Joomla articles (J2XML) to HTML pages converter, eg Oracle Web Center

j2owc.rb

###############################################################
# Joomla to Oracle Web Center Content Server transformer
# Thanks to http://railstips.org/
#

gem 'libxml-ruby'
%w[benchmark pp rubygems htmlentities xml].each { |x| require x }

puts Benchmark.measure {
  parser = XML::Parser.file('input/input.xml')
  doc, list = parser.parse, []
  doc.find('//j2xml/content').each do |s|
    h = { }
    %w[id title alias introtext sectionid catid created modified_by].each do |a|
      h[a.intern] = s.find(a).first.content
    end
    list << h
  end

  # create doc files
  list.each do |item|
    f = File::new('output/' + item[:id] + '.html', "w+")
    coder = HTMLEntities.new
    f << <<-EOS
<h2>
  #{coder.decode(item[:title])}</h2>
<h3>
  #{coder.decode(item[:alias])}</h3>
<p>
  #{coder.decode(item[:introtext])}</p>
EOS
    f.close
  end

  # create batch file
  f = File::new('output/batch.txt', "w+")
  list.each do |item|
    f << <<-EOS
Action=insert
dDocName=HR001
dDocType=Form
dDocTitle=New Employee Information Form
dDocAuthor=Olson
dSecurityGroup=Public
primaryFile=#{item[:id]}.html
dIndate=3/15/97
<<EOD>>

EOS
  end
  f.close
}