cdc23dd4-7656-4660-bfe1-6a9fb1bebcca

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'
        @inv_xml = []
        @tab_newline = []
        @leader = []
        @composed_chars = []
        @bad_utf8 = []
      end

      def attach_dump_file(filepath, dump_file_type: nil)
        dump_file_type ||= @dump_file_type
        df = DumpFile.create(dump_file_type:, path: filepath)
        df.zip
        df.save
        @dump.dump_files << df
        @dump.save
      end

      def process_partner_updates(files:, file_prefix: 'scsb_update_')
        xml_files = []
        files.each do |file|
          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"
              xml_files << target
              entry.extract(target)
              file_increment += 1
            end
          end
          File.unlink(file)
        end
        xml_files.each do |file|
          filename = File.basename(file)
          reader = MARC::XMLReader.new(file.to_s, external_encoding: 'UTF-8')
          filepath = "#{@scsb_file_dir}/#{file_prefix}#{filename}"
          writer = MARC::XMLWriter.new(filepath)
          reader.each { |record| writer.write(process_record(record)) }
          writer.close
          File.unlink(file)
          attach_dump_file(filepath)
        end
      end

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

pulibrary / bibdata / cdc23dd4-7656-4660-bfe1-6a9fb1bebcca

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