You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by ma...@apache.org on 2024/09/08 12:07:00 UTC
(spark) branch master updated: [SPARK-48376][SQL][FOLLOWUP] Add ITERATE statement fixes
This is an automated email from the ASF dual-hosted git repository.
maxgekk pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new c159033ee146 [SPARK-48376][SQL][FOLLOWUP] Add ITERATE statement fixes
c159033ee146 is described below
commit c159033ee146d000e8cd13322e9449abc78d84fb
Author: David Milicevic <da...@databricks.com>
AuthorDate: Sun Sep 8 14:06:46 2024 +0200
[SPARK-48376][SQL][FOLLOWUP] Add ITERATE statement fixes
### What changes were proposed in this pull request?
Previous [pull request](https://github.com/apache/spark/pull/47973) introduced new logic for `LEAVE` and `ITERATE` statements, but I missed to introduce minor part of `ITERATE` statement handling.
While `ITERATE` statement is not allowed for compounds (i.e. user cannot use `LEAVE <label>` where label belongs to compound) it's still possible to use `ITERATE` statement within the compound (i.e. when using label of the surrounding `WHILE` loop for example). In such cases, it's required to drop variables defined in the compound (the same way as for `ITERATE` statement).
We don't yet have execution logic (I will work on POC and design doc during the next week), but this is setting up stuff now, so we don't miss anything in future.
### Why are the changes needed?
Changes are minor, they improve consistency among test suites for SQL scripting.
### Does this PR introduce _any_ user-facing change?
No.
### How was this patch tested?
Added small test, but not completely related to this change. Since we don't have execution logic yet, it's hard to test. I will add more tests together with the execution logic.
### Was this patch authored or co-authored using generative AI tooling?
No.
Closes #48022 from davidm-db/missing_logic_for_leave_statement.
Authored-by: David Milicevic <da...@databricks.com>
Signed-off-by: Max Gekk <ma...@gmail.com>
---
.../sql/scripting/SqlScriptingExecutionNode.scala | 26 ++++++++++++++++-
.../scripting/SqlScriptingInterpreterSuite.scala | 34 ++++++++++++++++++++++
2 files changed, 59 insertions(+), 1 deletion(-)
diff --git a/sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingExecutionNode.scala b/sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingExecutionNode.scala
index c2e6abf184b5..284ccc5d5bfe 100644
--- a/sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingExecutionNode.scala
+++ b/sql/core/src/main/scala/org/apache/spark/sql/scripting/SqlScriptingExecutionNode.scala
@@ -176,6 +176,10 @@ abstract class CompoundNestedStatementIteratorExec(
handleLeaveStatement(leaveStatement)
curr = None
leaveStatement
+ case Some(iterateStatement: IterateStatementExec) =>
+ handleIterateStatement(iterateStatement)
+ curr = None
+ iterateStatement
case Some(statement: LeafStatementExec) =>
curr = if (localIterator.hasNext) Some(localIterator.next()) else None
statement
@@ -185,6 +189,9 @@ abstract class CompoundNestedStatementIteratorExec(
case leaveStatement: LeaveStatementExec =>
handleLeaveStatement(leaveStatement)
leaveStatement
+ case iterateStatement: IterateStatementExec =>
+ handleIterateStatement(iterateStatement)
+ iterateStatement
case other => other
}
} else {
@@ -206,18 +213,35 @@ abstract class CompoundNestedStatementIteratorExec(
stopIteration = false
}
- /** Actions to do when LEAVE statement is encountered to stop the execution of this compound. */
+ /** Actions to do when LEAVE statement is encountered, to stop the execution of this compound. */
private def handleLeaveStatement(leaveStatement: LeaveStatementExec): Unit = {
if (!leaveStatement.hasBeenMatched) {
// Stop the iteration.
stopIteration = true
// TODO: Variable cleanup (once we add SQL script execution logic).
+ // TODO: Add interpreter tests as well.
// Check if label has been matched.
leaveStatement.hasBeenMatched = label.isDefined && label.get.equals(leaveStatement.label)
}
}
+
+ /**
+ * Actions to do when ITERATE statement is encountered, to stop the execution of this compound.
+ */
+ private def handleIterateStatement(iterateStatement: IterateStatementExec): Unit = {
+ if (!iterateStatement.hasBeenMatched) {
+ // Stop the iteration.
+ stopIteration = true
+
+ // TODO: Variable cleanup (once we add SQL script execution logic).
+ // TODO: Add interpreter tests as well.
+
+ // No need to check if label has been matched, since ITERATE statement is already
+ // not allowed in CompoundBody.
+ }
+ }
}
/**
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/scripting/SqlScriptingInterpreterSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/scripting/SqlScriptingInterpreterSuite.scala
index 6d836884c5d5..4b47529591c0 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/scripting/SqlScriptingInterpreterSuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/scripting/SqlScriptingInterpreterSuite.scala
@@ -678,4 +678,38 @@ class SqlScriptingInterpreterSuite extends QueryTest with SharedSparkSession {
)
verifySqlScriptResult(sqlScriptText, expected)
}
+
+ test("nested compounds in loop - leave in inner compound") {
+ val sqlScriptText =
+ """
+ |BEGIN
+ | DECLARE x INT;
+ | SET x = 0;
+ | lbl: WHILE x < 2 DO
+ | SET x = x + 1;
+ | BEGIN
+ | SELECT 1;
+ | lbl2: BEGIN
+ | SELECT 2;
+ | LEAVE lbl2;
+ | SELECT 3;
+ | END;
+ | END;
+ | END WHILE;
+ | SELECT x;
+ |END""".stripMargin
+ val expected = Seq(
+ Seq.empty[Row], // declare
+ Seq.empty[Row], // set x = 0
+ Seq.empty[Row], // set x = 1
+ Seq(Row(1)), // select 1
+ Seq(Row(2)), // select 2
+ Seq.empty[Row], // set x = 2
+ Seq(Row(1)), // select 1
+ Seq(Row(2)), // select 2
+ Seq(Row(2)), // select x
+ Seq.empty[Row] // drop
+ )
+ verifySqlScriptResult(sqlScriptText, expected)
+ }
}
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org