dbd 0.0.9 → 0.0.10

data/spec/lib/dbd/graph/add_to_graph_spec.rb

@@ -4,53 +4,53 @@ module Dbd
   describe Graph do
 
     def new_subject
-      Fact.new_subject
+      Fact.factory.new_subject
     end
 
-    let(:data_fact) { Factories::Fact.data_fact(new_subject, new_subject) }
-    let(:fact_no_subject) { Factories::Fact.data_fact(new_subject, nil) }
-    let(:fact_no_provenance) { Factories::Fact.data_fact(nil, new_subject) }
+    let(:data_fact) { TestFactories::Fact.data_fact(new_subject, new_subject) }
+    let(:fact_no_subject) { TestFactories::Fact.data_fact(new_subject, nil) }
+    let(:fact_no_provenance) { TestFactories::Fact.data_fact(nil, new_subject) }
 
-    let(:provenance_facts) { Factories::Fact::Collection.provenance_facts(new_subject) }
+    let(:provenance_facts) { TestFactories::Fact::Collection.provenance_facts(new_subject) }
     let(:provenance_fact_1) { provenance_facts.first }
 
     let(:subject_regexp) { Fact::Subject.regexp }
 
-    let(:provenance_resource) { Factories::ProvenanceResource.provenance_resource }
-    let(:resource) { Factories::Resource.facts_resource(provenance_resource.subject) }
+    let(:provenance_resource) { TestFactories::ProvenanceResource.provenance_resource }
+    let(:resource) { TestFactories::Resource.facts_resource(provenance_resource.subject) }
     let(:resource_array) { [provenance_resource, resource]}
 
-    describe "create a graph" do
-      it "does not fail" do
+    describe 'create a graph' do
+      it 'does not fail' do
         described_class.new # should_not raise_error
       end
     end
 
-    describe "<< " do
-      describe "a Fact" do
-        it "a data_fact does not fail" do
+    describe '<< ' do
+      describe 'a Fact' do
+        it 'a data_fact does not fail' do
           subject << data_fact
         end
 
-        it "a provenance_fact does not fail" do
+        it 'a provenance_fact does not fail' do
           subject << provenance_fact_1
         end
 
-        it "two facts does not fail" do
+        it 'two facts does not fail' do
           subject << provenance_fact_1
           subject << data_fact
         end
 
-        it "fact with missing subject raises FactError" do
+        it 'fact with missing subject raises FactError' do
           lambda { subject << fact_no_subject } . should raise_error FactError
         end
 
-        it "fact with missing provenance raises FactError" do
+        it 'fact with missing provenance raises FactError' do
           lambda { subject << fact_no_provenance } . should raise_error FactError
         end
       end
 
-      describe "sets the time_stamp and adds a random time (1..999 nanoseconds) if needed" do
+      describe 'sets the time_stamp and adds a random time (1..999 nanoseconds) if needed' do
 
         # NOTE: reduced the far_future from 2500 to 2250 as work around for
         #       http://jira.codehaus.org/browse/JRUBY-7095
@@ -62,7 +62,7 @@ module Dbd
           subject.first.time_stamp.should == far_future
         end
 
-        describe "sets the time_stamp if not yet set" do
+        describe 'sets the time_stamp if not yet set' do
 
           let(:near_future) { Time.now.utc + 100}
           let(:fake_time_stamp) { TimeStamp.new(time: near_future) }
@@ -72,14 +72,14 @@ module Dbd
             fake_time_stamp # get this before setting the stub
           end
 
-          it "sets it (to TimeStamp.new)" do
+          it 'sets it (to TimeStamp.new)' do
             TimeStamp.stub(:new).and_return(fake_time_stamp)
             data_fact.time_stamp.should be_nil # assert pre-condition
             subject << data_fact
             subject.first.time_stamp.should == fake_time_stamp
           end
 
-          it "sends a slightly higher time_stamp than newest_time_stamp if Time.now <= newest_time_stamp" do
+          it 'sends a slightly higher time_stamp than newest_time_stamp if Time.now <= newest_time_stamp' do
             subject.stub(:newest_time_stamp).and_return(fake_time_stamp)
             subject << data_fact
             subject.first.time_stamp.should > fake_time_stamp
@@ -88,18 +88,18 @@ module Dbd
         end
       end
 
-      describe "a ProvenanceResource and a Resource" do
+      describe 'a ProvenanceResource and a Resource' do
 
-        it "does not fail" do
+        it 'does not fail' do
           subject << provenance_resource
         end
 
-        it "Adds the facts from the provenance_resource to the graph" do
+        it 'Adds the facts from the provenance_resource to the graph' do
           subject << provenance_resource
           subject.size.should == 2
         end
 
-        it "Adds the facts from the provenance_resource and the resource to the graph" do
+        it 'Adds the facts from the provenance_resource and the resource to the graph' do
           subject << provenance_resource
           subject << resource
           subject.size.should == 4
@@ -108,31 +108,31 @@ module Dbd
         end
       end
 
-      describe "an array of Resources" do
-        it "does not fail" do
+      describe 'an array of Resources' do
+        it 'does not fail' do
           subject << resource_array
         end
 
-        it "Adds the facts from the provenance_resource and the resource to the graph" do
+        it 'Adds the facts from the provenance_resource and the resource to the graph' do
           subject << resource_array
           subject.first.class.should == ProvenanceFact
           subject.last.class.should == Fact
           subject.size.should == 4
         end
 
-        it "goes 3 levels over collection deep" do
+        it 'goes 3 levels over collection deep' do
           subject << [resource_array]
           subject.size.should == 4
         end
 
-        it "works with different levels deep in 1 collection" do
+        it 'works with different levels deep in 1 collection' do
           subject << [provenance_resource, [[resource]]]
           subject.size.should == 4
         end
       end
 
-      it "returns self" do
-        (subject << Factories::Fact::Collection.provenance_facts(new_subject)).should be_a(described_class)
+      it 'returns self' do
+        (subject << TestFactories::Fact::Collection.provenance_facts(new_subject)).should be_a(described_class)
       end
     end
   end

data/spec/lib/dbd/graph/from_csv_spec.rb

@@ -5,60 +5,87 @@ module Dbd
   describe Graph do
 
     def round_tripped_graph(graph)
-      Graph.from_CSV(StringIO.new(graph.to_CSV))
+      described_class.new.from_CSV(StringIO.new(graph.to_CSV))
     end
 
     def validate_round_trip(graph)
       graph_from_CSV = round_tripped_graph(graph)
-      # temporarily use to_csv as the "identity function" for Graph
+      # temporarily use to_csv as the 'identity function' for Graph
       # TODO define a proper Equality for Graph and Fact
       graph_from_CSV.to_CSV.should == graph.to_CSV
     end
 
-    describe ".from_CSV reads back a csv exported graph correctly" do
+    describe '#from_CSV reads back a csv exported graph correctly' do
+      describe 'for a graph with only provenance_facts' do
 
-      describe "for a graph with only provenance_facts" do
+        let(:graph) { TestFactories::Graph.only_provenance }
 
-        let(:graph) { Factories::Graph.only_provenance }
-
-        it "round_trip validates" do
+        it 'round_trip validates' do
           validate_round_trip(graph)
         end
 
-        it "for a provenance_fact, the provenance_subject must be equal (nil)" do
+        it 'for a provenance_fact, the provenance_subject must be equal (nil)' do
           graph_from_CSV = round_tripped_graph(graph)
           provenance_fact = graph_from_CSV.first
           provenance_fact.provenance_subject.should be_nil
         end
       end
 
-      describe "for a graph with facts and provenance_facts" do
+      describe 'for a graph with facts and provenance_facts' do
 
-        let(:graph) { Factories::Graph.full }
+        let(:graph) { TestFactories::Graph.full }
 
-        it "round_trip validates" do
+        it 'round_trip validates' do
           validate_round_trip(graph)
         end
 
-        it "the short export of a graph is correct after a round trip" do
-          imported_graph = Dbd::Graph.from_CSV(graph.to_CSV)
+        it 'the short export of a graph is correct after a round trip' do
+          imported_graph = described_class.new.from_CSV(graph.to_CSV)
           imported_graph.map(&:short).should == (graph.map(&:short))
         end
       end
     end
 
-    describe ".from_CSV reads special cases correctly" do
+    describe '#from_CSV reads back _two_ csv exported graphs correctly' do
+      describe 'for a graph with facts and provenance_facts' do
+
+        let(:graph_provenance) { TestFactories::Graph.only_provenance }
+        let(:graph_facts) { TestFactories::Graph.only_facts(graph_provenance.first.subject) }
+        let(:graph_provenance_csv) { graph_provenance.to_CSV }
+        let(:graph_facts_csv) { graph_facts.to_CSV }
+
+        let(:graph_from_2_csv_s) do
+          stream_1 = StringIO.new(graph_provenance_csv)
+          stream_2 = StringIO.new(graph_facts_csv)
+          graph = described_class.new
+          graph.from_CSV(stream_1)
+          graph.from_CSV(stream_2)
+        end
+
+        it 'round_trip validates' do
+          # we do not have full graph equivalence yet
+          graph_from_2_csv_s.first.should be_equivalent(graph_provenance.first)
+          graph_from_2_csv_s.last.should be_equivalent(graph_facts.last)
+        end
+
+        it 'a string concat of 2 CSV files works to logically concat them' do
+          graph_from_2_csv_s.to_CSV.should == (graph_provenance_csv + graph_facts_csv)
+        end
+      end
+    end
+
+    describe '#from_CSV reads special cases correctly' do
 
-      let(:provenance_subject) { Factories::Fact::Subject.fixed_provenance_subject }
-      let(:resource) { Factories::Resource.empty(provenance_subject) }
-      let(:special_fact) { Factories::Fact.fact_with_special_chars(provenance_subject, resource.subject) }
+      let(:provenance_subject) { TestFactories::Fact::Subject.fixed_provenance_subject }
+      let(:resource) { TestFactories::Resource.empty(provenance_subject) }
+      let(:special_fact) { TestFactories::Fact.fact_with_special_chars(provenance_subject, resource.subject) }
 
-      it "as object" do
+      it 'as object' do
         resource << special_fact
         graph = described_class.new << resource
         csv = graph.to_CSV
-        csv.should match(%r{A long story\nreally with a comma, a double quote "" and a non-ASCII char éà Über.})
-        graph_from_CSV = described_class.from_CSV(csv)
+        csv.should match(%r{A long story with a newline\nreally with a comma, a double quote "" and a non-ASCII char éà Über.})
+        graph_from_CSV = described_class.new.from_CSV(csv)
         graph_from_CSV.first.should be_equivalent(graph.first)
       end
     end

data/spec/lib/dbd/graph/test_factories_spec.rb

@@ -0,0 +1,58 @@
+require 'spec_helper'
+
+module TestFactories
+  describe Graph do
+    describe 'with only provenance facts' do
+
+      let(:only_provenance) { described_class.only_provenance }
+
+      it 'is a Graph' do
+        only_provenance.should be_a(described_class.factory_for)
+      end
+
+      it 'has some facts' do
+        only_provenance.size.should >= 2
+      end
+    end
+
+    describe 'with only facts' do
+
+      let(:subject) { described_class.new_subject }
+      let(:only_facts_without_provenance_subject) { described_class.only_facts }
+      let(:only_facts_with_provenance_subject) { described_class.only_facts(subject) }
+
+      describe 'only_facts_without_provenance_subject' do
+        it 'is a Graph' do
+          only_facts_without_provenance_subject.should be_a(described_class.factory_for)
+        end
+
+        it 'has some facts' do
+          only_facts_without_provenance_subject.size.should >= 2
+        end
+      end
+
+      describe 'only_facts_with_subject' do
+        it 'is a Graph' do
+          only_facts_with_provenance_subject.should be_a(described_class.factory_for)
+        end
+
+        it 'has the set subject' do
+          only_facts_with_provenance_subject.first.provenance_subject.should == subject
+        end
+      end
+    end
+
+    describe 'full' do
+
+      let(:full) { described_class.full }
+
+      it 'is a Graph' do
+        full.should be_a(described_class.factory_for)
+      end
+
+      it 'full has many facts' do
+        full.size.should >= 4
+      end
+    end
+  end
+end

data/spec/lib/dbd/graph/to_csv_spec.rb

@@ -5,18 +5,19 @@ module Dbd
   describe Graph do
 
     def new_subject
-      Fact.new_subject
+      Fact.factory.new_subject
     end
 
-    let(:provenance_facts) { Factories::Fact::Collection.provenance_facts(new_subject) }
+    let(:provenance_facts) { TestFactories::Fact::Collection.provenance_facts(new_subject) }
     let(:provenance_fact_1) { provenance_facts.first }
-    let(:fact_2_3) { Factories::Fact::Collection.fact_2_3(provenance_fact_1.subject) }
-    let(:fact_special_characters) { Factories::Fact::fact_with_special_chars(provenance_fact_1.subject, new_subject) }
+    let(:fact_2_3) { TestFactories::Fact::Collection.fact_2_3(provenance_fact_1.subject) }
+    let(:fact_special_characters) { TestFactories::Fact::fact_with_special_chars(provenance_fact_1.subject, new_subject) }
 
-    let(:subject_regexp) { Fact::Subject.regexp }
-    let(:id_regexp) { Fact::ID.regexp }
+    let(:subject_valid_regexp) { Fact::Subject.valid_regexp }
+    let(:id_valid_regexp) { Fact::ID.valid_regexp }
+    let(:time_stamp_valid_regexp) { TimeStamp.valid_regexp }
 
-    describe "#to_CSV with only provenance_facts" do
+    describe '#to_CSV with only provenance_facts' do
       before do
         provenance_facts.each_with_index do |provenance_fact, index|
           subject << provenance_fact
@@ -27,7 +28,7 @@ module Dbd
         subject.to_CSV.should be_a(String)
       end
 
-      it "returns a string in UTF-8 encoding" do
+      it 'returns a string in UTF-8 encoding' do
         subject.to_CSV.encoding.should == Encoding::UTF_8
       end
 
@@ -35,66 +36,66 @@ module Dbd
         subject.to_CSV.should match(/\A"[^",]+","[^",]+","[^",]*","[^",]+"/)
       end
 
-      describe "with a single provenance_fact collection" do
-        it "has three logical lines (but one with embedded newline)" do
+      describe 'with a single provenance_fact collection' do
+        it 'has three logical lines (but one with embedded newline)' do
           subject.to_CSV.lines.count.should == 4
         end
 
-        it "ends with a newline" do
+        it 'ends with a newline' do
           subject.to_CSV.lines.to_a.last[-1].should == "\n"
         end
       end
 
-      describe "has all attributes of the provenance_fact_collection" do
+      describe 'has all attributes of the provenance_fact_collection' do
 
         let(:first_line) do
           subject.to_CSV.lines.to_a.first.chomp
         end
 
-        it "has id (a Fact::ID) as first value" do
-          first_line.split(',')[0].gsub(/"/, '').should match(id_regexp)
+        it 'has id (a Fact::ID) as first value' do
+          first_line.split(',')[0].gsub(/"/, '').should match(id_valid_regexp)
         end
 
-        it "has time_stamp as second value" do
-          first_line.split(',')[1].should match(TimeStamp.to_s_regexp)
+        it 'has time_stamp as second value' do
+          first_line.split(',')[1][1..-2].should match(time_stamp_valid_regexp)
         end
 
-        it "has an empty third value (signature of a provenance_fact)" do
-          first_line.split(',')[2].should == "\"\""
+        it 'has an empty third value (signature of a provenance_fact)' do
+          first_line.split(',')[2].should == '""'
         end
 
-        it "has subject as 4th value" do
-          first_line.split(',')[3].gsub(/"/, '').should match(subject_regexp)
+        it 'has subject as 4th value' do
+          first_line.split(',')[3].gsub(/"/, '').should match(subject_valid_regexp)
         end
 
-        it "has data_predicate as 5th value" do
+        it 'has data_predicate as 5th value' do
           first_line.split(',')[4].should == '"https://data.vandenabeele.com/ontologies/provenance#context"'
         end
 
-        it "has object as 6th value" do
+        it 'has object as 6th value' do
           first_line.split(',')[5].should == '"public"'
         end
       end
 
-      describe "handles comma, double quote and newline correctly" do
-        it "has original_source with special characters and double quote escaped" do
+      describe 'handles comma, double quote and newline correctly' do
+        it 'has original_source with special characters and double quote escaped' do
           subject.to_CSV.should match(/"this has a comma , a newline \n and a double quote """/)
         end
       end
     end
 
-    describe "#to_CSV with only facts" do
+    describe '#to_CSV with only facts' do
       before do
         fact_2_3.each_with_index do |fact, index|
           subject << fact
          end
       end
 
-      it "returns a string" do
+      it 'returns a string' do
         subject.to_CSV.should be_a(String)
       end
 
-      it "returns a string in UTF-8 encoding" do
+      it 'returns a string in UTF-8 encoding' do
         subject.to_CSV.encoding.should == Encoding::UTF_8
       end
 
@@ -102,49 +103,49 @@ module Dbd
         subject.to_CSV.should match(/\A"[^",]+","[^",]+","[^",]+"/)
       end
 
-      describe "with a single fact collection" do
-        it "has two lines" do
+      describe 'with a single fact collection' do
+        it 'has two lines' do
           subject.to_CSV.lines.count.should == 2
         end
 
-        it "ends with a newline" do
+        it 'ends with a newline' do
           subject.to_CSV.lines.to_a.last[-1].should == "\n"
         end
       end
 
-      describe "has all attributes of the fact_collection" do
+      describe 'has all attributes of the fact_collection' do
 
         let(:first_line) do
           subject.to_CSV.lines.to_a.first.chomp
         end
 
-        it "has id (a Fact::ID) as first value" do
-          first_line.split(',')[0].gsub(/"/, '').should match(id_regexp)
+        it 'has id (a Fact::ID) as first value' do
+          first_line.split(',')[0].gsub(/"/, '').should match(id_valid_regexp)
         end
 
-        it "has time_stamp as second value" do
-          first_line.split(',')[1].should match(TimeStamp.to_s_regexp)
+        it 'has time_stamp as second value' do
+          first_line.split(',')[1][1..-2].should match(time_stamp_valid_regexp)
         end
 
-        it "has provenance_fact_1.subject as third value" do
+        it 'has provenance_fact_1.subject as third value' do
           first_line.split(',')[2].should == "\"#{provenance_fact_1.subject.to_s}\""
         end
 
-        it "has subject as 4th value" do
-          first_line.split(',')[3].gsub(/"/, '').should match(subject_regexp)
+        it 'has subject as 4th value' do
+          first_line.split(',')[3].gsub(/"/, '').should match(subject_valid_regexp)
         end
 
-        it "has data_predicate as 5th value" do
+        it 'has data_predicate as 5th value' do
           first_line.split(',')[4].should == '"http://example.org/test/name"'
         end
 
-        it "has object as 6th value" do
+        it 'has object as 6th value' do
           first_line.split(',')[5].should == '"Mandela"'
         end
       end
     end
 
-    describe "#to_CSV with provenance_facts and facts" do
+    describe '#to_CSV with provenance_facts and facts' do
 
       before do
         provenance_facts.each do |provenance_fact|
@@ -155,12 +156,12 @@ module Dbd
          end
       end
 
-      it "has six lines" do
+      it 'has six lines' do
         subject.to_CSV.lines.count.should == 6
       end
     end
 
-    describe "#to_CSV_file" do
+    describe '#to_CSV_file' do
 
       before do
         provenance_facts.each do |provenance_fact|
@@ -172,7 +173,7 @@ module Dbd
         subject << fact_special_characters
       end
 
-      it "has eight lines" do
+      it 'has eight lines' do
         filename = 'data/foo.csv'
         subject.to_CSV_file(filename)
         File.open(filename) do |f|
@@ -180,7 +181,7 @@ module Dbd
         end
       end
 
-      it "reads back UTF-8 characters correctly" do
+      it 'reads back UTF-8 characters correctly' do
         filename = 'data/foo.csv'
         subject.to_CSV_file(filename)
         File.open(filename) do |f|