diff options
| -rw-r--r-- | python/refcat/tasks.py | 5 |
1 files changed, 3 insertions, 2 deletions
diff --git a/python/refcat/tasks.py b/python/refcat/tasks.py index 77690c5..915d406 100644 --- a/python/refcat/tasks.py +++ b/python/refcat/tasks.py @@ -228,7 +228,7 @@ class RefsWithUnstructured(Refcat): class ReleaseExportReduced(Refcat): """ - Reduce dataset size, stripping some heave fields. + Reduce dataset size, stripping some heave fields. 110min. """ def requires(self): return ReleaseExportExpanded() @@ -297,7 +297,7 @@ class URLTabs(Refcat): class RefsDOI(Refcat): """ - Sorted (doi, doc) tuplics from refs. + Sorted (doi, doc) tuples from refs. 225m48.755s """ def requires(self): return RefsWithUnstructured() @@ -306,6 +306,7 @@ class RefsDOI(Refcat): output = shellout(""" zstdcat -T0 {input} | skate-map -m ff -x biblio.doi -skip-on-empty 1 | + skate-to-doi -f 1 | LC_ALL=C sort -T {tmpdir} -k1,1 -S25% --parallel 4 | zstd -T0 -c > {output} """, |