discovery-indexer 3.0.1 → 3.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 32f16c9c6a49b290815357fa39f9aad6dd53ed4e
-  data.tar.gz: e110a3a509c0e8e354c42949418acb6f7ba39eab
+  metadata.gz: 9f64eea714259a5affc67b00288a36ad0748f5b7
+  data.tar.gz: bf28bbd7dfef5326c5b47b67a38ed8993b297d03
 SHA512:
-  metadata.gz: bf0e4464eb5fc84e5a821816502e4c58e526bec8720986fd5e8f979d79d5f034959f444c9331bb201b79a9e78def6ef2c74543e0b4d710d6075e06bd13ce3ee4
-  data.tar.gz: b43ad5545d7068c9d4e9ea3758b7bff0c7dd593199a42b8fc606f5f61ab72fb9fc000d0fe1d436ed93069dd80113ecabed0f1b8a0d4de85a9f473bb4783130d0
+  metadata.gz: d0ba91632921efb45a5c0cee754d5681a48420dc7c35799b654b92ff3c3a962b68f5a422c70a89928e6ab1c4f0b0281161828dccbaba5dd91f3d788207d0c648
+  data.tar.gz: a4f79864d64473a0409447c2c8f1d7d791eeea0edd87b9956bafa1571997248a4d0381e3d83bd8af7c8a65f7070ff1f8db15d4d30a43ce8bae09cf123618b27e

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

@@ -69,6 +69,12 @@ module DiscoveryIndexer
       #  ["pc0065_b08_f10_i031.jp2","pc0065_b08_f10_i032.jp2"]
       attr_accessor :image_ids
 
+      # @!attribute [rw] thumb
+      # @return [String] a thumbnail image if it exists in the PURL
+      # @example
+      #  "oo000oo0001/pc0065_b08_f10_i031.jp2"
+      attr_accessor :thumb
+
       # @!attribute [rw] sw_image_ids
       # @return [Array] a list of the image ids and corresponding druids with %2F
       #  separator from the file and externalFile tags in the content_metadata

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

@@ -30,6 +30,7 @@ module DiscoveryIndexer
         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.thumb             = parse_thumb
         purlxml_model.image_ids         = parse_image_ids
         purlxml_model.sw_image_ids      = parse_sw_image_ids
         purlxml_model.catkey            = parse_catkey
@@ -142,16 +143,42 @@ module DiscoveryIndexer
         content_md.xpath('//resource[@type="page" or @type="image" or @type="thumb"]/file[@mimetype="image/jp2"]/@id').map(&:to_s)
       end
 
+      # the thumbnail in publicXML, falling back to the first image if no thumb node is found
+      # @return [String] thumb filename with druid prepended, e.g. oo000oo0001/filename withspace.jp2
+      def parse_thumb
+        unless @purlxml_ng_doc.nil?
+          thumb = @purlxml_ng_doc.xpath('//thumb')
+          # first try and parse what is in the thumb node of publicXML, but fallback to the first image if needed
+          if thumb.size == 1
+            thumb.first.content
+          elsif thumb.size == 0 && parse_sw_image_ids.size > 0
+            parse_sw_image_ids.first
+          else
+            nil
+          end
+        end
+      end
+
+      # the thumbnail in publicXML properly URI encoded, including the slash separator 
+      # @return [String] thumb filename with druid prepended, e.g. oo000oo0001%2Ffilename%20withspace.jp2
+      def encoded_thumb
+        thumb=parse_thumb
+        return unless thumb
+        thumb_druid=thumb.split('/').first # the druid (before the first slash)
+        thumb_filename=thumb.split(/[a-zA-Z]{2}[0-9]{3}[a-zA-Z]{2}[0-9]{4}[\/]/).last # everything after the druid
+        "#{thumb_druid}%2F#{URI.escape(thumb_filename)}"
+      end
+      
       # the druid and id attribute of resource/file and objectId and fileId of the
       # resource/externalFile elements that match the image, page, or thumb resource type, including extension
-      # Also, prepends the corresponding druid and %2F specifically for Searchworks use
+      # Also, prepends the corresponding druid and / specifically for Searchworks use
       # @return [Array<String>] filenames
       def parse_sw_image_ids
         content_md = parse_content_metadata
         return [] if content_md.nil?
         content_md.xpath('//resource[@type="page" or @type="image" or @type="thumb"]').map do |node|
-          node.xpath('./file[@mimetype="image/jp2"]/@id').map{ |x| "#{@druid}%2F" + x } << node.xpath('./externalFile[@mimetype="image/jp2"]').map do |y|
-            "#{y.attributes['objectId'].text.split(':').last}" + "%2F" + "#{y.attributes['fileId']}"
+          node.xpath('./file[@mimetype="image/jp2"]/@id').map{ |x| "#{@druid.gsub('druid:','')}/" + x } << node.xpath('./externalFile[@mimetype="image/jp2"]').map do |y|
+            "#{y.attributes['objectId'].text.split(':').last}" + "/" + "#{y.attributes['fileId']}"
           end
         end.flatten
       end

data/lib/discovery-indexer/version.rb

@@ -1,3 +1,3 @@
 module DiscoveryIndexer
-  VERSION = '3.0.1'
+  VERSION = '3.1.0'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: discovery-indexer
 version: !ruby/object:Gem::Version
-  version: 3.0.1
+  version: 3.1.0
 platform: ruby
 authors:
 - Ahmed AlSum
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-09-22 00:00:00.000000000 Z
+date: 2016-10-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -232,7 +232,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.5.1
+rubygems_version: 2.6.7
 signing_key: 
 specification_version: 4
 summary: Shared library for the basic discovery indexing operation for Stanford DLSS.