Search in sources :

Example 1 with OutputDatasetFacet

use of io.openlineage.client.OpenLineage.OutputDatasetFacet in project OpenLineage by OpenLineage.

the class OutputStatisticsOutputDatasetFacetBuilderTest method testBuild.

@Test
public void testBuild() {
    OutputStatisticsOutputDatasetFacetBuilder builder = new OutputStatisticsOutputDatasetFacetBuilder(OpenLineageContext.builder().openLineage(new OpenLineage(OpenLineageClient.OPEN_LINEAGE_CLIENT_URI)).sparkContext(sparkContext).build());
    JobMetricsHolder.getInstance().addJobStages(1, Collections.singleton(1));
    TaskMetrics taskMetrics = new TaskMetrics();
    taskMetrics.outputMetrics().setBytesWritten(10L);
    taskMetrics.outputMetrics().setRecordsWritten(100L);
    JobMetricsHolder.getInstance().addMetrics(1, taskMetrics);
    Map<String, OutputDatasetFacet> facetsMap = new HashMap<>();
    builder.build(new SparkListenerJobEnd(1, 1L, JobSucceeded$.MODULE$), facetsMap::put);
    assertThat(facetsMap).hasEntrySatisfying("outputStatistics", facet -> assertThat(facet).hasFieldOrPropertyWithValue("rowCount", 100L).hasFieldOrPropertyWithValue("size", 10L));
}
Also used : TaskMetrics(org.apache.spark.executor.TaskMetrics) HashMap(java.util.HashMap) SparkListenerJobEnd(org.apache.spark.scheduler.SparkListenerJobEnd) OpenLineage(io.openlineage.client.OpenLineage) OutputDatasetFacet(io.openlineage.client.OpenLineage.OutputDatasetFacet) Test(org.junit.jupiter.api.Test)

Example 2 with OutputDatasetFacet

use of io.openlineage.client.OpenLineage.OutputDatasetFacet in project OpenLineage by OpenLineage.

the class OpenLineageRunEventBuilder method buildOutputDatasets.

private List<OpenLineage.OutputDataset> buildOutputDatasets(List<Object> nodes) {
    log.info("Visiting query plan {} with output dataset builders {}", openLineageContext.getQueryExecution(), outputDatasetBuilders);
    Function1<LogicalPlan, Collection<OutputDataset>> visitor = visitLogicalPlan(PlanUtils.merge(outputDatasetQueryPlanVisitors));
    List<OutputDataset> datasets = Stream.concat(buildDatasets(nodes, outputDatasetBuilders), openLineageContext.getQueryExecution().map(qe -> visitor.apply(qe.optimizedPlan())).map(Collection::stream).orElse(Stream.empty())).collect(Collectors.toList());
    OpenLineage openLineage = openLineageContext.getOpenLineage();
    if (!datasets.isEmpty()) {
        Map<String, OutputDatasetFacet> outputFacetsMap = new HashMap<>();
        nodes.forEach(event -> outputDatasetFacetBuilders.forEach(fn -> fn.accept(event, outputFacetsMap::put)));
        Map<String, DatasetFacet> datasetFacetsMap = new HashMap<>();
        nodes.forEach(event -> datasetFacetBuilders.forEach(fn -> fn.accept(event, datasetFacetsMap::put)));
        return datasets.stream().map(ds -> openLineage.newOutputDatasetBuilder().name(ds.getName()).namespace(ds.getNamespace()).outputFacets(mergeFacets(outputFacetsMap, ds.getOutputFacets(), OutputDatasetOutputFacets.class)).facets(mergeFacets(datasetFacetsMap, ds.getFacets(), DatasetFacets.class)).build()).collect(Collectors.toList());
    }
    return datasets;
}
Also used : OpenLineageClient(io.openlineage.spark.agent.client.OpenLineageClient) Arrays(java.util.Arrays) InputDataset(io.openlineage.client.OpenLineage.InputDataset) RunFacetsBuilder(io.openlineage.client.OpenLineage.RunFacetsBuilder) RunEventBuilder(io.openlineage.client.OpenLineage.RunEventBuilder) DatasetFacets(io.openlineage.client.OpenLineage.DatasetFacets) OutputDataset(io.openlineage.client.OpenLineage.OutputDataset) Map(java.util.Map) JobFacet(io.openlineage.client.OpenLineage.JobFacet) SparkListenerSQLExecutionStart(org.apache.spark.sql.execution.ui.SparkListenerSQLExecutionStart) JsonAnyGetter(com.fasterxml.jackson.annotation.JsonAnyGetter) TypeReference(com.fasterxml.jackson.core.type.TypeReference) JsonDeserializer(com.fasterxml.jackson.databind.JsonDeserializer) Method(java.lang.reflect.Method) RunEvent(io.openlineage.client.OpenLineage.RunEvent) Stage(org.apache.spark.scheduler.Stage) ScalaConversionUtils.toScalaFn(io.openlineage.spark.agent.util.ScalaConversionUtils.toScalaFn) LogicalPlan(org.apache.spark.sql.catalyst.plans.logical.LogicalPlan) PartialFunction(scala.PartialFunction) NonNull(lombok.NonNull) Collection(java.util.Collection) DatasetFacet(io.openlineage.client.OpenLineage.DatasetFacet) Collectors(java.util.stream.Collectors) IntrospectionException(java.beans.IntrospectionException) OutputDatasetOutputFacets(io.openlineage.client.OpenLineage.OutputDatasetOutputFacets) PlanUtils(io.openlineage.spark.agent.util.PlanUtils) JsonAnySetter(com.fasterxml.jackson.annotation.JsonAnySetter) List(java.util.List) Slf4j(lombok.extern.slf4j.Slf4j) Stream(java.util.stream.Stream) CustomFacetBuilder(io.openlineage.spark.api.CustomFacetBuilder) Type(java.lang.reflect.Type) PropertyDescriptor(java.beans.PropertyDescriptor) Optional(java.util.Optional) RDD(org.apache.spark.rdd.RDD) RunFacet(io.openlineage.client.OpenLineage.RunFacet) JobFailed(org.apache.spark.scheduler.JobFailed) OutputDatasetFacet(io.openlineage.client.OpenLineage.OutputDatasetFacet) ParentRunFacet(io.openlineage.client.OpenLineage.ParentRunFacet) Function1(scala.Function1) HashMap(java.util.HashMap) InputDatasetInputFacets(io.openlineage.client.OpenLineage.InputDatasetInputFacets) ScalaConversionUtils.fromSeq(io.openlineage.spark.agent.util.ScalaConversionUtils.fromSeq) ArrayList(java.util.ArrayList) Introspector(java.beans.Introspector) RunFacets(io.openlineage.client.OpenLineage.RunFacets) DeserializationProblemHandler(com.fasterxml.jackson.databind.deser.DeserializationProblemHandler) JobBuilder(io.openlineage.client.OpenLineage.JobBuilder) BeanInfo(java.beans.BeanInfo) SparkListenerJobEnd(org.apache.spark.scheduler.SparkListenerJobEnd) SparkListenerSQLExecutionEnd(org.apache.spark.sql.execution.ui.SparkListenerSQLExecutionEnd) DeserializationContext(com.fasterxml.jackson.databind.DeserializationContext) JsonParser(com.fasterxml.jackson.core.JsonParser) OpenLineageContext(io.openlineage.spark.api.OpenLineageContext) ActiveJob(org.apache.spark.scheduler.ActiveJob) SparkListenerJobStart(org.apache.spark.scheduler.SparkListenerJobStart) ObjectMapper(com.fasterxml.jackson.databind.ObjectMapper) InputDatasetFacet(io.openlineage.client.OpenLineage.InputDatasetFacet) ScalaConversionUtils(io.openlineage.spark.agent.util.ScalaConversionUtils) SparkListenerStageSubmitted(org.apache.spark.scheduler.SparkListenerStageSubmitted) OpenLineageEventHandlerFactory(io.openlineage.spark.api.OpenLineageEventHandlerFactory) ParameterizedType(java.lang.reflect.ParameterizedType) AllArgsConstructor(lombok.AllArgsConstructor) SparkListenerStageCompleted(org.apache.spark.scheduler.SparkListenerStageCompleted) OpenLineage(io.openlineage.client.OpenLineage) Collections(java.util.Collections) HashMap(java.util.HashMap) OutputDatasetOutputFacets(io.openlineage.client.OpenLineage.OutputDatasetOutputFacets) OutputDataset(io.openlineage.client.OpenLineage.OutputDataset) OpenLineage(io.openlineage.client.OpenLineage) Collection(java.util.Collection) LogicalPlan(org.apache.spark.sql.catalyst.plans.logical.LogicalPlan) DatasetFacet(io.openlineage.client.OpenLineage.DatasetFacet) OutputDatasetFacet(io.openlineage.client.OpenLineage.OutputDatasetFacet) InputDatasetFacet(io.openlineage.client.OpenLineage.InputDatasetFacet) OutputDatasetFacet(io.openlineage.client.OpenLineage.OutputDatasetFacet)

Aggregations

OpenLineage (io.openlineage.client.OpenLineage)2 OutputDatasetFacet (io.openlineage.client.OpenLineage.OutputDatasetFacet)2 HashMap (java.util.HashMap)2 SparkListenerJobEnd (org.apache.spark.scheduler.SparkListenerJobEnd)2 JsonAnyGetter (com.fasterxml.jackson.annotation.JsonAnyGetter)1 JsonAnySetter (com.fasterxml.jackson.annotation.JsonAnySetter)1 JsonParser (com.fasterxml.jackson.core.JsonParser)1 TypeReference (com.fasterxml.jackson.core.type.TypeReference)1 DeserializationContext (com.fasterxml.jackson.databind.DeserializationContext)1 JsonDeserializer (com.fasterxml.jackson.databind.JsonDeserializer)1 ObjectMapper (com.fasterxml.jackson.databind.ObjectMapper)1 DeserializationProblemHandler (com.fasterxml.jackson.databind.deser.DeserializationProblemHandler)1 DatasetFacet (io.openlineage.client.OpenLineage.DatasetFacet)1 DatasetFacets (io.openlineage.client.OpenLineage.DatasetFacets)1 InputDataset (io.openlineage.client.OpenLineage.InputDataset)1 InputDatasetFacet (io.openlineage.client.OpenLineage.InputDatasetFacet)1 InputDatasetInputFacets (io.openlineage.client.OpenLineage.InputDatasetInputFacets)1 JobBuilder (io.openlineage.client.OpenLineage.JobBuilder)1 JobFacet (io.openlineage.client.OpenLineage.JobFacet)1 OutputDataset (io.openlineage.client.OpenLineage.OutputDataset)1