From 8be5db4e2917f4bc0dd9cd584b931050bfa6be51 Mon Sep 17 00:00:00 2001
From: Diomidis Spinellis <dds@aueb.gr>
Date: Tue, 2 Jul 2024 18:03:40 +0300
Subject: [PATCH] Add top publishers

---
 examples/datacite/README.md           | 14 ++++++++++++++
 examples/datacite/doi-prefixes.sql    |  4 ++++
 examples/datacite/publisher-works.sql |  4 ++++
 3 files changed, 22 insertions(+)
 create mode 100644 examples/datacite/doi-prefixes.sql
 create mode 100644 examples/datacite/publisher-works.sql

diff --git a/examples/datacite/README.md b/examples/datacite/README.md
index 77384ee..49e339a 100644
--- a/examples/datacite/README.md
+++ b/examples/datacite/README.md
@@ -26,6 +26,20 @@ For schemes only the first ten values with the highest occurrence are listed.
 |work\_titles|57,359,160|
 |works|52,863,283|
 
+# Top ten publishers
+
+| Publisher | Count |
+|:------|------:|
+|Geoscience Australia|5,948,695|
+|SESAR|4,968,745|
+|Zenodo|4,904,143|
+|UNITE Community|2,859,190|
+|arXiv|2,393,236|
+|The Global Biodiversity Information Facility|2,270,374|
+|figshare|1,774,442|
+|Unpublished|1,087,504|
+|Cambridge Crystallographic Data Centre|1,052,983|
+|DSMZ|851,965|
 
 ## dc\_contributor\_name\_identifiers.name\_identifier\_scheme
 
diff --git a/examples/datacite/doi-prefixes.sql b/examples/datacite/doi-prefixes.sql
new file mode 100644
index 0000000..0f2ad99
--- /dev/null
+++ b/examples/datacite/doi-prefixes.sql
@@ -0,0 +1,4 @@
+-- List of DOI prefixes by number of works for each
+
+SELECT SUBSTR(doi, 1, INSTR(doi, '/') - 1) AS prefix, Count(*) AS n
+  FROM dc_works GROUP BY prefix ORDER BY n DESC;
diff --git a/examples/datacite/publisher-works.sql b/examples/datacite/publisher-works.sql
new file mode 100644
index 0000000..a95e326
--- /dev/null
+++ b/examples/datacite/publisher-works.sql
@@ -0,0 +1,4 @@
+-- List of publishers and works ordered  y number of works for each
+
+SELECT publisher, Count(*) AS n
+  FROM dc_works GROUP BY publisher ORDER BY n DESC;