grundprinzip commented on code in PR #37710: URL: https://github.com/apache/spark/pull/37710#discussion_r977629941
########## connect/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectService.scala: ########## @@ -0,0 +1,249 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.sql.connect.service + +import java.util +import java.util.concurrent.TimeUnit + +import scala.collection.JavaConverters._ + +import com.google.common.base.Ticker +import com.google.common.cache.CacheBuilder +import io.grpc.{Server, Status} +import io.grpc.netty.shaded.io.grpc.netty.NettyServerBuilder +import io.grpc.protobuf.services.ProtoReflectionService +import io.grpc.stub.StreamObserver + +import org.apache.spark.{SparkContext, SparkEnv} +import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.api.plugin.{DriverPlugin, ExecutorPlugin, PluginContext, SparkPlugin} +import org.apache.spark.connect.proto +import org.apache.spark.connect.proto.{ + AnalyzeResponse, + Request, + Response, + SparkConnectServiceGrpc +} +import org.apache.spark.internal.Logging +import org.apache.spark.sql.{Dataset, SparkSession} +import org.apache.spark.sql.connect.planner.SparkConnectPlanner +import org.apache.spark.sql.execution.ExtendedMode + +/** + * The SparkConnectService Implementation. + * + * This class implements the service stub from the generated code of GRPC. + * + * @param debug + * delegates debug behavior to the handlers. + */ +@Experimental +@Since("3.3.1") +class SparkConnectService(debug: Boolean) + extends SparkConnectServiceGrpc.SparkConnectServiceImplBase + with Logging { + + /** + * This is the main entry method for Spark Connect and all calls to execute a plan. + * + * The plan execution is delegated to the [[SparkConnectStreamHandler]]. All error handling + * should be directly implemented in the deferred implementation. But this method catches + * generic errors. + * + * @param request + * @param responseObserver + */ + override def executePlan(request: Request, responseObserver: StreamObserver[Response]): Unit = { + try { + new SparkConnectStreamHandler(responseObserver).handle(request) + } catch { + case e: Exception => Review Comment: Done ########## connect/src/main/scala/org/apache/spark/sql/connect/service/SparkConnectService.scala: ########## @@ -0,0 +1,249 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.spark.sql.connect.service + +import java.util +import java.util.concurrent.TimeUnit + +import scala.collection.JavaConverters._ + +import com.google.common.base.Ticker +import com.google.common.cache.CacheBuilder +import io.grpc.{Server, Status} +import io.grpc.netty.shaded.io.grpc.netty.NettyServerBuilder +import io.grpc.protobuf.services.ProtoReflectionService +import io.grpc.stub.StreamObserver + +import org.apache.spark.{SparkContext, SparkEnv} +import org.apache.spark.annotation.{Experimental, Since} +import org.apache.spark.api.plugin.{DriverPlugin, ExecutorPlugin, PluginContext, SparkPlugin} +import org.apache.spark.connect.proto +import org.apache.spark.connect.proto.{ + AnalyzeResponse, + Request, + Response, + SparkConnectServiceGrpc +} +import org.apache.spark.internal.Logging +import org.apache.spark.sql.{Dataset, SparkSession} +import org.apache.spark.sql.connect.planner.SparkConnectPlanner +import org.apache.spark.sql.execution.ExtendedMode + +/** + * The SparkConnectService Implementation. + * + * This class implements the service stub from the generated code of GRPC. + * + * @param debug + * delegates debug behavior to the handlers. + */ +@Experimental +@Since("3.3.1") +class SparkConnectService(debug: Boolean) + extends SparkConnectServiceGrpc.SparkConnectServiceImplBase + with Logging { + + /** + * This is the main entry method for Spark Connect and all calls to execute a plan. + * + * The plan execution is delegated to the [[SparkConnectStreamHandler]]. All error handling + * should be directly implemented in the deferred implementation. But this method catches + * generic errors. + * + * @param request + * @param responseObserver + */ + override def executePlan(request: Request, responseObserver: StreamObserver[Response]): Unit = { + try { + new SparkConnectStreamHandler(responseObserver).handle(request) + } catch { + case e: Exception => + log.error("Error executing plan.", e) + responseObserver.onError( + Status.UNKNOWN.withCause(e).withDescription(e.getLocalizedMessage).asRuntimeException()) + } + } + + /** + * Analyze a plan provide metadata and debugging information. + * + * This method is called to generate the explain plan for a SparkConnect plan. In its simplest + * implementation, the plan that is generated by the [[SparkConnectPlanner]] is used to build a + * [[Dataset]] and derive the explain string from the query execution details. + * + * Errors during planning are returned via the [[StreamObserver]] interface. + * + * @param request + * @param responseObserver + */ + override def analyzePlan( + request: Request, + responseObserver: StreamObserver[AnalyzeResponse]): Unit = { + try { + val session = + SparkConnectService.getOrCreateIsolatedSession(request.getUserContext.getUserId).session + + val logicalPlan = request.getPlan.getOpTypeCase match { + case proto.Plan.OpTypeCase.ROOT => + new SparkConnectPlanner(request.getPlan.getRoot, session).transform() + case _ => + responseObserver.onError( + new UnsupportedOperationException( + s"${request.getPlan.getOpTypeCase} not supported for analysis.")) + return + } + val ds = Dataset.ofRows(session, logicalPlan) + val explainString = ds.queryExecution.explainString(ExtendedMode) + + val resp = proto.AnalyzeResponse + .newBuilder() + .setExplainString(explainString) + .setClientId(request.getClientId) + + resp.addAllColumnTypes(ds.schema.fields.map(_.dataType.sql).toSeq.asJava) + resp.addAllColumnNames(ds.schema.fields.map(_.name).toSeq.asJava) + responseObserver.onNext(resp.build()) + responseObserver.onCompleted() + } catch { + case e: Exception => Review Comment: Done -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
