Module: Cul::Hydra::Solrizer::ModsFieldable

Extended by:
ActiveSupport::Concern, ClassMethods
Includes:
Solrizer::DefaultDescriptors::Normal
Included in:
Datastreams::ModsDocument
Defined in:
lib/cul_hydra/solrizer/mods_fieldable.rb

Defined Under Namespace

Modules: ClassMethods

Constant Summary collapse

MODS_NS = 
{'mods'=>'http://www.loc.gov/mods/v3', 'cul' => 'http://id.library.columbia.edu/property/'}
ORIGIN_INFO_DATES = 
["dateCreated", "dateIssued", "dateOther"]

Instance Method Summary collapse

Methods included from ClassMethods

map_field, map_value, maps_field?, normalize, role_text_to_solr_field_name, value_mapper

Instance Method Details

#add_names_by_text_role!(solr_doc) ⇒ Object 



427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 427

def add_names_by_text_role!(solr_doc)
  # Note: These roles usually come from http://www.loc.gov/marc/relators/relaterm.html,
  # but there are known cases when non-marc relator values are used (e.g. 'Owner/Agent'),
  # and those roles won't have marcrelator codes.
  # e.g. author_ssim = ['Author 1', 'Author 2'] or project_director_ssim = ['Director 1', 'Director 2']
  roleterm_xpath_segment = "mods:roleTerm[@type='text' and string-length(text()) > 0]"
  names_with_roles_xpath = "./mods:name/mods:role/#{roleterm_xpath_segment}/ancestor::mods:name"
  mods.xpath(names_with_roles_xpath, MODS_NS).collect do |node|
    name_text = node.xpath('./mods:namePart', MODS_NS).collect { |c| c.text }.join(' ')
    name_text = ModsFieldable.normalize(name_text, true)
    solr_role_fields = Set.new
    node.xpath("./mods:role/#{roleterm_xpath_segment}", MODS_NS).collect do |role_node|
      solr_role_fields << ModsFieldable.role_text_to_solr_field_name(role_node.text)
    end

    solr_role_fields.each do |solr_field_name|
      solr_doc[solr_field_name] ||= []
      solr_doc[solr_field_name] << name_text
    end
  end
end

#add_notes_by_type!(solr_doc, node = mods) ⇒ Object 



297
298
299
300
301
302
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 297

def add_notes_by_type!(solr_doc, node=mods)
  notes_by_type(mods).each do |solr_field_name, values|
    solr_doc[solr_field_name] ||= []
    solr_doc[solr_field_name].concat(values)
  end
end

#all_subjects(node = mods) ⇒ Object 



337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 337

def all_subjects(node=mods)
  list_of_subjects = []

  node.xpath("./mods:subject[not(@authority) or @authority != 'Durst']/mods:topic", MODS_NS).collect do |n|
    list_of_subjects << ModsFieldable.normalize(n.text, true)
  end
  node.xpath("./mods:subject/mods:geographic", MODS_NS).collect do |n|
    list_of_subjects << ModsFieldable.normalize(n.text, true)
  end
  node.xpath("./mods:subject/mods:name", MODS_NS).collect do |n|
    list_of_subjects << ModsFieldable.normalize(n.text, true)
  end
  node.xpath("./mods:subject/mods:temporal", MODS_NS).collect do |n|
    list_of_subjects << ModsFieldable.normalize(n.text, true)
  end
  node.xpath("./mods:subject/mods:titleInfo", MODS_NS).collect do |n|
    list_of_subjects << ModsFieldable.normalize(n.text, true)
  end
  node.xpath("./mods:subject/mods:genre", MODS_NS).collect do |n|
    list_of_subjects << ModsFieldable.normalize(n.text, true)
  end

  return list_of_subjects.uniq
end

#alternative_titles(node = mods) ⇒ Object 



118
119
120
121
122
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 118

def alternative_titles(node=mods)
  node.xpath('./mods:titleInfo[@type and (@type="alternative" or @type="abbreviated" or @type="translated" or @type="uniform")]', MODS_NS).collect do |t|
    ModsFieldable.normalize(t.text)
  end
end

#archival_context_json(node = mods) ⇒ Object 



449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 449

def archival_context_json(node=mods)
  node.xpath("./mods:relatedItem[@displayLabel='Collection']", MODS_NS).map do |collection|
    collection_title = collection.xpath("./mods:titleInfo/mods:title", MODS_NS).text
    collection_id = collection.xpath("./mods:titleInfo/@valueURI", MODS_NS).text
    collection_bib_id = collection.xpath("./mods:identifier[@type='CLIO']", MODS_NS).text
    collection_org = collection.xpath("./mods:part/mods:detail/mods:title", MODS_NS).map do |title|
      {
        'ead:level' => title[:level],
        'dc:type' => title[:type],
        'dc:title' => title.text
      }
    end
    unless collection_org.empty?
      collection_org.sort! { |a,b| a['ead:level'] <=> b['ead:level'] }
      collection_org.each_with_index {|node, ix| node['@id'] = "_:n#{ix}"}
      collection_org[0].delete('ead:level')
      while collection_org.length > 1 do
        collection_org[-1].delete('ead:level')
        tail = collection_org.pop
        tail.delete('ead:level')
        collection_org[-1]['dc:hasPart'] = tail
      end
    end
    {
      '@context': {'dc': "http://purl.org/dc/terms/"},
      '@id' => collection_id,
      'dc:title' => collection_title,
      'dc:bibliographicCitation' => {
        '@id' => "https://clio.columbia.edu/catalog/#{collection_bib_id}",
        '@type' => 'dc:BibliographicResource'
      },
      'dc:coverage' => collection_org
    }
  end
end

#archive_org_identifier(node = mods) ⇒ Object 



421
422
423
424
425
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 421

def archive_org_identifier(node=mods)
  node.at_xpath('./mods:identifier[@type="archive.org"]', MODS_NS)&.tap do |t|
    return ModsFieldable.normalize(t.text)
  end
end

#archive_org_identifiers(node = mods) ⇒ Object 



412
413
414
415
416
417
418
419
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 412

def archive_org_identifiers(node=mods)
  node.xpath('./mods:identifier[@type="archive.org"]', MODS_NS).collect do |t|
    {
      displayLabel: t['displayLabel'] || ModsFieldable.normalize(t.text),
      id: ModsFieldable.normalize(t.text)
    }.compact
  end
end

#classification_other(node = mods) ⇒ Object 



378
379
380
381
382
383
384
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 378

def classification_other(node=mods)
  classification_other_values = []
  node.xpath("./mods:classification[@authority='z']", MODS_NS).collect do |n|
    classification_other_values << ModsFieldable.normalize(n.text, true)
  end
  return classification_other_values
end

#clio_ids(node = mods) ⇒ Object 



124
125
126
127
128
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 124

def clio_ids(node=mods)
  node.xpath('./mods:identifier[@type="CLIO"]', MODS_NS).collect do |t|
    ModsFieldable.normalize(t.text)
  end
end

#collections ⇒ Object 



68
69
70
71
72
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 68

def collections
  mods.xpath("./mods:relatedItem[@type='host' and @displayLabel='Collection']", MODS_NS).collect do |p_node|
    ModsFieldable.normalize(main_title(p_node), true)
  end
end

#coordinates(node = mods) ⇒ Object 



400
401
402
403
404
405
406
407
408
409
410
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 400

def coordinates(node=mods)
  coordinate_values = []
  node.xpath("./mods:subject/mods:cartographics/mods:coordinates", MODS_NS).collect do |n|
    nt = ModsFieldable.normalize(n.text, true)
    if nt.match(/-*\d+\.\d+\s*,\s*-*\d+\.\d+\s*/) # Expected coordinate format: 40.123456,-73.5678
      nt = "-#{nt}" if n.text[n.text.index(nt) - 1] == '-'
      coordinate_values << nt
    end
  end
  coordinate_values
end

#copyright_statement(node = mods) ⇒ Object 



485
486
487
488
489
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 485

def copyright_statement(node=mods)
  node.at_xpath('./mods:accessCondition[@type="use and reproduction"]', MODS_NS)&.tap do |t|
    return t['xlink:href']
  end
end

#date_range_to_textual_date(start_year, end_year) ⇒ Object 



266
267
268
269
270
271
272
273
274
275
276
277
278
279
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 266

def date_range_to_textual_date(start_year, end_year)
  start_year = start_year.to_i.to_s # Remove zero-padding if present
  end_year = end_year.to_i.to_s # Remove zero-padding if present

  if start_year == end_year
    return [start_year]
  else
    return [('Between ' +
      (start_year.to_i > 0 ? start_year : start_year[1,start_year.length] + ' BCE') +
      ' and ' +
      (end_year.to_i > 0 ? (start_year.to_i > 0 ? end_year : end_year + ' CE') : end_year[1,end_year.length] + ' BCE')
    )]
  end
end

#dates(node = mods) ⇒ Object 



157
158
159
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 157

def dates(node=mods)
  # get all the dateIssued with keyDate = 'yes', but not point = 'end'
end

#durst_subjects(node = mods) ⇒ Object 



362
363
364
365
366
367
368
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 362

def durst_subjects(node=mods)
  list_of_subjects = []
  node.xpath("./mods:subject[@authority='Durst']/mods:topic", MODS_NS).collect do |n|
    list_of_subjects << ModsFieldable.normalize(n.text, true)
  end
  return list_of_subjects.uniq
end

#formats(node = mods) ⇒ Object 



161
162
163
164
165
166
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 161

def formats(node=mods)
  # get all the form values with authority != 'marcform'
  node.xpath("./mods:physicalDescription/mods:form[@authority != 'marcform']", MODS_NS).collect do |n|
    ModsFieldable.normalize(n.text)
  end
end

#item_in_context_url(node = mods) ⇒ Object 



304
305
306
307
308
309
310
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 304

def item_in_context_url(node=mods)
  item_in_context_url_val = []
  node.xpath("./mods:location/mods:url[@access='object in context']", MODS_NS).collect do |n|
    item_in_context_url_val << ModsFieldable.normalize(n.text, true)
  end
  item_in_context_url_val
end

#key_date_range(node = mods) ⇒ Object 



246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 246

def key_date_range(node=mods)
  dates = []
  encodings = ['w3cdtf','iso8601']
  ORIGIN_INFO_DATES.each do |element|
    encodings.each do |encoding|
      xpath = "./mods:originInfo/mods:#{element}[(@keyDate) and (@encoding = '#{encoding}')]"
      node.xpath(xpath, MODS_NS).collect do |n|
        range = [ModsFieldable.normalize(n.text, true)]
        if n['point'] != 'end'
          n.xpath("../mods:#{element}[(@encoding = '#{encoding}' and @point = 'end')]", MODS_NS).each do |ep|
            range << ModsFieldable.normalize(ep.text, true)
          end
        end
        dates << range
      end
    end
  end
  return dates.first || dates
end

#languages_iso639_2_code ⇒ Object 



80
81
82
83
84
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 80

def languages_iso639_2_code
  mods.xpath("./mods:language/mods:languageTerm[@type='code' and @authority='iso639-2']", MODS_NS).collect do |n|
    ModsFieldable.normalize(n.text, true)
  end
end

#languages_iso639_2_text ⇒ Object 



74
75
76
77
78
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 74

def languages_iso639_2_text
  mods.xpath("./mods:language/mods:languageTerm[@type='text' and @authority='iso639-2']", MODS_NS).collect do |n|
    ModsFieldable.normalize(n.text, true)
  end
end

#main_title(node = mods) ⇒ Object 



100
101
102
103
104
105
106
107
108
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 100

def main_title(node=mods)
  # include only the untyped [!@type] titleInfo
  t = node.xpath('./mods:titleInfo[not(@type)]', MODS_NS).first
  if t
    ModsFieldable.normalize(t.text)
  else
    nil
  end
end

#mods ⇒ Object 



58
59
60
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 58

def mods
  ng_xml.xpath('/mods:mods', MODS_NS).first
end

#names(role_authority = nil, role = nil) ⇒ Object 



130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 130

def names(role_authority=nil, role=nil)
  # get all the name nodes
  # keep all child text except the role terms
  xpath = "./mods:name"
  unless role_authority.nil?
    xpath << "/mods:role/mods:roleTerm[@authority='#{role_authority.to_s}'"
    unless role.nil?
      xpath << " and normalize-space(text()) = '#{role.to_s.strip}'"
    end
    xpath << "]/ancestor::mods:name"
  end
  names = mods.xpath(xpath, MODS_NS).collect do |node|
    base_text = node.xpath('./mods:namePart', MODS_NS).collect { |c| c.text }.join(' ')
    ModsFieldable.normalize(base_text, true)
  end

  # Note: Removing subject names from name field extraction.
  # See: https://issues.cul.columbia.edu/browse/DCV-231 and https://issues.cul.columbia.edu/browse/SCV-102
  #xpath = "./mods:subject" + xpath[1,xpath.length]
  #mods.xpath(xpath, MODS_NS).each do |node|
  #  base_text = node.xpath('./mods:namePart', MODS_NS).collect { |c| c.text }.join(' ')
  #  names << ModsFieldable.normalize(base_text, true)
  #end

  names
end

#non_item_in_context_url(node = mods) ⇒ Object 



312
313
314
315
316
317
318
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 312

def non_item_in_context_url(node=mods)
  non_item_in_context_url_val = []
  node.xpath("./mods:location/mods:url[not(@access='object in context')]", MODS_NS).collect do |n|
    non_item_in_context_url_val << ModsFieldable.normalize(n.text, true)
  end
  non_item_in_context_url_val
end

#notes_by_type(node = mods) ⇒ Object 



281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 281

def notes_by_type(node=mods)
  results = {}
  normal_date_types = ['date','date_source']
  node.xpath("./mods:note", MODS_NS).collect do |n|
    type = n.attr('type')
    type = 'untyped' if type.blank?
    normal_type = type.downcase
    normal_type.gsub!(/\s/,'_')
    normal_type = 'date' if normal_date_types.include?(normal_type)
    field_name = "lib_#{normal_type}_notes_ssm"
    results[field_name] ||= []
    results[field_name] << ModsFieldable.normalize(n.text, true)
  end
  results
end

#origin_info_place(node = mods) ⇒ Object 



370
371
372
373
374
375
376
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 370

def origin_info_place(node=mods)
  places = []
  node.xpath("./mods:originInfo/mods:place/mods:placeTerm", MODS_NS).collect do |n|
    places << ModsFieldable.normalize(n.text, true)
  end
  return places
end

#origin_info_place_for_display(node = mods) ⇒ Object 



386
387
388
389
390
391
392
393
394
395
396
397
398
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 386

def origin_info_place_for_display(node=mods)
  # If there are multiple origin_info place elements, choose only the ones without valueURI attributes.  Otherwise show the others.
  places_with_uri = []
  places_without_uri = []
  node.xpath("./mods:originInfo/mods:place/mods:placeTerm[@valueURI]", MODS_NS).collect do |n|
    places_with_uri << ModsFieldable.normalize(n.text, true)
  end
  node.xpath("./mods:originInfo/mods:place/mods:placeTerm[not(@valueURI)]", MODS_NS).collect do |n|
    places_without_uri << ModsFieldable.normalize(n.text, true)
  end

  return (places_without_uri.length > 0 ? places_without_uri : places_with_uri)
end

#project_url(node = mods) ⇒ Object 



320
321
322
323
324
325
326
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 320

def project_url(node=mods)
  project_url_val = []
  node.xpath("./mods:relatedItem[@type='host' and @displayLabel='Project']/mods:location/mods:url", MODS_NS).collect do |n|
    project_url_val << ModsFieldable.normalize(n.text, true)
  end
  project_url_val
end

#projects ⇒ Object 



62
63
64
65
66
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 62

def projects
  mods.xpath("./mods:relatedItem[@type='host' and @displayLabel='Project']", MODS_NS).collect do |p_node|
    ModsFieldable.normalize(main_title(p_node), true)
  end
end

#reading_room_locations(node = mods) ⇒ Object 



491
492
493
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 491

def reading_room_locations(node=mods)
  node.xpath("./mods:extension/cul:readingRoom", MODS_NS).map { |room_node| room_node.attr('valueUri') }
end

#repository_code(node = mods) ⇒ Object 



168
169
170
171
172
173
174
175
176
177
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 168

def repository_code(node=mods)
  # get the location/physicalLocation[@authority = 'marcorg']
  repo_code_node = node.xpath("./mods:location/mods:physicalLocation[@authority = 'marcorg']", MODS_NS).first

  if repo_code_node
    ModsFieldable.normalize(repo_code_node.text)
  else
    return nil
  end
end

#repository_text(node = mods) ⇒ Object 



179
180
181
182
183
184
185
186
187
188
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 179

def repository_text(node=mods)
  # get the location/physicalLocation[not(@authority)]
  repo_text_node = node.xpath("./mods:location/mods:physicalLocation[not(@authority)]", MODS_NS).first

  if repo_text_node
    ModsFieldable.normalize(repo_text_node.text)
  else
    return nil
  end
end

#search_scope(node = mods) ⇒ Object 



495
496
497
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 495

def search_scope(node=mods)
  node.xpath("./mods:extension/cul:searchScope", MODS_NS).map { |scope_node| scope_node.attr('value') }
end

#shelf_locators(node = mods) ⇒ Object 



216
217
218
219
220
221
222
223
224
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 216

def shelf_locators(node=mods)
  values = node.xpath("./mods:location/mods:shelfLocator", MODS_NS).collect do |n|
    ModsFieldable.normalize(n.text, true)
  end
  values += node.xpath("./mods:location/mods:holdingSimple/mods:copyInformation/mods:shelfLocator", MODS_NS).collect do |n|
    ModsFieldable.normalize(n.text, true)
  end
  values
end

#sort_title(node = mods) ⇒ Object 



86
87
88
89
90
91
92
93
94
95
96
97
98
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 86

def sort_title(node=mods)
  # include only the untyped [!@type] titleInfo, exclude noSort
  base_text = ''
  t = node.xpath('./mods:titleInfo[not(@type)]', MODS_NS).first
  if t
    t.children.each do |child|
      base_text << child.text unless child.name == 'nonSort'
    end
  end
  base_text = ModsFieldable.normalize(base_text, true)
  base_text = nil if base_text.empty?
  base_text
end

#sublocation(node = mods) ⇒ Object 



226
227
228
229
230
231
232
233
234
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 226

def sublocation(node=mods)
  values = node.xpath("./mods:location/mods:sublocation", MODS_NS).collect do |n|
    ModsFieldable.normalize(n.text, true)
  end
  values += node.xpath("./mods:location/mods:holdingSimple/mods:copyInformation/mods:sublocation", MODS_NS).collect do |n|
    ModsFieldable.normalize(n.text, true)
  end
  values
end

#textual_dates(node = mods) ⇒ Object 



236
237
238
239
240
241
242
243
244
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 236

def textual_dates(node=mods)
  dates = []
  ORIGIN_INFO_DATES.each do |element|
    node.xpath("./mods:originInfo/mods:#{element}[not(@keyDate) and not(@point) and not(@encoding)]", MODS_NS).collect do |n|
      dates << n.text.strip
    end
  end
  return dates
end

#titles(node = mods) ⇒ Object 



110
111
112
113
114
115
116
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 110

def titles(node=mods)
  # all titles without descending into relatedItems
  # For now, this only includes the main title and selected alternate_titles
  all_titles = []
  all_titles << main_title unless main_title.nil?
  all_titles += alternative_titles unless alternative_titles.nil?
end

#to_solr(solr_doc = {}) ⇒ Object 



499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 499

def to_solr(solr_doc={})
  solr_doc = (defined? super) ? super : solr_doc

  return solr_doc if mods.nil?  # There is no mods.  Return because there is nothing to process, otherwise NoMethodError will be raised by subsequent lines.

  solr_doc["all_text_teim"] ||= []

  solr_doc["title_si"] = sort_title
  solr_doc["title_ssm"] = titles
  solr_doc["alternative_title_ssm"] = alternative_titles
  solr_doc["all_text_teim"] += solr_doc["alternative_title_ssm"]
  solr_doc["clio_ssim"] = clio_ids
  solr_doc["archive_org_identifier_ssi"] = archive_org_identifier
  solr_doc["archive_org_identifiers_json_ss"] = JSON.generate(archive_org_identifiers)
  solr_doc["lib_collection_sim"] = collections
  solr_doc["lib_name_sim"] = names
  solr_doc["lib_name_teim"] = solr_doc["lib_name_sim"]
  solr_doc["all_text_teim"] += solr_doc["lib_name_teim"]
  solr_doc["lib_all_subjects_ssm"] = all_subjects
  solr_doc["durst_subjects_ssim"] = durst_subjects
  solr_doc["lib_all_subjects_teim"] = solr_doc["lib_all_subjects_ssm"]
  solr_doc["all_text_teim"] += solr_doc["lib_all_subjects_teim"]
  solr_doc["lib_name_ssm"] = solr_doc["lib_name_sim"]
  solr_doc["lib_author_sim"] = names(:marcrelator, 'aut')
  solr_doc["lib_recipient_sim"] = names(:marcrelator, 'rcp')
  solr_doc["lib_format_sim"] = formats
  solr_doc["lib_genre_ssim"] = solr_doc["lib_format_sim"].dup if solr_doc["lib_genre_ssim"].blank?
  solr_doc["lib_shelf_sim"] = shelf_locators
  solr_doc['location_shelf_locator_ssm'] = solr_doc["lib_shelf_sim"]
  solr_doc["all_text_teim"] += solr_doc["lib_shelf_sim"]
  solr_doc['lib_sublocation_sim'] = sublocation
  solr_doc['lib_sublocation_ssm'] = solr_doc['lib_sublocation_sim']
  solr_doc["all_text_teim"] += solr_doc['lib_sublocation_sim']
  solr_doc["lib_date_textual_ssm"] = textual_dates
  solr_doc["lib_item_in_context_url_ssm"] = item_in_context_url
  solr_doc["lib_non_item_in_context_url_ssm"] = non_item_in_context_url
  solr_doc["location_url_json_ss"] = JSON.generate(url_locations)
  solr_doc["lib_project_url_ssm"] = project_url
  solr_doc["origin_info_place_ssm"] = origin_info_place
  solr_doc["origin_info_place_for_display_ssm"] = origin_info_place_for_display
  solr_doc["classification_other_ssim"] = classification_other

  repo_marc_code = repository_code
  unless repo_marc_code.nil?
    solr_doc["lib_repo_code_ssim"] = [repo_marc_code]
    solr_doc["lib_repo_short_ssim"] = [translate_repo_marc_code(repo_marc_code, 'short')]
    solr_doc["lib_repo_long_sim"] = [translate_repo_marc_code(repo_marc_code, 'long')]
    solr_doc["lib_repo_full_ssim"] = [translate_repo_marc_code(repo_marc_code, 'full')]
  end
  solr_doc["lib_repo_text_ssm"] = repository_text

  project_titles = projects
  unless project_titles.nil?
    solr_doc["lib_project_short_ssim"] = []
    solr_doc["lib_project_full_ssim"] = []
    project_titles.each {|project_title|
      solr_doc["lib_project_short_ssim"] << translate_project_title(project_title, 'short')
      solr_doc["lib_project_full_ssim"] << translate_project_title(project_title, 'full')
    }
    solr_doc["lib_project_short_ssim"].uniq!
    solr_doc["lib_project_full_ssim"].uniq!
  end

  # Create convenient start and end date values based on one of the many possible originInfo/dateX elements.
  start_date, end_date = key_date_range
  start_year = nil
  end_year = nil

  if start_date.present?

    start_year = nil
    end_year = nil

    start_date = nil if start_date == 'uuuu'
    end_date = nil if end_date == 'uuuu'
    start_date = start_date.gsub('u', '0') unless start_date.nil?
    end_date = end_date.gsub('u', '0') unless end_date.nil?

    end_date = start_date if end_date.blank?
    start_date = end_date if start_date.blank?

    year_regex = /^(-?\d{1,4}).*/

    unless start_date.blank?
      start_year_match = start_date.match(year_regex)
      if start_year_match && start_year_match.captures.length > 0
        start_year = start_year_match.captures[0]
        start_year = zero_pad_year(start_year)
        solr_doc["lib_start_date_year_itsi"] = start_year.to_i # TrieInt version for searches
      end
    end

    unless end_date.blank?
      end_year_match = end_date.match(year_regex)
      if end_year_match && end_year_match.captures.length > 0
        end_year = end_year_match.captures[0]
        end_year = zero_pad_year(end_year)
        solr_doc["lib_end_date_year_itsi"] = end_year.to_i # TrieInt version for searches
      end
    end

    solr_doc["lib_date_year_range_si"] = start_year + '-' + end_year if start_year && end_year
    solr_doc["lib_date_year_range_ss"] = solr_doc["lib_date_year_range_si"]

    # When no textual date is available, fall back to other date data (if available)
    if solr_doc["lib_date_textual_ssm"].blank?
      solr_doc["lib_date_textual_ssm"] = date_range_to_textual_date(start_year.to_i, end_year.to_i)
    end
  end

  # Geo data
  solr_doc["geo"] = coordinates
  solr_doc["has_geo_bsi"] = true if solr_doc["geo"].present?

  ## Handle alternate form of language authority for language_language_term_text_ssim
  ## We already capture elements when authority="iso639-2b", but we want to additionally
  ## capture language elements when authority="iso639-2".
  solr_doc['language_language_term_text_ssim'] ||= []
  solr_doc['language_language_term_text_ssim'] += languages_iso639_2_text
  solr_doc['language_language_term_code_ssim'] ||= []
  solr_doc['language_language_term_code_ssim'] +=languages_iso639_2_code

  archival_context = archival_context_json
  solr_doc['archival_context_json_ss'] = JSON.generate(archival_context) if archival_context.present?


  # Add names to role-derived keys
  add_names_by_text_role!(solr_doc)

  # Add names to type-derived keys
  add_notes_by_type!(solr_doc)

  solr_doc['copyright_statement_ssi'] = copyright_statement

  # Publish Target/Site fields for location indexes
  solr_doc['search_scope_ssi'] = search_scope.first
  solr_doc['reading_room_ssim'] = reading_room_locations

  solr_doc.each do |k, v|
    if self.class.maps_field? k
      solr_doc[k] = self.class.map_value(k, v)
    end
  end

  solr_doc
end

#translate_project_title(project_title, type) ⇒ Object 



204
205
206
207
208
209
210
211
212
213
214
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 204

def translate_project_title(project_title, type)
  normalized_project_title = ModsFieldable.normalize(project_title)

  if type == 'short'
    return translate_with_default(SHORT_PROJ, normalized_project_title, normalized_project_title)
  elsif type == 'full'
    return translate_with_default(FULL_PROJ, normalized_project_title, normalized_project_title)
  end

  return nil
end

#translate_repo_marc_code(code, type) ⇒ Object 



190
191
192
193
194
195
196
197
198
199
200
201
202
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 190

def translate_repo_marc_code(code, type)
  #code = ModsFieldable.normalize(code)

  if type == 'short'
    return translate_with_default(SHORT_REPO, code, 'Non-Columbia Location')
  elsif type == 'long'
    return translate_with_default(LONG_REPO, code, 'Non-Columbia Location')
  elsif type == 'full'
    return translate_with_default(FULL_REPO, code, 'Non-Columbia Location')
  end

  return nil
end

#url_locations(node = mods) ⇒ Array<Hash>

Create a list of attribute hashes for top-level URL locations

Parameters:

  • node (Nokogiri::XML::Node) (defaults to: mods) —

    search context

Returns:

  • (Array<Hash>) —

    array of url locations as attribute hashes



331
332
333
334
335
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 331

def url_locations(node=mods)
  node.xpath("./mods:location/mods:url", MODS_NS).map do |n|
    {access: n['access'], usage: n['usage'], displayLabel: n['displayLabel'], url: n.text.strip }.compact
  end
end

#zero_pad_year(year) ⇒ Object 



646
647
648
649
650
651
652
653
654
655
 
# File 'lib/cul_hydra/solrizer/mods_fieldable.rb', line 646

def zero_pad_year(year)
  year = year.to_s
  is_negative = year.start_with?('-')
  year_without_sign = (is_negative ? year[1, year.length]: year)
  if year_without_sign.length < 4
    year_without_sign = year_without_sign.rjust(4, '0')
  end

  return (is_negative ? '-' : '') + year_without_sign
end