commonmeta-ruby 3.5 → 3.5.1

data/lib/commonmeta/readers/crossref_reader.rb

@@ -4,19 +4,19 @@ module Commonmeta
   module Readers
     module CrossrefReader
       def get_crossref(id: nil, **options)
-        return { 'string' => nil, 'state' => 'not_found' } unless id.present?
+        return { "string" => nil, "state" => "not_found" } unless id.present?
 
         api_url = crossref_api_url(id, options)
         response = HTTP.get(api_url)
-        return { 'string' => nil, 'state' => 'not_found' } unless response.status.success?
+        return { "string" => nil, "state" => "not_found" } unless response.status.success?
 
-        { 'string' => response.body.to_s }
+        { "string" => response.body.to_s }
       end
 
       def read_crossref(string: nil, **options)
         if string.present?
           errors = jsonlint(string)
-          return { 'errors' => errors } if errors.present?
+          return { "errors" => errors } if errors.present?
         end
 
         read_options = ActiveSupport::HashWithIndifferentAccess.new(options.except(:doi, :id, :url,
@@ -24,159 +24,168 @@ module Commonmeta
         meta = string.present? ? JSON.parse(string) : {}
 
         # optionally strip out the message wrapper from API
-        meta = meta.dig('message') if meta.dig('message').present?
+        meta = meta.dig("message") if meta.dig("message").present?
 
-        resource_type = meta.fetch('type', nil)
+        resource_type = meta.fetch("type", nil)
         resource_type = resource_type.present? ? resource_type.underscore.camelcase : nil
-        type = Commonmeta::Utils::CR_TO_CM_TRANSLATIONS.fetch(resource_type, 'Other')
+        type = Commonmeta::Utils::CR_TO_CM_TRANSLATIONS.fetch(resource_type, "Other")
 
-        member_id = meta.fetch('member', nil)
+        member_id = meta.fetch("member", nil)
         # TODO: get publisher from member_id almost always return publisher name, but sometimes does not
         publisher = if member_id.present?
-                      get_crossref_member(member_id)
-                    else
-                      meta.fetch('publisher', nil)
-                    end
-
-        contributors = if meta.fetch('author', nil).present?
-                     get_authors(from_csl(Array.wrap(meta.fetch('author', nil))))
-                   else
-                     []
-                   end
-        editors = Array.wrap(meta.fetch('editor', nil)).each { |e| e['contributorType'] = 'Editor' }
+            get_crossref_member(member_id)
+          else
+            meta.fetch("publisher", nil)
+          end
+
+        contributors = if meta.fetch("author", nil).present?
+            get_authors(from_csl(Array.wrap(meta.fetch("author", nil))))
+          else
+            []
+          end
+        editors = Array.wrap(meta.fetch("editor", nil)).each { |e| e["contributorType"] = "Editor" }
         contributors += get_authors(from_csl(editors))
 
         date = {}
-        date['submitted'] = nil
-        date['accepted'] = meta.dig('accepted', 'date-time')
-        date['published'] =
-          meta.dig('issued',
-                   'date-time') || get_date_from_date_parts(meta.fetch('issued',
+        date["submitted"] = nil
+        date["accepted"] = meta.dig("accepted", "date-time")
+        date["published"] =
+          meta.dig("issued",
+                   "date-time") || get_date_from_date_parts(meta.fetch("issued",
                                                                        nil)) || get_date_from_date_parts(meta.fetch(
-                                                                                                           'created', nil
-                                                                                                         ))
-        date['updated'] =
-          meta.dig('updated',
-                   'date-time') || meta.dig('deposited',
-                                            'date-time') || get_date_from_date_parts(meta.fetch(
-                                                                                       'deposited', nil
-                                                                                     ))
+            "created", nil
+          ))
+        date["updated"] =
+          meta.dig("updated",
+                   "date-time") || meta.dig("deposited",
+                                            "date-time") || get_date_from_date_parts(meta.fetch(
+            "deposited", nil
+          ))
 
         # TODO: fix timestamp. Until then, remove time as this is not always stable with Crossref (different server timezones)
-        date['published'] = get_iso8601_date(date['published']) if date['published'].present?
-        date['updated'] = get_iso8601_date(date['updated']) if date['updated'].present?
+        date["published"] = get_iso8601_date(date["published"]) if date["published"].present?
+        date["updated"] = get_iso8601_date(date["updated"]) if date["updated"].present?
 
-        license = if meta.fetch('license', nil)
-                    hsh_to_spdx('rightsURI' => meta.dig('license', 0, 'URL'))
-                  end
-        issn = Array.wrap(meta.fetch('issn-type', nil)).find { |i| i['type'] == 'electronic' } ||
-               Array.wrap(meta.fetch('issn-type', nil)).find { |i| i['type'] == 'print' } || {}
-        issn = issn.fetch('value', nil) if issn.present?
+        license = if meta.fetch("license", nil)
+            hsh_to_spdx("rightsURI" => meta.dig("license", 0, "URL"))
+          end
+        issn = Array.wrap(meta.fetch("issn-type", nil)).find { |i| i["type"] == "electronic" } ||
+               Array.wrap(meta.fetch("issn-type", nil)).find { |i| i["type"] == "print" } || {}
+        issn = issn.fetch("value", nil) if issn.present?
 
-        references = Array.wrap(meta.fetch('reference', nil)).map { |r| get_reference(r) }
+        references = Array.wrap(meta.fetch("reference", nil)).map { |r| get_reference(r) }
 
-        funding_references = Array.wrap(meta.fetch('funder', nil)).reduce([]) do |sum, funding|
+        funding_references = Array.wrap(meta.fetch("funder", nil)).reduce([]) do |sum, funding|
           funding_reference = {
-            'funderName' => funding['name'],
-            'funderIdentifier' => funding['DOI'] ? doi_as_url(funding['DOI']) : nil,
-            'funderIdentifierType' => funding['DOI'].to_s.starts_with?('10.13039') ? 'Crossref Funder ID' : nil
+            "funderName" => funding["name"],
+            "funderIdentifier" => funding["DOI"] ? doi_as_url(funding["DOI"]) : nil,
+            "funderIdentifierType" => funding["DOI"].to_s.starts_with?("10.13039") ? "Crossref Funder ID" : nil,
           }.compact
-          if funding['name'].present? && funding['award'].present?
-            Array.wrap(funding['award']).each do |award|
-              funding_reference['awardNumber'] = award
+          if funding["name"].present? && funding["award"].present?
+            Array.wrap(funding["award"]).each do |award|
+              funding_reference["awardNumber"] = award
             end
           end
 
           sum += [funding_reference] if funding_reference.present?
           sum
         end
+        files = Array.wrap(meta.fetch("link", nil)).reduce([]) do |sum, file|
+          if file["content-type"] != "unspecified"
+            file = { "url" => file.fetch("URL", nil), "mimeType" => file.fetch("content-type", nil) }
+            sum += [file]
+          end
+          sum
+        end
+        
         container_type = case resource_type
-                         when 'JournalArticle', 'JournalIssue'
-                           'Journal'
-                         when 'BookChapter'
-                           'Book'
-                         when 'Monograph'
-                           'BookSeries'
-                         end
-
-        first_page = if meta.fetch('page', nil).present?
-                       meta.fetch('page').split('-').map(&:strip)[0]
-                     end
-        last_page = if meta.fetch('page', nil).present?
-                      meta.fetch('page').split('-').map(&:strip)[1]
-                    end
-
-        container = { 'type' => container_type,
-                      'title' => parse_attributes(meta.fetch('container-title', nil),
+          when "JournalArticle", "JournalIssue"
+            "Journal"
+          when "BookChapter"
+            "Book"
+          when "Monograph"
+            "BookSeries"
+          end
+
+        first_page = if meta.fetch("page", nil).present?
+            meta.fetch("page").split("-").map(&:strip)[0]
+          end
+        last_page = if meta.fetch("page", nil).present?
+            meta.fetch("page").split("-").map(&:strip)[1]
+          end
+
+        container = { "type" => container_type,
+                      "title" => parse_attributes(meta.fetch("container-title", nil),
                                                   first: true).to_s.squish.presence,
-                      'identifier' => issn.present? ? issn : nil,
-                      'identifierType' => issn.present? ? 'ISSN' : nil,
-                      'volume' => meta.fetch('volume', nil),
-                      'issue' => meta.fetch('issue', nil),
-                      'firstPage' => first_page,
-                      'lastPage' => last_page }.compact
-
-        id = normalize_id(meta.fetch('id', nil) || meta.fetch('DOI', nil))
-
-        id = normalize_doi(options[:doi] || options[:id] || meta.fetch('DOI', nil))
-        title = if meta.fetch('title', nil).is_a?(Array)
-                  meta.fetch('title', nil)[0]
-                else
-                  meta.fetch('title', nil)
-                end
-        title = title.blank? ? ':(unav)' : title.squish
-        state = meta.present? || read_options.present? ? 'findable' : 'not_found'
-        subjects = Array.wrap(meta.fetch('categories', nil)).reduce([]) do |sum, subject|
+                      "identifier" => issn.present? ? issn : nil,
+                      "identifierType" => issn.present? ? "ISSN" : nil,
+                      "volume" => meta.fetch("volume", nil),
+                      "issue" => meta.fetch("issue", nil),
+                      "firstPage" => first_page,
+                      "lastPage" => last_page }.compact
+
+        id = normalize_id(meta.fetch("id", nil) || meta.fetch("DOI", nil))
+
+        id = normalize_doi(options[:doi] || options[:id] || meta.fetch("DOI", nil))
+        title = if meta.fetch("title", nil).is_a?(Array)
+            meta.fetch("title", nil)[0]
+          else
+            meta.fetch("title", nil)
+          end
+        title = title.blank? ? ":(unav)" : title.squish
+        state = meta.present? || read_options.present? ? "findable" : "not_found"
+        subjects = Array.wrap(meta.fetch("categories", nil)).reduce([]) do |sum, subject|
           sum += name_to_fos(subject)
 
           sum
         end
-        abstract = meta.fetch('abstract', nil)
+        abstract = meta.fetch("abstract", nil)
         provider = get_doi_ra(id)
 
-        { 'id' => id,
-          'type' => type,
-          'url' => normalize_id(meta.dig('resource', 'primary', 'URL')),
-          'titles' => [{ 'title' => title }],
-          'contributors' => contributors,
-          'container' => container,
-          'publisher' => publisher,
-          'references' => references,
-          'date' => date.compact,
-          'descriptions' => if abstract.present?
-                              [{ 'description' => sanitize(abstract),
-                                 'descriptionType' => 'Abstract' }]
-                            else
-                              []
-                            end,
-          'license' => license,
-          'alternate_identifiers' => [],
-          'funding_references' => funding_references,
-          'version' => meta.fetch('version', nil),
-          'subjects' => subjects,
-          'provider' => provider,
-          'schema_version' => 'http://datacite.org/schema/kernel-4',
-          'state' => state }.compact.merge(read_options)
+        { "id" => id,
+          "type" => type,
+          "url" => normalize_id(meta.dig("resource", "primary", "URL")),
+          "titles" => [{ "title" => title }],
+          "contributors" => contributors,
+          "container" => container,
+          "publisher" => publisher,
+          "references" => references,
+          "date" => date.compact,
+          "descriptions" => if abstract.present?
+          [{ "description" => sanitize(abstract),
+             "descriptionType" => "Abstract" }]
+        else
+          []
+        end,
+          "license" => license,
+          "alternate_identifiers" => [],
+          "funding_references" => funding_references,
+          "files" => files.presence,
+          "version" => meta.fetch("version", nil),
+          "subjects" => subjects,
+          "provider" => provider,
+          "schema_version" => "http://datacite.org/schema/kernel-4",
+          "state" => state }.compact.merge(read_options)
       end
 
       def get_reference(reference)
         return nil unless reference.present? || !reference.is_a?(Hash)
 
-        doi = reference.dig('DOI')
+        doi = reference.dig("DOI")
         {
-          'key' => reference.dig('key'),
-          'doi' => doi ? normalize_doi(doi) : nil,
-          'contributor' => reference.dig('author'),
-          'title' => reference.dig('article-title'),
-          'publisher' => reference.dig('publisher'),
-          'publicationYear' => reference.dig('year'),
-          'volume' => reference.dig('volume'),
-          'issue' => reference.dig('issue'),
-          'firstPage' => reference.dig('first-page'),
-          'lastPage' => reference.dig('last-page'),
-          'containerTitle' => reference.dig('journal-title'),
-          'edition' => nil,
-          'unstructured' => doi.nil? ? reference.dig('unstructured') : nil
+          "key" => reference.dig("key"),
+          "doi" => doi ? normalize_doi(doi) : nil,
+          "contributor" => reference.dig("author"),
+          "title" => reference.dig("article-title"),
+          "publisher" => reference.dig("publisher"),
+          "publicationYear" => reference.dig("year"),
+          "volume" => reference.dig("volume"),
+          "issue" => reference.dig("issue"),
+          "firstPage" => reference.dig("first-page"),
+          "lastPage" => reference.dig("last-page"),
+          "containerTitle" => reference.dig("journal-title"),
+          "edition" => nil,
+          "unstructured" => doi.nil? ? reference.dig("unstructured") : nil,
         }.compact
       end
     end

data/lib/commonmeta/readers/datacite_reader.rb

@@ -88,6 +88,7 @@ module Commonmeta
                      end.map do |reference|
           get_datacite_reference(reference)
         end
+        files = Array.wrap(meta.fetch("content_url", nil)).map { |file| { "url" => file } }    
         formats = meta.fetch('formats', nil)
         sizes = meta.fetch('sizes', nil)
         schema_version = meta.fetch('schema_version', nil) || 'http://datacite.org/schema/kernel-4'
@@ -105,6 +106,7 @@ module Commonmeta
           'alternate_identifiers' => alternate_identifiers.presence,
           'references' => references,
           'funding_references' => funding_references,
+          'files' => files.presence,
           'date' => date.compact,
           'descriptions' => descriptions,
           'license' => license,

data/lib/commonmeta/readers/json_feed_reader.rb

@@ -20,9 +20,13 @@ module Commonmeta
 
         meta = string.present? ? JSON.parse(string) : {}
 
-        url = normalize_url(meta.fetch("url", nil))
+        if (meta.dig("blog", "status") == "archived")
+          url = normalize_url(meta.fetch("archive_url", nil))
+        else
+          url = normalize_url(meta.fetch("url", nil))
+        end
         id = options[:doi] ? normalize_doi(options[:doi]) : normalize_id(meta.fetch("doi", nil))
-        id = url if id.blank? && url.present?
+        id = normalize_url(meta.fetch("url", nil)) if id.blank?
 
         type = "Article"
         contributors = if meta.fetch("authors", nil).present?

data/lib/commonmeta/readers/schema_org_reader.rb

@@ -207,6 +207,8 @@ module Commonmeta
           }.compact
         end
 
+        files = Array.wrap(meta.fetch("contentUrl", nil)).map { |file| { "url" => file } }    
+        
         # handle keywords as array and as comma-separated string
         subjects = meta.fetch('keywords', nil)
         subjects = subjects.to_s.split(', ') if subjects.is_a?(String)
@@ -222,7 +224,7 @@ module Commonmeta
           'additional_type' => additional_type,
           'alternate_identifiers' => alternate_identifiers.presence,
           'url' => normalize_id(meta.fetch('url', nil)),
-          'content_url' => Array.wrap(meta.fetch('contentUrl', nil)),
+          'files' => files.presence,
           'sizes' => Array.wrap(meta.fetch('contenSize', nil)),
           'formats' => Array.wrap(meta.fetch('encodingFormat',
                                              nil) || meta.fetch('fileFormat', nil)),

data/lib/commonmeta/schema_utils.rb

@@ -5,7 +5,7 @@ require "pathname"
 
 module Commonmeta
   module SchemaUtils
-    COMMONMETA = File.read(File.expand_path("../../resources/commonmeta_v0.10.json",
+    COMMONMETA = File.read(File.expand_path("../../resources/commonmeta_v0.10.3.json",
                                             __dir__))
 
     def json_schema_errors

data/lib/commonmeta/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Commonmeta
-  VERSION = '3.5'
+  VERSION = '3.5.1'
 end

data/lib/commonmeta/writers/schema_org_writer.rb

@@ -35,7 +35,7 @@ module Commonmeta
           'spatialCoverage' => to_schema_org_spatial_coverage(geo_locations),
           'citation' => Array.wrap(references).map { |r| to_schema_org_citation(r) },
           '@reverse' => reverse.presence,
-          'contentUrl' => Array.wrap(content_url).unwrap,
+          'contentUrl' => Array.wrap(files).map { |f| f["url"] }.unwrap,
           'schemaVersion' => schema_version,
           'periodical' => if type == 'Dataset'
                             nil

data/resources/{commonmeta_v0.10.json → commonmeta_v0.10.3.json}

@@ -1,7 +1,7 @@
 {
   "$schema": "http://json-schema.org/draft-07/schema#",
-  "$id": "https://commonmeta.org/commonmeta_v0.10.json",
-  "title": "Commonmeta v0.10",
+  "$id": "https://commonmeta.org/commonmeta_v0.10.3.json",
+  "title": "Commonmeta v0.10.3",
   "description": "JSON representation of the Commonmeta schema.",
   "additionalProperties": false,
   "definitions": {
@@ -37,7 +37,21 @@
         "Reader",
         "Translator",
         "ContactPerson",
-        "Maintainer",
+        "DataManager",
+        "Distributor",
+        "HostingInstitution",
+        "Producer",
+        "ProjectLeader",
+        "ProjectManager",
+        "ProjectMember",
+        "RegistrationAgency",
+        "RegistrationAuthority",
+        "RelatedPerson",
+        "ResearchGroup",
+        "RightsHolder",
+        "Researcher",
+        "Sponsor",
+        "WorkPackageLeader",
         "Conceptualization",
         "DataCuration",
         "FormalAnalysis",
@@ -52,6 +66,7 @@
         "Visualization",
         "WritingOriginalDraft",
         "WritingReviewEditing",
+        "Maintainer",
         "Other"
       ],
       "type": "string"
@@ -190,8 +205,38 @@
     },
     "date": {
       "description": "The dates for the resource.",
+      "$comment": "The date fields are not required. Dates should be formatted as ISO 8601 dates.",
       "type": "object",
-      "format": "date"
+      "properties": {
+        "created": {
+          "description": "The date the resource was created.",
+          "type": "string"
+        },
+        "submitted": {
+          "description": "The date the resource was submitted.",
+          "type": "string"
+        },
+        "accepted": {
+          "description": "The date the resource was accepted.",
+          "type": "string"
+        },
+        "published": {
+          "description": "The date the resource was published.",
+          "type": "string"
+        },
+        "updated": {
+          "description": "The date the resource was updated.",
+          "type": "string"
+        },
+        "available": {
+          "description": "The date the resource was made available.",
+          "type": "string"
+        },
+        "withdrawn": {
+          "description": "The date the resource was withdrawn.",
+          "type": "string"
+        }
+      }
     },
     "titles": {
       "description": "The titles of the resource.",
@@ -226,9 +271,11 @@
           "enum": [
             "Book",
             "BookSeries",
+            "DataCatalog",
             "Journal",
             "Periodical",
             "ProceedingsSeries",
+            "Repository",
             "Series"
           ]
         },
@@ -316,17 +363,21 @@
           "type": {
             "type": "string",
             "enum": [
-              "IsIdenticalTo",
               "IsNewVersionOf",
               "IsPreviousVersionOf",
+              "IsVersionOf",
+              "HasVersion",
               "IsPartOf",
               "HasPart",
               "IsVariantFormOf",
+              "IsOriginalFormOf",
+              "IsIdenticalTo",
               "IsTranslationOf",
-              "IsVersionOf",
-              "IsReviewOf",
+              "IsReviewedBy",
+              "Reviews",
               "IsPreprintOf",
-              "HasPreprint"
+              "HasPreprint",
+              "isSupplementTo"
             ]
           }
         },
@@ -437,12 +488,20 @@
         "required": ["alternateIdentifier", "alternateIdentifierType"]
       }
     },
-    "content_url": {
-      "description": "The URL of the content of the resource.",
+    "files": {
+      "description": "The downloadable files for the resource.",
       "type": "array",
       "items": {
-        "type": "string",
-        "format": "uri"
+        "type": "object",
+        "properties": {
+          "bucket": { "type": "string" },
+          "key": { "type": "string" },
+          "checksum": { "type": "string" },
+          "url": { "type": "string", "format": "uri" },
+          "size": { "type": "integer" },
+          "mimeType": { "type": "string" }
+        },
+        "required": ["url"]
       }
     },
     "schema_version": {
@@ -459,5 +518,13 @@
       "enum": ["findable", "not_found"]
     }
   },
-  "required": ["id", "type", "url", "contributors", "titles", "publisher", "date"]
+  "required": [
+    "id",
+    "type",
+    "url",
+    "contributors",
+    "titles",
+    "publisher",
+    "date"
+  ]
 }