rexml 3.4.1 → 3.4.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a9dc6a26dcc5ba93c112d65fa910e49ca970108c726cdce28324d7771a0831a3
-  data.tar.gz: b03ad34d3180aeeaa1ecc7ab21bf5ffe5f2845107a2c35ca3198653f80b932fa
+  metadata.gz: 75f7d0bba9d8346e2374abacaf7aea57044c66f368a695521bc16f6b07e31eaf
+  data.tar.gz: 674cf531dbe9684f3cc9945255aec412d0b80ae0117da3c57552c5ae3bbc66a1
 SHA512:
-  metadata.gz: c0d493943fab795f3c8fc8490a40750382e3c4cf38c73532b1f850612384795c2bb916afc70ebff0bd26e9e2f304ea6a22299a0481523bd0322d5655df05edbd
-  data.tar.gz: bfb02a2bfadb24cbdeed951e06e113e17b123015271cabfffacc3ecc4bbb1bd7c7f56e358d42173feb8b333309f725d57b76f155fea814d70c6decae3b791165
+  metadata.gz: c36c00f2e2c0ed931c85a0e0fb7720771d314f93fa1e66e1057b4e8fb7fe1d1bd3f50debdfa05587e511f1cad8d7345aa8066b18392554da6e8f6baad6a3b9d7
+  data.tar.gz: dc53db592782ad36f083493b8864d49872b8c989b9e2f5d9a1811d56fae3100cf2cad27bb4ab81b9d308715da523d0a4f71d4e236e5847d540d0e92a85c1bd20

data/NEWS.md

@@ -1,5 +1,107 @@
 # News
 
+## 3.4.2 - 2025-08-26 {#version-3-4-2}
+
+### Improvement
+
+  * Improved performance.
+    * GH-244
+    * GH-245
+    * GH-246
+    * GH-249
+    * GH-256
+    * Patch by NAITOH Jun
+
+  * Raise appropriate exception when failing to match start tag in DOCTYPE
+    * GH-247
+    * Patch by NAITOH Jun
+
+  * Deprecate accepting array as an element in XPath.match, first and each
+    * GH-252
+    * Patch by tomoya ishida
+
+  * Don't call needless encoding_updated
+    * GH-259
+    * Patch by Sutou Kouhei
+
+  * Reuse XPath::match
+    * GH-263
+    * Patch by pboling
+
+  * Cache redundant calls for doctype
+    * GH-264
+    * Patch by pboling
+
+  * Use Safe Navigation (&.) from Ruby 2.3
+    * GH-265
+    * Patch by pboling
+
+  * Remove redundant return statements
+    * GH-266
+    * Patch by pboling
+
+  * Added XML declaration check & Source#skip_spaces method
+    * GH-282
+    * Patch by NAITOH Jun
+    * Reported by Sofi Aberegg
+
+### Fixes
+
+  * Fix docs typo
+    * GH-248
+    * Patch by James Coleman
+
+  * Fix reverse sort in xpath_parser
+    * GH-251
+    * Patch by tomoya ishida
+
+  * Fix duplicate responses in XPath following, following-sibling, preceding, preceding-sibling
+    * GH-255
+    * Patch by NAITOH Jun
+
+  * Fix wrong Encoding resolution
+    * GH-258
+    * Patch by Sutou Kouhei
+
+  * Handle nil when parsing fragment
+    * GH-267
+    * GH-268
+    * Patch by pboling
+
+  * [Documentation] Use # to reference instance methods
+    * GH-269
+    * GH-270
+    * Patch by pboling
+
+  * Fix & Deprecate REXML::Text#text_indent
+    * GH-273
+    * GH-275
+    * Patch by pboling
+
+  * remove bundler from dev deps
+    * GH-276
+    * GH-277
+    * Patch by pboling
+
+  * remove ostruct from dev deps
+    * GH-280
+    * GH-281
+    * Patch by pboling
+
+### Thanks
+
+  * NAITOH Jun
+
+  * tomoya ishida
+
+  * James Coleman
+
+  * pboling
+
+  * Sutou Kouhei
+
+  * Sofi Aberegg
+
 ## 3.4.1 - 2025-02-16 {#version-3-4-1}
 
 ### Improvement
@@ -386,7 +488,7 @@
 
     * Patch by NAITOH Jun.
 
-  * Improved parse performance when an attribute has many `<`s.
+  * Improved parse performance when an attribute has many `>`s.
 
     * GH-126
 

data/lib/rexml/attribute.rb

@@ -130,10 +130,7 @@ module REXML
     end
 
     def doctype
-      if @element
-        doc = @element.document
-        doc.doctype if doc
-      end
+      @element&.document&.doctype
     end
 
     # Returns the attribute value, with entities replaced
@@ -173,7 +170,7 @@ module REXML
       @element = element
 
       if @normalized
-        Text.check( @normalized, NEEDS_A_SECOND_CHECK, doctype )
+        Text.check( @normalized, NEEDS_A_SECOND_CHECK )
       end
 
       self
@@ -202,9 +199,11 @@ module REXML
     end
 
     def xpath
-      path = @element.xpath
-      path += "/@#{self.expanded_name}"
-      return path
+      @element.xpath + "/@#{self.expanded_name}"
+    end
+
+    def document
+      @element&.document
     end
   end
 end

data/lib/rexml/cdata.rb

@@ -58,7 +58,7 @@ module REXML
     #  c = CData.new( " Some text " )
     #  c.write( $stdout )     #->  <![CDATA[ Some text ]]>
     def write( output=$stdout, indent=-1, transitive=false, ie_hack=false )
-      Kernel.warn( "#{self.class.name}.write is deprecated", uplevel: 1)
+      Kernel.warn( "#{self.class.name}#write is deprecated", uplevel: 1)
       indent( output, indent )
       output << START
       output << @string

data/lib/rexml/child.rb

@@ -83,13 +83,12 @@ module REXML
     # Returns:: the document this child belongs to, or nil if this child
     # belongs to no document
     def document
-      return parent.document unless parent.nil?
-      nil
+      parent&.document
     end
 
     # This doesn't yet handle encodings
     def bytes
-      document.encoding
+      document&.encoding
 
       to_s
     end

data/lib/rexml/comment.rb

@@ -48,7 +48,7 @@ module REXML
     # ie_hack::
     #    Needed for conformity to the child API, but not used by this class.
     def write( output, indent=-1, transitive=false, ie_hack=false )
-      Kernel.warn("Comment.write is deprecated.  See REXML::Formatters", uplevel: 1)
+      Kernel.warn("#{self.class.name}#write is deprecated.  See REXML::Formatters", uplevel: 1)
       indent( output, indent )
       output << START
       output << @string

data/lib/rexml/doctype.rb

@@ -171,15 +171,11 @@ module REXML
     end
 
     def context
-      if @parent
-        @parent.context
-      else
-        nil
-      end
+      @parent&.context
     end
 
     def entity( name )
-      @entities[name].unnormalized if @entities[name]
+      @entities[name]&.unnormalized
     end
 
     def add child
@@ -288,8 +284,7 @@ module REXML
     end
 
     def to_s
-      context = nil
-      context = parent.context if parent
+      context = parent&.context
       notation = "<!NOTATION #{@name}"
       reference_writer = ReferenceWriter.new(@middle, @public, @system, context)
       reference_writer.write(notation)

data/lib/rexml/document.rb

@@ -309,8 +309,8 @@ module REXML
     end
 
     # :call-seq:
-    #    doc.write(output=$stdout, indent=-1, transtive=false, ie_hack=false, encoding=nil)
-    #    doc.write(options={:output => $stdout, :indent => -1, :transtive => false, :ie_hack => false, :encoding => nil})
+    #    doc.write(output=$stdout, indent=-1, transitive=false, ie_hack=false, encoding=nil)
+    #    doc.write(options={:output => $stdout, :indent => -1, :transitive => false, :ie_hack => false, :encoding => nil})
     #
     # Write the XML tree out, optionally with indent.  This writes out the
     # entire XML document, including XML declarations, doctype declarations,
@@ -415,7 +415,7 @@ module REXML
     #
     # Deprecated. Use REXML::Security.entity_expansion_limit= instead.
     def Document::entity_expansion_limit
-      return Security.entity_expansion_limit
+      Security.entity_expansion_limit
     end
 
     # Set the entity expansion limit. By default the limit is set to 10240.
@@ -429,7 +429,7 @@ module REXML
     #
     # Deprecated. Use REXML::Security.entity_expansion_text_limit instead.
     def Document::entity_expansion_text_limit
-      return Security.entity_expansion_text_limit
+      Security.entity_expansion_text_limit
     end
 
     attr_reader :entity_expansion_count
@@ -448,6 +448,20 @@ module REXML
     end
 
     private
+
+    attr_accessor :namespaces_cache
+
+    # New document level cache is created and available in this block.
+    # This API is thread unsafe. Users can't change this document in this block.
+    def enable_cache
+      @namespaces_cache = {}
+      begin
+        yield
+      ensure
+        @namespaces_cache = nil
+      end
+    end
+
     def build( source )
       Parsers::TreeParser.new( source, self ).parse
     end

data/lib/rexml/element.rb

@@ -473,8 +473,7 @@ module REXML
     # Related: #root, #root_node.
     #
     def document
-      rt = root
-      rt.parent if rt
+      root&.parent
     end
 
     # :call-seq:
@@ -566,7 +565,7 @@ module REXML
       prefixes = []
       prefixes = parent.prefixes if parent
       prefixes |= attributes.prefixes
-      return prefixes
+      prefixes
     end
 
     # :call-seq:
@@ -589,10 +588,12 @@ module REXML
     #   d.elements['//c'].namespaces # => {"x"=>"1", "y"=>"2", "z"=>"3"}
     #
     def namespaces
-      namespaces = {}
-      namespaces = parent.namespaces if parent
-      namespaces = namespaces.merge( attributes.namespaces )
-      return namespaces
+      namespaces_cache = document&.__send__(:namespaces_cache)
+      if namespaces_cache
+        namespaces_cache[self] ||= calculate_namespaces
+      else
+        calculate_namespaces
+      end
     end
 
     # :call-seq:
@@ -619,19 +620,11 @@ module REXML
       if prefix.nil?
         prefix = prefix()
       end
-      if prefix == ''
-        prefix = "xmlns"
-      else
-        prefix = "xmlns:#{prefix}" unless prefix[0,5] == 'xmlns'
-      end
-      ns = nil
-      target = self
-      while ns.nil? and target
-        ns = target.attributes[prefix]
-        target = target.parent
-      end
+      prefix = (prefix == '') ? 'xmlns' : prefix.delete_prefix("xmlns:")
+      ns = namespaces[prefix]
+
       ns = '' if ns.nil? and prefix == 'xmlns'
-      return ns
+      ns
     end
 
     # :call-seq:
@@ -963,7 +956,7 @@ module REXML
     def next_element
       element = next_sibling
       element = element.next_sibling until element.nil? or element.kind_of? Element
-      return element
+      element
     end
 
     # :call-seq:
@@ -979,7 +972,7 @@ module REXML
     def previous_element
       element = previous_sibling
       element = element.previous_sibling until element.nil? or element.kind_of? Element
-      return element
+      element
     end
 
 
@@ -1029,8 +1022,7 @@ module REXML
     #
     def text( path = nil )
       rv = get_text(path)
-      return rv.value unless rv.nil?
-      nil
+      rv&.value
     end
 
     # :call-seq:
@@ -1058,7 +1050,7 @@ module REXML
       else
         rv = @children.find { |node| node.kind_of? Text }
       end
-      return rv
+      rv
     end
 
     # :call-seq:
@@ -1102,7 +1094,7 @@ module REXML
           old_text.replace_with( text )
         end
       end
-      return self
+      self
     end
 
     # :call-seq:
@@ -1153,7 +1145,7 @@ module REXML
         text = Text.new( text, whitespace(), nil, raw() )
       end
       self << text unless text.nil?
-      return self
+      self
     end
 
     # :call-seq:
@@ -1197,7 +1189,7 @@ module REXML
         cur = cur.parent
         path_elements << __to_xpath_helper( cur )
       end
-      return path_elements.reverse.join( "/" )
+      path_elements.reverse.join( "/" )
     end
 
     #################################################
@@ -1299,7 +1291,6 @@ module REXML
       return nil unless ( namespaces[ prefix ] == namespaces[ 'xmlns' ] )
 
       attributes.get_attribute( name )
-
     end
 
     # :call-seq:
@@ -1313,7 +1304,7 @@ module REXML
     #   b.has_attributes? # => false
     #
     def has_attributes?
-      return !@attributes.empty?
+      !@attributes.empty?
     end
 
     # :call-seq:
@@ -1502,7 +1493,7 @@ module REXML
     #  doc.write( out )     #-> doc is written to the string 'out'
     #  doc.write( $stdout ) #-> doc written to the console
     def write(output=$stdout, indent=-1, transitive=false, ie_hack=false)
-      Kernel.warn("#{self.class.name}.write is deprecated.  See REXML::Formatters", uplevel: 1)
+      Kernel.warn("#{self.class.name}#write is deprecated.  See REXML::Formatters", uplevel: 1)
       formatter = if indent > -1
           if transitive
             require_relative "formatters/transitive"
@@ -1516,8 +1507,15 @@ module REXML
       formatter.write( self, output )
     end
 
-
     private
+    def calculate_namespaces
+      if parent
+        parent.namespaces.merge(attributes.namespaces)
+      else
+        attributes.namespaces
+      end
+    end
+
     def __to_xpath_helper node
       rv = node.expanded_name.clone
       if node.parent
@@ -1684,11 +1682,7 @@ module REXML
           (num += 1) == index
         }
       else
-        return XPath::first( @element, index )
-        #{ |element|
-        #       return element if element.kind_of? Element
-        #}
-        #return nil
+        XPath::first( @element, index )
       end
     end
 
@@ -1735,7 +1729,7 @@ module REXML
       else
         previous.replace_with element
       end
-      return previous
+      previous
     end
 
     # :call-seq:
@@ -1774,7 +1768,7 @@ module REXML
         child == element
       end
       return rv if found == element
-      return -1
+      -1
     end
 
     # :call-seq:
@@ -1853,7 +1847,7 @@ module REXML
         @element.delete element
         element.remove
       end
-      return rv
+      rv
     end
 
     # :call-seq:
@@ -2180,8 +2174,7 @@ module REXML
     #
     def [](name)
       attr = get_attribute(name)
-      return attr.value unless attr.nil?
-      return nil
+      attr&.value
     end
 
     # :call-seq:
@@ -2324,11 +2317,11 @@ module REXML
             return attr
           end
         end
-        element_document = @element.document
-        if element_document and element_document.doctype
+        doctype = @element.document&.doctype
+        if doctype
           expn = @element.expanded_name
-          expn = element_document.doctype.name if expn.size == 0
-          attr_val = element_document.doctype.attribute_of(expn, name)
+          expn = doctype.name if expn.size == 0
+          attr_val = doctype.attribute_of(expn, name)
           return Attribute.new( name, attr_val ) if attr_val
         end
         return nil
@@ -2336,7 +2329,7 @@ module REXML
       if attr.kind_of? Hash
         attr = attr[ @element.prefix ]
       end
-      return attr
+      attr
     end
 
     # :call-seq:
@@ -2370,8 +2363,9 @@ module REXML
       end
 
       unless value.kind_of? Attribute
-        if @element.document and @element.document.doctype
-          value = Text::normalize( value, @element.document.doctype )
+        doctype = @element.document&.doctype
+        if doctype
+          value = Text::normalize( value, doctype )
         else
           value = Text::normalize( value, nil )
         end
@@ -2389,7 +2383,7 @@ module REXML
       else
         store value.name, value
       end
-      return @element
+      @element
     end
 
     # :call-seq:
@@ -2408,10 +2402,11 @@ module REXML
       each_attribute do |attribute|
         ns << attribute.name if attribute.prefix == 'xmlns'
       end
-      if @element.document and @element.document.doctype
+      doctype = @element.document&.doctype
+      if doctype
         expn = @element.expanded_name
-        expn = @element.document.doctype.name if expn.size == 0
-        @element.document.doctype.attributes_of(expn).each {
+        expn = doctype.name if expn.size == 0
+        doctype.attributes_of(expn).each {
           |attribute|
           ns << attribute.name if attribute.prefix == 'xmlns'
         }
@@ -2433,10 +2428,11 @@ module REXML
       each_attribute do |attribute|
         namespaces[attribute.name] = attribute.value if attribute.prefix == 'xmlns' or attribute.name == 'xmlns'
       end
-      if @element.document and @element.document.doctype
+      doctype = @element.document&.doctype
+      if doctype
         expn = @element.expanded_name
-        expn = @element.document.doctype.name if expn.size == 0
-        @element.document.doctype.attributes_of(expn).each {
+        expn = doctype.name if expn.size == 0
+        doctype.attributes_of(expn).each {
           |attribute|
           namespaces[attribute.name] = attribute.value if attribute.prefix == 'xmlns' or attribute.name == 'xmlns'
         }
@@ -2491,9 +2487,7 @@ module REXML
           old.each_value{|v| repl = v}
           store name, repl
         end
-      elsif old.nil?
-        return @element
-      else # the supplied attribute is a top-level one
+      elsif old # the supplied attribute is a top-level one
         super(name)
       end
       @element
@@ -2547,7 +2541,7 @@ module REXML
         rv << attribute if attribute.expanded_name == name
       }
       rv.each{ |attr| attr.remove }
-      return rv
+      rv
     end
 
     # :call-seq:

data/lib/rexml/encoding.rb

@@ -5,7 +5,7 @@ module REXML
     # ID ---> Encoding name
     attr_reader :encoding
     def encoding=(encoding)
-      encoding = encoding.name if encoding.is_a?(Encoding)
+      encoding = encoding.name if encoding.is_a?(::Encoding)
       if encoding.is_a?(String)
         original_encoding = encoding
         encoding = find_encoding(encoding)
@@ -13,12 +13,9 @@ module REXML
           raise ArgumentError, "Bad encoding name #{original_encoding}"
         end
       end
+      encoding = encoding.upcase if encoding
       return false if defined?(@encoding) and encoding == @encoding
-      if encoding
-        @encoding = encoding.upcase
-      else
-        @encoding = 'UTF-8'
-      end
+      @encoding = encoding || "UTF-8"
       true
     end
 

data/lib/rexml/functions.rb

@@ -39,11 +39,11 @@ module REXML
 
     def Functions::text( )
       if @@context[:node].node_type == :element
-        return @@context[:node].find_all{|n| n.node_type == :text}.collect{|n| n.value}
+        @@context[:node].find_all{|n| n.node_type == :text}.collect{|n| n.value}
       elsif @@context[:node].node_type == :text
-        return @@context[:node].value
+        @@context[:node].value
       else
-        return false
+        false
       end
     end
 

data/lib/rexml/instruction.rb

@@ -49,7 +49,7 @@ module REXML
     # See the rexml/formatters package
     #
     def write writer, indent=-1, transitive=false, ie_hack=false
-      Kernel.warn( "#{self.class.name}.write is deprecated", uplevel: 1)
+      Kernel.warn( "#{self.class.name}#write is deprecated", uplevel: 1)
       indent(writer, indent)
       writer << START
       writer << @target

data/lib/rexml/namespace.rb

@@ -42,11 +42,11 @@ module REXML
     # Compares names optionally WITH namespaces
     def has_name?( other, ns=nil )
       if ns
-        return (namespace() == ns and name() == other)
+        namespace() == ns and name() == other
       elsif other.include? ":"
-        return fully_expanded_name == other
+        fully_expanded_name == other
       else
-        return name == other
+        name == other
       end
     end
 
@@ -57,7 +57,7 @@ module REXML
     def fully_expanded_name
       ns = prefix
       return "#{ns}:#@name" if ns.size > 0
-      return @name
+      @name
     end
   end
 end

data/lib/rexml/node.rb

@@ -26,7 +26,7 @@ module REXML
     #   REXML::Formatters package for changing the output style.
     def to_s indent=nil
       unless indent.nil?
-        Kernel.warn( "#{self.class.name}.to_s(indent) parameter is deprecated", uplevel: 1)
+        Kernel.warn( "#{self.class.name}#to_s(indent) parameter is deprecated", uplevel: 1)
         f = REXML::Formatters::Pretty.new( indent )
         f.write( self, rv = "" )
       else
@@ -68,7 +68,7 @@ module REXML
       each_recursive {|node|
         return node if block.call(node)
       }
-      return nil
+      nil
     end
 
     # Returns the position that +self+ holds in its parent's array, indexed