From 516e5ecd1dbb168bd8213082b883ea3c7cbd154e Mon Sep 17 00:00:00 2001
From: Alan Orth <alan.orth@gmail.com>
Date: Sat, 13 May 2017 13:48:40 +0300
Subject: [PATCH] Add notes for 2017-05-13

---
 content/post/2017-05.md   |  6 ++++++
 public/2017-05/index.html | 14 +++++++++++---
 public/sitemap.xml        | 10 +++++-----
 3 files changed, 22 insertions(+), 8 deletions(-)

diff --git a/content/post/2017-05.md b/content/post/2017-05.md
index 584067be5..8de99f28f 100644
--- a/content/post/2017-05.md
+++ b/content/post/2017-05.md
@@ -126,3 +126,9 @@ $ for item in /home/aorth/10947-1/ITEM@10947-*; do [dspace]/bin/dspace packager
 ```
 dspace=# delete from metadatavalue where resource_type_id=2 and text_value='';
 ```
+
+## 2017-05-13
+
+- After quite a bit of troubleshooting with importing cleaned up data as CSV, it seems that there are actually [NUL](https://en.wikipedia.org/wiki/Null_character) characters in the `dc.description.abstract` field (at least) on the lines where CSV importing was failing
+- I tried to find a way to remove the characters in vim or Open Refine, but decided it was quicker to just remove the column temporarily and import it
+- The import was successful and detected 2022 changes, which should likely be the rest that were failing to import before
diff --git a/public/2017-05/index.html b/public/2017-05/index.html
index 78898707d..461dbf830 100644
--- a/public/2017-05/index.html
+++ b/public/2017-05/index.html
@@ -13,7 +13,7 @@
 
 
 <meta property="article:published_time" content="2017-05-01T16:21:52&#43;02:00"/>
-<meta property="article:modified_time" content="2017-05-10T11:20:27&#43;03:00"/>
+<meta property="article:modified_time" content="2017-05-10T23:44:44&#43;03:00"/>
 
 
 
@@ -45,9 +45,9 @@
   "@type": "BlogPosting",
   "headline": "May, 2017",
   "url": "https://alanorth.github.io/cgspace-notes/2017-05/",
-  "wordCount": "1037",
+  "wordCount": "1122",
   "datePublished": "2017-05-01T16:21:52&#43;02:00",
-  "dateModified": "2017-05-10T11:20:27&#43;03:00",
+  "dateModified": "2017-05-10T23:44:44&#43;03:00",
   "author": {
     "@type": "Person",
     "name": "Alan Orth"
@@ -263,6 +263,14 @@ $ for item in /home/aorth/10947-1/ITEM@10947-*; do [dspace]/bin/dspace packager
 <pre><code>dspace=# delete from metadatavalue where resource_type_id=2 and text_value='';
 </code></pre>
 
+<h2 id="2017-05-13">2017-05-13</h2>
+
+<ul>
+<li>After quite a bit of troubleshooting with importing cleaned up data as CSV, it seems that there are actually <a href="https://en.wikipedia.org/wiki/Null_character">NUL</a> characters in the <code>dc.description.abstract</code> field (at least) on the lines where CSV importing was failing</li>
+<li>I tried to find a way to remove the characters in vim or Open Refine, but decided it was quicker to just remove the column temporarily and import it</li>
+<li>The import was successful and detected 2022 changes, which should likely be the rest that were failing to import before</li>
+</ul>
+
 
   
 
diff --git a/public/sitemap.xml b/public/sitemap.xml
index c79ab2223..3f5b8089f 100644
--- a/public/sitemap.xml
+++ b/public/sitemap.xml
@@ -4,7 +4,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/2017-05/</loc>
-    <lastmod>2017-05-10T11:20:27+03:00</lastmod>
+    <lastmod>2017-05-10T23:44:44+03:00</lastmod>
   </url>
   
   <url>
@@ -99,7 +99,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/</loc>
-    <lastmod>2017-05-10T11:20:27+03:00</lastmod>
+    <lastmod>2017-05-10T23:44:44+03:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -110,19 +110,19 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/notes/</loc>
-    <lastmod>2017-05-10T11:20:27+03:00</lastmod>
+    <lastmod>2017-05-10T23:44:44+03:00</lastmod>
     <priority>0</priority>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/post/</loc>
-    <lastmod>2017-05-10T11:20:27+03:00</lastmod>
+    <lastmod>2017-05-10T23:44:44+03:00</lastmod>
     <priority>0</priority>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/</loc>
-    <lastmod>2017-05-10T11:20:27+03:00</lastmod>
+    <lastmod>2017-05-10T23:44:44+03:00</lastmod>
     <priority>0</priority>
   </url>