b9c905b4-2897-4d3e-a367-72f83b94e852

Committed 28 Oct 2024 03:54PM UTC coverage: 84.116% (+0.03%) from 84.083%

Build # b9c905b4-2897-4d3e-a367-72f83b94e852

Build Type

push

circleci

Committed by

web-flow

Commit Message

Updating to set mediaflux id and storage performance to Standard for imported works (#1009)

Run Details

4 of 4 branches covered (100.0%)

0 of 1 new or added line in 1 file covered. (0.0%)

2150 of 2556 relevant lines covered (84.12%)

302.07 hits per line

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

19.05

/lib/tasks/import.rake

require 'csv'
# frozen_string_literal: true
#
# The input file can be created by running by running the following script in aterm:
#
# set ids [xvalues id [asset.query :where xpath(tigerdata:project/ProjectID) has value]]
# puts "asset,path,creatorDomain,creatorUser,createdOn,quota,store,projectDirectory,title,description,dataSponsor,dataManager,dataUser,department,projectID"
# foreach id $ids {
#     set asset [asset.get :id $id]
#     set path [xvalue asset/path $asset]
#     set creatorDomain [xvalue asset/creator/domain $asset]
#     set creatorUser [xvalue asset/creator/user $asset]
#     set createdOn [xvalue  asset/ctime $asset]
#     set store [xvalue asset/collection/store $asset]
#     set projectDirectory [xvalue asset/meta/tigerdata:project/ProjectDirectory $asset]
#     set title [xvalue asset/meta/tigerdata:project/Title $asset]
#     set description [xvalue asset/meta/tigerdata:project/Description $asset]
#     set dataSponsor [xvalue asset/meta/tigerdata:project/DataSponsor $asset]
#     set dataManager [xvalue asset/meta/tigerdata:project/DataManager $asset]
#     set dataUser [xvalue asset/meta/tigerdata:project/DataUser $asset]
#     set department [xvalue asset/meta/tigerdata:project/Department $asset]
#     set projectID [xvalue asset/meta/tigerdata:project/ProjectID $asset]
#     set quota [xvalue asset/collection/quota/allocation $asset]
#     puts $id "," $path "," $creatorDomain "," $creatorUser "," $createdOn "," \
#         $quota "," $store "," $projectDirectory "," \"$title\" "," \"$description\" "," \
#         $dataSponsor "," $dataManager "," $dataUser "," $department "," $projectID 
# }
#
#


namespace :import do
    # command line syntax: bundle exec rake metadata:update_pppl_subcommunities\["netid"\]
    desc "import projects from mediaflux csv file"
    task :mediaflux_projects, [:project_file, :test_run] => [:environment] do |_, args|
      project_file = args[:project_file]
      test_run = args[:test_run] || false
      mediaflux_projects = CSV.read(project_file, headers: true)
      mediaflux_projects.each do |project_metadata|
        project_id = project_metadata["projectID"]
        existing_project = Project.where("metadata_json @> ?", JSON.dump(project_id:))
        if existing_project.count > 0
          puts "Skipping project #{project_id}.  There are already #{existing_project.count} version of that project in the system"
        else
          data_user = if project_metadata["dataUser"].blank?
                        []
                      else
                        [project_metadata["dataUser"]]
                      end
          storage_size_gb = project_metadata["quota"].to_i/1000000000.0
          metadata = ProjectMetadata.new_from_hash({
            project_id:,
            title: project_metadata["title"],
            description: project_metadata["description"],
            status: Project::ACTIVE_STATUS,
            data_sponsor: project_metadata["dataSponsor"],
            data_manager: project_metadata["dataManager"],
            departments: [project_metadata["department"]],
            data_user_read_only: data_user,
            project_directory: project_metadata["path"],
            storage_capacity: {size: { approved: storage_size_gb, requested: storage_size_gb}, unit: {approved: "GB", requested: "GB"}},
            storage_performance_expectations: { requested: "Standard", approved: "Standard" },
            created_by: project_metadata["creatorUser"],
            created_on: project_metadata["createdOn"]
          })
          if test_run
            puts metadata.to_json
          else
            project = Project.create!(metadata:, mediaflux_id: project_metadata["asset"])
            puts "Created project for #{project_id}"
          end
        end
      end
    end
  end

1	require 'csv'	1✔
2	# frozen_string_literal: true
3	#
4	# The input file can be created by running by running the following script in aterm:
5	#
6	# set ids [xvalues id [asset.query :where xpath(tigerdata:project/ProjectID) has value]]
7	# puts "asset,path,creatorDomain,creatorUser,createdOn,quota,store,projectDirectory,title,description,dataSponsor,dataManager,dataUser,department,projectID"
8	# foreach id $ids {
9	# set asset [asset.get :id $id]
10	# set path [xvalue asset/path $asset]
11	# set creatorDomain [xvalue asset/creator/domain $asset]
12	# set creatorUser [xvalue asset/creator/user $asset]
13	# set createdOn [xvalue asset/ctime $asset]
14	# set store [xvalue asset/collection/store $asset]
15	# set projectDirectory [xvalue asset/meta/tigerdata:project/ProjectDirectory $asset]
16	# set title [xvalue asset/meta/tigerdata:project/Title $asset]
17	# set description [xvalue asset/meta/tigerdata:project/Description $asset]
18	# set dataSponsor [xvalue asset/meta/tigerdata:project/DataSponsor $asset]
19	# set dataManager [xvalue asset/meta/tigerdata:project/DataManager $asset]
20	# set dataUser [xvalue asset/meta/tigerdata:project/DataUser $asset]
21	# set department [xvalue asset/meta/tigerdata:project/Department $asset]
22	# set projectID [xvalue asset/meta/tigerdata:project/ProjectID $asset]
23	# set quota [xvalue asset/collection/quota/allocation $asset]
24	# puts $id "," $path "," $creatorDomain "," $creatorUser "," $createdOn "," \
25	# $quota "," $store "," $projectDirectory "," \"$title\" "," \"$description\" "," \
26	# $dataSponsor "," $dataManager "," $dataUser "," $department "," $projectID
27	# }
28	#
29	#
30
31
32	namespace :import do	1✔
33	# command line syntax: bundle exec rake metadata:update_pppl_subcommunities\["netid"\]
34	desc "import projects from mediaflux csv file"	1✔
35	task :mediaflux_projects, [:project_file, :test_run] => [:environment] do \|_, args\|	1✔
36	project_file = args[:project_file]	×
37	test_run = args[:test_run] \|\| false	×
38	mediaflux_projects = CSV.read(project_file, headers: true)	×
39	mediaflux_projects.each do \|project_metadata\|	×
40	project_id = project_metadata["projectID"]	×
41	existing_project = Project.where("metadata_json @> ?", JSON.dump(project_id:))	×
42	if existing_project.count > 0	×
43	puts "Skipping project #{project_id}. There are already #{existing_project.count} version of that project in the system"	×
44	else
45	data_user = if project_metadata["dataUser"].blank?	×
46	[]	×
47	else
48	[project_metadata["dataUser"]]	×
49	end
50	storage_size_gb = project_metadata["quota"].to_i/1000000000.0	×
51	metadata = ProjectMetadata.new_from_hash({	×
52	project_id:,
53	title: project_metadata["title"],
54	description: project_metadata["description"],
55	status: Project::ACTIVE_STATUS,
56	data_sponsor: project_metadata["dataSponsor"],
57	data_manager: project_metadata["dataManager"],
58	departments: [project_metadata["department"]],
59	data_user_read_only: data_user,
60	project_directory: project_metadata["path"],
61	storage_capacity: {size: { approved: storage_size_gb, requested: storage_size_gb}, unit: {approved: "GB", requested: "GB"}},
62	storage_performance_expectations: { requested: "Standard", approved: "Standard" },
63	created_by: project_metadata["creatorUser"],
64	created_on: project_metadata["createdOn"]
65	})
66	if test_run	×
67	puts metadata.to_json	×
68	else
NEW 69	project = Project.create!(metadata:, mediaflux_id: project_metadata["asset"])	×
70	puts "Created project for #{project_id}"	×
71	end
72	end
73	end
74	end
75	end

pulibrary / tigerdata-app / b9c905b4-2897-4d3e-a367-72f83b94e852

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