[spark] branch master updated: [SPARK-39190][SQL] Provide query context for decimal precision overflow error when WSCG is off

[gengliang]

This is an automated email from the ASF dual-hosted git repository.

gengliang 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 17b85ff9756 [SPARK-39190][SQL] Provide query context for decimal 
precision overflow error when WSCG is off
17b85ff9756 is described below

commit 17b85ff97569a43d7fd33863d17bfdaf62d539e0
Author: Gengliang Wang <gengli...@apache.org>
AuthorDate: Mon May 16 17:44:53 2022 +0800

    [SPARK-39190][SQL] Provide query context for decimal precision overflow 
error when WSCG is off
    
    ### What changes were proposed in this pull request?
    
    Similar to https://github.com/apache/spark/pull/36525, this PR provides 
query context for decimal precision overflow error when WSCG is off
    
    ### Why are the changes needed?
    
    Enhance the runtime error query context of checking decimal overflow. After 
changes, it works when the whole stage codegen is not available.
    
    ### Does this PR introduce _any_ user-facing change?
    
    NO
    
    ### How was this patch tested?
    
    UT
    
    Closes #36557 from gengliangwang/decimalContextWSCG.
    
    Authored-by: Gengliang Wang <gengli...@apache.org>
    Signed-off-by: Gengliang Wang <gengli...@apache.org>
---
 .../sql/catalyst/expressions/decimalExpressions.scala    | 12 +++++++++---
 .../test/scala/org/apache/spark/sql/SQLQuerySuite.scala  | 16 ++++++++++++++++
 2 files changed, 25 insertions(+), 3 deletions(-)

diff --git 
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/decimalExpressions.scala
 
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/decimalExpressions.scala
index 4a4b8e0fc0d..2cdd784ea4d 100644
--- 
a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/decimalExpressions.scala
+++ 
b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/decimalExpressions.scala
@@ -128,7 +128,7 @@ case class PromotePrecision(child: Expression) extends 
UnaryExpression {
 case class CheckOverflow(
     child: Expression,
     dataType: DecimalType,
-    nullOnOverflow: Boolean) extends UnaryExpression {
+    nullOnOverflow: Boolean) extends UnaryExpression with SupportQueryContext {
 
   override def nullable: Boolean = true
 
@@ -138,11 +138,11 @@ case class CheckOverflow(
       dataType.scale,
       Decimal.ROUND_HALF_UP,
       nullOnOverflow,
-      origin.context)
+      queryContext)
 
   override protected def doGenCode(ctx: CodegenContext, ev: ExprCode): 
ExprCode = {
     val errorContextCode = if (nullOnOverflow) {
-      ctx.addReferenceObj("errCtx", origin.context)
+      ctx.addReferenceObj("errCtx", queryContext)
     } else {
       "\"\""
     }
@@ -163,6 +163,12 @@ case class CheckOverflow(
 
   override protected def withNewChildInternal(newChild: Expression): 
CheckOverflow =
     copy(child = newChild)
+
+  override def initQueryContext(): String = if (nullOnOverflow) {
+    ""
+  } else {
+    origin.context
+  }
 }
 
 // A variant `CheckOverflow`, which treats null as overflow. This is necessary 
in `Sum`.
diff --git a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala 
b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala
index 0355bd90d04..07ec4290250 100644
--- a/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala
+++ b/sql/core/src/test/scala/org/apache/spark/sql/SQLQuerySuite.scala
@@ -4376,6 +4376,22 @@ class SQLQuerySuite extends QueryTest with 
SharedSparkSession with AdaptiveSpark
     }
   }
 
+  test("SPARK-39190: Query context of decimal overflow error should be 
serialized to executors" +
+    " when WSCG is off") {
+    withSQLConf(SQLConf.WHOLESTAGE_CODEGEN_ENABLED.key -> "false",
+      SQLConf.ANSI_ENABLED.key -> "true") {
+      withTable("t") {
+        sql("create table t(d decimal(38, 0)) using parquet")
+        sql("insert into t values (2e37BD)")
+        val query = "select d / 0.1 from t"
+        val msg = intercept[SparkException] {
+          sql(query).collect()
+        }.getMessage
+        assert(msg.contains(query))
+      }
+    }
+  }
+
   test("SPARK-38589: try_avg should return null if overflow happens before 
merging") {
     val yearMonthDf = Seq(Int.MaxValue, Int.MaxValue, 2)
       .map(Period.ofMonths)


---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org