From d765b637c6543091249e8fc88edd213ee3fd47f6 Mon Sep 17 00:00:00 2001
From: Alan Orth <alan.orth@gmail.com>
Date: Wed, 21 Aug 2019 01:26:32 +0300
Subject: [PATCH] Add notes for 2019-08-20

---
 content/posts/2019-08.md | 15 +++++++++++++++
 docs/2019-08/index.html  | 26 +++++++++++++++++++++++---
 docs/sitemap.xml         | 10 +++++-----
 3 files changed, 43 insertions(+), 8 deletions(-)

diff --git a/content/posts/2019-08.md b/content/posts/2019-08.md
index 1723309e9..f5bbfe294 100644
--- a/content/posts/2019-08.md
+++ b/content/posts/2019-08.md
@@ -210,4 +210,19 @@ statistics-2015: org.apache.solr.common.SolrException:org.apache.solr.common.Sol
 - After reboot the statistics-2018 core failed to load so I restarted `tomcat7` again
 - After this last restart all Solr cores seem to be up and running
 
+## 2019-08-20
+
+- Francesco sent me a new CSV with the raw filenames and paths for the Bioversity migration
+  - All file paths are relative to the Typo3 upload path of `/fileadmin` on the Bioversity website
+  - I create a new column with the derived URL that I can use to download the PDFs with my `generate-thumbnails.py` script
+  - Unfortunately now the filename column has paths too, so I have to use a simple Python/Jython script in OpenRefine to get the basename of the files in the filename column:
+
+```
+import os
+
+return os.path.basename(value)
+```
+
+- Then I can try to download all the files again with the script
+
 <!-- vim: set sw=2 ts=2: -->
diff --git a/docs/2019-08/index.html b/docs/2019-08/index.html
index 2385603cd..0654e9051 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="2019-08-16T17:10:11+03:00" />
+<meta property="article:modified_time" content="2019-08-18T23:07:48+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": "1536",
+  "wordCount": "1637",
   "datePublished": "2019-08-03T12:39:51\x2b03:00",
-  "dateModified": "2019-08-16T17:10:11\x2b03:00",
+  "dateModified": "2019-08-18T23:07:48\x2b03:00",
   "author": {
     "@type": "Person",
     "name": "Alan Orth"
@@ -400,6 +400,26 @@ $ dspace metadata-import -f /tmp/bioversity2.csv -e blah@blah.com
 <li><p>After this last restart all Solr cores seem to be up and running</p></li>
 </ul>
 
+<h2 id="2019-08-20">2019-08-20</h2>
+
+<ul>
+<li><p>Francesco sent me a new CSV with the raw filenames and paths for the Bioversity migration</p>
+
+<ul>
+<li>All file paths are relative to the Typo3 upload path of <code>/fileadmin</code> on the Bioversity website</li>
+<li>I create a new column with the derived URL that I can use to download the PDFs with my <code>generate-thumbnails.py</code> script</li>
+
+<li><p>Unfortunately now the filename column has paths too, so I have to use a simple Python/Jython script in OpenRefine to get the basename of the files in the filename column:</p>
+
+<pre><code>import os
+
+return os.path.basename(value)
+</code></pre></li>
+</ul></li>
+
+<li><p>Then I can try to download all the files again with the script</p></li>
+</ul>
+
 <!-- vim: set sw=2 ts=2: -->
 
   
diff --git a/docs/sitemap.xml b/docs/sitemap.xml
index 936be9bee..a696b98f8 100644
--- a/docs/sitemap.xml
+++ b/docs/sitemap.xml
@@ -4,27 +4,27 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/2019-08/</loc>
-    <lastmod>2019-08-16T17:10:11+03:00</lastmod>
+    <lastmod>2019-08-18T23:07:48+03:00</lastmod>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/</loc>
-    <lastmod>2019-08-16T17:10:11+03:00</lastmod>
+    <lastmod>2019-08-18T23:07:48+03:00</lastmod>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/notes/</loc>
-    <lastmod>2019-08-16T17:10:11+03:00</lastmod>
+    <lastmod>2019-08-18T23:07:48+03:00</lastmod>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/posts/</loc>
-    <lastmod>2019-08-16T17:10:11+03:00</lastmod>
+    <lastmod>2019-08-18T23:07:48+03:00</lastmod>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/</loc>
-    <lastmod>2019-08-16T17:10:11+03:00</lastmod>
+    <lastmod>2019-08-18T23:07:48+03:00</lastmod>
   </url>
   
   <url>