dusantism-db commented on code in PR #48794:
URL: https://github.com/apache/spark/pull/48794#discussion_r1848807614
##########
sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingExecutionNode.scala:
##########
@@ -649,3 +662,223 @@ class LoopStatementExec(
body.reset()
}
}
+
+/**
+ * Executable node for ForStatement.
+ * @param query Executable node for the query.
+ * @param variableName Name of variable used for accessing current row during
iteration.
+ * @param body Executable node for the body.
+ * @param label Label set to ForStatement by user or None otherwise.
+ * @param session Spark session that SQL script is executed within.
+ */
+class ForStatementExec(
+ query: SingleStatementExec,
+ variableName: Option[String],
+ body: CompoundBodyExec,
+ val label: Option[String],
+ session: SparkSession) extends NonLeafStatementExec {
+
+ private object ForState extends Enumeration {
+ val VariableAssignment, Body, VariableCleanup = Value
+ }
+ private var state = ForState.VariableAssignment
+ private var currRow = 0
+ private var areVariablesDeclared = false
+
+ // map of all variables created internally by the for statement
+ // (variableName -> variableExpression)
+ private var variablesMap: Map[String, Expression] = Map()
+
+ // compound body used for dropping variables while in
ForState.VariableAssignment
+ private var dropVariablesExec: CompoundBodyExec = null
+
+ private var queryResult: Array[Row] = null
+ private var isResultCacheValid = false
+ private def cachedQueryResult(): Array[Row] = {
+ if (!isResultCacheValid) {
+ queryResult = query.buildDataFrame(session).collect()
+ isResultCacheValid = true
+ }
+ queryResult
+ }
+
+ /**
+ * For can be interrupted by LeaveStatementExec
+ */
+ private var interrupted: Boolean = false
+
+ private lazy val treeIterator: Iterator[CompoundStatementExec] =
+ new Iterator[CompoundStatementExec] {
+
+ override def hasNext: Boolean = {
+ val resultSize = cachedQueryResult().length
+ (state == ForState.VariableCleanup &&
dropVariablesExec.getTreeIterator.hasNext) ||
+ (!interrupted && resultSize > 0 && currRow < resultSize)
+ }
+
+ override def next(): CompoundStatementExec = state match {
+
+ case ForState.VariableAssignment =>
+ variablesMap =
createVariablesMapFromRow(cachedQueryResult()(currRow))
Review Comment:
We need to create it every time because the map is different for every row
in the result set. You can see we call it on the `currRow`.
--
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]
