From 223453adbbc8b4fd4e8f33e1ae77ca7aa6992808 Mon Sep 17 00:00:00 2001 From: Alan Orth Date: Mon, 13 May 2024 08:21:17 +0300 Subject: [PATCH] Add notes for 2023-05-13 --- content/posts/2024-05.md | 48 +++++++++++++++++ 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 | 2 +- docs/2024-04/index.html | 2 +- docs/2024-05/index.html | 62 ++++++++++++++++++++-- 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 +- 150 files changed, 290 insertions(+), 188 deletions(-) diff --git a/content/posts/2024-05.md b/content/posts/2024-05.md index 79b3ddea2..f054d64ea 100644 --- a/content/posts/2024-05.md +++ b/content/posts/2024-05.md @@ -16,4 +16,52 @@ categories: ["Notes"] - Spend some time looking at duplicate DOIs again... +## 2024-05-06 + +- Spend some time looking at duplicate DOIs again... + +## 2024-05-07 + +- Discuss RSS feeds and OpenSearch with IWMI + - It seems our OpenSearch feed settings are using the defaults, so I need to copy some of those over from our old DSpace 6 branch +- I saw a patch for an interesting issue on DSpace GitHub: [Error submitting or deleting items - URI too long when user is in a large number of groups](https://github.com/DSpace/DSpace/issues/9544) + - I hadn't realized it, but we have lots of those errors: + +```console +$ zstdgrep -a 'URI Too Long' log/dspace.log-2024-04-* | wc -l +1423 +``` + +- Spend some time looking at duplicate DOIs again... + +## 2024-05-08 + +- Spend some time looking at duplicate DOIs again... + - I finally finished looking at the duplicate DOIs for journal articles + - I updated the list of handle redirects and there are 386 of them! + +## 2024-05-09 + +- Spend some time working on the IFPRI 2020–2021 batch + - I started by checking for exact duplicates (1.0 similarity) using DOI, type, and issue date + +## 2024-05-12 + +- I couldn't figure out how to do a complex join on withdrawn items along with their metadata, so I pull out a few like titles, handles, and provenance separately: + +```psql +dspace=# \COPY (SELECT i.uuid, m.text_value AS uri FROM item i JOIN metadatavalue m ON i.uuid = m.dspace_object_id WHERE withdrawn AND m.metadata_field_id=25) TO /tmp/withdrawn-handles.csv CSV HEADER; +dspace=# \COPY (SELECT i.uuid, m.text_value AS title FROM item i JOIN metadatavalue m ON i.uuid = m.dspace_object_id WHERE withdrawn AND m.metadata_field_id=64) TO /tmp/withdrawn-titles.csv CSV HEADER; +dspace=# \COPY (SELECT i.uuid, m.text_value AS submitted_by FROM item i JOIN metadatavalue m ON i.uuid = m.dspace_object_id WHERE withdrawn AND m.metadata_field_id=28 AND m.text_value LIKE 'Submitted by%') TO /tmp/withdrawn-submitted-by.csv CSV HEADER; +``` + +- Then joined them: + +```console +$ csvjoin -c uuid /tmp/withdrawn-title.csv /tmp/withdrawn-handles.csv /tmp/withdrawn-submitted-by.csv > /tmp/withdrawn.csv +``` + +- This gives me an insight into who submitted at 334 of the duplicates over the past few years... +- I fixed a few hundred titles with leading/trailing whitespace, newlines, and ligatures like ff, fi, fl, ffi, and ffl + diff --git a/docs/2015-11/index.html b/docs/2015-11/index.html index 16066bff6..4b54fa4ff 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 83eb46843..2d29da4f7 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 ddd52da2b..b417ad910 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 d762c126a..4234a6842 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 ee970cfcc..f87bf7ac9 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 710fd5e5e..dfe288562 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 e56def67b..ff3121674 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 ab9491a53..d8bb0a49a 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 7c151a34a..cd7947b04 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 5a1295b97..59ffeb1c9 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 c2c51244f..b7c519603 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 605d7b4c2..a050141f5 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 fdd87918f..6ad400ffa 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 80f2082c1..4c60069b6 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 2722f09c9..51298957a 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 e0800e6fd..14f179838 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 7926f3378..2a4cec7d9 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 e27a9d61a..91b1a4ce7 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 892609ab3..04c7df790 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 d7dbbbbc9..33189f156 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 7f2948a46..e9a2bc4b0 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 edb25c7e9..3beb96867 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 566bfa80f..e2b08e802 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 3ebfe68af..69c1f18c3 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 74c665506..08bb59973 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 8d7e85e06..fce8d89f6 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 e3f2fec4e..77fc1df54 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 a809a5e7f..3150ebcb9 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 45773f400..d2f2b6df6 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 afe448f1b..46ec0cec1 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 5df43cb50..12328c007 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 7fe6508f7..210b7caed 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 12375262f..f6b377e87 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 16307a1c9..666503d91 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 aa7bb48ba..607c592f0 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 5e82950e0..f61039a3f 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 dd72b59fd..2bf89f4bf 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 a6e5fac87..f9edd2aaf 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 052d0e056..b33fc609a 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 44eb40eea..0d289ee79 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 5596f2538..30dad6bd5 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 48eca5009..709ccb741 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 422cb6b71..45fd57bd1 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 7775aa164..d1324b319 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 c7b3504a2..42859dc10 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 630951544..0958e3f1a 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 dc817a662..f42f4eee8 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 2178cf52e..4ae186e21 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 f029e2d67..2d41d6514 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 03ce9a48c..e1d7d9b07 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 3b9456073..92da8423d 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 ac883bed1..3c3be5a23 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 0215facd5..e705cc840 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 c86304919..89b4c9dd5 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 402de0034..72b02112b 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 2adb348cf..5384ba863 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 bdf46326a..ac5b8dfea 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 56e7504eb..73b29a3c5 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 cb701e0de..d7628b585 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 9c1f2ab0f..23de0d828 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 6fef50ec7..4b4716618 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 e890d66ad..511231286 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 a8e98c2d3..fd5997a90 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 73c4645df..05e88590e 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 a2b05234e..a8e815443 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 8e287d3a1..e3600b5ee 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 031e21c1c..8592a64cf 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 8a9f9fb54..38c9a9fc1 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 f45f4f460..594fb129d 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 8fcedfbb3..674946bc3 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 f8c7d9497..5cce49793 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 2ce9fd992..06c5f1fa2 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 6c45ac9e0..f719dce85 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 9c5a981c8..144e54bd9 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 9ac2a32de..3550dd491 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 020986f60..c03b989b8 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 bc33c708b..5a3ce23c6 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 4bb4ce49c..b2e1ce6ba 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 ee526d018..80d5af0d0 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 5350d9091..3e40f8f2d 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 cf9115dc7..a6c0f9f3d 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 6f67abae6..dbfa87790 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 b23a8ad28..a0514cba4 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 3fd51cd1c..6d5692167 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 7c89136c4..f3703f3c0 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 77f9afffd..147a8f76a 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 1471f0131..171eed30e 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 83ae0c48d..008ab5830 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 0eedb6bf3..4deb48ea5 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 489d418ee..979a5d702 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 9fd9e09c0..c35a980d4 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 0d6fd081a..47deea61c 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 26a51a191..6425ac4d3 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 c5d549193..561532462 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 1e2d5eacf..61f0a6a50 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 6bc1632ff..bb4642f41 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 267a6c592..8d9fbd1f7 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 aefe2a98a..9bf83c7a8 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 6b77decc8..32833938b 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 5de738789..935a92f4c 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 0fe5ac74e..9520fe2ea 100644 --- a/docs/2024-03/index.html +++ b/docs/2024-03/index.html @@ -34,7 +34,7 @@ It might be this issue: https://github.com/DSpace/dspace-angular/issues/2808 "/> - + diff --git a/docs/2024-04/index.html b/docs/2024-04/index.html index ec34aea60..ffc9714af 100644 --- a/docs/2024-04/index.html +++ b/docs/2024-04/index.html @@ -24,7 +24,7 @@ Work on CGSpace duplicate DOIs more Work on CGSpace duplicate DOIs more "/> - + diff --git a/docs/2024-05/index.html b/docs/2024-05/index.html index d5fe242ce..795747107 100644 --- a/docs/2024-05/index.html +++ b/docs/2024-05/index.html @@ -18,7 +18,7 @@ Then I did some work to add missing abstracts (about 900!), volumes, issues, lic - + @@ -32,7 +32,7 @@ Then I did some work to add missing abstracts (about 900!), volumes, issues, lic "/> - + @@ -42,9 +42,9 @@ Then I did some work to add missing abstracts (about 900!), volumes, issues, lic "@type": "BlogPosting", "headline": "May, 2024", "url": "https://alanorth.github.io/cgspace-notes/2024-05/", - "wordCount": "41", + "wordCount": "359", "datePublished": "2024-05-01T10:39:00+03:00", - "dateModified": "2024-05-01T17:10:05+03:00", + "dateModified": "2024-05-05T21:43:52+03:00", "author": { "@type": "Person", "name": "Alan Orth" @@ -130,6 +130,60 @@ Then I did some work to add missing abstracts (about 900!), volumes, issues, lic +

2024-05-06

+ +

2024-05-07

+ +
$ zstdgrep -a 'URI Too Long' log/dspace.log-2024-04-* | wc -l
+1423
+
+

2024-05-08

+ +

2024-05-09

+ +

2024-05-12

+ +
dspace=# \COPY (SELECT i.uuid, m.text_value AS uri FROM item i JOIN metadatavalue m ON i.uuid = m.dspace_object_id WHERE withdrawn AND m.metadata_field_id=25) TO /tmp/withdrawn-handles.csv CSV HEADER;
+dspace=# \COPY (SELECT i.uuid, m.text_value AS title FROM item i JOIN metadatavalue m ON i.uuid = m.dspace_object_id WHERE withdrawn AND m.metadata_field_id=64) TO /tmp/withdrawn-titles.csv CSV HEADER;
+dspace=# \COPY (SELECT i.uuid, m.text_value AS submitted_by FROM item i JOIN metadatavalue m ON i.uuid = m.dspace_object_id WHERE withdrawn AND m.metadata_field_id=28 AND m.text_value LIKE 'Submitted by%') TO /tmp/withdrawn-submitted-by.csv CSV HEADER;
+
+
$ csvjoin -c uuid /tmp/withdrawn-title.csv /tmp/withdrawn-handles.csv /tmp/withdrawn-submitted-by.csv > /tmp/withdrawn.csv
+
diff --git a/docs/404.html b/docs/404.html index cdd4e789a..78eb0374d 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 eff7294e0..bd5cce247 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 704584827..127593168 100644 --- a/docs/categories/index.xml +++ b/docs/categories/index.xml @@ -6,7 +6,7 @@ Recent content in Categories on CGSpace Notes Hugo en-us - Wed, 01 May 2024 17:10:05 +0300 + Sun, 05 May 2024 21:43:52 +0300 Notes diff --git a/docs/categories/notes/index.html b/docs/categories/notes/index.html index 4a04742ee..c4422dcea 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 8fed944fd..718fa36f0 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 en-us - Wed, 01 May 2024 17:10:05 +0300 + Sun, 05 May 2024 21:43:52 +0300 May, 2024 diff --git a/docs/categories/notes/page/2/index.html b/docs/categories/notes/page/2/index.html index 88155862e..ba01353d2 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 c849fe1a2..4df03b395 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 e0dec53b1..b4778076a 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 19b886b46..753811b7f 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 2fd732eb1..ef6be6875 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 406169dd6..2d4eda2a9 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 85a3a009f..1faa40093 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 545e7e628..0677cfc19 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 2fafba71c..aef4d97a4 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 2b0d127e5..6c20653cb 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 066ac46a3..35a686c4c 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 ea4edb62e..be5db493d 100644 --- a/docs/index.html +++ b/docs/index.html @@ -10,14 +10,14 @@ - + - + diff --git a/docs/index.xml b/docs/index.xml index ef6eeea02..2b30a69d1 100644 --- a/docs/index.xml +++ b/docs/index.xml @@ -6,7 +6,7 @@ Recent content on CGSpace Notes Hugo en-us - Wed, 01 May 2024 17:10:05 +0300 + Sun, 05 May 2024 21:43:52 +0300 May, 2024 diff --git a/docs/page/10/index.html b/docs/page/10/index.html index cdb0b46fc..bad042ded 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 f6fbbc92a..20f542332 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 b2b4703eb..11e6d22af 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 1da857b32..86dd82b2e 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 49c395483..dd2f18b3d 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 c05781c4a..24aac9861 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 61c594c4b..47bfeb070 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 521ed5bfe..1f571dc89 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 885b7a312..65ac70aaf 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 6ea75812c..127162f38 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 ee7d3a90c..0ad80352d 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 d57f5c8ac..7cded0aa5 100644 --- a/docs/posts/index.xml +++ b/docs/posts/index.xml @@ -6,7 +6,7 @@ Recent content in Posts on CGSpace Notes Hugo en-us - Wed, 01 May 2024 17:10:05 +0300 + Sun, 05 May 2024 21:43:52 +0300 May, 2024 diff --git a/docs/posts/page/10/index.html b/docs/posts/page/10/index.html index 856ed8b68..af7a58737 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 2f70a146f..6030d62f9 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 2a5dc7487..be3c0067d 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 75f1b0e46..c2419fe13 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 cd3152ef1..932476aed 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 a8b42b007..0cac92b3e 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 ad5e0a10a..0ad1814a1 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 ae44fc2c8..51c4cc03d 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 a5e526cc2..f8efc610a 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 3816c15b8..57a575960 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 e3eb43985..1e67a32ce 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/ - 2024-05-01T17:10:05+03:00 + 2024-05-05T21:43:52+03:00 https://alanorth.github.io/cgspace-notes/ - 2024-05-01T17:10:05+03:00 + 2024-05-05T21:43:52+03:00 https://alanorth.github.io/cgspace-notes/2024-05/ - 2024-05-01T17:10:05+03:00 + 2024-05-05T21:43:52+03:00 https://alanorth.github.io/cgspace-notes/categories/notes/ - 2024-05-01T17:10:05+03:00 + 2024-05-05T21:43:52+03:00 https://alanorth.github.io/cgspace-notes/posts/ - 2024-05-01T17:10:05+03:00 + 2024-05-05T21:43:52+03:00 https://alanorth.github.io/cgspace-notes/2024-04/ 2024-04-29T17:21:28+03:00 diff --git a/docs/tags/index.html b/docs/tags/index.html index 7f6b75729..da8b978ec 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 3272bbf71..2e03f49bd 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 2fdf4befe..0f3e6e1c0 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 c614ec14c..46aeec5f2 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 56c0700b8..28ba29d05 100644 --- a/docs/tags/notes/page/3/index.html +++ b/docs/tags/notes/page/3/index.html @@ -17,7 +17,7 @@ - +