
         attributes = {}
         closed = false
-        match_data = @source.match(/^(.*?)(\/)?>/um, true)
-        if match_data.nil?
-          message = "Start tag isn't ended"
-          raise REXML::ParseException.new(message, @source)
-        end
-
-        raw_attributes = match_data[1]
-        closed = !match_data[2].nil?
-        return attributes, closed if raw_attributes.nil?
-        return attributes, closed if raw_attributes.empty?
-
-        scanner = StringScanner.new(raw_attributes)
-        until scanner.eos?
-          if scanner.scan(/\s+/)
-            break if scanner.eos?
-          end
-
-          pos = scanner.pos
-          loop do
-            break if scanner.scan(ATTRIBUTE_PATTERN)
-            unless scanner.scan(QNAME)
-              message = "Invalid attribute name: <#{scanner.rest}>"
-              raise REXML::ParseException.new(message, @source)
-            end
-            name = scanner[0]
-            unless scanner.scan(/\s*=\s*/um)
+        while true
+          if @source.match(">", true)
+            return attributes, closed
+          elsif @source.match("/>", true)
+            closed = true
+            return attributes, closed
+          elsif match = @source.match(QNAME, true)
+            name = match[1]
+            prefix = match[2]
+            local_part = match[3]
+
+            unless @source.match(/\s*=\s*/um, true)
               message = "Missing attribute equal: <#{name}>"
               raise REXML::ParseException.new(message, @source)
             end
-            quote = scanner.scan(/['"]/)
-            unless quote
+            unless match = @source.match(/(['"])/, true)
               message = "Missing attribute value start quote: <#{name}>"
               raise REXML::ParseException.new(message, @source)
             end
-            unless scanner.scan(/.*#{Regexp.escape(quote)}/um)
-              match_data = @source.match(/^(.*?)(\/)?>/um, true)
-              if match_data
-                scanner << "/" if closed
-                scanner << ">"
-                scanner << match_data[1]
-                scanner.pos = pos
-                closed = !match_data[2].nil?
-                next
-              end
-              message =
-                "Missing attribute value end quote: <#{name}>: <#{quote}>"
+            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
-          end
-          name = scanner[1]
-          prefix = scanner[2]
-          local_part = scanner[3]
-          # quote = scanner[4]
-          value = scanner[5]
-          if prefix == "xmlns"
-            if local_part == "xml"
-              if value != "http://www.w3.org/XML/1998/namespace"
-                msg = "The 'xml' prefix must not be bound to any other namespace "+
+            @source.match(/\s*/um, true)
+            if prefix == "xmlns"
+              if local_part == "xml"
+                if value != "http://www.w3.org/XML/1998/namespace"
+                  msg = "The 'xml' prefix must not be bound to any other namespace "+
+                    "(http://www.w3.org/TR/REC-xml-names/#ns-decl)"
+                  raise REXML::ParseException.new( msg, @source, self )
+                end
+              elsif local_part == "xmlns"
+                msg = "The 'xmlns' prefix must not be declared "+
                   "(http://www.w3.org/TR/REC-xml-names/#ns-decl)"
-                raise REXML::ParseException.new( msg, @source, self )
+                raise REXML::ParseException.new( msg, @source, self)
               end
-            elsif local_part == "xmlns"
-              msg = "The 'xmlns' prefix must not be declared "+
-                "(http://www.w3.org/TR/REC-xml-names/#ns-decl)"
-              raise REXML::ParseException.new( msg, @source, self)
+              curr_ns << local_part
+            elsif prefix
+              prefixes << prefix unless prefix == "xml"
             end
-            curr_ns << local_part
-          elsif prefix
-            prefixes << prefix unless prefix == "xml"
-          end
 
-          if attributes.has_key?(name)
-            msg = "Duplicate attribute #{name.inspect}"
-            raise REXML::ParseException.new(msg, @source, self)
-          end
+            if attributes[name]
+              msg = "Duplicate attribute #{name.inspect}"
+              raise REXML::ParseException.new(msg, @source, self)
+            end
 
-          attributes[name] = value
+            attributes[name] = value
+          else
+            message = "Invalid attribute name: <#{@source.buffer.split(%r{[/>\s]}).first}>"
+            raise REXML::ParseException.new(message, @source)
+          end
         end
-        return attributes, closed
       end
     end
   end

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 = "3.2.9"
   REVISION = ""
 
   Copyright = COPYRIGHT

data/lib/rexml/source.rb

@@ -30,18 +30,27 @@ 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
+      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
+    include 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
@@ -50,6 +59,14 @@ module REXML
       @line = 0
     end
 
+    # The current buffer (what we're going to read next)
+    def buffer
+      @scanner.rest
+    end
+
+    def buffer_encoding=(encoding)
+      @scanner.string.force_encoding(encoding)
+    end
 
     # Inherited from Encoding
     # Overridden to support optimized en/decoding
@@ -58,98 +75,78 @@ 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 +169,7 @@ 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 +178,62 @@ 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
-          end
-        end
-        rv = super
-      end
-      rv.taint if RUBY_VERSION < '2.7'
-      rv
-    end
-
-    def read
+    def read(term = nil)
+      term = encode(term) if term
       begin
-        @buffer << readline
+        @scanner << readline(term)
+        true
       rescue Exception, NameError
         @source = nil
+        false
+      end
+    end
+
+    def read_until(term)
+      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
 
-    def consume( pattern )
-      match( pattern, true )
+    def ensure_buffer
+      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 )
-      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
+      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
       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
@@ -263,8 +257,8 @@ module REXML
     end
 
     private
-    def readline
-      str = @source.readline(@line_break)
+    def readline(term = nil)
+      str = @source.readline(term || @line_break)
       if @pending_buffer
         if str.nil?
           str = @pending_buffer
@@ -290,7 +284,7 @@ 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/xpath_parser.rb

@@ -590,6 +590,7 @@ module REXML
 
     def evaluate_predicate(expression, nodesets)
       enter(:predicate, expression, nodesets) if @debug
+      new_nodeset_count = 0
       new_nodesets = nodesets.collect do |nodeset|
         new_nodeset = []
         subcontext = { :size => nodeset.size }
@@ -606,17 +607,20 @@ module REXML
           result = result[0] if result.kind_of? Array and result.length == 1
           if result.kind_of? Numeric
             if result == node.position
-              new_nodeset << XPathNode.new(node, position: new_nodeset.size + 1)
+              new_nodeset_count += 1
+              new_nodeset << XPathNode.new(node, position: new_nodeset_count)
             end
           elsif result.instance_of? Array
             if result.size > 0 and result.inject(false) {|k,s| s or k}
               if result.size > 0
-                new_nodeset << XPathNode.new(node, position: new_nodeset.size + 1)
+                new_nodeset_count += 1
+                new_nodeset << XPathNode.new(node, position: new_nodeset_count)
               end
             end
           else
             if result
-              new_nodeset << XPathNode.new(node, position: new_nodeset.size + 1)
+              new_nodeset_count += 1
+              new_nodeset << XPathNode.new(node, position: new_nodeset_count)
             end
           end
         end

metadata

@@ -1,51 +1,22 @@
 --- !ruby/object:Gem::Specification
 name: rexml
 version: !ruby/object:Gem::Version
-  version: 3.2.6
+  version: 3.2.9
 platform: ruby
 authors:
 - Kouhei Sutou
-autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-07-27 00:00:00.000000000 Z
+date: 2024-06-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: bundler
+  name: strscan
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: rake
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-- !ruby/object:Gem::Dependency
-  name: test-unit
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - ">="
-      - !ruby/object:Gem::Version
-        version: '0'
-  type: :development
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
@@ -145,7 +116,6 @@ homepage: https://github.com/ruby/rexml
 licenses:
 - BSD-2-Clause
 metadata: {}
-post_install_message:
 rdoc_options:
 - "--main"
 - README.md
@@ -162,8 +132,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.0.dev
-signing_key:
+rubygems_version: 3.6.0.dev
 specification_version: 4
 summary: An XML toolkit for Ruby
 test_files: []