From 226a940ff34ea61838c056927729110d277a258d Mon Sep 17 00:00:00 2001
From: Alan Orth <alan.orth@gmail.com>
Date: Sun, 17 Dec 2017 10:56:56 +0200
Subject: [PATCH] Update notes for 2017-12-17

---
 content/post/2017-12.md   | 10 ++++++++++
 public/2017-11/index.html |  6 +++---
 public/2017-12/index.html | 19 ++++++++++++++++---
 public/sitemap.xml        | 12 ++++++------
 4 files changed, 35 insertions(+), 12 deletions(-)

diff --git a/content/post/2017-12.md b/content/post/2017-12.md
index f3f50c633..d67da8ec9 100644
--- a/content/post/2017-12.md
+++ b/content/post/2017-12.md
@@ -193,3 +193,13 @@ UPDATE 1
 ## 2017-12-17
 
 - Reboot DSpace Test to get new Linode Linux kernel
+- Looking at CCAFS bulk import for Magdalena Haman (she originally sent them in November but some of the thumbnails were missing and dates were messed up so she resent them now)
+- A few issues with the data and thumbnails:
+  - Her thumbnail files all use capital JPG so I had to rename them to lowercase: `rename -fc *.JPG`
+  - thumbnail20.jpg is 1.7MB so I have to resize it
+  - I also had to add the .jpg to the thumbnail string in the CSV
+  - The thumbnail11.jpg is missing
+  - The dates are in super long ISO8601 format (from Excel?) like `2016-02-07T00:00:00Z` so I converted them to simpler forms in GREL: `value.toString("yyyy-MM-dd")`
+  - I trimmed the whitespaces in a few fields but it wasn't many
+  - Rename her thumbnail column to filename, and format it so SAFBuilder adds the files to the thumbnail bundle with this GREL in OpenRefine: `value + "__bundle:THUMBNAIL"`
+  - I will send her feedback on some author names like UNEP and ICRISAT and ask her for the missing thumbnail11.jpg
diff --git a/public/2017-11/index.html b/public/2017-11/index.html
index 84c862fd5..464bcba2c 100644
--- a/public/2017-11/index.html
+++ b/public/2017-11/index.html
@@ -38,7 +38,7 @@ COPY 54701
 
 <meta property="article:published_time" content="2017-11-02T09:37:54&#43;02:00"/>
 
-<meta property="article:modified_time" content="2017-11-30T18:32:56&#43;03:00"/>
+<meta property="article:modified_time" content="2017-12-17T10:43:56&#43;02:00"/>
 
 
 
@@ -88,7 +88,7 @@ COPY 54701
   "url": "https://alanorth.github.io/cgspace-notes/2017-11/",
   "wordCount": "5428",
   "datePublished": "2017-11-02T09:37:54&#43;02:00",
-  "dateModified": "2017-11-30T18:32:56&#43;03:00",
+  "dateModified": "2017-12-17T10:43:56&#43;02:00",
   "author": {
     "@type": "Person",
     "name": "Alan Orth"
@@ -916,7 +916,7 @@ dspace6=# CREATE EXTENSION pgcrypto;
 </code></pre>
 
 <ul>
-<li>Looking at the MBeans you can drill down in Catalina→Manager→<webapp>→localhost→Attributes and see active sessions, etc</li>
+<li>Looking at the MBeans you can drill down in Catalina→Manager→webapp→localhost→Attributes and see active sessions, etc</li>
 <li>I want to enable JMX listener on CGSpace but I need to do some more testing on DSpace Test and see if it causes any performance impact, for example</li>
 <li>If I hit the server with some requests as a normal user I see the session counter increase, but if I specify a bot user agent then the sessions seem to be reused (meaning the Crawler Session Manager is working)</li>
 <li>Here is the Jconsole screen after looping <code>http --print Hh https://dspacetest.cgiar.org/handle/10568/1</code> for a few minutes:</li>
diff --git a/public/2017-12/index.html b/public/2017-12/index.html
index 57fe8fd3d..9e5927dfc 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="2017-12-17T00:48:43&#43;02:00"/>
+<meta property="article:modified_time" content="2017-12-17T09:55:04&#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": "964",
+  "wordCount": "1128",
   "datePublished": "2017-12-01T13:53:54&#43;03:00",
-  "dateModified": "2017-12-17T00:48:43&#43;02:00",
+  "dateModified": "2017-12-17T09:55:04&#43;02:00",
   "author": {
     "@type": "Person",
     "name": "Alan Orth"
@@ -336,6 +336,19 @@ UPDATE 1
 
 <ul>
 <li>Reboot DSpace Test to get new Linode Linux kernel</li>
+<li>Looking at CCAFS bulk import for Magdalena Haman (she originally sent them in November but some of the thumbnails were missing and dates were messed up so she resent them now)</li>
+<li>A few issues with the data and thumbnails:
+
+<ul>
+<li>Her thumbnail files all use capital JPG so I had to rename them to lowercase: <code>rename -fc *.JPG</code></li>
+<li>thumbnail20.jpg is 1.7MB so I have to resize it</li>
+<li>I also had to add the .jpg to the thumbnail string in the CSV</li>
+<li>The thumbnail11.jpg is missing</li>
+<li>The dates are in super long ISO8601 format (from Excel?) like <code>2016-02-07T00:00:00Z</code> so I converted them to simpler forms in GREL: <code>value.toString(&quot;yyyy-MM-dd&quot;)</code></li>
+<li>I trimmed the whitespaces in a few fields but it wasn&rsquo;t many</li>
+<li>Rename her thumbnail column to filename, and format it so SAFBuilder adds the files to the thumbnail bundle with this GREL in OpenRefine: <code>value + &quot;__bundle:THUMBNAIL&quot;</code></li>
+<li>I will send her feedback on some author names like UNEP and ICRISAT and ask her for the missing thumbnail11.jpg</li>
+</ul></li>
 </ul>
 
   
diff --git a/public/sitemap.xml b/public/sitemap.xml
index 41b63e4e5..06e265523 100644
--- a/public/sitemap.xml
+++ b/public/sitemap.xml
@@ -4,12 +4,12 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/2017-12/</loc>
-    <lastmod>2017-12-17T00:48:43+02:00</lastmod>
+    <lastmod>2017-12-17T09:55:04+02:00</lastmod>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/2017-11/</loc>
-    <lastmod>2017-11-30T18:32:56+03:00</lastmod>
+    <lastmod>2017-12-17T10:43:56+02:00</lastmod>
   </url>
   
   <url>
@@ -139,7 +139,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/</loc>
-    <lastmod>2017-12-17T00:48:43+02:00</lastmod>
+    <lastmod>2017-12-17T09:55:04+02:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -150,7 +150,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/notes/</loc>
-    <lastmod>2017-12-17T00:48:43+02:00</lastmod>
+    <lastmod>2017-12-17T09:55:04+02:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -162,13 +162,13 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/post/</loc>
-    <lastmod>2017-12-17T00:48:43+02:00</lastmod>
+    <lastmod>2017-12-17T09:55:04+02:00</lastmod>
     <priority>0</priority>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/</loc>
-    <lastmod>2017-12-17T00:48:43+02:00</lastmod>
+    <lastmod>2017-12-17T09:55:04+02:00</lastmod>
     <priority>0</priority>
   </url>