From cad7ceaba1a849e9c14daa29c77fc1fd2cc314f1 Mon Sep 17 00:00:00 2001
From: Alan Orth <alan.orth@gmail.com>
Date: Sun, 2 Dec 2018 17:55:32 +0200
Subject: [PATCH] Update notes for 2018-12-02

---
 content/posts/2018-12.md | 24 ++++++++++++++++++++++++
 docs/2018-12/index.html  | 34 +++++++++++++++++++++++++++++++---
 docs/sitemap.xml         | 10 +++++-----
 3 files changed, 60 insertions(+), 8 deletions(-)

diff --git a/content/posts/2018-12.md b/content/posts/2018-12.md
index 8d0dc9322..1a670c3d5 100644
--- a/content/posts/2018-12.md
+++ b/content/posts/2018-12.md
@@ -56,4 +56,28 @@ $ gs -q -dQUIET -dSAFER -dBATCH -dNOPAUSE -dNOPROMPT -dMaxBitmap=500000000 -dAli
 DEBUG: FC_WEIGHT didn't match
 ```
 
+- Start proofing the latest round of 226 IITA archive records that Bosede sent last week and Sisay uploaded to DSpace Test this weekend ([IITA_Dec_1_1997 aka Daniel1807](https://dspacetest.cgiar.org/handle/10568/108298))
+  - One item missing the authorship type
+  - Some invalid countries (smart quotes, mispellings)
+  - Added countries to some items that mentioned research in particular countries in their abstracts
+  - One item had "MADAGASCAR" for ISI Journal
+  - Minor corrections in IITA subject (LIVELIHOOD→LIVELIHOODS)
+  - Trim whitespace in abstract field
+  - Fix some sponsors (though some with "Governments of Canada" etc I'm not sure why those are plural)
+  - Eighteen items had `en||fr` for the language, but the content was only in French so changed them to just `fr`
+  - Six items had encoding errors in French text so I will ask Bosede to re-do them carefully
+  - Correct and normalize a few AGROVOC subjects
+- Expand my "encoding error" detection GREL to include `~` as I saw a lot of that in some copy pasted French text recently:
+
+```
+or(
+  isNotNull(value.match(/.*\uFFFD.*/)),
+  isNotNull(value.match(/.*\u00A0.*/)),
+  isNotNull(value.match(/.*\u200A.*/)),
+  isNotNull(value.match(/.*\u2019.*/)),
+  isNotNull(value.match(/.*\u00b4.*/)),
+  isNotNull(value.match(/.*\u007e.*/))
+)
+```
+
 <!-- vim: set sw=2 ts=2: -->
diff --git a/docs/2018-12/index.html b/docs/2018-12/index.html
index 0fc1bd8dc..35f0cbdca 100644
--- a/docs/2018-12/index.html
+++ b/docs/2018-12/index.html
@@ -21,7 +21,7 @@ I noticed that there is another issue with PDF thumbnails on CGSpace, and I see
 " />
 <meta property="og:type" content="article" />
 <meta property="og:url" content="https://alanorth.github.io/cgspace-notes/2018-12/" /><meta property="article:published_time" content="2018-12-02T02:09:30&#43;02:00"/>
-<meta property="article:modified_time" content="2018-12-02T10:47:41&#43;02:00"/>
+<meta property="article:modified_time" content="2018-12-02T10:57:41&#43;02:00"/>
 
 <meta name="twitter:card" content="summary"/>
 <meta name="twitter:title" content="December, 2018"/>
@@ -48,9 +48,9 @@ I noticed that there is another issue with PDF thumbnails on CGSpace, and I see
   "@type": "BlogPosting",
   "headline": "December, 2018",
   "url": "https://alanorth.github.io/cgspace-notes/2018-12/",
-  "wordCount": "301",
+  "wordCount": "463",
   "datePublished": "2018-12-02T02:09:30&#43;02:00",
-  "dateModified": "2018-12-02T10:47:41&#43;02:00",
+  "dateModified": "2018-12-02T10:57:41&#43;02:00",
   "author": {
     "@type": "Person",
     "name": "Alan Orth"
@@ -172,6 +172,34 @@ zsh: segmentation fault (core dumped)  gs -q -dQUIET -dSAFER -dBATCH -dNOPAUSE -
 DEBUG: FC_WEIGHT didn't match
 </code></pre>
 
+<ul>
+<li>Start proofing the latest round of 226 IITA archive records that Bosede sent last week and Sisay uploaded to DSpace Test this weekend (<a href="https://dspacetest.cgiar.org/handle/10568/108298">IITA_Dec_1_1997 aka Daniel1807</a>)
+
+<ul>
+<li>One item missing the authorship type</li>
+<li>Some invalid countries (smart quotes, mispellings)</li>
+<li>Added countries to some items that mentioned research in particular countries in their abstracts</li>
+<li>One item had &ldquo;MADAGASCAR&rdquo; for ISI Journal</li>
+<li>Minor corrections in IITA subject (LIVELIHOOD→LIVELIHOODS)</li>
+<li>Trim whitespace in abstract field</li>
+<li>Fix some sponsors (though some with &ldquo;Governments of Canada&rdquo; etc I&rsquo;m not sure why those are plural)</li>
+<li>Eighteen items had <code>en||fr</code> for the language, but the content was only in French so changed them to just <code>fr</code></li>
+<li>Six items had encoding errors in French text so I will ask Bosede to re-do them carefully</li>
+<li>Correct and normalize a few AGROVOC subjects</li>
+</ul></li>
+<li>Expand my &ldquo;encoding error&rdquo; detection GREL to include <code>~</code> as I saw a lot of that in some copy pasted French text recently:</li>
+</ul>
+
+<pre><code>or(
+  isNotNull(value.match(/.*\uFFFD.*/)),
+  isNotNull(value.match(/.*\u00A0.*/)),
+  isNotNull(value.match(/.*\u200A.*/)),
+  isNotNull(value.match(/.*\u2019.*/)),
+  isNotNull(value.match(/.*\u00b4.*/)),
+  isNotNull(value.match(/.*\u007e.*/))
+)
+</code></pre>
+
 <!-- vim: set sw=2 ts=2: -->
 
   
diff --git a/docs/sitemap.xml b/docs/sitemap.xml
index 41cd0731e..58cd68683 100644
--- a/docs/sitemap.xml
+++ b/docs/sitemap.xml
@@ -4,7 +4,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/2018-12/</loc>
-    <lastmod>2018-12-02T10:47:41+02:00</lastmod>
+    <lastmod>2018-12-02T10:57:41+02:00</lastmod>
   </url>
   
   <url>
@@ -199,7 +199,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/</loc>
-    <lastmod>2018-12-02T10:47:41+02:00</lastmod>
+    <lastmod>2018-12-02T10:57:41+02:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -210,7 +210,7 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/notes/</loc>
-    <lastmod>2018-12-02T10:47:41+02:00</lastmod>
+    <lastmod>2018-12-02T10:57:41+02:00</lastmod>
     <priority>0</priority>
   </url>
   
@@ -222,13 +222,13 @@
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/posts/</loc>
-    <lastmod>2018-12-02T10:47:41+02:00</lastmod>
+    <lastmod>2018-12-02T10:57:41+02:00</lastmod>
     <priority>0</priority>
   </url>
   
   <url>
     <loc>https://alanorth.github.io/cgspace-notes/tags/</loc>
-    <lastmod>2018-12-02T10:47:41+02:00</lastmod>
+    <lastmod>2018-12-02T10:57:41+02:00</lastmod>
     <priority>0</priority>
   </url>