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: 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: 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: 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: 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",
  "Instrument" => "Instrument",
  "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",
  "StudyRegistration" => "StudyRegistration",
  "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",
  "Instrument" => "Instrument",
  "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",
  "StudyRegistration" => "StudyRegistration",
  "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",
  "Instrument" => "Instrument",
  "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",
  "Instrument" => "Instrument",
  "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 



1499
1500
1501
 
# File 'lib/commonmeta/utils.rb', line 1499

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

#decode_doi(doi, options = {}) ⇒ Object 



1483
1484
1485
1486
1487
1488
1489
1490
 
# File 'lib/commonmeta/utils.rb', line 1483

def decode_doi(doi, options = {})
  suffix = doi.split("/", 5).last
  if options[:uuid]
    Base32::URL.decode_uuid(suffix)
  else
    Base32::URL.decode(suffix)
  end
end

#encode_container_id ⇒ Object 



1492
1493
1494
1495
1496
1497
 
# File 'lib/commonmeta/utils.rb', line 1492

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, options = {}) ⇒ Object 



1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
 
# File 'lib/commonmeta/utils.rb', line 1449

def encode_doi(prefix, options = {})
  return nil unless prefix.present?

  # 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
  if options[:uuid]
    str = Base32::URL.encode_uuid(options[:uuid], split: 7, checksum: true)
    return nil unless str.present?
  else
    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]}"
  end
  "https://doi.org/#{prefix}/#{str}"
end

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



1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
 
# File 'lib/commonmeta/utils.rb', line 1466

def encode_doi_for_id(id, options = {})
  # look up prefix for rogue scholar blog associated with id
  # returns nil if unknown id or doi registration is not enabled for blog
  json_feed_by_id(id)
  # 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
  if options[:uuid]
    str = Base32::URL.encode_uuid(options[:uuid], split: 7, checksum: true)
  else
    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]}"
  end
  "https://doi.org/#{prefix}/#{str}"
end

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



447
448
449
450
451
452
453
454
455
456
457
458
459
 
# File 'lib/commonmeta/utils.rb', line 447

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 



492
493
494
495
496
497
498
499
500
501
 
# File 'lib/commonmeta/utils.rb', line 492

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 



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

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 



461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
 
# File 'lib/commonmeta/utils.rb', line 461

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):/(/)?api\.rogue-scholar\.org/posts/(.+)\z}.match?(id)
    "json_feed_item"
  else
    "schema_org"
  end
end

#find_from_format_by_string(string) ⇒ Object 



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
532
533
534
535
536
537
538
539
540
541
 
# File 'lib/commonmeta/utils.rb', line 503

def find_from_format_by_string(string)
  begin # try to parse as JSON
    hsh = MultiJson.load(string).to_h
    if hsh.dig("blog", "version") == "https://jsonfeed.org/version/1.1"
      return "json_feed_item"
    elsif hsh.dig("schema_version").to_s.start_with?("https://commonmeta.org")
      return "commonmeta"
    elsif 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 hsh.dig("@context") && 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 



960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
 
# File 'lib/commonmeta/utils.rb', line 960

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 



769
770
771
772
773
 
# File 'lib/commonmeta/utils.rb', line 769

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

  map_hash_keys(element: element, mapping: mapping)
end

#from_json_feed(element) ⇒ Object 



954
955
956
957
958
 
# File 'lib/commonmeta/utils.rb', line 954

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

  map_hash_keys(element: element, mapping: mapping)
end

#from_schema_org(element) ⇒ Object 



912
913
914
915
916
 
# File 'lib/commonmeta/utils.rb', line 912

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

  map_hash_keys(element: element, mapping: mapping)
end

#generate_ghost_token(admin_api_key = ) ⇒ Object 



1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
 
# File 'lib/commonmeta/utils.rb', line 1519

def generate_ghost_token(admin_api_key = ENV["API_KEY"])
  # from https://ghost.org/docs/admin-api/

  return nil unless admin_api_key.present?

  # Split the key into ID and SECRET
  id, secret = admin_api_key.split(":")

  # Prepare header and payload
  iat = Time.now.to_i

  header = { alg: "HS256", typ: "JWT", kid: id }
  payload = {
    iat: iat,
    exp: iat + 5 * 60,
    aud: "/admin/",
  }

  # Create the token (including decoding secret)
  JWT.encode payload, [secret].pack("H*"), "HS256", header
end

#get_contributor(contributor, contributor_type) ⇒ Object 



1208
1209
1210
 
# File 'lib/commonmeta/utils.rb', line 1208

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

#get_date(dates, date_type) ⇒ Object 



1180
1181
1182
1183
 
# File 'lib/commonmeta/utils.rb', line 1180

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 



1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
 
# File 'lib/commonmeta/utils.rb', line 1083

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 



1095
1096
1097
1098
1099
 
# File 'lib/commonmeta/utils.rb', line 1095

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_from_unix_timestamp(unix_timestamp) ⇒ Object

parsing of unix timestamps such as 1427846400



1154
1155
1156
1157
1158
 
# File 'lib/commonmeta/utils.rb', line 1154

def get_date_from_unix_timestamp(unix_timestamp)
  DateTime.strptime(unix_timestamp.to_s, "%s").strftime("%Y-%m-%d")
rescue StandardError
  nil
end

#get_date_parts(iso8601_time) ⇒ Object 



1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
 
# File 'lib/commonmeta/utils.rb', line 1072

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 



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

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



1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
 
# File 'lib/commonmeta/utils.rb', line 1195

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



1140
1141
1142
1143
1144
 
# File 'lib/commonmeta/utils.rb', line 1140

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



1174
1175
1176
1177
1178
 
# File 'lib/commonmeta/utils.rb', line 1174

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_datetime_from_unix_timestamp(unix_timestamp) ⇒ Object

parsing of unix timestamps such as 1427846400



1147
1148
1149
1150
1151
 
# File 'lib/commonmeta/utils.rb', line 1147

def get_datetime_from_unix_timestamp(unix_timestamp)
  strip_milliseconds(DateTime.strptime(unix_timestamp.to_s, "%s").iso8601)
rescue StandardError
  nil
end

#get_identifier(identifiers, identifier_type) ⇒ Object 



1212
1213
1214
1215
 
# File 'lib/commonmeta/utils.rb', line 1212

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 



1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
 
# File 'lib/commonmeta/utils.rb', line 1217

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 



1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
 
# File 'lib/commonmeta/utils.rb', line 1105

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 



1185
1186
1187
1188
 
# File 'lib/commonmeta/utils.rb', line 1185

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 



1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
 
# File 'lib/commonmeta/utils.rb', line 1247

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 



1118
1119
1120
1121
1122
1123
1124
1125
 
# File 'lib/commonmeta/utils.rb', line 1118

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 



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

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 



1062
1063
1064
1065
1066
1067
1068
1069
1070
 
# File 'lib/commonmeta/utils.rb', line 1062

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 



1052
1053
1054
1055
1056
1057
1058
1059
1060
 
# File 'lib/commonmeta/utils.rb', line 1052

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 



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

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 



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

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 



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

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 



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

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 



1029
1030
1031
 
# File 'lib/commonmeta/utils.rb', line 1029

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

#github_release_from_url(url) ⇒ Object 



1025
1026
1027
 
# File 'lib/commonmeta/utils.rb', line 1025

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

#github_repo_from_url(url) ⇒ Object 



1021
1022
1023
 
# File 'lib/commonmeta/utils.rb', line 1021

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

#hsh_to_fos(hsh) ⇒ Object 



1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
 
# File 'lib/commonmeta/utils.rb', line 1376

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 



1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
 
# File 'lib/commonmeta/utils.rb', line 1292

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_by_blog_url(blog_id) ⇒ Object 



1511
1512
1513
 
# File 'lib/commonmeta/utils.rb', line 1511

def json_feed_by_blog_url(blog_id)
  "https://api.rogue-scholar.org/blogs/#{blog_id}"
end

#json_feed_item_by_id_url(id) ⇒ Object 



1515
1516
1517
 
# File 'lib/commonmeta/utils.rb', line 1515

def json_feed_item_by_id_url(id)
  "https://api.rogue-scholar.org/posts/#{id}"
end

#json_feed_unregistered_url ⇒ Object 



1507
1508
1509
 
# File 'lib/commonmeta/utils.rb', line 1507

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

#json_feed_updated_url ⇒ Object 



1503
1504
1505
 
# File 'lib/commonmeta/utils.rb', line 1503

def json_feed_updated_url
  "https://api.rogue-scholar.org/posts/updated"
end

#jsonlint(json) ⇒ Object 



1269
1270
1271
1272
1273
1274
1275
1276
 
# File 'lib/commonmeta/utils.rb', line 1269

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 



918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
 
# File 'lib/commonmeta/utils.rb', line 918

def map_hash_keys(element: nil, mapping: nil)
  a = 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 k == "contributorRoles"
        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 



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
1369
1370
1371
1372
1373
1374
 
# File 'lib/commonmeta/utils.rb', line 1331

def name_to_fos(name)
  # make sure name is capitalized
  name = name.capitalize

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

#name_to_spdx(name) ⇒ Object 



1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
 
# File 'lib/commonmeta/utils.rb', line 1278

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 



639
640
641
642
 
# File 'lib/commonmeta/utils.rb', line 639

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

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



594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
 
# File 'lib/commonmeta/utils.rb', line 594

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_isni(isni) ⇒ Object 



688
689
690
691
692
693
694
695
 
# File 'lib/commonmeta/utils.rb', line 688

def normalize_isni(isni)
  # TODO fix validation
  # isni = validate_isni(isni)
  return nil unless isni.present?

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

#normalize_issn(input, options = {}) ⇒ Object

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



699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
 
# File 'lib/commonmeta/utils.rb', line 699

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



722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
 
# File 'lib/commonmeta/utils.rb', line 722

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_name_identifier(hsh) ⇒ Object 



660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
 
# File 'lib/commonmeta/utils.rb', line 660

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

  name_identifier = hsh["nameIdentifier"]
  name_identifier_scheme = hsh["nameIdentifierScheme"]
  scheme_uri = hsh["schemeURI"] || hsh["schemeUri"] 
  return nil unless name_identifier.present?
    
  if name_identifier_scheme == "ORCID" || scheme_uri == "https://orcid.org"
    return normalize_orcid(name_identifier)
  elsif name_identifier_scheme == "ROR" || scheme_uri == "https://ror.org"
    return normalize_ror(name_identifier)
  elsif name_identifier_scheme == "ISNI" || scheme_uri == "https://isni.org"
    return normalize_isni(name_identifier)
  elsif validate_url(name_identifier) == "URL"
    return name_identifier
  elsif scheme_uri.present?
    return scheme_uri + Addressable::URI.encode(name_identifier)
  end

  return nil
end

#normalize_orcid(orcid) ⇒ Object 



644
645
646
647
648
649
650
 
# File 'lib/commonmeta/utils.rb', line 644

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_ror(ror) ⇒ Object 



652
653
654
655
656
657
658
 
# File 'lib/commonmeta/utils.rb', line 652

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

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

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



611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
 
# File 'lib/commonmeta/utils.rb', line 611

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 



547
548
549
 
# File 'lib/commonmeta/utils.rb', line 547

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

#orcid_from_url(url) ⇒ Object 



543
544
545
 
# File 'lib/commonmeta/utils.rb', line 543

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

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



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

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 



1190
1191
1192
 
# File 'lib/commonmeta/utils.rb', line 1190

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

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



996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
 
# File 'lib/commonmeta/utils.rb', line 996

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 



1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
 
# File 'lib/commonmeta/utils.rb', line 1310

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



1162
1163
1164
1165
1166
1167
1168
1169
1170
 
# File 'lib/commonmeta/utils.rb', line 1162

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 



976
977
978
979
980
981
982
983
984
 
# File 'lib/commonmeta/utils.rb', line 976

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", "contributorRoles").compact
  end.presence
end

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



760
761
762
763
764
765
766
767
 
# File 'lib/commonmeta/utils.rb', line 760

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 



946
947
948
949
950
951
952
 
# File 'lib/commonmeta/utils.rb', line 946

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

#to_ris(element) ⇒ Object 



986
987
988
989
990
991
992
993
994
 
# File 'lib/commonmeta/utils.rb', line 986

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 



775
776
777
778
779
 
# File 'lib/commonmeta/utils.rb', line 775

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 



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

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 



781
782
783
784
785
786
787
788
789
790
 
# File 'lib/commonmeta/utils.rb', line 781

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 



826
827
828
829
830
831
832
833
834
835
836
 
# File 'lib/commonmeta/utils.rb', line 826

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 



792
793
794
795
796
797
798
799
800
 
# File 'lib/commonmeta/utils.rb', line 792

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 



802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
 
# File 'lib/commonmeta/utils.rb', line 802

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 



849
850
851
852
853
854
855
856
857
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
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
 
# File 'lib/commonmeta/utils.rb', line 849

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

#update_ghost_post_via_api(id) ⇒ Object 



1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
 
# File 'lib/commonmeta/utils.rb', line 1541

def update_ghost_post_via_api(id)
  api_key = ENV["API_KEY"]
  api_url = ENV["API_URL"]

  return nil unless id.present? && api_key.present? && api_url.present?

  # generate short lived jwt for ghost admin api
  ghost_jwt = generate_ghost_token(api_key)

  # get post url and doi from Rogue Scholar API
  url = json_feed_item_by_id_url(id)
  response = HTTP.get(url)
  return nil unless response.status.success?

  post = JSON.parse(response.body.to_s)
  url = post.to_h.dig("url")
  doi = validate_doi(post.to_h.dig("doi"))
  doi = doi_as_url(doi)

  return nil unless url.present? && doi.present?

  # get post_id and updated_at from ghost api
  slug = url.chomp("/").split("/").last
  ghost_url = "#{api_url}/ghost/api/admin/posts/slug/#{slug}/"
  response = HTTP.auth("Ghost #{ghost_jwt}").get(ghost_url)
  return nil unless response.status.success?

  ghost_post = JSON.parse(response.body.to_s).dig("posts").first
  ghost_id = ghost_post.dig("id")
  updated_at = ghost_post.dig("updated_at")

  return nil unless ghost_id.present? && updated_at.present?

  # update post canonical_url with new doi
  ghost_url = "#{api_url}/ghost/api/admin/posts/#{ghost_id}/"
  response = HTTP.auth("Ghost #{ghost_jwt}").headers("Content-Type" => "application/json", "Accept-Version" => "v5").put(ghost_url, :json => { "posts" => [{ "canonical_url" => doi, "updated_at" => updated_at }] })
  "#{response.status} DOI #{doi} added to post #{ghost_id}"
end

#validate_email(str) ⇒ Object 



575
576
577
578
579
 
# File 'lib/commonmeta/utils.rb', line 575

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_isni(isni) ⇒ Object 



683
684
685
686
 
# File 'lib/commonmeta/utils.rb', line 683

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

#validate_orcid(orcid) ⇒ Object 



551
552
553
554
 
# File 'lib/commonmeta/utils.rb', line 551

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 



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

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

#validate_ror(ror) ⇒ Object 



556
557
558
559
 
# File 'lib/commonmeta/utils.rb', line 556

def validate_ror(ror)
  ror = Array(%r{\A(?:(?:http|https)://ror\.org/)?([0-9a-z]{7}\d{2})\z}.match(ror)).last
  ror.gsub(/[[:space:]]/, "-") if ror.present?
end

#validate_url(str) ⇒ Object 



565
566
567
568
569
570
571
572
573
 
# File 'lib/commonmeta/utils.rb', line 565

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