From cc24e999dff240bdefad693f10ea7ecc545da2bb Mon Sep 17 00:00:00 2001 From: Alan Orth Date: Wed, 25 May 2022 17:05:40 +0300 Subject: [PATCH] Add notes for 2022-05-25 --- content/posts/2022-05.md | 37 ++++++++++++++++++++++ docs/2022-05/index.html | 42 ++++++++++++++++++++++--- docs/categories/index.html | 2 +- docs/categories/notes/index.html | 2 +- docs/categories/notes/page/2/index.html | 2 +- docs/categories/notes/page/3/index.html | 2 +- docs/categories/notes/page/4/index.html | 2 +- docs/categories/notes/page/5/index.html | 2 +- docs/categories/notes/page/6/index.html | 2 +- docs/index.html | 2 +- docs/page/2/index.html | 2 +- docs/page/3/index.html | 2 +- docs/page/4/index.html | 2 +- docs/page/5/index.html | 2 +- docs/page/6/index.html | 2 +- docs/page/7/index.html | 2 +- docs/page/8/index.html | 2 +- docs/page/9/index.html | 2 +- docs/posts/index.html | 2 +- docs/posts/page/2/index.html | 2 +- docs/posts/page/3/index.html | 2 +- docs/posts/page/4/index.html | 2 +- docs/posts/page/5/index.html | 2 +- docs/posts/page/6/index.html | 2 +- docs/posts/page/7/index.html | 2 +- docs/posts/page/8/index.html | 2 +- docs/posts/page/9/index.html | 2 +- docs/sitemap.xml | 10 +++--- 28 files changed, 105 insertions(+), 34 deletions(-) diff --git a/content/posts/2022-05.md b/content/posts/2022-05.md index 5009f239b..a66b0d9ad 100644 --- a/content/posts/2022-05.md +++ b/content/posts/2022-05.md @@ -176,4 +176,41 @@ $ csvgrep -c matched -m false /tmp/2022-05-13-ror.csv | csvcut -c organization > - Update CGSpace to latest `6_x-prod` branch, which removes a handful of Mirage 2 themes and migrates to Node.js 14 and some newer build deps - Run all system updates on CGSpace (linode18) and reboot it +## 2022-05-25 + +- Maria Garruccio sent me a handful of new ORCID identifiers for Alliance staff + - We currently have 1349 unique identifiers and this adds about forty-five new ones (!): + +```console +$ grep -oE '[A-Z0-9]{4}-[A-Z0-9]{4}-[A-Z0-9]{4}-[A-Z0-9]{4}' ~/src/git/DSpace/dspace/config/controlled-vocabularies/cg-creator-identifier.xml | sort | uniq | wc -l +1349 +$ cat ~/src/git/DSpace/dspace/config/controlled-vocabularies/cg-creator-identifier.xml /tmp/new-abc-orcids.txt | grep -oE '[A-Z0-9]{4}-[A-Z0-9]{4}-[A-Z0-9]{4}-[A-Z0-9]{4}' | sort | uniq > /tmp/2022-05-25-combined-orcids.txt +$ wc -l /tmp/2022-05-25-combined-orcids.txt +1395 /tmp/2022-05-25-combined-orcids.txt +``` + +- After combining and filtering them I resolved their names using my `resolve-orcids.py` script: + +```console +$ ./ilri/resolve-orcids.py -i /tmp/2022-05-25-combined-orcids.txt -o /tmp/2022-05-25-combined-orcids-names.txt +``` + +- There are some names that changed, so I need to run them through the `fix-metadata-values.py` script: + +```console +$ cat 2022-05-25-update-orcids.csv +cg.creator.identifier,correct +"Andrea Fongar: 0000-0003-2084-1571","ANDREA CECILIA SANCHEZ BOGADO: 0000-0003-4549-6970" +"Bekele Shiferaw: 0000-0002-3645-320X","Bekele A. Shiferaw: 0000-0002-3645-320X" +"Henry Kpaka: 0000-0002-7480-2933","Henry Musa Kpaka: 0000-0002-7480-2933" +"Josephine Agogbua: 0000-0001-6317-1227","Josephine Udunma Agogbua: 0000-0001-6317-1227" +"Martha Lilia Del Río Duque: 0000-0002-0879-0292","Martha Del Río: 0000-0002-0879-0292" +$ ./ilri/fix-metadata-values.py -i 2022-05-25-update-orcids.csv -db dspace -u dspace -p 'fuuu' -f cg.creator.identifier -m 247 -t correct -d -n +Connected to database. +Would fix 4 occurences of: Andrea Fongar: 0000-0003-2084-1571 +Would fix 1 occurences of: Bekele Shiferaw: 0000-0002-3645-320X +Would fix 2 occurences of: Josephine Agogbua: 0000-0001-6317-1227 +Would fix 34 occurences of: Martha Lilia Del Río Duque: 0000-0002-0879-0292 +``` + diff --git a/docs/2022-05/index.html b/docs/2022-05/index.html index 9df4a9925..ec743bcd9 100644 --- a/docs/2022-05/index.html +++ b/docs/2022-05/index.html @@ -35,7 +35,7 @@ I purged 93,974 hits from these IPs using my check-spider-ip-hits.sh script - + @@ -76,9 +76,9 @@ I purged 93,974 hits from these IPs using my check-spider-ip-hits.sh script "@type": "BlogPosting", "headline": "May, 2022", "url": "https://alanorth.github.io/cgspace-notes/2022-05/", - "wordCount": "1223", + "wordCount": "1423", "datePublished": "2022-05-04T09:13:39+03:00", - "dateModified": "2022-05-24T09:42:54+03:00", + "dateModified": "2022-05-24T22:10:47+03:00", "author": { "@type": "Person", "name": "Alan Orth" @@ -341,8 +341,42 @@ I purged 93,974 hits from these IPs using my check-spider-ip-hits.sh script

2022-05-24

- +

2022-05-25

+ +
$ grep -oE '[A-Z0-9]{4}-[A-Z0-9]{4}-[A-Z0-9]{4}-[A-Z0-9]{4}' ~/src/git/DSpace/dspace/config/controlled-vocabularies/cg-creator-identifier.xml | sort | uniq | wc -l
+1349
+$ cat ~/src/git/DSpace/dspace/config/controlled-vocabularies/cg-creator-identifier.xml /tmp/new-abc-orcids.txt | grep -oE '[A-Z0-9]{4}-[A-Z0-9]{4}-[A-Z0-9]{4}-[A-Z0-9]{4}' | sort | uniq > /tmp/2022-05-25-combined-orcids.txt
+$ wc -l /tmp/2022-05-25-combined-orcids.txt
+1395 /tmp/2022-05-25-combined-orcids.txt
+
+
$ ./ilri/resolve-orcids.py -i /tmp/2022-05-25-combined-orcids.txt -o /tmp/2022-05-25-combined-orcids-names.txt
+
+
$ cat 2022-05-25-update-orcids.csv
+cg.creator.identifier,correct
+"Andrea Fongar: 0000-0003-2084-1571","ANDREA CECILIA SANCHEZ BOGADO: 0000-0003-4549-6970"
+"Bekele Shiferaw: 0000-0002-3645-320X","Bekele A. Shiferaw: 0000-0002-3645-320X"
+"Henry Kpaka: 0000-0002-7480-2933","Henry Musa Kpaka: 0000-0002-7480-2933"
+"Josephine Agogbua: 0000-0001-6317-1227","Josephine Udunma Agogbua: 0000-0001-6317-1227"
+"Martha Lilia Del Río Duque: 0000-0002-0879-0292","Martha Del Río: 0000-0002-0879-0292"
+$ ./ilri/fix-metadata-values.py -i 2022-05-25-update-orcids.csv -db dspace -u dspace -p 'fuuu' -f cg.creator.identifier -m 247 -t correct -d -n
+Connected to database.
+Would fix 4 occurences of: Andrea Fongar: 0000-0003-2084-1571
+Would fix 1 occurences of: Bekele Shiferaw: 0000-0002-3645-320X
+Would fix 2 occurences of: Josephine Agogbua: 0000-0001-6317-1227
+Would fix 34 occurences of: Martha Lilia Del Río Duque: 0000-0002-0879-0292
+
diff --git a/docs/categories/index.html b/docs/categories/index.html index ec33732d5..26c5512c2 100644 --- a/docs/categories/index.html +++ b/docs/categories/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/categories/notes/index.html b/docs/categories/notes/index.html index ba0c21e1d..6e5f79ce7 100644 --- a/docs/categories/notes/index.html +++ b/docs/categories/notes/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/categories/notes/page/2/index.html b/docs/categories/notes/page/2/index.html index 94d3f16ea..39c39ca82 100644 --- a/docs/categories/notes/page/2/index.html +++ b/docs/categories/notes/page/2/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/categories/notes/page/3/index.html b/docs/categories/notes/page/3/index.html index 6d8d51389..6e41ad6d5 100644 --- a/docs/categories/notes/page/3/index.html +++ b/docs/categories/notes/page/3/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/categories/notes/page/4/index.html b/docs/categories/notes/page/4/index.html index ea18405b4..25e91db88 100644 --- a/docs/categories/notes/page/4/index.html +++ b/docs/categories/notes/page/4/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/categories/notes/page/5/index.html b/docs/categories/notes/page/5/index.html index 6851b0f9e..b68aa2942 100644 --- a/docs/categories/notes/page/5/index.html +++ b/docs/categories/notes/page/5/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/categories/notes/page/6/index.html b/docs/categories/notes/page/6/index.html index 21d81a4b4..34ad50f70 100644 --- a/docs/categories/notes/page/6/index.html +++ b/docs/categories/notes/page/6/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/index.html b/docs/index.html index 1bb57d94f..46bdb02bb 100644 --- a/docs/index.html +++ b/docs/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/page/2/index.html b/docs/page/2/index.html index f4fd898d8..ab12485a9 100644 --- a/docs/page/2/index.html +++ b/docs/page/2/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/page/3/index.html b/docs/page/3/index.html index 24403cdfe..255f103b3 100644 --- a/docs/page/3/index.html +++ b/docs/page/3/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/page/4/index.html b/docs/page/4/index.html index 3607a08ab..a8b9bc47b 100644 --- a/docs/page/4/index.html +++ b/docs/page/4/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/page/5/index.html b/docs/page/5/index.html index c2bcbbf20..ab2dd022b 100644 --- a/docs/page/5/index.html +++ b/docs/page/5/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/page/6/index.html b/docs/page/6/index.html index e33c55de1..52fe87e75 100644 --- a/docs/page/6/index.html +++ b/docs/page/6/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/page/7/index.html b/docs/page/7/index.html index 5a556a5e6..ccb7fb529 100644 --- a/docs/page/7/index.html +++ b/docs/page/7/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/page/8/index.html b/docs/page/8/index.html index b3ca86a03..7fe07522a 100644 --- a/docs/page/8/index.html +++ b/docs/page/8/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/page/9/index.html b/docs/page/9/index.html index 777edfecf..95222c6de 100644 --- a/docs/page/9/index.html +++ b/docs/page/9/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/index.html b/docs/posts/index.html index 80faa5eba..d826f607a 100644 --- a/docs/posts/index.html +++ b/docs/posts/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/page/2/index.html b/docs/posts/page/2/index.html index 527569936..8d8428588 100644 --- a/docs/posts/page/2/index.html +++ b/docs/posts/page/2/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/page/3/index.html b/docs/posts/page/3/index.html index 153513073..d4766a853 100644 --- a/docs/posts/page/3/index.html +++ b/docs/posts/page/3/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/page/4/index.html b/docs/posts/page/4/index.html index 46ef7c029..e2105ed50 100644 --- a/docs/posts/page/4/index.html +++ b/docs/posts/page/4/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/page/5/index.html b/docs/posts/page/5/index.html index 589dfcd0e..ee588e35b 100644 --- a/docs/posts/page/5/index.html +++ b/docs/posts/page/5/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/page/6/index.html b/docs/posts/page/6/index.html index 1099dc4ff..74e8aeb53 100644 --- a/docs/posts/page/6/index.html +++ b/docs/posts/page/6/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/page/7/index.html b/docs/posts/page/7/index.html index 8a38e0052..123defc5d 100644 --- a/docs/posts/page/7/index.html +++ b/docs/posts/page/7/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/page/8/index.html b/docs/posts/page/8/index.html index fe201b3ce..b13cbd93a 100644 --- a/docs/posts/page/8/index.html +++ b/docs/posts/page/8/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/page/9/index.html b/docs/posts/page/9/index.html index 7298b1a95..bc6930abc 100644 --- a/docs/posts/page/9/index.html +++ b/docs/posts/page/9/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/sitemap.xml b/docs/sitemap.xml index 19101d6bd..ed248d2a2 100644 --- a/docs/sitemap.xml +++ b/docs/sitemap.xml @@ -3,19 +3,19 @@ xmlns:xhtml="http://www.w3.org/1999/xhtml"> https://alanorth.github.io/cgspace-notes/categories/ - 2022-05-24T09:42:54+03:00 + 2022-05-24T22:10:47+03:00 https://alanorth.github.io/cgspace-notes/ - 2022-05-24T09:42:54+03:00 + 2022-05-24T22:10:47+03:00 https://alanorth.github.io/cgspace-notes/2022-05/ - 2022-05-24T09:42:54+03:00 + 2022-05-24T22:10:47+03:00 https://alanorth.github.io/cgspace-notes/categories/notes/ - 2022-05-24T09:42:54+03:00 + 2022-05-24T22:10:47+03:00 https://alanorth.github.io/cgspace-notes/posts/ - 2022-05-24T09:42:54+03:00 + 2022-05-24T22:10:47+03:00 https://alanorth.github.io/cgspace-notes/2022-04/ 2022-05-04T11:09:45+03:00