38778a1e-2dd3-4ec3-b4d6-a6c4d301682a

Committed 07 Dec 2023 05:02PM UTC coverage: 87.536% (+0.6%) from 86.964%

Build # 38778a1e-2dd3-4ec3-b4d6-a6c4d301682a

Build Type

push

circleci

Committed by

web-flow

Commit Message

Merge pull request #79 from pulibrary/i77-jrgriffiniii-date-display

Updates Rubocop, refactors DataSpace Solr Document generation, and ensures that invalid embargo dates trigger log warnings

Run Details

190 of 196 new or added lines in 5 files covered. (96.94%)

12 existing lines in 1 file now uncovered.

604 of 690 relevant lines covered (87.54%)

18.31 hits per line

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

87.28

/lib/orangetheses/indexer.rb

# frozen_string_literal: true

require 'rsolr'
require 'rexml/document'
require 'chronic'
require 'logger'
require 'json'
require 'iso-639'
require 'yaml'
require 'erb'

module Orangetheses
  class Indexer
    SET = 'Princeton University Senior Theses'

    NON_SPECIAL_ELEMENT_MAPPING = {
      'creator' => %w[author_display author_s],
      'contributor' => %w[advisor_display author_s],
      'format' => ['description_display'],
      'rights' => ['rights_reproductions_note_display'],
      'description' => ['summary_note_display']
    }.freeze

    REST_NON_SPECIAL_ELEMENT_MAPPING = {
      'dc.contributor.author' => %w[author_display author_s],
      'dc.contributor.advisor' => %w[advisor_display author_s],
      'dc.contributor' => %w[contributor_display author_s],
      'pu.department' => %w[department_display author_s],
      'pu.certificate' => %w[certificate_display author_s],
      'dc.format.extent' => ['description_display'],
      'dc.description.abstract' => ['summary_note_display']
    }.freeze

    HARD_CODED_TO_ADD = {
      'format' => 'Senior thesis'
    }.freeze

    # @todo This needs to be refactored into a separate Class
    def self.config_file
      File.join(File.dirname(__FILE__), '..', '..', 'config', 'solr.yml')
    end

    def self.config_yaml
      ERB.new(IO.read(config_file)).result(binding)
    rescue StandardError, SyntaxError => e
      raise("#{config_file} was found, but could not be parsed with ERB. \n#{e.inspect}")
    end

    def self.config_values
      YAML.safe_load(config_yaml)
    end

    def self.env
      ENV['ORANGETHESES_ENV'] || 'development'
    end

    def self.config
      OpenStruct.new(solr: config_values[env])
    end

    def self.default_solr_url
      config.solr['url']
    end

    def initialize(solr_server = nil)
      solr_server ||= self.class.default_solr_url

      @solr = RSolr.connect(url: solr_server)
      @logger = Logger.new($stdout)
      @logger.level = Logger::INFO
      @logger.formatter = proc do |severity, datetime, _progname, msg|
        time = datetime.strftime('%H:%M:%S')
        "[#{time}] #{severity}: #{msg}\n"
      end
    end

    # @param element  A REXML::Element (because this is what we get from the OAI gem)
    # @return  The HTTP response status from Solr (??)
    def index(metadata_element)
      dc_elements = pull_dc_elements(metadata_element)
      doc = build_hash(dc_elements)
      @logger.info("Adding #{doc['id']}")
      @solr.add(doc, add_attributes: { commitWithin: 10 })
    rescue NoMethodError => e
      @logger.error(e.to_s)
      @logger.error(metadata_element)
    rescue StandardError => e
      @logger.error(e.to_s)
      dc_elements.each { |element| @logger.error(element.to_s) }
    end

    # Constructs DataspaceDocument objects from a Hash of attributes
    # @returns [DataspaceDocument]
    def build_solr_document(**values)
      id = values['id']

      title = values['dc.title']
      title_t = title_search_hash(title)
      title_citation_display = first_or_nil(title)
      title_display = title_citation_display
      title_sort = title_sort_hash(title)

      author = values['dc.contributor.author']
      author_sort = first_or_nil(author)

      electronic_access_1display = ark_hash(values)

      identifier_other = values['dc.identifier.other']
      call_number_display = call_number(identifier_other)
      call_number_browse_s = call_number_display

      language_iso = values['dc.language.iso']
      language_facet = code_to_language(language_iso)
      language_name_display = language_facet

      embargo_lift = values['pu.embargo.lift']
      embargo_terms = values['pu.embargo.terms']
      walkin = values['pu.mudd.walkin']
      location = values['pu.location']
      access_rights = values['dc.rights.accessRights']

      attrs = {
        'id' => id,
        'title_t' => title_t,
        'title_citation_display' => title_citation_display,
        'title_display' => title_display,
        'title_sort' => title_sort,
        'author_sort' => author_sort,
        'electronic_access_1display' => electronic_access_1display,
        'pu.embargo.lift' => embargo_lift,
        'pu.embargo.terms' => embargo_terms,
        'pu.mudd.walkin' => walkin,
        'pu.location' => location,
        'dc.rights.accessRights' => access_rights,
        'call_number_display' => call_number_display,
        'call_number_browse_s' => call_number_browse_s,
        'language_facet' => language_facet,
        'language_name_display' => language_name_display
      }
      mapped = map_rest_non_special_to_solr(values)
      attrs.merge!(mapped)

      holdings = holdings_access(values)
      attrs.merge!(holdings)

      class_years = class_year_fields(values)
      attrs.merge!(class_years)

      attrs.merge!(HARD_CODED_TO_ADD)

      DataspaceDocument.new(document: attrs, logger: @logger)
    end

    # @param doc [Hash] Metadata hash with dc and pu terms
    # @return  The HTTP response status from Solr (??)
    def index_document(**values)
      solr_doc = build_solr_document(**values)

      @logger.info("Adding #{solr_doc['id']}")
      @solr.add(solr_doc, add_attributes: { commitWithin: 10 })
    rescue NoMethodError => e
      @logger.error(e.to_s)
      @logger.error(doc.to_s)
    rescue StandardError => e
      @logger.error(e.to_s)
      @logger.error(doc.to_s)
    end

    private

    def build_hash(dc_elements)
      date = choose_date(dc_elements)
      h = {
        'id' => id(dc_elements),
        'title_t' => title(dc_elements),
        'title_citation_display' => title(dc_elements),
        'title_display' => title(dc_elements),
        'title_sort' => title_sort(dc_elements),
        'author_sort' => author_sort(dc_elements),
        'format' => 'Senior Thesis',
        'pub_date_display' => date,
        'pub_date_start_sort' => date,
        'pub_date_end_sort' => date,
        'class_year_s' => date,
        'access_facet' => 'Online',
        'electronic_access_1display' => ark(dc_elements),
        'standard_no_1display' => non_ark_ids(dc_elements),
        'electronic_portfolio_s' => online_holding({})

      }
      h.merge!(map_non_special_to_solr(dc_elements))
      h.merge!(HARD_CODED_TO_ADD)
      h
    end

    # @return Array<REXML::Element>  the descriptive elements
    def pull_dc_elements(element)
      element.elements.to_a('oai_dc:dc/*')
    end

    def choose_date(dc_elements)
      dates = all_date_elements(dc_elements).map { |d| Chronic.parse(d.text) }
      dates.empty? ? nil : dates.min.year
    end

    def all_date_elements(dc_elements)
      dc_elements.select { |e| e.name == 'date' }
    end

    def title(dc_elements)
      titles = dc_elements.select { |e| e.name == 'title' }
      titles.empty? ? nil : titles.first.text
    end

    def title_sort(dc_elements)
      titles = dc_elements.select { |e| e.name == 'title' }
      title = titles.empty? ? nil : titles.first.text
      title.downcase.gsub(/[^\p{Alnum}\s]/, '').gsub(/^(a|an|the)\s/, '').gsub(/\s/, '') unless title.nil?
    end

    def ark(dc_elements)
      arks = dc_elements.select do |e|
        e.name == 'identifier' && e.text.start_with?('http://arks.princeton')
      end
      arks.empty? ? nil : { arks.first.text => dspace_display_text(dc_elements) }.to_json.to_s
    end

    def online_holding(doc)
      {
        'thesis' => {
          'call_number' => call_number(doc['dc.identifier.other']),
          'call_number_browse' => call_number(doc['dc.identifier.other']),
          'dspace' => true
        }
      }.to_json.to_s
    end

    def physical_holding(doc, accessible: true)
      {
        'thesis' => {
          'location' => 'Mudd Manuscript Library',
          'library' => 'Mudd Manuscript Library',
          'location_code' => 'mudd$stacks',
          'call_number' => call_number(doc['dc.identifier.other']),
          'call_number_browse' => call_number(doc['dc.identifier.other']),
          'dspace' => accessible
        }
      }.to_json.to_s
    end

    def non_ark_ids(dc_elements)
      non_ark_ids = dc_elements.select do |e|
        e.name == 'identifier' && !e.text.start_with?('http://arks.princeton')
      end
      return { 'Other identifier' => non_ark_ids.map(&:text) }.to_json.to_s unless non_ark_ids.empty?

      nil
    end

    def id(dc_elements)
      arks = dc_elements.select do |e|
        e.name == 'identifier' && e.text.start_with?('http://arks.princeton')
      end
      arks.empty? ? nil : arks.first.text.split('/').last
    end

    def author_sort(dc_elements)
      authors = dc_elements.select { |e| e.name == 'creator' }
      authors.empty? ? nil : authors.first.text
    end

    def choose_date_hash(doc)
      dates = all_date_elements_hash(doc).map { |_k, v| Chronic.parse(v.first) }.compact
      dates.empty? ? nil : dates.min.year
    end

    def all_date_elements_hash(doc)
      doc.select { |k, _v| k[/dc\.date/] }
    end

    def title_sort_hash(titles)
      titles.first.downcase.gsub(/[^\p{Alnum}\s]/, '').gsub(/^(a|an|the)\s/, '').gsub(/\s/, '') unless titles.nil?
    end

    # Take first title, strip out latex expressions when present to include along
    # with non-normalized version (allowing users to get matches both when LaTex
    # is pasted directly into the search box and when sub/superscripts are placed
    # adjacent to regular characters
    def title_search_hash(titles)
      return if titles.nil?

      title = titles.first
      title.scan(/\\\(.*?\\\)/).each do |latex|
        title = title.gsub(latex, latex.gsub(/[^\p{Alnum}]/, ''))
      end
      title == titles.first ? title : [titles.first, title]
    end

    def ark_hash(doc)
      arks = doc['dc.identifier.uri']
      arks.nil? ? nil : { arks.first => dspace_display_text_hash(doc) }.to_json.to_s
    end

    def call_number(non_ark_ids)
      non_ark_ids.nil? ? 'AC102' : "AC102 #{non_ark_ids.first}"
    end

    def first_or_nil(field)
      field&.first
    end

    def dspace_display_text(dc_elements)
      text = [dataspace]
      text << if dc_elements.select { |e| e.name == 'rights' }.empty?
                full_text
              else
                citation
              end
      text
    end

    def dspace_display_text_hash(doc)
      text = [dataspace]
      text << if on_site_only?(doc)
                citation
              else
                full_text
              end
      text
    end

    def on_site_only?(doc)
      doc.key?('pu.location') || doc.key?('dc.rights.accessRights') ||
        embargo?(doc) || walkin?(doc)
    end

    def embargo?(doc)
      date = doc['pu.embargo.lift'] || doc['pu.embargo.terms']
      return false if date.nil?

      date = Chronic.parse(date.first)
      if date.nil?
        @logger.info("No valid embargo date for #{doc['id']}")
        return false
      end

      date > Time.now
    end

    def embargo(doc)
      return if doc.key?('pu.embargo.lift')

      date = doc['pu.embargo.lift'] || doc['pu.embargo.terms']
      date = Chronic.parse(date.first) unless date.nil?
      date = date.strftime('%B %-d, %Y') unless date.nil?
      date
    end

    def walkin?(doc)
      walkin = doc['pu.mudd.walkin']
      !walkin.nil? && walkin.first == 'yes'
    end

    def restrictions_display_text(doc)
      if embargo?(doc)
        date = embargo(doc)
        "This content is embargoed until #{date}. For more information contact the "\
        "<a href=\"mailto:dspadmin@princeton.edu?subject=Regarding embargoed DataSpace Item 88435/#{doc['id']}\"> "\
        'Mudd Manuscript Library</a>.'
      elsif doc.key?('pu.location') || doc.key?('dc.rights.accessRights')
        [doc['pu.location'], doc['dc.rights.accessRights']].flatten.compact
      elsif walkin?(doc)
        walkin_text
      end
    end

    def walkin_text
      'Walk-in Access. This thesis can only be viewed on computer terminals at the '\
      '<a href=\"http://mudd.princeton.edu\">Mudd Manuscript Library</a>.'
    end

    def dataspace
      'DataSpace'
    end

    def full_text
      'Full text'
    end

    def citation
      'Citation only'
    end

    # this is kind of a mess...
    def map_non_special_to_solr(dc_elements)
      h = {}
      NON_SPECIAL_ELEMENT_MAPPING.each do |element_name, fields|
        elements = dc_elements.select { |e| e.name == element_name }
        fields.each do |f|
          if h.key?(f)
            h[f].push(*elements.map(&:text))
          else
            h[f] = elements.map(&:text)
          end
        end
      end
      h
    end

    # default English
    def code_to_language(codes)
      languages = []
      # en_US is not valid iso code
      codes&.each do |c|
        code_lang = ISO_639.find(c[/^[^_]*/]) # en_US is not valid iso code
        l = code_lang.nil? ? 'English' : code_lang.english_name
        languages << l
      end
      languages.empty? ? 'English' : languages.uniq
    end

    def map_rest_non_special_to_solr(doc)
      h = {}
      REST_NON_SPECIAL_ELEMENT_MAPPING.each do |field_name, solr_fields|
        next unless doc.key?(field_name)

        solr_fields.each do |f|
          val = []
          val << h[f]
          val << doc[field_name]
          h[f] = val.flatten.compact
          # Ruby might have a bug here
          # if h.has_key?(f)
          #   h[f].push(doc[field_name])
          # else
          #   h[f] = doc[field_name]
          # end
        end
      end
      h
    end

    def class_year_fields(doc)
      h = {}
      if doc.key?('pu.date.classyear') && doc['pu.date.classyear'].first =~ /^\d+$/
        h['class_year_s'] = doc['pu.date.classyear']
        h['pub_date_start_sort'] = doc['pu.date.classyear']
        h['pub_date_end_sort'] = doc['pu.date.classyear']
      end
      h
    end

    # online access when there isn't a restriction/location note
    def holdings_access(doc)
      if embargo?(doc)
        {
          'location' => 'Mudd Manuscript Library',
          'location_display' => 'Mudd Manuscript Library',
          'location_code_s' => 'mudd$stacks',
          'advanced_location_s' => ['mudd$stacks', 'Mudd Manuscript Library'],
          'holdings_1display' => physical_holding(doc, accessible: false)
        }
      elsif on_site_only?(doc)
        {
          'location' => 'Mudd Manuscript Library',
          'location_display' => 'Mudd Manuscript Library',
          'location_code_s' => 'mudd$stacks',
          'advanced_location_s' => ['mudd$stacks', 'Mudd Manuscript Library'],
          'access_facet' => 'In the Library',
          'holdings_1display' => physical_holding(doc)
        }
      else
        {
          'access_facet' => 'Online',
          'electronic_portfolio_s' => online_holding(doc)
        }
      end
    end
  end
end

1	# frozen_string_literal: true
2
3	require 'rsolr'	1✔
4	require 'rexml/document'	1✔
5	require 'chronic'	1✔
6	require 'logger'	1✔
7	require 'json'	1✔
8	require 'iso-639'	1✔
9	require 'yaml'	1✔
10	require 'erb'	1✔
11
12	module Orangetheses	1✔
13	class Indexer	1✔
14	SET = 'Princeton University Senior Theses'	1✔
15
16	NON_SPECIAL_ELEMENT_MAPPING = {
17	'creator' => %w[author_display author_s],	1✔
18	'contributor' => %w[advisor_display author_s],
19	'format' => ['description_display'],
20	'rights' => ['rights_reproductions_note_display'],
21	'description' => ['summary_note_display']
22	}.freeze
23
24	REST_NON_SPECIAL_ELEMENT_MAPPING = {
25	'dc.contributor.author' => %w[author_display author_s],	1✔
26	'dc.contributor.advisor' => %w[advisor_display author_s],
27	'dc.contributor' => %w[contributor_display author_s],
28	'pu.department' => %w[department_display author_s],
29	'pu.certificate' => %w[certificate_display author_s],
30	'dc.format.extent' => ['description_display'],
31	'dc.description.abstract' => ['summary_note_display']
32	}.freeze
33
34	HARD_CODED_TO_ADD = {	1✔
35	'format' => 'Senior thesis'
36	}.freeze
37
38	# @todo This needs to be refactored into a separate Class
39	def self.config_file	1✔
40	File.join(File.dirname(__FILE__), '..', '..', 'config', 'solr.yml')	74✔
41	end
42
43	def self.config_yaml	1✔
44	ERB.new(IO.read(config_file)).result(binding)	74✔
45	rescue StandardError, SyntaxError => e
NEW 46	raise("#{config_file} was found, but could not be parsed with ERB. \n#{e.inspect}")	×
47	end
48
49	def self.config_values	1✔
50	YAML.safe_load(config_yaml)	74✔
51	end
52
53	def self.env	1✔
54	ENV['ORANGETHESES_ENV'] \|\| 'development'	74✔
55	end
56
57	def self.config	1✔
58	OpenStruct.new(solr: config_values[env])	74✔
59	end
60
61	def self.default_solr_url	1✔
62	config.solr['url']	74✔
63	end
64
65	def initialize(solr_server = nil)	1✔
66	solr_server \|\|= self.class.default_solr_url	74✔
67
68	@solr = RSolr.connect(url: solr_server)	74✔
69	@logger = Logger.new($stdout)	74✔
70	@logger.level = Logger::INFO	74✔
71	@logger.formatter = proc do \|severity, datetime, _progname, msg\|	74✔
72	time = datetime.strftime('%H:%M:%S')	3✔
73	"[#{time}] #{severity}: #{msg}\n"	3✔
74	end
75	end
76
77	# @param element A REXML::Element (because this is what we get from the OAI gem)
78	# @return The HTTP response status from Solr (??)
79	def index(metadata_element)	1✔
80	dc_elements = pull_dc_elements(metadata_element)	×
81	doc = build_hash(dc_elements)	×
82	@logger.info("Adding #{doc['id']}")	×
83	@solr.add(doc, add_attributes: { commitWithin: 10 })	×
84	rescue NoMethodError => e
85	@logger.error(e.to_s)	×
86	@logger.error(metadata_element)	×
87	rescue StandardError => e
88	@logger.error(e.to_s)	×
89	dc_elements.each { \|element\| @logger.error(element.to_s) }	×
90	end
91
92	# Constructs DataspaceDocument objects from a Hash of attributes
93	# @returns [DataspaceDocument]
94	def build_solr_document(**values)	1✔
95	id = values['id']	10✔
96
97	title = values['dc.title']	10✔
98	title_t = title_search_hash(title)	10✔
99	title_citation_display = first_or_nil(title)	10✔
100	title_display = title_citation_display	10✔
101	title_sort = title_sort_hash(title)	10✔
102
103	author = values['dc.contributor.author']	10✔
104	author_sort = first_or_nil(author)	10✔
105
106	electronic_access_1display = ark_hash(values)	10✔
107
108	identifier_other = values['dc.identifier.other']	10✔
109	call_number_display = call_number(identifier_other)	10✔
110	call_number_browse_s = call_number_display	10✔
111
112	language_iso = values['dc.language.iso']	10✔
113	language_facet = code_to_language(language_iso)	10✔
114	language_name_display = language_facet	10✔
115
116	embargo_lift = values['pu.embargo.lift']	10✔
117	embargo_terms = values['pu.embargo.terms']	10✔
118	walkin = values['pu.mudd.walkin']	10✔
119	location = values['pu.location']	10✔
120	access_rights = values['dc.rights.accessRights']	10✔
121
122	attrs = {
123	'id' => id,	10✔
124	'title_t' => title_t,
125	'title_citation_display' => title_citation_display,
126	'title_display' => title_display,
127	'title_sort' => title_sort,
128	'author_sort' => author_sort,
129	'electronic_access_1display' => electronic_access_1display,
130	'pu.embargo.lift' => embargo_lift,
131	'pu.embargo.terms' => embargo_terms,
132	'pu.mudd.walkin' => walkin,
133	'pu.location' => location,
134	'dc.rights.accessRights' => access_rights,
135	'call_number_display' => call_number_display,
136	'call_number_browse_s' => call_number_browse_s,
137	'language_facet' => language_facet,
138	'language_name_display' => language_name_display
139	}
140	mapped = map_rest_non_special_to_solr(values)	10✔
141	attrs.merge!(mapped)	10✔
142
143	holdings = holdings_access(values)	10✔
144	attrs.merge!(holdings)	10✔
145
146	class_years = class_year_fields(values)	10✔
147	attrs.merge!(class_years)	10✔
148
149	attrs.merge!(HARD_CODED_TO_ADD)	10✔
150
151	DataspaceDocument.new(document: attrs, logger: @logger)	10✔
152	end
153
154	# @param doc [Hash] Metadata hash with dc and pu terms
155	# @return The HTTP response status from Solr (??)
156	def index_document(**values)	1✔
NEW 157	solr_doc = build_solr_document(**values)	×
158
159	@logger.info("Adding #{solr_doc['id']}")	×
160	@solr.add(solr_doc, add_attributes: { commitWithin: 10 })	×
161	rescue NoMethodError => e
162	@logger.error(e.to_s)	×
163	@logger.error(doc.to_s)	×
164	rescue StandardError => e
165	@logger.error(e.to_s)	×
166	@logger.error(doc.to_s)	×
167	end
168
169	private	1✔
170
171	def build_hash(dc_elements)	1✔
172	date = choose_date(dc_elements)	1✔
173	h = {
174	'id' => id(dc_elements),	1✔
175	'title_t' => title(dc_elements),
176	'title_citation_display' => title(dc_elements),
177	'title_display' => title(dc_elements),
178	'title_sort' => title_sort(dc_elements),
179	'author_sort' => author_sort(dc_elements),
180	'format' => 'Senior Thesis',
181	'pub_date_display' => date,
182	'pub_date_start_sort' => date,
183	'pub_date_end_sort' => date,
184	'class_year_s' => date,
185	'access_facet' => 'Online',
186	'electronic_access_1display' => ark(dc_elements),
187	'standard_no_1display' => non_ark_ids(dc_elements),
188	'electronic_portfolio_s' => online_holding({})
189
190	}
191	h.merge!(map_non_special_to_solr(dc_elements))	1✔
192	h.merge!(HARD_CODED_TO_ADD)	1✔
193	h	1✔
194	end
195
196	# @return Array<REXML::Element> the descriptive elements
197	def pull_dc_elements(element)	1✔
198	element.elements.to_a('oai_dc:dc/*')	1✔
199	end
200
201	def choose_date(dc_elements)	1✔
202	dates = all_date_elements(dc_elements).map { \|d\| Chronic.parse(d.text) }	11✔
203	dates.empty? ? nil : dates.min.year	4✔
204	end
205
206	def all_date_elements(dc_elements)	1✔
207	dc_elements.select { \|e\| e.name == 'date' }	15✔
208	end
209
210	def title(dc_elements)	1✔
211	titles = dc_elements.select { \|e\| e.name == 'title' }	12✔
212	titles.empty? ? nil : titles.first.text	5✔
213	end
214
215	def title_sort(dc_elements)	1✔
216	titles = dc_elements.select { \|e\| e.name == 'title' }	10✔
217	title = titles.empty? ? nil : titles.first.text	5✔
218	title.downcase.gsub(/[^\p{Alnum}\s]/, '').gsub(/^(a\|an\|the)\s/, '').gsub(/\s/, '') unless title.nil?	5✔
219	end
220
221	def ark(dc_elements)	1✔
222	arks = dc_elements.select do \|e\|	4✔
223	e.name == 'identifier' && e.text.start_with?('http://arks.princeton')	9✔
224	end
225	arks.empty? ? nil : { arks.first.text => dspace_display_text(dc_elements) }.to_json.to_s	4✔
226	end
227
228	def online_holding(doc)	1✔
229	{
230	'thesis' => {	8✔
231	'call_number' => call_number(doc['dc.identifier.other']),
232	'call_number_browse' => call_number(doc['dc.identifier.other']),
233	'dspace' => true
234	}
235	}.to_json.to_s
236	end
237
238	def physical_holding(doc, accessible: true)	1✔
239	{
240	'thesis' => {	16✔
241	'location' => 'Mudd Manuscript Library',
242	'library' => 'Mudd Manuscript Library',
243	'location_code' => 'mudd$stacks',
244	'call_number' => call_number(doc['dc.identifier.other']),
245	'call_number_browse' => call_number(doc['dc.identifier.other']),
246	'dspace' => accessible
247	}
248	}.to_json.to_s
249	end
250
251	def non_ark_ids(dc_elements)	1✔
252	non_ark_ids = dc_elements.select do \|e\|	1✔
253	e.name == 'identifier' && !e.text.start_with?('http://arks.princeton')	1✔
254	end
255	return { 'Other identifier' => non_ark_ids.map(&:text) }.to_json.to_s unless non_ark_ids.empty?	1✔
256
257	nil
258	end
259
260	def id(dc_elements)	1✔
261	arks = dc_elements.select do \|e\|	1✔
262	e.name == 'identifier' && e.text.start_with?('http://arks.princeton')	1✔
263	end
264	arks.empty? ? nil : arks.first.text.split('/').last	1✔
265	end
266
267	def author_sort(dc_elements)	1✔
268	authors = dc_elements.select { \|e\| e.name == 'creator' }	9✔
269	authors.empty? ? nil : authors.first.text	3✔
270	end
271
272	def choose_date_hash(doc)	1✔
273	dates = all_date_elements_hash(doc).map { \|_k, v\| Chronic.parse(v.first) }.compact	9✔
274	dates.empty? ? nil : dates.min.year	3✔
275	end
276
277	def all_date_elements_hash(doc)	1✔
278	doc.select { \|k, _v\| k[/dc\.date/] }	13✔
279	end
280
281	def title_sort_hash(titles)	1✔
282	titles.first.downcase.gsub(/[^\p{Alnum}\s]/, '').gsub(/^(a\|an\|the)\s/, '').gsub(/\s/, '') unless titles.nil?	14✔
283	end
284
285	# Take first title, strip out latex expressions when present to include along
286	# with non-normalized version (allowing users to get matches both when LaTex
287	# is pasted directly into the search box and when sub/superscripts are placed
288	# adjacent to regular characters
289	def title_search_hash(titles)	1✔
290	return if titles.nil?	11✔
291
292	title = titles.first	4✔
293	title.scan(/\\\(.*?\\\)/).each do \|latex\|	4✔
294	title = title.gsub(latex, latex.gsub(/[^\p{Alnum}]/, ''))	2✔
295	end
296	title == titles.first ? title : [titles.first, title]	4✔
297	end
298
299	def ark_hash(doc)	1✔
300	arks = doc['dc.identifier.uri']	13✔
301	arks.nil? ? nil : { arks.first => dspace_display_text_hash(doc) }.to_json.to_s	13✔
302	end
303
304	def call_number(non_ark_ids)	1✔
305	non_ark_ids.nil? ? 'AC102' : "AC102 #{non_ark_ids.first}"	60✔
306	end
307
308	def first_or_nil(field)	1✔
309	field&.first	22✔
310	end
311
312	def dspace_display_text(dc_elements)	1✔
313	text = [dataspace]	2✔
314	text << if dc_elements.select { \|e\| e.name == 'rights' }.empty?	8✔
315	full_text	1✔
316	else
317	citation	1✔
318	end
319	text	2✔
320	end
321
322	def dspace_display_text_hash(doc)	1✔
323	text = [dataspace]	5✔
324	text << if on_site_only?(doc)	5✔
325	citation	4✔
326	else
327	full_text	1✔
328	end
329	text	5✔
330	end
331
332	def on_site_only?(doc)	1✔
333	doc.key?('pu.location') \|\| doc.key?('dc.rights.accessRights') \|\|	24✔
334	embargo?(doc) \|\| walkin?(doc)
335	end
336
337	def embargo?(doc)	1✔
338	date = doc['pu.embargo.lift'] \|\| doc['pu.embargo.terms']	28✔
339	return false if date.nil?	28✔
340
341	date = Chronic.parse(date.first)	14✔
342	if date.nil?	14✔
343	@logger.info("No valid embargo date for #{doc['id']}")	2✔
344	return false	2✔
345	end
346
347	date > Time.now	12✔
348	end
349
350	def embargo(doc)	1✔
NEW 351	return if doc.key?('pu.embargo.lift')	×
352
UNCOV 353	date = doc['pu.embargo.lift'] \|\| doc['pu.embargo.terms']	×
UNCOV 354	date = Chronic.parse(date.first) unless date.nil?	×
UNCOV 355	date = date.strftime('%B %-d, %Y') unless date.nil?	×
UNCOV 356	date	×
357	end
358
359	def walkin?(doc)	1✔
360	walkin = doc['pu.mudd.walkin']	10✔
361	!walkin.nil? && walkin.first == 'yes'	10✔
362	end
363
364	def restrictions_display_text(doc)	1✔
UNCOV 365	if embargo?(doc)	×
UNCOV 366	date = embargo(doc)	×
UNCOV 367	"This content is embargoed until #{date}. For more information contact the "\	×
368	"<a href=\"mailto:dspadmin@princeton.edu?subject=Regarding embargoed DataSpace Item 88435/#{doc['id']}\"> "\
369	'Mudd Manuscript Library</a>.'
UNCOV 370	elsif doc.key?('pu.location') \|\| doc.key?('dc.rights.accessRights')	×
UNCOV 371	[doc['pu.location'], doc['dc.rights.accessRights']].flatten.compact	×
UNCOV 372	elsif walkin?(doc)	×
UNCOV 373	walkin_text	×
374	end
375	end
376
377	def walkin_text	1✔
UNCOV 378	'Walk-in Access. This thesis can only be viewed on computer terminals at the '\	×
379	'<a href=\"http://mudd.princeton.edu\">Mudd Manuscript Library</a>.'
380	end
381
382	def dataspace	1✔
383	'DataSpace'	11✔
384	end
385
386	def full_text	1✔
387	'Full text'	4✔
388	end
389
390	def citation	1✔
391	'Citation only'	7✔
392	end
393
394	# this is kind of a mess...
395	def map_non_special_to_solr(dc_elements)	1✔
396	h = {}	3✔
397	NON_SPECIAL_ELEMENT_MAPPING.each do \|element_name, fields\|	3✔
398	elements = dc_elements.select { \|e\| e.name == element_name }	80✔
399	fields.each do \|f\|	15✔
400	if h.key?(f)	21✔
401	h[f].push(*elements.map(&:text))	3✔
402	else
403	h[f] = elements.map(&:text)	18✔
404	end
405	end
406	end
407	h	3✔
408	end
409
410	# default English
411	def code_to_language(codes)	1✔
412	languages = []	14✔
413	# en_US is not valid iso code
414	codes&.each do \|c\|	14✔
415	code_lang = ISO_639.find(c[/^[^_]*/]) # en_US is not valid iso code	5✔
416	l = code_lang.nil? ? 'English' : code_lang.english_name	5✔
417	languages << l	5✔
418	end
419	languages.empty? ? 'English' : languages.uniq	14✔
420	end
421
422	def map_rest_non_special_to_solr(doc)	1✔
423	h = {}	12✔
424	REST_NON_SPECIAL_ELEMENT_MAPPING.each do \|field_name, solr_fields\|	12✔
425	next unless doc.key?(field_name)	84✔
426
427	solr_fields.each do \|f\|	21✔
428	val = []	35✔
429	val << h[f]	35✔
430	val << doc[field_name]	35✔
431	h[f] = val.flatten.compact	35✔
432	# Ruby might have a bug here
433	# if h.has_key?(f)
434	# h[f].push(doc[field_name])
435	# else
436	# h[f] = doc[field_name]
437	# end
438	end
439	end
440	h	12✔
441	end
442
443	def class_year_fields(doc)	1✔
444	h = {}	15✔
445	if doc.key?('pu.date.classyear') && doc['pu.date.classyear'].first =~ /^\d+$/	15✔
446	h['class_year_s'] = doc['pu.date.classyear']	6✔
447	h['pub_date_start_sort'] = doc['pu.date.classyear']	6✔
448	h['pub_date_end_sort'] = doc['pu.date.classyear']	6✔
449	end
450	h	15✔
451	end
452
453	# online access when there isn't a restriction/location note
454	def holdings_access(doc)	1✔
455	if embargo?(doc)	16✔
456	{
457	'location' => 'Mudd Manuscript Library',	4✔
458	'location_display' => 'Mudd Manuscript Library',
459	'location_code_s' => 'mudd$stacks',
460	'advanced_location_s' => ['mudd$stacks', 'Mudd Manuscript Library'],
461	'holdings_1display' => physical_holding(doc, accessible: false)
462	}
463	elsif on_site_only?(doc)	12✔
464	{
465	'location' => 'Mudd Manuscript Library',	7✔
466	'location_display' => 'Mudd Manuscript Library',
467	'location_code_s' => 'mudd$stacks',
468	'advanced_location_s' => ['mudd$stacks', 'Mudd Manuscript Library'],
469	'access_facet' => 'In the Library',
470	'holdings_1display' => physical_holding(doc)
471	}
472	else
473	{
474	'access_facet' => 'Online',	5✔
475	'electronic_portfolio_s' => online_holding(doc)
476	}
477	end
478	end
479	end
480	end

pulibrary / orangetheses / 38778a1e-2dd3-4ec3-b4d6-a6c4d301682a

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