From ee1e5f831e825f2408dfe1a7c184fdb7fcd7e4f3 Mon Sep 17 00:00:00 2001
From: Alan Orth <alan.orth@gmail.com>
Date: Mon, 12 Aug 2019 18:08:00 +0300
Subject: [PATCH] Add notes for 2019-08-12

---
 content/posts/2019-08.md | 10 ++++++++++
 docs/2019-08/index.html  | 21 ++++++++++++++++++---
 docs/sitemap.xml         | 10 +++++-----
 3 files changed, 33 insertions(+), 8 deletions(-)

diff --git a/content/posts/2019-08.md b/content/posts/2019-08.md
index 0c56e81b9..49bb8e345 100644
--- a/content/posts/2019-08.md
+++ b/content/posts/2019-08.md
@@ -138,4 +138,14 @@ proxy_set_header Host dev.ares.codeobia.com;
 
 - Add checks for uncommon filename extensions and replacements for unneccesary Unicode to the csv-metadata-quality script
 
+## 2019-08-12
+
+- Looking at the 128 IITA records again:
+  - Validate and normalize affiliations against our 2019-02 list using reconcile-csv and OpenRefine:
+    - `$ lein run ~/src/git/DSpace/2019-02-22-sponsorships.csv name id`
+    - I always forget how to copy the reconciled values in OpenRefine, but you need to make a new colum and populate it using this GREL: `if(cell.recon.matched, cell.recon.match.name, value)`
+  - I checked the collection for duplicates and found a few:
+    - https://dspacetest.cgiar.org/handle/10568/102513 is a duplicate of CIAT item: https://cgspace.cgiar.org/handle/10568/44158
+    - https://dspacetest.cgiar.org/handle/10568/102512 is a duplicate of CIAT item: https://cgspace.cgiar.org/handle/10568/43557
+
 <!-- vim: set sw=2 ts=2: -->
diff --git a/docs/2019-08/index.html b/docs/2019-08/index.html
index 1b7568313..07f1cb3bd 100644
--- a/docs/2019-08/index.html
+++ b/docs/2019-08/index.html
@@ -27,7 +27,7 @@ Run system updates on DSpace Test (linode19) and reboot it
 <meta property="og:type" content="article" />
 <meta property="og:url" content="https://alanorth.github.io/cgspace-notes/2019-08/" />
 <meta property="article:published_time" content="2019-08-03T12:39:51+03:00" />
-<meta property="article:modified_time" content="2019-08-09T09:57:26+03:00" />
+<meta property="article:modified_time" content="2019-08-11T00:12:28+03:00" />
 
 <meta name="twitter:card" content="summary"/>
 <meta name="twitter:title" content="August, 2019"/>
@@ -59,9 +59,9 @@ Run system updates on DSpace Test (linode19) and reboot it
   "@type": "BlogPosting",
   "headline": "August, 2019",
   "url": "https:\/\/alanorth.github.io\/cgspace-notes\/2019-08\/",
-  "wordCount": "1059",
+  "wordCount": "1139",
   "datePublished": "2019-08-03T12:39:51\x2b03:00",
-  "dateModified": "2019-08-09T09:57:26\x2b03:00",
+  "dateModified": "2019-08-11T00:12:28\x2b03:00",
   "author": {
     "@type": "Person",
     "name": "Alan Orth"
@@ -307,6 +307,21 @@ $ ./generate-thumbnails.py -i /tmp/user-upload2.csv -w --url-field-name url -d |
 <li>Add checks for uncommon filename extensions and replacements for unneccesary Unicode to the csv-metadata-quality script</li>
 </ul>
 
+<h2 id="2019-08-12">2019-08-12</h2>
+
+<ul>
+<li>Looking at the 128 IITA records again:
+
+<ul>
+<li>Validate and normalize affiliations against our 2019-02 list using reconcile-csv and OpenRefine:</li>
+<li><code>$ lein run ~/src/git/DSpace/2019-02-22-sponsorships.csv name id</code></li>
+<li>I always forget how to copy the reconciled values in OpenRefine, but you need to make a new colum and populate it using this GREL: <code>if(cell.recon.matched, cell.recon.match.name, value)</code></li>
+<li>I checked the collection for duplicates and found a few:</li>
+<li><a href="https://dspacetest.cgiar.org/handle/10568/102513">https://dspacetest.cgiar.org/handle/10568/102513</a> is a duplicate of CIAT item: <a href="https://cgspace.cgiar.org/handle/10568/44158">https://cgspace.cgiar.org/handle/10568/44158</a></li>
+<li><a href="https://dspacetest.cgiar.org/handle/10568/102512">https://dspacetest.cgiar.org/handle/10568/102512</a> is a duplicate of CIAT item: <a href="https://cgspace.cgiar.org/handle/10568/43557">https://cgspace.cgiar.org/handle/10568/43557</a></li>
+</ul></li>
+</ul>
+
 <!-- vim: set sw=2 ts=2: -->
 
   
diff --git a/docs/sitemap.xml b/docs/sitemap.xml
index 36251ccbf..db55a4016 100644
--- a/docs/sitemap.xml
+++ b/docs/sitemap.xml
@@ -4,30 +4,30 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/2019-08/</loc>
-    <lastmod>2019-08-09T09:57:26+03:00</lastmod>
+    <lastmod>2019-08-11T00:12:28+03:00</lastmod>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/</loc>
-    <lastmod>2019-08-09T09:57:26+03:00</lastmod>
+    <lastmod>2019-08-11T00:12:28+03:00</lastmod>
     <priority>0</priority>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/notes/</loc>
-    <lastmod>2019-08-09T09:57:26+03:00</lastmod>
+    <lastmod>2019-08-11T00:12:28+03:00</lastmod>
     <priority>0</priority>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/posts/</loc>
-    <lastmod>2019-08-09T09:57:26+03:00</lastmod>
+    <lastmod>2019-08-11T00:12:28+03:00</lastmod>
     <priority>0</priority>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/</loc>
-    <lastmod>2019-08-09T09:57:26+03:00</lastmod>
+    <lastmod>2019-08-11T00:12:28+03:00</lastmod>
     <priority>0</priority>
   </url>