bolognese 0.2.2 → 2.7.0

data/.travis.yml

@@ -1,23 +0,0 @@
-language: ruby
-rvm:
-- 2.3.3
-
-before_install:
-- export TZ=Europe/Berlin
-
-install:
-- travis_retry bundle install
-
-script: bundle exec rspec
-
-notifications:
-  email: false
-
-deploy:
-  provider: rubygems
-  api_key:
-    secure: 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
-  gem: bolognese
-  on:
-    tags: true
-    repo: datacite/bolognese

data/lib/bolognese/crossref.rb

@@ -1,202 +0,0 @@
-require_relative 'doi_utils'
-require_relative 'utils'
-
-module Bolognese
-  class Crossref < Metadata
-    include Bolognese::DoiUtils
-    include Bolognese::Utils
-
-    # CrossRef types from https://api.crossref.org/types
-    CROSSREF_TYPE_TRANSLATIONS = {
-      "Proceedings" => nil,
-      "ReferenceBook" => nil,
-      "JournalIssue" => nil,
-      "ProceedingsArticle" => nil,
-      "Other" => nil,
-      "Dissertation" => "Thesis",
-      "Dataset" => "Dataset",
-      "EditedBook" => "Book",
-      "JournalArticle" => "ScholarlyArticle",
-      "Journal" => nil,
-      "Report" => nil,
-      "BookSeries" => nil,
-      "ReportSeries" => nil,
-      "BookTrack" => nil,
-      "Standard" => nil,
-      "BookSection" => nil,
-      "BookPart" => nil,
-      "Book" => "Book",
-      "BookChapter" => "Chapter",
-      "StandardSeries" => nil,
-      "Monograph" => "Book",
-      "Component" => nil,
-      "ReferenceEntry" => nil,
-      "JournalVolume" => nil,
-      "BookSet" => nil,
-      "PostedContent" => nil
-    }
-
-    attr_reader = :id, :metadata, :schema_org
-
-    def initialize(doi)
-      @id = normalize_doi(doi)
-    end
-
-    def raw
-      response = Maremma.get(@id, accept: "application/vnd.crossref.unixref+xml", host: true, raw: true)
-      @raw ||= response.body.fetch("data", nil)
-    end
-
-    def metadata
-      @metadata ||= raw.present? ? Maremma.from_xml(raw).fetch("doi_records", {}).fetch("doi_record", {}) : {}
-    end
-
-    def exists?
-      metadata.present?
-    end
-
-    def journal_metadata
-      metadata.dig("crossref", "journal", "journal_metadata").presence || {}
-    end
-
-    def bibliographic_metadata
-      if metadata.dig("crossref", "journal", "journal_article").present?
-        metadata.dig("crossref", "journal", "journal_article")
-      else
-        k = metadata.dig("crossref").keys.last
-        metadata.dig("crossref", k).presence || {}
-      end
-    end
-
-    def program_metadata
-      bibliographic_metadata.dig("program") ||
-      bibliographic_metadata.dig("crossmark", "custom_metadata", "program") || {}
-    end
-
-    def additional_type
-      if metadata.dig("crossref", "journal").present?
-        metadata.dig("crossref", "journal").keys.last.camelize
-      else
-        metadata.dig("crossref").keys.last.camelize
-      end
-    end
-
-    def type
-      CROSSREF_TYPE_TRANSLATIONS[additional_type] || "CreativeWork"
-    end
-
-    def name
-      parse_attribute(bibliographic_metadata.dig("titles", "title"))
-    end
-
-    def alternate_name
-      if bibliographic_metadata.fetch("publisher_item", nil).present?
-        parse_attribute(bibliographic_metadata.dig("publisher_item", "item_number"))
-      else
-        parse_attribute(bibliographic_metadata.fetch("item_number", nil))
-      end
-    end
-
-    def description
-      bibliographic_metadata.fetch("abstract", {}).values.first
-    end
-
-    def license
-      access_indicator = Array.wrap(program_metadata).find { |m| m["name"] == "AccessIndicators" }
-      if access_indicator.present?
-        parse_attribute(access_indicator["license_ref"])
-      else
-        nil
-      end
-    end
-
-    def author
-      person = bibliographic_metadata.dig("contributors", "person_name")
-      Array(person).select { |a| a["contributor_role"] == "author" }.map do |a|
-        { "@type" => "Person",
-          "@id" => a["ORCID"],
-          "givenName" => a["given_name"],
-          "familyName" => a["surname"] }.compact
-      end
-    end
-
-    def editor
-      person = bibliographic_metadata.dig("contributors", "person_name")
-      Array(person).select { |a| a["contributor_role"] == "editor" }.map do |a|
-        { "@type" => "Person",
-          "@id" => a["ORCID"],
-          "givenName" => a["given_name"],
-          "familyName" => a["surname"] }.compact
-      end.presence
-    end
-
-    def date_published
-      pub_date = bibliographic_metadata.fetch("publication_date", nil) ||
-        bibliographic_metadata.fetch("acceptance_date", nil)
-      if pub_date.present?
-        get_date_from_parts(pub_date["year"], pub_date["month"], pub_date["day"])
-      else
-        nil
-      end
-    end
-
-    def date_modified
-      Time.parse(metadata.fetch("timestamp", "")).utc.iso8601
-    end
-
-    def page_start
-      bibliographic_metadata.dig("pages", "first_page")
-    end
-
-    def page_end
-      bibliographic_metadata.dig("pages", "last_page")
-    end
-
-    def is_part_of
-      if journal_metadata.present?
-        { "@type" => "Periodical",
-          "name" => journal_metadata["full_title"],
-          "issn" => parse_attribute(journal_metadata.fetch("issn", nil)) }.compact
-      else
-        nil
-      end
-    end
-
-    def citation
-       citations = bibliographic_metadata.dig("citation_list", "citation")
-       Array(citations).map do |c|
-         { "@type" => "CreativeWork",
-           "@id" => normalize_doi(c["doi"]),
-           "position" => c["key"],
-           "name" => c["article_title"],
-           "datePublished" => c["cYear"] }.compact
-       end.presence
-    end
-
-    def provider
-      { "@type" => "Organization",
-        "name" => "Crossref" }
-    end
-
-    def as_schema_org
-      { "@context" => "http://schema.org",
-        "@type" => type,
-        "@id" => id,
-        "additionalType" => additional_type,
-        "name" => name,
-        "alternateName" => alternate_name,
-        "author" => author,
-        "editor" => editor,
-        "description" => description,
-        "license" => license,
-        "datePublished" => date_published,
-        "dateModified" => date_modified,
-        "pageStart" => page_start,
-        "pageEnd" => page_end,
-        "isPartOf" => is_part_of,
-        "citation" => citation,
-        "provider" => provider
-      }.compact
-    end
-  end
-end

data/lib/bolognese/datacite.rb

@@ -1,157 +0,0 @@
-require_relative 'doi_utils'
-require_relative 'utils'
-
-module Bolognese
-  class Datacite < Metadata
-    include Bolognese::DoiUtils
-    include Bolognese::Utils
-
-    DATACITE_TYPE_TRANSLATIONS = {
-      "Audiovisual" => "VideoObject",
-      "Collection" => "Collection",
-      "Dataset" => "Dataset",
-      "Event" => "Event",
-      "Image" => "ImageObject",
-      "InteractiveResource" => nil,
-      "Model" => nil,
-      "PhysicalObject" => nil,
-      "Service" => "Service",
-      "Software" => "SoftwareSourceCode",
-      "Sound" => "AudioObject",
-      "Text" => "ScholarlyArticle",
-      "Workflow" => nil,
-      "Other" => "CreativeWork"
-    }
-
-    attr_reader = :id, :metadata, :schema_org
-
-    def initialize(doi)
-      @id = normalize_doi(doi)
-    end
-
-    def raw
-      response = Maremma.get(id, accept: "application/vnd.datacite.datacite+xml", raw: true)
-      @raw = response.body.fetch("data", nil)
-    end
-
-    def metadata
-      @metadata ||= raw.present? ? Maremma.from_xml(raw).fetch("resource", {}) : {}
-    end
-
-    def exists?
-      metadata.present?
-    end
-
-    def type
-      k = metadata.dig("resourceType", "resourceTypeGeneral")
-      DATACITE_TYPE_TRANSLATIONS[k.to_s.dasherize] || "CreativeWork"
-    end
-
-    def additional_type
-      metadata.fetch("resourceType", {}).fetch("text", nil) ||
-      metadata.fetch("resourceType", {}).fetch("resourceTypeGeneral", nil)
-    end
-
-    def name
-      metadata.dig("titles", "title")
-    end
-
-    def alternate_name
-      metadata.dig("alternateIdentifiers", "alternateIdentifier", "text")
-    end
-
-    def description
-      metadata.dig("descriptions", "description", "text")
-    end
-
-    def license
-      metadata.dig("rightsList", "rights", "rightsURI")
-    end
-
-    def keywords
-      Array(metadata.dig("subjects", "subject")).join(", ")
-    end
-
-    def author
-      authors = metadata.dig("creators", "creator")
-      authors = [authors] if authors.is_a?(Hash)
-      get_authors(authors)
-    end
-
-    def version
-      metadata.fetch("version", nil)
-    end
-
-    def dates
-      Array(metadata.dig("dates", "date"))
-    end
-
-    def date_created
-      created = dates.find { |d| d["dateType"] == "Created" } || {}
-      created.fetch("text", nil)
-    end
-
-    def date_published
-      published = dates.find { |d| d["dateType"] == "Issued" } || {}
-      published.fetch("text", nil) || metadata.fetch("publicationYear")
-    end
-
-    def date_modified
-      modified = dates.find { |d| d["dateType"] == "Updated" } || {}
-      modified.fetch("text", nil)
-    end
-
-    def related_identifiers(relation_type)
-      Array(metadata.dig("relatedIdentifiers", "relatedIdentifier"))
-        .select { |r| relation_type.split(" ").include?(r["relationType"]) && %w(DOI URL).include?(r["relatedIdentifierType"]) }
-        .map do |work|
-          work_id = work["relatedIdentifierType"] == "DOI" ? normalize_doi(work["text"]) : work["text"]
-          { "@type" => "CreativeWork",
-            "@id" => work_id }
-        end
-    end
-
-    def is_part_of
-      related_identifiers("IsPartOf").first
-    end
-
-    def has_part
-      related_identifiers("HasPart").presence
-    end
-
-    def citation
-      related_identifiers("Cites IsCitedBy Supplements IsSupplementTo References IsReferencedBy").presence
-    end
-
-    def publisher
-      metadata.fetch("publisher")
-    end
-
-    def provider
-      { "@type" => "Organization",
-        "name" => "DataCite" }
-    end
-
-    def as_schema_org
-      { "@context" => "http://schema.org",
-        "@type" => type,
-        "@id" => id,
-        "name" => name,
-        "alternateName" => alternate_name,
-        "author" => author,
-        "description" => description,
-        "license" => license,
-        "version" => version,
-        "keywords" => keywords,
-        "dateCreated" => date_created,
-        "datePublished" => date_published,
-        "dateModified" => date_modified,
-        "isPartOf" => is_part_of,
-        "hasPart" => has_part,
-        "citation" => citation,
-        "publisher" => publisher,
-        "provider" => provider
-      }.compact
-    end
-  end
-end

data/lib/bolognese/date_utils.rb

@@ -1,48 +0,0 @@
-module Bolognese
-  module DateUtils
-    def get_date_parts(iso8601_time)
-      return { "date_parts" => [[]] } if iso8601_time.nil?
-
-      year = iso8601_time[0..3].to_i
-      month = iso8601_time[5..6].to_i
-      day = iso8601_time[8..9].to_i
-      { 'date-parts' => [[year, month, day].reject { |part| part == 0 }] }
-    end
-
-    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
-
-    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
-
-    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
-
-    def get_date_from_parts(year, month = nil, day = nil)
-      [year.to_s.rjust(4, '0'), month.to_s.rjust(2, '0'), day.to_s.rjust(2, '0')].reject { |part| part == "00" }.join("-")
-    end
-
-    # parsing of incomplete iso8601 timestamps such as 2015-04 is broken
-    # in standard library
-    # return nil if invalid iso8601 timestamp
-    def get_datetime_from_iso8601(iso8601_time)
-      ISO8601::DateTime.new(iso8601_time).to_time.utc
-    rescue
-      nil
-    end
-  end
-end

data/lib/bolognese/github.rb

@@ -1,106 +0,0 @@
-module Bolognese
-  class Github < Metadata
-    # def get_github_metadata(url, options = {})
-    #   return {} if url.blank?
-
-    #   github_hash = github_from_url(url)
-    #   repo_url = "https://api.github.com/repos/#{github_hash[:owner]}/#{github_hash[:repo]}"
-    #   response = Maremma.get(repo_url, options.merge(bearer: ENV['GITHUB_PERSONAL_ACCESS_TOKEN']))
-
-    #   return { error: 'Resource not found.', status: 404 } if response.body.fetch("errors", nil).present?
-
-    #   author = get_github_owner(github_hash[:owner])
-
-    #   language = response.body.fetch("data", {}).fetch('language', nil)
-    #   type = language.present? && language != "HTML" ? 'computer_program' : 'webpage'
-
-    #   { "author" => [get_one_author(author)],
-    #     "title" => response.body.fetch("data", {}).fetch('description', nil).presence || github_hash[:repo],
-    #     "container-title" => "Github",
-    #     "issued" => response.body.fetch("data", {}).fetch('created_at', nil).presence || "0000",
-    #     "URL" => url,
-    #     "type" => type }
-    # end
-
-    # def get_github_owner_metadata(url, options = {})
-    #   return {} if url.blank?
-
-    #   github_hash = github_from_url(url)
-    #   owner_url = "https://api.github.com/users/#{github_hash[:owner]}"
-    #   response = Maremma.get(owner_url, options.merge(bearer: ENV['GITHUB_PERSONAL_ACCESS_TOKEN']))
-
-    #   return { error: 'Resource not found.', status: 404 } if response.body.fetch("data", {}).fetch("message", nil) == "Not Found"
-
-    #   author = response.body.fetch("data", {}).fetch('name', nil).presence || github_hash[:owner]
-    #   title = "Github profile for #{author}"
-
-    #   { "author" => [get_one_author(author)],
-    #     "title" => title,
-    #     "container-title" => "Github",
-    #     "issued" => response.body.fetch("data", {}).fetch('created_at', nil).presence || "0000",
-    #     "URL" => url,
-    #     "type" => 'entry' }
-    # end
-
-    # def get_github_release_metadata(url, options = {})
-    #   return {} if url.blank?
-
-    #   github_hash = github_from_url(url)
-    #   release_url = "https://api.github.com/repos/#{github_hash[:owner]}/#{github_hash[:repo]}/releases/tags/#{github_hash[:release]}"
-    #   response = Maremma.get(release_url, options.merge(bearer: ENV['GITHUB_PERSONAL_ACCESS_TOKEN']))
-
-    #   return { error: 'Resource not found.', status: 404 } if response.body.fetch("data", {})["message"] == "Not Found"
-
-    #   author = get_github_owner(github_hash[:owner])
-
-    #   { "author" => [get_one_author(author)],
-    #     "title" => response.body.fetch("data", {}).fetch('name', nil),
-    #     "container-title" => "Github",
-    #     "issued" => response.body.fetch("data", {}).fetch('created_at', nil).presence || "0000",
-    #     "URL" => url,
-    #     "type" => 'computer_program' }
-    # end
-
-    # def get_github_owner(owner)
-    #   url = "https://api.github.com/users/#{owner}"
-    #   response = Maremma.get(url, bearer: ENV['GITHUB_PERSONAL_ACCESS_TOKEN'])
-
-    #   return nil if response.body.fetch("data", {}).fetch("message", nil) == "Not Found"
-
-    #   response.body.fetch("data", {}).fetch('name', nil).presence || owner
-    # end
-
-    # def github_from_url(url)
-    #   return {} unless /\Ahttps:\/\/github\.com\/(.+)(?:\/)?(.+)?(?:\/tree\/)?(.*)\z/.match(url)
-    #   words = URI.parse(url).path[1..-1].split('/')
-
-    #   { owner: words[0],
-    #     repo: words[1],
-    #     release: words[3] }.compact
-    # end
-
-    # def github_repo_from_url(url)
-    #   github_from_url(url).fetch(:repo, nil)
-    # end
-
-    # def github_release_from_url(url)
-    #   github_from_url(url).fetch(:release, nil)
-    # end
-
-    # def github_owner_from_url(url)
-    #   github_from_url(url).fetch(:owner, nil)
-    # end
-
-    # def github_as_owner_url(github_hash)
-    #   "https://github.com/#{github_hash[:owner]}" if github_hash[:owner].present?
-    # end
-
-    # def github_as_repo_url(github_hash)
-    #   "https://github.com/#{github_hash[:owner]}/#{github_hash[:repo]}" if github_hash[:repo].present?
-    # end
-
-    # def github_as_release_url(github_hash)
-    #   "https://github.com/#{github_hash[:owner]}/#{github_hash[:repo]}/tree/#{github_hash[:release]}" if github_hash[:release].present?
-    # end
-  end
-end

data/lib/bolognese/orcid.rb

@@ -1,24 +0,0 @@
-module Bolognese
-  class Orcid < Metadata
-    include Bolognese::PidUtils
-    # def get_orcid_metadata(orcid, options = {})
-    #   return {} if orcid.blank?
-
-    #   url = "https://pub.orcid.org/v2.0/#{orcid}/person"
-    #   response = Maremma.get(url, options.merge(accept: "json"))
-
-    #   name = response.body.fetch("data", {}).fetch("name", nil)
-    #   return { "errors" => 'Resource not found.' } unless name.present?
-
-    #   author = { "family" => name.fetch("family-name", {}).fetch("value", nil),
-    #              "given" => name.fetch("given-names", {}).fetch("value", nil) }
-
-    #   { "author" => [author],
-    #     "title" => "ORCID record for #{[author.fetch('given', nil), author.fetch('family', nil)].compact.join(' ')}",
-    #     "container-title" => "ORCID Registry",
-    #     "issued" => Time.now.year.to_s,
-    #     "URL" => orcid_as_url(orcid),
-    #     "type" => 'entry' }
-    # end
-  end
-end

data/lib/bolognese/pid_utils.rb

@@ -1,23 +0,0 @@
-module Bolognese
-  module PidUtils
-    def normalize_orcid(orcid)
-      orcid = validate_orcid(orcid)
-      return nil unless orcid.present?
-
-      # turn ORCID ID into URL
-      "http://orcid.org/" + Addressable::URI.encode(orcid)
-    end
-
-    def orcid_from_url(url)
-      Array(/\Ahttp:\/\/orcid\.org\/(.+)/.match(url)).last
-    end
-
-    def orcid_as_url(orcid)
-      "http://orcid.org/#{orcid}" if orcid.present?
-    end
-
-    def validate_orcid(orcid)
-      Array(/\A(?:http:\/\/orcid\.org\/)?(\d{4}-\d{4}-\d{4}-\d{3}[0-9X]+)\z/.match(orcid)).last
-    end
-  end
-end

data/spec/cli_spec.rb

@@ -1,37 +0,0 @@
-require 'spec_helper'
-require 'bolognese/cli'
-
-describe Bolognese::CLI do
-  let(:subject) do
-    described_class.new
-  end
-
-  describe "read", vcr: true do
-    context "crossref" do
-      let(:id) { "10.7554/eLife.01567" }
-      it 'as schema_org' do
-        subject.options = { as: "schema_org" }
-        expect { subject.read id }.to output(/additionalType/).to_stdout
-      end
-
-      it 'as crossref' do
-        subject.options = { as: "crossref" }
-        expect { subject.read id }.to output(/journal_metadata/).to_stdout
-      end
-    end
-
-    context "datacite" do
-      let(:id) { "10.5061/dryad.8515" }
-
-      it 'as schema_org' do
-        subject.options = { as: "schema_org" }
-        expect { subject.read id }.to output(/Phylogeny, Malaria, Parasites, Taxonomy, Mitochondrial genome, Africa, Plasmodium/).to_stdout
-      end
-
-      it 'as datacite' do
-        subject.options = { as: "datacite" }
-        expect { subject.read id }.to output(/http:\/\/datacite.org\/schema\/kernel-3/).to_stdout
-      end
-    end
-  end
-end