787041f3-bb1b-461b-9eaa-c391c9c1e54a

Committed 19 Feb 2025 03:50PM UTC coverage: 96.483% (-0.003%) from 96.486%

Build # 787041f3-bb1b-461b-9eaa-c391c9c1e54a

Build Type

push

circleci

Committed by

web-flow

Commit Message

Bump nokogiri from 1.16.8 to 1.18.3 (#756)

Bumps [nokogiri](https://github.com/sparklemotion/nokogiri) from 1.16.8 to 1.18.3.
- [Release notes](https://github.com/sparklemotion/nokogiri/releases)
- [Changelog](https://github.com/sparklemotion/nokogiri/blob/v1.18.3/CHANGELOG.md)
- [Commits](https://github.com/sparklemotion/nokogiri/compare/v1.16.8...v1.18.3)

---
updated-dependencies:
- dependency-name: nokogiri
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

Run Details

3649 of 3782 relevant lines covered (96.48%)

180.75 hits per line

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

99.56

/spec/lib/describe_indexer_spec.rb

# frozen_string_literal: true
require "rails_helper"

# rubocop:disable Metrics/BlockLength
RSpec.describe DescribeIndexer do
  describe 'indexing a single record' do
    let(:single_item) { file_fixture("bitklavier_binaural.json").read }
    let(:indexer) do
      described_class.new(rss_url: "file://whatever.rss")
    end
    let(:indexed_record) do
      Blacklight.default_index.connection.delete_by_query("*:*")
      Blacklight.default_index.connection.commit
      indexer.index_one(single_item)
      response = Blacklight.default_index.connection.get 'select', params: { q: '*:*' }
      response["response"]["docs"].first
    end

    context "basic fields" do
      ##
      # The id is based on the DOI
      # A doi of 10.34770/r75s-9j74 will become doi-10-34770-r75s-9j74
      it "id" do
        expect(indexed_record["id"]).to eq "doi-10-34770-r75s-9j74"
      end

      it "stores a copy of the full JSON in CDATA" do
        stored_json = indexed_record["pdc_describe_json_ss"]
        parsed_json = JSON.parse(stored_json)
        expect(parsed_json["resource"]["titles"][0]["title"]).to eq "bitKlavier Grand Sample Library—Binaural Mic Image"
      end

      it "author" do
        expect(indexed_record["author_tesim"]).to eq ['Trueman, Daniel']
      end

      it "description" do
        description = "The bitKlavier Grand consists"
        expect(indexed_record["description_tsim"].first.include?(description)).to be true
      end

      it "contributors" do
        expect(indexed_record["contributor_tsim"].include?("Villalta, Andrés")).to eq true
        expect(indexed_record["contributor_tsim"].include?("Chou, Katie")).to eq true
        expect(indexed_record["contributor_tsim"].include?("Ayres, Christien")).to eq true
        expect(indexed_record["contributor_tsim"].include?("Wang, Matthew")).to eq true
      end

      it "title" do
        # title includes all titles
        main_title = "bitKlavier Grand Sample Library—Binaural Mic Image"
        alt_title = "alter title for bitKlavier"
        expect(indexed_record["title_tesim"].include?(main_title)).to eq true
        expect(indexed_record["title_tesim"].include?(alt_title)).to eq true
        # alt title does not include the main title
        expect(indexed_record["alternative_title_tesim"].include?(main_title)).to eq false
        expect(indexed_record["alternative_title_tesim"].include?(alt_title)).to eq true
      end

      it "rights" do
        expect(indexed_record["rights_name_ssi"]).to eq "GNU General Public License"
        expect(indexed_record["rights_uri_ssi"]).to eq "https://www.gnu.org/licenses/gpl-3.0.en.html"
      end

      it "keywords" do
        expect(indexed_record["subject_all_ssim"].include?("keyword1")).to eq true
        expect(indexed_record["subject_all_ssim"].include?("keyword2")).to eq true
        expect(indexed_record["subject_all_ssim"].include?("keyword3")).to eq true
      end

      it "collection tag" do
        expect(indexed_record["collection_tag_ssim"].include?("Humanities")).to eq true
        expect(indexed_record["collection_tag_ssim"].include?("Something else")).to eq true
      end

      it "community" do
        expect(indexed_record["community_name_ssi"]).to eq "Research Data"
      end

      it "genre_ssim" do
        expect(indexed_record["genre_ssim"].first).to eq "Dataset"
      end

      it "issue_date_ssim" do
        expect(indexed_record["issue_date_ssim"].first).to eq "2021"
      end

      # The pdc_created_at_dtsi field is used to describe when a record was created in PDC
      # This is used to sort the Recently Published page
      it "pdc_created_at_dtsi" do
        expect(indexed_record["pdc_created_at_dtsi"]).to eq "2021-12-31T19:00:00Z"
        # example timestamp 1997-12-31T23:59:59Z
      end

      it "pdc_updated_at_dtsi" do
        expect(indexed_record["pdc_updated_at_dtsi"]).to eq "2021-12-31T20:00:00Z"
      end

      it "issue_date_strict_ssi" do
        expect(indexed_record["issue_date_strict_ssi"]).to eq "2021-01-01"
      end

      it "publisher_ssim" do
        expect(indexed_record["publisher_ssim"].first).to eq "Princeton University"
      end

      it "migrated_bsi" do
        expect(indexed_record["migrated_bsi"]).to eq true
      end

      xit 'referenced_by' do
        expect(result['referenced_by_ssim'].first).to eq 'https://arxiv.org/abs/1903.06605'
      end
    end

    context "uris" do
      it "stores full URL for ARK and DOI" do
        expect(indexed_record["uri_ssim"].include?("http://arks.princeton.edu/ark:/88435/dsp015999n653h")).to eq true
        expect(indexed_record["uri_ssim"].include?("https://doi.org/10.34770/r75s-9j74")).to eq true
      end
    end

    context "files" do
      it "stores file detailed information" do
        files = JSON.parse(indexed_record['pdc_describe_json_ss'])['files']
        file1 = files.find { |file| file["filename"] == "10.80021/3m1k-6036/122/file1.jpg" }
        file2 = files.find { |file| file["filename"] == "10.80021/3m1k-6036/122/file2.txt" }
        file3 = files.find { |file| file["filename"] == "10.80021/3m1k-6036/122/folder-a/file3.txt" }
        expect(file1["size"]).to eq 316_781
        expect(file1["url"]).to eq "https://g-5beea4.90d4e.bd7c.data.globus.org/pdc-describe-staging-postcuration/10.80021/3m1k-6036/122/file1.jpg"
        expect(file2["size"]).to eq 396_003
        expect(file3["url"]).to eq "https://g-5beea4.90d4e.bd7c.data.globus.org/pdc-describe-staging-postcuration/10.80021/3m1k-6036/122/folder-a/file3.txt"
      end
    end

    context "all text catch all field" do
      it "indexes the file name in the all text catch all field" do
        files = JSON.parse(indexed_record['pdc_describe_json_ss'])['files']
        file_name = File.basename(files.first["filename"])
        response = Blacklight.default_index.connection.get 'select', params: { q: file_name }
        expect(response["response"]["numFound"]).to eq 1

        response = Blacklight.default_index.connection.get 'select', params: { q: "non-existing-value" }
        expect(response["response"]["numFound"]).to eq 0
      end
    end
  end

  describe 'indexing an RSS feed from PDC Describe' do
    let(:rss_feed) { file_fixture("works.rss").read }
    let(:resource1) { file_fixture("bitklavier_binaural.json").read }
    let(:resource2) { file_fixture("sowing_the_seeds.json").read }
    let(:rss_url_string) { "https://pdc-describe-prod.princeton.edu/describe/works.rss" }
    let(:indexer) { described_class.new(rss_url: rss_url_string) }

    it "has a traject indexer" do
      expect(indexer.traject_indexer).to be_instance_of Traject::Indexer::NokogiriIndexer
    end

    context 'indexing to solr' do
      before do
        Blacklight.default_index.connection.delete_by_query("*:*")
        Blacklight.default_index.connection.commit
        stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works.rss")
          .to_return(status: 200, body: rss_feed, headers: {})
        stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works/6.json")
          .to_return(status: 200, body: resource1, headers: {})
        stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works/20.json")
          .to_return(status: 200, body: resource2, headers: {})
      end

      it "sends items to solr" do
        response = Blacklight.default_index.connection.get 'select', params: { q: '*:*' }
        expect(response["response"]["numFound"]).to eq 0

        # If index_pdc_describe == false, do not index PDC Describe.
        # This is a safety measure so we don't index in production until we're ready
        # See config/pdc_discovery.yml to change this setting for real
        Rails.configuration.pdc_discovery.index_pdc_describe = false
        indexer.index
        response = Blacklight.default_index.connection.get 'select', params: { q: '*:*' }
        expect(response["response"]["numFound"]).to eq 0

        # If index_pdc_describe == true, DO index PDC Describe.
        Rails.configuration.pdc_discovery.index_pdc_describe = true
        indexer.index
        response = Blacklight.default_index.connection.get 'select', params: { q: '*:*' }
        expect(response["response"]["numFound"]).to eq 2
      end

      it "can sort by issue_date_strict_ssi" do
        Rails.configuration.pdc_discovery.index_pdc_describe = true
        indexer.index
        response = Blacklight.default_index.connection.get 'select', params: { q: '*:*', sort: 'issue_date_strict_ssi desc' }
        expect(response["response"]["numFound"]).to eq 2
        expect(response["response"]['docs'].first['pdc_created_at_dtsi']).to eq("2023-07-11T11:06:10Z")
        expect(response["response"]['docs'].last['pdc_created_at_dtsi']).to eq("2021-12-31T19:00:00Z")
        expect(response["response"]['docs'].first["issue_date_strict_ssi"]).to eq "2023-01-01"
        expect(response["response"]['docs'].last["issue_date_strict_ssi"]).to eq "2021-01-01"
      end

      context "works with multiple creators" do
        let(:pppl1) { File.read(File.join(fixture_paths.first, 'files', 'pppl1.json')) }
        let(:pppl2) { File.read(File.join(fixture_paths.first, 'files', 'pppl2.json')) }
        before do
          stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works/6.json")
            .to_return(status: 200, body: pppl1, headers: {})
          stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works/20.json")
            .to_return(status: 200, body: pppl2, headers: {})
        end

        it "can sort by the first author" do
          Rails.configuration.pdc_discovery.index_pdc_describe = true
          indexer.index
          response = Blacklight.default_index.connection.get 'select', params: { q: '*:*', sort: 'author_si desc' }
          expect(response["response"]["numFound"]).to eq 2
          expect(response["response"]['docs'].first['author_tesim'].first).to eq("Wang, Yin")
          expect(response["response"]['docs'].last['author_tesim'].first).to eq("Schwartz, Jacob A.")
          expect(response["response"]['docs'].first["issue_date_strict_ssi"]).to eq "2021-12-30"
          expect(response["response"]['docs'].last["issue_date_strict_ssi"]).to eq "2022-01-01"
        end
      end

      context "when there are items which are under active embargo" do
        let(:item_file_fixture) { file_fixture("pdc_describe_active_embargo.json") }
        let(:embargo_resource) { item_file_fixture.read }
        # This redundancy is required for consistent testing
        let(:rss_feed) { file_fixture("works.rss").read }
        let(:rss_url) { "https://pdc-describe-prod.princeton.edu/describe/works.rss" }
        let(:indexer) do
          described_class.new(rss_url: rss_url)
        end
        let(:solr_response) do
          Blacklight.default_index.connection.get 'select', params: { q: '*:*' }
        end
        let(:response) { solr_response["response"] }
        let(:num_found) { response["numFound"] }
        let(:docs) { response["docs"] }
        let(:doc) { docs.first }
        let(:files) { JSON.parse(doc['pdc_describe_json_ss'])['files'] }

        before do
          stub_request(:get, rss_url)
            .to_return(status: 200, body: rss_feed, headers: {})
          stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works/6.json")
            .to_return(status: 200, body: embargo_resource, headers: {})
          stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works/20.json")
            .to_return(status: 200, body: embargo_resource, headers: {})

          Rails.configuration.pdc_discovery.index_pdc_describe = true
          indexer.index
        end

        it "indexes the embargo date" do
          expect(solr_response).to include("response")
          expect(response).to include("numFound")
          expect(num_found).to eq 1
          expect(docs).not_to be_empty
          expect(doc).to include("embargo_date_dtsi")
        end

        it "does not index the files" do
          expect(solr_response).to include("response")
          expect(response).to include("numFound")
          expect(num_found).to eq 1
          expect(docs).not_to be_empty
          expect(doc).to include("pdc_describe_json_ss")
          expect(files).to be_empty
        end
      end

      context "when there are items which are under an expired embargo" do
        let(:item_file_fixture) { file_fixture("pdc_describe_expired_embargo.json") }
        let(:embargo_resource) { item_file_fixture.read }
        # This redundancy is required for consistent testing
        let(:rss_feed) { file_fixture("works.rss").read }
        let(:rss_url) { "https://pdc-describe-prod.princeton.edu/describe/works.rss" }
        let(:indexer) do
          described_class.new(rss_url: rss_url)
        end
        let(:solr_response) do
          Blacklight.default_index.connection.get 'select', params: { q: '*:*' }
        end
        let(:response) { solr_response["response"] }
        let(:num_found) { response["numFound"] }
        let(:docs) { response["docs"] }
        let(:doc) { docs.first }
        let(:files) { doc['pdc_describe_json_ss']['files'] }

        before do
          stub_request(:get, rss_url)
            .to_return(status: 200, body: rss_feed, headers: {})
          stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works/6.json")
            .to_return(status: 200, body: embargo_resource, headers: {})
          stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works/20.json")
            .to_return(status: 200, body: embargo_resource, headers: {})

          Rails.configuration.pdc_discovery.index_pdc_describe = true
          indexer.index
        end

        it "does indexes the files" do
          expect(solr_response).to include("response")
          expect(response).to include("numFound")
          expect(num_found).to eq 1
          expect(docs).not_to be_empty
          expect(doc).to include("pdc_describe_json_ss")
          expect(files).not_to be_empty
        end
      end

      context "when there work is not under embargo" do
        let(:item_file_fixture) { file_fixture("pdc_describe_no_embargo.json") }
        let(:embargo_resource) { item_file_fixture.read }
        # This redundancy is required for consistent testing
        let(:rss_feed) { file_fixture("works.rss").read }
        let(:rss_url) { "https://pdc-describe-prod.princeton.edu/describe/works.rss" }
        let(:indexer) do
          described_class.new(rss_url: rss_url)
        end
        let(:solr_response) do
          Blacklight.default_index.connection.get 'select', params: { q: '*:*' }
        end
        let(:response) { solr_response["response"] }
        let(:num_found) { response["numFound"] }
        let(:docs) { response["docs"] }
        let(:doc) { docs.first }
        let(:files) { doc['pdc_describe_json_ss']['files'] }

        before do
          stub_request(:get, rss_url)
            .to_return(status: 200, body: rss_feed, headers: {})
          stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works/6.json")
            .to_return(status: 200, body: embargo_resource, headers: {})
          stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works/20.json")
            .to_return(status: 200, body: embargo_resource, headers: {})

          Rails.configuration.pdc_discovery.index_pdc_describe = true
          indexer.index
        end

        it "does not index an embargo date" do
          expect(solr_response).to include("response")
          expect(response).to include("numFound")
          expect(num_found).to eq 1
          expect(docs).not_to be_empty
          expect(doc).not_to include("embargo_date_dtsi")
        end

        it "does index the files" do
          expect(solr_response).to include("response")
          expect(response).to include("numFound")
          expect(num_found).to eq 1
          expect(docs).not_to be_empty
          expect(doc).to include("pdc_describe_json_ss")
          expect(files).not_to be_empty
        end
      end
    end
  end
end
# rubocop:enable Metrics/BlockLength

1	# frozen_string_literal: true
2	require "rails_helper"	1✔
3
4	# rubocop:disable Metrics/BlockLength
5	RSpec.describe DescribeIndexer do	1✔
6	describe 'indexing a single record' do	1✔
7	let(:single_item) { file_fixture("bitklavier_binaural.json").read }	21✔
8	let(:indexer) do	1✔
9	described_class.new(rss_url: "file://whatever.rss")	20✔
10	end
11	let(:indexed_record) do	1✔
12	Blacklight.default_index.connection.delete_by_query(":")	20✔
13	Blacklight.default_index.connection.commit	20✔
14	indexer.index_one(single_item)	20✔
15	response = Blacklight.default_index.connection.get 'select', params: { q: ':' }	20✔
16	response["response"]["docs"].first	20✔
17	end
18
19	context "basic fields" do	1✔
20	##
21	# The id is based on the DOI
22	# A doi of 10.34770/r75s-9j74 will become doi-10-34770-r75s-9j74
23	it "id" do	1✔
24	expect(indexed_record["id"]).to eq "doi-10-34770-r75s-9j74"	1✔
25	end
26
27	it "stores a copy of the full JSON in CDATA" do	1✔
28	stored_json = indexed_record["pdc_describe_json_ss"]	1✔
29	parsed_json = JSON.parse(stored_json)	1✔
30	expect(parsed_json["resource"]["titles"][0]["title"]).to eq "bitKlavier Grand Sample Library—Binaural Mic Image"	1✔
31	end
32
33	it "author" do	1✔
34	expect(indexed_record["author_tesim"]).to eq ['Trueman, Daniel']	1✔
35	end
36
37	it "description" do	1✔
38	description = "The bitKlavier Grand consists"	1✔
39	expect(indexed_record["description_tsim"].first.include?(description)).to be true	1✔
40	end
41
42	it "contributors" do	1✔
43	expect(indexed_record["contributor_tsim"].include?("Villalta, Andrés")).to eq true	1✔
44	expect(indexed_record["contributor_tsim"].include?("Chou, Katie")).to eq true	1✔
45	expect(indexed_record["contributor_tsim"].include?("Ayres, Christien")).to eq true	1✔
46	expect(indexed_record["contributor_tsim"].include?("Wang, Matthew")).to eq true	1✔
47	end
48
49	it "title" do	1✔
50	# title includes all titles
51	main_title = "bitKlavier Grand Sample Library—Binaural Mic Image"	1✔
52	alt_title = "alter title for bitKlavier"	1✔
53	expect(indexed_record["title_tesim"].include?(main_title)).to eq true	1✔
54	expect(indexed_record["title_tesim"].include?(alt_title)).to eq true	1✔
55	# alt title does not include the main title
56	expect(indexed_record["alternative_title_tesim"].include?(main_title)).to eq false	1✔
57	expect(indexed_record["alternative_title_tesim"].include?(alt_title)).to eq true	1✔
58	end
59
60	it "rights" do	1✔
61	expect(indexed_record["rights_name_ssi"]).to eq "GNU General Public License"	1✔
62	expect(indexed_record["rights_uri_ssi"]).to eq "https://www.gnu.org/licenses/gpl-3.0.en.html"	1✔
63	end
64
65	it "keywords" do	1✔
66	expect(indexed_record["subject_all_ssim"].include?("keyword1")).to eq true	1✔
67	expect(indexed_record["subject_all_ssim"].include?("keyword2")).to eq true	1✔
68	expect(indexed_record["subject_all_ssim"].include?("keyword3")).to eq true	1✔
69	end
70
71	it "collection tag" do	1✔
72	expect(indexed_record["collection_tag_ssim"].include?("Humanities")).to eq true	1✔
73	expect(indexed_record["collection_tag_ssim"].include?("Something else")).to eq true	1✔
74	end
75
76	it "community" do	1✔
77	expect(indexed_record["community_name_ssi"]).to eq "Research Data"	1✔
78	end
79
80	it "genre_ssim" do	1✔
81	expect(indexed_record["genre_ssim"].first).to eq "Dataset"	1✔
82	end
83
84	it "issue_date_ssim" do	1✔
85	expect(indexed_record["issue_date_ssim"].first).to eq "2021"	1✔
86	end
87
88	# The pdc_created_at_dtsi field is used to describe when a record was created in PDC
89	# This is used to sort the Recently Published page
90	it "pdc_created_at_dtsi" do	1✔
91	expect(indexed_record["pdc_created_at_dtsi"]).to eq "2021-12-31T19:00:00Z"	1✔
92	# example timestamp 1997-12-31T23:59:59Z
93	end
94
95	it "pdc_updated_at_dtsi" do	1✔
96	expect(indexed_record["pdc_updated_at_dtsi"]).to eq "2021-12-31T20:00:00Z"	1✔
97	end
98
99	it "issue_date_strict_ssi" do	1✔
100	expect(indexed_record["issue_date_strict_ssi"]).to eq "2021-01-01"	1✔
101	end
102
103	it "publisher_ssim" do	1✔
104	expect(indexed_record["publisher_ssim"].first).to eq "Princeton University"	1✔
105	end
106
107	it "migrated_bsi" do	1✔
108	expect(indexed_record["migrated_bsi"]).to eq true	1✔
109	end
110
111	xit 'referenced_by' do	1✔
112	expect(result['referenced_by_ssim'].first).to eq 'https://arxiv.org/abs/1903.06605'	×
113	end
114	end
115
116	context "uris" do	1✔
117	it "stores full URL for ARK and DOI" do	1✔
118	expect(indexed_record["uri_ssim"].include?("http://arks.princeton.edu/ark:/88435/dsp015999n653h")).to eq true	1✔
119	expect(indexed_record["uri_ssim"].include?("https://doi.org/10.34770/r75s-9j74")).to eq true	1✔
120	end
121	end
122
123	context "files" do	1✔
124	it "stores file detailed information" do	1✔
125	files = JSON.parse(indexed_record['pdc_describe_json_ss'])['files']	1✔
126	file1 = files.find { \|file\| file["filename"] == "10.80021/3m1k-6036/122/file1.jpg" }	2✔
127	file2 = files.find { \|file\| file["filename"] == "10.80021/3m1k-6036/122/file2.txt" }	3✔
128	file3 = files.find { \|file\| file["filename"] == "10.80021/3m1k-6036/122/folder-a/file3.txt" }	5✔
129	expect(file1["size"]).to eq 316_781	1✔
130	expect(file1["url"]).to eq "https://g-5beea4.90d4e.bd7c.data.globus.org/pdc-describe-staging-postcuration/10.80021/3m1k-6036/122/file1.jpg"	1✔
131	expect(file2["size"]).to eq 396_003	1✔
132	expect(file3["url"]).to eq "https://g-5beea4.90d4e.bd7c.data.globus.org/pdc-describe-staging-postcuration/10.80021/3m1k-6036/122/folder-a/file3.txt"	1✔
133	end
134	end
135
136	context "all text catch all field" do	1✔
137	it "indexes the file name in the all text catch all field" do	1✔
138	files = JSON.parse(indexed_record['pdc_describe_json_ss'])['files']	1✔
139	file_name = File.basename(files.first["filename"])	1✔
140	response = Blacklight.default_index.connection.get 'select', params: { q: file_name }	1✔
141	expect(response["response"]["numFound"]).to eq 1	1✔
142
143	response = Blacklight.default_index.connection.get 'select', params: { q: "non-existing-value" }	1✔
144	expect(response["response"]["numFound"]).to eq 0	1✔
145	end
146	end
147	end
148
149	describe 'indexing an RSS feed from PDC Describe' do	1✔
150	let(:rss_feed) { file_fixture("works.rss").read }	4✔
151	let(:resource1) { file_fixture("bitklavier_binaural.json").read }	9✔
152	let(:resource2) { file_fixture("sowing_the_seeds.json").read }	9✔
153	let(:rss_url_string) { "https://pdc-describe-prod.princeton.edu/describe/works.rss" }	5✔
154	let(:indexer) { described_class.new(rss_url: rss_url_string) }	5✔
155
156	it "has a traject indexer" do	1✔
157	expect(indexer.traject_indexer).to be_instance_of Traject::Indexer::NokogiriIndexer	1✔
158	end
159
160	context 'indexing to solr' do	1✔
161	before do	1✔
162	Blacklight.default_index.connection.delete_by_query(":")	8✔
163	Blacklight.default_index.connection.commit	8✔
164	stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works.rss")	8✔
165	.to_return(status: 200, body: rss_feed, headers: {})
166	stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works/6.json")	8✔
167	.to_return(status: 200, body: resource1, headers: {})
168	stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works/20.json")	8✔
169	.to_return(status: 200, body: resource2, headers: {})
170	end
171
172	it "sends items to solr" do	1✔
173	response = Blacklight.default_index.connection.get 'select', params: { q: ':' }	1✔
174	expect(response["response"]["numFound"]).to eq 0	1✔
175
176	# If index_pdc_describe == false, do not index PDC Describe.
177	# This is a safety measure so we don't index in production until we're ready
178	# See config/pdc_discovery.yml to change this setting for real
179	Rails.configuration.pdc_discovery.index_pdc_describe = false	1✔
180	indexer.index	1✔
181	response = Blacklight.default_index.connection.get 'select', params: { q: ':' }	1✔
182	expect(response["response"]["numFound"]).to eq 0	1✔
183
184	# If index_pdc_describe == true, DO index PDC Describe.
185	Rails.configuration.pdc_discovery.index_pdc_describe = true	1✔
186	indexer.index	1✔
187	response = Blacklight.default_index.connection.get 'select', params: { q: ':' }	1✔
188	expect(response["response"]["numFound"]).to eq 2	1✔
189	end
190
191	it "can sort by issue_date_strict_ssi" do	1✔
192	Rails.configuration.pdc_discovery.index_pdc_describe = true	1✔
193	indexer.index	1✔
194	response = Blacklight.default_index.connection.get 'select', params: { q: ':', sort: 'issue_date_strict_ssi desc' }	1✔
195	expect(response["response"]["numFound"]).to eq 2	1✔
196	expect(response["response"]['docs'].first['pdc_created_at_dtsi']).to eq("2023-07-11T11:06:10Z")	1✔
197	expect(response["response"]['docs'].last['pdc_created_at_dtsi']).to eq("2021-12-31T19:00:00Z")	1✔
198	expect(response["response"]['docs'].first["issue_date_strict_ssi"]).to eq "2023-01-01"	1✔
199	expect(response["response"]['docs'].last["issue_date_strict_ssi"]).to eq "2021-01-01"	1✔
200	end
201
202	context "works with multiple creators" do	1✔
203	let(:pppl1) { File.read(File.join(fixture_paths.first, 'files', 'pppl1.json')) }	2✔
204	let(:pppl2) { File.read(File.join(fixture_paths.first, 'files', 'pppl2.json')) }	2✔
205	before do	1✔
206	stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works/6.json")	1✔
207	.to_return(status: 200, body: pppl1, headers: {})
208	stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works/20.json")	1✔
209	.to_return(status: 200, body: pppl2, headers: {})
210	end
211
212	it "can sort by the first author" do	1✔
213	Rails.configuration.pdc_discovery.index_pdc_describe = true	1✔
214	indexer.index	1✔
215	response = Blacklight.default_index.connection.get 'select', params: { q: ':', sort: 'author_si desc' }	1✔
216	expect(response["response"]["numFound"]).to eq 2	1✔
217	expect(response["response"]['docs'].first['author_tesim'].first).to eq("Wang, Yin")	1✔
218	expect(response["response"]['docs'].last['author_tesim'].first).to eq("Schwartz, Jacob A.")	1✔
219	expect(response["response"]['docs'].first["issue_date_strict_ssi"]).to eq "2021-12-30"	1✔
220	expect(response["response"]['docs'].last["issue_date_strict_ssi"]).to eq "2022-01-01"	1✔
221	end
222	end
223
224	context "when there are items which are under active embargo" do	1✔
225	let(:item_file_fixture) { file_fixture("pdc_describe_active_embargo.json") }	3✔
226	let(:embargo_resource) { item_file_fixture.read }	3✔
227	# This redundancy is required for consistent testing
228	let(:rss_feed) { file_fixture("works.rss").read }	3✔
229	let(:rss_url) { "https://pdc-describe-prod.princeton.edu/describe/works.rss" }	3✔
230	let(:indexer) do	1✔
231	described_class.new(rss_url: rss_url)	2✔
232	end
233	let(:solr_response) do	1✔
234	Blacklight.default_index.connection.get 'select', params: { q: ':' }	2✔
235	end
236	let(:response) { solr_response["response"] }	3✔
237	let(:num_found) { response["numFound"] }	3✔
238	let(:docs) { response["docs"] }	3✔
239	let(:doc) { docs.first }	3✔
240	let(:files) { JSON.parse(doc['pdc_describe_json_ss'])['files'] }	2✔
241
242	before do	1✔
243	stub_request(:get, rss_url)	2✔
244	.to_return(status: 200, body: rss_feed, headers: {})
245	stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works/6.json")	2✔
246	.to_return(status: 200, body: embargo_resource, headers: {})
247	stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works/20.json")	2✔
248	.to_return(status: 200, body: embargo_resource, headers: {})
249
250	Rails.configuration.pdc_discovery.index_pdc_describe = true	2✔
251	indexer.index	2✔
252	end
253
254	it "indexes the embargo date" do	1✔
255	expect(solr_response).to include("response")	1✔
256	expect(response).to include("numFound")	1✔
257	expect(num_found).to eq 1	1✔
258	expect(docs).not_to be_empty	1✔
259	expect(doc).to include("embargo_date_dtsi")	1✔
260	end
261
262	it "does not index the files" do	1✔
263	expect(solr_response).to include("response")	1✔
264	expect(response).to include("numFound")	1✔
265	expect(num_found).to eq 1	1✔
266	expect(docs).not_to be_empty	1✔
267	expect(doc).to include("pdc_describe_json_ss")	1✔
268	expect(files).to be_empty	1✔
269	end
270	end
271
272	context "when there are items which are under an expired embargo" do	1✔
273	let(:item_file_fixture) { file_fixture("pdc_describe_expired_embargo.json") }	2✔
274	let(:embargo_resource) { item_file_fixture.read }	2✔
275	# This redundancy is required for consistent testing
276	let(:rss_feed) { file_fixture("works.rss").read }	2✔
277	let(:rss_url) { "https://pdc-describe-prod.princeton.edu/describe/works.rss" }	2✔
278	let(:indexer) do	1✔
279	described_class.new(rss_url: rss_url)	1✔
280	end
281	let(:solr_response) do	1✔
282	Blacklight.default_index.connection.get 'select', params: { q: ':' }	1✔
283	end
284	let(:response) { solr_response["response"] }	2✔
285	let(:num_found) { response["numFound"] }	2✔
286	let(:docs) { response["docs"] }	2✔
287	let(:doc) { docs.first }	2✔
288	let(:files) { doc['pdc_describe_json_ss']['files'] }	2✔
289
290	before do	1✔
291	stub_request(:get, rss_url)	1✔
292	.to_return(status: 200, body: rss_feed, headers: {})
293	stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works/6.json")	1✔
294	.to_return(status: 200, body: embargo_resource, headers: {})
295	stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works/20.json")	1✔
296	.to_return(status: 200, body: embargo_resource, headers: {})
297
298	Rails.configuration.pdc_discovery.index_pdc_describe = true	1✔
299	indexer.index	1✔
300	end
301
302	it "does indexes the files" do	1✔
303	expect(solr_response).to include("response")	1✔
304	expect(response).to include("numFound")	1✔
305	expect(num_found).to eq 1	1✔
306	expect(docs).not_to be_empty	1✔
307	expect(doc).to include("pdc_describe_json_ss")	1✔
308	expect(files).not_to be_empty	1✔
309	end
310	end
311
312	context "when there work is not under embargo" do	1✔
313	let(:item_file_fixture) { file_fixture("pdc_describe_no_embargo.json") }	3✔
314	let(:embargo_resource) { item_file_fixture.read }	3✔
315	# This redundancy is required for consistent testing
316	let(:rss_feed) { file_fixture("works.rss").read }	3✔
317	let(:rss_url) { "https://pdc-describe-prod.princeton.edu/describe/works.rss" }	3✔
318	let(:indexer) do	1✔
319	described_class.new(rss_url: rss_url)	2✔
320	end
321	let(:solr_response) do	1✔
322	Blacklight.default_index.connection.get 'select', params: { q: ':' }	2✔
323	end
324	let(:response) { solr_response["response"] }	3✔
325	let(:num_found) { response["numFound"] }	3✔
326	let(:docs) { response["docs"] }	3✔
327	let(:doc) { docs.first }	3✔
328	let(:files) { doc['pdc_describe_json_ss']['files'] }	2✔
329
330	before do	1✔
331	stub_request(:get, rss_url)	2✔
332	.to_return(status: 200, body: rss_feed, headers: {})
333	stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works/6.json")	2✔
334	.to_return(status: 200, body: embargo_resource, headers: {})
335	stub_request(:get, "https://pdc-describe-prod.princeton.edu/describe/works/20.json")	2✔
336	.to_return(status: 200, body: embargo_resource, headers: {})
337
338	Rails.configuration.pdc_discovery.index_pdc_describe = true	2✔
339	indexer.index	2✔
340	end
341
342	it "does not index an embargo date" do	1✔
343	expect(solr_response).to include("response")	1✔
344	expect(response).to include("numFound")	1✔
345	expect(num_found).to eq 1	1✔
346	expect(docs).not_to be_empty	1✔
347	expect(doc).not_to include("embargo_date_dtsi")	1✔
348	end
349
350	it "does index the files" do	1✔
351	expect(solr_response).to include("response")	1✔
352	expect(response).to include("numFound")	1✔
353	expect(num_found).to eq 1	1✔
354	expect(docs).not_to be_empty	1✔
355	expect(doc).to include("pdc_describe_json_ss")	1✔
356	expect(files).not_to be_empty	1✔
357	end
358	end
359	end
360	end
361	end
362	# rubocop:enable Metrics/BlockLength

pulibrary / pdc_discovery / 787041f3-bb1b-461b-9eaa-c391c9c1e54a

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