cloud-fan commented on code in PR #53530: URL: https://github.com/apache/spark/pull/53530#discussion_r2646502266
########## sql/core/src/main/scala/org/apache/spark/sql/execution/command/v2/OpenCursorExec.scala: ########## @@ -0,0 +1,173 @@ +/* + * 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.execution.command.v2 + +import org.apache.spark.sql.AnalysisException +import org.apache.spark.sql.catalyst.{InternalRow, SqlScriptingContextManager} +import org.apache.spark.sql.catalyst.expressions.{Attribute, Expression} +import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan +import org.apache.spark.sql.execution.datasources.v2.LeafV2CommandExec + +/** + * Physical plan node for opening cursors. + * + * @param cursorName Name of the cursor to open + * @param args Parameter expressions from USING clause (for parameterized cursors) + * @param paramNames Names for each parameter (empty string for positional parameters) + */ +case class OpenCursorExec( + cursorName: String, + args: Seq[Expression] = Seq.empty, + paramNames: Seq[String] = Seq.empty) extends LeafV2CommandExec { + + override protected def run(): Seq[InternalRow] = { + val scriptingContextManager = SqlScriptingContextManager.get() + .getOrElse(throw new AnalysisException( + errorClass = "CURSOR_OUTSIDE_SCRIPT", + messageParameters = Map("cursorName" -> cursorName))) + + val scriptingContext = scriptingContextManager.getContext + .asInstanceOf[org.apache.spark.sql.scripting.SqlScriptingExecutionContext] + + // Parse and normalize cursor name for case sensitivity + val cursorNameParts = parseCursorName(cursorName) + + // Find cursor in scope hierarchy + val cursorDef = scriptingContext.currentFrame.findCursorByNameParts(cursorNameParts) + .getOrElse( + throw new AnalysisException( + errorClass = "CURSOR_NOT_FOUND", + messageParameters = Map("cursorName" -> cursorName))) + + // Validate cursor is not already open + if (cursorDef.isOpen) { + throw new AnalysisException( + errorClass = "CURSOR_ALREADY_OPEN", + messageParameters = Map("cursorName" -> cursorName)) + } + + // Execute the query and collect results + val resultData = if (args.nonEmpty) { + // Parameterized cursor: re-parse query text with bound parameters + val (data, analyzedPlan) = executeParameterizedQuery(cursorDef.queryText, args) + // Update the cursor's query with the analyzed plan so FETCH can access the schema + cursorDef.query = analyzedPlan + data + } else { + // Non-parameterized cursor: execute the analyzed plan directly + val queryExecution = session.sessionState.executePlan(cursorDef.query) + queryExecution.executedPlan.executeCollect() Review Comment: this is very memory intensive. Can we use `df.toLocalIterator`? This is also how we implement FOR loop in scripting. Using iterator means we can only read the record one by one, not going back. Does the CURSOR feature need to go back and read previous rows? -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
