From 1fe5b9b7f7d6451089d8add099e647ea5475fc6b Mon Sep 17 00:00:00 2001
From: Alan Orth <alan.orth@gmail.com>
Date: Mon, 15 Apr 2019 17:42:53 +0300
Subject: [PATCH] Update notes for 2019-04-15

---
 content/posts/2019-04.md | 25 +++++++++++++++++++++++++
 docs/2019-04/index.html  | 38 +++++++++++++++++++++++++++++++++++---
 docs/sitemap.xml         | 10 +++++-----
 3 files changed, 65 insertions(+), 8 deletions(-)

diff --git a/content/posts/2019-04.md b/content/posts/2019-04.md
index af022f295..92fc560d9 100644
--- a/content/posts/2019-04.md
+++ b/content/posts/2019-04.md
@@ -649,5 +649,30 @@ GC_TUNE="-XX:NewRatio=3 \
 
 - Rework the dspace-statistics-api to use the vanilla Python requests library instead of Solr client
   - [Tag version 1.0.0](https://github.com/ilri/dspace-statistics-api/releases/tag/v1.0.0) and deploy it on DSpace Test
+- Pretty annoying to see CGSpace (linode18) with 20–50% CPU steal according to `iostat 1 10`, though I haven't had any Linode alerts in a few days
+- Abenet sent me a list of ILRI items that don't have CRPs added to them
+  - The spreadsheet only had Handles (no IDs), so I'm experimenting with using Python in OpenRefine to get the IDs
+  - I cloned the handle column and then did a transform to get the IDs from the CGSpace REST API:
+
+```
+import json
+import re
+import urllib
+import urllib2
+
+handle = re.findall('[0-9]+/[0-9]+', value)
+
+url = 'https://cgspace.cgiar.org/rest/handle/' + handle[0]
+req = urllib2.Request(url)
+req.add_header('User-agent', 'Alan Python bot')
+res = urllib2.urlopen(req)
+data = json.load(res)
+item_id = data['id']
+
+return item_id
+```
+
+- Luckily none of the items already had CRPs, so I didn't have to worry about them getting removed
+  - It would have been much trickier if I had to get the CRPs for the items first, then add the CRPs...
 
 <!-- vim: set sw=2 ts=2: -->
diff --git a/docs/2019-04/index.html b/docs/2019-04/index.html
index 8bb7d2963..a88c25a83 100644
--- a/docs/2019-04/index.html
+++ b/docs/2019-04/index.html
@@ -38,7 +38,7 @@ $ ./delete-metadata-values.py -i /tmp/2019-02-21-delete-1-region.csv -db dspace
 <meta property="og:type" content="article" />
 <meta property="og:url" content="https://alanorth.github.io/cgspace-notes/2019-04/" />
 <meta property="article:published_time" content="2019-04-01T09:00:43&#43;03:00"/>
-<meta property="article:modified_time" content="2019-04-14T16:59:47&#43;03:00"/>
+<meta property="article:modified_time" content="2019-04-15T12:58:07&#43;03:00"/>
 
 <meta name="twitter:card" content="summary"/>
 <meta name="twitter:title" content="April, 2019"/>
@@ -81,9 +81,9 @@ $ ./delete-metadata-values.py -i /tmp/2019-02-21-delete-1-region.csv -db dspace
   "@type": "BlogPosting",
   "headline": "April, 2019",
   "url": "https:\/\/alanorth.github.io\/cgspace-notes\/2019-04\/",
-  "wordCount": "3748",
+  "wordCount": "3901",
   "datePublished": "2019-04-01T09:00:43\x2b03:00",
-  "dateModified": "2019-04-14T16:59:47\x2b03:00",
+  "dateModified": "2019-04-15T12:58:07\x2b03:00",
   "author": {
     "@type": "Person",
     "name": "Alan Orth"
@@ -924,6 +924,38 @@ $ ./delete-metadata-values.py -i /tmp/2019-04-11-delete-6-subjects.csv -db dspac
 <ul>
 <li><a href="https://github.com/ilri/dspace-statistics-api/releases/tag/v1.0.0">Tag version 1.0.0</a> and deploy it on DSpace Test</li>
 </ul></li>
+<li>Pretty annoying to see CGSpace (linode18) with 20–50% CPU steal according to <code>iostat 1 10</code>, though I haven&rsquo;t had any Linode alerts in a few days</li>
+<li>Abenet sent me a list of ILRI items that don&rsquo;t have CRPs added to them
+
+<ul>
+<li>The spreadsheet only had Handles (no IDs), so I&rsquo;m experimenting with using Python in OpenRefine to get the IDs</li>
+<li>I cloned the handle column and then did a transform to get the IDs from the CGSpace REST API:</li>
+</ul></li>
+</ul>
+
+<pre><code>import json
+import re
+import urllib
+import urllib2
+
+handle = re.findall('[0-9]+/[0-9]+', value)
+
+url = 'https://cgspace.cgiar.org/rest/handle/' + handle[0]
+req = urllib2.Request(url)
+req.add_header('User-agent', 'Alan Python bot')
+res = urllib2.urlopen(req)
+data = json.load(res)
+item_id = data['id']
+
+return item_id
+</code></pre>
+
+<ul>
+<li>Luckily none of the items already had CRPs, so I didn&rsquo;t have to worry about them getting removed
+
+<ul>
+<li>It would have been much trickier if I had to get the CRPs for the items first, then add the CRPs&hellip;</li>
+</ul></li>
 </ul>
 
 <!-- vim: set sw=2 ts=2: -->
diff --git a/docs/sitemap.xml b/docs/sitemap.xml
index 8bdd07656..3d231b232 100644
--- a/docs/sitemap.xml
+++ b/docs/sitemap.xml
@@ -4,30 +4,30 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/2019-04/</loc>
-    <lastmod>2019-04-14T16:59:47+03:00</lastmod>
+    <lastmod>2019-04-15T12:58:07+03:00</lastmod>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/</loc>
-    <lastmod>2019-04-14T16:59:47+03:00</lastmod>
+    <lastmod>2019-04-15T12:58:07+03:00</lastmod>
     <priority>0</priority>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/notes/</loc>
-    <lastmod>2019-04-14T16:59:47+03:00</lastmod>
+    <lastmod>2019-04-15T12:58:07+03:00</lastmod>
     <priority>0</priority>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/posts/</loc>
-    <lastmod>2019-04-14T16:59:47+03:00</lastmod>
+    <lastmod>2019-04-15T12:58:07+03:00</lastmod>
     <priority>0</priority>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/</loc>
-    <lastmod>2019-04-14T16:59:47+03:00</lastmod>
+    <lastmod>2019-04-15T12:58:07+03:00</lastmod>
     <priority>0</priority>
   </url>