spotlight-dor-resources 0.3.1 → 0.3.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 534c3d40d1d186aca706291383b277b9cb0e0cf5
-  data.tar.gz: 53c135866d04b314fea7bfb3bf9928552bd1ee85
+  metadata.gz: df866b5840fd2ef1f3068c6244ef96aaf50f463b
+  data.tar.gz: 484fb0089d890785d1b7cbfa9560cd7a95f9b83c
 SHA512:
-  metadata.gz: b938262cb1da8a5fc3fc1e6c683ec34d502306bd3b0ccbf917d19141907203226af358649bad002e00ade0539a83793756e6e7a6f7bfd0c9fc093ed7f2b8a468
-  data.tar.gz: d377966f349fc1e1d627985e095729a7a76cbb1d24eb4afbd003c5375be501da5e50c72f93391e6136dddb8ac274aa657ceda00b98e3b69dae5f87c7b293cbb6
+  metadata.gz: 1dee32477104678ade84fc9ccdc0400c56a2981af353063dac19a6415938e2c010e2c7f3137bb1b4cd06cad33afb47863bb518205db044e2221612d5291af413
+  data.tar.gz: f2b17bd142699edda90806158fcd60dba2ad687d28d16b22c08fae04df58f2e79a2705d2603e0d8010a8ea37f53606647f8d140f770ed71e79254bf01994e803

data/README.md

@@ -1,4 +1,4 @@
-[![Build Status](https://travis-ci.org/sul-dlss/spotlight-dor-resources.png?branch=master)](https://travis-ci.org/sul-dlss/spotlight-dor-resources) | [![Coverage Status](https://coveralls.io/repos/sul-dlss/spotlight-dor-resources/badge.png?branch=master)](https://coveralls.io/r/sul-dlss/spotlight-dor-resources) | [![Gem Version](https://badge.fury.io/rb/spotlight-dor-resources.png)](http://badge.fury.io/rb/spotlight-dor-resources)
+[![Build Status](https://travis-ci.org/sul-dlss/spotlight-dor-resources.png?branch=master)](https://travis-ci.org/sul-dlss/spotlight-dor-resources) | [![Coverage Status](https://coveralls.io/repos/sul-dlss/spotlight-dor-resources/badge.png?branch=master)](https://coveralls.io/r/sul-dlss/spotlight-dor-resources) | [![Dependency Status](https://gemnasium.com/sul-dlss/spotlight-dor-resources.svg)](https://gemnasium.com/sul-dlss/spotlight-dor-resources) | [![Gem Version](https://badge.fury.io/rb/spotlight-dor-resources.png)](http://badge.fury.io/rb/spotlight-dor-resources)
 
 # Spotlight::Dor::Resources
 
@@ -34,7 +34,7 @@ For access to a Rails console with the gem loaded up for testing purposes, you c
 ### First time only configuration for local testing
 
     $ bundle
-    $ bundle exec rake:ci
+    $ bundle exec rake ci
 
 This will download a test jetty instance (to run Solr), generate a testing app at ```.internal_test_app``` and run the tests.
 

data/lib/spotlight/dor/indexer.rb

@@ -32,9 +32,11 @@ module Spotlight::Dor
         before_index :add_author_no_collector
         before_index :add_box
         before_index :add_collector
+        before_index :add_coordinates
         before_index :add_folder
         before_index :add_genre
         before_index :add_location
+        before_index :add_point_bbox
         before_index :add_series
       end
 
@@ -48,6 +50,12 @@ module Spotlight::Dor
         solr_doc['box_ssi'] = sdb.smods_rec.box
       end
 
+      # add coordinates solr field containing the cartographic coordinates per
+      # MODS subject.cartographics.coordinates (via stanford-mods gem)
+      def add_coordinates(sdb, solr_doc)
+        solr_doc['coordinates'] = sdb.smods_rec.coordinates
+      end
+
       # add collector_ssim solr field containing the collector per MODS names (via stanford-mods gem)
       def add_collector(sdb, solr_doc)
         insert_field solr_doc, 'collector', sdb.smods_rec.collectors_w_dates, :symbol # _ssim field
@@ -66,10 +74,16 @@ module Spotlight::Dor
         solr_doc['location_ssi'] = sdb.smods_rec.location
       end
 
+      # add point_bbox solr field containing the point bounding box per
+      # MODS subject.cartographics.coordinates (via stanford-mods gem)
+      def add_point_bbox(sdb, solr_doc)
+        solr_doc['point_bbox'] = sdb.smods_rec.point_bbox
+      end
+
       def add_series(sdb, solr_doc)
         solr_doc['series_ssi'] = sdb.smods_rec.series
       end
-    end
+    end # StanfordMods concern
 
     concerning :ContentMetadata do
       included do
@@ -125,8 +139,15 @@ module Spotlight::Dor
       # only create these fields on an as-needed basis.
 
       included do
+        before_index :add_document_subtype
         before_index :add_donor_tags
         before_index :add_folder_name
+        before_index :add_general_notes
+      end
+
+      def add_document_subtype(sdb, solr_doc)
+        subtype = sdb.smods_rec.note.select { |n| n.displayLabel == 'Document subtype' }.map(&:content)
+        solr_doc['doc_subtype_ssi'] = subtype.first if subtype.size > 0
       end
 
       def add_donor_tags(sdb, solr_doc)
@@ -142,7 +163,12 @@ module Spotlight::Dor
         match_data = preferred_citation.first.match(/Title: +(.+)/i) if preferred_citation.present?
         solr_doc['folder_name_ssi'] = match_data[1].strip if match_data.present?
       end
-    end
+
+      def add_general_notes(sdb, solr_doc)
+        general_notes = sdb.smods_rec.note.select { |n| n.type_at.blank? && n.displayLabel.blank? }.map(&:content)
+        insert_field solr_doc, 'general_notes', general_notes, :symbol # this is a _ssim field
+      end
+    end # end feigbenbaum specific fields
 
     concerning :FullTextIndexing do
       included do
@@ -187,51 +213,6 @@ module Spotlight::Dor
       end
     end
 
-    concerning :CartographicIndexing do
-      included do
-        before_index :mods_cartographics_indexing
-      end
-
-      def mods_cartographics_indexing(sdb, solr_doc)
-        coordinates = Array(sdb.smods_rec.subject.cartographics.coordinates)
-
-        insert_field(solr_doc, 'coordinates', coordinates.map(&:text), :stored_searchable)
-
-        solr_doc['point_bbox'] ||= []
-        solr_doc['point_bbox'] += coords_to_bboxes(coordinates)
-      end
-
-      private
-
-      def coords_to_bboxes(coordinates)
-        coordinates.select { |n| n.text =~ /^\(.*\)$/ }.map do |n|
-          coord_to_bbox(n.text)
-        end
-      end
-
-      def coord_to_bbox(coord)
-        bbox = coord.delete('(').delete(')')
-
-        lng, lat = bbox.split('/')
-
-        min_x, max_x = lng.split('--').map { |x| coord_to_decimal(x) }
-        max_y, min_y = lat.split('--').map { |y| coord_to_decimal(y) }
-        "#{min_x} #{min_y} #{max_x} #{max_y}"
-      end
-
-      def coord_to_decimal(point)
-        regex = /(?<dir>[NESW])\s*(?<deg>\d+)°(?:(?<sec>\d+)ʹ)?/
-        match = regex.match(point)
-        dec = 0
-
-        dec += match['deg'].to_i
-        dec += match['sec'].to_f / 60
-        dec = -1 * dec if match['dir'] == 'W' || match['dir'] == 'S'
-
-        dec
-      end
-    end
-
     def insert_field(solr_doc, field, values, *args)
       Array(values).each do |v|
         Solrizer.insert_field solr_doc, field, v, *args

data/lib/spotlight/dor/resources.rb

@@ -20,7 +20,7 @@ module Spotlight
         end
 
         def solr_config
-          Blacklight.solr_config
+          Blacklight.connection_config
         end
       end
     end

data/lib/spotlight/dor/resources/version.rb

@@ -2,7 +2,7 @@ module Spotlight
   module Dor
     # :nodoc:
     module Resources
-      VERSION = '0.3.1'
+      VERSION = '0.3.2'
     end
   end
 end

data/spec/lib/spotlight/dor/indexer_spec.rb

@@ -76,49 +76,188 @@ describe Spotlight::Dor::Indexer do
     end
   end
 
-  describe '#add_donor_tags' do
-    before do
-      allow(r).to receive(:mods).and_return(mods)
-      subject.send(:add_donor_tags, sdb, solr_doc)
-    end
+  context 'Feigbenbaum specific fields concern' do
+    describe '#add_document_subtype' do
+      before do
+        allow(r).to receive(:mods).and_return(mods)
+        subject.send(:add_document_subtype, sdb, solr_doc)
+      end
 
-    context 'with a record without donor tags' do
-      let(:mods) do
-        Nokogiri::XML <<-EOF
-          <mods xmlns="#{Mods::MODS_NS}">
-            <note displayLabel="preferred citation">(not a donor tag)</note>
-          </mods>
-          EOF
+      context 'with a record without document subtype' do
+        let(:mods) do
+          Nokogiri::XML <<-EOF
+            <mods xmlns="#{Mods::MODS_NS}">
+              <note displayLabel="preferred citation">(not a document subtype)</note>
+              <note>a generic note</note>
+            </mods>
+            EOF
+        end
+
+        it 'is blank' do
+          expect(solr_doc['doc_subtype_ssi']).to be_blank
+        end
       end
 
-      it 'is blank' do
-        expect(solr_doc['donor_tags_ssim']).to be_blank
+      context 'with a record with document subtype' do
+        let(:mods) do
+          Nokogiri::XML <<-EOF
+            <mods xmlns="#{Mods::MODS_NS}">
+              <note displayLabel="Document subtype">memorandums</note>
+              <note>a generic note</note>
+            </mods>
+            EOF
+        end
+
+        it 'extracts the doc subtypes' do
+          expect(solr_doc['doc_subtype_ssi']).to eq('memorandums')
+        end
       end
-    end
+    end # doc subtype
 
-    context 'with a record with donor tags' do
-      let(:mods) do
-        # e.g. from https://purl.stanford.edu/vw282gv1740
+    describe '#add_donor_tags' do
+      before do
+        allow(r).to receive(:mods).and_return(mods)
+        subject.send(:add_donor_tags, sdb, solr_doc)
+      end
+
+      context 'with a record without donor tags' do
+        let(:mods) do
+          Nokogiri::XML <<-EOF
+            <mods xmlns="#{Mods::MODS_NS}">
+              <note displayLabel="preferred citation">(not a donor tag)</note>
+            </mods>
+            EOF
+        end
+
+        it 'is blank' do
+          expect(solr_doc['donor_tags_ssim']).to be_blank
+        end
+      end
+
+      context 'with a record with donor tags' do
+        let(:mods) do
+          # e.g. from https://purl.stanford.edu/vw282gv1740
+          Nokogiri::XML <<-EOF
+            <mods xmlns="#{Mods::MODS_NS}">
+              <note displayLabel="Donor tags">Knowledge Systems Laboratory</note>
+              <note displayLabel="Donor tags">medical applications</note>
+              <note displayLabel="Donor tags">Publishing</note>
+              <note displayLabel="Donor tags">Stanford</note>
+              <note displayLabel="Donor tags">Stanford Computer Science Department</note>
+            </mods>
+            EOF
+        end
+
+        it 'extracts the donor tags' do
+          expect(solr_doc['donor_tags_ssim']).to contain_exactly 'Knowledge Systems Laboratory',
+                                                                 'medical applications',
+                                                                 'Publishing',
+                                                                 'Stanford',
+                                                                 'Stanford Computer Science Department'
+        end
+      end
+    end # donor tags
+
+    # rubocop:disable Metrics/LineLength
+    describe '#add_folder_name' do
+      let(:mods_note_plain) do
         Nokogiri::XML <<-EOF
           <mods xmlns="#{Mods::MODS_NS}">
-            <note displayLabel="Donor tags">Knowledge Systems Laboratory</note>
-            <note displayLabel="Donor tags">medical applications</note>
-            <note displayLabel="Donor tags">Publishing</note>
-            <note displayLabel="Donor tags">Stanford</note>
-            <note displayLabel="Donor tags">Stanford Computer Science Department</note>
+            <note>#{example}</note>
           </mods>
-          EOF
+        EOF
       end
+      let(:mods_note_preferred_citation) do
+        Nokogiri::XML <<-EOF
+          <mods xmlns="#{Mods::MODS_NS}">
+            <note type="preferred citation">#{example}</note>
+          </mods>
+        EOF
+      end
+      # example string as key, expected folder name as value
+      # all from feigenbaum (or based on feigenbaum), as that is only coll with this data
+      {
+        'Call Number: SC0340, Accession: 1986-052, Box: 20, Folder: 40, Title: S': 'S',
+        'Call Number: SC0340, Accession: 1986-052, Box: 54, Folder: 25, Title: Balzer': 'Balzer',
+        'Call Number: SC0340, Accession: 1986-052, Box : 30, Folder: 21, Title: Feigenbaum, Publications. 2 of 2.': 'Feigenbaum, Publications. 2 of 2.',
+        # colon in name
+        'Call Number: SC0340, Accession 2005-101, Box: 10, Folder: 26, Title: Gordon Bell Letter rdf:about blah (AI) 1987': 'Gordon Bell Letter rdf:about blah (AI) 1987',
+        'Call Number: SC0340, Accession 2005-101, Box: 11, Folder: 74, Title: Microcomputer Systems Proposal: blah blah': 'Microcomputer Systems Proposal: blah blah',
+        'Call Number: SC0340, Accession 2005-101, Box: 14, Folder: 20, Title: blah "bleah: blargW^"ugh" seriously?.': 'blah "bleah: blargW^"ugh" seriously?.',
+        # quotes in name
+        'Call Number: SC0340, Accession 2005-101, Box: 29, Folder: 18, Title: "bleah" blah': '"bleah" blah',
+        'Call Number: SC0340, Accession 2005-101, Box: 11, Folder: 58, Title: "M": blah': '"M": blah',
+        'Call Number: SC0340, Accession 2005-101, Box : 32A, Folder: 19, Title: blah "bleah" blue': 'blah "bleah" blue',
+        # not parseable
+        'Call Number: SC0340, Accession 2005-101': nil,
+        'Call Number: SC0340, Accession: 1986-052': nil,
+        'Call Number: SC0340, Accession: 1986-052, Box 36 Folder 38': nil,
+        'blah blah ... with the umbrella title Feigenbaum and Feldman, Computers and Thought II. blah blah': nil,
+        'blah blah ... Title ... blah blah': nil
+      }.each do |example, expected|
+        describe "for example '#{example}'" do
+          let(:example) { example }
+          context 'in preferred citation note' do
+            before do
+              allow(r).to receive(:mods).and_return(mods_note_preferred_citation)
+              subject.send(:add_folder_name, sdb, solr_doc)
+            end
+            it "has the expected folder name '#{expected}'" do
+              expect(solr_doc['folder_name_ssi']).to eq expected
+            end
+          end
+          context 'in plain note' do
+            before do
+              allow(r).to receive(:mods).and_return(mods_note_plain)
+              subject.send(:add_folder_name, sdb, solr_doc)
+            end
+            it 'does not have a folder name' do
+              expect(solr_doc['folder_name_ssi']).to be_falsey
+            end
+          end
+        end # for example
+      end # each
+    end # add_folder_name
+    # rubocop:enable Metrics/LineLength
 
-      it 'extracts the donor tags' do
-        expect(solr_doc['donor_tags_ssim']).to contain_exactly 'Knowledge Systems Laboratory',
-                                                               'medical applications',
-                                                               'Publishing',
-                                                               'Stanford',
-                                                               'Stanford Computer Science Department'
+    describe '#add_general_notes' do
+      before do
+        allow(r).to receive(:mods).and_return(mods)
+        subject.send(:add_general_notes, sdb, solr_doc)
       end
-    end
-  end
+
+      context 'no general notes, but other types of notes' do
+        let(:mods) do
+          Nokogiri::XML <<-EOF
+            <mods xmlns="#{Mods::MODS_NS}">
+              <note displayLabel="preferred citation">(not a document subtype)</note>
+              <note displayLabel="Document subtype">memorandums</note>
+              <note displayLabel="Donor tags">Knowledge Systems Laboratory</note>
+            </mods>
+            EOF
+        end
+
+        it 'is blank' do
+          expect(solr_doc['general_notes_ssim']).to be_blank
+        end
+      end
+
+      context 'ignore extra notes' do
+        let(:mods) do
+          Nokogiri::XML <<-EOF
+            <mods xmlns="#{Mods::MODS_NS}">
+              <note displayLabel="Document subtype">memorandums</note>
+              <note>a generic note</note>
+            </mods>
+            EOF
+        end
+
+        it 'extracts the doc subtypes' do
+          expect(solr_doc['general_notes_ssim']).to contain_exactly 'a generic note'
+        end
+      end
+    end # general notes
+  end # feigbenbaum specific fields concern
 
   context 'StanfordMods concern' do
     describe '#add_author_no_collector' do
@@ -216,6 +355,44 @@ describe Spotlight::Dor::Indexer do
       end
     end
 
+    describe '#add_coordinates' do
+      before do
+        allow(r).to receive(:mods).and_return(mods)
+        subject.send(:add_coordinates, sdb, solr_doc)
+      end
+      context 'with a record without coordinates' do
+        let(:mods) do
+          Nokogiri::XML <<-EOF
+            <mods xmlns="#{Mods::MODS_NS}">
+            </mods>
+          EOF
+        end
+
+        it 'is blank' do
+          expect(solr_doc['coordinates']).to be_blank
+        end
+      end
+      context 'with a record with coordinates' do
+        let(:mods) do
+          # e.g. from https://purl.stanford.edu/vw282gv1740
+          Nokogiri::XML <<-EOF
+            <mods xmlns="#{Mods::MODS_NS}">
+              <subject>
+                <cartographics>
+                  <scale>Scale 1:500,000</scale>
+                  <coordinates>(W16°--E28°/N13°--S15°).</coordinates>
+                </cartographics>
+              </subject>
+            </mods>
+          EOF
+        end
+
+        it 'extracts the coordinates' do
+          expect(solr_doc['coordinates']).to eq(['(W16°--E28°/N13°--S15°).'])
+        end
+      end
+    end # add_coordinates
+
     describe '#add_folder' do
       before do
         allow(r).to receive(:mods).and_return(mods)
@@ -321,6 +498,44 @@ describe Spotlight::Dor::Indexer do
       end
     end # add_location
 
+    describe '#add_point_bbox' do
+      before do
+        allow(r).to receive(:mods).and_return(mods)
+        subject.send(:add_point_bbox, sdb, solr_doc)
+      end
+      context 'with a record without coordinates' do
+        let(:mods) do
+          Nokogiri::XML <<-EOF
+            <mods xmlns="#{Mods::MODS_NS}">
+            </mods>
+          EOF
+        end
+
+        it 'is blank' do
+          expect(solr_doc['point_bbox']).to be_blank
+        end
+      end
+      context 'with a record with coordinates' do
+        let(:mods) do
+          # e.g. from https://purl.stanford.edu/vw282gv1740
+          Nokogiri::XML <<-EOF
+            <mods xmlns="#{Mods::MODS_NS}">
+              <subject>
+                <cartographics>
+                  <scale>Scale 1:500,000</scale>
+                  <coordinates>(W16°--E28°/N13°--S15°).</coordinates>
+                </cartographics>
+              </subject>
+            </mods>
+          EOF
+        end
+
+        it 'extracts the point_bbox' do
+          expect(solr_doc['point_bbox']).to eq(['-16.0 -15.0 28.0 13.0'])
+        end
+      end
+    end # add_point_bbox
+
     describe '#add_series' do
       before do
         allow(r).to receive(:mods).and_return(mods)
@@ -358,139 +573,81 @@ describe Spotlight::Dor::Indexer do
   end # context StanfordMods concern
 
   # rubocop:disable Metrics/LineLength
-  describe '#add_folder_name' do
-    let(:mods_note_plain) do
-      Nokogiri::XML <<-EOF
-        <mods xmlns="#{Mods::MODS_NS}">
-          <note>#{example}</note>
-        </mods>
-      EOF
-    end
-    let(:mods_note_preferred_citation) do
-      Nokogiri::XML <<-EOF
-        <mods xmlns="#{Mods::MODS_NS}">
-          <note type="preferred citation">#{example}</note>
-        </mods>
-      EOF
-    end
-    # example string as key, expected folder name as value
-    # all from feigenbaum (or based on feigenbaum), as that is only coll with this data
-    {
-      'Call Number: SC0340, Accession: 1986-052, Box: 20, Folder: 40, Title: S': 'S',
-      'Call Number: SC0340, Accession: 1986-052, Box: 54, Folder: 25, Title: Balzer': 'Balzer',
-      'Call Number: SC0340, Accession: 1986-052, Box : 30, Folder: 21, Title: Feigenbaum, Publications. 2 of 2.': 'Feigenbaum, Publications. 2 of 2.',
-      # colon in name
-      'Call Number: SC0340, Accession 2005-101, Box: 10, Folder: 26, Title: Gordon Bell Letter rdf:about blah (AI) 1987': 'Gordon Bell Letter rdf:about blah (AI) 1987',
-      'Call Number: SC0340, Accession 2005-101, Box: 11, Folder: 74, Title: Microcomputer Systems Proposal: blah blah': 'Microcomputer Systems Proposal: blah blah',
-      'Call Number: SC0340, Accession 2005-101, Box: 14, Folder: 20, Title: blah "bleah: blargW^"ugh" seriously?.': 'blah "bleah: blargW^"ugh" seriously?.',
-      # quotes in name
-      'Call Number: SC0340, Accession 2005-101, Box: 29, Folder: 18, Title: "bleah" blah': '"bleah" blah',
-      'Call Number: SC0340, Accession 2005-101, Box: 11, Folder: 58, Title: "M": blah': '"M": blah',
-      'Call Number: SC0340, Accession 2005-101, Box : 32A, Folder: 19, Title: blah "bleah" blue': 'blah "bleah" blue',
-      # not parseable
-      'Call Number: SC0340, Accession 2005-101': nil,
-      'Call Number: SC0340, Accession: 1986-052': nil,
-      'Call Number: SC0340, Accession: 1986-052, Box 36 Folder 38': nil,
-      'blah blah ... with the umbrella title Feigenbaum and Feldman, Computers and Thought II. blah blah': nil,
-      'blah blah ... Title ... blah blah': nil
-    }.each do |example, expected|
-      describe "for example '#{example}'" do
-        let(:example) { example }
-        context 'in preferred citation note' do
-          before do
-            allow(r).to receive(:mods).and_return(mods_note_preferred_citation)
-            subject.send(:add_folder_name, sdb, solr_doc)
-          end
-          it "has the expected folder name '#{expected}'" do
-            expect(solr_doc['folder_name_ssi']).to eq expected
-          end
-        end
-        context 'in plain note' do
-          before do
-            allow(r).to receive(:mods).and_return(mods_note_plain)
-            subject.send(:add_folder_name, sdb, solr_doc)
-          end
-          it 'does not have a folder name' do
-            expect(solr_doc['folder_name_ssi']).to be_falsey
-          end
-        end
-      end # for example
-    end # each
-  end # add_folder_name
+  context 'Full Text Indexing concern' do
+    describe '#add_object_full_text' do
+      let(:full_text_solr_fname) { 'full_text_tesimv' }
+      before do
+        allow(sdb).to receive(:bare_druid).and_return(fake_druid)
+      end
+      let!(:expected_text) { 'SOME full text string that is returned from the server' }
+      let!(:full_file_path) { 'https://stacks.stanford.edu/file/oo000oo0000/oo000oo0000.txt' }
+      it 'indexes the full text into the appropriate field if a recognized file pattern is found' do
+        public_xml_with_feigenbaum_full_text = Nokogiri::XML <<-EOF
+          <publicObject id="druid:oo000oo0000" published="2015-10-17T18:24:08-07:00">
+            <contentMetadata objectId="oo000oo0000" type="book">
+              <resource id="oo000oo0000_4" sequence="4" type="object">
+                <label>Document</label>
+                <file id="oo000oo0000.pdf" mimetype="application/pdf" size="6801421"></file>
+                <file id="oo000oo0000.txt" mimetype="text/plain" size="23376"></file>
+              </resource>
+              <resource id="oo000oo0000_5" sequence="5" type="page">
+                <label>Page 1</label>
+                <file id="oo000oo0000_00001.jp2" mimetype="image/jp2" size="1864266"><imageData width="2632" height="3422"/></file>
+              </resource>
+              </contentMetadata>
+            </publicObject>
+          EOF
+        allow(sdb).to receive(:public_xml).and_return(public_xml_with_feigenbaum_full_text)
+        # don't actually attempt a call to the stacks
+        allow(subject).to receive(:get_file_content).with(full_file_path).and_return(expected_text)
+        subject.send(:add_object_full_text, sdb, solr_doc)
+        expect(subject.object_level_full_text_urls(sdb)).to eq [full_file_path]
+        expect(solr_doc[full_text_solr_fname]).to eq [expected_text]
+      end
+      it 'does not index the full text if no recognized pattern is found' do
+        public_xml_with_no_recognized_full_text = Nokogiri::XML <<-EOF
+          <publicObject id="druid:oo000oo0000" published="2015-10-17T18:24:08-07:00">
+            <contentMetadata objectId="oo000oo0000" type="book">
+              <resource id="oo000oo0000_4" sequence="4" type="object">
+                <label>Document</label>
+                <file id="oo000oo0000.pdf" mimetype="application/pdf" size="6801421"></file>
+              </resource>
+              <resource id="oo000oo0000_5" sequence="5" type="page">
+                <label>Page 1</label>
+                <file id="oo000oo0000_00001.jp2" mimetype="image/jp2" size="1864266"><imageData width="2632" height="3422"/></file>
+              </resource>
+              </contentMetadata>
+            </publicObject>
+          EOF
+        allow(sdb).to receive(:public_xml).and_return(public_xml_with_no_recognized_full_text)
+        subject.send(:add_object_full_text, sdb, solr_doc)
+        expect(subject.object_level_full_text_urls(sdb)).to eq []
+        expect(solr_doc[full_text_solr_fname]).to be_nil
+      end
+      it 'indexes the full text from two files if two recognized patterns are found' do
+        public_xml_with_two_recognized_full_text_files = Nokogiri::XML <<-EOF
+          <publicObject id="druid:oo000oo0000" published="2015-10-17T18:24:08-07:00">
+            <contentMetadata objectId="oo000oo0000" type="book">
+              <resource id="oo000oo0000_4" sequence="4" type="object">
+                <label>Document</label>
+                <file id="oo000oo0000.pdf" mimetype="application/pdf" size="6801421"></file>
+                <file id="oo000oo0000.txt" mimetype="text/plain" size="23376"></file>
+              </resource>
+              <resource id="oo000oo0000_5" sequence="5" type="page">
+                <label>Page 1</label>
+                <file id="oo000oo0000_00001.jp2" mimetype="image/jp2" size="1864266"><imageData width="2632" height="3422"/></file>
+                <file id="oo000oo0000.txt" mimetype="text/plain" size="23376"></file>
+              </resource>
+              </contentMetadata>
+            </publicObject>
+          EOF
+        allow(sdb).to receive(:public_xml).and_return(public_xml_with_two_recognized_full_text_files)
+        allow(subject).to receive(:get_file_content).with(full_file_path).and_return(expected_text)
+        subject.send(:add_object_full_text, sdb, solr_doc)
+        expect(subject.object_level_full_text_urls(sdb)).to eq [full_file_path, full_file_path]
+        expect(solr_doc[full_text_solr_fname]).to eq [expected_text, expected_text] # same file twice in a 2 element array
+      end
+    end # add_object_full_text
+  end # full text indexing concern
   # rubocop:enable Metrics/LineLength
-
-  describe '#add_object_full_text' do
-    let(:full_text_solr_fname) { 'full_text_tesimv' }
-    before do
-      allow(sdb).to receive(:bare_druid).and_return(fake_druid)
-    end
-    let!(:expected_text) { 'SOME full text string that is returned from the server' }
-    let!(:full_file_path) { 'https://stacks.stanford.edu/file/oo000oo0000/oo000oo0000.txt' }
-    it 'indexes the full text into the appropriate field if a recognized file pattern is found' do
-      public_xml_with_feigenbaum_full_text = Nokogiri::XML <<-EOF
-        <publicObject id="druid:oo000oo0000" published="2015-10-17T18:24:08-07:00">
-          <contentMetadata objectId="oo000oo0000" type="book">
-            <resource id="oo000oo0000_4" sequence="4" type="object">
-              <label>Document</label>
-              <file id="oo000oo0000.pdf" mimetype="application/pdf" size="6801421"></file>
-              <file id="oo000oo0000.txt" mimetype="text/plain" size="23376"></file>
-            </resource>
-            <resource id="oo000oo0000_5" sequence="5" type="page">
-              <label>Page 1</label>
-              <file id="oo000oo0000_00001.jp2" mimetype="image/jp2" size="1864266"><imageData width="2632" height="3422"/></file>
-            </resource>
-            </contentMetadata>
-          </publicObject>
-        EOF
-      allow(sdb).to receive(:public_xml).and_return(public_xml_with_feigenbaum_full_text)
-      # don't actually attempt a call to the stacks
-      allow(subject).to receive(:get_file_content).with(full_file_path).and_return(expected_text)
-      subject.send(:add_object_full_text, sdb, solr_doc)
-      expect(subject.object_level_full_text_urls(sdb)).to eq [full_file_path]
-      expect(solr_doc[full_text_solr_fname]).to eq [expected_text]
-    end
-    it 'does not index the full text if no recognized pattern is found' do
-      public_xml_with_no_recognized_full_text = Nokogiri::XML <<-EOF
-        <publicObject id="druid:oo000oo0000" published="2015-10-17T18:24:08-07:00">
-          <contentMetadata objectId="oo000oo0000" type="book">
-            <resource id="oo000oo0000_4" sequence="4" type="object">
-              <label>Document</label>
-              <file id="oo000oo0000.pdf" mimetype="application/pdf" size="6801421"></file>
-            </resource>
-            <resource id="oo000oo0000_5" sequence="5" type="page">
-              <label>Page 1</label>
-              <file id="oo000oo0000_00001.jp2" mimetype="image/jp2" size="1864266"><imageData width="2632" height="3422"/></file>
-            </resource>
-            </contentMetadata>
-          </publicObject>
-        EOF
-      allow(sdb).to receive(:public_xml).and_return(public_xml_with_no_recognized_full_text)
-      subject.send(:add_object_full_text, sdb, solr_doc)
-      expect(subject.object_level_full_text_urls(sdb)).to eq []
-      expect(solr_doc[full_text_solr_fname]).to be_nil
-    end
-    it 'indexes the full text from two files if two recognized patterns are found' do
-      public_xml_with_two_recognized_full_text_files = Nokogiri::XML <<-EOF
-        <publicObject id="druid:oo000oo0000" published="2015-10-17T18:24:08-07:00">
-          <contentMetadata objectId="oo000oo0000" type="book">
-            <resource id="oo000oo0000_4" sequence="4" type="object">
-              <label>Document</label>
-              <file id="oo000oo0000.pdf" mimetype="application/pdf" size="6801421"></file>
-              <file id="oo000oo0000.txt" mimetype="text/plain" size="23376"></file>
-            </resource>
-            <resource id="oo000oo0000_5" sequence="5" type="page">
-              <label>Page 1</label>
-              <file id="oo000oo0000_00001.jp2" mimetype="image/jp2" size="1864266"><imageData width="2632" height="3422"/></file>
-              <file id="oo000oo0000.txt" mimetype="text/plain" size="23376"></file>
-            </resource>
-            </contentMetadata>
-          </publicObject>
-        EOF
-      allow(sdb).to receive(:public_xml).and_return(public_xml_with_two_recognized_full_text_files)
-      allow(subject).to receive(:get_file_content).with(full_file_path).and_return(expected_text)
-      subject.send(:add_object_full_text, sdb, solr_doc)
-      expect(subject.object_level_full_text_urls(sdb)).to eq [full_file_path, full_file_path]
-      expect(solr_doc[full_text_solr_fname]).to eq [expected_text, expected_text] # same file twice in a 2 element array
-    end
-  end # add_object_full_text
 end

data/spotlight-dor-resources.gemspec

@@ -25,8 +25,7 @@ Gem::Specification.new do |spec|
   spec.add_dependency 'gdor-indexer'
   # newer versions of harvestdor-indexer have performance improvements for collections
   spec.add_dependency 'harvestdor-indexer', '~> 2.3'
-  # stanford-mods 1.2.1 includes additional name fields and a bug fix
-  spec.add_dependency 'stanford-mods', '>= 1.2.1'
+  spec.add_dependency 'stanford-mods', '>= 1.3.0'
   spec.add_dependency 'rails'
   spec.add_dependency 'blacklight-spotlight', '~> 0.6'
   spec.add_dependency 'parallel'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: spotlight-dor-resources
 version: !ruby/object:Gem::Version
-  version: 0.3.1
+  version: 0.3.2
 platform: ruby
 authors:
 - Chris Beer
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-11-19 00:00:00.000000000 Z
+date: 2015-12-02 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: faraday
@@ -72,14 +72,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.2.1
+        version: 1.3.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.2.1
+        version: 1.3.0
 - !ruby/object:Gem::Dependency
   name: rails
   requirement: !ruby/object:Gem::Requirement