dwc-archive 0.9.10 → 1.1.2

data/spec/lib/generator_eml_xml_spec.rb

@@ -1,21 +1,22 @@
-require_relative '../spec_helper'
+# frozen_string_literal: true
 
 describe DarwinCore::Generator::EmlXml do
-  subject(:eml) { DarwinCore::Generator::EmlXml.new(data, path) }
+  subject { DarwinCore::Generator::EmlXml.new(data, path) }
   let(:data) { EML_DATA }
   let(:path) { DarwinCore::DEFAULT_TMP_DIR }
 
-  describe '.new' do
-    it 'initializes generator' do
-      expect(eml).to be_kind_of DarwinCore::Generator::EmlXml
-    end
+  describe ".new" do
+    it { is_expected.to be_kind_of DarwinCore::Generator::EmlXml }
   end
 
-  describe '#create' do
-    it 'should create eml xml' do
-      eml.create
-      eml_xml = File.read(File.join(path, 'eml.xml'))
-      expect(eml_xml).to match /Test Classification/
+  describe "#create" do
+    let(:content) do
+      subject.create
+      File.read(File.join(path, "eml.xml"))
+    end
+
+    it "should create eml xml" do
+      expect(content).to match(/Test Classification/)
     end
   end
 end

data/spec/lib/generator_meta_xml_spec.rb

@@ -1,21 +1,22 @@
-require_relative '../spec_helper'
+# frozen_string_literal: true
 
 describe DarwinCore::Generator::MetaXml do
-  subject(:meta) { DarwinCore::Generator::MetaXml.new(data, path) }
+  subject { DarwinCore::Generator::MetaXml.new(data, path) }
   let(:data) { META_DATA }
   let(:path) { DarwinCore::DEFAULT_TMP_DIR }
 
-  describe '.new' do
-    it 'initializes' do
-      expect(meta).to be_kind_of DarwinCore::Generator::MetaXml
-    end
+  describe ".new" do
+    it { is_expected.to be_kind_of DarwinCore::Generator::MetaXml }
   end
 
-  describe '#create' do
-    it 'creates metadata file' do
-      meta.create
-      meta = File.read(File.join(path, 'meta.xml'))
-      expect(meta).to match %r|<location>core.csv</location>|  
+  describe "#create" do
+    let(:content) do
+      subject.create
+      File.read(File.join(path, "meta.xml"))
+    end
+
+    it "creates metadata file" do
+      expect(content).to match(%r{<location>core.csv</location>})
     end
   end
 end

data/spec/lib/generator_spec.rb

@@ -1,116 +1,124 @@
-# encoding: utf-8
-require_relative '../spec_helper'
+# frozen_string_literal: true
 
 describe DarwinCore::Generator do
   subject(:gen) { DarwinCore::Generator.new(dwc_path, tmp_dir) }
   let(:tmp_dir) { DarwinCore::DEFAULT_TMP_DIR }
-  let(:dwc_path) { File.join(tmp_dir, 'spec_dwca.tar.gz') } 
+  let(:dwc_path) { File.join(tmp_dir, "spec_dwca.tar.gz") }
 
-  describe '.new' do
-    it 'initializes empty DwCA' do
-      expect(gen).to be_kind_of DarwinCore::Generator      
+  def generate_dwca(gen)
+    gen.add_core(CORE_DATA.dup, "core.csv", true)
+    gen.add_extension(EXTENSION_DATA.dup, "vern.csv", true,
+                      "http://rs.gbif.org/terms/1.0/VernacularName")
+    gen.add_meta_xml
+    gen.add_eml_xml(EML_DATA)
+  end
+
+  describe ".new" do
+    it "initializes empty DwCA" do
+      expect(gen).to be_kind_of DarwinCore::Generator
     end
   end
 
-  describe '#add_core' do
-    it 'adds core to DwCA instance' do
-      gen.add_core(CORE_DATA.dup, 'core.csv', true)
-      core = File.read(File.join(gen.path, 'core.csv'))
-      expect(core).to match /taxonID,parentNameUsageID,scientificName/
+  describe "#add_core" do
+    it "adds core to DwCA instance" do
+      gen.add_core(CORE_DATA.dup, "core.csv", true)
+      core = File.read(File.join(gen.path, "core.csv"))
+      expect(core).to match(/taxonID,parentNameUsageID,scientificName/)
     end
 
-    context 'urls are not given in header' do
-      it 'raises error' do
+    context "urls are not given in header" do
+      it "raises error" do
         data = CORE_DATA.dup
-        data[0] = data[0].map { |f| f.split('/')[-1] }
-        expect { gen.add_core(data, 'core.csv', true) }.
-                              to raise_error DarwinCore::GeneratorError
+        data[0] = data[0].map { |f| f.split("/")[-1] }
+        expect { gen.add_core(data, "core.csv", true) }.
+          to raise_error DarwinCore::GeneratorError
       end
     end
   end
 
-  describe '#add_extension' do
-    it 'adds extension to DwCA instance' do
-      gen.add_extension(EXTENSION_DATA.dup, 
-                        'vern.csv', 
-                        true, 
-                        'http://rs.gbif.org/terms/1.0/VernacularName')
-      extension = File.read(File.join(gen.path, 'vern.csv'))
-      
-      expect(extension).to match /Береза/
+  describe "#add_extension" do
+    it "adds extension to DwCA instance" do
+      gen.add_extension(EXTENSION_DATA.dup,
+                        "vern.csv",
+                        true,
+                        "http://rs.gbif.org/terms/1.0/VernacularName")
+      extension = File.read(File.join(gen.path, "vern.csv"))
+
+      expect(extension).to match(/Береза/)
     end
   end
 
-  describe '#add_meta_xml' do
-    it 'creates metadata for DwCA' do
-      gen.add_core(CORE_DATA.dup, 'core.csv', true)
-      gen.add_extension(EXTENSION_DATA.dup, 
-                        'vern.csv', 
-                        true, 
-                        'http://rs.gbif.org/terms/1.0/VernacularName')
+  describe "#add_meta_xml" do
+    it "creates metadata for DwCA" do
+      gen.add_core(CORE_DATA.dup, "core.csv", true)
+      gen.add_extension(EXTENSION_DATA.dup,
+                        "vern.csv",
+                        true,
+                        "http://rs.gbif.org/terms/1.0/VernacularName")
 
       gen.add_meta_xml
-      meta = File.read(File.join(gen.path, 'meta.xml'))
-      expect(meta).to match %r|<location>core.csv</location>|
+      meta = File.read(File.join(gen.path, "meta.xml")).strip
+      meta_from_file = File.read(
+        File.expand_path("../files/generator_meta.xml", __dir__)
+      ).strip
+      expect(meta).to eq meta_from_file
     end
   end
 
-  describe '#add_eml_data' do
-    it 'adds eml data' do
+  describe "#add_eml_data" do
+    it "adds eml data" do
       gen.add_eml_xml(EML_DATA)
-      eml = File.read(File.join(gen.path, 'eml.xml'))
-      expect(eml).to match /jdoe@example.com/
+      eml = File.read(File.join(gen.path, "eml.xml")).strip
+      eml.gsub!(%r{(<pubDate>).*?(</pubDate>)}, '\12013-12-30 14:45:33 -0500\2')
+      eml.gsub!(/(packageId=").*?"/, '\11234/2013-12-30::19:45:33"')
+
+      eml_from_file = File.read(
+        File.expand_path("../files/generator_eml.xml", __dir__)
+      ).strip
+      expect(eml.strip).to eq eml_from_file.strip
     end
   end
 
-  describe '#path' do
-    it 'returns temporary path for assembling DwCA' do
-      expect(gen.path).to match /dwc_\d+$/
+  describe "#path" do
+    it "returns temporary path for assembling DwCA" do
+      expect(gen.path).to match(/dwc_\d+$/)
     end
   end
 
-  describe '#files' do
-    it 'returns created files' do
-      gen.add_core(CORE_DATA.dup, 'core.csv', true)
-      gen.add_extension(EXTENSION_DATA.dup, 
-                        'vern.csv', 
-                        true, 
-                        'http://rs.gbif.org/terms/1.0/VernacularName')
+  describe "#files" do
+    before(:example) { generate_dwca(gen) }
 
-      gen.add_meta_xml
-      expect(gen.files).to match_array ['core.csv', 'meta.xml', 'vern.csv']  
+    it "returns created files" do
+      expect(gen.files).
+        to match_array ["core.csv", "eml.xml", "meta.xml", "vern.csv"]
     end
   end
 
-  describe '#pack' do
-    it 'creates final DwCA file' do
-      FileUtils.rm dwc_path if File.exists?(dwc_path)
-      gen.add_core(CORE_DATA.dup, 'core.csv', true)
-      gen.add_extension(EXTENSION_DATA.dup, 
-                        'vern.csv', 
-                        true, 
-                        'http://rs.gbif.org/terms/1.0/VernacularName')
+  describe "#pack" do
+    before(:example) do
+      FileUtils.rm dwc_path if File.exist?(dwc_path)
+      generate_dwca(gen)
+    end
 
-      gen.add_meta_xml
-      gen.add_eml_xml(EML_DATA)
+    it "creates final DwCA file" do
       gen.pack
-      expect(File.exists?(dwc_path)).to be_true 
+      expect(File.exist?(dwc_path)).to be true
     end
   end
 
-  describe '#clean' do
-    it 'removes temporary directory for DwCA' do
-      gen.add_eml_xml(EML_DATA)
-      expect(File.exists?(gen.path)).to be true
+  describe "#clean" do
+    before(:example) { gen.add_eml_xml(EML_DATA) }
+
+    it "removes temporary directory for DwCA" do
+      expect(File.exist?(gen.path)).to be true
       gen.clean
-      expect(File.exists?(gen.path)).to be false
+      expect(File.exist?(gen.path)).to be false
     end
   end
 
-  describe '#eml_xml_data' do
-    it 'returns current eml data' do
+  describe "#eml_xml_data" do
+    it "returns current eml data" do
       expect(gen.eml_xml_data).to be_kind_of Hash
     end
   end
-  
 end

data/spec/lib/gnub_taxon_spec.rb

@@ -1,34 +1,32 @@
-require_relative '../spec_helper'
+# frozen_string_literal: true
 
 describe DarwinCore::GnubTaxon do
   subject(:dwca) { DarwinCore.new(file_path) }
   subject(:normalizer) { DarwinCore::ClassificationNormalizer.new(dwca) }
-  let(:file_dir) { File.expand_path('../../files', __FILE__) }
+  let(:file_dir) { File.expand_path("../files", __dir__) }
   let(:file_path) { File.join(file_dir, file_name) }
-  let(:file_name) { 'gnub.tar.gz' }
+  let(:file_name) { "gnub.tar.gz" }
 
-  it 'should get uuids from GNUB' do
+  it "should get uuids from GNUB" do
     normalizer.normalize
-    tn = normalizer.normalized_data['9c399f90-cfb8-5a7f-9a21-18285a473488']
+    tn = normalizer.normalized_data["9c399f90-cfb8-5a7f-9a21-18285a473488"]
     expect(tn).to be_kind_of DarwinCore::GnubTaxon
     expect(tn).to be_kind_of DarwinCore::TaxonNormalized
-    expect(tn.uuid).to eq '8faa91f6-663f-4cfe-b785-0ab4e9415a51'
-    expect(tn.uuid_path).to eq [
-      '9a9f9eeb-d5f9-4ff6-b6cb-a5ad345e33c3',
-      'bf4c91c0-3d1f-44c7-9d3b-249382182a26',
-      '8faa91f6-663f-4cfe-b785-0ab4e9415a51']
-
+    expect(tn.uuid).to eq "8faa91f6-663f-4cfe-b785-0ab4e9415a51"
+    expect(tn.uuid_path).to eq %w[
+      9a9f9eeb-d5f9-4ff6-b6cb-a5ad345e33c3
+      bf4c91c0-3d1f-44c7-9d3b-249382182a26
+      8faa91f6-663f-4cfe-b785-0ab4e9415a51
+    ]
   end
 
-
-  context 'not a gnub data' do
-    let(:file_name) { 'data.tar.gz' }
-    it 'should not be of GnubTaxon type' do
+  context "not a gnub data" do
+    let(:file_name) { "data.tar.gz" }
+    it "should not be of GnubTaxon type" do
       normalizer.normalize
-      tn = normalizer.normalized_data['leptogastrinae:tid:42']
+      tn = normalizer.normalized_data["leptogastrinae:tid:42"]
       expect(tn).to be_kind_of DarwinCore::TaxonNormalized
       expect(tn).not_to be_kind_of DarwinCore::GnubTaxon
     end
   end
-    
 end

data/spec/lib/metadata_spec.rb

@@ -1,80 +1,89 @@
-require_relative '../spec_helper'
+# frozen_string_literal: true
 
 describe DarwinCore::Metadata do
-  subject(:dwca) { DarwinCore.new(file_path) }
   subject(:eml) { DarwinCore::Metadata.new(dwca.archive) }
-  let(:file_path) { File.join(File.expand_path('../../files', __FILE__), 
-                              file_name) }
-  let(:file_name) { 'data.tar.gz' }
-  
-  describe '.new' do
-    it 'initializes' do
+  let(:dwca) { DarwinCore.new(file_path) }
+  let(:file_path) do
+    File.join(File.expand_path("../files", __dir__), file_name)
+  end
+  let(:file_name) { "data.tar.gz" }
+
+  describe ".new" do
+    it "initializes" do
       expect(eml).to be_kind_of DarwinCore::Metadata
     end
   end
 
-  describe '#data' do
-    it 'returns hash of metadata' do
+  describe "#data" do
+    it "returns hash of metadata" do
       expect(eml.data).to be_kind_of Hash
     end
   end
 
-  describe '#id' do
-    it 'returns id of the archive if it exists' do
-      expect(eml.id).to eq 'leptogastrinae:version:2.5'
+  describe "#id" do
+    it "returns id of the archive if it exists" do
+      expect(eml.id).to eq "leptogastrinae:version:2.5"
     end
   end
 
-  describe '#package_id' do
-    context 'no package id is given' do
-      it 'returns id of the DwCA file if exists' do
+  describe "#package_id" do
+    context "no package id is given" do
+      before(:example) do
+        @attributes = eml.data[:eml].delete(:attributes)
+      end
+
+      after(:example) do
+        eml.data[:eml][:attributes] = @attributes
+      end
+
+      it "returns id of the DwCA file if exists" do
+        expect { eml.data[:eml][:attributes][:packageId] }.
+          to raise_exception NoMethodError
         expect(eml.package_id).to be_nil
       end
     end
   end
 
-  describe '#title' do
-    it 'returns name of the archive' do
+  describe "#title" do
+    it "returns name of the archive" do
       expect(eml.title).
-        to eq 'Leptogastrinae (Diptera: Asilidae) Classification'
+        to eq "Leptogastrinae (Diptera: Asilidae) Classification"
     end
   end
 
-  describe '#authors' do
-    it 'returns authors of the archive' do
+  describe "#authors" do
+    it "returns authors of the archive" do
       expect(eml.authors).
         to eq [
-          {:first_name=>"Keith", 
-           :last_name=>"Bayless", 
-           :email=>"keith.bayless@gmail.com"}, 
-          {:first_name=>"Torsten", 
-            :last_name=>"Dikow", 
-            :email=>"dshorthouse@eol.org"}]
+          { first_name: "Keith",
+            last_name: "Bayless",
+            email: "keith.bayless@gmail.com" },
+          { first_name: "Torsten",
+            last_name: "Dikow",
+            email: "dshorthouse@eol.org" }
+        ]
     end
 
-    describe '#abstract' do
-      it 'returns abstract of an article' do
+    describe "#abstract" do
+      it "returns abstract of an article" do
         expect(eml.abstract).
-          to eq 'These are all the names in the Leptogastrinae classification.'
+          to eq "These are all the names in the Leptogastrinae classification."
       end
     end
 
-    describe '#citation' do
-      it 'returns citation of the archive' do
+    describe "#citation" do
+      it "returns citation of the archive" do
         expect(eml.citation).
-          to eq 'Dikow, Torsten. 2010. The Leptogastrinae classification.'
+          to eq "Dikow, Torsten. 2010. The Leptogastrinae classification."
       end
     end
 
-    describe '#url' do
-      it 'returns url to the archive' do
-        expect(eml.url).to eq 'http://leptogastrinae.lifedesks.org'\
-                              '/files/leptogastrinae/'\
-                              'classification_export/shared/'\
-                              'leptogastrinae.tar.gz'
+    describe "#url" do
+      it "returns url to the archive" do
+        expect(eml.url).
+          to eq "http://leptogastrinae.lifedesks.org/files/leptogastrinae/"\
+                "classification_export/shared/leptogastrinae.tar.gz"
       end
     end
-
   end
 end
-

data/spec/lib/taxon_normalized_spec.rb

@@ -1,99 +1,97 @@
-require_relative '../spec_helper'
-# encoding: utf-8
+# frozen_string_literal: true
 
 describe DarwinCore::TaxonNormalized do
   subject(:dwca) { DarwinCore.new(file_path) }
   subject(:normalizer) { DarwinCore::ClassificationNormalizer.new(dwca) }
-  let(:file_dir) { File.expand_path('../../files', __FILE__) }
+  let(:file_dir) { File.expand_path("../files", __dir__) }
 
-  context 'typical case' do
-    let(:file_path) { File.join(file_dir, 'data.tar.gz') }
+  context "typical case" do
+    let(:file_path) { File.join(file_dir, "data.tar.gz") }
     let(:normalized) { normalizer.normalize }
-    let(:tn) { normalized['leptogastrinae:tid:2681'] }
+    let(:tn) { normalized["leptogastrinae:tid:2681"] }
 
-    it 'has TaxonNormalized type' do
+    it "has TaxonNormalized type" do
       expect(tn).to be_kind_of DarwinCore::TaxonNormalized
     end
 
-    describe '#id' do
-      it 'returns taxon_id' do
-        expect(tn.id).to eq 'leptogastrinae:tid:2681'
+    describe "#id" do
+      it "returns taxon_id" do
+        expect(tn.id).to eq "leptogastrinae:tid:2681"
       end
     end
 
-    describe '#local_id' do
-      it 'returns local id' do
-        expect(tn.id).to eq 'leptogastrinae:tid:2681'
+    describe "#local_id" do
+      it "returns local id" do
+        expect(tn.id).to eq "leptogastrinae:tid:2681"
       end
     end
 
-    describe '#global_id' do
-      it 'returns global id' do
-        expect(tn.global_id).to eq '843ff0df-4bcd-4aad-ba94-643f8695a292'
+    describe "#global_id" do
+      it "returns global id" do
+        expect(tn.global_id).to eq "843ff0df-4bcd-4aad-ba94-643f8695a292"
       end
     end
 
-    describe '#source' do
-      it 'returns url to the data' do
+    describe "#source" do
+      it "returns url to the data" do
         expect(tn.source).
-          to eq 'http://leptogastrinae.lifedesks.org/pages/2681'
+          to eq "http://leptogastrinae.lifedesks.org/pages/2681"
       end
-    end 
+    end
 
-    describe '#parent_id' do
-      it 'returns ancestor\'s id' do
-        expect(tn.parent_id).to eq 'leptogastrinae:tid:2584'
+    describe "#parent_id" do
+      it "returns ancestor's id" do
+        expect(tn.parent_id).to eq "leptogastrinae:tid:2584"
       end
     end
-      
-    describe '#classification_path_id' do
-      it 'returns an array' do
+
+    describe "#classification_path_id" do
+      it "returns an array" do
         expect(tn.classification_path_id).to be_kind_of Array
       end
 
-      it 'returns ids of classification path elements' do
+      it "returns ids of classification path elements" do
         expect(tn.classification_path_id).
-          to eq ['leptogastrinae:tid:42', 
-                 'leptogastrinae:tid:2045', 
-                 'leptogastrinae:tid:2584', 
-                 'leptogastrinae:tid:2681']
+          to eq ["leptogastrinae:tid:42",
+                 "leptogastrinae:tid:2045",
+                 "leptogastrinae:tid:2584",
+                 "leptogastrinae:tid:2681"]
       end
     end
 
-    describe '#classification_path' do
+    describe "#classification_path" do
       let(:cp) { tn.classification_path }
-      it 'returns array of name strings of the classification path' do
+      it "returns array of name strings of the classification path" do
         expect(cp).to be_kind_of Array
-        expect(cp).to eq ["Leptogastrinae", 
-                          "Leptogastrini", 
-                          "Leptogaster", 
-                          "Leptogaster flavipes"] 
+        expect(cp).to eq ["Leptogastrinae",
+                          "Leptogastrini",
+                          "Leptogaster",
+                          "Leptogaster flavipes"]
       end
     end
 
-    describe '#linnean_classification_path' do
-      it 'returns empty array for parent/child based classification' do
+    describe "#linnean_classification_path" do
+      it "returns empty array for parent/child based classification" do
         expect(tn.linnean_classification_path).to be_kind_of Array
         expect(tn.linnean_classification_path).to be_empty
       end
     end
 
-    describe '#current_name' do
-      it 'returns name marked as currently valid for the taxon' do
-        expect(tn.current_name).to eq 'Leptogaster flavipes Loew, 1862'
+    describe "#current_name" do
+      it "returns name marked as currently valid for the taxon" do
+        expect(tn.current_name).to eq "Leptogaster flavipes Loew, 1862"
       end
     end
-    
-    describe '#current_name_canonical' do
-      it 'returns canonical form of valid name' do
-        expect(tn.current_name_canonical).to eq 'Leptogaster flavipes'
+
+    describe "#current_name_canonical" do
+      it "returns canonical form of valid name" do
+        expect(tn.current_name_canonical).to eq "Leptogaster flavipes"
       end
     end
 
-    describe '#synonyms' do
-      context 'synonyms not found' do 
-
-        it 'returns empty array' do
+    describe "#synonyms" do
+      context "synonyms not found" do
+        it "returns empty array" do
           expect(tn.synonyms).to be_kind_of Array
           synonym = tn.synonyms[0]
           expect(synonym).to be_kind_of DarwinCore::SynonymNormalized
@@ -101,26 +99,26 @@ describe DarwinCore::TaxonNormalized do
         end
       end
 
-      context 'synonyms found' do
-        let(:tn) { normalized['leptogastrinae:tid:2858'] }
-        it 'returns array of synonyms' do
+      context "synonyms found" do
+        let(:tn) { normalized["leptogastrinae:tid:2858"] }
+        it "returns array of synonyms" do
           expect(tn.synonyms).to be_kind_of Array
           expect(tn.synonyms).to be_empty
         end
       end
     end
 
-    describe '#vernacular_names' do
-      context 'vernacular names not found' do
-        it 'returns empty array' do
+    describe "#vernacular_names" do
+      context "vernacular names not found" do
+        it "returns empty array" do
           expect(tn.vernacular_names).to be_kind_of Array
           expect(tn.vernacular_names).to be_empty
         end
       end
 
-      context 'vernacular names found' do
-        let(:tn) { normalized['leptogastrinae:tid:42'] }
-        it 'returns array with vernacular name structure' do
+      context "vernacular names found" do
+        let(:tn) { normalized["leptogastrinae:tid:42"] }
+        it "returns array with vernacular name structure" do
           expect(tn.vernacular_names).to be_kind_of Array
           vn = tn.vernacular_names[0]
           expect(vn).to be_kind_of DarwinCore::VernacularNormalized
@@ -129,17 +127,16 @@ describe DarwinCore::TaxonNormalized do
       end
     end
 
-    describe '#rank' do
-      it 'returns rank of the taxon' do
-        expect(tn.rank).to eq 'species'
+    describe "#rank" do
+      it "returns rank of the taxon" do
+        expect(tn.rank).to eq "species"
       end
     end
 
-    describe '#status' do
-      it 'returns status of taxon' do
+    describe "#status" do
+      it "returns status of taxon" do
         expect(tn.status).to be_nil
       end
     end
   end
-
 end