Module: Bolognese::Readers::CrossrefReader

Included in:
MetadataUtils
Defined in:
lib/bolognese/readers/crossref_reader.rb

Constant Summary collapse

CONTACT_EMAIL =

CrossRef types from api.crossref.org/types

"[email protected]"

Instance Method Summary collapse

Instance Method Details

#crossref_alternate_identifier(bibliographic_metadata) ⇒ Object 



119
120
121
122
123
124
125
 
# File 'lib/bolognese/readers/crossref_reader.rb', line 119

def crossref_alternate_identifier(bibliographic_metadata)
  if bibliographic_metadata.fetch("publisher_item", nil).present?
    parse_attributes(bibliographic_metadata.dig("publisher_item", "item_number"))
  else
    parse_attributes(bibliographic_metadata.fetch("item_number", nil))
  end
end

#crossref_date_published(bibliographic_metadata) ⇒ Object

def datacite_funding_reference(meta)

Array.wrap(meta.dig("fundingReferences", "fundingReference")).map do |f|
  funder_id = parse_attributes(f["funderIdentifier"])
  funder = { "type" => "Organization",
             "id" => normalize_id(funder_id),
             "name" => f["funderName"] }.compact
  if f["awardNumber"].present? || f["awardTitle"].present?
    { "type" => "Award",
      "name" => f.fetch("awardTitle", nil),
      "identifier" => f.dig("awardNumber", "__content__"),
      "url" => f.dig("awardNumber", "awardURI"),
      "funder" => funder }
  else
    funder
  end
end.uniq

end



202
203
204
205
206
207
208
209
210
 
# File 'lib/bolognese/readers/crossref_reader.rb', line 202

def crossref_date_published(bibliographic_metadata)
  pub_date = Array.wrap(bibliographic_metadata.fetch("publication_date", nil)).presence ||
    Array.wrap(bibliographic_metadata.fetch("acceptance_date", nil))
  if pub_date.present?
    get_date_from_parts(pub_date.first["year"], pub_date.first["month"], pub_date.first["day"])
  else
    nil
  end
end

#crossref_description(bibliographic_metadata) ⇒ Object 



127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
 
# File 'lib/bolognese/readers/crossref_reader.rb', line 127

def crossref_description(bibliographic_metadata)
  abstract = Array.wrap(bibliographic_metadata.dig("abstract")).map do |r|
    { "type" => "Abstract", "text" => sanitize(parse_attributes(r, content: 'p')) }.compact
  end

  description = Array.wrap(bibliographic_metadata.dig("description")).map do |r|
    if abstract.present?
      { "text" => sanitize(parse_attributes(r)) }.compact
    else
      sanitize(parse_attributes(r))
    end
  end

  (abstract + description).unwrap
end

#crossref_funding_reference(program_metadata) ⇒ Object 



165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
 
# File 'lib/bolognese/readers/crossref_reader.rb', line 165

def crossref_funding_reference(program_metadata)
  fundref = Array.wrap(program_metadata).find { |a| a["name"] == "fundref" } || {}
  Array.wrap(fundref.fetch("assertion", [])).select { |a| a["name"] == "fundgroup" }.map do |f|
    f = Array.wrap(f.fetch("assertion", nil)).first
    funder = { "type" => "Organization",
               "id" => normalize_id(f.dig("assertion", "__content__")),
               "name" => f.dig("__content__").strip }.compact
     if f["awardNumber"].present? || f["awardTitle"].present?
       { "type" => "Award",
         "name" => f.fetch("awardTitle", nil),
         "identifier" => f.dig("awardNumber", "__content__"),
         "url" => f.dig("awardNumber", "awardURI"),
         "funder" => funder }
     else
       funder
     end
  end.unwrap
end

#crossref_is_part_of(model_metadata) ⇒ Object 



212
213
214
215
216
217
218
219
220
 
# File 'lib/bolognese/readers/crossref_reader.rb', line 212

def crossref_is_part_of(model_metadata)
  if model_metadata.present?
    { "type" => "Periodical",
      "title" => model_metadata["full_title"],
      "issn" => parse_attributes(model_metadata.fetch("issn", nil), first: true) }.compact
  else
    nil
  end
end

#crossref_license(program_metadata) ⇒ Object 



143
144
145
146
147
148
149
150
151
152
 
# File 'lib/bolognese/readers/crossref_reader.rb', line 143

def crossref_license(program_metadata)
  access_indicator = Array.wrap(program_metadata).find { |m| m["name"] == "AccessIndicators" }
  if access_indicator.present?
    Array.wrap(access_indicator["license_ref"]).map do |license|
      { "id" => normalize_url(parse_attributes(license)) }
    end.uniq.unwrap
  else
    nil
  end
end

#crossref_people(bibliographic_metadata, contributor_role) ⇒ Object 



154
155
156
157
158
159
160
161
162
163
 
# File 'lib/bolognese/readers/crossref_reader.rb', line 154

def crossref_people(bibliographic_metadata, contributor_role)
  person = bibliographic_metadata.dig("contributors", "person_name")
  Array.wrap(person).select { |a| a["contributor_role"] == contributor_role }.map do |a|
    { "type" => "Person",
      "id" => parse_attributes(a["ORCID"]),
      "name" => [a["given_name"], a["surname"]].join(" "),
      "givenName" => a["given_name"],
      "familyName" => a["surname"] }.compact
  end.unwrap
end

#crossref_references(bibliographic_metadata) ⇒ Object 



222
223
224
225
226
227
228
229
 
# File 'lib/bolognese/readers/crossref_reader.rb', line 222

def crossref_references(bibliographic_metadata)
   refs = bibliographic_metadata.dig("citation_list", "citation")
   Array.wrap(refs).select { |a| a["doi"].present? }.map do |c|
     { "type" => "CreativeWork",
       "id" => normalize_id(parse_attributes(c["doi"])),
       "title" => c["article_title"] }.compact
   end.unwrap
end

#get_crossref(id: nil, **options) ⇒ Object 



10
11
12
13
14
15
16
17
18
19
20
 
# File 'lib/bolognese/readers/crossref_reader.rb', line 10

def get_crossref(id: nil, **options)
  return { "string" => nil, "state" => "not_found" } unless id.present?

  doi = doi_from_url(id)
  url = "http://www.crossref.org/openurl/?id=doi:#{doi}&noredirect=true&pid=#{CONTACT_EMAIL}&format=unixref"
  response = Maremma.get(url, accept: "text/xml", raw: true)
  string = response.body.fetch("data", nil)
  string = Nokogiri::XML(string, nil, 'UTF-8', &:noblanks).to_s if string.present?

  { "string" => string }
end

#read_crossref(string: nil, **options) ⇒ Object 



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
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
 
# File 'lib/bolognese/readers/crossref_reader.rb', line 22

def read_crossref(string: nil, **options)
  if string.present?
    m = Maremma.from_xml(string).dig("doi_records", "doi_record") || {}
    meta = m.dig("crossref", "error").nil? ? m : {}
  else
    meta = {}
  end

  # model should be one of book, conference, database, dissertation, journal, peer_review, posted_content,
  # report-paper, sa_component, standard
  model = meta.dig("crossref").to_h.keys.first

  additional_type = nil
  bibliographic_metadata = {}
  program_metadata = {}
  journal_metadata = nil
  journal_issue = {}
  publisher = nil

  case model
  when "book"
    book_metadata = meta.dig("crossref", "book", "book_metadata")
    book_series_metadata = meta.dig("crossref", "book", "book_series_metadata")
    book_set_metadata = meta.dig("crossref", "book", "book_set_metadata")
    bibliographic_metadata = meta.dig("crossref", "book", "content_item").to_h
    additional_type = bibliographic_metadata.fetch("component_type", nil) ? "book-" + bibliographic_metadata.fetch("component_type") : "book"
    publisher = book_metadata.dig("publisher", "publisher_name")
  when "conference"
    event_metadata = meta.dig("crossref", "conference", "event_metadata") ||