commonmeta-ruby 3.2.6 → 3.2.7

data/spec/author_utils_spec.rb

@@ -44,10 +44,42 @@ describe Commonmeta::Metadata, vcr: true do
       expect(subject.is_personal_name?(name: author['name'])).to be true
     end
 
+    it 'has unknown given name and middle initial' do
+      author = { 'name' => 'Tejas S. Sathe' }
+      expect(subject.is_personal_name?(name: author['name'])).to be true
+    end
+
     it 'has no info' do
       author = { 'name' => 'M Fenner' }
       expect(subject.is_personal_name?(name: author['name'])).to be true
     end
+
+    it 'name with title' do
+      author = { 'name' => 'Tejas S. Sathe, MD' }
+      expect(subject.is_personal_name?(name: author['name'])).to be true
+    end
+  end
+
+  context 'cleanup_author' do
+    it 'Smith J.' do
+      author = 'Smith J.'
+      expect(subject.cleanup_author(author)).to eq('Smith, J.')
+    end
+
+    it 'Smith, John' do
+      author = 'Smith, John'
+      expect(subject.cleanup_author(author)).to eq('Smith, John')
+    end
+
+    it 'John Smith' do
+      author = 'John Smith'
+      expect(subject.cleanup_author(author)).to eq('John Smith')
+    end
+
+    it 'with email' do
+      author = 'noreply@blogger.com (Roderic Page)'
+      expect(subject.cleanup_author(author)).to eq('Roderic Page')
+    end
   end
 
   context 'get_one_author' do
@@ -69,6 +101,12 @@ describe Commonmeta::Metadata, vcr: true do
       )
     end
 
+    it 'has name with title' do
+      author = { 'name' => "Tejas S. Sathe, MD" }
+      response = subject.get_one_author(author)
+      expect(response).to eq('givenName' => 'Tejas S.', 'familyName' => 'Sathe', 'type' => 'Person')
+    end
+
     it 'has name in display-order with ORCID' do
       input = 'https://doi.org/10.6084/M9.FIGSHARE.4700788'
       subject = described_class.new(input: input)

data/spec/cli_spec.rb

@@ -341,9 +341,9 @@ describe Commonmeta::CLI do
     end
   end
 
-  describe "json_feed", vcr: true do
-    it "blog post uuid" do
-      expect { subject.json_feed }.to output(/e4872b3e-cd15-407d-8406-33642c1a98b0\n/).to_stdout
-    end
-  end
+  # describe "json_feed_unregistered", vcr: true do
+  #   it "blog post uuid" do
+  #     expect { subject.json_feed_unregistered }.to output(/e4872b3e-cd15-407d-8406-33642c1a98b0\n/).to_stdout
+  #   end
+  # end
 end

data/spec/fixtures/vcr_cassettes/Commonmeta_CLI/json_feed_unregistered/blog_post_uuid.yml

@@ -0,0 +1,49 @@
+---
+http_interactions:
+- request:
+    method: get
+    uri: https://rogue-scholar.org/api/posts/unregistered
+    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:
+      - '2'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Sat, 10 Jun 2023 08:41:01 GMT
+      Etag:
+      - '"38jmpejbxv2"'
+      Server:
+      - Vercel
+      Strict-Transport-Security:
+      - max-age=63072000
+      X-Matched-Path:
+      - "/api/posts/unregistered"
+      X-Vercel-Cache:
+      - MISS
+      X-Vercel-Id:
+      - fra1::iad1::zmnzt-1686386457205-d9f9a0745c33
+      Connection:
+      - close
+    body:
+      encoding: UTF-8
+      string: "[]"
+  recorded_at: Sat, 10 Jun 2023 08:41:01 GMT
+recorded_with: VCR 6.1.0

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

@@ -0,0 +1,215 @@
+---
+http_interactions:
+- request:
+    method: get
+    uri: https://rogue-scholar.org/api/posts/unregistered
+    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:
+      - '16766'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Sun, 11 Jun 2023 15:55:11 GMT
+      Etag:
+      - '"ojfwmyfwfacxk"'
+      Server:
+      - Vercel
+      Strict-Transport-Security:
+      - max-age=63072000
+      X-Matched-Path:
+      - "/api/posts/unregistered"
+      X-Vercel-Cache:
+      - MISS
+      X-Vercel-Id:
+      - fra1::iad1::tfxzn-1686498910666-ea864f114549
+      Connection:
+      - close
+    body:
+      encoding: UTF-8
+      string: '[{"id":"https://svpow.com/2023/06/09/three-presentations-today-at-mte14-and-the-papers-that-go-with-them/","uuid":"ca2a7df4-f3b9-487c-82e9-27f54de75ea8","url":"https://svpow.com/2023/06/09/three-presentations-today-at-mte14-and-the-papers-that-go-with-them/","title":"Three
+        presentations today at MTE14, and the papers that go with them","summary":"BIG
+        day today. The 14th Symposium on Mesozoic Terrestrial Ecosystems and Biota
+        (MTE14) is taking place in Salt Lake City this week. Normally I’d be there
+        in a heartbeat, but my son is graduating from high...","date_published":"2023-06-09T13:02:26Z","date_modified":"2023-06-09T13:02:26Z","authors":[{"url":null,"name":"Matt
+        Wedel"}],"image":null,"content_html":"<p><a href=\"https://svpow.files.wordpress.com/2023/06/ripple-rock-in-the-oklahoma-morrison.jpg\"><img
+        loading=\"lazy\" data-attachment-id=\"21001\" data-permalink=\"https://svpow.com/2023/06/09/three-presentations-today-at-mte14-and-the-papers-that-go-with-them/ripple-rock-in-the-oklahoma-morrison/\"
+        data-orig-file=\"https://svpow.files.wordpress.com/2023/06/ripple-rock-in-the-oklahoma-morrison.jpg\"
+        data-orig-size=\"2000,2000\" data-comments-opened=\"1\" data-image-meta=\"{\"aperture\":\"1.8\",\"credit\":\"\",\"camera\":\"iPhone
+        7\",\"caption\":\"\",\"created_timestamp\":\"1530009833\",\"copyright\":\"\",\"focal_length\":\"3.99\",\"iso\":\"20\",\"shutter_speed\":\"0.00051203277009729\",\"title\":\"\",\"orientation\":\"1\"}\"
+        data-image-title=\"Ripple rock in the Oklahoma Morrison\" data-image-description=\"\"
+        data-image-caption=\"\" data-medium-file=\"https://svpow.files.wordpress.com/2023/06/ripple-rock-in-the-oklahoma-morrison.jpg?w=300\"
+        data-large-file=\"https://svpow.files.wordpress.com/2023/06/ripple-rock-in-the-oklahoma-morrison.jpg?w=480\"
+        class=\"size-large wp-image-21001 aligncenter\" src=\"https://svpow.files.wordpress.com/2023/06/ripple-rock-in-the-oklahoma-morrison.jpg?w=480\"
+        alt=\"\" width=\"480\" height=\"480\" srcset=\"https://svpow.files.wordpress.com/2023/06/ripple-rock-in-the-oklahoma-morrison.jpg?w=480
+        480w, https://svpow.files.wordpress.com/2023/06/ripple-rock-in-the-oklahoma-morrison.jpg?w=960
+        960w, https://svpow.files.wordpress.com/2023/06/ripple-rock-in-the-oklahoma-morrison.jpg?w=150
+        150w, https://svpow.files.wordpress.com/2023/06/ripple-rock-in-the-oklahoma-morrison.jpg?w=300
+        300w, https://svpow.files.wordpress.com/2023/06/ripple-rock-in-the-oklahoma-morrison.jpg?w=768
+        768w\" sizes=\"(max-width: 480px) 100vw, 480px\" /></a></p>\n<p>BIG day today.
+        The 14th Symposium on Mesozoic Terrestrial Ecosystems and Biota (MTE14) is
+        taking place in Salt Lake City this week. Normally I&#8217;d be there in a
+        heartbeat, but my son is graduating from high school next week and I&#8217;m
+        far too busy to get away. Still, I&#8217;m an author on one poster and two
+        talks that are running today, along with the three associated short papers
+        that are published in the conference volume in The Anatomical Record. </p>\n<p>I
+        will be blogging about these things, and shortly, but for now here are Wedel-related
+        presentations and links to the papers, in chronological order. (The whole
+        conference volume is available <a href=\"https://anatomypubs.onlinelibrary.wiley.com/doi/full/10.1002/ar.25219\">here</a>,
+        I just extracted the papers I&#8217;m on as separate PDFs to post in the links
+        below.)</p>\n<p>1. Wedel and Atterholt on expanded neurocentral joints in
+        sauropods &#8212; Jessie is presenting our poster, which should be up for
+        most of the day. Citation and link to paper:</p>\n<p style=\"padding-left:
+        40px\"><a href=\"https://sauroposeidon.files.wordpress.com/2010/04/wedel-and-atterholt-2023-expanded-neurocentral-joints-in-sauropods.pdf\">Wedel,
+        M.J., and Atterholt, J. 2023. Expanded neurocentral joints in the vertebrae
+        of sauropod dinosaurs. In Hunt-Foster, R.K., Kirkland, J.I., and Loewen, M.A.
+        (eds), 14th Symposium on Mesozoic Terrestrial Ecosystems and Biota. The Anatomical
+        Record 306(S1):256-257.</a></p>\n<p>2. Curtice et al. on the first material
+        of <em>Haplocanthosaurus</em> from Dry Mesa &#8212; I believe Brian Curtice
+        and Colin Boisvert are tag-teaming this talk at 2:00 pm MDT. </p>\n<p style=\"padding-left:
+        40px\"><a href=\"https://sauroposeidon.files.wordpress.com/2010/04/curtice-et-al-2023-haplocanthosaurus-from-dry-mesa.pdf\">Curtice,
+        B., Wedel, M.J., Wilhite, D.R., and Boisvert, C. 2023. New material of <em>Haplocanthosaurus</em>
+        (Hatcher 1903) from the Dry Mesa Dinosaur Quarry and a comment on sauropod
+        diversity. In Hunt-Foster, R.K., Kirkland, J.I., and Loewen, M.A. (eds), 14th
+        Symposium on Mesozoic Terrestrial Ecosystems and Biota. The Anatomical Record
+        306(S1):79-81.</a></p>\n<p>3. Weil et al. on Morrison microvertebrates from
+        the Oklahoma panhandle &#8212; Anne Weil is giving this talk at 2:15 pm MDT.</p>\n<p
+        style=\"padding-left: 40px\"><a href=\"https://sauroposeidon.files.wordpress.com/2010/04/weil-et-al-2023-oklahoma-morrison-microvertebrates.pdf\">Weil,
+        A., Hall, L., and Wedel, M.J. 2023. Microvertebrate expansion of known fauna
+        of the Morrison Formation of Oklahoma will enable more meaningful comparisons
+        with other regions. In Hunt-Foster, R.K., Kirkland, J.I., and Loewen, M.A.
+        (eds), 14th Symposium on Mesozoic Terrestrial Ecosystems and Biota. The Anatomical
+        Record 306(S1):257-258.</a></p>\n<p>Stand by for more info on all this stuff.
+        And if you&#8217;re attending MTE14, go catch these presentations and say
+        hi to all these excellent human beings!</p>\n","tags":["#MTE14","conferences","navel
+        blogging","timely"],"language":"en","blog_id":"dkvra02","blog":{"id":"dkvra02","title":"Sauropod
+        Vertebra Picture of the Week","description":"SV-POW!  ...  All sauropod vertebrae,
+        except when we&#039;re talking about Open Access","language":"en","favicon":null,"feed_url":"https://svpow.com/feed/atom/","home_page_url":"https://svpow.com","user_id":"8498eaf6-8c58-4b58-bc15-27eda292b1aa","created_at":"2023-05-31T14:28:02+00:00","indexed_at":"2023-02-01","feed_format":"application/atom+xml","license":"https://creativecommons.org/licenses/by/4.0/legalcode","generator":"WordPress
+        (.com)","category":"Natural Sciences","prefix":"10.59350","modified_at":"2023-05-27T00:26:38+00:00","version":"https://jsonfeed.org/version/1.1","backlog":true}},{"id":"http://bjoern.brembs.net/2023/06/the-beginning-of-the-end-for-academic-publishers/","uuid":"c0ebaf2d-8e50-404c-8db7-4fd04e56aded","url":"http://bjoern.brembs.net/2023/06/the-beginning-of-the-end-for-academic-publishers/","title":"The
+        beginning of the end for academic publishers?","summary":"On May 23, the Council
+        of the EU adopted a set of conclusions on scholarly publishing that, if followed
+        through, would spell the end for academic publishers and scholarly journals
+        as we know them. On the same...","date_published":"2023-06-02T07:01:14Z","date_modified":"2023-06-02T07:01:15Z","authors":[{"url":null,"name":"Björn
+        Brembs"}],"image":null,"content_html":"<img src=\"http://bjoern.brembs.net/wp//wp-content/uploads/2013/05/politics.gif\"
+        width=\"50\" height=\"50\" alt=\"science politics\" title=\"science politics\"
+        /><br/>\n<p>On May 23, the <a href=\"https://en.wikipedia.org/wiki/Council_of_the_European_Union\">Council
+        of the EU</a> adopted a <a href=\"https://www.consilium.europa.eu/en/press/press-releases/2023/05/23/council-calls-for-transparent-equitable-and-open-access-to-scholarly-publications/\">set
+        of conclusions</a> on scholarly publishing that, if followed through, would
+        spell the end for academic publishers and scholarly journals as we know them.
+        On the same day, the adoption was followed by a <a href=\"https://www.coalition-s.org/open-science-stakeholders-welcome-european-efforts-towards-publicly-owned-and-not-for-profit-scholarly-communication/\">joint
+        statement</a> of support by the largest and most influential research organizations
+        in Europe. At the heart of the goals spelled out in the conclusions and the
+        statement of support is the creation of a &#8220;publicly owned and not-for-profit&#8221;
+        infrastructure for scholarly publications.</p>\n\n\n\n<p>Specifically, the
+        Council </p>\n\n\n\n<blockquote class=\"wp-block-quote\">\n<p>ENCOURAGES Member
+        States and the Commission to invest in and foster interoperable, not-for-profit
+        infrastructures for publishing based on open source software and open standards,
+        in order to avoid the lock-in of services as well as proprietary systems,
+        and to connect these infrastructures to the EOSC</p>\n</blockquote>\n\n\n\n<p>This
+        echos almost verbatim our proposal from 2021 where we outline a <a href=\"https://doi.org/10.5281/zenodo.5526634\">replacement
+        for academic journals</a>. In this post, we detail the reasons behind this
+        seemingly radical proposal:</p>\n\n\n\n<figure class=\"wp-block-image size-large
+        is-resized\"><a href=\"http://bjoern.brembs.net/wp/wp-content/uploads/2023/06/FIG_circular_v1.5.png\"><img
+        decoding=\"async\" src=\"http://bjoern.brembs.net/wp/wp-content/uploads/2023/06/FIG_circular_v1.5-1024x863.png\"
+        alt=\"Three major scholarly crises in a vicious cycle\" class=\"wp-image-2571\"
+        width=\"512\" height=\"432\" srcset=\"http://bjoern.brembs.net/wp/wp-content/uploads/2023/06/FIG_circular_v1.5-1024x863.png
+        1024w, http://bjoern.brembs.net/wp/wp-content/uploads/2023/06/FIG_circular_v1.5-300x253.png
+        300w, http://bjoern.brembs.net/wp/wp-content/uploads/2023/06/FIG_circular_v1.5-768x647.png
+        768w, http://bjoern.brembs.net/wp/wp-content/uploads/2023/06/FIG_circular_v1.5-50x42.png
+        50w, http://bjoern.brembs.net/wp/wp-content/uploads/2023/06/FIG_circular_v1.5.png
+        1175w\" sizes=\"(max-width: 512px) 100vw, 512px\" /></a><figcaption class=\"wp-element-caption\"><em>A
+        vicious cycle of three crises</em>.<br />With their supra-inflationary price
+        increases, profit-maximizing journals overcharge (via subscriptions or article
+        processing charges) institutions by a factor of up to tenfold, extracting
+        library budgets with little if anything left for infrastructural development.
+        The resulting lack of infrastructure funds is a crisis of affordability: institutions
+        cannot afford to invest in technology and human support for relieving researchers
+        of menial tasks such as manuscript submission, data deposition, code publication,
+        etc. This results in a functionality crisis that entails researchers lacking
+        time, functionalities and human support both for efficient scrutiny during
+        the review process as well as for making their own research open and reproducible.
+        Not shown: Journals have apparently not invested their surplus into reviewer
+        support, resulting in little improvement over the last decades, such that
+        researchers are still lacking basic functionalities such as, e.g., comments
+        via authoring system, direct author communication, AI-assisted error and fraud
+        detection, efficient manuscript submission, etc., contributing to the functionality
+        crisis. As the journals keep increasing their prices without a concomitant
+        rise in investments, they fuel the replicability crisis.</figcaption></figure>\n\n\n\n<p>This
+        vicious cycle has been allowed to go on for so long, that more and more experts
+        are now calling for precisely such a disruptive break. The time for small,
+        evolutionary steps has passed and the parasitic publishing corporations have
+        shown little willingness over the last decades even to just mitigate, let
+        alone solve the problems caused by their extractive business models. For more
+        than a decade, an ever-growing group of researchers have called to <a href=\"http://bjoern.brembs.net/2013/06/cut-out-the-parasitic-middlemen/\">cut
+        out these parasitic middle-men</a>. It now finally seems as if our arguments
+        have been convincing. Everything in the Council&#8217;s conclusions reiterates
+        what the open science community has been fighting for in all this time: vendor
+        lock-in needs to be broken, scholarly governance established and fragmenting
+        silos replaced with interoperable, federated infrastructure.</p>\n\n\n\n<p>The
+        technical solutions needed for this modernization from 17th century journals
+        to 21 century digital technology are plenty and readily available off the
+        shelf. Scholarship has the choice of either picking pre-existing solutions
+        such as <a href=\"https://core.ac.uk/\">CORE</a> or <a href=\"https://openresearchcentral.org/\">ORC</a>,
+        or design a new network. In either case, the general structural design of
+        such a network may look something like this:</p>\n\n\n\n<figure class=\"wp-block-image
+        size-large is-resized\"><a href=\"http://bjoern.brembs.net/wp/wp-content/uploads/2023/06/FIG_openscience_platform_v1.6.png\"><img
+        decoding=\"async\" loading=\"lazy\" src=\"http://bjoern.brembs.net/wp/wp-content/uploads/2023/06/FIG_openscience_platform_v1.6-1024x623.png\"
+        alt=\"\" class=\"wp-image-2572\" width=\"512\" height=\"312\" srcset=\"http://bjoern.brembs.net/wp/wp-content/uploads/2023/06/FIG_openscience_platform_v1.6-1024x623.png
+        1024w, http://bjoern.brembs.net/wp/wp-content/uploads/2023/06/FIG_openscience_platform_v1.6-300x182.png
+        300w, http://bjoern.brembs.net/wp/wp-content/uploads/2023/06/FIG_openscience_platform_v1.6-768x467.png
+        768w, http://bjoern.brembs.net/wp/wp-content/uploads/2023/06/FIG_openscience_platform_v1.6-1536x934.png
+        1536w, http://bjoern.brembs.net/wp/wp-content/uploads/2023/06/FIG_openscience_platform_v1.6-2048x1245.png
+        2048w, http://bjoern.brembs.net/wp/wp-content/uploads/2023/06/FIG_openscience_platform_v1.6-50x30.png
+        50w\" sizes=\"(max-width: 512px) 100vw, 512px\" /></a><figcaption class=\"wp-element-caption\"><em>Concept
+        for a federated scholarly information network</em>.<br />A federated network
+        of institutional repositories constitutes the underlying infrastructure. Ideally,
+        this infrastructure is designed redundantly, such that large fractions of
+        nodes may go offline and the remaining nodes still provide 100% of the content.
+        Users only directly interact with the output and narrative layers. The output
+        layer contains all research objects, text, data and code. The narrative layer
+        combines research objects in various forms, including research articles. The
+        community layer encompasses standard social technologies such as likes, follows
+        and other network tools (see also &#8220;<a href=\"https://doi.org/10.5281/zenodo.7643817\">Mastodon
+        over Mammon</a>&#8220;). Modified from <a href=\"https://blogs.lse.ac.uk/impactofsocialsciences/2017/04/10/rather-than-simply-moving-from-paying-to-read-to-paying-to-publish-its-time-for-a-european-open-access-platform\">LSE</a>.</figcaption></figure>\n\n\n\n<p>Picking
+        an existing solution such as CORE or ORC comes with the advantage that little
+        new development has to be done and that it is obviously very cheap: everything
+        is already in place and only needs to be expanded. The downsides are that
+        the existing solutions have been designed in the current ecosystem and that
+        may have entailed some historical baggage one would need to identify and fix.
+        Conversely, picking off-the-shelf components to build a replacement from scratch
+        costs more, but has the advantage to be able to build a state-of.the-art system
+        with all the bells and whistles from the ground up. It&#8217;s a bit like
+        the choice between buying a used or new car or house.</p>\n\n\n\n<p>Obviously,
+        right after the declaration came out, the corporate misinformation machine
+        sprang into high gear. I won&#8217;t repeat the misleading, false or sometimes
+        just comically desperate attempts at smearing an obviously well thought-through,
+        sound and logical solution that has been decades in the making. Suffice it
+        to say, there are plenty of reasons why the plans outlined by the Council
+        have drawn such widespread support from all corners of the research community,
+        while the only resistance comes from the monopolistic corporations. This declaration
+        tackles the root of the replicability, affordability and functionality crises.
+        It aims to treat the disease, not the symptoms and has the potential to develop
+        into an effective vaccine against parasitic businesses striving to leech the
+        public purse. Little wonder these businesses fear it so much.</p>\n","tags":["science
+        politics","Council of the EU","infrastructure","publishers"],"language":"en","blog_id":"8q8xh52","blog":{"id":"8q8xh52","title":"bjoern.brembs.blog","description":"The
+        blog of neurobiologist Björn Brembs","language":"en","favicon":null,"feed_url":"http://bjoern.brembs.net/feed/atom/","home_page_url":"http://bjoern.brembs.net","user_id":"8498eaf6-8c58-4b58-bc15-27eda292b1aa","created_at":"2023-05-31T08:09:10+00:00","indexed_at":"2023-04-04","feed_format":"application/atom+xml","license":"https://creativecommons.org/licenses/by/4.0/legalcode","generator":"WordPress","category":"Natural
+        Sciences","prefix":"10.59350","modified_at":"2023-03-14T14:13:30+00:00","version":"https://jsonfeed.org/version/1.1","backlog":true}}]'
+  recorded_at: Sun, 11 Jun 2023 15:55:11 GMT
+recorded_with: VCR 6.1.0

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

@@ -23,13 +23,13 @@ http_interactions:
       Cache-Control:
       - public, max-age=0, must-revalidate
       Content-Length:
-      - '5600'
+      - '6660'
       Content-Type:
       - application/json; charset=utf-8
       Date:
-      - Mon, 05 Jun 2023 08:32:17 GMT
+      - Thu, 15 Jun 2023 11:05:02 GMT
       Etag:
-      - '"w8lx6j7dgj4b8"'
+      - '"dpw65zvlfg54i"'
       Server:
       - Vercel
       Strict-Transport-Security:
@@ -39,7 +39,7 @@ http_interactions:
       X-Vercel-Cache:
       - MISS
       X-Vercel-Id:
-      - fra1::iad1::d8547-1685953936768-f6b887a2cfc5
+      - fra1::iad1::k6rcq-1686827099670-a22865de7b2f
       Connection:
       - close
     body:
@@ -48,10 +48,14 @@ http_interactions:
         years and a million links","summary":"As trailed on a Twitter thread last
         week I’ve been working on a manuscript describing the efforts to map taxonomic
         names to their original descriptions in the taxonomic literature. Putting
-        together a...","date_published":"2023-05-31T17:26:00Z","date_modified":null,"authors":[{"url":null,"name":"Roderic
-        Page"}],"image":null,"content_html":"<p>As trailed on a Twitter thread last
-        week I’ve been working on a manuscript describing the efforts to map taxonomic
-        names to their original descriptions in the taxonomic literature.</p>\n<blockquote
+        together a manuscript on linking taxonomic names to the primary literature,
+        basically “um, what, exactly, have you been doing all these years?”. TL;DR
+        Across fungi, plants, and animals approx 1.3 million names have been linked
+        to a persistent identifier for a publication.— Roderic Page (@rdmpage) May
+        25,...","date_published":"2023-05-31T17:26:00Z","date_modified":null,"authors":[{"url":null,"name":"noreply@blogger.com
+        (Roderic Page)"}],"image":null,"content_html":"<p>As trailed on a Twitter
+        thread last week I’ve been working on a manuscript describing the efforts
+        to map taxonomic names to their original descriptions in the taxonomic literature.</p>\n<blockquote
         class=\"twitter-tweet\"><p lang=\"en\" dir=\"ltr\">Putting together a manuscript
         on linking taxonomic names to the primary literature, basically “um, what,
         exactly, have you been doing all these years?”. TL;DR Across fungi, plants,
@@ -88,7 +92,12 @@ http_interactions:
         border=\"0\" width=\"320\" data-original-height=\"2276\" data-original-width=\"2276\"
         src=\"https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgf0YBuvNSXWAJTfQ1jk4XSocMzCYHP7t6IPUqhjQ3mftgM_850igWaD2copgNH6Xk6T62xBU641wvwOvXgCCDY3m2xC_gaILXO9RGx8H3Gpy5OOncsLb9smpT2LIgtYOExVBVdDRWqA0AZ8-mQjWL7dL5TiG7MqVu8spT8ACoGOPR_T36hRA/s320/plants-coverage.png\"/></a></div>\n\n\nThere
         is also a simple app to demonstrate these links, see <a href=\"https://species-cite.herokuapp.com\">https://species-cite.herokuapp.com</a>.\n\n\n\n<blockquote>\n<p>Written
-        with <a href=\"https://stackedit.io/\">StackEdit</a>.</p>\n</blockquote>","tags":[],"language":"en","blog_id":"tyfqw20","blog":{"id":"tyfqw20","title":"iPhylo","language":"en","favicon":null,"feed_url":"https://iphylo.blogspot.com/feeds/posts/default?alt=rss","home_page_url":"https://iphylo.blogspot.com/","license":"https://creativecommons.org/licenses/by/4.0/legalcode","category":"Natural
-        Sciences"}}'
-  recorded_at: Mon, 05 Jun 2023 08:32:17 GMT
+        with <a href=\"https://stackedit.io/\">StackEdit</a>.</p>\n</blockquote>","tags":[],"language":"en","references":[],"blog_id":"tyfqw20","blog":{"id":"tyfqw20","title":"iPhylo","description":"Rants,
+        raves (and occasionally considered opinions) on phyloinformatics, taxonomy,
+        and biodiversity informatics.  For more ranty and less considered opinions,
+        see my <a href=\"https://twitter.com/rdmpage\">Twitter feed</a>.<br>ISSN 2051-8188.
+        Written content on this site is licensed under a <a href=\"https://creativecommons.org/licenses/by/4.0/\">Creative
+        Commons Attribution 4.0 International license</a>.","language":"en","favicon":null,"feed_url":"https://iphylo.blogspot.com/feeds/posts/default?alt=rss","home_page_url":"https://iphylo.blogspot.com/","user_id":"8498eaf6-8c58-4b58-bc15-27eda292b1aa","created_at":"2023-05-31T08:03:14+00:00","indexed_at":"2023-02-06","feed_format":"application/rss+xml","license":"https://creativecommons.org/licenses/by/4.0/legalcode","generator":"Blogger","category":"Natural
+        Sciences","prefix":"10.59350","modified_at":"2023-05-31T17:26:00+00:00","version":"https://jsonfeed.org/version/1.1","backlog":true}}'
+  recorded_at: Thu, 15 Jun 2023 11:05:03 GMT
 recorded_with: VCR 6.1.0

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

@@ -0,0 +1,215 @@
+---
+http_interactions:
+- request:
+    method: get
+    uri: https://rogue-scholar.org/api/posts/6179ad80-cc7f-4904-9260-0ecb3c3a90ba
+    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:
+      - '14725'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Thu, 15 Jun 2023 05:34:55 GMT
+      Etag:
+      - '"12ntu9by009bd1"'
+      Server:
+      - Vercel
+      Strict-Transport-Security:
+      - max-age=63072000
+      X-Matched-Path:
+      - "/api/posts/[slug]"
+      X-Vercel-Cache:
+      - MISS
+      X-Vercel-Id:
+      - fra1::iad1::svxc9-1686807294657-7dc3d3c6f0b6
+      Connection:
+      - close
+    body:
+      encoding: UTF-8
+      string: '{"id":"https://www.ideasurg.pub/academic-powerhouse","uuid":"6179ad80-cc7f-4904-9260-0ecb3c3a90ba","url":"https://www.ideasurg.pub/academic-powerhouse/","title":"How
+        to Build an Academic Powerhouse: Let''s Study Who''s Doing it","summary":"A
+        Data Exploration with Public Data from the Academic Surgical Congress","date_published":"2023-06-03T04:54:30Z","date_modified":null,"authors":[{"url":null,"name":"Tejas
+        S. Sathe, MD"}],"image":null,"content_html":"<p>Students and residents aspiring
+        for a career in academic surgery are looking for training programs that will
+        help jumpstart their careers by exposing them to mentorship and opportunities
+        to conduct research. While the gold standard of academic productivity (for
+        the time being) remains peer-reviewed publications, conference presentations
+        are an important secondary metric. In addition to feeding eventual papers,
+        conference talks allow trainees to practice presentation skills, build their
+        networks, and learn about the work being done at peer institutions and the
+        field more broadly. Residents pursuing professional development are encouraged
+        to apply to and attend conferences, though in the post COVID era the cost
+        of conference attendance and travel are being re-evaluated. Even moreso than
+        publications, conference presentations are typically led by students and residents.
+        For now, academic conference participation can serve as an important albeit
+        limited metric to evaluate an overall institution''s research power &#x2013;
+        especially as it relates to trainees.</p><p>In order to understand how to
+        build a successful research program, we wanted to understand who had already
+        done so. Conceivably, by finding successful examples, we can conduct interviews
+        and focus groups among key stakeholders at these programs to understand what
+        they did, and how these actions can be replicated. We were particularly interested
+        in seeing which programs demonstrated a high number of accepted abstracts
+        and which programs were able to improve their abstract performance from year
+        to year. </p><p>The <a href=\"https://www.academicsurgicalcongress.org/?ref=ideasurg.pub\">Academic
+        Surgical Congress</a> (ASC) is a joint surgical meeting co-hosted by the <a
+        href=\"https://www.aasurg.org/?ref=ideasurg.pub\">Association for Academic
+        Surgery</a> (AAS) and the <a href=\"https://www.susweb.org/?ref=ideasurg.pub\">Society
+        for University Surgeons</a> (SUS) and held annually in February. Anecdotally,
+        it is a popular conference for students and residents to attend. The ASC maintains
+        a public archive of all abstracts dating from 2015-2020. We obtained a machine
+        readable version of this public database through the webmaster (this version
+        of the data spans 2016 to 2023).</p><p>For each abstract, we looked at the
+        year and primary institution at which the work was conducted. In order to
+        intuit the primary institution, we searched the institution block string for
+        the first presence of \"university\", \"hospital\", \"institute\", or \"medical
+        center\" or the first expression to occur before a comma. This method was
+        chosen as institutions&#x2019; names are written variably (Department of Surgery,
+        University Hospital, New York, NY vs. University Hospital, Division of Colorectal
+        Surgery, Department of Surgery, New York, NY). Unfortunately, our code is
+        unable to merge slight variations in the resultant institution name (University
+        of Michigan vs. University of Michigan Ann Arbor). </p><p>In order to do a
+        primary survey of institutional trends in this dataset, we conducted the following
+        analyses. First, we measured the number of abstracts accepted each year from
+        2016 to 2023. Second, we looked at the number of accepted abstracts by institution
+        over the entire study period. Then, we looked at the number of abstract institutions
+        by institution and year to study changes in institutional trends over time.
+        Finally, we did a subset analysis on post-COVID data (2021 to 2023) to look
+        at absolute and per cent year-over-year changes in accepted abstracts to see
+        which institutions were able to significantly increase their abstract performance
+        in one year. </p><h3 id=\"accepted-abstracts-are-increasing-but-down-from-peak\">Accepted
+        Abstracts are increasing but down from peak</h3><p>We plotted the total number
+        of abstracts accepted by year. The number of accepted abstracts increased
+        from 1125 in 2016 to an all-time high of 1742 in 2020 before declining to
+        922 and 848 in 2021 and 2022, respectively. Accepted abstracts have since
+        rebounded to 1469 in 2023, or roughly 84% of the maximum amount. Of note,
+        the 2021 and 2022 meetings were held virtually due to the COVID-19 pandemic.
+        Conversely the 2020 meeting was held immediately prior to the institution
+        of lockdowns and other social distancing policies.</p><figure class=\"kg-card
+        kg-image-card kg-width-wide\"><img src=\"https://www.ideasurg.pub/content/images/2023/06/newplot--1-.png\"
+        class=\"kg-image\" alt loading=\"lazy\" width=\"1400\" height=\"800\" srcset=\"https://www.ideasurg.pub/content/images/size/w600/2023/06/newplot--1-.png
+        600w, https://www.ideasurg.pub/content/images/size/w1000/2023/06/newplot--1-.png
+        1000w, https://www.ideasurg.pub/content/images/2023/06/newplot--1-.png 1400w\"
+        sizes=\"(min-width: 1200px) 1200px\"></figure><h3 id=\"alabama-michigan-lead-abstract-acceptances-during-study-period\">Alabama,
+        Michigan lead abstract acceptances during study period</h3><p>Next, we plotted
+        the total number of accepted abstracts by institution. The graph shows data
+        for the twenty leading institutions. The University of Alabama and the University
+        of Michigan lead in abstract acceptances during the study period (477 and
+        348, respectively). Given an eight year time-range, the top twenty institutions
+        reflect an average annual abstract acceptance ranging from roughly thirteen
+        to 60.</p><figure class=\"kg-card kg-image-card kg-width-wide\"><img src=\"https://www.ideasurg.pub/content/images/2023/06/newplot--2-.png\"
+        class=\"kg-image\" alt loading=\"lazy\" width=\"1400\" height=\"800\" srcset=\"https://www.ideasurg.pub/content/images/size/w600/2023/06/newplot--2-.png
+        600w, https://www.ideasurg.pub/content/images/size/w1000/2023/06/newplot--2-.png
+        1000w, https://www.ideasurg.pub/content/images/2023/06/newplot--2-.png 1400w\"
+        sizes=\"(min-width: 1200px) 1200px\"></figure><p>We also plotted the number
+        of accepted abstracts by year using a separate line plot for each individual.
+        While Michigan has maintained between 30 and 60 abstracts for each year, Alabama
+        went from 6 to 48 abstracts between 2016 and 2017 and has maintained greater
+        than 60 accepted abstracts each year. There is a notable dip in the number
+        of accepted abstracts from 2021 to 2022, consistent with a similar trend in
+        the total yearly acceptance data. </p><figure class=\"kg-card kg-image-card
+        kg-width-wide\"><img src=\"https://www.ideasurg.pub/content/images/2023/06/newplot--8-.png\"
+        class=\"kg-image\" alt loading=\"lazy\" width=\"1400\" height=\"800\" srcset=\"https://www.ideasurg.pub/content/images/size/w600/2023/06/newplot--8-.png
+        600w, https://www.ideasurg.pub/content/images/size/w1000/2023/06/newplot--8-.png
+        1000w, https://www.ideasurg.pub/content/images/2023/06/newplot--8-.png 1400w\"
+        sizes=\"(min-width: 1200px) 1200px\"></figure><p>Overall, there appears to
+        be a general clustering of the other eighteen institutions in the top twenty,
+        a trend seen in both the aggregate and the year-to-year data.</p><h3 id=\"mgh-brigham-lead-absolute-and-per-cent-increase-in-abstracts-in-2023\">MGH,
+        Brigham lead absolute and per cent increase in abstracts in 2023</h3><p>Next,
+        we measured the absolute and percent change between accepted abstracts in
+        consecutive years for the top twenty institutions. We restricted our analysis
+        to 2021, 2022, and 2023. The greatest absolute increases in accepted abstracts
+        came from Massachusetts General Hospital in 2023 (27), Brigham and Women''s
+        Hospital in 2023 (16), and UCLA in 2022 (16). The greatest percentage increases
+        in accepted abstracts came from Brigham and Women''s Hospital in 2023 (800%),
+        Johns Hopkins in 2023 (500%), and Massachusetts General Hospital in 2023 (386%).
+        Of note, Johns Hopkins and Brigham and Women''s Hospital also had the largest
+        absolute and percentage decrease in accepted abstracts in 2022. Interestingly,
+        University of Alabama (+4 in 2022, +3 in 2023) and University of Michigan
+        (+11 in 2023) &#xA0;- which rank at the top in all time and yearly abstracts
+        - experienced less extreme swings during the 2021-2023 time period.</p><figure
+        class=\"kg-card kg-image-card kg-width-wide\"><img src=\"https://www.ideasurg.pub/content/images/2023/06/newplot--7-.png\"
+        class=\"kg-image\" alt loading=\"lazy\" width=\"1400\" height=\"800\" srcset=\"https://www.ideasurg.pub/content/images/size/w600/2023/06/newplot--7-.png
+        600w, https://www.ideasurg.pub/content/images/size/w1000/2023/06/newplot--7-.png
+        1000w, https://www.ideasurg.pub/content/images/2023/06/newplot--7-.png 1400w\"
+        sizes=\"(min-width: 1200px) 1200px\"></figure><figure class=\"kg-card kg-image-card
+        kg-width-wide\"><img src=\"https://www.ideasurg.pub/content/images/2023/06/newplot--4-.png\"
+        class=\"kg-image\" alt loading=\"lazy\" width=\"1400\" height=\"800\" srcset=\"https://www.ideasurg.pub/content/images/size/w600/2023/06/newplot--4-.png
+        600w, https://www.ideasurg.pub/content/images/size/w1000/2023/06/newplot--4-.png
+        1000w, https://www.ideasurg.pub/content/images/2023/06/newplot--4-.png 1400w\"
+        sizes=\"(min-width: 1200px) 1200px\"></figure><h3 id=\"conclusions\">Conclusions</h3><p>In
+        this data exploration, we analyzed abstract acceptance data for the Academic
+        Surgical Congress between 2016 and 2023. We showed that the number of abstracts
+        increased from 2016 to 2020, dipped in 2021 and 2022, and is recovering in
+        2023 - likely reflecting the variability forced by COVID19 and the transition
+        to virtual conferences in 2021 and 2022. We also showed that the University
+        of Alabama and the University of Michigan have significantly led accepted
+        abstracts throughout the study period with University of Alabama maintaining
+        a top position following an impressive 700 percent increase in abstracts between
+        2016 and 2017. In 2023, Massachusetts General Hospital and Brigham and Women''s
+        Hospital have led absolute and percent increases in abstract submissions,
+        though this may reflect some degree of reversion following drops in abstract
+        acceptances in 2022.</p><h3 id=\"limitations-and-future-directions\">Limitations
+        and Future Directions</h3><p>This data exploration has several limitations.
+        First, our study is limited to one conference and conferences themselves are
+        only a limited component of academic productivity. However, the Academic Surgical
+        Congress is an international meeting that is well regarded, popular among
+        trainees, and has consistent multi-year data. Another limitation of our study
+        is our assumption that the first institution listed in the author block is
+        the primary institution&#x2013;a method which does not take into account multi-institutional
+        abstracts. However, we suspect this reflects the minority of the abstracts.
+        Finally, we have not fully optimized name-matching to correctly combine terms
+        like \"University of Michigan\" and \"University of Michigan Ann Arbor\".
+        However, given that most of the data currently is only for the top 20 institutions,
+        we believe the overall trends will be preserved.</p><p>In the future, we can
+        attempt to obtain more granular data on authors and institutions and optimize
+        the capture of this data for aggregated analysis. We are also researching
+        different techniques to perform string matching to fix the institution name
+        issue. We can improve the generalizability of our findings by bringing in
+        similar data from other large meetings &#x2013; such as the American College
+        of Surgeons Clinical Congress and the Society of American Gastrointestinal
+        and Endoscopic Surgeons (SAGES). We can also use the PubMed API to perform
+        similar analyses in top surgical journals such as JAMA Surgery or the Annals
+        of Surgery.</p><p>With regards to the data we have obtained, we can conduct
+        survey-based studies or focus groups with key stakeholders from institutions
+        that have demonstrated strong abstract performance during the study period
+        as well as those who have shown significant improvement. By talking to department
+        chairs, program directors, and research and education leaders we can understand
+        what steps each institution took to improve abstract acceptance (e.g. hiring
+        a new research faculty, creating a mentorship program, providing administrative
+        support for IRBs/stats etc.). Following this, we can map individual interventions
+        to improvements to understand the contribution that each can have on increased
+        academic productivity.</p><p>We have also not yet mined the abstract body
+        for themes. Using natural language processing, we can understand how themes
+        and trends of emergent research change from year to year, and even develop
+        models to predict which topics will be of interest in future works. This will
+        likely be the subject of a future data exploration.</p><p>Overall, we hope
+        to demonstrate that abstract acceptance data from a single international meeting
+        can provide interesting, meaningful data on which programs have strong research
+        infrastructure and which programs are making strides to achieve it. By studying
+        this data and improving the inputs, we can better understand whose example
+        to follow and ultimately develop a playbook that all institutions can employ
+        to maximize the academic opportunities of students and trainees.</p><h3 id=\"see-the-data\">See
+        the Data</h3><p>You can see the raw data as well as all of our code here,
+        and use this for your own studies with appropriate attribution.</p><p><a href=\"https://deepnote.com/@tejas-sathe-a73f/ASC-Data-Exploration-948ca211-bfc7-459b-9d6d-ef952a5baf32?ref=ideasurg.pub\">https://deepnote.com/@tejas-sathe-a73f/ASC-Data-Exploration-948ca211-bfc7-459b-9d6d-ef952a5baf32</a></p>","tags":["Pre-Print"],"language":"en","references":[],"blog_id":"3cxcm20","blog":{"id":"3cxcm20","title":"I.D.E.A.S.","description":"Innovation
+        and Design Experiments in Academic Surgery (I.D.E.A.S.)","language":"en","favicon":"https://www.ideasurg.pub/favicon.png","feed_url":"https://www.ideasurg.pub/rss/","home_page_url":"https://www.ideasurg.pub/","user_id":"8498eaf6-8c58-4b58-bc15-27eda292b1aa","created_at":"2023-05-31T13:44:29+00:00","indexed_at":"2023-01-04","feed_format":"application/rss+xml","license":"https://creativecommons.org/licenses/by/4.0/legalcode","generator":"Ghost
+        5.51","category":"Medical and Health Sciences","prefix":"10.59350","modified_at":"2023-06-03T04:54:30+00:00","version":"https://jsonfeed.org/version/1.1","backlog":false}}'
+  recorded_at: Thu, 15 Jun 2023 05:34:55 GMT
+recorded_with: VCR 6.1.0