From 809faab7a57a6b9a97c5396133270a06f8aaf28f Mon Sep 17 00:00:00 2001
From: Alan Orth <alan.orth@gmail.com>
Date: Mon, 27 Aug 2018 10:27:13 +0300
Subject: [PATCH] Update notes for 2018-08-26

---
 content/posts/2018-08.md | 17 +++++++++++++++++
 docs/2018-08/index.html  | 25 ++++++++++++++++++++++---
 docs/sitemap.xml         | 10 +++++-----
 3 files changed, 44 insertions(+), 8 deletions(-)

diff --git a/content/posts/2018-08.md b/content/posts/2018-08.md
index ab9feedfd..0d54658ea 100644
--- a/content/posts/2018-08.md
+++ b/content/posts/2018-08.md
@@ -302,5 +302,22 @@ $ sudo su -
 ```
 
 - After reboot I logged in and cleared all the XMLUI caches and everything looked to be working fine
+- Adam from WLE had asked a few weeks ago about getting the metadata for a bunch of items related to gender from 2013 until now
+- They want a CSV with *all* metadata, which the Atmire Listings and Reports module can't do
+- I exported a list of items from Listings and Reports with the following criteria: from year 2013 until now, have WLE subject `GENDER` or `GENDER POVERTY AND INSTITUTIONS`, and CRP `Water, Land and Ecosystems`
+- Then I extracted the Handle links from the report so I could export each item's metadata as CSV
+
+```
+$ grep -o -E "[0-9]{5}/[0-9]{0,5}" listings-export.txt > /tmp/iwmi-gender-items.txt
+```
+
+- Then on the DSpace server I exported the metadata for each item one by one:
+
+```
+$ while read -r line; do dspace metadata-export -f "/tmp/${line/\//-}.csv" -i $line; sleep 2; done < /tmp/iwmi-gender-items.txt
+```
+
+- But from here I realized that each of the fifty-nine items will have different columns in their CSVs, making it difficult to combine them
+- I'm not sure how to proceed without writing some script to parse and join the CSVs, and I don't think it's worth my time
 
 <!-- vim: set sw=2 ts=2: -->
diff --git a/docs/2018-08/index.html b/docs/2018-08/index.html
index bacfa3598..5996e485f 100644
--- a/docs/2018-08/index.html
+++ b/docs/2018-08/index.html
@@ -34,7 +34,7 @@ I ran all system updates on DSpace Test and rebooted it
 
 <meta property="article:published_time" content="2018-08-01T11:52:54&#43;03:00"/>
 
-<meta property="article:modified_time" content="2018-08-23T16:34:16&#43;03:00"/>
+<meta property="article:modified_time" content="2018-08-26T09:38:15&#43;03:00"/>
 
 
 
@@ -79,9 +79,9 @@ I ran all system updates on DSpace Test and rebooted it
   "@type": "BlogPosting",
   "headline": "August, 2018",
   "url": "https://alanorth.github.io/cgspace-notes/2018-08/",
-  "wordCount": "2245",
+  "wordCount": "2426",
   "datePublished": "2018-08-01T11:52:54&#43;03:00",
-  "dateModified": "2018-08-23T16:34:16&#43;03:00",
+  "dateModified": "2018-08-26T09:38:15&#43;03:00",
   "author": {
     "@type": "Person",
     "name": "Alan Orth"
@@ -481,6 +481,25 @@ $ dspace database migrate ignored
 
 <ul>
 <li>After reboot I logged in and cleared all the XMLUI caches and everything looked to be working fine</li>
+<li>Adam from WLE had asked a few weeks ago about getting the metadata for a bunch of items related to gender from 2013 until now</li>
+<li>They want a CSV with <em>all</em> metadata, which the Atmire Listings and Reports module can&rsquo;t do</li>
+<li>I exported a list of items from Listings and Reports with the following criteria: from year 2013 until now, have WLE subject <code>GENDER</code> or <code>GENDER POVERTY AND INSTITUTIONS</code>, and CRP <code>Water, Land and Ecosystems</code></li>
+<li>Then I extracted the Handle links from the report so I could export each item&rsquo;s metadata as CSV</li>
+</ul>
+
+<pre><code>$ grep -o -E &quot;[0-9]{5}/[0-9]{0,5}&quot; listings-export.txt &gt; /tmp/iwmi-gender-items.txt
+</code></pre>
+
+<ul>
+<li>Then on the DSpace server I exported the metadata for each item one by one:</li>
+</ul>
+
+<pre><code>$ while read -r line; do dspace metadata-export -f &quot;/tmp/${line/\//-}.csv&quot; -i $line; sleep 2; done &lt; /tmp/iwmi-gender-items.txt
+</code></pre>
+
+<ul>
+<li>But from here I realized that each of the fifty-nine items will have different columns in their CSVs, making it difficult to combine them</li>
+<li>I&rsquo;m not sure how to proceed without writing some script to parse and join the CSVs, and I don&rsquo;t think it&rsquo;s worth my time</li>
 </ul>
 
 <!-- vim: set sw=2 ts=2: -->
diff --git a/docs/sitemap.xml b/docs/sitemap.xml
index b07a1ac35..8803f777c 100644
--- a/docs/sitemap.xml
+++ b/docs/sitemap.xml
@@ -4,7 +4,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/2018-08/</loc>
-    <lastmod>2018-08-23T16:34:16+03:00</lastmod>
+    <lastmod>2018-08-26T09:38:15+03:00</lastmod>
   </url>
   
   <url>
@@ -179,7 +179,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/</loc>
-    <lastmod>2018-08-23T16:34:16+03:00</lastmod>
+    <lastmod>2018-08-26T09:38:15+03:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -190,7 +190,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/notes/</loc>
-    <lastmod>2018-08-23T16:34:16+03:00</lastmod>
+    <lastmod>2018-08-26T09:38:15+03:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -202,13 +202,13 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/posts/</loc>
-    <lastmod>2018-08-23T16:34:16+03:00</lastmod>
+    <lastmod>2018-08-26T09:38:15+03:00</lastmod>
     <priority>0</priority>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/</loc>
-    <lastmod>2018-08-23T16:34:16+03:00</lastmod>
+    <lastmod>2018-08-26T09:38:15+03:00</lastmod>
     <priority>0</priority>
   </url>