bplmodels 0.0.91 → 0.0.93
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/app/models/bplmodels/characterization.rb +3 -1
- data/app/models/bplmodels/collection.rb +29 -5
- data/app/models/bplmodels/ereader_file.rb +14 -0
- data/app/models/bplmodels/file.rb +152 -12
- data/app/models/bplmodels/institution.rb +73 -1
- data/app/models/bplmodels/marc_file.rb +14 -0
- data/app/models/bplmodels/mods_desc_metadata.rb +124 -8
- data/app/models/bplmodels/object_base.rb +692 -252
- data/app/models/bplmodels/page_metadata.rb +56 -0
- data/app/models/bplmodels/transcription_file.rb +14 -0
- data/app/models/bplmodels/volume.rb +37 -0
- data/app/models/bplmodels/workflow_metadata.rb +6 -0
- data/lib/active_fedora/rdf/indexing_service.rb +88 -0
- data/lib/active_fedora/rdf/term.rb +189 -0
- data/lib/bplmodels/constants.rb +1 -0
- data/lib/bplmodels/datastream_input_funcs.rb +4 -1
- data/lib/bplmodels/finder.rb +104 -0
- data/lib/bplmodels/version.rb +1 -1
- metadata +25 -18
@@ -77,6 +77,18 @@ module Bplmodels
|
|
77
77
|
}
|
78
78
|
}
|
79
79
|
|
80
|
+
#CLASSIFICATION--------------------------------------------------------
|
81
|
+
t.classification(:path => 'classification') {
|
82
|
+
t.displayLabel :path=>{:attribute=>'displayLabel'}
|
83
|
+
t.edition :path =>{:attribute=>"edition"}
|
84
|
+
::Mods::AUTHORITY_ATTRIBS.each { |attr_name|
|
85
|
+
t.send attr_name, :path =>{:attribute=>"#{attr_name}"}
|
86
|
+
}
|
87
|
+
::Mods::LANG_ATTRIBS.each { |attr_name|
|
88
|
+
t.send attr_name, :path =>{:attribute=>"#{attr_name}"}
|
89
|
+
}
|
90
|
+
}
|
91
|
+
|
80
92
|
=begin
|
81
93
|
# CLASSIFICATION -------------------------------------------------------------------------
|
82
94
|
t.classification(:path => 'mods/oxns:classification') {
|
@@ -289,6 +301,8 @@ module Bplmodels
|
|
289
301
|
t.authorityURI(:path=>{:attribute=>"authorityURI"})
|
290
302
|
t.valueURI(:path=>{:attribute=>"valueURI"})
|
291
303
|
t.subtitle(:path=>"subTitle", :label=>"subtitle")
|
304
|
+
t.part_number(:path=>"partNumber", :label=>"partNumber")
|
305
|
+
t.part_name(:path=>"partName", :label=>"partName")
|
292
306
|
}
|
293
307
|
t.title(:proxy=>[:title_info, :main_title])
|
294
308
|
|
@@ -322,6 +336,14 @@ module Bplmodels
|
|
322
336
|
t.issuance(:path=>"issuance")
|
323
337
|
t.edition(:path=>"edition")
|
324
338
|
t.event_type(:path=>{:attribute=>"eventType"})
|
339
|
+
t.frequency(:path=>"frequency") {
|
340
|
+
t.authority(:path=>{:attribute=>"authority"})
|
341
|
+
}
|
342
|
+
}
|
343
|
+
|
344
|
+
t.target_audience(:path=>"targetAudience") {
|
345
|
+
t.authority(:path=>{:attribute=>"authority"})
|
346
|
+
t.display_label(:path=>{:attribute=>"displayLabel"})
|
325
347
|
}
|
326
348
|
|
327
349
|
t.item_location(:path=>"location") {
|
@@ -353,6 +375,7 @@ module Bplmodels
|
|
353
375
|
t.local_accession :path => 'identifier', :attributes => { :type => "local-accession" }
|
354
376
|
t.local_call :path => 'identifier', :attributes => { :type => "local-call" }
|
355
377
|
t.local_barcode :path => 'identifier', :attributes => { :type => "local-barcode" }
|
378
|
+
t.ia_id :path => 'identifier', :attributes => { :type => "internet-archive" }
|
356
379
|
t.identifier_uri :path => 'identifier', :attributes => { :type => "uri" }
|
357
380
|
|
358
381
|
t.physical_description(:path=>"physicalDescription") {
|
@@ -556,7 +579,9 @@ module Bplmodels
|
|
556
579
|
}
|
557
580
|
|
558
581
|
|
559
|
-
t.table_of_contents(:path=>'tableOfContents')
|
582
|
+
t.table_of_contents(:path=>'tableOfContents') {
|
583
|
+
t.href(:path=>{:attribute=>'xlink:href'})
|
584
|
+
}
|
560
585
|
|
561
586
|
|
562
587
|
end
|
@@ -688,6 +713,13 @@ module Bplmodels
|
|
688
713
|
self.mods(0).accessCondition(access_index).displayLabel = displayLabel unless displayLabel.blank?
|
689
714
|
end
|
690
715
|
|
716
|
+
def insert_target_audience(value=nil, authority=nil, display_label=nil)
|
717
|
+
audience_index = self.mods(0).target_audience.count
|
718
|
+
self.mods(0).target_audience(audience_index, value) unless value.blank?
|
719
|
+
self.mods(0).target_audience(audience_index).authority = authority unless authority.blank?
|
720
|
+
self.mods(0).target_audience(audience_index).display_label = display_label unless display_label.blank?
|
721
|
+
end
|
722
|
+
|
691
723
|
|
692
724
|
def insert_type_of_resource(value=nil, manuscript=nil)
|
693
725
|
resource_index = self.mods(0).type_of_resource.count
|
@@ -824,6 +856,13 @@ module Bplmodels
|
|
824
856
|
self.mods(0).origin_info(origin_index).event_type = event_type unless event_type.blank?
|
825
857
|
end
|
826
858
|
|
859
|
+
def insert_origin_frequency(frequency, authority)
|
860
|
+
#Currently only supporting one elements...
|
861
|
+
origin_index = 0
|
862
|
+
self.mods(0).origin_info(origin_index).frequency = frequency unless frequency.blank?
|
863
|
+
self.mods(0).origin_info(origin_index).frequency.authority = authority unless authority.blank?
|
864
|
+
end
|
865
|
+
|
827
866
|
def insert_tgn(tgn_id)
|
828
867
|
puts 'TGN ID is: ' + tgn_id
|
829
868
|
|
@@ -947,7 +986,7 @@ module Bplmodels
|
|
947
986
|
end
|
948
987
|
|
949
988
|
#usage=nil, supplied=nil, subtitle=nil, language=nil, type=nil, authority=nil, authorityURI=nil, valueURI=nil
|
950
|
-
def insert_title(nonSort=nil, main_title=nil, usage=nil, supplied=nil, type=nil, subtitle=nil, language=nil, display_label=nil, args={})
|
989
|
+
def insert_title(nonSort=nil, main_title=nil, usage=nil, supplied=nil, type=nil, subtitle=nil, language=nil, display_label=nil, part_number=nil, part_name=nil, args={})
|
951
990
|
title_index = self.mods(0).title_info.count
|
952
991
|
|
953
992
|
self.mods(0).title_info(title_index).nonSort = nonSort unless nonSort.blank?
|
@@ -976,6 +1015,10 @@ module Bplmodels
|
|
976
1015
|
|
977
1016
|
self.mods(0).title_info(title_index).display_label = display_label unless display_label.blank?
|
978
1017
|
|
1018
|
+
self.mods(0).title_info(title_index).part_number = part_number unless part_number.blank?
|
1019
|
+
|
1020
|
+
self.mods(0).title_info(title_index).part_name = part_name unless part_name.blank?
|
1021
|
+
|
979
1022
|
if args.present?
|
980
1023
|
raise 'broken args in Active Fedora 7'
|
981
1024
|
end
|
@@ -1104,6 +1147,66 @@ module Bplmodels
|
|
1104
1147
|
|
1105
1148
|
|
1106
1149
|
|
1150
|
+
self.insert_note(converted[:date_note],"date") unless !converted.has_key?(:date_note)
|
1151
|
+
|
1152
|
+
end
|
1153
|
+
|
1154
|
+
def insert_oai_date_copyright(date)
|
1155
|
+
#converted = Bplmodels::DatastreamInputFuncs.convert_to_mods_date(date)
|
1156
|
+
converted = BplEnrich::Dates.standardize(date)
|
1157
|
+
|
1158
|
+
#date_index = self.date.length
|
1159
|
+
date_index = 0
|
1160
|
+
dup_found = false
|
1161
|
+
|
1162
|
+
#Prevent duplicate entries... Using a flag as keep the potential note?
|
1163
|
+
(self.mods(0).date(date_index).dates_copyright.length-1).times do |index|
|
1164
|
+
if converted.has_key?(:single_date)
|
1165
|
+
if self.mods(0).date(date_index).dates_copyright(index).point.blank? && self.mods(0).date(date_index).dates_copyright(index).first == converted[:single_date]
|
1166
|
+
dup_found = true
|
1167
|
+
end
|
1168
|
+
elsif converted.has_key?(:date_range)
|
1169
|
+
if self.mods(0).date(date_index).dates_copyright(index).point == 'start' && self.mods(0).date(date_index).dates_copyright(index).first == converted[:date_range][:start]
|
1170
|
+
if self.mods(0).date(date_index).dates_copyright(index+1).point == 'end' && self.mods(0).date(date_index).dates_copyright(index+1).first == converted[:date_range][:end]
|
1171
|
+
dup_found = true
|
1172
|
+
end
|
1173
|
+
|
1174
|
+
end
|
1175
|
+
end
|
1176
|
+
end
|
1177
|
+
|
1178
|
+
if !dup_found
|
1179
|
+
if converted.has_key?(:single_date) && !self.date.dates_copyright.include?(converted[:single_date])
|
1180
|
+
date_created_index = self.date(date_index).dates_copyright.length
|
1181
|
+
self.date(date_index).dates_copyright(date_created_index, converted[:single_date])
|
1182
|
+
self.date(date_index).dates_copyright(date_created_index).encoding = 'w3cdtf'
|
1183
|
+
if date_created_index == 0
|
1184
|
+
self.date(date_index).dates_copyright(date_created_index).key_date = 'yes'
|
1185
|
+
end
|
1186
|
+
|
1187
|
+
if converted.has_key?(:date_qualifier)
|
1188
|
+
self.date(date_index).dates_copyright(date_created_index).qualifier = converted[:date_qualifier]
|
1189
|
+
end
|
1190
|
+
elsif converted.has_key?(:date_range)
|
1191
|
+
date_created_index = self.date(date_index).dates_copyright.length
|
1192
|
+
self.date(date_index).dates_copyright(date_created_index, converted[:date_range][:start])
|
1193
|
+
self.date(date_index).dates_copyright(date_created_index).encoding = 'w3cdtf'
|
1194
|
+
if date_created_index == 0
|
1195
|
+
self.date(date_index).dates_copyright(date_created_index).key_date = 'yes'
|
1196
|
+
end
|
1197
|
+
self.date(date_index).dates_copyright(date_created_index).point = 'start'
|
1198
|
+
self.date(date_index).dates_copyright(date_created_index).qualifier = converted[:date_qualifier]
|
1199
|
+
|
1200
|
+
date_created_index = self.date(date_index).dates_copyright.length
|
1201
|
+
self.date(date_index).dates_copyright(date_created_index, converted[:date_range][:end])
|
1202
|
+
self.date(date_index).dates_copyright(date_created_index).encoding = 'w3cdtf'
|
1203
|
+
self.date(date_index).dates_copyright(date_created_index).point = 'end'
|
1204
|
+
self.date(date_index).dates_copyright(date_created_index).qualifier = converted[:date_qualifier]
|
1205
|
+
end
|
1206
|
+
end
|
1207
|
+
|
1208
|
+
|
1209
|
+
|
1107
1210
|
self.insert_note(converted[:date_note],"date") unless !converted.has_key?(:date_note)
|
1108
1211
|
|
1109
1212
|
end
|
@@ -1639,9 +1742,10 @@ module Bplmodels
|
|
1639
1742
|
self.find_by_terms(:subject_cartographic).slice(index.to_i).remove
|
1640
1743
|
end
|
1641
1744
|
|
1642
|
-
def insert_table_of_contents(
|
1745
|
+
def insert_table_of_contents(text_value, url=nil)
|
1643
1746
|
contents_index = self.mods(0).table_of_contents.count
|
1644
|
-
self.mods(0).table_of_contents(contents_index,
|
1747
|
+
self.mods(0).table_of_contents(contents_index, text_value) unless text_value.blank?
|
1748
|
+
self.mods(0).table_of_contents(contents_index).href = url unless url.blank?
|
1645
1749
|
end
|
1646
1750
|
|
1647
1751
|
def remove_table_of_contents(index)
|
@@ -1765,16 +1869,28 @@ module Bplmodels
|
|
1765
1869
|
def insert_identifier(identifier=nil, type=nil, display_label=nil, invalid=nil)
|
1766
1870
|
identifier_index = self.mods(0).identifier.count
|
1767
1871
|
|
1768
|
-
|
1769
|
-
|
1770
|
-
|
1771
|
-
|
1872
|
+
if identifier.present?
|
1873
|
+
self.mods(0).identifier(identifier_index, identifier) unless identifier.blank?
|
1874
|
+
self.mods(0).identifier(identifier_index).type_at = type unless type.blank?
|
1875
|
+
self.mods(0).identifier(identifier_index).displayLabel = display_label unless display_label.blank?
|
1876
|
+
self.mods(0).identifier(identifier_index).invalid = 'yes' if (invalid.present? && invalid == 'yes')
|
1877
|
+
end
|
1772
1878
|
end
|
1773
1879
|
|
1774
1880
|
def remove_identifier(index)
|
1775
1881
|
self.find_by_terms(:identifier).slice(index.to_i).remove
|
1776
1882
|
end
|
1777
1883
|
|
1884
|
+
def insert_classification(value=nil, edition=nil, authority=nil, display_label=nil)
|
1885
|
+
classification_index = self.mods(0).classification.count
|
1886
|
+
if value.present?
|
1887
|
+
self.mods(0).classification(classification_index, value)
|
1888
|
+
self.mods(0).classification(classification_index).edition = edition unless edition.blank?
|
1889
|
+
self.mods(0).classification(classification_index).authority = authority unless authority.blank?
|
1890
|
+
self.mods(0).classification(classification_index).displayLabel = display_label unless display_label.blank?
|
1891
|
+
end
|
1892
|
+
end
|
1893
|
+
|
1778
1894
|
|
1779
1895
|
define_template :mcgreevy do |xml|
|
1780
1896
|
xml.recordInfo {
|
@@ -13,20 +13,33 @@ module Bplmodels
|
|
13
13
|
|
14
14
|
has_many :document_files, :class_name => "Bplmodels::DocumentFile", :property=> :is_document_of
|
15
15
|
|
16
|
+
has_many :ereader_files, :class_name => "Bplmodels::EreaderFile", :property=> :is_ereader_of
|
17
|
+
|
16
18
|
has_many :files, :class_name => "Bplmodels::File", :property=> :is_file_of
|
17
19
|
|
18
20
|
|
19
21
|
|
20
22
|
belongs_to :institution, :class_name => 'Bplmodels::Institution', :property => :is_member_of
|
21
23
|
|
22
|
-
|
24
|
+
has_and_belongs_to_many :collection, :class_name => 'Bplmodels::Collection', :property => :is_member_of_collection
|
25
|
+
|
26
|
+
#has_and_belongs_to_many :organization, :class_name => 'Bplmodels::Collection', :property => :is_member_of_collection
|
27
|
+
|
28
|
+
belongs_to :admin_set, :class_name => 'Bplmodels::Collection', :property => :administrative_set
|
23
29
|
|
24
|
-
belongs_to :organization, :class_name => 'Bplmodels::Collection', :property => :is_member_of_collection
|
25
30
|
has_and_belongs_to_many :members, :class_name=> "Bplmodels::Collection", :property=> :hasSubset
|
26
31
|
|
27
32
|
has_metadata :name => "descMetadata", :type => ModsDescMetadata
|
28
33
|
has_metadata :name => "workflowMetadata", :type => WorkflowMetadata
|
29
34
|
|
35
|
+
has_file_datastream 'marc', versionable: false, label: 'MARC metadata'
|
36
|
+
has_file_datastream 'marcXML', versionable: false, label: 'MARC XML metadata'
|
37
|
+
has_file_datastream 'iaMeta', versionable: false, label: 'Internet Archive metadata'
|
38
|
+
has_file_datastream 'scanData', versionable: false, label: 'Internet Archive scanData metadata'
|
39
|
+
has_file_datastream 'plainText', versionable: false, label: 'Plain Text representation of this object'
|
40
|
+
has_file_datastream 'djvuXML', versionable: false, label: 'XML version of DJVU output'
|
41
|
+
has_file_datastream 'abbyy', versionable: false, label: 'Abbyy OCR of this object'
|
42
|
+
|
30
43
|
# Uses the Hydra Rights Metadata Schema for tracking access permissions & copyright
|
31
44
|
has_metadata :name => "rightsMetadata", :type => Hydra::Datastream::RightsMetadata
|
32
45
|
|
@@ -69,6 +82,10 @@ module Bplmodels
|
|
69
82
|
self.add_relationship(:oai_item_id, "oai:digitalcommonwealth.org:" + self.pid, true)
|
70
83
|
end
|
71
84
|
|
85
|
+
def remove_oai_relationships
|
86
|
+
self.remove_relationship(:oai_item_id, "oai:digitalcommonwealth.org:" + self.pid, true)
|
87
|
+
end
|
88
|
+
|
72
89
|
#alias :limited_delete :delete
|
73
90
|
|
74
91
|
=begin
|
@@ -86,6 +103,55 @@ module Bplmodels
|
|
86
103
|
}
|
87
104
|
end
|
88
105
|
end
|
106
|
+
|
107
|
+
#FIXME: What if this is interuppted? Need to do this better...
|
108
|
+
#Broken so no match for now
|
109
|
+
if self.class.name == "Bplmodels::Volume2"
|
110
|
+
next_object = nil
|
111
|
+
previous_object = nil
|
112
|
+
#volume_object = Bplmodels::Finder.getVolumeObjects(self.pid)
|
113
|
+
self.relationships.each_statement do |statement|
|
114
|
+
puts statement.predicate
|
115
|
+
if statement.predicate == "http://projecthydra.org/ns/relations#isPrecedingVolumeOf"
|
116
|
+
next_object = ActiveFedora::Base.find(statement.object.to_s.split('/').last).adapt_to_cmodel
|
117
|
+
elsif statement.predicate == "http://projecthydra.org/ns/relations#isFollowingVolumeOf"
|
118
|
+
previous_object = ActiveFedora::Base.find(statement.object.to_s.split('/').last).adapt_to_cmodel
|
119
|
+
end
|
120
|
+
end
|
121
|
+
|
122
|
+
if next_object.present? and previous_object.present?
|
123
|
+
next_object.relationships.each_statement do |statement|
|
124
|
+
if statement.predicate == "http://projecthydra.org/ns/relations#isFollowingVolumeOf"
|
125
|
+
next_object.remove_relationship(:is_following_volume_of, statement.object)
|
126
|
+
end
|
127
|
+
end
|
128
|
+
|
129
|
+
previous_object.relationships.each_statement do |statement|
|
130
|
+
if statement.predicate == "http://projecthydra.org/ns/relations#isPrecedingVolumeOf"
|
131
|
+
previous_object.remove_relationship(:is_preceding_volume_of, statement.object)
|
132
|
+
end
|
133
|
+
end
|
134
|
+
|
135
|
+
next_object.add_relationship(:is_following_volume_of, "info:fedora/#{previous_object.pid}", true)
|
136
|
+
previous_object.add_relationship(:is_preceding_volume_of, "info:fedora/#{next_object.pid}", true)
|
137
|
+
next_object.save
|
138
|
+
previous_object.save
|
139
|
+
elsif next_object.present? and previous_object.blank?
|
140
|
+
next_object.relationships.each_statement do |statement|
|
141
|
+
if statement.predicate == "http://projecthydra.org/ns/relations#isFollowingVolumeOf"
|
142
|
+
next_object.remove_relationship(:is_following_volume_of, statement.object)
|
143
|
+
end
|
144
|
+
end
|
145
|
+
|
146
|
+
elsif next_object.blank? and previous_object.present?
|
147
|
+
previous_object.relationships.each_statement do |statement|
|
148
|
+
if statement.predicate == "http://projecthydra.org/ns/relations#isPrecedingVolumeOf"
|
149
|
+
previous_object.remove_relationship(:is_preceding_volume_of, statement.object)
|
150
|
+
end
|
151
|
+
end
|
152
|
+
end
|
153
|
+
self.collection.first.update_index
|
154
|
+
end
|
89
155
|
super()
|
90
156
|
end
|
91
157
|
|
@@ -95,9 +161,10 @@ module Bplmodels
|
|
95
161
|
#if !self.instance_of?(klass)
|
96
162
|
adapted_object = self.adapt_to(klass)
|
97
163
|
|
98
|
-
|
164
|
+
adapted_object.relationships.each_statement do |statement|
|
99
165
|
if statement.predicate == "info:fedora/fedora-system:def/model#hasModel"
|
100
|
-
|
166
|
+
adapted_object.remove_relationship(:has_model, statement.object)
|
167
|
+
#puts statement.object
|
101
168
|
end
|
102
169
|
end
|
103
170
|
|
@@ -124,7 +191,8 @@ module Bplmodels
|
|
124
191
|
|
125
192
|
|
126
193
|
doc['label_ssim'] = self.label.to_s
|
127
|
-
|
194
|
+
|
195
|
+
# dates
|
128
196
|
doc['date_start_dtsi'] = []
|
129
197
|
doc['date_start_tsim'] = []
|
130
198
|
doc['date_end_dtsi'] = []
|
@@ -132,16 +200,23 @@ module Bplmodels
|
|
132
200
|
doc['date_facet_ssim'] = []
|
133
201
|
doc['date_type_ssm'] = []
|
134
202
|
doc['date_start_qualifier_ssm'] = []
|
203
|
+
doc['note_date_tsim'] = []
|
135
204
|
dates_static = []
|
136
205
|
dates_start = []
|
137
206
|
dates_end = []
|
138
207
|
|
208
|
+
# these values get appended to dates in _dtsi Solr format
|
209
|
+
start_date_suffix_for_yyyy = '-01-01T00:00:00.000Z'
|
210
|
+
start_date_suffix_for_yyyymm = '-01T01:00:00.000Z'
|
211
|
+
start_date_suffix_for_yyyymmdd = 'T00:00:00.000Z'
|
212
|
+
end_date_suffix_for_yyyy = '-12-31T23:59:59.999Z'
|
213
|
+
end_date_suffix_for_yyyymm = '-28T23:59:59.999Z' # TODO: end DD value should depend on MM value ('31' for Jan., '28' for Feb., etc.)
|
214
|
+
end_date_suffix_for_yyyymmdd = 'T23:59:59.999Z'
|
215
|
+
|
139
216
|
# dateOther
|
140
|
-
if self.descMetadata.date(0).date_other[0]
|
141
|
-
|
142
|
-
|
143
|
-
else
|
144
|
-
# TODO insert code for date_other values here
|
217
|
+
if self.descMetadata.date(0).date_other[0]
|
218
|
+
self.descMetadata.date(0).date_other.each do |date_other|
|
219
|
+
doc['note_date_tsim'] << date_other
|
145
220
|
end
|
146
221
|
end
|
147
222
|
|
@@ -151,8 +226,8 @@ module Bplmodels
|
|
151
226
|
#dateCreated
|
152
227
|
if self.descMetadata.date(0).dates_created[0]
|
153
228
|
self.descMetadata.date(0).dates_created.each_with_index do |date,index|
|
154
|
-
|
155
|
-
|
229
|
+
#FIXME: Has to add "date.present" and the when '' case for oai-test:h415pc718
|
230
|
+
if date.present?
|
156
231
|
case self.descMetadata.date(0).dates_created(index).point[0]
|
157
232
|
when nil, ''
|
158
233
|
dates_static << date
|
@@ -216,48 +291,63 @@ module Bplmodels
|
|
216
291
|
end
|
217
292
|
|
218
293
|
# set the date ranges for date-time fields and decade faceting
|
219
|
-
|
294
|
+
sorted_start_dates = (dates_static + dates_start).sort
|
295
|
+
earliest_date = sorted_start_dates[0]
|
220
296
|
date_facet_start = earliest_date[0..3].to_i
|
221
|
-
|
222
|
-
|
223
|
-
|
224
|
-
|
225
|
-
|
226
|
-
|
227
|
-
|
228
|
-
|
229
|
-
|
297
|
+
latest_date = dates_end.sort.reverse[0]
|
298
|
+
|
299
|
+
# set earliest date
|
300
|
+
if earliest_date =~ /[0-9]{4}[0-9-]*\z/ # rough date format matching
|
301
|
+
if earliest_date.length == 4
|
302
|
+
doc['date_start_dtsi'].append(earliest_date + start_date_suffix_for_yyyy)
|
303
|
+
elsif earliest_date.length == 7
|
304
|
+
doc['date_start_dtsi'].append(earliest_date + start_date_suffix_for_yyyymm)
|
305
|
+
elsif earliest_date.length > 11
|
306
|
+
doc['date_start_dtsi'].append(earliest_date)
|
307
|
+
else
|
308
|
+
doc['date_start_dtsi'].append(earliest_date + start_date_suffix_for_yyyymmdd)
|
309
|
+
end
|
230
310
|
end
|
231
311
|
|
232
|
-
|
233
|
-
|
312
|
+
# set latest date
|
313
|
+
if latest_date && latest_date =~ /[0-9]{4}[0-9-]*\z/
|
234
314
|
date_facet_end = latest_date[0..3].to_i
|
235
315
|
if latest_date.length == 4
|
236
|
-
doc['date_end_dtsi'].append(latest_date +
|
316
|
+
doc['date_end_dtsi'].append(latest_date + end_date_suffix_for_yyyy)
|
237
317
|
elsif latest_date.length == 7
|
238
|
-
|
239
|
-
# e.g., '31' for January, but '28' for February, etc.
|
240
|
-
doc['date_end_dtsi'].append(latest_date + '-28T23:59:59.999Z')
|
318
|
+
doc['date_end_dtsi'].append(latest_date + end_date_suffix_for_yyyymm)
|
241
319
|
elsif latest_date.length > 11
|
242
320
|
doc['date_end_dtsi'].append(latest_date)
|
243
321
|
else
|
244
|
-
doc['date_end_dtsi'].append(latest_date +
|
322
|
+
doc['date_end_dtsi'].append(latest_date + end_date_suffix_for_yyyymmdd)
|
245
323
|
end
|
246
324
|
else
|
247
325
|
date_facet_end = 0
|
326
|
+
latest_start_date = sorted_start_dates[-1]
|
327
|
+
if latest_start_date =~ /[0-9]{4}[0-9-]*\z/
|
328
|
+
if latest_start_date.length == 4
|
329
|
+
doc['date_end_dtsi'].append(latest_start_date + end_date_suffix_for_yyyy)
|
330
|
+
elsif latest_start_date.length == 7
|
331
|
+
doc['date_end_dtsi'].append(latest_start_date + end_date_suffix_for_yyyymm)
|
332
|
+
elsif latest_start_date.length > 11
|
333
|
+
doc['date_end_dtsi'].append(latest_start_date)
|
334
|
+
else
|
335
|
+
doc['date_end_dtsi'].append(latest_start_date + end_date_suffix_for_yyyymmdd)
|
336
|
+
end
|
337
|
+
end
|
248
338
|
end
|
249
339
|
|
250
340
|
# decade faceting
|
251
|
-
(
|
252
|
-
if (
|
341
|
+
(1100..2020).step(10) do |index|
|
342
|
+
if (date_facet_start >= index && date_facet_start < index+10) || (date_facet_end != -1 && index > date_facet_start && date_facet_end >= index)
|
253
343
|
doc['date_facet_ssim'].append(index.to_s + 's')
|
254
344
|
end
|
255
345
|
end
|
256
346
|
|
257
347
|
doc['date_facet_yearly_ssim'] = []
|
258
348
|
# yearly faceting
|
259
|
-
(
|
260
|
-
if (
|
349
|
+
(1100..2020).step(1) do |index|
|
350
|
+
if (date_facet_start >= index && date_facet_start < index+1) || (date_facet_end != -1 && index > date_facet_start && date_facet_end >= index)
|
261
351
|
doc['date_facet_yearly_ssim'].append(index.to_s + 's')
|
262
352
|
end
|
263
353
|
end
|
@@ -293,26 +383,48 @@ module Bplmodels
|
|
293
383
|
doc['identifier_local_barcode_tsim'] = self.descMetadata.local_barcode
|
294
384
|
doc['identifier_isbn_tsim'] = self.descMetadata.isbn
|
295
385
|
doc['identifier_lccn_tsim'] = self.descMetadata.lccn
|
386
|
+
doc['identifier_ia_id_ssi'] = self.descMetadata.ia_id
|
296
387
|
|
297
388
|
doc['identifier_ark_ssi'] = ''
|
298
389
|
|
299
390
|
doc['local_accession_id_tsim'] = self.descMetadata.local_accession[0].to_s
|
300
|
-
|
301
|
-
|
302
|
-
|
303
|
-
|
304
|
-
|
305
|
-
|
306
|
-
|
307
|
-
|
308
|
-
|
309
|
-
|
310
|
-
|
391
|
+
|
392
|
+
#Assign collection, admin, and institution labels
|
393
|
+
doc['collection_name_ssim'] = []
|
394
|
+
doc['collection_name_tsim'] = []
|
395
|
+
doc['collection_pid_ssm'] = []
|
396
|
+
|
397
|
+
object_institution_pid = nil
|
398
|
+
object_collections = self.relationships(:is_member_of_collection)
|
399
|
+
object_collections.each do |collection_ident|
|
400
|
+
solr_response_collection = ActiveFedora::Base.find_with_conditions("id"=>collection_ident.gsub('info:fedora/','')).first
|
401
|
+
doc['collection_name_ssim'] << solr_response_collection["label_ssim"].first.to_s
|
402
|
+
doc['collection_name_tsim'] << solr_response_collection["label_ssim"].first.to_s
|
403
|
+
doc['collection_pid_ssm'] << solr_response_collection["id"].to_s
|
404
|
+
|
405
|
+
if object_institution_pid.blank?
|
406
|
+
object_institution_pid = solr_response_collection['institution_pid_ssi']
|
407
|
+
solr_response_institution = ActiveFedora::Base.find_with_conditions("id"=>object_institution_pid).first
|
408
|
+
doc['institution_name_ssim'] = solr_response_institution["label_ssim"].first.to_s
|
409
|
+
doc['institution_name_tsim'] = solr_response_institution["label_ssim"].first.to_s
|
410
|
+
doc['institution_pid_ssi'] = solr_response_institution["id"].to_s
|
411
|
+
doc['institution_pid_si'] = solr_response_institution["id"].to_s
|
311
412
|
end
|
413
|
+
end
|
312
414
|
|
415
|
+
object_admin_set = self.relationships(:administrative_set).first
|
416
|
+
if object_admin_set.present?
|
417
|
+
solr_response_admin = ActiveFedora::Base.find_with_conditions("id"=>object_admin_set.gsub('info:fedora/','')).first
|
418
|
+
doc['admin_set_name_ssim'] = solr_response_admin["label_ssim"].first.to_s
|
419
|
+
doc['admin_set_name_tsim'] = solr_response_admin["label_ssim"].first.to_s
|
420
|
+
doc['admin_set_pid_ssm'] = solr_response_admin["id"].to_s
|
421
|
+
else
|
422
|
+
raise "Potential problem setting administrative set?"
|
313
423
|
end
|
314
424
|
|
315
425
|
|
426
|
+
|
427
|
+
|
316
428
|
#self.descMetadata.identifier_uri.each do |identifier|
|
317
429
|
#if idenfifier.include?("ark")
|
318
430
|
#doc['identifier_uri_ss'] = self.descMetadata.identifier_uri
|
@@ -333,6 +445,8 @@ module Bplmodels
|
|
333
445
|
|
334
446
|
doc['issuance_tsim'] = self.descMetadata.origin_info.issuance
|
335
447
|
|
448
|
+
doc['classification_tsim'] = self.descMetadata.classification
|
449
|
+
|
336
450
|
doc['lang_term_ssim'] = self.descMetadata.language.language_term
|
337
451
|
#doc['lang_val_uri_ssim'] = self.descMetadata.language.language_term.lang_val_uri
|
338
452
|
|
@@ -396,7 +510,7 @@ module Bplmodels
|
|
396
510
|
doc['name_personal_tsim'].append(self.descMetadata.mods(0).name(index).namePart[0])
|
397
511
|
end
|
398
512
|
if self.descMetadata.mods(0).name(index).role.length > 1
|
399
|
-
doc['name_personal_role_tsim'].append(self.descMetadata.mods(0).name(
|
513
|
+
doc['name_personal_role_tsim'].append(self.descMetadata.mods(0).name(index).role.join('||').gsub(/[\n]\s*/,''))
|
400
514
|
else
|
401
515
|
doc['name_personal_role_tsim'].append(self.descMetadata.mods(0).name(index).role.text[0])
|
402
516
|
end
|
@@ -411,7 +525,7 @@ module Bplmodels
|
|
411
525
|
doc['name_corporate_tsim'].append(corporate_name)
|
412
526
|
end
|
413
527
|
if self.descMetadata.mods(0).name(index).role.length > 1
|
414
|
-
doc['name_corporate_role_tsim'].append(self.descMetadata.mods(0).name(
|
528
|
+
doc['name_corporate_role_tsim'].append(self.descMetadata.mods(0).name(index).role.join('||').gsub(/[\n]\s*/,''))
|
415
529
|
else
|
416
530
|
doc['name_corporate_role_tsim'].append(self.descMetadata.mods(0).name(index).role.text[0])
|
417
531
|
end
|
@@ -423,7 +537,7 @@ module Bplmodels
|
|
423
537
|
doc['name_generic_tsim'].append(self.descMetadata.mods(0).name(index).namePart[0])
|
424
538
|
end
|
425
539
|
if self.descMetadata.mods(0).name(index).role.length > 1
|
426
|
-
doc['name_generic_role_tsim'].append(self.descMetadata.mods(0).name(
|
540
|
+
doc['name_generic_role_tsim'].append(self.descMetadata.mods(0).name(index).role.join('||').gsub(/[\n]\s*/,''))
|
427
541
|
else
|
428
542
|
doc['name_generic_role_tsim'].append(self.descMetadata.mods(0).name(index).role.text[0])
|
429
543
|
end
|
@@ -440,12 +554,12 @@ module Bplmodels
|
|
440
554
|
doc['digital_origin_ssi'] = self.descMetadata.physical_description(0).digital_origin[0]
|
441
555
|
doc['internet_media_type_ssim'] = self.descMetadata.physical_description(0).internet_media_type
|
442
556
|
|
443
|
-
doc['physical_location_ssim'] = self.descMetadata.item_location
|
444
|
-
doc['physical_location_tsim'] = self.descMetadata.item_location
|
557
|
+
doc['physical_location_ssim'] = self.descMetadata.item_location.physical_location
|
558
|
+
doc['physical_location_tsim'] = self.descMetadata.item_location.physical_location
|
445
559
|
|
446
|
-
doc['sub_location_tsim'] = self.descMetadata.item_location
|
560
|
+
doc['sub_location_tsim'] = self.descMetadata.item_location.holding_simple.copy_information.sub_location
|
447
561
|
|
448
|
-
doc['shelf_locator_tsim'] = self.descMetadata.item_location
|
562
|
+
doc['shelf_locator_tsim'] = self.descMetadata.item_location.holding_simple.copy_information.shelf_locator
|
449
563
|
|
450
564
|
doc['subject_topic_tsim'] = self.descMetadata.subject.topic
|
451
565
|
|
@@ -608,52 +722,6 @@ module Bplmodels
|
|
608
722
|
|
609
723
|
end
|
610
724
|
|
611
|
-
=begin
|
612
|
-
new_logger = Logger.new('log/geo_log')
|
613
|
-
new_logger.level = Logger::ERROR
|
614
|
-
|
615
|
-
#Blacklight-maps esque placename_coords
|
616
|
-
0.upto self.descMetadata.subject.length-1 do |subject_index|
|
617
|
-
if self.descMetadata.mods(0).subject(subject_index).cartographics.present? && self.descMetadata.mods(0).subject(subject_index).cartographics.scale.blank?
|
618
|
-
place_name = "Results"
|
619
|
-
|
620
|
-
if self.descMetadata.mods(0).subject(subject_index).authority == ['tgn'] && self.descMetadata.mods(0).subject(subject_index).hierarchical_geographic[0].blank?
|
621
|
-
new_logger.error "Weird Geography for: " + self.pid
|
622
|
-
end
|
623
|
-
|
624
|
-
if self.descMetadata.mods(0).subject(subject_index).authority == ['tgn'] && self.descMetadata.mods(0).subject(subject_index).hierarchical_geographic[0].present?
|
625
|
-
place_locations = []
|
626
|
-
self.descMetadata.mods(0).subject(subject_index).hierarchical_geographic[0].split("\n").each do |split_geo|
|
627
|
-
split_geo = split_geo.strip
|
628
|
-
place_locations << split_geo if split_geo.present? && !split_geo.include?('North and Central America') && !split_geo.include?('United States')
|
629
|
-
end
|
630
|
-
place_name = place_locations.reverse.join(', ')
|
631
|
-
elsif self.descMetadata.mods(0).subject(subject_index).geographic.present?
|
632
|
-
place_name = self.descMetadata.mods(0).subject(subject_index).geographic.first
|
633
|
-
end
|
634
|
-
|
635
|
-
doc['subject_blacklight_maps_ssim'] = "#{place_name}-|-#{self.descMetadata.mods(0).subject(subject_index).cartographics.coordinates[0].split(',').first}-|-#{self.descMetadata.mods(0).subject(subject_index).cartographics.coordinates[0].split(',').last}"
|
636
|
-
end
|
637
|
-
end
|
638
|
-
=end
|
639
|
-
#Blacklight-maps coords only
|
640
|
-
=begin
|
641
|
-
best_coords_found = false
|
642
|
-
0.upto self.descMetadata.subject.length-1 do |subject_index|
|
643
|
-
if self.descMetadata.mods(0).subject(subject_index).cartographics.present?
|
644
|
-
if self.descMetadata.mods(0).subject(subject_index).authority.present? && self.descMetadata.mods(0).subject(subject_index).authority != ['tgn']
|
645
|
-
best_coords_found = true
|
646
|
-
doc['subject_blacklight_maps_coords_ssim'] = self.descMetadata.mods(0).subject(subject_index).cartographics.coordinates[0]
|
647
|
-
end
|
648
|
-
end
|
649
|
-
end
|
650
|
-
0.upto self.descMetadata.subject.length-1 do |subject_index|
|
651
|
-
if self.descMetadata.mods(0).subject(subject_index).cartographics.present? && !best_coords_found
|
652
|
-
doc['subject_blacklight_maps_coords_ssim'] = self.descMetadata.mods(0).subject(subject_index).cartographics.coordinates[0]
|
653
|
-
end
|
654
|
-
end
|
655
|
-
=end
|
656
|
-
|
657
725
|
# name subjects
|
658
726
|
doc['subject_name_personal_tsim'] = []
|
659
727
|
doc['subject_name_corporate_tsim'] = []
|
@@ -687,59 +755,79 @@ module Bplmodels
|
|
687
755
|
|
688
756
|
end
|
689
757
|
|
690
|
-
#doc['subject_facet_ssim'] = self.descMetadata.subject.topic + self.descMetadata.subject.corporate_name.name_part + self.descMetadata.subject.personal_name.name_part
|
691
|
-
|
692
758
|
doc['subject_facet_ssim'].concat(self.descMetadata.subject.topic)
|
693
759
|
|
694
760
|
# temporal subjects
|
695
761
|
if self.descMetadata.subject.temporal.length > 0
|
762
|
+
|
696
763
|
doc['subject_temporal_start_tsim'] = []
|
697
764
|
doc['subject_temporal_start_dtsim'] = []
|
698
765
|
doc['subject_temporal_facet_ssim'] = []
|
766
|
+
doc['subject_temporal_end_tsim'] = []
|
767
|
+
doc['subject_temporal_end_dtsim'] = []
|
699
768
|
subject_date_range_start = []
|
700
769
|
subject_date_range_end = []
|
770
|
+
|
701
771
|
self.descMetadata.subject.temporal.each_with_index do |value,index|
|
702
772
|
if self.descMetadata.subject.temporal.point[index] != 'end'
|
703
|
-
|
704
|
-
|
705
|
-
|
706
|
-
|
707
|
-
|
708
|
-
doc['
|
709
|
-
elsif subject_temporal_start.length == 7
|
710
|
-
doc['subject_temporal_start_dtsim'].append(subject_temporal_start + '-01T01:00:00.000Z')
|
711
|
-
else
|
712
|
-
doc['subject_temporal_start_dtsim'].append(subject_temporal_start + 'T00:00:00.000Z')
|
773
|
+
doc['subject_temporal_start_tsim'] << value
|
774
|
+
subject_date_range_start << value
|
775
|
+
# if there is no accompanying end date, create nil value placeholders
|
776
|
+
unless self.descMetadata.subject.temporal.point[index+1] == 'end'
|
777
|
+
subject_date_range_end << nil
|
778
|
+
doc['subject_temporal_end_tsim'] << 'nil'
|
713
779
|
end
|
714
780
|
else
|
715
|
-
doc['subject_temporal_end_tsim']
|
716
|
-
|
717
|
-
subject_temporal_end = value
|
718
|
-
doc['subject_temporal_end_tsim'].append(subject_temporal_end)
|
719
|
-
subject_date_range_end.append(subject_temporal_end)
|
720
|
-
# subject_temporal_end.length > 4 ? subject_date_range_end.append(subject_temporal_end[0..3]) : subject_date_range_end.append(subject_temporal_end)
|
721
|
-
if subject_temporal_end.length == 4
|
722
|
-
doc['subject_temporal_end_dtsim'].append(subject_temporal_end + '-01-01T00:00:00.000Z')
|
723
|
-
elsif subject_temporal_end.length == 7
|
724
|
-
doc['subject_temporal_end_dtsim'].append(subject_temporal_end + '-01T01:00:00.000Z')
|
725
|
-
else
|
726
|
-
doc['subject_temporal_end_dtsim'].append(subject_temporal_end + 'T00:00:00.000Z')
|
727
|
-
end
|
781
|
+
doc['subject_temporal_end_tsim'] << value
|
782
|
+
subject_date_range_end << value
|
728
783
|
end
|
729
784
|
end
|
730
785
|
|
731
786
|
if subject_date_range_start.length > 0
|
732
787
|
subject_date_range_start.each_with_index do |date_start,index|
|
733
|
-
|
734
|
-
|
788
|
+
formatted_date_subject_start = false
|
789
|
+
formatted_date_subject_end = false
|
790
|
+
if date_start =~ /[0-9]{4}[0-9-]*\z/ # rough check for date formatting
|
791
|
+
formatted_date_subject_start = true
|
792
|
+
if date_start.length == 7
|
793
|
+
doc['subject_temporal_start_dtsim'] << date_start + start_date_suffix_for_yyyymm
|
794
|
+
elsif date_start.length == 10
|
795
|
+
doc['subject_temporal_start_dtsim'] << date_start + start_date_suffix_for_yyyymmdd
|
796
|
+
else
|
797
|
+
doc['subject_temporal_start_dtsim'] << date_start[0..3] + start_date_suffix_for_yyyy
|
798
|
+
end
|
799
|
+
end
|
800
|
+
if subject_date_range_end[index]
|
801
|
+
doc['subject_temporal_facet_ssim'] << date_start[0..3] + '-' + subject_date_range_end[index][0..3]
|
802
|
+
if formatted_date_subject_start
|
803
|
+
if subject_date_range_end[index] =~ /[0-9]{4}[0-9-]*\z/ # rough check for date formatting
|
804
|
+
formatted_date_subject_end = true
|
805
|
+
if subject_date_range_end[index].length == 7
|
806
|
+
doc['subject_temporal_end_dtsim'] << subject_date_range_end[index] + end_date_suffix_for_yyyymm
|
807
|
+
elsif subject_date_range_end[index].length == 10
|
808
|
+
doc['subject_temporal_end_dtsim'] << subject_date_range_end[index] + end_date_suffix_for_yyyymmdd
|
809
|
+
else
|
810
|
+
doc['subject_temporal_end_dtsim'] << subject_date_range_end[index][0..3] + end_date_suffix_for_yyyy
|
811
|
+
end
|
812
|
+
end
|
813
|
+
end
|
735
814
|
else
|
736
|
-
doc['subject_temporal_facet_ssim']
|
815
|
+
doc['subject_temporal_facet_ssim'] << date_start
|
816
|
+
end
|
817
|
+
if formatted_date_subject_start && !formatted_date_subject_end
|
818
|
+
if date_start.length == 7
|
819
|
+
doc['subject_temporal_end_dtsim'] << date_start + end_date_suffix_for_yyyymm
|
820
|
+
elsif date_start.length == 10
|
821
|
+
doc['subject_temporal_end_dtsim'] << date_start + end_date_suffix_for_yyyymmdd
|
822
|
+
else
|
823
|
+
doc['subject_temporal_end_dtsim'] << date_start[0..3] + end_date_suffix_for_yyyy
|
824
|
+
end
|
737
825
|
end
|
738
826
|
end
|
739
827
|
end
|
740
828
|
|
829
|
+
# add temporal subject values to subject facet field
|
741
830
|
doc['subject_facet_ssim'].concat(doc['subject_temporal_facet_ssim'])
|
742
|
-
|
743
831
|
end
|
744
832
|
|
745
833
|
# title subjects
|
@@ -762,7 +850,8 @@ module Bplmodels
|
|
762
850
|
if doc['subject_geo_nonhier_ssim'] && doc['subject_hiergeo_geojson_ssm']
|
763
851
|
doc['subject_geo_nonhier_ssim'].each do |non_hier_geo_subj|
|
764
852
|
doc['subject_hiergeo_geojson_ssm'].each do |hiergeo_geojson_feature|
|
765
|
-
if hiergeo_geojson_feature.match(/#{non_hier_geo_subj}/)
|
853
|
+
#if hiergeo_geojson_feature.match(/#{non_hier_geo_subj}/)
|
854
|
+
if hiergeo_geojson_feature.include?(non_hier_geo_subj)
|
766
855
|
doc['subject_geo_nonhier_ssim'].delete(non_hier_geo_subj)
|
767
856
|
end
|
768
857
|
end
|
@@ -786,12 +875,12 @@ module Bplmodels
|
|
786
875
|
|
787
876
|
doc['note_tsim'] = []
|
788
877
|
doc['note_resp_tsim'] = []
|
789
|
-
doc['note_date_tsim'] = []
|
790
878
|
doc['note_performers_tsim'] = []
|
791
879
|
doc['note_acquisition_tsim'] = []
|
792
880
|
doc['note_ownership_tsim'] = []
|
793
881
|
doc['note_citation_tsim'] = []
|
794
882
|
doc['note_reference_tsim'] = []
|
883
|
+
doc['note_physical_tsim'] = []
|
795
884
|
|
796
885
|
0.upto self.descMetadata.note.length-1 do |index|
|
797
886
|
if self.descMetadata.note(index).type_at.first == 'statement of responsibility'
|
@@ -813,11 +902,10 @@ module Bplmodels
|
|
813
902
|
end
|
814
903
|
end
|
815
904
|
|
816
|
-
|
817
905
|
0.upto self.descMetadata.physical_description.length-1 do |physical_index|
|
818
906
|
0.upto self.descMetadata.physical_description(physical_index).note.length-1 do |note_index|
|
819
907
|
if self.descMetadata.physical_description(physical_index).note(note_index).first != nil
|
820
|
-
doc['
|
908
|
+
doc['note_physical_tsim'].append(self.descMetadata.physical_description(physical_index).note(note_index).first)
|
821
909
|
end
|
822
910
|
end
|
823
911
|
end
|
@@ -833,12 +921,16 @@ module Bplmodels
|
|
833
921
|
if self.descMetadata.mods(0).title_info(index).display_label[0] == 'primary_display'
|
834
922
|
doc['title_info_primary_tsi'] = title_prefix + title_value
|
835
923
|
doc['title_info_primary_ssort'] = title_value
|
924
|
+
doc['title_info_partnum_tsi'] = self.descMetadata.mods(0).title_info(index).part_number
|
925
|
+
doc['title_info_partname_tsi'] = self.descMetadata.mods(0).title_info(index).part_name
|
836
926
|
else
|
837
927
|
doc['title_info_primary_trans_tsim'] << title_prefix + title_value
|
838
928
|
end
|
839
929
|
else
|
840
930
|
doc['title_info_primary_tsi'] = title_prefix + title_value
|
841
931
|
doc['title_info_primary_ssort'] = title_value
|
932
|
+
doc['title_info_partnum_tsi'] = self.descMetadata.mods(0).title_info(index).part_number
|
933
|
+
doc['title_info_partname_tsi'] = self.descMetadata.mods(0).title_info(index).part_name
|
842
934
|
end
|
843
935
|
if self.descMetadata.mods(0).title_info(index).supplied[0] == 'yes'
|
844
936
|
doc['supplied_title_bs'] = 'true'
|
@@ -858,11 +950,6 @@ module Bplmodels
|
|
858
950
|
|
859
951
|
doc['subtitle_tsim'] = self.descMetadata.title_info.subtitle
|
860
952
|
|
861
|
-
if self.collection
|
862
|
-
if self.collection.institutions
|
863
|
-
doc['institution_pid_si'] = self.collection.institutions.pid
|
864
|
-
end
|
865
|
-
end
|
866
953
|
|
867
954
|
if self.workflowMetadata
|
868
955
|
doc['workflow_state_ssi'] = self.workflowMetadata.item_status.state
|
@@ -875,6 +962,57 @@ module Bplmodels
|
|
875
962
|
}
|
876
963
|
end
|
877
964
|
|
965
|
+
=begin
|
966
|
+
ocr_text_normal = ''
|
967
|
+
ocr_text_squished = ''
|
968
|
+
ActiveFedora::Base.find_in_batches('is_image_of_ssim'=>"info:fedora/#{self.pid}") do |group|
|
969
|
+
group.each { |image_file|
|
970
|
+
if image_file['has_ocr_master_ssi'] == 'true'
|
971
|
+
ocr_text_normal += image_file['full_ocr_ssi']
|
972
|
+
ocr_text_squished += image_file['compressed_ocr_ssi']
|
973
|
+
end
|
974
|
+
|
975
|
+
}
|
976
|
+
end
|
977
|
+
|
978
|
+
doc['full_ocr_si'] = ocr_text_normal[0..10000] if ocr_text_normal.present?
|
979
|
+
doc['full_ocr_ssi'] = ocr_text_normal[0..10000] if ocr_text_normal.present?
|
980
|
+
doc['compressed_ocr_si'] = ocr_text_squished[0..10000] if ocr_text_squished.present?
|
981
|
+
doc['compressed_ocr_ssi'] = ocr_text_squished[0..10000] if ocr_text_squished.present?
|
982
|
+
=end
|
983
|
+
|
984
|
+
if self.plainText.present?
|
985
|
+
doc['ocr_tiv'] = self.plainText.content.squish
|
986
|
+
|
987
|
+
pages_ocr_check = Bplmodels::ImageFile.find_with_conditions({"is_image_of_ssim"=>"info:fedora/#{self.pid}","has_ocr_text_bsi"=>"true"}, rows: '1', fl: 'id,has_ocr_text_bsi' )
|
988
|
+
doc['has_searchable_text_bsi'] = true if pages_ocr_check.present?
|
989
|
+
end
|
990
|
+
|
991
|
+
if self.scanData.present?
|
992
|
+
scan_data_xml = Nokogiri::XML(self.scanData.content)
|
993
|
+
#See http://archive.org/download/handbookforkitch00neel (created in 2009) for a record lacking this
|
994
|
+
doc['text_direction_ssi'] = scan_data_xml.xpath("//globalHandedness/page-progression").first.text if scan_data_xml.xpath("//globalHandedness/page-progression").first.present?
|
995
|
+
end
|
996
|
+
|
997
|
+
#Handle the case of multiple volumes...
|
998
|
+
if self.class.name == 'Bplmodels::Book'
|
999
|
+
volume_check = Bplmodels::Finder.getVolumeObjects(self.pid)
|
1000
|
+
if volume_check.present?
|
1001
|
+
doc['ocr_tiv'] = ''
|
1002
|
+
volume_check.each do |volume|
|
1003
|
+
#FIXME!!!
|
1004
|
+
volume_object = ActiveFedora::Base.find(volume['id']).adapt_to_cmodel
|
1005
|
+
doc['ocr_tiv'] += volume_object.plainText.content.squish + ' ' if volume_object.plainText.present?
|
1006
|
+
end
|
1007
|
+
end
|
1008
|
+
end
|
1009
|
+
|
1010
|
+
|
1011
|
+
if self.workflowMetadata.volume_match_md5s.present?
|
1012
|
+
doc['marc_md5_sum_ssi'] = self.workflowMetadata.volume_match_md5s.marc.first
|
1013
|
+
doc['iaMeta_matcher_md5_ssi'] = self.workflowMetadata.volume_match_md5s.iaMeta.first
|
1014
|
+
end
|
1015
|
+
|
878
1016
|
if self.workflowMetadata.marked_for_deletion.present?
|
879
1017
|
doc['marked_for_deletion_bsi'] = self.workflowMetadata.marked_for_deletion.first
|
880
1018
|
doc['marked_for_deletion_reason_ssi'] = self.workflowMetadata.marked_for_deletion.reason.first
|
@@ -898,14 +1036,28 @@ module Bplmodels
|
|
898
1036
|
#local_id_type => type of that local ID
|
899
1037
|
#label => label of the object
|
900
1038
|
#institution_pid => instituional access of this file
|
1039
|
+
#secondary_parent_pids => optional array of additional parent pids
|
901
1040
|
def self.mint(args)
|
902
1041
|
|
1042
|
+
expected_aguments = [:parent_pid, :local_id, :local_id_type, :institution_pid, :secondary_parent_pids]
|
1043
|
+
expected_aguments.each do |arg|
|
1044
|
+
if !args.keys.include?(arg)
|
1045
|
+
raise "Mint called but missing parameter: #{arg}"
|
1046
|
+
end
|
1047
|
+
end
|
1048
|
+
|
903
1049
|
#TODO: Duplication check here to prevent over-writes?
|
904
1050
|
|
905
1051
|
args[:namespace_id] ||= ARK_CONFIG_GLOBAL['namespace_commonwealth_pid']
|
1052
|
+
args[:secondary_parent_pids] ||= []
|
906
1053
|
|
907
|
-
response = Typhoeus::Request.post(ARK_CONFIG_GLOBAL['url'] + "/arks.json", :params => {:ark=>{:parent_pid=>args[:parent_pid], :namespace_ark => ARK_CONFIG_GLOBAL['namespace_commonwealth_ark'], :namespace_id=>args[:namespace_id], :url_base => ARK_CONFIG_GLOBAL['ark_commonwealth_base'], :model_type => self.name, :local_original_identifier=>args[:local_id], :local_original_identifier_type=>args[:local_id_type]}})
|
908
|
-
|
1054
|
+
response = Typhoeus::Request.post(ARK_CONFIG_GLOBAL['url'] + "/arks.json", :params => {:ark=>{:parent_pid=>args[:parent_pid], :secondary_parent_pids=>args[:secondary_parent_pids], :namespace_ark => ARK_CONFIG_GLOBAL['namespace_commonwealth_ark'], :namespace_id=>args[:namespace_id], :url_base => ARK_CONFIG_GLOBAL['ark_commonwealth_base'], :model_type => self.name, :local_original_identifier=>args[:local_id], :local_original_identifier_type=>args[:local_id_type]}})
|
1055
|
+
|
1056
|
+
begin
|
1057
|
+
as_json = JSON.parse(response.body)
|
1058
|
+
rescue => ex
|
1059
|
+
raise('Error in JSON response for minting an object pid.')
|
1060
|
+
end
|
909
1061
|
|
910
1062
|
puts as_json['pid']
|
911
1063
|
|
@@ -926,6 +1078,12 @@ module Bplmodels
|
|
926
1078
|
object = self.new(:pid=>as_json["pid"])
|
927
1079
|
|
928
1080
|
object.add_relationship(:is_member_of_collection, "info:fedora/" + args[:parent_pid])
|
1081
|
+
object.add_relationship(:administrative_set, "info:fedora/" + args[:parent_pid])
|
1082
|
+
|
1083
|
+
args[:secondary_parent_pids].each do |other_collection_pid|
|
1084
|
+
object.add_relationship(:is_member_of_collection, "info:fedora/" + other_collection_pid)
|
1085
|
+
end
|
1086
|
+
|
929
1087
|
object.add_oai_relationships
|
930
1088
|
|
931
1089
|
object.label = args[:label] if args[:label].present?
|
@@ -952,41 +1110,121 @@ module Bplmodels
|
|
952
1110
|
return ARK_CONFIG_GLOBAL['url'] + '/ark:/' + ARK_CONFIG_GLOBAL["namespace_commonwealth_ark"].to_s + "/" + self.pid.split(':').last.to_s
|
953
1111
|
end
|
954
1112
|
|
1113
|
+
def insert_marc(file_content)
|
1114
|
+
self.marc.content = file_content
|
1115
|
+
self.marc.mimeType = 'application/marc'
|
1116
|
+
end
|
1117
|
+
|
1118
|
+
def insert_marc_xml(file_content)
|
1119
|
+
self.marcXML.content = file_content
|
1120
|
+
self.marcXML.mimeType = 'application/xml'
|
1121
|
+
end
|
1122
|
+
|
1123
|
+
def insert_ia_meta(file_content)
|
1124
|
+
self.iaMeta.content = file_content
|
1125
|
+
self.iaMeta.mimeType = 'application/xml'
|
1126
|
+
end
|
1127
|
+
|
1128
|
+
def insert_scan_data(file_content)
|
1129
|
+
self.scanData.content = file_content
|
1130
|
+
self.scanData.mimeType = 'application/xml'
|
1131
|
+
end
|
1132
|
+
|
1133
|
+
def insert_plain_text(file_content)
|
1134
|
+
self.plainText.content = file_content
|
1135
|
+
self.plainText.mimeType = 'text/plain'
|
1136
|
+
end
|
1137
|
+
|
1138
|
+
def insert_djvu_xml(file_content)
|
1139
|
+
self.djvuXML.content = file_content
|
1140
|
+
self.djvuXML.mimeType = 'application/xml'
|
1141
|
+
end
|
1142
|
+
|
1143
|
+
def insert_abbyy(file_content)
|
1144
|
+
self.abbyy.content = file_content
|
1145
|
+
self.abbyy.mimeType = 'application/xml'
|
1146
|
+
end
|
1147
|
+
|
1148
|
+
def simple_insert_file(file_path, file_name, ingest_source, institution_pid, original_file_location=nil, set_exemplary=nil)
|
1149
|
+
files_hash = []
|
1150
|
+
file_hash = {}
|
1151
|
+
file_hash[:datastream] = 'productionMaster'
|
1152
|
+
file_hash[:file_path] = file_path
|
1153
|
+
file_hash[:file_name] = file_name
|
1154
|
+
file_hash[:original_file_location] = original_file_location
|
1155
|
+
files_hash << file_hash
|
1156
|
+
|
1157
|
+
insert_new_file(files_hash, ingest_source, institution_pid, set_exemplary)
|
1158
|
+
end
|
1159
|
+
|
955
1160
|
# Expects a hash of the following keys
|
956
1161
|
# :file_path -> The path to the file
|
957
1162
|
# :datastream -> The datastream for the file
|
958
1163
|
# :file_name -> The name of the file
|
959
|
-
def insert_new_file(files_hash, file_ingest_source, institution_pid)
|
1164
|
+
def insert_new_file(files_hash, file_ingest_source, institution_pid, set_exemplary=nil)
|
960
1165
|
puts files_hash.to_s
|
961
1166
|
|
962
1167
|
raise 'Missing insert_new_file params' if files_hash.first[:file_path].blank? || files_hash.first[:datastream].blank? || files_hash.first[:file_name].blank?
|
963
1168
|
|
964
1169
|
production_master = files_hash.select{ |hash| hash[:datastream] == 'productionMaster' }.first
|
965
1170
|
|
966
|
-
if production_master[:file_name].include?('.tif')
|
1171
|
+
if production_master[:file_name].downcase.include?('.tif')
|
967
1172
|
self.descMetadata.insert_media_type('image/tiff')
|
968
1173
|
self.descMetadata.insert_media_type('image/jpeg')
|
969
1174
|
self.descMetadata.insert_media_type('image/jp2')
|
970
|
-
self.insert_new_image_file(files_hash, institution_pid)
|
971
|
-
elsif production_master[:file_name].include?('.
|
1175
|
+
inserted_obj = self.insert_new_image_file(files_hash, institution_pid,set_exemplary)
|
1176
|
+
elsif production_master[:file_name].downcase.include?('.jp2')
|
1177
|
+
self.descMetadata.insert_media_type('image/jpeg')
|
1178
|
+
self.descMetadata.insert_media_type('image/jp2')
|
1179
|
+
inserted_obj = self.insert_new_image_file(files_hash, institution_pid,set_exemplary)
|
1180
|
+
elsif production_master[:file_name].downcase.include?('.png')
|
1181
|
+
self.descMetadata.insert_media_type('image/png')
|
1182
|
+
self.descMetadata.insert_media_type('image/jpeg')
|
1183
|
+
self.descMetadata.insert_media_type('image/jp2')
|
1184
|
+
inserted_obj = self.insert_new_image_file(files_hash, institution_pid,set_exemplary)
|
1185
|
+
elsif production_master[:file_name].downcase.include?('.mp3')
|
972
1186
|
self.descMetadata.insert_media_type('audio/mpeg')
|
973
|
-
self.insert_new_audio_file(files_hash, institution_pid)
|
974
|
-
elsif production_master[:file_name].include?('.
|
1187
|
+
inserted_obj = self.insert_new_audio_file(files_hash, institution_pid)
|
1188
|
+
elsif production_master[:file_name].downcase.include?('.wav')
|
1189
|
+
self.descMetadata.insert_media_type('audio/x-wav')
|
1190
|
+
inserted_obj = self.insert_new_audio_file(files_hash, institution_pid)
|
1191
|
+
elsif production_master[:file_name].downcase.include?('.aif')
|
1192
|
+
self.descMetadata.insert_media_type('audio/x-aiff')
|
1193
|
+
inserted_obj = self.insert_new_audio_file(files_hash, institution_pid)
|
1194
|
+
elsif production_master[:file_name].downcase.include?('.pdf')
|
975
1195
|
self.descMetadata.insert_media_type('application/pdf')
|
976
|
-
|
1196
|
+
ocr_preproduction_master = files_hash.select{ |hash| hash[:datastream] == 'preProductionNegativeMaster' }.first
|
1197
|
+
=begin
|
1198
|
+
if ocr_preproduction_master.present?
|
1199
|
+
self.descMetadata.insert_media_type('application/vnd.openxmlformats-officedocument.wordprocessingml.document')
|
1200
|
+
end
|
1201
|
+
=end
|
1202
|
+
inserted_obj = self.insert_new_document_file(files_hash, institution_pid,set_exemplary)
|
1203
|
+
elsif production_master[:file_name].downcase.include?('.epub')
|
1204
|
+
self.descMetadata.insert_media_type('application/epub+zip')
|
1205
|
+
inserted_obj = self.insert_new_ereader_file(files_hash, institution_pid)
|
1206
|
+
elsif production_master[:file_name].downcase.include?('.mobi')
|
1207
|
+
self.descMetadata.insert_media_type('application/x-mobipocket-ebook')
|
1208
|
+
inserted_obj = self.insert_new_ereader_file(files_hash, institution_pid)
|
1209
|
+
elsif production_master[:file_name].downcase.include?('daisy.zip')
|
1210
|
+
self.descMetadata.insert_media_type('application/zip')
|
1211
|
+
inserted_obj = self.insert_new_ereader_file(files_hash, institution_pid)
|
977
1212
|
else
|
978
1213
|
self.descMetadata.insert_media_type('image/jpeg')
|
979
1214
|
self.descMetadata.insert_media_type('image/jp2')
|
980
|
-
self.insert_new_image_file(files_hash, institution_pid)
|
1215
|
+
inserted_obj = self.insert_new_image_file(files_hash, institution_pid,set_exemplary)
|
981
1216
|
end
|
982
1217
|
|
983
|
-
self.workflowMetadata.item_source.ingest_origin = file_ingest_source
|
1218
|
+
self.workflowMetadata.item_source.ingest_origin = file_ingest_source if self.workflowMetadata.item_source.ingest_origin.blank?
|
984
1219
|
files_hash.each do |file|
|
985
|
-
|
1220
|
+
original_file_location = file[:original_file_location]
|
1221
|
+
original_file_location ||= file[:file_path]
|
1222
|
+
self.workflowMetadata.insert_file_source(original_file_location,file[:file_name],file[:datastream])
|
986
1223
|
end
|
1224
|
+
inserted_obj
|
987
1225
|
end
|
988
1226
|
|
989
|
-
def insert_new_image_file(files_hash, institution_pid)
|
1227
|
+
def insert_new_image_file(files_hash, institution_pid, set_exemplary)
|
990
1228
|
#raise 'insert new image called with no files or more than one!' if file.blank? || file.is_a?(Array)
|
991
1229
|
|
992
1230
|
puts 'processing image of: ' + self.pid.to_s + ' with file_hash: ' + files_hash.to_s
|
@@ -1002,7 +1240,8 @@ module Bplmodels
|
|
1002
1240
|
if image_file.is_a?(String)
|
1003
1241
|
#Bplmodels::ImageFile.find(last_image_file).delete
|
1004
1242
|
#last_image_file = Bplmodels::ImageFile.mint(:parent_pid=>self.pid, :local_id=>final_file_name, :local_id_type=>'File Name', :label=>final_file_name, :institution_pid=>institution_pid)
|
1005
|
-
return true
|
1243
|
+
#return true
|
1244
|
+
return Bplmodels::ImageFile.find(image_file)
|
1006
1245
|
end
|
1007
1246
|
|
1008
1247
|
files_hash.each_with_index do |file, file_index|
|
@@ -1015,175 +1254,359 @@ module Bplmodels
|
|
1015
1254
|
image_file.send(datastream).mimeType = 'image/tiff'
|
1016
1255
|
elsif file[:file_name].split('.').last.downcase == 'jpg'
|
1017
1256
|
image_file.send(datastream).mimeType = 'image/jpeg'
|
1257
|
+
elsif file[:file_name].split('.').last.downcase == 'jp2'
|
1258
|
+
image_file.send(datastream).mimeType = 'image/jp2'
|
1259
|
+
elsif file[:file_name].split('.').last.downcase == 'png'
|
1260
|
+
image_file.send(datastream).mimeType = 'image/png'
|
1261
|
+
elsif file[:file_name].split('.').last.downcase == 'txt'
|
1262
|
+
image_file.send(datastream).mimeType = 'text/plain'
|
1018
1263
|
else
|
1019
|
-
image_file.send(datastream).mimeType = 'image/jpeg'
|
1264
|
+
#image_file.send(datastream).mimeType = 'image/jpeg'
|
1265
|
+
raise "Could not find a mimeType for #{file[:file_name].split('.').last.downcase}"
|
1020
1266
|
end
|
1021
1267
|
|
1022
|
-
image_file.send(datastream).dsLabel = file[:file_name].gsub(
|
1268
|
+
image_file.send(datastream).dsLabel = file[:file_name].gsub(/\.(tif|TIF|jpg|JPG|jpeg|JPEG|jp2|JP2|png|PNG|txt|TXT)$/, '')
|
1023
1269
|
|
1024
1270
|
#FIXME!!!
|
1025
|
-
|
1271
|
+
original_file_location = file[:original_file_location]
|
1272
|
+
original_file_location ||= file[:file_path]
|
1273
|
+
image_file.workflowMetadata.insert_file_source(original_file_location,file[:file_name],datastream)
|
1026
1274
|
image_file.workflowMetadata.item_status.state = "published"
|
1027
1275
|
image_file.workflowMetadata.item_status.state_comment = "Added via the ingest image object base method on " + Time.new.year.to_s + "/" + Time.new.month.to_s + "/" + Time.new.day.to_s
|
1028
1276
|
|
1029
1277
|
|
1030
1278
|
end
|
1031
1279
|
|
1032
|
-
|
1033
1280
|
other_images_exist = false
|
1034
1281
|
Bplmodels::ImageFile.find_in_batches('is_image_of_ssim'=>"info:fedora/#{self.pid}", 'is_preceding_image_of_ssim'=>'') do |group|
|
1035
1282
|
group.each { |image_id|
|
1036
|
-
other_images_exist
|
1037
|
-
|
1038
|
-
|
1039
|
-
|
1040
|
-
|
1283
|
+
if other_images_exist
|
1284
|
+
raise 'This object has an error... likely was interupted during a previous ingest so multiple starting files. Pid: ' + self.pid
|
1285
|
+
else
|
1286
|
+
other_images_exist = true
|
1287
|
+
preceding_image = Bplmodels::ImageFile.find(image_id['id'])
|
1288
|
+
preceding_image.add_relationship(:is_preceding_image_of, "info:fedora/#{image_file.pid}", true)
|
1289
|
+
preceding_image.save
|
1290
|
+
image_file.add_relationship(:is_following_image_of, "info:fedora/#{image_id['id']}", true)
|
1291
|
+
end
|
1292
|
+
|
1041
1293
|
}
|
1042
1294
|
end
|
1043
1295
|
|
1044
1296
|
image_file.add_relationship(:is_image_of, "info:fedora/" + self.pid)
|
1045
1297
|
image_file.add_relationship(:is_file_of, "info:fedora/" + self.pid)
|
1046
|
-
|
1298
|
+
|
1299
|
+
if set_exemplary.nil? || set_exemplary
|
1300
|
+
if ActiveFedora::Base.find_with_conditions("is_exemplary_image_of_ssim"=>"info:fedora/#{self.pid}").blank?
|
1301
|
+
image_file.add_relationship(:is_exemplary_image_of, "info:fedora/" + self.pid)
|
1302
|
+
end
|
1303
|
+
end
|
1304
|
+
|
1047
1305
|
|
1048
1306
|
image_file.save
|
1049
1307
|
|
1050
1308
|
image_file
|
1051
1309
|
end
|
1052
1310
|
|
1053
|
-
|
1054
|
-
|
1055
|
-
|
1311
|
+
def insert_new_ereader_file(files_hash, institution_pid)
|
1312
|
+
puts 'processing ereader of: ' + self.pid.to_s + ' with file_hash: ' + files_hash.to_s
|
1313
|
+
|
1314
|
+
production_master = files_hash.select{ |hash| hash[:datastream] == 'productionMaster' }.first
|
1315
|
+
|
1316
|
+
epub_file = Bplmodels::EreaderFile.mint(:parent_pid=>self.pid, :local_id=>production_master[:file_name], :local_id_type=>'File Name', :label=>production_master[:file_name], :institution_pid=>institution_pid)
|
1317
|
+
|
1318
|
+
if epub_file.is_a?(String)
|
1319
|
+
#Bplmodels::ImageFile.find(last_image_file).delete
|
1320
|
+
#last_image_file = Bplmodels::ImageFile.mint(:parent_pid=>self.pid, :local_id=>final_file_name, :local_id_type=>'File Name', :label=>final_file_name, :institution_pid=>institution_pid)
|
1321
|
+
#return true
|
1322
|
+
return Bplmodels::EreaderFile.find(epub_file)
|
1323
|
+
end
|
1324
|
+
|
1325
|
+
files_hash.each_with_index do |file, file_index|
|
1326
|
+
datastream = file[:datastream]
|
1327
|
+
|
1328
|
+
|
1329
|
+
epub_file.send(datastream).content = ::File.open(file[:file_path])
|
1330
|
+
|
1331
|
+
if file[:file_name].split('.').last.downcase == 'epub'
|
1332
|
+
epub_file.send(datastream).mimeType = 'application/epub+zip'
|
1333
|
+
elsif file[:file_name].split('.').last.downcase == 'mobi'
|
1334
|
+
epub_file.send(datastream).mimeType = 'application/x-mobipocket-ebook'
|
1335
|
+
elsif file[:file_name].split('.').last.downcase == 'zip'
|
1336
|
+
epub_file.send(datastream).mimeType = 'application/zip'
|
1337
|
+
elsif file[:file_name].split('.').last.downcase == 'txt'
|
1338
|
+
epub_file.send(datastream).mimeType = 'text/plain'
|
1339
|
+
else
|
1340
|
+
epub_file.send(datastream).mimeType = 'application/epub+zip'
|
1341
|
+
end
|
1342
|
+
|
1343
|
+
epub_file.send(datastream).dsLabel = file[:file_name].gsub(/\.(epub|EPUB|mobi|MOBI|zip|ZIP|txt|TXT)$/, '')
|
1344
|
+
|
1345
|
+
#FIXME!!!
|
1346
|
+
original_file_location = file[:original_file_location]
|
1347
|
+
original_file_location ||= file[:file_path]
|
1348
|
+
epub_file.workflowMetadata.insert_file_source(original_file_location,file[:file_name],datastream)
|
1349
|
+
epub_file.workflowMetadata.item_status.state = "published"
|
1350
|
+
epub_file.workflowMetadata.item_status.state_comment = "Added via the ingest image object base method on " + Time.new.year.to_s + "/" + Time.new.month.to_s + "/" + Time.new.day.to_s
|
1351
|
+
|
1056
1352
|
|
1057
|
-
uri_file_part = audio_file
|
1058
|
-
#Fix common url errors
|
1059
|
-
if uri_file_part.match(/^http/)
|
1060
|
-
#uri_file_part = uri_file_part.gsub(' ', '%20')
|
1061
|
-
uri_file_part = URI::escape(uri_file_part)
|
1062
1353
|
end
|
1063
1354
|
|
1064
|
-
|
1065
|
-
|
1066
|
-
|
1067
|
-
|
1068
|
-
|
1355
|
+
|
1356
|
+
Bplmodels::EreaderFile.find_in_batches('is_ereader_of_ssim'=>"info:fedora/#{self.pid}", 'is_preceding_ereader_of_ssim'=>'') do |group|
|
1357
|
+
group.each { |ereader_id|
|
1358
|
+
other_images_exist = true
|
1359
|
+
preceding_ereader = Bplmodels::EreaderFile.find(ereader_id['id'])
|
1360
|
+
preceding_ereader.add_relationship(:is_preceding_ereader_of, "info:fedora/#{epub_file.pid}", true)
|
1361
|
+
preceding_ereader.save
|
1362
|
+
epub_file.add_relationship(:is_following_ereader_of, "info:fedora/#{ereader_id['id']}", true)
|
1363
|
+
}
|
1069
1364
|
end
|
1070
1365
|
|
1366
|
+
epub_file.add_relationship(:is_ereader_of, "info:fedora/" + self.pid)
|
1367
|
+
epub_file.add_relationship(:is_file_of, "info:fedora/" + self.pid)
|
1071
1368
|
|
1072
|
-
|
1073
|
-
|
1074
|
-
|
1075
|
-
|
1076
|
-
|
1369
|
+
epub_file.save
|
1370
|
+
|
1371
|
+
epub_file
|
1372
|
+
end
|
1373
|
+
|
1374
|
+
def insert_new_audio_file(files_hash, institution_pid, set_exemplary=false)
|
1375
|
+
production_master = files_hash.select{ |hash| hash[:datastream] == 'productionMaster' }.first
|
1376
|
+
audio_file = Bplmodels::AudioFile.mint(:parent_pid=>self.pid, :local_id=>production_master[:file_name], :local_id_type=>'File Name', :label=>production_master[:file_name], :institution_pid=>institution_pid)
|
1377
|
+
|
1378
|
+
if audio_file.is_a?(String)
|
1379
|
+
#Bplmodels::ImageFile.find(last_image_file).delete
|
1380
|
+
#last_image_file = Bplmodels::ImageFile.mint(:parent_pid=>self.pid, :local_id=>final_file_name, :local_id_type=>'File Name', :label=>final_file_name, :institution_pid=>institution_pid)
|
1381
|
+
#return true
|
1382
|
+
return Bplmodels::AudioFile.find(image_file)
|
1077
1383
|
end
|
1078
1384
|
|
1385
|
+
files_hash.each_with_index do |file, file_index|
|
1386
|
+
datastream = file[:datastream]
|
1387
|
+
|
1388
|
+
|
1389
|
+
audio_file.send(datastream).content = ::File.open(file[:file_path])
|
1390
|
+
|
1391
|
+
if file[:file_name].split('.').last.downcase == 'mp3'
|
1392
|
+
audio_file.send(datastream).mimeType = 'audio/mpeg'
|
1393
|
+
elsif file[:file_name].split('.').last.downcase == 'wav'
|
1394
|
+
audio_file.send(datastream).mimeType = 'audio/x-wav'
|
1395
|
+
elsif file[:file_name].split('.').last.downcase == 'aif'
|
1396
|
+
audio_file.send(datastream).mimeType = 'audio/x-aiff'
|
1397
|
+
elsif file[:file_name].split('.').last.downcase == 'txt'
|
1398
|
+
audio_file.send(datastream).mimeType = 'text/plain'
|
1399
|
+
else
|
1400
|
+
raise "Could not find a mimeType for #{file[:file_name].split('.').last.downcase}"
|
1401
|
+
end
|
1402
|
+
|
1403
|
+
audio_file.send(datastream).dsLabel = file[:file_name].gsub(/\.(mp3|MP3|wav|WAV|aif|AIF|txt|TXT)$/, '')
|
1404
|
+
|
1405
|
+
#FIXME!!!
|
1406
|
+
original_file_location = file[:original_file_location]
|
1407
|
+
original_file_location ||= file[:file_path]
|
1408
|
+
audio_file.workflowMetadata.insert_file_source(original_file_location,file[:file_name],datastream)
|
1409
|
+
audio_file.workflowMetadata.item_status.state = "published"
|
1410
|
+
audio_file.workflowMetadata.item_status.state_comment = "Added via the ingest image object base method on " + Time.new.year.to_s + "/" + Time.new.month.to_s + "/" + Time.new.day.to_s
|
1411
|
+
|
1412
|
+
|
1413
|
+
end
|
1079
1414
|
|
1080
1415
|
other_audio_exist = false
|
1081
1416
|
Bplmodels::AudioFile.find_in_batches('is_audio_of_ssim'=>"info:fedora/#{self.pid}", 'is_preceding_audio_of_ssim'=>'') do |group|
|
1082
1417
|
group.each { |audio|
|
1083
|
-
other_audio_exist
|
1084
|
-
|
1085
|
-
|
1086
|
-
|
1087
|
-
|
1418
|
+
if other_audio_exist
|
1419
|
+
raise 'This object has an error... likely was interupted during a previous ingest so multiple starting files. Pid: ' + self.pid
|
1420
|
+
else
|
1421
|
+
other_images_exist = true
|
1422
|
+
preceding_audio = Bplmodels::AudioFile.find(audio['id'])
|
1423
|
+
preceding_audio.add_relationship(:is_preceding_image_of, "info:fedora/#{audio_file.pid}", true)
|
1424
|
+
preceding_audio.save
|
1425
|
+
audio_file.add_relationship(:is_following_image_of, "info:fedora/#{audio['id']}", true)
|
1426
|
+
end
|
1427
|
+
|
1088
1428
|
}
|
1089
1429
|
end
|
1090
1430
|
|
1091
|
-
|
1092
|
-
|
1093
|
-
|
1094
|
-
current_audio_file.workflowMetadata.insert_file_path(audio_file)
|
1095
|
-
current_audio_file.workflowMetadata.insert_file_name(final_audio_name)
|
1096
|
-
current_audio_file.workflowMetadata.item_status.state = "published"
|
1097
|
-
current_audio_file.workflowMetadata.item_status.state_comment = "Added via the ingest audio object base method on " + Time.new.year.to_s + "/" + Time.new.month.to_s + "/" + Time.new.day.to_s
|
1431
|
+
audio_file.add_relationship(:is_audio_of, "info:fedora/" + self.pid)
|
1432
|
+
audio_file.add_relationship(:is_file_of, "info:fedora/" + self.pid)
|
1098
1433
|
|
1099
|
-
|
1434
|
+
audio_file.save
|
1100
1435
|
|
1101
|
-
|
1436
|
+
audio_file
|
1102
1437
|
end
|
1103
1438
|
|
1104
|
-
|
1105
|
-
|
1106
|
-
def insert_new_document_file(document_file, institution_pid)
|
1107
|
-
raise 'document file missing!' if document_file.blank?
|
1108
|
-
|
1109
|
-
puts 'processing document of: ' + self.pid.to_s + ' with file: ' + document_file
|
1110
|
-
|
1111
|
-
uri_file_part = document_file
|
1439
|
+
def insert_new_document_file(files_hash, institution_pid, set_exemplary)
|
1440
|
+
production_master = files_hash.select{ |hash| hash[:datastream] == 'productionMaster' }.first
|
1112
1441
|
|
1442
|
+
#uri_file_part = file
|
1113
1443
|
#Fix common url errors
|
1114
|
-
if uri_file_part.match(/^http/)
|
1115
|
-
#uri_file_part = uri_file_part.gsub(' ', '%20')
|
1116
|
-
uri_file_part = URI::escape(uri_file_part)
|
1117
|
-
end
|
1444
|
+
#uri_file_part = URI::escape(uri_file_part) if uri_file_part.match(/^http/)
|
1118
1445
|
|
1119
|
-
|
1120
|
-
|
1121
|
-
if
|
1122
|
-
Bplmodels::
|
1123
|
-
|
1446
|
+
document_file = Bplmodels::DocumentFile.mint(:parent_pid=>self.pid, :local_id=>production_master[:file_name], :local_id_type=>'File Name', :label=>production_master[:file_name], :institution_pid=>institution_pid)
|
1447
|
+
|
1448
|
+
if document_file.is_a?(String)
|
1449
|
+
#Bplmodels::ImageFile.find(last_image_file).delete
|
1450
|
+
#last_image_file = Bplmodels::ImageFile.mint(:parent_pid=>self.pid, :local_id=>final_file_name, :local_id_type=>'File Name', :label=>final_file_name, :institution_pid=>institution_pid)
|
1124
1451
|
#return true
|
1452
|
+
return Bplmodels::DocumentFile.find(document_file)
|
1125
1453
|
end
|
1126
1454
|
|
1127
|
-
|
1128
|
-
|
1129
|
-
current_document_file.productionMaster.mimeType = 'application/pdf'
|
1130
|
-
else
|
1131
|
-
current_document_file.productionMaster.mimeType = 'application/pdf'
|
1132
|
-
end
|
1455
|
+
files_hash.each_with_index do |file, file_index|
|
1456
|
+
datastream = file[:datastream]
|
1133
1457
|
|
1134
|
-
|
1135
|
-
|
1136
|
-
|
1137
|
-
|
1138
|
-
|
1139
|
-
|
1140
|
-
}.first
|
1141
|
-
total_colors = img.total_colors
|
1142
|
-
current_page = current_page + 1
|
1143
|
-
end
|
1458
|
+
#Fix common url errors
|
1459
|
+
if file[:file_path].match(/^http/)
|
1460
|
+
document_file.send(datastream).content = ::File.open(URI::escape(file[:file_path]))
|
1461
|
+
else
|
1462
|
+
document_file.send(datastream).content = ::File.open(file[:file_path])
|
1463
|
+
end
|
1144
1464
|
|
1145
|
-
#This is horrible. But if you don't do this, some PDF files won't come out right at all.
|
1146
|
-
#Multiple attempts have failed to fix this but perhaps the bug will be patched in ImageMagick.
|
1147
|
-
#To duplicate, one can use the PDF files at: http://libspace.uml.edu/omeka/files/original/7ecb4dc9579b11e2b53ccc2040e58d36.pdf
|
1148
|
-
img = Magick::Image.from_blob( img.to_blob { self.format = "jpg" } ).first
|
1149
1465
|
|
1150
|
-
|
1466
|
+
if file[:file_name].split('.').last.downcase == 'pdf'
|
1467
|
+
document_file.send(datastream).mimeType = 'application/pdf'
|
1468
|
+
elsif file[:file_name].split('.').last.downcase == 'docx'
|
1469
|
+
document_file.send(datastream).mimeType = 'application/vnd.openxmlformats-officedocument.wordprocessingml.document'
|
1470
|
+
elsif file[:file_name].split('.').last.downcase == 'doc'
|
1471
|
+
document_file.send(datastream).mimeType = 'application/msword'
|
1472
|
+
elsif file[:file_name].split('.').last.downcase == 'txt'
|
1473
|
+
document_file.send(datastream).mimeType = 'text/plain'
|
1474
|
+
else
|
1475
|
+
raise "Could not find a mimeType for #{file[:file_name].split('.').last.downcase}"
|
1476
|
+
end
|
1477
|
+
|
1478
|
+
document_file.send(datastream).dsLabel = file[:file_name].gsub(/\.(pdf|PDF|docx|DOCX|doc|DOC|txt|TXT)$/, '')
|
1479
|
+
|
1480
|
+
#FIXME!!!
|
1481
|
+
original_file_location = file[:original_file_location]
|
1482
|
+
original_file_location ||= file[:file_path]
|
1483
|
+
document_file.workflowMetadata.insert_file_source(original_file_location,file[:file_name],datastream)
|
1484
|
+
document_file.workflowMetadata.item_status.state = "published"
|
1485
|
+
document_file.workflowMetadata.item_status.state_comment = "Added via the ingest document object base method on " + Time.new.year.to_s + "/" + Time.new.month.to_s + "/" + Time.new.day.to_s
|
1486
|
+
|
1487
|
+
|
1488
|
+
end
|
1151
1489
|
|
1152
|
-
current_document_file.thumbnail300.content = thumb.to_blob { self.format = "jpg" }
|
1153
|
-
current_document_file.thumbnail300.mimeType = 'image/jpeg'
|
1154
1490
|
|
1155
1491
|
Bplmodels::DocumentFile.find_in_batches('is_document_of_ssim'=>"info:fedora/#{self.pid}", 'is_preceding_document_of_ssim'=>'') do |group|
|
1156
|
-
group.each { |
|
1157
|
-
|
1158
|
-
preceding_document
|
1159
|
-
preceding_document.add_relationship(:is_preceding_document_of, "info:fedora/#{current_document_file.pid}", true)
|
1492
|
+
group.each { |document_id|
|
1493
|
+
preceding_document = Bplmodels::DocumentFile.find(document_id['id'])
|
1494
|
+
preceding_document.add_relationship(:is_preceding_document_of, "info:fedora/#{document_file.pid}", true)
|
1160
1495
|
preceding_document.save
|
1161
|
-
|
1496
|
+
preceding_document.add_relationship(:is_following_document_of, "info:fedora/#{document_id['id']}", true)
|
1162
1497
|
}
|
1163
1498
|
end
|
1164
1499
|
|
1165
|
-
|
1166
|
-
|
1167
|
-
|
1168
|
-
|
1169
|
-
|
1170
|
-
|
1500
|
+
document_file.add_relationship(:is_image_of, "info:fedora/" + self.pid)
|
1501
|
+
document_file.add_relationship(:is_file_of, "info:fedora/" + self.pid)
|
1502
|
+
|
1503
|
+
if set_exemplary.nil? || set_exemplary
|
1504
|
+
if ActiveFedora::Base.find_with_conditions("is_exemplary_image_of_ssim"=>"info:fedora/#{self.pid}").blank?
|
1505
|
+
document_file.add_relationship(:is_exemplary_image_of, "info:fedora/" + self.pid)
|
1506
|
+
end
|
1171
1507
|
end
|
1172
1508
|
|
1173
|
-
current_document_file.add_relationship(:is_document_of, "info:fedora/" + self.pid)
|
1174
|
-
current_document_file.add_relationship(:is_file_of, "info:fedora/" + self.pid)
|
1175
1509
|
|
1176
|
-
|
1510
|
+
document_file.save
|
1511
|
+
|
1512
|
+
document_file
|
1513
|
+
end
|
1514
|
+
|
1515
|
+
def add_new_volume(pid)
|
1516
|
+
#raise 'insert new image called with no files or more than one!' if file.blank? || file.is_a?(Array)
|
1517
|
+
volume = Bplmodels::Volume.find(pid).adapt_to_cmodel
|
1518
|
+
placement_location = volume.descMetadata.title_info.part_number.first.match(/\d+/).to_s.to_i
|
1519
|
+
|
1520
|
+
other_volumes_exist = false
|
1521
|
+
volume_placed = false
|
1522
|
+
queryed_placement_start_val = 0
|
1523
|
+
|
1524
|
+
volume_objects = Bplmodels::Finder.getVolumeObjects(self.pid)
|
1525
|
+
volume_objects.each do |volume_id|
|
1526
|
+
if !volume_placed
|
1527
|
+
queryed_placement_end_val = volume_id['title_info_partnum_tsi'].match(/\d+/).to_s.to_i
|
1528
|
+
queryed_placement_start_val ||= queryed_placement_end_val
|
1529
|
+
other_volumes_exist = true
|
1530
|
+
|
1531
|
+
#Case of insert at end
|
1532
|
+
if volume_id['is_preceding_volume_of_ssim'].blank? && queryed_placement_end_val < placement_location
|
1533
|
+
preceding_volume = Bplmodels::Volume.find(volume_id['id'])
|
1534
|
+
preceding_volume.add_relationship(:is_preceding_volume_of, "info:fedora/#{pid}", true)
|
1535
|
+
preceding_volume.save
|
1536
|
+
volume.add_relationship(:is_following_volume_of, "info:fedora/#{volume_id['id']}", true)
|
1537
|
+
volume_placed = true
|
1538
|
+
#Case of only 1 element of volume 2... insert at beginning
|
1539
|
+
elsif volume_id['is_preceding_volume_of_ssim'].blank?
|
1540
|
+
following_volume = Bplmodels::Volume.find(volume_id['id'])
|
1541
|
+
following_volume.add_relationship(:is_following_volume_of, "info:fedora/#{pid}", true)
|
1542
|
+
|
1543
|
+
volume.add_relationship(:is_preceding_volume_of, "info:fedora/#{volume_id['id']}", true)
|
1544
|
+
following_volume.save
|
1545
|
+
volume_placed = true
|
1546
|
+
#Case of multiple but insert at front
|
1547
|
+
elsif volume_id['is_following_volume_of_ssim'].blank? && queryed_placement_start_val < placement_location and queryed_placement_end_val > placement_location
|
1548
|
+
following_volume = Bplmodels::Volume.find(volume_id['id'])
|
1549
|
+
following_volume.add_relationship(:is_following_volume_of, "info:fedora/#{pid}", true)
|
1550
|
+
|
1551
|
+
volume.add_relationship(:is_preceding_volume_of, "info:fedora/#{volume_id['id']}", true)
|
1552
|
+
following_volume.save
|
1553
|
+
volume_placed = true
|
1554
|
+
#Normal case
|
1555
|
+
elsif queryed_placement_start_val < placement_location and queryed_placement_end_val > placement_location
|
1556
|
+
following_volume = Bplmodels::Volume.find(volume_id['id'])
|
1557
|
+
preceding_volume = Bplmodels::Volume.find(volume_id['is_preceding_volume_of_ssim'].gsub('info:fedora/', ''))
|
1558
|
+
|
1559
|
+
following_volume.remove_relationship(:is_following_volume_of, "info:fedora/#{preceding_volume.pid}", true)
|
1560
|
+
preceding_volume.remove_relationship(:is_preceding_volume_of, "info:fedora/#{following_volume.pid}", true)
|
1561
|
+
|
1562
|
+
|
1563
|
+
following_volume.add_relationship(:is_following_volume_of, "info:fedora/#{pid}", true)
|
1564
|
+
preceding_volume.add_relationship(:is_preceding_volume_of, "info:fedora/#{pid}", true)
|
1565
|
+
|
1566
|
+
|
1567
|
+
volume.add_relationship(:is_following_volume_of, "info:fedora/#{preceding_volume.pid}", true)
|
1568
|
+
volume.add_relationship(:is_preceding_volume_of, "info:fedora/#{following_volume.pid}", true)
|
1569
|
+
preceding_volume.save
|
1570
|
+
following_volume.save
|
1571
|
+
volume_placed = true
|
1572
|
+
end
|
1573
|
+
end
|
1574
|
+
|
1575
|
+
queryed_placement_start_val = queryed_placement_end_val
|
1576
|
+
end
|
1577
|
+
|
1578
|
+
volume.add_relationship(:is_volume_of, "info:fedora/" + self.pid)
|
1579
|
+
|
1580
|
+
#FIXME: Doesn't work with PDF?
|
1581
|
+
#FIXME: Do this better?
|
1582
|
+
if !other_volumes_exist
|
1583
|
+
ActiveFedora::Base.find_in_batches('is_exemplary_image_of_ssim'=>"info:fedora/#{pid}") do |group|
|
1584
|
+
group.each { |exemplary_solr|
|
1585
|
+
exemplary_image = Bplmodels::File.find(exemplary_solr['id']).adapt_to_cmodel
|
1586
|
+
exemplary_image.add_relationship(:is_exemplary_image_of, "info:fedora/" + self.pid)
|
1587
|
+
exemplary_image.save
|
1588
|
+
}
|
1589
|
+
end
|
1590
|
+
elsif placement_location == 1
|
1591
|
+
if ActiveFedora::Base.find_with_conditions("is_exemplary_image_of_ssim"=>"info:fedora/#{self.pid}").present?
|
1592
|
+
exemplary_to_remove_id = ActiveFedora::Base.find_with_conditions("is_exemplary_image_of_ssim"=>"info:fedora/#{self.pid}").first['id']
|
1593
|
+
exemplary_to_remove = ActiveFedora::Base.find(exemplary_to_remove_id).adapt_to_cmodel
|
1594
|
+
exemplary_to_remove.remove_relationship(:is_exemplary_image_of, "info:fedora/" + exemplary_to_remove_id)
|
1595
|
+
end
|
1596
|
+
|
1597
|
+
ActiveFedora::Base.find_in_batches('is_exemplary_image_of_ssim'=>"info:fedora/#{pid}") do |group|
|
1598
|
+
group.each { |exemplary_solr|
|
1599
|
+
exemplary_image = Bplmodels::File.find(exemplary_solr['id']).adapt_to_cmodel
|
1600
|
+
exemplary_image.add_relationship(:is_exemplary_image_of, "info:fedora/" + self.pid)
|
1601
|
+
exemplary_image.save
|
1602
|
+
}
|
1603
|
+
end
|
1604
|
+
end
|
1177
1605
|
|
1178
|
-
current_document_file.workflowMetadata.insert_file_path(document_file)
|
1179
|
-
current_document_file.workflowMetadata.insert_file_name(final_document_name)
|
1180
|
-
current_document_file.workflowMetadata.item_status.state = "published"
|
1181
|
-
current_document_file.workflowMetadata.item_status.state_comment = "Added via the ingest document object base method on " + Time.new.year.to_s + "/" + Time.new.month.to_s + "/" + Time.new.day.to_s
|
1182
1606
|
|
1183
|
-
|
1607
|
+
volume.save
|
1184
1608
|
|
1185
|
-
|
1186
|
-
current_document_file
|
1609
|
+
volume
|
1187
1610
|
end
|
1188
1611
|
|
1189
1612
|
def deleteAllFiles
|
@@ -1237,5 +1660,22 @@ module Bplmodels
|
|
1237
1660
|
return true
|
1238
1661
|
end
|
1239
1662
|
|
1663
|
+
def cache_invalidate
|
1664
|
+
response = Typhoeus::Request.post(DERIVATIVE_CONFIG_GLOBAL['url'] + "/processor/objectcacheinvalidation.json", :params => {:object_pid=>self.pid, :environment=>Bplmodels.environment})
|
1665
|
+
as_json = JSON.parse(response.body)
|
1666
|
+
|
1667
|
+
if as_json['result'] == "false"
|
1668
|
+
raise "Error Deleting the Cache! Server error!"
|
1669
|
+
end
|
1670
|
+
|
1671
|
+
return true
|
1672
|
+
end
|
1673
|
+
|
1674
|
+
|
1675
|
+
def calculate_volume_match_md5s
|
1676
|
+
self.workflowMetadata.volume_match_md5s.marc = Digest::MD5.hexdigest(self.marc.content)
|
1677
|
+
self.workflowMetadata.volume_match_md5s.iaMeta = Digest::MD5.hexdigest(self.iaMeta.content.gsub(/<\/page_progression>.+$/, '').gsub(/<volume>.+<\/volume>/, ''))
|
1678
|
+
end
|
1679
|
+
|
1240
1680
|
end
|
1241
1681
|
end
|