mirror of
https://github.com/dtomlinson91/street_group_tech_test
synced 2025-12-22 03:55:43 +00:00
adding latest beam pipeline code for dataflow
This commit is contained in:
@@ -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 = list(list(element[0]), list([element[1][0]]))
|
deduplicated_element = (list(element[0]), [list(element[1])[0]])
|
||||||
yield deduplicated_element
|
yield deduplicated_element
|
||||||
else:
|
else:
|
||||||
yield element
|
yield element
|
||||||
|
|||||||
Reference in New Issue
Block a user