discovery-indexer 0.0.1 → 0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: c02b6da0be42381bffd949f1afb336909bfaa768
-  data.tar.gz: 1ba06814d93eef836acff2399624d6d55a06d2a5
+  metadata.gz: 073a6699afc6ef96ee080e00be2dfe3180bfb734
+  data.tar.gz: e4361f9aad38081a92598e53fb0f55e564807812
 SHA512:
-  metadata.gz: 7164b01c893146b50a41429aaacfa50f5592c86b322b38e9a2fbd779ab4152bfdc0e296457bcce4ad6393bdf22b1fcf21358cfbce3cc395ef661144e3716ff12
-  data.tar.gz: ae30908c3aa0b56c2cdcc5646452db595bd9755d86c1de6a5794a950e654c51cfae06966088a18861f544e46ce4543efd15a055e108363bdb56a2a378f0b2089
+  metadata.gz: 29e0c0dd830b66cc7cfe61bd4da7a42d3ee6fbb55721bf01ecf1f4b1679585d7aae9cc7c6f2a35d77b80b0017b45babea77516b9a4373191b7c8899b0a9a371c
+  data.tar.gz: 09c61dd4fa8501865bc4081dcb584224de912921eae74bb34121d6aafd05f4a762f45cdaffdf2c0a0282d318bc501629dcb0f1228c48d1fcba9ca769d4ab07db

data/lib/discovery-indexer.rb

@@ -0,0 +1,22 @@
+require 'reader/purlxml'
+require 'reader/purlxml_reader'
+require 'reader/purlxml_parser'
+require 'reader/purlxml_parser_strict'
+require 'reader/purlxml_model'
+
+require 'reader/modsxml'
+require 'reader/modsxml_reader'
+
+require 'mapper/general_mapper'
+require 'mapper/index_mapper'
+
+require 'writer/solr_client'
+require 'writer/solr_writer'
+
+#require 'utilities/extract_sub_targets'
+
+require 'errors'
+
+module DiscoveryIndexer
+  PURL_DEFAULT = 'http://purl-test.stanford.edu'
+end

data/lib/errors.rb

@@ -0,0 +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) 
+    MissingDC = Class.new(StandardError)
+    MissingModsPage = Class.new(StandardError)
+  end
+end

data/lib/mapper/general_mapper.rb

@@ -0,0 +1,18 @@
+module DiscoveryIndexer
+  module Mapper
+    class GeneralMapper
+      
+      def initialize(druid, modsxml, purlxml, collection_names={})
+        @druid = druid
+        @modsxml = modsxml
+        @purlxml = purlxml
+        @collection_names = collection_names
+      end
+
+      def map()
+      end
+          
+    end
+  end
+end
+  

data/lib/mapper/index_mapper.rb

@@ -0,0 +1,179 @@
+module DiscoveryIndexer
+  module Mapper
+    
+    # This class is responsible for creating the solr_doc hash based on the input
+    # of druid_id, modsxml, purlxml, and optional hash of collection_names
+    class IndexMapper < 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_names represents a hash of collection_druid and 
+      #  collection_name !{"aa111aa1111"=>"First Collection", "bb123bb1234"=>"Second Collection"}
+      def initialize(druid, modsxml, purlxml, collection_names={})
+        super druid, modsxml, purlxml, collection_names
+      end  
+      
+      # Create a Hash representing a Solr doc, with all MODS related fields populated.  
+      # @return [Hash] Hash representing the Solr document
+      def map()
+        solr_doc = {}
+        solr_doc[:id] = @druid
+        solr_doc.update mods_to_title_fields
+        solr_doc.update mods_to_author_fields
+        solr_doc.update mods_to_subject_search_fields
+        solr_doc.update mods_to_publication_fields
+        solr_doc.update mods_to_pub_date
+        solr_doc.update mods_to_others
+        
+        solr_doc[:all_search] = @modsxml.text.gsub(/\s+/, ' ')
+        return solr_doc
+      end
+
+      # @return [Hash] Hash representing the title fields
+      def mods_to_title_fields
+        # title fields
+        doc_hash = { 
+          :title_245a_search => @modsxml.sw_short_title,
+          :title_245_search => @modsxml.sw_full_title,
+          :title_variant_search => @modsxml.sw_addl_titles,
+          :title_sort => @modsxml.sw_sort_title,
+          :title_245a_display => @modsxml.sw_short_title,
+          :title_display => @modsxml.sw_title_display,
+          :title_full_display => @modsxml.sw_full_title,
+        }
+        doc_hash
+      end
+      
+      # @return [Hash] Hash representing the author fields
+      def mods_to_author_fields
+        doc_hash = { 
+          # author fields
+          :author_1xx_search => @modsxml.sw_main_author,
+          :author_7xx_search => @modsxml.sw_addl_authors,
+          :author_person_facet => @modsxml.sw_person_authors,
+          :author_other_facet => @modsxml.sw_impersonal_authors,
+          :author_sort => @modsxml.sw_sort_author[1..-1],
+          :author_corp_display => @modsxml.sw_corporate_authors,
+          :author_meeting_display => @modsxml.sw_meeting_authors,
+          :author_person_display => @modsxml.sw_person_authors,
+          :author_person_full_display => @modsxml.sw_person_authors,
+        }
+        doc_hash
+      end
+      
+      # @return [Hash] Hash representing the search fields
+      def mods_to_subject_search_fields
+        doc_hash = { 
+          # subject search fields
+          :topic_search => @modsxml.topic_search, 
+          :geographic_search => @modsxml.geographic_search,
+          :subject_other_search => @modsxml.subject_other_search, 
+          :subject_other_subvy_search => @modsxml.subject_other_subvy_search,
+          :subject_all_search => @modsxml.subject_all_search, 
+          :topic_facet => @modsxml.topic_facet,
+          :geographic_facet => @modsxml.geographic_facet,
+          :era_facet => @modsxml.era_facet,
+        }
+      end
+      
+      # @return [Hash] Hash representing the publication fields
+      def mods_to_publication_fields
+        doc_hash = { 
+          # publication fields
+          :pub_search =>  @modsxml.place,
+          :pub_date_sort =>  @modsxml.pub_date_sort,
+          :imprint_display =>  @modsxml.pub_date_display,
+          :pub_date =>  @modsxml.pub_date_facet,
+          :pub_date_display =>  @modsxml.pub_date_display, # pub_date_display may be deprecated
+        }
+      end
+      
+      # @return [Hash] Hash representing the pub date
+      def mods_to_pub_date
+        doc_hash = {}
+        pub_date_sort = @modsxml.pub_date_sort
+        if is_positive_int? pub_date_sort
+          doc_hash[:pub_year_tisim] =  pub_date_sort # for date slider
+          # put the displayable year in the correct field, :creation_year_isi for example
+          doc_hash[date_type_sym] =  @modsxml.pub_date_sort  if date_type_sym
+        end
+        return doc_hash
+      end    
+        
+      # @return [Hash] Hash representing some fields 
+      def mods_to_others
+        doc_hash = { 
+          :format_main_ssim => format_main_ssim,
+          :format => format, # for backwards compatibility
+          :language => @modsxml.sw_language_facet,
+          :physical =>  @modsxml.term_values([:physical_description, :extent]),
+          :summary_search => @modsxml.term_values(:abstract),
+          :toc_search => @modsxml.term_values(:tableOfContents),
+          :url_suppl => @modsxml.term_values([:related_item, :location, :url]),
+        }
+        return doc_hash
+      end
+    
+      # select one or more format values from the controlled vocabulary here:
+      #   http://searchworks-solr-lb.stanford.edu:8983/solr/select?facet.field=format&rows=0&facet.sort=index
+      # via stanford-mods gem
+      # @return [Array<String>] value(s) in the SearchWorks controlled vocabulary, or []
+      def format
+        vals = @modsxml.format
+        if vals.empty?
+          puts "#{@druid} has no SearchWorks format from MODS - check <typeOfResource> and other implicated MODS elements"
+        end
+        vals
+      end
+      
+      # call stanford-mods format_main to get results
+      # @return [Array<String>] value(s) in the SearchWorks controlled vocabulary, or []
+      def format_main_ssim
+        vals = @modsxml.format_main
+        if vals.empty?
+          puts "#{@druid} has no SearchWorks Resource Type from MODS - check <typeOfResource> and other implicated MODS elements"
+        end
+        vals
+      end
+    
+      # call stanford-mods sw_genre to get results
+      # @return [Array<String>] value(s) 
+      def genre_ssim
+        @modsxml.sw_genre
+      end
+    
+    protected
+    
+      # @return true if the string parses into an int, and if so, the int is >= 0
+      def is_positive_int? str
+        begin
+          if str.to_i >= 0
+            return true
+          else
+            return false
+          end
+        rescue
+        end
+        return false
+      end
+    
+      # determines particular flavor of displayable publication year field 
+      # @return Solr field name as a symbol
+      def date_type_sym
+        vals = @modsxml.term_values([:origin_info,:dateIssued])
+        if vals and vals.length > 0
+          return :publication_year_isi
+        end
+        vals = @modsxml.term_values([:origin_info,:dateCreated])  
+        if vals and vals.length > 0
+          return :creation_year_isi
+        end
+        nil
+      end
+      
+    end
+  end
+end
+  

data/lib/reader/modsxml.rb

@@ -0,0 +1,44 @@
+require 'stanford-mods'
+module DiscoveryIndexer
+  module InputXml
+    
+    # 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 
+      # @param druid [String] the druid object in the format "aa111aa1111"
+      def initialize(druid)
+        @druid = druid
+        @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
+        
+        modsxml_model = Stanford::Mods::Record.new
+        modsxml_model.from_nk_node(@modsxml_ng_doc)
+        return 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()
+        @modsxml_ng_doc = ModsxmlReader.read(@druid)
+        return load()
+      end
+
+    end
+  end
+end

data/lib/reader/modsxml_reader.rb

@@ -0,0 +1,23 @@
+require 'nokogiri'
+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
+        rescue
+          raise DiscoveryIndexer::Errors::MissingModsPage.new(mods_uri)
+        end
+      end
+    end
+  end
+end

data/lib/reader/purlxml.rb

@@ -0,0 +1,43 @@
+module DiscoveryIndexer
+  module InputXml
+    
+    # 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 
+      # @param druid [String] the druid object in the format "aa111aa1111"
+      def initialize(druid)
+        @druid = druid
+        @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(@purlxml_ng_doc)
+        purlxml_model = purlxml_parser.parse()
+        return 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()
+        @purlxml_ng_doc = PurlxmlReader.read(@druid)
+        return load()
+      end
+  	end
+  end
+end
+  

data/lib/reader/purlxml_model.rb

@@ -0,0 +1,29 @@
+module DiscoveryIndexer
+  module InputXml
+    class PurlxmlModel
+      attr_accessor :public_xml
+      attr_accessor :content_metadata
+      attr_accessor :identity_metadata
+      attr_accessor :rights_metadata
+      attr_accessor :dc
+      attr_accessor :rdf
+      attr_accessor :release_tags_hash     
+      attr_accessor :dor_content_type
+      attr_accessor :is_collection
+      attr_accessor :collection_druids
+      attr_accessor :dor_content_type
+      attr_accessor :file_ids
+      attr_accessor :image_ids
+      attr_accessor :catkey
+      attr_accessor :barcode
+      attr_accessor :label
+      
+    end
+  end
+end
+  
+
+
+
+
+

data/lib/reader/purlxml_parser.rb

@@ -0,0 +1,13 @@
+module DiscoveryIndexer
+  module InputXml
+    class PurlxmlParser
+      
+      def initialize(purlxml_ng_doc)
+        @purlxml_ng_doc = purlxml_ng_doc
+      end
+      
+      def parse()
+      end
+    end
+  end
+end

data/lib/reader/purlxml_parser_strict.rb

@@ -0,0 +1,210 @@
+module DiscoveryIndexer
+  module InputXml
+    class PurlxmlParserStrict < PurlxmlParser
+      
+      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'
+
+      def initialize(purlxml_ng_doc)
+        super
+      end
+      
+      # it parses the purlxml into a purlxml model
+      # @return [PurlxmlModel] represents the purlxml as parsed based on the parser rules
+      def parse()
+        purlxml_model = PurlxmlModel.new
+        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.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()
+        return 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 contentMetadata
+      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
+      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
+      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
+      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
+      end
+      
+      
+      # extracts the release tag element for this fedora object, from the the identity metadata in purl xml
+      # @return [Hash] the release tags for the fedora object
+      def parse_release_tags_hash
+        release_tags={}
+        identity_metadata  = parse_identity_metadata
+        unless identity_metadata.nil?
+          release_elements = identity_metadata.xpath('//release')
+          release_elements.each { |n| 
+            unless n.attr("to").nil?
+              release_target = n.attr("to")
+              
+              
+              #target = release_target.split(":").first
+              #sub_target = "default"
+              #if target != release_target.split(":").last then
+              #  sub_target = release_target.split(":").last
+              #end
+              text = n.text
+              unless text.nil? 
+                release_tags[release_target]= text 
+              end
+            end
+          }
+          return release_tags
+        end
+      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
+     #   begin
+          ng_doc = Nokogiri::XML(@purlxml_ng_doc.root.xpath('/publicObject/contentMetadata').to_xml)
+      #    raise DiscoveryIndexer::Errors::MissingContentMetadata.new(@purlxml_ng_doc.inspect) if !ng_doc || ng_doc.children.empty?
+          ng_doc 
+      #  rescue
+      #    raise DiscoveryIndexer::Errors::MissingContentMetadata.new(@purlxml_ng_doc.inspect)
+      #  end 
+      end
+      
+      # @return true if the identityMetadata has <objectType>collection</objectType>, false otherwise
+      def parse_is_collection
+        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| n.text == 'collection'}
+        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#", '' => ''}
+        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| 
+          druids << n.value.split('druid:').last unless n.value.empty?
+        }
+        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] 
+      def parse_dor_content_type
+        content_md = parse_content_metadata
+        dct = content_md ? content_md.xpath('@type').text : nil
+        puts " has no DOR content type (<contentMetadata> element may be missing type attribute)" if !dct || dct.empty?
+        dct
+      end
+      
+      # the @id attribute of resource/file elements that match the display_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
+        end
+      end
+      
+      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
+      
+      def parse_catkey
+        catkey = nil
+        node = @purlxml_ng_doc.xpath("/publicObject/identityMetadata/otherId[@name='catkey']") 
+        catkey = node.first.content if node && node.first
+        return catkey
+      end
+
+      def parse_barcode
+        barcode = nil
+        node = @purlxml_ng_doc.xpath("/publicObject/identityMetadata/otherId[@name='barcode']")
+        barcode = node.first.content if node && node.first
+        return barcode
+      end
+
+      def parse_label
+        label = nil
+        node = @purlxml_ng_doc.xpath("/publicObject/identityMetadata/objectLabel")
+        label = node.first.content if node && node.first
+        return label
+      end
+    end
+  end
+end
+  

data/lib/reader/purlxml_reader.rb

@@ -0,0 +1,23 @@
+require 'nokogiri'
+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
+        rescue
+          raise DiscoveryIndexer::Errors::MissingPurlPage.new(purlxml_uri)
+        end
+      end
+    end
+  end
+end

data/lib/utilities/extract_sub_targets.rb

@@ -0,0 +1,13 @@
+module DiscoveryIndexer
+  module Utilities
+    class ExtractSubTargets
+      
+      def self.by_name target_name, release_tags
+        if release_tags.keys.include?(target_name) then
+          return release_tags[target_name]
+        end
+      end
+      
+    end
+  end
+end

data/lib/version.rb

@@ -1,3 +1,3 @@
 module DiscoveryIndexer
-    VERSION = '0.0.1'
+    VERSION = '0.1'
 end

data/lib/writer/solr_client.rb

@@ -0,0 +1,51 @@
+require 'retries'
+require 'rsolr'
+
+module DiscoveryIndexer
+  module Writer
+    class SolrClient
+      
+      # Add the document to solr, retry if an error occurs.
+      # See https://github.com/ooyala/retries for docs on with_retries.
+      # @param [Hash] solr_doc a Hash representation of the solr document
+      # @param [RSolr::Client] solr_connector is an open connection with the solr core
+      # @param [Integer] max_retries the maximum number of tries before fail
+      def self.add(solr_doc, solr_connector, max_retries = 10)
+        process(solr_doc, solr_connector, max_retries, is_delete=false)  
+      end
+
+      # Add the document to solr, retry if an error occurs.
+      # See https://github.com/ooyala/retries for docs on with_retries.
+      # @param [Hash] solr_doc that has only the id !{:id=>"ab123cd4567"}
+      # @param [RSolr::Client] solr_connector is an open connection with the solr core
+      # @param [Integer] max_retries the maximum number of tries before fail
+      def self.delete(solr_doc, solr_connector, max_retries = 10)
+        process(solr_doc, solr_connector, max_retries, is_delete=true)
+      end
+      
+      def self.process(solr_doc, solr_connector, max_retries, is_delete=false)
+       logger  = Logger.new STDOUT
+       id = solr_doc[:id]
+        puts id
+        handler = Proc.new do |exception, attempt_number, total_delay|
+          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|
+          logger.debug "Attempt #{attempt} for #{id}"
+          
+          if is_delete
+            solr_connector.delete_by_id(id)
+            logger.info "Successfully deleted #{id} on attempt #{attempt}"
+          else
+            solr_connector.add(solr_doc)
+            logger.info "Successfully indexed #{id} on attempt #{attempt}"
+          end
+          
+        end
+        solr_connector.commit
+      end
+     
+    end
+  end
+end

data/lib/writer/solr_writer.rb

@@ -0,0 +1,61 @@
+require 'retries'
+require 'rsolr'
+
+module DiscoveryIndexer
+  module Writer
+    class SolrWriter
+      
+      def process(druid, index_doc, targets, solr_targets_configs)
+        @solr_targets_configs = solr_targets_configs
+        index_targets = []
+        delete_targets = []
+        puts targets
+        targets.keys.each do |target| 
+          if targets[target] then
+            index_targets.append(target)
+          else
+            delete_targets.append(target)
+          end
+        end
+        
+        # get targets with true
+        solr_index_client(index_doc, index_targets)
+        # get targets with false
+        solr_delete_client(druid, delete_targets)
+      end
+      
+      def solr_delete_from_all(druid, solr_targets_configs)
+        # Get a list of all registered targets
+        @solr_targets_configs=solr_targets_configs
+        targets = @solr_targets_configs.keys()
+        solr_delete_client(druid, targets)
+      end
+            
+      def solr_index_client(index_doc, targets)
+        targets.each do |solr_target|
+          solr_connector = get_connector_for_target(solr_target)     
+           SolrClient.add(index_doc, solr_connector)
+        end          
+      end
+      
+      def solr_delete_client(druid, targets)
+        targets.each do |solr_target|
+          solr_connector = get_connector_for_target(solr_target)     
+          SolrClient.delete({:id=>druid}, solr_connector)
+        end         
+      end
+
+      def get_connector_for_target(solr_target)
+        solr_connector = nil
+        puts solr_target
+        puts @solr_targets_configs
+        if @solr_targets_configs.keys.include?(solr_target) then
+          config = @solr_targets_configs[solr_target]
+          solr_connector = RSolr.connect(config)
+        end
+        return solr_connector
+      end
+      
+    end
+  end
+end

metadata

@@ -1,15 +1,127 @@
 --- !ruby/object:Gem::Specification
 name: discovery-indexer
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: '0.1'
 platform: ruby
 authors:
 - Ahmed AlSum
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-03-09 00:00:00.000000000 Z
-dependencies: []
+date: 2015-03-19 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: stanford-mods
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: retries
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rsolr
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: 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'
+- !ruby/object:Gem::Dependency
+  name: webmock
+  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: equivalent-xml
+  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: vcr
+  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: aalsum@stanford.edu
@@ -18,7 +130,20 @@ extensions: []
 extra_rdoc_files: []
 files:
 - lib/discovery-indexer.rb
+- lib/errors.rb
+- lib/mapper/general_mapper.rb
+- lib/mapper/index_mapper.rb
+- lib/reader/modsxml.rb
+- lib/reader/modsxml_reader.rb
+- lib/reader/purlxml.rb
+- lib/reader/purlxml_model.rb
+- lib/reader/purlxml_parser.rb
+- lib/reader/purlxml_parser_strict.rb
+- lib/reader/purlxml_reader.rb
+- lib/utilities/extract_sub_targets.rb
 - lib/version.rb
+- lib/writer/solr_client.rb
+- lib/writer/solr_writer.rb
 homepage: 
 licenses:
 - Stanford University
@@ -29,12 +154,12 @@ require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>='
+  - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []