From da85011fae50053c5e835eef0e94ab397712e811 Mon Sep 17 00:00:00 2001
From: Alan Orth <alan.orth@gmail.com>
Date: Sun, 10 Jun 2018 19:32:12 +0300
Subject: [PATCH] Update notes for 2018-06-10

---
 content/posts/2018-06.md | 13 +++++++++++++
 docs/2018-06/index.html  | 22 +++++++++++++++++++---
 docs/sitemap.xml         | 10 +++++-----
 3 files changed, 37 insertions(+), 8 deletions(-)

diff --git a/content/posts/2018-06.md b/content/posts/2018-06.md
index a34241fbe..627358944 100644
--- a/content/posts/2018-06.md
+++ b/content/posts/2018-06.md
@@ -92,3 +92,16 @@ Failed to startup the DSpace Service Manager: failure starting up spring service
 
 - I can fix this by commenting out the `ItemCollectionPlugin` line of `discovery.xml`, but from looking at the git log I'm not actually sure if that is related to MQM or not
 - I will have to ask Atmire
+- I continued to look at Sisay's IITA records from last week
+  - I normalized all DOIs to use HTTPS and "doi.org" instead of "dx.doi.org"
+  - I cleaned up white space in `cg.subject.iita` and `dc.subject`
+  - Even a bunch of IITA and AGROVOC subjects are missing accents, ie "FERTILIT DU SOL"
+  - More organization names in `dc.description.sponsorship` are incorrect (ie, missing accents) or inconsistent (ie, CGIAR centers should be spelled in English or multiple spellings of the same one, like "Rockefeller Foundation" and "Rockefeller foundation")
+  - A few dozen items have abstracts with character encoding errors, ie:
+    - 33.7øC
+    - MgSO4ú7H2O
+    - ha??1&/sup;
+    - En gen6ral
+    - dÕpassÕ
+  - Also the abstracts have missing accents, ie "recherche sur le d veloppement"
+- I will have to tell IITA people to redo these entirely I think...
diff --git a/docs/2018-06/index.html b/docs/2018-06/index.html
index 2b08fa229..e43e643b0 100644
--- a/docs/2018-06/index.html
+++ b/docs/2018-06/index.html
@@ -41,7 +41,7 @@ sys     2m7.289s
 
 <meta property="article:published_time" content="2018-06-04T19:49:54-07:00"/>
 
-<meta property="article:modified_time" content="2018-06-09T11:48:41&#43;03:00"/>
+<meta property="article:modified_time" content="2018-06-10T14:12:07&#43;03:00"/>
 
 
 
@@ -93,9 +93,9 @@ sys     2m7.289s
   "@type": "BlogPosting",
   "headline": "June, 2018",
   "url": "https://alanorth.github.io/cgspace-notes/2018-06/",
-  "wordCount": "628",
+  "wordCount": "750",
   "datePublished": "2018-06-04T19:49:54-07:00",
-  "dateModified": "2018-06-09T11:48:41&#43;03:00",
+  "dateModified": "2018-06-10T14:12:07&#43;03:00",
   "author": {
     "@type": "Person",
     "name": "Alan Orth"
@@ -267,6 +267,22 @@ Failed to startup the DSpace Service Manager: failure starting up spring service
 <ul>
 <li>I can fix this by commenting out the <code>ItemCollectionPlugin</code> line of <code>discovery.xml</code>, but from looking at the git log I&rsquo;m not actually sure if that is related to MQM or not</li>
 <li>I will have to ask Atmire</li>
+<li>I continued to look at Sisay&rsquo;s IITA records from last week
+
+<ul>
+<li>I normalized all DOIs to use HTTPS and &ldquo;doi.org&rdquo; instead of &ldquo;dx.doi.org&rdquo;</li>
+<li>I cleaned up white space in <code>cg.subject.iita</code> and <code>dc.subject</code></li>
+<li>Even a bunch of IITA and AGROVOC subjects are missing accents, ie &ldquo;FERTILIT DU SOL&rdquo;</li>
+<li>More organization names in <code>dc.description.sponsorship</code> are incorrect (ie, missing accents) or inconsistent (ie, CGIAR centers should be spelled in English or multiple spellings of the same one, like &ldquo;Rockefeller Foundation&rdquo; and &ldquo;Rockefeller foundation&rdquo;)</li>
+<li>A few dozen items have abstracts with character encoding errors, ie:</li>
+<li>33.7øC</li>
+<li>MgSO4ú7H2O</li>
+<li>ha??1&amp;/sup;</li>
+<li>En gen6ral</li>
+<li>dÕpassÕ</li>
+<li>Also the abstracts have missing accents, ie &ldquo;recherche sur le d veloppement&rdquo;</li>
+</ul></li>
+<li>I will have to tell IITA people to redo these entirely I think&hellip;</li>
 </ul>
 
   
diff --git a/docs/sitemap.xml b/docs/sitemap.xml
index 9d7ec4e93..998a2873f 100644
--- a/docs/sitemap.xml
+++ b/docs/sitemap.xml
@@ -4,7 +4,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/2018-06/</loc>
-    <lastmod>2018-06-09T11:48:41+03:00</lastmod>
+    <lastmod>2018-06-10T14:12:07+03:00</lastmod>
   </url>
   
   <url>
@@ -169,7 +169,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/</loc>
-    <lastmod>2018-06-09T11:48:41+03:00</lastmod>
+    <lastmod>2018-06-10T14:12:07+03:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -180,7 +180,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/notes/</loc>
-    <lastmod>2018-06-09T11:48:41+03:00</lastmod>
+    <lastmod>2018-06-10T14:12:07+03:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -192,13 +192,13 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/posts/</loc>
-    <lastmod>2018-06-09T11:48:41+03:00</lastmod>
+    <lastmod>2018-06-10T14:12:07+03:00</lastmod>
     <priority>0</priority>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/</loc>
-    <lastmod>2018-06-09T11:48:41+03:00</lastmod>
+    <lastmod>2018-06-10T14:12:07+03:00</lastmod>
     <priority>0</priority>
   </url>