Examples with PipelineResult org.apache.beam.sdk.PipelineResult used on opensource projects

Example 51 with PipelineResult

use of org.apache.beam.sdk.PipelineResult in project DataflowJavaSDK-examples by GoogleCloudPlatform.

the class GameStats method main.

public static void main(String[] args) throws Exception {
    Options options = PipelineOptionsFactory.fromArgs(args).withValidation().as(Options.class);
    // Enforce that this pipeline is always run in streaming mode.
    options.setStreaming(true);
    ExampleUtils exampleUtils = new ExampleUtils(options);
    Pipeline pipeline = Pipeline.create(options);
    // Read Events from Pub/Sub using custom timestamps
    PCollection<GameActionInfo> rawEvents = pipeline.apply(PubsubIO.readStrings().withTimestampAttribute(TIMESTAMP_ATTRIBUTE).fromTopic(options.getTopic())).apply("ParseGameEvent", ParDo.of(new ParseEventFn()));
    // Extract username/score pairs from the event stream
    PCollection<KV<String, Integer>> userEvents = rawEvents.apply("ExtractUserScore", MapElements.into(TypeDescriptors.kvs(TypeDescriptors.strings(), TypeDescriptors.integers())).via((GameActionInfo gInfo) -> KV.of(gInfo.getUser(), gInfo.getScore())));
    // Calculate the total score per user over fixed windows, and
    // cumulative updates for late data.
    final PCollectionView<Map<String, Integer>> spammersView = userEvents.apply("FixedWindowsUser", Window.<KV<String, Integer>>into(FixedWindows.of(Duration.standardMinutes(options.getFixedWindowDuration())))).apply("CalculateSpammyUsers", new CalculateSpammyUsers()).apply("CreateSpammersView", View.<String, Integer>asMap());
    // [START DocInclude_FilterAndCalc]
    // Calculate the total score per team over fixed windows,
    // and emit cumulative updates for late data. Uses the side input derived above-- the set of
    // suspected robots-- to filter out scores from those users from the sum.
    // Write the results to BigQuery.
    rawEvents.apply("WindowIntoFixedWindows", Window.<GameActionInfo>into(FixedWindows.of(Duration.standardMinutes(options.getFixedWindowDuration())))).apply("FilterOutSpammers", ParDo.of(new DoFn<GameActionInfo, GameActionInfo>() {

        @ProcessElement
        public void processElement(ProcessContext c) {
            // If the user is not in the spammers Map, output the data element.
            if (c.sideInput(spammersView).get(c.element().getUser().trim()) == null) {
                c.output(c.element());
            }
        }
    }).withSideInputs(spammersView)).apply("ExtractTeamScore", new ExtractAndSumScore("team")).apply("WriteTeamSums", new WriteWindowedToBigQuery<KV<String, Integer>>(options.as(GcpOptions.class).getProject(), options.getDataset(), options.getGameStatsTablePrefix() + "_team", configureWindowedWrite()));
    // [START DocInclude_SessionCalc]
    // Detect user sessions-- that is, a burst of activity separated by a gap from further
    // activity. Find and record the mean session lengths.
    // This information could help the game designers track the changing user engagement
    // as their set of games changes.
    userEvents.apply("WindowIntoSessions", Window.<KV<String, Integer>>into(Sessions.withGapDuration(Duration.standardMinutes(options.getSessionGap()))).withTimestampCombiner(TimestampCombiner.END_OF_WINDOW)).apply(Combine.perKey(x -> 0)).apply("UserSessionActivity", ParDo.of(new UserSessionInfoFn())).apply("WindowToExtractSessionMean", Window.<Integer>into(FixedWindows.of(Duration.standardMinutes(options.getUserActivityWindowDuration())))).apply(Mean.<Integer>globally().withoutDefaults()).apply("WriteAvgSessionLength", new WriteWindowedToBigQuery<Double>(options.as(GcpOptions.class).getProject(), options.getDataset(), options.getGameStatsTablePrefix() + "_sessions", configureSessionWindowWrite()));
    // [END DocInclude_Rewindow]
    // Run the pipeline and wait for the pipeline to finish; capture cancellation requests from the
    // command line.
    PipelineResult result = pipeline.run();
    exampleUtils.waitToFinish(result);
}

Example 52 with PipelineResult

use of org.apache.beam.sdk.PipelineResult in project DataflowJavaSDK-examples by GoogleCloudPlatform.

the class LeaderBoard method main.

public static void main(String[] args) throws Exception {
    Options options = PipelineOptionsFactory.fromArgs(args).withValidation().as(Options.class);
    // Enforce that this pipeline is always run in streaming mode.
    options.setStreaming(true);
    ExampleUtils exampleUtils = new ExampleUtils(options);
    Pipeline pipeline = Pipeline.create(options);
    // Read game events from Pub/Sub using custom timestamps, which are extracted from the pubsub
    // data elements, and parse the data.
    PCollection<GameActionInfo> gameEvents = pipeline.apply(PubsubIO.readStrings().withTimestampAttribute(TIMESTAMP_ATTRIBUTE).fromTopic(options.getTopic())).apply("ParseGameEvent", ParDo.of(new ParseEventFn()));
    gameEvents.apply("CalculateTeamScores", new CalculateTeamScores(Duration.standardMinutes(options.getTeamWindowDuration()), Duration.standardMinutes(options.getAllowedLateness()))).apply("WriteTeamScoreSums", new WriteWindowedToBigQuery<KV<String, Integer>>(options.as(GcpOptions.class).getProject(), options.getDataset(), options.getLeaderBoardTableName() + "_team", configureWindowedTableWrite()));
    gameEvents.apply("CalculateUserScores", new CalculateUserScores(Duration.standardMinutes(options.getAllowedLateness()))).apply("WriteUserScoreSums", new WriteToBigQuery<KV<String, Integer>>(options.as(GcpOptions.class).getProject(), options.getDataset(), options.getLeaderBoardTableName() + "_user", configureGlobalWindowBigQueryWrite()));
    // Run the pipeline and wait for the pipeline to finish; capture cancellation requests from the
    // command line.
    PipelineResult result = pipeline.run();
    exampleUtils.waitToFinish(result);
}

Example 53 with PipelineResult

use of org.apache.beam.sdk.PipelineResult in project beam by apache.

the class TestPipeline method run.

/**
   * Runs this {@link TestPipeline}, unwrapping any {@code AssertionError} that is raised during
   * testing.
   */
public PipelineResult run() {
    checkState(enforcement.isPresent(), "Is your TestPipeline declaration missing a @Rule annotation? Usage: " + "@Rule public final transient TestPipeline pipeline = TestPipeline.create();");
    final PipelineResult pipelineResult;
    try {
        enforcement.get().beforePipelineExecution();
        pipelineResult = super.run();
        verifyPAssertsSucceeded(this, pipelineResult);
    } catch (RuntimeException exc) {
        Throwable cause = exc.getCause();
        if (cause instanceof AssertionError) {
            throw (AssertionError) cause;
        } else {
            throw exc;
        }
    }
    // If we reach this point, the pipeline has been run and no exceptions have been thrown during
    // its execution.
    enforcement.get().afterPipelineExecution();
    return pipelineResult;
}

Example 54 with PipelineResult

use of org.apache.beam.sdk.PipelineResult in project beam by apache.

the class MetricsTest method testCommittedGaugeMetrics.

@Category({ ValidatesRunner.class, UsesCommittedMetrics.class, UsesGaugeMetrics.class })
@Test
public void testCommittedGaugeMetrics() {
    PipelineResult result = runPipelineWithMetrics();
    MetricQueryResults metrics = queryTestMetrics(result);
    assertGaugeMetrics(metrics, true);
}

Example 55 with PipelineResult

use of org.apache.beam.sdk.PipelineResult in project beam by apache.

the class MetricsTest method testBoundedSourceMetrics.

@Test
@Category({ ValidatesRunner.class, UsesAttemptedMetrics.class, UsesCounterMetrics.class })
public void testBoundedSourceMetrics() {
    long numElements = 1000;
    pipeline.apply(GenerateSequence.from(0).to(numElements));
    PipelineResult pipelineResult = pipeline.run();
    MetricQueryResults metrics = pipelineResult.metrics().queryMetrics(MetricsFilter.builder().addNameFilter(MetricNameFilter.named(ELEMENTS_READ.namespace(), ELEMENTS_READ.name())).build());
    assertThat(metrics.counters(), hasItem(attemptedMetricsResult(ELEMENTS_READ.namespace(), ELEMENTS_READ.name(), "Read(BoundedCountingSource)", 1000L)));
}