373ad6ff-fad2-405a-ab26-3d30fb5ceecf

Committed 24 Dec 2024 08:24PM UTC coverage: 91.938% (+0.08%) from 91.859%

Build # 373ad6ff-fad2-405a-ab26-3d30fb5ceecf

Build Type

Pull #2563

circleci

Committed by

maxkadel

Commit Message

Put attaching xml files in their own batch

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

Run Details

152 of 156 new or added lines in 10 files covered. (97.44%)

65 existing lines in 17 files now uncovered.

3478 of 3783 relevant lines covered (91.94%)

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

pulibrary / bibdata / 373ad6ff-fad2-405a-ab26-3d30fb5ceecf

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