From 11f1935f856e0c9068876e45f3a86ff595ee11e7 Mon Sep 17 00:00:00 2001 From: Alan Orth Date: Fri, 8 Mar 2024 17:31:19 +0300 Subject: [PATCH] Add notes for 2024-03-08 --- content/posts/2024-03.md | 44 ++++++++++++++++++ docs/2015-11/index.html | 2 +- docs/2015-12/index.html | 2 +- docs/2016-01/index.html | 2 +- docs/2016-02/index.html | 2 +- docs/2016-03/index.html | 2 +- docs/2016-04/index.html | 2 +- docs/2016-05/index.html | 2 +- docs/2016-06/index.html | 2 +- docs/2016-07/index.html | 2 +- docs/2016-08/index.html | 2 +- docs/2016-09/index.html | 2 +- docs/2016-10/index.html | 2 +- docs/2016-11/index.html | 2 +- docs/2016-12/index.html | 2 +- docs/2017-01/index.html | 2 +- docs/2017-02/index.html | 2 +- docs/2017-03/index.html | 2 +- docs/2017-04/index.html | 2 +- docs/2017-05/index.html | 2 +- docs/2017-06/index.html | 2 +- docs/2017-07/index.html | 2 +- docs/2017-08/index.html | 2 +- docs/2017-09/index.html | 2 +- docs/2017-10/index.html | 2 +- docs/2017-11/index.html | 2 +- docs/2017-12/index.html | 2 +- docs/2018-01/index.html | 2 +- docs/2018-02/index.html | 2 +- docs/2018-03/index.html | 2 +- docs/2018-04/index.html | 2 +- docs/2018-05/index.html | 2 +- docs/2018-06/index.html | 2 +- docs/2018-07/index.html | 2 +- docs/2018-08/index.html | 2 +- docs/2018-09/index.html | 2 +- docs/2018-10/index.html | 2 +- docs/2018-11/index.html | 2 +- docs/2018-12/index.html | 2 +- docs/2019-01/index.html | 2 +- docs/2019-02/index.html | 2 +- docs/2019-03/index.html | 2 +- docs/2019-04/index.html | 2 +- docs/2019-05/index.html | 2 +- docs/2019-06/index.html | 2 +- docs/2019-07/index.html | 2 +- docs/2019-08/index.html | 2 +- docs/2019-09/index.html | 2 +- docs/2019-10/index.html | 2 +- docs/2019-11/index.html | 2 +- docs/2019-12/index.html | 2 +- docs/2020-01/index.html | 2 +- docs/2020-02/index.html | 2 +- docs/2020-03/index.html | 2 +- docs/2020-04/index.html | 2 +- docs/2020-05/index.html | 2 +- docs/2020-06/index.html | 2 +- docs/2020-07/index.html | 2 +- docs/2020-08/index.html | 2 +- docs/2020-09/index.html | 2 +- docs/2020-10/index.html | 2 +- docs/2020-11/index.html | 2 +- docs/2020-12/index.html | 2 +- docs/2021-01/index.html | 2 +- docs/2021-02/index.html | 2 +- docs/2021-03/index.html | 2 +- docs/2021-04/index.html | 2 +- docs/2021-05/index.html | 2 +- docs/2021-06/index.html | 2 +- docs/2021-07/index.html | 2 +- docs/2021-08/index.html | 2 +- docs/2021-09/index.html | 2 +- docs/2021-10/index.html | 2 +- docs/2021-11/index.html | 2 +- docs/2021-12/index.html | 2 +- docs/2022-01/index.html | 2 +- docs/2022-02/index.html | 2 +- docs/2022-03/index.html | 2 +- docs/2022-04/index.html | 2 +- docs/2022-05/index.html | 2 +- docs/2022-06/index.html | 2 +- docs/2022-07/index.html | 2 +- docs/2022-08/index.html | 2 +- docs/2022-09/index.html | 2 +- docs/2022-10/index.html | 2 +- docs/2022-11/index.html | 2 +- docs/2022-12/index.html | 2 +- docs/2023-01/index.html | 2 +- docs/2023-02/index.html | 2 +- docs/2023-03/index.html | 2 +- docs/2023-04/index.html | 2 +- docs/2023-05/index.html | 2 +- docs/2023-06/index.html | 2 +- docs/2023-07/index.html | 2 +- docs/2023-08/index.html | 2 +- docs/2023-09/index.html | 2 +- docs/2023-10/index.html | 2 +- docs/2023-11/index.html | 2 +- docs/2023-12/index.html | 2 +- docs/2024-01/index.html | 2 +- docs/2024-02/index.html | 2 +- docs/2024-03/index.html | 53 ++++++++++++++++++++-- docs/404.html | 2 +- docs/categories/index.html | 4 +- docs/categories/index.xml | 2 +- docs/categories/notes/index.html | 4 +- docs/categories/notes/index.xml | 2 +- docs/categories/notes/page/2/index.html | 4 +- docs/categories/notes/page/3/index.html | 4 +- docs/categories/notes/page/4/index.html | 4 +- docs/categories/notes/page/5/index.html | 4 +- docs/categories/notes/page/6/index.html | 4 +- docs/categories/notes/page/7/index.html | 4 +- docs/categories/notes/page/8/index.html | 4 +- docs/categories/notes/page/9/index.html | 4 +- docs/cgiar-library-migration/index.html | 2 +- docs/cgspace-cgcorev2-migration/index.html | 2 +- docs/cgspace-dspace6-upgrade/index.html | 2 +- docs/index.html | 4 +- docs/index.xml | 2 +- docs/page/10/index.html | 4 +- docs/page/11/index.html | 4 +- docs/page/2/index.html | 4 +- docs/page/3/index.html | 4 +- docs/page/4/index.html | 4 +- docs/page/5/index.html | 4 +- docs/page/6/index.html | 4 +- docs/page/7/index.html | 4 +- docs/page/8/index.html | 4 +- docs/page/9/index.html | 4 +- docs/posts/index.html | 4 +- docs/posts/index.xml | 2 +- docs/posts/page/10/index.html | 4 +- docs/posts/page/11/index.html | 4 +- docs/posts/page/2/index.html | 4 +- docs/posts/page/3/index.html | 4 +- docs/posts/page/4/index.html | 4 +- docs/posts/page/5/index.html | 4 +- docs/posts/page/6/index.html | 4 +- docs/posts/page/7/index.html | 4 +- docs/posts/page/8/index.html | 4 +- docs/posts/page/9/index.html | 4 +- docs/sitemap.xml | 10 ++-- docs/tags/index.html | 2 +- docs/tags/migration/index.html | 2 +- docs/tags/notes/index.html | 2 +- docs/tags/notes/page/2/index.html | 2 +- docs/tags/notes/page/3/index.html | 2 +- 148 files changed, 275 insertions(+), 186 deletions(-) diff --git a/content/posts/2024-03.md b/content/posts/2024-03.md index 4850da861..0f2dbc163 100644 --- a/content/posts/2024-03.md +++ b/content/posts/2024-03.md @@ -21,4 +21,48 @@ categories: ["Notes"] - I did some cleanups on abstracts, licenses, and dates from CrossRef - I also did some minor cleanups to affiliations because I saw some incorrect and duplicate ones in our list +## 2024-03-05 + +- I tried a new technique to get some affiliations from Crossref using OpenRefine + - First I split them and clustered, resolving a few hundred clusters out of 1500 (!) + - Then I used a custom text facet with a few dozen CGIAR and other large affiliations to reduce the work + - Then I joined them with our affiliations, paying no attention to duplicates + - Then I deduped them using the Jython technique I learned in 2023-02 + +## 2024-03-06 + +- Peter sent me some more corrections for the authors that I had sent him in 2023-12 + +## 2024-03-08 + +- IFPRI sent me their 2023 records from CONTENTdm so I started working on those + - I found a way to match their ORCID identifiers in our list using Jython in OpenRefine: + +```python +import re + +with open(r"/tmp/cg-creator-identifier.txt",'r') as f : + orcid_ids = [orcid_id.strip() for orcid_id in f] + +matched = False +for orcid_id in orcid_ids: + if re.search(r'.+: {}'.format(value), orcid_id): + matched = True + break + +if matched: + return orcid_id +else: + return value +``` + + +- I realized that [UNICEF was renamed to its current name in 1953](https://www.unicef.org/about-unicef/frequently-asked-questions#3) so I replaced all other variations in our vocabularies and metadata: + +```sql +UPDATE metadatavalue SET text_value='United Nations Children''s Fund' WHERE dspace_object_id IN (SELECT uuid FROM item) AND text_value IN ('United Nations International Children''s Emergency Fund', 'United Nations International Children''s Emergency Fund', 'UNICEF'); +``` + +- Note the use of two single quotes to escape the one in the name + diff --git a/docs/2015-11/index.html b/docs/2015-11/index.html index 17c4e90bf..220d84244 100644 --- a/docs/2015-11/index.html +++ b/docs/2015-11/index.html @@ -34,7 +34,7 @@ Last week I had increased the limit from 30 to 60, which seemed to help, but now $ psql -c 'SELECT * from pg_stat_activity;' | grep idle | grep -c cgspace 78 "/> - + diff --git a/docs/2015-12/index.html b/docs/2015-12/index.html index 05cbbb307..1af8b973b 100644 --- a/docs/2015-12/index.html +++ b/docs/2015-12/index.html @@ -36,7 +36,7 @@ Replace lzop with xz in log compression cron jobs on DSpace Test—it uses less -rw-rw-r-- 1 tomcat7 tomcat7 387K Nov 18 23:59 dspace.log.2015-11-18.lzo -rw-rw-r-- 1 tomcat7 tomcat7 169K Nov 18 23:59 dspace.log.2015-11-18.xz "/> - + diff --git a/docs/2016-01/index.html b/docs/2016-01/index.html index dac05fb9d..4a42d28a7 100644 --- a/docs/2016-01/index.html +++ b/docs/2016-01/index.html @@ -28,7 +28,7 @@ Move ILRI collection 10568/12503 from 10568/27869 to 10568/27629 using the move_ I realized it is only necessary to clear the Cocoon cache after moving collections—rather than reindexing—as no metadata has changed, and therefore no search or browse indexes need to be updated. Update GitHub wiki for documentation of maintenance tasks. "/> - + diff --git a/docs/2016-02/index.html b/docs/2016-02/index.html index 4ed64076f..723c4f4f8 100644 --- a/docs/2016-02/index.html +++ b/docs/2016-02/index.html @@ -38,7 +38,7 @@ I noticed we have a very interesting list of countries on CGSpace: Not only are there 49,000 countries, we have some blanks (25)… Also, lots of things like “COTE D`LVOIRE” and “COTE D IVOIRE” "/> - + diff --git a/docs/2016-03/index.html b/docs/2016-03/index.html index 1b8f72c5c..b0a9f7756 100644 --- a/docs/2016-03/index.html +++ b/docs/2016-03/index.html @@ -28,7 +28,7 @@ Looking at issues with author authorities on CGSpace For some reason we still have the index-lucene-update cron job active on CGSpace, but I’m pretty sure we don’t need it as of the latest few versions of Atmire’s Listings and Reports module Reinstall my local (Mac OS X) DSpace stack with Tomcat 7, PostgreSQL 9.3, and Java JDK 1.7 to match environment on CGSpace server "/> - + diff --git a/docs/2016-04/index.html b/docs/2016-04/index.html index a7d8f6d87..75ee0c60e 100644 --- a/docs/2016-04/index.html +++ b/docs/2016-04/index.html @@ -32,7 +32,7 @@ After running DSpace for over five years I’ve never needed to look in any This will save us a few gigs of backup space we’re paying for on S3 Also, I noticed the checker log has some errors we should pay attention to: "/> - + diff --git a/docs/2016-05/index.html b/docs/2016-05/index.html index eb279bc3d..c7182bdb3 100644 --- a/docs/2016-05/index.html +++ b/docs/2016-05/index.html @@ -34,7 +34,7 @@ There are 3,000 IPs accessing the REST API in a 24-hour period! # awk '{print $1}' /var/log/nginx/rest.log | uniq | wc -l 3168 "/> - + diff --git a/docs/2016-06/index.html b/docs/2016-06/index.html index b152417df..07decfab8 100644 --- a/docs/2016-06/index.html +++ b/docs/2016-06/index.html @@ -34,7 +34,7 @@ This is their publications set: http://ebrary.ifpri.org/oai/oai.php?verb=ListRec You can see the others by using the OAI ListSets verb: http://ebrary.ifpri.org/oai/oai.php?verb=ListSets Working on second phase of metadata migration, looks like this will work for moving CPWF-specific data in dc.identifier.fund to cg.identifier.cpwfproject and then the rest to dc.description.sponsorship "/> - + diff --git a/docs/2016-07/index.html b/docs/2016-07/index.html index 837ad1bbf..2d499e782 100644 --- a/docs/2016-07/index.html +++ b/docs/2016-07/index.html @@ -44,7 +44,7 @@ dspacetest=# select text_value from metadatavalue where metadata_field_id=3 and In this case the select query was showing 95 results before the update "/> - + diff --git a/docs/2016-08/index.html b/docs/2016-08/index.html index 8e98fb147..ebe4cbe89 100644 --- a/docs/2016-08/index.html +++ b/docs/2016-08/index.html @@ -42,7 +42,7 @@ $ git checkout -b 55new 5_x-prod $ git reset --hard ilri/5_x-prod $ git rebase -i dspace-5.5 "/> - + diff --git a/docs/2016-09/index.html b/docs/2016-09/index.html index 18fad619c..f46647126 100644 --- a/docs/2016-09/index.html +++ b/docs/2016-09/index.html @@ -34,7 +34,7 @@ It looks like we might be able to use OUs now, instead of DCs: $ ldapsearch -x -H ldaps://svcgroot2.cgiarad.org:3269/ -b "dc=cgiarad,dc=org" -D "admigration1@cgiarad.org" -W "(sAMAccountName=admigration1)" "/> - + diff --git a/docs/2016-10/index.html b/docs/2016-10/index.html index fb7cd1021..e1578b0eb 100644 --- a/docs/2016-10/index.html +++ b/docs/2016-10/index.html @@ -42,7 +42,7 @@ I exported a random item’s metadata as CSV, deleted all columns except id 0000-0002-6115-0956||0000-0002-3812-8793||0000-0001-7462-405X "/> - + diff --git a/docs/2016-11/index.html b/docs/2016-11/index.html index 220f52e16..fb453445c 100644 --- a/docs/2016-11/index.html +++ b/docs/2016-11/index.html @@ -26,7 +26,7 @@ Add dc.type to the output options for Atmire’s Listings and Reports module Add dc.type to the output options for Atmire’s Listings and Reports module (#286) "/> - + diff --git a/docs/2016-12/index.html b/docs/2016-12/index.html index f6fd34275..c4c819ad4 100644 --- a/docs/2016-12/index.html +++ b/docs/2016-12/index.html @@ -46,7 +46,7 @@ I see thousands of them in the logs for the last few months, so it’s not r I’ve raised a ticket with Atmire to ask Another worrying error from dspace.log is: "/> - + diff --git a/docs/2017-01/index.html b/docs/2017-01/index.html index 2c954db9a..7d5eb1fa5 100644 --- a/docs/2017-01/index.html +++ b/docs/2017-01/index.html @@ -28,7 +28,7 @@ I checked to see if the Solr sharding task that is supposed to run on January 1s I tested on DSpace Test as well and it doesn’t work there either I asked on the dspace-tech mailing list because it seems to be broken, and actually now I’m not sure if we’ve ever had the sharding task run successfully over all these years "/> - + diff --git a/docs/2017-02/index.html b/docs/2017-02/index.html index a5b5509c4..278433887 100644 --- a/docs/2017-02/index.html +++ b/docs/2017-02/index.html @@ -50,7 +50,7 @@ DELETE 1 Create issue on GitHub to track the addition of CCAFS Phase II project tags (#301) Looks like we’ll be using cg.identifier.ccafsprojectpii as the field name "/> - + diff --git a/docs/2017-03/index.html b/docs/2017-03/index.html index 061ad25ab..04fc23ee6 100644 --- a/docs/2017-03/index.html +++ b/docs/2017-03/index.html @@ -54,7 +54,7 @@ Interestingly, it seems DSpace 4.x’s thumbnails were sRGB, but forcing reg $ identify ~/Desktop/alc_contrastes_desafios.jpg /Users/aorth/Desktop/alc_contrastes_desafios.jpg JPEG 464x600 464x600+0+0 8-bit CMYK 168KB 0.000u 0:00.000 "/> - + diff --git a/docs/2017-04/index.html b/docs/2017-04/index.html index c0eddb641..a5d989f21 100644 --- a/docs/2017-04/index.html +++ b/docs/2017-04/index.html @@ -40,7 +40,7 @@ Testing the CMYK patch on a collection with 650 items: $ [dspace]/bin/dspace filter-media -f -i 10568/16498 -p "ImageMagick PDF Thumbnail" -v >& /tmp/filter-media-cmyk.txt "/> - + diff --git a/docs/2017-05/index.html b/docs/2017-05/index.html index 2c9e24c5b..d645b8d23 100644 --- a/docs/2017-05/index.html +++ b/docs/2017-05/index.html @@ -18,7 +18,7 @@ - + diff --git a/docs/2017-06/index.html b/docs/2017-06/index.html index ea8f59c29..29fce3174 100644 --- a/docs/2017-06/index.html +++ b/docs/2017-06/index.html @@ -18,7 +18,7 @@ - + diff --git a/docs/2017-07/index.html b/docs/2017-07/index.html index 7c99de375..b29b2e149 100644 --- a/docs/2017-07/index.html +++ b/docs/2017-07/index.html @@ -36,7 +36,7 @@ Merge changes for WLE Phase II theme rename (#329) Looking at extracting the metadata registries from ICARDA’s MEL DSpace database so we can compare fields with CGSpace We can use PostgreSQL’s extended output format (-x) plus sed to format the output into quasi XML: "/> - + diff --git a/docs/2017-08/index.html b/docs/2017-08/index.html index d6ce10dc0..607f99fec 100644 --- a/docs/2017-08/index.html +++ b/docs/2017-08/index.html @@ -60,7 +60,7 @@ This was due to newline characters in the dc.description.abstract column, which I exported a new CSV from the collection on DSpace Test and then manually removed the characters in vim using g/^$/d Then I cleaned up the author authorities and HTML characters in OpenRefine and sent the file back to Abenet "/> - + diff --git a/docs/2017-09/index.html b/docs/2017-09/index.html index 99a7d5239..721b7bb5c 100644 --- a/docs/2017-09/index.html +++ b/docs/2017-09/index.html @@ -32,7 +32,7 @@ Linode sent an alert that CGSpace (linode18) was using 261% CPU for the past two Ask Sisay to clean up the WLE approvers a bit, as Marianne’s user account is both in the approvers step as well as the group "/> - + diff --git a/docs/2017-10/index.html b/docs/2017-10/index.html index 40f4f16b3..9ada63a1c 100644 --- a/docs/2017-10/index.html +++ b/docs/2017-10/index.html @@ -34,7 +34,7 @@ http://hdl.handle.net/10568/78495||http://hdl.handle.net/10568/79336 There appears to be a pattern but I’ll have to look a bit closer and try to clean them up automatically, either in SQL or in OpenRefine Add Katherine Lutz to the groups for content submission and edit steps of the CGIAR System collections "/> - + diff --git a/docs/2017-11/index.html b/docs/2017-11/index.html index a8da52e97..b3ba4b08f 100644 --- a/docs/2017-11/index.html +++ b/docs/2017-11/index.html @@ -48,7 +48,7 @@ Generate list of authors on CGSpace for Peter to go through and correct: dspace=# \copy (select distinct text_value, count(*) as count from metadatavalue where metadata_field_id = (select metadata_field_id from metadatafieldregistry where element = 'contributor' and qualifier = 'author') AND resource_type_id = 2 group by text_value order by count desc) to /tmp/authors.csv with csv; COPY 54701 "/> - + diff --git a/docs/2017-12/index.html b/docs/2017-12/index.html index c80ea238b..fe09f2e9f 100644 --- a/docs/2017-12/index.html +++ b/docs/2017-12/index.html @@ -30,7 +30,7 @@ The logs say “Timeout waiting for idle object” PostgreSQL activity says there are 115 connections currently The list of connections to XMLUI and REST API for today: "/> - + diff --git a/docs/2018-01/index.html b/docs/2018-01/index.html index d9c8e3ed1..46cc16ab9 100644 --- a/docs/2018-01/index.html +++ b/docs/2018-01/index.html @@ -150,7 +150,7 @@ dspace.log.2018-01-02:34 Danny wrote to ask for help renewing the wildcard ilri.org certificate and I advised that we should probably use Let’s Encrypt if it’s just a handful of domains "/> - + diff --git a/docs/2018-02/index.html b/docs/2018-02/index.html index 6a4480104..194cfc632 100644 --- a/docs/2018-02/index.html +++ b/docs/2018-02/index.html @@ -30,7 +30,7 @@ We don’t need to distinguish between internal and external works, so that Yesterday I figured out how to monitor DSpace sessions using JMX I copied the logic in the jmx_tomcat_dbpools provided by Ubuntu’s munin-plugins-java package and used the stuff I discovered about JMX in 2018-01 "/> - + diff --git a/docs/2018-03/index.html b/docs/2018-03/index.html index 0472578eb..924233bf5 100644 --- a/docs/2018-03/index.html +++ b/docs/2018-03/index.html @@ -24,7 +24,7 @@ Export a CSV of the IITA community metadata for Martin Mueller Export a CSV of the IITA community metadata for Martin Mueller "/> - + diff --git a/docs/2018-04/index.html b/docs/2018-04/index.html index c326def61..95c055f4c 100644 --- a/docs/2018-04/index.html +++ b/docs/2018-04/index.html @@ -26,7 +26,7 @@ Catalina logs at least show some memory errors yesterday: I tried to test something on DSpace Test but noticed that it’s down since god knows when Catalina logs at least show some memory errors yesterday: "/> - + diff --git a/docs/2018-05/index.html b/docs/2018-05/index.html index 263b83d47..c6254fffa 100644 --- a/docs/2018-05/index.html +++ b/docs/2018-05/index.html @@ -38,7 +38,7 @@ http://localhost:3000/solr/statistics/update?stream.body=%3Ccommit/%3E Then I reduced the JVM heap size from 6144 back to 5120m Also, I switched it to use OpenJDK instead of Oracle Java, as well as re-worked the Ansible infrastructure scripts to support hosts choosing which distribution they want to use "/> - + diff --git a/docs/2018-06/index.html b/docs/2018-06/index.html index b4a0ef8e5..3bb6c3e16 100644 --- a/docs/2018-06/index.html +++ b/docs/2018-06/index.html @@ -58,7 +58,7 @@ real 74m42.646s user 8m5.056s sys 2m7.289s "/> - + diff --git a/docs/2018-07/index.html b/docs/2018-07/index.html index 6baf30232..719b2a11c 100644 --- a/docs/2018-07/index.html +++ b/docs/2018-07/index.html @@ -36,7 +36,7 @@ During the mvn package stage on the 5.8 branch I kept getting issues with java r There is insufficient memory for the Java Runtime Environment to continue. "/> - + diff --git a/docs/2018-08/index.html b/docs/2018-08/index.html index 0773cff26..b08da772b 100644 --- a/docs/2018-08/index.html +++ b/docs/2018-08/index.html @@ -46,7 +46,7 @@ Anyways, perhaps I should increase the JVM heap from 5120m to 6144m like we did The server only has 8GB of RAM so we’ll eventually need to upgrade to a larger one because we’ll start starving the OS, PostgreSQL, and command line batch processes I ran all system updates on DSpace Test and rebooted it "/> - + diff --git a/docs/2018-09/index.html b/docs/2018-09/index.html index 3334d4bd2..9cf01ec9c 100644 --- a/docs/2018-09/index.html +++ b/docs/2018-09/index.html @@ -30,7 +30,7 @@ I’ll update the DSpace role in our Ansible infrastructure playbooks and ru Also, I’ll re-run the postgresql tasks because the custom PostgreSQL variables are dynamic according to the system’s RAM, and we never re-ran them after migrating to larger Linodes last month I’m testing the new DSpace 5.8 branch in my Ubuntu 18.04 environment and I’m getting those autowire errors in Tomcat 8.5.30 again: "/> - + diff --git a/docs/2018-10/index.html b/docs/2018-10/index.html index 92b636702..f3359ebf6 100644 --- a/docs/2018-10/index.html +++ b/docs/2018-10/index.html @@ -26,7 +26,7 @@ I created a GitHub issue to track this #389, because I’m super busy in Nai Phil Thornton got an ORCID identifier so we need to add it to the list on CGSpace and tag his existing items I created a GitHub issue to track this #389, because I’m super busy in Nairobi right now "/> - + diff --git a/docs/2018-11/index.html b/docs/2018-11/index.html index f69a1aaa5..bec1e9b5a 100644 --- a/docs/2018-11/index.html +++ b/docs/2018-11/index.html @@ -36,7 +36,7 @@ Send a note about my dspace-statistics-api to the dspace-tech mailing list Linode has been sending mails a few times a day recently that CGSpace (linode18) has had high CPU usage Today these are the top 10 IPs: "/> - + diff --git a/docs/2018-12/index.html b/docs/2018-12/index.html index 36b9b898e..0001a2d93 100644 --- a/docs/2018-12/index.html +++ b/docs/2018-12/index.html @@ -36,7 +36,7 @@ Then I ran all system updates and restarted the server I noticed that there is another issue with PDF thumbnails on CGSpace, and I see there was another Ghostscript vulnerability last week "/> - + diff --git a/docs/2019-01/index.html b/docs/2019-01/index.html index 9e6b920ea..dabfe2a64 100644 --- a/docs/2019-01/index.html +++ b/docs/2019-01/index.html @@ -50,7 +50,7 @@ I don’t see anything interesting in the web server logs around that time t 357 207.46.13.1 903 54.70.40.11 "/> - + diff --git a/docs/2019-02/index.html b/docs/2019-02/index.html index 72be98312..20e36644e 100644 --- a/docs/2019-02/index.html +++ b/docs/2019-02/index.html @@ -72,7 +72,7 @@ real 0m19.873s user 0m22.203s sys 0m1.979s "/> - + diff --git a/docs/2019-03/index.html b/docs/2019-03/index.html index 3ca929e57..680ec6522 100644 --- a/docs/2019-03/index.html +++ b/docs/2019-03/index.html @@ -46,7 +46,7 @@ Most worryingly, there are encoding errors in the abstracts for eleven items, fo I think I will need to ask Udana to re-copy and paste the abstracts with more care using Google Docs "/> - + diff --git a/docs/2019-04/index.html b/docs/2019-04/index.html index 2604a3d4d..7c21203b0 100644 --- a/docs/2019-04/index.html +++ b/docs/2019-04/index.html @@ -64,7 +64,7 @@ $ ./fix-metadata-values.py -i /tmp/2019-02-21-fix-4-regions.csv -db dspace -u ds $ ./delete-metadata-values.py -i /tmp/2019-02-21-delete-2-countries.csv -db dspace -u dspace -p 'fuuu' -m 228 -f cg.coverage.country -d $ ./delete-metadata-values.py -i /tmp/2019-02-21-delete-1-region.csv -db dspace -u dspace -p 'fuuu' -m 231 -f cg.coverage.region -d "/> - + diff --git a/docs/2019-05/index.html b/docs/2019-05/index.html index e55ee8af7..6da22d67d 100644 --- a/docs/2019-05/index.html +++ b/docs/2019-05/index.html @@ -48,7 +48,7 @@ DELETE 1 But after this I tried to delete the item from the XMLUI and it is still present… "/> - + diff --git a/docs/2019-06/index.html b/docs/2019-06/index.html index a80728f3f..51fbfc0c7 100644 --- a/docs/2019-06/index.html +++ b/docs/2019-06/index.html @@ -34,7 +34,7 @@ Run system updates on CGSpace (linode18) and reboot it Skype with Marie-Angélique and Abenet about CG Core v2 "/> - + diff --git a/docs/2019-07/index.html b/docs/2019-07/index.html index 1b9a4fd58..46d61f690 100644 --- a/docs/2019-07/index.html +++ b/docs/2019-07/index.html @@ -38,7 +38,7 @@ CGSpace Abenet had another similar issue a few days ago when trying to find the stats for 2018 in the RTB community "/> - + diff --git a/docs/2019-08/index.html b/docs/2019-08/index.html index 714c8a099..686499339 100644 --- a/docs/2019-08/index.html +++ b/docs/2019-08/index.html @@ -46,7 +46,7 @@ After rebooting, all statistics cores were loaded… wow, that’s luck Run system updates on DSpace Test (linode19) and reboot it "/> - + diff --git a/docs/2019-09/index.html b/docs/2019-09/index.html index 26bdb47bd..ffb3e96e5 100644 --- a/docs/2019-09/index.html +++ b/docs/2019-09/index.html @@ -72,7 +72,7 @@ Here are the top ten IPs in the nginx XMLUI and REST/OAI logs this morning: 7249 2a01:7e00::f03c:91ff:fe18:7396 9124 45.5.186.2 "/> - + diff --git a/docs/2019-10/index.html b/docs/2019-10/index.html index 8a8e16f57..1bd2ca6b8 100644 --- a/docs/2019-10/index.html +++ b/docs/2019-10/index.html @@ -18,7 +18,7 @@ - + diff --git a/docs/2019-11/index.html b/docs/2019-11/index.html index d2dcacddc..3c4927bb4 100644 --- a/docs/2019-11/index.html +++ b/docs/2019-11/index.html @@ -58,7 +58,7 @@ Let’s see how many of the REST API requests were for bitstreams (because t # zcat --force /var/log/nginx/rest.log.*.gz | grep -E "[0-9]{1,2}/Oct/2019" | grep -c -E "/rest/bitstreams" 106781 "/> - + diff --git a/docs/2019-12/index.html b/docs/2019-12/index.html index ca20339f0..995ccdb41 100644 --- a/docs/2019-12/index.html +++ b/docs/2019-12/index.html @@ -46,7 +46,7 @@ Make sure all packages are up to date and the package manager is up to date, the # dpkg -C # reboot "/> - + diff --git a/docs/2020-01/index.html b/docs/2020-01/index.html index a41c3044c..04230acec 100644 --- a/docs/2020-01/index.html +++ b/docs/2020-01/index.html @@ -56,7 +56,7 @@ I tweeted the CGSpace repository link "/> - + diff --git a/docs/2020-02/index.html b/docs/2020-02/index.html index 13de39996..fedc0f329 100644 --- a/docs/2020-02/index.html +++ b/docs/2020-02/index.html @@ -38,7 +38,7 @@ The code finally builds and runs with a fresh install "/> - + diff --git a/docs/2020-03/index.html b/docs/2020-03/index.html index a7f50bb1f..63b946572 100644 --- a/docs/2020-03/index.html +++ b/docs/2020-03/index.html @@ -42,7 +42,7 @@ You need to download this into the DSpace 6.x source and compile it "/> - + diff --git a/docs/2020-04/index.html b/docs/2020-04/index.html index f674ea245..0c1fb7519 100644 --- a/docs/2020-04/index.html +++ b/docs/2020-04/index.html @@ -48,7 +48,7 @@ The third item now has a donut with score 1 since I tweeted it last week On the same note, the one item Abenet pointed out last week now has a donut with score of 104 after I tweeted it last week "/> - + diff --git a/docs/2020-05/index.html b/docs/2020-05/index.html index 0b9e191c4..cf59b0296 100644 --- a/docs/2020-05/index.html +++ b/docs/2020-05/index.html @@ -34,7 +34,7 @@ I see that CGSpace (linode18) is still using PostgreSQL JDBC driver version 42.2 "/> - + diff --git a/docs/2020-06/index.html b/docs/2020-06/index.html index b4840c63d..6c3aafd39 100644 --- a/docs/2020-06/index.html +++ b/docs/2020-06/index.html @@ -36,7 +36,7 @@ I sent Atmire the dspace.log from today and told them to log into the server to In other news, I checked the statistics API on DSpace 6 and it’s working I tried to build the OAI registry on the freshly migrated DSpace 6 on DSpace Test and I get an error: "/> - + diff --git a/docs/2020-07/index.html b/docs/2020-07/index.html index 7e53ca75d..5ee59b163 100644 --- a/docs/2020-07/index.html +++ b/docs/2020-07/index.html @@ -38,7 +38,7 @@ I restarted Tomcat and PostgreSQL and the issue was gone Since I was restarting Tomcat anyways I decided to redeploy the latest changes from the 5_x-prod branch and I added a note about COVID-19 items to the CGSpace frontpage at Peter’s request "/> - + diff --git a/docs/2020-08/index.html b/docs/2020-08/index.html index c0ab16a8f..5e91149c9 100644 --- a/docs/2020-08/index.html +++ b/docs/2020-08/index.html @@ -36,7 +36,7 @@ It is class based so I can easily add support for other vocabularies, and the te "/> - + diff --git a/docs/2020-09/index.html b/docs/2020-09/index.html index b8abf5e00..24b3db071 100644 --- a/docs/2020-09/index.html +++ b/docs/2020-09/index.html @@ -48,7 +48,7 @@ I filed a bug on OpenRXV: https://github.com/ilri/OpenRXV/issues/39 I filed an issue on OpenRXV to make some minor edits to the admin UI: https://github.com/ilri/OpenRXV/issues/40 "/> - + diff --git a/docs/2020-10/index.html b/docs/2020-10/index.html index 39c00a694..7467ea24b 100644 --- a/docs/2020-10/index.html +++ b/docs/2020-10/index.html @@ -44,7 +44,7 @@ During the FlywayDB migration I got an error: "/> - + diff --git a/docs/2020-11/index.html b/docs/2020-11/index.html index 9f5950620..c66384272 100644 --- a/docs/2020-11/index.html +++ b/docs/2020-11/index.html @@ -32,7 +32,7 @@ So far we’ve spent at least fifty hours to process the statistics and stat "/> - + diff --git a/docs/2020-12/index.html b/docs/2020-12/index.html index 0ae64af60..ee3641686 100644 --- a/docs/2020-12/index.html +++ b/docs/2020-12/index.html @@ -36,7 +36,7 @@ I started processing those (about 411,000 records): "/> - + diff --git a/docs/2021-01/index.html b/docs/2021-01/index.html index 94093b61c..777dbacf7 100644 --- a/docs/2021-01/index.html +++ b/docs/2021-01/index.html @@ -50,7 +50,7 @@ For example, this item has 51 views on CGSpace, but 0 on AReS "/> - + diff --git a/docs/2021-02/index.html b/docs/2021-02/index.html index f70382406..33968b1f4 100644 --- a/docs/2021-02/index.html +++ b/docs/2021-02/index.html @@ -60,7 +60,7 @@ $ curl -s 'http://localhost:9200/openrxv-items-temp/_count?q=*&pretty } } "/> - + diff --git a/docs/2021-03/index.html b/docs/2021-03/index.html index 4638a70de..65a335289 100644 --- a/docs/2021-03/index.html +++ b/docs/2021-03/index.html @@ -34,7 +34,7 @@ Also, we found some issues building and running OpenRXV currently due to ecosyst "/> - + diff --git a/docs/2021-04/index.html b/docs/2021-04/index.html index 507a3533b..4babee4b5 100644 --- a/docs/2021-04/index.html +++ b/docs/2021-04/index.html @@ -44,7 +44,7 @@ Perhaps one of the containers crashed, I should have looked closer but I was in "/> - + diff --git a/docs/2021-05/index.html b/docs/2021-05/index.html index 3b9f5a3d9..58bfb2a48 100644 --- a/docs/2021-05/index.html +++ b/docs/2021-05/index.html @@ -36,7 +36,7 @@ I looked at the top user agents and IPs in the Solr statistics for last month an I will add the RI/1.0 pattern to our DSpace agents overload and purge them from Solr (we had previously seen this agent with 9,000 hits or so in 2020-09), but I think I will leave the Microsoft Word one… as that’s an actual user… "/> - + diff --git a/docs/2021-06/index.html b/docs/2021-06/index.html index c715f9689..7ff44b911 100644 --- a/docs/2021-06/index.html +++ b/docs/2021-06/index.html @@ -36,7 +36,7 @@ I simply started it and AReS was running again: "/> - + diff --git a/docs/2021-07/index.html b/docs/2021-07/index.html index 4bce5e6da..b4141a9d1 100644 --- a/docs/2021-07/index.html +++ b/docs/2021-07/index.html @@ -30,7 +30,7 @@ Export another list of ALL subjects on CGSpace, including AGROVOC and non-AGROVO localhost/dspace63= > \COPY (SELECT DISTINCT LOWER(text_value) AS subject, count(*) FROM metadatavalue WHERE dspace_object_id in (SELECT dspace_object_id FROM item) AND metadata_field_id IN (119, 120, 127, 122, 128, 125, 135, 203, 208, 210, 215, 123, 236, 242, 187) GROUP BY subject ORDER BY count DESC) to /tmp/2021-07-01-all-subjects.csv WITH CSV HEADER; COPY 20994 "/> - + diff --git a/docs/2021-08/index.html b/docs/2021-08/index.html index 093405e3c..abe8b5287 100644 --- a/docs/2021-08/index.html +++ b/docs/2021-08/index.html @@ -32,7 +32,7 @@ Update Docker images on AReS server (linode20) and reboot the server: I decided to upgrade linode20 from Ubuntu 18.04 to 20.04 "/> - + diff --git a/docs/2021-09/index.html b/docs/2021-09/index.html index e6a458694..df2a8d678 100644 --- a/docs/2021-09/index.html +++ b/docs/2021-09/index.html @@ -48,7 +48,7 @@ The syntax Moayad showed me last month doesn’t seem to honor the search qu "/> - + diff --git a/docs/2021-10/index.html b/docs/2021-10/index.html index 485ac9dfd..7e6114259 100644 --- a/docs/2021-10/index.html +++ b/docs/2021-10/index.html @@ -46,7 +46,7 @@ $ wc -l /tmp/2021-10-01-affiliations.txt So we have 1879/7100 (26.46%) matching already "/> - + diff --git a/docs/2021-11/index.html b/docs/2021-11/index.html index 0dd50503a..886d12590 100644 --- a/docs/2021-11/index.html +++ b/docs/2021-11/index.html @@ -32,7 +32,7 @@ First I exported all the 2019 stats from CGSpace: $ ./run.sh -s http://localhost:8081/solr/statistics -f 'time:2019-*' -a export -o statistics-2019.json -k uid $ zstd statistics-2019.json "/> - + diff --git a/docs/2021-12/index.html b/docs/2021-12/index.html index 97b7ea871..245b7aa25 100644 --- a/docs/2021-12/index.html +++ b/docs/2021-12/index.html @@ -40,7 +40,7 @@ Purging 455 hits from WhatsApp in statistics Total number of bot hits purged: 3679 "/> - + diff --git a/docs/2022-01/index.html b/docs/2022-01/index.html index c2b4eb0d5..558fb583d 100644 --- a/docs/2022-01/index.html +++ b/docs/2022-01/index.html @@ -24,7 +24,7 @@ Start a full harvest on AReS Start a full harvest on AReS "/> - + diff --git a/docs/2022-02/index.html b/docs/2022-02/index.html index 21c16db8e..f34b69440 100644 --- a/docs/2022-02/index.html +++ b/docs/2022-02/index.html @@ -38,7 +38,7 @@ We agreed to try to do more alignment of affiliations/funders with ROR "/> - + diff --git a/docs/2022-03/index.html b/docs/2022-03/index.html index eef15eb55..fa3505504 100644 --- a/docs/2022-03/index.html +++ b/docs/2022-03/index.html @@ -34,7 +34,7 @@ $ ./ilri/check-duplicates.py -i /tmp/tac4.csv -db dspace -u dspace -p 'fuuu& $ 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 "/> - + diff --git a/docs/2022-04/index.html b/docs/2022-04/index.html index 4bacf780e..063acee46 100644 --- a/docs/2022-04/index.html +++ b/docs/2022-04/index.html @@ -18,7 +18,7 @@ - + diff --git a/docs/2022-05/index.html b/docs/2022-05/index.html index 69920ba50..fe2e0d8bb 100644 --- a/docs/2022-05/index.html +++ b/docs/2022-05/index.html @@ -66,7 +66,7 @@ If I query Solr for time:2022-04* AND dns:*msnbot* AND dns:*.msn.com. I see a ha I purged 93,974 hits from these IPs using my check-spider-ip-hits.sh script "/> - + diff --git a/docs/2022-06/index.html b/docs/2022-06/index.html index 85fa733f8..309ce988a 100644 --- a/docs/2022-06/index.html +++ b/docs/2022-06/index.html @@ -48,7 +48,7 @@ There seem to be many more of these: "/> - + diff --git a/docs/2022-07/index.html b/docs/2022-07/index.html index 99e418bf5..8adc494a3 100644 --- a/docs/2022-07/index.html +++ b/docs/2022-07/index.html @@ -34,7 +34,7 @@ Also, the trgm functions I’ve used before are case insensitive, but Levens "/> - + diff --git a/docs/2022-08/index.html b/docs/2022-08/index.html index ee516a06d..5db376d73 100644 --- a/docs/2022-08/index.html +++ b/docs/2022-08/index.html @@ -24,7 +24,7 @@ Our request to add CC-BY-3.0-IGO to SPDX was approved a few weeks ago Our request to add CC-BY-3.0-IGO to SPDX was approved a few weeks ago "/> - + diff --git a/docs/2022-09/index.html b/docs/2022-09/index.html index 7292688e8..7019229aa 100644 --- a/docs/2022-09/index.html +++ b/docs/2022-09/index.html @@ -46,7 +46,7 @@ I also fixed a few bugs and improved the region-matching logic "/> - + diff --git a/docs/2022-10/index.html b/docs/2022-10/index.html index 337a74ea0..cee218601 100644 --- a/docs/2022-10/index.html +++ b/docs/2022-10/index.html @@ -36,7 +36,7 @@ I filed an issue to ask about Java 11+ support "/> - + diff --git a/docs/2022-11/index.html b/docs/2022-11/index.html index 16794ecfa..60305914c 100644 --- a/docs/2022-11/index.html +++ b/docs/2022-11/index.html @@ -44,7 +44,7 @@ I want to make sure they use groups instead of individuals where possible! I reverted the Cocoon autosave change because it was more of a nuissance that Peter can’t upload CSVs from the web interface and is a very low severity security issue "/> - + diff --git a/docs/2022-12/index.html b/docs/2022-12/index.html index 6e4971304..f291c512a 100644 --- a/docs/2022-12/index.html +++ b/docs/2022-12/index.html @@ -36,7 +36,7 @@ I exported the CCAFS and IITA communities, extracted just the country and region Add a few more authors to my CSV with author names and ORCID identifiers and tag 283 items! Replace “East Asia” with “Eastern Asia” region on CGSpace (UN M.49 region) "/> - + diff --git a/docs/2023-01/index.html b/docs/2023-01/index.html index 459db0d92..41ddc136d 100644 --- a/docs/2023-01/index.html +++ b/docs/2023-01/index.html @@ -34,7 +34,7 @@ I see we have some new ones that aren’t in our list if I combine with this "/> - + diff --git a/docs/2023-02/index.html b/docs/2023-02/index.html index 0919e7992..00d63ef8b 100644 --- a/docs/2023-02/index.html +++ b/docs/2023-02/index.html @@ -32,7 +32,7 @@ I want to try to expand my use of their data to journals, publishers, volumes, i "/> - + diff --git a/docs/2023-03/index.html b/docs/2023-03/index.html index 0ede20f24..4b53f30ef 100644 --- a/docs/2023-03/index.html +++ b/docs/2023-03/index.html @@ -28,7 +28,7 @@ Remove cg.subject.wle and cg.identifier.wletheme from CGSpace input form after c iso-codes 4.13.0 was released, which incorporates my changes to the common names for Iran, Laos, and Syria I finally got through with porting the input form from DSpace 6 to DSpace 7 "/> - + diff --git a/docs/2023-04/index.html b/docs/2023-04/index.html index 754e331f1..1c1ded563 100644 --- a/docs/2023-04/index.html +++ b/docs/2023-04/index.html @@ -36,7 +36,7 @@ I also did a check for missing country/region mappings with csv-metadata-quality Start a harvest on AReS "/> - + diff --git a/docs/2023-05/index.html b/docs/2023-05/index.html index 9b6efb502..c63ed90c0 100644 --- a/docs/2023-05/index.html +++ b/docs/2023-05/index.html @@ -46,7 +46,7 @@ Also I found at least two spelling mistakes, for example “decison support Work on cleaning, proofing, and uploading twenty-seven records for IFPRI to CGSpace "/> - + diff --git a/docs/2023-06/index.html b/docs/2023-06/index.html index 148f0e6ca..425cd6d63 100644 --- a/docs/2023-06/index.html +++ b/docs/2023-06/index.html @@ -44,7 +44,7 @@ From what I can see we need to upgrade the MODS schema from 3.1 to 3.7 and then "/> - + diff --git a/docs/2023-07/index.html b/docs/2023-07/index.html index 195b06caf..07b799c28 100644 --- a/docs/2023-07/index.html +++ b/docs/2023-07/index.html @@ -18,7 +18,7 @@ - + diff --git a/docs/2023-08/index.html b/docs/2023-08/index.html index 1678d646b..f6d73e5dc 100644 --- a/docs/2023-08/index.html +++ b/docs/2023-08/index.html @@ -34,7 +34,7 @@ I did some minor cleanups myself and applied them to CGSpace Start working on some batch uploads for IFPRI "/> - + diff --git a/docs/2023-09/index.html b/docs/2023-09/index.html index 88c7d2796..ea03c262f 100644 --- a/docs/2023-09/index.html +++ b/docs/2023-09/index.html @@ -26,7 +26,7 @@ Start a harvest on AReS Export CGSpace to check for missing Initiative collection mappings Start a harvest on AReS "/> - + diff --git a/docs/2023-10/index.html b/docs/2023-10/index.html index 186907ecf..c9dedd531 100644 --- a/docs/2023-10/index.html +++ b/docs/2023-10/index.html @@ -36,7 +36,7 @@ We can be on the safe side by using only abstracts for items that are licensed u "/> - + diff --git a/docs/2023-11/index.html b/docs/2023-11/index.html index dbbe537f2..0c8145198 100644 --- a/docs/2023-11/index.html +++ b/docs/2023-11/index.html @@ -42,7 +42,7 @@ I improved the filtering and wrote some Python using pandas to merge my sources Export CGSpace to check missing Initiative collection mappings Start a harvest on AReS "/> - + diff --git a/docs/2023-12/index.html b/docs/2023-12/index.html index 283f3b064..3b39e362d 100644 --- a/docs/2023-12/index.html +++ b/docs/2023-12/index.html @@ -18,7 +18,7 @@ - + diff --git a/docs/2024-01/index.html b/docs/2024-01/index.html index 514981eb7..4991e897d 100644 --- a/docs/2024-01/index.html +++ b/docs/2024-01/index.html @@ -40,7 +40,7 @@ I sent the bundle to the Handle admins to make sure it’s OK before we do t Continue testing and debugging the cgspace-java-helpers on DSpace 7 Work on IFPRI ISNAR archive cleanup "/> - + diff --git a/docs/2024-02/index.html b/docs/2024-02/index.html index 5c388c3e1..5400d6ac7 100644 --- a/docs/2024-02/index.html +++ b/docs/2024-02/index.html @@ -26,7 +26,7 @@ Lower case all the AGROVOC subjects on CGSpace Delete duplicate metadata as described in my DSpace issue from last year: https://github.com/DSpace/DSpace/issues/8253 Lower case all the AGROVOC subjects on CGSpace "/> - + diff --git a/docs/2024-03/index.html b/docs/2024-03/index.html index 20cc0bdad..c3a03c9c9 100644 --- a/docs/2024-03/index.html +++ b/docs/2024-03/index.html @@ -19,7 +19,7 @@ It might be this issue: https://github.com/DSpace/dspace-angular/issues/2808 - + @@ -34,7 +34,7 @@ It might be this issue: https://github.com/DSpace/dspace-angular/issues/2808 "/> - + @@ -44,9 +44,9 @@ It might be this issue: https://github.com/DSpace/dspace-angular/issues/2808 "@type": "BlogPosting", "headline": "March, 2024", "url": "https://alanorth.github.io/cgspace-notes/2024-03/", - "wordCount": "93", + "wordCount": "317", "datePublished": "2024-03-01T09:55:00+03:00", - "dateModified": "2024-03-01T09:55:00+03:00", + "dateModified": "2024-03-04T10:02:14+03:00", "author": { "@type": "Person", "name": "Alan Orth" @@ -141,6 +141,51 @@ It might be this issue: https://github.com/DSpace/dspace-angular/issues/2808
  • I did some cleanups on abstracts, licenses, and dates from CrossRef
  • I also did some minor cleanups to affiliations because I saw some incorrect and duplicate ones in our list
    • +

    2024-03-05

    + +

    2024-03-06

    + +

    2024-03-08

    + +
    import re
+
+with open(r"/tmp/cg-creator-identifier.txt",'r') as f :
+    orcid_ids = [orcid_id.strip() for orcid_id in f]
+
+matched = False
+for orcid_id in orcid_ids:
+    if re.search(r'.+: {}'.format(value), orcid_id):
+        matched = True
+        break
+
+if matched:
+    return orcid_id
+else:
+    return value
+
    +
    UPDATE metadatavalue SET text_value='United Nations Children''s Fund' WHERE dspace_object_id IN (SELECT uuid FROM item) AND text_value IN ('United Nations International Children''s Emergency Fund', 'United Nations International Children''s Emergency Fund', 'UNICEF');
+
    diff --git a/docs/404.html b/docs/404.html index 0510fe45f..1e356be9e 100644 --- a/docs/404.html +++ b/docs/404.html @@ -17,7 +17,7 @@ - + diff --git a/docs/categories/index.html b/docs/categories/index.html index 32baa1a9a..70aabf526 100644 --- a/docs/categories/index.html +++ b/docs/categories/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/categories/index.xml b/docs/categories/index.xml index 73d74977f..f6b02a371 100644 --- a/docs/categories/index.xml +++ b/docs/categories/index.xml @@ -6,7 +6,7 @@ Recent content in Categories on CGSpace Notes Hugo -- gohugo.io en-us - Fri, 01 Mar 2024 09:55:02 +0300 + Mon, 04 Mar 2024 10:02:14 +0300 Notes diff --git a/docs/categories/notes/index.html b/docs/categories/notes/index.html index a867a057d..89132c1cb 100644 --- a/docs/categories/notes/index.html +++ b/docs/categories/notes/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/categories/notes/index.xml b/docs/categories/notes/index.xml index 880bfd7d0..3fdcc0d00 100644 --- a/docs/categories/notes/index.xml +++ b/docs/categories/notes/index.xml @@ -6,7 +6,7 @@ Recent content in Notes on CGSpace Notes Hugo -- gohugo.io en-us - Fri, 01 Mar 2024 09:55:02 +0300 + Mon, 04 Mar 2024 10:02:14 +0300 March, 2024 diff --git a/docs/categories/notes/page/2/index.html b/docs/categories/notes/page/2/index.html index 0c04bc3ac..602f51e43 100644 --- a/docs/categories/notes/page/2/index.html +++ b/docs/categories/notes/page/2/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/categories/notes/page/3/index.html b/docs/categories/notes/page/3/index.html index 1f914e118..a2452f68e 100644 --- a/docs/categories/notes/page/3/index.html +++ b/docs/categories/notes/page/3/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/categories/notes/page/4/index.html b/docs/categories/notes/page/4/index.html index 2082d12a1..e2f181abd 100644 --- a/docs/categories/notes/page/4/index.html +++ b/docs/categories/notes/page/4/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/categories/notes/page/5/index.html b/docs/categories/notes/page/5/index.html index 5914995ff..4b3fde71f 100644 --- a/docs/categories/notes/page/5/index.html +++ b/docs/categories/notes/page/5/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/categories/notes/page/6/index.html b/docs/categories/notes/page/6/index.html index a1be7e8f7..50567623e 100644 --- a/docs/categories/notes/page/6/index.html +++ b/docs/categories/notes/page/6/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/categories/notes/page/7/index.html b/docs/categories/notes/page/7/index.html index 1ec39e903..82c87fd3f 100644 --- a/docs/categories/notes/page/7/index.html +++ b/docs/categories/notes/page/7/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/categories/notes/page/8/index.html b/docs/categories/notes/page/8/index.html index 9f76aa656..0588a583b 100644 --- a/docs/categories/notes/page/8/index.html +++ b/docs/categories/notes/page/8/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/categories/notes/page/9/index.html b/docs/categories/notes/page/9/index.html index 4945c1b02..c1add2d33 100644 --- a/docs/categories/notes/page/9/index.html +++ b/docs/categories/notes/page/9/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/cgiar-library-migration/index.html b/docs/cgiar-library-migration/index.html index 9b821d02a..31e2d44af 100644 --- a/docs/cgiar-library-migration/index.html +++ b/docs/cgiar-library-migration/index.html @@ -18,7 +18,7 @@ - + diff --git a/docs/cgspace-cgcorev2-migration/index.html b/docs/cgspace-cgcorev2-migration/index.html index bc7fb6398..a7719546a 100644 --- a/docs/cgspace-cgcorev2-migration/index.html +++ b/docs/cgspace-cgcorev2-migration/index.html @@ -18,7 +18,7 @@ - + diff --git a/docs/cgspace-dspace6-upgrade/index.html b/docs/cgspace-dspace6-upgrade/index.html index 5077c8843..93622f8a0 100644 --- a/docs/cgspace-dspace6-upgrade/index.html +++ b/docs/cgspace-dspace6-upgrade/index.html @@ -18,7 +18,7 @@ - + diff --git a/docs/index.html b/docs/index.html index e64f2a16d..41db5a193 100644 --- a/docs/index.html +++ b/docs/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/index.xml b/docs/index.xml index 95a3351ac..fb9901bfe 100644 --- a/docs/index.xml +++ b/docs/index.xml @@ -6,7 +6,7 @@ Recent content on CGSpace Notes Hugo -- gohugo.io en-us - Fri, 01 Mar 2024 09:55:02 +0300 + Mon, 04 Mar 2024 10:02:14 +0300 March, 2024 diff --git a/docs/page/10/index.html b/docs/page/10/index.html index 7e0639675..c40cca0e4 100644 --- a/docs/page/10/index.html +++ b/docs/page/10/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/page/11/index.html b/docs/page/11/index.html index 5f774781f..751eb45aa 100644 --- a/docs/page/11/index.html +++ b/docs/page/11/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/page/2/index.html b/docs/page/2/index.html index ce5f53bfb..a77552979 100644 --- a/docs/page/2/index.html +++ b/docs/page/2/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/page/3/index.html b/docs/page/3/index.html index c0664a09f..e1e465e33 100644 --- a/docs/page/3/index.html +++ b/docs/page/3/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/page/4/index.html b/docs/page/4/index.html index 634171958..fa5a4604a 100644 --- a/docs/page/4/index.html +++ b/docs/page/4/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/page/5/index.html b/docs/page/5/index.html index 9e2c8854d..05968fcdb 100644 --- a/docs/page/5/index.html +++ b/docs/page/5/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/page/6/index.html b/docs/page/6/index.html index 1ee71aa26..8b076c941 100644 --- a/docs/page/6/index.html +++ b/docs/page/6/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/page/7/index.html b/docs/page/7/index.html index 3771b63a4..1378201c5 100644 --- a/docs/page/7/index.html +++ b/docs/page/7/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/page/8/index.html b/docs/page/8/index.html index e4465da23..2e35f57ba 100644 --- a/docs/page/8/index.html +++ b/docs/page/8/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/page/9/index.html b/docs/page/9/index.html index 27ef6cc8e..6045f83d0 100644 --- a/docs/page/9/index.html +++ b/docs/page/9/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/posts/index.html b/docs/posts/index.html index 2a987efea..e9b73eade 100644 --- a/docs/posts/index.html +++ b/docs/posts/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/posts/index.xml b/docs/posts/index.xml index c9d2a6f0d..ce4d64938 100644 --- a/docs/posts/index.xml +++ b/docs/posts/index.xml @@ -6,7 +6,7 @@ Recent content in Posts on CGSpace Notes Hugo -- gohugo.io en-us - Fri, 01 Mar 2024 09:55:02 +0300 + Mon, 04 Mar 2024 10:02:14 +0300 March, 2024 diff --git a/docs/posts/page/10/index.html b/docs/posts/page/10/index.html index b9b8b2282..c3ea9d2b5 100644 --- a/docs/posts/page/10/index.html +++ b/docs/posts/page/10/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/posts/page/11/index.html b/docs/posts/page/11/index.html index 39bbb0470..233c4299f 100644 --- a/docs/posts/page/11/index.html +++ b/docs/posts/page/11/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/posts/page/2/index.html b/docs/posts/page/2/index.html index 428e139c7..3b024ca27 100644 --- a/docs/posts/page/2/index.html +++ b/docs/posts/page/2/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/posts/page/3/index.html b/docs/posts/page/3/index.html index 880a06f9b..17b07c4b4 100644 --- a/docs/posts/page/3/index.html +++ b/docs/posts/page/3/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/posts/page/4/index.html b/docs/posts/page/4/index.html index 68472fd25..c21cea271 100644 --- a/docs/posts/page/4/index.html +++ b/docs/posts/page/4/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/posts/page/5/index.html b/docs/posts/page/5/index.html index 6b19169c5..1afd8110a 100644 --- a/docs/posts/page/5/index.html +++ b/docs/posts/page/5/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/posts/page/6/index.html b/docs/posts/page/6/index.html index aba321d9e..9f30e98dc 100644 --- a/docs/posts/page/6/index.html +++ b/docs/posts/page/6/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/posts/page/7/index.html b/docs/posts/page/7/index.html index 11f29dce1..607bc6a3a 100644 --- a/docs/posts/page/7/index.html +++ b/docs/posts/page/7/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/posts/page/8/index.html b/docs/posts/page/8/index.html index 5921db4b9..d7330f762 100644 --- a/docs/posts/page/8/index.html +++ b/docs/posts/page/8/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/posts/page/9/index.html b/docs/posts/page/9/index.html index effa51b6a..38989af93 100644 --- a/docs/posts/page/9/index.html +++ b/docs/posts/page/9/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/sitemap.xml b/docs/sitemap.xml index f9629cc8c..9c4270d93 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/ - 2024-03-01T09:55:02+03:00 + 2024-03-04T10:02:14+03:00 https://alanorth.github.io/cgspace-notes/ - 2024-03-01T09:55:02+03:00 + 2024-03-04T10:02:14+03:00 https://alanorth.github.io/cgspace-notes/2024-03/ - 2024-03-01T09:55:00+03:00 + 2024-03-04T10:02:14+03:00 https://alanorth.github.io/cgspace-notes/categories/notes/ - 2024-03-01T09:55:02+03:00 + 2024-03-04T10:02:14+03:00 https://alanorth.github.io/cgspace-notes/posts/ - 2024-03-01T09:55:02+03:00 + 2024-03-04T10:02:14+03:00 https://alanorth.github.io/cgspace-notes/2024-02/ 2024-03-01T09:55:02+03:00 diff --git a/docs/tags/index.html b/docs/tags/index.html index 82a2ae75b..fd447f03f 100644 --- a/docs/tags/index.html +++ b/docs/tags/index.html @@ -17,7 +17,7 @@ - + diff --git a/docs/tags/migration/index.html b/docs/tags/migration/index.html index 620df66fb..3e6e42715 100644 --- a/docs/tags/migration/index.html +++ b/docs/tags/migration/index.html @@ -17,7 +17,7 @@ - + diff --git a/docs/tags/notes/index.html b/docs/tags/notes/index.html index f117d0a5b..7ecfbc295 100644 --- a/docs/tags/notes/index.html +++ b/docs/tags/notes/index.html @@ -17,7 +17,7 @@ - + diff --git a/docs/tags/notes/page/2/index.html b/docs/tags/notes/page/2/index.html index 89549a35c..ce8b9fe80 100644 --- a/docs/tags/notes/page/2/index.html +++ b/docs/tags/notes/page/2/index.html @@ -17,7 +17,7 @@ - + diff --git a/docs/tags/notes/page/3/index.html b/docs/tags/notes/page/3/index.html index ccede39ab..9a6c3288c 100644 --- a/docs/tags/notes/page/3/index.html +++ b/docs/tags/notes/page/3/index.html @@ -17,7 +17,7 @@ - +