rexml 3.2.3 → 3.2.8

data/lib/rexml/source.rb

@@ -30,8 +30,6 @@ 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
@@ -41,7 +39,8 @@ module REXML
     # @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 +49,14 @@ 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 +65,72 @@ 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)
+      @scanner.scan_until(Regexp.union(term)) or @scanner.rest
     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 +153,7 @@ 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 +162,57 @@ 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
+    def read(term = nil)
+      begin
+        @scanner << readline(term)
+        true
+      rescue Exception, NameError
+        @source = nil
+        false
       end
-      rv.taint
-      rv
     end
 
-    def read
+    def read_until(term)
+      pattern = Regexp.union(term)
       begin
-        @buffer << readline
-      rescue Exception, NameError
-        @source = nil
+        until str = @scanner.scan_until(pattern)
+          @scanner << readline(term)
+        end
+      rescue EOFError
+        @scanner.rest
+      else
+        read if @scanner.eos? and !@source.eof?
+        str
       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
-      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 +236,8 @@ 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 +263,7 @@ 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

@@ -1,4 +1,4 @@
-# frozen_string_literal: false
+# frozen_string_literal: true
 require_relative 'security'
 require_relative 'entity'
 require_relative 'doctype'
@@ -109,7 +109,7 @@ module REXML
         @string = arg.instance_variable_get(:@string).dup
         @raw = arg.raw
         @entity_filter = arg.instance_variable_get(:@entity_filter)
-      elsif
+      else
         raise "Illegal argument of type #{arg.type} for Text constructor (#{arg})"
       end
 
@@ -131,7 +131,7 @@ module REXML
     def Text.check string, pattern, doctype
 
       # illegal anywhere
-      if string !~ VALID_XML_CHARS
+      if !string.match?(VALID_XML_CHARS)
         if String.method_defined? :encode
           string.chars.each do |c|
             case c.ord
@@ -371,7 +371,7 @@ module REXML
       copy = input.to_s
       # Doing it like this rather than in a loop improves the speed
       #copy = copy.gsub( EREFERENCE, '&' )
-      copy = copy.gsub( "&", "&" )
+      copy = copy.gsub( "&", "&" ) if copy.include?("&")
       if doctype
         # Replace all ampersands that aren't part of an entity
         doctype.entities.each_value do |entity|
@@ -382,7 +382,9 @@ module REXML
       else
         # Replace all ampersands that aren't part of an entity
         DocType::DEFAULT_ENTITIES.each_value do |entity|
-          copy = copy.gsub(entity.value, "&#{entity.name};" )
+          if copy.include?(entity.value)
+            copy = copy.gsub(entity.value, "&#{entity.name};" )
+          end
         end
       end
       copy

data/lib/rexml/xpath_parser.rb

@@ -7,39 +7,45 @@ require_relative 'xmltokens'
 require_relative 'attribute'
 require_relative 'parsers/xpathparser'
 
-class Object
-  # provides a unified +clone+ operation, for REXML::XPathParser
-  # to use across multiple Object types
-  def dclone
-    clone
-  end
-end
-class Symbol
-  # provides a unified +clone+ operation, for REXML::XPathParser
-  # to use across multiple Object types
-  def dclone ; self ; end
-end
-class Integer
-  # provides a unified +clone+ operation, for REXML::XPathParser
-  # to use across multiple Object types
-  def dclone ; self ; end
-end
-class Float
-  # provides a unified +clone+ operation, for REXML::XPathParser
-  # to use across multiple Object types
-  def dclone ; self ; end
-end
-class Array
-  # provides a unified +clone+ operation, for REXML::XPathParser
-  # to use across multiple Object+ types
-  def dclone
-    klone = self.clone
-    klone.clear
-    self.each{|v| klone << v.dclone}
-    klone
+module REXML
+  module DClonable
+    refine Object do
+      # provides a unified +clone+ operation, for REXML::XPathParser
+      # to use across multiple Object types
+      def dclone
+        clone
+      end
+    end
+    refine Symbol do
+      # provides a unified +clone+ operation, for REXML::XPathParser
+      # to use across multiple Object types
+      def dclone ; self ; end
+    end
+    refine Integer do
+      # provides a unified +clone+ operation, for REXML::XPathParser
+      # to use across multiple Object types
+      def dclone ; self ; end
+    end
+    refine Float do
+      # provides a unified +clone+ operation, for REXML::XPathParser
+      # to use across multiple Object types
+      def dclone ; self ; end
+    end
+    refine Array do
+      # provides a unified +clone+ operation, for REXML::XPathParser
+      # to use across multiple Object+ types
+      def dclone
+        klone = self.clone
+        klone.clear
+        self.each{|v| klone << v.dclone}
+        klone
+      end
+    end
   end
 end
 
+using REXML::DClonable
+
 module REXML
   # You don't want to use this class.  Really.  Use XPath, which is a wrapper
   # for this class.  Believe me.  You don't want to poke around in here.
@@ -584,6 +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 }
@@ -600,17 +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

data/lib/rexml.rb

@@ -0,0 +1,3 @@
+# frozen_string_literal: true
+
+require_relative "rexml/document"

metadata

@@ -1,57 +1,68 @@
 --- !ruby/object:Gem::Specification
 name: rexml
 version: !ruby/object:Gem::Version
-  version: 3.2.3
+  version: 3.2.8
 platform: ruby
 authors:
 - Kouhei Sutou
-autorequire: 
-bindir: exe
+bindir: bin
 cert_chain: []
-date: 2019-10-11 00:00:00.000000000 Z
+date: 2024-05-16 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
+        version: 3.0.9
+  type: :runtime
   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'
+        version: 3.0.9
 description: An XML toolkit for Ruby
 email:
 - kou@cozmixng.org
 executables: []
 extensions: []
-extra_rdoc_files: []
+extra_rdoc_files:
+- LICENSE.txt
+- NEWS.md
+- README.md
+- doc/rexml/context.rdoc
+- doc/rexml/tasks/rdoc/child.rdoc
+- doc/rexml/tasks/rdoc/document.rdoc
+- doc/rexml/tasks/rdoc/element.rdoc
+- doc/rexml/tasks/rdoc/node.rdoc
+- doc/rexml/tasks/rdoc/parent.rdoc
+- doc/rexml/tasks/tocs/child_toc.rdoc
+- doc/rexml/tasks/tocs/document_toc.rdoc
+- doc/rexml/tasks/tocs/element_toc.rdoc
+- doc/rexml/tasks/tocs/master_toc.rdoc
+- doc/rexml/tasks/tocs/node_toc.rdoc
+- doc/rexml/tasks/tocs/parent_toc.rdoc
+- doc/rexml/tutorial.rdoc
 files:
-- ".gitignore"
-- ".travis.yml"
-- Gemfile
 - LICENSE.txt
 - NEWS.md
 - README.md
-- Rakefile
+- doc/rexml/context.rdoc
+- doc/rexml/tasks/rdoc/child.rdoc
+- doc/rexml/tasks/rdoc/document.rdoc
+- doc/rexml/tasks/rdoc/element.rdoc
+- doc/rexml/tasks/rdoc/node.rdoc
+- doc/rexml/tasks/rdoc/parent.rdoc
+- doc/rexml/tasks/tocs/child_toc.rdoc
+- doc/rexml/tasks/tocs/document_toc.rdoc
+- doc/rexml/tasks/tocs/element_toc.rdoc
+- doc/rexml/tasks/tocs/master_toc.rdoc
+- doc/rexml/tasks/tocs/node_toc.rdoc
+- doc/rexml/tasks/tocs/parent_toc.rdoc
+- doc/rexml/tutorial.rdoc
+- lib/rexml.rb
 - lib/rexml/attlistdecl.rb
 - lib/rexml/attribute.rb
 - lib/rexml/cdata.rb
@@ -101,29 +112,27 @@ files:
 - lib/rexml/xmltokens.rb
 - lib/rexml/xpath.rb
 - lib/rexml/xpath_parser.rb
-- rexml.gemspec
 homepage: https://github.com/ruby/rexml
 licenses:
 - BSD-2-Clause
 metadata: {}
-post_install_message: 
-rdoc_options: []
+rdoc_options:
+- "--main"
+- README.md
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 2.5.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.6.2
-signing_key: 
+rubygems_version: 3.6.0.dev
 specification_version: 4
 summary: An XML toolkit for Ruby
 test_files: []

data/.gitignore

@@ -1,9 +0,0 @@
-/.bundle/
-/.yardoc
-/_yardoc/
-/coverage/
-/doc/
-/pkg/
-/spec/reports/
-/tmp/
-Gemfile.lock

data/.travis.yml

@@ -1,24 +0,0 @@
-notifications:
-  webhooks:
-    - https://webhook.commit-email.info/
-matrix:
-  include:
-    - name: "2.3"
-      rvm: 2.3
-    - name: "2.4"
-      rvm: 2.4.5
-    - name: "2.5"
-      rvm: 2.5.2
-    - name: "2.6"
-      rvm: 2.6.0-rc2
-    - name: "trunk"
-      rvm: ruby-head
-    - name: "gem"
-      rvm: 2.6
-      install:
-        - rake install
-      script:
-        - mkdir -p tmp
-        - cd tmp
-        - cp -a ../test/ ./
-        - ../run-test.rb

data/Gemfile

@@ -1,6 +0,0 @@
-source "https://rubygems.org"
-
-git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
-
-# Specify your gem's dependencies in rexml.gemspec
-gemspec

data/Rakefile

@@ -1,8 +0,0 @@
-require "bundler/gem_tasks"
-
-desc "Run test"
-task :test do
-  ruby("run-test.rb")
-end
-
-task :default => :test