commonmeta-ruby 3.6.1 → 3.7.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a0e998cf4561292b7e4ddc596a8fd98313346fff9db6fc585f364178e81dfac7
-  data.tar.gz: 98f697d6ef30b4f7c284c47198ac85f0004c03f0f07c4c2e08b4b4aef5950394
+  metadata.gz: 1dac29584f1bdb4c76e200aa6ec5b0bc29d35afb356d3bc989cc9e58de06c7c7
+  data.tar.gz: 111511119b2c69e406db7575fd7fb5f576c4d490784224570619a6f1a84f128a
 SHA512:
-  metadata.gz: 5a7eaf1fcdf95a28b070e002abf5df911951691734687a67c53f96af449ec3b1e66db642a3595ad2d4a362dbd72407e6c6260689fb317eefac3dd4804f33c0b5
-  data.tar.gz: b039cf08b546311930c1c31e893af64d2a09bcd5b57b96f8e14e0dbfcabe3863ec5db89c42a5247689367f2f81f1943b959096c3f2290a2aaec46661cf758fa6
+  metadata.gz: f65384ec8af14670156ec9f7103b1722c298e2ca4cd753346b22ceb115a9a568afb8da4158a56f09a7a3e7eaaa738f3956c1282f2daff68c2d86c736c34a5fc7
+  data.tar.gz: 3146795dc05d4a5d358cd38c1502cc19e16de7297a0e8ce43269242790adf2ca0916b94be80ddfe215842637bcca301bf1a31cd4b7cc8e5ecc114d641b15f507

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    commonmeta-ruby (3.6.1)
+    commonmeta-ruby (3.7.0)
       activesupport (>= 4.2.5, < 8.0)
       addressable (~> 2.8.1, < 2.8.2)
       base32-url (>= 0.7.0, < 1)
@@ -27,7 +27,7 @@ PATH
 GEM
   remote: https://rubygems.org/
   specs:
-    activesupport (7.1.0)
+    activesupport (7.1.1)
       base64
       bigdecimal
       concurrent-ruby (~> 1.0, >= 1.0.2)
@@ -128,7 +128,7 @@ GEM
       ffi-compiler (~> 1.0)
       rake (~> 13.0)
     logutils (0.6.1)
-    loofah (2.21.3)
+    loofah (2.21.4)
       crass (~> 1.0.2)
       nokogiri (>= 1.12.0)
     matrix (0.4.2)
@@ -151,12 +151,12 @@ GEM
     props (1.2.0)
       iniparser (>= 0.1.0)
     public_suffix (4.0.7)
-    racc (1.7.1)
+    racc (1.7.3)
     rack (3.0.8)
     rack-test (2.1.0)
       rack (>= 1.3)
     rainbow (3.1.1)
-    rake (13.0.6)
+    rake (13.1.0)
     rdf (3.3.1)
       bcp47_spec (~> 0.2)
       link_header (~> 0.0, >= 0.0.8)
@@ -171,7 +171,7 @@ GEM
     rdf-xsd (3.3.0)
       rdf (~> 3.3)
       rexml (~> 3.2)
-    regexp_parser (2.8.1)
+    regexp_parser (2.8.2)
     rexml (3.2.6)
     rspec (3.12.0)
       rspec-core (~> 3.12.0)
@@ -189,19 +189,18 @@ GEM
     rspec-xsd (0.1.0)
       nokogiri (~> 1.6)
       rspec (~> 3)
-    rubocop (1.56.4)
-      base64 (~> 0.1.1)
+    rubocop (1.57.2)
       json (~> 2.3)
       language_server-protocol (>= 3.17.0)
       parallel (~> 1.10)
-      parser (>= 3.2.2.3)
+      parser (>= 3.2.2.4)
       rainbow (>= 2.2.2, < 4.0)
       regexp_parser (>= 1.8, < 3.0)
       rexml (>= 3.2.5, < 4.0)
       rubocop-ast (>= 1.28.1, < 2.0)
       ruby-progressbar (~> 1.7)
       unicode-display_width (>= 2.4.0, < 3.0)
-    rubocop-ast (1.29.0)
+    rubocop-ast (1.30.0)
       parser (>= 3.2.1.0)
     rubocop-capybara (2.19.0)
       rubocop (~> 1.41)
@@ -212,8 +211,8 @@ GEM
       rubocop-ast (>= 0.4.0)
     rubocop-rake (0.6.0)
       rubocop (~> 1.0)
-    rubocop-rspec (2.24.1)
-      rubocop (~> 1.33)
+    rubocop-rspec (2.25.0)
+      rubocop (~> 1.40)
       rubocop-capybara (~> 2.17)
       rubocop-factory_bot (~> 2.22)
     ruby-progressbar (1.13.0)
@@ -236,7 +235,7 @@ GEM
       logutils (>= 0.6.1)
       props (>= 1.1.2)
       rubyzip (>= 1.0.0)
-    thor (1.2.2)
+    thor (1.3.0)
     tzinfo (2.0.6)
       concurrent-ruby (~> 1.0)
     unf (0.1.4)

data/lib/commonmeta/crossref_utils.rb

@@ -65,6 +65,7 @@ module Commonmeta
           insert_funding_references(xml)
           insert_crossref_access_indicators(xml)
           insert_crossref_relations(xml)
+          insert_archive_locations(xml)
           insert_doi_data(xml)
           insert_citation_list(xml)
         end
@@ -85,6 +86,7 @@ module Commonmeta
         insert_funding_references(xml)
         insert_crossref_access_indicators(xml)
         insert_crossref_relations(xml)
+        insert_archive_locations(xml)
         insert_doi_data(xml)
         insert_citation_list(xml)
       end
@@ -327,6 +329,16 @@ module Commonmeta
       end
     end
 
+    def insert_archive_locations(xml)
+      return xml if archive_locations.blank?
+
+      xml.archive_locations do
+        archive_locations.each do |archive_location|
+          xml.archive("name" => archive_location)
+        end
+      end
+    end
+
     def insert_doi_data(xml)
       return xml if doi_from_url(id).blank? || url.blank?
 

data/lib/commonmeta/metadata.rb

@@ -10,7 +10,7 @@ module Commonmeta
                   :email, :registrant
     attr_reader :doc, :page_start, :page_end
     attr_writer :id, :provider_id, :client_id, :doi, :alternate_identifiers, :contributors,
-                :titles, :publisher, :license, :date, :volume, :url, :version, :subjects, :descriptions, :language, :sizes, :formats, :schema_version, :meta, :container, :provider, :format, :funding_references, :state, :geo_locations, :type, :additional_type, :files, :references, :related_identifiers, :related_items, :style, :locale
+                :titles, :publisher, :license, :date, :volume, :url, :version, :subjects, :descriptions, :language, :sizes, :formats, :schema_version, :meta, :container, :provider, :format, :funding_references, :state, :geo_locations, :type, :additional_type, :files, :references, :related_identifiers, :related_items, :style, :locale, :archive_locations
 
     def initialize(options = {})
       options.symbolize_keys!
@@ -253,5 +253,9 @@ module Commonmeta
     def contributors
       @contributors ||= meta.fetch('contributors', nil)
     end
+
+    def archive_locations
+      @archive_locations ||= meta.fetch('archive_locations', nil)
+    end
   end
 end

data/lib/commonmeta/readers/json_feed_reader.rb

@@ -69,6 +69,19 @@ module Commonmeta
         funding_references = get_funding_references(meta)
         related_identifiers = get_related_identifiers(meta)
         alternate_identifiers = [{ "alternateIdentifier" => meta["id"], "alternateIdentifierType" => "UUID" }]
+        
+        archive_url = meta.fetch("archive_url", nil)
+
+        if archive_url
+          host = URI.parse(archive_url).host
+          if ["web.archive.org", "wayback.archive-it.org"].include?(host)
+            archive_locations = ["Internet Archive"]
+          else
+            archive_locations = nil
+          end
+        else
+          archive_locations = nil
+        end
 
         { "id" => id,
           "type" => type,
@@ -86,6 +99,7 @@ module Commonmeta
           "funding_references" => funding_references.presence,
           "related_identifiers" => related_identifiers.presence,
           "alternate_identifiers" => alternate_identifiers,
+          "archive_locations" => archive_locations,
           "state" => state }.compact.merge(read_options)
       end
 

data/lib/commonmeta/schema_utils.rb

@@ -5,7 +5,7 @@ require "pathname"
 
 module Commonmeta
   module SchemaUtils
-    COMMONMETA = File.read(File.expand_path("../../resources/commonmeta_v0.10.3.json",
+    COMMONMETA = File.read(File.expand_path("../../resources/commonmeta_v0.10.4.json",
                                             __dir__))
 
     def json_schema_errors

data/lib/commonmeta/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Commonmeta
-  VERSION = '3.6.1'
+  VERSION = '3.7.0'
 end

data/resources/{commonmeta_v0.10.3.json → commonmeta_v0.10.4.json}

@@ -1,7 +1,7 @@
 {
   "$schema": "http://json-schema.org/draft-07/schema#",
-  "$id": "https://commonmeta.org/commonmeta_v0.10.3.json",
-  "title": "Commonmeta v0.10.3",
+  "$id": "https://commonmeta.org/commonmeta_v0.10.4.json",
+  "title": "Commonmeta v0.10.4",
   "description": "JSON representation of the Commonmeta schema.",
   "additionalProperties": false,
   "definitions": {
@@ -516,6 +516,15 @@
       "description": "The state of the resource.",
       "type": "string",
       "enum": ["findable", "not_found"]
+    },
+    "archive_locations": {
+      "description": "The location where content is archived.",
+      "type": "array",
+      "items": {
+        "type": "string",
+        "enum": ["CLOCKSS", "Internet Archive", "KB", "LOCKSS", "Portico", "Other"]
+      },
+      "uniqueItems": true
     }
   },
   "required": [

data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/archived_wordpress_post.yml

@@ -21,31 +21,103 @@ http_interactions:
       Content-Type:
       - application/json
       Content-Length:
-      - '2184'
+      - '7862'
+      Ratelimit-Limit:
+      - '15'
+      Ratelimit-Remaining:
+      - '14'
+      Ratelimit-Reset:
+      - '3'
       Date:
-      - Thu, 05 Oct 2023 20:37:43 GMT
+      - Sat, 04 Nov 2023 15:12:52 GMT
       Server:
-      - Fly/e440b950 (2023-09-20)
+      - Fly/7328d5b5 (2023-10-27)
       Via:
       - 1.1 fly.io
       Fly-Request-Id:
-      - 01HC0RYZRPBEHQ83AFVH9KEXD8-fra
+      - 01HEDE9R2T7K7FBRF7D93MN1JN-fra
     body:
       encoding: UTF-8
-      string: '{"archive_url":"https://web.archive.org/web/20190709153404/https://project-thor.eu/2016/08/10/orcid-integration-in-pangaea","authors":[{"name":"Markus
-        Stocker","url":"https://orcid.org/0000-0001-5492-3212"}],"blog":{"api":false,"archive_prefix":"https://web.archive.org/web/20190709153404/","authors":null,"backlog":0,"canonical_url":null,"category":"computerAndInformationSciences","created_at":"2023-09-21","current_feed_url":null,"description":"Technical
+      string: '{"archive_url":"https://wayback.archive-it.org/22143/20231103191454/https://project-thor.eu/2016/08/10/orcid-integration-in-pangaea","authors":[{"name":"Markus
+        Stocker","url":"https://orcid.org/0000-0001-5492-3212"}],"blog":{"api":true,"archive_prefix":"https://wayback.archive-it.org/22143/20231103191454/","authors":null,"backlog":0,"canonical_url":null,"category":"computerAndInformationSciences","created_at":1695254400,"current_feed_url":null,"description":"Technical
         and Human infrastructure for Open Research.","favicon":null,"feed_format":"application/atom+xml","feed_url":"https://project-thor.eu/feed/atom/","filter":null,"funding":{"award_number":"654039","award_uri":"https://doi.org/10.3030/654039","funder_id":"https://doi.org/10.13039/501100007601","funder_name":"European
-        Union\u2019s Horizon 2020 research and innovation programme"},"generator":"WordPress.com","home_page_url":"https://project-thor.eu","id":"cg9zq26","issn":null,"language":"en","license":"https://creativecommons.org/licenses/by/4.0/legalcode","modified_at":"1970-01-01T00:00:00+00:00","plan":"Team","prefix":"10.59350","relative_url":null,"slug":"thor","status":"archived","title":"Project
-        THOR","use_api":null,"use_mastodon":false,"user_id":"dead81b3-8a8b-45c9-85fe-f01bb3948c77","version":"https://jsonfeed.org/version/1.1"},"blog_name":"Project
-        THOR","blog_slug":"thor","doi":"https://doi.org/10.59350/faeph-x4x84","id":"570c8129-e867-49e6-8517-bd783627e76e","image":null,"indexed_at":1695449798,"language":"en","published_at":1470819639,"reference":[],"relationships":[],"summary":"This
-        is the first in a series of posts\u00a0describing how THOR partners have recently
+        Union\u2019s Horizon 2020 research and innovation programme"},"generator":"WordPress.com","generator_raw":"WordPress.com","home_page_url":"https://project-thor.eu","id":"cg9zq26","indexed":false,"issn":null,"language":"en","license":"https://creativecommons.org/licenses/by/4.0/legalcode","plan":"Team","prefix":"10.59350","relative_url":null,"secure":true,"slug":"thor","status":"archived","title":"Project
+        THOR","updated_at":1511522178,"use_api":true,"use_mastodon":false,"user_id":"dead81b3-8a8b-45c9-85fe-f01bb3948c77","version":"https://jsonfeed.org/version/1.1"},"blog_name":"Project
+        THOR","blog_slug":"thor","content_html":"<p><span style=\"font-weight:400;\">This
+        is the first in a <a href=\"http://wp.me/p5O69U-aF\">series of posts</a></span><span
+        style=\"font-weight:400;\">\u00a0describing how THOR partners have recently
+        integrated <a href=\"http://orcid.org/\">ORCID</a> in their disciplinary data
+        repositories. This post describes ORCID integration in <a href=\"https://www.pangaea.de/\">PANGAEA</a>,
+        the Data Publisher for Earth &amp; Environmental Science.</span></p>\n<p><span
+        style=\"font-weight:400;\">PANGAEA is rolling out a new version of its website.
+        Developers and designers are currently ironing out a few remaining open issues.
+        The release is expected for autumn 2016. Among major improvements in search,
+        design, and usability, a key new feature is the integration of ORCID.</span></p>\n<p><span
+        style=\"font-weight:400;\">The new feature enables existing PANGAEA users
+        to connect their PANGAEA profile with their ORCID iD, as demonstrated in the
+        video below.\u00a0</span></p>\n<p style=\"text-align:center;\"><span class=\"embed-youtube\"
+        style=\"text-align:center; display: block;\"><iframe class=\"youtube-player\"
+        width=\"640\" height=\"360\" src=\"https://www.youtube.com/embed/Eg81xbbgzI0?version=3&#038;rel=1&#038;showsearch=0&#038;showinfo=1&#038;iv_load_policy=1&#038;fs=1&#038;hl=en&#038;autohide=2&#038;wmode=transparent\"
+        allowfullscreen=\"true\" style=\"border:0;\" sandbox=\"allow-scripts allow-same-origin
+        allow-popups allow-presentation allow-popups-to-escape-sandbox\"></iframe></span></p>\n<p><span
+        style=\"font-weight:400;\">With this connection, PANGAEA obtains the </span><i><span
+        style=\"font-weight:400;\">validated</span></i><span style=\"font-weight:400;\">
+        ORCID iD of its users from ORCID. By connecting their ORCID iD, users can
+        also choose to sign in to PANGAEA using ORCID, as an alternative to signing
+        in using PANGAEA user credentials. This can be handy when a user is already
+        signed in to ORCID, or it is quicker to recall ORCID credentials.</span></p>\n<p><span
+        style=\"font-weight:400;\">Obtaining the validated ORCID iDs of its users
+        is significant for PANGAEA as, contrary to a researcher\u2019s name, the iD
+        is unambiguous: two researchers with the same name can be distinguished by
+        their respective iDs. The iD is also persistent through possible changes in
+        a person\u2019s name: the same researcher may change marital status, or their
+        name may appear in different permutations, at times appear with full name,
+        initials for first name, and with or without middle name (initial). Furthermore,
+        the iD is actionable and can be used to discover information about the researcher.</span></p>\n<p><span
+        style=\"font-weight:400;\">For researchers, the greatest advantage of connecting
+        their ORCID iD to their PANGAEA profile is that PANGAEA can then record the
+        relationships between dataset publication DOIs and contributor ORCID iDs.
+        This information is then shared with the global network of PID infrastructures,
+        and researchers benefit from automated updates to their ORCID Record for data
+        published at PANGAEA, gaining unambiguous attribution for published datasets
+        and benefiting from greater credit for sharing data early.</span></p>\n<p><span
+        style=\"font-weight:400;\">Let\u2019s take a look at how the ORCID integration
+        in PANGAEA is making a difference to <a href=\"https://www.marum.de/en/Alice_Lefebvre.html\">Dr
+        Alice Lefebvre</a>, <a href=\"https://www.marum.de/en/GLOMAR.html\">GLOMAR</a>
+        Associate Scientist at the <a href=\"https://www.marum.de/en/index.html\">MARUM</a>
+        Center for Marine Environmental Sciences of the <a href=\"http://www.uni-bremen.de/en.html\">University
+        of Bremen</a>. </span></p>\n<p><span style=\"font-weight:400;\">Alice has
+        recently joined ORCID and decided to claim the 14 data publications deposited
+        at PANGAEA that she has authored. As a consequence, Alice gains a more complete
+        <a href=\"http://orcid.org/0000-0002-9234-8279\">ORCID Record</a>, one that
+        does not just include her journal article publications but also her authorship
+        in data publications </span><span style=\"font-weight:400;\">\u2212</span><span
+        style=\"font-weight:400;\"> a record that better reflects her true contribution
+        to the scientific record. Alice was also surprised to learn about <a href=\"http://datacite.org\">DataCite</a>
+        and the <a href=\"http://search.datacite.org/contributors/0000-0002-9234-8279\">overview</a>
+        DataCite provides about her contributions. </span></p>\n<p><span style=\"font-weight:400;\">The
+        upcoming release of the PANGAEA website automates the sharing of information
+        with the global network of PID infrastructures. Authors of datasets published
+        at PANGAEA who have connected their ORCID iD, like Alice, will benefit from
+        a workflow that ensures information appears automatically and accurately on
+        their ORCID Record.</span></p>\n<p><span style=\"font-weight:400;\">This shows
+        how far the integration between disciplinary repositories and the global network
+        of PID infrastructures has come over the past years, and how the persistent
+        identification of contributors and research artefacts together with infrastructures
+        that aggregate, process, and share information about persistently identified
+        resources are driving and shaping 21st-century attribution, credit, communication,
+        and measurement of scholarly activity.</span></p>\n<p><b>Want to Know More?<br
+        />\n</b><span style=\"font-weight:400;\">Readers interested in performing
+        an ORCID integration in their own disciplinary repository can find more information
+        in our recent report, &#8216;<a href=\"http://doi.org/10.5281/zenodo.58971\">Demonstration
+        of Services to Integrate ORCIDs into Data Records and Database Systems</a>&#8216;</span><span
+        style=\"font-weight:400;\">. </span></p>\n","doi":"https://doi.org/10.59350/faeph-x4x84","guid":"http://project-thor.eu/?p=664","id":"570c8129-e867-49e6-8517-bd783627e76e","image":null,"indexed_at":1695449798,"language":"en","published_at":1470819639,"reference":[],"relationships":[],"summary":"This
+        is the first in a series of posts&nbsp;describing how THOR partners have recently
         integrated ORCID in their disciplinary data repositories. This post describes
         ORCID integration in PANGAEA, the Data Publisher for Earth &amp; Environmental
-        Science.  PANGAEA is rolling out a new version of its website. Developers
-        and designers are currently ironing out a few remaining open issues. The release
-        is expected for autumn 2016.","tags":["Uncategorized","ORCID","Persistent
-        Identifier"],"title":"ORCID Integration Series: PANGAEA","updated_at":1470819639,"url":"https://project-thor.eu/2016/08/10/orcid-integration-in-pangaea"}
+        Science. PANGAEA is rolling out a new version of its website.","tags":["Uncategorized"],"title":"ORCID
+        Integration Series: PANGAEA","updated_at":1470818410,"url":"https://project-thor.eu/2016/08/10/orcid-integration-in-pangaea"}
 
         '
-  recorded_at: Thu, 05 Oct 2023 20:37:43 GMT
+  recorded_at: Sat, 04 Nov 2023 15:12:52 GMT
 recorded_with: VCR 6.2.0

data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/json_feed_item_from_rogue_scholar_with_archived_content.yml

@@ -0,0 +1,123 @@
+---
+http_interactions:
+- request:
+    method: get
+    uri: https://api.rogue-scholar.org/posts/570c8129-e867-49e6-8517-bd783627e76e
+    body:
+      encoding: ASCII-8BIT
+      string: ''
+    headers:
+      Connection:
+      - close
+      Host:
+      - api.rogue-scholar.org
+      User-Agent:
+      - http.rb/5.1.1
+  response:
+    status:
+      code: 200
+      message: OK
+    headers:
+      Content-Type:
+      - application/json
+      Content-Length:
+      - '7862'
+      Ratelimit-Limit:
+      - '15'
+      Ratelimit-Remaining:
+      - '14'
+      Ratelimit-Reset:
+      - '3'
+      Date:
+      - Sat, 04 Nov 2023 15:30:00 GMT
+      Server:
+      - Fly/7328d5b5 (2023-10-27)
+      Via:
+      - 1.1 fly.io
+      Fly-Request-Id:
+      - 01HEDF93TFCEYGFQ8ADFYBSTFW-fra
+    body:
+      encoding: UTF-8
+      string: '{"archive_url":"https://wayback.archive-it.org/22143/20231103191454/https://project-thor.eu/2016/08/10/orcid-integration-in-pangaea","authors":[{"name":"Markus
+        Stocker","url":"https://orcid.org/0000-0001-5492-3212"}],"blog":{"api":true,"archive_prefix":"https://wayback.archive-it.org/22143/20231103191454/","authors":null,"backlog":0,"canonical_url":null,"category":"computerAndInformationSciences","created_at":1695254400,"current_feed_url":null,"description":"Technical
+        and Human infrastructure for Open Research.","favicon":null,"feed_format":"application/atom+xml","feed_url":"https://project-thor.eu/feed/atom/","filter":null,"funding":{"award_number":"654039","award_uri":"https://doi.org/10.3030/654039","funder_id":"https://doi.org/10.13039/501100007601","funder_name":"European
+        Union\u2019s Horizon 2020 research and innovation programme"},"generator":"WordPress.com","generator_raw":"WordPress.com","home_page_url":"https://project-thor.eu","id":"cg9zq26","indexed":false,"issn":null,"language":"en","license":"https://creativecommons.org/licenses/by/4.0/legalcode","plan":"Team","prefix":"10.59350","relative_url":null,"secure":true,"slug":"thor","status":"archived","title":"Project
+        THOR","updated_at":1511522178,"use_api":true,"use_mastodon":false,"user_id":"dead81b3-8a8b-45c9-85fe-f01bb3948c77","version":"https://jsonfeed.org/version/1.1"},"blog_name":"Project
+        THOR","blog_slug":"thor","content_html":"<p><span style=\"font-weight:400;\">This
+        is the first in a <a href=\"http://wp.me/p5O69U-aF\">series of posts</a></span><span
+        style=\"font-weight:400;\">\u00a0describing how THOR partners have recently
+        integrated <a href=\"http://orcid.org/\">ORCID</a> in their disciplinary data
+        repositories. This post describes ORCID integration in <a href=\"https://www.pangaea.de/\">PANGAEA</a>,
+        the Data Publisher for Earth &amp; Environmental Science.</span></p>\n<p><span
+        style=\"font-weight:400;\">PANGAEA is rolling out a new version of its website.
+        Developers and designers are currently ironing out a few remaining open issues.
+        The release is expected for autumn 2016. Among major improvements in search,
+        design, and usability, a key new feature is the integration of ORCID.</span></p>\n<p><span
+        style=\"font-weight:400;\">The new feature enables existing PANGAEA users
+        to connect their PANGAEA profile with their ORCID iD, as demonstrated in the
+        video below.\u00a0</span></p>\n<p style=\"text-align:center;\"><span class=\"embed-youtube\"
+        style=\"text-align:center; display: block;\"><iframe class=\"youtube-player\"
+        width=\"640\" height=\"360\" src=\"https://www.youtube.com/embed/Eg81xbbgzI0?version=3&#038;rel=1&#038;showsearch=0&#038;showinfo=1&#038;iv_load_policy=1&#038;fs=1&#038;hl=en&#038;autohide=2&#038;wmode=transparent\"
+        allowfullscreen=\"true\" style=\"border:0;\" sandbox=\"allow-scripts allow-same-origin
+        allow-popups allow-presentation allow-popups-to-escape-sandbox\"></iframe></span></p>\n<p><span
+        style=\"font-weight:400;\">With this connection, PANGAEA obtains the </span><i><span
+        style=\"font-weight:400;\">validated</span></i><span style=\"font-weight:400;\">
+        ORCID iD of its users from ORCID. By connecting their ORCID iD, users can
+        also choose to sign in to PANGAEA using ORCID, as an alternative to signing
+        in using PANGAEA user credentials. This can be handy when a user is already
+        signed in to ORCID, or it is quicker to recall ORCID credentials.</span></p>\n<p><span
+        style=\"font-weight:400;\">Obtaining the validated ORCID iDs of its users
+        is significant for PANGAEA as, contrary to a researcher\u2019s name, the iD
+        is unambiguous: two researchers with the same name can be distinguished by
+        their respective iDs. The iD is also persistent through possible changes in
+        a person\u2019s name: the same researcher may change marital status, or their
+        name may appear in different permutations, at times appear with full name,
+        initials for first name, and with or without middle name (initial). Furthermore,
+        the iD is actionable and can be used to discover information about the researcher.</span></p>\n<p><span
+        style=\"font-weight:400;\">For researchers, the greatest advantage of connecting
+        their ORCID iD to their PANGAEA profile is that PANGAEA can then record the
+        relationships between dataset publication DOIs and contributor ORCID iDs.
+        This information is then shared with the global network of PID infrastructures,
+        and researchers benefit from automated updates to their ORCID Record for data
+        published at PANGAEA, gaining unambiguous attribution for published datasets
+        and benefiting from greater credit for sharing data early.</span></p>\n<p><span
+        style=\"font-weight:400;\">Let\u2019s take a look at how the ORCID integration
+        in PANGAEA is making a difference to <a href=\"https://www.marum.de/en/Alice_Lefebvre.html\">Dr
+        Alice Lefebvre</a>, <a href=\"https://www.marum.de/en/GLOMAR.html\">GLOMAR</a>
+        Associate Scientist at the <a href=\"https://www.marum.de/en/index.html\">MARUM</a>
+        Center for Marine Environmental Sciences of the <a href=\"http://www.uni-bremen.de/en.html\">University
+        of Bremen</a>. </span></p>\n<p><span style=\"font-weight:400;\">Alice has
+        recently joined ORCID and decided to claim the 14 data publications deposited
+        at PANGAEA that she has authored. As a consequence, Alice gains a more complete
+        <a href=\"http://orcid.org/0000-0002-9234-8279\">ORCID Record</a>, one that
+        does not just include her journal article publications but also her authorship
+        in data publications </span><span style=\"font-weight:400;\">\u2212</span><span
+        style=\"font-weight:400;\"> a record that better reflects her true contribution
+        to the scientific record. Alice was also surprised to learn about <a href=\"http://datacite.org\">DataCite</a>
+        and the <a href=\"http://search.datacite.org/contributors/0000-0002-9234-8279\">overview</a>
+        DataCite provides about her contributions. </span></p>\n<p><span style=\"font-weight:400;\">The
+        upcoming release of the PANGAEA website automates the sharing of information
+        with the global network of PID infrastructures. Authors of datasets published
+        at PANGAEA who have connected their ORCID iD, like Alice, will benefit from
+        a workflow that ensures information appears automatically and accurately on
+        their ORCID Record.</span></p>\n<p><span style=\"font-weight:400;\">This shows
+        how far the integration between disciplinary repositories and the global network
+        of PID infrastructures has come over the past years, and how the persistent
+        identification of contributors and research artefacts together with infrastructures
+        that aggregate, process, and share information about persistently identified
+        resources are driving and shaping 21st-century attribution, credit, communication,
+        and measurement of scholarly activity.</span></p>\n<p><b>Want to Know More?<br
+        />\n</b><span style=\"font-weight:400;\">Readers interested in performing
+        an ORCID integration in their own disciplinary repository can find more information
+        in our recent report, &#8216;<a href=\"http://doi.org/10.5281/zenodo.58971\">Demonstration
+        of Services to Integrate ORCIDs into Data Records and Database Systems</a>&#8216;</span><span
+        style=\"font-weight:400;\">. </span></p>\n","doi":"https://doi.org/10.59350/faeph-x4x84","guid":"http://project-thor.eu/?p=664","id":"570c8129-e867-49e6-8517-bd783627e76e","image":null,"indexed_at":1695449798,"language":"en","published_at":1470819639,"reference":[],"relationships":[],"summary":"This
+        is the first in a series of posts&nbsp;describing how THOR partners have recently
+        integrated ORCID in their disciplinary data repositories. This post describes
+        ORCID integration in PANGAEA, the Data Publisher for Earth &amp; Environmental
+        Science. PANGAEA is rolling out a new version of its website.","tags":["Uncategorized"],"title":"ORCID
+        Integration Series: PANGAEA","updated_at":1470818410,"url":"https://project-thor.eu/2016/08/10/orcid-integration-in-pangaea"}
+
+        '
+  recorded_at: Sat, 04 Nov 2023 15:30:00 GMT
+recorded_with: VCR 6.2.0

data/spec/readers/json_feed_reader_spec.rb

@@ -233,7 +233,7 @@ describe Commonmeta::Metadata, vcr: true do
       subject = described_class.new(input: input)
       # expect(subject.valid?).to be true
       expect(subject.id).to eq("https://doi.org/10.59350/faeph-x4x84")
-      expect(subject.url).to eq("https://web.archive.org/web/20190709153404/https://project-thor.eu/2016/08/10/orcid-integration-in-pangaea")
+      expect(subject.url).to eq("https://wayback.archive-it.org/22143/20231103191454/https://project-thor.eu/2016/08/10/orcid-integration-in-pangaea")
       expect(subject.alternate_identifiers).to eq([{ "alternateIdentifier" => "570c8129-e867-49e6-8517-bd783627e76e", "alternateIdentifierType" => "UUID" }])
       expect(subject.type).to eq("Article")
       expect(subject.contributors.length).to eq(1)
@@ -255,6 +255,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.language).to eq("en")
       expect(subject.funding_references).to eq([{ "awardNumber" => "654039", "funderIdentifier" => "https://doi.org/10.13039/501100007601", "funderIdentifierType"=>"Crossref Funder ID", "funderName" => "European Union’s Horizon 2020 research and innovation programme" }])
       expect(subject.container).to eq("identifier" => "https://project-thor.eu", "identifierType" => "URL", "title" => "Project THOR", "type" => "Periodical")
+      expect(subject.archive_locations).to eq(["Internet Archive"])
     end
 
     it "wordpress post with references" do

data/spec/writers/crossref_xml_writer_spec.rb

@@ -323,6 +323,45 @@ describe Commonmeta::Metadata, vcr: true do
       expect(crossref_xml.dig("group_title")).to eq("Social sciences")
     end
 
+    it "json_feed_item from rogue scholar with archived content" do
+      input = "https://api.rogue-scholar.org/posts/570c8129-e867-49e6-8517-bd783627e76e"
+      subject = described_class.new(input: input)
+      # expect(subject.valid?).to be true
+      expect(subject.id).to eq("https://doi.org/10.59350/faeph-x4x84")
+      expect(subject.url).to eq("https://wayback.archive-it.org/22143/20231103191454/https://project-thor.eu/2016/08/10/orcid-integration-in-pangaea")
+      expect(subject.alternate_identifiers).to eq([{ "alternateIdentifier" => "570c8129-e867-49e6-8517-bd783627e76e", "alternateIdentifierType" => "UUID" }])
+      expect(subject.type).to eq("Article")
+      expect(subject.contributors.length).to eq(1)
+      expect(subject.contributors.first).to eq("contributorRoles" => ["Author"],
+           "type" => "Person",
+           "familyName" => "Stocker",
+           "givenName" => "Markus",
+           "id" => "https://orcid.org/0000-0001-5492-3212")
+      expect(subject.titles).to eq([{ "title" => "ORCID Integration Series: PANGAEA" }])
+      expect(subject.license).to eq("id" => "CC-BY-4.0",
+                                    "url" => "https://creativecommons.org/licenses/by/4.0/legalcode")
+      expect(subject.date).to eq("published" => "2016-08-10", "updated" => "2016-08-10")
+      expect(subject.descriptions.first["description"]).to start_with("This is the first in a series of posts describing how THOR partners")
+      expect(subject.publisher).to eq("name" => "Project THOR")
+      expect(subject.subjects).to eq([{ "subject" => "Computer and information sciences" },
+                                      { "schemeUri" => "http://www.oecd.org/science/inno/38235147.pdf",
+                                        "subject" => "FOS: Computer and information sciences",
+                                        "subjectScheme" => "Fields of Science and Technology (FOS)" }])
+      expect(subject.language).to eq("en")
+      expect(subject.funding_references).to eq([{ "awardNumber" => "654039", "funderIdentifier" => "https://doi.org/10.13039/501100007601", "funderIdentifierType"=>"Crossref Funder ID", "funderName" => "European Union’s Horizon 2020 research and innovation programme" }])
+      expect(subject.container).to eq("identifier" => "https://project-thor.eu", "identifierType" => "URL", "title" => "Project THOR", "type" => "Periodical")
+      expect(subject.archive_locations).to eq(["Internet Archive"])
+      # puts subject.crossref_xml
+      crossref_xml = Hash.from_xml(subject.crossref_xml).dig("doi_batch", "body", "posted_content")
+      expect(Array.wrap(crossref_xml.dig("contributors", "person_name")).length).to eq(1)
+      expect(Array.wrap(crossref_xml.dig("contributors",
+                                         "person_name")).first).to eq("ORCID"=>"https://orcid.org/0000-0001-5492-3212", "contributor_role"=>"author", "given_name"=>"Markus", "sequence"=>"first", "surname"=>"Stocker")
+      expect(crossref_xml.dig("titles",
+                              "title")).to eq("ORCID Integration Series: PANGAEA")
+      expect(crossref_xml.dig("item_number")).to eq("__content__" => "570c8129e86749e68517bd783627e76e", "item_number_type" => "uuid")
+      expect(crossref_xml.dig("group_title")).to eq("Computer and information sciences")
+    end
+
     it "json_feed_item from rogue scholar with relations" do
       input = "https://api.rogue-scholar.org/posts/8a4de443-3347-4b82-b57d-e3c82b6485fc"
       subject = described_class.new(input: input, doi: "10.53731/r79v4e1-97aq74v-ag578")

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: commonmeta-ruby
 version: !ruby/object:Gem::Version
-  version: 3.6.1
+  version: 3.7.0
 platform: ruby
 authors:
 - Martin Fenner
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-10-06 00:00:00.000000000 Z
+date: 2023-11-04 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
@@ -657,7 +657,7 @@ files:
 - lib/commonmeta/xml_converter.rb
 - resources/2008/09/xsd.xsl
 - resources/cff.json
-- resources/commonmeta_v0.10.3.json
+- resources/commonmeta_v0.10.4.json
 - resources/crossref/AccessIndicators.xsd
 - resources/crossref/JATS-journalpublishing1-3d2-mathml3-elements.xsd
 - resources/crossref/JATS-journalpublishing1-3d2-mathml3.xsd
@@ -930,6 +930,7 @@ files:
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/journal_article_from_datacite.yml
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/journal_article_plos.yml
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/json_feed_item_from_rogue_scholar_with_anonymous_author.yml
+- spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/json_feed_item_from_rogue_scholar_with_archived_content.yml
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/json_feed_item_from_rogue_scholar_with_doi.yml
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/json_feed_item_from_rogue_scholar_with_organizational_author.yml
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/write_metadata_as_crossref/json_feed_item_from_rogue_scholar_with_relations.yml