Parsing huge XML in Ruby

big.xml

<?xml version="1.0"?>
<catalog>
   <book id="bk101">
      <author>Gauthorambardella, Matthew</author>
      <title>XML Developer's Guide</title>
      <genre>Computer</genre>
      <price>44.95</price>
      <publish_date>2000-10-01</publish_date>
      <description>An in-depth look at creating applications 
      with XML.</description>
   </book>
   <!-- comment -->
   <book id="bk102">
      <author>Ralls, Kim</author>
      <title>Midnight Rain</title>
      <genre>Fantasy</genre>
      <price>5.95</price>
      <publish_date>2000-12-16</publish_date>
      <description>A former architect battles corporate zombies, 
      an evil sorceress, and her own childhood to become queen 
      of the world.</description>
   </book>
   <book id="bk103">
      <author>Corets, Eva</author>
      <title>Maeve Ascendant</title>
      <genre>Fantasy</genre>
      <price>5.95</price>
      <publish_date>2000-11-17</publish_date>
      <description>After the collapse of a nanotechnology 
      society in England, the young survivors lay the 
      foundation for a new society.</description>
   </book>
   <book id="bk104">
      <author>Corets, Eva</author>
      <title>Oberon's Legacy</title>
      <genre>Fantasy</genre>
      <price>5.95</price>
      <publish_date>2001-03-10</publish_date>
      <description>In post-apocalypse England, the mysterious 
      agent known only as Oberon helps to create a new life 
      for the inhabitants of London. Sequel to Maeve 
      Ascendant.</description>
   </book>
   <book id="bk105">
      <author>Corets, Eva</author>
      <title>The Sundered Grail</title>
      <genre>Fantasy</genre>
      <price>5.95</price>
      <publish_date>2001-09-10</publish_date>
      <description>The two daughters of Maeve, half-sisters, 
      battle one another for control of England. Sequel to 
      Oberon's Legacy.</description>
   </book>
   <book id="bk106">
      <author>Randall, Cynthia</author>
      <title>Lover Birds</title>
      <genre>Romance</genre>
      <price>4.95</price>
      <publish_date>2000-09-02</publish_date>
      <description>When Carla meets Paul at an ornithology 
      conference, tempers fly as feathers get ruffled.</description>
   </book>
   <book id="bk107">
      <author>Thurman, Paula</author>
      <title>Splish Splash</title>
      <genre>Romance</genre>
      <price>4.95</price>
      <publish_date>2000-11-02</publish_date>
      <description>A deep sea diver finds true love twenty 
      thousand leagues beneath the sea.</description>
   </book>
   <book id="bk108">
      <author>Knorr, Stefan</author>
      <title>Creepy Crawlies</title>
      <genre>Horror</genre>
      <price>4.95</price>
      <publish_date>2000-12-06</publish_date>
      <description>An anthology of horror stories about roaches,
      centipedes, scorpions  and other insects.</description>
   </book>
   <book id="bk109">
      <author>Kress, Peter</author>
      <title>Paradox Lost</title>
      <genre>Science Fiction</genre>
      <price>6.95</price>
      <publish_date>2000-11-02</publish_date>
      <description>After an inadvertant trip through a Heisenberg
      Uncertainty Device, James Salway discovers the problems 
      of being quantum.</description>
   </book>
   <book id="bk110">
      <author>O'Brien, Tim</author>
      <title>Microsoft .NET: The Programming Bible</title>
      <genre>Computer</genre>
      <price>36.95</price>
      <publish_date>2000-12-09</publish_date>
      <description>Microsoft's .NET initiative is explored in 
      detail in this deep programmer's reference.</description>
   </book>
   <book id="bk111">
      <author>O'Brien, Tim</author>
      <title>MSXML3: A Comprehensive Guide</title>
      <genre>Computer</genre>
      <price>36.95</price>
      <publish_date>2000-12-01</publish_date>
      <description>The Microsoft MSXML3 parser is covered in 
      detail, with attention to XML DOM interfaces, XSLT processing, 
      SAX and more.</description>
   </book>
   <book id="bk112">
      <author>Galos, Mike</author>
      <title>Visual Studio 7: A Comprehensive Guide</title>
      <genre>Computer</genre>
      <price>49.95</price>
      <publish_date>2001-04-16</publish_date>
      <description>Microsoft Visual Studio 7 is explored in depth,
      looking at how Visual Basic, Visual C++, C#, and ASP+ are 
      integrated into a comprehensive development 
      environment.</description>
   </book>
</catalog>

big_sax.rb

# frozen_string_literal: true

require 'ox'

module BigXML
  class SaxParse < ::Ox::Sax
    def initialize(block)
      @yield_to = block
    end

    def start_element(name)
      case name
      when :catalog
        @catalog = {}
      when :book
        @book = {}
      else
        @current_node = name
      end
    end

    def end_element(name)
      case name
      when :catalog
        yield_to.call(catalog)
        @catalog = nil
      when :book
        catalog.merge!("book_#{attr_id}": book)
        @book = nil
      end
    end

    def attr(name, value)
      @attr_id = value
    end

    def text(value)
      book.merge!("#{current_node}": value)
    end

    def comment(value); end

    private

    attr_reader :yield_to, :catalog, :book, :attr_id, :current_node
  end
end

big_xml.rb

# frozen_string_literal: true

require 'nokogiri'

module BigXML
  class Parser
    def initialize(xml_file)
      raise(ArgumentError, "Please provide the path of the XML file, not a #{xml_file.class}") unless xml_file.is_a?(String)
      @xml_file = xml_file
    end

    def each_node
      raise(SyntaxError, "Please provide a XML valid") unless valid?

      file_open = File.open(xml_file)
      reader = Nokogiri::XML::Reader(file_open)
      reader.each do |node|
        yield(node) if node.node_type == TYPE_ELEMENT
      end
      file_open.close
    end

    private

    attr_reader :xml_file

    TYPE_ELEMENT = Nokogiri::XML::Reader::TYPE_ELEMENT

    def valid?
      file_open = File.open(xml_file)
      Nokogiri::XML::Reader(file_open).each { }
      file_open.close
      true
    rescue
      return false
    end
  end
end

read_big_xml.rb

# frozen_string_literal: true

# Quickstart:
# > ruby read_big_xml.rb big.xml

require_relative 'big_xml.rb'
require_relative 'big_sax.rb'

require 'ox'
require 'pry'
require 'pry-nav'
require 'json'

def execute_with_nokogiri
  xml = BigXML::Parser.new(ARGV[0])
  xml.each_node do |node|
    name = node.name

    case name
    when 'catalog'
      puts "#{name.capitalize}:"
    when 'book'
      puts "  #{name.capitalize}:"
    else
      puts "    #{name.capitalize}: #{node.inner_xml}"
    end
  end
end

def execute_with_ox
  file = File.open(ARGV[0])
  pro = proc { |catalog| puts "Catalog: #{Pry::ColorPrinter.pp(catalog.to_h)}" }
  # pro = proc { |catalog| puts "Catalog: #{JSON.pretty_generate(catalog.to_h)}" }
  handler = BigXML::SaxParse.new(pro)
  
  Ox.sax_parse(handler, file)
  file.close
end

puts '- With Nokogiri'
execute_with_nokogiri

puts "\n- With OX"
execute_with_ox