Examples with DataStream org.apache.flink.streaming.api.datastream.DataStream used on opensource projects

Example 46 with DataStream

use of org.apache.flink.streaming.api.datastream.DataStream in project flink by apache.

the class StreamOperatorChainingTest method testMultiChainingWithSplit.

/**
 * Verify that multi-chaining works with object reuse enabled.
 */
private void testMultiChainingWithSplit(StreamExecutionEnvironment env) throws Exception {
    // set parallelism to 2 to avoid chaining with source in case when available processors is
    // 1.
    env.setParallelism(2);
    // the actual elements will not be used
    DataStream<Integer> input = env.fromElements(1, 2, 3);
    sink1Results = new ArrayList<>();
    sink2Results = new ArrayList<>();
    sink3Results = new ArrayList<>();
    input = input.map(value -> value);
    OutputTag<Integer> oneOutput = new OutputTag<Integer>("one") {
    };
    OutputTag<Integer> otherOutput = new OutputTag<Integer>("other") {
    };
    SingleOutputStreamOperator<Object> split = input.process(new ProcessFunction<Integer, Object>() {

        private static final long serialVersionUID = 1L;

        @Override
        public void processElement(Integer value, Context ctx, Collector<Object> out) throws Exception {
            if (value.equals(1)) {
                ctx.output(oneOutput, value);
            } else {
                ctx.output(otherOutput, value);
            }
        }
    });
    split.getSideOutput(oneOutput).map(value -> "First 1: " + value).addSink(new SinkFunction<String>() {

        @Override
        public void invoke(String value, Context ctx) throws Exception {
            sink1Results.add(value);
        }
    });
    split.getSideOutput(oneOutput).map(value -> "First 2: " + value).addSink(new SinkFunction<String>() {

        @Override
        public void invoke(String value, Context ctx) throws Exception {
            sink2Results.add(value);
        }
    });
    split.getSideOutput(otherOutput).map(value -> "Second: " + value).addSink(new SinkFunction<String>() {

        @Override
        public void invoke(String value, Context ctx) throws Exception {
            sink3Results.add(value);
        }
    });
    // be build our own StreamTask and OperatorChain
    JobGraph jobGraph = env.getStreamGraph().getJobGraph();
    Assert.assertTrue(jobGraph.getVerticesSortedTopologicallyFromSources().size() == 2);
    JobVertex chainedVertex = jobGraph.getVerticesSortedTopologicallyFromSources().get(1);
    Configuration configuration = chainedVertex.getConfiguration();
    StreamConfig streamConfig = new StreamConfig(configuration);
    StreamMap<Integer, Integer> headOperator = streamConfig.getStreamOperator(Thread.currentThread().getContextClassLoader());
    try (MockEnvironment environment = createMockEnvironment(chainedVertex.getName())) {
        StreamTask<Integer, StreamMap<Integer, Integer>> mockTask = createMockTask(streamConfig, environment);
        OperatorChain<Integer, StreamMap<Integer, Integer>> operatorChain = createOperatorChain(streamConfig, environment, mockTask);
        headOperator.setup(mockTask, streamConfig, operatorChain.getMainOperatorOutput());
        operatorChain.initializeStateAndOpenOperators(null);
        headOperator.processElement(new StreamRecord<>(1));
        headOperator.processElement(new StreamRecord<>(2));
        headOperator.processElement(new StreamRecord<>(3));
        assertThat(sink1Results, contains("First 1: 1"));
        assertThat(sink2Results, contains("First 2: 1"));
        assertThat(sink3Results, contains("Second: 2", "Second: 3"));
    }
}

Example 47 with DataStream

use of org.apache.flink.streaming.api.datastream.DataStream in project flink by apache.

the class DataStreamJavaITCase method getComplexUnifiedPipeline.

// --------------------------------------------------------------------------------------------
// Helper methods
// --------------------------------------------------------------------------------------------
private Table getComplexUnifiedPipeline(StreamExecutionEnvironment env) {
    final DataStream<String> allowedNamesStream = env.fromElements("Bob", "Alice");
    final StreamTableEnvironment tableEnv = StreamTableEnvironment.create(env);
    tableEnv.createTemporaryView("AllowedNamesTable", tableEnv.fromDataStream(allowedNamesStream).as("allowedName"));
    final Table nameCountTable = tableEnv.sqlQuery("SELECT name, COUNT(*) AS c " + "FROM (VALUES ('Bob'), ('Alice'), ('Greg'), ('Bob')) AS NameTable(name) " + "WHERE name IN (SELECT allowedName FROM AllowedNamesTable)" + "GROUP BY name");
    final DataStream<Row> nameCountStream = tableEnv.toChangelogStream(nameCountTable);
    final DataStream<Tuple2<String, Long>> updatesPerNameStream = nameCountStream.keyBy(r -> r.<String>getFieldAs("name")).process(new KeyedProcessFunction<String, Row, Tuple2<String, Long>>() {

        ValueState<Long> count;

        @Override
        public void open(Configuration parameters) {
            count = getRuntimeContext().getState(new ValueStateDescriptor<>("count", Long.class));
        }

        @Override
        public void processElement(Row r, Context ctx, Collector<Tuple2<String, Long>> out) throws IOException {
            Long currentCount = count.value();
            if (currentCount == null) {
                currentCount = 0L;
            }
            final long updatedCount = currentCount + 1;
            count.update(updatedCount);
            out.collect(Tuple2.of(ctx.getCurrentKey(), updatedCount));
        }
    });
    tableEnv.createTemporaryView("UpdatesPerName", updatesPerNameStream);
    return tableEnv.sqlQuery("SELECT DISTINCT f0, f1 FROM UpdatesPerName");
}

Example 48 with DataStream

use of org.apache.flink.streaming.api.datastream.DataStream in project flink by apache.

the class DataStreamJavaITCase method testFromAndToChangelogStreamEventTime.

@Test
public void testFromAndToChangelogStreamEventTime() throws Exception {
    final StreamTableEnvironment tableEnv = StreamTableEnvironment.create(env);
    final DataStream<Tuple3<Long, Integer, String>> dataStream = getWatermarkedDataStream();
    final DataStream<Row> changelogStream = dataStream.map(t -> Row.ofKind(RowKind.INSERT, t.f1, t.f2)).returns(Types.ROW(Types.INT, Types.STRING));
    // derive physical columns and add a rowtime
    final Table table = tableEnv.fromChangelogStream(changelogStream, Schema.newBuilder().columnByMetadata("rowtime", TIMESTAMP_LTZ(3)).columnByExpression("computed", $("f1").upperCase()).watermark("rowtime", sourceWatermark()).build());
    tableEnv.createTemporaryView("t", table);
    // access and reorder columns
    final Table reordered = tableEnv.sqlQuery("SELECT computed, rowtime, f0 FROM t");
    // write out the rowtime column with fully declared schema
    final DataStream<Row> result = tableEnv.toChangelogStream(reordered, Schema.newBuilder().column("f1", STRING()).columnByMetadata("rowtime", TIMESTAMP_LTZ(3)).columnByExpression("ignored", $("f1").upperCase()).column("f0", INT()).build());
    // test event time window and field access
    testResult(result.keyBy(k -> k.getField("f1")).window(TumblingEventTimeWindows.of(Time.milliseconds(5))).<Row>apply((key, window, input, out) -> {
        int sum = 0;
        for (Row row : input) {
            sum += row.<Integer>getFieldAs("f0");
        }
        out.collect(Row.of(key, sum));
    }).returns(Types.ROW(Types.STRING, Types.INT)), Row.of("A", 47), Row.of("C", 1000), Row.of("C", 1000));
}

Example 49 with DataStream

use of org.apache.flink.streaming.api.datastream.DataStream in project beam by apache.

the class FlinkStreamingPortablePipelineTranslator method translateFlatten.

private <T> void translateFlatten(String id, RunnerApi.Pipeline pipeline, StreamingTranslationContext context) {
    RunnerApi.PTransform transform = pipeline.getComponents().getTransformsOrThrow(id);
    Map<String, String> allInputs = transform.getInputsMap();
    if (allInputs.isEmpty()) {
        // create an empty dummy source to satisfy downstream operations
        // we cannot create an empty source in Flink, therefore we have to
        // add the flatMap that simply never forwards the single element
        long shutdownAfterIdleSourcesMs = context.getPipelineOptions().getShutdownSourcesAfterIdleMs();
        DataStreamSource<WindowedValue<byte[]>> dummySource = context.getExecutionEnvironment().addSource(new ImpulseSourceFunction(shutdownAfterIdleSourcesMs));
        DataStream<WindowedValue<T>> result = dummySource.<WindowedValue<T>>flatMap((s, collector) -> {
        // never return anything
        }).returns(new CoderTypeInformation<>(WindowedValue.getFullCoder((Coder<T>) VoidCoder.of(), GlobalWindow.Coder.INSTANCE), context.getPipelineOptions()));
        context.addDataStream(Iterables.getOnlyElement(transform.getOutputsMap().values()), result);
    } else {
        DataStream<T> result = null;
        // Determine DataStreams that we use as input several times. For those, we need to uniquify
        // input streams because Flink seems to swallow watermarks when we have a union of one and
        // the same stream.
        HashMultiset<DataStream<T>> inputCounts = HashMultiset.create();
        for (String input : allInputs.values()) {
            DataStream<T> current = context.getDataStreamOrThrow(input);
            inputCounts.add(current, 1);
        }
        for (String input : allInputs.values()) {
            DataStream<T> current = context.getDataStreamOrThrow(input);
            final int timesRequired = inputCounts.count(current);
            if (timesRequired > 1) {
                current = current.flatMap(new FlatMapFunction<T, T>() {

                    private static final long serialVersionUID = 1L;

                    @Override
                    public void flatMap(T t, Collector<T> collector) {
                        collector.collect(t);
                    }
                });
            }
            result = (result == null) ? current : result.union(current);
        }
        context.addDataStream(Iterables.getOnlyElement(transform.getOutputsMap().values()), result);
    }
}

Example 50 with DataStream

use of org.apache.flink.streaming.api.datastream.DataStream in project flink by apache.

the class KafkaTableSinkTestBase method testKafkaTableSink.

@Test
@SuppressWarnings("unchecked")
public void testKafkaTableSink() throws Exception {
    DataStream dataStream = mock(DataStream.class);
    KafkaTableSink kafkaTableSink = spy(createTableSink());
    kafkaTableSink.emitDataStream(dataStream);
    verify(dataStream).addSink(eq(PRODUCER));
    verify(kafkaTableSink).createKafkaProducer(eq(TOPIC), eq(PROPERTIES), any(getSerializationSchema().getClass()), eq(PARTITIONER));
}