From b3331f7ae4585c2995746e0d6750a71d97f2aa42 Mon Sep 17 00:00:00 2001 From: Alan Orth Date: Tue, 4 Apr 2017 16:23:29 +0300 Subject: [PATCH] Update notes for 2017-04-04 --- content/post/2017-04.md | 29 +++++++++++++++++++++++++++ public/2017-04/index.html | 39 ++++++++++++++++++++++++++++++++++--- public/index.xml | 33 +++++++++++++++++++++++++++++++ public/post/index.xml | 33 +++++++++++++++++++++++++++++++ public/sitemap.xml | 8 ++++---- public/tags/notes/index.xml | 33 +++++++++++++++++++++++++++++++ 6 files changed, 168 insertions(+), 7 deletions(-) diff --git a/content/post/2017-04.md b/content/post/2017-04.md index 275509f6e..de7230810 100644 --- a/content/post/2017-04.md +++ b/content/post/2017-04.md @@ -54,3 +54,32 @@ dspace=# select text_value from metadatavalue where resource_type_id=2 and metad $ grep -c profile /tmp/filter-media-cmyk.txt 1584 ``` + +- Trying to find a way to get the number of items submitted by a certain user in 2016 +- It's not possible in the DSpace search / module interfaces, but might be able to be derived from `dc.description.provenance`, as that field contains the name and email of the submitter/approver, ie: + +``` +Submitted by Francesca Giampieri (fgiampieri) on 2016-01-19T13:56:43Z^M +No. of bitstreams: 1^M +ILAC_Brief21_PMCA.pdf: 113462 bytes, checksum: 249fef468f401c066a119f5db687add0 (MD5) +``` + +- This SQL query returns fields that were submitted or approved by giampieri in 2016 and contain a "checksum" (ie, there was a bitstream in the submission): + +``` +dspace=# select * from metadatavalue where resource_type_id=2 and metadata_field_id=28 and text_value ~ '^(Submitted|Approved).*giampieri.*2016-.*checksum.*'; +``` + +- Then this one does the same, but for fields that don't contain checksums (ie, there was no bitstream in the submission): + +``` +dspace=# select * from metadatavalue where resource_type_id=2 and metadata_field_id=28 and text_value ~ '^(Submitted|Approved).*giampieri.*2016-.*' and text_value !~ '^(Submitted|Approved).*giampieri.*2016-.*checksum.*'; +``` + +- For some reason there seem to be way too many fields, for example there are 498 + 13 here, which is 511 items for just this one user. +- It looks like there can be a scenario where the user submitted AND approved it, so some records might be doubled... +- In that case it might just be better to see how many the user submitted (both _with_ and _without_ bitstreams): + +``` +dspace=# select * from metadatavalue where resource_type_id=2 and metadata_field_id=28 and text_value ~ '^(Submitted).*giampieri.*2016-.*'; +``` diff --git a/public/2017-04/index.html b/public/2017-04/index.html index 0c66aafc9..6ead8d902 100644 --- a/public/2017-04/index.html +++ b/public/2017-04/index.html @@ -30,7 +30,7 @@ $ [dspace]/bin/dspace filter-media -f -i 10568/16498 -p "ImageMagick PDF Th - + @@ -79,9 +79,9 @@ $ [dspace]/bin/dspace filter-media -f -i 10568/16498 -p "ImageMagick PDF Th "@type": "BlogPosting", "headline": "April, 2017", "url": "https://alanorth.github.io/cgspace-notes/2017-04/", - "wordCount": "226", + "wordCount": "451", "datePublished": "2017-04-02T17:08:52+02:00", - "dateModified": "2017-04-03T13:16:24+03:00", + "dateModified": "2017-04-04T15:05:54+03:00", "author": { "@type": "Person", "name": "Alan Orth" @@ -204,6 +204,39 @@ $ [dspace]/bin/dspace filter-media -f -i 10568/16498 -p "ImageMagick PDF Th 1584 + + +
Submitted by Francesca Giampieri (fgiampieri) on 2016-01-19T13:56:43Z^M
+No. of bitstreams: 1^M
+ILAC_Brief21_PMCA.pdf: 113462 bytes, checksum: 249fef468f401c066a119f5db687add0 (MD5)
+
+ + + +
dspace=# select * from metadatavalue where resource_type_id=2 and metadata_field_id=28 and text_value ~ '^(Submitted|Approved).*giampieri.*2016-.*checksum.*';
+
+ + + +
dspace=# select * from metadatavalue where resource_type_id=2 and metadata_field_id=28 and text_value ~ '^(Submitted|Approved).*giampieri.*2016-.*' and text_value !~ '^(Submitted|Approved).*giampieri.*2016-.*checksum.*';
+
+ + + +
dspace=# select * from metadatavalue where resource_type_id=2 and metadata_field_id=28 and text_value ~ '^(Submitted).*giampieri.*2016-.*';
+
+ diff --git a/public/index.xml b/public/index.xml index f71727fc7..618f991b7 100644 --- a/public/index.xml +++ b/public/index.xml @@ -73,6 +73,39 @@ <pre><code>$ grep -c profile /tmp/filter-media-cmyk.txt 1584 +</code></pre> + +<ul> +<li>Trying to find a way to get the number of items submitted by a certain user in 2016</li> +<li>It&rsquo;s not possible in the DSpace search / module interfaces, but might be able to be derived from <code>dc.description.provenance</code>, as that field contains the name and email of the submitter/approver, ie:</li> +</ul> + +<pre><code>Submitted by Francesca Giampieri (fgiampieri) on 2016-01-19T13:56:43Z^M +No. of bitstreams: 1^M +ILAC_Brief21_PMCA.pdf: 113462 bytes, checksum: 249fef468f401c066a119f5db687add0 (MD5) +</code></pre> + +<ul> +<li>This SQL query returns fields that were submitted or approved by giampieri in 2016 and contain a &ldquo;checksum&rdquo; (ie, there was a bitstream in the submission):</li> +</ul> + +<pre><code>dspace=# select * from metadatavalue where resource_type_id=2 and metadata_field_id=28 and text_value ~ '^(Submitted|Approved).*giampieri.*2016-.*checksum.*'; +</code></pre> + +<ul> +<li>Then this one does the same, but for fields that don&rsquo;t contain checksums (ie, there was no bitstream in the submission):</li> +</ul> + +<pre><code>dspace=# select * from metadatavalue where resource_type_id=2 and metadata_field_id=28 and text_value ~ '^(Submitted|Approved).*giampieri.*2016-.*' and text_value !~ '^(Submitted|Approved).*giampieri.*2016-.*checksum.*'; +</code></pre> + +<ul> +<li>For some reason there seem to be way too many fields, for example there are 498 + 13 here, which is 511 items for just this one user.</li> +<li>It looks like there can be a scenario where the user submitted AND approved it, so some records might be doubled&hellip;</li> +<li>In that case it might just be better to see how many the user submitted (both <em>with</em> and <em>without</em> bitstreams):</li> +</ul> + +<pre><code>dspace=# select * from metadatavalue where resource_type_id=2 and metadata_field_id=28 and text_value ~ '^(Submitted).*giampieri.*2016-.*'; </code></pre> diff --git a/public/post/index.xml b/public/post/index.xml index 8a2eaaac2..6c4c9aff2 100644 --- a/public/post/index.xml +++ b/public/post/index.xml @@ -73,6 +73,39 @@ <pre><code>$ grep -c profile /tmp/filter-media-cmyk.txt 1584 +</code></pre> + +<ul> +<li>Trying to find a way to get the number of items submitted by a certain user in 2016</li> +<li>It&rsquo;s not possible in the DSpace search / module interfaces, but might be able to be derived from <code>dc.description.provenance</code>, as that field contains the name and email of the submitter/approver, ie:</li> +</ul> + +<pre><code>Submitted by Francesca Giampieri (fgiampieri) on 2016-01-19T13:56:43Z^M +No. of bitstreams: 1^M +ILAC_Brief21_PMCA.pdf: 113462 bytes, checksum: 249fef468f401c066a119f5db687add0 (MD5) +</code></pre> + +<ul> +<li>This SQL query returns fields that were submitted or approved by giampieri in 2016 and contain a &ldquo;checksum&rdquo; (ie, there was a bitstream in the submission):</li> +</ul> + +<pre><code>dspace=# select * from metadatavalue where resource_type_id=2 and metadata_field_id=28 and text_value ~ '^(Submitted|Approved).*giampieri.*2016-.*checksum.*'; +</code></pre> + +<ul> +<li>Then this one does the same, but for fields that don&rsquo;t contain checksums (ie, there was no bitstream in the submission):</li> +</ul> + +<pre><code>dspace=# select * from metadatavalue where resource_type_id=2 and metadata_field_id=28 and text_value ~ '^(Submitted|Approved).*giampieri.*2016-.*' and text_value !~ '^(Submitted|Approved).*giampieri.*2016-.*checksum.*'; +</code></pre> + +<ul> +<li>For some reason there seem to be way too many fields, for example there are 498 + 13 here, which is 511 items for just this one user.</li> +<li>It looks like there can be a scenario where the user submitted AND approved it, so some records might be doubled&hellip;</li> +<li>In that case it might just be better to see how many the user submitted (both <em>with</em> and <em>without</em> bitstreams):</li> +</ul> + +<pre><code>dspace=# select * from metadatavalue where resource_type_id=2 and metadata_field_id=28 and text_value ~ '^(Submitted).*giampieri.*2016-.*'; </code></pre> diff --git a/public/sitemap.xml b/public/sitemap.xml index 3316dcfc8..dcfdd3c38 100644 --- a/public/sitemap.xml +++ b/public/sitemap.xml @@ -3,7 +3,7 @@ https://alanorth.github.io/cgspace-notes/2017-04/ - 2017-04-03T13:16:24+03:00 + 2017-04-04T15:05:54+03:00 @@ -93,19 +93,19 @@ https://alanorth.github.io/cgspace-notes/ - 2017-04-03T13:16:24+03:00 + 2017-04-04T15:05:54+03:00 0 https://alanorth.github.io/cgspace-notes/tags/notes/ - 2017-04-03T13:16:24+03:00 + 2017-04-04T15:05:54+03:00 0 https://alanorth.github.io/cgspace-notes/post/ - 2017-04-03T13:16:24+03:00 + 2017-04-04T15:05:54+03:00 0 diff --git a/public/tags/notes/index.xml b/public/tags/notes/index.xml index 676364d23..5f7077fe7 100644 --- a/public/tags/notes/index.xml +++ b/public/tags/notes/index.xml @@ -72,6 +72,39 @@ <pre><code>$ grep -c profile /tmp/filter-media-cmyk.txt 1584 +</code></pre> + +<ul> +<li>Trying to find a way to get the number of items submitted by a certain user in 2016</li> +<li>It&rsquo;s not possible in the DSpace search / module interfaces, but might be able to be derived from <code>dc.description.provenance</code>, as that field contains the name and email of the submitter/approver, ie:</li> +</ul> + +<pre><code>Submitted by Francesca Giampieri (fgiampieri) on 2016-01-19T13:56:43Z^M +No. of bitstreams: 1^M +ILAC_Brief21_PMCA.pdf: 113462 bytes, checksum: 249fef468f401c066a119f5db687add0 (MD5) +</code></pre> + +<ul> +<li>This SQL query returns fields that were submitted or approved by giampieri in 2016 and contain a &ldquo;checksum&rdquo; (ie, there was a bitstream in the submission):</li> +</ul> + +<pre><code>dspace=# select * from metadatavalue where resource_type_id=2 and metadata_field_id=28 and text_value ~ '^(Submitted|Approved).*giampieri.*2016-.*checksum.*'; +</code></pre> + +<ul> +<li>Then this one does the same, but for fields that don&rsquo;t contain checksums (ie, there was no bitstream in the submission):</li> +</ul> + +<pre><code>dspace=# select * from metadatavalue where resource_type_id=2 and metadata_field_id=28 and text_value ~ '^(Submitted|Approved).*giampieri.*2016-.*' and text_value !~ '^(Submitted|Approved).*giampieri.*2016-.*checksum.*'; +</code></pre> + +<ul> +<li>For some reason there seem to be way too many fields, for example there are 498 + 13 here, which is 511 items for just this one user.</li> +<li>It looks like there can be a scenario where the user submitted AND approved it, so some records might be doubled&hellip;</li> +<li>In that case it might just be better to see how many the user submitted (both <em>with</em> and <em>without</em> bitstreams):</li> +</ul> + +<pre><code>dspace=# select * from metadatavalue where resource_type_id=2 and metadata_field_id=28 and text_value ~ '^(Submitted).*giampieri.*2016-.*'; </code></pre>