Update notes for 2018-07-12

content/posts/2018-07.md

@@ -314,5 +314,15 @@ $ grep -c -E 'session_id=[A-Z0-9]{32}:ip_addr=95.108.181.88' dspace.log.2018-07-
 
 - So this bot is just like Baiduspider, and I need to add it to the nginx rate limiting
 - I'll also add it to Tomcat's Crawler Session Manager Valve to force the re-use of a common Tomcat sesssion for all crawlers just in case
+- Generate a list of all affiliations in CGSpace to send to Mohamed Salem to compare with the list on MEL (sorting the list by most occurrences):
+
+```
+dspace=# \copy (select distinct text_value, count(*) as count from metadatavalue where resource_type_id=2 and metadata_field_id=211 group by text_value order by count desc) to /tmp/affiliations.csv with csv header
+COPY 4518
+dspace=# \q
+$ csvcut -c 1 < /tmp/affiliations.csv > /tmp/affiliations-1.csv
+```
+
+- We also need to discuss standardizing our countries and comparing our ORCID iDs
 
 <!-- vim: set sw=2 ts=2: -->

docs/2018-07/index.html

@@ -30,7 +30,7 @@ There is insufficient memory for the Java Runtime Environment to continue.
 
 <meta property="article:published_time" content="2018-07-01T12:56:54&#43;03:00"/>
 
-<meta property="article:modified_time" content="2018-07-12T08:35:39&#43;03:00"/>
+<meta property="article:modified_time" content="2018-07-12T09:00:08&#43;03:00"/>
 
 
 
@@ -71,9 +71,9 @@ There is insufficient memory for the Java Runtime Environment to continue.
   "@type": "BlogPosting",
   "headline": "July, 2018",
   "url": "https://alanorth.github.io/cgspace-notes/2018-07/",
-  "wordCount": "2079",
+  "wordCount": "2156",
   "datePublished": "2018-07-01T12:56:54&#43;03:00",
-  "dateModified": "2018-07-12T08:35:39&#43;03:00",
+  "dateModified": "2018-07-12T09:00:08&#43;03:00",
   "author": {
     "@type": "Person",
     "name": "Alan Orth"
@@ -493,6 +493,17 @@ org.apache.solr.client.solrj.SolrServerException: IOException occured when talki
 <ul>
 <li>So this bot is just like Baiduspider, and I need to add it to the nginx rate limiting</li>
 <li>I&rsquo;ll also add it to Tomcat&rsquo;s Crawler Session Manager Valve to force the re-use of a common Tomcat sesssion for all crawlers just in case</li>
+<li>Generate a list of all affiliations in CGSpace to send to Mohamed Salem to compare with the list on MEL (sorting the list by most occurrences):</li>
+</ul>
+
+<pre><code>dspace=# \copy (select distinct text_value, count(*) as count from metadatavalue where resource_type_id=2 and metadata_field_id=211 group by text_value order by count desc) to /tmp/affiliations.csv with csv header
+COPY 4518
+dspace=# \q
+$ csvcut -c 1 &lt; /tmp/affiliations.csv &gt; /tmp/affiliations-1.csv
+</code></pre>
+
+<ul>
+<li>We also need to discuss standardizing our countries and comparing our ORCID iDs</li>
 </ul>
 
 <!-- vim: set sw=2 ts=2: -->

docs/robots.txt

@@ -37,7 +37,7 @@ Disallow: /cgspace-notes/2015-12/
 Disallow: /cgspace-notes/2015-11/
 Disallow: /cgspace-notes/
 Disallow: /cgspace-notes/categories/
-Disallow: /cgspace-notes/categories/notes/
 Disallow: /cgspace-notes/tags/notes/
+Disallow: /cgspace-notes/categories/notes/
 Disallow: /cgspace-notes/posts/
 Disallow: /cgspace-notes/tags/

docs/sitemap.xml

@@ -4,7 +4,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/2018-07/</loc>
-    <lastmod>2018-07-12T08:35:39+03:00</lastmod>
+    <lastmod>2018-07-12T09:00:08+03:00</lastmod>
   </url>
   
   <url>
@@ -174,7 +174,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/</loc>
-    <lastmod>2018-07-12T08:35:39+03:00</lastmod>
+    <lastmod>2018-07-12T09:00:08+03:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -183,27 +183,27 @@
     <priority>0</priority>
   </url>
   
+  <url>
+    <loc>https://alanorth.github.io/cgspace-notes/tags/notes/</loc>
+    <lastmod>2018-07-12T09:00:08+03:00</lastmod>
+    <priority>0</priority>
+  </url>
+  
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/categories/notes/</loc>
     <lastmod>2018-03-09T22:10:33+02:00</lastmod>
     <priority>0</priority>
   </url>
   
-  <url>
-    <loc>https://alanorth.github.io/cgspace-notes/tags/notes/</loc>
-    <lastmod>2018-07-12T08:35:39+03:00</lastmod>
-    <priority>0</priority>
-  </url>
-  
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/posts/</loc>
-    <lastmod>2018-07-12T08:35:39+03:00</lastmod>
+    <lastmod>2018-07-12T09:00:08+03:00</lastmod>
     <priority>0</priority>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/</loc>
-    <lastmod>2018-07-12T08:35:39+03:00</lastmod>
+    <lastmod>2018-07-12T09:00:08+03:00</lastmod>
     <priority>0</priority>
   </url>