Module: Commonmeta::Readers::CrossrefXmlReader
- Included in:
- MetadataUtils
- Defined in:
- lib/commonmeta/readers/crossref_xml_reader.rb
Instance Method Summary collapse
- #crossref_alternate_identifiers(bibmeta) ⇒ Object
- #crossref_date_published(bibmeta) ⇒ Object
- #crossref_description(bibmeta) ⇒ Object
- #crossref_funding_reference(program_metadata) ⇒ Object
- #crossref_license(program_metadata) ⇒ Object
- #crossref_people(bibmeta, contributor_role) ⇒ Object
- #crossref_references(bibmeta) ⇒ Object
-
#get_crossref_xml(id: nil, **_options) ⇒ Object
CrossRef types from api.crossref.org/types.
- #read_crossref_xml(string: nil, **options) ⇒ Object
Instance Method Details
#crossref_alternate_identifiers(bibmeta) ⇒ Object
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 |
# File 'lib/commonmeta/readers/crossref_xml_reader.rb', line 212 def crossref_alternate_identifiers() if .dig('publisher_item', 'item_number').present? Array.wrap(.dig('publisher_item', 'item_number')).map do |item| if item.is_a?(String) { 'alternateIdentifier' => item, 'alternateIdentifierType' => 'Publisher ID' } else { 'alternateIdentifier' => item.fetch('__content__', nil), 'alternateIdentifierType' => item.fetch('item_number_type', nil) || 'Publisher ID' } end end elsif parse_attributes(.fetch('item_number', nil)).present? [{ 'alternateIdentifier' => parse_attributes(.fetch('item_number', nil)), 'alternateIdentifierType' => parse_attributes(.dig('item_number', 'item_number_type')) || 'Publisher ID' }] elsif parse_attributes(.fetch('isbn', nil)).present? [{ 'alternateIdentifier' => parse_attributes(.fetch('isbn', nil), first: true), 'alternateIdentifierType' => 'ISBN' }] else [] end end |
#crossref_date_published(bibmeta) ⇒ Object
344 345 346 347 348 349 350 |
# File 'lib/commonmeta/readers/crossref_xml_reader.rb', line 344 def crossref_date_published() pub_date = Array.wrap(.fetch('publication_date', nil)).presence || Array.wrap(.fetch('acceptance_date', nil)) return unless pub_date.present? get_date_from_parts(pub_date.first['year'], pub_date.first['month'], pub_date.first['day']) end |
#crossref_description(bibmeta) ⇒ Object
235 236 237 238 239 240 241 242 243 244 245 246 |
# File 'lib/commonmeta/readers/crossref_xml_reader.rb', line 235 def crossref_description() abstract = Array.wrap(['abstract']).map do |r| { 'descriptionType' => r.fetch('abstract_type', nil).present? ? 'Other' : 'Abstract', 'description' => sanitize(parse_attributes(r, content: 'p'), first: true) }.compact end description = Array.wrap(['description']).map do |r| { 'descriptionType' => 'Other', 'description' => sanitize(parse_attributes(r)) }.compact end (abstract + description) end |
#crossref_funding_reference(program_metadata) ⇒ Object
308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 |
# File 'lib/commonmeta/readers/crossref_xml_reader.rb', line 308 def crossref_funding_reference() fundref = Array.wrap().find { |a| a['name'] == 'fundref' } || {} Array.wrap(fundref.fetch('assertion', [])).select do |a| a['name'] == 'fundgroup' && a['assertion'].present? end.map do |f| funder_identifier = nil funder_identifier_type = nil funder_name = nil award_title = nil award_number = nil award_uri = nil Array.wrap(f.fetch('assertion')).each do |a| case a.fetch('name') when 'award_number' award_number = a.fetch('__content__', nil) award_uri = a.fetch('awardURI', nil) when 'funder_name' funder_name = a.fetch('__content__', nil).to_s.squish.presence funder_identifier = validate_funder_doi(a.dig('assertion', '__content__')) funder_identifier_type = 'Crossref Funder ID' if funder_identifier.present? end end # funder_name is required in DataCite next unless funder_name.present? { 'funderIdentifier' => funder_identifier, 'funderIdentifierType' => funder_identifier_type, 'funderName' => funder_name, 'awardTitle' => award_title, 'awardNumber' => award_number, 'awardUri' => award_uri }.compact end.compact end |
#crossref_license(program_metadata) ⇒ Object
248 249 250 251 252 253 254 255 |
# File 'lib/commonmeta/readers/crossref_xml_reader.rb', line 248 def crossref_license() access_indicator = Array.wrap().find { |m| m['name'] == 'AccessIndicators' } return unless access_indicator.present? Array.wrap(access_indicator['license_ref']).reduce({}) do |sum, license| sum.merge!(hsh_to_spdx('rightsURI' => parse_attributes(license))) end end |
#crossref_people(bibmeta, contributor_role) ⇒ Object
257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 |
# File 'lib/commonmeta/readers/crossref_xml_reader.rb', line 257 def crossref_people(, contributor_role) person = .dig('contributors', 'person_name') || ['person_name'] organization = Array.wrap(.dig('contributors', 'organization')) if contributor_role == 'author' && Array.wrap(person).select do |a| a['contributor_role'] == 'author' end.blank? && Array.wrap(organization).select do |a| a['contributor_role'] == 'author' end.blank? person = [{ 'name' => ':(unav)', 'contributor_role' => 'author' }] end (Array.wrap(person) + Array.wrap(organization)).select do |a| a['contributor_role'] == contributor_role end.map do |a| id = parse_attributes(a['ORCID']) ? normalize_orcid(parse_attributes(a['ORCID'])) : nil if a['surname'].present? || a['given_name'].present? given_name = parse_attributes(a['given_name']).presence family_name = parse_attributes(a['surname']).presence affiliation = Array.wrap(a['affiliation']).map do |a| if a.is_a?(Hash) && a.key?('__content__') && a['__content__'].strip.blank? nil elsif a.is_a?(Hash) && a.key?('__content__') { 'name' => a['__content__'] } elsif a.is_a?(Hash) a elsif a.strip.blank? nil elsif a.is_a?(String) { 'name' => a } end end.compact { 'type' => 'Person', 'id' => id, 'name' => if given_name || family_name nil else [family_name, given_name].compact.join(', ') end, 'givenName' => given_name, 'familyName' => family_name, 'affiliation' => affiliation.presence, 'contributorType' => contributor_role == 'editor' ? 'Editor' : nil }.compact else { 'type' => 'Organization', 'name' => a['name'] || a['__content__'], 'contributorType' => contributor_role == 'editor' ? 'Editor' : nil }.compact end end end |
#crossref_references(bibmeta) ⇒ Object
352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 |
# File 'lib/commonmeta/readers/crossref_xml_reader.rb', line 352 def crossref_references() refs = .dig('citation_list', 'citation') Array.wrap(refs).map do |reference| return nil unless reference.present? || !reference.is_a?(Hash) doi = parse_attributes(reference.dig('doi')) { 'key' => reference.dig('key'), 'doi' => doi ? normalize_doi(doi) : nil, 'creator' => reference.dig('author'), 'title' => reference.dig('article_title'), 'publisher' => reference.dig('publisher'), 'publicationYear' => reference.dig('cYear'), 'volume' => reference.dig('volume'), 'issue' => reference.dig('issue'), 'firstPage' => reference.dig('first_page'), 'lastPage' => reference.dig('last_page'), 'containerTitle' => reference.dig('journal_title'), 'edition' => nil, 'contributor' => nil, 'unstructured' => doi.nil? ? reference.dig('unstructured') : nil }.compact end.unwrap end |
#get_crossref_xml(id: nil, **_options) ⇒ Object
CrossRef types from api.crossref.org/types
7 8 9 10 11 12 13 14 15 16 |
# File 'lib/commonmeta/readers/crossref_xml_reader.rb', line 7 def get_crossref_xml(id: nil, **) return { 'string' => nil, 'state' => 'not_found' } unless id.present? doi = doi_from_url(id) api_url = "https://api.crossref.org/works/#{doi}/transform/application/vnd.crossref.unixsd+xml" response = HTTP.get(api_url) return { 'string' => nil, 'state' => 'not_found' } unless response.status.success? { 'string' => response.body.to_s } end |
#read_crossref_xml(string: nil, **options) ⇒ Object
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 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 |
# File 'lib/commonmeta/readers/crossref_xml_reader.rb', line 18 def read_crossref_xml(string: nil, **) = ActiveSupport::HashWithIndifferentAccess.new(.except(:doi, :id, :url, :sandbox, :validate, :ra)) if string.present? # query contains information from outside metadata schema, e.g. publisher name query = Hash.from_xml(string).dig('crossref_result', 'query_result', 'body', 'query') = query.dig('doi_record', 'crossref', 'error').nil? ? query.dig('doi_record') : {} else = {} query = {} end # model should be one of book, conference, database, dissertation, journal, peer_review, posted_content, # report_paper, sa_component, standard model = ['crossref'].to_h.keys.first resource_type = nil = {} = {} = nil journal_issue = {} = nil publisher = query.dig('crm_item', 0) publisher = nil unless publisher.is_a?(String) case model when 'book' = .dig('crossref', 'book', 'book_metadata') = .dig('crossref', 'book', 'book_series_metadata') = .dig('crossref', 'book', 'book_set_metadata') = .dig('crossref', 'book', 'content_item') || || || resource_type = if .fetch('component_type', nil) "book-#{.fetch('component_type')}" else 'book' end # publisher = if book_metadata.present? # book_metadata.dig("publisher", "publisher_name") # elsif book_series_metadata.present? # book_series_metadata.dig("publisher", "publisher_name") # end when 'conference' = .dig('crossref', 'conference', 'event_metadata') || {} = .dig('crossref', 'conference', 'conference_paper').to_h when 'journal' = .dig('crossref', 'journal', 'journal_metadata') || {} journal_issue = .dig('crossref', 'journal', 'journal_issue') || {} journal_article = .dig('crossref', 'journal', 'journal_article') || {} = journal_article.presence || journal_issue.presence || = .dig('crossmark', 'custom_metadata', 'program') || ['program'] resource_type = if journal_article.present? 'journal_article' elsif journal_issue.present? 'journal_issue' else 'journal' end when 'posted_content' = .dig('crossref', 'posted_content').to_h publisher ||= .dig('institution', 'institution_name') when 'sa_component' = .dig('crossref', 'sa_component', 'component_list', 'component').to_h = Array.wrap(query.to_h['crm_item']).find do |cr| cr['name'] == 'relation' end = { 'relatedIdentifier' => .to_h.fetch('__content', nil) } when 'database' = .dig('crossref', 'database', 'dataset').to_h resource_type = 'dataset' when 'report_paper' = .dig('crossref', 'report_paper', 'report_paper_metadata').to_h resource_type = 'report' when 'peer_review' = .dig('crossref', 'peer_review') when 'dissertation' = .dig('crossref', 'dissertation') end resource_type = (resource_type || model).to_s.underscore.camelcase.presence resource_type = resource_type.present? ? resource_type.underscore.camelcase : nil type = Commonmeta::Utils::CR_TO_CM_TRANSLATIONS.fetch(resource_type, 'Other') titles = if ['titles'].present? Array.wrap(['titles']).map do |r| if r.blank? || (r['title'].blank? && r['original_language_title'].blank?) nil elsif r['title'].is_a?(String) { 'title' => sanitize(r['title']) } elsif r['original_language_title'].present? { 'title' => sanitize(r.dig('original_language_title', '__content__')), 'lang' => r.dig('original_language_title', 'language') } else # TODO: handle titles with <i> and <b> tags { 'title' => sanitize(r.dig('title', '__content__')) }.compact end end.compact else [{ 'title' => ':(unav)' }] end date = {} date['published'] = crossref_date_published() # || Array.wrap(query.to_h["crm_item"]).find { |cr| cr["name"] == "created" } date['updated'] = parse_attributes(Array.wrap(query.to_h['crm_item']).find do |cr| cr['name'] == 'last-update' end) date['registered'] = Array.wrap(query.to_h['crm_item']).find do |cr| cr['name'] == 'deposit-timestamp' end if date['registered'].present? date['registered'] = get_datetime_from_time(parse_attributes(date['registered'])) end # check that date is valid iso8601 date date['published'] = nil unless Date.edtf(date['published']).present? date['updated'] = nil unless Date.edtf(date['updated']).present? # TODO: fix timestamp. Until then, remove time as this is not always stable with Crossref (different server timezones) date['published'] = get_iso8601_date(date['published']) if date['published'].present? date['registered'] = get_iso8601_date(date['registered']) if date['registered'].present? date['updated'] = get_iso8601_date(date['updated']) if date['updated'].present? state = .present? || .present? ? 'findable' : 'not_found' references = Array.wrap(crossref_references()) container = if .present? issn = normalize_issn(.to_h.fetch('issn', nil)) { 'type' => 'Journal', 'identifier' => issn, 'identifierType' => issn.present? ? 'ISSN' : nil, 'title' => parse_attributes(.to_h['full_title']), 'volume' => parse_attributes(journal_issue.dig('journal_volume', 'volume')), 'issue' => parse_attributes(journal_issue['issue']), 'firstPage' => .dig('pages', 'first_page') || parse_attributes(journal_article.to_h.dig('publisher_item', 'item_number'), first: true), 'lastPage' => .dig('pages', 'last_page') }.compact # By using book_metadata, we can account for where resource_type is `BookChapter` and not assume its a whole book elsif .present? identifiers = crossref_alternate_identifiers() { 'type' => 'Book', 'title' => .dig('titles', 'title'), 'firstPage' => .dig('pages', 'first_page'), 'lastPage' => .dig('pages', 'last_page'), 'identifiers' => identifiers }.compact elsif .to_h.fetch('series_metadata', nil).present? issn = normalize_issn(.dig('series_metadata', 'issn')) { 'type' => 'Book Series', 'identifier' => issn, 'identifierType' => issn.present? ? 'ISSN' : nil, 'title' => .dig('series_metadata', 'titles', 'title'), 'volume' => .fetch('volume', nil) }.compact end id = normalize_doi([:doi] || [:id] || .dig('doi_data', 'doi')) # Let sections override this in case of alternative metadata structures, such as book chapters, which # have their meta inside `content_item`, but the main book indentifers inside of `book_metadata` alternate_identifiers ||= crossref_alternate_identifiers() url = parse_attributes(.dig('doi_data', 'resource'), first: true) url = normalize_url(url) if url.present? { 'id' => id, 'type' => type, 'url' => url, 'titles' => titles, 'alternate_identifiers' => alternate_identifiers, 'creators' => crossref_people(, 'author'), 'contributors' => crossref_people(, 'editor'), 'funding_references' => crossref_funding_reference(), 'publisher' => { 'name' => publisher }, 'container' => container, 'provider' => provider = [:ra] || get_doi_ra(id) || 'Crossref', 'references' => references, 'date' => date.compact, 'descriptions' => crossref_description(), 'license' => crossref_license(), 'version' => nil, 'subjects' => nil, 'language' => nil, 'sizes' => nil, 'state' => state }.compact.merge() end |