From 0fafc7a6264bbd5986c5ac222e3ad7c9bbb2e8a9 Mon Sep 17 00:00:00 2001
From: Alan Orth <alan.orth@gmail.com>
Date: Wed, 30 May 2018 14:48:10 -0700
Subject: [PATCH] Update notes

---
 content/posts/2018-05.md |  9 +++++++++
 docs/2018-05/index.html  | 16 +++++++++++++---
 docs/sitemap.xml         | 10 +++++-----
 3 files changed, 27 insertions(+), 8 deletions(-)

diff --git a/content/posts/2018-05.md b/content/posts/2018-05.md
index c7b50e3c0..aa08acfb0 100644
--- a/content/posts/2018-05.md
+++ b/content/posts/2018-05.md
@@ -356,3 +356,12 @@ dspace=# select email, netid from eperson where email not like '%cgiar.org%' and
 - It might be possible to adjust some things, but eventually we'll need a larger VPS instance
 - For some reason there are no JVM stats in Munin, ugh
 - Run all system updates on DSpace Test and reboot it
+- I generated a list of CIFOR duplicates from the `CIFOR_May_9` collection using the Atmire MQM module and then dumped the HTML source so I could process it for sending to Vika
+- I used grep to filter all relevant handle lines from the HTML source then used sed to insert a newline before each "Item1" line (as the duplicates are grouped like Item1, Item2, Item3 for each set of duplicates):
+
+```
+$ grep -E 'aspect.duplicatechecker.DuplicateResults.field.del_handle_[0-9]{1,3}_Item' ~/Desktop/https\ _dspacetest.cgiar.org_atmire_metadata-quality_duplicate-checker.html > ~/cifor-duplicates.txt
+$ sed 's/.*Item1.*/\n&/g' ~/cifor-duplicates.txt > ~/cifor-duplicates-cleaned.txt
+```
+
+- I told Vika to look through the list manually and indicate which ones are indeed duplicates that we should delete, and which ones to map to CIFOR's collection
diff --git a/docs/2018-05/index.html b/docs/2018-05/index.html
index 0c268e30f..c0b4b058a 100644
--- a/docs/2018-05/index.html
+++ b/docs/2018-05/index.html
@@ -27,7 +27,7 @@ Also, I switched it to use OpenJDK instead of Oracle Java, as well as re-worked
 
 <meta property="article:published_time" content="2018-05-01T16:43:54&#43;03:00"/>
 
-<meta property="article:modified_time" content="2018-05-30T09:05:40-07:00"/>
+<meta property="article:modified_time" content="2018-05-30T10:50:55-07:00"/>
 
 
 
@@ -65,9 +65,9 @@ Also, I switched it to use OpenJDK instead of Oracle Java, as well as re-worked
   "@type": "BlogPosting",
   "headline": "May, 2018",
   "url": "https://alanorth.github.io/cgspace-notes/2018-05/",
-  "wordCount": "3024",
+  "wordCount": "3135",
   "datePublished": "2018-05-01T16:43:54&#43;03:00",
-  "dateModified": "2018-05-30T09:05:40-07:00",
+  "dateModified": "2018-05-30T10:50:55-07:00",
   "author": {
     "@type": "Person",
     "name": "Alan Orth"
@@ -555,6 +555,16 @@ $ ./bin/post -c countries ~/src/git/DSpace/2018-05-10-countries.csv
 <li>It might be possible to adjust some things, but eventually we&rsquo;ll need a larger VPS instance</li>
 <li>For some reason there are no JVM stats in Munin, ugh</li>
 <li>Run all system updates on DSpace Test and reboot it</li>
+<li>I generated a list of CIFOR duplicates from the <code>CIFOR_May_9</code> collection using the Atmire MQM module and then dumped the HTML source so I could process it for sending to Vika</li>
+<li>I used grep to filter all relevant handle lines from the HTML source then used sed to insert a newline before each &ldquo;Item1&rdquo; line (as the duplicates are grouped like Item1, Item2, Item3 for each set of duplicates):</li>
+</ul>
+
+<pre><code>$ grep -E 'aspect.duplicatechecker.DuplicateResults.field.del_handle_[0-9]{1,3}_Item' ~/Desktop/https\ _dspacetest.cgiar.org_atmire_metadata-quality_duplicate-checker.html &gt; ~/cifor-duplicates.txt
+$ sed 's/.*Item1.*/\n&amp;/g' ~/cifor-duplicates.txt &gt; ~/cifor-duplicates-cleaned.txt
+</code></pre>
+
+<ul>
+<li>I told Vika to look through the list manually and indicate which ones are indeed duplicates that we should delete, and which ones to map to CIFOR&rsquo;s collection</li>
 </ul>
 
   
diff --git a/docs/sitemap.xml b/docs/sitemap.xml
index abc6ab005..44eb28bf8 100644
--- a/docs/sitemap.xml
+++ b/docs/sitemap.xml
@@ -4,7 +4,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/2018-05/</loc>
-    <lastmod>2018-05-30T09:05:40-07:00</lastmod>
+    <lastmod>2018-05-30T10:50:55-07:00</lastmod>
   </url>
   
   <url>
@@ -164,7 +164,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/</loc>
-    <lastmod>2018-05-30T09:05:40-07:00</lastmod>
+    <lastmod>2018-05-30T10:50:55-07:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -175,7 +175,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/notes/</loc>
-    <lastmod>2018-05-30T09:05:40-07:00</lastmod>
+    <lastmod>2018-05-30T10:50:55-07:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -187,13 +187,13 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/posts/</loc>
-    <lastmod>2018-05-30T09:05:40-07:00</lastmod>
+    <lastmod>2018-05-30T10:50:55-07:00</lastmod>
     <priority>0</priority>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/</loc>
-    <lastmod>2018-05-30T09:05:40-07:00</lastmod>
+    <lastmod>2018-05-30T10:50:55-07:00</lastmod>
     <priority>0</priority>
   </url>