Module: Bolognese::Utils

Included in:
CLI, MetadataUtils
Defined in:
lib/bolognese/utils.rb

Constant Summary collapse

LICENSE_NAMES = 
{
  "http://creativecommons.org/publicdomain/zero/1.0/" => "Public Domain (CC0 1.0)",
  "http://creativecommons.org/licenses/by/3.0/" => "Creative Commons Attribution 3.0 (CC-BY 3.0)",
  "http://creativecommons.org/licenses/by/4.0/" => "Creative Commons Attribution 4.0 (CC-BY 4.0)",
  "http://creativecommons.org/licenses/by-nc/4.0/" => "Creative Commons Attribution Noncommercial 4.0 (CC-BY-NC 4.0)",
  "http://creativecommons.org/licenses/by-sa/4.0/" => "Creative Commons Attribution Share Alike 4.0 (CC-BY-SA 4.0)",
  "http://creativecommons.org/licenses/by-nc-nd/4.0/" => "Creative Commons Attribution Noncommercial No Derivatives 4.0 (CC-BY-NC-ND 4.0)"
}
DC_TO_SO_TRANSLATIONS = 
{
  "Audiovisual" => "MediaObject",
  "Collection" => "Collection",
  "Dataset" => "Dataset",
  "Event" => "Event",
  "Image" => "ImageObject",
  "InteractiveResource" => nil,
  "Model" => nil,
  "PhysicalObject" => nil,
  "Service" => "Service",
  "Software" => "SoftwareSourceCode",
  "Sound" => "AudioObject",
  "Text" => "ScholarlyArticle",
  "Workflow" => nil,
  "Other" => "CreativeWork",
  # not part of DataCite schema, but used internally
  "Periodical" => "Periodical",
  "DataCatalog" => "DataCatalog"
}
DC_TO_CP_TRANSLATIONS = 
{
  "Audiovisual" => "motion_picture",
  "Collection" => nil,
  "Dataset" => "dataset",
  "Event" => nil,
  "Image" => "graphic",
  "InteractiveResource" => nil,
  "Model" => nil,
  "PhysicalObject" => nil,
  "Service" => nil,
  "Sound" => "song",
  "Text" => "report",
  "Workflow" => nil,
  "Other" => nil
}
CR_TO_CP_TRANSLATIONS = 
{
  "Proceedings" => nil,
  "ReferenceBook" => nil,
  "JournalIssue" => nil,
  "ProceedingsArticle" => "paper-conference",
  "Other" => nil,
  "Dissertation" => "thesis",
  "Dataset" => "dataset",
  "EditedBook" => "book",
  "JournalArticle" => "article-journal",
  "Journal" => nil,
  "Report" => "report",
  "BookSeries" => nil,
  "ReportSeries" => nil,
  "BookTrack" => nil,
  "Standard" => nil,
  "BookSection" => "chapter",
  "BookPart" => nil,
  "Book" => "book",
  "BookChapter" => "chapter",
  "StandardSeries" => nil,
  "Monograph" => "book",
  "Component" => nil,
  "ReferenceEntry" => "entry-dictionary",
  "JournalVolume" => nil,
  "BookSet" => nil
}
CR_TO_SO_TRANSLATIONS = 
{
  "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"
}
BIB_TO_CR_TRANSLATIONS = 
{
  "proceedings" => "Proceedings",
  "phdthesis" => "Dissertation",
  "article" => "JournalArticle",
  "book" => "Book",
  "inbook" => "BookChapter"
}
CR_TO_JATS_TRANSLATIONS = 
{
  "Proceedings" => "working-paper",
  "ReferenceBook" => "book",
  "JournalIssue" => "journal",
  "ProceedingsArticle" => "working-paper",
  "Other" => nil,
  "Dissertation" => nil,
  "Dataset" => "data",
  "EditedBook" => "book",
  "JournalArticle" => "journal",
  "Journal" => "journal",
  "Report" => "report",
  "BookSeries" => "book",
  "ReportSeries" => "report",
  "BookTrack" => "book",
  "Standard" => "standard",
  "BookSection" => "chapter",
  "BookPart" => "chapter",
  "Book" => "book",
  "BookChapter" => "chapter",
  "StandardSeries" => "standard",
  "Monograph" => "book",
  "Component" => nil,
  "ReferenceEntry" => nil,
  "JournalVolume" => "journal",
  "BookSet" => "book"
}
SO_TO_DC_TRANSLATIONS = 
{
  "Article" => "Text",
  "AudioObject" => "Sound",
  "Blog" => "Text",
  "BlogPosting" => "Text",
  "Chapter" => "Text",
  "Collection" => "Collection",
  "DataCatalog" => "Dataset",
  "Dataset" => "Dataset",
  "Event" => "Event",
  "ImageObject" => "Image",
  "Movie" => "Audiovisual",
  "PublicationIssue" => "Text",
  "ScholarlyArticle" => "Text",
  "Thesis" => "Text",
  "Service" => "Service",
  "SoftwareSourceCode" => "Software",
  "VideoObject" => "Audiovisual",
  "WebPage" => "Text",
  "WebSite" => "Text"
}
SO_TO_JATS_TRANSLATIONS = 
{
  "Article" => "journal",
  "AudioObject" => nil,
  "Blog" => nil,
  "BlogPosting" => nil,
  "Book" => "book",
  "Collection" => nil,
  "CreativeWork" => nil,
  "DataCatalog" => "data",
  "Dataset" => "data",
  "Event" => nil,
  "ImageObject" => nil,
  "Movie" => nil,
  "PublicationIssue" => "journal",
  "ScholarlyArticle" => "journal",
  "Service" => nil,
  "SoftwareSourceCode" => "software",
  "VideoObject" => nil,
  "WebPage" => nil,
  "WebSite" => "website"
}
SO_TO_CP_TRANSLATIONS = 
{
  "Article" => "",
  "AudioObject" => "song",
  "Blog" => "report",
  "BlogPosting" => "post-weblog",
  "Collection" => nil,
  "CreativeWork" => nil,
  "DataCatalog" => "dataset",
  "Dataset" => "dataset",
  "Event" => nil,
  "ImageObject" => "graphic",
  "Movie" => "motion_picture",
  "PublicationIssue" => nil,
  "ScholarlyArticle" => "article-journal",
  "Service" => nil,
  "Thesis" => "thesis",
  "VideoObject" => "broadcast",
  "WebPage" => "webpage",
  "WebSite" => "webpage"
}
SO_TO_RIS_TRANSLATIONS = 
{
  "Article" => nil,
  "AudioObject" => nil,
  "Blog" => nil,
  "BlogPosting" => "BLOG",
  "Collection" => nil,
  "CreativeWork" => "GEN",
  "DataCatalog" => "CTLG",
  "Dataset" => "DATA",
  "Event" => nil,
  "ImageObject" => "FIGURE",
  "Movie" => "MPCT",
  "PublicationIssue" => nil,
  "ScholarlyArticle" => "JOUR",
  "Service" => nil,
  "SoftwareSourceCode" => "COMP",
  "VideoObject" => "VIDEO",
  "WebPage" => "ELEC",
  "WebSite" => nil
}
CR_TO_RIS_TRANSLATIONS = 
{
  "Proceedings" => "CONF",
  "ReferenceBook" => "BOOK",
  "JournalIssue" => nil,
  "ProceedingsArticle" => "CPAPER",
  "Other" => "GEN",
  "Dissertation" => "THES",
  "Dataset" => "DATA",
  "EditedBook" => "BOOK",
  "JournalArticle" => "JOUR",
  "Journal" => nil,
  "Report" => nil,
  "BookSeries" => nil,
  "ReportSeries" => nil,
  "BookTrack" => nil,
  "Standard" => nil,
  "BookSection" => "CHAP",
  "BookPart" => "CHAP",
  "Book" => "BOOK",
  "BookChapter" => "CHAP",
  "StandardSeries" => nil,
  "Monograph" => "BOOK",
  "Component" => nil,
  "ReferenceEntry" => "DICT",
  "JournalVolume" => nil,
  "BookSet" => nil
}
DC_TO_RIS_TRANSLATIONS = 
{
  "Audiovisual" => "MPCT",
  "Collection" => nil,
  "Dataset" => "DATA",
  "Event" => nil,
  "Image" => "FIGURE",
  "InteractiveResource" => nil,
  "Model" => nil,
  "PhysicalObject" => nil,
  "Service" => nil,
  "Software" => "COMP",
  "Sound" => "SOUND",
  "Text" => "RPRT",
  "Workflow" => nil,
  "Other" => nil
}
SO_TO_BIB_TRANSLATIONS = 
{
  "Article" => "article",
  "AudioObject" => "misc",
  "Thesis" => "phdthesis",
  "Blog" => "misc",
  "BlogPosting" => "article",
  "Collection" => "misc",
  "CreativeWork" => "misc",
  "DataCatalog" => "misc",
  "Dataset" => "misc",
  "Event" => "misc",
  "ImageObject" => "misc",
  "Movie" => "misc",
  "PublicationIssue" => "misc",
  "ScholarlyArticle" => "article",
  "Service" => "misc",
  "SoftwareSourceCode" => "misc",
  "VideoObject" => "misc",
  "WebPage" => "misc",
  "WebSite" => "misc"
}

Instance Method Summary collapse

Instance Method Details

#find_from_format(id: nil, string: nil, ext: nil) ⇒ Object 



325
326
327
328
329
330
331
332
333
334
335
 
# File 'lib/bolognese/utils.rb', line 325

def find_from_format(id: nil, string: nil, ext: nil)
  if id.present?
    find_from_format_by_id(id)
  elsif ext.present?
    find_from_format_by_ext(string, ext: ext)
  elsif string.present?
    find_from_format_by_string(string)
  else
    "datacite"
  end
end

#find_from_format_by_ext(string, options = {}) ⇒ Object 



352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
 
# File 'lib/bolognese/utils.rb', line 352

def find_from_format_by_ext(string, options={})
  if options[:ext] == ".bib"
    "bibtex"
  elsif options[:ext] == ".ris"
    "ris"
  elsif options[:ext] == ".xml" && Maremma.from_xml(string).to_h.dig("doi_records", "doi_record", "crossref")
    "crossref"
  elsif options[:ext] == ".xml" && Nokogiri::XML(string, nil, 'UTF-8', &:noblanks).collect_namespaces.find { |k, v| v.start_with?("http://datacite.org/schema/kernel") }      
    "datacite"
  elsif options[:ext] == ".json" && Maremma.from_json(string).to_h.dig("@context").to_s.start_with?("http://schema.org", "https://schema.org")
    "schema_org"
  elsif options[:ext] == ".json" && Maremma.from_json(string).to_h.dig("@context") == ("https://raw.githubusercontent.com/codemeta/codemeta/master/codemeta.jsonld")
    "codemeta"
  elsif options[:ext] == ".json" && Maremma.from_json(string).to_h.dig("schemaVersion").to_s.start_with?("http://datacite.org/schema/kernel")
    "datacite_json"
  elsif options[:ext] == ".json" && Maremma.from_json(string).to_h.dig("types")
    "crosscite"
  elsif options[:ext] == ".json" && Maremma.from_json(string).to_h.dig("issued", "date-parts").present?
    "citeproc"
  end
end

#find_from_format_by_id(id) ⇒ Object 



337
338
339
340
341
342
343
344
345
346
347
348
349
350
 
# File 'lib/bolognese/utils.rb', line 337

def find_from_format_by_id(id)
  id = normalize_id(id)

  if /\A(?:(http|https):\/(\/)?(dx\.)?(doi.org|handle.test.datacite.org)\/)?(doi:)?(10\.\d{4,5}\/.+)\z/.match(id)
    ra = get_doi_ra(id)
    %w(DataCite Crossref).include?(ra) ? ra.downcase : nil
  elsif /\A(?:(http|https):\/(\/)?orcid\.org\/)?(\d{4}-\d{4}-\d{4}-\d{3}[0-9X]+)\z/.match(id)
    "orcid"
  elsif /\A(http|https):\/(\/)?github\.com\/(.+)\z/.match(id)
    "codemeta"
  else
    "schema_org"
  end
end

#find_from_format_by_string(string) ⇒ Object 



374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
 
# File 'lib/bolognese/utils.rb', line 374

def find_from_format_by_string(string)
  if Maremma.from_xml(string).to_h.dig("doi_records", "doi_record", "crossref").present?
    "crossref"
  elsif Nokogiri::XML(string, nil, 'UTF-8', &:noblanks).collect_namespaces.find { |k, v| v.start_with?("http://datacite.org/schema/kernel") }  
    "datacite"
  elsif Maremma.from_json(string).to_h.dig("@context").to_s.start_with?("http://schema.org", "https://schema.org")
    "schema_org"
  elsif Maremma.from_json(string).to_h.dig("@context") == ("https://raw.githubusercontent.com/codemeta/codemeta/master/codemeta.jsonld")
    "codemeta"
  elsif Maremma.from_json(string).to_h.dig("schema-version").to_s.start_with?("http://datacite.org/schema/kernel")
    "datacite_json"
  elsif Maremma.from_json(string).to_h.dig("types").present?
    "crosscite"
  elsif Maremma.from_json(string).to_h.dig("issued", "date-parts").present?
    "citeproc"
  elsif string.start_with?("TY  - ")
    "ris"
  elsif BibTeX.parse(string).first
    "bibtex"
  end
rescue BibTeX::ParseError => error
  nil
end

#from_citeproc(element) ⇒ Object 



714
715
716
717
718
719
720
721
722
723
724
725
726
727
 
# File 'lib/bolognese/utils.rb', line 714

def from_citeproc(element)
  Array.wrap(element).map do |a|
    if a["literal"].present?
      a["@type"] = "Organization"
      a["name"] = a["literal"]
    else
      a["@type"] = "Person"
      a["name"] = [a["given"], a["family"]].compact.join(" ")
    end
    a["givenName"] = a["given"]
    a["familyName"] = a["family"]
    a.except("given", "family", "literal").compact
  end.unwrap
end

#from_datacite_json(element) ⇒ Object 



539
540
541
542
543
 
# File 'lib/bolognese/utils.rb', line 539

def from_datacite_json(element)
  Array.wrap(element).map do |e|
    e.inject({}) {|h, (k,v)| h[k.underscore] = v; h }
  end
end

#from_schema_org(element) ⇒ Object 



671
672
673
674
675
 
# File 'lib/bolognese/utils.rb', line 671

def from_schema_org(element)
  mapping = { "@type" => "type", "@id" => "id" }

  map_hash_keys(element: element, mapping: mapping)
end

#from_schema_org_contributors(element) ⇒ Object 



685
686
687
688
689
690
691
 
# File 'lib/bolognese/utils.rb', line 685

def from_schema_org_contributors(element)
  element = Array.wrap(element).map do |c|
    c["nameIdentifier"] = [{ "__content__" => c["@id"], "nameIdentifierScheme" => "ORCID" }] if normalize_orcid(c["@id"])
    c["contributorName"] = { "nameType" => c["@type"].present? ? c["@type"].titleize + "al" : nil, "__content__" => c["name"] }.compact
    c.except("@id", "@type", "name") 
  end
end

#from_schema_org_creators(element) ⇒ Object 



677
678
679
680
681
682
683
 
# File 'lib/bolognese/utils.rb', line 677

def from_schema_org_creators(element)
  element = Array.wrap(element).map do |c|
    c["nameIdentifier"] = [{ "__content__" => c["@id"], "nameIdentifierScheme" => "ORCID" }] if normalize_orcid(c["@id"])
    c["creatorName"] = { "nameType" => c["@type"].present? ? c["@type"].titleize + "al" : nil, "__content__" => c["name"] }.compact
    c.except("@id", "@type", "name") 
  end
end

#get_contributor(contributor, contributor_type) ⇒ Object 



875
876
877
 
# File 'lib/bolognese/utils.rb', line 875

def get_contributor(contributor, contributor_type)
  contributor.select { |c| c["contributorType"] == contributor_type }
end

#get_date(dates, date_type) ⇒ Object 



870
871
872
873
 
# File 'lib/bolognese/utils.rb', line 870

def get_date(dates, date_type)
  dd = Array.wrap(dates).find { |d| d["dateType"] == date_type } || {}
  dd.fetch("date", nil)
end

#get_date_from_date_parts(date_as_parts) ⇒ Object 



822
823
824
825
826
 
# File 'lib/bolognese/utils.rb', line 822

def get_date_from_date_parts(date_as_parts)
  date_parts = date_as_parts.fetch("date-parts", []).first
  year, month, day = date_parts[0], date_parts[1], date_parts[2]
  get_date_from_parts(year, month, day)
end

#get_date_from_parts(year, month = nil, day = nil) ⇒ Object 



828
829
830
 
# File 'lib/bolognese/utils.rb', line 828

def get_date_from_parts(year, month = nil, day = nil)
  [year.to_s.rjust(4, '0'), month.to_s.rjust(2, '0'), day.to_s.rjust(2, '0')].reject { |part| part == "00" }.join("-")
end

#get_date_parts(iso8601_time) ⇒ Object 



813
814
815
816
817
818
819
820
 
# File 'lib/bolognese/utils.rb', line 813

def get_date_parts(iso8601_time)
  return { 'date-parts' => [[]] } if iso8601_time.nil?

  year = iso8601_time[0..3].to_i
  month = iso8601_time[5..6].to_i
  day = iso8601_time[8..9].to_i
  { 'date-parts' => [[year, month, day].reject { |part| part == 0 }] }
end

#get_date_parts_from_parts(year, month = nil, day = nil) ⇒ Object 



832
833
834
 
# File 'lib/bolognese/utils.rb', line 832

def get_date_parts_from_parts(year, month = nil, day = nil)
  { 'date-parts' => [[year.to_i, month.to_i, day.to_i].reject { |part| part == 0 }] }
end

#get_datetime_from_iso8601(iso8601_time) ⇒ Object

parsing of incomplete iso8601 timestamps such as 2015-04 is broken in standard library return nil if invalid iso8601 timestamp



864
865
866
867
868
 
# File 'lib/bolognese/utils.rb', line 864

def get_datetime_from_iso8601(iso8601_time)
  ISO8601::DateTime.new(iso8601_time).to_time.utc
rescue
  nil
end

#get_identifier(identifiers, identifier_type) ⇒ Object 



879
880
881
882
 
# File 'lib/bolognese/utils.rb', line 879

def get_identifier(identifiers, identifier_type)
  id = Array.wrap(identifiers).find { |i| i["identifierType"] == identifier_type } || {}
  id.fetch("identifier", nil)
end

#get_identifier_type(identifier_type) ⇒ Object 



884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
 
# File 'lib/bolognese/utils.rb', line 884

def get_identifier_type(identifier_type)
  return nil unless identifier_type.present?

  identifierTypes = {
    "ark" => "ARK",
    "arxiv" => "arXiv",
    "bibcode" => "bibcode",
    "doi" => "DOI",
    "ean13" => "EAN13",
    "eissn" => "EISSN",
    "handle" => "Handle",
    "igsn" => "IGSN",
    "isbn" => "ISBN",
    "issn" => "ISSN",
    "istc" => "ISTC",
    "lissn" => "LISSN",
    "lsid" => "LSID",
    "pmid" => "PMID",
    "purl" => "PURL",
    "upc" => "UPC",
    "url" => "URL",
    "urn" => "URN",
    "md5" => "md5",
    "minid" => "minid",
    "dataguid" => "dataguid"
  }

  identifierTypes[identifier_type.downcase] || identifier_type
end

#get_iso8601_date(iso8601_time) ⇒ Object 



836
837
838
839
840
 
# File 'lib/bolognese/utils.rb', line 836

def get_iso8601_date(iso8601_time)
  return nil if iso8601_time.nil?
  
  iso8601_time[0..9]
end

#get_series_information(str) ⇒ Object 



914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
 
# File 'lib/bolognese/utils.rb', line 914

def get_series_information(str)
  return {} unless str.present?

  str = str.split(",").map(&:strip)

  title = str.first
  volume_issue = str.length > 2 ? str[1].rpartition(/\(([^)]+)\)/) : nil
  volume = volume_issue.present? ? volume_issue[0].presence || volume_issue[2].presence : nil
  issue = volume_issue.present? ? volume_issue[1][1...-1].presence : nil
  pages = str.length > 1 ? str.last : nil
  first_page = pages.present? ? pages.split("-").map(&:strip)[0] : nil
  last_page = pages.present? ? pages.split("-").map(&:strip)[1] : nil

  { 
    "title" => title,
    "volume" => volume,
    "issue" => issue,
    "firstPage" => first_page,
    "lastPage" => last_page }.compact
end

#get_year_month(iso8601_time) ⇒ Object 



842
843
844
845
846
847
848
849
 
# File 'lib/bolognese/utils.rb', line 842

def get_year_month(iso8601_time)
  return [] if iso8601_time.nil?

  year = iso8601_time[0..3]
  month = iso8601_time[5..6]

  [year.to_i, month.to_i].reject { |part| part == 0 }
end

#get_year_month_day(iso8601_time) ⇒ Object 



851
852
853
854
855
856
857
858
859
 
# File 'lib/bolognese/utils.rb', line 851

def get_year_month_day(iso8601_time)
  return [] if iso8601_time.nil?

  year = iso8601_time[0..3]
  month = iso8601_time[5..6]
  day = iso8601_time[8..9]

  [year.to_i, month.to_i, day.to_i].reject { |part| part == 0 }
end

#github_as_codemeta_url(url) ⇒ Object 



803
804
805
806
807
808
809
810
811
 
# File 'lib/bolognese/utils.rb', line 803

def github_as_codemeta_url(url)
  github_hash = github_from_url(url)

  if github_hash[:path].to_s.end_with?("codemeta.json")
    "https://raw.githubusercontent.com/#{github_hash[:owner]}/#{github_hash[:repo]}/#{github_hash[:release]}/#{github_hash[:path]}"
  elsif github_hash[:owner].present?
    "https://raw.githubusercontent.com/#{github_hash[:owner]}/#{github_hash[:repo]}/master/codemeta.json"
  end
end

#github_as_owner_url(url) ⇒ Object 



788
789
790
791
 
# File 'lib/bolognese/utils.rb', line 788

def github_as_owner_url(url)
  github_hash = github_from_url(url)
  "https://github.com/#{github_hash[:owner]}" if github_hash[:owner].present?
end

#github_as_release_url(url) ⇒ Object 



798
799
800
801
 
# File 'lib/bolognese/utils.rb', line 798

def github_as_release_url(url)
  github_hash = github_from_url(url)
  "https://github.com/#{github_hash[:owner]}/#{github_hash[:repo]}/tree/#{github_hash[:release]}" if github_hash[:release].present?
end

#github_as_repo_url(url) ⇒ Object 



793
794
795
796
 
# File 'lib/bolognese/utils.rb', line 793

def github_as_repo_url(url)
  github_hash = github_from_url(url)
  "https://github.com/#{github_hash[:owner]}/#{github_hash[:repo]}" if github_hash[:repo].present?
end

#github_from_url(url) ⇒ Object 



765
766
767
768
769
770
771
772
773
774
 
# File 'lib/bolognese/utils.rb', line 765

def github_from_url(url)
  return {} unless /\Ahttps:\/\/github\.com\/(.+)(?:\/)?(.+)?(?:\/tree\/)?(.*)\z/.match(url)
  words = URI.parse(url).path[1..-1].split('/')
  path = words.length > 3 ? words[4...words.length].join("/") : nil

  { owner: words[0],
    repo: words[1],
    release: words[3],
    path: path }.compact
end

#github_owner_from_url(url) ⇒ Object 



784
785
786
 
# File 'lib/bolognese/utils.rb', line 784

def github_owner_from_url(url)
  github_from_url(url).fetch(:owner, nil)
end

#github_release_from_url(url) ⇒ Object 



780
781
782
 
# File 'lib/bolognese/utils.rb', line 780

def github_release_from_url(url)
  github_from_url(url).fetch(:release, nil)
end

#github_repo_from_url(url) ⇒ Object 



776
777
778
 
# File 'lib/bolognese/utils.rb', line 776

def github_repo_from_url(url)
  github_from_url(url).fetch(:repo, nil)
end

#jsonlint(json) ⇒ Object 



935
936
937
938
939
940
941
942
 
# File 'lib/bolognese/utils.rb', line 935

def jsonlint(json)
  return ["No JSON provided"] unless json.present?

  error_array = []
  linter = JsonLint::Linter.new
  linter.send(:check_data, json, error_array)
  error_array
end

#map_hash_keys(element: nil, mapping: nil) ⇒ Object 



693
694
695
696
697
698
699
700
701
702
703
704
705
 
# File 'lib/bolognese/utils.rb', line 693

def map_hash_keys(element: nil, mapping: nil)
  Array.wrap(element).map do |a|
    a.map {|k, v| [mapping.fetch(k, k), v] }.reduce({}) do |hsh, (k, v)|
      if v.is_a?(Hash)
        hsh[k] = to_schema_org(v)
        hsh
      else
        hsh[k] = v
        hsh
      end
    end
  end.unwrap
end

#normalize_id(id, options = {}) ⇒ Object 



440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
 
# File 'lib/bolognese/utils.rb', line 440

def normalize_id(id, options={})
  return nil unless id.present?

  # check for valid DOI
  doi = normalize_doi(id, options)
  return doi if doi.present?

  # check for valid HTTP uri
  uri = Addressable::URI.parse(id)
  return nil unless uri && uri.host && %w(http https).include?(uri.scheme)

  # clean up URL
  PostRank::URI.clean(id)
rescue Addressable::URI::InvalidURIError
  nil
end

#normalize_ids(ids: nil, relation_type: nil) ⇒ Object 



482
483
484
485
486
487
488
489
490
491
492
493
 
# File 'lib/bolognese/utils.rb', line 482

def normalize_ids(ids: nil, relation_type: nil)
  Array.wrap(ids).select { |idx| idx["@id"].present? }.map do |idx|
    id = normalize_id(idx["@id"])
    related_identifier_type = doi_from_url(id).present? ? "DOI" : "URL"
    id = doi_from_url(id) || id

    { "relatedIdentifier" => id,
      "relationType" => relation_type,
      "relatedIdentifierType" => related_identifier_type,
      "resourceTypeGeneral" => Metadata::SO_TO_DC_TRANSLATIONS[idx["@type"]] }.compact
  end.unwrap
end

#normalize_licenses(licenses) ⇒ Object

find Creative Commons or OSI license in licenses array, normalize url and name



496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
 
# File 'lib/bolognese/utils.rb', line 496

def normalize_licenses(licenses)
  standard_licenses = Array.wrap(licenses).map { |l| URI.parse(l["url"]) }.select { |li| li.host && li.host[/(creativecommons.org|opensource.org)$/] }
  return licenses unless standard_licenses.present?

  # use HTTPS
  uri.scheme = "https"

  # use host name without subdomain
  uri.host = Array(/(creativecommons.org|opensource.org)/.match uri.host).last

  # normalize URLs
  if uri.host == "creativecommons.org"
    uri.path = uri.path.split('/')[0..-2].join("/") if uri.path.split('/').last == "legalcode"
    uri.path << '/' unless uri.path.end_with?('/')
  else
    uri.path = uri.path.gsub(/(-license|\.php|\.html)/, '')
    uri.path = uri.path.sub(/(mit|afl|apl|osl|gpl|ecl)/) { |match| match.upcase }
    uri.path = uri.path.sub(/(artistic|apache)/) { |match| match.titleize }
    uri.path = uri.path.sub(/([^0-9\-]+)(-)?([1-9])?(\.)?([0-9])?$/) do
      m = Regexp.last_match
      text = m[1]

      if m[3].present?
        version = [m[3], m[5].presence || "0"].join(".")
        [text, version].join("-")
      else
        text
      end
    end
  end

  uri.to_s
rescue URI::InvalidURIError
  nil
end

#normalize_orcid(orcid) ⇒ Object 



474
475
476
477
478
479
480
 
# File 'lib/bolognese/utils.rb', line 474

def normalize_orcid(orcid)
  orcid = validate_orcid(orcid)
  return nil unless orcid.present?

  # turn ORCID ID into URL
  "https://orcid.org/" + Addressable::URI.encode(orcid)
end

#normalize_url(id) ⇒ Object 



457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
 
# File 'lib/bolognese/utils.rb', line 457

def normalize_url(id)
  return nil unless id.present?

  # handle info URIs
  return id if id.to_s.start_with?("info")

  # check for valid HTTP uri
  uri = Addressable::URI.parse(id)

  return nil unless uri && uri.host && %w(http https ftp).include?(uri.scheme)

  # clean up URL
  PostRank::URI.clean(id)
rescue Addressable::URI::InvalidURIError
  nil
end

#orcid_as_url(orcid) ⇒ Object 



402
403
404
 
# File 'lib/bolognese/utils.rb', line 402

def orcid_as_url(orcid)
  "https://orcid.org/#{orcid}" if orcid.present?
end

#orcid_from_url(url) ⇒ Object 



398
399
400
 
# File 'lib/bolognese/utils.rb', line 398

def orcid_from_url(url)
  Array(/\A:(http|https):\/\/orcid\.org\/(.+)/.match(url)).last
end

#parse_attributes(element, options = {}) ⇒ Object 



425
426
427
428
429
430
431
432
433
434
435
436
437
438
 
# File 'lib/bolognese/utils.rb', line 425

def parse_attributes(element, options={})
  content = options[:content] || "__content__"

  if element.is_a?(String) && options[:content].nil?
    CGI.unescapeHTML(element)
  elsif element.is_a?(Hash)
    element.fetch( CGI.unescapeHTML(content), nil)
  elsif element.is_a?(Array)
    a = element.map { |e| e.is_a?(Hash) ? e.fetch( CGI.unescapeHTML(content), nil) : e }.uniq
    a = options[:first] ? a.first : a.unwrap
  else
    nil
  end
end

#sanitize(text, options = {}) ⇒ Object 



748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
 
# File 'lib/bolognese/utils.rb', line 748

def sanitize(text, options={})
  options[:tags] ||= Set.new(%w(strong em b i code pre sub sup br))
  content = options[:content] || "__content__"
  custom_scrubber = Bolognese::WhitelistScrubber.new(options)

  if text.is_a?(String)
    Loofah.scrub_fragment(text, custom_scrubber).to_s.gsub(/\u00a0/, ' ').strip
  elsif text.is_a?(Hash)
    sanitize(text.fetch(content, nil))
  elsif text.is_a?(Array)
    a = text.map { |e| e.is_a?(Hash) ? sanitize(e.fetch(content, nil)) : sanitize(e) }.uniq
    a = options[:first] ? a.first : a.unwrap
  else
    nil
  end
end

#to_citeproc(element) ⇒ Object 



729
730
731
732
733
734
735
736
 
# File 'lib/bolognese/utils.rb', line 729

def to_citeproc(element)
  Array.wrap(element).map do |a|
    a["family"] = a["familyName"]
    a["given"] = a["givenName"]
    a["literal"] = a["name"] unless a["familyName"].present?
    a.except("nameType", "type", "@type", "id", "@id", "name", "familyName", "givenName", "affiliation", "nameIdentifiers").compact
  end.presence
end

#to_datacite_json(element, options = {}) ⇒ Object 



532
533
534
535
536
537
 
# File 'lib/bolognese/utils.rb', line 532

def to_datacite_json(element, options={})
  a = Array.wrap(element).map do |e|
    e.inject({}) {|h, (k,v)| h[k.dasherize] = v; h }
  end
  options[:first] ? a.unwrap : a.presence
end

#to_identifier(identifier) ⇒ Object 



707
708
709
710
711
712
 
# File 'lib/bolognese/utils.rb', line 707

def to_identifier(identifier)
  {
    "@type" => "PropertyValue",
    "propertyID" => identifier["relatedIdentifierType"],
    "value" => identifier["relatedIdentifier"] }
end

#to_ris(element) ⇒ Object 



738
739
740
741
742
743
744
745
746
 
# File 'lib/bolognese/utils.rb', line 738

def to_ris(element)
  Array.wrap(element).map do |a|
    if a["familyName"].present?
      [a["familyName"], a["givenName"]].join(", ")
    else
      a["name"]
    end
  end.unwrap
end

#to_schema_org(element) ⇒ Object 



545
546
547
548
549
 
# File 'lib/bolognese/utils.rb', line 545

def to_schema_org(element)
  mapping = { "type" => "@type", "id" => "@id", "title" => "name" }

  map_hash_keys(element: element, mapping: mapping)
end

#to_schema_org_container(element, options = {}) ⇒ Object 



571
572
573
574
575
576
577
578
 
# File 'lib/bolognese/utils.rb', line 571

def to_schema_org_container(element, options={})
  return nil unless (element.is_a?(Hash) || (element.nil? && options[:container_title].present?))

  { 
    "@id" => element["identifier"],
    "@type" => (options[:type] == "Dataset") ? "DataCatalog" : "Periodical",
    "name" => element["title"] || options[:container_title] }.compact
end

#to_schema_org_contributors(element) ⇒ Object 



561
562
563
564
565
566
567
568
569
 
# File 'lib/bolognese/utils.rb', line 561

def to_schema_org_contributors(element)
  element = Array.wrap(element).map do |c|
    c["affiliation"] = { "@type" => "Organization", "name" => c["affiliation"] } if c["affiliation"].present?
    c["@type"] = c["nameType"].present? ? c["nameType"][0..-3] : nil
    c["@id"] = Array.wrap(c["nameIdentifiers"]).first.to_h.fetch("nameIdentifier", nil)
    c["name"] = c["familyName"].present? ? [c["givenName"], c["familyName"]].join(" ") : c["name"]
    c.except("nameIdentifiers", "nameType").compact
  end.unwrap
end

#to_schema_org_creators(element) ⇒ Object 



551
552
553
554
555
556
557
558
559
 
# File 'lib/bolognese/utils.rb', line 551

def to_schema_org_creators(element)
  element = Array.wrap(element).map do |c|
    c["affiliation"] = { "@type" => "Organization", "name" => c["affiliation"] } if c["affiliation"].present?
    c["@type"] = c["nameType"].present? ? c["nameType"][0..-3] : nil
    c["@id"] = Array.wrap(c["nameIdentifiers"]).first.to_h.fetch("nameIdentifier", nil)
    c["name"] = c["familyName"].present? ? [c["givenName"], c["familyName"]].join(" ") : c["name"]
    c.except("nameIdentifiers", "nameType").compact
  end.unwrap
end

#to_schema_org_funder(funding_references) ⇒ Object 



607
608
609
610
611
612
613
614
615
616
 
# File 'lib/bolognese/utils.rb', line 607

def to_schema_org_funder(funding_references)
  return nil unless funding_references.present?

  Array.wrap(funding_references).map do |fr|
    {
      "@id" => fr["funderIdentifier"],
      "@type" => "Organization",
      "name" => fr["funderName"] }.compact
  end.unwrap
end

#to_schema_org_identifiers(element, options = {}) ⇒ Object 



580
581
582
583
584
585
586
587
 
# File 'lib/bolognese/utils.rb', line 580

def to_schema_org_identifiers(element, options={})
  Array.wrap(element).map do |ai|
    { 
      "@type" => "PropertyValue",
      "propertyID" => ai["identifierType"],
      "value" => ai["identifier"] }
  end.unwrap
end

#to_schema_org_relation(related_identifiers: nil, relation_type: nil) ⇒ Object 



589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
 
# File 'lib/bolognese/utils.rb', line 589

def to_schema_org_relation(related_identifiers: nil, relation_type: nil)
  return nil unless related_identifiers.present? && relation_type.present?

  relation_type = relation_type == "References" ? ["References", "Cites", "Documents"] : [relation_type] 

  Array.wrap(related_identifiers).select { |ri| relation_type.include?(ri["relationType"]) }.map do |r|
    if r["relatedIdentifierType"] == "ISSN" && r["relationType"] == "IsPartOf"
      {
        "@type" => "Periodical",
        "issn" => r["relatedIdentifier"] }.compact
    else
    {
      "@id" => normalize_id(r["relatedIdentifier"]),
      "@type" => DC_TO_SO_TRANSLATIONS[r["resourceTypeGeneral"]] || "CreativeWork" }.compact
    end
  end.unwrap
end

#to_schema_org_spatial_coverage(geo_location) ⇒ Object 



618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
 
# File 'lib/bolognese/utils.rb', line 618

def to_schema_org_spatial_coverage(geo_location)
  return nil unless geo_location.present?

  Array.wrap(geo_location).reduce([]) do |sum, gl|
    if gl.fetch("geoLocationPoint", nil)
      sum << { 
        "@type" => "Place",
        "geo" => {
          "@type" => "GeoCoordinates",
          "address" => gl["geoLocationPlace"],
          "latitude" => gl.dig("geoLocationPoint", "pointLatitude"),
          "longitude" => gl.dig("geoLocationPoint", "pointLongitude") }
      }.compact
    end

    if gl.fetch("geoLocationBox", nil)
      sum << { 
        "@type" => "Place",
        "geo" => {
          "@type" => "GeoShape",
          "address" => gl["geoLocationPlace"],
          "box" => [gl.dig("geoLocationBox", "southBoundLatitude"),
                    gl.dig("geoLocationBox", "westBoundLongitude"),
                    gl.dig("geoLocationBox", "northBoundLatitude"),
                    gl.dig("geoLocationBox", "eastBoundLongitude")].compact.join(" ").presence }.compact
      }.compact
    end

    if gl.fetch("geoLocationPolygon", nil)
      sum << { 
        "@type" => "Place",
        "geo" => {
          "@type" => "GeoShape",
          "address" => gl["geoLocationPlace"],
          "polygon" => Array.wrap(gl.dig("geoLocationPolygon")).map do |glp| 
            [glp.dig("polygonPoint", "pointLongitude"), glp.dig("polygonPoint", "pointLatitude")].compact
          end.compact }
      }
    end

    if gl.fetch("geoLocationPlace", nil) && !gl.fetch("geoLocationPoint", nil) && !gl.fetch("geoLocationBox", nil) && !gl.fetch("geoLocationPolygon", nil)
      sum << { 
        "@type" => "Place",
        "geo" => {
          "@type" => "GeoCoordinates",
          "address" => gl["geoLocationPlace"] }
      }.compact
    end

    sum
  end.unwrap
end

#validate_orcid(orcid) ⇒ Object 



406
407
408
409
 
# File 'lib/bolognese/utils.rb', line 406

def validate_orcid(orcid)
  orcid = Array(/\A(?:(http|https):\/\/(www\.)?orcid\.org\/)?(\d{4}[[:space:]-]\d{4}[[:space:]-]\d{4}[[:space:]-]\d{3}[0-9X]+)\z/.match(orcid)).last
  orcid.gsub(/[[:space:]]/, "-") if orcid.present?
end

#validate_orcid_scheme(orcid_scheme) ⇒ Object 



411
412
413
 
# File 'lib/bolognese/utils.rb', line 411

def validate_orcid_scheme(orcid_scheme)
  Array(/\A(http|https):\/\/(www\.)?(orcid\.org)/.match(orcid_scheme)).last
end

#validate_url(str) ⇒ Object 



415
416
417
418
419
420
421
422
423
 
# File 'lib/bolognese/utils.rb', line 415

def validate_url(str)
  if /\A(?:(http|https):\/\/(dx\.)?doi.org\/)?(doi:)?(10\.\d{4,5}\/.+)\z/.match(str)
    "DOI"
  elsif /\A(http|https):\/\//.match(str)
    "URL"
  elsif /\A(ISSN|eISSN) (\d{4}-\d{3}[0-9X]+)\z/.match(str)
    "ISSN"
  end
end