Feat: support array_except function

native/core/src/execution/planner.rs

@@ -69,6 +69,7 @@ use datafusion_functions_nested::array_has::array_has_any_udf;
 use datafusion_functions_nested::concat::ArrayAppend;
 use datafusion_functions_nested::remove::array_remove_all_udf;
 use datafusion_functions_nested::set_ops::array_intersect_udf;
+use datafusion_functions_nested::except::array_except_udf;
 use datafusion_functions_nested::string::array_to_string_udf;
 use datafusion_physical_expr::aggregate::{AggregateExprBuilder, AggregateFunctionExpr};
 
@@ -834,6 +835,22 @@ impl PhysicalPlanner {
                 ));
                 Ok(array_has_any_expr)
             }
+            ExprStruct::ArrayExcept(expr) => {
+                let left_expr =
+                    self.create_expr(expr.left.as_ref().unwrap(), Arc::clone(&input_schema))?;
+                let right_expr =
+                    self.create_expr(expr.right.as_ref().unwrap(), Arc::clone(&input_schema))?;
+                let return_type = left_expr.data_type(&input_schema)?;
+                let args = vec![Arc::clone(&left_expr), right_expr];
+
+                let array_except_expr = Arc::new(ScalarFunctionExpr::new(
+                    "array_except",
+                    array_except_udf(),
+                    args,
+                    return_type,
+                ));
+                Ok(array_except_expr)
+            }
             expr => Err(ExecutionError::GeneralError(format!(
                 "Not implemented: {:?}",
                 expr

native/proto/src/proto/expr.proto

@@ -89,6 +89,7 @@ message Expr {
     BinaryExpr array_intersect = 62;
     ArrayJoin array_join = 63;
     BinaryExpr arrays_overlap = 64;
+    BinaryExpr array_except = 65;
   }
 }
 

spark/src/main/scala/org/apache/comet/serde/QueryPlanSerde.scala

@@ -2444,6 +2444,23 @@ object QueryPlanSerde extends Logging with ShimQueryPlanSerde with CometExprShim
               s"${CometConf.COMET_CAST_ALLOW_INCOMPATIBLE.key}=true")
           None
         }
+      case _ if expr.prettyName == "array_except" =>
+        if (CometConf.COMET_CAST_ALLOW_INCOMPATIBLE.get()) {
+          createBinaryExpr(
+            expr,
+            expr.children(0),
+            expr.children(1),
+            inputs,
+            binding,
+            (builder, binaryExpr) => builder.setArrayExcept(binaryExpr))
+        } else {
+          withInfo(
+            expr,
+            s"array_except is not fully compatible with Spark. " +
+              s"Set ${CometConf.COMET_CAST_ALLOW_INCOMPATIBLE.key}=true " +
+              "to allow it anyway.")
+          None
+        }
       case _ =>
         withInfo(expr, s"${expr.prettyName} is not supported", expr.children: _*)
         None

spark/src/test/scala/org/apache/comet/CometExpressionSuite.scala

@@ -2722,4 +2722,21 @@ class CometExpressionSuite extends CometTestBase with AdaptiveSparkPlanHelper {
     }
   }
 
+  test("array_except") {
+    withSQLConf(CometConf.COMET_CAST_ALLOW_INCOMPATIBLE.key -> "true") {
+      Seq(true, false).foreach { dictionaryEnabled =>
+        withTempDir { dir =>
+          val path = new Path(dir.toURI.toString, "test.parquet")
+          makeParquetFileAllTypes(path, dictionaryEnabled, 10000)
+          spark.read.parquet(path.toString).createOrReplaceTempView("t1")
+
+          checkSparkAnswerAndOperator(
+            sql("SELECT array_except(array(_2, _3, _4), array(_3, _4)) from t1"))
+          checkSparkAnswerAndOperator(sql("SELECT array_except(array(_18), array(_19)) from t1"))
+          checkSparkAnswerAndOperator(spark.sql(
+            "SELECT array_except((CASE WHEN _2 = _3 THEN array(_2, _3, _4) END), array(_4)) FROM t1"))
+        }
+      }
+    }
+  }
 }