def python_data_stream_example(): env = StreamExecutionEnvironment.get_execution_environment() # Set the parallelism to be one to make sure that all data including fired timer and normal data # are processed by the same worker and the collected result would be in order which is good for # assertion. env.set_parallelism(1) env.set_stream_time_characteristic(TimeCharacteristic.EventTime) type_info = Types.ROW_NAMED(['createTime', 'orderId', 'payAmount', 'payPlatform', 'provinceId'], [Types.LONG(), Types.LONG(), Types.DOUBLE(), Types.INT(), Types.INT()]) json_row_schema = JsonRowDeserializationSchema.builder().type_info(type_info).build() kafka_props = {'bootstrap.servers': 'localhost:9092', 'group.id': 'pyflink-e2e-source'} kafka_consumer = FlinkKafkaConsumer("timer-stream-source", json_row_schema, kafka_props) kafka_producer = FlinkKafkaProducer("timer-stream-sink", SimpleStringSchema(), kafka_props) watermark_strategy = WatermarkStrategy.for_bounded_out_of_orderness(Duration.of_seconds(5))\ .with_timestamp_assigner(KafkaRowTimestampAssigner()) kafka_consumer.set_start_from_earliest() ds = env.add_source(kafka_consumer).assign_timestamps_and_watermarks(watermark_strategy) ds.key_by(MyKeySelector(), key_type_info=Types.LONG()) \ .process(MyProcessFunction(), output_type=Types.STRING()) \ .add_sink(kafka_producer) env.execute_async("test data stream timer")
def test_for_bounded_out_of_orderness(self): jvm = get_gateway().jvm j_watermark_strategy = WatermarkStrategy.for_bounded_out_of_orderness( Duration.of_seconds(3))._j_watermark_strategy j_watermark_generator = j_watermark_strategy.createWatermarkGenerator( None) self.assertTrue( is_instance_of( j_watermark_generator, jvm.org.apache.flink.api.common. eventtime.BoundedOutOfOrdernessWatermarks)) self.assertEqual( get_field_value(j_watermark_generator, "outOfOrdernessMillis"), 3000)