Class: Stanford::Mods::Record

Inherits:
Mods::Record
  • Object
show all
Defined in:
lib/stanford-mods/geo_spatial.rb,
lib/stanford-mods.rb,
lib/stanford-mods/name.rb,
lib/stanford-mods/origin_info.rb,
lib/stanford-mods/searchworks.rb,
lib/stanford-mods/physical_location.rb,
lib/stanford-mods/searchworks_subjects.rb

Overview

NON-SearchWorks specific wranglings of MODS cartographics metadata

Constant Summary collapse

COLLECTOR_ROLE_URI = 
'http://id.loc.gov/vocabulary/relators/col'

Class Method Summary collapse

Instance Method Summary collapse

Class Method Details

.date_is_approximate?(date_element) ⇒ Boolean

NOTE: legal values for MODS date elements with attribute qualifier are

'approximate', 'inferred' or 'questionable'



123
124
125
126
 
# File 'lib/stanford-mods/origin_info.rb', line 123

def self.date_is_approximate?(date_element)
  qualifier = date_element["qualifier"] if date_element.respond_to?('[]')
  qualifier == 'approximate' || qualifier == 'questionable'
end

.earliest_year_int(date_el_array) ⇒ Object

get earliest parseable year (as an Integer) from the passed date elements



133
134
135
 
# File 'lib/stanford-mods/origin_info.rb', line 133

def self.earliest_year_int(date_el_array)
  earliest_year(date_el_array, :year_int_from_date_str)
end

.earliest_year_str(date_el_array) ⇒ Object

get earliest parseable year (as a String) from the passed date elements



142
143
144
 
# File 'lib/stanford-mods/origin_info.rb', line 142

def self.earliest_year_str(date_el_array)
  earliest_year(date_el_array, :sortable_year_string_from_date_str)
end

.keyDate(elements) ⇒ Nokogiri::XML::Element?

given a set of date elements, return the single element with attribute keyDate=“yes”

or return nil if no elements have attribute keyDate="yes", or if multiple elements have keyDate="yes"



105
106
107
108
 
# File 'lib/stanford-mods/origin_info.rb', line 105

def self.keyDate(elements)
  keyDates = elements.select { |node| node["keyDate"] == 'yes' }
  keyDates.first if keyDates.size == 1
end

.remove_approximate(nodeset) ⇒ Array<Nokogiri::XML::Element>

remove Elements from NodeSet if they have a qualifier attribute of ‘approximate’ or ‘questionable’



114
115
116
 
# File 'lib/stanford-mods/origin_info.rb', line 114

def self.remove_approximate(nodeset)
  nodeset.select { |node| node unless date_is_approximate?(node) }
end

Instance Method Details

#additional_authors_w_dates ⇒ Object

all names, in display form, except the main_author

names will be the display_value_w_date form
see Mods::Record.name  in nom_terminology for details on the display_value algorithm



39
40
41
42
43
44
45
46
 
# File 'lib/stanford-mods/name.rb', line 39

def additional_authors_w_dates
  results = []
  @mods_ng_xml.plain_name.each { |n|
    results << n.display_value_w_date
  }
  results.delete(main_author_w_date)
  results
end

#box ⇒ Object

return box number (note: single valued and might be something like 35A)

data in location/physicalLocation or in relatedItem/location/physicalLocation
so use _location to get the data from either one of them

TODO: should it be hierarchical series/box/folder?



13
14
15
16
17
18
19
20
21
22
23
24
 
# File 'lib/stanford-mods/physical_location.rb', line 13

def box
  #   _location.physicalLocation should find top level and relatedItem
  box_num = @mods_ng_xml._location.physicalLocation.map do |node|
    val = node.text
    # note that this will also find Flatbox or Flat-box
    match_data = val.match(/Box ?:? ?([^,|(Folder)]+)/i)
    match_data[1].strip if match_data.present?
  end.compact

  # There should only be one box
  box_num.first
end

#catkey ⇒ String 



359
360
361
362
363
364
365
 
# File 'lib/stanford-mods/searchworks.rb', line 359

def catkey
  catkey = self.term_values([:record_info, :recordIdentifier])
  if catkey && catkey.length > 0
    return catkey.first.tr('a', '') # ensure catkey is numeric only
  end
  nil
end

#collectors_w_dates ⇒ Object 



64
65
66
67
68
69
70
71
72
73
 
# File 'lib/stanford-mods/name.rb', line 64

def collectors_w_dates
  result = []
  @mods_ng_xml.personal_name.each do |n|
    next if n.role.size.zero?
    n.role.each { |r|
      result << n.display_value_w_date if includes_marc_relator_collector_role?(r)
    }
  end
  result unless result.empty?
end

#coordinates ⇒ Object 



9
10
11
 
# File 'lib/stanford-mods/geo_spatial.rb', line 9

def coordinates
  Array(@mods_ng_xml.subject.cartographics.coordinates).map(&:text)
end

#date_created_elements(ignore_approximate = false) ⇒ Array<Nokogiri::XML::Element>

return /originInfo/dateCreated elements in MODS records



85
86
87
88
89
 
# File 'lib/stanford-mods/origin_info.rb', line 85

def date_created_elements(ignore_approximate=false)
  date_created_nodeset = @mods_ng_xml.origin_info.dateCreated
  return self.class.remove_approximate(date_created_nodeset) if ignore_approximate
  date_created_nodeset.to_a
end

#date_issued_elements(ignore_approximate = false) ⇒ Array<Nokogiri::XML::Element>

return /originInfo/dateIssued elements in MODS records



95
96
97
98
99
 
# File 'lib/stanford-mods/origin_info.rb', line 95

def date_issued_elements(ignore_approximate=false)
  date_issued_nodeset = @mods_ng_xml.origin_info.dateIssued
  return self.class.remove_approximate(date_issued_nodeset) if ignore_approximate
  date_issued_nodeset.to_a
end

#druid ⇒ Object 



371
372
373
 
# File 'lib/stanford-mods/searchworks.rb', line 371

def druid
  @druid ? @druid : 'Unknown item'
end

#druid=(new_druid) ⇒ Object 



367
368
369
 
# File 'lib/stanford-mods/searchworks.rb', line 367

def druid=(new_druid)
  @druid = new_druid
end

#era_facet ⇒ Array<String>

subject/temporal values with trailing comma, semicolon, and backslash (and any preceding spaces) removed



104
105
106
 
# File 'lib/stanford-mods/searchworks_subjects.rb', line 104

def era_facet
  subject_temporal.map { |val| val.sub(/[\\,;]$/, '').strip } unless !subject_temporal
end

#folder ⇒ Object

returns folder number (note: single valued)

data in location/physicalLocation or in relatedItem/location/physicalLocation
so use _location to get the data from either one of them

TODO: should it be hierarchical series/box/folder?



30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
 
# File 'lib/stanford-mods/physical_location.rb', line 30

def folder
  #   _location.physicalLocation should find top level and relatedItem
  folder_num = @mods_ng_xml._location.physicalLocation.map do |node|
    val = node.text

    match_data = if val =~ /\|/
                   # we assume the data is pipe-delimited, and may contain commas within values
                   val.match(/Folder ?:? ?([^|]+)/)
                 else
                   # the data should be comma-delimited, and may not contain commas within values
                   val.match(/Folder ?:? ?([^,]+)/)
                 end

    match_data[1].strip if match_data.present?
  end.compact

  # There should be one folder
  folder_num.first
end

#format ⇒ Array[String]

Deprecated.

  • kept for backwards compatibility but not part of SW UI redesign work Summer 2014

select one or more format values from the controlled vocabulary here:

http://searchworks-solr-lb.stanford.edu:8983/solr/select?facet.field=format&rows=0&facet.sort=index

@deprecated: this is no longer used in SW, Revs or Spotlight Jan 2016



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
264
265
266
267
268
269
270
271
272
273
274
275
 
# File 'lib/stanford-mods/searchworks.rb', line 227

def format
  val = []
  types = self.term_values(:typeOfResource)
  if types
    genres = self.term_values(:genre)
    issuance = self.term_values([:origin_info,:issuance])
    types.each do |type|
      case type
        when 'cartographic'
          val << 'Map/Globe'
        when 'mixed material'
          val << 'Manuscript/Archive'
        when 'moving image'
          val << 'Video'
        when 'notated music'
          val << 'Music - Score'
        when 'software, multimedia'
          val << 'Computer File'
        when 'sound recording-musical'
          val << 'Music - Recording'
        when 'sound recording-nonmusical', 'sound recording'
          val << 'Sound Recording'
        when 'still image'
          val << 'Image'
        when 'text'
          val << 'Book' if issuance && issuance.include?('monographic')
          book_genres = ['book chapter', 'Book chapter', 'Book Chapter',
            'issue brief', 'Issue brief', 'Issue Brief',
            'librettos', 'Librettos',
            'project report', 'Project report', 'Project Report',
            'technical report', 'Technical report', 'Technical Report',
            'working paper', 'Working paper', 'Working Paper']
          val << 'Book' if genres && !(genres & book_genres).empty?
          conf_pub = ['conference publication', 'Conference publication', 'Conference Publication']
          val << 'Conference Proceedings' if genres && !(genres & conf_pub).empty?
          val << 'Journal/Periodical' if issuance && issuance.include?('continuing')
          article = ['article', 'Article']
          val << 'Journal/Periodical' if genres && !(genres & article).empty?
          stu_proj_rpt = ['student project report', 'Student project report', 'Student Project report', 'Student Project Report']
          val << 'Other' if genres && !(genres & stu_proj_rpt).empty?
          thesis = ['thesis', 'Thesis']
          val << 'Thesis' if genres && !(genres & thesis).empty?
        when 'three dimensional object'
          val << 'Other'
      end
    end
  end
  val.uniq
end

#format_main ⇒ Array[String]

select one or more format values from the controlled vocabulary per JVine Summer 2014

http://searchworks-solr-lb.stanford.edu:8983/solr/select?facet.field=format_main_ssim&rows=0&facet.sort=index



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
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
 
# File 'lib/stanford-mods/searchworks.rb', line 280

def format_main
  val = []
  types = self.term_values(:typeOfResource)
  article_genres = ['article', 'Article',
    'book chapter', 'Book chapter', 'Book Chapter',
    'issue brief', 'Issue brief', 'Issue Brief',
    'project report', 'Project report', 'Project Report',
    'student project report', 'Student project report', 'Student Project report', 'Student Project Report',
    'technical report', 'Technical report', 'Technical Report',
    'working paper', 'Working paper', 'Working Paper'
  ]
  book_genres = ['conference publication', 'Conference publication', 'Conference Publication',
    'instruction', 'Instruction',
    'librettos', 'Librettos',
    'thesis', 'Thesis'
  ]
  if types
    genres = self.term_values(:genre)
    issuance = self.term_values([:origin_info, :issuance])
    types.each do |type|
      case type
        when 'cartographic'
          val << 'Map'
        when 'mixed material'
          val << 'Archive/Manuscript'
        when 'moving image'
          val << 'Video'
        when 'notated music'
          val << 'Music score'
        when 'software, multimedia'
          if genres && (genres.include?('dataset') || genres.include?('Dataset'))
            val << 'Dataset'
          else
            val << 'Software/Multimedia'
          end
        when 'sound recording-musical'
          val << 'Music recording'
        when 'sound recording-nonmusical', 'sound recording'
          val << 'Sound recording'
        when 'still image'
          val << 'Image'
        when 'text'
          val << 'Book' if genres && !(genres & article_genres).empty?
          val << 'Book' if issuance && issuance.include?('monographic')
          val << 'Book' if genres && !(genres & book_genres).empty?
          val << 'Journal/Periodical' if issuance && issuance.include?('continuing')
        when 'three dimensional object'
          val << 'Object'
      end
    end
  end
  val.uniq
end

#geographic_facet ⇒ Array<String>

geographic_search values with trailing comma, semicolon, and backslash (and any preceding spaces) removed



98
99
100
 
# File 'lib/stanford-mods/searchworks_subjects.rb', line 98

def geographic_facet
  geographic_search.map { |val| val.sub(/[\\,;]$/, '').strip } unless !geographic_search
end

#geographic_search ⇒ Array<String>

Values are the contents of:

subject/geographic
subject/hierarchicalGeographic
subject/geographicCode  (only include the translated value if it isn't already present from other mods geo fields)



113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
 
# File 'lib/stanford-mods/searchworks_subjects.rb', line 113

def geographic_search
  @geographic_search ||= begin
    result = self.sw_geographic_search

    # TODO:  this should go into stanford-mods ... but then we have to set that gem up with a Logger
    # print a message for any unrecognized encodings
    xvals = self.subject.geographicCode.translated_value
    codes = self.term_values([:subject, :geographicCode])
    if codes && codes.size > xvals.size
      self.subject.geographicCode.each { |n|
        if n.authority != 'marcgac' && n.authority != 'marccountry'
          sw_logger.info("#{druid} has subject geographicCode element with untranslated encoding (#{n.authority}): #{n.to_xml}")
        end
      }
    end

    # FIXME:  stanford-mods should be returning [], not nil ...
    return nil if !result || result.empty?
    result
  end
end

#includes_marc_relator_collector_role?(role_node) ⇒ Boolean 



79
80
81
82
 
# File 'lib/stanford-mods/name.rb', line 79

def includes_marc_relator_collector_role?(role_node)
  (role_node.authority.include?('marcrelator') && role_node.value.include?('Collector')) ||
  role_node.roleTerm.valueURI.first == COLLECTOR_ROLE_URI
end

#location ⇒ Object

return entire contents of physicalLocation (note: single valued)

but only if it has series, accession, box or folder data
data in location/physicalLocation or in relatedItem/location/physicalLocation
so use _location to get the data from either one of them

TODO: should it be hierarchical series/box/folder?



55
56
57
58
59
60
61
62
63
 
# File 'lib/stanford-mods/physical_location.rb', line 55

def location
  #   _location.physicalLocation should find top level and relatedItem
  loc = @mods_ng_xml._location.physicalLocation.map do |node|
    node.text if node.text.match(/.*(Series)|(Accession)|(Folder)|(Box).*/i)
  end.compact

  # There should only be one location
  loc.first
end

#main_author_w_date ⇒ String

the first encountered <mods><name> element with marcrelator flavor role of ‘Creator’ or ‘Author’. if no marcrelator ‘Creator’ or ‘Author’, the first name without a role. if no name without a role, then nil see Mods::Record.name in nom_terminology for details on the display_value algorithm



16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
 
# File 'lib/stanford-mods/name.rb', line 16

def main_author_w_date
  result = nil
  first_wo_role = nil
  @mods_ng_xml.plain_name.each { |n|
    if n.role.size == 0
      first_wo_role ||= n
    end
    n.role.each { |r|
      if r.authority.include?('marcrelator') &&
            (r.value.include?('Creator') || r.value.include?('Author'))
        result ||= n.display_value_w_date
      end
    }
  }
  if !result && first_wo_role
    result = first_wo_role.display_value_w_date
  end
  result
end

#main_author_w_date_test ⇒ Object 



100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
 
# File 'lib/stanford-mods/searchworks.rb', line 100

def main_author_w_date_test
  result = nil
  first_wo_role = nil
  self.plain_name.each { |n|
    if n.role.size == 0
      first_wo_role ||= n
    end
    n.role.each { |r|
      if r.authority.include?('marcrelator') &&
        (r.value.include?('Creator') || r.value.include?('Author'))
        result ||= n.display_value_w_date
      end
    }
  }
  if !result && first_wo_role
    result = first_wo_role.display_value_w_date
  end
  result
end

#non_collector_person_authors ⇒ Object

FIXME: this is broken if there are multiple role codes and some of them are not marcrelator



51
52
53
54
55
56
57
58
59
60
 
# File 'lib/stanford-mods/name.rb', line 51

def non_collector_person_authors
  result = []
  @mods_ng_xml.personal_name.map do |n|
    next if n.role.size.zero?
    n.role.each { |r|
      result << n.display_value_w_date unless includes_marc_relator_collector_role?(r)
    }
  end
  result unless result.empty?
end

#place ⇒ Object

—- old date parsing methods used downstream of gem; will be deprecated/replaced with new date parsing methods



198
199
200
201
 
# File 'lib/stanford-mods/origin_info.rb', line 198

def place
  vals = self.term_values([:origin_info, :place, :placeTerm])
  vals
end

#point_bbox ⇒ Object 



13
14
15
16
17
18
19
20
21
22
23
 
# File 'lib/stanford-mods/geo_spatial.rb', line 13

def point_bbox
  coordinates.map do |n|
    matches = n.match(/^\(?([^)]+)\)?\.?$/)

    if matches
      coord_to_bbox(matches[1])
    else
      coord_to_bbox(n)
    end
  end.compact
end

#pub_date_display ⇒ String

For the date display only, the first place to look is in the dates without encoding=marc array. If no such dates, select the first date in the dates_marc_encoding array. Otherwise return nil @deprecated: DO NOT USE: this is no longer used in SW, Revs or Spotlight Jan 2016



244
245
246
247
248
 
# File 'lib/stanford-mods/origin_info.rb', line 244

def pub_date_display
  return dates_no_marc_encoding.first unless dates_no_marc_encoding.empty?
  return dates_marc_encoding.first unless dates_marc_encoding.empty?
  nil
end

#pub_date_facet ⇒ Array[String]

Values for the pub date facet. This is less strict than the 4 year date requirements for pub_date Jan 2016: used to populate Solr pub_date field for Spotlight and SearchWorks

Spotlight:  pub_date field should be replaced by pub_year_w_approx_isi and pub_year_no_approx_isi
SearchWorks:  pub_date field used for display in search results and show view; for sorting nearby-on-shelf
   these could be done with more approp fields/methods (pub_year_int for sorting;  new pub year methods to populate field)

TODO: prob should deprecated this in favor of pub_date_facet_single_value;

need head-to-head testing with pub_date_facet_single_value



211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
 
# File 'lib/stanford-mods/origin_info.rb', line 211

def pub_date_facet
  if pub_date
    if pub_date.start_with?('-')
      return (pub_date.to_i + 1000).to_s + ' B.C.'
    end
    if pub_date.include? '--'
      cent = pub_date[0, 2].to_i
      cent += 1
      cent = cent.to_s + 'th century'
      return cent
    else
      return pub_date
    end
  end
  nil
end

#pub_date_facet_single_value(ignore_approximate = false) ⇒ String

return a single string intended for facet use for pub date prefer dateIssued (any) before dateCreated (any) before dateCaptured (any)

look for a keyDate and use it if there is one;  otherwise pick earliest date



21
22
23
 
# File 'lib/stanford-mods/origin_info.rb', line 21

def pub_date_facet_single_value(ignore_approximate = false)
  single_pub_year(ignore_approximate, :year_facet_str)
end

#pub_date_sort ⇒ Object

creates a date suitable for sorting. Guarnteed to be 4 digits or nil @deprecated: use pub_year_int, or pub_year_sort_str if you must have a string (why?)



230
231
232
233
234
235
236
237
238
 
# File 'lib/stanford-mods/origin_info.rb', line 230

def pub_date_sort
  if pub_date
    pd = pub_date
    pd = '0' + pd if pd.length == 3
    pd = pd.gsub('--', '00')
  end
  fail "pub_date_sort was about to return a non 4 digit value #{pd}!" if pd && pd.length != 4
  pd
end

#pub_year_int(ignore_approximate = false) ⇒ Integer

return pub year as an Integer prefer dateIssued (any) before dateCreated (any) before dateCaptured (any)

look for a keyDate and use it if there is one;  otherwise pick earliest date



32
33
34
 
# File 'lib/stanford-mods/origin_info.rb', line 32

def pub_year_int(ignore_approximate = false)
  single_pub_year(ignore_approximate, :year_int)
end

#pub_year_sort_str(ignore_approximate = false) ⇒ String

Deprecated.

use pub_year_int

return a single string intended for lexical sorting for pub date prefer dateIssued (any) before dateCreated (any) before dateCaptured (any)

look for a keyDate and use it if there is one;  otherwise pick earliest date



44
45
46
 
# File 'lib/stanford-mods/origin_info.rb', line 44

def pub_year_sort_str(ignore_approximate = false)
  single_pub_year(ignore_approximate, :year_sort_str)
end

#series ⇒ Object

return series/accession ‘number’ (note: single valued)

data in location/physicalLocation or in relatedItem/location/physicalLocation
so use _location to get the data from either one of them

TODO: should it be hierarchical series/box/folder?



69
70
71
72
73
74
75
76
77
78
79
80
 
# File 'lib/stanford-mods/physical_location.rb', line 69

def series
  #   _location.physicalLocation should find top level and relatedItem
  series_num = @mods_ng_xml._location.physicalLocation.map do |node|
    val = node.text
    # feigenbaum uses 'Accession'
    match_data = val.match(/(?:(?:Series)|(?:Accession)):? ([^,|]+)/i)
    match_data[1].strip if match_data.present?
  end.compact

  # There should be only one series
  series_num.first
end

#subject_all_search ⇒ Array<String>

Values are the contents of:

all subject subelements except subject/cartographic plus  genre top level element



171
172
173
174
175
176
177
 
# File 'lib/stanford-mods/searchworks_subjects.rb', line 171

def subject_all_search
  vals = topic_search ? Array.new(topic_search) : []
  vals.concat(geographic_search) if geographic_search
  vals.concat(subject_other_search) if subject_other_search
  vals.concat(subject_other_subvy_search) if subject_other_subvy_search
  vals.empty? ? nil : vals
end

#subject_other_search ⇒ Array<String>

Values are the contents of:

subject/name
subject/occupation  - no subelements
subject/titleInfo



140
141
142
143
144
145
146
147
 
# File 'lib/stanford-mods/searchworks_subjects.rb', line 140

def subject_other_search
  @subject_other_search ||= begin
    vals = subject_occupations ? Array.new(subject_occupations) : []
    vals.concat(subject_names) if subject_names
    vals.concat(subject_titles) if subject_titles
    vals.empty? ? nil : vals
  end
end

#subject_other_subvy_search ⇒ Array<String>

Values are the contents of:

subject/temporal
subject/genre



153
154
155
156
157
158
159
160
161
162
163
164
165
166
 
# File 'lib/stanford-mods/searchworks_subjects.rb', line 153

def subject_other_subvy_search
  @subject_other_subvy_search ||= begin
    vals = subject_temporal ? Array.new(subject_temporal) : []
    gvals = self.term_values([:subject, :genre])
    vals.concat(gvals) if gvals

    # print a message for any temporal encodings
    self.subject.temporal.each { |n|
      sw_logger.info("#{druid} has subject temporal element with untranslated encoding: #{n.to_xml}") if !n.encoding.empty?
    }

    vals.empty? ? nil : vals
  end
end

#sw_addl_authors ⇒ Array<String> 



64
65
66
 
# File 'lib/stanford-mods/searchworks.rb', line 64

def sw_addl_authors
  additional_authors_w_dates
end

#sw_addl_titles ⇒ Array<String>

this includes all titles except



180
181
182
 
# File 'lib/stanford-mods/searchworks.rb', line 180

def sw_addl_titles
  full_titles.select { |s| s !~ Regexp.new(Regexp.escape(sw_short_title)) }
end

#sw_corporate_authors ⇒ Array<String> 



80
81
82
83
 
# File 'lib/stanford-mods/searchworks.rb', line 80

def sw_corporate_authors
  val = @mods_ng_xml.plain_name.select {|n| n.type_at == 'corporate'}.map { |n| n.display_value_w_date }
  val
end

#sw_full_title ⇒ String 



130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
 
# File 'lib/stanford-mods/searchworks.rb', line 130

def sw_full_title
  outer_nodes = @mods_ng_xml.title_info
  outer_node = outer_nodes ? outer_nodes.first : nil
  if outer_node
    nonSort = outer_node.nonSort.text.strip.empty? ? nil : outer_node.nonSort.text.strip
    title   = outer_node.title.text.strip.empty?   ? nil : outer_node.title.text.strip
    preSubTitle = nonSort ? [nonSort, title].compact.join(" ") : title
    preSubTitle.sub!(/:$/, '') if preSubTitle # remove trailing colon

    subTitle = outer_node.subTitle.text.strip
    preParts = subTitle.empty? ? preSubTitle : preSubTitle + " : " + subTitle
    preParts.sub!(/\.$/, '') if preParts # remove trailing period

    partName   = outer_node.partName.text.strip   unless outer_node.partName.text.strip.empty?
    partNumber = outer_node.partNumber.text.strip unless outer_node.partNumber.text.strip.empty?
    partNumber.sub!(/,$/, '') if partNumber # remove trailing comma
    if partNumber && partName
      parts = partNumber + ", " + partName
    elsif partNumber
      parts = partNumber
    elsif partName
      parts = partName
    end
    parts.sub!(/\.$/, '') if parts

    result = parts ? preParts + ". " + parts : preParts
    result += "." if !result.match(/[[:punct:]]$/)
    result.strip!
    result = nil if result.empty?
    result
  else
    nil
  end
end

#sw_full_title_without_commas ⇒ Object

Deprecated.

in favor of sw_title_display

remove trailing commas



202
203
204
205
206
 
# File 'lib/stanford-mods/searchworks.rb', line 202

def sw_full_title_without_commas
  result = self.sw_full_title
  result.sub!(/,$/, '') if result
  result
end

#sw_genre ⇒ Array[String]

return values for the genre facet in SearchWorks



336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
 
# File 'lib/stanford-mods/searchworks.rb', line 336

def sw_genre
  val = []
  genres = self.term_values(:genre)
  if genres
    val << genres.map(&:capitalize)
    val.flatten! if !val.empty?
    if genres.include?('thesis') || genres.include?('Thesis')
      val << 'Thesis/Dissertation'
      val.delete 'Thesis'
    end
    conf_pub = ['conference publication', 'Conference publication', 'Conference Publication']
    if !(genres & conf_pub).empty?
      types = self.term_values(:typeOfResource)
      if types && types.include?('text')
        val << 'Conference proceedings'
        val.delete 'Conference publication'
      end
    end
  end
  val.uniq
end

#sw_geographic_search(sep = ' ') ⇒ Array<String>

Values are the contents of:

subject/geographic
subject/hierarchicalGeographic
subject/geographicCode  (only include the translated value if it isn't already present from other mods geo fields)



16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
 
# File 'lib/stanford-mods/searchworks_subjects.rb', line 16

def sw_geographic_search(sep = ' ')
  result = term_values([:subject, :geographic]) || []

  # hierarchicalGeographic has sub elements
  @mods_ng_xml.subject.hierarchicalGeographic.each { |hg_node|
    hg_vals = []
    hg_node.element_children.each { |e|
      hg_vals << e.text unless e.text.empty?
    }
    result << hg_vals.join(sep) unless hg_vals.empty?
  }

  trans_code_vals = @mods_ng_xml.subject.geographicCode.translated_value
  if trans_code_vals
    trans_code_vals.each { |val|
      result << val if !result.include?(val)
    }
  end

  result
end

#sw_impersonal_authors ⇒ Array<String>

return the display_value_w_date for all <mods><name> elements that do not have type=‘personal’



75
76
77
 
# File 'lib/stanford-mods/searchworks.rb', line 75

def sw_impersonal_authors
  @mods_ng_xml.plain_name.select {|n| n.type_at != 'personal'}.map { |n| n.display_value_w_date }
end

#sw_language_facet ⇒ Object

include langagues known to SearchWorks; try to error correct when possible (e.g. when ISO-639 disagrees with MARC standard)



14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
 
# File 'lib/stanford-mods/searchworks.rb', line 14

def sw_language_facet
  result = []
  @mods_ng_xml.language.each { |n|
    # get languageTerm codes and add their translations to the result
    n.code_term.each { |ct|
      if ct.authority.match(/^iso639/)
        begin
          vals = ct.text.split(/[,|\ ]/).reject {|x| x.strip.length == 0 }
          vals.each do |v|
            iso639_val = ISO_639.find(v.strip).english_name
            if SEARCHWORKS_LANGUAGES.has_value?(iso639_val)
              result << iso639_val
            else
              result << SEARCHWORKS_LANGUAGES[v.strip]
            end
          end
        rescue
          # TODO:  this should be written to a logger
          p "Couldn't find english name for #{ct.text}"
        end
      else
        vals = ct.text.split(/[,|\ ]/).reject {|x| x.strip.length == 0 }
        vals.each do |v|
          result << SEARCHWORKS_LANGUAGES[v.strip]
        end
      end
    }
    # add languageTerm text values
    n.text_term.each { |tt|
      val = tt.text.strip
      result << val if val.length > 0 && SEARCHWORKS_LANGUAGES.has_value?(val)
    }

    # add language values that aren't in languageTerm subelement
    if n.languageTerm.size == 0
      result << n.text if SEARCHWORKS_LANGUAGES.has_value?(n.text)
    end
  }
  result.uniq
end

#sw_logger ⇒ Object

—- PUBLICATION (place, year) —- see origin_info.rb (as all this information comes from top level originInfo element) —- end PUBLICATION (place, year) —-



218
219
220
 
# File 'lib/stanford-mods/searchworks.rb', line 218

def sw_logger
  @logger ||= Logger.new(STDOUT)
end

#sw_main_author ⇒ String 



59
60
61
 
# File 'lib/stanford-mods/searchworks.rb', line 59

def sw_main_author
  main_author_w_date
end

#sw_meeting_authors ⇒ Array<String> 



86
87
88
 
# File 'lib/stanford-mods/searchworks.rb', line 86

def sw_meeting_authors
  @mods_ng_xml.plain_name.select {|n| n.type_at == 'conference'}.map { |n| n.display_value_w_date }
end

#sw_person_authors ⇒ Array<String> 



69
70
71
 
# File 'lib/stanford-mods/searchworks.rb', line 69

def sw_person_authors
  personal_names_w_dates
end

#sw_short_title ⇒ String 



125
126
127
 
# File 'lib/stanford-mods/searchworks.rb', line 125

def sw_short_title
  short_titles ? short_titles.first : nil
end

#sw_sort_author ⇒ String

Returns a sortable version of the main_author:

main_author + sorting title

which is the mods approximation of the value created for a marc record



94
95
96
97
98
 
# File 'lib/stanford-mods/searchworks.rb', line 94

def sw_sort_author
  #  substitute java Character.MAX_CODE_POINT for nil main_author so missing main authors sort last
  val = '' + (main_author_w_date ? main_author_w_date : "\u{10FFFF} ") + ( sort_title ? sort_title : '')
  val.gsub(/[[:punct:]]*/, '').strip
end

#sw_sort_title ⇒ String

Returns a sortable version of the main title



186
187
188
189
190
191
192
193
194
195
196
197
198
 
# File 'lib/stanford-mods/searchworks.rb', line 186

def sw_sort_title
  # get nonSort piece
  outer_nodes = @mods_ng_xml.title_info
  outer_node = outer_nodes ? outer_nodes.first : nil
  if outer_node
    nonSort = outer_node.nonSort.text.strip.empty? ? nil : outer_node.nonSort.text.strip
  end

  val = '' + ( sw_full_title ? sw_full_title : '')
  val.sub!(Regexp.new("^" + Regexp.escape(nonSort)), '') if nonSort
  val.gsub!(/[[:punct:]]*/, '').strip
  val.squeeze(" ").strip
end

#sw_subject_names(sep = ', ') ⇒ Array<String>

Values are the contents of:

 subject/name/namePart
"Values from namePart subelements should be concatenated in the order they appear (e.g. "Shakespeare, William, 1564-1616")"



43
44
45
46
47
48
49
50
 
# File 'lib/stanford-mods/searchworks_subjects.rb', line 43

def sw_subject_names(sep = ', ')
  result = []
  @mods_ng_xml.subject.name_el.select { |n_el| n_el.namePart }.each { |name_el_w_np|
    parts = name_el_w_np.namePart.map { |npn| npn.text unless npn.text.empty? }.compact
    result << parts.join(sep).strip unless parts.empty?
  }
  result
end

#sw_subject_titles(sep = ' ') ⇒ Array<String>

Values are the contents of:

subject/titleInfo/(subelements)



56
57
58
59
60
61
62
63
 
# File 'lib/stanford-mods/searchworks_subjects.rb', line 56

def sw_subject_titles(sep = ' ')
  result = []
  @mods_ng_xml.subject.titleInfo.each { |ti_el|
    parts = ti_el.element_children.map { |el| el.text unless el.text.empty? }.compact
    result << parts.join(sep).strip unless parts.empty?
  }
  result
end

#sw_title_display ⇒ String

like sw_full_title without trailing ,/;:. spec from solrmarc-sw sw_index.properties

title_display = custom, removeTrailingPunct(245abdefghijklmnopqrstuvwxyz, [\\\\,/;:], ([A-Za-z]{4}|[0-9]{3}|\\)|\\,))



169
170
171
172
173
174
175
176
 
# File 'lib/stanford-mods/searchworks.rb', line 169

def sw_title_display
  result = sw_full_title ? sw_full_title : nil
  if result
    result.sub!(/[\.,;:\/\\]+$/, '')
    result.strip!
  end
  result
end

#topic_facet ⇒ Array<String>

Values are the contents of:

 subject/topic
 subject/name
 subject/title
 subject/occupation
with trailing comma, semicolon, and backslash (and any preceding spaces) removed



84
85
86
87
88
89
90
91
92
93
94
 
# File 'lib/stanford-mods/searchworks_subjects.rb', line 84

def topic_facet
  vals = subject_topics ? Array.new(subject_topics) : []
  vals.concat(subject_names) if subject_names
  vals.concat(subject_titles) if subject_titles
  vals.concat(subject_occupations) if subject_occupations
  vals.map! { |val|
    v = val.sub(/[\\,;]$/, '')
    v.strip
  }
  vals.empty? ? nil : vals
end

#topic_search ⇒ Array<String>

Values are the contents of:

mods/genre
mods/subject/topic



69
70
71
72
73
74
75
 
# File 'lib/stanford-mods/searchworks_subjects.rb', line 69

def topic_search
  @topic_search ||= begin
    vals = self.term_values(:genre) || []
    vals.concat(subject_topics) if subject_topics
    vals.empty? ? nil : vals
  end
end

#year_facet_str(date_el_array) ⇒ String

given the passed date elements, look for a single keyDate and use it if there is one;

otherwise pick earliest parseable date



52
53
54
55
56
57
 
# File 'lib/stanford-mods/origin_info.rb', line 52

def year_facet_str(date_el_array)
  result = date_parsing_result(date_el_array, :facet_string_from_date_str)
  return result if result
  _ignore, orig_str_to_parse = self.class.earliest_year_str(date_el_array)
  DateParsing.facet_string_from_date_str(orig_str_to_parse) if orig_str_to_parse
end

#year_int(date_el_array) ⇒ Integer

given the passed date elements, look for a single keyDate and use it if there is one;

otherwise pick earliest parseable date



63
64
65
66
67
68
 
# File 'lib/stanford-mods/origin_info.rb', line 63

def year_int(date_el_array)
  result = date_parsing_result(date_el_array, :year_int_from_date_str)
  return result if result
  year_int, _ignore = self.class.earliest_year_int(date_el_array)
  year_int if year_int
end

#year_sort_str(date_el_array) ⇒ String

given the passed date elements, look for a single keyDate and use it if there is one;

otherwise pick earliest parseable date



74
75
76
77
78
79
 
# File 'lib/stanford-mods/origin_info.rb', line 74

def year_sort_str(date_el_array)
  result = date_parsing_result(date_el_array, :sortable_year_string_from_date_str)
  return result if result
  sortable_str, _ignore = self.class.earliest_year_str(date_el_array)
  sortable_str if sortable_str
end