discovery-indexer 0.1 → 0.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 073a6699afc6ef96ee080e00be2dfe3180bfb734
-  data.tar.gz: e4361f9aad38081a92598e53fb0f55e564807812
+  metadata.gz: f852ef4d15e2ba4dc67d49b1a0ec599ce5791234
+  data.tar.gz: 781d104e85d4b7ce490b639ca29b5aa31e03ef7e
 SHA512:
-  metadata.gz: 29e0c0dd830b66cc7cfe61bd4da7a42d3ee6fbb55721bf01ecf1f4b1679585d7aae9cc7c6f2a35d77b80b0017b45babea77516b9a4373191b7c8899b0a9a371c
-  data.tar.gz: 09c61dd4fa8501865bc4081dcb584224de912921eae74bb34121d6aafd05f4a762f45cdaffdf2c0a0282d318bc501629dcb0f1228c48d1fcba9ca769d4ab07db
+  metadata.gz: 12bc9321557bc08c608763546a185404d47fe4d8225df32604378f864acde9ceb93f8df48c63e755ffe6fb236b7e5a60ea15453ce2e07ba18f213e37f8249d8a
+  data.tar.gz: 91402727cff066c16adf1f29a8b9a156dc2c175de887760b2e343fe49caed6ab97f6c8bfd190b034bf8add13095c60553f71eda75b5890b2c96bddfc82682c7a

data/lib/discovery-indexer.rb

@@ -1,3 +1,6 @@
+require 'errors'
+require 'logging'
+
 require 'reader/purlxml'
 require 'reader/purlxml_reader'
 require 'reader/purlxml_parser'
@@ -15,7 +18,6 @@ require 'writer/solr_writer'
 
 #require 'utilities/extract_sub_targets'
 
-require 'errors'
 
 module DiscoveryIndexer
   PURL_DEFAULT = 'http://purl-test.stanford.edu'

data/lib/logging.rb

@@ -0,0 +1,16 @@
+require 'logger'
+
+module DiscoveryIndexer
+  module Logging
+    class << self
+      def logger
+        @logger ||= Logger.new(STDOUT)
+      end
+  
+      def logger=(logger)
+        @logger = logger
+      end
+    end
+
+  end
+end

data/lib/reader/modsxml.rb

@@ -5,9 +5,9 @@ module DiscoveryIndexer
     # 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()
+    #  druid = "aa111aa1111"
+    #  p =  DiscoveryIndexer::InputXml::Modsxml.new(druid)
+    #  model =  p.load()
     # 
     # 
     class Modsxml

data/lib/reader/purlxml.rb

@@ -4,9 +4,9 @@ module DiscoveryIndexer
     # 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()
+    #  druid = "aa111aa1111"
+    #  p =  DiscoveryIndexer::InputXml::Purlxml.new(druid)
+    #  model =  p.load()
     # 
     class Purlxml
       

data/lib/reader/purlxml_model.rb

@@ -1,21 +1,75 @@
 module DiscoveryIndexer
   module InputXml
     class PurlxmlModel
+      
+      #@!attribute [rw] public_xml
+      # @return [Nokogiri::XML] The publix xml as retrieved from purl server 
       attr_accessor :public_xml
+
+      #@!attribute [rw] content_metadata
+      # @return [Nokogiri::XML] The content_metadata as extracted from public xml
       attr_accessor :content_metadata
+
+      #@!attribute [rw] identity_metadata
+      # @return [Nokogiri::XML] The identity_metadata as extracted from public xml
       attr_accessor :identity_metadata
+
+      #@!attribute [rw] rights_metadata
+      # @return [Nokogiri::XML] The rights_metadata as extracted from public xml
       attr_accessor :rights_metadata
+
+      #@!attribute [rw] dc
+      # @return [Nokogiri::XML] The dc element as extracted from public xml
       attr_accessor :dc
+      
+      #@!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 asextracted from public xml
+      #  identity_metadata. 
+      # @example
+      #  !{"target1"=>true, "target2"=>false}
       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] 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
-      attr_accessor :dor_content_type
+      
+      # @!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"]   
       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"]   
       attr_accessor :image_ids
+      
+      # @!attribute [rw] catkey
+      # @return [String] the catkey attribute in identity_metadata
       attr_accessor :catkey
+
+      # @!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
       
     end

data/lib/reader/purlxml_parser_strict.rb

@@ -34,7 +34,7 @@ module DiscoveryIndexer
       
       # 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
+      # @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)
@@ -113,13 +113,9 @@ 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
-     #   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 = nil 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
@@ -153,18 +149,18 @@ module DiscoveryIndexer
       # @return [String] 
       def parse_dor_content_type
         content_md = parse_content_metadata
-        dct = content_md ? content_md.xpath('@type').text : nil
+        dct = content_md ? content_md.xpath('contentMetadata/@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
+      # 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|
+            content_md.xpath('//resource[@type="image"]/file/@id').each { |node|
               ids << node.text if !node.text.empty?
             }
           return nil if ids.empty?
@@ -172,11 +168,13 @@ module DiscoveryIndexer
         end
       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|
+            content_md.xpath('//resource/file/@id').each { |node|
               ids << node.text if !node.text.empty?
             }
           return nil if ids.empty?
@@ -184,6 +182,7 @@ module DiscoveryIndexer
         end 
       end
       
+      # @return catkey value from the DOR identity_metadata, or nil if there is no catkey
       def parse_catkey
         catkey = nil
         node = @purlxml_ng_doc.xpath("/publicObject/identityMetadata/otherId[@name='catkey']") 
@@ -191,6 +190,7 @@ module DiscoveryIndexer
         return catkey
       end
 
+      # @return barcode value from the DOR identity_metadata, or nil if there is no barcode
       def parse_barcode
         barcode = nil
         node = @purlxml_ng_doc.xpath("/publicObject/identityMetadata/otherId[@name='barcode']")
@@ -198,6 +198,7 @@ module DiscoveryIndexer
         return barcode
       end
 
+      # @return objectLabel value from the DOR identity_metadata, or nil if there is no barcode
       def parse_label
         label = nil
         node = @purlxml_ng_doc.xpath("/publicObject/identityMetadata/objectLabel")

data/lib/version.rb

@@ -1,3 +1,3 @@
 module DiscoveryIndexer
-    VERSION = '0.1'
+    VERSION = '0.2.1'
 end

data/lib/writer/solr_client.rb

@@ -4,7 +4,8 @@ require 'rsolr'
 module DiscoveryIndexer
   module Writer
     class SolrClient
-      
+      include DiscoveryIndexer::Logging
+
       # 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
@@ -24,22 +25,21 @@ module DiscoveryIndexer
       end
       
       def self.process(solr_doc, solr_connector, max_retries, is_delete=false)
-       logger  = Logger.new STDOUT
-       id = solr_doc[:id]
+        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}"
+          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|
-          logger.debug "Attempt #{attempt} for #{id}"
+          DiscoveryIndexer::Logging.logger.debug "Attempt #{attempt} for #{id}"
           
           if is_delete
             solr_connector.delete_by_id(id)
-            logger.info "Successfully deleted #{id} on attempt #{attempt}"
+            DiscoveryIndexer::Logging.logger.info "Successfully deleted #{id} on attempt #{attempt}"
           else
             solr_connector.add(solr_doc)
-            logger.info "Successfully indexed #{id} on attempt #{attempt}"
+            DiscoveryIndexer::Logging.logger.info "Successfully indexed #{id} on attempt #{attempt}"
           end
           
         end

data/lib/writer/solr_writer.rb

@@ -4,6 +4,7 @@ require 'rsolr'
 module DiscoveryIndexer
   module Writer
     class SolrWriter
+      include DiscoveryIndexer::Logging
       
       def process(druid, index_doc, targets, solr_targets_configs)
         @solr_targets_configs = solr_targets_configs
@@ -47,8 +48,6 @@ module DiscoveryIndexer
 
       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)

metadata

@@ -1,125 +1,125 @@
 --- !ruby/object:Gem::Specification
 name: discovery-indexer
 version: !ruby/object:Gem::Version
-  version: '0.1'
+  version: 0.2.1
 platform: ruby
 authors:
 - Ahmed AlSum
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-03-19 00:00:00.000000000 Z
+date: 2015-03-23 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
@@ -131,6 +131,7 @@ extra_rdoc_files: []
 files:
 - lib/discovery-indexer.rb
 - lib/errors.rb
+- lib/logging.rb
 - lib/mapper/general_mapper.rb
 - lib/mapper/index_mapper.rb
 - lib/reader/modsxml.rb
@@ -154,12 +155,12 @@ 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: []