puree 1.9.1 → 2.0.0

data/lib/puree/xml_extractor/research_output.rb

@@ -0,0 +1,189 @@
+module Puree
+
+  module XMLExtractor
+
+    # Research output XML extractor.
+    #
+    class ResearchOutput < Puree::XMLExtractor::Resource
+      include Puree::XMLExtractor::AbstractMixin
+      include Puree::XMLExtractor::KeywordMixin
+      include Puree::XMLExtractor::OrganisationalUnitMixin
+      include Puree::XMLExtractor::OwnerMixin
+      include Puree::XMLExtractor::PersonMixin
+      include Puree::XMLExtractor::ResearchOutputMixin
+      include Puree::XMLExtractor::WorkflowMixin
+      include Puree::XMLExtractor::TitleMixin
+      include Puree::XMLExtractor::TypeMixin
+
+      def initialize(xml)
+        super
+        setup_model :research_output
+      end
+
+      # @return [String, nil]
+      def bibliographical_note
+        xpath_query_for_single_value('/bibliographicalNote')
+      end
+
+      # @return [String, nil]
+      def category
+        xpath_query_for_single_value '/category'
+      end
+
+      # Digital Object Identifier
+      # @return [String, nil]
+      def doi
+        xpath_query_for_single_value '/electronicVersions/electronicVersion[@type="wsElectronicVersionDoiAssociation"]/doi'
+      end
+
+      # @return [Array<Puree::Model::File>]
+      def files
+        xpath_result = xpath_query '/electronicVersions/electronicVersion[@type="wsElectronicVersionFileAssociation"]'
+        docs = []
+        xpath_result.each do |d|
+          model = Puree::Model::File.new
+          model.name = d.xpath('file/fileName').text.strip
+          model.mime = d.xpath('file/mimeType').text.strip
+          model.size = d.xpath('file/size').text.strip.to_i
+          model.url = d.xpath('file/URL').text.strip
+          # document_license = d.xpath('licenseType')
+          # if !document_license.empty?
+          #   license = Puree::Model::CopyrightLicense.new
+          #   license.name = document_license.xpath('term/localizedString').text.strip
+          #   license.url = document_license.xpath('description/localizedString').text.strip
+          #   model.license = license if license.data?
+          # end
+          docs << model
+        end
+        docs.uniq { |d| d.url }
+      end
+
+      # @return [Array<String>]
+      def keywords
+        keyword_group 'keywordContainers'
+      end
+
+      # @return [String, nil]
+      def language
+        xpath_query_for_single_value '/language'
+      end
+
+      # @return [Array<String>, nil]
+      def links
+        xpath_query_for_multi_value '/electronicVersions/electronicVersion[@type="wsElectronicVersionLinkAssociation"]/link'
+      end
+
+      # @return [String, nil]
+      def open_access_permission
+        xpath_query_for_single_value '/openAccessPermission'
+      end
+
+      # @return [Array<Puree::Model::EndeavourPerson>]
+      def persons_internal
+        persons 'internal', '/personAssociations/personAssociation'
+      end
+
+      # @return [Array<Puree::Model::EndeavourPerson>]
+      def persons_external
+        persons 'external', '/personAssociations/personAssociation'
+      end
+
+      # @return [Array<Puree::Model::EndeavourPerson>]
+      def persons_other
+        persons 'other', '/personAssociations/personAssociation'
+      end
+
+      # @return [Array<Puree::Model::PublicationStatus>]
+      def publication_statuses
+        xpath_result = xpath_query '/publicationStatuses/publicationStatus'
+        data = []
+        xpath_result.each do |i|
+          s = Puree::Model::PublicationStatus.new
+          s.stage = i.xpath('publicationStatus').text.strip
+
+          ymd = {}
+          ymd['year'] = i.xpath('publicationDate/year').text.strip
+          ymd['month'] = i.xpath('publicationDate/month').text.strip
+          ymd['day'] = i.xpath('publicationDate/day').text.strip
+
+          s.date = Puree::Util::Date.hash_to_time ymd
+
+          data << s
+        end
+        data.uniq { |d| d.stage }
+      end
+
+      # @return [Fixnum, nil]
+      def scopus_citations_count
+        xpath_result = xpath_query_for_single_value '/totalScopusCitations'
+        xpath_result ? xpath_result.to_i : nil
+      end
+
+      # @return [Array<Puree::Model::ResearchOutputScopusMetric>]
+      def scopus_metrics
+        xpath_result = xpath_query '/scopusMetrics/scopusMetric'
+        data = []
+        xpath_result.each do |i|
+          s = Puree::Model::ResearchOutputScopusMetric.new
+          s.value = i.xpath('value').text.strip
+          s.year = i.xpath('year').text.strip
+          data << s
+        end
+        data
+      end
+
+      # @return [String, nil]
+      def subtitle
+        xpath_query_for_single_value '/subTitle'
+      end
+
+      # @return [String, nil]
+      def translated_subtitle
+        xpath_query_for_single_value '/translatedSubTitle'
+      end
+
+      # @return [String, nil]
+      def translated_title
+        xpath_query_for_single_value '/translatedTitle'
+      end
+
+      private
+
+      def xpath_root
+        '/*'
+      end
+
+      def combine_metadata
+        super
+        @model.bibliographical_note = bibliographical_note
+        @model.category = category
+        @model.description = description
+        @model.doi = doi
+        @model.files = files
+        @model.keywords = keywords
+        @model.language = language
+        @model.links = links
+        @model.open_access_permission = open_access_permission
+        @model.organisations = organisational_units
+        @model.owner = owner
+        @model.persons_internal = persons_internal
+        @model.persons_external = persons_external
+        @model.persons_other = persons_other
+        @model.publication_statuses = publication_statuses
+        @model.research_outputs = research_outputs
+        @model.scopus_citations_count = scopus_citations_count
+        @model.scopus_metrics = scopus_metrics
+        @model.subtitle = subtitle
+        @model.title = title
+        @model.translated_subtitle = translated_subtitle
+        @model.translated_title = translated_title
+        @model.type = type
+        @model.workflow = workflow
+        @model
+      end
+
+    end
+
+  end
+
+end

data/lib/puree/xml_extractor/resource.rb

@@ -6,34 +6,33 @@ module Puree
     #
     class Resource < Puree::XMLExtractor::Base
 
-      def initialize(xml:)
+      def initialize(xml)
         super
       end
 
-      # content based
-      def xpath_query(path)
-        path_from_root = service_xpath path
-        @doc.xpath path_from_root
+      # @return [Puree::Model::Resource subclass]
+      def model
+        combine_metadata
       end
 
-      # Is there any data after get? For a response that provides a count of the results.
-      # @return [Boolean]
-      def get_data?
-        path = service_xpath_count
-        xpath_result = @doc.xpath path
-        xpath_result.text.strip === '1' ? true : false
+      # @return [String, nil]
+      def created_by
+        xpath_query_for_single_value('/info/createdBy')
       end
 
       # @return [Time, nil]
-      def created
-        xpath_result = xpath_query_for_single_value('/created')
-        Time.parse xpath_result if xpath_result
+      def created_at
+        Time.parse xpath_query_for_single_value('/info/createdDate')
+      end
+
+      # @return [String, nil]
+      def modified_by
+        xpath_query_for_single_value('/info/modifiedBy')
       end
 
       # @return [Time, nil]
-      def modified
-        xpath_result = xpath_query_for_single_value('/modified')
-        Time.parse xpath_result if xpath_result
+      def modified_at
+        Time.parse xpath_query_for_single_value('/info/modifiedDate')
       end
 
       # @return [String, nil]
@@ -41,29 +40,22 @@ module Puree
         xpath_query_for_single_value '/@uuid'
       end
 
-      # Locale (e.g. en-GB)
-      # @return [String, nil]
-      def locale
-        str = xpath_query_for_single_value '/@locale'
-        str.tr('_','-') if str
-      end
-
       private
 
-      def service_response_name
-        @api_map[:resource_type][@resource_type][:response]
-      end
-
-      def service_xpath_base
-        service_response_name + '/result/content'
-      end
-
-      def service_xpath_count
-        service_response_name + '/count'
+      def xpath_query(path)
+        path_from_root = File.join xpath_root, path
+        @doc.xpath path_from_root
       end
 
-      def service_xpath(str_to_find)
-        service_xpath_base + str_to_find
+      # All metadata
+      # @return [Hash]
+      def combine_metadata
+        raise 'No model to populate' if !@model
+        @model.uuid = uuid
+        @model.created_by = created_by
+        @model.created_at = created_at
+        @model.modified_by = modified_by
+        @model.modified_at = modified_at
       end
 
     end

data/lib/puree/xml_extractor/shared.rb

@@ -11,32 +11,35 @@ module Puree
         h = Puree::Model::ExternalOrganisationHeader.new
         h.uuid = nokogiri_xml_element.xpath('@uuid').text.strip
         h.name = nokogiri_xml_element.xpath('name').text.strip
-        h
+        h.type = nokogiri_xml_element.xpath('type').text.strip
+        h.data? ? h : nil
       end
 
       # @return [Array<Puree::Model::ExternalOrganisationHeader>]
       def self.external_organisation_multi_header(nokogiri_xml_nodeset)
         data = []
         nokogiri_xml_nodeset.each do |i|
-          data << external_organisation_header(i)
+          header =  external_organisation_header(i)
+          data << header if header
         end
         data.uniq { |d| d.uuid }
       end
 
-      # @return [Puree::Model::OrganisationHeader]
+      # @return [Puree::Model::OrganisationalUnitHeader]
       def self.organisation_header(nokogiri_xml_element)
-        h = Puree::Model::OrganisationHeader.new
+        h = Puree::Model::OrganisationalUnitHeader.new
         h.uuid = nokogiri_xml_element.xpath('@uuid').text.strip
-        h.name = nokogiri_xml_element.xpath('name/localizedString').text.strip
-        h.type = nokogiri_xml_element.xpath('typeClassification/term/localizedString').text.strip
-        h
+        h.name = nokogiri_xml_element.xpath('name').text.strip
+        h.type = nokogiri_xml_element.xpath('type').text.strip
+        h.data? ? h : nil
       end
 
-      # @return [Array<Puree::Model::OrganisationHeader>]
+      # @return [Array<Puree::Model::OrganisationalUnitHeader>]
       def self.organisation_multi_header(nokogiri_xml_nodeset)
         data = []
         nokogiri_xml_nodeset.each do |i|
-          data << organisation_header(i)
+          header = organisation_header(i)
+          data << header if header
         end
         data.uniq { |d| d.uuid }
       end

data/lib/puree/xml_extractor/thesis.rb

@@ -3,42 +3,56 @@ module Puree
 
     # Thesis XML extractor.
     #
-    class Thesis < Puree::XMLExtractor::Publication
+    class Thesis < Puree::XMLExtractor::ResearchOutput
       include Puree::XMLExtractor::DoiMixin
       include Puree::XMLExtractor::PagesMixin
+      include Puree::XMLExtractor::PublisherMixin
 
-      def initialize(xml:)
+      def initialize(xml)
         super
+        setup_model :thesis
       end
 
       # @return [Time, nil]
       def award_date
-        xpath_result = xpath_query_for_single_value('/awardDate')
+        xpath_result = xpath_query_for_single_value('/awardedDate')
         Time.parse xpath_result if xpath_result
       end
 
-      # @return [Puree::Model::OrganisationHeader, nil]
+      # @return [Puree::Model::ExternalOrganisationHeader, nil]
       def awarding_institution
-        xpath_result = xpath_query '/awardingInstitution/internalExternalOrganisationAssociation/organisation'
-        Puree::XMLExtractor::Shared.organisation_header xpath_result
+        xpath_result = xpath_query '/awardingInstitutions/awardingInstitution/externalOrganisationalUnit'
+        Puree::XMLExtractor::Shared.external_organisation_header xpath_result if xpath_result
       end
 
       # @return [String, nil]
       def qualification
-        types = {
-            '/dk/atira/pure/thesis/qualification/mphil' => 'MPhil',
-            '/dk/atira/pure/thesis/qualification/phd' => 'PhD',
-            '/dk/atira/pure/thesis/qualification/masters_by_research' => 'Masters by Research'
-        }
-        xpath_result = xpath_query_for_single_value '/qualification/uri'
-        types[xpath_result]
+        xpath_query_for_single_value '/qualification'
       end
 
-      # @return [Array<String>]
+      # @return [Array<Puree::Model::ExternalOrganisationHeader>]
       def sponsors
-        xpath_query_for_multi_value '/sponsors/externalOrganisation/name'
+        xpath_result = xpath_query '/sponsors/sponsor'
+        Puree::XMLExtractor::Shared.external_organisation_multi_header xpath_result if xpath_result
       end
 
+      private
+
+      def xpath_root
+        '/thesis'
+      end
+
+      def combine_metadata
+        super
+        @model.award_date = award_date
+        @model.awarding_institution = awarding_institution
+        @model.doi = doi
+        @model.pages = pages
+        @model.publisher = publisher
+        @model.qualification = qualification
+        @model.sponsors = sponsors
+        @model      
+      end
     end
   end
 end

data/lib/puree/xml_extractor/xml_extractor.rb

@@ -1,3 +1,46 @@
+require 'nokogiri'
+
+require 'puree/xml_extractor/mixins/abstract_mixin'
+require 'puree/xml_extractor/mixins/description_mixin'
+require 'puree/xml_extractor/mixins/doi_mixin'
+require 'puree/xml_extractor/mixins/event_mixin'
+require 'puree/xml_extractor/mixins/external_organisation_mixin'
+require 'puree/xml_extractor/mixins/identifier_mixin'
+require 'puree/xml_extractor/mixins/keyword_mixin'
+require 'puree/xml_extractor/mixins/organisational_unit_mixin'
+require 'puree/xml_extractor/mixins/owner_mixin'
+require 'puree/xml_extractor/mixins/pages_mixin'
+require 'puree/xml_extractor/mixins/person_mixin'
+require 'puree/xml_extractor/mixins/page_range_mixin'
+require 'puree/xml_extractor/mixins/peer_reviewed_mixin'
+require 'puree/xml_extractor/mixins/publisher_mixin'
+require 'puree/xml_extractor/mixins/research_output_mixin'
+require 'puree/xml_extractor/mixins/workflow_mixin'
+require 'puree/xml_extractor/mixins/title_mixin'
+require 'puree/xml_extractor/mixins/type_mixin'
+
+require 'puree/xml_extractor/shared'
+require 'puree/xml_extractor/base'
+require 'puree/xml_extractor/resource'
+require 'puree/xml_extractor/dataset'
+require 'puree/xml_extractor/event'
+require 'puree/xml_extractor/external_organisation'
+require 'puree/xml_extractor/journal'
+require 'puree/xml_extractor/organisational_unit'
+require 'puree/xml_extractor/person'
+require 'puree/xml_extractor/project'
+require 'puree/xml_extractor/publisher'
+
+require 'puree/xml_extractor/research_output'
+require 'puree/xml_extractor/thesis'
+require 'puree/xml_extractor/doctoral_thesis'
+require 'puree/xml_extractor/masters_thesis'
+require 'puree/xml_extractor/journal_article'
+require 'puree/xml_extractor/paper'
+require 'puree/xml_extractor/conference_paper'
+
+require 'puree/xml_extractor/collection'
+
 module Puree
 
   # An XMLExtractor manages the extraction of metadata from XML into Ruby

data/lib/puree.rb

@@ -1,119 +1,10 @@
-require 'http'
-require 'nokogiri'
-
+require 'puree/extractor/extractor'
+require 'puree/model/model'
+require 'puree/rest/rest'
+require 'puree/util/util'
+require 'puree/xml_extractor/xml_extractor'
 require 'puree/version'
 
-require 'puree/util/date'
-require 'puree/util/string'
-
-require 'puree/xml_extractor/mixins/associated_mixin'
-require 'puree/xml_extractor/mixins/doi_mixin'
-require 'puree/xml_extractor/mixins/event_mixin'
-require 'puree/xml_extractor/mixins/external_organisations_mixin'
-require 'puree/xml_extractor/mixins/pages_mixin'
-require 'puree/xml_extractor/mixins/page_range_mixin'
-require 'puree/xml_extractor/mixins/peer_reviewed_mixin'
-require 'puree/xml_extractor/mixins/workflow_state_mixin'
-
-require 'puree/xml_extractor/shared'
-require 'puree/xml_extractor/base'
-require 'puree/xml_extractor/collection'
-require 'puree/xml_extractor/resource'
-require 'puree/xml_extractor/dataset'
-require 'puree/xml_extractor/download'
-require 'puree/xml_extractor/event'
-require 'puree/xml_extractor/journal'
-require 'puree/xml_extractor/organisation'
-require 'puree/xml_extractor/external_organisation'
-require 'puree/xml_extractor/person'
-require 'puree/xml_extractor/project'
-
-require 'puree/xml_extractor/publication'
-require 'puree/xml_extractor/thesis'
-require 'puree/xml_extractor/doctoral_thesis'
-require 'puree/xml_extractor/masters_thesis'
-require 'puree/xml_extractor/journal_article'
-require 'puree/xml_extractor/paper_base'
-require 'puree/xml_extractor/conference_paper'
-require 'puree/xml_extractor/paper'
-
-require 'puree/xml_extractor/publisher'
-require 'puree/xml_extractor/server'
-
-require 'puree/api/map'
-require 'puree/api/request'
-require 'puree/api/person_request'
-require 'puree/api/configuration'
-require 'puree/api/authentication'
-
-require 'puree/model/helper/validation'
-require 'puree/model/structure'
-
-require 'puree/model/resource'
-require 'puree/model/dataset'
-require 'puree/model/download_header'
-require 'puree/model/event'
-require 'puree/model/event_header'
-require 'puree/model/external_organisation'
-require 'puree/model/journal'
-require 'puree/model/journal_header'
-require 'puree/model/link'
-require 'puree/model/organisation'
-require 'puree/model/person'
-require 'puree/model/project'
-
-require 'puree/model/publication'
-require 'puree/model/thesis'
-require 'puree/model/doctoral_thesis'
-require 'puree/model/masters_thesis'
-require 'puree/model/journal_article'
-require 'puree/model/paper_base'
-require 'puree/model/conference_paper'
-require 'puree/model/paper'
-
-require 'puree/model/publisher'
-require 'puree/model/related_content_header'
-require 'puree/model/spatial_point'
-
-require 'puree/model/address'
-require 'puree/model/copyright_license'
-require 'puree/model/event_header'
-require 'puree/model/external_organisation_header'
-require 'puree/model/file'
-require 'puree/model/legal_condition'
-require 'puree/model/organisation_header'
-require 'puree/model/endeavour_person'
-require 'puree/model/person_name'
-require 'puree/model/publication_status'
-require 'puree/model/server'
-require 'puree/model/temporal_range'
-
-require 'puree/extractor/resource'
-require 'puree/extractor/dataset'
-require 'puree/extractor/event'
-require 'puree/extractor/external_organisation'
-require 'puree/extractor/journal'
-require 'puree/extractor/organisation'
-require 'puree/extractor/person'
-require 'puree/extractor/project'
-
-require 'puree/extractor/publication'
-require 'puree/extractor/thesis'
-require 'puree/extractor/doctoral_thesis'
-require 'puree/extractor/masters_thesis'
-require 'puree/extractor/journal_article'
-require 'puree/extractor/paper_base'
-require 'puree/extractor/conference_paper'
-require 'puree/extractor/paper'
-
-require 'puree/extractor/publisher'
-require 'puree/extractor/collection'
-require 'puree/extractor/download'
-require 'puree/extractor/server'
-
-require 'puree/query/funding'
-require 'puree/query/person'
-
 # Metadata extraction from the Pure Research Information System.
 #
 module Puree

data/puree.gemspec

@@ -21,5 +21,5 @@ Gem::Specification.new do |spec|
   spec.add_runtime_dependency 'http', '~> 2.0'
   spec.add_runtime_dependency 'nokogiri', '~> 1.6'
 
-  spec.add_development_dependency 'rspec'
+  spec.add_development_dependency 'minitest-reporters', '~> 1.1'
 end

data/test/extractor/resource_test.rb

@@ -0,0 +1,103 @@
+require 'test_helper'
+
+class TestResourceFind < Minitest::Test
+
+  def test_conference_paper
+    # A Negative Effect of Evaluation Upon Analogical Problem Solving
+    id = '96e1495e-70a2-4529-9721-33b2cb62df8d'
+    extractor = Puree::Extractor::ConferencePaper.new config
+    model = extractor.find id
+
+    assert_instance_of Puree::Model::ConferencePaper, model
+  end
+
+  def test_dataset
+    # The 2014 Ebola virus disease outbreak in West Africa
+    id = 'b050f4b5-e272-4914-8cac-3bdc1e673c58'
+    extractor = Puree::Extractor::Dataset.new config
+    model = extractor.find id
+
+    assert_instance_of Puree::Model::Dataset, model
+  end
+
+  def test_event
+    # 31st Annual European Meeting on Atmospheric Studies by Optical Methods and 1st International Riometer Workshop
+    id = 'cd2bf302-4629-4f71-9c02-2dfe50a384bf'
+    extractor = Puree::Extractor::Event.new config
+    model = extractor.find id
+
+    assert_instance_of Puree::Model::Event, model
+  end
+
+  def test_external_organisation
+    # STFC
+    id = '2ea6bbc4-c957-4a07-a1e7-604a2d944c20'
+    extractor = Puree::Extractor::ExternalOrganisation.new config
+    model = extractor.find id
+
+    assert_instance_of Puree::Model::ExternalOrganisation, model
+  end
+
+  def test_journal
+    # Chemical Geology
+    id = '95e40a10-1799-4e74-9a70-8b03f27d9acb'
+    extractor = Puree::Extractor::Journal.new config
+    model = extractor.find id
+
+    assert_instance_of Puree::Model::Journal, model
+  end
+
+  def test_journal_article
+    # A theoretical framework for estimation of AUCs in complete and incomplete sampling designs
+    id = 'a7c104d0-e243-463e-a2a4-b4e07bcfde3f'
+    extractor = Puree::Extractor::JournalArticle.new config
+    model = extractor.find id
+
+    assert_instance_of Puree::Model::JournalArticle, model
+  end
+
+  def test_organisation
+    # Faculty of Health and Medicine
+    id = '8a58c4ad-2d5a-463a-841a-38839ff73a63'
+    extractor = Puree::Extractor::OrganisationalUnit.new config
+    model = extractor.find id
+
+    assert_instance_of Puree::Model::OrganisationalUnit, model
+  end
+
+  def test_person
+    # Peter Diggle
+    id = '811d7fc3-047a-40d2-89e6-c85d14a97fb8'
+    extractor = Puree::Extractor::Person.new config
+    model = extractor.find id
+
+    assert_instance_of Puree::Model::Person, model
+  end
+
+  def test_project
+    # The Channel Scheme - Preston
+    id = '2af1fb5c-ac04-40f3-9cb4-073fb92fcf96'
+    extractor = Puree::Extractor::Project.new config
+    model = extractor.find id
+
+    assert_instance_of Puree::Model::Project, model
+  end
+
+  def test_research_output
+    # A theoretical framework for estimation of AUCs in complete and incomplete sampling designs
+    id = 'a7c104d0-e243-463e-a2a4-b4e07bcfde3f'
+    extractor = Puree::Extractor::ResearchOutput.new config
+    model = extractor.find id
+
+    assert_instance_of Puree::Model::ResearchOutput, model
+  end
+
+  def test_thesis
+    # Multimodalita e 'city branding'
+    id = '376173c0-fd7a-4d63-93d3-3f2e58e8dc01'
+    extractor = Puree::Extractor::Thesis.new config
+    model = extractor.find id
+
+    assert_instance_of Puree::Model::Thesis, model
+  end
+end