diff --git a/content/posts/2024-04.md b/content/posts/2024-04.md index 9e4c4b1a4..96cb0f646 100644 --- a/content/posts/2024-04.md +++ b/content/posts/2024-04.md @@ -152,4 +152,18 @@ COPY 25666 - Spend some time looking at duplicate DOIs again... +## 2024-04-29 + +- Start working on the IFPRI 2020–2021 batch migration + - I modified my `check_duplicates.py` script to check for DOIs instead of titles, and use a similarity of 1.0 to make sure the match is exact +- I noticed something in the Tomcat log: + +```console +tomcat9[690]: WARNING: The HTTP response header [Content-Disposition] with value [attachment; filename="Literature review on Women’s Empowerment and their Resilience2.pdf"] has been removed from the response because it is invalid +tomcat9[690]: java.lang.IllegalArgumentException: The Unicode character [’] at code point [8,217] cannot be encoded as it is outside the permitted range of 0 to 255 +``` + +- I found the bitstream's ID and then used the `ds6_bitstream2itemhandle` [SQL helper function](https://wiki.lyrasis.org/display/DSPACE/Helper+SQL+functions+for+DSpace+6) to find the item's handle + - Then I replaced the curly quote with a regular quote in all bistreams + diff --git a/docs/2024-04/index.html b/docs/2024-04/index.html index c09936843..8cd0c7483 100644 --- a/docs/2024-04/index.html +++ b/docs/2024-04/index.html @@ -14,7 +14,7 @@ Work on CGSpace duplicate DOIs more - + @@ -34,9 +34,9 @@ Work on CGSpace duplicate DOIs more "@type": "BlogPosting", "headline": "April, 2024", "url": "https://alanorth.github.io/cgspace-notes/2024-04/", - "wordCount": "728", + "wordCount": "852", "datePublished": "2024-04-04T10:23:00+03:00", - "dateModified": "2024-04-25T15:28:20+03:00", + "dateModified": "2024-04-27T11:22:58+03:00", "author": { "@type": "Person", "name": "Alan Orth" @@ -264,6 +264,24 @@ curl -s -o /dev/null 0.01s user 0.01s system 0% cpu 4.764 total +

2024-04-29

+ +
tomcat9[690]: WARNING: The HTTP response header [Content-Disposition] with value [attachment; filename="Literature review on Women’s Empowerment and their Resilience2.pdf"] has been removed from the response because it is invalid
+tomcat9[690]: java.lang.IllegalArgumentException: The Unicode character [’] at code point [8,217] cannot be encoded as it is outside the permitted range of 0 to 255
+
diff --git a/docs/categories/index.html b/docs/categories/index.html index 171d2580b..2dcfe86d4 100644 --- a/docs/categories/index.html +++ b/docs/categories/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/categories/index.xml b/docs/categories/index.xml index 7c5b8199b..41d704d29 100644 --- a/docs/categories/index.xml +++ b/docs/categories/index.xml @@ -6,7 +6,7 @@ Recent content in Categories on CGSpace Notes Hugo en-us - Thu, 25 Apr 2024 15:28:20 +0300 + Sat, 27 Apr 2024 11:22:58 +0300 Notes diff --git a/docs/categories/notes/index.html b/docs/categories/notes/index.html index 9ee46b3bb..28686c2fa 100644 --- a/docs/categories/notes/index.html +++ b/docs/categories/notes/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/categories/notes/index.xml b/docs/categories/notes/index.xml index 9d95cd698..44845b186 100644 --- a/docs/categories/notes/index.xml +++ b/docs/categories/notes/index.xml @@ -6,7 +6,7 @@ Recent content in Notes on CGSpace Notes Hugo en-us - Thu, 25 Apr 2024 15:28:20 +0300 + Sat, 27 Apr 2024 11:22:58 +0300 April, 2024 diff --git a/docs/categories/notes/page/2/index.html b/docs/categories/notes/page/2/index.html index 6c944ba18..aaf2fdfaf 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 5c30dc9cb..38d575e41 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 7ae84a23f..a08d572a8 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 6e077eb9e..58fc8d46f 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 f393f8761..37e1e1bd4 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 7d743c4ed..45bbc605c 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 38af56aef..3726316a9 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/categories/notes/page/9/index.html b/docs/categories/notes/page/9/index.html index 475708fd7..05042c3c3 100644 --- a/docs/categories/notes/page/9/index.html +++ b/docs/categories/notes/page/9/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/index.html b/docs/index.html index 912f3f461..2ce2a0ba4 100644 --- a/docs/index.html +++ b/docs/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/index.xml b/docs/index.xml index d6e854dcf..ccd6ed08f 100644 --- a/docs/index.xml +++ b/docs/index.xml @@ -6,7 +6,7 @@ Recent content on CGSpace Notes Hugo en-us - Thu, 25 Apr 2024 15:28:20 +0300 + Sat, 27 Apr 2024 11:22:58 +0300 April, 2024 diff --git a/docs/page/10/index.html b/docs/page/10/index.html index 521f7ffdb..f1e5d388e 100644 --- a/docs/page/10/index.html +++ b/docs/page/10/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/page/11/index.html b/docs/page/11/index.html index b12463803..92ab923dc 100644 --- a/docs/page/11/index.html +++ b/docs/page/11/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/page/2/index.html b/docs/page/2/index.html index 98168a9c0..fec6c7f23 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 258d7fde7..1f6bcc24f 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 d95a9e8ad..a647cc39d 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 c2dbcdbe9..54d30cd95 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 5888dbfe5..d5fecb25d 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 39f20f843..7170d275c 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 49a173cc0..c56389c68 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 8dcdf3aaf..5b93e8ebf 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 f0efb3da3..bb8e07048 100644 --- a/docs/posts/index.html +++ b/docs/posts/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/index.xml b/docs/posts/index.xml index 7254cd71a..769157d92 100644 --- a/docs/posts/index.xml +++ b/docs/posts/index.xml @@ -6,7 +6,7 @@ Recent content in Posts on CGSpace Notes Hugo en-us - Thu, 25 Apr 2024 15:28:20 +0300 + Sat, 27 Apr 2024 11:22:58 +0300 April, 2024 diff --git a/docs/posts/page/10/index.html b/docs/posts/page/10/index.html index aa86e41e7..1f5826648 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/11/index.html b/docs/posts/page/11/index.html index b329c130f..45e6a7f85 100644 --- a/docs/posts/page/11/index.html +++ b/docs/posts/page/11/index.html @@ -10,7 +10,7 @@ - + diff --git a/docs/posts/page/2/index.html b/docs/posts/page/2/index.html index 4f33323da..3b25cc724 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 712615041..244cfd6a8 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 2da2a4144..908561ec2 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 ca5012c37..9d761d32d 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 b83554430..df855fe62 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 66765fc07..b5c4c8983 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 7a7ba88d6..62cad330a 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 c9da763f6..6a0f305e4 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 e2291216b..8a8f6cee7 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/2024-04/ - 2024-04-25T15:28:20+03:00 + 2024-04-27T11:22:58+03:00 https://alanorth.github.io/cgspace-notes/categories/ - 2024-04-25T15:28:20+03:00 + 2024-04-27T11:22:58+03:00 https://alanorth.github.io/cgspace-notes/ - 2024-04-25T15:28:20+03:00 + 2024-04-27T11:22:58+03:00 https://alanorth.github.io/cgspace-notes/categories/notes/ - 2024-04-25T15:28:20+03:00 + 2024-04-27T11:22:58+03:00 https://alanorth.github.io/cgspace-notes/posts/ - 2024-04-25T15:28:20+03:00 + 2024-04-27T11:22:58+03:00 https://alanorth.github.io/cgspace-notes/2024-03/ 2024-04-04T10:23:49+03:00