cace366a-ffad-45f1-9b60-678e607fa527

Committed 14 May 2024 02:21PM UTC coverage: 60.862% (-35.0%) from 95.908%

Build # cace366a-ffad-45f1-9b60-678e607fa527

Build Type

push

circleci

Committed by

jrgriffiniii

Commit Message

wip

Run Details

1 of 3 new or added lines in 2 files covered. (33.33%)

1194 existing lines in 57 files now uncovered.

2076 of 3411 relevant lines covered (60.86%)

22.71 hits per line

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

20.93

/app/services/pul_dspace_connector.rb

1	# frozen_string_literal: true
2	class PULDspaceConnector	1✔
3	attr_reader :work, :ark, :download_base	1✔
4
5	DSPACE_PAGE_SIZE = 20	1✔
6
7	def initialize(work)	1✔
UNCOV 8	@work = work	×
UNCOV 9	@ark = work.ark&.gsub("ark:/", "")	×
UNCOV 10	@download_base = "#{Rails.configuration.dspace.base_url.gsub('rest/', '')}bitstream/#{ark}"	×
11	end
12
13	def id	1✔
UNCOV 14	@id \|\|= begin	×
UNCOV 15	json = get_data("handle/#{ark}")	×
UNCOV 16	json["id"]	×
17	end
18	end
19
20	def bitstreams	1✔
UNCOV 21	@bitstreams \|\|= begin	×
UNCOV 22	data = []	×
23	# handle pages if needed
24	# this is a inelegant way to get all the files, but I am not seeing a count anywhere
UNCOV 25	loop do	×
UNCOV 26	new_data = get_data("items/#{id}/bitstreams?offset=#{data.length}&limit=#{DSPACE_PAGE_SIZE}")	×
UNCOV 27	data.concat(new_data) unless new_data.empty?	×
UNCOV 28	break if new_data.count < DSPACE_PAGE_SIZE	×
29	end
UNCOV 30	data	×
31	end
32	end
33
34	def metadata	1✔
UNCOV 35	@metadata \|\|= begin	×
UNCOV 36	json = get_data("items/#{id}/metadata")	×
UNCOV 37	metadata = {}	×
UNCOV 38	json.each do \|value\|	×
UNCOV 39	key = value["key"]	×
UNCOV 40	metadata[key] = [] if metadata[key].blank?	×
UNCOV 41	metadata[key] << value["value"]	×
42	end
UNCOV 43	metadata	×
44	end
45	end
46
47	def list_bitsteams	1✔
UNCOV 48	@list_bitsteams \|\|=	×
49	original_bitstreams.map do \|bitstream\|
UNCOV 50	path = File.join(Rails.configuration.dspace.download_file_path, "dspace_download", work.id.to_s)	×
UNCOV 51	filename = File.join(path, bitstream["name"])	×
UNCOV 52	if bitstream["checkSum"]["checkSumAlgorithm"] != "MD5"	×
53	Honeybadger.notify("Unknown checksum algorithm #{bitstream['checkSum']['checkSumAlgorithm']} #{filename} #{bitstream}")	×
54	end
55
UNCOV 56	S3File.new(filename_display: bitstream["name"], checksum: base64digest(bitstream["checkSum"]["value"]), last_modified: DateTime.now,	×
57	size: -1, work:, url: "#{download_base}/#{bitstream['sequenceId']}", filename:)
58	end
59	end
60
61	def download_bitstreams(bitstream_list)	1✔
UNCOV 62	bitstream_list.map do \|file\|	×
UNCOV 63	filename = download_bitstream(file.url, file.filename)	×
UNCOV 64	if checksum_file(filename, file.checksum)	×
UNCOV 65	file	×
66	else
UNCOV 67	{ file:, error: "Checsum Missmatch" }	×
68	end
69	end
70	end
71
72	def doi	1✔
UNCOV 73	return "" if ark.nil?	×
UNCOV 74	@doi \|\|= begin	×
UNCOV 75	doi_url = metadata["dc.identifier.uri"].select { \|value\| value.starts_with?("https://doi.org/") }&.first	×
UNCOV 76	doi_url&.gsub("https://doi.org/", "")	×
77	end
78	end
79
80	private	1✔
81
82	def get_data(url_path)	1✔
UNCOV 83	return {} if ark.nil?	×
84
UNCOV 85	url = "#{Rails.configuration.dspace.base_url}#{url_path}"	×
UNCOV 86	uri = URI(url)	×
UNCOV 87	http = request_http(url)	×
UNCOV 88	req = Net::HTTP::Get.new uri	×
UNCOV 89	response = http.request req	×
UNCOV 90	if response.code != "200"	×
91	Honeybadger.notify("Error retreiving dspace data from #{url} #{response.code} #{response.body}")	×
92	return nil	×
93	end
UNCOV 94	JSON.parse(response.body)	×
95	end
96
97	def download_bitstream(retrieval_url, filename)	1✔
UNCOV 98	path = File.join(Rails.configuration.dspace.download_file_path, "dspace_download", work.id.to_s)	×
UNCOV 99	FileUtils.mkdir_p path	×
UNCOV 100	download_file(retrieval_url, filename)	×
UNCOV 101	filename	×
102	end
103
104	def download_file(url, filename)	1✔
UNCOV 105	stdout_and_stderr_str, status = Open3.capture2e("wget -c '#{url}' -O '#{filename}'")	×
UNCOV 106	unless status.success?	×
107	Honeybadger.notify("Error dowloading file #{url} for work id #{work.id} to #{filename}! Error: #{stdout_and_stderr_str}")	×
108	end
109	end
110
111	def checksum_file(filename, original_checksum)	1✔
UNCOV 112	checksum = Digest::MD5.file(filename)	×
UNCOV 113	base64 = checksum.base64digest	×
UNCOV 114	if base64 != original_checksum	×
UNCOV 115	msg = "Mismatching checksum #{filename} #{original_checksum} for work: #{work.id} doi: #{work.doi} ark: #{work.ark}"	×
UNCOV 116	Rails.logger.error msg	×
UNCOV 117	Honeybadger.notify(msg)	×
UNCOV 118	false	×
119	else
UNCOV 120	Rails.logger.debug { "Matching checksums for #{filename}" }	×
UNCOV 121	true	×
122	end
123	end
124
125	def base64digest(hexdigest)	1✔
UNCOV 126	[[hexdigest].pack("H*")].pack("m0")	×
127	end
128
129	def request_http(url)	1✔
UNCOV 130	uri = URI(url)	×
UNCOV 131	http = Net::HTTP.new(uri.host, uri.port)	×
UNCOV 132	http.use_ssl = true	×
UNCOV 133	http	×
134	end
135
136	def original_bitstreams	1✔
UNCOV 137	bitstreams.select { \|bitstream\| bitstream["bundleName"] == "ORIGINAL" }	×
138	end
139	end

pulibrary / pdc_describe / cace366a-ffad-45f1-9b60-678e607fa527

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