discovery-indexer 0.9.6 → 0.9.7

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 3c328198b5aaf90f99e8b239b37aabacf9cfcdc7
-  data.tar.gz: 7ffabf609d7b24d5ae413f4cac213a9aabef2e8e
+  metadata.gz: 9cddff2ef4144cc3d17af7bd71bdb6f68840d38c
+  data.tar.gz: ca19a7acbb80341c1d6440567e305ef0bf170542
 SHA512:
-  metadata.gz: 7ec36accf3a418d95040bc8ca561a7f08fac0fabcb6d2cac133589f451620b885c16218daa7338c2b478771978eed2d2a6ae236a0eb9cde1b836941b8eb41434
-  data.tar.gz: 2595c1da62ab979b6f12db5ca3cc64102c622924090cc0cf355e3b14b405f33fbafb859282b65bc16c1516369a407c6bae61809e19b7f0e417a92ac9ae43857c
+  metadata.gz: 65fa148806dcf8dc498b262cbc3acf811c89fcad0d81397099009e0e8eb368577477e50c9c5bbee7e0921e11b17542cf4857b2aff4e54a319f5f97ea22e1bb8f
+  data.tar.gz: a28465c230937c24168114d91f41a58e59492a16b0b479ab8e4ae41429c4682dc7eec99a4b796ff93869d37b7e34ed78a6d7485ff1500ee2bc91e99e3a6e070f

data/lib/discovery-indexer.rb

@@ -15,9 +15,8 @@ require 'mapper/general_mapper'
 require 'writer/solr_client'
 require 'writer/solr_writer'
 
-#require 'utilities/extract_sub_targets'
-
+# require 'utilities/extract_sub_targets'
 
 module DiscoveryIndexer
   PURL_DEFAULT = 'http://purl.stanford.edu'
-end
+end

data/lib/errors.rb

@@ -1,13 +1,13 @@
 module DiscoveryIndexer
   module Errors
-    MissingPurlPage = Class.new(StandardError) 
-    MissingMods = Class.new(StandardError) 
-    MissingPublicXml = Class.new(StandardError) 
-    MissingContentMetadata = Class.new(StandardError) 
-    MissingIdentityMetadata = Class.new(StandardError) 
-    MissingRightsMetadata = Class.new(StandardError) 
-    MissingRDF = Class.new(StandardError) 
+    MissingPurlPage = Class.new(StandardError)
+    MissingMods = Class.new(StandardError)
+    MissingPublicXml = Class.new(StandardError)
+    MissingContentMetadata = Class.new(StandardError)
+    MissingIdentityMetadata = Class.new(StandardError)
+    MissingRightsMetadata = Class.new(StandardError)
+    MissingRDF = Class.new(StandardError)
     MissingDC = Class.new(StandardError)
     MissingModsPage = Class.new(StandardError)
   end
-end
+end

data/lib/logging.rb

@@ -6,11 +6,8 @@ module DiscoveryIndexer
       def logger
         @logger ||= Logger.new(STDOUT)
       end
-  
-      def logger=(logger)
-        @logger = logger
-      end
-    end
 
+      attr_writer :logger
+    end
   end
-end
+end

data/lib/mapper/general_mapper.rb

@@ -1,29 +1,27 @@
 module DiscoveryIndexer
   module Mapper
     class GeneralMapper
-      
       # 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
       # e.g. @collection_data = {'aa00bb0001'=>{:name=>'Test Collection Name',:ckey=>'000001'},'nt028fd5773'=>{:name=>'Revs Institute Archive',:ckey=>'000002'}}
-      def initialize(druid, modsxml, purlxml, collection_data={})
+      def initialize(druid, modsxml, purlxml, collection_data = {})
         @druid = druid
         @modsxml = modsxml
         @purlxml = purlxml
         @collection_data = collection_data
       end
 
-      # Create a Hash representing a Solr doc, with all MODS related fields populated.  
+      # Create a Hash representing a Solr doc, with all MODS related fields populated.
       # @return [Hash] Hash representing the Solr document
-      def convert_to_solr_doc()
+      def convert_to_solr_doc
         solr_doc = {}
         solr_doc[:id] = @druid
         solr_doc[:title] = @modsxml.sw_full_title
-        return solr_doc
+        solr_doc
       end
     end
   end
 end
-  

data/lib/reader/modsxml.rb

@@ -1,44 +1,40 @@
 require 'stanford-mods'
 module DiscoveryIndexer
   module InputXml
-    
-    # This class is the main class to access and parse the mods xml 
+    # This class is the main class to access and parse the mods xml
     #    as retrieved from PURL server
     # @example to run the code
     #  druid = "aa111aa1111"
     #  p =  DiscoveryIndexer::InputXml::Modsxml.new(druid)
     #  model =  p.load()
-    # 
-    # 
+    #
+    #
     class Modsxml
-      # initializes a new object 
+      # initializes a new object
       # @param druid [String] the druid object in the format "aa111aa1111"
       def initialize(druid)
         @druid = druid
-        @modsxml_ng_doc = nil 
+        @modsxml_ng_doc = nil
       end
 
       # loads the mods xml to stanford mods model for the fedora object defind in the druid,
-      #    it reads the mods xml once from PURL server, and repeat the parsing with each call
-      # @return [Stanford::Mods::Record] represents the mods xml 
-      def load()
-        if @modsxml_ng_doc.nil? then
-          @modsxml_ng_doc = ModsxmlReader.read(@druid)
-        end
-        
+      # it reads the mods xml once from PURL server, and repeat the parsing with each call
+      # @return [Stanford::Mods::Record] represents the mods xml
+      def load
+        @modsxml_ng_doc = ModsxmlReader.read(@druid) if @modsxml_ng_doc.nil?
+
         modsxml_model = Stanford::Mods::Record.new
         modsxml_model.from_nk_node(@modsxml_ng_doc)
-        return modsxml_model
+        modsxml_model
       end
-      
+
       # loads the mods xml to stanford mods model for the fedora object defind in the druid,
-      #    it reads the mods xml from PURL server with every call
-      # @return [Stanford::Mods::Record] represents the mods xml 
-      def reload()
+      # it reads the mods xml from PURL server with every call
+      # @return [Stanford::Mods::Record] represents the mods xml
+      def reload
         @modsxml_ng_doc = ModsxmlReader.read(@druid)
-        return load()
+        load
       end
-
     end
   end
 end

data/lib/reader/modsxml_reader.rb

@@ -3,21 +3,18 @@ require 'open-uri'
 module DiscoveryIndexer
   module InputXml
     class ModsxmlReader
-
       # reads the mods xml for the fedora object that is defined , from the purl server
       # @param [String] druid e.g. ab123cd4567
       # @return [Nokogiri::XML::Document] the mods xml for the fedora object
       # @raise [MissingModsXml] if there's no mods xml available for this druid
       def self.read(druid)
         mods_uri = "#{DiscoveryIndexer::PURL_DEFAULT}/#{druid}.mods"
-        
         begin
-          modsxml_ng_doc = Nokogiri::XML(open(mods_uri))
-          return modsxml_ng_doc
+          Nokogiri::XML(open(mods_uri))
         rescue
           raise DiscoveryIndexer::Errors::MissingModsPage.new(mods_uri)
         end
       end
     end
   end
-end
+end

data/lib/reader/purlxml.rb

@@ -1,43 +1,36 @@
 module DiscoveryIndexer
   module InputXml
-    
-    # This class is the main class to access and parse the purl xml 
+    # This class is the main class to access and parse the purl xml
     #    as retrieved from PURL server
     # @example to run the code
     #  druid = "aa111aa1111"
     #  p =  DiscoveryIndexer::InputXml::Purlxml.new(druid)
     #  model =  p.load()
-    # 
     class Purlxml
-      
-      # initializes a new object 
+      # initializes a new object
       # @param druid [String] the druid object in the format "aa111aa1111"
       def initialize(druid)
         @druid = druid
-        @purlxml_ng_doc = nil 
+        @purlxml_ng_doc = 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()
-        if @purlxml_ng_doc.nil? then
-          @purlxml_ng_doc = PurlxmlReader.read(@druid)
-        end
-        
-        purlxml_parser = PurlxmlParserStrict.new(@druid,@purlxml_ng_doc)
-        purlxml_model = purlxml_parser.parse()
-        return purlxml_model
+      # 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)
+        purlxml_model = purlxml_parser.parse
+        purlxml_model
       end
-      
+
       # loads the purl xml to purlxml model for the fedora object defind in the druid
-      #    it reads the purl xml from PURL server with every call
-      # @return [PurlxmlModel] represents the purlxml 
-      def reload()
+      # it reads the purl xml from PURL server with every call
+      # @return [PurlxmlModel] represents the purlxml
+      def reload
         @purlxml_ng_doc = PurlxmlReader.read(@druid)
-        return load()
+        load
       end
-  	end
+    end
   end
 end
-  

data/lib/reader/purlxml_model.rb

@@ -1,47 +1,46 @@
 module DiscoveryIndexer
   module InputXml
     class PurlxmlModel
-      
-      #@!attribute [rw] druid
-      # @return [String] The druid value eg., ab123cd4567 
-      attr_accessor :druid      
-      
-      #@!attribute [rw] public_xml
-      # @return [Nokogiri::XML] The publix xml as retrieved from purl server 
+      # @!attribute [rw] druid
+      # @return [String] The druid value eg., ab123cd4567
+      attr_accessor :druid
+
+      # @!attribute [rw] public_xml
+      # @return [Nokogiri::XML] The publix xml as retrieved from purl server
       attr_accessor :public_xml
 
-      #@!attribute [rw] content_metadata
+      # @!attribute [rw] content_metadata
       # @return [Nokogiri::XML] The content_metadata as extracted from public xml
       attr_accessor :content_metadata
 
-      #@!attribute [rw] identity_metadata
+      # @!attribute [rw] identity_metadata
       # @return [Nokogiri::XML] The identity_metadata as extracted from public xml
       attr_accessor :identity_metadata
 
-      #@!attribute [rw] rights_metadata
+      # @!attribute [rw] rights_metadata
       # @return [Nokogiri::XML] The rights_metadata as extracted from public xml
       attr_accessor :rights_metadata
 
-      #@!attribute [rw] dc
+      # @!attribute [rw] dc
       # @return [Nokogiri::XML] The dc element as extracted from public xml
       attr_accessor :dc
-      
-      #@!attribute [rw] rdf
+
+      # @!attribute [rw] rdf
       # @return [Nokogiri::XML] The rdf element as extracted from public xml
       attr_accessor :rdf
 
       # @!attribute [rw] release_tags_hash
       # @return [Hash] The release_tag in hash format as extracted from public xml
-      #  ReleaseData element. 
+      #  ReleaseData element.
       # @example
       #  !{"target1"=>true, "target2"=>false}
-      attr_accessor :release_tags_hash     
+      attr_accessor :release_tags_hash
 
       # @!attribute [rw] dor_content_type
       # @return [String] The dor_content_type as extracted from public xml
       #  content_metadata.
       attr_accessor :dor_content_type
-      
+
       # @!attribute [rw] dor_display_type
       # @return [String] The displayType as extracted from public xml
       #  identity_metadata.
@@ -50,25 +49,25 @@ module DiscoveryIndexer
       # @!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
       # @example
       #  ["aa11aaa1111","bb111bb1111"]
       attr_accessor :collection_druids
-      
+
       # @!attribute [rw] file_ids
       # @return [Array] a list of the file ids in the content_metadata
       # @example
-      #  ["pc0065_b08_f10_i031.txt","pc0065_b08_f10_i032.txt"]   
+      #  ["pc0065_b08_f10_i031.txt","pc0065_b08_f10_i032.txt"]
       attr_accessor :file_ids
 
       # @!attribute [rw] image_ids
       # @return [Array] a list of the image ids in the content_metadata
       # @example
-      #  ["pc0065_b08_f10_i031.jp2","pc0065_b08_f10_i032.jp2"]   
+      #  ["pc0065_b08_f10_i031.jp2","pc0065_b08_f10_i032.jp2"]
       attr_accessor :image_ids
-      
+
       # @!attribute [rw] catkey
       # @return [String] the catkey attribute in identity_metadata
       attr_accessor :catkey
@@ -76,15 +75,15 @@ module DiscoveryIndexer
       # @!attribute [rw] barcode
       # @return [String] the barcode attribute in identity_metadata
       attr_accessor :barcode
-      
+
       # @!attribute [rw] label
       # @return [String] the objectLabel attribute in identity_metadata
       attr_accessor :label
- 
+
       # @!attribute [rw] copyright
       # @return [String] the copyright statement from rights metadata
       attr_accessor :copyright
-      
+
       # @!attribute [rw] use_and_reproduction
       # @return [String] the use and reproduction statement from rights metadata
       attr_accessor :use_and_reproduction
@@ -92,13 +91,6 @@ module DiscoveryIndexer
       # @!attribute [rw] source_id
       # @return [String] the sourceid from identity metadata
       attr_accessor :source_id
-            
     end
   end
 end
-  
-
-
-
-
-

data/lib/reader/purlxml_parser.rb

@@ -1,13 +1,12 @@
 module DiscoveryIndexer
   module InputXml
     class PurlxmlParser
-      
       def initialize(druid, purlxml_ng_doc)
         @purlxml_ng_doc = purlxml_ng_doc
         @druid = druid
       end
-      
-      def parse()
+
+      def parse
       end
     end
   end

data/lib/reader/purlxml_parser_strict.rb

@@ -3,154 +3,142 @@ module DiscoveryIndexer
     class PurlxmlParserStrict < PurlxmlParser
       include DiscoveryIndexer::Logging
 
-      
       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'
 
       # it parses the purlxml into a purlxml model
       # @return [PurlxmlModel] represents the purlxml as parsed based on the parser rules
-      def parse()
+      def parse
         purlxml_model = PurlxmlModel.new
         purlxml_model.druid             = @druid
         purlxml_model.public_xml        = @purlxml_ng_doc
-        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.rdf               = parse_rdf()
-        purlxml_model.is_collection     = parse_is_collection()
-        purlxml_model.collection_druids = parse_collection_druids()
-        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()
-        purlxml_model.catkey            = parse_catkey()
-        purlxml_model.barcode           = parse_barcode()
-        purlxml_model.label             = parse_label()
-        purlxml_model.copyright         = parse_copyright()
-        purlxml_model.use_and_reproduction = parse_use_and_reproduction()
-        purlxml_model.source_id  = parse_sourceid()
-        return purlxml_model
-      end
-      
+        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.rdf               = parse_rdf
+        purlxml_model.is_collection     = parse_is_collection
+        purlxml_model.collection_druids = parse_collection_druids
+        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
+        purlxml_model.catkey            = parse_catkey
+        purlxml_model.barcode           = parse_barcode
+        purlxml_model.label             = parse_label
+        purlxml_model.copyright         = parse_copyright
+        purlxml_model.use_and_reproduction = parse_use_and_reproduction
+        purlxml_model.source_id = parse_sourceid
+        purlxml_model
+      end
+
       # 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
-        begin
-          ng_doc = Nokogiri::XML(@purlxml_ng_doc.root.xpath('/publicObject/identityMetadata').to_xml)
-          raise DiscoveryIndexer::Errors::MissingIdentityMetadata.new(@purlxml_ng_doc.inspect) if !ng_doc || ng_doc.children.empty?
-          ng_doc 
-        rescue
-          raise DiscoveryIndexer::Errors::MissingIdentityMetadata.new(@purlxml_ng_doc.inspect)
-        end
+        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
+      rescue
+        raise DiscoveryIndexer::Errors::MissingIdentityMetadata.new(@purlxml_ng_doc.inspect)
       end
-      
-      def parse_rights_metadata 
-        begin
-          ng_doc = Nokogiri::XML(@purlxml_ng_doc.root.xpath('/publicObject/rightsMetadata').to_xml)
-          raise DiscoveryIndexer::Errors::MissingRightsMetadata.new(@purlxml_ng_doc.inspect) if !ng_doc || ng_doc.children.empty?
-          ng_doc
-        rescue
-          raise DiscoveryIndexer::Errors::MissingRightsMetadata.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
+      rescue
+        raise DiscoveryIndexer::Errors::MissingRightsMetadata.new(@purlxml_ng_doc.inspect)
       end
-        
+
       # extracts the dc field for this fedora object, from the purl xml
       # @return [Nokogiri::XML::Document] the dc for the fedora object
       # @raise [DiscoveryIndexer::Errors::MissingDC] if there is no dc element
       def parse_dc
-          begin
-            ng_doc = Nokogiri::XML(@purlxml_ng_doc.root.xpath('/publicObject/dc:dc', {'dc' => OAI_DC_NAMESPACE}).to_xml(:encoding => 'utf-8'))
-            raise DiscoveryIndexer::Errors::MissingDC.new(@purlxml_ng_doc.inspect) if !ng_doc || ng_doc.children.empty?
-            ng_doc
-          rescue
-            raise DiscoveryIndexer::Errors::MissingDC.new(@purlxml_ng_doc.inspect)
-          end
+        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
+      rescue
+        raise DiscoveryIndexer::Errors::MissingDC.new(@purlxml_ng_doc.inspect)
       end
-        
+
       # extracts the rdf field for this fedora object, from the purl xml
       # @return [Nokogiri::XML::Document] the rdf for the fedora object
       # @raise [DiscoveryIndexer::Errors::MissingRDF] if there is no rdf element
       def parse_rdf
-        begin
-          ng_doc = Nokogiri::XML(@purlxml_ng_doc.root.xpath('/publicObject/rdf:RDF', {'rdf' => RDF_NAMESPACE}).to_xml)
-          raise DiscoveryIndexer::Errors::MissingRDF.new(@purlxml_ng_doc.inspect) if !ng_doc || ng_doc.children.empty?
-          ng_doc
-        rescue
-          raise DiscoveryIndexer::Errors::MissingRDF.new(@purlxml_ng_doc.inspect)
-        end
+        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
+      rescue
+        raise DiscoveryIndexer::Errors::MissingRDF.new(@purlxml_ng_doc.inspect)
       end
-      
-      
+
       # extracts the release tag element for this fedora object, from the the ReleaseData element in purl xml
       # @return [Hash] the release tags for the fedora object
       def parse_release_tags_hash
-        release_tags={}
-        unless  @purlxml_ng_doc.nil?
-          release_elements =  @purlxml_ng_doc.xpath('//ReleaseData/release')
-          release_elements.each { |n| 
-            unless n.attr("to").nil?
-              release_target = n.attr("to")
+        release_tags = {}
+        unless @purlxml_ng_doc.nil?
+          release_elements = @purlxml_ng_doc.xpath('//ReleaseData/release')
+          release_elements.each do |n|
+            unless n.attr('to').nil?
+              release_target = n.attr('to')
               text = n.text
-              unless text.nil? 
-                release_tags[release_target]= to_boolean(text) 
-              end
+              release_tags[release_target] = to_boolean(text) unless text.nil?
             end
-          }
+          end
         end
-        return release_tags
+        release_tags
       end
- 
+
       # extracts the contentMetadata for this fedora object, from the purl xml
       # @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 
+        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
       end
-      
+
       # @return true if the identityMetadata has <objectType>collection</objectType>, false otherwise
       def parse_is_collection
-        identity_metadata  = parse_identity_metadata
+        identity_metadata = parse_identity_metadata
         unless identity_metadata.nil?
           object_type_nodes = identity_metadata.xpath('//objectType')
-          return true if object_type_nodes.find_index { |n| ['collection','set'].include? n.text.downcase}
+          return true if object_type_nodes.find_index { |n| %w(collection set).include? n.text.downcase }
         end
         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#", '' => ''}
+        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
         druids = []
-        is_member_of_nodes.each { |n| 
+        is_member_of_nodes.each do |n|
           druids << n.value.split('druid:').last unless n.value.empty?
-        }
+        end
         return nil if druids.empty?
         druids
       end
-      
+
       # the value of the type attribute for a DOR object's contentMetadata
       #  more info about these values is here:
       #    https://consul.stanford.edu/display/chimera/DOR+content+types%2C+resource+types+and+interpretive+metadata
       #    https://consul.stanford.edu/display/chimera/Summary+of+Content+Types%2C+Resource+Types+and+their+behaviors
-      # @return [String] 
+      # @return [String]
       def parse_dor_content_type
         content_md = parse_content_metadata
         dct = content_md ? content_md.xpath('contentMetadata/@type').text : nil
         DiscoveryIndexer::Logging.logger.debug "#{@druid} has no DOR content type (<contentMetadata> element may be missing type attribute)" if !dct || dct.empty?
         dct
       end
-      
+
       # the value of the displyType tag from a DOR collection's identityMetadata
-      # @return [String] 
+      # @return [String]
       def parse_dor_display_type
         identity_md = parse_identity_metadata
         ddt = identity_md ? identity_md.xpath('//displayType').text : nil
@@ -161,43 +149,44 @@ module DiscoveryIndexer
       # the @id attribute of resource/file elements that match the image type, including extension
       # @return [Array<String>] filenames
       def parse_image_ids
-          ids = []
-          content_md = parse_content_metadata
-          unless content_md.nil?
-            content_md.xpath('//resource[@type="image"]/file/@id').each { |node|
-              ids << node.text if !node.text.empty?
-            }
-          return nil if ids.empty?
-          ids
+        ids = []
+        content_md = parse_content_metadata
+        return nil if content_md.nil?
+        content_md.xpath('//resource[@type="image"]/file/@id').each do |node|
+          ids << node.text unless node.text.empty?
         end
+        content_md.xpath('//resource[@type="page"]/file/@id').each do |node|
+          ids << node.text unless node.text.empty?
+        end
+        return nil if ids.empty?
+        ids
       end
 
       def parse_sourceid
         get_value(@purlxml_ng_doc.css('//identityMetadata/sourceId'))
       end
-            
+
       def parse_copyright
         get_value(@purlxml_ng_doc.css('//rightsMetadata/copyright/human[type="copyright"]'))
       end
-  
+
       def parse_use_and_reproduction
         get_value(@purlxml_ng_doc.css('//rightsMetadata/use/human[type="useAndReproduction"]'))
       end
-      
+
       # the @id attribute of resource/file elements, including extension
       # @return [Array<String>] filenames
       def parse_file_ids
         ids = []
         content_md = parse_content_metadata
-        unless content_md.nil?
-            content_md.xpath('//resource/file/@id').each { |node|
-              ids << node.text if !node.text.empty?
-            }
-          return nil if ids.empty?
-          ids
-        end 
-      end
-      
+        return unless content_md.nil?
+        content_md.xpath('//resource/file/@id').each do |node|
+          ids << node.text unless node.text.empty?
+        end
+        return nil if ids.empty?
+        ids
+      end
+
       # @return catkey value from the DOR identity_metadata, or nil if there is no catkey
       def parse_catkey
         get_value(@purlxml_ng_doc.xpath("/publicObject/identityMetadata/otherId[@name='catkey']"))
@@ -210,23 +199,22 @@ module DiscoveryIndexer
 
       # @return objectLabel value from the DOR identity_metadata, or nil if there is no barcode
       def parse_label
-        get_value(@purlxml_ng_doc.xpath("/publicObject/identityMetadata/objectLabel"))
+        get_value(@purlxml_ng_doc.xpath('/publicObject/identityMetadata/objectLabel'))
       end
-      
+
       def get_value(node)
-        (node && node.first) ? node.first.content : nil 
+        (node && node.first) ? node.first.content : nil
       end
-      
+
       def to_boolean(text)
-        if text.nil? || text.empty? then
+        if text.nil? || text.empty?
           return false
-        elsif text.downcase.eql?("true") || text.downcase == "t" then
+        elsif text.downcase.eql?('true') || text.downcase == 't'
           return true
         else
           return false
         end
-      end    
+      end
     end
   end
 end
-  

data/lib/reader/purlxml_reader.rb

@@ -3,14 +3,13 @@ require 'open-uri'
 module DiscoveryIndexer
   module InputXml
     class PurlxmlReader
-
       # reads the public xml for the fedora object that is defined , from the purl server
       # @param [String] druid e.g. ab123cd4567
       # @return [Nokogiri::XML::Document] the public xml for the fedora object
       # @raise [MissingPublicXml] if there's no purl xml available for this druid
       def self.read(druid)
         purlxml_uri = "#{DiscoveryIndexer::PURL_DEFAULT}/#{druid}.xml"
-        
+
         begin
           purlxml_object = Nokogiri::XML(open(purlxml_uri))
           return purlxml_object
@@ -20,4 +19,4 @@ module DiscoveryIndexer
       end
     end
   end
-end
+end

data/lib/version.rb

@@ -1,3 +1,3 @@
 module DiscoveryIndexer
-    VERSION = '0.9.6'
+  VERSION = '0.9.7'
 end

data/lib/writer/solr_client.rb

@@ -3,6 +3,7 @@ require 'rsolr'
 require 'rest-client'
 module DiscoveryIndexer
   module Writer
+    # Processes adds and deletes to the solr core
     class SolrClient
       include DiscoveryIndexer::Logging
 
@@ -13,7 +14,7 @@ module DiscoveryIndexer
       # @param solr_connector [RSolr::Client]  is an open connection with the solr core
       # @param max_retries [Integer] the maximum number of tries before fail
       def self.add(id, solr_doc, solr_connector, max_retries = 10)
-        process(id, solr_doc, solr_connector, max_retries, is_delete=false)  
+        process(id, solr_doc, solr_connector, max_retries, false)
       end
 
       # Add the document to solr, retry if an error occurs.
@@ -22,79 +23,76 @@ module DiscoveryIndexer
       # @param solr_connector[RSolr::Client]  is an open connection with the solr core
       # @param max_retries [Integer] the maximum number of tries before fail
       def self.delete(id, solr_connector, max_retries = 10)
-        process(id, {}, solr_connector, max_retries, is_delete=true)
+        process(id, {}, solr_connector, max_retries, true)
       end
 
       # It's an internal method that receives all the requests and deal with
       # SOLR core. This method can call add, delete, or update
       #
       # @param id [String] the document id, usually it will be druid.
-      # @param solr_doc [Hash] is the solr doc in hash format 
+      # @param solr_doc [Hash] is the solr doc in hash format
       # @param solr_connector [RSolr::Client]  is an open connection with the solr core
       # @param max_retries [Integer] the maximum number of tries before fail
-      def self.process(id, solr_doc, solr_connector, max_retries, is_delete=false)
-        handler = Proc.new do |exception, attempt_number, total_delay|
+      def self.process(id, solr_doc, solr_connector, max_retries, is_delete = false)
+        handler = proc do |exception, attempt_number, _total_delay|
           DiscoveryIndexer::Logging.logger.debug "#{exception.class} on attempt #{attempt_number} for #{id}"
         end
-          
-        with_retries(:max_tries => max_retries, :handler => handler, :base_sleep_seconds => 1, :max_sleep_seconds => 5) do |attempt|
+
+        with_retries(max_tries: max_retries, handler: handler, base_sleep_seconds: 1, max_sleep_seconds: 5) do |attempt|
           DiscoveryIndexer::Logging.logger.debug "Attempt #{attempt} for #{id}"
-        
+
           if is_delete
             DiscoveryIndexer::Logging.logger.info "Deleting #{id} on attempt #{attempt}"
             solr_connector.delete_by_id(id)
-          elsif allow_update?(solr_connector) && doc_exists?(id,solr_connector)
+          elsif allow_update?(solr_connector) && doc_exists?(id, solr_connector)
             DiscoveryIndexer::Logging.logger.info "Updating #{id} on attempt #{attempt}"
-            update_solr_doc(id,solr_doc,solr_connector)
+            update_solr_doc(id, solr_doc, solr_connector)
           else
             DiscoveryIndexer::Logging.logger.info "Indexing #{id} on attempt #{attempt}"
             solr_connector.add(solr_doc)
           end
           solr_connector.commit
           DiscoveryIndexer::Logging.logger.info "Completing #{id} successfully on attempt #{attempt}"
-          
         end
       end
 
       # @param solr_connector [RSolr::Client]  is an open connection with the solr core
       # @return [Boolean] true if the solr core allowing update feature
       def self.allow_update?(solr_connector)
-        return solr_connector.options.include?(:allow_update) ? solr_connector.options[:allow_update] : false
+        solr_connector.options.include?(:allow_update) ? solr_connector.options[:allow_update] : false
       end
 
       # @param id [String] the document id, usually it will be druid.
       # @param solr_connector [RSolr::Client]  is an open connection with the solr core
       # @return [Boolean] true if the solr doc defined by this id exists
-      def self.doc_exists?(id,solr_connector)
-        response=solr_connector.get 'select', :params=>{:q=>'id:"' + id + '"'}  
+      def self.doc_exists?(id, solr_connector)
+        response = solr_connector.get 'select', params: { q: 'id:"' + id + '"' }
         response['response']['numFound'] == 1
       end
-      
+
       # It is an internal method that updates the solr doc instead of adding a new one.
-      def self.update_solr_doc(id,solr_doc,solr_connector)
+      def self.update_solr_doc(id, solr_doc, solr_connector)
         # update_solr_doc can't used RSolr because updating hash doc is not supported
         #  so we need to build the json input manually
         solr_url = solr_connector.options[:url]
-        if solr_url.end_with?("/") then
-          url="#{solr_connector.options[:url]}update?commit=true"
+        if solr_url.end_with?('/')
+          url = "#{solr_connector.options[:url]}update?commit=true"
         else
-          url="#{solr_connector.options[:url]}/update?commit=true"
+          url = "#{solr_connector.options[:url]}/update?commit=true"
         end
-          
-        params="[{\"id\":\"#{id}\","
-        solr_doc.each do |field_name,new_values|
-          unless field_name == :id
-            params+="\"#{field_name}\":"
-            new_values=[new_values] unless new_values.class==Array
-            new_values = new_values.map {|s| s.to_s.gsub("\\","\\\\\\").gsub('"','\"').strip} # strip leading/trailing spaces and escape quotes for each value
-            params+="{\"set\":[\"#{new_values.join('","')}\"]},"
-          end
+
+        params = "[{\"id\":\"#{id}\","
+        solr_doc.each do |field_name, new_values|
+          next unless field_name == :id
+          params += "\"#{field_name}\":"
+          new_values = [new_values] unless new_values.class == Array
+          new_values = new_values.map { |s| s.to_s.gsub('\\', '\\\\\\').gsub('"', '\"').strip } # strip leading/trailing spaces and escape quotes for each value
+          params += "{\"set\":[\"#{new_values.join('","')}\"]},"
         end
         params.chomp!(',')
-        params+="}]"
-        RestClient.post url, params,:content_type => :json, :accept=>:json
+        params += '}]'
+        RestClient.post url, params, content_type: :json, accept: :json
       end
-      
     end
   end
-end
+end

data/lib/writer/solr_writer.rb

@@ -3,57 +3,57 @@ require 'rsolr'
 
 module DiscoveryIndexer
   module Writer
+    # Performs writes to solr client based upon true and false release flags
     class SolrWriter
       include DiscoveryIndexer::Logging
-      
+
       def process(id, index_doc, targets, solr_targets_configs)
         @solr_targets_configs = solr_targets_configs
         index_targets = []
         delete_targets = []
-        targets.keys.each do |target| 
-          if targets[target] then
+        targets.keys.each do |target|
+          if targets[target]
             index_targets.append(target)
           else
             delete_targets.append(target)
           end
         end
-        
+
         # get targets with true
         solr_index_client(id, index_doc, index_targets)
         # get targets with false
         solr_delete_client(id, delete_targets)
       end
-      
+
       def solr_delete_from_all(id, solr_targets_configs)
         # Get a list of all registered targets
-        @solr_targets_configs=solr_targets_configs
-        targets = @solr_targets_configs.keys()
+        @solr_targets_configs = solr_targets_configs
+        targets = @solr_targets_configs.keys
         solr_delete_client(id, targets)
       end
-            
+
       def solr_index_client(id, index_doc, targets)
         targets.each do |solr_target|
-          solr_connector = get_connector_for_target(solr_target)     
+          solr_connector = get_connector_for_target(solr_target)
           SolrClient.add(id, index_doc, solr_connector) unless solr_connector.nil?
-        end          
+        end
       end
-      
+
       def solr_delete_client(id, targets)
         targets.each do |solr_target|
           solr_connector = get_connector_for_target(solr_target)
           SolrClient.delete(id, solr_connector) unless solr_connector.nil?
-        end         
+        end
       end
 
       def get_connector_for_target(solr_target)
         solr_connector = nil
-        if @solr_targets_configs.keys.include?(solr_target) then
+        if @solr_targets_configs.keys.include?(solr_target)
           config = @solr_targets_configs[solr_target]
           solr_connector = RSolr.connect(config.deep_symbolize_keys)
         end
-        return solr_connector
+        solr_connector
       end
-      
     end
   end
 end

metadata

@@ -1,14 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: discovery-indexer
 version: !ruby/object:Gem::Version
-  version: 0.9.6
+  version: 0.9.7
 platform: ruby
 authors:
 - Ahmed AlSum
+- Laney McGlohon
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-06-30 00:00:00.000000000 Z
+date: 2015-09-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -138,7 +139,7 @@ dependencies:
         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: aalsum@stanford.edu
+email: laneymcg@stanford.edu
 executables: []
 extensions: []
 extra_rdoc_files: []