diff --git a/content/posts/2022-02.md b/content/posts/2022-02.md
index 3535271ce..9d12f5cad 100644
--- a/content/posts/2022-02.md
+++ b/content/posts/2022-02.md
@@ -374,4 +374,42 @@ sys 3m2.459s
- Start a full harvest on AReS
+## 2022-02-14
+
+- Last week Gaia sent me her notes on the second batch of TAC/ICW documents (items 201–400 in the spreadsheet)
+ - I created a filter in LibreOffice and selected the IDs for items with the action "delete", then I created a custom text facet in OpenRefine with this GREL:
+
+```
+or(
+isNotNull(value.match('201')),
+isNotNull(value.match('203')),
+isNotNull(value.match('209')),
+isNotNull(value.match('209')),
+isNotNull(value.match('215')),
+isNotNull(value.match('220')),
+isNotNull(value.match('225')),
+isNotNull(value.match('226')),
+isNotNull(value.match('227')),
+...
+isNotNull(value.match('396'))
+```
+
+- Then I flagged all matching records and exported a CSV to use with SAFBuilder
+ - Then I imported the SAF bundle on DSpace Test:
+
+```console
+$ JAVA_OPTS="-Xmx1024m -Dfile.encoding=UTF-8" dspace import --add --eperson=fuuu@umm.com --source /tmp/SimpleArchiveFormat --mapfile=./2022-02-14-tac-batch2-201to400.map
+```
+
+- Export the next batch from OpenRefine (items with ID 401 to 700), check duplicates, and then join with the file names:
+
+```console
+$ csvcut -c id,dc.title,dcterms.issued,dcterms.type ~/Downloads/2022-01-21-CGSpace-TAC-ICW-batch3-401to700.csv > /tmp/tac3.csv
+$ ./ilri/check-duplicates.py -i /tmp/tac3.csv -db dspacetest -u dspacetest -p 'dom@in34sniper' -o /tmp/2022-02-14-tac-batch3-401-700.csv
+$ csvcut -c id,filename ~/Downloads/2022-01-21-CGSpace-TAC-ICW-batch3-401to700.csv > /tmp/tac3-filenames.csv
+$ csvjoin -c id /tmp/2022-02-14-tac-batch3-401-700.csv /tmp/tac3-filenames.csv > /tmp/2022-02-14-tac-batch3-401-700-filenames.csv
+```
+
+- I sent these 300 items to Gaia...
+
diff --git a/docs/2022-02/index.html b/docs/2022-02/index.html
index ddfaf7a9a..5f4736fa9 100644
--- a/docs/2022-02/index.html
+++ b/docs/2022-02/index.html
@@ -21,7 +21,7 @@ We agreed to try to do more alignment of affiliations/funders with ROR
-
+
@@ -48,9 +48,9 @@ We agreed to try to do more alignment of affiliations/funders with ROR
"@type": "BlogPosting",
"headline": "February, 2022",
"url": "https://alanorth.github.io/cgspace-notes/2022-02/",
- "wordCount": "2039",
+ "wordCount": "2194",
"datePublished": "2022-02-01T14:06:54+02:00",
- "dateModified": "2022-02-11T09:41:05+03:00",
+ "dateModified": "2022-02-14T09:40:59+03:00",
"author": {
"@type": "Person",
"name": "Alan Orth"
@@ -494,6 +494,44 @@ sys 3m2.459s
- Start a full harvest on AReS
+2022-02-14
+
+- Last week Gaia sent me her notes on the second batch of TAC/ICW documents (items 201–400 in the spreadsheet)
+
+- I created a filter in LibreOffice and selected the IDs for items with the action “delete”, then I created a custom text facet in OpenRefine with this GREL:
+
+
+
+or(
+isNotNull(value.match('201')),
+isNotNull(value.match('203')),
+isNotNull(value.match('209')),
+isNotNull(value.match('209')),
+isNotNull(value.match('215')),
+isNotNull(value.match('220')),
+isNotNull(value.match('225')),
+isNotNull(value.match('226')),
+isNotNull(value.match('227')),
+...
+isNotNull(value.match('396'))
+
+- Then I flagged all matching records and exported a CSV to use with SAFBuilder
+
+- Then I imported the SAF bundle on DSpace Test:
+
+
+
+$ JAVA_OPTS="-Xmx1024m -Dfile.encoding=UTF-8" dspace import --add --eperson=fuuu@umm.com --source /tmp/SimpleArchiveFormat --mapfile=./2022-02-14-tac-batch2-201to400.map
+
+- Export the next batch from OpenRefine (items with ID 401 to 700), check duplicates, and then join with the file names:
+
+$ csvcut -c id,dc.title,dcterms.issued,dcterms.type ~/Downloads/2022-01-21-CGSpace-TAC-ICW-batch3-401to700.csv > /tmp/tac3.csv
+$ ./ilri/check-duplicates.py -i /tmp/tac3.csv -db dspacetest -u dspacetest -p 'dom@in34sniper' -o /tmp/2022-02-14-tac-batch3-401-700.csv
+$ csvcut -c id,filename ~/Downloads/2022-01-21-CGSpace-TAC-ICW-batch3-401to700.csv > /tmp/tac3-filenames.csv
+$ csvjoin -c id /tmp/2022-02-14-tac-batch3-401-700.csv /tmp/tac3-filenames.csv > /tmp/2022-02-14-tac-batch3-401-700-filenames.csv
+
+- I sent these 300 items to Gaia…
+
diff --git a/docs/categories/index.html b/docs/categories/index.html
index bee9a145e..c64e90c8e 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 2bc168edc..bc05e63cb 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 05673f661..21c082527 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 a6f6c03fc..bf3867dd4 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 534c06124..81da010fc 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 9cc3473a8..1cd762e30 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 1dab3147a..3b5061e9b 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/index.html b/docs/index.html
index 96c0cf168..54bdb554c 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 c0edba763..be516a771 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 0500171c7..1254c855d 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 9a304de47..b73ff6934 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 cd8f76f71..b2e7e83a1 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 45ef08abd..7c2ebbe77 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 8db482455..f96a8dff0 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 9a2d63da6..774058f2a 100644
--- a/docs/page/8/index.html
+++ b/docs/page/8/index.html
@@ -10,7 +10,7 @@
-
+
diff --git a/docs/posts/index.html b/docs/posts/index.html
index 12ec7fecf..5510738c6 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 08bd8a442..8238af0a8 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 e602863e1..5aa45f575 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 9350a3cc9..5184a4c10 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 04b3e7651..8063b1537 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 6fb2883f7..7861727a5 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 2dd219247..c556f5a07 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 bfdf56a99..016182e41 100644
--- a/docs/posts/page/8/index.html
+++ b/docs/posts/page/8/index.html
@@ -10,7 +10,7 @@
-
+
diff --git a/docs/sitemap.xml b/docs/sitemap.xml
index a1f4e3f86..5273e6776 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/
- 2022-02-11T09:41:05+03:00
+ 2022-02-14T09:40:59+03:00
https://alanorth.github.io/cgspace-notes/
- 2022-02-11T09:41:05+03:00
+ 2022-02-14T09:40:59+03:00
https://alanorth.github.io/cgspace-notes/2022-02/
- 2022-02-11T09:41:05+03:00
+ 2022-02-14T09:40:59+03:00
https://alanorth.github.io/cgspace-notes/categories/notes/
- 2022-02-11T09:41:05+03:00
+ 2022-02-14T09:40:59+03:00
https://alanorth.github.io/cgspace-notes/posts/
- 2022-02-11T09:41:05+03:00
+ 2022-02-14T09:40:59+03:00
https://alanorth.github.io/cgspace-notes/2022-01/
2022-02-07T09:49:34+03:00