Class: EAD3Serializer

Inherits:
EADSerializer show all
Defined in:
backend/app/exporters/serializers/ead3.rb

Class Method Summary collapse

Instance Method Summary collapse

Methods inherited from EADSerializer

#add_xlink_prefix, #escape_content, #handle_linebreaks, #is_digital_object_published?, #serialize_eadheader

Methods inherited from ASpaceExport::Serializer

inherited, serializer_for, serializer_for?, with_namespace

Class Method Details

.add_serialize_step(serialize_step) ⇒ Object

Allow plugins to hook in to record processing by providing their own serialization step (a class with a ‘call’ method accepting the arguments defined in run_serialize_step.



131
132
133
134
 
# File 'backend/app/exporters/serializers/ead3.rb', line 131

def self.add_serialize_step(serialize_step)
  @extra_serialize_steps ||= []
  @extra_serialize_steps << serialize_step
end

.run_serialize_step(data, xml, fragments, context) ⇒ Object 



137
138
139
140
141
 
# File 'backend/app/exporters/serializers/ead3.rb', line 137

def self.run_serialize_step(data, xml, fragments, context)
  Array(@extra_serialize_steps).each do |step|
    step.new.call(data, xml, fragments, context)
  end
end

Instance Method Details

#access_elements ⇒ Object 



68
69
70
71
 
# File 'backend/app/exporters/serializers/ead3.rb', line 68

def access_elements
  ['corpname', 'famname', 'function', 'genreform', 'geogname', 'name',
    'occupation', 'persname', 'subject', 'title']
end

#attribute_replacements(element_name = nil) ⇒ Object

Use to specify new names for EAD 2002 attributes nil value indicates attribute should be removed



94
95
96
97
98
99
100
101
102
103
104
105
106
107
 
# File 'backend/app/exporters/serializers/ead3.rb', line 94

def attribute_replacements(element_name=nil)
  replacements = {
    'list' => {
      'type' => 'listtype'
    },
    'ref' => {
      'title' => 'linktitle'
    },
    'language' => {
      'scriptcode' => 'script'
    }
  }
  element_name ? replacements[element_name] : replacements
end

#closed_list_attributes ⇒ Object 



52
53
54
55
56
57
 
# File 'backend/app/exporters/serializers/ead3.rb', line 52

def closed_list_attributes
  ['actuate', 'align', 'approximate', 'audience', 'colsep', 'countryencoding',
    'coverage', 'daotype', 'dateencoding', 'dsctype', 'frame', 'langencoding', 'level', 'listtype', 'mark',
    'numeration', 'parallel', 'pgwide', 'physdescstructuredtype', 'relationtype', 'render',
    'repositoryencoding', 'rowsep', 'scriptencoding', 'show', 'unitdatetype', 'valign', 'value']
end

#convert_ead2002_markup(content) ⇒ Object 



314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
 
# File 'backend/app/exporters/serializers/ead3.rb', line 314

def convert_ead2002_markup(content)
  apply_changes = lambda do |fn, fragment|
    fragment.element_children.each do |e|
      fn.(e)
      if !e.element_children.empty?
        e.element_children.each { |ec| fn.(ec) }
      end
    end
    fragment
  end

  strip_attribute_namespace_prefixes = lambda do |e|
    e.attributes.each do |k, a|
      a.name = a.name.gsub(/^[A-Za-z0-9]*\:/, '')
    end
  end

  convert_extref = lambda do |e|
    if e.name == 'extref'
      e.name = 'ref'
      e.remove_attribute('type') if e['type']
    end
  end

  convert_attribute_names = lambda do |e|
    e.attributes.each do |k, a|
      if replace = attribute_replacements(e.name)
        if new_name = replace[a.name]
          a.name = new_name
        end
      end
      if a.name == 'authfilenumber'
        a.name = 'identifier'
      end
    end
  end

  # must run after convert_attribute_names
  convert_list_attribute_values = lambda do |e|
    if e.name == 'list'
      if e['listtype']
        case e['listtype']
        when 'simple'
          e.remove_attribute('listtype')
        when 'marked'
          e['listtype'] = 'unordered'
        when 'deflist', 'ordered'
          # leave
        else
          e.remove_attribute('listtype')
        end
      end
      if e['numeration']
        e['numeration'] = list_numeration_value(e['numeration'])
      end
    end
  end

  convert_type_to_localtype = lambda do |e|
    if localtype_applicable_elements.include? e.name
      if a = e.attribute('type')
        a.name = 'localtype'
      end
    end
  end

  wrap_access_terms_in_part = lambda do |e|
    if access_elements.include? e.name
      e.children.each do |c|
        if c.text?
          part_wrapped_text = "<part>#{ c.inner_text }</part>"
          c.replace(part_wrapped_text)
        end
      end
    end
  end

  downcase_closed_list_attribute_values = lambda do |e|
    e.attributes.each do |k, a|
      if closed_list_attributes.include? a.name
        e[a.name] = a.value.downcase
      end
    end
  end

  strip_invalid_children_of_mixed_elements = lambda do |e|
    children = e.element_children
    if !children.empty?
      if (valid_children = valid_children_of_mixed_elements(e.name))
        children.each do |el|
          if !valid_children.include?(el.name) && el.inner_text
            el.replace( el.inner_text.gsub(/\s+/, ' ') )
          end
        end
      end
    end
  end

  strip_text_content = lambda do |e|
    if e.element_children.empty? && e.inner_text
      e.content = e.inner_text.strip
    end
  end

  temp_doc = Nokogiri::XML::Document.new
  temp_doc.encoding = "UTF-8"
  fragment = Nokogiri::XML::DocumentFragment.new(temp_doc, content)

  process_fragment = lambda do |f|
    apply_changes.(strip_attribute_namespace_prefixes, f)
    apply_changes.(convert_extref, f)
    apply_changes.(convert_attribute_names, f)
    apply_changes.(convert_list_attribute_values, f)
    apply_changes.(convert_type_to_localtype, f)
    apply_changes.(wrap_access_terms_in_part, f)
    apply_changes.(downcase_closed_list_attribute_values, f)
    apply_changes.(strip_invalid_children_of_mixed_elements, f)
    apply_changes.(strip_text_content, f)

    f.element_children.each do |e|
      process_fragment.(e)
    end
  end

  process_fragment.(fragment)

  fragment.inner_html
end

#escape_ampersands(content) ⇒ Object 



165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
 
# File 'backend/app/exporters/serializers/ead3.rb', line 165

def escape_ampersands(content)
  # first, find any pre-escaped entities and "mark" them by replacing & with @@
  # so something like &lt; becomes @@lt;
  # and &#1234 becomes @@#1234

  content.gsub!(/&\w+;/) {|t| t.gsub('&', '@@')}
  content.gsub!(/&#\d{4}/) {|t| t.gsub('&', '@@')}
  content.gsub!(/&#\d{3}/) {|t| t.gsub('&', '@@')}

  # now we know that all & characters remaining are not part of some pre-escaped entity, and we can escape them safely
  content.gsub!('&', '&amp;')

  # 'unmark' our pre-escaped entities
  content.gsub!(/@@\w+;/) {|t| t.gsub('@@', '&')}
  content.gsub!(/@@#\d{4}/) {|t| t.gsub('@@', '&')}
  content.gsub!(/@@#\d{3}/) {|t| t.gsub('@@', '&')}

  # only allow predefined XML entities, otherwise convert ampersand so XML will validate
  valid_entities = ['&quot;', '&amp;', '&apos;', '&lt;', '&gt;']
  content.gsub!(/&\w+;/) { |t| valid_entities.include?(t) ? t : t.gsub(/&/, '&amp;') }

  return content
end

#extract_head_text(content, backup = "") ⇒ Object

this extracts <head> content and returns it. optionally, you can provide a backup text node that will be returned if there is no <head> nodes in the content



1146
1147
1148
1149
1150
1151
1152
1153
1154
 
# File 'backend/app/exporters/serializers/ead3.rb', line 1146

def extract_head_text(content, backup = "")
  content ||= ""
  match = content.strip.match(/<head( [^<>]+)?>(.+?)<\/head>/)
  if match.nil? # content has no head so we return it as it
    return [content, backup ]
  else
    [ content.gsub(match.to_a.first, ''), match.to_a.last]
  end
end

#fragment_has_unwrapped_text?(fragment_or_element) ⇒ Boolean

Returns:

  • (Boolean) 


110
111
112
113
114
115
116
117
118
 
# File 'backend/app/exporters/serializers/ead3.rb', line 110

def fragment_has_unwrapped_text?(fragment_or_element)
  text = ''
  fragment_or_element.children.each do |e|
    if e.text?
      text << e.inner_text
    end
  end
  text.strip.length > 0
end

#handle_arks(data, xml) ⇒ Object 



1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
 
# File 'backend/app/exporters/serializers/ead3.rb', line 1243

def handle_arks(data, xml)
  return unless AppConfig[:arks_enabled]
  return unless data.ark_name

  if current_ark = data.ark_name.fetch('current', nil)
    xml.unitid ({
                  "localtype" => "ark",
                }) {
      xml.ref ({"href" => current_ark,
                "actuate" => "onload",
                "show" => "new",
               }) { xml.text 'Archival Resource Key' }
    }
  end

  data.ark_name.fetch('previous', []).each do |old_ark_url|
    xml.unitid ({
      "localtype" => "ark-superseded",
    }) {
      xml.ref ({"href" => old_ark_url,
                "actuate" => "onload",
                "show" => "new",
      }) { xml.text 'Previous Archival Resource Key' }
    }
  end
end

#has_unwrapped_text?(content) ⇒ Boolean

Returns:

  • (Boolean) 


121
122
123
124
 
# File 'backend/app/exporters/serializers/ead3.rb', line 121

def has_unwrapped_text?(content)
  fragment = Nokogiri::XML::DocumentFragment.parse(content)
  fragment_has_unwrapped_text?(fragment)
end

#list_numeration_value(value) ⇒ Object 



74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
 
# File 'backend/app/exporters/serializers/ead3.rb', line 74

def list_numeration_value(value)
  case value
  when 'arabic'
    'decimal'
  when 'loweralpha'
    'lower-alpha'
  when 'upperalpha'
    'upper-alpha'
  when 'lowerroman'
    'lower-roman'
  when 'upperroman'
    'upper-roman'
  else
    value
  end
end

#localtype_applicable_elements ⇒ Object 



60
61
62
63
64
65
 
# File 'backend/app/exporters/serializers/ead3.rb', line 60

def localtype_applicable_elements
  ['abstract', 'materialspec', 'accessrestrict', 'altformavail', 'archdesc', 'container',
    'originalsloc', 'phystech', 'processinfo', 'relatedmaterial', 'separatedmaterial', 'titleproper', 'title',
    'unitid', 'unittitle', 'userestrict', 'odd', 'note', 'date', 'name', 'persname', 'famname', 'corpname',
    'subject', 'occupation', 'genreform', 'function', 'num', 'physloc', 'extent', 'descgrp']
end

#prefix_id(id) ⇒ Object 



144
145
146
147
148
149
150
151
152
 
# File 'backend/app/exporters/serializers/ead3.rb', line 144

def prefix_id(id)
  if id.nil? or id.empty? or id == 'null'
    ""
  elsif id =~ /^#{@id_prefix}/
    id
  else
    "#{@id_prefix}#{id}"
  end
end

#remove_smart_quotes(content) ⇒ Object 



272
273
274
 
# File 'backend/app/exporters/serializers/ead3.rb', line 272

def remove_smart_quotes(content)
  content = content.gsub(/\xE2\x80\x9C/, '"').gsub(/\xE2\x80\x9D/, '"').gsub(/\xE2\x80\x98/, "\'").gsub(/\xE2\x80\x99/, "\'")
end

#sanitize_mixed_content(content, context, fragments, allow_p = false) ⇒ Object 



277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
 
# File 'backend/app/exporters/serializers/ead3.rb', line 277

def sanitize_mixed_content(content, context, fragments, allow_p = false )
  # remove smart quotes from text
  content = remove_smart_quotes(content)

  # br's should be self closing
  content = content.gsub("<br>", "<br/>").gsub("</br>", '')

  ## moved this to structure_children and strop_p for easier testablity
  ## leaving this reference here in case you thought it should go here
  # content = escape_ampersands(content)

  if allow_p
    content = structure_children(content, context.parent.name)
  else
    content = strip_p(content)
  end

  # convert & to @@ before generating XML fragments for processing
  content.gsub!(/&/, '@@')

  content = convert_ead2002_markup(content)

  # convert @@ back to & on return value
  content.gsub!(/@@/, '&')

  begin
    if ASpaceExport::Utils.has_html?(content)
      context.text( fragments << content )
    else
      context.text content.gsub("&amp;", "&") #thanks, Nokogiri
    end
  rescue
    context.cdata content
  end
end

#serialize_aspace_uri(data, xml) ⇒ Object 



1239
1240
1241
 
# File 'backend/app/exporters/serializers/ead3.rb', line 1239

def serialize_aspace_uri(data, xml)
  xml.unitid ({ 'localtype' => 'aspace_uri' }) { xml.text data.uri }
end

#serialize_bibliographies(data, xml, fragments) ⇒ Object 



1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
 
# File 'backend/app/exporters/serializers/ead3.rb', line 1489

def serialize_bibliographies(data, xml, fragments)
  data.bibliographies.each do |note|
    next if note["publish"] === false && !@include_unpublished
    content = ASpaceExport::Utils.extract_note_text(note, @include_unpublished)
    note_type = note["type"] ? note["type"] : "bibliography"
    head_text = note['label'] ? note['label'] : I18n.t("enumerations._note_types.#{note_type}", :default => note_type )

    atts = {
      audience: note["publish"] === false ? 'internal' : nil,
      id: prefix_id(note['persistent_id'].gsub(/\s/, '_'))
    }
    atts.delete_if { |k, v| v.nil? || v.empty? || v == "null" }

    xml.bibliography(atts) {
      xml.head { sanitize_mixed_content(head_text, xml, fragments) }
      sanitize_mixed_content( content, xml, fragments, true)
      note['items'].each do |item|
        xml.bibref { sanitize_mixed_content( item, xml, fragments) } unless item.empty?
      end
    }
  end
end

#serialize_child(data, xml, fragments, c_depth = 1) ⇒ Object 



1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
 
# File 'backend/app/exporters/serializers/ead3.rb', line 1157

def serialize_child(data, xml, fragments, c_depth = 1)
  begin
    return if data["publish"] === false && !@include_unpublished
    return if data["suppressed"] === true

    tag_name = @use_numbered_c_tags ? :"c#{c_depth.to_s.rjust(2, '0')}" : :c

    atts = {:level => data.level, :otherlevel => data.other_level, :id => prefix_id(data.ref_id)}

    if data.publish === false
      atts[:audience] = 'internal'
    end

    atts.reject! {|k, v| v.nil?}
    xml.send(tag_name, atts) {

      xml.did {
        if (val = data.title)
          xml.unittitle { sanitize_mixed_content( val, xml, fragments) }
        end

        handle_arks(data, xml)

        if @include_uris
          serialize_aspace_uri(data, xml)
        end

        if !data.component_id.nil? && !data.component_id.empty?
          xml.unitid data.component_id
        end

        if @include_unpublished
          data.external_ids.each do |exid|
            xml.unitid ({ "audience" => "internal", "type" => exid['source'], "identifier" => exid['external_id']}) { xml.text exid['external_id']}
          end
        end

        serialize_origination(data, xml, fragments)
        serialize_extents(data, xml, fragments)
        serialize_dates(data, xml, fragments)
        serialize_did_notes(data, xml, fragments)

        unless (languages = data.lang_materials).empty?
          serialize_languages(languages, xml, fragments)
        end

        EAD3Serializer.run_serialize_step(data, xml, fragments, :did)

        data.instances_with_sub_containers.each do |instance|
          serialize_container(instance, xml, @fragments)
        end

        if @include_daos
          data.instances_with_digital_objects.each do |instance|
            digital_object = instance['digital_object']['_resolved']
            serialize_digital_object(digital_object, xml, fragments)
          end
        end
      }

      serialize_nondid_notes(data, xml, fragments)
      serialize_bibliographies(data, xml, fragments)
      serialize_indexes(data, xml, fragments)
      serialize_controlaccess(data, xml, fragments)
      EAD3Serializer.run_serialize_step(data, xml, fragments, :archdesc)

      data.children_indexes.each do |i|
        xml.text(
                 @stream_handler.buffer {|xml, new_fragments|
                   serialize_child(data.get_child(i), xml, new_fragments, c_depth + 1)
                 }
                 )
      end
    }
  rescue => e
    xml.text "ASPACE EXPORT ERROR : YOU HAVE A PROBLEM WITH YOUR EXPORT OF ARCHIVAL OBJECTS. THE FOLLOWING INFORMATION MAY HELP:\n

              MESSAGE: #{e.message.inspect}  \n
              TRACE: #{e.backtrace.inspect} \n "
  end
end

#serialize_container(inst, xml, fragments) ⇒ Object 



1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
 
# File 'backend/app/exporters/serializers/ead3.rb', line 1375

def serialize_container(inst, xml, fragments)
  atts = {}

  sub = inst['sub_container']
  top = sub['top_container']['_resolved']

  # top container
  atts[:id] = prefix_id(SecureRandom.hex)
  last_id = atts[:id]
  atts[:localtype] = top['type'] unless (top['type'].nil? || top['type'].empty?)
  text = top['indicator']
  atts[:label] = I18n.t("enumerations.instance_instance_type.#{inst['instance_type']}",
                        :default => inst['instance_type'])
  if top['barcode']
    atts[:containerid] = "#{top['barcode']}"
  end

  if (cp = top['container_profile'])
    atts[:altrender] = cp['_resolved']['url'] || cp['_resolved']['name']
  end

  xml.container(atts) {
    sanitize_mixed_content(text, xml, fragments)
  }

  # sub container
  (2..3).each do |n|
    atts = {}

    next unless sub["type_#{n}"]

    atts[:id] = prefix_id(SecureRandom.hex)
    atts[:parent] = last_id
    last_id = atts[:id]

    atts[:localtype] = sub["type_#{n}"]
    text = sub["indicator_#{n}"]

    xml.container(atts) {
      sanitize_mixed_content(text, xml, fragments)
    }
  end
end

#serialize_control(data, xml, fragments) ⇒ Object 



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
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
 
# File 'backend/app/exporters/serializers/ead3.rb', line 580

def serialize_control(data, xml, fragments)
  control_atts = {
    repositoryencoding: "iso15511",
    countryencoding: "iso3166-1",
    dateencoding: "iso8601",
    relatedencoding: "marc",
    langencoding: "iso639-2b",
    scriptencoding: "iso15924"
  }.reject {|k, v| v.nil? || v.empty? || v == "null"}

  xml.control(control_atts) {
    ins_url = data.ead_location

    if AppConfig[:arks_enabled] && data.ark_name && (current_ark = data.ark_name.fetch('current', nil))
      ins_url = current_ark
    end

    recordid_atts = {
      instanceurl: ins_url
    }

    xml.recordid(recordid_atts) {
      xml.text(data.ead_id)
    }

    xml.filedesc {

      xml.titlestmt {
        # titleproper
        titleproper = ""
        titleproper += "#{data.finding_aid_title} " if data.finding_aid_title
        titleproper += "#{data.title}" if ( data.title && titleproper.empty? )
        xml.titleproper { strip_tags_and_sanitize(titleproper, xml, fragments) }

        # titleproper (filing)
        unless data.finding_aid_filing_title.nil?
          xml.titleproper("localtype" => "filing") {
            sanitize_mixed_content(data.finding_aid_filing_title, xml, fragments)
          }
        end

        # subtitle
        unless data.finding_aid_subtitle.nil?
          xml.subtitle {
            sanitize_mixed_content(data.finding_aid_subtitle, xml, fragments)
          }
        end

        # author
        unless data.finding_aid_author.nil?
          xml.author {
            sanitize_mixed_content(data.finding_aid_author, xml, fragments)
          }
        end

        # sponsor
        unless data.finding_aid_sponsor.nil?
          xml.sponsor {
            sanitize_mixed_content( data.finding_aid_sponsor, xml, fragments)
          }
        end
      }

      unless data.finding_aid_edition_statement.nil?
        xml.editionstmt {
          sanitize_mixed_content(data.finding_aid_edition_statement, xml, fragments, true )
        }
      end

      xml.publicationstmt {

        xml.publisher { sanitize_mixed_content(data.repo.name, xml, fragments) }

        repo_addresslines = data.addresslines_keyed

        unless repo_addresslines.empty?
          xml.address {

            repo_addresslines.each do |key, line|
              if key.start_with?('telephone')
                addressline_atts = { localtype: line[0] }
                xml.addressline(addressline_atts) {
                  sanitize_mixed_content(line[1], xml, fragments)
                }
              elsif key == 'email'
                addressline_atts = { localtype: key }
                xml.addressline(addressline_atts) {
                  sanitize_mixed_content(line, xml, fragments)
                }
              else
                xml.addressline { sanitize_mixed_content( line, xml, fragments) }
              end
            end

            if data.repo.url
              xml.addressline {
                xml.ref ({ href: data.repo.url, linktitle: data.repo.url, show: "new" }) {
                  xml.text(data.repo.url)
                }
              }
            end
          }
        end

        if (data.finding_aid_date)
          xml.date { sanitize_mixed_content( data.finding_aid_date, xml, fragments) }
        end

        num = (0..3).map { |i| data.send("id_#{i}") }.compact.join('.')
        unless num.empty?
          xml.num() {
            xml.text(num)
          }
        end

        if data.repo.image_url
          xml.p {
            xml.ptr ({
              href: data.repo.image_url,
              actuate: "onload",
              show: "embed"
            })
          }
        end

        data.metadata_rights_declaration_in_publicationstmt do |mrd|
          xml.p (mrd["descriptive_note"])
        end
      }

      if (data.finding_aid_series_statement)
        xml.seriesstmt {
          sanitize_mixed_content( data.finding_aid_series_statement, xml, fragments, true )
        }
      end

      if ( data.finding_aid_note )
        xml.notestmt {
          xml.controlnote {
            sanitize_mixed_content( data.finding_aid_note, xml, fragments, true )
          }
        }
      end
    } # END filedesc

    xml.maintenancestatus( { value: 'derived' } )

    maintenanceagency_atts = {
      countrycode: data.repo.country
    }.delete_if { |k, v| v.nil? || v.empty? }

    xml.maintenanceagency(maintenanceagency_atts) {

      unless data.repo.org_code.nil?
        agencycode = data.repo.country ? "#{data.repo.country}-" : ''
        agencycode += data.repo.org_code
        xml.agencycode() {
          xml.text(agencycode)
        }
      end

      xml.agencyname() {
        xml.text(data.repo.name)
      }
    }

    unless data.finding_aid_language.nil?
      xml.languagedeclaration() {

        xml.language({ langcode: "#{data.finding_aid_language}"}) {
          xml.text(I18n.t("enumerations.language_iso639_2.#{data.finding_aid_language}"))
        }

        xml.script({ scriptcode: "#{data.finding_aid_script}" }) {
          xml.text(I18n.t("enumerations.script_iso15924.#{data.finding_aid_script}"))
        }

        unless data.finding_aid_language_note.nil?
          xml.descriptivenote {
            sanitize_mixed_content(data.finding_aid_language_note, xml, fragments, true)
          }
        end

      }
    end

    unless data.finding_aid_description_rules.nil?
      xml.conventiondeclaration {
        xml.abbr {
          xml.text(data.finding_aid_description_rules)
        }
        xml.citation {
          xml.text(I18n.t("enumerations.resource_finding_aid_description_rules.#{ data.finding_aid_description_rules}"))
        }
      }
    end

    data.metadata_rights_declaration_in_rightsdeclaration do |mrd|
      xml.rightsdeclaration {
        attributes = { href: mrd["file_uri"] }
        attributes[:arcrole] = mrd["xlink_arcrole_attribute"] if mrd["xlink_arcrole_attribute"]
        attributes[:linkrole] = mrd["xlink_role_attribute"] if mrd["xlink_role_attribute"]
        xml.citation (attributes) {
          if mrd["license"]
            xml.text (I18n.t("enumerations.metadata_license.#{mrd['license']}", :default => mrd['license']))
          end
        }
        if mrd["license"]
          xml.abbr (mrd["license"])
        end
        if mrd["descriptive_note"]
          xml.descriptivenote {

            if mrd["descriptive_note"]
              xml.p (mrd["descriptive_note"])
            end
          }
        end
      }
    end

    if @include_unpublished || data.is_finding_aid_status_published
      finding_aid_status = data.finding_aid_status
    else
      finding_aid_status = nil
    end

    unless finding_aid_status.nil?
      xml.localcontrol( { localtype: 'findaidstatus'} ) {
        xml.term() {
          xml.text(finding_aid_status)
        }
      }
    end

    xml.maintenancehistory() {
      xml.maintenanceevent() {
        xml.eventtype( { value: 'derived' } ) {}
        xml.eventdatetime() {
          xml.text(DateTime.now.to_s)
        }
        xml.agenttype( { value: 'machine' } ) {}
        xml.agent() {
          xml.text("ArchivesSpace #{ ASConstants.VERSION }")
        }
        xml.eventdescription {
          xml.text("This finding aid was produced using ArchivesSpace on #{ DateTime.now.strftime('%A %B %e, %Y at %H:%M') }")
        }
      }

      export_rs = @include_unpublished ? data.revision_statements : data.revision_statements.reject { |rs| !rs['publish'] }
      if export_rs.length > 0
        export_rs.each do |rs|
          xml.maintenanceevent(rs['publish'] ? nil : {:audience => 'internal'}) {
            xml.eventtype( { value: 'revised' } ) {}
            xml.eventdatetime() {
              xml.text(rs['date'].to_s)
            }
            xml.agenttype( { value: 'unknown' } ) {}
            xml.agent() {}
            xml.eventdescription() {
              sanitize_mixed_content( rs['description'], xml, fragments)
            }
          }
        end
      end
    }
  }
end

#serialize_controlaccess(data, xml, fragments) ⇒ Object 



1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
 
# File 'backend/app/exporters/serializers/ead3.rb', line 1271

def serialize_controlaccess(data, xml, fragments)
  if (data.controlaccess_subjects.length + data.controlaccess_linked_agents(@include_unpublished).reject {|x| x.empty?}.length) > 0
    xml.controlaccess {

      data.controlaccess_subjects.zip(data.subjects).each do |node_data, subject|

        if node_data[:atts]['authfilenumber']
          node_data[:atts]['identifier'] = node_data[:atts]['authfilenumber'].clone
          node_data[:atts].delete('authfilenumber')
        end

        xml.send(node_data[:node_name], node_data[:atts]) {
          xml.part() {
            sanitize_mixed_content( node_data[:content], xml, fragments, ASpaceExport::Utils.include_p?(node_data[:node_name]) )
            EAD3Serializer.run_serialize_step(subject['_resolved'], xml, fragments, node_data[:node_name].to_sym)
          }
        }
      end

      data.controlaccess_linked_agents(@include_unpublished).zip(data.linked_agents).each do |node_data, agent|

        next if node_data.empty?

        if node_data[:atts][:role]
          node_data[:atts][:relator] = node_data[:atts][:role]
          node_data[:atts].delete(:role)
        end

        if node_data[:atts][:authfilenumber]
          node_data[:atts][:identifier] = node_data[:atts][:authfilenumber].clone
          node_data[:atts].delete(:authfilenumber)
        end

        xml.send(node_data[:node_name], node_data[:atts]) {
          xml.part() {
            sanitize_mixed_content( node_data[:content], xml, fragments, ASpaceExport::Utils.include_p?(node_data[:node_name]) )
            EAD3Serializer.run_serialize_step(agent['_resolved'], xml, fragments, node_data[:node_name].to_sym)
          }
        }
      end

    } #</controlaccess>
  end
end

#serialize_dates(obj, xml, fragments) ⇒ Object 



911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
 
# File 'backend/app/exporters/serializers/ead3.rb', line 911

def serialize_dates(obj, xml, fragments)
  add_unitdate = Proc.new do |value, context, fragments, atts={}|
    context.unitdate(atts) {
      sanitize_mixed_content( value, context, fragments )
    }
  end

  obj.dates.each do |date|
    next if date["publish"] === false && !@include_unpublished

    date_atts = {
      certainty: date['certainty'] ? date['certainty'] : nil,
      era: date['era'] ? date['era'] : nil,
      calendar: date['calendar'] ? date['calendar'] : nil,
      audience: date['publish'] === false ? 'internal' : nil,
      datechar: date['label'] ? date['label'] : nil
    }

    unless date['date_type'].nil?
      date_atts[:unitdatetype] = date['date_type'] == 'bulk' ? 'bulk' : 'inclusive'
    end

    date_atts.delete_if { |k, v| v.nil? }

    if date['begin'] || date['end']

      xml.unitdatestructured(date_atts) {

        if date['date_type'] == 'single' && date['begin']

          xml.datesingle( { standarddate: date['begin'] } ) {
            value = date['expression'].nil? ? date['begin'] : date['expression']
            xml.text(value)
          }

        else

          xml.daterange() {
            if date['begin']
              xml.fromdate( { standarddate: date['begin'] } ) {
                xml.text(date['begin'])
              }
            end
            if date['end']
              xml.todate( { standarddate: date['end'] } ) {
                xml.text(date['end'])
              }
            end
          }
        end
      }

      if date['begin'] && date['end'] && date['expression']
        add_unitdate.call(date['expression'], xml, fragments, date_atts)
      end

    elsif date['expression']
      add_unitdate.call(date['expression'], xml, fragments, date_atts)
    end
  end
end

#serialize_did_notes(data, xml, fragments) ⇒ Object 



995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
 
# File 'backend/app/exporters/serializers/ead3.rb', line 995

def serialize_did_notes(data, xml, fragments)
  data.notes.each do |note|
    next if note["publish"] === false && !@include_unpublished
    # SEE backend/app/exporters/lib/export_helpers.rb - did note types valid for both EAD 2002 and EAD3
    next unless data.did_note_types.include?(note['type'])

    atts = {
      audience: note["publish"] === false ? 'internal' : nil,
      id: prefix_id(note['persistent_id'].gsub(/\s/, '_'))
    }
    atts.delete_if { |k, v| v.nil? || v.empty? || v == "null" }

    append_note_content = Proc.new do |note, context, fragments, parent_element_name|
      content = ASpaceExport::Utils.extract_note_text(note, @include_unpublished)
      content = strip_invalid_children_from_note_content(content, parent_element_name)
      sanitize_mixed_content( content, context, fragments, ASpaceExport::Utils.include_p?(note['type']) )
    end

    case note['type']
    when 'dimensions', 'physfacet'
      atts[:label] = note['label'] if note['label']
      xml.physdesc(atts) {
        append_note_content.(note, xml, fragments, 'physdesc')
      }
    when 'physdesc', 'physloc'
      atts[:label] = note['label'] if note['label']
      xml.send(note['type'], atts) {
        append_note_content.(note, xml, fragments, note['type'])
      }
    when 'langmaterial'
      xml.langmaterial(atts) {
        xml.language() {
          append_note_content.(note, xml, fragments, 'language')
        }
      }
    else
      xml.send(note['type'], atts) {
        append_note_content.(note, xml, fragments, note['type'])
      }
    end

  end
end

#serialize_digital_object(digital_object, xml, fragments) ⇒ Object 



1420
1421
1422
1423
1424
1425
1426
1427
1428
 
# File 'backend/app/exporters/serializers/ead3.rb', line 1420

def serialize_digital_object(digital_object, xml, fragments)
  if (digital_object['file_versions'].count > 1) && digital_object['_is_in_representative_instance']
    xml.daoset(linkrole: "representative") {
      serialize_digital_object_dao(digital_object, xml, fragments)
    }
  else
    serialize_digital_object_dao(digital_object, xml, fragments)
  end
end

#serialize_digital_object_dao(digital_object, xml, fragments) ⇒ Object 



1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
 
# File 'backend/app/exporters/serializers/ead3.rb', line 1431

def serialize_digital_object_dao(digital_object, xml, fragments)
  return if digital_object["publish"] === false && !@include_unpublished
  return if digital_object["suppressed"] === true

  file_versions = digital_object['file_versions']
  title = digital_object['title']
  date = digital_object['dates'][0] || {}

  atts = {}

  content = ""
  content << title if title
  content << ": " if date['expression'] || date['begin']
  if date['expression']
    content << date['expression']
  elsif date['begin']
    content << date['begin']
    if date['end'] != date['begin']
      content << "-#{date['end']}"
    end
  end

  atts['linktitle'] = digital_object['title'] if digital_object['title']

  if digital_object['digital_object_type']
    atts['daotype'] = 'otherdaotype'
    atts['otherdaotype'] = digital_object['digital_object_type']
  else
    atts['daotype'] = 'unknown'
  end

  if file_versions.empty?
    atts['href'] = digital_object['digital_object_id']
    atts['actuate'] = 'onrequest'
    atts['show'] = 'new'
    atts['audience'] = 'internal' unless is_digital_object_published?(digital_object)
    xml.dao(atts) {
      xml.descriptivenote { sanitize_mixed_content(content, xml, fragments, true) } if content
    }
  else
    file_versions.each do |file_version|
      atts['href'] = file_version['file_uri'] || digital_object['digital_object_id']
      atts['actuate'] = (file_version['xlink_actuate_attribute'].respond_to?(:downcase) && file_version['xlink_actuate_attribute'].downcase) || 'onrequest'
      atts['show'] = (file_version['xlink_show_attribute'].respond_to?(:downcase) && file_version['xlink_show_attribute'].downcase) || 'new'
      atts['localtype'] = file_version['use_statement'] if file_version['use_statement']
      atts['audience'] = 'internal' unless is_digital_object_published?(digital_object, file_version)
      if digital_object['_is_in_representative_instance']
        atts['linkrole'] = [file_version['use_statement'], 'representative'].compact.join(" ")
      end
      xml.dao(atts) {
        xml.descriptivenote { sanitize_mixed_content(content, xml, fragments, true) } if content
      }
    end
  end
  EAD3Serializer.run_serialize_step(digital_object, xml, fragments, :dao)
end

#serialize_extents(obj, xml, fragments) ⇒ Object 



851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
 
# File 'backend/app/exporters/serializers/ead3.rb', line 851

def serialize_extents(obj, xml, fragments)
  if obj.extents.length
    obj.extents.each do |e|
      next if e["publish"] === false && !@include_unpublished

      # physdescstructuredtype is based on extent_type
      # These mappings only account for the default value options
      physdescstructured_atts = { coverage: e['portion'] }

      if e["publish"] === false
        physdescstructured_atts[:audience] = 'internal'
      end

      case e['extent_type']
      when 'cassettes', 'leaves', 'photographic_prints', 'photographic_slides', 'reels', 'sheets', 'volumes'
        physdescstructured_atts[:physdescstructuredtype] = 'materialtype'
      when 'cubic_feet', 'linear_feet'
        physdescstructured_atts[:physdescstructuredtype] = 'spaceoccupied'
      when 'gigabytes', 'megabytes', 'terabytes'
        physdescstructured_atts[:physdescstructuredtype] = 'otherphysdescstructuredtype'
      else
        physdescstructured_atts[:physdescstructuredtype] = 'spaceoccupied'
      end

      xml.physdescstructured(physdescstructured_atts) {
        if e['number']
          xml.quantity() {
            xml.text(e['number'])
          }
        end

        if e['extent_type']
          xml.unittype() {
            xml.text( I18n.t('enumerations.extent_extent_type.' + e['extent_type'], :default => e['extent_type']) )
          }
        end

        if e['physical_details']
          xml.physfacet() {
            sanitize_mixed_content(e['physical_details'], xml, fragments)
          }
        end

        if e['dimensions']
          xml.dimensions() {
            sanitize_mixed_content(e['dimensions'], xml, fragments)
          }
        end
      }

      if e['container_summary']
        xml.physdesc({ localtype: 'container_summary' }) {
          sanitize_mixed_content( e['container_summary'], xml, fragments)
        }
      end
    end
  end
end

#serialize_indexes(data, xml, fragments) ⇒ Object 



1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
 
# File 'backend/app/exporters/serializers/ead3.rb', line 1513

def serialize_indexes(data, xml, fragments)
  data.indexes.each do |note|
    next if note["publish"] === false && !@include_unpublished
    content = ASpaceExport::Utils.extract_note_text(note, @include_unpublished)
    head_text = nil

    if note['label']
      head_text = note['label']
    elsif note['type']
      head_text = I18n.t("enumerations._note_types.#{note['type']}", :default => note['type'])
    end

    atts = {
      audience: note["publish"] === false ? 'internal' : nil,
      id: prefix_id(note['persistent_id'].gsub(/\s/, '_'))
    }
    atts.delete_if { |k, v| v.nil? || v.empty? || v == "null" }

    content, head_text = extract_head_text(content, head_text)

    xml.index(atts) {
      xml.head { sanitize_mixed_content(head_text, xml, fragments ) } unless head_text.nil?

      sanitize_mixed_content(content, xml, fragments, true)

      note['items'].each do |item|
        next unless (node_name = data.index_item_type_map[item['type']])
        xml.indexentry {

          atts = item['reference'] ? {:target => prefix_id( item['reference']) } : {}

          if (val = item['value'])
            xml.send(node_name) {
              xml.part() {
                sanitize_mixed_content(val, xml, fragments )
              }
            }
          end

          if (val = item['reference_text'])
            xml.ref(atts) {
              sanitize_mixed_content( val, xml, fragments)
            }
          end
        }
      end
    }
  end
end

#serialize_languages(languages, xml, fragments) ⇒ Object 



1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
 
# File 'backend/app/exporters/serializers/ead3.rb', line 1039

def serialize_languages(languages, xml, fragments)
  language_vals = languages.map {|l| l['language_and_script']}.compact
  # Language and Script subrecords with recorded values in both fields should be exported as <languageset> elements.
  xml.langmaterial {
    language_vals.map {|language|
      if !language['script']
        xml.language(:langcode => language['language']) {
            xml.text I18n.t("enumerations.language_iso639_2.#{language['language']}", :default => language['language'])
          }
      # Language and Script subrecord entries with only a Language value record should be exported as <language> elements.
      else
        xml.languageset {
          xml.language(:langcode => language['language']) {
             xml.text I18n.t("enumerations.language_iso639_2.#{language['language']}", :default => language['language'])
           }
          xml.script(:scriptcode => language['script']) {
            xml.text I18n.t("enumerations.script_iso15924.#{language['script']}", :default => language['script'])
          }
        }
      end
    }
    # Language Text subrecord content should be exported as a <descriptivenote> element
    language_notes = languages.map {|l| l['notes']}.compact.reject {|e| e == [] }.flatten
    if !language_notes.empty?
      language_notes.each do |note|
        content = ASpaceExport::Utils.extract_note_text(note)
        xml.descriptivenote {
          sanitize_mixed_content(content, xml, fragments, true)
        }
      end
    end
  }
end

#serialize_nondid_notes(data, xml, fragments) ⇒ Object 



1098
1099
1100
1101
1102
1103
1104
1105
1106
 
# File 'backend/app/exporters/serializers/ead3.rb', line 1098

def serialize_nondid_notes(data, xml, fragments)
  data.notes.each do |note|
    next if note["publish"] === false && !@include_unpublished
    next if note['internal']
    next if note['type'].nil?
    next unless data.archdesc_note_types.include?(note['type'])
    serialize_note_content(note, xml, fragments)
  end
end

#serialize_note_content(note, xml, fragments) ⇒ Object 



1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
 
# File 'backend/app/exporters/serializers/ead3.rb', line 1074

def serialize_note_content(note, xml, fragments)
  return if note["publish"] === false && !@include_unpublished
  content = note["content"]

  atts = {
    audience: note['publish'] === false ? 'internal' : nil,
    id: prefix_id(note['persistent_id'].gsub(/\s/, '_'))
  }
  atts.delete_if { |k, v| v.nil? || v.empty? || v == "null" }

  head_text = note['label'] ? note['label'] : I18n.t("enumerations._note_types.#{note['type']}", :default => note['type'])

  content, head_text = extract_head_text(content, head_text)

  xml.send(note['type'], atts) {
    xml.head { sanitize_mixed_content(head_text, xml, fragments) } unless ASpaceExport::Utils.headless_note?(note['type'], content )
    sanitize_mixed_content(content, xml, fragments, ASpaceExport::Utils.include_p?(note['type']) ) if content
    if note['subnotes']
      serialize_subnotes(note['subnotes'], xml, fragments, ASpaceExport::Utils.include_p?(note['type']))
    end
  }
end

#serialize_origination(data, xml, fragments) ⇒ Object 



1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
 
# File 'backend/app/exporters/serializers/ead3.rb', line 1109

def serialize_origination(data, xml, fragments)
  unless data.creators_and_sources.nil?
    data.creators_and_sources.each do |link|
      agent = link['_resolved']
      link['role'] == 'creator' ? role = link['role'].capitalize : role = link['role']
      relator = link['relator']
      sort_name = agent['display_name']['sort_name']
      rules = agent['display_name']['rules']
      source = agent['display_name']['source']
      authfilenumber = agent['display_name']['authority_id']
      node_name = case agent['agent_type']
                  when 'agent_person'; 'persname'
                  when 'agent_family'; 'famname'
                  when 'agent_corporate_entity'; 'corpname'
                  when 'agent_software'; 'name'
                  end
      xml.origination(:label => role) {

        atts = {:relator => relator, :source => source, :rules => rules, :identifier => authfilenumber}

        atts.reject! {|k, v| v.nil?}

        xml.send(node_name, atts) {
          xml.part() {
            sanitize_mixed_content(sort_name, xml, fragments )
            EAD3Serializer.run_serialize_step(agent, xml, fragments, node_name.to_sym)
          }
        }
      }
    end
  end
end

#serialize_subnotes(subnotes, xml, fragments, include_p = true) ⇒ Object 



1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
 
# File 'backend/app/exporters/serializers/ead3.rb', line 1317

def serialize_subnotes(subnotes, xml, fragments, include_p = true)
  subnotes.each do |sn|
    next if sn["publish"] === false && !@include_unpublished

    audatt = sn["publish"] === false ? {:audience => 'internal'} : {}

    title = sn['title']

    case sn['jsonmodel_type']
    when 'note_text'
      sanitize_mixed_content(sn['content'], xml, fragments, include_p )
    when 'note_chronology'
      xml.chronlist(audatt) {
        xml.head { sanitize_mixed_content(title, xml, fragments) } if title

        sn['items'].each do |item|
          xml.chronitem {
            if (val = item['event_date'])
              xml.datesingle { sanitize_mixed_content( val, xml, fragments) }
            end
            if item['events'] && !item['events'].empty?
              xml.chronitemset {
                item['events'].each do |event|
                  xml.event { sanitize_mixed_content(event, xml, fragments) }
                end
              }
            end
          }
        end
      }
    when 'note_orderedlist'
      atts = {:listtype => 'ordered', :numeration => sn['enumeration']}.reject {|k, v| v.nil? || v.empty? || v == "null" }.merge(audatt)

      atts[:numeration] = list_numeration_value(atts[:numeration])

      xml.list(atts) {
        xml.head { sanitize_mixed_content(title, xml, fragments) } if title

        sn['items'].each do |item|
          xml.item { sanitize_mixed_content(item, xml, fragments)}
        end
      }
    when 'note_definedlist'
      xml.list({:listtype => 'deflist'}.merge(audatt)) {
        xml.head { sanitize_mixed_content(title, xml, fragments) } if title

        sn['items'].each do |item|
          xml.defitem {
            xml.label { sanitize_mixed_content(item['label'], xml, fragments) } if item['label']
            xml.item { sanitize_mixed_content(item['value'], xml, fragments )} if item['value']
          }
        end
      }
    end
  end
end

#stream(data) ⇒ Object 



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
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
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
 
# File 'backend/app/exporters/serializers/ead3.rb', line 450

def stream(data)
  @stream_handler = ASpaceExport::StreamHandler.new
  @fragments = ASpaceExport::RawXMLHandler.new
  @include_unpublished = data.include_unpublished?
  @include_daos = data.include_daos?
  @include_uris = data.include_uris?
  @use_numbered_c_tags = data.use_numbered_c_tags?
  @id_prefix = I18n.t('archival_object.ref_id_export_prefix', :default => 'aspace_')

  builder = Nokogiri::XML::Builder.new(:encoding => "UTF-8") do |xml|
    begin
      ead_attributes = {}

      if data.publish === false
        ead_attributes['audience'] = 'internal'
      end

      xml.ead( ead_attributes ) {

        xml.text (
          @stream_handler.buffer { |xml, new_fragments|
            serialize_control(data, xml, new_fragments)
          }
        )

        atts = {:level => data.level, :otherlevel => data.other_level}
        atts.reject! {|k, v| v.nil?}

        xml.archdesc(atts) {

          xml.did {

            unless data.title.nil?
              xml.unittitle { sanitize_mixed_content(data.title, xml, @fragments) }
            end

            xml.unitid (0..3).map { |i| data.send("id_#{i}") }.compact.join('.')

            handle_arks(data, xml)


            if @include_uris
              serialize_aspace_uri(data, xml)
            end

            unless data.repo.nil? || data.repo.name.nil?
              xml.repository {
                xml.corpname {
                  xml.part {
                    sanitize_mixed_content(data.repo.name, xml, @fragments)
                  }
                }
              }
            end

            unless (languages = data.lang_materials).empty?
              serialize_languages(languages, xml, @fragments)
            end

            data.instances_with_sub_containers.each do |instance|
              serialize_container(instance, xml, @fragments)
            end

            serialize_extents(data, xml, @fragments)

            serialize_dates(data, xml, @fragments)

            serialize_did_notes(data, xml, @fragments)

            serialize_origination(data, xml, @fragments)

            if @include_unpublished
              data.external_ids.each do |exid|
                xml.unitid ({ "audience" => "internal", "type" => exid['source'], "identifier" => exid['external_id']}) { xml.text exid['external_id']}
              end
            end

            EAD3Serializer.run_serialize_step(data, xml, @fragments, :did)

            # Change from EAD 2002: dao must be children of did in EAD3, not archdesc
            data.digital_objects.each do |dob|
              serialize_digital_object(dob, xml, @fragments)
            end

          }# </did>

          serialize_nondid_notes(data, xml, @fragments)

          serialize_bibliographies(data, xml, @fragments)

          serialize_indexes(data, xml, @fragments)

          serialize_controlaccess(data, xml, @fragments)

          EAD3Serializer.run_serialize_step(data, xml, @fragments, :archdesc)

          xml.dsc {

            data.children_indexes.each do |i|
              xml.text( @stream_handler.buffer {
                |xml, new_fragments| serialize_child(data.get_child(i), xml, new_fragments)
                }
              )
            end
          }
        }
      }

    rescue => e
      xml.text "ASPACE EXPORT ERROR : YOU HAVE A PROBLEM WITH YOUR EXPORT OF YOUR RESOURCE. THE FOLLOWING INFORMATION MAY HELP:\n
                MESSAGE: #{e.message.inspect}  \n
                TRACE: #{e.backtrace.inspect} \n "
    end
  end

  # Add xml-model for rng
  # Make this conditional if XSD or DTD are requested
  xmlmodel_content = 'href="https://raw.githubusercontent.com/SAA-SDT/EAD3/master/ead3.rng"
    type="application/xml" schematypens="http://relaxng.org/ns/structure/1.0"'

  xmlmodel = Nokogiri::XML::ProcessingInstruction.new(builder.doc, "xml-model", xmlmodel_content)
  builder.doc.root.add_previous_sibling(xmlmodel)
  builder.doc.root.add_namespace nil, 'http://ead3.archivists.org/schema/'

  Enumerator.new do |y|
    @stream_handler.stream_out(builder, @fragments, y)
  end
end

#strip_invalid_children_from_note_content(content, parent_element_name) ⇒ Object 



974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
 
# File 'backend/app/exporters/serializers/ead3.rb', line 974

def strip_invalid_children_from_note_content(content, parent_element_name)
  # convert & to @@ before generating XML fragment for processing
  content.gsub!(/&/, '@@')
  fragment = Nokogiri::XML::DocumentFragment.parse(content)
  children = fragment.element_children

  if !children.empty?
    if valid_children = valid_children_of_mixed_elements(parent_element_name)
      children.each do |e|
        if !valid_children.include?(e.name) && e.inner_text
          e.replace( e.inner_text.gsub(/\s+/, ' ') )
        end
      end
    end
  end

  # convert @@ back to & on return value
  fragment.inner_html.gsub(/@@/, '&')
end

#strip_p(content) ⇒ Object 



266
267
268
269
 
# File 'backend/app/exporters/serializers/ead3.rb', line 266

def strip_p(content)
  content = escape_ampersands(content)
  content.gsub("<p>", "").gsub("</p>", "").gsub("<p/>", '')
end

#strip_tags_and_sanitize(content, context, fragments) ⇒ Object 



444
445
446
447
 
# File 'backend/app/exporters/serializers/ead3.rb', line 444

def strip_tags_and_sanitize(content, context, fragments)
  content.gsub!(/\<[^\>]*\>/, '')
  sanitize_mixed_content(content, context, fragments)
end

#structure_children(content, parent_name = nil) ⇒ Object 



190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
 
# File 'backend/app/exporters/serializers/ead3.rb', line 190

def structure_children(content, parent_name = nil)
  # 4archon...
  content.gsub!("\n\t", "\n\n")

  content.strip!

  original_content = content

  content = escape_ampersands(content)

  valid_children = valid_children_of_unmixed_elements(parent_name)

  # wrap text in <p> if it isn't already
  p_wrap = lambda do |text|
    text.chomp!
    text.strip!
    if text =~ /^<p(\s|\/|>)/
      if !(text =~ /<\/p>$/)
        text += '</p>'
      end
    else
      text = "<p>#{ text }</p>"
    end
    return text
  end

  # this should only be called if the text fragment only has element children
  p_wrap_invalid_children = lambda do |text|
    text.strip!
    if valid_children
      fragment = Nokogiri::XML::DocumentFragment.parse(text)
      new_text = ''
      fragment.element_children.each do |e|
        if valid_children.include?(e.name)
          new_text << e.to_s
        else
          new_text << "<p>#{ e.to_s }</p>"
        end
      end
      return new_text
    else
      return p_wrap.call(text)
    end
  end

  if !has_unwrapped_text?(content)
    content = p_wrap_invalid_children.call(content)
  else
    return content if content.length < 1
    new_content = ''
    blocks = content.split("\n\n").select { |b| !b.strip.empty? }
    blocks.each do |b|
      if has_unwrapped_text?(b)
        new_content << p_wrap.call(b)
      else
        new_content << p_wrap_invalid_children.call(b)
      end
    end
    content = new_content
  end

  ## REMOVED 2018-09 - leaving here for future reference
  # first lets see if there are any &
  # note if there's a &somewordwithnospace , the error is EntityRef and wont
  # be fixed here...
  # if xml_errors(content).any? { |e| e.message.include?("The entity name must immediately follow the '&' in the entity reference.") }
  #   content.gsub!("& ", "&amp; ")
  # end
  # END - REMOVED 2018-09

  # in some cases adding p tags can create invalid markup with mixed content
  # just return the original content if there's still problems
  xml_errors(content).any? ? original_content : content
end

#valid_children_of_mixed_elements(element_name) ⇒ Object 



40
41
42
43
44
45
46
47
48
49
 
# File 'backend/app/exporters/serializers/ead3.rb', line 40

def valid_children_of_mixed_elements(element_name)
  valid_children_map = {}
  valid_children_map['p'] = valid_children_of_p
  valid_children_map['archref'] = valid_children_of_p - ['list']
  valid_children_map['bibref'] = valid_children_of_p - ['list']
  ['head', 'date', 'emph', 'num', 'quote', 'physdesc'].each do |e|
    valid_children_map[e] = ['abbr', 'emph', 'expan', 'foreign', 'lb', 'ptr', 'ref']
  end
  valid_children_map[element_name] || nil
end

#valid_children_of_p ⇒ Object 



6
7
8
9
 
# File 'backend/app/exporters/serializers/ead3.rb', line 6

def valid_children_of_p
  ['abbr', 'corpname', 'date', 'emph', 'expan', 'famname', 'footnote', 'foreign', 'function', 'genreform',
    'geogname', 'lb', 'list', 'name', 'num', 'occupation', 'persname', 'ptr', 'quote', 'ref', 'subject', 'title']
end

#valid_children_of_unmixed_elements(element_name) ⇒ Object 



12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
 
# File 'backend/app/exporters/serializers/ead3.rb', line 12

def valid_children_of_unmixed_elements(element_name)
  common_children = [ 'blockquote', 'chronlist', 'head', 'list', 'p', 'table' ]
  valid_children_map = {}
  standard_elements = ['accessrestrict', 'accruals', 'acqinfo', 'altformavail', 'appraisal', 'arrangement', 'bioghist',
    'custodhist', 'fileplan', 'legalstatus', 'odd', 'originalsloc', 'phystech', 'prefercite',
    'processinfo', 'scopecontent', 'userestrict']

  standard_elements.each do |e|
    valid_children_map[e] = [e] + common_children
  end

  valid_children_map['bibliography'] = [ 'archref', 'bibliography', 'bibref' ] + common_children
  valid_children_map['controlaccess'] = [ 'controlaccess', 'corpname', 'famname', 'function', 'genreform', 'geogname',
    'name', 'occupation', 'persname', 'subject', 'title' ] + common_children
  valid_children_map['controlnote'] = [ 'blockquote', 'chronlist', 'list', 'p', 'table' ]
  valid_children_map['descriptivenote'] = [ 'p' ]
  valid_children_map['editionstmt'] = [ 'edition', 'p' ]
  valid_children_map['footnote'] = [ 'blockquote', 'chronlist', 'list', 'p', 'table' ]
  valid_children_map['index'] = [ 'index', 'indexentry', 'listhead' ] + common_children
  valid_children_map['otherfindaid'] = [ 'archref', 'bibref', 'otherfindaid' ] + common_children
  valid_children_map['publicationstmt'] = [ 'address', 'date', 'num', 'p', 'publisher' ]
  valid_children_map['relatedmaterial'] = [ 'archref', 'bibref', 'relatedmaterial' ] + common_children
  valid_children_map['separatedmaterial'] = [ 'archref', 'bibref', 'separatedmaterial' ] + common_children
  valid_children_map['seriesstmt'] = [ 'num', 'p', 'titleproper' ]
  valid_children_map[element_name] || nil
end

#xml_errors(content) ⇒ Object 



155
156
157
158
159
160
161
162
 
# File 'backend/app/exporters/serializers/ead3.rb', line 155

def xml_errors(content)
  # there are message we want to ignore. annoying that java xml lib doesn't
  # use codes like libxml does...
  ignore = [ /Namespace prefix .* is not defined/, /The prefix .* is not bound/ ]
  ignore = Regexp.union(ignore)
  # the "wrap" is just to ensure that there is a psuedo root element to eliminate a "false" error
  Nokogiri::XML("<wrap>#{content}</wrap>").errors.reject { |e| e.message =~ ignore }
end