aboutsummaryrefslogtreecommitdiffstats
path: root/python
diff options
context:
space:
mode:
Diffstat (limited to 'python')
-rw-r--r--python/refcat/tasks.py14
1 files changed, 12 insertions, 2 deletions
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)