Search in sources :

Example 1 with SparkPlanInfo

use of org.apache.spark.sql.execution.SparkPlanInfo in project OpenLineage by OpenLineage.

the class OpenLineageSparkListenerTest method testSqlEventWithJobEventEmitsOnce.

@Test
public void testSqlEventWithJobEventEmitsOnce() {
    SparkSession sparkSession = mock(SparkSession.class);
    SparkContext sparkContext = mock(SparkContext.class);
    EventEmitter emitter = mock(EventEmitter.class);
    QueryExecution qe = mock(QueryExecution.class);
    LogicalPlan query = UnresolvedRelation$.MODULE$.apply(TableIdentifier.apply("tableName"));
    SparkPlan plan = mock(SparkPlan.class);
    when(sparkSession.sparkContext()).thenReturn(sparkContext);
    when(sparkContext.appName()).thenReturn("appName");
    when(qe.optimizedPlan()).thenReturn(new InsertIntoHadoopFsRelationCommand(new Path("file:///tmp/dir"), null, false, Seq$.MODULE$.empty(), Option.empty(), null, Map$.MODULE$.empty(), query, SaveMode.Overwrite, Option.empty(), Option.empty(), Seq$.MODULE$.<String>empty()));
    when(qe.executedPlan()).thenReturn(plan);
    when(plan.sparkContext()).thenReturn(sparkContext);
    when(plan.nodeName()).thenReturn("execute");
    OpenLineageContext olContext = OpenLineageContext.builder().sparkSession(Optional.of(sparkSession)).sparkContext(sparkSession.sparkContext()).openLineage(new OpenLineage(OpenLineageClient.OPEN_LINEAGE_CLIENT_URI)).queryExecution(qe).build();
    olContext.getOutputDatasetQueryPlanVisitors().add(new InsertIntoHadoopFsRelationVisitor(olContext));
    ExecutionContext executionContext = new StaticExecutionContextFactory(emitter).createSparkSQLExecutionContext(1L, emitter, qe, olContext);
    executionContext.start(new SparkListenerSQLExecutionStart(1L, "", "", "", new SparkPlanInfo("name", "string", Seq$.MODULE$.empty(), Map$.MODULE$.empty(), Seq$.MODULE$.empty()), 1L));
    executionContext.start(new SparkListenerJobStart(0, 2L, Seq$.MODULE$.<StageInfo>empty(), new Properties()));
    ArgumentCaptor<OpenLineage.RunEvent> lineageEvent = ArgumentCaptor.forClass(OpenLineage.RunEvent.class);
    verify(emitter, times(2)).emit(lineageEvent.capture());
}
Also used : Path(org.apache.hadoop.fs.Path) SparkSession(org.apache.spark.sql.SparkSession) SparkPlan(org.apache.spark.sql.execution.SparkPlan) SparkListenerJobStart(org.apache.spark.scheduler.SparkListenerJobStart) StageInfo(org.apache.spark.scheduler.StageInfo) StaticExecutionContextFactory(io.openlineage.spark.agent.lifecycle.StaticExecutionContextFactory) InsertIntoHadoopFsRelationCommand(org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand) Properties(java.util.Properties) QueryExecution(org.apache.spark.sql.execution.QueryExecution) SparkListenerSQLExecutionStart(org.apache.spark.sql.execution.ui.SparkListenerSQLExecutionStart) SparkContext(org.apache.spark.SparkContext) ExecutionContext(io.openlineage.spark.agent.lifecycle.ExecutionContext) SparkPlanInfo(org.apache.spark.sql.execution.SparkPlanInfo) OpenLineage(io.openlineage.client.OpenLineage) LogicalPlan(org.apache.spark.sql.catalyst.plans.logical.LogicalPlan) OpenLineageContext(io.openlineage.spark.api.OpenLineageContext) InsertIntoHadoopFsRelationVisitor(io.openlineage.spark.agent.lifecycle.plan.InsertIntoHadoopFsRelationVisitor) Test(org.junit.jupiter.api.Test)

Aggregations

OpenLineage (io.openlineage.client.OpenLineage)1 ExecutionContext (io.openlineage.spark.agent.lifecycle.ExecutionContext)1 StaticExecutionContextFactory (io.openlineage.spark.agent.lifecycle.StaticExecutionContextFactory)1 InsertIntoHadoopFsRelationVisitor (io.openlineage.spark.agent.lifecycle.plan.InsertIntoHadoopFsRelationVisitor)1 OpenLineageContext (io.openlineage.spark.api.OpenLineageContext)1 Properties (java.util.Properties)1 Path (org.apache.hadoop.fs.Path)1 SparkContext (org.apache.spark.SparkContext)1 SparkListenerJobStart (org.apache.spark.scheduler.SparkListenerJobStart)1 StageInfo (org.apache.spark.scheduler.StageInfo)1 SparkSession (org.apache.spark.sql.SparkSession)1 LogicalPlan (org.apache.spark.sql.catalyst.plans.logical.LogicalPlan)1 QueryExecution (org.apache.spark.sql.execution.QueryExecution)1 SparkPlan (org.apache.spark.sql.execution.SparkPlan)1 SparkPlanInfo (org.apache.spark.sql.execution.SparkPlanInfo)1 InsertIntoHadoopFsRelationCommand (org.apache.spark.sql.execution.datasources.InsertIntoHadoopFsRelationCommand)1 SparkListenerSQLExecutionStart (org.apache.spark.sql.execution.ui.SparkListenerSQLExecutionStart)1 Test (org.junit.jupiter.api.Test)1