adding latest beam pipeline code for dataflow

This commit is contained in:
2021-09-26 16:16:58 +01:00
parent 9f53c66975
commit 8047b5ced4

View File

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