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 



1392
1393
1394
 
# File 'lib/commonmeta/utils.rb', line 1392

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

#decode_doi(doi) ⇒ Object 



1380
1381
1382
1383
 
# File 'lib/commonmeta/utils.rb', line 1380

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

#encode_container_id ⇒ Object 



1385
1386
1387
1388
1389
1390
 
# File 'lib/commonmeta/utils.rb', line 1385

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 



1370
1371
1372
1373
1374
1375
1376
1377
1378
 
# File 'lib/commonmeta/utils.rb', line 1370

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 



486
487
488
489
490
491
492
493
494
495
 
# File 'lib/commonmeta/utils.rb', line 486

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 



478
479
480
481
482
483
484
 
# File 'lib/commonmeta/utils.rb', line 478

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
475
476
 
# 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"
  elsif %r{\A(http|https):/(/)?rogue-scholar\.org/api/posts/(.+)\z}.match?(id)
    "json_feed_item"
  else
    "schema_org"
  end
end

#find_from_format_by_string(string) ⇒ Object 



497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
 
# File 'lib/commonmeta/utils.rb', line 497

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 



898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
 
# File 'lib/commonmeta/utils.rb', line 898

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 



709
710
711
712
713
 
# File 'lib/commonmeta/utils.rb', line 709

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

  map_hash_keys(element: element, mapping: mapping)
end

#from_json_feed(element) ⇒ Object 



892
893
894
895
896
 
# File 'lib/commonmeta/utils.rb', line 892

def from_json_feed(element)
  mapping = { "url" => "id" }

  map_hash_keys(element: element, mapping: mapping)
end

#from_schema_org(element) ⇒ Object 



852
853
854
855
856
 
# File 'lib/commonmeta/utils.rb', line 852

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

  map_hash_keys(element: element, mapping: mapping)
end

#get_contributor(contributor, contributor_type) ⇒ Object 



1132
1133
1134
 
# File 'lib/commonmeta/utils.rb', line 1132

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

#get_date(dates, date_type) ⇒ Object 



1104
1105
1106
1107
 
# File 'lib/commonmeta/utils.rb', line 1104

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 



1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
 
# File 'lib/commonmeta/utils.rb', line 1021

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 



1033
1034
1035
1036
1037
 
# File 'lib/commonmeta/utils.rb', line 1033

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 



1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
 
# File 'lib/commonmeta/utils.rb', line 1010

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 



1039
1040
1041
 
# File 'lib/commonmeta/utils.rb', line 1039

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



1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
 
# File 'lib/commonmeta/utils.rb', line 1119

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



1078
1079
1080
1081
1082
 
# File 'lib/commonmeta/utils.rb', line 1078

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



1098
1099
1100
1101
1102
 
# File 'lib/commonmeta/utils.rb', line 1098

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 



1136
1137
1138
1139
 
# File 'lib/commonmeta/utils.rb', line 1136

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 



1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
 
# File 'lib/commonmeta/utils.rb', line 1141

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 



1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
 
# File 'lib/commonmeta/utils.rb', line 1043

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_link(links, link_type) ⇒ Object 



1109
1110
1111
1112
 
# File 'lib/commonmeta/utils.rb', line 1109

def get_link(links, link_type)
  ll = Array.wrap(links).find { |d| d["rel"] == link_type } || {}
  ll.fetch("href", nil)
end

#get_series_information(str) ⇒ Object 



1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
 
# File 'lib/commonmeta/utils.rb', line 1171

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 



1056
1057
1058
1059
1060
1061
1062
1063
 
# File 'lib/commonmeta/utils.rb', line 1056

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 



1065
1066
1067
1068
1069
1070
1071
1072
1073
 
# File 'lib/commonmeta/utils.rb', line 1065

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 



1000
1001
1002
1003
1004
1005
1006
1007
1008
 
# File 'lib/commonmeta/utils.rb', line 1000

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 



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

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 



971
972
973
974
 
# File 'lib/commonmeta/utils.rb', line 971

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 



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

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 



976
977
978
979
980
981
 
# File 'lib/commonmeta/utils.rb', line 976

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 



950
951
952
953
954
955
956
957
 
# File 'lib/commonmeta/utils.rb', line 950

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 



967
968
969
 
# File 'lib/commonmeta/utils.rb', line 967

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

#github_release_from_url(url) ⇒ Object 



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

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

#github_repo_from_url(url) ⇒ Object 



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

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

#hsh_to_fos(hsh) ⇒ Object 



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
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
 
# File 'lib/commonmeta/utils.rb', line 1297

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 



1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
 
# File 'lib/commonmeta/utils.rb', line 1216

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

#json_feed_unregistered_url ⇒ Object 



1396
1397
1398
 
# File 'lib/commonmeta/utils.rb', line 1396

def json_feed_unregistered_url
  "https://rogue-scholar.org/api/posts/unregistered"
end

#jsonlint(json) ⇒ Object 



1193
1194
1195
1196
1197
1198
1199
1200
 
# File 'lib/commonmeta/utils.rb', line 1193

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 



858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
 
# File 'lib/commonmeta/utils.rb', line 858

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 



1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
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
 
# File 'lib/commonmeta/utils.rb', line 1255

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 



1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
 
# File 'lib/commonmeta/utils.rb', line 1202

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 



624
625
626
627
 
# File 'lib/commonmeta/utils.rb', line 624

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

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



579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
 
# File 'lib/commonmeta/utils.rb', line 579

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



639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
 
# File 'lib/commonmeta/utils.rb', line 639

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



662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
 
# File 'lib/commonmeta/utils.rb', line 662

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 



629
630
631
632
633
634
635
 
# File 'lib/commonmeta/utils.rb', line 629

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 



596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
 
# File 'lib/commonmeta/utils.rb', line 596

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)

  # optionally remove query and fragment
  if options[:remove_query_string]
    uri.query = nil
    uri.fragment = nil
  end

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

#orcid_as_url(orcid) ⇒ Object 



537
538
539
 
# File 'lib/commonmeta/utils.rb', line 537

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

#orcid_from_url(url) ⇒ Object 



533
534
535
 
# File 'lib/commonmeta/utils.rb', line 533

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

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



566
567
568
569
570
571
572
573
574
575
576
577
 
# File 'lib/commonmeta/utils.rb', line 566

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

#rogue_scholar_api_url(id, _options = {}) ⇒ Object 



1114
1115
1116
 
# File 'lib/commonmeta/utils.rb', line 1114

def rogue_scholar_api_url(id, _options = {})
  "https://rogue-scholar.org/api/posts/#{id}"
end

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



934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
 
# File 'lib/commonmeta/utils.rb', line 934

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 



1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
 
# File 'lib/commonmeta/utils.rb', line 1234

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



1086
1087
1088
1089
1090
1091
1092
1093
1094
 
# File 'lib/commonmeta/utils.rb', line 1086

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? "."

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

  iso8601_time
end

#to_csl(element) ⇒ Object 



914
915
916
917
918
919
920
921
922
 
# File 'lib/commonmeta/utils.rb', line 914

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 



700
701
702
703
704
705
706
707
 
# File 'lib/commonmeta/utils.rb', line 700

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 



884
885
886
887
888
889
890
 
# File 'lib/commonmeta/utils.rb', line 884

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

#to_ris(element) ⇒ Object 



924
925
926
927
928
929
930
931
932
 
# File 'lib/commonmeta/utils.rb', line 924

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 



715
716
717
718
719
 
# File 'lib/commonmeta/utils.rb', line 715

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 



778
779
780
781
782
783
784
785
786
787
 
# File 'lib/commonmeta/utils.rb', line 778

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 



721
722
723
724
725
726
727
728
729
730
 
# File 'lib/commonmeta/utils.rb', line 721

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 



766
767
768
769
770
771
772
773
774
775
776
 
# File 'lib/commonmeta/utils.rb', line 766

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 



732
733
734
735
736
737
738
739
740
 
# File 'lib/commonmeta/utils.rb', line 732

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 



742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
 
# File 'lib/commonmeta/utils.rb', line 742

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 



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
837
838
839
840
841
842
843
844
845
846
847
848
849
850
 
# File 'lib/commonmeta/utils.rb', line 789

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_email(str) ⇒ Object 



560
561
562
563
564
 
# File 'lib/commonmeta/utils.rb', line 560

def validate_email(str)
  email_regex = /\b[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,4}\b/i
  parsed_emails = str.scan(email_regex)
  parsed_emails.first
end

#validate_orcid(orcid) ⇒ Object 



541
542
543
544
 
# File 'lib/commonmeta/utils.rb', line 541

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 



546
547
548
 
# File 'lib/commonmeta/utils.rb', line 546

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

#validate_url(str) ⇒ Object 



550
551
552
553
554
555
556
557
558
 
# File 'lib/commonmeta/utils.rb', line 550

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