From 164748b5d2e6d3a2e29b74621be7692ad4fc451b Mon Sep 17 00:00:00 2001
From: Alan Orth <alan.orth@gmail.com>
Date: Fri, 29 Dec 2017 18:45:09 +0200
Subject: [PATCH] Add notes for 2017-12-29

---
 content/post/2017-12.md   | 27 +++++++++++++++++++++++++++
 public/2017-12/index.html | 36 +++++++++++++++++++++++++++++++++---
 public/robots.txt         |  2 +-
 public/sitemap.xml        | 20 ++++++++++----------
 4 files changed, 71 insertions(+), 14 deletions(-)

diff --git a/content/post/2017-12.md b/content/post/2017-12.md
index ed41982d9..759d2f2db 100644
--- a/content/post/2017-12.md
+++ b/content/post/2017-12.md
@@ -672,3 +672,30 @@ $ schedtool -D -e ionice -c2 -n7 nice -n19 dspace filter-media -i 10568/89287
 - Here are the Munin stats for the past week on CGSpace:
 
 ![CGSpace PostgreSQL connections week](/cgspace-notes/2017/12/postgres-connections-cgspace.png)
+
+## 2017-12-29
+
+- Looking at some old notes for metadata to clean up, I found a few hundred corrections in `cg.fulltextstatus` and `dc.language.iso`:
+
+```
+# update metadatavalue set text_value='Formally Published' where resource_type_id=2 and metadata_field_id=214 and text_value like 'Formally published';
+UPDATE 5
+# delete from metadatavalue where resource_type_id=2 and metadata_field_id=214 and text_value like 'NO';
+DELETE 17
+# update metadatavalue set text_value='en' where resource_type_id=2 and metadata_field_id=38 and text_value ~ '(En|English)';
+UPDATE 49
+# update metadatavalue set text_value='fr' where resource_type_id=2 and metadata_field_id=38 and text_value ~ '(fre|frn|French)';
+UPDATE 4
+# update metadatavalue set text_value='es' where resource_type_id=2 and metadata_field_id=38 and text_value ~ '(Spanish|spa)';
+UPDATE 16
+# update metadatavalue set text_value='vi' where resource_type_id=2 and metadata_field_id=38 and text_value='Vietnamese';
+UPDATE 9
+# update metadatavalue set text_value='ru' where resource_type_id=2 and metadata_field_id=38 and text_value='Ru';
+UPDATE 1
+# update metadatavalue set text_value='in' where resource_type_id=2 and metadata_field_id=38 and text_value ~ '(IN|In)';
+UPDATE 5
+# delete from metadatavalue where resource_type_id=2 and metadata_field_id=38 and text_value ~ '(dc.language.iso|CGIAR Challenge Program on Water and Food)';
+DELETE 20
+```
+
+- I need to figure out why we have records with language `in` because that's not a language!
diff --git a/public/2017-12/index.html b/public/2017-12/index.html
index 46532fc2f..e4b557d96 100644
--- a/public/2017-12/index.html
+++ b/public/2017-12/index.html
@@ -23,7 +23,7 @@ The list of connections to XMLUI and REST API for today:
 
 <meta property="article:published_time" content="2017-12-01T13:53:54&#43;03:00"/>
 
-<meta property="article:modified_time" content="2017-12-24T13:59:25&#43;02:00"/>
+<meta property="article:modified_time" content="2017-12-25T22:26:01&#43;02:00"/>
 
 
 
@@ -56,9 +56,9 @@ The list of connections to XMLUI and REST API for today:
   "@type": "BlogPosting",
   "headline": "December, 2017",
   "url": "https://alanorth.github.io/cgspace-notes/2017-12/",
-  "wordCount": "3722",
+  "wordCount": "3897",
   "datePublished": "2017-12-01T13:53:54&#43;03:00",
-  "dateModified": "2017-12-24T13:59:25&#43;02:00",
+  "dateModified": "2017-12-25T22:26:01&#43;02:00",
   "author": {
     "@type": "Person",
     "name": "Alan Orth"
@@ -874,6 +874,36 @@ $ schedtool -D -e ionice -c2 -n7 nice -n19 dspace filter-media -i 10568/89287
 
 <p><img src="/cgspace-notes/2017/12/postgres-connections-cgspace.png" alt="CGSpace PostgreSQL connections week" /></p>
 
+<h2 id="2017-12-29">2017-12-29</h2>
+
+<ul>
+<li>Looking at some old notes for metadata to clean up, I found a few hundred corrections in <code>cg.fulltextstatus</code> and <code>dc.language.iso</code>:</li>
+</ul>
+
+<pre><code># update metadatavalue set text_value='Formally Published' where resource_type_id=2 and metadata_field_id=214 and text_value like 'Formally published';
+UPDATE 5
+# delete from metadatavalue where resource_type_id=2 and metadata_field_id=214 and text_value like 'NO';
+DELETE 17
+# update metadatavalue set text_value='en' where resource_type_id=2 and metadata_field_id=38 and text_value ~ '(En|English)';
+UPDATE 49
+# update metadatavalue set text_value='fr' where resource_type_id=2 and metadata_field_id=38 and text_value ~ '(fre|frn|French)';
+UPDATE 4
+# update metadatavalue set text_value='es' where resource_type_id=2 and metadata_field_id=38 and text_value ~ '(Spanish|spa)';
+UPDATE 16
+# update metadatavalue set text_value='vi' where resource_type_id=2 and metadata_field_id=38 and text_value='Vietnamese';
+UPDATE 9
+# update metadatavalue set text_value='ru' where resource_type_id=2 and metadata_field_id=38 and text_value='Ru';
+UPDATE 1
+# update metadatavalue set text_value='in' where resource_type_id=2 and metadata_field_id=38 and text_value ~ '(IN|In)';
+UPDATE 5
+# delete from metadatavalue where resource_type_id=2 and metadata_field_id=38 and text_value ~ '(dc.language.iso|CGIAR Challenge Program on Water and Food)';
+DELETE 20
+</code></pre>
+
+<ul>
+<li>I need to figure out why we have records with language <code>in</code> because that&rsquo;s not a language!</li>
+</ul>
+
   
 
   
diff --git a/public/robots.txt b/public/robots.txt
index 7c86be3fe..d2ae9994d 100644
--- a/public/robots.txt
+++ b/public/robots.txt
@@ -30,7 +30,7 @@ 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/post/
 Disallow: /cgspace-notes/tags/
diff --git a/public/sitemap.xml b/public/sitemap.xml
index cfad2e45d..47e0d9015 100644
--- a/public/sitemap.xml
+++ b/public/sitemap.xml
@@ -4,7 +4,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/2017-12/</loc>
-    <lastmod>2017-12-24T13:59:25+02:00</lastmod>
+    <lastmod>2017-12-25T22:26:01+02:00</lastmod>
   </url>
   
   <url>
@@ -139,7 +139,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/</loc>
-    <lastmod>2017-12-24T13:59:25+02:00</lastmod>
+    <lastmod>2017-12-25T22:26:01+02:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -148,27 +148,27 @@
     <priority>0</priority>
   </url>
   
+  <url>
+    <loc>https://alanorth.github.io/cgspace-notes/tags/notes/</loc>
+    <lastmod>2017-12-25T22:26:01+02:00</lastmod>
+    <priority>0</priority>
+  </url>
+  
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/categories/notes/</loc>
     <lastmod>2017-09-28T12:00:49+03:00</lastmod>
     <priority>0</priority>
   </url>
   
-  <url>
-    <loc>https://alanorth.github.io/cgspace-notes/tags/notes/</loc>
-    <lastmod>2017-12-24T13:59:25+02:00</lastmod>
-    <priority>0</priority>
-  </url>
-  
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/post/</loc>
-    <lastmod>2017-12-24T13:59:25+02:00</lastmod>
+    <lastmod>2017-12-25T22:26:01+02:00</lastmod>
     <priority>0</priority>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/</loc>
-    <lastmod>2017-12-24T13:59:25+02:00</lastmod>
+    <lastmod>2017-12-25T22:26:01+02:00</lastmod>
     <priority>0</priority>
   </url>