529bb1cf-d0bf-4901-97c6-12679aea8117

Committed 17 Aug 2023 01:30PM UTC coverage: 90.265% (-6.3%) from 96.544%

Build # 529bb1cf-d0bf-4901-97c6-12679aea8117

Build Type

Pull #478

circleci

Committed by

carolyncole

Commit Message

Updates to css to fix tests after bundle update
Also ran rubocop -A && Prettier

Pull Request Pull Request #478: Switching to selenium to fix CI

Run Details

2 of 2 new or added lines in 2 files covered. (100.0%)

2142 of 2373 relevant lines covered (90.27%)

93.35 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

57.41

/spec/lib/dspace_research_data_harvester_spec.rb

# frozen_string_literal: true

RSpec.describe DspaceResearchDataHarvester do
  let(:rdh) { described_class.new }

  it "has a list of collections to index" do
    expect(rdh.collections_to_index.count).to eq 34
  end

  it "has a convenience method for indexing all collections" do
    expect_any_instance_of(described_class).to receive(:harvest).exactly(34).times
    described_class.harvest(true)
  end

  context "harvesting a collection" do
    let(:csv_data) do
      {
        "ParentCommunity" => "Princeton Plasma Physics Laboratory",
        "Community" => "Spherical Torus",
        "CollectionName" => "NSTX",
        "Handle" => "88435/dsp018p58pg29j",
        "CollectionID" => "1282",
        "ItemCount" => "33",
        nil => nil
      }
    end
    let(:csv_row) { CSV::Row.new(csv_data.keys, csv_data.values) }
    let(:rdc) { ResearchDataCollection.new(csv_row) }
    let(:collection_1282_xml) { File.read(File.join(fixture_path, 'spherical_torus.xml')) }
    let(:dspace_1308_items) { File.read(File.join(fixture_path, "migration", "1308_items.xml")) }
    let(:dspace_3386_items) { File.read(File.join(fixture_path, "migration", "3386_items.xml")) }

    before do
      Blacklight.default_index.connection.delete_by_query("*:*")
      Blacklight.default_index.connection.commit

      stub_request(:get, "https://dataspace-dev.princeton.edu/rest/collections/1282/items?expand=all&limit=100&offset=0")
        .with(
          headers: {
            'Accept' => 'application/xml'
          }
        )
        .to_return(status: 200, body: collection_1282_xml, headers: {})

      stub_request(:get, "https://dataspace.princeton.edu/rest/collections/1308/items")
        .with(
          headers: {
            'Accept' => 'application/xml'
          }
        )
        .to_return(status: 200, body: dspace_1308_items, headers: {})

      stub_request(:get, "https://dataspace.princeton.edu/rest/collections/3386/items")
        .with(
        headers: {
          'Accept' => 'application/xml'
        }
      )
        .to_return(status: 200, body: dspace_3386_items, headers: {})
    end

    it "retrieves data from dspace and indexes it to solr" do
      response = Blacklight.default_index.connection.get 'select', params: { q: '*:*' }
      expect(response["response"]["numFound"]).to eq 0

      rdh.harvest(rdc)

      response = Blacklight.default_index.connection.get 'select', params: { q: '*:*' }
      expect(response["response"]["numFound"]).to eq 32
    end

    context "migration tracking" do
      let(:shortened_collections_csv) { File.join(fixture_path, 'migration', 'collections.csv') }
      let(:tracking_csv) { File.join(fixture_path, "migration", 'dspace_migration.csv') }

      require 'csv'

      before do
        File.delete(tracking_csv) if File.exist? tracking_csv
        # Run migration queries against production, which is the only place all of this data exists
        allow(rdh).to receive(:server) { "https://dataspace.princeton.edu/rest" }
      end

      # The data for this comes from here: https://dataspace.princeton.edu/rest/collections/1308/items
      it "takes a dspace collection_id and produces a CSV file" do
        CSV.open(tracking_csv, "a") do |csv|
          csv << rdh.migration_csv_headers
        end
        collection = rdh.collections_to_index[2]
        rdh.produce_migration_spreadsheet(
                                          collection.parent_community,
                                          collection.community,
                                          collection.collection_name,
                                          collection.collection_id,
                                          tracking_csv
                                        )
        csv = CSV.parse(File.read(tracking_csv), headers: true)
        expect(csv[0]["title"]).to eq "Geometric concepts for stellarator permanent magnet arrays"
        expect(csv[0]["handle"]).to eq "88435/dsp01db78tg01d"
      end

      context "parent_community in a migration CSV" do
        let(:three_levels) { ["Princeton Plasma Physics Laboratory", "Advanced Projects", "Stellerators"] }
        let(:two_levels) { ["NA", "Princeton Plasma Physics Laboratory", "Plasma Science & Technology"] }
        it "is correct when there are three levels of hierarchy" do
          expect(rdh.csv_communities(three_levels)).to eq three_levels
        end
        it "is correct when there are two levels of hierarchy" do
          expect(rdh.csv_communities(two_levels)).to eq ["Princeton Plasma Physics Laboratory", "Plasma Science & Technology", ""]
        end
      end

      it "produces a CSV file for all items that need migration" do
        rdh.produce_full_migration_spreadsheet(tracking_csv, shortened_collections_csv)
        csv = CSV.parse(File.read(tracking_csv), headers: true)
        expect(csv[0]["title"]).to eq "Hyperdiffusion of dust particles in a turbulent tokamak plasma"
        expect(csv[7]["title"]).to eq "A novel scheme for error field correction in permanent magnet stellarators"
      end
    end
  end
end

1	# frozen_string_literal: true
2
3	RSpec.describe DspaceResearchDataHarvester do	1✔
4	let(:rdh) { described_class.new }	2✔
5
6	it "has a list of collections to index" do	1✔
7	expect(rdh.collections_to_index.count).to eq 34	1✔
8	end
9
10	it "has a convenience method for indexing all collections" do	1✔
11	expect_any_instance_of(described_class).to receive(:harvest).exactly(34).times	1✔
12	described_class.harvest(true)	1✔
13	end
14
15	context "harvesting a collection" do	1✔
16	let(:csv_data) do	1✔
17	{	×
18	"ParentCommunity" => "Princeton Plasma Physics Laboratory",
19	"Community" => "Spherical Torus",
20	"CollectionName" => "NSTX",
21	"Handle" => "88435/dsp018p58pg29j",
22	"CollectionID" => "1282",
23	"ItemCount" => "33",
24	nil => nil
25	}
26	end
27	let(:csv_row) { CSV::Row.new(csv_data.keys, csv_data.values) }	1✔
28	let(:rdc) { ResearchDataCollection.new(csv_row) }	1✔
29	let(:collection_1282_xml) { File.read(File.join(fixture_path, 'spherical_torus.xml')) }	6✔
30	let(:dspace_1308_items) { File.read(File.join(fixture_path, "migration", "1308_items.xml")) }	1✔
31	let(:dspace_3386_items) { File.read(File.join(fixture_path, "migration", "3386_items.xml")) }	1✔
32
33	before do	1✔
34	Blacklight.default_index.connection.delete_by_query(":")	5✔
35	Blacklight.default_index.connection.commit	5✔
36
37	stub_request(:get, "https://dataspace-dev.princeton.edu/rest/collections/1282/items?expand=all&limit=100&offset=0")	5✔
38	.with(
39	headers: {
40	'Accept' => 'application/xml'
41	}
42	)
43	.to_return(status: 200, body: collection_1282_xml, headers: {})
44
45	stub_request(:get, "https://dataspace.princeton.edu/rest/collections/1308/items")	×
46	.with(
47	headers: {
48	'Accept' => 'application/xml'
49	}
50	)
51	.to_return(status: 200, body: dspace_1308_items, headers: {})
52
53	stub_request(:get, "https://dataspace.princeton.edu/rest/collections/3386/items")	×
54	.with(
55	headers: {
56	'Accept' => 'application/xml'
57	}
58	)
59	.to_return(status: 200, body: dspace_3386_items, headers: {})
60	end
61
62	it "retrieves data from dspace and indexes it to solr" do	1✔
63	response = Blacklight.default_index.connection.get 'select', params: { q: ':' }	×
64	expect(response["response"]["numFound"]).to eq 0	×
65
66	rdh.harvest(rdc)	×
67
68	response = Blacklight.default_index.connection.get 'select', params: { q: ':' }	×
69	expect(response["response"]["numFound"]).to eq 32	×
70	end
71
72	context "migration tracking" do	1✔
73	let(:shortened_collections_csv) { File.join(fixture_path, 'migration', 'collections.csv') }	1✔
74	let(:tracking_csv) { File.join(fixture_path, "migration", 'dspace_migration.csv') }	1✔
75
76	require 'csv'	1✔
77
78	before do	1✔
79	File.delete(tracking_csv) if File.exist? tracking_csv	×
80	# Run migration queries against production, which is the only place all of this data exists
81	allow(rdh).to receive(:server) { "https://dataspace.princeton.edu/rest" }	×
82	end
83
84	# The data for this comes from here: https://dataspace.princeton.edu/rest/collections/1308/items
85	it "takes a dspace collection_id and produces a CSV file" do	1✔
86	CSV.open(tracking_csv, "a") do \|csv\|	×
87	csv << rdh.migration_csv_headers	×
88	end
89	collection = rdh.collections_to_index[2]	×
90	rdh.produce_migration_spreadsheet(	×
91	collection.parent_community,
92	collection.community,
93	collection.collection_name,
94	collection.collection_id,
95	tracking_csv
96	)
97	csv = CSV.parse(File.read(tracking_csv), headers: true)	×
98	expect(csv[0]["title"]).to eq "Geometric concepts for stellarator permanent magnet arrays"	×
99	expect(csv[0]["handle"]).to eq "88435/dsp01db78tg01d"	×
100	end
101
102	context "parent_community in a migration CSV" do	1✔
103	let(:three_levels) { ["Princeton Plasma Physics Laboratory", "Advanced Projects", "Stellerators"] }	1✔
104	let(:two_levels) { ["NA", "Princeton Plasma Physics Laboratory", "Plasma Science & Technology"] }	1✔
105	it "is correct when there are three levels of hierarchy" do	1✔
106	expect(rdh.csv_communities(three_levels)).to eq three_levels	×
107	end
108	it "is correct when there are two levels of hierarchy" do	1✔
109	expect(rdh.csv_communities(two_levels)).to eq ["Princeton Plasma Physics Laboratory", "Plasma Science & Technology", ""]	×
110	end
111	end
112
113	it "produces a CSV file for all items that need migration" do	1✔
114	rdh.produce_full_migration_spreadsheet(tracking_csv, shortened_collections_csv)	×
115	csv = CSV.parse(File.read(tracking_csv), headers: true)	×
116	expect(csv[0]["title"]).to eq "Hyperdiffusion of dust particles in a turbulent tokamak plasma"	×
117	expect(csv[7]["title"]).to eq "A novel scheme for error field correction in permanent magnet stellarators"	×
118	end
119	end
120	end
121	end

pulibrary / pdc_discovery / 529bb1cf-d0bf-4901-97c6-12679aea8117

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous