From 363dbb4505dc561127dabee028c427cd5d16012b Mon Sep 17 00:00:00 2001 From: Alan Orth Date: Thu, 8 Jun 2023 17:04:20 +0300 Subject: [PATCH] Add notes for 2023-06-08 --- content/posts/2023-06.md | 11 +++++++++++ docs/2023-06/index.html | 20 +++++++++++++++++--- 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/categories/notes/page/6/index.html | 2 +- docs/categories/notes/page/7/index.html | 2 +- docs/categories/notes/page/8/index.html | 2 +- docs/index.html | 2 +- docs/page/10/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/page/8/index.html | 2 +- docs/page/9/index.html | 2 +- docs/posts/index.html | 2 +- docs/posts/page/10/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/posts/page/8/index.html | 2 +- docs/posts/page/9/index.html | 2 +- docs/sitemap.xml | 10 +++++----- 32 files changed, 62 insertions(+), 37 deletions(-) diff --git a/content/posts/2023-06.md b/content/posts/2023-06.md index 72ef6d9f3..ae9fb124a 100644 --- a/content/posts/2023-06.md +++ b/content/posts/2023-06.md @@ -50,4 +50,15 @@ $ ./ilri/update_orcids.py -i /tmp/2023-06-06-orcids-names.txt -db dspacetest -u - Start working on updating the MODS schema in CGSpace from 3.1 to 3.8 based on Stefano and Salem's work last year +## 2023-06-08 + +- Continue working on the MODS schema mapping +- Export CGSpace to check and update `dcterms.extent` fields + - I normalized about 1,500 to use either "p. 1-6" or "5 p." format + - Also, I used this GREL expression to extract missing pages from the citation field: `cells['dcterms.bibliographicCitation[en_US]'].value.match(/.*(pp?\.\s?\d+[-–]\d+).*/)[0]` + - This was over 4,000 items with a format like "p. 1-6" and "pp. 1-6" in the citation + - I used another GREL expression to extract another 5,000: `cells['dcterms.bibliographicCitation[en_US]'].value.match(/.*?(\d+\s+?[Pp]+\.).*/)[0]` + - This was for the format like "1 p." (note we had to protect against the greedy `.*` in the beginning) +- I also did some work to capture a handful of missing DOIs and ISSNs, but it was only about 100 items and I will have to wait until the 10,000+ above finish importing + diff --git a/docs/2023-06/index.html b/docs/2023-06/index.html index a668b2943..23629d4e0 100644 --- a/docs/2023-06/index.html +++ b/docs/2023-06/index.html @@ -24,7 +24,7 @@ From what I can see we need to upgrade the MODS schema from 3.1 to 3.7 and then - + @@ -54,9 +54,9 @@ From what I can see we need to upgrade the MODS schema from 3.1 to 3.7 and then "@type": "BlogPosting", "headline": "June, 2023", "url": "https://alanorth.github.io/cgspace-notes/2023-06/", - "wordCount": "327", + "wordCount": "451", "datePublished": "2023-06-02T10:29:36+03:00", - "dateModified": "2023-06-04T11:00:30+03:00", + "dateModified": "2023-06-06T16:54:25+03:00", "author": { "@type": "Person", "name": "Alan Orth" @@ -179,6 +179,20 @@ From what I can see we need to upgrade the MODS schema from 3.1 to 3.7 and then +

2023-06-08

+ diff --git a/docs/categories/index.html b/docs/categories/index.html index 041b22974..f7cf3bc30 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 f164ec1ac..0de4fb21e 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 d79e09c07..07688f5cb 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 3a5dac78b..d3e68f4b2 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 bb5b55ee4..b64157ee7 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 de428e100..e0ff25347 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/categories/notes/page/6/index.html b/docs/categories/notes/page/6/index.html index f966bcf27..3fcd189dd 100644 --- a/docs/categories/notes/page/6/index.html +++ b/docs/categories/notes/page/6/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/categories/notes/page/7/index.html b/docs/categories/notes/page/7/index.html index 814d40a62..b19c8d734 100644 --- a/docs/categories/notes/page/7/index.html +++ b/docs/categories/notes/page/7/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/categories/notes/page/8/index.html b/docs/categories/notes/page/8/index.html index 8b73d956a..3d0f40d0c 100644 --- a/docs/categories/notes/page/8/index.html +++ b/docs/categories/notes/page/8/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/index.html b/docs/index.html index 761d6435f..5070ca4fe 100644 --- a/docs/index.html +++ b/docs/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/page/10/index.html b/docs/page/10/index.html index eb9caadd2..c7fde2f80 100644 --- a/docs/page/10/index.html +++ b/docs/page/10/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/page/2/index.html b/docs/page/2/index.html index d47977e3c..2eb57e60b 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 7de13d242..5bad2404b 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 1cd65cca3..c2fb22f21 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 3a43cb6ef..635046003 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 c6eaf5bcb..2ff739e4d 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 262072ca9..e3820d92b 100644 --- a/docs/page/7/index.html +++ b/docs/page/7/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/page/8/index.html b/docs/page/8/index.html index a060dddab..a68dcc545 100644 --- a/docs/page/8/index.html +++ b/docs/page/8/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/page/9/index.html b/docs/page/9/index.html index e05d407f3..a7b041883 100644 --- a/docs/page/9/index.html +++ b/docs/page/9/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/index.html b/docs/posts/index.html index a49f40b5d..750e2591a 100644 --- a/docs/posts/index.html +++ b/docs/posts/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/page/10/index.html b/docs/posts/page/10/index.html index ba29e4335..00609a358 100644 --- a/docs/posts/page/10/index.html +++ b/docs/posts/page/10/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/page/2/index.html b/docs/posts/page/2/index.html index 7b725316f..8693ea012 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 143b19b45..c4f9c67bd 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 4f0caa337..1eff0dcbb 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 6dfe247aa..e0be22dea 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 58399710a..b3fc7719a 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 478fd5a9c..c5da65cbe 100644 --- a/docs/posts/page/7/index.html +++ b/docs/posts/page/7/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/page/8/index.html b/docs/posts/page/8/index.html index cd10bd8f3..a42a53994 100644 --- a/docs/posts/page/8/index.html +++ b/docs/posts/page/8/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/page/9/index.html b/docs/posts/page/9/index.html index da7fcf46b..44d427ec9 100644 --- a/docs/posts/page/9/index.html +++ b/docs/posts/page/9/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/sitemap.xml b/docs/sitemap.xml index 4d0f082eb..996944cc4 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/ - 2023-06-04T11:00:30+03:00 + 2023-06-06T16:54:25+03:00 https://alanorth.github.io/cgspace-notes/ - 2023-06-04T11:00:30+03:00 + 2023-06-06T16:54:25+03:00 https://alanorth.github.io/cgspace-notes/2023-06/ - 2023-06-04T11:00:30+03:00 + 2023-06-06T16:54:25+03:00 https://alanorth.github.io/cgspace-notes/categories/notes/ - 2023-06-04T11:00:30+03:00 + 2023-06-06T16:54:25+03:00 https://alanorth.github.io/cgspace-notes/posts/ - 2023-06-04T11:00:30+03:00 + 2023-06-06T16:54:25+03:00 https://alanorth.github.io/cgspace-notes/2023-05/ 2023-05-30T20:19:17+03:00