Module: Commonmeta::Utils

Included in:
CLI, MetadataUtils
Defined in:
lib/commonmeta/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/2.0/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",
}
BIB_TO_CM_TRANSLATIONS =

source: https://www.bibtex.com/e/entry-types/

{
  "article" => "JournalArticle",
  "book" => "Book",
  "booklet" => "Book",
  "inbook" => "BookChapter",
  "inproceedings" => "ProceedingsArticle",
  "manual" => "Report",
  "mastersthesis" => "Dissertation",
  "misc" => "Other",
  "phdthesis" => "Dissertation",
  "proceedings" => "Proceedings",
  "techreport" => "Report",
  "unpublished" => "Manuscript",
}
CM_TO_BIB_TRANSLATIONS = 
{
  "Article" => "article",
  "Book" => "book",
  "BookChapter" => "inbook",
  "Dissertation" => "phdthesis",
  "JournalArticle" => "article",
  "Manuscript" => "unpublished",
  "Other" => "misc",
  "Proceedings" => "proceedings",
  "ProceedingsArticle" => "inproceedings",
  "Report" => "techreport",
}
CSL_TO_CM_TRANSLATIONS =

source: https://docs.citationstyles.org/en/stable/specification.html?highlight=book#appendix-iii-types

{
  "article" => "Article",
  "article-journal" => "JournalArticle",
  "article-magazine" => "Article",
  "article-newspaper" => "Article",
  "bill" => "LegalDocument",
  "book" => "Book",
  "broadcast" => "Audiovisual",
  "chapter" => "BookChapter",
  "classic" => "Book",
  "collection" => "Collection",
  "dataset" => "Dataset",
  "document" => "Document",
  "entry" => "Entry",
  "entry-dictionary" => "Entry",
  "entry-encyclopedia" => "Entry",
  "event" => "Event",
  "figure" => "Figure",
  "graphic" => "Image",
  "hearing" => "LegalDocument",
  "interview" => "Document",
  "legal_case" => "LegalDocument",
  "legislation" => "LegalDocument",
  "manuscript" => "Manuscript",
  "map" => "Map",
  "motion_picture" => "Audiovisual",
  "musical_score" => "Document",
  "pamphlet" => "Document",
  "paper-conference" => "ProceedingsArticle",
  "patent" => "Patent",
  "performance" => "Performance",
  "periodical" => "Journal",
  "personal_communication" => "PersonalCommunication",
  "post" => "Post",
  "post-weblog" => "Article",
  "regulation" => "LegalDocument",
  "report" => "Report",
  "review" => "Review",
  "review-book" => "Review",
  "software" => "Software",
  "song" => "Audiovisual",
  "speech" => "Speech",
  "standard" => "Standard",
  "thesis" => "Dissertation",
  "treaty" => "LegalDocument",
  "webpage" => "WebPage",
}
CM_TO_CSL_TRANSLATIONS = 
{
  "Article" => "article",
  "JournalArticle" => "article-journal",
  "Book" => "book",
  "BookChapter" => "chapter",
  "Collection" => "collection",
  "Dataset" => "dataset",
  "Document" => "document",
  "Entry" => "entry",
  "Event" => "event",
  "Figure" => "figure",
  "Image" => "graphic",
  "LegalDocument" => "legal_case",
  "Manuscript" => "manuscript",
  "Map" => "map",
  "Audiovisual" => "motion_picture",
  "Patent" => "patent",
  "Performance" => "performance",
  "Journal" => "periodical",
  "PersonalCommunication" => "personal_communication",
  "Post" => "post",
  "Report" => "report",
  "Review" => "review",
  "Software" => "software",
  "Speech" => "speech",
  "Standard" => "standard",
  "Dissertation" => "thesis",
  "WebPage" => "webpage",
}
CR_TO_CM_TRANSLATIONS =

source: http://api.crossref.org/types

{
  "BookChapter" => "BookChapter",
  "BookPart" => "BookPart",
  "BookSection" => "BookSection",
  "BookSeries" => "BookSeries",
  "BookSet" => "BookSet",
  "BookTrack" => "BookTrack",
  "Book" => "Book",
  "Component" => "Component",
  "Database" => "Database",
  "Dataset" => "Dataset",
  "Dissertation" => "Dissertation",
  "EditedBook" => "EditedBook",
  "Grant" => "Grant",
  "JournalArticle" => "JournalArticle",
  "JournalIssue" => "JournalIssue",
  "JournalVolume" => "JournalVolume",
  "Journal" => "Journal",
  "Monograph" => "Book",
  "Other" => "Other",
  "PeerReview" => "PeerReview",
  "PostedContent" => "Article",
  "ProceedingsArticle" => "ProceedingsArticle",
  "ProceedingsSeries" => "ProceedingsSeries",
  "Proceedings" => "Proceedings",
  "ReferenceBook" => "ReferenceBook",
  "ReferenceEntry" => "Entry",
  "ReportComponent" => "ReportComponent",
  "ReportSeries" => "ReportSeries",
  "Report" => "Report",
  "Standard" => "Standard",
}
CM_TO_CR_TRANSLATIONS = 
{
  "Article" => "PostedContent",
  "BookChapter" => "BookChapter",
  "BookSeries" => "BookSeries",
  "Book" => "Book",
  "Component" => "Component",
  "Dataset" => "Dataset",
  "Dissertation" => "Dissertation",
  "Grant" => "Grant",
  "JournalArticle" => "JournalArticle",
  "JournalIssue" => "JournalIssue",
  "JournalVolume" => "JournalVolume",
  "Journal" => "Journal",
  "ProceedingsArticle" => "ProceedingsArticle",
  "ProceedingsSeries" => "ProceedingsSeries",
  "Proceedings" => "Proceedings",
  "ReportComponent" => "ReportComponent",
  "ReportSeries" => "ReportSeries",
  "Report" => "Report",
  "PeerReview" => "PeerReview",
  "Other" => "Other",
}
DC_TO_CM_TRANSLATIONS =

source: https://github.com/datacite/schema/blob/master/source/meta/kernel-4/include/datacite-resourceType-v4.xsd

{
  "Audiovisual" => "Audiovisual",
  "BlogPosting" => "Article",
  "Book" => "Book",
  "BookChapter" => "BookChapter",
  "Collection" => "Collection",
  "ComputationalNotebook" => "ComputationalNotebook",
  "ConferencePaper" => "ProceedingsArticle",
  "ConferenceProceeding" => "Proceedings",
  "DataPaper" => "JournalArticle",
  "Dataset" => "Dataset",
  "Dissertation" => "Dissertation",
  "Event" => "Event",
  "Image" => "Image",
  "InteractiveResource" => "InteractiveResource",
  "Journal" => "Journal",
  "JournalArticle" => "JournalArticle",
  "Model" => "Model",
  "OutputManagementPlan" => "OutputManagementPlan",
  "PeerReview" => "PeerReview",
  "PhysicalObject" => "PhysicalObject",
  "Poster" => "Speech",
  "Preprint" => "Article",
  "Report" => "Report",
  "Service" => "Service",
  "Software" => "Software",
  "Sound" => "Sound",
  "Standard" => "Standard",
  "Text" => "Document",
  "Thesis" => "Dissertation",
  "Workflow" => "Workflow",
  "Other" => "Other",
}
CM_TO_DC_TRANSLATIONS = 
{
  "Article" => "Preprint",
  "Audiovisual" => "Audiovisual",
  "Book" => "Book",
  "BookChapter" => "BookChapter",
  "Collection" => "Collection",
  "Dataset" => "Dataset",
  "Dissertation" => "Dissertation",
  "Document" => "Text",
  "Entry" => "Text",
  "Event" => "Event",
  "Figure" => "Image",
  "Image" => "Image",
  "JournalArticle" => "JournalArticle",
  "LegalDocument" => "Text",
  "Manuscript" => "Text",
  "Map" => "Image",
  "Patent" => "Text",
  "Performance" => "Audiovisual",
  "PersonalCommunication" => "Text",
  "Post" => "Text",
  "ProceedingsArticle" => "ConferencePaper",
  "Proceedings" => "ConferenceProceeding",
  "Report" => "Report",
  "PeerReview" => "PeerReview",
  "Software" => "Software",
  "Sound" => "Sound",
  "Standard" => "Standard",
  "WebPage" => "Text",
}
RIS_TO_CM_TRANSLATIONS = 
{
  "ABST" => "Text",
  "ADVS" => "Text",
  "AGGR" => "Text",
  "ANCIENT" => "Text",
  "ART" => "Text",
  "BILL" => "Text",
  "BLOG" => "Text",
  "BOOK" => "Book",
  "CASE" => "Text",
  "CHAP" => "BookChapter",
  "CHART" => "Text",
  "CLSWK" => "Text",
  "CTLG" => "Collection",
  "COMP" => "Software",
  "DATA" => "Dataset",
  "DBASE" => "Database",
  "DICT" => "Dictionary",
  "EBOOK" => "Book",
  "ECHAP" => "BookChapter",
  "EDBOOK" => "Book",
  "EJOUR" => "JournalArticle",
  "ELEC" => "Text",
  "ENCYC" => "Encyclopedia",
  "EQUA" => "Equation",
  "FIGURE" => "Image",
  "GEN" => "CreativeWork",
  "GOVDOC" => "GovernmentDocument",
  "GRANT" => "Grant",
  "HEAR" => "Hearing",
  "ICOMM" => "Text",
  "INPR" => "Text",
  "JFULL" => "JournalArticle",
  "JOUR" => "JournalArticle",
  "LEGAL" => "LegalRuleOrRegulation",
  "MANSCPT" => "Text",
  "MAP" => "Map",
  "MGZN" => "MagazineArticle",
  "MPCT" => "Audiovisual",
  "MULTI" => "Audiovisual",
  "MUSIC" => "MusicScore",
  "NEWS" => "NewspaperArticle",
  "PAMP" => "Pamphlet",
  "PAT" => "Patent",
  "PCOMM" => "PersonalCommunication",
  "RPRT" => "Report",
  "SER" => "SerialPublication",
  "SLIDE" => "Slide",
  "SOUND" => "SoundRecording",
  "STAND" => "Standard",
  "THES" => "Dissertation",
  "UNBILL" => "UnenactedBill",
  "UNPB" => "UnpublishedWork",
  "VIDEO" => "Audiovisual",
  "WEB" => "WebPage",
}
CM_TO_RIS_TRANSLATIONS = 
{
  "Article" => "JOUR",
  "Audiovisual" => "VIDEO",
  "Book" => "BOOK",
  "BookChapter" => "CHAP",
  "Collection" => "CTLG",
  "Dataset" => "DATA",
  "Dissertation" => "THES",
  "Document" => "GEN",
  "Entry" => "DICT",
  "Event" => "GEN",
  "Figure" => "FIGURE",
  "Image" => "FIGURE",
  "JournalArticle" => "JOUR",
  "LegalDocument" => "GEN",
  "Manuscript" => "GEN",
  "Map" => "MAP",
  "Patent" => "PAT",
  "Performance" => "GEN",
  "PersonalCommunication" => "PCOMM",
  "Post" => "GEN",
  "ProceedingsArticle" => "CPAPER",
  "Proceedings" => "CONF",
  "Report" => "RPRT",
  "Review" => "GEN",
  "Software" => "COMP",
  "Sound" => "SOUND",
  "Standard" => "STAND",
  "WebPage" => "WEB",
}
SO_TO_CM_TRANSLATIONS = 
{
  "Article" => "Article",
  "BlogPosting" => "Article",
  "Book" => "Book",
  "BookChapter" => "BookChapter",
  "CreativeWork" => "Other",
  "Dataset" => "Dataset",
  "Dissertation" => "Dissertation",
  "NewsArticle" => "Article",
  "Legislation" => "LegalDocument",
  "ScholarlyArticle" => "JournalArticle",
  "SoftwareSourceCode" => "Software",
}
CM_TO_SO_TRANSLATIONS = 
{
  "Article" => "Article",
  "Audiovisual" => "CreativeWork",
  "Book" => "Book",
  "BookChapter" => "BookChapter",
  "Collection" => "CreativeWork",
  "Dataset" => "Dataset",
  "Dissertation" => "Dissertation",
  "Document" => "CreativeWork",
  "Entry" => "CreativeWork",
  "Event" => "CreativeWork",
  "Figure" => "CreativeWork",
  "Image" => "CreativeWork",
  "JournalArticle" => "ScholarlyArticle",
  "LegalDocument" => "Legislation",
  "Software" => "SoftwareSourceCode",
}
CM_TO_JATS_TRANSLATIONS = 
{
  "Proceedings" => "working-paper",
  "ReferenceBook" => "book",
  "JournalIssue" => "journal",
  "ProceedingsArticle" => "working-paper",
  "Other" => nil,
  "Dissertation" => nil,
  "Dataset" => "data",
  "Document" => "journal",
  "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",
  "Article" => "journal",
  "Software" => "software",
}
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)",
}

Instance Method Summary collapse

Instance Method Details

#decode_container_id(id) ⇒ Object 



1361
1362
1363
 
# File 'lib/commonmeta/utils.rb', line 1361

def decode_container_id(id)
  Base32::URL.decode(id)
end

#decode_doi(doi) ⇒ Object 



1349
1350
1351
1352
 
# File 'lib/commonmeta/utils.rb', line 1349

def decode_doi(doi)
  suffix = doi.split("/", 5).last
  Base32::URL.decode(suffix)
end

#encode_container_id ⇒ Object 



1354
1355
1356
1357
1358
1359
 
# File 'lib/commonmeta/utils.rb', line 1354

def encode_container_id
  # suffix has 5 digits plus two checksum digits. With base32 there are
  # 32 possible digits, so 5 digits gives 32^5 possible combinations
  random_int = SecureRandom.random_number(32 ** 4..(32 ** 5) - 1)
  Base32::URL.encode(random_int, checksum: true)
end

#encode_doi(prefix) ⇒ Object 



1339
1340
1341
1342
1343
1344
1345
1346
1347
 
# File 'lib/commonmeta/utils.rb', line 1339

def encode_doi(prefix)
  # DOI suffix is a generated from a random number, encoded in base32
  # suffix has 8 digits plus two checksum digits. With base32 there are
  # 32 possible digits, so 8 digits gives 32^8 possible combinations
  random_int = SecureRandom.random_number(32 ** 7..(32 ** 8) - 1)
  suffix = Base32::URL.encode(random_int, checksum: true)
  str = "#{suffix[0, 5]}-#{suffix[5, 10]}"
  "https://doi.org/#{prefix}/#{str}"
end

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



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

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

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



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

def find_from_format_by_ext(string, options = {})
  case options[:ext]
  when ".bib"
    "bibtex"
  when ".ris"
    "ris"
  when ".xml", ".json"
    find_from_format_by_string(string)
  end
end

#find_from_format_by_filename(filename) ⇒ Object 



476
477
478
479
480
481
482
 
# File 'lib/commonmeta/utils.rb', line 476

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

#find_from_format_by_id(id) ⇒ Object 



455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
 
# File 'lib/commonmeta/utils.rb', line 455

def find_from_format_by_id(id)
  id = normalize_id(id)

  if %r{\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 %r{\A(?:(http|https):/(/)?orcid\.org/)?(\d{4}-\d{4}-\d{4}-\d{3}[0-9X]+)\z}.match?(id)
    "orcid"
  elsif %r{\A(http|https):/(/)?github\.com/(.+)/package.json\z}.match?(id)
    "npm"
  elsif %r{\A(http|https):/(/)?github\.com/(.+)/codemeta.json\z}.match?(id)
    "codemeta"
  elsif %r{\A(http|https):/(/)?github\.com/(.+)/CITATION.cff\z}.match?(id)
    "cff"
  elsif %r{\A(http|https):/(/)?github\.com/(.+)\z}.match?(id)
    "cff"
  else
    "schema_org"
  end
end

#find_from_format_by_string(string) ⇒ Object 



495
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
 
# File 'lib/commonmeta/utils.rb', line 495

def find_from_format_by_string(string)
  begin # try to parse as JSON
    hsh = MultiJson.load(string).to_h
    if hsh.dig("@context") && URI.parse(hsh.dig("@context")).host == "schema.org"
      return "schema_org"
    elsif hsh.dig("schemaVersion").to_s.start_with?("http://datacite.org/schema/kernel")
      return "datacite"
    elsif hsh.dig("source") == "Crossref"
      return "crossref"
    elsif hsh.dig("issued", "date-parts").present?
      return "csl"
    elsif URI.parse(hsh.dig("@context")).to_s == "https://raw.githubusercontent.com/codemeta/codemeta/master/codemeta.jsonld"
      return "codemeta"
    end
  rescue MultiJson::ParseError
  end

  begin # try to parse as XML
    hsh = Hash.from_xml(string)
    return "crossref_xml" if hsh.to_h.dig("crossref_result").present?
  rescue Nokogiri::XML::SyntaxError
  end

  begin # try to parse as YAML
    hsh = YAML.load(string, permitted_classes: [Date])
    return "cff" if hsh.is_a?(Hash) && hsh.fetch("cff-version", nil).present?
  rescue Psych::SyntaxError
  end

  if string.start_with?("TY  - ")
    "ris"
  elsif BibTeX.parse(string).first
    "bibtex"
  end
end

#from_csl(element) ⇒ Object 



878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
 
# File 'lib/commonmeta/utils.rb', line 878

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

#from_datacite(element) ⇒ Object 



695
696
697
698
699
 
# File 'lib/commonmeta/utils.rb', line 695

def from_datacite(element)
  mapping = { "nameType" => "type", "creatorName" => "name" }

  map_hash_keys(element: element, mapping: mapping)
end

#from_schema_org(element) ⇒ Object 



838
839
840
841
842
 
# File 'lib/commonmeta/utils.rb', line 838

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

  map_hash_keys(element: element, mapping: mapping)
end

#get_contributor(contributor, contributor_type) ⇒ Object 



1101
1102
1103
 
# File 'lib/commonmeta/utils.rb', line 1101

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

#get_date(dates, date_type) ⇒ Object 



1082
1083
1084
1085
 
# File 'lib/commonmeta/utils.rb', line 1082

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 



1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
 
# File 'lib/commonmeta/utils.rb', line 1001

def get_date_from_date_parts(date_as_parts)
  date_parts = date_as_parts.fetch("date-parts", []).first
  return nil if date_parts == [nil]

  year = date_parts[0]
  month = date_parts[1]
  day = date_parts[2]
  get_date_from_parts(year, month, day)
rescue NoMethodError # if date_parts is nil
  nil
end

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



1013
1014
1015
1016
1017
 
# File 'lib/commonmeta/utils.rb', line 1013

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 do |part|
    part == "00"
  end.join("-")
end

#get_date_parts(iso8601_time) ⇒ Object 



990
991
992
993
994
995
996
997
998
999
 
# File 'lib/commonmeta/utils.rb', line 990

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 



1019
1020
1021
 
# File 'lib/commonmeta/utils.rb', line 1019

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_dates_from_date(date) ⇒ Object

convert commonmeta dates to DataCite format



1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
 
# File 'lib/commonmeta/utils.rb', line 1088

def get_dates_from_date(date)
  return nil if date.nil?

  mapping = { "published" => "issued" }

  date = map_hash_keys(element: date, mapping: mapping)

  date.map do |k, v|
    { "date" => v,
      "dateType" => k.capitalize }
  end
end

#get_datetime_from_iso8601(iso8601_time) ⇒ Object

parsing of incomplete iso8601 timestamps such as 2015-04 is broken in standard library, so we use the edtf gem return nil if invalid iso8601 timestamp



1058
1059
1060
1061
1062
 
# File 'lib/commonmeta/utils.rb', line 1058

def get_datetime_from_iso8601(iso8601_time)
  Date.edtf(iso8601_time).to_time.utc
rescue StandardError
  nil
end

#get_datetime_from_time(time) ⇒ Object

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



1076
1077
1078
1079
1080
 
# File 'lib/commonmeta/utils.rb', line 1076

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 



1105
1106
1107
1108
 
# File 'lib/commonmeta/utils.rb', line 1105

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 



1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
 
# File 'lib/commonmeta/utils.rb', line 1110

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 



1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
 
# File 'lib/commonmeta/utils.rb', line 1023

def get_iso8601_date(iso8601_time)
  return nil if iso8601_time.nil? || iso8601_time.length < 4

  case iso8601_time.length
  when 4
    iso8601_time[0..3]
  when 7
    iso8601_time[0..6]
  else
    iso8601_time[0..9]
  end
end

#get_series_information(str) ⇒ Object 



1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
 
# File 'lib/commonmeta/utils.rb', line 1140

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 



1036
1037
1038
1039
1040
1041
1042
1043
 
# File 'lib/commonmeta/utils.rb', line 1036

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 



1045
1046
1047
1048
1049
1050
1051
1052
1053
 
# File 'lib/commonmeta/utils.rb', line 1045

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_cff_url(url) ⇒ Object 



980
981
982
983
984
985
986
987
988
 
# File 'lib/commonmeta/utils.rb', line 980

def github_as_cff_url(url)
  github_hash = github_from_url(url)

  if github_hash[:path].to_s.end_with?("CITATION.cff")
    "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]}/main/CITATION.cff"
  end
end

#github_as_codemeta_url(url) ⇒ Object 



970
971
972
973
974
975
976
977
978
 
# File 'lib/commonmeta/utils.rb', line 970

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 



951
952
953
954
 
# File 'lib/commonmeta/utils.rb', line 951

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 



963
964
965
966
967
968
 
# File 'lib/commonmeta/utils.rb', line 963

def github_as_release_url(url)
  github_hash = github_from_url(url)
  return unless github_hash[:release].present?

  "https://github.com/#{github_hash[:owner]}/#{github_hash[:repo]}/tree/#{github_hash[:release]}"
end

#github_as_repo_url(url) ⇒ Object 



956
957
958
959
960
961
 
# File 'lib/commonmeta/utils.rb', line 956

def github_as_repo_url(url)
  github_hash = github_from_url(url)
  return unless github_hash[:repo].present?

  "https://github.com/#{github_hash[:owner]}/#{github_hash[:repo]}"
end

#github_from_url(url) ⇒ Object 



930
931
932
933
934
935
936
937
 
# File 'lib/commonmeta/utils.rb', line 930

def github_from_url(url)
  return {} unless %r{\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 



947
948
949
 
# File 'lib/commonmeta/utils.rb', line 947

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

#github_release_from_url(url) ⇒ Object 



943
944
945
 
# File 'lib/commonmeta/utils.rb', line 943

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

#github_repo_from_url(url) ⇒ Object 



939
940
941
 
# File 'lib/commonmeta/utils.rb', line 939

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

#hsh_to_fos(hsh) ⇒ Object 



1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
 
# File 'lib/commonmeta/utils.rb', line 1266

def hsh_to_fos(hsh)
  # first find subject in Fields of Science (OECD)
  fos = JSON.load(File.read(File.expand_path("../../resources/oecd/fos-mappings.json",
                                             __dir__))).fetch("fosFields")
  subject = fos.find do |l|
    l["fosLabel"] == hsh["__content__"] || "FOS: " + l["fosLabel"] == hsh["__content__"] || l["fosLabel"] == hsh["subject"]
  end

  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 = JSON.load(File.read(File.expand_path("../../resources/oecd/for-mappings.json",
                                               __dir__)))
  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 do |l|
      l["forLabel"] == hsh["__content__"] || l["forLabel"] == hsh["subject"]
    end ||
              for_disciplines.find do |l|
                l["forLabel"] == hsh["__content__"] || l["forLabel"] == hsh["subject"]
              end
  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 



1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
 
# File 'lib/commonmeta/utils.rb', line 1185

def hsh_to_spdx(hsh)
  spdx = JSON.load(File.read(File.expand_path("../../resources/spdx/licenses.json",
                                              __dir__))).fetch("licenses")
  hsh["rightsUri"] = hsh.delete("rightsURI") if hsh["rightsUri"].blank?
  license = spdx.find do |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"])
  end

  if license
    { "id" => license["licenseId"], "url" => license["seeAlso"].first }.compact
  else
    {
      "id" => hsh["rightsIdentifier"].present? ? hsh["rightsIdentifier"].downcase : nil,
      "url" => hsh["rightsURI"] || hsh["rightsUri"],
    }.compact
  end
end

#jsonlint(json) ⇒ Object 



1162
1163
1164
1165
1166
1167
1168
1169
 
# File 'lib/commonmeta/utils.rb', line 1162

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 



844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
 
# File 'lib/commonmeta/utils.rb', line 844

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 k == "affiliation" && v.is_a?(Array)
        hsh[k] = v.map do |affiliation|
          if affiliation.is_a?(Hash)
            affiliation.merge("@type" => "Organization")
          else
            affiliation
          end
        end
        hsh
      elsif k == "type" && v.is_a?(String)
        hsh[k] = v.capitalize
        hsh
      elsif 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 



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
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
 
# File 'lib/commonmeta/utils.rb', line 1224

def name_to_fos(name)
  # first find subject in Fields of Science (OECD)
  fos = JSON.load(File.read(File.expand_path("../../resources/oecd/fos-mappings.json",
                                             __dir__))).fetch("fosFields")

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

  if subject
    return [{
             "subject" => sanitize(name).downcase,
           },
            {
             "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 = JSON.load(File.read(File.expand_path("../../resources/oecd/for-mappings.json",
                                               __dir__)))
  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).downcase,
    },
     {
      "subject" => "FOS: " + subject["fosLabel"],
      "subjectScheme" => "Fields of Science and Technology (FOS)",
      "schemeUri" => "http://www.oecd.org/science/inno/38235147.pdf",
    }]
  else
    [{ "subject" => sanitize(name).downcase }]
  end
end

#name_to_spdx(name) ⇒ Object 



1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
 
# File 'lib/commonmeta/utils.rb', line 1171

def name_to_spdx(name)
  spdx = JSON.load(File.read(File.expand_path("../../resources/spdx/licenses.json",
                                              __dir__))).fetch("licenses")
  license = spdx.find do |l|
    l["name"] == name || l["licenseId"] == name || l["seeAlso"].first == normalize_cc_url(name)
  end

  if license
    { "id" => license["licenseId"], "url" => license["seeAlso"].first }.compact
  else
    { "rights" => name }
  end
end

#normalize_cc_url(id) ⇒ Object 



610
611
612
613
 
# File 'lib/commonmeta/utils.rb', line 610

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

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



571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
 
# File 'lib/commonmeta/utils.rb', line 571

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_issn(input, options = {}) ⇒ Object

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



625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
 
# File 'lib/commonmeta/utils.rb', line 625

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]
  end
end

#normalize_licenses(licenses) ⇒ Object

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



648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
 
# File 'lib/commonmeta/utils.rb', line 648

def normalize_licenses(licenses)
  standard_licenses = Array.wrap(licenses).map do |l|
    URI.parse(l["url"])
  end.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 



615
616
617
618
619
620
621
 
# File 'lib/commonmeta/utils.rb', line 615

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, options = {}) ⇒ Object 



588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
 
# File 'lib/commonmeta/utils.rb', line 588

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 



535
536
537
 
# File 'lib/commonmeta/utils.rb', line 535

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

#orcid_from_url(url) ⇒ Object 



531
532
533
 
# File 'lib/commonmeta/utils.rb', line 531

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

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



558
559
560
561
562
563
564
565
566
567
568
569
 
# File 'lib/commonmeta/utils.rb', line 558

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
  end
end

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



914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
 
# File 'lib/commonmeta/utils.rb', line 914

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

  if text.is_a?(String)
    # remove excessive internal whitespace with squish
    Loofah.scrub_fragment(text, custom_scrubber).to_s.squish
  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
  end
end

#spdx_to_hsh(hsh) ⇒ Object 



1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
 
# File 'lib/commonmeta/utils.rb', line 1203

def spdx_to_hsh(hsh)
  return nil unless hsh.present? && hsh.is_a?(Hash)

  spdx = JSON.load(File.read(File.expand_path("../../resources/spdx/licenses.json",
                                              __dir__))).fetch("licenses")

  license = spdx.find { |l| l["licenseId"].casecmp?(hsh["id"]) }

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

#strip_milliseconds(iso8601_time) ⇒ Object

strip milliseconds if there is a time, as it interferes with edtc parsing keep dates unchanged



1066
1067
1068
1069
1070
1071
1072
 
# File 'lib/commonmeta/utils.rb', line 1066

def strip_milliseconds(iso8601_time)
  return iso8601_time.split(" ").first if iso8601_time.to_s.include? " "

  return iso8601_time.split(".").first + "Z" if iso8601_time.to_s.include? "."

  iso8601_time
end

#to_csl(element) ⇒ Object 



894
895
896
897
898
899
900
901
902
 
# File 'lib/commonmeta/utils.rb', line 894

def to_csl(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", "contributorType").compact
  end.presence
end

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



686
687
688
689
690
691
692
693
 
# File 'lib/commonmeta/utils.rb', line 686

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

#to_identifier(identifier) ⇒ Object 



870
871
872
873
874
875
876
 
# File 'lib/commonmeta/utils.rb', line 870

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

#to_ris(element) ⇒ Object 



904
905
906
907
908
909
910
911
912
 
# File 'lib/commonmeta/utils.rb', line 904

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 



701
702
703
704
705
 
# File 'lib/commonmeta/utils.rb', line 701

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

  map_hash_keys(element: element, mapping: mapping)
end

#to_schema_org_citation(reference) ⇒ Object 



764
765
766
767
768
769
770
771
772
773
 
# File 'lib/commonmeta/utils.rb', line 764

def to_schema_org_citation(reference)
  return nil unless reference.present?

  {
    "@type" => "CreativeWork",
    "@id" => reference["doi"] ? normalize_id(reference["doi"]) : nil,
    "name" => reference["title"],
    "datePublished" => reference["publicationYear"],
  }.compact
end

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



707
708
709
710
711
712
713
714
715
716
 
# File 'lib/commonmeta/utils.rb', line 707

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

  issn = element["identifier"] if element["identifierType"] == "ISSN"
  id = issn.blank? ? element["identifier"] : nil
  name = options[:container_title] || element["title"]
  type = id || name ? options[:type] || element["type"] : nil

  { "@id" => id, "@type" => type, "name" => name, "issn" => issn }.compact
end

#to_schema_org_funder(funding_references) ⇒ Object 



752
753
754
755
756
757
758
759
760
761
762
 
# File 'lib/commonmeta/utils.rb', line 752

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 



718
719
720
721
722
723
724
725
726
 
# File 'lib/commonmeta/utils.rb', line 718

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

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



728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
 
# File 'lib/commonmeta/utils.rb', line 728

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

  relation_type = if relation_type == "References"
      %w[References Cites
         Documents]
    else
      [relation_type]
    end

  Array.wrap(related_identifiers).select do |ri|
    relation_type.include?(ri["relationType"])
  end.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 



775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
 
# File 'lib/commonmeta/utils.rb', line 775

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

  Array.wrap(geo_location).each_with_object([]) do |gl, sum|
    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|
              [glpp.dig("polygonPoint", "pointLongitude"),
               glpp.dig("polygonPoint", "pointLatitude")].compact
            end.compact
          end.compact.presence,
        },
      }
    end

    next unless 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.unwrap
end

#validate_orcid(orcid) ⇒ Object 



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

def validate_orcid(orcid)
  orcid = Array(%r{\A(?:(?:http|https)://(?:(?:www|sandbox)?\.)?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 



544
545
546
 
# File 'lib/commonmeta/utils.rb', line 544

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

#validate_url(str) ⇒ Object 



548
549
550
551
552
553
554
555
556
 
# File 'lib/commonmeta/utils.rb', line 548

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