Daniel Hernandez
d2481d6e80
19 queries in updates/ convert categorical columns (continent, country, city, gender, profession, etc.) from literals to typed RDF objects with rdfs:label. map/step-02.rb applies them to produce data/graph-02.ttl. Also fix step-01.rb to sanitize column names with spaces and avoid prefix serialization issues with fragment IRIs.
38 lines
1.1 KiB
Ruby
38 lines
1.1 KiB
Ruby
#!/usr/bin/env ruby
|
|
# frozen_string_literal: true
|
|
|
|
# Step 2: Transform literal values into RDF objects using SPARQL UPDATE queries
|
|
|
|
require 'rdf'
|
|
require 'rdf/turtle'
|
|
require 'sparql'
|
|
|
|
input_path = File.expand_path('../data/graph-01.ttl', __dir__)
|
|
output_path = File.expand_path('../data/graph-02.ttl', __dir__)
|
|
updates_dir = File.expand_path('../updates', __dir__)
|
|
|
|
puts "Loading graph from #{input_path}..."
|
|
graph = RDF::Graph.load(input_path)
|
|
puts "Loaded #{graph.count} triples."
|
|
|
|
Dir.glob(File.join(updates_dir, '*.rq')).sort.each do |query_file|
|
|
query = File.read(query_file)
|
|
name = File.basename(query_file)
|
|
|
|
before = graph.count
|
|
SPARQL.execute(query, graph, update: true)
|
|
after = graph.count
|
|
puts "Applied #{name}: #{before} -> #{after} triples (#{after - before >= 0 ? '+' : ''}#{after - before})"
|
|
end
|
|
|
|
puts "Writing #{graph.count} triples to #{output_path}..."
|
|
RDF::Turtle::Writer.open(output_path, prefixes: {
|
|
rdf: RDF.to_uri,
|
|
rdfs: RDF::RDFS.to_uri,
|
|
xsd: RDF::XSD.to_uri,
|
|
base: RDF::URI.new('http://example.org/migrants/')
|
|
}) do |writer|
|
|
graph.each_statement { |stmt| writer << stmt }
|
|
end
|
|
|
|
puts "Done."
|