feat: add support for array_contains expression

native/core/src/execution/datafusion/planner.rs

@@ -113,6 +113,7 @@ use datafusion_expr::{
     AggregateUDF, ScalarUDF, WindowFrame, WindowFrameBound, WindowFrameUnits,
     WindowFunctionDefinition,
 };
+use datafusion_functions_nested::array_has::ArrayHas;
 use datafusion_physical_expr::expressions::{Literal, StatsType};
 use datafusion_physical_expr::window::WindowExpr;
 use datafusion_physical_expr::LexOrdering;
@@ -735,6 +736,20 @@ impl PhysicalPlanner {
                     expr.legacy_negative_index,
                 )))
             }
+            ExprStruct::ArrayContains(expr) => {
+                let src_array_expr =
+                    self.create_expr(expr.left.as_ref().unwrap(), Arc::clone(&input_schema))?;
+                let key_expr =
+                    self.create_expr(expr.right.as_ref().unwrap(), Arc::clone(&input_schema))?;
+                let args = vec![Arc::clone(&src_array_expr), key_expr];
+                let array_has_expr = Arc::new(ScalarFunctionExpr::new(
+                    "array_has",
+                    Arc::new(ScalarUDF::new_from_impl(ArrayHas::new())),
+                    args,
+                    DataType::Boolean,
+                ));
+                Ok(array_has_expr)
+            }
             expr => Err(ExecutionError::GeneralError(format!(
                 "Not implemented: {:?}",
                 expr

native/proto/src/proto/expr.proto

@@ -84,6 +84,7 @@ message Expr {
     GetArrayStructFields get_array_struct_fields = 57;
     BinaryExpr array_append = 58;
     ArrayInsert array_insert = 59;
+    BinaryExpr array_contains = 60;
   }
 }
 

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

@@ -2266,6 +2266,12 @@ object QueryPlanSerde extends Logging with ShimQueryPlanSerde with CometExprShim
             withInfo(expr, "unsupported arguments for GetArrayStructFields", child)
             None
           }
+        case expr if expr.prettyName == "array_contains" =>
+          createBinaryExpr(
+            expr.children(0),
+            expr.children(1),
+            inputs,
+            (builder, binaryExpr) => builder.setArrayContains(binaryExpr))
         case _ if expr.prettyName == "array_append" =>
           createBinaryExpr(
             expr.children(0),

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

@@ -2390,4 +2390,14 @@ class CometExpressionSuite extends CometTestBase with AdaptiveSparkPlanHelper {
       checkSparkAnswer(df.select("arrUnsupportedArgs"))
     }
   }
+
+  test("array_contains") {
+    withTempDir { dir =>
+      val path = new Path(dir.toURI.toString, "test.parquet")
+      makeParquetFileAllTypes(path, dictionaryEnabled = false, n = 10000)
+      spark.read.parquet(path.toString).createOrReplaceTempView("t1");
+      checkSparkAnswerAndOperator(
+        spark.sql("SELECT array_contains(array(_2, _3, _4), _2) FROM t1"))
+    }
+  }
 }