adding latest beam pipeline code for dataflow

This commit is contained in:
2021-09-26 16:23:19 +01:00
parent 8047b5ced4
commit bb71d55f8c

View File

@@ -91,7 +91,7 @@ class DeduplicateByID(beam.DoFn):
def process(self, element):
if len(list(element[1])) > 0:
deduplicated_element = list(list(element[0]), list([element[1][0]]))
deduplicated_element = (list(element[0]), [list(element[1])[0]])
yield deduplicated_element
else:
yield element