From a84f008b09c91f09a16ddb65a6d7ce552367ccf3 Mon Sep 17 00:00:00 2001 From: Alan Orth Date: Thu, 17 Dec 2020 16:50:56 +0200 Subject: [PATCH] Add notes for 2020-12-17 --- content/posts/2020-12.md | 55 +++++++++++++++++++++++ docs/2020-12/index.html | 60 +++++++++++++++++++++++-- docs/categories/index.html | 2 +- docs/categories/notes/index.html | 2 +- docs/categories/notes/page/2/index.html | 2 +- docs/categories/notes/page/3/index.html | 2 +- docs/categories/notes/page/4/index.html | 2 +- docs/categories/notes/page/5/index.html | 2 +- docs/index.html | 2 +- docs/page/2/index.html | 2 +- docs/page/3/index.html | 2 +- docs/page/4/index.html | 2 +- docs/page/5/index.html | 2 +- docs/page/6/index.html | 2 +- docs/page/7/index.html | 2 +- docs/posts/index.html | 2 +- docs/posts/page/2/index.html | 2 +- docs/posts/page/3/index.html | 2 +- docs/posts/page/4/index.html | 2 +- docs/posts/page/5/index.html | 2 +- docs/posts/page/6/index.html | 2 +- docs/posts/page/7/index.html | 2 +- docs/sitemap.xml | 10 ++--- 23 files changed, 136 insertions(+), 29 deletions(-) diff --git a/content/posts/2020-12.md b/content/posts/2020-12.md index 87d88229f..be59bd059 100644 --- a/content/posts/2020-12.md +++ b/content/posts/2020-12.md @@ -480,4 +480,59 @@ $ grep -o -E 'by .*)' /tmp/provenance.txt | grep -v -E "( on |checksum)" | sed - - Peter wanted it to send some mail to the users... +## 2020-12-17 + +- I see some errors from CUA in our Tomcat logs: + +```console +Thu Dec 17 07:35:27 CET 2020 | Query:containerItem:b049326a-0e76-45a8-ac0c-d8ec043a50c6 +Error while updating +java.lang.UnsupportedOperationException: Multiple update components target the same field:solr_update_time_stamp + at com.atmire.dspace.cua.CUASolrLoggerServiceImpl$5.visit(SourceFile:1155) + at com.atmire.dspace.cua.CUASolrLoggerServiceImpl.visitEachStatisticShard(SourceFile:241) + at com.atmire.dspace.cua.CUASolrLoggerServiceImpl.update(SourceFile:1140) + at com.atmire.dspace.cua.CUASolrLoggerServiceImpl.update(SourceFile:1129) +... +``` + +- I sent the full stack to Atmire to investigate + - I know we've had thisi "Multiple update components target the same field" error in the past with DSpace 5.x and Atmire said it was harmless, but would nevertheless be fixed in a future update +- I was trying to export the ILRI community on CGSpace so I could update one of the ILRI author's names, but it throws an error... + +```console +$ dspace metadata-export -i 10568/1 -f /tmp/2020-12-17-ILRI.csv +Loading @mire database changes for module MQM +Changes have been processed +Exporting community 'International Livestock Research Institute (ILRI)' (10568/1) + Exception: null +java.lang.NullPointerException + at com.google.common.base.Preconditions.checkNotNull(Preconditions.java:212) + at com.google.common.collect.Iterators.concat(Iterators.java:464) + at org.dspace.app.bulkedit.MetadataExport.addItemsToResult(MetadataExport.java:136) + at org.dspace.app.bulkedit.MetadataExport.buildFromCommunity(MetadataExport.java:125) + at org.dspace.app.bulkedit.MetadataExport.(MetadataExport.java:77) + at org.dspace.app.bulkedit.MetadataExport.main(MetadataExport.java:282) + at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) + at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) + at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) + at java.lang.reflect.Method.invoke(Method.java:498) + at org.dspace.app.launcher.ScriptLauncher.runOneCommand(ScriptLauncher.java:229) + at org.dspace.app.launcher.ScriptLauncher.main(ScriptLauncher.java:81) +``` + +- I did it via CSV with `fix-metadata-values.py` instead: + +```console +$ cat 2020-12-17-update-ILRI-author.csv +dc.contributor.author,correct +"Padmakumar, V.P.","Varijakshapanicker, Padmakumar" +$ ./fix-metadata-values.py -i 2020-12-17-update-ILRI-author.csv -db dspace -u dspace -p 'fuuu' -f dc.contributor.author -t 'correct' -m 3 + +- Abenet needed a list of all 2020 outputs from the Livestock CRP that were Limited Access + - I exported the community from CGSpace and used `csvcut` and `csvgrep` to get a list: + +``` +$ csvcut -c 'dc.identifier.citation[en_US],dc.identifier.uri,dc.identifier.uri[],dc.identifier.uri[en_US],dc.date.issued,dc.date.issued[],dc.date.issued[en_US],cg.identifier.status[en_US]' ~/Downloads/10568-80099.csv | csvgrep -c 'cg.identifier.status[en_US]' -m 'Limited Access' | csvgrep -c 'dc.date.issued' -m 2020 -c 'dc.date.issued[]' -m 2020 -c 'dc.date.issued[en_US]' -m 2020 > /tmp/limited-2020.csv +``` + diff --git a/docs/2020-12/index.html b/docs/2020-12/index.html index a92ae487a..14015875d 100644 --- a/docs/2020-12/index.html +++ b/docs/2020-12/index.html @@ -20,7 +20,7 @@ I started processing those (about 411,000 records): - + @@ -46,9 +46,9 @@ I started processing those (about 411,000 records): "@type": "BlogPosting", "headline": "December, 2020", "url": "https://alanorth.github.io/cgspace-notes/2020-12/", - "wordCount": "2711", + "wordCount": "2970", "datePublished": "2020-12-01T11:32:54+02:00", - "dateModified": "2020-12-16T09:54:40+02:00", + "dateModified": "2020-12-16T12:08:00+02:00", "author": { "@type": "Person", "name": "Alan Orth" @@ -616,7 +616,59 @@ $ grep -o -E 'by .*)' /tmp/provenance.txt | grep -v -E "( on |checksum)&quo - +

2020-12-17

+ +
Thu Dec 17 07:35:27 CET 2020 | Query:containerItem:b049326a-0e76-45a8-ac0c-d8ec043a50c6
+Error while updating
+java.lang.UnsupportedOperationException: Multiple update components target the same field:solr_update_time_stamp
+        at com.atmire.dspace.cua.CUASolrLoggerServiceImpl$5.visit(SourceFile:1155)
+        at com.atmire.dspace.cua.CUASolrLoggerServiceImpl.visitEachStatisticShard(SourceFile:241)
+        at com.atmire.dspace.cua.CUASolrLoggerServiceImpl.update(SourceFile:1140)
+        at com.atmire.dspace.cua.CUASolrLoggerServiceImpl.update(SourceFile:1129)
+...
+
+
$ dspace metadata-export -i 10568/1 -f /tmp/2020-12-17-ILRI.csv
+Loading @mire database changes for module MQM
+Changes have been processed
+Exporting community 'International Livestock Research Institute (ILRI)' (10568/1)
+           Exception: null
+java.lang.NullPointerException
+        at com.google.common.base.Preconditions.checkNotNull(Preconditions.java:212)
+        at com.google.common.collect.Iterators.concat(Iterators.java:464)
+        at org.dspace.app.bulkedit.MetadataExport.addItemsToResult(MetadataExport.java:136)
+        at org.dspace.app.bulkedit.MetadataExport.buildFromCommunity(MetadataExport.java:125)
+        at org.dspace.app.bulkedit.MetadataExport.<init>(MetadataExport.java:77)
+        at org.dspace.app.bulkedit.MetadataExport.main(MetadataExport.java:282)
+        at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
+        at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
+        at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
+        at java.lang.reflect.Method.invoke(Method.java:498)
+        at org.dspace.app.launcher.ScriptLauncher.runOneCommand(ScriptLauncher.java:229)
+        at org.dspace.app.launcher.ScriptLauncher.main(ScriptLauncher.java:81)
+
+
$ cat 2020-12-17-update-ILRI-author.csv
+dc.contributor.author,correct
+"Padmakumar, V.P.","Varijakshapanicker, Padmakumar"
+$ ./fix-metadata-values.py -i 2020-12-17-update-ILRI-author.csv -db dspace -u dspace -p 'fuuu' -f dc.contributor.author -t 'correct' -m 3
+
+- Abenet needed a list of all 2020 outputs from the Livestock CRP that were Limited Access
+  - I exported the community from CGSpace and used `csvcut` and `csvgrep` to get a list:
+
+

$ csvcut -c ‘dc.identifier.citation[en_US],dc.identifier.uri,dc.identifier.uri[],dc.identifier.uri[en_US],dc.date.issued,dc.date.issued[],dc.date.issued[en_US],cg.identifier.status[en_US]’ ~/Downloads/10568-80099.csv | csvgrep -c ‘cg.identifier.status[en_US]’ -m ‘Limited Access’ | csvgrep -c ‘dc.date.issued’ -m 2020 -c ‘dc.date.issued[]’ -m 2020 -c ‘dc.date.issued[en_US]’ -m 2020 > /tmp/limited-2020.csv

+

+<!-- vim: set sw=2 ts=2: -->
+
diff --git a/docs/categories/index.html b/docs/categories/index.html index 39d8fe1bb..6a8590833 100644 --- a/docs/categories/index.html +++ b/docs/categories/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/categories/notes/index.html b/docs/categories/notes/index.html index e45eb23af..3eb6c7e77 100644 --- a/docs/categories/notes/index.html +++ b/docs/categories/notes/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/categories/notes/page/2/index.html b/docs/categories/notes/page/2/index.html index a79080ef7..e2d38630a 100644 --- a/docs/categories/notes/page/2/index.html +++ b/docs/categories/notes/page/2/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/categories/notes/page/3/index.html b/docs/categories/notes/page/3/index.html index e8f357c27..c7f8e3320 100644 --- a/docs/categories/notes/page/3/index.html +++ b/docs/categories/notes/page/3/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/categories/notes/page/4/index.html b/docs/categories/notes/page/4/index.html index c0fa1a5af..0aa1e964c 100644 --- a/docs/categories/notes/page/4/index.html +++ b/docs/categories/notes/page/4/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/categories/notes/page/5/index.html b/docs/categories/notes/page/5/index.html index 8434fd64c..f133619b2 100644 --- a/docs/categories/notes/page/5/index.html +++ b/docs/categories/notes/page/5/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/index.html b/docs/index.html index 5d67c24fc..083474c59 100644 --- a/docs/index.html +++ b/docs/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/page/2/index.html b/docs/page/2/index.html index 0d03b1cbb..3d854e54d 100644 --- a/docs/page/2/index.html +++ b/docs/page/2/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/page/3/index.html b/docs/page/3/index.html index 3ddda39f6..508d67fdf 100644 --- a/docs/page/3/index.html +++ b/docs/page/3/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/page/4/index.html b/docs/page/4/index.html index 1a9543204..8ac42f8fb 100644 --- a/docs/page/4/index.html +++ b/docs/page/4/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/page/5/index.html b/docs/page/5/index.html index 94442b9d3..a3235a314 100644 --- a/docs/page/5/index.html +++ b/docs/page/5/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/page/6/index.html b/docs/page/6/index.html index 714490c87..b726221b0 100644 --- a/docs/page/6/index.html +++ b/docs/page/6/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/page/7/index.html b/docs/page/7/index.html index 7e81418a8..5a9b89726 100644 --- a/docs/page/7/index.html +++ b/docs/page/7/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/index.html b/docs/posts/index.html index 4391c12c4..199d76735 100644 --- a/docs/posts/index.html +++ b/docs/posts/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/page/2/index.html b/docs/posts/page/2/index.html index def0d740b..7d53ddd37 100644 --- a/docs/posts/page/2/index.html +++ b/docs/posts/page/2/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/page/3/index.html b/docs/posts/page/3/index.html index 36d5c5d06..f681ab182 100644 --- a/docs/posts/page/3/index.html +++ b/docs/posts/page/3/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/page/4/index.html b/docs/posts/page/4/index.html index 22bfac0e3..19abc8203 100644 --- a/docs/posts/page/4/index.html +++ b/docs/posts/page/4/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/page/5/index.html b/docs/posts/page/5/index.html index 84faeaa2b..32a712734 100644 --- a/docs/posts/page/5/index.html +++ b/docs/posts/page/5/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/page/6/index.html b/docs/posts/page/6/index.html index d9025998f..66bb8dec2 100644 --- a/docs/posts/page/6/index.html +++ b/docs/posts/page/6/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/page/7/index.html b/docs/posts/page/7/index.html index 85231c9b8..c5f8bcd6f 100644 --- a/docs/posts/page/7/index.html +++ b/docs/posts/page/7/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/sitemap.xml b/docs/sitemap.xml index 7dd7690f3..d5865c47b 100644 --- a/docs/sitemap.xml +++ b/docs/sitemap.xml @@ -4,27 +4,27 @@ https://alanorth.github.io/cgspace-notes/categories/ - 2020-12-16T09:54:40+02:00 + 2020-12-16T12:08:00+02:00 https://alanorth.github.io/cgspace-notes/ - 2020-12-16T09:54:40+02:00 + 2020-12-16T12:08:00+02:00 https://alanorth.github.io/cgspace-notes/2020-12/ - 2020-12-16T09:54:40+02:00 + 2020-12-16T12:08:00+02:00 https://alanorth.github.io/cgspace-notes/categories/notes/ - 2020-12-16T09:54:40+02:00 + 2020-12-16T12:08:00+02:00 https://alanorth.github.io/cgspace-notes/posts/ - 2020-12-16T09:54:40+02:00 + 2020-12-16T12:08:00+02:00