Class: PennMARC::Identifier

Inherits:
Helper
  • Object
show all
Defined in:
lib/pennmarc/helpers/identifier.rb

Overview

Parser methods for extracting identifier values.

Constant Summary

Constants included from Util

Util::TRAILING_PUNCTUATIONS_PATTERNS

Class Method Summary collapse

Methods included from Util

#append_relator, #append_trailing, #datafield_and_linked_alternate, #field_defined?, #field_or_its_linked_alternate?, #join_and_squish, #join_subfields, #linked_alternate, #linked_alternate_not_6_or_8, #no_subfield_value_matches?, #prefixed_subject_and_alternate, #relator, #relator_join_separator, #relator_term_subfield, #remove_paren_value_from_subfield_i, #subfield_defined?, #subfield_in?, #subfield_not_in?, #subfield_undefined?, #subfield_value?, #subfield_value_in?, #subfield_value_not_in?, #subfield_values, #subfield_values_for, #substring_after, #substring_before, #translate_relator, #trim_punctuation, #trim_trailing, #trim_trailing!, #valid_subject_genre_source_code?

Class Method Details

.doi_show(record) ⇒ Array<String>

Retrieve DOI values stored in 024. Penn MARC records give the first indicator a value of ‘7’ and ǂ2 a value of ‘doi’ to denote that ǂa is a doi.



151
152
153
154
155
156
157
158
159
160
 
# File 'lib/pennmarc/helpers/identifier.rb', line 151

def doi_show(record)
  record.fields('024').filter_map { |field|
    # skip unless indicator1 is '7'
    next unless field.indicator1.in?(%w[7])
    # skip unless ǂ2 is the string literal 'doi'
    next unless subfield_value_in?(field, '2', %w[doi])

    join_subfields(field, &subfield_in?(%w[a]))
  }.uniq
end

.fingerprint_show(record) ⇒ Array<String>

Retrieve fingerprint for display from the 026 field



141
142
143
144
145
 
# File 'lib/pennmarc/helpers/identifier.rb', line 141

def fingerprint_show(record)
  record.fields('026').map { |field|
    join_subfields(field, &subfield_not_in?(%w[2 5 6 8]))
  }.uniq
end

.host_record_id(record) ⇒ Array<String>

Gets any Host record MMS ID values from an Enriched::Pub::RELATED_RECORD_TAG field added during Alma enrichment. This aids in our handling of “bound with” records.



166
167
168
169
170
171
172
 
# File 'lib/pennmarc/helpers/identifier.rb', line 166

def host_record_id(record)
  record.fields(Enriched::Pub::RELATED_RECORD_TAGS).filter_map { |field|
    next unless subfield_value?(field, 'c', /contains/i)

    subfield_values field, :w
  }.flatten.uniq
end

.isbn_show(record) ⇒ Array<String>

Get ISBN values for display from the 020 field and related 880 field.



36
37
38
39
40
41
42
43
 
# File 'lib/pennmarc/helpers/identifier.rb', line 36

def isbn_show(record)
  values = record.fields('020').filter_map do |field|
    joined_isbn = join_subfields(field, &subfield_in?(%w[a]))
    joined_isbn.presence
  end
  isbn_values = values + linked_alternate(record, '020', &subfield_in?(%w[a]))
  isbn_values.uniq
end

.issn_show(record) ⇒ Array<String>

Get ISSN values for display from the 022 field and related 880 field.



50
51
52
53
54
55
56
57
 
# File 'lib/pennmarc/helpers/identifier.rb', line 50

def issn_show(record)
  values = record.fields('022').filter_map do |field|
    joined_issn = join_subfields(field, &subfield_in?(%w[a]))
    joined_issn.presence
  end
  issn_values = values + linked_alternate(record, '022', &subfield_in?(%w[a]))
  issn_values.uniq
end

.isxn_search(record) ⇒ Array<String>

Get normalized ISXN values for searching of a record. Values aggregated from subfield ‘a’ and ‘z’ of the 020 field, and subfield ‘a’, ‘l’, and ‘z’ of the the 022 field.



21
22
23
24
25
26
27
28
29
 
# File 'lib/pennmarc/helpers/identifier.rb', line 21

def isxn_search(record)
  record.fields(%w[020 022]).filter_map { |field|
    if field.tag == '020'
      field.filter_map { |subfield| normalize_isbn(subfield.value) if subfield_in?(%w[a z]).call(subfield) }
    else
      field.filter_map { |subfield| subfield.value if subfield_in?(%w[a l m y z]).call(subfield) }
    end
  }.flatten.uniq
end

.mmsid(record) ⇒ String

Get Alma MMS ID value



11
12
13
 
# File 'lib/pennmarc/helpers/identifier.rb', line 11

def mmsid(record)
  record.fields('001').first.value
end

.oclc_id_search(record) ⇒ Array<String>

Retrieve valid and invalid numeric OCLC IDs from 035 field for search.



86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
 
# File 'lib/pennmarc/helpers/identifier.rb', line 86

def oclc_id_search(record)
  record.fields('035').flat_map { |field|
    field.filter_map do |subfield|
      # skip unless subfield 'a' or 'z'
      next unless subfield.code.in?(%w[a z])

      # skip unless subfield value matches OCLC ID
      next unless subfield_is_oclc?(subfield)

      # search for numeric part of oclc id
      match = match_oclc_number(subfield)

      # skip unless search to find numeric part of oclc id has a match
      next unless match

      match[1]
    end
  }.uniq
end

.oclc_id_show(record) ⇒ String?

Get numeric OCLC ID of first 035 field with an OCLC ID defined in subfield ‘a’.



63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
 
# File 'lib/pennmarc/helpers/identifier.rb', line 63

def oclc_id_show(record)
  ids = Array.wrap(record.fields('035')
                     .find { |field| field.any? { |subfield| subfield_a_is_oclc?(subfield) } })
  ids.flat_map { |field|
    field.filter_map do |subfield|
      # skip unless subfield 'a' is an oclc id value
      next unless subfield_a_is_oclc?(subfield)

      # search for numeric part of oclc id (e.g. '610094484' in '(OCoLC)ocn610094484')
      match = match_oclc_number(subfield)

      # skip unless search to find numeric part of oclc id has a match
      next unless match

      match[1]
    end
  }.first
end

.publisher_number_search(record) ⇒ Array<String>

Get publisher issued identifiers for searching of a record. Values extracted from fields 024 and 028.



131
132
133
134
135
136
 
# File 'lib/pennmarc/helpers/identifier.rb', line 131

def publisher_number_search(record)
  record.fields(%w[024 028]).filter_map { |field|
    joined_identifiers = join_subfields(field, &subfield_in?(%w[a]))
    joined_identifiers.presence
  }.uniq
end

.publisher_number_show(record) ⇒ Array<string>

Get publisher issued identifiers from fields 024, 028, and related 880 field. We do not return DOI values stored in 024 ǂ2, see doi_show for parsing DOI values.



113
114
115
116
117
118
119
120
121
122
123
124
 
# File 'lib/pennmarc/helpers/identifier.rb', line 113

def publisher_number_show(record)
  record.fields(%w[024 028 880]).filter_map { |field|
    next if field.tag == '880' && no_subfield_value_matches?(field, '6', /^(024|028)/)

    # do not return doi values from 024 ǂ2
    if field.tag == '024' && subfield_value_in?(field, '2', %w[doi])
      join_subfields(field, &subfield_not_in?(%w[a 2 5 6])).presence
    else
      join_subfields(field, &subfield_not_in?(%w[5 6])).presence
    end
  }.uniq
end