Examples with MaxWatermarkSource org.apache.flink.state.api.utils.MaxWatermarkSource used on opensource projects

Example 6 with MaxWatermarkSource

use of org.apache.flink.state.api.utils.MaxWatermarkSource in project flink by apache.

the class SavepointWriterWindowITCase method testSlideWindow.

@Test
public void testSlideWindow() throws Exception {
    final String savepointPath = getTempDirPath(new AbstractID().toHexString());
    StreamExecutionEnvironment env = StreamExecutionEnvironment.getExecutionEnvironment();
    env.setStateBackend(stateBackend);
    env.setRuntimeMode(RuntimeExecutionMode.AUTOMATIC);
    DataStream<Tuple2<String, Integer>> bootstrapData = env.fromCollection(WORDS).map(word -> Tuple2.of(word, 1), TUPLE_TYPE_INFO).assignTimestampsAndWatermarks(WatermarkStrategy.<Tuple2<String, Integer>>noWatermarks().withTimestampAssigner((record, ts) -> 2L));
    WindowedStateTransformation<Tuple2<String, Integer>, String, TimeWindow> transformation = OperatorTransformation.bootstrapWith(bootstrapData).keyBy(tuple -> tuple.f0, Types.STRING).window(SlidingEventTimeWindows.of(Time.milliseconds(5), Time.milliseconds(1)));
    SavepointWriter.newSavepoint(stateBackend, 128).withOperator(UID, windowBootstrap.bootstrap(transformation)).write(savepointPath);
    env.execute("write state");
    WindowedStream<Tuple2<String, Integer>, String, TimeWindow> stream = env.addSource(new MaxWatermarkSource<Tuple2<String, Integer>>()).returns(TUPLE_TYPE_INFO).keyBy(tuple -> tuple.f0).window(SlidingEventTimeWindows.of(Time.milliseconds(5), Time.milliseconds(1)));
    DataStream<Tuple2<String, Integer>> windowed = windowStream.window(stream).uid(UID);
    CompletableFuture<Collection<Tuple2<String, Integer>>> future = collector.collect(windowed);
    submitJob(savepointPath, env);
    Collection<Tuple2<String, Integer>> results = future.get().stream().distinct().collect(Collectors.toList());
    Assert.assertThat("Incorrect results from bootstrapped windows", results, STANDARD_MATCHER);
}

Example 7 with MaxWatermarkSource

use of org.apache.flink.state.api.utils.MaxWatermarkSource in project flink by apache.

the class WritableSavepointWindowITCase method testSlideWindow.

@Test
public void testSlideWindow() throws Exception {
    final String savepointPath = getTempDirPath(new AbstractID().toHexString());
    ExecutionEnvironment bEnv = ExecutionEnvironment.getExecutionEnvironment();
    DataSet<Tuple2<String, Integer>> bootstrapData = bEnv.fromCollection(WORDS).map(word -> Tuple2.of(word, 1)).returns(TUPLE_TYPE_INFO);
    WindowedOperatorTransformation<Tuple2<String, Integer>, String, TimeWindow> transformation = OperatorTransformation.bootstrapWith(bootstrapData).assignTimestamps(record -> 2L).keyBy(tuple -> tuple.f0, Types.STRING).window(SlidingEventTimeWindows.of(Time.milliseconds(5), Time.milliseconds(1)));
    Savepoint.create(new MemoryStateBackend(), 128).withOperator(UID, windowBootstrap.bootstrap(transformation)).write(savepointPath);
    bEnv.execute("write state");
    StreamExecutionEnvironment sEnv = StreamExecutionEnvironment.getExecutionEnvironment();
    WindowedStream<Tuple2<String, Integer>, String, TimeWindow> stream = sEnv.addSource(new MaxWatermarkSource<Tuple2<String, Integer>>()).returns(TUPLE_TYPE_INFO).keyBy(tuple -> tuple.f0).window(SlidingEventTimeWindows.of(Time.milliseconds(5), Time.milliseconds(1)));
    DataStream<Tuple2<String, Integer>> windowed = windowStream.window(stream).uid(UID);
    CompletableFuture<Collection<Tuple2<String, Integer>>> future = collector.collect(windowed);
    submitJob(savepointPath, sEnv);
    Collection<Tuple2<String, Integer>> results = future.get();
    Assert.assertEquals("Incorrect number of results", 15, results.size());
    Assert.assertThat("Incorrect bootstrap state", new HashSet<>(results), STANDARD_MATCHER);
}

Example 8 with MaxWatermarkSource

use of org.apache.flink.state.api.utils.MaxWatermarkSource in project flink by apache.

the class WritableSavepointWindowITCase method testSlideWindowWithEvictor.

@Test
public void testSlideWindowWithEvictor() throws Exception {
    final String savepointPath = getTempDirPath(new AbstractID().toHexString());
    ExecutionEnvironment bEnv = ExecutionEnvironment.getExecutionEnvironment();
    DataSet<Tuple2<String, Integer>> bootstrapData = bEnv.fromCollection(WORDS).map(word -> Tuple2.of(word, 1)).returns(TUPLE_TYPE_INFO);
    WindowedOperatorTransformation<Tuple2<String, Integer>, String, TimeWindow> transformation = OperatorTransformation.bootstrapWith(bootstrapData).assignTimestamps(record -> 2L).keyBy(tuple -> tuple.f0, Types.STRING).window(SlidingEventTimeWindows.of(Time.milliseconds(5), Time.milliseconds(1))).evictor(CountEvictor.of(1));
    Savepoint.create(new MemoryStateBackend(), 128).withOperator(UID, windowBootstrap.bootstrap(transformation)).write(savepointPath);
    bEnv.execute("write state");
    StreamExecutionEnvironment sEnv = StreamExecutionEnvironment.getExecutionEnvironment();
    WindowedStream<Tuple2<String, Integer>, String, TimeWindow> stream = sEnv.addSource(new MaxWatermarkSource<Tuple2<String, Integer>>()).returns(TUPLE_TYPE_INFO).keyBy(tuple -> tuple.f0).window(SlidingEventTimeWindows.of(Time.milliseconds(5), Time.milliseconds(1))).evictor(CountEvictor.of(1));
    DataStream<Tuple2<String, Integer>> windowed = windowStream.window(stream).uid(UID);
    CompletableFuture<Collection<Tuple2<String, Integer>>> future = collector.collect(windowed);
    submitJob(savepointPath, sEnv);
    Collection<Tuple2<String, Integer>> results = future.get();
    Assert.assertEquals("Incorrect number of results", 15, results.size());
    Assert.assertThat("Incorrect bootstrap state", new HashSet<>(results), EVICTOR_MATCHER);
}