puree 1.5.0 → 1.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 647da98cd2670d75fc42262e0065907dae349f5a
-  data.tar.gz: 4de66341673526e53c8130c0324beb99fa71d342
+  metadata.gz: a5f9f37e95e788189e6f4acb7a066e5732e157e8
+  data.tar.gz: b1f37ec7f78e5adef5d0443f565b5526bc2f85c9
 SHA512:
-  metadata.gz: 741a1e488e1d1f829d02dee741776e656446eda31a3da6df90fbca3bf27f98ad46ba05d0ee7c59642d1d614705558133cbb0e241379470392ff36f7c4b4ddfbf
-  data.tar.gz: 49420c09bf3040c81ac7b1d3bb436fde06be860cb4b4300beca00510733106b8824fb8a938bc2f76e8b55020e139ac16d06c7be72b3149eb713b090e50260426
+  metadata.gz: 7356834acf18066281420d8794360b747828f684fe7a709f22b01a38f4cc2c67768a66aa7f72f4b3b7c7b227014115a8eae66d22e1f77221e892b5ecfc56b33d
+  data.tar.gz: 499e3b30bedd4b2d08c957f041fd070488a63af104f5bcc06689f3df2a0086e6b290d35c2e39370c9c43aafbe5785f43439e6eacaf6aa2aabfea2e92de803560

data/CHANGELOG.md

@@ -5,6 +5,13 @@ This project adheres to [Semantic Versioning](http://semver.org/).
 ## Unreleased
 - Metadata: activity?, clipping?, externalPerson?
 
+## 1.6.0 - 2017-10-24
+### Added
+- ExternalOrganisation.
+- Person - employee_id.
+- Query - Person - publication_count, publications.
+- Query - Funding - project_funders, publication_funders.
+
 ## 1.5.0 - 2017-10-03
 ### Added
 - Dataset, Publication - workflow_state.

data/README.md

@@ -1,4 +1,4 @@
-# Purée
+     # Purée
 
 Metadata extraction from the Pure Research Information System.
 
@@ -92,7 +92,7 @@ collection_extractor = Puree::Extractor::Collection.new config:   config,
 Fetch a bunch of resources.
 
 ```ruby
-dataset_collection = collection_extractor.find limit: 2
+collection_extractor.find limit: 2
 # =>
 #<Puree::Model::Dataset:0xa62fd90>
 #<Puree::Model::Dataset:0xa5e8c24>
@@ -101,7 +101,53 @@ dataset_collection = collection_extractor.find limit: 2
 Fetch a random resource from the entire collection.
 
 ```ruby
-random_dataset = collection_extractor.random_resource
+collection_extractor.random_resource
 # =>
 #<Puree::Model::Dataset:0x97998bc>
+```
+
+### Query
+
+Get answers to important questions.
+
+#### Funding
+
+Configure a funding query to retrieve data from a Pure host.
+
+```ruby
+funding_query = Puree::Query::Funding.new config
+```
+
+Who are the funders (if any) for a project?
+
+```ruby
+funding_query.project_funders uuid: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx'
+# =>
+#<Puree::Model::ExternalOrganisation:0x98986f0>
+```
+
+Who are the funders (if any) for a publication, via a project?
+
+```ruby
+funding_query.publication_funders uuid: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx'
+```
+
+#### Person
+
+Configure a person query to retrieve data from a Pure host.
+
+```ruby
+person_query = Puree::Query::Person.new config
+```
+
+Get at most ten publications published by a person during the first six months of 2017.
+
+```ruby
+person_query.publications uuid: 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx',
+                          limit: 10,
+                          published_start: '2017-01-01',
+                          published_end: '2017-06-30'
+# =>
+#<Puree::Model::Publication:0x9d2c004>
+#<Puree::Model::Publication:0xa285028>
 ```

data/lib/puree/api/map.rb

@@ -31,6 +31,10 @@ module Puree
             server: {
               service: 'servermeta',
               response: 'GetServerMetaResponse'
+            },
+            external_organisation: {
+              service: 'externalOrganisation',
+              response: 'GetExternalOrganisationResponse'
             }
           }
         }

data/lib/puree/extractor/collection.rb

@@ -86,7 +86,7 @@ module Puree
 
       def collect_resources
         data = []
-        resource_class = "Puree::Extractor::#{@resource_type.to_s.capitalize}"
+        resource_class = "Puree::Extractor::#{Puree::Util::String.titleize(@resource_type)}"
 
         # whitelist symbol
         if @api_map[:resource_type].has_key?(@resource_type)

data/lib/puree/extractor/external_organisation.rb

@@ -0,0 +1,28 @@
+module Puree
+
+  module Extractor
+
+    # External organisation extractor.
+    #
+    class ExternalOrganisation < Puree::Extractor::Resource
+
+      # @option (see Puree::Extractor::Resource#initialize)
+      def initialize(config)
+        super
+        setup :external_organisation
+      end
+
+      private
+
+      def combine_metadata
+        super
+        @model.name = @extractor.name
+        @model.type = @extractor.type
+        @model
+      end
+
+    end
+
+  end
+
+end

data/lib/puree/extractor/person.rb

@@ -18,6 +18,7 @@ module Puree
         super
         @model.affiliations = @extractor.affiliations
         @model.email_addresses = @extractor.email_addresses
+        @model.employee_id = @extractor.employee_id
         @model.image_urls = @extractor.image_urls
         @model.keywords = @extractor.keywords
         @model.name = @extractor.name

data/lib/puree/extractor/resource.rb

@@ -48,18 +48,18 @@ module Puree
       def setup(resource)
         @resource_type = resource
         if @model_type
-          resource_class = "Puree::Model::#{Puree::Util::String.titleize(@model_type.to_s)}"
+          resource_class = "Puree::Model::#{Puree::Util::String.titleize(@model_type)}"
         else
-          resource_class = "Puree::Model::#{resource.to_s.capitalize}"
+          resource_class = "Puree::Model::#{Puree::Util::String.titleize(resource)}"
         end
         @model = Object.const_get(resource_class).new
       end
 
       def make_xml_extractor xml
         if @model_type
-          resource_class = "Puree::XMLExtractor::#{Puree::Util::String.titleize(@model_type.to_s)}"
+          resource_class = "Puree::XMLExtractor::#{Puree::Util::String.titleize(@model_type)}"
         else
-          resource_class = "Puree::XMLExtractor::#{@resource_type.to_s.capitalize}"
+          resource_class = "Puree::XMLExtractor::#{Puree::Util::String.titleize(@resource_type)}"
         end
         @extractor = Object.const_get(resource_class).new xml: xml
       end

data/lib/puree/model/external_organisation.rb

@@ -0,0 +1,16 @@
+module Puree
+  module Model
+
+    # An external organisational unit as defined by the institution.
+    #
+    class ExternalOrganisation < Resource
+
+      # @return [String, nil]
+      attr_accessor :name
+
+      # @return [String, nil]
+      attr_accessor :type
+
+    end
+  end
+end

data/lib/puree/model/person.rb

@@ -11,6 +11,9 @@ module Puree
       # @return [Array<String>]
       attr_accessor :email_addresses
 
+      # @return [String, nil]
+      attr_accessor :employee_id
+
       # @return [Array<String>]
       attr_accessor :image_urls
 

data/lib/puree/query/funding.rb

@@ -0,0 +1,69 @@
+module Puree
+
+  module Query
+
+    # For querying information about funding.
+    #
+    class Funding
+
+      def initialize(config)
+        @config = config
+      end
+
+      # Project funders
+      # @param uuid [String] Project UUID.
+      # @return [Array<Puree::Model::ExternalOrganisation>] List of funders which have funded this project.
+      def project_funders(uuid:)
+        funders = []
+        project_extractor = Puree::Extractor::Project.new @config
+        project = project_extractor.find uuid: uuid
+        if project
+          if project.funded
+            project.external_organisations.each do |org|
+              external_organisation_extractor = Puree::Extractor::ExternalOrganisation.new @config
+              external_organisation = external_organisation_extractor.find uuid: org.uuid
+              funders << external_organisation if external_organisation.type == '/dk/atira/pure/ueoexternalorganisation/ueoexternalorganisationtypes/ueoexternalorganisation/researchFundingBody'
+            end
+          end
+        end
+        deduplicate_funders funders
+      end
+
+      # Publication funders
+      # @param uuid [String] Publication UUID.
+      # @return [Array<Puree::Model::ExternalOrganisation>] List of funders which have funded this publication via a project.
+      def publication_funders(uuid:)
+        funders = []
+        publication_extractor = Puree::Extractor::Publication.new @config
+        publication = publication_extractor.find uuid: uuid
+        if publication
+          publication.associated.each do |associated|
+            if associated.type == 'Research'
+              single_project_funders = project_funders uuid: associated.uuid
+              funders += single_project_funders
+            end
+          end
+        end
+        deduplicate_funders funders
+      end
+
+      private
+
+      def deduplicate_funders(funders)
+        uuids_in_list = []
+        funder_list = []
+        funders.each do |funder|
+          uuid = funder.uuid
+          unless uuids_in_list.include? uuid
+            funder_list << funder
+            uuids_in_list << uuid
+          end
+        end
+        funder_list
+      end
+
+    end
+
+  end
+
+end

data/lib/puree/query/person.rb

@@ -0,0 +1,121 @@
+module Puree
+
+  module Query
+
+    # For querying information about a person.
+    #
+    class Person
+
+      def initialize(config)
+        @url = config[:url]
+        @headers = {}
+        basic_auth username: config[:username],
+                   password: config[:password]
+        @config = config
+      end
+
+      # Count of publications available for a person.
+      #
+      # @param uuid [String] person UUID.
+      # @return [Fixnum]
+      def publication_count(uuid:)
+        params = {}
+        params['associatedPersonUuids.uuid'] = uuid
+        params['rendering'] = :system
+        params['window.size'] = 0
+        headers
+        response = @req.get(build_publication_url, params: params)
+        doc = make_doc response.body
+        extract_publication_count doc
+      end
+
+      # Publications for a person.
+      #
+      # @param uuid [String] person UUID.
+      # @param limit [Fixnum]
+      # @param offset [Fixnum]
+      # @param published_start [String] using format YYYY-MM-DD
+      # @param published_end [String] using format YYYY-MM-DD
+      # @return [Array<Puree::Model::Publication>]
+      def publications(uuid:, limit:, offset: 0, published_start: nil, published_end: nil)
+        uuids = publication_uuids(uuid: uuid,
+                                  limit: limit,
+                                  offset: offset,
+                                  published_start: published_start,
+                                  published_end: published_end)
+        publications = []
+        uuids.each do |uuid|
+          publication_extractor = Puree::Extractor::Publication.new @config
+          publication = publication_extractor.find uuid: uuid
+          publications << publication if publication
+        end
+        publications
+      end
+
+
+      private
+
+      def publication_uuids(uuid:, limit:, offset: 0, published_start: nil, published_end: nil)
+        params = {}
+        params['associatedPersonUuids.uuid'] = uuid
+        params['rendering'] = :system
+        params['window.size'] = limit.to_s
+        params['window.offset'] = offset if limit > 0
+        params['publicationDate.fromDate'] = published_start if published_start
+        params['publicationDate.toDate'] = published_end if published_end
+        headers
+        response = @req.get(build_publication_url, params: params)
+        doc = make_doc response.body
+        extract_publication_uuids doc
+      end
+
+      def make_doc(xml)
+        doc = Nokogiri::XML xml
+        doc.remove_namespaces!
+        doc
+      end
+
+      def extract_publication_count(doc)
+        doc.xpath('/GetPublicationResponse/count').text.strip.to_i
+      end
+
+      def extract_publication_uuids(doc)
+        records = doc.xpath('/GetPublicationResponse/result/renderedItem')
+        uuids = []
+        records.each do |record|
+          uuid = extract_publication_uuid record
+          uuids << uuid
+        end
+        uuids
+      end
+
+      def extract_publication_uuid(doc)
+        doc.xpath('@renderedContentUUID').text.strip
+      end
+
+      def build_publication_url
+        "#{@url}/publication.current"
+      end
+
+      # Provide credentials if necessary
+      #
+      # @param username [String]
+      # @param password [String]
+      def basic_auth(username:, password:)
+        auth = Base64::strict_encode64("#{username}:#{password}")
+        @headers['Authorization'] = 'Basic ' + auth
+      end
+
+      def headers
+        @headers['Accept'] = 'application/xml'
+        @req = HTTP.headers accept: @headers['Accept']
+        if @headers['Authorization']
+          @req = @req.auth @headers['Authorization']
+        end
+      end
+
+    end
+
+  end
+
+end

data/lib/puree/query/query.rb

@@ -0,0 +1,6 @@
+module Puree
+  # For pulling data together from several places to answer important questions.
+  #
+  module Query
+  end
+end

data/lib/puree/version.rb

@@ -1,5 +1,5 @@
 module Puree
   # Semantic version number
   #
-  VERSION = "1.5.0"
+  VERSION = "1.6.0"
 end

data/lib/puree/xml_extractor/external_organisation.rb

@@ -0,0 +1,28 @@
+module Puree
+
+  module XMLExtractor
+
+    # External organisation XML extractor.
+    #
+    class ExternalOrganisation < Puree::XMLExtractor::Resource
+
+      def initialize(xml:)
+        super
+        @resource_type = :external_organisation
+      end
+
+      # @return [String, nil]
+      def name
+        xpath_query_for_single_value '/name'
+      end
+
+      # @return [String, nil]
+      def type
+        xpath_query_for_single_value '/typeClassification/uri'
+      end
+
+    end
+
+  end
+
+end

data/lib/puree/xml_extractor/person.rb

@@ -22,6 +22,18 @@ module Puree
         xpath_query_for_multi_value '//emails/classificationDefinedStringFieldExtension/value'
       end
 
+      # @return [String, nil]
+      def employee_id
+        xpath_result = xpath_query '/sources/classificationDefinedStringFieldExtension'
+        if xpath_result
+          xpath_result.each do |i|
+            if i.xpath('classification/uri').text.strip === '/dk/atira/pure/person/personsources/employee'
+              return i.xpath('value').text.strip
+            end
+          end
+        end
+      end
+
       # @return [Array<String>]
       def image_urls
         xpath_query_for_multi_value '/photos/file/url'

data/lib/puree.rb

@@ -24,6 +24,7 @@ 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'
 
@@ -52,6 +53,7 @@ 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'
@@ -88,6 +90,7 @@ 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'
@@ -107,6 +110,9 @@ 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/spec/query/funding_http_spec.rb

@@ -0,0 +1,29 @@
+require 'spec_helper'
+
+describe 'Funding' do
+
+  it '#new' do
+    q = Puree::Query::Funding.new config
+    expect(q).to be_a Puree::Query::Funding
+  end
+
+  describe 'project data retrieval' do
+    before(:all) do
+      request :project
+      @project_uuid = @p.uuid
+      @q = Puree::Query::Funding.new config
+    end
+
+    it '#project_funders' do
+      funders = @q.project_funders uuid: @project_uuid
+      expect(funders).to all( be_a Puree::Model::ExternalOrganisation )
+    end
+
+    it '#publication_funders' do
+      funders = @q.publication_funders uuid: @project_uuid
+      expect(funders).to all( be_a Puree::Model::ExternalOrganisation )
+    end
+
+  end
+
+end

data/spec/query/person_http_spec.rb

@@ -0,0 +1,30 @@
+require 'spec_helper'
+
+describe 'Person' do
+
+  it '#new' do
+    q = Puree::Query::Person.new config
+    expect(q).to be_a Puree::Query::Person
+  end
+
+  before(:all) do
+    request :person
+    @person_uuid = @p.uuid
+    @q = Puree::Query::Person.new config
+  end
+
+  describe 'data retrieval' do
+    it '#publication_count' do
+      publication_count = @q.publication_count uuid: @person_uuid
+      expect(publication_count).to be_a Fixnum if publication_count
+    end
+
+    it '#publications' do
+      publications = @q.publications uuid: @person_uuid,
+                                     limit: 3
+      expect(publications).to all( be_a Puree::Model::Publication )
+    end
+
+  end
+
+end

data/spec/resource/person_http_spec.rb

@@ -27,6 +27,10 @@ describe 'Person' do
       expect(@p.email_addresses).to all( be_a String )
     end
 
+    it '#employee_id' do
+      expect(@p.employee_id).to be_a String if @p.employee_id
+    end
+
     it '#image_urls' do
       expect(@p.image_urls).to all( be_a String )
     end

data/spec/spec_helper.rb

@@ -24,6 +24,7 @@ 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'
 
@@ -52,6 +53,7 @@ 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'
@@ -88,6 +90,7 @@ 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'
@@ -107,6 +110,9 @@ require 'puree/extractor/collection'
 require 'puree/extractor/download'
 require 'puree/extractor/server'
 
+require 'puree/query/funding'
+require 'puree/query/person'
+
 def config
   {
     url:      ENV['PURE_URL'],

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: puree
 version: !ruby/object:Gem::Version
-  version: 1.5.0
+  version: 1.6.0
 platform: ruby
 authors:
 - Adrian Albin-Clark
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-10-03 00:00:00.000000000 Z
+date: 2017-10-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: http
@@ -77,6 +77,7 @@ files:
 - lib/puree/extractor/doctoral_thesis.rb
 - lib/puree/extractor/download.rb
 - lib/puree/extractor/event.rb
+- lib/puree/extractor/external_organisation.rb
 - lib/puree/extractor/extractor.rb
 - lib/puree/extractor/journal.rb
 - lib/puree/extractor/journal_article.rb
@@ -100,6 +101,7 @@ files:
 - lib/puree/model/endeavour_person.rb
 - lib/puree/model/event.rb
 - lib/puree/model/event_header.rb
+- lib/puree/model/external_organisation.rb
 - lib/puree/model/external_organisation_header.rb
 - lib/puree/model/file.rb
 - lib/puree/model/helper/validation.rb
@@ -127,6 +129,9 @@ files:
 - lib/puree/model/structure.rb
 - lib/puree/model/temporal_range.rb
 - lib/puree/model/thesis.rb
+- lib/puree/query/funding.rb
+- lib/puree/query/person.rb
+- lib/puree/query/query.rb
 - lib/puree/util/date.rb
 - lib/puree/util/string.rb
 - lib/puree/util/util.rb
@@ -138,6 +143,7 @@ files:
 - lib/puree/xml_extractor/doctoral_thesis.rb
 - lib/puree/xml_extractor/download.rb
 - lib/puree/xml_extractor/event.rb
+- lib/puree/xml_extractor/external_organisation.rb
 - lib/puree/xml_extractor/journal.rb
 - lib/puree/xml_extractor/journal_article.rb
 - lib/puree/xml_extractor/masters_thesis.rb
@@ -164,6 +170,8 @@ files:
 - puree.gemspec
 - spec/download_http_spec.rb
 - spec/open_api_dataset_http_spec.rb
+- spec/query/funding_http_spec.rb
+- spec/query/person_http_spec.rb
 - spec/resource/collection_all_http_spec.rb
 - spec/resource/collection_http_spec.rb
 - spec/resource/dataset_http_spec.rb
@@ -203,6 +211,8 @@ summary: Metadata extraction from the Pure Research Information System.
 test_files:
 - spec/download_http_spec.rb
 - spec/open_api_dataset_http_spec.rb
+- spec/query/funding_http_spec.rb
+- spec/query/person_http_spec.rb
 - spec/resource/collection_all_http_spec.rb
 - spec/resource/collection_http_spec.rb
 - spec/resource/dataset_http_spec.rb