2ac48f63-1531-4c4d-b0c7-21f5447613b7

Committed 12 Sep 2024 05:36PM UTC coverage: 97.189% (+0.1%) from 97.054%

Build # 2ac48f63-1531-4c4d-b0c7-21f5447613b7

Build Type

push

circleci

Committed by

web-flow

Commit Message

Fix coverage reporting by using coveralls circleci orb (#680)

Run Details

3457 of 3557 relevant lines covered (97.19%)

286.43 hits per line

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

93.59

/spec/system/pppl_indexing_spec.rb

# frozen_string_literal: true
require 'rails_helper'

describe 'PPPL research data indexing', type: :system do
  let(:processed) do
    indexer.process(dspace_xml_io)
    indexer.complete
  end
  let(:query_sort) { 'internal_id_lsi desc' }
  let(:blacklight_index) { Blacklight.default_index }
  let(:blacklight_connection) { blacklight_index.connection }
  let(:documents) do
    processed
    http_response = blacklight_connection.select(q: '*:*', params: { rows: 100, sort: query_sort })
    solr_response = http_response['response']
    solr_response['docs']
  end
  let(:output) { TrajectOutput.new }
  let(:indexer) do
    Traject::Indexer::NokogiriIndexer.new.tap do |i|
      i.load_config_file(Rails.root.join('lib', 'traject', 'dataspace_research_data_config.rb'))
    end
  end
  let(:dspace_xml) do
    File.join(fixture_path, 'astrophysical_sciences.xml')
  end
  let(:dspace_xml_io) { File.read(dspace_xml) }
  let(:nokogiri_reader) do
    Traject::NokogiriReader.new(dspace_xml_io, indexer.settings)
  end
  let(:records) do
    nokogiri_reader.to_a
  end

  before do
    class TrajectOutput < Array
      def put(context)
        push(context.output_hash)
      end
    end

    blacklight_connection.delete_by_query('*:*')
    blacklight_connection.commit
  end

  after do
    Object.send(:remove_const, :TrajectOutput)
    blacklight_connection.delete_by_query('*:*')
    blacklight_connection.commit
  end

  context "when the XML documents has been indexed" do
    let(:first_document) { documents.first }
    let(:last_document) { documents.last }

    before do
      documents
    end

    it 'indexes all XML documents' do
      expect(documents).not_to be_empty
      expect(documents.length).to eq(39)
    end

    it 'indexes the IDs' do
      expect(first_document).to include('id')
      expect(first_document['id']).to eq('104131')
      expect(last_document).to include('id')
      expect(last_document['id']).to eq('777')
    end

    context "when indexing XML documents in a different initial order" do
      let(:records) do
        values = nokogiri_reader.to_a
        values.shuffle
      end

      it 'orders the document IDs consistently' do
        expect(first_document).to include('id')
        expect(first_document['id']).to eq('104131')
        expect(last_document).to include('id')
        expect(last_document['id']).to eq('777')
      end
    end

    it 'indexes the titles' do
      expect(first_document).to include('title_tesim')
      titles = first_document['title_tesim']
      expect(titles).not_to be_empty
      expect(titles.length).to eq(1)
      first_title = titles.first
      expect(first_title).to eq('The Dark Side of the Gravitational Force: Lessons from Astrophysics on Gravity, Black Holes, and Dark Matter')
    end

    it 'indexes the DOI into the `referenced_by` field' do
      expect(documents.length).to eq(39)
      third_document = documents[-3]
      expect(third_document).to include('referenced_by_ssim')
      references = third_document['referenced_by_ssim']
      expect(references).not_to be_empty
      reference = references.first
      expect(reference).to eq('https://arxiv.org/abs/1903.06605')
    end

    it 'indexes the file metadata' do
      expect(last_document).to include('files_ss')
      files_values = last_document['files_ss']
      files = JSON.parse(files_values)

      expect(files.count).to eq(1)
      first_file = files.first
      expect(first_file["name"]).to eq('Sironi_princeton_0181D_10002.pdf')
    end
  end
end

1	# frozen_string_literal: true
2	require 'rails_helper'	1✔
3
4	describe 'PPPL research data indexing', type: :system do	1✔
5	let(:processed) do	1✔
6	indexer.process(dspace_xml_io)	6✔
7	indexer.complete	6✔
8	end
9	let(:query_sort) { 'internal_id_lsi desc' }	7✔
10	let(:blacklight_index) { Blacklight.default_index }	7✔
11	let(:blacklight_connection) { blacklight_index.connection }	7✔
12	let(:documents) do	1✔
13	processed	6✔
14	http_response = blacklight_connection.select(q: ':', params: { rows: 100, sort: query_sort })	6✔
15	solr_response = http_response['response']	6✔
16	solr_response['docs']	6✔
17	end
18	let(:output) { TrajectOutput.new }	1✔
19	let(:indexer) do	1✔
20	Traject::Indexer::NokogiriIndexer.new.tap do \|i\|	6✔
21	i.load_config_file(Rails.root.join('lib', 'traject', 'dataspace_research_data_config.rb'))	6✔
22	end
23	end
24	let(:dspace_xml) do	1✔
25	File.join(fixture_path, 'astrophysical_sciences.xml')	6✔
26	end
27	let(:dspace_xml_io) { File.read(dspace_xml) }	7✔
28	let(:nokogiri_reader) do	1✔
29	Traject::NokogiriReader.new(dspace_xml_io, indexer.settings)	×
30	end
31	let(:records) do	1✔
32	nokogiri_reader.to_a	×
33	end
34
35	before do	1✔
36	class TrajectOutput < Array	6✔
37	def put(context)	6✔
38	push(context.output_hash)	×
39	end
40	end
41
42	blacklight_connection.delete_by_query(':')	6✔
43	blacklight_connection.commit	6✔
44	end
45
46	after do	1✔
47	Object.send(:remove_const, :TrajectOutput)	6✔
48	blacklight_connection.delete_by_query(':')	6✔
49	blacklight_connection.commit	6✔
50	end
51
52	context "when the XML documents has been indexed" do	1✔
53	let(:first_document) { documents.first }	4✔
54	let(:last_document) { documents.last }	4✔
55
56	before do	1✔
57	documents	6✔
58	end
59
60	it 'indexes all XML documents' do	1✔
61	expect(documents).not_to be_empty	1✔
62	expect(documents.length).to eq(39)	1✔
63	end
64
65	it 'indexes the IDs' do	1✔
66	expect(first_document).to include('id')	1✔
67	expect(first_document['id']).to eq('104131')	1✔
68	expect(last_document).to include('id')	1✔
69	expect(last_document['id']).to eq('777')	1✔
70	end
71
72	context "when indexing XML documents in a different initial order" do	1✔
73	let(:records) do	1✔
74	values = nokogiri_reader.to_a	×
75	values.shuffle	×
76	end
77
78	it 'orders the document IDs consistently' do	1✔
79	expect(first_document).to include('id')	1✔
80	expect(first_document['id']).to eq('104131')	1✔
81	expect(last_document).to include('id')	1✔
82	expect(last_document['id']).to eq('777')	1✔
83	end
84	end
85
86	it 'indexes the titles' do	1✔
87	expect(first_document).to include('title_tesim')	1✔
88	titles = first_document['title_tesim']	1✔
89	expect(titles).not_to be_empty	1✔
90	expect(titles.length).to eq(1)	1✔
91	first_title = titles.first	1✔
92	expect(first_title).to eq('The Dark Side of the Gravitational Force: Lessons from Astrophysics on Gravity, Black Holes, and Dark Matter')	1✔
93	end
94
95	it 'indexes the DOI into the `referenced_by` field' do	1✔
96	expect(documents.length).to eq(39)	1✔
97	third_document = documents[-3]	1✔
98	expect(third_document).to include('referenced_by_ssim')	1✔
99	references = third_document['referenced_by_ssim']	1✔
100	expect(references).not_to be_empty	1✔
101	reference = references.first	1✔
102	expect(reference).to eq('https://arxiv.org/abs/1903.06605')	1✔
103	end
104
105	it 'indexes the file metadata' do	1✔
106	expect(last_document).to include('files_ss')	1✔
107	files_values = last_document['files_ss']	1✔
108	files = JSON.parse(files_values)	1✔
109
110	expect(files.count).to eq(1)	1✔
111	first_file = files.first	1✔
112	expect(first_file["name"]).to eq('Sironi_princeton_0181D_10002.pdf')	1✔
113	end
114	end
115	end

pulibrary / pdc_discovery / 2ac48f63-1531-4c4d-b0c7-21f5447613b7

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