Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Propagate annotations of CombinePerKey transforms to resulting component transforms #28489

Merged
merged 4 commits into from
Sep 18, 2023
Merged

Propagate annotations of CombinePerKey transforms to resulting component transforms #28489

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
e7e140e
Implement unittest
hjtran Sep 15, 2023
f37d860
Implement fix
hjtran Sep 15, 2023
4a5a007
Update translations_test.py
hjtran Sep 15, 2023
b3a8e15
yapf
hjtran Sep 16, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions sdks/python/apache_beam/runners/portability/fn_api_runner/translations.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1346,6 +1346,7 @@ def lifted_stages(stage):
payload=transform.spec.payload),
inputs=transform.inputs,
outputs={'out': precombined_pcoll_id},
annotations=transform.annotations,
environment_id=transform.environment_id))

yield make_stage(
Expand All @@ -1355,6 +1356,7 @@ def lifted_stages(stage):
spec=beam_runner_api_pb2.FunctionSpec(
urn=common_urns.primitives.GROUP_BY_KEY.urn),
inputs={'in': precombined_pcoll_id},
annotations=transform.annotations,
outputs={'out': grouped_pcoll_id}))

yield make_stage(
Expand All @@ -1367,6 +1369,7 @@ def lifted_stages(stage):
payload=transform.spec.payload),
inputs={'in': grouped_pcoll_id},
outputs={'out': merged_pcoll_id},
annotations=transform.annotations,
environment_id=transform.environment_id))

yield make_stage(
Expand All @@ -1379,6 +1382,7 @@ def lifted_stages(stage):
payload=transform.spec.payload),
inputs={'in': merged_pcoll_id},
outputs=transform.outputs,
annotations=transform.annotations,
environment_id=transform.environment_id))

def unlifted_stages(stage):
Expand Down
29 changes: 29 additions & 0 deletions sdks/python/apache_beam/runners/portability/fn_api_runner/translations_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -384,6 +384,35 @@ def expand(self, pcoll):
'multiple-small-combines/min-4-globally/CombinePerKey',
optimized_stage_names)

def test_combineperkey_annotation_propagation(self):
"""
Test that the CPK component transforms inherit annotations from the
source CPK
"""
class MyCombinePerKey(beam.CombinePerKey):
def annotations(self):
return {"my_annotation":b""}
with TestPipeline() as pipeline:
pipeline | beam.Create([(1, 2)]) | MyCombinePerKey(min)

# Verify the annotations are propagated to the split up
# CPK transforms
proto = pipeline.to_runner_api(
default_environment=environments.EmbeddedPythonEnvironment(
capabilities=environments.python_sdk_capabilities()))
optimized = translations.optimize_pipeline(
proto,
phases=[translations.lift_combiners],
known_runner_urns=frozenset(),
partial=True)
for transform_id in [
'MyCombinePerKey(min)/Precombine',
'MyCombinePerKey(min)/Group',
'MyCombinePerKey(min)/Merge',
'MyCombinePerKey(min)/ExtractOutputs']:
assert ("my_annotation" in
optimized.components.transforms[transform_id].annotations)

def test_conditionally_packed_combiners(self):
class RecursiveCombine(beam.PTransform):
def __init__(self, labels):
Expand Down
Loading