Remove dataspace code from DatasetFile (#764)

refs #685

app/models/dataset_file.rb

@@ -4,32 +4,8 @@ class DatasetFile
   attr_accessor :name, :description, :format, :size, :display_size, :mime_type, :sequence, :handle, :extension,
     :source, :download_url, :full_path
 
-  def self.from_hash(data, data_source)
-    if data_source == "pdc_describe"
-      from_hash_describe(data)
-    else
-      from_hash_dataspace(data)
-    end
-  end
-
-  def self.from_hash_dataspace(data)
-    hash = data.with_indifferent_access
-    file = DatasetFile.new
-    file.source = "dataspace"
-    file.full_path = hash[:name]
-    file.name = hash[:name]
-    file.extension = File.extname(file.name)
-    file.extension = file.extension[1..] if file.extension != "." # drop the leading period
-    file.description = hash[:description]
-    file.mime_type = hash[:mime_type]
-    file.size = hash[:size]
-    file.display_size = ActiveSupport::NumberHelper.number_to_human_size(file.size)
-    file.sequence = (hash[:sequence] || "").to_i
-    # Technically the handle is a property of the dataset item rather than the file (aka bitstream)
-    # but we store it at the file level for convenience.
-    file.handle = hash[:handle]
-    file.download_url = "#{DatasetFile.download_root}/#{file.handle}/#{file.sequence}"
-    file
+  def self.from_hash(data, _data_source)
+    from_hash_describe(data)
   end
 
   def self.from_hash_describe(data)
@@ -70,10 +46,6 @@ def self.filename_without_doi(full_path)
     end
   end
 
-  def self.download_root
-    "#{Rails.configuration.pdc_discovery.dataspace_url}/bitstream"
-  end
-
   def self.sort_file_array(file_array)
     sorted_by_name = file_array.sort_by(&:name)
     sorted_file_array = []

spec/models/dataset_file_spec.rb

@@ -4,12 +4,6 @@
 
 RSpec.describe DatasetFile do
   describe "#download_url" do
-    it "builds the proper URL for a DataSpace record" do
-      hash = { name: "big file.zip", handle: "123/dsp456", sequence: 1 }
-      file = described_class.from_hash(hash, "dataspace")
-      expect(file.download_url).to eq "https://dataspace-dev.princeton.edu/bitstream/123/dsp456/1"
-    end
-
     it "builds the proper URL for a PDC Describe record" do
       hash = {
         filename: "10.34770/qyrs-vg25/50/file_name.txt",

spec/models/document_export_spec.rb

@@ -8,10 +8,6 @@
     { files: [{ filename: "/folder1/file1.zip", size: 27, url: "https://pdc_describe", display_size: "11 KB" }, { filename: "data.csv", size: 100 }, { filename: "file2.zip", size: 200 }] }
   end
 
-  let(:files_dataspace) do
-    [{ name: "file1.zip", size: 27, handle: "xyz" }, { name: "data.csv", size: 29, handle: "yzx" }, { name: "file2.zip", size: 28, handle: "zxy" }]
-  end
-
   let(:solr_doc_pdc_describe) do
     SolrDocument.new({
                        id: "1", title_tesim: ["Hello World"], pdc_describe_json_ss: files_pdc_describe.to_json,
@@ -25,10 +21,6 @@
                      })
   end
 
-  let(:solr_doc_dataspace) do
-    SolrDocument.new({ id: "1", title_tesim: ["Hello World"], files_ss: files_dataspace.to_json, data_source_ssi: "dataspace", description_tsim: ["Something"], abstract_tsim: ["Abstract"] })
-  end
-
   it "returns DocumentExport object's information from pdc_describe" do
     document = described_class.new(solr_doc_pdc_describe)
     expect(document.id).to be "1"
@@ -47,16 +39,5 @@
     expect(document.authors.count).to be 6
     expect(document.authors[0].value).to eq "Alt, Andrew"
   end
-
-  it "returns DocumentExport object's information from dataspace" do
-    document = described_class.new(solr_doc_dataspace)
-    expect(document.id).to be "1"
-    expect(document.title).to be "Hello World"
-    expect(document.files.count).to eq 3
-    expect(document.description).to eq "Something"
-    expect(document.abstract).to eq "Abstract"
-    expect(document.files.first.name).to eq "file1.zip"
-    expect(document.files.first.download_url).to eq "https://dataspace-dev.princeton.edu/bitstream/xyz/0"
-  end
 end
 # rubocop:enable Layout/LineLength

spec/models/solr_document_spec.rb

@@ -29,13 +29,6 @@
       doc = described_class.new({ id: "2", data_source_ssi: "pdc_describe" })
       expect(doc.dates_created.first).to be nil
     end
-    it "handles dataspace dates" do
-      doc = described_class.new({ id: "3", date_created_ssim: ["2024-10-30"], data_source_ssi: "dataspace" })
-      expect(doc.dates_created.first).to eq "2024-10-30"
-
-      doc = described_class.new({ id: "4", data_source_ssi: "dataspace" })
-      expect(doc.dates_created.first).to be nil
-    end
   end
 
   describe "#dates_modified" do
@@ -52,13 +45,6 @@
       doc = described_class.new({ id: "4", pdc_updated_at_dtsi: "string", data_source_ssi: "pdc_describe" })
       expect(doc.dates_modified.first).to be nil
     end
-    it "handles dataspace dates" do
-      doc = described_class.new({ id: "4", date_modified_ssim: ["2024-10-30"], data_source_ssi: "dataspace" })
-      expect(doc.dates_modified.first).to eq "2024-10-30"
-
-      doc = described_class.new({ id: "6", data_source_ssi: "dataspace" })
-      expect(doc.dates_modified.first).to be nil
-    end
   end
 
   describe "#icons_css" do
@@ -83,7 +69,9 @@
     end
 
     it "calculates file counts and sorts data descending by count" do
-      files = [{ name: "file1.zip" }, { name: "data.csv" }, { name: "file2.zip" }]
+      files = [{ filename: "file1.zip", "size": 10_588, "display_size": "10.6 KB", "url": "https://example.com" },
+               { filename: "data.csv", "size": 10_588, "display_size": "10.6 KB", "url": "https://example.com" },
+               { filename: "file2.zip", "size": 10_588, "display_size": "10.6 KB", "url": "https://example.com" }]
       doc = described_class.new({ id: "1", files_ss: files.to_json })
       zip_group = { extension: "zip", file_count: 2 }
       csv_group = { extension: "csv", file_count: 1 }