puree 0.20.0 → 1.0.0

data/lib/puree/xml_extractor/publisher.rb

@@ -0,0 +1,28 @@
+module Puree
+
+  module XMLExtractor
+
+    # Publisher XML extractor.
+    #
+    class Publisher < Puree::XMLExtractor::Resource
+
+      def initialize(xml:)
+        super
+        @resource_type = :publisher
+      end
+
+      # @return [String, nil]
+      def name
+        xpath_query_for_single_value '/name'
+      end
+
+      # Adds no value as value is Publisher
+      # def type
+      #   xpath_query_for_single_value '/typeClassification/term/localizedString'
+      # end
+
+    end
+
+  end
+
+end

data/lib/puree/xml_extractor/resource.rb

@@ -0,0 +1,71 @@
+module Puree
+
+  module XMLExtractor
+
+    # Resource XML extractor.
+    #
+    class Resource < Puree::XMLExtractor::Base
+
+      def initialize(xml:)
+        super
+      end
+
+      # content based
+      def xpath_query(path)
+        path_from_root = service_xpath path
+        @doc.xpath path_from_root
+      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
+      end
+
+      # @return [Time, nil]
+      def created
+        Time.parse xpath_query_for_single_value('/created')
+      end
+
+      # @return [Time, nil]
+      def modified
+        Time.parse xpath_query_for_single_value('/modified')
+      end
+
+      # @return [String, nil]
+      def uuid
+        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'
+      end
+
+      def service_xpath(str_to_find)
+        service_xpath_base + str_to_find
+      end
+
+    end
+
+  end
+
+end

data/lib/puree/xml_extractor/server.rb

@@ -0,0 +1,32 @@
+module Puree
+
+  module XMLExtractor
+
+    # Server XML extractor.
+    #
+    class Server < Puree::XMLExtractor::Base
+
+      def initialize(xml:)
+        @resource_type = :server
+        super
+      end
+
+      # @return [String]
+      def version
+        path = "#{service_response_name}/baseVersion"
+        @doc.xpath(path).text.strip
+      end
+
+      # Is there any data after get?
+      #
+      # @return [Boolean]
+      def get_data?
+        # n.b. arbitrary element existence check
+        version.empty? ? false : true
+      end
+
+    end
+
+  end
+
+end

data/lib/puree/xml_extractor/shared.rb

@@ -0,0 +1,31 @@
+module Puree
+
+  module XMLExtractor
+
+    # Shared XML extractor.
+    #
+    module Shared
+
+      # @return [Puree::Model::OrganisationHeader]
+      def self.organisation_header(nokogiri_xml_element)
+        h = Puree::Model::OrganisationHeader.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
+      end
+
+      # @return [Array<Puree::Model::OrganisationHeader>]
+      def self.organisation_multi_header(nokogiri_xml_nodeset)
+        data = []
+        nokogiri_xml_nodeset.each do |i|
+          data << organisation_header(i)
+        end
+        data.uniq { |d| d.uuid }
+      end
+
+    end
+
+  end
+
+end

data/lib/puree/xml_extractor/xml_extractor.rb

@@ -0,0 +1,10 @@
+module Puree
+
+  # An XMLExtractor manages the extraction of metadata from XML into Ruby
+  # data structures.
+  #
+  module XMLExtractor
+
+  end
+
+end

data/puree.gemspec

@@ -4,21 +4,24 @@ $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 require 'puree/version'
 
 Gem::Specification.new do |spec|
-  spec.name          = "puree"
+  spec.name          = 'puree'
   spec.version       = Puree::VERSION
-  spec.authors       = ["Adrian Albin-Clark"]
-  spec.email         = ["a.albin-clark@lancaster.ac.uk"]
-  spec.summary       = %q{A client for the Pure Research Information System API.}
-  spec.description   = %q{Consumes the Pure Research Information System API and puts the metadata into simple data structures.}
-  spec.homepage      = "https://aalbinclark.gitbooks.io/puree"
-  spec.license       = "MIT"
+  spec.authors       = 'Adrian Albin-Clark'
+  spec.email         = 'a.albin-clark@lancaster.ac.uk'
+  spec.summary       = %q{Metadata extraction from the Pure Research Information System.}
+  spec.description   = %q{Fetches metadata from the Pure Research Information System and
+                          extracts it into Ruby data models.}
+  spec.homepage      = 'https://github.com/lulibrary/puree'
+  spec.license       = 'MIT'
   spec.files         = `git ls-files -z`.split("\x0")
   spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
   spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
-  spec.require_paths = ["lib"]
+  spec.require_paths = ['lib']
 
   spec.required_ruby_version = '~> 2.1'
 
   spec.add_runtime_dependency 'http', '~> 2.0'
   spec.add_runtime_dependency 'nokogiri', '~> 1.6'
+
+  spec.add_development_dependency 'rspec'
 end

data/spec/download_http_spec.rb

@@ -0,0 +1,31 @@
+require 'spec_helper'
+
+describe 'Download' do
+
+  before(:all) do
+
+  end
+
+  it '#new' do
+    p = Puree::Extractor::Download.new config
+    expect(p).to be_a Puree::Extractor::Download
+  end
+
+  describe 'data retrieval' do
+    before(:all) do
+      @p = Puree::Extractor::Download.new config
+      @metadata = @p.find resource: :dataset,
+                          limit:    10
+    end
+
+    it '#find' do
+      expect(@metadata).to all( be_a Puree::Model::DownloadHeader )
+    end
+
+    it '#find' do
+      expect(@metadata).not_to be_empty
+    end
+
+  end
+
+end

data/spec/open_api_dataset_http_spec.rb

@@ -0,0 +1,15 @@
+require 'spec_helper'
+
+describe 'Open API' do
+
+  describe 'dataset retrieval' do
+    before(:all) do
+      resource = :dataset
+      request_open resource
+    end
+
+    resource_header
+
+  end
+
+end

data/spec/resource/collection_all_http_spec.rb

@@ -0,0 +1,77 @@
+require 'spec_helper'
+
+def new
+  @p = Puree::Extractor::Collection.new resource: @resource_type,
+                                        config: config
+end
+
+def go resource_type
+  @resource_type = resource_type
+  new
+  fetch
+end
+
+def fetch
+  count = @p.count
+  (0..count-1).each do |i|
+    resource = @p.find limit: 1,
+                       offset: i
+    expect(resource[0]).to be_a resource_class
+    puts "#{i+1} of #{count} #{@resource_type}s"
+    sleep 1
+    system 'clear'
+  end
+end
+
+def resource_class
+  str = "Puree::Model::#{@resource_type.to_s.capitalize}"
+  Object.const_get(str)
+end
+
+describe 'dataset' do
+  it 'get all, one at a time' do
+    go :dataset
+  end
+end
+
+describe 'event' do
+  it 'get all, one at a time' do
+    go :event
+  end
+end
+
+describe 'journal' do
+  it 'get all, one at a time' do
+    go :journal
+  end
+end
+
+describe 'organisation' do
+  it 'get all, one at a time' do
+    go :organisation
+  end
+end
+
+describe 'person' do
+  it 'get all, one at a time' do
+    go :person
+  end
+end
+
+describe 'project' do
+  it 'get all, one at a time' do
+    go :project
+  end
+end
+
+describe 'publication' do
+  it 'get all, one at a time' do
+    go :publication
+  end
+end
+
+describe 'publisher' do
+  it 'get all, one at a time' do
+    go :publisher
+  end
+end

data/spec/resource/collection_http_spec.rb

@@ -0,0 +1,65 @@
+require 'spec_helper'
+
+describe 'Collection of datasets' do
+
+  def new
+    @p = Puree::Extractor::Collection.new resource: :dataset,
+                                          config:   config
+  end
+
+  def setup
+    new
+  end
+
+  it '#new' do
+    new
+    expect(@p).to be_a(Puree::Extractor::Collection)
+  end
+
+  describe 'data retrieval' do
+    before(:all) do
+      setup
+      @metadata = @p.find limit: 5
+    end
+
+    it 'collection' do
+      expect(@metadata).to be_a(Array)
+    end
+
+  end
+
+  describe 'data retrieval instance' do
+    before(:all) do
+      setup
+      @metadata = @p.find limit: 5
+    end
+
+    it 'collection' do
+      expect(@metadata).to be_a(Array)
+    end
+
+    it 'collection item' do
+      expect(@metadata).to all( be_a Puree::Model::Dataset )
+    end
+
+  end
+
+  describe 'data retrieval count' do
+    before(:all) do
+      setup
+      @p.find limit: 0
+    end
+
+    it '#count' do
+      expect(@p.count).to be_a(Fixnum)
+    end
+
+  end
+
+  it '#random_resource' do
+    setup
+    metadata = @p.random_resource
+    expect(metadata).to be_a Puree::Model::Dataset
+  end
+
+end

data/spec/resource/dataset_http_spec.rb

@@ -0,0 +1,104 @@
+require 'spec_helper'
+
+describe 'Dataset' do
+
+  it '#new' do
+    p = Puree::Extractor::Dataset.new config
+    expect(p).to be_a Puree::Extractor::Dataset
+  end
+
+  before(:all) do
+    request :dataset
+  end
+
+  describe 'data retrieval' do
+
+    resource_header
+
+    it 'data structure' do
+      expect(@p).to be_a Puree::Model::Dataset
+    end
+
+    it '#access' do
+      expect(@p.access).to be_a String if @p.access
+    end
+
+    it '#associated' do
+      expect(@p.associated).to all( be_a Puree::Model::RelatedContentHeader )
+    end
+
+    it '#available' do
+      expect(@p.available).to be_a Time if @p.available
+    end
+
+    it '#description' do
+      expect(@p.description).to be_a String if @p.description
+    end
+
+    it '#doi' do
+      expect(@p.doi).to be_a String if @p.doi
+    end
+
+    it '#files' do
+      expect(@p.files).to all( be_a Puree::Model::File )
+    end
+
+    it '#keywords' do
+      expect(@p.keywords).to all( be_a String )
+    end
+
+    it '#legal_conditions' do
+      expect(@p.legal_conditions).to all( be_a Puree::Model::LegalCondition )
+    end
+
+    it '#links' do
+      expect(@p.links).to all( be_a Puree::Model::Link )
+    end
+
+    it '#persons_internal' do
+      expect(@p.persons_internal).to all( be_a Puree::Model::EndeavourPerson )
+    end
+
+    it '#persons_external' do
+      expect(@p.persons_external).to all( be_a Puree::Model::EndeavourPerson )
+    end
+
+    it '#persons_other' do
+      expect(@p.persons_other).to all( be_a Puree::Model::EndeavourPerson )
+    end
+
+    it '#production' do
+      expect(@p.production).to be_a Puree::Model::TemporalRange if @p.production
+    end
+
+    it '#projects' do
+      expect(@p.projects).to all( be_a Puree::Model::RelatedContentHeader )
+    end
+
+    it '#publications' do
+      expect(@p.publications).to all( be_a Puree::Model::RelatedContentHeader )
+    end
+
+    it '#publisher' do
+      expect(@p.publisher).to be_a String if @p.publisher
+    end
+
+    it '#spatial_places' do
+      expect(@p.spatial_places).to all( be_a String ) if @p.spatial_places
+    end
+
+    it '#spatial_point' do
+      expect(@p.spatial_point).to be_a Puree::Model::SpatialPoint if @p.spatial_point
+    end
+
+    it '#temporal' do
+      expect(@p.temporal).to be_a Puree::Model::TemporalRange if @p.temporal
+    end
+
+    it '#title' do
+      expect(@p.title).to be_a String if @p.title
+    end
+
+  end
+
+end