Examples with OutputTag org.apache.flink.util.OutputTag used on opensource projects

Example 46 with OutputTag

use of org.apache.flink.util.OutputTag in project flink by splunk.

the class SideOutputITCase method testCoProcessFunctionSideOutputWithMultipleConsumers.

/**
 * Test CoProcessFunction side output with multiple consumers.
 */
@Test
public void testCoProcessFunctionSideOutputWithMultipleConsumers() throws Exception {
    final OutputTag<String> sideOutputTag1 = new OutputTag<String>("side1") {
    };
    final OutputTag<String> sideOutputTag2 = new OutputTag<String>("side2") {
    };
    TestListResultSink<String> sideOutputResultSink1 = new TestListResultSink<>();
    TestListResultSink<String> sideOutputResultSink2 = new TestListResultSink<>();
    TestListResultSink<Integer> resultSink = new TestListResultSink<>();
    StreamExecutionEnvironment see = StreamExecutionEnvironment.getExecutionEnvironment();
    see.setParallelism(3);
    DataStream<Integer> ds1 = see.fromCollection(elements);
    DataStream<Integer> ds2 = see.fromCollection(elements);
    SingleOutputStreamOperator<Integer> passThroughtStream = ds1.connect(ds2).process(new CoProcessFunction<Integer, Integer, Integer>() {

        @Override
        public void processElement1(Integer value, Context ctx, Collector<Integer> out) throws Exception {
            if (value < 4) {
                out.collect(value);
                ctx.output(sideOutputTag1, "sideout1-" + String.valueOf(value));
            }
        }

        @Override
        public void processElement2(Integer value, Context ctx, Collector<Integer> out) throws Exception {
            if (value >= 4) {
                out.collect(value);
                ctx.output(sideOutputTag2, "sideout2-" + String.valueOf(value));
            }
        }
    });
    passThroughtStream.getSideOutput(sideOutputTag1).addSink(sideOutputResultSink1);
    passThroughtStream.getSideOutput(sideOutputTag2).addSink(sideOutputResultSink2);
    passThroughtStream.addSink(resultSink);
    see.execute();
    assertEquals(Arrays.asList("sideout1-1", "sideout1-2", "sideout1-3"), sideOutputResultSink1.getSortedResult());
    assertEquals(Arrays.asList("sideout2-4", "sideout2-5"), sideOutputResultSink2.getSortedResult());
    assertEquals(Arrays.asList(1, 2, 3, 4, 5), resultSink.getSortedResult());
}

Example 47 with OutputTag

use of org.apache.flink.util.OutputTag in project flink by splunk.

the class SideOutputITCase method testCoProcessFunctionSideOutput.

/**
 * Test CoProcessFunction side output.
 */
@Test
public void testCoProcessFunctionSideOutput() throws Exception {
    final OutputTag<String> sideOutputTag = new OutputTag<String>("side") {
    };
    TestListResultSink<String> sideOutputResultSink = new TestListResultSink<>();
    TestListResultSink<Integer> resultSink = new TestListResultSink<>();
    StreamExecutionEnvironment see = StreamExecutionEnvironment.getExecutionEnvironment();
    see.setParallelism(3);
    DataStream<Integer> ds1 = see.fromCollection(elements);
    DataStream<Integer> ds2 = see.fromCollection(elements);
    SingleOutputStreamOperator<Integer> passThroughtStream = ds1.connect(ds2).process(new CoProcessFunction<Integer, Integer, Integer>() {

        @Override
        public void processElement1(Integer value, Context ctx, Collector<Integer> out) throws Exception {
            if (value < 3) {
                out.collect(value);
                ctx.output(sideOutputTag, "sideout1-" + String.valueOf(value));
            }
        }

        @Override
        public void processElement2(Integer value, Context ctx, Collector<Integer> out) throws Exception {
            if (value >= 3) {
                out.collect(value);
                ctx.output(sideOutputTag, "sideout2-" + String.valueOf(value));
            }
        }
    });
    passThroughtStream.getSideOutput(sideOutputTag).addSink(sideOutputResultSink);
    passThroughtStream.addSink(resultSink);
    see.execute();
    assertEquals(Arrays.asList("sideout1-1", "sideout1-2", "sideout2-3", "sideout2-4", "sideout2-5"), sideOutputResultSink.getSortedResult());
    assertEquals(Arrays.asList(1, 2, 3, 4, 5), resultSink.getSortedResult());
}

Example 48 with OutputTag

use of org.apache.flink.util.OutputTag in project flink by splunk.

the class SideOutputITCase method testKeyedCoProcessFunctionSideOutputWithMultipleConsumers.

/**
 * Test keyed KeyedCoProcessFunction side output with multiple consumers.
 */
@Test
public void testKeyedCoProcessFunctionSideOutputWithMultipleConsumers() throws Exception {
    final OutputTag<String> sideOutputTag1 = new OutputTag<String>("side1") {
    };
    final OutputTag<String> sideOutputTag2 = new OutputTag<String>("side2") {
    };
    TestListResultSink<String> sideOutputResultSink1 = new TestListResultSink<>();
    TestListResultSink<String> sideOutputResultSink2 = new TestListResultSink<>();
    TestListResultSink<Integer> resultSink = new TestListResultSink<>();
    StreamExecutionEnvironment see = StreamExecutionEnvironment.getExecutionEnvironment();
    see.setParallelism(3);
    DataStream<Integer> ds1 = see.fromCollection(elements);
    DataStream<Integer> ds2 = see.fromCollection(elements);
    SingleOutputStreamOperator<Integer> passThroughtStream = ds1.keyBy(i -> i).connect(ds2.keyBy(i -> i)).process(new KeyedCoProcessFunction<Integer, Integer, Integer, Integer>() {

        @Override
        public void processElement1(Integer value, Context ctx, Collector<Integer> out) throws Exception {
            if (value < 4) {
                out.collect(value);
                ctx.output(sideOutputTag1, "sideout1-" + ctx.getCurrentKey() + "-" + String.valueOf(value));
            }
        }

        @Override
        public void processElement2(Integer value, Context ctx, Collector<Integer> out) throws Exception {
            if (value >= 4) {
                out.collect(value);
                ctx.output(sideOutputTag2, "sideout2-" + ctx.getCurrentKey() + "-" + String.valueOf(value));
            }
        }
    });
    passThroughtStream.getSideOutput(sideOutputTag1).addSink(sideOutputResultSink1);
    passThroughtStream.getSideOutput(sideOutputTag2).addSink(sideOutputResultSink2);
    passThroughtStream.addSink(resultSink);
    see.execute();
    assertEquals(Arrays.asList("sideout1-1-1", "sideout1-2-2", "sideout1-3-3"), sideOutputResultSink1.getSortedResult());
    assertEquals(Arrays.asList("sideout2-4-4", "sideout2-5-5"), sideOutputResultSink2.getSortedResult());
    assertEquals(Arrays.asList(1, 2, 3, 4, 5), resultSink.getSortedResult());
}

Example 49 with OutputTag

use of org.apache.flink.util.OutputTag in project flink by splunk.

the class SortingBoundedInputITCase method testBatchExecutionWithTimersTwoInput.

@Test
public void testBatchExecutionWithTimersTwoInput() {
    StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
    // set parallelism to 1 to have consistent order of results
    env.setParallelism(1);
    Configuration config = new Configuration();
    config.set(ExecutionOptions.RUNTIME_MODE, RuntimeExecutionMode.BATCH);
    env.configure(config, this.getClass().getClassLoader());
    WatermarkStrategy<Tuple2<Integer, Integer>> watermarkStrategy = WatermarkStrategy.forGenerator(ctx -> GENERATE_WATERMARK_AFTER_4_14_TIMESTAMP).withTimestampAssigner((r, previousTimestamp) -> r.f1);
    SingleOutputStreamOperator<Integer> elements1 = env.fromElements(Tuple2.of(1, 3), Tuple2.of(1, 1), Tuple2.of(2, 1), Tuple2.of(1, 4), // late element
    Tuple2.of(2, 3), // late element
    Tuple2.of(1, 2), Tuple2.of(1, 13), Tuple2.of(1, 11), Tuple2.of(2, 14), // late element
    Tuple2.of(1, 11)).assignTimestampsAndWatermarks(watermarkStrategy).map(element -> element.f0);
    SingleOutputStreamOperator<Integer> elements2 = env.fromElements(Tuple2.of(1, 3), Tuple2.of(1, 1), Tuple2.of(2, 1), Tuple2.of(1, 4), // late element
    Tuple2.of(2, 3), // late element
    Tuple2.of(1, 2), Tuple2.of(1, 13), Tuple2.of(1, 11), Tuple2.of(2, 14), // late element
    Tuple2.of(1, 11)).assignTimestampsAndWatermarks(watermarkStrategy).map(element -> element.f0);
    OutputTag<Integer> lateElements = new OutputTag<>("late_elements", BasicTypeInfo.INT_TYPE_INFO);
    SingleOutputStreamOperator<Tuple3<Long, Integer, Integer>> sums = elements1.connect(elements2).keyBy(element -> element, element -> element).process(new KeyedCoProcessFunction<Integer, Integer, Integer, Tuple3<Long, Integer, Integer>>() {

        private MapState<Long, Integer> countState;

        private ValueState<Long> previousTimestampState;

        @Override
        public void open(Configuration parameters) {
            countState = getRuntimeContext().getMapState(new MapStateDescriptor<>("sum", BasicTypeInfo.LONG_TYPE_INFO, BasicTypeInfo.INT_TYPE_INFO));
            previousTimestampState = getRuntimeContext().getState(new ValueStateDescriptor<>("previousTimestamp", BasicTypeInfo.LONG_TYPE_INFO));
        }

        @Override
        public void processElement1(Integer value, Context ctx, Collector<Tuple3<Long, Integer, Integer>> out) throws Exception {
            processElement(value, ctx);
        }

        @Override
        public void processElement2(Integer value, Context ctx, Collector<Tuple3<Long, Integer, Integer>> out) throws Exception {
            processElement(value, ctx);
        }

        private void processElement(Integer value, Context ctx) throws Exception {
            Long elementTimestamp = ctx.timestamp();
            long nextTen = ((elementTimestamp + 10) / 10) * 10;
            ctx.timerService().registerEventTimeTimer(nextTen);
            if (elementTimestamp < ctx.timerService().currentWatermark()) {
                ctx.output(lateElements, value);
            } else {
                Long previousTimestamp = Optional.ofNullable(previousTimestampState.value()).orElse(0L);
                assertThat(elementTimestamp, greaterThanOrEqualTo(previousTimestamp));
                previousTimestampState.update(elementTimestamp);
                Integer currentCount = Optional.ofNullable(countState.get(nextTen)).orElse(0);
                countState.put(nextTen, currentCount + 1);
            }
        }

        @Override
        public void onTimer(long timestamp, OnTimerContext ctx, Collector<Tuple3<Long, Integer, Integer>> out) throws Exception {
            out.collect(Tuple3.of(timestamp, ctx.getCurrentKey(), countState.get(timestamp)));
            countState.remove(timestamp);
            // this would go in infinite loop if we did not quiesce the
            // timer service.
            ctx.timerService().registerEventTimeTimer(timestamp + 1);
        }
    });
    DataStream<Integer> lateStream = sums.getSideOutput(lateElements);
    List<Integer> lateRecordsCollected = CollectionUtil.iteratorToList(DataStreamUtils.collect(lateStream));
    List<Tuple3<Long, Integer, Integer>> sumsCollected = CollectionUtil.iteratorToList(DataStreamUtils.collect(sums));
    assertTrue(lateRecordsCollected.isEmpty());
    assertThat(sumsCollected, equalTo(Arrays.asList(Tuple3.of(10L, 1, 8), Tuple3.of(20L, 1, 6), Tuple3.of(10L, 2, 4), Tuple3.of(20L, 2, 2))));
}

Example 50 with OutputTag

use of org.apache.flink.util.OutputTag in project java-in-depth by tenstone.

the class EventTimeWMApp method test01.

public static void test01(StreamExecutionEnvironment env) {
    OutputTag<Tuple2<String, Integer>> outputTag = new OutputTag<Tuple2<String, Integer>>("late-data") {
    };
    SingleOutputStreamOperator<String> lines = env.socketTextStream("localhost", 9527).assignTimestampsAndWatermarks(new BoundedOutOfOrdernessTimestampExtractor<String>(Time.seconds(0)) {

        @Override
        public long extractTimestamp(String element) {
            return Long.parseLong(element.split(",")[0]);
        }
    });
    SingleOutputStreamOperator<Tuple2<String, Integer>> mapStream = lines.map(new MapFunction<String, Tuple2<String, Integer>>() {

        @Override
        public Tuple2<String, Integer> map(String value) throws Exception {
            String[] splits = value.split(",");
            return Tuple2.of(splits[1].trim(), Integer.parseInt(splits[2].trim()));
        }
    });
    // [0000,5000) [5000,10000)
    SingleOutputStreamOperator<String> window = mapStream.keyBy(x -> x.f0).window(TumblingEventTimeWindows.of(Time.seconds(5))).sideOutputLateData(outputTag).reduce((ReduceFunction<Tuple2<String, Integer>>) (value1, value2) -> {
        System.out.println("-----reduce invoked----" + value1.f0 + "==>" + (value1.f1 + value2.f1));
        return Tuple2.of(value1.f0, value1.f1 + value2.f1);
    }, new ProcessWindowFunction<>() {

        FastDateFormat format = FastDateFormat.getInstance("yyyy-MM-dd HH:mm:ss");

        @Override
        public void process(String s, Context context, Iterable<Tuple2<String, Integer>> elements, Collector<String> out) throws Exception {
            for (Tuple2<String, Integer> element : elements) {
                out.collect("[" + format.format(context.window().getStart()) + "==>" + format.format(context.window().getEnd()) + "], " + element.f0 + "==>" + element.f1);
            }
        }
    });
    window.print();
    DataStream<Tuple2<String, Integer>> sideOutput = window.getSideOutput(outputTag);
    sideOutput.printToErr();
/**
 * WM其实就是延迟触发的一种机制
 * WM = 数据所携带的时间(窗口中最大的时间) - 延迟执行的时间
 * WM >= 上一个窗口的结束边界 就会触发窗口的执行
 * 6999 - 2000  = 4999 >= 上一个窗口的结束边界
 */
}