本文整理汇总了Java中org.apache.beam.runners.spark.SparkRunner类的典型用法代码示例。如果您正苦于以下问题:Java SparkRunner类的具体用法?Java SparkRunner怎么用?Java SparkRunner使用的例子?那么, 这里精选的类代码示例或许可以为您提供帮助。
SparkRunner类属于org.apache.beam.runners.spark包,在下文中一共展示了SparkRunner类的12个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Java代码示例。
示例1: rejectStateAndTimers
import org.apache.beam.runners.spark.SparkRunner; //导入依赖的package包/类
/**
* Reject state and timers {@link DoFn}.
*
* @param doFn the {@link DoFn} to possibly reject.
*/
public static void rejectStateAndTimers(DoFn<?, ?> doFn) {
DoFnSignature signature = DoFnSignatures.getSignature(doFn.getClass());
if (signature.stateDeclarations().size() > 0) {
throw new UnsupportedOperationException(
String.format(
"Found %s annotations on %s, but %s cannot yet be used with state in the %s.",
DoFn.StateId.class.getSimpleName(),
doFn.getClass().getName(),
DoFn.class.getSimpleName(),
SparkRunner.class.getSimpleName()));
}
if (signature.timerDeclarations().size() > 0) {
throw new UnsupportedOperationException(
String.format(
"Found %s annotations on %s, but %s cannot yet be used with timers in the %s.",
DoFn.TimerId.class.getSimpleName(),
doFn.getClass().getName(),
DoFn.class.getSimpleName(),
SparkRunner.class.getSimpleName()));
}
}
示例2: testTrackSingle
import org.apache.beam.runners.spark.SparkRunner; //导入依赖的package包/类
@Test
public void testTrackSingle() {
options.setRunner(SparkRunner.class);
JavaSparkContext jsc = SparkContextFactory.getSparkContext(options);
JavaStreamingContext jssc = new JavaStreamingContext(jsc,
new org.apache.spark.streaming.Duration(options.getBatchIntervalMillis()));
Pipeline p = Pipeline.create(options);
CreateStream<Integer> emptyStream =
CreateStream.of(
VarIntCoder.of(),
Duration.millis(options.getBatchIntervalMillis())).emptyBatch();
p.apply(emptyStream).apply(ParDo.of(new PassthroughFn<>()));
p.traverseTopologically(new StreamingSourceTracker(jssc, p, ParDo.MultiOutput.class, 0));
assertThat(StreamingSourceTracker.numAssertions, equalTo(1));
}
示例3: rejectSplittable
import org.apache.beam.runners.spark.SparkRunner; //导入依赖的package包/类
public static void rejectSplittable(DoFn<?, ?> doFn) {
DoFnSignature signature = DoFnSignatures.getSignature(doFn.getClass());
if (signature.processElement().isSplittable()) {
throw new UnsupportedOperationException(
String.format(
"%s does not support splittable DoFn: %s", SparkRunner.class.getSimpleName(), doFn));
}
}
示例4: call
import org.apache.beam.runners.spark.SparkRunner; //导入依赖的package包/类
@Override
public JavaStreamingContext call() throws Exception {
LOG.info("Creating a new Spark Streaming Context");
// validate unbounded read properties.
checkArgument(
options.getMinReadTimeMillis() < options.getBatchIntervalMillis(),
"Minimum read time has to be less than batch time.");
checkArgument(
options.getReadTimePercentage() > 0 && options.getReadTimePercentage() < 1,
"Read time percentage is bound to (0, 1).");
SparkPipelineTranslator translator =
new StreamingTransformTranslator.Translator(new TransformTranslator.Translator());
Duration batchDuration = new Duration(options.getBatchIntervalMillis());
LOG.info("Setting Spark streaming batchDuration to {} msec", batchDuration.milliseconds());
JavaSparkContext jsc = SparkContextFactory.getSparkContext(options);
JavaStreamingContext jssc = new JavaStreamingContext(jsc, batchDuration);
// We must first init accumulators since translators expect them to be instantiated.
SparkRunner.initAccumulators(options, jsc);
EvaluationContext ctxt = new EvaluationContext(jsc, pipeline, options, jssc);
// update cache candidates
SparkRunner.updateCacheCandidates(pipeline, translator, ctxt);
pipeline.traverseTopologically(new SparkRunner.Evaluator(translator, ctxt));
ctxt.computeOutputs();
checkpoint(jssc, checkpointDir);
return jssc;
}
示例5: testTrackFlattened
import org.apache.beam.runners.spark.SparkRunner; //导入依赖的package包/类
@Test
public void testTrackFlattened() {
options.setRunner(SparkRunner.class);
JavaSparkContext jsc = SparkContextFactory.getSparkContext(options);
JavaStreamingContext jssc = new JavaStreamingContext(jsc,
new org.apache.spark.streaming.Duration(options.getBatchIntervalMillis()));
Pipeline p = Pipeline.create(options);
CreateStream<Integer> queueStream1 =
CreateStream.of(
VarIntCoder.of(),
Duration.millis(options.getBatchIntervalMillis())).emptyBatch();
CreateStream<Integer> queueStream2 =
CreateStream.of(
VarIntCoder.of(),
Duration.millis(options.getBatchIntervalMillis())).emptyBatch();
PCollection<Integer> pcol1 = p.apply(queueStream1);
PCollection<Integer> pcol2 = p.apply(queueStream2);
PCollection<Integer> flattened =
PCollectionList.of(pcol1).and(pcol2).apply(Flatten.<Integer>pCollections());
flattened.apply(ParDo.of(new PassthroughFn<>()));
p.traverseTopologically(new StreamingSourceTracker(jssc, p, ParDo.MultiOutput.class, 0, 1));
assertThat(StreamingSourceTracker.numAssertions, equalTo(1));
}
示例6: StreamingSourceTracker
import org.apache.beam.runners.spark.SparkRunner; //导入依赖的package包/类
private StreamingSourceTracker(
JavaStreamingContext jssc,
Pipeline pipeline,
Class<? extends PTransform> transformClassToAssert,
Integer... expected) {
this.ctxt = new EvaluationContext(jssc.sparkContext(), pipeline, options, jssc);
this.evaluator = new SparkRunner.Evaluator(
new StreamingTransformTranslator.Translator(new TransformTranslator.Translator()), ctxt);
this.transformClassToAssert = transformClassToAssert;
this.expected = expected;
}
示例7: createSparkRunnerPipeline
import org.apache.beam.runners.spark.SparkRunner; //导入依赖的package包/类
private Pipeline createSparkRunnerPipeline() {
PipelineOptions o = PipelineOptionsFactory.create();
SparkContextOptions options = o.as(SparkContextOptions.class);
JavaSparkContext jsc = new JavaSparkContext("local[2]", "PubSubInput");
options.setProvidedSparkContext(jsc);
options.setUsesProvidedSparkContext(true);
options.setRunner(SparkRunner.class);
runtimeContainer = new BeamJobRuntimeContainer(options);
return Pipeline.create(options);
}
示例8: createSparkRunnerPipeline
import org.apache.beam.runners.spark.SparkRunner; //导入依赖的package包/类
private Pipeline createSparkRunnerPipeline() {
JavaSparkContext jsc = new JavaSparkContext("local[2]", this.getClass().getName());
PipelineOptions o = PipelineOptionsFactory.create();
SparkContextOptions options = o.as(SparkContextOptions.class);
options.setProvidedSparkContext(jsc);
options.setUsesProvidedSparkContext(true);
options.setRunner(SparkRunner.class);
runtimeContainer = new BeamJobRuntimeContainer(options);
return Pipeline.create(options);
}
示例9: setupLazyAvroCoder
import org.apache.beam.runners.spark.SparkRunner; //导入依赖的package包/类
@Before
public void setupLazyAvroCoder() {
options = PipelineOptionsFactory.as(SparkPipelineOptions.class);
options.setRunner(SparkRunner.class);
options.setSparkMaster("local");
options.setStreaming(false);
pWrite = Pipeline.create(options);
pRead = Pipeline.create(options);
}
示例10: getOptions
import org.apache.beam.runners.spark.SparkRunner; //导入依赖的package包/类
/**
* @return the options used to create this pipeline. These can be or changed before the Pipeline is created.
*/
public SparkContextOptions getOptions() {
if (options == null) {
options = PipelineOptionsFactory.as(SparkContextOptions.class);
options.setRunner(SparkRunner.class);
}
return options;
}
示例11: createSparkRunnerPipeline
import org.apache.beam.runners.spark.SparkRunner; //导入依赖的package包/类
private Pipeline createSparkRunnerPipeline() {
PipelineOptions o = PipelineOptionsFactory.create();
SparkContextOptions options = o.as(SparkContextOptions.class);
options.setProvidedSparkContext(jsc);
options.setUsesProvidedSparkContext(true);
options.setRunner(SparkRunner.class);
runtimeContainer = new BeamJobRuntimeContainer(options);
return Pipeline.create(options);
}
示例12: createSparkRunnerPipeline
import org.apache.beam.runners.spark.SparkRunner; //导入依赖的package包/类
private Pipeline createSparkRunnerPipeline() {
PipelineOptions o = PipelineOptionsFactory.create();
SparkContextOptions options = o.as(SparkContextOptions.class);
SparkConf conf = new SparkConf();
conf.setAppName("KinesisInput");
conf.setMaster("local[2]");
conf.set("spark.driver.allowMultipleContexts", "true");
JavaSparkContext jsc = new JavaSparkContext(new SparkContext(conf));
options.setProvidedSparkContext(jsc);
options.setUsesProvidedSparkContext(true);
options.setRunner(SparkRunner.class);
return Pipeline.create(options);
}