Module: Bolognese::Readers::DataciteReader
- Included in:
- MetadataUtils
- Defined in:
- lib/bolognese/readers/datacite_reader.rb
Instance Method Summary collapse
- #datacite_date(dates, date_type) ⇒ Object
- #datacite_funder_contributor(meta) ⇒ Object
- #datacite_funding_reference(meta) ⇒ Object
- #datacite_has_part(meta) ⇒ Object
- #datacite_is_identical_to(meta) ⇒ Object
- #datacite_is_new_version_of(meta) ⇒ Object
- #datacite_is_original_form_of(meta) ⇒ Object
- #datacite_is_part_of(meta) ⇒ Object
- #datacite_is_previous_version_of(meta) ⇒ Object
- #datacite_is_referenced_by(meta) ⇒ Object
- #datacite_is_reviewed_by(meta) ⇒ Object
- #datacite_is_supplement_to(meta) ⇒ Object
- #datacite_is_supplemented_by(meta) ⇒ Object
- #datacite_is_variant_form_of(meta) ⇒ Object
- #datacite_references(meta) ⇒ Object
- #datacite_related_identifier(meta, relation_type: nil) ⇒ Object
- #datacite_reviews(meta) ⇒ Object
- #get_datacite(id: nil, **options) ⇒ Object
- #read_datacite(string: nil, **options) ⇒ Object
Instance Method Details
#datacite_date(dates, date_type) ⇒ Object
147 148 149 150 |
# File 'lib/bolognese/readers/datacite_reader.rb', line 147 def datacite_date(dates, date_type) dd = dates.find { |d| d["dateType"] == date_type } || {} dd.fetch("__content__", nil) end |
#datacite_funder_contributor(meta) ⇒ Object
170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 |
# File 'lib/bolognese/readers/datacite_reader.rb', line 170 def datacite_funder_contributor() Array.wrap(.dig("contributors", "contributor")).reduce([]) do |sum, f| if f["contributorType"] == "Funder" # handle special case of OpenAIRE metadata id = f.dig("nameIdentifier", "__content__").to_s.start_with?("info:eu-repo/grantAgreement/EC") ? "https://doi.org/10.13039/501100000780" : nil funder = { "type" => "Organization", "id" => id, "name" => f["contributorName"] }.compact if f.dig("nameIdentifier", "nameIdentifierScheme") == "info" sum << { "type" => "Award", "identifier" => f.dig("nameIdentifier", "__content__").split("/").last, "funder" => funder } else sum << funder end else sum end end end |
#datacite_funding_reference(meta) ⇒ Object
152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 |
# File 'lib/bolognese/readers/datacite_reader.rb', line 152 def datacite_funding_reference() Array.wrap(.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["awardNumber"].is_a?(Hash) ? f.dig("awardNumber", "__content__") : f["awardNumber"], "url" => f["awardNumber"].is_a?(Hash) ? f.dig("awardNumber", "awardURI") : nil, "funder" => funder }.compact else funder end end.uniq end |
#datacite_has_part(meta) ⇒ Object
207 208 209 |
# File 'lib/bolognese/readers/datacite_reader.rb', line 207 def datacite_has_part() (, relation_type: "HasPart") end |
#datacite_is_identical_to(meta) ⇒ Object
199 200 201 |
# File 'lib/bolognese/readers/datacite_reader.rb', line 199 def datacite_is_identical_to() (, relation_type: "IsIdenticalTo") end |
#datacite_is_new_version_of(meta) ⇒ Object
215 216 217 |
# File 'lib/bolognese/readers/datacite_reader.rb', line 215 def datacite_is_new_version_of() (, relation_type: "IsNewVersionOf") end |
#datacite_is_original_form_of(meta) ⇒ Object
223 224 225 |
# File 'lib/bolognese/readers/datacite_reader.rb', line 223 def datacite_is_original_form_of() (, relation_type: "IsOriginalFormOf") end |
#datacite_is_part_of(meta) ⇒ Object
203 204 205 |
# File 'lib/bolognese/readers/datacite_reader.rb', line 203 def datacite_is_part_of() (, relation_type: "IsPartOf") end |
#datacite_is_previous_version_of(meta) ⇒ Object
211 212 213 |
# File 'lib/bolognese/readers/datacite_reader.rb', line 211 def datacite_is_previous_version_of() (, relation_type: "IsPreviousVersionOf") end |
#datacite_is_referenced_by(meta) ⇒ Object
231 232 233 |
# File 'lib/bolognese/readers/datacite_reader.rb', line 231 def datacite_is_referenced_by() (, relation_type: "IsCitedBy IsReferencedBy").presence end |
#datacite_is_reviewed_by(meta) ⇒ Object
247 248 249 |
# File 'lib/bolognese/readers/datacite_reader.rb', line 247 def datacite_is_reviewed_by() (, relation_type: "IsReviewedBy").presence end |
#datacite_is_supplement_to(meta) ⇒ Object
235 236 237 |
# File 'lib/bolognese/readers/datacite_reader.rb', line 235 def datacite_is_supplement_to() (, relation_type: "IsSupplementTo") end |
#datacite_is_supplemented_by(meta) ⇒ Object
239 240 241 |
# File 'lib/bolognese/readers/datacite_reader.rb', line 239 def datacite_is_supplemented_by() (, relation_type: "isSupplementedBy") end |
#datacite_is_variant_form_of(meta) ⇒ Object
219 220 221 |
# File 'lib/bolognese/readers/datacite_reader.rb', line 219 def datacite_is_variant_form_of() (, relation_type: "IsVariantFormOf") end |
#datacite_references(meta) ⇒ Object
227 228 229 |
# File 'lib/bolognese/readers/datacite_reader.rb', line 227 def datacite_references() (, relation_type: "References Cites").presence end |
#datacite_related_identifier(meta, relation_type: nil) ⇒ Object
192 193 194 195 196 197 |
# File 'lib/bolognese/readers/datacite_reader.rb', line 192 def (, relation_type: nil) arr = Array.wrap(.dig("relatedIdentifiers", "relatedIdentifier")).select { |r| %w(DOI URL).include?(r["relatedIdentifierType"]) } arr = arr.select { |r| relation_type.split(" ").include?(r["relationType"]) } if relation_type.present? arr.map { |work| { "type" => "CreativeWork", "id" => normalize_id(work["__content__"]) } }.unwrap end |
#datacite_reviews(meta) ⇒ Object
243 244 245 |
# File 'lib/bolognese/readers/datacite_reader.rb', line 243 def datacite_reviews() (, relation_type: "Reviews").presence end |
#get_datacite(id: nil, **options) ⇒ Object
6 7 8 9 10 11 12 13 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 |
# File 'lib/bolognese/readers/datacite_reader.rb', line 6 def get_datacite(id: nil, **) return { "string" => nil, "state" => "not_found" } unless id.present? search_url = doi_search(id, ) doi = doi_from_url(id) params = { q: doi, fl: "doi,url,xml,state,allocator_symbol,datacentre_symbol,media,minted,updated", defType: "edismax", wt: "json" } search_url += "?" + URI.encode_www_form(params) response = Maremma.get search_url attributes = response.body.dig("data", "response", "docs").first return { "string" => nil, "state" => "not_found" } unless attributes.present? string = attributes.fetch('xml', nil) string = Base64.decode64(string) if string.present? if string.present? doc = Nokogiri::XML(string, nil, 'UTF-8', &:noblanks) # remove leading and trailing whitespace in text nodes doc.xpath("//text()").each do |node| if node.content =~ /\S/ node.content = node.content.strip else node.remove end end string = doc.to_xml(:indent => 2) end { "string" => string, "b_url" => attributes.fetch("url", nil), "state" => attributes.fetch("state", nil), "date_registered" => attributes.fetch("minted", nil), "date_updated" => attributes.fetch("updated", nil), "provider_id" => attributes.fetch("allocator_symbol", nil), "client_id" => attributes.fetch("datacentre_symbol", nil) } end |
#read_datacite(string: nil, **options) ⇒ Object
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 |
# File 'lib/bolognese/readers/datacite_reader.rb', line 47 def read_datacite(string: nil, **) = Maremma.from_xml(string).to_h.fetch("resource", {}) schema_version = .fetch("xmlns", nil) # validate only when option is set, as this step is expensive and # not needed if XML comes from DataCite MDS if [:validate] errors = datacite_errors(xml: string, schema_version: schema_version) return { "errors" => errors } if errors.present? end if [:doi] id = normalize_doi([:doi], sandbox: [:sandbox]) else id = normalize_doi(.dig("identifier", "__content__") || [:id], sandbox: [:sandbox]) end doi = doi_from_url(id) resource_type_general = .dig("resourceType", "resourceTypeGeneral") additional_type = .fetch("resourceType", {}).fetch("__content__", nil) type = Bolognese::Utils::CR_TO_SO_TRANSLATIONS[additional_type.to_s.underscore.camelcase] || Bolognese::Utils::DC_TO_SO_TRANSLATIONS[resource_type_general.to_s.dasherize] || "CreativeWork" title = Array.wrap(.dig("titles", "title")).map do |r| if r.is_a?(String) sanitize(r) else { "title_type" => r["titleType"], "lang" => r["xml:lang"], "text" => sanitize(r["__content__"]) }.compact end end.unwrap container_title = Array.wrap(.dig("descriptions", "description")).find { |r| r["descriptionType"] == "SeriesInformation" }.to_h.fetch("__content__", nil) alternate_name = Array.wrap(.dig("alternateIdentifiers", "alternateIdentifier")).map do |r| { "type" => r["alternateIdentifierType"], "name" => r["__content__"] }.compact end.unwrap description = Array.wrap(.dig("descriptions", "description")).select { |r| r["descriptionType"] != "SeriesInformation" }.map do |r| { "type" => r["descriptionType"], "text" => sanitize(r["__content__"]) }.compact end.unwrap license = Array.wrap(.dig("rightsList", "rights")).map do |r| { "id" => normalize_url(r["rightsURI"]), "name" => r["__content__"] }.compact end.unwrap keywords = Array.wrap(.dig("subjects", "subject")).map do |k| if k.nil? nil elsif k.is_a?(String) sanitize(k) else { "subject_scheme" => k["subjectScheme"], "scheme_uri" => k["schemeURI"], "text" => sanitize(k["__content__"]) }.compact end end.compact dates = Array.wrap(.dig("dates", "date")) funding = begin f = datacite_funder_contributor() + datacite_funding_reference() f.length > 1 ? f : f.first end state = doi.present? ? "findable" : "not_found" { "id" => id, "type" => type, "additional_type" => additional_type, "citeproc_type" => Bolognese::Utils::CR_TO_CP_TRANSLATIONS[additional_type.to_s.underscore.camelcase] || Bolognese::Utils::SO_TO_CP_TRANSLATIONS[type] || "article", "bibtex_type" => Bolognese::Utils::CR_TO_BIB_TRANSLATIONS[additional_type.to_s.underscore.camelcase] || Bolognese::Utils::SO_TO_BIB_TRANSLATIONS[type] || "misc", "ris_type" => Bolognese::Utils::CR_TO_RIS_TRANSLATIONS[additional_type.to_s.underscore.camelcase] || Bolognese::Utils::DC_TO_RIS_TRANSLATIONS[resource_type_general.to_s.dasherize] || "GEN", "resource_type_general" => resource_type_general, "doi" => doi, "url" => .fetch(:url, nil), "title" => title, "alternate_name" => alternate_name, "author" => (Array.wrap(.dig("creators", "creator"))), "editor" => (Array.wrap(.dig("contributors", "contributor")).select { |r| r["contributorType"] == "Editor" }), "container_title" => container_title, "publisher" => .fetch("publisher", nil), "service_provider" => "DataCite", "funding" => funding, "is_identical_to" => datacite_is_identical_to(), "is_part_of" => datacite_is_part_of(), "has_part" => datacite_has_part(), "references" => datacite_references(), "is_referenced_by" => datacite_is_referenced_by(), "is_supplement_to" => datacite_is_supplement_to(), "is_supplemented_by" => datacite_is_supplemented_by(), "date_created" => datacite_date(dates, "Created"), "date_accepted" => datacite_date(dates, "Accepted"), "date_available" => datacite_date(dates, "Available"), "date_copyrighted" => datacite_date(dates, "Copyrightes"), "date_collected" => datacite_date(dates, "Collected"), "date_submitted" => datacite_date(dates, "Submitted"), "date_valid" => datacite_date(dates, "Valid"), "date_published" => datacite_date(dates, "Issued") || .fetch("publicationYear", nil), "date_modified" => datacite_date(dates, "Updated"), "description" => description, "license" => license, "b_version" => .fetch("version", nil), "keywords" => keywords, "language" => .fetch("language", nil), "content_size" => .fetch("size", nil), "schema_version" => schema_version, "state" => state } end |