1 files changed, 64 insertions, 0 deletions
diff --git a/python/pyspark/streaming/tests.py b/python/pyspark/streaming/tests.py
index 188c8ff120..4ecae1e4bf 100644
--- a/python/pyspark/streaming/tests.py
+++ b/python/pyspark/streaming/tests.py
@@ -678,6 +678,70 @@ class KafkaStreamTests(PySparkStreamingTestCase):
         rdd = KafkaUtils.createRDD(self.sc, kafkaParams, offsetRanges, leaders)
         self._validateRddResult(sendData, rdd)
 
+    @unittest.skipIf(sys.version >= "3", "long type not support")
+    def test_kafka_rdd_get_offsetRanges(self):
+        """Test Python direct Kafka RDD get OffsetRanges."""
+        topic = self._randomTopic()
+        sendData = {"a": 3, "b": 4, "c": 5}
+        offsetRanges = [OffsetRange(topic, 0, long(0), long(sum(sendData.values())))]
+        kafkaParams = {"metadata.broker.list": self._kafkaTestUtils.brokerAddress()}
+
+        self._kafkaTestUtils.createTopic(topic)
+        self._kafkaTestUtils.sendMessages(topic, sendData)
+        rdd = KafkaUtils.createRDD(self.sc, kafkaParams, offsetRanges)
+        self.assertEqual(offsetRanges, rdd.offsetRanges())
+
+    @unittest.skipIf(sys.version >= "3", "long type not support")
+    def test_kafka_direct_stream_foreach_get_offsetRanges(self):
+        """Test the Python direct Kafka stream foreachRDD get offsetRanges."""
+        topic = self._randomTopic()
+        sendData = {"a": 1, "b": 2, "c": 3}
+        kafkaParams = {"metadata.broker.list": self._kafkaTestUtils.brokerAddress(),
+                       "auto.offset.reset": "smallest"}
+
+        self._kafkaTestUtils.createTopic(topic)
+        self._kafkaTestUtils.sendMessages(topic, sendData)
+
+        stream = KafkaUtils.createDirectStream(self.ssc, [topic], kafkaParams)
+
+        offsetRanges = []
+
+        def getOffsetRanges(_, rdd):
+            for o in rdd.offsetRanges():
+                offsetRanges.append(o)
+
+        stream.foreachRDD(getOffsetRanges)
+        self.ssc.start()
+        self.wait_for(offsetRanges, 1)
+
+        self.assertEqual(offsetRanges, [OffsetRange(topic, 0, long(0), long(6))])
+
+    @unittest.skipIf(sys.version >= "3", "long type not support")
+    def test_kafka_direct_stream_transform_get_offsetRanges(self):
+        """Test the Python direct Kafka stream transform get offsetRanges."""
+        topic = self._randomTopic()
+        sendData = {"a": 1, "b": 2, "c": 3}
+        kafkaParams = {"metadata.broker.list": self._kafkaTestUtils.brokerAddress(),
+                       "auto.offset.reset": "smallest"}
+
+        self._kafkaTestUtils.createTopic(topic)
+        self._kafkaTestUtils.sendMessages(topic, sendData)
+
+        stream = KafkaUtils.createDirectStream(self.ssc, [topic], kafkaParams)
+
+        offsetRanges = []
+
+        def transformWithOffsetRanges(rdd):
+            for o in rdd.offsetRanges():
+                offsetRanges.append(o)
+            return rdd
+
+        stream.transform(transformWithOffsetRanges).foreachRDD(lambda rdd: rdd.count())
+        self.ssc.start()
+        self.wait_for(offsetRanges, 1)
+
+        self.assertEqual(offsetRanges, [OffsetRange(topic, 0, long(0), long(6))])
+
 
 class FlumeStreamTests(PySparkStreamingTestCase):
     timeout = 20  # seconds