Skip to content

Parse all subsets of a usage report rather than only the last #238

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
codycooperross merged 2 commits into from
Feb 11, 2026
Merged

Parse all subsets of a usage report rather than only the last #238

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
42183b4
Parse all subsets rather than only the last
codycooperross Feb 10, 2026
df064a0
Add test for parse_multi_subset_report
codycooperross Feb 11, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 17 additions & 9 deletions app/models/report.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,11 +24,6 @@ def initialize(report, _options = {})
end

def self.parse_multi_subset_report(report)
subset = report.subsets.last

compressed = decode_report subset["gzip"]
json = decompress_report compressed
dataset_array = parse_subset json
url = case true
when Rails.env.production?
"https://api.datacite.org/reports/#{report.report_id}"
Expand All @@ -37,11 +32,24 @@ def self.parse_multi_subset_report(report)
else
"https://api.stage.datacite.org/reports/#{report.report_id}"
end
dataset_array.map do |dataset|
args = { header: report.header, url: url }
UsageUpdateParseJob.perform_later(dataset, args)

subsets = report.subsets
all_datasets = []

subsets.each do |subset|
compressed = decode_report subset["gzip"]
json = decompress_report compressed
dataset_array = parse_subset json

dataset_array.map do |dataset|
args = { header: report.header, url: url }
UsageUpdateParseJob.perform_later(dataset, args)
end

all_datasets.concat(dataset_array)
end
dataset_array

all_datasets
end

def self.parse_normal_report(report)
Expand Down
62 changes: 62 additions & 0 deletions ...subset_report/when_report_is_ok/should_parse_and_return_all_datasets_from_all_subsets.yml
View file
Open in desktop

Large diffs are not rendered by default.

35 changes: 14 additions & 21 deletions spec/models/report_spec.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,33 +7,26 @@
let(:url) do
"https://api.stage.datacite.org/reports/9e5461d8-0713-4abd-8e87-e4533a76ab3d"
end
# let(:url) {"https://api.stage.datacite.org/reports/82022fc3-8b31-47f2-88a8-24814d9bd2f0"}

# describe "parse_multi_subset_report" do
# context "when report is ok" do
# let(:body) {File.read(fixture_path + 'multi_subset_report.json')}
# let(:uncompressed) {File.read(fixture_path + 'datacite_resolution_report_2018-09.json')}
# let(:result) {OpenStruct.new(body: JSON.parse(body), url:"https://api.stage.datacite.org/reports/5cac6ca0-9391-4e1d-95cf-ba2f475cbfad")}
# let(:report) {Report.new(result)}

# it "should parsed it give you two arrays that are in every gzip" do
# live_results = Maremma.get(url, host: "https://api.stage.datacite.org/")
# report = Report.new(live_results)
describe "parse_multi_subset_report" do
context "when report is ok" do
it "should parse and return all datasets from all subsets" do
allow(UsageUpdateParseJob).to receive(:perform_later)

# rr = Report.parse_multi_subset_report report
# expect(rr).to be_a(Array)
# expect(rr.size).to eq(408)
# expect(rr.first.dig("performance")).to be_present
# end
# end
# end
response = UsageUpdate.get_data("https://api.datacite.org/reports/d0b2b372-1d0a-4aa6-8aad-a04673050cb2")
report = Report.new(response)
rr = Report.parse_multi_subset_report report

expect(rr).to be_a(Array)
expect(rr.size).to eq(57929)
expect(rr.first.dig("performance")).to be_present
end
end
end

describe "parse_normal_report" do
context "when report is ok" do
let(:body) { File.read("#{fixture_path}multi_subset_report.json") }
let(:uncompressed) do
File.read("#{fixture_path}datacite_resolution_report_2018-09.json")
end
let(:result) do
OpenStruct.new(body: JSON.parse(body),
url: "https://api.stage.datacite.org/reports/5cac6ca0-9391-4e1d-95cf-ba2f475cbfad")
Expand Down