Class: Toccatore::Base
- Inherits:
-
Object
- Object
- Toccatore::Base
- Defined in:
- lib/toccatore/base.rb
Direct Known Subclasses
Instance Method Summary collapse
-
#clean_doi(doi) ⇒ Object
remove non-printing whitespace.
- #cleanup_author(author) ⇒ Object
- #config_fields ⇒ Object
- #doi_as_url(doi) ⇒ Object
- #doi_from_url(url) ⇒ Object
-
#get_authors(authors, options = {}) ⇒ Object
parse array of author strings into CSL format.
-
#get_contributions(obj, items) ⇒ Object
we are flipping subj and obj for contributions.
- #get_data(options = {}) ⇒ Object
- #get_doi_relations(subj, items) ⇒ Object
- #get_github_relations(subj, items) ⇒ Object
-
#get_hashed_authors(authors) ⇒ Object
parse array of author hashes into CSL format.
- #get_name_identifier(author) ⇒ Object
-
#get_one_author(author, options = {}) ⇒ Object
parse author string into CSL format only assume personal name when using sort-order: “Turing, Alan”.
- #get_one_hashed_author(author) ⇒ Object
- #get_query_url(options = {}) ⇒ Object
- #get_relations_with_related_works(items) ⇒ Object
- #get_total(options = {}) ⇒ Object
- #is_personal_name?(author) ⇒ Boolean
- #job_batch_size ⇒ Object
- #name_detector ⇒ Object
- #orcid_as_url(orcid) ⇒ Object
- #orcid_from_url(url) ⇒ Object
- #parse_data(result, options = {}) ⇒ Object
- #process_data(options = {}) ⇒ Object
-
#push_data(items, options = {}) ⇒ Object
push to Lagotto deposit API if no error and we have collected works.
- #queue_jobs(options = {}) ⇒ Object
- #timeout ⇒ Object
- #unfreeze(hsh) ⇒ Object
- #url ⇒ Object
- #validate_orcid(orcid) ⇒ Object
Instance Method Details
#clean_doi(doi) ⇒ Object
remove non-printing whitespace
275 276 277 |
# File 'lib/toccatore/base.rb', line 275 def clean_doi(doi) doi.gsub(/\u200B/, '') end |
#cleanup_author(author) ⇒ Object
322 323 324 325 326 327 328 329 330 |
# File 'lib/toccatore/base.rb', line 322 def () # detect pattern "Smith J.", but not "Smith, John K." = .gsub(/[[:space:]]([A-Z]\.)?(-?[A-Z]\.)$/, ', \1\2') unless .include?(",") # titleize strings # remove non-standard space characters .my_titleize .gsub(/[[:space:]]/, ' ') end |
#config_fields ⇒ Object
258 259 260 |
# File 'lib/toccatore/base.rb', line 258 def config_fields [:url, :push_url, :access_token] end |
#doi_as_url(doi) ⇒ Object
288 289 290 |
# File 'lib/toccatore/base.rb', line 288 def doi_as_url(doi) Addressable::URI.encode("https://doi.org/#{clean_doi(doi)}") if doi.present? end |
#doi_from_url(url) ⇒ Object
279 280 281 282 283 284 285 286 |
# File 'lib/toccatore/base.rb', line 279 def doi_from_url(url) if /(http|https):\/\/(dx\.)?doi\.org\/(\w+)/.match(url) uri = Addressable::URI.parse(url) uri.path[1..-1].upcase elsif url.starts_with?("doi:") url[4..-1].upcase end end |
#get_authors(authors, options = {}) ⇒ Object
parse array of author strings into CSL format
340 341 342 |
# File 'lib/toccatore/base.rb', line 340 def (, ={}) Array().map { || (, ) } end |
#get_contributions(obj, items) ⇒ Object
we are flipping subj and obj for contributions
236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 |
# File 'lib/toccatore/base.rb', line 236 def get_contributions(obj, items) prefix = obj["DOI"][/^10\.\d{4,5}/] Array(items).reduce([]) do |sum, item| orcid = item.split(':', 2).last orcid = validate_orcid(orcid) return sum if orcid.nil? sum << { prefix: prefix, message_type: "contribution", relation: { "subj_id" => orcid_as_url(orcid), "obj_id" => obj["pid"], "relation_type_id" => nil, "source_id" => source_id, "publisher_id" => obj["publisher_id"], "registration_agency_id" => "datacite", "occurred_at" => obj["issued"] }, obj: obj } end end |
#get_data(options = {}) ⇒ Object
85 86 87 88 |
# File 'lib/toccatore/base.rb', line 85 def get_data(={}) query_url = get_query_url() Maremma.get(query_url, ) end |
#get_doi_relations(subj, items) ⇒ Object
208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 |
# File 'lib/toccatore/base.rb', line 208 def get_doi_relations(subj, items) prefix = subj["DOI"][/^10\.\d{4,5}/] Array(items).reduce([]) do |sum, item| raw_relation_type, , = item.split(':', 3) doi = .strip.upcase registration_agency = get_doi_ra(doi) if source_id == "datacite_crossref" && registration_agency == "datacite" sum else _source_id = registration_agency == "crossref" ? "datacite_crossref" : "datacite_related" pid = doi_as_url(doi) sum << { prefix: prefix, relation: { "subj_id" => subj["pid"], "obj_id" => pid, "relation_type_id" => raw_relation_type.underscore, "source_id" => _source_id, "publisher_id" => subj["publisher_id"], "registration_agency_id" => registration_agency, "occurred_at" => subj["issued"] }, subj: subj } end end end |
#get_github_relations(subj, items) ⇒ Object
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 |
# File 'lib/toccatore/base.rb', line 167 def get_github_relations(subj, items) prefix = subj["DOI"][/^10\.\d{4,5}/] Array(items).reduce([]) do |sum, item| raw_relation_type, , = item.split(':', 3) # get parent repo # code from https://github.com/octokit/octokit.rb/blob/master/lib/octokit/repository.rb = PostRank::URI.clean() github_hash = github_from_url() owner_url = github_as_owner_url(github_hash) repo_url = github_as_repo_url(github_hash) sum << { prefix: prefix, relation: { "subj_id" => subj["pid"], "obj_id" => , "relation_type_id" => raw_relation_type.underscore, "source_id" => source_id, "publisher_id" => subj["publisher_id"], "registration_agency_id" => "github", "occurred_at" => subj["issued"] }, subj: subj } # if relatedIdentifier is release URL rather than repo URL if != repo_url sum << { relation: { "subj_id" => , "obj_id" => repo_url, "relation_type_id" => "is_part_of", "source_id" => source_id, "publisher_id" => "github", "registration_agency_id" => "github" } } end sum << { message_type: "contribution", relation: { "subj_id" => owner_url, "obj_id" => repo_url, "source_id" => "github_contributor", "registration_agency_id" => "github" }} end end |
#get_hashed_authors(authors) ⇒ Object
parse array of author hashes into CSL format
345 346 347 |
# File 'lib/toccatore/base.rb', line 345 def () Array().map { || () } end |
#get_name_identifier(author) ⇒ Object
357 358 359 360 361 362 363 364 365 |
# File 'lib/toccatore/base.rb', line 357 def get_name_identifier() name_identifier = .fetch("nameIdentifier", nil) name_identifier_scheme = .fetch("nameIdentifierScheme", "orcid").downcase if name_identifier_scheme == "orcid" && name_identifier = validate_orcid(name_identifier) "http://orcid.org/#{name_identifier}" else nil end end |
#get_one_author(author, options = {}) ⇒ Object
parse author string into CSL format only assume personal name when using sort-order: “Turing, Alan”
306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 |
# File 'lib/toccatore/base.rb', line 306 def (, = {}) return { "literal" => "" } if .strip.blank? = () names = Namae.parse() if names.blank? || is_personal_name?().blank? { "literal" => } else name = names.first { "family" => name.family, "given" => name.given }.compact end end |
#get_one_hashed_author(author) ⇒ Object
349 350 351 352 353 354 355 |
# File 'lib/toccatore/base.rb', line 349 def () raw_name = .fetch("creatorName", nil) = (raw_name) ["ORCID"] = get_name_identifier() .compact end |
#get_query_url(options = {}) ⇒ Object
23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 |
# File 'lib/toccatore/base.rb', line 23 def get_query_url(={}) updated = "updated:[#{options[:from_date]}T00:00:00Z TO #{options[:until_date]}T23:59:59Z]" fq = "#{updated} AND has_metadata:true AND is_active:true" if [:doi].present? q = "doi:#{options[:doi]}" elsif [:orcid].present? q = "nameIdentifier:ORCID\\:#{options[:orcid]}" elsif [:query].present? q = [:query] else q = query end params = { q: q, start: [:offset], rows: [:rows], fl: "doi,creator,title,publisher,publicationYear,resourceTypeGeneral,datacentre_symbol,relatedIdentifier,nameIdentifier,xml,minted,updated", fq: fq, wt: "json" } url + URI.encode_www_form(params) end |
#get_relations_with_related_works(items) ⇒ Object
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 |
# File 'lib/toccatore/base.rb', line 120 def (items) Array(items).reduce([]) do |sum, item| doi = item.fetch("doi", nil) prefix = doi[/^10\.\d{4,5}/] pid = doi_as_url(doi) type = item.fetch("resourceTypeGeneral", nil) publisher_id = item.fetch("datacentre_symbol", nil) xml = Base64.decode64(item.fetch('xml', "PGhzaD48L2hzaD4=\n")) xml = Hash.from_xml(xml).fetch("resource", {}) = xml.fetch("creators", {}).fetch("creator", []) = [] if .is_a?(Hash) subj = { "pid" => pid, "DOI" => doi, "author" => (), "title" => item.fetch("title", []).first, "container-title" => item.fetch("publisher", nil), "published" => item.fetch("publicationYear", nil), "issued" => item.fetch("minted", nil), "publisher_id" => publisher_id, "registration_agency_id" => "datacite", "tracked" => true, "type" => type } = item.fetch('relatedIdentifier', []).select { |id| id =~ /:DOI:.+/ } sum += get_doi_relations(subj, ) = item.fetch('relatedIdentifier', []).select { |id| id =~ /:URL:https:\/\/github.com.+/ } sum += get_github_relations(subj, ) name_identifiers = item.fetch('nameIdentifier', []).select { |id| id =~ /^ORCID:.+/ } sum += get_contributions(subj, name_identifiers) if source_id == "datacite_import" sum += [{ prefix: prefix, relation: { "subj_id" => subj["pid"], "source_id" => source_id, "publisher_id" => subj["publisher_id"], "occurred_at" => subj["issued"] }, subj: subj }] end sum end end |
#get_total(options = {}) ⇒ Object
46 47 48 49 50 |
# File 'lib/toccatore/base.rb', line 46 def get_total(={}) query_url = get_query_url(.merge(rows: 0)) result = Maremma.get(query_url, ) result.body.fetch("data", {}).fetch("response", {}).fetch("numFound", 0) end |
#is_personal_name?(author) ⇒ Boolean
332 333 334 335 336 337 |
# File 'lib/toccatore/base.rb', line 332 def is_personal_name?() return true if .include?(",") # lookup given name name_detector.name_exists?(.split.first) end |
#job_batch_size ⇒ Object
270 271 272 |
# File 'lib/toccatore/base.rb', line 270 def job_batch_size 1000 end |
#name_detector ⇒ Object
367 368 369 |
# File 'lib/toccatore/base.rb', line 367 def name_detector GenderDetector.new end |
#orcid_as_url(orcid) ⇒ Object
296 297 298 |
# File 'lib/toccatore/base.rb', line 296 def orcid_as_url(orcid) "http://orcid.org/#{orcid}" if orcid.present? end |
#orcid_from_url(url) ⇒ Object
292 293 294 |
# File 'lib/toccatore/base.rb', line 292 def orcid_from_url(url) Array(/\Ahttp:\/\/orcid\.org\/(.+)/.match(url)).last end |
#parse_data(result, options = {}) ⇒ Object
90 91 92 93 94 95 |
# File 'lib/toccatore/base.rb', line 90 def parse_data(result, ={}) return result.body.fetch("errors") if result.body.fetch("errors", nil).present? items = result.fetch("data", {}).fetch('response', {}).fetch('docs', nil) (items) end |
#process_data(options = {}) ⇒ Object
76 77 78 79 80 81 82 83 |
# File 'lib/toccatore/base.rb', line 76 def process_data( = {}) data = get_data(.merge(timeout: timeout, source_id: source_id)) data = parse_data(data, .merge(source_id: source_id)) return [OpenStruct.new(body: { "data" => [] })] if data.empty? push_data(data, ) end |
#push_data(items, options = {}) ⇒ Object
push to Lagotto deposit API if no error and we have collected works
98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 |
# File 'lib/toccatore/base.rb', line 98 def push_data(items, ={}) if items.empty? puts "No works found for date range #{options[:from_date]} - #{options[:until_date]}." else Array(items).map do |item| relation = item.fetch(:relation, {}) deposit = { "deposit" => { "subj_id" => relation.fetch("subj_id", nil), "obj_id" => relation.fetch("obj_id", nil), "relation_type_id" => relation.fetch("relation_type_id", nil), "source_id" => relation.fetch("source_id", nil), "publisher_id" => relation.fetch("publisher_id", nil), "subj" => item.fetch(:subj, {}), "obj" => item.fetch(:obj, {}), "message_type" => item.fetch(:message_type, "relation"), "prefix" => item.fetch(:prefix, nil), "source_token" => uuid } } Maremma.post push_url, data: deposit.to_json, content_type: 'json', token: access_token end end end |
#queue_jobs(options = {}) ⇒ Object
52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 |
# File 'lib/toccatore/base.rb', line 52 def queue_jobs(={}) [:offset] = [:offset].to_i || 0 [:rows] = [:rows].presence || job_batch_size [:from_date] = [:from_date].presence || (Time.now.to_date - 1.day).iso8601 [:until_date] = [:until_date].presence || Time.now.to_date.iso8601 total = get_total() if total > 0 # walk through paginated results total_pages = (total.to_f / job_batch_size).ceil (0...total_pages).each do |page| [:offset] = page * job_batch_size process_data() end else puts "No works found for date range #{options[:from_date]} - #{options[:until_date]}." end # return number of works queued total end |
#timeout ⇒ Object
266 267 268 |
# File 'lib/toccatore/base.rb', line 266 def timeout 120 end |
#unfreeze(hsh) ⇒ Object
371 372 373 374 375 |
# File 'lib/toccatore/base.rb', line 371 def unfreeze(hsh) new_hash = {} hsh.each_pair { |k,v| new_hash.merge!({k.downcase.to_sym => v}) } new_hash end |
#url ⇒ Object
262 263 264 |
# File 'lib/toccatore/base.rb', line 262 def url "https://search.datacite.org/api?" end |
#validate_orcid(orcid) ⇒ Object
300 301 302 |
# File 'lib/toccatore/base.rb', line 300 def validate_orcid(orcid) Array(/\A(?:http:\/\/orcid\.org\/)?(\d{4}-\d{4}-\d{4}-\d{3}[0-9X]+)\z/.match(orcid)).last end |