381ebe8c-8717-4a37-93a5-7a9a805ad9de

Committed 20 Dec 2024 07:43PM UTC coverage: 91.859% (-0.05%) from 91.904%

Build # 381ebe8c-8717-4a37-93a5-7a9a805ad9de

Build Type

Pull #2563

circleci

Committed by

maxkadel

Commit Message

Test for idempotency

Pull Request Pull Request #2563: I2321 Shift SCSB full index tasks into separate background jobs

Run Details

91 of 92 new or added lines in 6 files covered. (98.91%)

5 existing lines in 1 file now uncovered.

3419 of 3722 relevant lines covered (91.86%)

375.43 hits per line

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

89.53

/app/models/scsb/partner_updates/update.rb

module Scsb
  class PartnerUpdates
    class Update
      attr_accessor :dump
      def initialize(dump:, dump_file_type:, timestamp:)
        @last_dump = timestamp
        @dump = dump
        @dump_file_type = dump_file_type
        @s3_bucket = Scsb::S3Bucket.partner_transfer_client
        @scsb_file_dir = ENV['SCSB_FILE_DIR']
        @update_directory = ENV['SCSB_PARTNER_UPDATE_DIRECTORY'] || '/tmp/updates'
      end

      def process_partner_updates(files:, file_prefix: 'scsb_update_')
        xml_files = []
        files.each do |file|
          xml_files << Scsb::PartnerUpdates::Update.extract_files(file:, update_directory: @update_directory)
        end
        xml_files.flatten.each do |file|
          Scsb::PartnerUpdates::Update.attach_cleaned_dump_file(file:, dump_id: @dump.id, file_prefix:, dump_file_type: @dump_file_type)
        end
      end

      def self.extract_files(file:, update_directory:)
        extracted_files = []
        filename = File.basename(file, '.zip')
        filename.gsub!(/^[^_]+_([0-9]+)_([0-9]+).*$/, '\1_\2')
        file_increment = 1
        Zip::File.open(file) do |zip_file|
          zip_file.each do |entry|
            target = "#{update_directory}/#{filename}_#{file_increment}.xml"
            extracted_files << target
            entry.extract(target)
            file_increment += 1
          end
        end
        File.unlink(file)
        extracted_files
      end

      def self.attach_cleaned_dump_file(file:, dump_id:, file_prefix:, dump_file_type: :recap_records_full)
        scsb_file_dir = ENV['SCSB_FILE_DIR']
        @inv_xml = []
        @tab_newline = []
        @leader = []
        @composed_chars = []
        @bad_utf8 = []
        original_filename = File.basename(file)
        reader = MARC::XMLReader.new(file.to_s, external_encoding: 'UTF-8')
        new_filepath = "#{scsb_file_dir}/#{file_prefix}#{original_filename}"
        writer = MARC::XMLWriter.new(new_filepath)
        reader.each { |record| writer.write(process_record(record)) }
        writer.close
        File.unlink(file)
        Dump.attach_dump_file(dump_id:, filepath: new_filepath, dump_file_type:)
      end

      def self.process_record(record)
        record = field_delete(['856', '959'], record)
        record.leader[5] = 'c' if record.leader[5].eql?('d')
        if bad_utf8?(record)
          @bad_utf8 << record['001']
          record = bad_utf8_fix(record)
        end
        if invalid_xml_chars?(record)
          @inv_xml << record['001']
          record = invalid_xml_fix(record)
        end
        if tab_newline_char?(record)
          @tab_newline << record['001']
          record = tab_newline_fix(record)
        end
        if leader_errors?(record)
          @leader << record['001']
          record = leaderfix(record)
        end
        if composed_chars_errors?(record)
          @composed_chars << record['001']
          record = composed_chars_normalize(record)
        end
        record = extra_space_fix(record)
        empty_subfield_fix(record)
      end

      def add_error(message:)
        error = Array.wrap(@dump.event.error)
        error << message
        @dump.event.error = error.join("; ")
        @dump.event.save
      end

      def log_record_fixes
        log_file = {
          inv_xml: @inv_xml,
          tab_newline: @tab_newline,
          leader: @leader,
          composed_chars: @composed_chars,
          bad_utf8: @bad_utf8
        }
        filepath = log_file_name
        File.write(filepath, log_file.to_json.to_s)
        Dump.attach_dump_file(dump_id: @dump.id, filepath:, dump_file_type: :log_file)
      end

      def log_file_name
        "#{@scsb_file_dir}/fixes_#{@last_dump.to_time.strftime('%Y_%m_%d')}.json"
      end

      def set_generated_date
        @dump.generated_date = date_strings.map { |str| DateTime.parse(str) }.sort.first
      end

      def date_strings
        @dump.dump_files.map do |df|
          if df.dump_file_type == "recap_records_full_metadata"
            File.basename(df.path).split("_")[3]
          else
            File.basename(df.path).split("_")[2]
          end
        end
      end

      def prepare_directory
        FileUtils.mkdir_p(@update_directory)
      end
    end
  end
end

1	module Scsb	1✔
2	class PartnerUpdates	1✔
3	class Update	1✔
4	attr_accessor :dump	1✔
5	def initialize(dump:, dump_file_type:, timestamp:)	1✔
6	@last_dump = timestamp	13✔
7	@dump = dump	13✔
8	@dump_file_type = dump_file_type	13✔
9	@s3_bucket = Scsb::S3Bucket.partner_transfer_client	13✔
10	@scsb_file_dir = ENV['SCSB_FILE_DIR']	13✔
11	@update_directory = ENV['SCSB_PARTNER_UPDATE_DIRECTORY'] \|\| '/tmp/updates'	13✔
12	end
13
14	def process_partner_updates(files:, file_prefix: 'scsb_update_')	1✔
15	xml_files = []	3✔
16	files.each do \|file\|	3✔
17	xml_files << Scsb::PartnerUpdates::Update.extract_files(file:, update_directory: @update_directory)	3✔
18	end
19	xml_files.flatten.each do \|file\|	3✔
20	Scsb::PartnerUpdates::Update.attach_cleaned_dump_file(file:, dump_id: @dump.id, file_prefix:, dump_file_type: @dump_file_type)	6✔
21	end
22	end
23
24	def self.extract_files(file:, update_directory:)	1✔
25	extracted_files = []	11✔
26	filename = File.basename(file, '.zip')	11✔
27	filename.gsub!(/^[^_]+_([0-9]+)_([0-9]+).*$/, '\1_\2')	11✔
28	file_increment = 1	11✔
29	Zip::File.open(file) do \|zip_file\|	11✔
30	zip_file.each do \|entry\|	9✔
31	target = "#{update_directory}/#{filename}_#{file_increment}.xml"	18✔
32	extracted_files << target	18✔
33	entry.extract(target)	18✔
34	file_increment += 1	18✔
35	end
36	end
37	File.unlink(file)	10✔
38	extracted_files	10✔
39	end
40
41	def self.attach_cleaned_dump_file(file:, dump_id:, file_prefix:, dump_file_type: :recap_records_full)	1✔
42	scsb_file_dir = ENV['SCSB_FILE_DIR']	18✔
43	@inv_xml = []	18✔
44	@tab_newline = []	18✔
45	@leader = []	18✔
46	@composed_chars = []	18✔
47	@bad_utf8 = []	18✔
48	original_filename = File.basename(file)	18✔
49	reader = MARC::XMLReader.new(file.to_s, external_encoding: 'UTF-8')	18✔
50	new_filepath = "#{scsb_file_dir}/#{file_prefix}#{original_filename}"	18✔
51	writer = MARC::XMLWriter.new(new_filepath)	18✔
52	reader.each { \|record\| writer.write(process_record(record)) }	54✔
53	writer.close	18✔
54	File.unlink(file)	18✔
55	Dump.attach_dump_file(dump_id:, filepath: new_filepath, dump_file_type:)	18✔
56	end
57
58	def self.process_record(record)	1✔
59	record = field_delete(['856', '959'], record)	37✔
60	record.leader[5] = 'c' if record.leader[5].eql?('d')	37✔
61	if bad_utf8?(record)	37✔
62	@bad_utf8 << record['001']	×
63	record = bad_utf8_fix(record)	×
64	end
65	if invalid_xml_chars?(record)	37✔
66	@inv_xml << record['001']	×
67	record = invalid_xml_fix(record)	×
68	end
69	if tab_newline_char?(record)	37✔
70	@tab_newline << record['001']	3✔
71	record = tab_newline_fix(record)	3✔
72	end
73	if leader_errors?(record)	37✔
74	@leader << record['001']	8✔
75	record = leaderfix(record)	8✔
76	end
77	if composed_chars_errors?(record)	37✔
78	@composed_chars << record['001']	11✔
79	record = composed_chars_normalize(record)	11✔
80	end
81	record = extra_space_fix(record)	37✔
82	empty_subfield_fix(record)	37✔
83	end
84
85	def add_error(message:)	1✔
UNCOV 86	error = Array.wrap(@dump.event.error)	×
UNCOV 87	error << message	×
UNCOV 88	@dump.event.error = error.join("; ")	×
UNCOV 89	@dump.event.save	×
90	end
91
92	def log_record_fixes	1✔
93	log_file = {
94	inv_xml: @inv_xml,	10✔
95	tab_newline: @tab_newline,
96	leader: @leader,
97	composed_chars: @composed_chars,
98	bad_utf8: @bad_utf8
99	}
100	filepath = log_file_name	10✔
101	File.write(filepath, log_file.to_json.to_s)	10✔
102	Dump.attach_dump_file(dump_id: @dump.id, filepath:, dump_file_type: :log_file)	8✔
103	end
104
105	def log_file_name	1✔
106	"#{@scsb_file_dir}/fixes_#{@last_dump.to_time.strftime('%Y_%m_%d')}.json"	10✔
107	end
108
109	def set_generated_date	1✔
110	@dump.generated_date = date_strings.map { \|str\| DateTime.parse(str) }.sort.first	16✔
111	end
112
113	def date_strings	1✔
114	@dump.dump_files.map do \|df\|	10✔
115	if df.dump_file_type == "recap_records_full_metadata"	6✔
UNCOV 116	File.basename(df.path).split("_")[3]	×
117	else
118	File.basename(df.path).split("_")[2]	6✔
119	end
120	end
121	end
122
123	def prepare_directory	1✔
124	FileUtils.mkdir_p(@update_directory)	10✔
125	end
126	end
127	end
128	end

pulibrary / bibdata / 381ebe8c-8717-4a37-93a5-7a9a805ad9de

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