Update notes

content/post/2018-02.md

@@ -65,3 +65,21 @@ real    0m23.839s
 user    0m27.225s
 sys     0m1.905s
 ```
+
+## 2018-02-05
+
+- Toying with correcting authors with trailing spaces via PostgreSQL:
+
+```
+dspace=# update metadatavalue set text_value=REGEXP_REPLACE(text_value, '\s+$' , '') where resource_type_id=2 and metadata_field_id=3 and text_value ~ '^.*?\s+$';
+UPDATE 20
+```
+
+- I tried the `TRIM(TRAILING from text_value)` function and it said it changed 20 items but the spaces didn't go away
+- This is on a fresh import of the CGSpace database, but when I tried to apply it on CGSpace there were no changes detected. Weird.
+- Anyways, Peter wants a new list of authors to clean up, so I exported another CSV:
+
+```
+dspace=# \copy (select distinct text_value, count(*) as count from metadatavalue where metadata_field_id = (select metadata_field_id from metadatafieldregistry where element = 'contributor' and qualifier = 'author') AND resource_type_id = 2 group by text_value order by count desc) to /tmp/authors-2018-02-05.csv with csv;
+COPY 55630
+```

public/2018-02/index.html

@@ -23,7 +23,7 @@ I copied the logic in the jmx_tomcat_dbpools provided by Ubuntu’s munin-pl
 
 <meta property="article:published_time" content="2018-02-01T16:28:54&#43;02:00"/>
 
-<meta property="article:modified_time" content="2018-02-04T00:00:51&#43;02:00"/>
+<meta property="article:modified_time" content="2018-02-04T11:26:07&#43;02:00"/>
 
 
 
@@ -57,9 +57,9 @@ I copied the logic in the jmx_tomcat_dbpools provided by Ubuntu&rsquo;s munin-pl
   "@type": "BlogPosting",
   "headline": "February, 2018",
   "url": "https://alanorth.github.io/cgspace-notes/2018-02/",
-  "wordCount": "328",
+  "wordCount": "459",
   "datePublished": "2018-02-01T16:28:54&#43;02:00",
-  "dateModified": "2018-02-04T00:00:51&#43;02:00",
+  "dateModified": "2018-02-04T11:26:07&#43;02:00",
   "author": {
     "@type": "Person",
     "name": "Alan Orth"
@@ -195,6 +195,26 @@ user    0m27.225s
 sys     0m1.905s
 </code></pre>
 
+<h2 id="2018-02-05">2018-02-05</h2>
+
+<ul>
+<li>Toying with correcting authors with trailing spaces via PostgreSQL:</li>
+</ul>
+
+<pre><code>dspace=# update metadatavalue set text_value=REGEXP_REPLACE(text_value, '\s+$' , '') where resource_type_id=2 and metadata_field_id=3 and text_value ~ '^.*?\s+$';
+UPDATE 20
+</code></pre>
+
+<ul>
+<li>I tried the <code>TRIM(TRAILING from text_value)</code> function and it said it changed 20 items but the spaces didn&rsquo;t go away</li>
+<li>This is on a fresh import of the CGSpace database, but when I tried to apply it on CGSpace there were no changes detected. Weird.</li>
+<li>Anyways, Peter wants a new list of authors to clean up, so I exported another CSV:</li>
+</ul>
+
+<pre><code>dspace=# \copy (select distinct text_value, count(*) as count from metadatavalue where metadata_field_id = (select metadata_field_id from metadatafieldregistry where element = 'contributor' and qualifier = 'author') AND resource_type_id = 2 group by text_value order by count desc) to /tmp/authors-2018-02-05.csv with csv;
+COPY 55630
+</code></pre>
+
   
 
   

public/sitemap.xml

@@ -4,7 +4,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/2018-02/</loc>
-    <lastmod>2018-02-04T00:00:51+02:00</lastmod>
+    <lastmod>2018-02-04T11:26:07+02:00</lastmod>
   </url>
   
   <url>
@@ -149,7 +149,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/</loc>
-    <lastmod>2018-02-04T00:00:51+02:00</lastmod>
+    <lastmod>2018-02-04T11:26:07+02:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -160,7 +160,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/notes/</loc>
-    <lastmod>2018-02-04T00:00:51+02:00</lastmod>
+    <lastmod>2018-02-04T11:26:07+02:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -172,13 +172,13 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/post/</loc>
-    <lastmod>2018-02-04T00:00:51+02:00</lastmod>
+    <lastmod>2018-02-04T11:26:07+02:00</lastmod>
     <priority>0</priority>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/</loc>
-    <lastmod>2018-02-04T00:00:51+02:00</lastmod>
+    <lastmod>2018-02-04T11:26:07+02:00</lastmod>
     <priority>0</priority>
   </url>