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

fix(ingest): include urn as key for kafka emitter #2634

Merged
merged 3 commits into from
Jun 3, 2021
Merged

fix(ingest): include urn as key for kafka emitter #2634

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
0f35368
fix(ingest): include urn as key for kafka
hsheth2 Jun 2, 2021
ac0758e
check for key in produce call within unit tests
hsheth2 Jun 3, 2021
b879af3
fix build issue
hsheth2 Jun 3, 2021
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
1 change: 1 addition & 0 deletions metadata-ingestion/src/datahub/emitter/kafka_emitter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,6 +61,7 @@ def emit_mce_async(
self.producer.poll(0)
self.producer.produce(
topic=self.config.topic,
key=mce.proposedSnapshot.urn,
value=mce,
on_delivery=callback,
)
Expand Down
19 changes: 16 additions & 3 deletions metadata-ingestion/tests/unit/test_kafka_sink.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
import unittest
from unittest.mock import MagicMock, patch, sentinel
from unittest.mock import MagicMock, patch

import datahub.emitter.mce_builder as builder
from datahub.ingestion.api.common import RecordEnvelope
from datahub.ingestion.api.sink import SinkReport, WriteCallback
from datahub.ingestion.sink.datahub_kafka import DatahubKafkaSink, _KafkaCallback
Expand Down Expand Up @@ -32,15 +33,27 @@ def test_kafka_sink_write(self, mock_k_callback, mock_producer, mock_context):
kafka_sink = DatahubKafkaSink.create(
{"connection": {"bootstrap": "foobar:9092"}}, mock_context
)
re = RecordEnvelope(record=sentinel, metadata={})
mce = builder.make_lineage_mce(
[
builder.make_dataset_urn("bigquery", "upstream1"),
builder.make_dataset_urn("bigquery", "upstream2"),
],
builder.make_dataset_urn("bigquery", "downstream1"),
)

re = RecordEnvelope(record=mce, metadata={})
kafka_sink.write_record_async(re, callback)
assert mock_producer_instance.poll.call_count == 1 # poll() called once

mock_producer_instance.poll.assert_called_once() # producer should call poll() first
self.validate_kafka_callback(
mock_k_callback, re, callback
) # validate kafka callback was constructed appropriately

# validate that confluent_kafka.Producer.produce was called with the right arguments
mock_producer_instance.produce.assert_called_once()
args, kwargs = mock_producer_instance.produce.call_args
assert kwargs["value"] == mce
assert kwargs["key"] # produce call should include a Kafka key
created_callback = kwargs["on_delivery"]
assert created_callback == mock_k_callback_instance.kafka_callback

Expand Down