Github user JoshRosen commented on a diff in the pull request:
https://github.com/apache/spark/pull/4961#discussion_r27717725
--- Diff: python/pyspark/streaming/tests.py ---
@@ -556,5 +559,42 @@ def check_output(n):
check_output(3)
+class KafkaStreamTests(PySparkStreamingTestCase):
+
+ def setUp(self):
+ super(KafkaStreamTests, self).setUp()
+
+ kafkaTestUtilsClz =
self.ssc._jvm.java.lang.Thread.currentThread().getContextClassLoader()\
+ .loadClass("org.apache.spark.streaming.kafka.KafkaTestUtils")
+ self._kafkaTestUtils = kafkaTestUtilsClz.newInstance()
+ self._kafkaTestUtils.setup()
+
+ def tearDown(self):
+ if self._kafkaTestUtils is not None:
+ self._kafkaTestUtils.teardown()
+ self._kafkaTestUtils = None
+
+ super(KafkaStreamTests, self).tearDown()
+
+ def test_kafka_stream(self):
+ """Test the Python Kafka stream API."""
+ topic = "topic1"
+ sendData = {"a": 3, "b": 5, "c": 10}
+ jSendData = MapConverter().convert(sendData,
+
self.ssc.sparkContext._gateway._gateway_client)
+
+ self._kafkaTestUtils.createTopic(topic)
+ self._kafkaTestUtils.sendMessages(topic, jSendData)
+
+ stream = KafkaUtils.createStream(self.ssc,
self._kafkaTestUtils.zkAddress(),
+ "test-streaming-consumer",
{topic: 1},
+ {"auto.offset.reset": "smallest"})
+
+ result = {}
+ for i in sum(self._collect(stream.map(lambda x: x[1]), 18), []):
--- End diff --
Instead of `18`, you could write `sum(sendData.values())` so it doesn't
look like a magic number.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
