From 98f18b3a1044eed995a26019dc14a37ace5aa9be Mon Sep 17 00:00:00 2001
From: Martin Czygan <martin.czygan@gmail.com>
Date: Tue, 30 Mar 2021 03:11:52 +0200
Subject: example task

---
 python/refcat/tasks.py | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

(limited to 'python')

diff --git a/python/refcat/tasks.py b/python/refcat/tasks.py
index df56b9d..fbed8ca 100644
--- a/python/refcat/tasks.py
+++ b/python/refcat/tasks.py
@@ -1429,10 +1429,20 @@ class MAGDOI(Refcat):
 
 # ==== WikipediaCitations
 
-class BiblioRefWikipediaCitations(Refcat):
+class BiblioRefWikiDOISortedKeys(Refcat):
     """
-    Generate a biblioref schema from wikipedia citations minimal file.
+    Sorted DOI keys from wikipedia.
     """
 
     def requires(self):
         return WikipediaCitationsMinimalDataset()
+
+    def run(self):
+        output = shellout("cat {input} |
+                          skate-biblioref-from-wikipedia |
+                          LC_ALL=C sort -s 10% -k2,2 |
+                          zstd -T0 -c > {output}
+                          """, input=self.input().path)
+
+    def output(self):
+        return luigi.LocalTarget(path=self.path(ext="tsv.zst"), format=Zstd)
-- 
cgit v1.2.3