[SPARK-46388][SQL] HiveAnalysis misses the pattern guard of `query.re…

…solved` ### What changes were proposed in this pull request? This PR adds `query.resolved` as a pattern guard when HiveAnalysis converts InsertIntoStatement to InsertIntoHiveTable. ### Why are the changes needed? Due to https://github.com/apache/spark/pull/41262/files#diff-ed19f376a63eba52eea59ca71f3355d4495fad4fad4db9a3324aade0d4986a47R1080, the `table` field is resolved regardless of the query field. Before, it never got a chance to be resolved as `HiveTableRelation` and then match any rule of HiveAnalysis. But now, it gets the chance always and results in a spark-kernel bug - `Invalid call to toAttribute on unresolved object.` ``` insert into t2 select cast(a as short) from t where b=1; Invalid call to toAttribute on unresolved object ``` ### Does this PR introduce _any_ user-facing change? no, bugfix for 3.5 and later ### How was this patch tested? added new test ### Was this patch authored or co-authored using generative AI tooling? no Closes #44326 from yaooqinn/SPARK-46388. Authored-by: Kent Yao <[email protected]> Signed-off-by: Kent Yao <[email protected]>
apache · Dec 13, 2023 · ccc436d · ccc436d
1 parent b3398e6
commit ccc436d
Show file tree

Hide file tree

Showing 2 changed files with 27 additions and 1 deletion.
diff --git a/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveStrategies.scala b/sql/hive/src/main/scala/org/apache/spark/sql/hive/HiveStrategies.scala
@@ -163,7 +163,7 @@ object HiveAnalysis extends Rule[LogicalPlan] {
   override def apply(plan: LogicalPlan): LogicalPlan = plan resolveOperators {
     case InsertIntoStatement(
         r: HiveTableRelation, partSpec, _, query, overwrite, ifPartitionNotExists, _)
-        if DDLUtils.isHiveTable(r.tableMeta) =>
+        if DDLUtils.isHiveTable(r.tableMeta) && query.resolved =>
       InsertIntoHiveTable(r.tableMeta, partSpec, query, overwrite,
         ifPartitionNotExists, query.output.map(_.name))
 

diff --git a/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala b/sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/SQLQuerySuite.scala
@@ -2669,6 +2669,32 @@ abstract class SQLQuerySuiteBase extends QueryTest with SQLTestUtils with TestHi
       checkAnswer(df, Seq.empty[Row])
     }
   }
+
+  test("SPARK-46388: HiveAnalysis convert InsertIntoStatement to InsertIntoHiveTable " +
+    "iff child resolved") {
+    withTable("t") {
+      sql("CREATE TABLE t (a STRING)")
+      checkError(
+        exception = intercept[AnalysisException](sql("INSERT INTO t SELECT a*2 FROM t where b=1")),
+        errorClass = "UNRESOLVED_COLUMN.WITH_SUGGESTION",
+        sqlState = None,
+        parameters = Map("objectName" -> "`b`", "proposal" -> "`a`"),
+        context = ExpectedContext(
+          fragment = "b",
+          start = 38,
+          stop = 38) )
+      checkError(
+        exception = intercept[AnalysisException](
+          sql("INSERT INTO t SELECT cast(a as short) FROM t where b=1")),
+        errorClass = "UNRESOLVED_COLUMN.WITH_SUGGESTION",
+        sqlState = None,
+        parameters = Map("objectName" -> "`b`", "proposal" -> "`a`"),
+        context = ExpectedContext(
+          fragment = "b",
+          start = 51,
+          stop = 51))
+    }
+  }
 }
 
 @SlowHiveTest