Qualified DC to N-Triples

qdc_rdf.rb

require 'nokogiri'
require 'rdf'
require 'chronic'

xmldoc = Nokogiri::XML('<metadata xmlns="http://example.org/myapp/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dcterms="http://purl.org/dc/terms/" xsi:schemaLocation="http://example.org/myapp/ http://example.org/myapp/schema.xsd">
  <dc:title>
    UKOLN
  </dc:title>
  <dcterms:alternative>
    UK Office for Library and Information Networking
  </dcterms:alternative>
  <dc:subject>
    national centre, network information support, library
    community, awareness, research, information services,public
    library networking, bibliographic management, distributed
    library systems, metadata, resource discovery,
    conferences,lectures, workshops
  </dc:subject>
  <dc:subject xsi:type="dcterms:DDC">
    062
  </dc:subject>
  <dc:subject xsi:type="dcterms:UDC">
    061(410)
  </dc:subject>
  <dc:description>
    UKOLN is a national focus of expertise in digital information
    management. It provides policy, research and awareness services
    to the UK library, information and cultural heritage communities.
    UKOLN is based at the University of Bath.
  </dc:description>
  <dc:publisher>
    UKOLN, University of Bath
  </dc:publisher>
  <dcterms:isPartOf xsi:type="dcterms:URI">
    http://www.bath.ac.uk/
  </dcterms:isPartOf>
  <dc:identifier xsi:type="dcterms:URI">
    http://www.ukoln.ac.uk/
  </dc:identifier>
  <dcterms:modified xsi:type="dcterms:W3CDTF">
    2001-07-18
  </dcterms:modified>
  <dc:format xsi:type="dcterms:IMT">
    text/html
  </dc:format>
  <dcterms:extent>
    14 Kbytes
  </dcterms:extent>
</metadata>
')

map = {
  'alternative' => RDF::DC.alternative,
  'description' => RDF::DC.description,
  'extent' => RDF::DC.extent,
  'format' => RDF::DC.format,
  'identifier' => RDF::DC.identifier,
  'isPartOf' => RDF::DC.isPartOf,
  'modified' => RDF::DC.modified,
  'publisher' => RDF::DC.publisher,
  'subject' => RDF::DC.subject,
  'title' => RDF::DC.title
}

date_localnames = [
  'modified', 
  'created', 
  'date',
  'dateAccepted',
  'dateCopyrighted', 
  'dateSubmitted'
]

g = RDF::Graph.new
id = RDF::URI.new('http://localhost/myobject')

xmldoc.xpath('/*/*').each do |e|
  ln = e.xpath('local-name()')
  v = e.text().strip()
  if date_localnames.include? ln
    v = DateTime.parse(Chronic::parse(v).to_s)
  else
    v= v.split.join(' ')
  end
  g << [id, map[ln], v]
end

puts g.dump(:ntriples)