@@ -12,6 +12,7 @@ module Calais :relevances => 'type/sys/RelevanceInfo', } + attr_accessor :submitter_code, :signature, :language, :submission_date, :request_id, :doc_title, :doc_date attr_accessor :hashes, :entities, :relations, :geographies, :categories def initialize(rdf_string) @@ -77,9 +78,28 @@ module Calais def extract_data doc = XML::Parser.string(@raw_response).parse - doc.root.find("rdf:Description/rdf:type[contains(@rdf:resource, '#{MATCHERS[:docinfo]}')]/..").each { |node| node.remove! } - doc.root.find("rdf:Description/rdf:type[contains(@rdf:resource, '#{MATCHERS[:docinfometa]}')]/..").each { |node| node.remove! } - doc.root.find("rdf:Description/rdf:type[contains(@rdf:resource, '#{MATCHERS[:defaultlangid]}')]/..").each { |node| node.remove! } + doc.root.find("rdf:Description/rdf:type[contains(@rdf:resource, '#{MATCHERS[:docinfometa]}')]/..").each do |node| + @language = node['language'] + @submission_date = DateTime.parse node['submissionDate'] + + attributes = extract_attributes(node.find("*[contains(name(), 'c:')]")) + + @signature = attributes.delete('signature') + @submitter_code = attributes.delete('submitterCode') + + node.remove! + end + + doc.root.find("rdf:Description/rdf:type[contains(@rdf:resource, '#{MATCHERS[:docinfo]}')]/..").each do |node| + @request_id = node['calaisRequestID'] + + attributes = extract_attributes(node.find("*[contains(name(), 'c:')]")) + + @doc_title = attributes.delete('docTitle') + @doc_date = Date.parse attributes.delete('docDate') + + node.remove! + end @categories = doc.root.find("rdf:Description/rdf:type[contains(@rdf:resource, '#{MATCHERS[:doccat]}')]/..").map do |node| category = Category.new @@ -138,6 +158,7 @@ module Calais geography end + doc.root.find("rdf:Description/rdf:type[contains(@rdf:resource, '#{MATCHERS[:defaultlangid]}')]/..").each { |node| node.remove! } doc.root.find("./*").each { |node| node.remove! } return @@ -159,7 +180,7 @@ module Calais rescue nil end - + def extract_attributes(nodes) nodes.inject({}) do |hsh, node| value = if node['resource'] lib/calais/response.rb @@ -11,6 +11,16 @@ describe Calais::Response, :new do @response = Calais::Response.new(SAMPLE_RESPONSE) end + it 'should extract document information' do + @response.language.should == 'English' + @response.submission_date.should be_a_kind_of(DateTime) + @response.signature.should == 'digestalg-1|iCEVI2NK1nAAvP+p5uaqnHISxdo=|U3QC5z6ZN1DLUJrqiP6gpTuxrdAxOaVOrjUQVuarCmb+zoqbm2fypA==' + @response.submitter_code.should == '4a388fbc-9897-def9-9233-efddbfbca363' + @response.request_id.should == '896ffd83-ad5f-4e4b-892b-4cc337a246af' + @response.doc_title.should == 'Record number of bicycles sold in Australia in 2006' + @response.doc_date.should be_a_kind_of(Date) + end + it 'should extract entities' do entities = @response.entities entities.map { |e| e.type }.sort.uniq.should == %w[City Continent Country IndustryTerm Organization Person ProvinceOrState] spec/calais/response_spec.rb 9741d4b503531c0a2b7d9a79208c88a30e804a41 Abhay Kumar abhay@opensynapse.net http://github.com/technicalpickles/calais/commit/29c1af323742c750a9b1a837e8ac553a8feb52d3 29c1af323742c750a9b1a837e8ac553a8feb52d3 2008-12-18T23:20:04-08:00 2008-12-18T23:20:04-08:00 extract all info from the response document b88ae28a470dfcfff76cb3f22b10a55c528985dd Abhay Kumar abhay@opensynapse.net