commonmeta-ruby 3.3.8 → 3.3.10

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e717e42ba9e8264cfc3ebb4bcb774c58b7f003afad4ffea7da385cd66e84eb27
-  data.tar.gz: bee1fe28c91acb00e3b5afae8b4305d6036dd4924f554b44d49145ac388fcf69
+  metadata.gz: 533ba980ff639a50d0a61e345be68413bdf63467fc319685b6b64c9b466c7bf5
+  data.tar.gz: 3b87fd2fba942083c9962f9acf6bc5e99d54422f977d5f8b27c99cb6617bf5d1
 SHA512:
-  metadata.gz: 1cc77541969f79992f5e8b6f0677939e64397ffbedfbb75c40d2d534c2a64ad2f8a29b86df1570d76cdd0245f2f80a01e422052c065ca5e45085b85fb9dda7ec
-  data.tar.gz: 1389f97cf9c919eda5a384a247b7cddb142b0bfb50ce4c7bb77d83f8c1da6812a20c3277a1a0860d42b4952c63c8862d29c6061e0c11cf2a1436ea0424cd3fc9
+  metadata.gz: 20cb1df5c515d34a2b782f48479e8f6ae271eb74ae23b685478d216034109677602f388468cd6b86944513f48b6f3e2a3544cf1d8359c46ce68369a0e20edfa0
+  data.tar.gz: aeedc938048a579bc6fa903a287a6f551e1e6e2e340a8809dc0e3505f0da134806f30ce2110f14394a03d3a3a82d4b9a6f8457e0dae5e51b2a49b17032279dfb

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    commonmeta-ruby (3.3.8)
+    commonmeta-ruby (3.3.10)
       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 (7.0.5)
+    activesupport (7.0.6)
       concurrent-ruby (~> 1.0, >= 1.0.2)
       i18n (>= 1.6, < 2)
       minitest (>= 5.1)
@@ -113,6 +113,7 @@ GEM
       oj (~> 3)
       optimist (~> 3)
     jwt (2.7.1)
+    language_server-protocol (3.17.0.3)
     latex-decode (0.4.0)
     link_header (0.0.8)
     llhttp-ffi (0.4.0)
@@ -186,12 +187,13 @@ GEM
     rspec-mocks (3.12.5)
       diff-lcs (>= 1.2.0, < 2.0)
       rspec-support (~> 3.12.0)
-    rspec-support (3.12.0)
+    rspec-support (3.12.1)
     rspec-xsd (0.1.0)
       nokogiri (~> 1.6)
       rspec (~> 3)
-    rubocop (1.52.1)
+    rubocop (1.54.0)
       json (~> 2.3)
+      language_server-protocol (>= 3.17.0)
       parallel (~> 1.10)
       parser (>= 3.2.2.3)
       rainbow (>= 2.2.2, < 4.0)
@@ -245,7 +247,7 @@ GEM
     unicode-display_width (2.4.2)
     unicode-types (1.8.0)
     uuidtools (2.2.0)
-    vcr (6.1.0)
+    vcr (6.2.0)
     webmock (3.18.1)
       addressable (>= 2.8.0)
       crack (>= 0.3.2)

data/lib/commonmeta/author_utils.rb

@@ -63,6 +63,8 @@ module Commonmeta
         type = 'Person'
       elsif type.blank? && is_personal_name?(name: name) && name.to_s.exclude?(';')
         type = 'Person'
+      elsif type.blank? && name.present? && !is_personal_name?(name: name)
+        type = 'Organization'
       end
 
       # parse author contributor role
@@ -127,8 +129,8 @@ module Commonmeta
     def is_personal_name?(name: nil)
       return true if name_exists?(name.to_s.split.first) || name_exists?(name.to_s.split(', ').last)
 
-      # check if a name has only one word, e.g. "FamousOrganization"
-      return false if name.to_s.split(' ').size == 1
+      # check if a name has only one word, e.g. "FamousOrganization", not including commas
+      return false if name.to_s.split(' ').size == 1 && name.to_s.exclude?(',')
 
       # check for suffixes, e.g. "John Smith, MD"
       return true if %w[MD PhD].include? name.split(', ').last

data/lib/commonmeta/cli.rb

@@ -105,8 +105,8 @@ module Commonmeta
 
     desc "", "json_feed_not_indexed"
 
-    def json_feed_not_indexed(date_indexed)
-      puts get_json_feed_not_indexed(date_indexed)
+    def json_feed_not_indexed
+      puts get_json_feed_not_indexed
     end
 
     desc "", "json_feed_by_blog"

data/lib/commonmeta/readers/json_feed_reader.rb

@@ -105,10 +105,10 @@ module Commonmeta
         posts.map { |post| post["uuid"] }.first
       end
 
-      def get_json_feed_not_indexed(date_indexed)
-        # get JSON Feed items not indexed in Crossref since a particular date
+      def get_json_feed_not_indexed
+        # get JSON Feed items not indexed in Crossref since they have been last updated
 
-        url = json_feed_not_indexed_url(date_indexed)
+        url = json_feed_not_indexed_url
         response = HTTP.get(url)
         return { "string" => nil, "state" => "not_found" } unless response.status.success?
 

data/lib/commonmeta/utils.rb

@@ -1437,8 +1437,8 @@ module Commonmeta
       Base32::URL.decode(id)
     end
 
-    def json_feed_not_indexed_url(date_indexed)
-      "https://rogue-scholar.org/api/posts/not_indexed/#{date_indexed}"
+    def json_feed_not_indexed_url
+      "https://rogue-scholar.org/api/posts/not_indexed"
     end
 
     def json_feed_unregistered_url

data/lib/commonmeta/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Commonmeta
-  VERSION = '3.3.8'
+  VERSION = '3.3.10'
 end

data/spec/cli_spec.rb

@@ -371,8 +371,7 @@ describe Commonmeta::CLI do
     end
     
     it "json_feed_not_indexed" do
-      input = "2023-01-01"
-      expect { subject.json_feed_not_indexed input }.to output(/ab58e412-06eb-42b7-b81a-d340825b9d48/).to_stdout
+      expect { subject.json_feed_not_indexed }.to output(/b1038a3f-c5aa-4a68-97cb-5c68b27942f7/).to_stdout
     end
 
     it "json_feed_by_blog" do

data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/json_feed/json_feed_not_indexed.yml

@@ -2152,4 +2152,74 @@ http_interactions:
         the Science","description":"Ein Blog aus dem Admin-Bereich der Wissenschaft","language":"de","favicon":null,"feed_url":"https://ulirockenbauch.blog/feed/atom/","home_page_url":"https://ulirockenbauch.blog","user_id":"8498eaf6-8c58-4b58-bc15-27eda292b1aa","created_at":"2023-05-31T07:28:16+00:00","indexed_at":"2023-04-21","feed_format":"application/atom+xml","license":"https://creativecommons.org/licenses/by/4.0/legalcode","generator":"WordPress
         (.com)","category":"Social Sciences","prefix":"10.59350","modified_at":"2023-04-13T17:48:41+00:00","version":"https://jsonfeed.org/version/1.1","backlog":true}}]'
   recorded_at: Fri, 16 Jun 2023 06:11:32 GMT
-recorded_with: VCR 6.1.0
+- request:
+    method: get
+    uri: https://rogue-scholar.org/api/posts/not_indexed
+    body:
+      encoding: UTF-8
+      string: ''
+    headers:
+      Connection:
+      - close
+      Host:
+      - rogue-scholar.org
+      User-Agent:
+      - http.rb/5.1.1
+  response:
+    status:
+      code: 200
+      message: OK
+    headers:
+      Age:
+      - '0'
+      Cache-Control:
+      - public, max-age=0, must-revalidate
+      Content-Length:
+      - '4252'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Sat, 01 Jul 2023 18:57:43 GMT
+      Etag:
+      - '"ll4w4ic9co3a0"'
+      Server:
+      - Vercel
+      Strict-Transport-Security:
+      - max-age=63072000
+      X-Matched-Path:
+      - "/api/posts/[[...params]]"
+      X-Vercel-Cache:
+      - MISS
+      X-Vercel-Id:
+      - fra1::iad1::sx58r-1688237863458-f29812df0cd7
+      Connection:
+      - close
+    body:
+      encoding: UTF-8
+      string: '[{"id":"https://doi.org/10.53731/r294649-6f79289-8cw1w","uuid":"b1038a3f-c5aa-4a68-97cb-5c68b27942f7","url":"https://blog.front-matter.io/posts/re3data-org-registry-of-research-data-repositories-launched","title":"re3data.org:
+        registry of research data repositories launched","summary":"Earlier this week
+        re3data.org – the Registry of Research Data Repositories – officially launched.
+        The registry is nicely described in a preprint also published this week.re3data.org
+        offers researchers, funding organizations, libraries and publishers and overview
+        of the heterogeneous research data repository landscape. Information icons
+        help researchers to identify an adequate repository for the storage and reuse
+        of their data.I really like re3data.org, and that is not because I personally
+        know...","date_published":"2013-06-01T00:00:00+00:00","date_modified":"2023-06-29T18:04:53+00:00","date_indexed":"2023-06-28T18:13:09+00:00","authors":[{"url":"https://orcid.org/0000-0003-1419-2405","name":"Martin
+        Fenner"}],"image":"https://blog.front-matter.io/content/images/2022/08/figure2.png","tags":["News"],"language":"en","references":[{"doi":"https://doi.org/10.7287/peerj.preprints.21v1","key":"ref1"},{"doi":"https://doi.org/10.2312/re3.002","key":"ref2"}],"blog_id":"f0m0e38","blog":{"id":"f0m0e38","title":"Front
+        Matter","description":"The Front Matter Blog covers the intersection of science
+        and technology since 2007.","language":"en","favicon":"https://blog.front-matter.io/favicon.png","feed_url":"https://blog.front-matter.io/atom-complete/","home_page_url":"https://blog.front-matter.io","user_id":"8498eaf6-8c58-4b58-bc15-27eda292b1aa","created_at":"2023-05-31T07:20:33+00:00","indexed_at":"2023-01-02","feed_format":"application/atom+xml","license":"https://creativecommons.org/licenses/by/4.0/legalcode","generator":"Ghost
+        5.52","category":"Engineering and Technology","prefix":"10.53731","modified_at":"2023-06-29T18:04:53+00:00","version":"https://jsonfeed.org/version/1.1","backlog":false,"authors":null,"current_feed_url":"https://blog.front-matter.io/atom/","expired":null}},{"id":"https://doi.org/10.53731/r294649-6f79289-8cw3h","uuid":"e4e13c41-5991-41b6-811b-6271510c1b0e","url":"https://blog.front-matter.io/posts/increased-cancer-risk-following-computed-tomography-scans","title":"Increased
+        cancer risk following computed tomography scans","summary":"Two papers (this
+        and this) and an editorial in the latest issue of Archives of Internal Medicine
+        examine the cancer risks associated with the use of computed tomography (CT)
+        examinations.1Ionizing radiation increases the risk for developing cancer.
+        There is direct evidence from atomic bomb survivors in Japan in 1945 and from
+        nuclear accidents such as the one in Chernobyl in 1986. There are no studies
+        directly demonstrating an increased cancer risk from the diagnostic use of
+        X-rays (either...","date_published":"2009-12-20T00:00:00+00:00","date_modified":"2023-06-29T17:49:57+00:00","date_indexed":"2023-06-28T18:13:09+00:00","authors":[{"url":"https://orcid.org/0000-0003-1419-2405","name":"Martin
+        Fenner"}],"image":"https://blog.front-matter.io/content/images/2022/08/ioi90119f2.jpg","tags":["Feature"],"language":"en","references":[{"doi":"https://doi.org/10.1001/archinternmed.2009.427","key":"ref1"},{"doi":"https://doi.org/10.1001/archinternmed.2009.440","key":"ref2"},{"doi":"https://doi.org/10.1001/archinternmed.2009.453","key":"ref3"}],"blog_id":"f0m0e38","blog":{"id":"f0m0e38","title":"Front
+        Matter","description":"The Front Matter Blog covers the intersection of science
+        and technology since 2007.","language":"en","favicon":"https://blog.front-matter.io/favicon.png","feed_url":"https://blog.front-matter.io/atom-complete/","home_page_url":"https://blog.front-matter.io","user_id":"8498eaf6-8c58-4b58-bc15-27eda292b1aa","created_at":"2023-05-31T07:20:33+00:00","indexed_at":"2023-01-02","feed_format":"application/atom+xml","license":"https://creativecommons.org/licenses/by/4.0/legalcode","generator":"Ghost
+        5.52","category":"Engineering and Technology","prefix":"10.53731","modified_at":"2023-06-29T18:04:53+00:00","version":"https://jsonfeed.org/version/1.1","backlog":false,"authors":null,"current_feed_url":"https://blog.front-matter.io/atom/","expired":null}}]'
+  recorded_at: Sat, 01 Jul 2023 18:57:43 GMT
+recorded_with: VCR 6.2.0

data/spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed/not_indexed_posts.yml

@@ -1420,4 +1420,74 @@ http_interactions:
         highlights interesting science stories from around the web.\",\"language\":\"en\",\"favicon\":\"https://syldavia-gazette.org/favicon.png\",\"feed_url\":\"https://syldavia-gazette.org/atom/\",\"home_page_url\":\"https://syldavia-gazette.org\",\"user_id\":\"8498eaf6-8c58-4b58-bc15-27eda292b1aa\",\"created_at\":\"2023-05-31T16:54:04+00:00\",\"indexed_at\":\"2023-02-01\",\"feed_format\":\"application/atom+xml\",\"license\":\"https://creativecommons.org/licenses/by/4.0/legalcode\",\"generator\":\"Ghost
         5.40\",\"category\":\"Humanities\",\"prefix\":\"10.53731\",\"modified_at\":\"2023-03-15T20:37:00+00:00\",\"version\":\"https://jsonfeed.org/version/1.1\",\"backlog\":false,\"authors\":null}}]"
   recorded_at: Sun, 18 Jun 2023 15:23:51 GMT
-recorded_with: VCR 6.1.0
+- request:
+    method: get
+    uri: https://rogue-scholar.org/api/posts/not_indexed
+    body:
+      encoding: UTF-8
+      string: ''
+    headers:
+      Connection:
+      - close
+      Host:
+      - rogue-scholar.org
+      User-Agent:
+      - http.rb/5.1.1
+  response:
+    status:
+      code: 200
+      message: OK
+    headers:
+      Age:
+      - '0'
+      Cache-Control:
+      - public, max-age=0, must-revalidate
+      Content-Length:
+      - '4252'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Sat, 01 Jul 2023 18:57:39 GMT
+      Etag:
+      - '"ll4w4ic9co3a0"'
+      Server:
+      - Vercel
+      Strict-Transport-Security:
+      - max-age=63072000
+      X-Matched-Path:
+      - "/api/posts/[[...params]]"
+      X-Vercel-Cache:
+      - MISS
+      X-Vercel-Id:
+      - fra1::iad1::jjzwd-1688237856423-827b9226d892
+      Connection:
+      - close
+    body:
+      encoding: UTF-8
+      string: '[{"id":"https://doi.org/10.53731/r294649-6f79289-8cw1w","uuid":"b1038a3f-c5aa-4a68-97cb-5c68b27942f7","url":"https://blog.front-matter.io/posts/re3data-org-registry-of-research-data-repositories-launched","title":"re3data.org:
+        registry of research data repositories launched","summary":"Earlier this week
+        re3data.org – the Registry of Research Data Repositories – officially launched.
+        The registry is nicely described in a preprint also published this week.re3data.org
+        offers researchers, funding organizations, libraries and publishers and overview
+        of the heterogeneous research data repository landscape. Information icons
+        help researchers to identify an adequate repository for the storage and reuse
+        of their data.I really like re3data.org, and that is not because I personally
+        know...","date_published":"2013-06-01T00:00:00+00:00","date_modified":"2023-06-29T18:04:53+00:00","date_indexed":"2023-06-28T18:13:09+00:00","authors":[{"url":"https://orcid.org/0000-0003-1419-2405","name":"Martin
+        Fenner"}],"image":"https://blog.front-matter.io/content/images/2022/08/figure2.png","tags":["News"],"language":"en","references":[{"doi":"https://doi.org/10.7287/peerj.preprints.21v1","key":"ref1"},{"doi":"https://doi.org/10.2312/re3.002","key":"ref2"}],"blog_id":"f0m0e38","blog":{"id":"f0m0e38","title":"Front
+        Matter","description":"The Front Matter Blog covers the intersection of science
+        and technology since 2007.","language":"en","favicon":"https://blog.front-matter.io/favicon.png","feed_url":"https://blog.front-matter.io/atom-complete/","home_page_url":"https://blog.front-matter.io","user_id":"8498eaf6-8c58-4b58-bc15-27eda292b1aa","created_at":"2023-05-31T07:20:33+00:00","indexed_at":"2023-01-02","feed_format":"application/atom+xml","license":"https://creativecommons.org/licenses/by/4.0/legalcode","generator":"Ghost
+        5.52","category":"Engineering and Technology","prefix":"10.53731","modified_at":"2023-06-29T18:04:53+00:00","version":"https://jsonfeed.org/version/1.1","backlog":false,"authors":null,"current_feed_url":"https://blog.front-matter.io/atom/","expired":null}},{"id":"https://doi.org/10.53731/r294649-6f79289-8cw3h","uuid":"e4e13c41-5991-41b6-811b-6271510c1b0e","url":"https://blog.front-matter.io/posts/increased-cancer-risk-following-computed-tomography-scans","title":"Increased
+        cancer risk following computed tomography scans","summary":"Two papers (this
+        and this) and an editorial in the latest issue of Archives of Internal Medicine
+        examine the cancer risks associated with the use of computed tomography (CT)
+        examinations.1Ionizing radiation increases the risk for developing cancer.
+        There is direct evidence from atomic bomb survivors in Japan in 1945 and from
+        nuclear accidents such as the one in Chernobyl in 1986. There are no studies
+        directly demonstrating an increased cancer risk from the diagnostic use of
+        X-rays (either...","date_published":"2009-12-20T00:00:00+00:00","date_modified":"2023-06-29T17:49:57+00:00","date_indexed":"2023-06-28T18:13:09+00:00","authors":[{"url":"https://orcid.org/0000-0003-1419-2405","name":"Martin
+        Fenner"}],"image":"https://blog.front-matter.io/content/images/2022/08/ioi90119f2.jpg","tags":["Feature"],"language":"en","references":[{"doi":"https://doi.org/10.1001/archinternmed.2009.427","key":"ref1"},{"doi":"https://doi.org/10.1001/archinternmed.2009.440","key":"ref2"},{"doi":"https://doi.org/10.1001/archinternmed.2009.453","key":"ref3"}],"blog_id":"f0m0e38","blog":{"id":"f0m0e38","title":"Front
+        Matter","description":"The Front Matter Blog covers the intersection of science
+        and technology since 2007.","language":"en","favicon":"https://blog.front-matter.io/favicon.png","feed_url":"https://blog.front-matter.io/atom-complete/","home_page_url":"https://blog.front-matter.io","user_id":"8498eaf6-8c58-4b58-bc15-27eda292b1aa","created_at":"2023-05-31T07:20:33+00:00","indexed_at":"2023-01-02","feed_format":"application/atom+xml","license":"https://creativecommons.org/licenses/by/4.0/legalcode","generator":"Ghost
+        5.52","category":"Engineering and Technology","prefix":"10.53731","modified_at":"2023-06-29T18:04:53+00:00","version":"https://jsonfeed.org/version/1.1","backlog":false,"authors":null,"current_feed_url":"https://blog.front-matter.io/atom/","expired":null}}]'
+  recorded_at: Sat, 01 Jul 2023 18:57:39 GMT
+recorded_with: VCR 6.2.0

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

@@ -0,0 +1,56 @@
+---
+http_interactions:
+- request:
+    method: get
+    uri: https://rogue-scholar.org/api/posts/2b3cdd27-5123-4167-9482-3c074392e2d2
+    body:
+      encoding: UTF-8
+      string: ''
+    headers:
+      Connection:
+      - close
+      Host:
+      - rogue-scholar.org
+      User-Agent:
+      - http.rb/5.1.1
+  response:
+    status:
+      code: 200
+      message: OK
+    headers:
+      Age:
+      - '0'
+      Cache-Control:
+      - public, max-age=0, must-revalidate
+      Content-Length:
+      - '1509'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Wed, 28 Jun 2023 07:30:24 GMT
+      Etag:
+      - '"8258swzkwh15x"'
+      Server:
+      - Vercel
+      Strict-Transport-Security:
+      - max-age=63072000
+      X-Matched-Path:
+      - "/api/posts/[slug]"
+      X-Vercel-Cache:
+      - MISS
+      X-Vercel-Id:
+      - fra1::iad1::wc777-1687937422070-9bb853322252
+      Connection:
+      - close
+    body:
+      encoding: UTF-8
+      string: '{"id":"63cef642602205003d6f50fb","uuid":"2b3cdd27-5123-4167-9482-3c074392e2d2","url":"https://blog.oa.works/nature-features-oa-reports-work-putting-oa-policy-into-practice/","title":"Nature
+        features OA.Report''s work putting OA policy into practice!","summary":"After
+        a couple of years of working to support institutions implementing their OA
+        policies, we''re so proud to see OA.Report, our development partner, and one
+        of our collaborators featured in Nature. We appreciate Nature bringing attention
+        to the progress being made in more effectively implementing OA policies.","date_published":"2023-01-24T11:11:47Z","date_modified":null,"date_indexed":"2023-06-20T06:34:19.365+00:00","authors":[{"url":null,"name":"OA.Works"}],"image":"https://blog.oa.works/content/images/2023/01/nature-website-v2.png","tags":["OA.Report"],"language":"en","references":[],"blog_id":"h7bpg11","blog":{"id":"h7bpg11","title":"OA.Works
+        Blog","description":"OA.Works Blog","language":"en","favicon":"https://blog.oa.works/favicon.png","feed_url":"https://blog.oa.works/rss/","home_page_url":"https://blog.oa.works/","user_id":"8498eaf6-8c58-4b58-bc15-27eda292b1aa","created_at":"2023-05-31T14:11:14+00:00","indexed_at":"2023-01-04","feed_format":"application/rss+xml","license":"https://creativecommons.org/licenses/by/4.0/legalcode","generator":"Ghost
+        5.53","category":"Engineering and Technology","prefix":null,"modified_at":"2023-03-23T12:24:58+00:00","version":"https://jsonfeed.org/version/1.1","backlog":true,"authors":null}}'
+  recorded_at: Wed, 28 Jun 2023 07:30:24 GMT
+recorded_with: VCR 6.1.0

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

@@ -0,0 +1,60 @@
+---
+http_interactions:
+- request:
+    method: get
+    uri: https://rogue-scholar.org/api/posts/5d95d90d-ff59-4c8b-b7f8-44e6b45fd593
+    body:
+      encoding: UTF-8
+      string: ''
+    headers:
+      Connection:
+      - close
+      Host:
+      - rogue-scholar.org
+      User-Agent:
+      - http.rb/5.1.1
+  response:
+    status:
+      code: 200
+      message: OK
+    headers:
+      Age:
+      - '0'
+      Cache-Control:
+      - public, max-age=0, must-revalidate
+      Content-Length:
+      - '1844'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Wed, 28 Jun 2023 07:39:01 GMT
+      Etag:
+      - '"6emrve7vie1ew"'
+      Server:
+      - Vercel
+      Strict-Transport-Security:
+      - max-age=63072000
+      X-Matched-Path:
+      - "/api/posts/[slug]"
+      X-Vercel-Cache:
+      - MISS
+      X-Vercel-Id:
+      - fra1::iad1::q9g2k-1687937937528-5f071f224fc7
+      Connection:
+      - close
+    body:
+      encoding: UTF-8
+      string: '{"id":"https://doi.org/10.59350/tpa8t-j6292","uuid":"5d95d90d-ff59-4c8b-b7f8-44e6b45fd593","url":"https://www.samuelmoore.org/2023/04/20/how-to-cultivate-good-closures-scaling-small-and-the-limits-of-openness","title":"How
+        to cultivate good closures: ‘scaling small’ and the limits of openness","summary":"Text
+        of a talk given to the COPIM end-of-project conference: “Scaling Small: Community-Owned
+        Futures for Open Access Books”, April 20th 2023 Open access publishing has
+        always had a difficult relationship with smoothness and scale. Openness implies
+        seamlessness, limitlessness or structureless-ness – or the idea that the removal
+        of price and permission barriers is what’s needed to allow research to reach
+        its full potential. The drive for seamlessness is on display in much of the
+        push for...","date_published":"2023-04-20T15:37:20Z","date_modified":"2023-06-19T11:01:51Z","date_indexed":"2023-06-20T06:34:19+00:00","authors":[{"url":"https://orcid.org/0000-0002-0504-2897","name":"Samuel
+        Moore"}],"image":null,"tags":["Open access"],"language":"en","references":null,"blog_id":"gr1by89","blog":{"id":"gr1by89","title":"Samuel
+        Moore","description":"publishing, technology, commons","language":"en","favicon":"https://www.samuelmoore.org/wp-content/uploads/2019/02/cropped-cropped-cropped-roAorange-icon-2-32x32.png","feed_url":"https://www.samuelmoore.org/feed/atom/","home_page_url":"https://www.samuelmoore.org/","user_id":"8498eaf6-8c58-4b58-bc15-27eda292b1aa","created_at":"2023-05-31T14:25:06+00:00","indexed_at":"2023-01-05","feed_format":"application/atom+xml","license":"https://creativecommons.org/licenses/by/4.0/legalcode","generator":"WordPress
+        6.2.2","category":"Social Sciences","prefix":null,"modified_at":"2023-04-20T15:37:20+00:00","version":"https://jsonfeed.org/version/1.1","backlog":true,"authors":null}}'
+  recorded_at: Wed, 28 Jun 2023 07:39:01 GMT
+recorded_with: VCR 6.1.0

data/spec/readers/json_feed_reader_spec.rb

@@ -174,6 +174,54 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.references.length).to eq(3)
       expect(subject.references.first).to eq("key" => "ref1", "url" => "https://sauroposeidon.files.wordpress.com/2010/04/foster-and-wedel-2014-haplocanthosaurus-from-snowmass-colorado.pdf")
     end
+    
+    it "wordpress post with tracking code on url" do
+      input = "https://rogue-scholar.org/api/posts/5d95d90d-ff59-4c8b-b7f8-44e6b45fd593"
+      subject = described_class.new(input: input)
+      puts subject.errors
+      # expect(subject.valid?).to be true
+      expect(subject.id).to eq("https://doi.org/10.59350/tpa8t-j6292")
+      expect(subject.url).to eq("https://www.samuelmoore.org/2023/04/20/how-to-cultivate-good-closures-scaling-small-and-the-limits-of-openness")
+      expect(subject.type).to eq("Article")
+      expect(subject.creators.length).to eq(1)
+      expect(subject.creators.first).to eq("familyName"=>"Moore", "givenName"=>"Samuel", "id"=>"https://orcid.org/0000-0002-0504-2897", "type"=>"Person")
+      expect(subject.titles).to eq([{ "title" => "How to cultivate good closures: ‘scaling small’ and the limits of openness" }])
+      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"=>"2023-04-20", "updated"=>"2023-06-19")
+      expect(subject.descriptions.first["description"]).to start_with("Text of a talk given to the COPIM end-of-project conference")
+      expect(subject.publisher).to eq("name" => "Samuel Moore")
+      expect(subject.subjects).to eq([{ "subject" => "Social sciences" },
+                                      { "schemeUri" => "http://www.oecd.org/science/inno/38235147.pdf",
+                                        "subject" => "FOS: Social sciences",
+                                        "subjectScheme" => "Fields of Science and Technology (FOS)" }])
+      expect(subject.language).to eq("en")
+      expect(subject.container).to eq("identifier" => "https://www.samuelmoore.org/", "identifierType" => "URL", "title" => "Samuel Moore", "type" => "Periodical")
+      expect(subject.references).to be_nil
+    end
+
+    it "ghost post with institutional author" do
+      input = "https://rogue-scholar.org/api/posts/2b3cdd27-5123-4167-9482-3c074392e2d2"
+      subject = described_class.new(input: input)
+      expect(subject.valid?).to be true
+      expect(subject.id).to eq("https://blog.oa.works/nature-features-oa-reports-work-putting-oa-policy-into-practice")
+      expect(subject.url).to eq("https://blog.oa.works/nature-features-oa-reports-work-putting-oa-policy-into-practice")
+      expect(subject.type).to eq("Article")
+      expect(subject.creators.length).to eq(1)
+      expect(subject.creators.first).to eq("name"=>"OA.Works", "type"=>"Organization")
+      expect(subject.titles).to eq([{ "title" => "Nature features OA.Report's work putting OA policy into practice!" }])
+      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" => "2023-01-24")
+      expect(subject.descriptions.first["description"]).to start_with("After a couple of years of working to support institutions implementing their OA policies")
+      expect(subject.publisher).to eq("name" => "OA.Works Blog")
+      expect(subject.subjects).to eq([{ "subject" => "Engineering and technology" },
+                                      { "schemeUri" => "http://www.oecd.org/science/inno/38235147.pdf",
+                                        "subject" => "FOS: Engineering and technology",
+                                        "subjectScheme" => "Fields of Science and Technology (FOS)" }])
+      expect(subject.language).to eq("en")
+      expect(subject.container).to eq("identifier" => "https://blog.oa.works/", "identifierType" => "URL", "title" => "OA.Works Blog", "type" => "Periodical")
+    end
 
     it "upstream post with references" do
       input = "https://rogue-scholar.org/api/posts/954f8138-0ecd-4090-87c5-cef1297f1470"
@@ -334,8 +382,8 @@ describe Commonmeta::Metadata, vcr: true do
     end
 
     it "not indexed posts" do
-      response = subject.get_json_feed_not_indexed("2023-01-01")
-      expect(response).to eq("ca2a7df4-f3b9-487c-82e9-27f54de75ea8")
+      response = subject.get_json_feed_not_indexed
+      expect(response).to eq("b1038a3f-c5aa-4a68-97cb-5c68b27942f7")
     end
 
     it "by blog_id" do

data/spec/readers/ris_reader_spec.rb

@@ -50,7 +50,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.state).to eq('not_found')
       expect(subject.id).to eq('https://doi.org/10.7554/elife.01567')
       expect(subject.type).to eq('Dissertation')
-      expect(subject.creators).to eq([{ 'name' => 'Toparlar,Y.' }])
+      expect(subject.creators).to eq([{"familyName"=>"Toparlar", "givenName"=>"Y.", "type"=>"Person"}])
       expect(subject.titles).to eq([{ 'title' => 'A multiscale analysis of the urban heat island effect' }])
       expect(subject.descriptions.first['description']).to start_with('Designing the climates of cities')
       expect(subject.date).to eq('created' => '2018-04-25', 'published' => '2018-04-25')

data/spec/readers/schema_org_reader_spec.rb

@@ -153,9 +153,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.titles).to eq([{ 'title' => 'Summary data ankylosing spondylitis GWAS' }])
       expect(subject.container).to eq('identifier' => 'https://dataverse.harvard.edu',
                                       'identifierType' => 'URL', 'title' => 'Harvard Dataverse', 'type' => 'DataRepository')
-      expect(subject.creators).to eq([{
-                                       'name' => 'International Genetics of Ankylosing Spondylitis Consortium (IGAS)'
-                                     }])
+      expect(subject.creators).to eq([{"name"=>"International Genetics of Ankylosing Spondylitis Consortium (IGAS)", "type"=>"Organization"}])
       expect(subject.subjects).to eq([{ 'subject' => 'Medicine, health and life sciences' },
                                       { 'subject' => 'genome-wide association studies' },
                                       { 'subject' => 'Ankylosing spondylitis' }])

data/spec/writers/schema_org_writer_spec.rb

@@ -177,7 +177,7 @@ describe Commonmeta::Metadata, vcr: true do
       expect(json['@id']).to eq('https://doi.org/10.23725/8na3-9s47')
       expect(json['@type']).to eq('Dataset')
       expect(json['name']).to eq('NWD165827.recab.cram')
-      expect(json['author']).to eq('name' => 'TOPMed')
+      expect(json['author']).to eq("@type"=>"Organization", "name"=>"TOPMed")
       expect(json['includedInDataCatalog']).to be_empty
       expect(json['identifier']).to eq(
         [{ '@type' => 'PropertyValue',

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: commonmeta-ruby
 version: !ruby/object:Gem::Version
-  version: 3.3.8
+  version: 3.3.10
 platform: ruby
 authors:
 - Martin Fenner
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-06-21 00:00:00.000000000 Z
+date: 2023-07-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
@@ -870,6 +870,7 @@ files:
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/blogger_post.yml
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/ghost_post_with_author_name_suffix.yml
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/ghost_post_with_doi.yml
+- spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/ghost_post_with_institutional_author.yml
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/ghost_post_with_organizational_author.yml
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/ghost_post_without_doi.yml
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/jekyll_post.yml
@@ -879,6 +880,7 @@ files:
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/upstream_post_with_references.yml
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/wordpress_post.yml
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/wordpress_post_with_references.yml
+- spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_json_feed_item_metadata/wordpress_post_with_tracking_code_on_url.yml
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_one_author/affiliation_is_space.yml
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_one_author/has_familyName.yml
 - spec/fixtures/vcr_cassettes/Commonmeta_Metadata/get_one_author/has_name_in_display-order_with_ORCID.yml