moxml 0.1.4 → 0.1.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 65fadaecfecbc8142d11c82c79c20ea9811e3b58e21b94f335ba822bdfbfc852
-  data.tar.gz: e0189194a594ff763ffec269d15e56dadf91b22369d2efb399e29e3c993f1ace
+  metadata.gz: 90a6a09c55ff15198efd4687fa31e58bc4b17fa6a72b46c0e9cb88d5474f8899
+  data.tar.gz: 27b376ff3bfa49b2bcb7c768451af8e39f491a7e2467c6965e85cee3cedc43f9
 SHA512:
-  metadata.gz: 6c20b0290ed6a6f9ea904564b7619c05f1aec9b9ebe9274a6ea042b9756caeb8792a4d6f45224af8019e2760b8d752ff20a9ef9c4f8f4acb893be069b7f95a92
-  data.tar.gz: 05d046559db87598410f122e51fa7a2276d975f40eabe19f32c65de6c2459238976551496937e33a2a319e3a7ff110bdc782af8ce9942bfcc24840f292d79150
+  metadata.gz: 3895bfc0612eddea337e083e6cdd66dbfda811d7d819c858d05a7e30b433c226ddaa8e7995690c65f142b329ac9454c8712c1cb9f6d95372c8cbbc0b0c8e7846
+  data.tar.gz: 52bf943812996dcd501d65dfe2d6f9b06578429de92fe2ad74f87080c1c57cc04a8574c3e85ad72f156918d5ada2415c8e4a4c5e97ff2f10d68b5056d821c599

data/.gitignore

@@ -1,4 +1,3 @@
-/.bundle/
 /.yardoc
 /_yardoc/
 /coverage/

data/.rubocop_todo.yml

@@ -38,7 +38,7 @@ Metrics/BlockLength:
 # Offense count: 5
 # Configuration parameters: CountComments, CountAsOne.
 Metrics/ClassLength:
-  Max: 335
+  Max: 373
 
 # Offense count: 7
 # Configuration parameters: AllowedMethods, AllowedPatterns.
@@ -53,7 +53,7 @@ Metrics/MethodLength:
 # Offense count: 3
 # Configuration parameters: AllowedMethods, AllowedPatterns.
 Metrics/PerceivedComplexity:
-  Max: 15
+  Max: 16
 
 # Offense count: 5
 # Configuration parameters: MinNameLength, AllowNamesEndingInNumbers, AllowedNames, ForbiddenNames.

data/Gemfile

@@ -15,6 +15,8 @@ gem "rexml"
 gem "rspec", "~> 3.0"
 gem "rubocop", "~> 1.21"
 gem "tempfile", "~> 0.3"
+#  Provides iteration per second benchmarking for Ruby
+gem "benchmark-ips"
 
 # Needed by get_process_mem on Windows
 gem "sys-proctable" if Gem.win_platform?

data/README.adoc

@@ -28,10 +28,10 @@ Key features:
 
 Moxml supports the following XML libraries:
 
-REXML:: (default) https://github.com/ruby/rexml[REXML], a pure Ruby XML parser
+REXML:: https://github.com/ruby/rexml[REXML], a pure Ruby XML parser
 distributed with standard Ruby. Not the fastest, but always available.
 
-Nokogiri:: (recommended) https://github.com/sparklemotion/nokogiri[Nokogiri], a
+Nokogiri:: (default) https://github.com/sparklemotion/nokogiri[Nokogiri], a
 widely used implementation which wraps around the performant
 https://github.com/GNOME/libxml2[libxml2] C library.
 
@@ -39,8 +39,53 @@ Oga:: https://github.com/yorickpeterse/oga[Oga], a pure Ruby XML parser.
 Recommended when you need a pure Ruby solution say for
 https://github.com/opal/opal[Opal].
 
-Ox:: https://github.com/ohler55/ox[Ox], a fast XML parser (to be supported)
+Ox:: https://github.com/ohler55/ox[Ox], a fast XML parser.
 
+=== Feature table
+
+Moxml exercises its best effort to provide a consistent interface across basic
+XML features, various XML libraries have different features and capabilities.
+
+The following table summarizes the features supported by each library.
+
+NOTE: The checkmarks indicate support for the feature, while the footnotes
+provide additional context for specific features.
+
+[cols="1,1,1,1,3"]
+|===
+|Feature |Nokogiri |Oga |REXML |Ox
+
+|Parsing, serializing
+| ✅
+| ✅
+| ✅
+| ✅
+
+|Node manipulation
+| ✅
+| ✅
+| ✅
+| ✅ See NOTE 1.
+
+|Basic XPath
+| ✅
+| ✅
+| ✅
+a|
+Uses `locate`. See NOTE 2.
+
+|XPath with namespaces
+| ✅
+| ✅
+| ❌
+a|
+Uses `locate`. See NOTE 2.
+
+|===
+
+NOTE 1: Ox's node manipulation may have issues, especially when manipulating Text nodes.
+
+NOTE 2: The native Ox method `locate` is similar to XPath but has a different syntax.
 
 == Getting started
 
@@ -52,7 +97,7 @@ Install the gem and at least one supported XML library:
 ----
 # In your Gemfile
 gem 'moxml'
-gem 'nokogiri'  # Or 'oga', 'rexml', or 'ox' when it is integrated
+gem 'nokogiri'  # Or 'oga', 'rexml', or 'ox'
 ----
 
 === Basic document creation
@@ -248,7 +293,7 @@ text.text?              # Returns true
 
 # Structure
 text.parent             # Get parent node
-text.remove            # Remove from document
+text.remove             # Remove from document
 text.replace(node)      # Replace with another node
 ----
 
@@ -270,7 +315,7 @@ cdata.cdata?           # Returns true
 
 # Structure
 cdata.parent           # Get parent node
-cdata.remove          # Remove from document
+cdata.remove           # Remove from document
 cdata.replace(node)    # Replace with another node
 ----
 
@@ -309,7 +354,7 @@ pi = doc.create_processing_instruction("xml-stylesheet",
 # PI properties
 pi.target              # Get PI target
 pi.target = "new"      # Set PI target
-pi.content            # Get PI content
+pi.content             # Get PI content
 pi.content = "new"     # Set PI content
 
 # Node type checking
@@ -317,7 +362,7 @@ pi.processing_instruction? # Returns true
 
 # Structure
 pi.parent             # Get parent node
-pi.remove            # Remove from document
+pi.remove             # Remove from document
 pi.replace(node)      # Replace with another node
 ----
 
@@ -364,15 +409,13 @@ Each node type provides methods for traversing the document structure:
 
 [source,ruby]
 ----
-node.parent               # Get parent node
+node.parent              # Get parent node
 node.children            # Get child nodes
 node.next_sibling        # Get next sibling
 node.previous_sibling    # Get previous sibling
-node.ancestors           # Get all ancestor nodes
-node.descendants         # Get all descendant nodes
 
 # Type checking
-node.element?           # Is it an element?
+node.element?          # Is it an element?
 node.text?             # Is it a text node?
 node.cdata?            # Is it a CDATA section?
 node.comment?          # Is it a comment?
@@ -382,14 +425,14 @@ node.namespace?        # Is it a namespace?
 
 # Node information
 node.document          # Get owning document
-node.path              # Get XPath to node
-node.line_number       # Get source line number (if available)
 ----
 
 == Advanced features
 
 === XPath querying and node mapping
 
+==== Nokogiri, Oga, REXML
+
 Moxml provides efficient XPath querying by leveraging the native XML library's
 implementation while maintaining consistent node mapping:
 
@@ -414,6 +457,12 @@ doc.xpath('//book').each do |book|
 end
 ----
 
+==== Ox
+
+The native Ox's query method
+https://www.ohler.com/ox/Ox/Element.html#method-i-locate[`locate`] resembles
+XPath but has a different syntax.
+
 === Namespace handling
 
 [source,ruby]
@@ -508,13 +557,13 @@ Moxml::Config.default_adapter = <adapter-symbol>
 
 Where, `<adapter-symbol>` is one of the following:
 
-`:rexml`:: REXML (default)
+`:rexml`:: REXML
 
-`:nokogiri`:: Nokogiri
+`:nokogiri`:: Nokogiri (default)
 
 `:oga`:: Oga
 
-`:ox`:: Ox (not yet supported)
+`:ox`:: Ox
 
 
 == Thread safety
@@ -567,7 +616,7 @@ doc.xpath('//book/title')
 doc.xpath('//title')
 
 # Most efficient - direct child access
-root.xpath('./title')
+root.xpath('./*/title')
 ----
 
 == Best practices
@@ -577,7 +626,7 @@ root.xpath('./title')
 [source,ruby]
 ----
 # Preferred - using builder pattern
-doc = Moxml.new.build do
+doc = Moxml::Builder.new(Moxml.new).build do
   declaration version: "1.0", encoding: "UTF-8"
   element 'root' do
     element 'child' do
@@ -588,7 +637,7 @@ end
 
 # Alternative - direct manipulation
 doc = Moxml.new.create_document
-doc.add_declaration(version: "1.0", encoding: "UTF-8")
+doc.add_child(doc.create_declaration("1.0", "UTF-8"))
 root = doc.create_element('root')
 doc.add_child(root)
 ----
@@ -604,6 +653,7 @@ element
 
 # Preferred - clear node type checking
 if node.element?
+  node.add_namespace('dc', 'http://purl.org/dc/elements/1.1/')
   node.add_child(doc.create_text('content'))
 end
 ----
@@ -618,7 +668,7 @@ end
 
 == License
 
-Copyright (c) Ribose Inc.
+Copyright Ribose.
 
 This project is licensed under the BSD-2-Clause License. See the
 link:LICENSE.md[] file for details.

data/lib/moxml/adapter/base.rb

@@ -19,7 +19,7 @@ module Moxml
           raise NotImplementedError
         end
 
-        def create_document
+        def create_document(native_doc = nil)
           raise NotImplementedError
         end
 
@@ -29,7 +29,8 @@ module Moxml
         end
 
         def create_text(content)
-          create_native_text(normalize_xml_value(content))
+          # Ox freezes the content, so we need to dup it
+          create_native_text(normalize_xml_value(content).dup)
         end
 
         def create_cdata(content)
@@ -75,6 +76,11 @@ module Moxml
           node.dup
         end
 
+        def patch_node(node, _parent = nil)
+          # monkey-patch the native node if necessary
+          node
+        end
+
         protected
 
         def create_native_element(name)

data/lib/moxml/adapter/customized_ox/attribute.rb

@@ -0,0 +1,29 @@
+# frozen_string_literal: true
+
+require_relative "../../../ox/node"
+
+module Moxml
+  module Adapter
+    module CustomizedOx
+      class Attribute < ::Ox::Node
+        attr_reader :name, :prefix
+
+        def initialize(attr_name, value, parent = nil)
+          self.name = attr_name
+          @parent = parent
+          super(value)
+        end
+
+        def name=(new_name)
+          @prefix, new_name = new_name.to_s.split(":", 2) if new_name.to_s.include?(":")
+
+          @name = new_name
+        end
+
+        def expanded_name
+          [prefix, name].compact.join(":")
+        end
+      end
+    end
+  end
+end

data/lib/moxml/adapter/customized_ox/namespace.rb

@@ -0,0 +1,34 @@
+# frozen_string_literal: true
+
+require_relative "../../../ox/node"
+
+module Moxml
+  module Adapter
+    module CustomizedOx
+      class Namespace
+        attr_accessor :uri, :parent
+        attr_writer :prefix
+
+        def initialize(prefix, uri, parent = nil)
+          @prefix = prefix
+          @uri = uri
+          @parent = parent
+        end
+
+        def prefix
+          return if @prefix == "xmlns" || @prefix.nil?
+
+          @prefix.to_s.delete_prefix("xmlns:")
+        end
+
+        def expanded_prefix
+          ["xmlns", prefix].compact.join(":")
+        end
+
+        def default?
+          prefix.nil?
+        end
+      end
+    end
+  end
+end

data/lib/moxml/adapter/customized_ox/text.rb

@@ -0,0 +1,12 @@
+# frozen_string_literal: true
+
+require_relative "../../../ox/node"
+
+module Moxml
+  module Adapter
+    module CustomizedOx
+      # Ox uses Strings, but a string cannot have a parent reference
+      class Text < ::Ox::Node; end
+    end
+  end
+end

data/lib/moxml/adapter/customized_rexml/formatter.rb

@@ -101,9 +101,9 @@ module Moxml
 
         def write_cdata(node, output)
           # output << ' ' * @level
-          output << "<![CDATA["
-          output << node.to_s.gsub("]]>", "]]]]><![CDATA[>")
-          output << "]]>"
+          output << ::REXML::CData::START
+          output << node.to_s.gsub(::REXML::CData::STOP, "]]]]><![CDATA[>")
+          output << ::REXML::CData::STOP
           # output << "\n"
         end
 

data/lib/moxml/adapter/nokogiri.rb

@@ -31,7 +31,7 @@ module Moxml
           DocumentBuilder.new(Context.new(:nokogiri)).build(native_doc)
         end
 
-        def create_document
+        def create_document(_native_doc = nil)
           ::Nokogiri::XML::Document.new
         end
 
@@ -120,6 +120,8 @@ module Moxml
           when ::Nokogiri::XML::CDATA then :cdata
           when ::Nokogiri::XML::Text then :text
           when ::Nokogiri::XML::Comment then :comment
+          when ::Nokogiri::XML::Attr then :attribute
+          when ::Nokogiri::XML::Namespace then :namespace
           when ::Nokogiri::XML::ProcessingInstruction then :processing_instruction
           when ::Nokogiri::XML::Document, ::Nokogiri::XML::DocumentFragment then :document
           when ::Nokogiri::XML::DTD then :doctype

data/lib/moxml/adapter/oga.rb

@@ -24,7 +24,7 @@ module Moxml
           DocumentBuilder.new(Context.new(:oga)).build(native_doc)
         end
 
-        def create_document
+        def create_document(_native_doc = nil)
           ::Oga::XML::Document.new
         end
 
@@ -111,6 +111,8 @@ module Moxml
           when ::Oga::XML::Text then :text
           when ::Oga::XML::Cdata then :cdata
           when ::Oga::XML::Comment then :comment
+          when ::Oga::XML::Attribute then :attribute
+          when ::Oga::XML::Namespace then :namespace
           when ::Oga::XML::ProcessingInstruction then :processing_instruction
           when ::Oga::XML::Document then :document
           when ::Oga::XML::Doctype then :doctype
@@ -261,7 +263,7 @@ module Moxml
         end
 
         def set_text_content(node, content)
-          if node.respond_to?(:inner_text)
+          if node.respond_to?(:inner_text=)
             node.inner_text = content
           else
             # Oga::XML::Text node for example