mirror of
https://github.com/alanorth/cgspace-notes.git
synced 2024-12-21 20:52:18 +01:00
Notes for 2023-12-08
This commit is contained in:
parent
804a505ae2
commit
2ecafafc17
@ -109,4 +109,21 @@ $ for network in $(csvcut -c network /tmp/ips.csv | sed 1d | sort -u); do grepci
|
||||
|
||||
- I will remove those for now so that Altmetric doesn't have any unexpected issues harvesting
|
||||
|
||||
## 2023-12-08
|
||||
|
||||
- Finalized the script to generate Solr statistics for Alliance research Mirjam
|
||||
- The script is `ilri/generate_solr_statistics.py`
|
||||
- I generated ~3,200 statistics based on her records of the download statistics of [that item](https://hdl.handle.net/10568/131997) and imported them on CGSpace
|
||||
- Peter asked for lists of affiliations, investors, and publishers to do some cleanups
|
||||
- I generated a list from a CSV export instead of doing it based on a SQL dump...
|
||||
|
||||
```console
|
||||
$ csvcut -c 'cg.contributor.affiliation[en_US]' /tmp/initiatives.csv \
|
||||
| sed -e 1d -e 's/^"//' -e 's/"$//' -e 's/||/\n/g' -e '/^$/d' \
|
||||
| sort | uniq -c | sort -hr \
|
||||
| awk 'BEGIN { FS = "^[[:space:]]+[[:digit:]]+[[:space:]]+" } {print $2}'\
|
||||
| sed -e '1i cg.contributor.affiliation' -e 's/^\(.*\)$/"\1"/' \
|
||||
> /tmp/2023-12-08-initiatives-affiliations.csv
|
||||
```
|
||||
|
||||
<!-- vim: set sw=2 ts=2: -->
|
||||
|
@ -28,7 +28,7 @@
|
||||
"@type": "BlogPosting",
|
||||
"headline": "December, 2023",
|
||||
"url": "https://alanorth.github.io/cgspace-notes/2023-12/",
|
||||
"wordCount": "529",
|
||||
"wordCount": "643",
|
||||
"datePublished": "2023-12-01T08:48:36+03:00",
|
||||
"dateModified": "2023-12-06T09:55:57+03:00",
|
||||
"author": {
|
||||
@ -212,7 +212,27 @@
|
||||
</span></span></code></pre></div><ul>
|
||||
<li>I will remove those for now so that Altmetric doesn’t have any unexpected issues harvesting</li>
|
||||
</ul>
|
||||
<!-- raw HTML omitted -->
|
||||
<h2 id="2023-12-08">2023-12-08</h2>
|
||||
<ul>
|
||||
<li>Finalized the script to generate Solr statistics for Alliance research Mirjam
|
||||
<ul>
|
||||
<li>The script is <code>ilri/generate_solr_statistics.py</code></li>
|
||||
<li>I generated ~3,200 statistics based on her records of the download statistics of <a href="https://hdl.handle.net/10568/131997">that item</a> and imported them on CGSpace</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li>Peter asked for lists of affiliations, investors, and publishers to do some cleanups
|
||||
<ul>
|
||||
<li>I generated a list from a CSV export instead of doing it based on a SQL dump…</li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
<div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code class="language-console" data-lang="console"><span style="display:flex;"><span>$ csvcut -c <span style="color:#e6db74">'cg.contributor.affiliation[en_US]'</span> /tmp/initiatives.csv <span style="color:#ae81ff">\
|
||||
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> | sed -e 1d -e 's/^"//' -e 's/"$//' -e 's/||/\n/g' -e '/^$/d' \
|
||||
</span></span><span style="display:flex;"><span> | sort | uniq -c | sort -hr \
|
||||
</span></span><span style="display:flex;"><span> | awk 'BEGIN { FS = "^[[:space:]]+[[:digit:]]+[[:space:]]+" } {print $2}'\
|
||||
</span></span><span style="display:flex;"><span> | sed -e '1i cg.contributor.affiliation' -e 's/^\(.*\)$/"\1"/' \
|
||||
</span></span><span style="display:flex;"><span> > /tmp/2023-12-08-initiatives-affiliations.csv
|
||||
</span></span></code></pre></div><!-- raw HTML omitted -->
|
||||
|
||||
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user