From dc637490f134bed3b887dae0766eb3a0b8cc641a Mon Sep 17 00:00:00 2001 From: Alan Orth Date: Tue, 11 Feb 2020 12:52:11 +0200 Subject: [PATCH] Add notes for 2020-02-11 --- content/posts/2020-02.md | 47 ++++++++++++++++++++ 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 | 6 +-- docs/2020-02/index.html | 50 ++++++++++++++++++++-- docs/404.html | 2 +- docs/categories/index.html | 2 +- docs/categories/notes/index.html | 2 +- docs/categories/notes/page/2/index.html | 2 +- docs/categories/notes/page/3/index.html | 2 +- docs/categories/notes/page/4/index.html | 2 +- docs/categories/page/2/index.html | 2 +- docs/categories/page/3/index.html | 2 +- docs/categories/page/4/index.html | 2 +- docs/categories/page/5/index.html | 2 +- docs/categories/page/6/index.html | 2 +- docs/cgiar-library-migration/index.html | 2 +- docs/cgspace-cgcorev2-migration/index.html | 2 +- docs/index.html | 2 +- docs/page/2/index.html | 2 +- docs/page/3/index.html | 2 +- docs/page/4/index.html | 2 +- docs/page/5/index.html | 2 +- docs/page/6/index.html | 2 +- docs/posts/index.html | 2 +- docs/posts/page/2/index.html | 2 +- docs/posts/page/3/index.html | 2 +- docs/posts/page/4/index.html | 2 +- docs/posts/page/5/index.html | 2 +- docs/posts/page/6/index.html | 2 +- docs/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 +- docs/tags/page/2/index.html | 2 +- docs/tags/page/3/index.html | 2 +- docs/tags/page/4/index.html | 2 +- docs/tags/page/5/index.html | 2 +- docs/tags/page/6/index.html | 2 +- 89 files changed, 187 insertions(+), 96 deletions(-) diff --git a/content/posts/2020-02.md b/content/posts/2020-02.md index 279e13608..1a9646c25 100644 --- a/content/posts/2020-02.md +++ b/content/posts/2020-02.md @@ -389,4 +389,51 @@ $ cat out.dspace510-1 | ../FlameGraph/stackcollapse-perf.pl | grep -E '^java' | - He uploaded them here: https://cgspace.cgiar.org/handle/10568/105926 - On a whim I checked and found five duplicates there, which means Sisay didn't even check +## 2020-02-10 + +- Follow up with [Atmire about DSpace 6.x upgrade](https://tracker.atmire.com/tickets-cgiar-ilri/view-ticket?id=706) + - I raised the issue of targetting 6.4-SNAPSHOT as well as the Discovery indexing performance issues in 6.x + +## 2020-02-11 + +- Maria from Bioversity asked me to add some ORCID iDs to our controlled vocabulary so I combined them with our existing ones and updated the names from the ORCID API: + +``` +$ cat ~/src/git/DSpace/dspace/config/controlled-vocabularies/cg-creator-id.xml /tmp/bioversity-orcid-ids.txt | grep -oE '[A-Z0-9]{4}-[A-Z0-9]{4}-[A-Z0-9]{4}-[A-Z0-9]{4}' | sort | uniq > /tmp/2020-02-11-combined-orcids.txt +$ ./resolve-orcids.py -i /tmp/2020-02-11-combined-orcids.txt -o /tmp/2020-02-11-combined-names.txt -d +# sort names, copy to cg-creator-id.xml, add XML formatting, and then format with tidy (preserving accents) +$ tidy -xml -utf8 -iq -m -w 0 dspace/config/controlled-vocabularies/cg-creator-id.xml +``` + +- Then I noticed some author names had changed, so I captured the old and new names in a CSV file and fixed them using `fix-metadata-values.py`: + +``` +$ ./fix-metadata-values.py -i 2020-02-11-correct-orcid-ids.csv -db dspace -u dspace -p 'fuuu' -f cg.creator.id -t correct -m 240 -d +``` + +- On a hunch I decided to try to add these ORCID iDs to existing items that might not have them yet + - I checked the database for likely matches to the author name and then created a CSV with the author names and ORCID iDs: + +``` +dc.contributor.author,cg.creator.id +"Staver, Charles",charles staver: 0000-0002-4532-6077 +"Staver, C.",charles staver: 0000-0002-4532-6077 +"Fungo, R.",Robert Fungo: 0000-0002-4264-6905 +"Remans, R.",Roseline Remans: 0000-0003-3659-8529 +"Remans, Roseline",Roseline Remans: 0000-0003-3659-8529 +"Rietveld A.",Anne Rietveld: 0000-0002-9400-9473 +"Rietveld, A.",Anne Rietveld: 0000-0002-9400-9473 +"Rietveld, A.M.",Anne Rietveld: 0000-0002-9400-9473 +"Rietveld, Anne M.",Anne Rietveld: 0000-0002-9400-9473 +"Fongar, A.",Andrea Fongar: 0000-0003-2084-1571 +"Müller, Anna",Anna Müller: 0000-0003-3120-8560 +"Müller, A.",Anna Müller: 0000-0003-3120-8560 +``` + +- Running the `add-orcid-identifiers-csv.py` script I added 144 ORCID iDs to items! + +``` +$ ./add-orcid-identifiers-csv.py -i /tmp/2020-02-11-add-orcid-ids.csv -db dspace -u dspace -p 'fuuu' +``` + diff --git a/docs/2015-11/index.html b/docs/2015-11/index.html index 791285416..77c0d5a22 100644 --- a/docs/2015-11/index.html +++ b/docs/2015-11/index.html @@ -31,7 +31,7 @@ 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 fbdccb218..92e4bc786 100644 --- a/docs/2015-12/index.html +++ b/docs/2015-12/index.html @@ -33,7 +33,7 @@ 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 db00ecce6..9e8eb6889 100644 --- a/docs/2016-01/index.html +++ b/docs/2016-01/index.html @@ -25,7 +25,7 @@ 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 573735585..3a9903069 100644 --- a/docs/2016-02/index.html +++ b/docs/2016-02/index.html @@ -35,7 +35,7 @@ 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 28fc8dc9f..aec19d4d7 100644 --- a/docs/2016-03/index.html +++ b/docs/2016-03/index.html @@ -25,7 +25,7 @@ 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 c2663b60d..bacadf92e 100644 --- a/docs/2016-04/index.html +++ b/docs/2016-04/index.html @@ -29,7 +29,7 @@ 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 68f435b20..eb761445e 100644 --- a/docs/2016-05/index.html +++ b/docs/2016-05/index.html @@ -31,7 +31,7 @@ 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 2c4018eb8..8097605cb 100644 --- a/docs/2016-06/index.html +++ b/docs/2016-06/index.html @@ -31,7 +31,7 @@ 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 9a29776e3..80c68d3ef 100644 --- a/docs/2016-07/index.html +++ b/docs/2016-07/index.html @@ -41,7 +41,7 @@ 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 91fd4a72d..e5b061afd 100644 --- a/docs/2016-08/index.html +++ b/docs/2016-08/index.html @@ -39,7 +39,7 @@ $ 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 842ce7131..567f0a4b7 100644 --- a/docs/2016-09/index.html +++ b/docs/2016-09/index.html @@ -31,7 +31,7 @@ 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 2bcd2f91f..619a9c92c 100644 --- a/docs/2016-10/index.html +++ b/docs/2016-10/index.html @@ -39,7 +39,7 @@ 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 d129f883d..f744f03de 100644 --- a/docs/2016-11/index.html +++ b/docs/2016-11/index.html @@ -23,7 +23,7 @@ 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 166ef160a..a5d73c62d 100644 --- a/docs/2016-12/index.html +++ b/docs/2016-12/index.html @@ -43,7 +43,7 @@ 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 b80d00da5..39ba258b9 100644 --- a/docs/2017-01/index.html +++ b/docs/2017-01/index.html @@ -25,7 +25,7 @@ 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 58eef8079..c9e4c2a02 100644 --- a/docs/2017-02/index.html +++ b/docs/2017-02/index.html @@ -47,7 +47,7 @@ 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 439401b6b..31dc173f8 100644 --- a/docs/2017-03/index.html +++ b/docs/2017-03/index.html @@ -51,7 +51,7 @@ 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 5ae816fd9..5b6833849 100644 --- a/docs/2017-04/index.html +++ b/docs/2017-04/index.html @@ -37,7 +37,7 @@ 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 2fd96e4ad..99db8b7f3 100644 --- a/docs/2017-05/index.html +++ b/docs/2017-05/index.html @@ -15,7 +15,7 @@ - + diff --git a/docs/2017-06/index.html b/docs/2017-06/index.html index c5d560008..a9385dfc5 100644 --- a/docs/2017-06/index.html +++ b/docs/2017-06/index.html @@ -15,7 +15,7 @@ - + diff --git a/docs/2017-07/index.html b/docs/2017-07/index.html index 2c7dfe1ef..657bcc403 100644 --- a/docs/2017-07/index.html +++ b/docs/2017-07/index.html @@ -33,7 +33,7 @@ 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 6468302c3..bfbedec65 100644 --- a/docs/2017-08/index.html +++ b/docs/2017-08/index.html @@ -57,7 +57,7 @@ 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 42889465d..26fff0b0e 100644 --- a/docs/2017-09/index.html +++ b/docs/2017-09/index.html @@ -29,7 +29,7 @@ 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 f06adaad1..d783042ff 100644 --- a/docs/2017-10/index.html +++ b/docs/2017-10/index.html @@ -31,7 +31,7 @@ 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 2c14fe894..6f839bee1 100644 --- a/docs/2017-11/index.html +++ b/docs/2017-11/index.html @@ -45,7 +45,7 @@ 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 16382e0cd..8ca035688 100644 --- a/docs/2017-12/index.html +++ b/docs/2017-12/index.html @@ -27,7 +27,7 @@ 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 bf0da8187..5eb9afef1 100644 --- a/docs/2018-01/index.html +++ b/docs/2018-01/index.html @@ -147,7 +147,7 @@ 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 162f4f63f..27bb1075a 100644 --- a/docs/2018-02/index.html +++ b/docs/2018-02/index.html @@ -27,7 +27,7 @@ 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 5c24c483c..a48f949c9 100644 --- a/docs/2018-03/index.html +++ b/docs/2018-03/index.html @@ -21,7 +21,7 @@ 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 caf2d95f1..ffb8332f0 100644 --- a/docs/2018-04/index.html +++ b/docs/2018-04/index.html @@ -23,7 +23,7 @@ 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 d5082b60c..52eaa7383 100644 --- a/docs/2018-05/index.html +++ b/docs/2018-05/index.html @@ -35,7 +35,7 @@ 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 0de986c99..325c29489 100644 --- a/docs/2018-06/index.html +++ b/docs/2018-06/index.html @@ -55,7 +55,7 @@ real 74m42.646s user 8m5.056s sys 2m7.289s "/> - + diff --git a/docs/2018-07/index.html b/docs/2018-07/index.html index 9b59b73b3..091d00efb 100644 --- a/docs/2018-07/index.html +++ b/docs/2018-07/index.html @@ -33,7 +33,7 @@ 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 505978335..f182926fd 100644 --- a/docs/2018-08/index.html +++ b/docs/2018-08/index.html @@ -43,7 +43,7 @@ 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 b8f4d0702..25374e810 100644 --- a/docs/2018-09/index.html +++ b/docs/2018-09/index.html @@ -27,7 +27,7 @@ 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 24298e749..bbc5af642 100644 --- a/docs/2018-10/index.html +++ b/docs/2018-10/index.html @@ -23,7 +23,7 @@ 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 1c6cfb575..33f4693d6 100644 --- a/docs/2018-11/index.html +++ b/docs/2018-11/index.html @@ -33,7 +33,7 @@ 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 4e10b8373..30bcf60df 100644 --- a/docs/2018-12/index.html +++ b/docs/2018-12/index.html @@ -33,7 +33,7 @@ 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 7ee2f44ac..b15ec15b0 100644 --- a/docs/2019-01/index.html +++ b/docs/2019-01/index.html @@ -47,7 +47,7 @@ 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 c08be8bdc..d96646b29 100644 --- a/docs/2019-02/index.html +++ b/docs/2019-02/index.html @@ -69,7 +69,7 @@ real 0m19.873s user 0m22.203s sys 0m1.979s "/> - + diff --git a/docs/2019-03/index.html b/docs/2019-03/index.html index 228cdb80f..d481741c3 100644 --- a/docs/2019-03/index.html +++ b/docs/2019-03/index.html @@ -43,7 +43,7 @@ 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 77b7f3966..55b431ed1 100644 --- a/docs/2019-04/index.html +++ b/docs/2019-04/index.html @@ -61,7 +61,7 @@ $ ./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 3a28b3b1e..fe8ab3020 100644 --- a/docs/2019-05/index.html +++ b/docs/2019-05/index.html @@ -45,7 +45,7 @@ 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 5b47fab24..87068a10f 100644 --- a/docs/2019-06/index.html +++ b/docs/2019-06/index.html @@ -31,7 +31,7 @@ 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 0ceefbbf1..f094bc328 100644 --- a/docs/2019-07/index.html +++ b/docs/2019-07/index.html @@ -35,7 +35,7 @@ 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 b889b30fa..d217803c2 100644 --- a/docs/2019-08/index.html +++ b/docs/2019-08/index.html @@ -43,7 +43,7 @@ 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 855c00c3a..3d17241b2 100644 --- a/docs/2019-09/index.html +++ b/docs/2019-09/index.html @@ -69,7 +69,7 @@ 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 cc1803362..570beb845 100644 --- a/docs/2019-10/index.html +++ b/docs/2019-10/index.html @@ -15,7 +15,7 @@ - + diff --git a/docs/2019-11/index.html b/docs/2019-11/index.html index ac2f56f97..3e6f4807d 100644 --- a/docs/2019-11/index.html +++ b/docs/2019-11/index.html @@ -55,7 +55,7 @@ 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 755f24f4e..a94877382 100644 --- a/docs/2019-12/index.html +++ b/docs/2019-12/index.html @@ -43,7 +43,7 @@ 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 dfa19a2f6..28621113f 100644 --- a/docs/2020-01/index.html +++ b/docs/2020-01/index.html @@ -29,7 +29,7 @@ I tweeted the CGSpace repository link - + @@ -53,7 +53,7 @@ I tweeted the CGSpace repository link "/> - + @@ -65,7 +65,7 @@ I tweeted the CGSpace repository link "url": "https:\/\/alanorth.github.io\/cgspace-notes\/2020-01\/", "wordCount": "3523", "datePublished": "2020-01-06T10:48:30+02:00", - "dateModified": "2020-02-04T13:06:23+02:00", + "dateModified": "2020-02-10T10:34:19+02:00", "author": { "@type": "Person", "name": "Alan Orth" diff --git a/docs/2020-02/index.html b/docs/2020-02/index.html index 9b8502164..3d02bf1d7 100644 --- a/docs/2020-02/index.html +++ b/docs/2020-02/index.html @@ -35,7 +35,7 @@ The code finally builds and runs with a fresh install "/> - + @@ -45,7 +45,7 @@ The code finally builds and runs with a fresh install "@type": "BlogPosting", "headline": "February, 2020", "url": "https:\/\/alanorth.github.io\/cgspace-notes\/2020-02\/", - "wordCount": "2551", + "wordCount": "2811", "datePublished": "2020-02-02T11:56:30+02:00", "dateModified": "2020-02-09T17:34:12+02:00", "author": { @@ -510,7 +510,51 @@ $ cat out.dspace510-1 | ../FlameGraph/stackcollapse-perf.pl | grep -E '^java' | - +

2020-02-10

+ +

2020-02-11

+ +
$ cat ~/src/git/DSpace/dspace/config/controlled-vocabularies/cg-creator-id.xml /tmp/bioversity-orcid-ids.txt | grep -oE '[A-Z0-9]{4}-[A-Z0-9]{4}-[A-Z0-9]{4}-[A-Z0-9]{4}' | sort | uniq > /tmp/2020-02-11-combined-orcids.txt
+$ ./resolve-orcids.py -i /tmp/2020-02-11-combined-orcids.txt -o /tmp/2020-02-11-combined-names.txt -d
+# sort names, copy to cg-creator-id.xml, add XML formatting, and then format with tidy (preserving accents)
+$ tidy -xml -utf8 -iq -m -w 0 dspace/config/controlled-vocabularies/cg-creator-id.xml
+
+
$ ./fix-metadata-values.py -i 2020-02-11-correct-orcid-ids.csv -db dspace -u dspace -p 'fuuu' -f cg.creator.id -t correct -m 240 -d
+
+
dc.contributor.author,cg.creator.id
+"Staver, Charles",charles staver: 0000-0002-4532-6077
+"Staver, C.",charles staver: 0000-0002-4532-6077
+"Fungo, R.",Robert Fungo: 0000-0002-4264-6905
+"Remans, R.",Roseline Remans: 0000-0003-3659-8529
+"Remans, Roseline",Roseline Remans: 0000-0003-3659-8529
+"Rietveld A.",Anne Rietveld: 0000-0002-9400-9473
+"Rietveld, A.",Anne Rietveld: 0000-0002-9400-9473
+"Rietveld, A.M.",Anne Rietveld: 0000-0002-9400-9473
+"Rietveld, Anne M.",Anne Rietveld: 0000-0002-9400-9473
+"Fongar, A.",Andrea Fongar: 0000-0003-2084-1571
+"Müller, Anna",Anna Müller: 0000-0003-3120-8560
+"Müller, A.",Anna Müller: 0000-0003-3120-8560
+
+
$ ./add-orcid-identifiers-csv.py -i /tmp/2020-02-11-add-orcid-ids.csv -db dspace -u dspace -p 'fuuu'
+
diff --git a/docs/404.html b/docs/404.html index 85ccc2a23..4bf4b1bd5 100644 --- a/docs/404.html +++ b/docs/404.html @@ -14,7 +14,7 @@ - + diff --git a/docs/categories/index.html b/docs/categories/index.html index 3a330e7cd..4853e1d20 100644 --- a/docs/categories/index.html +++ b/docs/categories/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/categories/notes/index.html b/docs/categories/notes/index.html index 41c780fdd..d0e793fb0 100644 --- a/docs/categories/notes/index.html +++ b/docs/categories/notes/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/categories/notes/page/2/index.html b/docs/categories/notes/page/2/index.html index a5b7af078..7b5382866 100644 --- a/docs/categories/notes/page/2/index.html +++ b/docs/categories/notes/page/2/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/categories/notes/page/3/index.html b/docs/categories/notes/page/3/index.html index ffb3de05c..76a21ed15 100644 --- a/docs/categories/notes/page/3/index.html +++ b/docs/categories/notes/page/3/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/categories/notes/page/4/index.html b/docs/categories/notes/page/4/index.html index 224d87fde..487b06cf5 100644 --- a/docs/categories/notes/page/4/index.html +++ b/docs/categories/notes/page/4/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/categories/page/2/index.html b/docs/categories/page/2/index.html index 89ff4df50..dab68bad9 100644 --- a/docs/categories/page/2/index.html +++ b/docs/categories/page/2/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/categories/page/3/index.html b/docs/categories/page/3/index.html index aeb91a155..1172f0f11 100644 --- a/docs/categories/page/3/index.html +++ b/docs/categories/page/3/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/categories/page/4/index.html b/docs/categories/page/4/index.html index f2321ac0f..725b1ef52 100644 --- a/docs/categories/page/4/index.html +++ b/docs/categories/page/4/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/categories/page/5/index.html b/docs/categories/page/5/index.html index 432157225..98c7096ab 100644 --- a/docs/categories/page/5/index.html +++ b/docs/categories/page/5/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/categories/page/6/index.html b/docs/categories/page/6/index.html index 815d69377..1016aae88 100644 --- a/docs/categories/page/6/index.html +++ b/docs/categories/page/6/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/cgiar-library-migration/index.html b/docs/cgiar-library-migration/index.html index 5fef46e21..f3963817b 100644 --- a/docs/cgiar-library-migration/index.html +++ b/docs/cgiar-library-migration/index.html @@ -15,7 +15,7 @@ - + diff --git a/docs/cgspace-cgcorev2-migration/index.html b/docs/cgspace-cgcorev2-migration/index.html index 19d34e811..95bbc86df 100644 --- a/docs/cgspace-cgcorev2-migration/index.html +++ b/docs/cgspace-cgcorev2-migration/index.html @@ -15,7 +15,7 @@ - + diff --git a/docs/index.html b/docs/index.html index c5712acb9..33075d6f3 100644 --- a/docs/index.html +++ b/docs/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/page/2/index.html b/docs/page/2/index.html index 819a5672d..a7f1aa4fd 100644 --- a/docs/page/2/index.html +++ b/docs/page/2/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/page/3/index.html b/docs/page/3/index.html index e75567cc8..3d6849a30 100644 --- a/docs/page/3/index.html +++ b/docs/page/3/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/page/4/index.html b/docs/page/4/index.html index 39998ed22..74c6e38d9 100644 --- a/docs/page/4/index.html +++ b/docs/page/4/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/page/5/index.html b/docs/page/5/index.html index bd95fe255..4b2aab91a 100644 --- a/docs/page/5/index.html +++ b/docs/page/5/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/page/6/index.html b/docs/page/6/index.html index 43f395024..d8faa31df 100644 --- a/docs/page/6/index.html +++ b/docs/page/6/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/posts/index.html b/docs/posts/index.html index a7e3baf47..7b9b5a3fc 100644 --- a/docs/posts/index.html +++ b/docs/posts/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/posts/page/2/index.html b/docs/posts/page/2/index.html index 08186693f..3e8da1088 100644 --- a/docs/posts/page/2/index.html +++ b/docs/posts/page/2/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/posts/page/3/index.html b/docs/posts/page/3/index.html index b6530a321..194accd38 100644 --- a/docs/posts/page/3/index.html +++ b/docs/posts/page/3/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/posts/page/4/index.html b/docs/posts/page/4/index.html index 78c31db65..1b7c0c466 100644 --- a/docs/posts/page/4/index.html +++ b/docs/posts/page/4/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/posts/page/5/index.html b/docs/posts/page/5/index.html index 36d9b5032..966859c4a 100644 --- a/docs/posts/page/5/index.html +++ b/docs/posts/page/5/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/posts/page/6/index.html b/docs/posts/page/6/index.html index 457f32a12..bada69722 100644 --- a/docs/posts/page/6/index.html +++ b/docs/posts/page/6/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/sitemap.xml b/docs/sitemap.xml index 5ae344315..9227ae751 100644 --- a/docs/sitemap.xml +++ b/docs/sitemap.xml @@ -4,12 +4,12 @@ https://alanorth.github.io/cgspace-notes/categories/ - 2020-02-09T17:34:12+02:00 + 2020-02-10T10:34:19+02:00 https://alanorth.github.io/cgspace-notes/ - 2020-02-09T17:34:12+02:00 + 2020-02-10T10:34:19+02:00 @@ -19,17 +19,17 @@ https://alanorth.github.io/cgspace-notes/categories/notes/ - 2020-02-09T17:34:12+02:00 + 2020-02-10T10:34:19+02:00 https://alanorth.github.io/cgspace-notes/posts/ - 2020-02-09T17:34:12+02:00 + 2020-02-10T10:34:19+02:00 https://alanorth.github.io/cgspace-notes/2020-01/ - 2020-02-04T13:06:23+02:00 + 2020-02-10T10:34:19+02:00 diff --git a/docs/tags/index.html b/docs/tags/index.html index bf16fa194..298c3caa7 100644 --- a/docs/tags/index.html +++ b/docs/tags/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/tags/migration/index.html b/docs/tags/migration/index.html index 1b1412c0f..554ac5585 100644 --- a/docs/tags/migration/index.html +++ b/docs/tags/migration/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/tags/notes/index.html b/docs/tags/notes/index.html index 7b0a4e937..24eeacabe 100644 --- a/docs/tags/notes/index.html +++ b/docs/tags/notes/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/tags/notes/page/2/index.html b/docs/tags/notes/page/2/index.html index 235b8e98e..3baac9ab5 100644 --- a/docs/tags/notes/page/2/index.html +++ b/docs/tags/notes/page/2/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/tags/notes/page/3/index.html b/docs/tags/notes/page/3/index.html index 0de6e10df..25c25bc93 100644 --- a/docs/tags/notes/page/3/index.html +++ b/docs/tags/notes/page/3/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/tags/page/2/index.html b/docs/tags/page/2/index.html index 7776eb64a..a3b4a4d34 100644 --- a/docs/tags/page/2/index.html +++ b/docs/tags/page/2/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/tags/page/3/index.html b/docs/tags/page/3/index.html index f8696df8d..c2216d3d3 100644 --- a/docs/tags/page/3/index.html +++ b/docs/tags/page/3/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/tags/page/4/index.html b/docs/tags/page/4/index.html index e12acaf75..070b58923 100644 --- a/docs/tags/page/4/index.html +++ b/docs/tags/page/4/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/tags/page/5/index.html b/docs/tags/page/5/index.html index 29593222f..10796f079 100644 --- a/docs/tags/page/5/index.html +++ b/docs/tags/page/5/index.html @@ -14,7 +14,7 @@ - + diff --git a/docs/tags/page/6/index.html b/docs/tags/page/6/index.html index 5850d93ed..35b87a76f 100644 --- a/docs/tags/page/6/index.html +++ b/docs/tags/page/6/index.html @@ -14,7 +14,7 @@ - +