Module: Bolognese::Utils

Extended by:
Utils
Included in:
CLI, Metadata, MetadataUtils, Utils
Defined in:
lib/bolognese/utils.rb

Constant Summary collapse

NORMALIZED_LICENSES = 
{
  "https://creativecommons.org/licenses/by/1.0" => "https://creativecommons.org/licenses/by/1.0/legalcode",
  "https://creativecommons.org/licenses/by/2.0" => "https://creativecommons.org/licenses/by/2.0/legalcode",
  "https://creativecommons.org/licenses/by/2.5" => "https://creativecommons.org/licenses/by/2.5/legalcode",
  "https://creativecommons.org/licenses/by/3.0" => "https://creativecommons.org/licenses/by/3.0/legalcode",
  "https://creativecommons.org/licenses/by/3.0/us" => "https://creativecommons.org/licenses/by/3.0/legalcode",
  "https://creativecommons.org/licenses/by/4.0" => "https://creativecommons.org/licenses/by/4.0/legalcode",
  "https://creativecommons.org/licenses/by-nc/1.0" => "https://creativecommons.org/licenses/by-nc/1.0/legalcode",
  "https://creativecommons.org/licenses/by-nc/2.0" => "https://creativecommons.org/licenses/by-nc/2.0/legalcode",
  "https://creativecommons.org/licenses/by-nc/2.5" => "https://creativecommons.org/licenses/by-nc/2.5/legalcode",
  "https://creativecommons.org/licenses/by-nc/3.0" => "https://creativecommons.org/licenses/by-nc/3.0/legalcode",
  "https://creativecommons.org/licenses/by-nc/4.0" => "https://creativecommons.org/licenses/by-nc/4.0/legalcode",
  "https://creativecommons.org/licenses/by-nd-nc/1.0" => "https://creativecommons.org/licenses/by-nd-nc/1.0/legalcode",
  "https://creativecommons.org/licenses/by-nd-nc/2.0" => "https://creativecommons.org/licenses/by-nd-nc/2.0/legalcode",
  "https://creativecommons.org/licenses/by-nd-nc/2.5" => "https://creativecommons.org/licenses/by-nd-nc/2.5/legalcode",
  "https://creativecommons.org/licenses/by-nd-nc/3.0" => "https://creativecommons.org/licenses/by-nd-nc/3.0/legalcode",
  "https://creativecommons.org/licenses/by-nd-nc/4.0" => "https://creativecommons.org/licenses/by-nd-nc/4.0/legalcode",
  "https://creativecommons.org/licenses/by-nc-sa/1.0" => "https://creativecommons.org/licenses/by-nc-sa/1.0/legalcode",
  "https://creativecommons.org/licenses/by-nc-sa/2.0" => "https://creativecommons.org/licenses/by-nc-sa/2.0/legalcode",
  "https://creativecommons.org/licenses/by-nc-sa/2.5" => "https://creativecommons.org/licenses/by-nc-sa/2.5/legalcode",
  "https://creativecommons.org/licenses/by-nc-sa/3.0" => "https://creativecommons.org/licenses/by-nc-sa/3.0/legalcode",
  "https://creativecommons.org/licenses/by-nc-sa/4.0" => "https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode",
  "https://creativecommons.org/licenses/by-nd/1.0" => "https://creativecommons.org/licenses/by-nd/1.0/legalcode",
  "https://creativecommons.org/licenses/by-nd/2.0" => "https://creativecommons.org/licenses/by-nd/2.0/legalcode",
  "https://creativecommons.org/licenses/by-nd/2.5" => "https://creativecommons.org/licenses/by-nd/2.5/legalcode",
  "https://creativecommons.org/licenses/by-nd/3.0" => "https://creativecommons.org/licenses/by-nd/3.0/legalcode",
  "https://creativecommons.org/licenses/by-nd/4.0" => "https://creativecommons.org/licenses/by-nd/4.0/legalcode",
  "https://creativecommons.org/licenses/by-sa/1.0" => "https://creativecommons.org/licenses/by-sa/1.0/legalcode",
  "https://creativecommons.org/licenses/by-sa/2.0" => "https://creativecommons.org/licenses/by-sa/2.0/legalcode",
  "https://creativecommons.org/licenses/by-sa/2.5" => "https://creativecommons.org/licenses/by-sa/2.5/legalcode",
  "https://creativecommons.org/licenses/by-sa/3.0" => "https://creativecommons.org/licenses/by-sa/3.0/legalcode",
  "https://creativecommons.org/licenses/by-sa/4.0" => "https://creativecommons.org/licenses/by-sa/4.0/legalcode",
  "https://creativecommons.org/licenses/by-nc-nd/1.0" => "https://creativecommons.org/licenses/by-nc-nd/1.0/legalcode",
  "https://creativecommons.org/licenses/by-nc-nd/2.0" => "https://creativecommons.org/licenses/by-nc-nd/2.0/legalcode",
  "https://creativecommons.org/licenses/by-nc-nd/2.5" => "https://creativecommons.org/licenses/by-nc-nd/2.5/legalcode",
  "https://creativecommons.org/licenses/by-nc-nd/3.0" => "https://creativecommons.org/licenses/by-nc-nd/3.0/legalcode",
  "https://creativecommons.org/licenses/by-nc-nd/4.0" => "https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode",
  "https://creativecommons.org/licenses/publicdomain" => "https://creativecommons.org/licenses/publicdomain/",
  "https://creativecommons.org/publicdomain/zero/1.0" => "https://creativecommons.org/publicdomain/zero/1.0/legalcode",
}
DC_TO_SO_TRANSLATIONS = 
{
  "Audiovisual" => "MediaObject",
  "Book" => "Book",
  "BookChapter" => "Chapter",
  "Collection" => "Collection",
  "ComputationalNotebook" => "SoftwareSourceCode",
  "ConferencePaper" => "Article",
  "ConferenceProceeding" => "Periodical",
  "DataPaper" => "Article",
  "Dataset" => "Dataset",
  "Dissertation" => "Thesis",
  "Event" => "Event",
  "Image" => "ImageObject",
  "InteractiveResource" => nil,
  "Journal" => "Periodical",
  "JournalArticle" => "ScholarlyArticle",
  "Model" => nil,
  "OutputManagementPlan" => nil,
  "PeerReview" => "Review",
  "PhysicalObject" => nil,
  "Preprint" => nil,
  "Report" => "Report",
  "Service" => "Service",
  "Software" => "SoftwareSourceCode",
  "Sound" => "AudioObject",
  "Standard" => nil,
  "Text" => "ScholarlyArticle",
  "Workflow" => nil,
  "Other" => "CreativeWork",
  # not part of DataCite schema, but used internally
  "Periodical" => "Periodical",
  "DataCatalog" => "DataCatalog",
  "Award" => "Grant",
  "Project" => "Project"
}
DC_TO_CP_TRANSLATIONS = 
{
  "Audiovisual" => "motion_picture",
  "Book" => "book",
  "BookChapter" => "chapter",
  "Collection" => nil,
  "ComputationalNotebook" => nil,
  "ConferencePaper" => "paper_conference",
  "ConferenceProceeding" => nil,
  "DataPaper" => "report",
  "Dataset" => "dataset",
  "Dissertation" => nil,
  "Event" => nil,
  "Image" => "graphic",
  "InteractiveResource" => nil,
  "Journal" => nil,
  "JournalArticle" => "article-journal",
  "Model" => nil,
  "OutputManagementPlan" => nil,
  "PeerReview" => "review",
  "PhysicalObject" => nil,
  "Preprint" => nil,
  "Report" => "report",
  "Service" => nil,
  "Sound" => "song",
  "Standard" => nil,
  "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" => "Report",
  "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",
  "PeerReview" => "Review"
}
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" => "techreport",
  "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"
}
CR_TO_DC_TRANSLATIONS = 
{
  "Proceedings" => nil,
  "ReferenceBook" => nil,
  "JournalIssue" => "Text",
  "ProceedingsArticle" => "ConferencePaper",
  "Other" => "Other",
  "Dissertation" => "Dissertation",
  "Dataset" => "Dataset",
  "EditedBook" => "Book",
  "JournalArticle" => "JournalArticle",
  "Journal" => "Journal",
  "Report" => "Report",
  "BookSeries" => nil,
  "ReportSeries" => nil,
  "BookTrack" => nil,
  "Standard" => "Standard",
  "BookSection" => "BookChapter",
  "BookPart" => nil,
  "Book" => "Book",
  "BookChapter" => "BookChapter",
  "SaComponent" => "Text",
  "StandardSeries" => "Standard",
  "Monograph" => "book",
  "Component" => nil,
  "ReferenceEntry" => nil,
  "JournalVolume" => nil,
  "BookSet" => nil,
  "PostedContent" => "JournalArticle",
  "PeerReview" => "PeerReview"
}
SO_TO_DC_TRANSLATIONS = 
{
  "Article" => "Text",
  "AudioObject" => "Sound",
  "Blog" => "Text",
  "BlogPosting" => "Text",
  "Book" => "Book",
  "Chapter" => "BookChapter",
  "Collection" => "Collection",
  "DataCatalog" => "Dataset",
  "Dataset" => "Dataset",
  "Event" => "Event",
  "ImageObject" => "Image",
  "Movie" => "Audiovisual",
  "PublicationIssue" => "Text",
  "Report" => "Report",
  "ScholarlyArticle" => "Text",
  "Thesis" => "Text",
  "Service" => "Service",
  "Review" => "PeerReview",
  "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,
  "Report" => "report",
  "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",
  "Report" => "RPRT",
  "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" => "RPRT",
  "BookSeries" => nil,
  "ReportSeries" => nil,
  "BookTrack" => nil,
  "Standard" => "STAND",
  "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",
  "Book" => "BOOK",
  "BookChapter" => "CHAP",
  "Collection" => nil,
  "ComputationalNotebook" => "COMP",
  "ConferencePaper" => "CPAPER",
  "ConferenceProceeding" => "CONF",
  "DataPaper" => nil,
  "Dataset" => "DATA",
  "Dissertation" => "THES",
  "Event" => nil,
  "Image" => "FIGURE",
  "InteractiveResource" => nil,
  "Journal" => nil,
  "JournalArticle" => "JOUR",
  "Model" => nil,
  "OutputManagementPlan" => nil,
  "PeerReview" => nil,
  "PhysicalObject" => nil,
  "Preprint" => nil,
  "Report" => "RRPT",
  "Service" => nil,
  "Software" => "COMP",
  "Sound" => "SOUND",
  "Standard" => nil,
  "Text" => "RPRT",
  "Workflow" => nil,
  "Other" => nil
}
RIS_TO_DC_TRANSLATIONS = 
{
  "BLOG" => "Text",
  "GEN" => "Text",
  "CTLG" => "Collection",
  "DATA" => "Dataset",
  "FIGURE" => "Image",
  "THES" => "Dissertation",
  "MPCT" => "Audiovisual",
  "JOUR" => "JournalArticle",
  "COMP" => "Software",
  "VIDEO" => "Audiovisual",
  "ELEC" => "Text"
}
BIB_TO_DC_TRANSLATIONS = 
{
  "article" => "JournalArticle",
  "book" => "Book",
  "inbook" => "BookChapter",
  "inproceedings" => nil,
  "manual" => nil,
  "misc" => "Other",
  "phdthesis" => "Dissertation",
  "proceedings" => "ConferenceProceeding",
  "techreport" => "Report",
  "unpublished" => nil
}
CP_TO_DC_TRANSLATIONS = 
{
  "song" => "Audiovisual",
  "post-weblog" => "Text",
  "dataset" => "Dataset",
  "graphic" => "Image",
  "motion_picture" => "Audiovisual",
  "article-journal" => "JournalArticle",
  "broadcast" => "Audiovisual",
  "webpage" => "Text"
}
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"
}
UNKNOWN_INFORMATION = 
{
  ":unac" => "temporarily inaccessible",
  ":unal" => "unallowed, suppressed intentionally",
  ":unap" => "not applicable, makes no sense",
  ":unas" => "value unassigned (e.g., Untitled)",
  ":unav" => "value unavailable, possibly unknown",
  ":unkn" => "known to be unknown (e.g., Anonymous, Inconnue)",
  ":none" => "never had a value, never will",
  ":null" => "explicitly and meaningfully empty",
  ":tba" => "to be assigned or announced later",
  ":etal" => "too numerous to list (et alia)"
}
RESOURCE_PATHS = 
{
  spdx: 'spdx/licenses.json',
  fos: 'oecd/fos-mappings.json',
  for: 'oecd/for-mappings.json',
  dfg: 'oecd/dfg-mappings.json'
}

Instance Method Summary collapse

Instance Method Details

#abstract_description ⇒ Object 



1433
1434
1435
1436
 
# File 'lib/bolognese/utils.rb', line 1433

def abstract_description
  # Fetch the first description with descriptionType "Abstract"
  Array.wrap(descriptions)&.find { |d| d["descriptionType"] == "Abstract" }
end

#dfg_ids_to_fos(dfg_ids) ⇒ Object 



1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
 
# File 'lib/bolognese/utils.rb', line 1418

def dfg_ids_to_fos(dfg_ids)
  dfgs = resource_json(:dfg).fetch("dfgFields")
  ids = Array.wrap(dfg_ids)

  subjects = dfgs.select { |l| ids.include?(l["dfgId"])}
  subjects.map do |subject|
    {
      "classificationCode" => subject["fosId"],
      "subject" =>  subject["fosLabel"],
      "subjectScheme" => "Fields of Science and Technology (FOS)",
      "schemeUri" => "http://www.oecd.org/science/inno/38235147.pdf"
    }
  end
end

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



515
516
517
518
519
520
521
522
523
524
525
 
# File 'lib/bolognese/utils.rb', line 515

def find_from_format(id: nil, string: nil, ext: nil, filename: nil)
  if id.present?
    find_from_format_by_id(id)
  elsif ext.present?
    find_from_format_by_filename(filename) || 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 



550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
 
# File 'lib/bolognese/utils.rb', line 550

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("crossref_result", "query_result", "body", "query", "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") && Maremma.from_json(string).to_h.dig("publication_year").present?
    "crosscite"
  elsif options[:ext] == ".json" && Maremma.from_json(string).to_h.dig("issued", "date-parts").present?
    "citeproc"
  end
end

#find_from_format_by_filename(filename) ⇒ Object 



544
545
546
547
548
 
# File 'lib/bolognese/utils.rb', line 544

def find_from_format_by_filename(filename)
  if filename == "package.json"
    "npm"
  end
end

#find_from_format_by_id(id) ⇒ Object 



527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
 
# File 'lib/bolognese/utils.rb', line 527

def find_from_format_by_id(id)
  id = normalize_id(id)

  if /\A(?:(http|https):\/(\/)?(dx\.)?(doi.org|handle.stage.datacite.org)\/)?(doi:)?(10\.\d{4,5}\/.+)\z/.match(id)
    ra = get_doi_ra(id)
    %w(DataCite Crossref mEDRA KISTI JaLC OP).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\/(.+)\/package.json\z/.match(id)
    "npm"
  elsif /\A(http|https):\/(\/)?github\.com\/(.+)\z/.match(id)
    "codemeta"
  else
    "schema_org"
  end
end

#find_from_format_by_string(string) ⇒ Object 



572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
 
# File 'lib/bolognese/utils.rb', line 572

def find_from_format_by_string(string)
  if Maremma.from_xml(string).to_h.dig("crossref_result", "query_result", "body", "query", "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? && Maremma.from_json(string).to_h.dig("publication_year").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 



1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
 
# File 'lib/bolognese/utils.rb', line 1033

def from_citeproc(element)
  Array.wrap(element).map do |a|
    if a["literal"].present?
      a["@type"] = "Organization"
      a["creatorName"] = 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 



793
794
795
796
797
 
# File 'lib/bolognese/utils.rb', line 793

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 



957
958
959
960
961
 
# File 'lib/bolognese/utils.rb', line 957

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

  map_hash_keys(element: element, mapping: mapping)
end

#from_schema_org_contributors(element) ⇒ Object 



988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
 
# File 'lib/bolognese/utils.rb', line 988

def from_schema_org_contributors(element)
  element = Array.wrap(element).map do |c|
    if c["affiliation"].is_a?(String)
      c["affiliation"] = { "name" => c["affiliation"] }
      affiliation_identifier_scheme = nil
      scheme_uri = nil
    elsif c.dig("affiliation", "@id").to_s.starts_with?("https://ror.org")
      affiliation_identifier_scheme = "ROR"
      scheme_uri = "https://ror.org/"
    elsif c.dig("affiliation", "@id").to_s.starts_with?("https://isni.org")
      affiliation_identifier_scheme = "ISNI"
      scheme_uri = "https://isni.org/isni/"
    else
      affiliation_identifier_scheme = nil
      scheme_uri = nil
    end

    c["nameIdentifier"] = [{ "__content__" => c["@id"], "nameIdentifierScheme" => "ORCID", "schemeUri" => "https://orcid.org" }] if normalize_orcid(c["@id"])
    c["contributorName"] = { "nameType" => c["@type"].present? ? c["@type"].titleize + "al" : nil, "__content__" => c["name"] }.compact
    c["affiliation"] = { "__content__" => c.dig("affiliation", "name"), "affiliationIdentifier" => c.dig("affiliation", "@id"), "affiliationIdentifierScheme" => affiliation_identifier_scheme, "schemeUri" => scheme_uri }.compact.presence
    c.except("@id", "@type", "name").compact
  end
end

#from_schema_org_creators(element) ⇒ Object 



963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
 
# File 'lib/bolognese/utils.rb', line 963

def from_schema_org_creators(element)
  element = Array.wrap(element).map do |c|
    if c["affiliation"].is_a?(String)
      c["affiliation"] = { "name" => c["affiliation"] }
      affiliation_identifier_scheme = nil
      scheme_uri = nil
    elsif c.dig("affiliation", "@id").to_s.starts_with?("https://ror.org")
      affiliation_identifier_scheme = "ROR"
      scheme_uri = "https://ror.org/"
    elsif c.dig("affiliation", "@id").to_s.starts_with?("https://isni.org")
      affiliation_identifier_scheme = "ISNI"
      scheme_uri = "https://isni.org/isni/"
    else
      affiliation_identifier_scheme = nil
      scheme_uri = nil
    end

    c["nameIdentifier"] = [{ "__content__" => c["@id"], "nameIdentifierScheme" => "ORCID", "schemeUri" => "https://orcid.org" }] if normalize_orcid(c["@id"])
    c["@type"] = c["@type"].find { |t| %w(Person Organization).include?(t) } if c["@type"].is_a?(Array)
    c["creatorName"] = { "nameType" => c["@type"].present? ? c["@type"].titleize + "al" : nil, "__content__" => c["name"] }.compact
    c["affiliation"] = { "__content__" => c.dig("affiliation", "name"), "affiliationIdentifier" => c.dig("affiliation", "@id"), "affiliationIdentifierScheme" => affiliation_identifier_scheme, "schemeUri" => scheme_uri }.compact.presence
    c.except("@id", "@type", "name").compact
  end
end

#generate_container(types, related_items, related_identifiers, descriptions) ⇒ Object 



1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
 
# File 'lib/bolognese/utils.rb', line 1438

def generate_container(types, related_items, related_identifiers, descriptions)
  container_type = (types.respond_to?(:dig) && types&.dig("resourceTypeGeneral")) == "Dataset" ? "DataRepository" : "Series"

  # relatedItem container
  related_item = Array.wrap(related_items).find { |ri| ri["relationType"] == "IsPublishedIn" }.to_h

  if related_item.present?
    return {
      "type" => container_type,
      "identifier" => related_item.dig("relatedItemIdentifier", "relatedItemIdentifier"),
      "identifierType" => related_item.dig("relatedItemIdentifier", "relatedItemIdentifierType"),
      "title" => related_item.dig("titles", 0).then { |t| t ? parse_attributes(t, content: "title", first: true) : nil },
      "volume" => related_item["volume"],
      "issue" => related_item["issue"],
      "edition" => related_item["edition"],
      "number" => related_item["number"],
      "chapterNumber" => related_item["numberType"] == "Chapter" ? related_item["number"] : nil,
      "firstPage" => related_item["firstPage"],
      "lastPage" => related_item["lastPage"]
    }.compact
  end

  # Legacy SeriesInformation/relatedIdentifier container fallback 
  series_information = Array.wrap(descriptions).find { |r| r["descriptionType"] == "SeriesInformation" }.to_h.fetch("description", nil)
  si = get_series_information(series_information)

  is_part_of = Array.wrap(related_identifiers).find { |ri| ri["relationType"] == "IsPartOf" }.to_h

  if si["title"].present?
    return {
      "type" => container_type,
      "identifier" => is_part_of["relatedIdentifier"],
      "identifierType" => is_part_of["relatedIdentifierType"],
      "title" => si["title"],
      "volume" => si["volume"],
      "issue" => si["issue"],
      "firstPage" => si["firstPage"],
      "lastPage" => si["lastPage"]
    }.compact
  end
end

#get_contributor(contributor, contributor_type) ⇒ Object 



1209
1210
1211
 
# File 'lib/bolognese/utils.rb', line 1209

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

#get_date(dates, date_type) ⇒ Object 



1204
1205
1206
1207
 
# File 'lib/bolognese/utils.rb', line 1204

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 



1148
1149
1150
1151
1152
 
# File 'lib/bolognese/utils.rb', line 1148

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 



1154
1155
1156
 
# File 'lib/bolognese/utils.rb', line 1154

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 



1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
 
# File 'lib/bolognese/utils.rb', line 1137

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 }] }
rescue TypeError
  nil
end

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



1158
1159
1160
 
# File 'lib/bolognese/utils.rb', line 1158

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



1190
1191
1192
1193
1194
 
# File 'lib/bolognese/utils.rb', line 1190

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

#get_datetime_from_time(time) ⇒ Object

iso8601 datetime without hyphens and colons, used by Crossref return nil if invalid



1198
1199
1200
1201
1202
 
# File 'lib/bolognese/utils.rb', line 1198

def get_datetime_from_time(time)
  DateTime.strptime(time.to_s, "%Y%m%d%H%M%S").strftime('%Y-%m-%dT%H:%M:%SZ')
rescue ArgumentError
  nil
end

#get_identifier(identifiers, identifier_type) ⇒ Object 



1213
1214
1215
1216
 
# File 'lib/bolognese/utils.rb', line 1213

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 



1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
 
# File 'lib/bolognese/utils.rb', line 1218

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",
    "cstr" => "CSTR",
    "rrid" => "RRID"
  }

  identifierTypes[identifier_type.downcase] || identifier_type
end

#get_iso8601_date(iso8601_time) ⇒ Object 



1162
1163
1164
1165
1166
 
# File 'lib/bolognese/utils.rb', line 1162

def get_iso8601_date(iso8601_time)
  return nil if iso8601_time.nil?

  iso8601_time[0..9]
end

#get_series_information(str) ⇒ Object 



1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
 
# File 'lib/bolognese/utils.rb', line 1250

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 



1168
1169
1170
1171
1172
1173
1174
1175
 
# File 'lib/bolognese/utils.rb', line 1168

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 



1177
1178
1179
1180
1181
1182
1183
1184
1185
 
# File 'lib/bolognese/utils.rb', line 1177

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 



1127
1128
1129
1130
1131
1132
1133
1134
1135
 
# File 'lib/bolognese/utils.rb', line 1127

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 



1112
1113
1114
1115
 
# File 'lib/bolognese/utils.rb', line 1112

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 



1122
1123
1124
1125
 
# File 'lib/bolognese/utils.rb', line 1122

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 



1117
1118
1119
1120
 
# File 'lib/bolognese/utils.rb', line 1117

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 



1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
 
# File 'lib/bolognese/utils.rb', line 1089

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 



1108
1109
1110
 
# File 'lib/bolognese/utils.rb', line 1108

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

#github_release_from_url(url) ⇒ Object 



1104
1105
1106
 
# File 'lib/bolognese/utils.rb', line 1104

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

#github_repo_from_url(url) ⇒ Object 



1100
1101
1102
 
# File 'lib/bolognese/utils.rb', line 1100

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

#hsh_to_fos(hsh) ⇒ Object 



1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
 
# File 'lib/bolognese/utils.rb', line 1357

def hsh_to_fos(hsh)
  # first find subject in Fields of Science (OECD)
  fos = resource_json(:fos).fetch("fosFields")
  subject = fos.find { |l| l["fosLabel"] == hsh["__content__"] || "FOS: " + l["fosLabel"] == hsh["__content__"] || l["fosLabel"] == hsh["subject"]}

  if subject
    return [{
      "subject" => sanitize(hsh["__content__"] || hsh["subject"]),
      "subjectScheme" => hsh["subjectScheme"],
      "schemeUri" => hsh["schemeURI"] || hsh["schemeUri"],
      "valueUri" => hsh["valueURI"] || hsh["valueUri"],
      "classificationCode" => hsh["classificationCode"],
      "lang" => hsh["lang"] }.compact,
    {
      "subject" => "FOS: " + subject["fosLabel"],
      "subjectScheme" => "Fields of Science and Technology (FOS)",
      "schemeUri" => "http://www.oecd.org/science/inno/38235147.pdf" }.compact]
  end

  # if not found, look in Fields of Research (Australian and New Zealand Standard Research Classification)
  # and map to Fields of Science. Add an extra entry for the latter
  fores = resource_json(:for)
  for_fields = fores.fetch("forFields")
  for_disciplines = fores.fetch("forDisciplines")

  # try to extract forId
  if hsh["subjectScheme"] == "FOR"
    for_id = hsh["__content__"].to_s.split(" ").first || hsh["subject"].to_s.split(" ").first
    for_id = for_id.rjust(6, "0")

    subject = for_fields.find { |l| l["forId"] == for_id } ||
              for_disciplines.find { |l| l["forId"] == for_id[0..3] }
  else
    subject = for_fields.find { |l| l["forLabel"] == hsh["__content__"] || l["forLabel"] == hsh["subject"] } ||
              for_disciplines.find { |l| l["forLabel"] == hsh["__content__"] || l["forLabel"] == hsh["subject"] }
  end

  if subject
    [{
      "subject" => sanitize(hsh["__content__"] || hsh["subject"]),
      "subjectScheme" => hsh["subjectScheme"],
      "classificationCode" => hsh["classificationCode"],
      "schemeUri" => hsh["schemeURI"] || hsh["schemeUri"],
      "valueUri" => hsh["valueURI"] || hsh["valueUri"],
      "lang" => hsh["lang"] }.compact,
    {
      "subject" => "FOS: " + subject["fosLabel"],
      "subjectScheme" => "Fields of Science and Technology (FOS)",
      "schemeUri" => "http://www.oecd.org/science/inno/38235147.pdf"
    }]
  else
    [{
      "subject" => sanitize(hsh["__content__"] || hsh["subject"]),
      "subjectScheme" => hsh["subjectScheme"],
      "classificationCode" => hsh["classificationCode"],
      "schemeUri" => hsh["schemeURI"] || hsh["schemeUri"],
      "valueUri" => hsh["valueURI"] || hsh["valueUri"],
      "lang" => hsh["lang"] }.compact]
  end
end

#hsh_to_spdx(hsh) ⇒ Object 



1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
 
# File 'lib/bolognese/utils.rb', line 1296

def hsh_to_spdx(hsh)
  spdx = resource_json(:spdx).fetch("licenses")
  license = spdx.find { |l| l["licenseId"].casecmp?(hsh["rightsIdentifier"]) || l["seeAlso"].first == normalize_cc_url(hsh["rightsURI"]) || l["name"] == hsh["rights"] || l["seeAlso"].first == normalize_cc_url(hsh["rights"]) }

  if license
    {
      "rights" => license["name"],
      "rightsUri" => license["seeAlso"].first,
      "rightsIdentifier" => license["licenseId"].downcase,
      "rightsIdentifierScheme" => "SPDX",
      "schemeUri" => "https://spdx.org/licenses/",
      "lang" => hsh["lang"] }.compact
  else
    {
      "rights" => hsh["__content__"] || hsh["rights"],
      "rightsUri" => hsh["rightsURI"] || hsh["rightsUri"],
      "rightsIdentifier" => hsh["rightsIdentifier"].present? ? hsh["rightsIdentifier"].downcase : nil,
      "rightsIdentifierScheme" => hsh["rightsIdentifierScheme"],
      "schemeUri" => hsh["schemeUri"],
      "lang" => hsh["lang"] }.compact
  end
end

#jsonlint(json) ⇒ Object 



1271
1272
1273
1274
1275
1276
1277
1278
 
# File 'lib/bolognese/utils.rb', line 1271

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 



1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
 
# File 'lib/bolognese/utils.rb', line 1012

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

#name_to_fos(name) ⇒ Object 



1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
 
# File 'lib/bolognese/utils.rb', line 1319

def name_to_fos(name)
  # first find subject in Fields of Science (OECD)
  fos = resource_json(:fos).fetch("fosFields")

  subject = fos.find { |l| l["fosLabel"] == name || "FOS: " + l["fosLabel"] == name }

  if subject
    return [{
      "subject" => sanitize(name) },
    {
      "subject" => "FOS: " + subject["fosLabel"],
      "subjectScheme" => "Fields of Science and Technology (FOS)",
      "schemeUri" => "http://www.oecd.org/science/inno/38235147.pdf"
    }]
  end

  # if not found, look in Fields of Research (Australian and New Zealand Standard Research Classification)
  # and map to Fields of Science. Add an extra entry for the latter
  fores = resource_json(:for)
  for_fields = fores.fetch("forFields")
  for_disciplines = fores.fetch("forDisciplines")

  subject = for_fields.find { |l| l["forLabel"] == name } ||
            for_disciplines.find { |l| l["forLabel"] == name }

  if subject
    [{
      "subject" => sanitize(name) },
    {
      "subject" => "FOS: " + subject["fosLabel"],
      "subjectScheme" => "Fields of Science and Technology (FOS)",
      "schemeUri" => "http://www.oecd.org/science/inno/38235147.pdf"
    }]
  else
    [{ "subject" => sanitize(name) }]
  end
end

#name_to_spdx(name) ⇒ Object 



1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
 
# File 'lib/bolognese/utils.rb', line 1280

def name_to_spdx(name)
  spdx = resource_json(:spdx).fetch("licenses")
  license = spdx.find { |l| l["name"] == name || l["licenseId"] == name || l["seeAlso"].first == normalize_cc_url(name) }

  if license
    {
      "rights" => license["name"],
      "rightsUri" => license["seeAlso"].first,
      "rightsIdentifier" => license["licenseId"].downcase,
      "rightsIdentifierScheme" => "SPDX",
      "schemeUri" => "https://spdx.org/licenses/" }.compact
  else
    { "rights" => name }
  end
end

#normalize_cc_url(id) ⇒ Object 



681
682
683
684
 
# File 'lib/bolognese/utils.rb', line 681

def normalize_cc_url(id)
  id = normalize_url(id, https: true)
  NORMALIZED_LICENSES.fetch(id, id)
end

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



642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
 
# File 'lib/bolognese/utils.rb', line 642

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

  # check for valid DOI
  doi = DoiUtils::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 



702
703
704
705
706
707
708
709
710
711
712
713
 
# File 'lib/bolognese/utils.rb', line 702

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 = DoiUtils::doi_from_url(id).present? ? "DOI" : "URL"
    id = DoiUtils::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_issn(input, options = {}) ⇒ Object

pick electronic issn if there are multiple format issn as xxxx-xxxx



717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
 
# File 'lib/bolognese/utils.rb', line 717

def normalize_issn(input, options={})
  content = options[:content] || "__content__"

  issn = if input.blank?
    nil
  elsif input.is_a?(String) && options[:content].nil?
    input
  elsif input.is_a?(Hash)
    input.fetch(content, nil)
  elsif input.is_a?(Array)
    a = input.find { |a| a["media_type"] == "electronic" } || input.first
    a.fetch(content, nil)
  end

  case issn.to_s.length
  when 9
    issn
  when 8
    issn[0..3] + "-" + issn[4..7]
  else
    nil
  end
end

#normalize_licenses(licenses) ⇒ Object

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



742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
 
# File 'lib/bolognese/utils.rb', line 742

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 



686
687
688
689
690
691
692
 
# File 'lib/bolognese/utils.rb', line 686

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_publisher(publisher) ⇒ Object 



778
779
780
781
782
783
784
 
# File 'lib/bolognese/utils.rb', line 778

def normalize_publisher(publisher)
  if publisher.respond_to?(:to_hash)
    publisher
  elsif publisher.respond_to?(:to_str)
    { "name" => publisher }
  end
end

#normalize_ror(ror) ⇒ Object 



694
695
696
697
698
699
700
 
# File 'lib/bolognese/utils.rb', line 694

def normalize_ror(ror)
  ror = validate_ror(ror)
  return nil unless ror.present?

  # turn ROR into URL
  "https://ror.org/" + Addressable::URI.encode(ror)
end

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



659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
 
# File 'lib/bolognese/utils.rb', line 659

def normalize_url(id, options={})
  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)

  # optionally turn into https URL
  uri.scheme = "https" if options[:https]

  # clean up URL
  uri.path = PostRank::URI.clean(uri.path)

  uri.to_s
rescue Addressable::URI::InvalidURIError
  nil
end

#orcid_as_url(orcid) ⇒ Object 



600
601
602
 
# File 'lib/bolognese/utils.rb', line 600

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

#orcid_from_url(url) ⇒ Object 



596
597
598
 
# File 'lib/bolognese/utils.rb', line 596

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

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



627
628
629
630
631
632
633
634
635
636
637
638
639
640
 
# File 'lib/bolognese/utils.rb', line 627

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

#resource_file(extra_path) ⇒ Object 



504
505
506
 
# File 'lib/bolognese/utils.rb', line 504

def resource_file( extra_path )
  File.read(resources_dir_path + extra_path)
end

#resource_json(resource_symbol) ⇒ Object 



508
509
510
511
512
 
# File 'lib/bolognese/utils.rb', line 508

def resource_json( resource_symbol )
  if RESOURCE_PATHS.keys().include?(resource_symbol)
    JSON.load(resource_file(RESOURCE_PATHS[resource_symbol]))
  end
end

#resources_dir_path ⇒ Object 



500
501
502
 
# File 'lib/bolognese/utils.rb', line 500

def resources_dir_path
  File.expand_path('../../../resources', __FILE__) + '/'
end

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



1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
 
# File 'lib/bolognese/utils.rb', line 1067

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)
    if options[:new_line]
      # Remove multiple spaces, tabs, and other whitespace characters while preserving single spaces and new lines
      Loofah.scrub_fragment(text, custom_scrubber).to_s.gsub(/[ \t]+/, ' ').strip
    else
      Loofah.scrub_fragment(text, custom_scrubber).to_s.squish
    end
  elsif text.is_a?(Hash)
    sanitize(text.fetch(content, nil), new_line: options[:new_line])
  elsif text.is_a?(Array)
    a = text.map { |e| e.is_a?(Hash) ? sanitize(e.fetch(content, nil), new_line: options[:new_line]) : sanitize(e, new_line: options[:new_line]) }.uniq
    a = options[:first] ? a.first : a.unwrap
  else
    nil
  end
end

#to_citeproc(element) ⇒ Object 



1048
1049
1050
1051
1052
1053
1054
1055
 
# File 'lib/bolognese/utils.rb', line 1048

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", "contributorType").compact
  end.presence
end

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



786
787
788
789
790
791
 
# File 'lib/bolognese/utils.rb', line 786

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 



1026
1027
1028
1029
1030
1031
 
# File 'lib/bolognese/utils.rb', line 1026

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

#to_ris(element) ⇒ Object 



1057
1058
1059
1060
1061
1062
1063
1064
1065
 
# File 'lib/bolognese/utils.rb', line 1057

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 



799
800
801
802
803
 
# File 'lib/bolognese/utils.rb', line 799

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 



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

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 



828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
 
# File 'lib/bolognese/utils.rb', line 828

def to_schema_org_contributors(element)
  element = Array.wrap(element).map do |c|
    transformed_c = c.dup
    transformed_c["affiliation"] = Array.wrap(c["affiliation"]).map do |a|
      if a.is_a?(String)
        name = a
        affiliation_identifier = nil
      else
        name = a["name"]
        affiliation_identifier = a["affiliationIdentifier"]
      end

      {
        "@type" => "Organization",
        "@id" => affiliation_identifier,
        "name" => name }.compact
    end.unwrap
    transformed_c["@type"] = c["nameType"].present? ? c["nameType"][0..-3] : nil
    transformed_c["@id"] = Array.wrap(c["nameIdentifiers"]).first.to_h.fetch("nameIdentifier", nil)
    transformed_c["name"] = c["familyName"].present? ? [c["givenName"], c["familyName"]].join(" ") : c["name"]
    transformed_c.except("nameIdentifiers", "nameType").compact
  end.unwrap
end

#to_schema_org_creators(element) ⇒ Object 



805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
 
# File 'lib/bolognese/utils.rb', line 805

def to_schema_org_creators(element)
  element = Array.wrap(element).map do |c|
    c["affiliation"] = Array.wrap(c["affiliation"]).map do |a|
      if a.is_a?(String)
        name = a
        affiliation_identifier = nil
      else
        name = a["name"]
        affiliation_identifier = a["affiliationIdentifier"]
      end

      {
        "@type" => "Organization",
        "@id" => affiliation_identifier,
        "name" => name }.compact
    end.unwrap
    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 



888
889
890
891
892
893
894
895
896
897
 
# File 'lib/bolognese/utils.rb', line 888

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 



861
862
863
864
865
866
867
868
 
# File 'lib/bolognese/utils.rb', line 861

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 



870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
 
# File 'lib/bolognese/utils.rb', line 870

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 



899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
 
# File 'lib/bolognese/utils.rb', line 899

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|
            Array.wrap(glp).map do |glpp|
              if glpp.dig("polygonPoint")
                [glpp.dig("polygonPoint", "pointLongitude"), glpp.dig("polygonPoint", "pointLatitude")].compact
              end
            end.compact.presence
          end.compact.presence,
          }
      }
    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 



604
605
606
607
 
# File 'lib/bolognese/utils.rb', line 604

def validate_orcid(orcid)
  orcid = Array(/\A(?:(?:http|https):\/\/(?:(?:www|sandbox)?\.)?orcid\.org\/)?(\d{4}[[:space:]-]\d{4}[[:space:]-]\d{4}[[:space:]-]\d{3}[0-9X]+)\/{0,1}\z/.match(orcid)).last
  orcid.gsub(/[[:space:]]/, "-") if orcid.present?
end

#validate_orcid_scheme(orcid_scheme) ⇒ Object 



613
614
615
 
# File 'lib/bolognese/utils.rb', line 613

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

#validate_ror(ror) ⇒ Object 



609
610
611
 
# File 'lib/bolognese/utils.rb', line 609

def validate_ror(ror)
  Array(/^(?:(?:(?:http|https):\/\/)?ror\.org\/)?(0\w{6}\d{2})\/{0,1}$/.match(ror)).last
end

#validate_url(str) ⇒ Object 



617
618
619
620
621
622
623
624
625
 
# File 'lib/bolognese/utils.rb', line 617

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