83785282-b493-4102-b828-c01dc1ed4e60

Committed 31 Dec 2024 07:48PM UTC coverage: 91.93% (+0.07%) from 91.859%

Build # 83785282-b493-4102-b828-c01dc1ed4e60

Build Type

Pull #2563

circleci

Committed by

maxkadel

Commit Message

Create more nested batches

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

Run Details

184 of 188 new or added lines in 11 files covered. (97.87%)

4 existing lines in 1 file now uncovered.

3497 of 3804 relevant lines covered (91.93%)

366.53 hits per line

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

91.49

/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) if dump_file_type == :recap_records
        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 self.generated_date(dump_id:)
        dump = Dump.find(dump_id)
        dump.generated_date = date_strings(dump:).map { |str| DateTime.parse(str) }.sort.first
      end

      def self.date_strings(dump:)
        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 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
6	def initialize(dump:, dump_file_type:, timestamp:)	1✔
7	@last_dump = timestamp	11✔
8	@dump = dump	11✔
9	@dump_file_type = dump_file_type	11✔
10	@s3_bucket = Scsb::S3Bucket.partner_transfer_client	11✔
11	@scsb_file_dir = ENV['SCSB_FILE_DIR']	11✔
12	@update_directory = ENV['SCSB_PARTNER_UPDATE_DIRECTORY'] \|\| '/tmp/updates'	11✔
13	end
14
15	def process_partner_updates(files:, file_prefix: 'scsb_update_')	1✔
16	xml_files = []	3✔
17	files.each do \|file\|	3✔
18	xml_files << Scsb::PartnerUpdates::Update.extract_files(file:, update_directory: @update_directory)	3✔
19	end
20	xml_files.flatten.each do \|file\|	3✔
21	Scsb::PartnerUpdates::Update.attach_cleaned_dump_file(file:, dump_id: @dump.id, file_prefix:, dump_file_type: @dump_file_type)	6✔
22	end
23	end
24
25	def self.extract_files(file:, update_directory:)	1✔
26	extracted_files = []	19✔
27	filename = File.basename(file, '.zip')	19✔
28	filename.gsub!(/^[^_]+_([0-9]+)_([0-9]+).*$/, '\1_\2')	19✔
29	file_increment = 1	19✔
30	Zip::File.open(file) do \|zip_file\|	19✔
31	zip_file.each do \|entry\|	16✔
32	target = "#{update_directory}/#{filename}_#{file_increment}.xml"	32✔
33	extracted_files << target	32✔
34	entry.extract(target)	32✔
35	file_increment += 1	32✔
36	end
37	end
38	File.unlink(file)	18✔
39	extracted_files	18✔
40	end
41
42	def self.attach_cleaned_dump_file(file:, dump_id:, file_prefix:, dump_file_type: :recap_records_full)	1✔
43	scsb_file_dir = ENV['SCSB_FILE_DIR']	32✔
44	@inv_xml = []	32✔
45	@tab_newline = []	32✔
46	@leader = []	32✔
47	@composed_chars = []	32✔
48	@bad_utf8 = []	32✔
49	original_filename = File.basename(file)	32✔
50	reader = MARC::XMLReader.new(file.to_s, external_encoding: 'UTF-8')	32✔
51	new_filepath = "#{scsb_file_dir}/#{file_prefix}#{original_filename}"	32✔
52	writer = MARC::XMLWriter.new(new_filepath)	32✔
53	reader.each { \|record\| writer.write(process_record(record)) }	96✔
54	writer.close	32✔
55	File.unlink(file) if dump_file_type == :recap_records	32✔
56	Dump.attach_dump_file(dump_id:, filepath: new_filepath, dump_file_type:)	32✔
57	end
58
59	def self.process_record(record)	1✔
60	record = field_delete(['856', '959'], record)	65✔
61	record.leader[5] = 'c' if record.leader[5].eql?('d')	65✔
62	if bad_utf8?(record)	65✔
63	@bad_utf8 << record['001']	×
64	record = bad_utf8_fix(record)	×
65	end
66	if invalid_xml_chars?(record)	65✔
67	@inv_xml << record['001']	×
68	record = invalid_xml_fix(record)	×
69	end
70	if tab_newline_char?(record)	65✔
71	@tab_newline << record['001']	3✔
72	record = tab_newline_fix(record)	3✔
73	end
74	if leader_errors?(record)	65✔
75	@leader << record['001']	10✔
76	record = leaderfix(record)	10✔
77	end
78	if composed_chars_errors?(record)	65✔
79	@composed_chars << record['001']	19✔
80	record = composed_chars_normalize(record)	19✔
81	end
82	record = extra_space_fix(record)	65✔
83	empty_subfield_fix(record)	65✔
84	end
85
86	def add_error(message:)	1✔
UNCOV 87	error = Array.wrap(@dump.event.error)	×
UNCOV 88	error << message	×
UNCOV 89	@dump.event.error = error.join('; ')	×
UNCOV 90	@dump.event.save	×
91	end
92
93	def log_record_fixes	1✔
94	log_file = {
95	inv_xml: @inv_xml,	8✔
96	tab_newline: @tab_newline,
97	leader: @leader,
98	composed_chars: @composed_chars,
99	bad_utf8: @bad_utf8
100	}
101	filepath = log_file_name	8✔
102	File.write(filepath, log_file.to_json.to_s)	8✔
103	Dump.attach_dump_file(dump_id: @dump.id, filepath:, dump_file_type: :log_file)	8✔
104	end
105
106	def log_file_name	1✔
107	"#{@scsb_file_dir}/fixes_#{@last_dump.to_time.strftime('%Y_%m_%d')}.json"	8✔
108	end
109
110	def self.generated_date(dump_id:)	1✔
111	dump = Dump.find(dump_id)	1✔
112	dump.generated_date = date_strings(dump:).map { \|str\| DateTime.parse(str) }.sort.first	10✔
113	end
114
115	def self.date_strings(dump:)	1✔
116	dump.dump_files.map do \|df\|	1✔
117	if df.dump_file_type == 'recap_records_full_metadata'	9✔
118	File.basename(df.path).split('_')[3]	3✔
119	else
120	File.basename(df.path).split('_')[2]	6✔
121	end
122	end
123	end
124
125	def set_generated_date	1✔
126	@dump.generated_date = date_strings.map { \|str\| DateTime.parse(str) }.sort.first	40✔
127	end
128
129	def date_strings	1✔
130	@dump.dump_files.map do \|df\|	8✔
131	if df.dump_file_type == 'recap_records_full_metadata'	32✔
132	File.basename(df.path).split('_')[3]	10✔
133	else
134	File.basename(df.path).split('_')[2]	22✔
135	end
136	end
137	end
138
139	def prepare_directory	1✔
140	FileUtils.mkdir_p(@update_directory)	8✔
141	end
142	end
143	end
144	end

pulibrary / bibdata / 83785282-b493-4102-b828-c01dc1ed4e60

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