gistfile1.rb

require 'rubygems'
require 'nokogiri'

puts "nokogiri: #{Nokogiri::VERSION}"
puts "libxml: #{Nokogiri::LIBXML_VERSION}"

count = 0

File.open(ARGV[0], "r") do |input|
  reader = Nokogiri::XML::Reader(input) { |cfg|
    cfg.dtdload.dtdattr
  }
  reader.each do |node|
    if reader.node_type == 1 && reader.name == "Product"
      # usually I'd be grabbing the entire node and doing something useful
      # with it..
      foo = reader.outer_xml
      count += 1
    end
  end
end

puts "found #{count} Product nodes"

gistfile2.xsl

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE ONIXMessage SYSTEM "http://www.editeur.org/onix/2.1/02/reference/onix-international.dtd">
<ONIXMessage>
  <Header>
    <FromCompany>HarperCollins Publishers</FromCompany>
    <ToCompany>Australian Booksellers Association</ToCompany>
    <SentDate>20081106</SentDate>
  </Header>
  <Product>
    <RecordReference>9780732287573</RecordReference>
    <NotificationType>03</NotificationType>
    <ProductIdentifier>
      <ProductIDType>02</ProductIDType>
      <IDValue>073228757X</IDValue>
    </ProductIdentifier>
    <ProductIdentifier>
      <ProductIDType>03</ProductIDType>
      <IDValue>9780732287573</IDValue>
    </ProductIdentifier>
    <ProductIdentifier>
      <ProductIDType>15</ProductIDType>
      <IDValue>9780732287573</IDValue>
    </ProductIdentifier>
    <ProductForm>BC</ProductForm>
    <ProductFormDetail>B106</ProductFormDetail>
    <Title>
      <TitleType>01</TitleType>
      <TitleText>High Noon&ndash;in Nimbin</TitleText>
    </Title>
    <Website>
      <WebsiteLink>http://www.harpercollins.com.au/global_scripts/product_catalog/book_xml.asp?isbn=073228757X</WebsiteLink>
    </Website>
    <Contributor>
      <ContributorRole>A01</ContributorRole>
      <PersonNameInverted>Barrett, Robert G</PersonNameInverted>
      <KeyNames>Barrett</KeyNames>
    </Contributor>
    <BICMainSubject>FA</BICMainSubject>
    <OtherText>
      <TextTypeCode>02</TextTypeCode>
      <Text textformat="02">&#39;He looks kind of happyn, the Ken Done of local literature&#39; Courier-Mail </Text>
    </OtherText>
    <Imprint>
      <ImprintName>HarperCollins</ImprintName>
    </Imprint>
    <Publisher>
      <PublishingRole>01</PublishingRole>
      <PublisherName>HarperCollins Publishers</PublisherName>
    </Publisher>
    <PublishingStatus>02</PublishingStatus>
    <PublicationDate>20090301</PublicationDate>
    <Measure><MeasureTypeCode>01</MeasureTypeCode>
      <Measurement>234</Measurement>
      <MeasureUnitCode>mm</MeasureUnitCode>
    </Measure>
    <Measure><MeasureTypeCode>02</MeasureTypeCode>
      <Measurement>153</Measurement>
      <MeasureUnitCode>mm</MeasureUnitCode>
    </Measure>
    <SupplyDetail>
      <SupplierName>Harper Entertainment Distribution Services</SupplierName>
      <Price>
        <PriceTypeCode>02</PriceTypeCode>
        <PriceAmount>29.99</PriceAmount>
      </Price>
    </SupplyDetail>
    <MarketRepresentation>
      <AgentName>HarperCollins Publishers</AgentName>
      <AgentRole>07</AgentRole>
      <MarketCountry>AU</MarketCountry>
      <MarketPublishingStatus>02</MarketPublishingStatus>
      <MarketDate>
        <MarketDateRole>01</MarketDateRole>
        <Date>20090301</Date>
      </MarketDate>
    </MarketRepresentation>
  </Product>
</ONIXMessage>

gistfile3.sh

[jh@gaz onix.git (master)]$ ruby entities.rb 
nokogiri: 1.4.0
libxml: 2.7.6
/var/lib/gems/1.8/gems/nokogiri-1.4.0/lib/nokogiri/xml/reader.rb:68:in `read': Entity 'ndash' not defined (Nokogiri::XML::SyntaxError)
	from /var/lib/gems/1.8/gems/nokogiri-1.4.0/lib/nokogiri/xml/reader.rb:68:in `each'
	from entities.rb:12
	from entities.rb:10:in `open'
	from entities.rb:10