Adding missing elements from physdesc

lib/arclight/traject/ead2_component_config.rb

@@ -155,12 +155,29 @@
   accumulator.concat settings[:root].output_hash['normalized_title_ssm']
 end
 
+# This accumulates direct text from a physdesc, ignoring child elements handled elsewhere
+to_field 'physdesc_ssm', extract_xpath('./did/physdesc', to_text: false) do |_record, accumulator|
+  accumulator.map! do |element|
+    physdesc = []
+    element.children.map do |child|
+      next if child.instance_of?(Nokogiri::XML::Element)
+
+      physdesc << child.text&.strip unless child.text&.strip&.empty?
+    end.flatten
+    physdesc.join(' ') unless physdesc.empty?
+  end
+end
+
+to_field 'physdesc_tesim' do |_record, accumulator, context|
+  accumulator.concat context.output_hash['physdesc_ssm'] || []
+end
+
 to_field 'extent_ssm' do |record, accumulator|
   physdescs = record.xpath('./did/physdesc')
   extents_per_physdesc = physdescs.map do |physdesc|
     extents = physdesc.xpath('./extent').map { |e| e.text.strip }
     # Join extents within the same physdesc with an empty string
-    extents.join(' ')
+    extents.join(' ') unless extents.empty?
   end
 
   # Add each physdesc separately to the accumulator
@@ -171,6 +188,12 @@
   accumulator.concat context.output_hash['extent_ssm'] || []
 end
 
+to_field 'physfacet_ssm', extract_xpath('./did/physdesc/physfacet')
+to_field 'physfacet_tesim', extract_xpath('./did/physdesc/physfacet')
+
+to_field 'dimensions_ssm', extract_xpath('./did/physdesc/dimensions')
+to_field 'dimensions_tesim', extract_xpath('./did/physdesc/dimensions')
+
 to_field 'creator_ssm', extract_xpath('./did/origination')
 to_field 'creator_ssim', extract_xpath('./did/origination')
 to_field 'creators_ssim', extract_xpath('./did/origination')

lib/arclight/traject/ead2_config.rb

@@ -183,12 +183,29 @@
   end
 end
 
+# This accumulates direct text from a physdesc, ignoring child elements handled elsewhere
+to_field 'physdesc_ssm', extract_xpath('/ead/archdesc/did/physdesc', to_text: false) do |_record, accumulator|
+  accumulator.map! do |element|
+    physdesc = []
+    element.children.map do |child|
+      next if child.instance_of?(Nokogiri::XML::Element)
+
+      physdesc << child.text&.strip unless child.text&.strip&.empty?
+    end.flatten
+    physdesc.join(' ') unless physdesc.empty?
+  end
+end
+
+to_field 'physdesc_tesim' do |_record, accumulator, context|
+  accumulator.concat context.output_hash['physdesc_ssm'] || []
+end
+
 to_field 'extent_ssm' do |record, accumulator|
   physdescs = record.xpath('/ead/archdesc/did/physdesc')
   extents_per_physdesc = physdescs.map do |physdesc|
     extents = physdesc.xpath('./extent').map { |e| e.text.strip }
     # Join extents within the same physdesc with an empty string
-    extents.join(' ')
+    extents.join(' ') unless extents.empty?
   end
 
   # Add each physdesc separately to the accumulator
@@ -199,6 +216,12 @@
   accumulator.concat context.output_hash['extent_ssm'] || []
 end
 
+to_field 'physfacet_ssm', extract_xpath('/ead/archdesc/did/physdesc/physfacet')
+to_field 'physfacet_tesim', extract_xpath('/ead/archdesc/did/physdesc/physfacet')
+
+to_field 'dimensions_ssm', extract_xpath('/ead/archdesc/did/physdesc/dimensions')
+to_field 'dimensions_tesim', extract_xpath('/ead/archdesc/did/physdesc/dimensions')
+
 to_field 'genreform_ssim', extract_xpath('/ead/archdesc/controlaccess/genreform')
 
 to_field 'date_range_isim', extract_xpath('/ead/archdesc/did/unitdate/@normal', to_text: false) do |_record, accumulator|

spec/features/traject/ead2_indexing_spec.rb

@@ -120,8 +120,22 @@ def components(result)
       expect(result['places_ssim']).to equal_array_ignoring_whitespace ['Yosemite National Park (Calif.)']
     end
 
-    it 'physdesc' do
-      expect(result['extent_ssm']).to equal_array_ignoring_whitespace ['1.25 Linear Feet (1 volume)', '1 document case', '16 DVDRs']
+    describe 'physdesc' do
+      it 'direct text' do
+        expect(result['physdesc_ssm']).to equal_array_ignoring_whitespace ['Photographic album', 'Single bound volume']
+      end
+
+      it 'extent' do
+        expect(result['extent_ssm']).to equal_array_ignoring_whitespace ['1.25 Linear Feet (1 volume)', '1 document case', '16 DVDRs']
+      end
+
+      it 'physfacet' do
+        expect(result['physfacet_ssm']).to equal_array_ignoring_whitespace ['Printed material', 'Digital Video Disc']
+      end
+
+      it 'dimensions' do
+        expect(result['dimensions_ssm']).to equal_array_ignoring_whitespace ['20 x 20 in.', '7.5 x 5.5 in.']
+      end
     end
 
     it 'has_online_content' do
@@ -295,18 +309,49 @@ def components(result)
       ).to_a.first
     end
 
-    it 'extent at the collection level' do
-      %w[extent_ssm extent_tesim].each do |field|
-        expect(result[field]).to equal_array_ignoring_whitespace(['15.0 linear feet (36 boxes + oversize folder)', '3 CDs'])
+    describe 'physdesc at the collection level' do
+      it 'direct text' do
+        expect(result['physdesc_ssm']).to equal_array_ignoring_whitespace ['Boxes and folders', 'Compact discs']
+      end
+
+      it 'extent' do
+        %w[extent_ssm extent_tesim].each do |field|
+          expect(result[field]).to equal_array_ignoring_whitespace(['15.0 linear feet (36 boxes + oversize folder)', '3 CDs'])
+        end
+      end
+
+      it 'physfacet' do
+        expect(result['physfacet_ssm']).to equal_array_ignoring_whitespace ['Compact digital disc']
+      end
+
+      it 'dimensions' do
+        expect(result['dimensions_ssm']).to equal_array_ignoring_whitespace ['7.5 x 5.5 in.']
       end
     end
 
-    it 'extent at the component level' do
-      component = all_components.find { |c| c['ref_ssi'] == ['aspace_a951375d104030369a993ff943f61a77'] }
-      %w[extent_ssm extent_tesim].each do |field|
-        expect(component[field]).to equal_array_ignoring_whitespace(
-          ['1.5 Linear Feet']
-        )
+    describe 'physdesc at the component level' do
+      let(:component) do
+        all_components.find { |c| c['ref_ssi'] == ['aspace_a951375d104030369a993ff943f61a77'] }
+      end
+
+      it 'direct text' do
+        expect(component['physdesc_ssm']).to equal_array_ignoring_whitespace ['Cards and sheets of various sizes']
+      end
+
+      it 'extent' do
+        %w[extent_ssm extent_tesim].each do |field|
+          expect(component[field]).to equal_array_ignoring_whitespace(
+            ['1.5 Linear Feet']
+          )
+        end
+      end
+
+      it 'physfacet' do
+        expect(component['physfacet_ssm']).to equal_array_ignoring_whitespace ['Informational cards']
+      end
+
+      it 'dimensions' do
+        expect(component['dimensions_ssm']).to equal_array_ignoring_whitespace ['various']
       end
     end
 

spec/fixtures/ead/nlm/alphaomegaalpha.xml

@@ -41,11 +41,19 @@
         <corpname source="ingest">Alpha Omega Alpha</corpname>
       </origination>
       <unitid>MS C 271</unitid>
+      <physdesc>
+        Boxes and folders
+      </physdesc>
+      <physdesc>
+        Compact discs
+      </physdesc>
       <physdesc altrender="part">
         <extent altrender="materialtype spaceoccupied">15.0 linear feet (36 boxes + oversize
           folder)</extent>
       </physdesc>
       <physdesc altrender="part">
+        <dimensions>7.5 x 5.5 in.</dimensions>
+        <physfacet>Compact digital disc</physfacet>
         <extent altrender="materialtype spaceoccupied">3 CDs</extent>
       </physdesc>
       <unitdate normal="1894/1992" type="inclusive">1894-1992</unitdate>
@@ -393,7 +401,7 @@
         <bioghist id="aspace_ff0f536406ce214f5u38e1f7c798d76e">
           <head>Historical Note</head>
           <p>
-            The Society started keeping consistent adminstrative records in 1975, the same year that E. L. Doctorow published <emph render="italic">Ragtime</emph>. 
+            The Society started keeping consistent adminstrative records in 1975, the same year that E. L. Doctorow published <emph render="italic">Ragtime</emph>.
           </p>
         </bioghist>
         <accessrestrict id="aspace_7bbec2cdc1e6e0cb7b2ff1acb7c9e364">
@@ -724,8 +732,16 @@
         <did>
           <unittitle>Series II: Membership,</unittitle>
           <unitid>MS C 271.II</unitid>
-          <physdesc altrender="whole"><extent altrender="materialtype spaceoccupied">1.5 Linear
-              Feet</extent></physdesc>
+          <physdesc>
+            Cards and sheets of various sizes
+          </physdesc>
+          <physdesc>
+            <physfacet>Informational cards</physfacet>
+          </physdesc>
+          <physdesc altrender="whole">
+            <dimensions>various</dimensions>
+            <extent altrender="materialtype spaceoccupied">1.5 Linear Feet</extent>
+          </physdesc>
           <unitdate normal="1902/1973" type="inclusive">1902-1973</unitdate>
           <abstract id="aspace_e806089c6553f2132b727ead99b47a70">Contains a mixture of membership
             cards and membership rosters.</abstract>

spec/fixtures/ead/sul-spec/a0011.xml

@@ -78,13 +78,23 @@
             </origination>
             <unitid>A0011</unitid>
             <physdesc altrender="part">
+                Photographic album
+            </physdesc>
+            <physdesc altrender="part">
+                Single bound volume
+            </physdesc>
+            <physdesc altrender="part">
+                <physfacet>Printed material</physfacet>
                 <extent altrender="materialtype spaceoccupied">1.25 Linear Feet</extent>
                 <extent altrender="carrier">(1 volume)</extent>
             </physdesc>
             <physdesc altrender="part">
+                <dimensions>20 x 20 in.</dimensions>
                 <extent altrender="materialtype spaceoccupied">1 document case</extent>
             </physdesc>
             <physdesc altrender="part">
+                <dimensions>7.5 x 5.5 in.</dimensions>
+                <physfacet>Digital Video Disc</physfacet>
                 <extent altrender="materialtype spaceoccupied">16 DVDRs</extent>
             </physdesc>
             <unitdate normal="1900/1906" type="inclusive">circa 1900-1906