From 28ab384194646b31f0d0568d38341dae100a2c5e Mon Sep 17 00:00:00 2001
From: Alan Orth <alan.orth@gmail.com>
Date: Tue, 4 Sep 2018 13:25:13 +0300
Subject: [PATCH] Add notes for 2018-09-04

---
 content/posts/2018-09.md |  8 ++++++++
 docs/2018-09/index.html  | 19 ++++++++++++++++---
 docs/sitemap.xml         | 10 +++++-----
 3 files changed, 29 insertions(+), 8 deletions(-)

diff --git a/content/posts/2018-09.md b/content/posts/2018-09.md
index f420d1837..9e81e2581 100644
--- a/content/posts/2018-09.md
+++ b/content/posts/2018-09.md
@@ -49,4 +49,12 @@ Caused by: java.lang.RuntimeException: Failed to startup the DSpace Service Mana
 - She will try to click the "Unsubscribe" link in the first two to see if it works, otherwise we should contact Atmire
 - The only one she remembers subscribing to is the top downloads one
 
+## 2018-09-04
+
+- I'm looking over the latest round of IITA records from Sisay: [Mercy1806_August_29](https://dspacetest.cgiar.org/handle/10568/104230)
+  - All fields are split with multiple columns like `cg.authorship.types` and `cg.authorship.types[]`
+  - This makes it super annoying to do the checks and cleanup, so I will merge them (also time consuming)
+  - Five issue dates had values like `2013-5` so I corrected them to be `2013-05`
+  - Several metadata fields had values with newlines in them (even in some titles!), which I fixed by trimming the consecutive whitespaces in Open Refine
+
 <!-- vim: set sw=2 ts=2: -->
diff --git a/docs/2018-09/index.html b/docs/2018-09/index.html
index db43112cd..cf86cefaa 100644
--- a/docs/2018-09/index.html
+++ b/docs/2018-09/index.html
@@ -18,7 +18,7 @@ I&rsquo;m testing the new DSpace 5.8 branch in my Ubuntu 18.04 environment and I
 " />
 <meta property="og:type" content="article" />
 <meta property="og:url" content="https://alanorth.github.io/cgspace-notes/2018-09/" /><meta property="article:published_time" content="2018-09-02T09:55:54&#43;03:00"/>
-<meta property="article:modified_time" content="2018-09-02T17:37:18&#43;03:00"/>
+<meta property="article:modified_time" content="2018-09-03T16:47:24&#43;03:00"/>
 <meta name="twitter:card" content="summary"/>
 <meta name="twitter:title" content="September, 2018"/>
 <meta name="twitter:description" content="2018-09-02
@@ -41,9 +41,9 @@ I&rsquo;m testing the new DSpace 5.8 branch in my Ubuntu 18.04 environment and I
   "@type": "BlogPosting",
   "headline": "September, 2018",
   "url": "https://alanorth.github.io/cgspace-notes/2018-09/",
-  "wordCount": "457",
+  "wordCount": "538",
   "datePublished": "2018-09-02T09:55:54&#43;03:00",
-  "dateModified": "2018-09-02T17:37:18&#43;03:00",
+  "dateModified": "2018-09-03T16:47:24&#43;03:00",
   "author": {
     "@type": "Person",
     "name": "Alan Orth"
@@ -158,6 +158,19 @@ Caused by: java.lang.RuntimeException: Failed to startup the DSpace Service Mana
 <li>The only one she remembers subscribing to is the top downloads one</li>
 </ul>
 
+<h2 id="2018-09-04">2018-09-04</h2>
+
+<ul>
+<li>I&rsquo;m looking over the latest round of IITA records from Sisay: <a href="https://dspacetest.cgiar.org/handle/10568/104230">Mercy1806_August_29</a>
+
+<ul>
+<li>All fields are split with multiple columns like <code>cg.authorship.types</code> and <code>cg.authorship.types[]</code></li>
+<li>This makes it super annoying to do the checks and cleanup, so I will merge them (also time consuming)</li>
+<li>Five issue dates had values like <code>2013-5</code> so I corrected them to be <code>2013-05</code></li>
+<li>Several metadata fields had values with newlines in them (even in some titles!), which I fixed by trimming the consecutive whitespaces in Open Refine</li>
+</ul></li>
+</ul>
+
 <!-- vim: set sw=2 ts=2: -->
 
   
diff --git a/docs/sitemap.xml b/docs/sitemap.xml
index fef9aeb3d..b71ab02d5 100644
--- a/docs/sitemap.xml
+++ b/docs/sitemap.xml
@@ -4,7 +4,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/2018-09/</loc>
-    <lastmod>2018-09-02T17:37:18+03:00</lastmod>
+    <lastmod>2018-09-03T16:47:24+03:00</lastmod>
   </url>
   
   <url>
@@ -184,7 +184,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/</loc>
-    <lastmod>2018-09-02T17:37:18+03:00</lastmod>
+    <lastmod>2018-09-03T16:47:24+03:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -195,7 +195,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/notes/</loc>
-    <lastmod>2018-09-02T17:37:18+03:00</lastmod>
+    <lastmod>2018-09-03T16:47:24+03:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -207,13 +207,13 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/posts/</loc>
-    <lastmod>2018-09-02T17:37:18+03:00</lastmod>
+    <lastmod>2018-09-03T16:47:24+03:00</lastmod>
     <priority>0</priority>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/</loc>
-    <lastmod>2018-09-02T17:37:18+03:00</lastmod>
+    <lastmod>2018-09-03T16:47:24+03:00</lastmod>
     <priority>0</priority>
   </url>