f04bc944-f9b4-4a42-8b26-dcacd0e3e688

Committed 11 Mar 2025 10:27PM UTC coverage: 34.017% (-58.1%) from 92.162%

Build # f04bc944-f9b4-4a42-8b26-dcacd0e3e688

Build Type

Pull #2653

circleci

Committed by

christinach

Commit Message

Add new lc_subject_facet field.
Helps with the vocabulary work https://github.com/pulibrary/orangelight/pull/3386
In this new field we index only the lc subject heading and the subdivisions
So that when the user searches using the Details section, they can query solr for
all the subject headings and their divisions.

This is needed for the Subject browse Vocabulary work.
example: "lc_subject_facet": [
             "Booksellers and bookselling—Italy—Directories",
             "Booksellers and bookselling-Italy",
             "Booksellers and bookselling"
              ]

Pull Request Pull Request #2653: Add new lc_subject_facet field.

Run Details

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

2215 existing lines in 93 files now uncovered.

1294 of 3804 relevant lines covered (34.02%)

0.99 hits per line

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

48.28

/app/models/dump.rb

require 'zip'
require 'net/sftp'
require 'date'

class Dump < ActiveRecord::Base
  ENQUEUED = 'enqueued'.freeze
  STARTED = 'started'.freeze
  DONE = 'done'.freeze

  belongs_to :event
  has_many :dump_files
  # These only apply to change dumps (stored in db rather than text files)
  serialize :delete_ids
  serialize :update_ids
  serialize :recap_barcodes
  validates :event_id, presence: true

  before_destroy do
    self.dump_files.each do |df|
      df.destroy
    end
  end

  enum dump_type: {
    full_dump: 1,
    changed_records: 2,
    princeton_recap: 3,
    partner_recap: 4,
    partner_recap_full: 5,
    bib_ids: 6,
    merged_ids: 7
  }

  class << self
    ##
    # Create a dump of partner recap incremental records.
    def partner_update
      dump = nil
      timestamp = incremental_update_timestamp.to_s
      Event.record do |event|
        event.save
        dump = Dump.create(dump_type: :partner_recap, event_id: event.id)
        Import::Partner::Incremental.perform_async(dump.id, timestamp)
        dump.save
      end
      dump
    end

    def latest_generated
      order('generated_date desc').first
    end

    def generated_date(dump_id)
      dump = Dump.find(dump_id)
      dump.generated_date = dump.date_strings.map { |str| DateTime.parse(str) }.min
      dump.save!
    end

    def attach_dump_file(dump_id, file_path, dump_file_type = nil)
      dump = Dump.find(dump_id)
      df = DumpFile.create(dump_file_type:, path: file_path)
      df.zip
      df.save
      dump.dump_files << df
      dump.save
    end

    private

      ##
      # Figure out when was the last time we got partner update records, and find
      # anything that has appeared since then. The ways we can know the last time
      # we got partner update records are:
      # * via an environment variable
      # * look for the last partner recap dump and get its creation date
      # * or, if neither of those, use yesterday
      def incremental_update_timestamp
        (ENV.fetch('TIMESTAMP', nil) || last_incremental_update || (DateTime.now - 1)).to_time.strftime('%Y-%m-%d %H:%M:%S.%6N %z')
      end

      def last_incremental_update
        Dump.partner_recap.last&.created_at
      end
  end # class << self

  def date_strings
    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 subsequent_partner_incrementals
    Dump.partner_recap.where(generated_date: generated_date..Float::INFINITY)
  end

  def enqueued?
    index_status == ENQUEUED
  end

  def started?
    index_status == STARTED
  end

  def done?
    index_status == DONE
  end
end

1	require 'zip'	1✔
2	require 'net/sftp'	1✔
3	require 'date'	1✔
4
5	class Dump < ActiveRecord::Base	1✔
6	ENQUEUED = 'enqueued'.freeze	1✔
7	STARTED = 'started'.freeze	1✔
8	DONE = 'done'.freeze	1✔
9
10	belongs_to :event	1✔
11	has_many :dump_files	1✔
12	# These only apply to change dumps (stored in db rather than text files)
13	serialize :delete_ids	1✔
14	serialize :update_ids	1✔
15	serialize :recap_barcodes	1✔
16	validates :event_id, presence: true	1✔
17
18	before_destroy do	1✔
UNCOV 19	self.dump_files.each do \|df\|	×
UNCOV 20	df.destroy	×
21	end
22	end
23
24	enum dump_type: {	1✔
25	full_dump: 1,
26	changed_records: 2,
27	princeton_recap: 3,
28	partner_recap: 4,
29	partner_recap_full: 5,
30	bib_ids: 6,
31	merged_ids: 7
32	}
33
34	class << self	1✔
35	##
36	# Create a dump of partner recap incremental records.
37	def partner_update	1✔
UNCOV 38	dump = nil	×
UNCOV 39	timestamp = incremental_update_timestamp.to_s	×
UNCOV 40	Event.record do \|event\|	×
UNCOV 41	event.save	×
UNCOV 42	dump = Dump.create(dump_type: :partner_recap, event_id: event.id)	×
UNCOV 43	Import::Partner::Incremental.perform_async(dump.id, timestamp)	×
UNCOV 44	dump.save	×
45	end
UNCOV 46	dump	×
47	end
48
49	def latest_generated	1✔
UNCOV 50	order('generated_date desc').first	×
51	end
52
53	def generated_date(dump_id)	1✔
UNCOV 54	dump = Dump.find(dump_id)	×
UNCOV 55	dump.generated_date = dump.date_strings.map { \|str\| DateTime.parse(str) }.min	×
UNCOV 56	dump.save!	×
57	end
58
59	def attach_dump_file(dump_id, file_path, dump_file_type = nil)	1✔
UNCOV 60	dump = Dump.find(dump_id)	×
UNCOV 61	df = DumpFile.create(dump_file_type:, path: file_path)	×
UNCOV 62	df.zip	×
UNCOV 63	df.save	×
UNCOV 64	dump.dump_files << df	×
UNCOV 65	dump.save	×
66	end
67
68	private	1✔
69
70	##
71	# Figure out when was the last time we got partner update records, and find
72	# anything that has appeared since then. The ways we can know the last time
73	# we got partner update records are:
74	# * via an environment variable
75	# * look for the last partner recap dump and get its creation date
76	# * or, if neither of those, use yesterday
77	def incremental_update_timestamp	1✔
UNCOV 78	(ENV.fetch('TIMESTAMP', nil) \|\| last_incremental_update \|\| (DateTime.now - 1)).to_time.strftime('%Y-%m-%d %H:%M:%S.%6N %z')	×
79	end
80
81	def last_incremental_update	1✔
UNCOV 82	Dump.partner_recap.last&.created_at	×
83	end
84	end # class << self
85
86	def date_strings	1✔
UNCOV 87	dump_files.map do \|df\|	×
UNCOV 88	if df.dump_file_type == 'recap_records_full_metadata'	×
UNCOV 89	File.basename(df.path).split('_')[3]	×
90	else
UNCOV 91	File.basename(df.path).split('_')[2]	×
92	end
93	end
94	end
95
96	def subsequent_partner_incrementals	1✔
UNCOV 97	Dump.partner_recap.where(generated_date: generated_date..Float::INFINITY)	×
98	end
99
100	def enqueued?	1✔
101	index_status == ENQUEUED	×
102	end
103
104	def started?	1✔
105	index_status == STARTED	×
106	end
107
108	def done?	1✔
109	index_status == DONE	×
110	end
111	end

pulibrary / bibdata / f04bc944-f9b4-4a42-8b26-dcacd0e3e688

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