discovery-indexer 0.11.0 → 1.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 51776b99172c16f9360bd19a8c51406a2e6379b1
-  data.tar.gz: c52db6afd40ad759784b4a9686fa3b61ffc55698
+  metadata.gz: 0da2f698e5d93f7b4c2e2413ec16cf6a96bf0a89
+  data.tar.gz: 874859db3a705393f1b801583c58800ee5dc8004
 SHA512:
-  metadata.gz: 289af09b8cbf7b4dedb28b69f5579393cece24d94cb98a2202d217fee855996df3cccb0772b88ac6977ea59fa1094709640633f8d53cf341d6b72b6266da6ad0
-  data.tar.gz: 7379566d52c7f17a8a2ecded2795ec4fc006199108302bf5b9998029bbd54478bb42687a8aa03a270199b039543dcdb67c7349aa0542e745222a63750cd1ce7b
+  metadata.gz: 7d56ddc0030ff54c25ad343fbaeef50111cbc874fae5234c7a39680acb0f4f9168b36adb0e7dd6c0e1f79a94ac8c75a3b310d598a98f44879ab987965a60f555
+  data.tar.gz: 3f2dc26535ff9cffbf0936d877ec8d0244742b4273b9a615d31e5acc257c1f1f97931481e627522ee4e9da823fdff41521a49f55b804b1d9fb1c426e5dbb78e1

data/lib/discovery-indexer/collection.rb

@@ -1,10 +1,9 @@
 module DiscoveryIndexer
 
-  # It caches the collection information such as name and catkey
+  # Collection information such as name (title/label) and catkey
   class Collection
 
     attr_reader :druid
-    delegate :present?, to: :collection_info
 
     def initialize(druid)
       @druid = druid
@@ -20,20 +19,11 @@ module DiscoveryIndexer
 
     private
 
-    # Returns the collection name from cache, otherwise will fetch it from PURL.
-    #
-    # @param collection_druid [String]  is the druid for a collection e.g., ab123cd4567
-    # @return [Array<String>] the collection data or [] if there is no name and catkey or the object
-    #   is not a collection
+    # @return [Hash] the collection data as { title: 'coll title', ckey: catkey'}
     def collection_info
-      from_purl || {}
-    end
-
-    # @param [String] collection_druid is the druid for a collection e.g., ab123cd4567
-    # @return [String] return the collection label from purl if available, nil otherwise
-    def from_purl
-      return unless purl_model
-      { title: purl_model.label, ckey: purl_model.catkey }
+      return {} unless purl_model
+      @info = {}
+      @info = { title: purl_model.label, ckey: purl_model.catkey } if @info.empty?
     end
 
     def purl_model

data/lib/discovery-indexer/general_mapper.rb

@@ -5,10 +5,6 @@ module DiscoveryIndexer
 
     # Initializes an instance from IndexMapper
     # @param [String] druid e.g. ab123cd4567
-    # @param [Stanford::Mods::Record] modsxml represents the MODS xml for the druid
-    # @param [DiscoveryIndexer::Reader::PurlxmlModel] purlxml represents the purlxml model
-    # @param [Hash] collection_data represents a hash of collection_druid and catkey
-    # collection_data = {'aa00bb0001'=>{:name=>'Test Collection Name',:ckey=>'000001'},'nt028fd5773'=>{:name=>'Revs Institute Archive',:ckey=>'000002'}}
     def initialize(druid)
       @druid = druid
     end
@@ -22,21 +18,36 @@ module DiscoveryIndexer
       solr_doc
     end
 
-    # It converts collection_druids list to a hash with names. If the druid doesn't
-    # have a collection name, it will be excluded from the hash
-    # @return [Hash] a hash for collection druid and its name
-    #   !{"ab123cd4567"=>"Collection 1", "ef123gh4567"=>"Collection 2"}
+    # @return [DiscoveryIndexer::Collection] for each collection druid, or [] if no collection druids
     def collection_data
       @collection_data ||= collection_druids.map do |cdruid|
         DiscoveryIndexer::Collection.new(cdruid)
       end
     end
+
+    # @return [Array<String>] Array of bare druids from rels-ext isMemberOfCollection in public xml (e.g. ['oo000oo0000'])
     def collection_druids
       purlxml.collection_druids
     end
+
+    # @return [DiscoveryIndexer::Collection] for each constituent druid, or [] if no constituent druids
+    def constituent_data
+      @constituent_data ||= constituent_druids.map do |cdruid|
+        DiscoveryIndexer::Collection.new(cdruid)
+      end
+    end
+
+    # @return [Array<String>] Array of bare druids from rels-ext isConstituentOf in public xml (e.g. ['oo000oo0000'])
+    def constituent_druids
+      purlxml.constituent_druids
+    end
+
+    # @return [Stanford::Mods::Record] the MODS xml for the druid
     def modsxml
       @modsxml ||= DiscoveryIndexer::InputXml::Modsxml.new(druid).load
     end
+
+    # @return [DiscoveryIndexer::Reader::PurlxmlModel] the purlxml model
     def purlxml
       @purlxml ||= DiscoveryIndexer::InputXml::Purlxml.new(druid).load
     end

data/lib/discovery-indexer/reader/purlxml.rb

@@ -1,25 +1,27 @@
 module DiscoveryIndexer
   module InputXml
-    # This class is the main class to access and parse the purl xml
-    #    as retrieved from PURL server
+    # Main model class to access the parsed purl xml retrieved from PURL server
     # @example to run the code
-    #  druid = "aa111aa1111"
-    #  p =  DiscoveryIndexer::InputXml::Purlxml.new(druid)
-    #  model =  p.load()
+    #    druid = "aa111aa1111"
+    #    p =  DiscoveryIndexer::InputXml::Purlxml.new(druid)
+    #    model =  p.load()
+    #  then you can access the bits of interest
+    #    model.collection_druids
     class Purlxml
       # initializes a new object
       # @param druid [String] the druid object in the format "aa111aa1111"
       def initialize(druid)
         @druid = druid
         @purlxml_ng_doc = nil
+        @populated_model = nil
       end
 
       # loads the purl xml to purlxml model for the fedora object defind in the druid,
       # it reads the purl xml once from PURL server, and repeat the parsing with each call
       # @return [PurlxmlModel] represents the purlxml
       def load
-        @purlxml_ng_doc = PurlxmlReader.read(@druid) if @purlxml_ng_doc.nil?
-        purlxml_parser = PurlxmlParserStrict.new(@druid, @purlxml_ng_doc).parse
+        @purlxml_ng_doc ||= PurlxmlReader.read(@druid)
+        @populated_model ||= PurlxmlParserStrict.new(@druid, @purlxml_ng_doc).parse
       end
     end
   end

data/lib/discovery-indexer/reader/purlxml_model.rb

@@ -41,21 +41,22 @@ module DiscoveryIndexer
       #  content_metadata.
       attr_accessor :dor_content_type
 
-      # @!attribute [rw] dor_display_type
-      # @return [String] The displayType as extracted from public xml
-      #  identity_metadata.
-      attr_accessor :dor_display_type
-
       # @!attribute [rw] is_collection
       # @return [Boolean] true if the item type is collection in the identity_metadata
       attr_accessor :is_collection
 
       # @!attribute [rw] collection_druids
-      # @return [Array] a list of the collections that this is druid belongs to
+      # @return [Array<String>] bare druids of the collections that this druid is a member of
       # @example
       #  ["aa11aaa1111","bb111bb1111"]
       attr_accessor :collection_druids
 
+      # @!attribute [rw] constituent_druids
+      # @return [Array<String>] bare druids of the objects that this druid is a constituent of
+      # @example
+      #  ["aa11aaa1111","bb111bb1111"]
+      attr_accessor :constituent_druids
+
       # @!attribute [rw] file_ids
       # @return [Array] a list of the file ids in the content_metadata
       # @example

data/lib/discovery-indexer/reader/purlxml_parser_strict.rb

@@ -6,6 +6,7 @@ module DiscoveryIndexer
       RDF_NAMESPACE = 'http://www.w3.org/1999/02/22-rdf-syntax-ns#'
       OAI_DC_NAMESPACE = 'http://www.openarchives.org/OAI/2.0/oai_dc/'
       MODS_NAMESPACE = 'http://www.loc.gov/mods/v3'
+      FEDORA_NAMESPACE = 'info:fedora/fedora-system:def/relations-external#'
 
       def initialize(druid, purlxml_ng_doc)
         @purlxml_ng_doc = purlxml_ng_doc
@@ -21,12 +22,12 @@ module DiscoveryIndexer
         purlxml_model.content_metadata  = parse_content_metadata
         purlxml_model.identity_metadata = parse_identity_metadata
         purlxml_model.rights_metadata   = parse_rights_metadata
-        purlxml_model.dc                = parse_dc
+        purlxml_model.dc                = parse_dc # why do we care?
         purlxml_model.rdf               = parse_rdf
         purlxml_model.is_collection     = parse_is_collection
-        purlxml_model.collection_druids = parse_collection_druids
+        purlxml_model.collection_druids = parse_predicate_druids('isMemberOfCollection', FEDORA_NAMESPACE)
+        purlxml_model.constituent_druids = parse_predicate_druids('isConstituentOf', FEDORA_NAMESPACE)
         purlxml_model.dor_content_type  = parse_dor_content_type
-        purlxml_model.dor_display_type  = parse_dor_display_type
         purlxml_model.release_tags_hash = parse_release_tags_hash
         purlxml_model.file_ids          = parse_file_ids
         purlxml_model.image_ids         = parse_image_ids
@@ -39,21 +40,23 @@ module DiscoveryIndexer
         purlxml_model
       end
 
+      private
+
       # extracts the identityMetadata for this fedora object, from the purl xml
       # @return [Nokogiri::XML::Document] the identityMetadata for the fedora object
       # @raise [DiscoveryIndexer::Errors::MissingIdentityMetadata] if there is no identity_metadata
       def parse_identity_metadata
-        ng_doc = Nokogiri::XML(@purlxml_ng_doc.root.xpath('/publicObject/identityMetadata').to_xml)
-        fail DiscoveryIndexer::Errors::MissingIdentityMetadata.new(@purlxml_ng_doc.inspect) if !ng_doc || ng_doc.children.empty?
-        ng_doc
+        @idmd_ng_doc ||= Nokogiri::XML(@purlxml_ng_doc.root.xpath('/publicObject/identityMetadata').to_xml)
+        fail DiscoveryIndexer::Errors::MissingIdentityMetadata.new(@purlxml_ng_doc.inspect) if !@idmd_ng_doc || @idmd_ng_doc.children.empty?
+        @idmd_ng_doc
       rescue
         raise DiscoveryIndexer::Errors::MissingIdentityMetadata.new(@purlxml_ng_doc.inspect)
       end
 
       def parse_rights_metadata
-        ng_doc = Nokogiri::XML(@purlxml_ng_doc.root.xpath('/publicObject/rightsMetadata').to_xml)
-        fail DiscoveryIndexer::Errors::MissingRightsMetadata.new(@purlxml_ng_doc.inspect) if !ng_doc || ng_doc.children.empty?
-        ng_doc
+        @rmd_ng_doc ||= Nokogiri::XML(@purlxml_ng_doc.root.xpath('/publicObject/rightsMetadata').to_xml)
+        fail DiscoveryIndexer::Errors::MissingRightsMetadata.new(@purlxml_ng_doc.inspect) if !@rmd_ng_doc || @rmd_ng_doc.children.empty?
+        @rmd_ng_doc
       rescue
         raise DiscoveryIndexer::Errors::MissingRightsMetadata.new(@purlxml_ng_doc.inspect)
       end
@@ -62,9 +65,9 @@ module DiscoveryIndexer
       # @return [Nokogiri::XML::Document] the dc for the fedora object
       # @raise [DiscoveryIndexer::Errors::MissingDC] if there is no dc element
       def parse_dc
-        ng_doc = Nokogiri::XML(@purlxml_ng_doc.root.xpath('/publicObject/dc:dc', 'dc' => OAI_DC_NAMESPACE).to_xml(encoding: 'utf-8'))
-        fail DiscoveryIndexer::Errors::MissingDC.new(@purlxml_ng_doc.inspect) if !ng_doc || ng_doc.children.empty?
-        ng_doc
+        @dc_ng_doc ||= Nokogiri::XML(@purlxml_ng_doc.root.xpath('/publicObject/dc:dc', 'dc' => OAI_DC_NAMESPACE).to_xml(encoding: 'utf-8'))
+        fail DiscoveryIndexer::Errors::MissingDC.new(@purlxml_ng_doc.inspect) if !@dc_ng_doc || @dc_ng_doc.children.empty?
+        @dc_ng_doc
       rescue
         raise DiscoveryIndexer::Errors::MissingDC.new(@purlxml_ng_doc.inspect)
       end
@@ -73,9 +76,9 @@ module DiscoveryIndexer
       # @return [Nokogiri::XML::Document] the rdf for the fedora object
       # @raise [DiscoveryIndexer::Errors::MissingRDF] if there is no rdf element
       def parse_rdf
-        ng_doc = Nokogiri::XML(@purlxml_ng_doc.root.xpath('/publicObject/rdf:RDF', 'rdf' => RDF_NAMESPACE).to_xml)
-        fail DiscoveryIndexer::Errors::MissingRDF.new(@purlxml_ng_doc.inspect) if !ng_doc || ng_doc.children.empty?
-        ng_doc
+        @rdf_ng_doc ||= Nokogiri::XML(@purlxml_ng_doc.root.xpath('/publicObject/rdf:RDF', 'rdf' => RDF_NAMESPACE).to_xml)
+        fail DiscoveryIndexer::Errors::MissingRDF.new(@purlxml_ng_doc.inspect) if !@rdf_ng_doc || @rdf_ng_doc.children.empty?
+        @rdf_ng_doc
       rescue
         raise DiscoveryIndexer::Errors::MissingRDF.new(@purlxml_ng_doc.inspect)
       end
@@ -101,9 +104,9 @@ module DiscoveryIndexer
       # @return [Nokogiri::XML::Document] the contentMetadata for the fedora object
       # @raise [DiscoveryIndexer::Errors::MissingContentMetadata] if there is no contentMetadata
       def parse_content_metadata
-        ng_doc = Nokogiri::XML(@purlxml_ng_doc.root.xpath('/publicObject/contentMetadata').to_xml)
-        ng_doc = nil if !ng_doc || ng_doc.children.empty?
-        ng_doc
+        @cntmd_ng_doc ||= Nokogiri::XML(@purlxml_ng_doc.root.xpath('/publicObject/contentMetadata').to_xml)
+        @cntmd_ng_doc = nil if !@cntmd_ng_doc || @cntmd_ng_doc.children.empty?
+        @cntmd_ng_doc
       end
 
       # @return true if the identityMetadata has <objectType>collection</objectType>, false otherwise
@@ -116,13 +119,13 @@ module DiscoveryIndexer
         false
       end
 
-      # get the druids from isMemberOfCollection relationships in rels-ext from public_xml
-      # @return [Array<String>] the druids (e.g. ww123yy1234) this object has isMemberOfColletion relationship with, or nil if none
-      def parse_collection_druids
-        ns_hash = { 'rdf' => 'http://www.w3.org/1999/02/22-rdf-syntax-ns#', 'fedora' => 'info:fedora/fedora-system:def/relations-external#', '' => '' }
-        is_member_of_nodes ||= @purlxml_ng_doc.xpath('/publicObject/rdf:RDF/rdf:Description/fedora:isMemberOfCollection/@rdf:resource', ns_hash)
-        # from public_xml rels-ext
-        is_member_of_nodes.reject { |n| n.value.empty? }.map do |n|
+      # get the druids from predicate relationships in rels-ext from public_xml
+      # @return [Array<String>, nil] the druids (e.g. ww123yy1234) from the rdf:resource of the predicate relationships, or nil if none
+      def parse_predicate_druids(predicate, predicate_ns)
+        ns_hash = { 'rdf' => 'http://www.w3.org/1999/02/22-rdf-syntax-ns#', 'pred_ns' => predicate_ns }
+        xpth = "/publicObject/rdf:RDF/rdf:Description/pred_ns:#{predicate}/@rdf:resource"
+        pred_nodes = @purlxml_ng_doc.xpath(xpth, ns_hash)
+        pred_nodes.reject { |n| n.value.empty? }.map do |n|
           n.value.split('druid:').last
         end
       end
@@ -139,15 +142,6 @@ module DiscoveryIndexer
         dct
       end
 
-      # the value of the displyType tag from a DOR collection's identityMetadata
-      # @return [String]
-      def parse_dor_display_type
-        identity_md = parse_identity_metadata
-        ddt = identity_md ? identity_md.xpath('//displayType').text : nil
-        DiscoveryIndexer::Logging.logger.debug "#{@druid} has no DOR display type (<identityMetadata> element may be missing displayType tag)" if !ddt || ddt.empty?
-        ddt
-      end
-
       # the @id attribute of resource/file elements that match the image type, including extension
       # @return [Array<String>] filenames
       def parse_image_ids

data/lib/discovery-indexer/version.rb

@@ -1,3 +1,3 @@
 module DiscoveryIndexer
-  VERSION = '0.11.0'
+  VERSION = '1.0.0'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: discovery-indexer
 version: !ruby/object:Gem::Version
-  version: 0.11.0
+  version: 1.0.0
 platform: ruby
 authors:
 - Ahmed AlSum
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-02-04 00:00:00.000000000 Z
+date: 2016-02-18 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -151,6 +151,48 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: yard
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rubocop-rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 description: This library manages the core operations for the discovery indexing such
   as reading PURL xml, mapping to the solr document, and writing to solr core.
 email: laneymcg@stanford.edu