From 33cb0325c12ccd188ed4c2eea96738397f92a9a3 Mon Sep 17 00:00:00 2001
From: Alan Orth <alan.orth@gmail.com>
Date: Mon, 18 Mar 2019 21:55:08 +0200
Subject: [PATCH] Update notes for 2019-03-18

---
 content/posts/2019-03.md |  8 ++++----
 docs/2019-03/index.html  | 14 +++++++-------
 docs/robots.txt          |  2 +-
 docs/sitemap.xml         | 20 ++++++++++----------
 4 files changed, 22 insertions(+), 22 deletions(-)

diff --git a/content/posts/2019-03.md b/content/posts/2019-03.md
index a49f780f2..43ccdfa91 100644
--- a/content/posts/2019-03.md
+++ b/content/posts/2019-03.md
@@ -356,15 +356,15 @@ $ ./agrovoc-lookup.py -l es -i 2019-03-18-top-1500-subject.csv -om /tmp/es-subje
 $ ./agrovoc-lookup.py -l fr -i 2019-03-18-top-1500-subject.csv -om /tmp/fr-subjects-matched.txt -or /tmp/fr-subjects-unmatched.txt
 $ cat /tmp/*-subjects-matched.txt | sort -u > /tmp/subjects-matched-sorted.txt
 $ wc -l /tmp/subjects-matched-sorted.txt                                                              
-1317 /tmp/subjects-matched-sorted.txt
+1318 /tmp/subjects-matched-sorted.txt
 $ sort -u 2019-03-18-top-1500-subject.csv > /tmp/1500-subjects-sorted.txt
-$ comm -13 /tmp/subjects-matched-sorted.txt /tmp/1500-subjects-sorted.txt > 2019-03-18-subjects-unmatch
-ed.txt
+$ comm -13 /tmp/subjects-matched-sorted.txt /tmp/1500-subjects-sorted.txt > 2019-03-18-subjects-unmatched.txt
 $ wc -l 2019-03-18-subjects-unmatched.txt
-183 2019-03-18-subjects-unmatched.txt
+182 2019-03-18-subjects-unmatched.txt
 ```
 
 - So the new total of matched terms with the updated regex is 1317 and unmatched is 183 (previous number of matched terms was 1187)
+- Create and merge a pull request to update the controlled vocabulary for AGROVOC terms ([#416](https://github.com/ilri/DSpace/pull/416))
 - We are getting the blank page issue on CGSpace again today and I see a ~~large number~~ of the "SQL QueryTable Error" in the DSpace log again (last time was 2019-03-15):
 
 ```
diff --git a/docs/2019-03/index.html b/docs/2019-03/index.html
index e002695f9..6f1c8b33b 100644
--- a/docs/2019-03/index.html
+++ b/docs/2019-03/index.html
@@ -25,7 +25,7 @@ I think I will need to ask Udana to re-copy and paste the abstracts with more ca
 <meta property="og:type" content="article" />
 <meta property="og:url" content="https://alanorth.github.io/cgspace-notes/2019-03/" />
 <meta property="article:published_time" content="2019-03-01T12:16:30&#43;01:00"/>
-<meta property="article:modified_time" content="2019-03-17T22:24:02&#43;02:00"/>
+<meta property="article:modified_time" content="2019-03-18T15:32:22&#43;02:00"/>
 
 <meta name="twitter:card" content="summary"/>
 <meta name="twitter:title" content="March, 2019"/>
@@ -55,9 +55,9 @@ I think I will need to ask Udana to re-copy and paste the abstracts with more ca
   "@type": "BlogPosting",
   "headline": "March, 2019",
   "url": "https://alanorth.github.io/cgspace-notes/2019-03/",
-  "wordCount": "2959",
+  "wordCount": "2973",
   "datePublished": "2019-03-01T12:16:30&#43;01:00",
-  "dateModified": "2019-03-17T22:24:02&#43;02:00",
+  "dateModified": "2019-03-18T15:32:22&#43;02:00",
   "author": {
     "@type": "Person",
     "name": "Alan Orth"
@@ -547,16 +547,16 @@ $ ./agrovoc-lookup.py -l es -i 2019-03-18-top-1500-subject.csv -om /tmp/es-subje
 $ ./agrovoc-lookup.py -l fr -i 2019-03-18-top-1500-subject.csv -om /tmp/fr-subjects-matched.txt -or /tmp/fr-subjects-unmatched.txt
 $ cat /tmp/*-subjects-matched.txt | sort -u &gt; /tmp/subjects-matched-sorted.txt
 $ wc -l /tmp/subjects-matched-sorted.txt                                                              
-1317 /tmp/subjects-matched-sorted.txt
+1318 /tmp/subjects-matched-sorted.txt
 $ sort -u 2019-03-18-top-1500-subject.csv &gt; /tmp/1500-subjects-sorted.txt
-$ comm -13 /tmp/subjects-matched-sorted.txt /tmp/1500-subjects-sorted.txt &gt; 2019-03-18-subjects-unmatch
-ed.txt
+$ comm -13 /tmp/subjects-matched-sorted.txt /tmp/1500-subjects-sorted.txt &gt; 2019-03-18-subjects-unmatched.txt
 $ wc -l 2019-03-18-subjects-unmatched.txt
-183 2019-03-18-subjects-unmatched.txt
+182 2019-03-18-subjects-unmatched.txt
 </code></pre>
 
 <ul>
 <li>So the new total of matched terms with the updated regex is 1317 and unmatched is 183 (previous number of matched terms was 1187)</li>
+<li>Create and merge a pull request to update the controlled vocabulary for AGROVOC terms (<a href="https://github.com/ilri/DSpace/pull/416">#416</a>)</li>
 <li>We are getting the blank page issue on CGSpace again today and I see a <del>large number</del> of the &ldquo;SQL QueryTable Error&rdquo; in the DSpace log again (last time was 2019-03-15):</li>
 </ul>
 
diff --git a/docs/robots.txt b/docs/robots.txt
index 9c8f41429..2b88ae317 100644
--- a/docs/robots.txt
+++ b/docs/robots.txt
@@ -45,7 +45,7 @@ Disallow: /cgspace-notes/2015-12/
 Disallow: /cgspace-notes/2015-11/
 Disallow: /cgspace-notes/
 Disallow: /cgspace-notes/categories/
-Disallow: /cgspace-notes/tags/notes/
 Disallow: /cgspace-notes/categories/notes/
+Disallow: /cgspace-notes/tags/notes/
 Disallow: /cgspace-notes/posts/
 Disallow: /cgspace-notes/tags/
diff --git a/docs/sitemap.xml b/docs/sitemap.xml
index 8d20443c6..b4f5b8cb9 100644
--- a/docs/sitemap.xml
+++ b/docs/sitemap.xml
@@ -4,7 +4,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/2019-03/</loc>
-    <lastmod>2019-03-17T22:24:02+02:00</lastmod>
+    <lastmod>2019-03-18T15:32:22+02:00</lastmod>
   </url>
   
   <url>
@@ -214,7 +214,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/</loc>
-    <lastmod>2019-03-17T22:24:02+02:00</lastmod>
+    <lastmod>2019-03-18T15:32:22+02:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -223,27 +223,27 @@
     <priority>0</priority>
   </url>
   
-  <url>
-    <loc>https://alanorth.github.io/cgspace-notes/tags/notes/</loc>
-    <lastmod>2019-03-17T22:24:02+02:00</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>2019-03-18T15:32:22+02:00</lastmod>
+    <priority>0</priority>
+  </url>
+  
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/posts/</loc>
-    <lastmod>2019-03-17T22:24:02+02:00</lastmod>
+    <lastmod>2019-03-18T15:32:22+02:00</lastmod>
     <priority>0</priority>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/</loc>
-    <lastmod>2019-03-17T22:24:02+02:00</lastmod>
+    <lastmod>2019-03-18T15:32:22+02:00</lastmod>
     <priority>0</priority>
   </url>