Module: Bolognese::Readers::CrossrefReader

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

Constant Summary collapse

CR_TO_SO_TRANSLATIONS =

CrossRef types from api.crossref.org/types

{
  "Proceedings" => nil,
  "ReferenceBook" => "Book",
  "JournalIssue" => "PublicationIssue",
  "ProceedingsArticle" => nil,
  "Other" => "CreativeWork",
  "Dissertation" => "Thesis",
  "Dataset" => "Dataset",
  "EditedBook" => "Book",
  "JournalArticle" => "ScholarlyArticle",
  "Journal" => nil,
  "Report" => nil,
  "BookSeries" => nil,
  "ReportSeries" => nil,
  "BookTrack" => nil,
  "Standard" => nil,
  "BookSection" => nil,
  "BookPart" => nil,
  "Book" => "Book",
  "BookChapter" => "Chapter",
  "StandardSeries" => nil,
  "Monograph" => "Book",
  "Component" => "CreativeWork",
  "ReferenceEntry" => nil,
  "JournalVolume" => "PublicationVolume",
  "BookSet" => nil,
  "PostedContent" => "ScholarlyArticle"
}
CR_TO_BIB_TRANSLATIONS =
{
  "Proceedings" => "proceedings",
  "ReferenceBook" => "book",
  "JournalIssue" => nil,
  "ProceedingsArticle" => nil,
  "Other" => nil,
  "Dissertation" => "phdthesis",
  "Dataset" => nil,
  "EditedBook" => "book",
  "JournalArticle" => "article",
  "Journal" => nil,
  "Report" => nil,
  "BookSeries" => nil,
  "ReportSeries" => nil,
  "BookTrack" => nil,
  "Standard" => nil,
  "BookSection" => "inbook",
  "BookPart" => nil,
  "Book" => "book",
  "BookChapter" => "inbook",
  "StandardSeries" => nil,
  "Monograph" => "book",
  "Component" => nil,
  "ReferenceEntry" => nil,
  "JournalVolume" => nil,
  "BookSet" => nil,
  "PostedContent" => "article"
}
CONTACT_EMAIL =
"[email protected]"

Instance Method Summary collapse

Instance Method Details

#crossref_alternate_name(bibliographic_metadata) ⇒ Object



170
171
172
173
174
175
176
# File 'lib/bolognese/readers/crossref_reader.rb', line 170

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



253
254
255
256
257
258
259
260
261
# File 'lib/bolognese/readers/crossref_reader.rb', line 253

def crossref_date_published()
  pub_date = Array.wrap(.fetch("publication_date", nil)).presence ||
    Array.wrap(.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



178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
# File 'lib/bolognese/readers/crossref_reader.rb', line 178

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

  description = Array.wrap(.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



216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
# File 'lib/bolognese/readers/crossref_reader.rb', line 216

def crossref_funding_reference()
  fundref = Array.wrap().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



263
264
265
266
267
268
269
270
271
# File 'lib/bolognese/readers/crossref_reader.rb', line 263

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

#crossref_license(program_metadata) ⇒ Object



194
195
196
197
198
199
200
201
202
203
# File 'lib/bolognese/readers/crossref_reader.rb', line 194

def crossref_license()
  access_indicator = Array.wrap().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



205
206
207
208
209
210
211
212
213
214
# File 'lib/bolognese/readers/crossref_reader.rb', line 205

def crossref_people(, contributor_role)
  person = .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



273
274
275
276
277
278
279
280
# File 'lib/bolognese/readers/crossref_reader.rb', line 273

def crossref_references()
   refs = .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



65
66
67
68
69
70
71
72
73
74
75
# File 'lib/bolognese/readers/crossref_reader.rb', line 65

def get_crossref(id: nil, **options)
  return nil 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



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
118
119
120
121
122
123
124
125
126
127
128
129
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
164
165
166
167
168
# File 'lib/bolognese/readers/crossref_reader.rb', line 77

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

  return meta unless meta["crossref"].present?

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

  additional_type = nil
   = {}
   = nil
  journal_issue = {}
  publisher = nil

  case model
  when "book"
     = meta.dig("crossref", "book", "book_metadata")
     = meta.dig("crossref", "book", "book_series_metadata")
     = meta.dig("crossref", "book", "book_set_metadata")
     = meta.dig("crossref", "book", "content_item") || {}
    additional_type = .fetch("component_type", nil) ? "book-" + .fetch("component_type") : "book"
    publisher = .dig("publisher", "publisher_name")
  when "conference"
     = meta.dig("crossref", "conference", "event_metadata") || {}
     = meta.dig("crossref", "conference", "conference_paper") || {}
  when "journal"
     = meta.dig("crossref", "journal", "journal_metadata") || {}
     = meta.dig("crossref", "journal", "journal_article") || {}
     = .dig("crossmark", "custom_metadata", "program") || .dig("program")
    journal_issue = meta.dig("crossref", "journal", "journal_issue") || {}
    journal_article = meta.dig("crossref", "journal", "journal_article") || {}

    additional_type = if journal_article.present?
                        "journal_article"
                      elsif journal_issue.present?
                        "journal_issue"
                      else
                        "journal"
                      end
  when "posted_content"
     = meta.dig("crossref", "posted_content") || {}
  when "sa_component"
     = meta.dig("crossref", "sa_component", "component_list", "component") || {}
  end

  additional_type = (additional_type || model).underscore.camelize
  type = CR_TO_SO_TRANSLATIONS[additional_type] || "ScholarlyArticle"
  doi = .dig("doi_data", "doi").to_s.downcase

  # Crossref servers run on Eastern Time
  Time.zone = 'Eastern Time (US & Canada)'
  date_modified = Time.zone.parse(meta.fetch("timestamp", "")).utc.iso8601

  { "id" => normalize_doi(doi),
    "type" => type,
    "additional_type" => additional_type,
    "citeproc_type" => Bolognese::Utils::CR_TO_CP_TRANSLATIONS[additional_type] || "article-journal",
    "bibtex_type" => CR_TO_BIB_TRANSLATIONS[additional_type] || "misc",
    "ris_type" => Bolognese::Utils::CR_TO_RIS_TRANSLATIONS[additional_type] || "JOUR",
    "resource_type_general" => Bolognese::Utils::SO_TO_DC_TRANSLATIONS[type],
    "doi" => doi,
    "url" => .dig("doi_data", "resource"),
    "title" => parse_attributes(.dig("titles", "title")),
    "alternate_name" => crossref_alternate_name(),
    "author" => crossref_people(, "author"),
    "editor" => crossref_people(, "editor"),
    "funding" => crossref_funding_reference(),
    "publisher" => publisher,
    "provider" => "Crossref",
    "is_part_of" => crossref_is_part_of(),
    "references" => crossref_references(),
    "date_published" => crossref_date_published(),
    "date_modified" => date_modified,
    "volume" => journal_issue.dig("journal_volume", "volume"),
    "issue" => journal_issue.dig("issue"),
    "first_page" => .dig("pages", "first_page"),
    "last_page" => .dig("pages", "last_page"),
    "description" => crossref_description(),
    "license" => crossref_license(),
    "version" => nil,
    "keywords" => nil,
    "language" => nil,
    "content_size" => nil,
    "schema_version" => nil
  }
end