[SPARK-46037][SQL] Correctness fix for Shuffled Hash Join build left without codegen

This is a re-submitting of #43938 to fix a join correctness bug caused by #41398 . Credits go to mcdull-zhang

correctness fix

Yes, the query result will be corrected.

new test

no

Closes #47905 from cloud-fan/join.

Authored-by: Wenchen Fan <wenchen@databricks.com>
Signed-off-by: Wenchen Fan <wenchen@databricks.com>
(cherry picked from commit af5e0a2)
Signed-off-by: Wenchen Fan <wenchen@databricks.com>

Author: cloud-fan

sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashJoin.scala

@@ -138,9 +138,8 @@ trait HashJoin extends JoinCodegenSupport {
     UnsafeProjection.create(streamedBoundKeys)
 
   @transient protected[this] lazy val boundCondition = if (condition.isDefined) {
-    if (joinType == FullOuter && buildSide == BuildLeft) {
-      // Put join left side before right side. This is to be consistent with
-      // `ShuffledHashJoinExec.fullOuterJoin`.
+    if ((joinType == FullOuter || joinType == LeftOuter) && buildSide == BuildLeft) {
+      // Put join left side before right side.
       Predicate.create(condition.get, buildPlan.output ++ streamedPlan.output).eval _
     } else {
       Predicate.create(condition.get, streamedPlan.output ++ buildPlan.output).eval _

sql/core/src/test/scala/org/apache/spark/sql/execution/joins/OuterJoinSuite.scala

@@ -26,10 +26,11 @@ import org.apache.spark.sql.catalyst.plans.logical.{Join, JoinHint}
 import org.apache.spark.sql.execution.{SparkPlan, SparkPlanTest}
 import org.apache.spark.sql.execution.exchange.EnsureRequirements
 import org.apache.spark.sql.internal.SQLConf
-import org.apache.spark.sql.test.SharedSparkSession
+import org.apache.spark.sql.test.{SharedSparkSession, SQLTestData}
 import org.apache.spark.sql.types.{DoubleType, IntegerType, StructType}
 
-class OuterJoinSuite extends SparkPlanTest with SharedSparkSession {
+class OuterJoinSuite extends SparkPlanTest with SharedSparkSession with SQLTestData {
+  setupTestData()
 
   private val EnsureRequirements = new EnsureRequirements()
 
@@ -325,4 +326,21 @@ class OuterJoinSuite extends SparkPlanTest with SharedSparkSession {
       (null, null, 7, 7.0)
     )
   )
+
+  testWithWholeStageCodegenOnAndOff(
+    "SPARK-46037: ShuffledHashJoin build left with left outer join, codegen off") { _ =>
+    def join(hint: String): DataFrame = {
+      sql(
+        s"""
+          |SELECT /*+ $hint */ *
+          |FROM testData t1
+          |LEFT OUTER JOIN
+          |testData2 t2
+          |ON key = a AND concat(value, b) = '12'
+          |""".stripMargin)
+    }
+    val df1 = join("SHUFFLE_HASH(t1)")
+    val df2 = join("SHUFFLE_MERGE(t1)")
+    checkAnswer(df1, identity, df2.collect().toSeq)
+  }
 }