Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/21028#discussion_r186052495
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala
---
@@ -378,6 +408,135 @@ case class ArrayContains(left: Expression, right:
Expression)
override def prettyName: String = "array_contains"
}
+/**
+ * Checks if the two arrays contain at least one common element.
+ */
+// scalastyle:off line.size.limit
+@ExpressionDescription(
+ usage = "_FUNC_(a1, a2) - Returns true if a1 contains at least an
element present also in a2. If the arrays have no common element and either of
them contains a null element null is returned, false otherwise.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(array(1, 2, 3), array(3, 4, 5));
+ true
+ """, since = "2.4.0")
+// scalastyle:off line.size.limit
+case class ArraysOverlap(left: Expression, right: Expression)
+ extends BinaryArrayExpressionWithImplicitCast {
+
+ override def dataType: DataType = BooleanType
+
+ override def nullable: Boolean = {
+ left.nullable || right.nullable ||
left.dataType.asInstanceOf[ArrayType].containsNull ||
+ right.dataType.asInstanceOf[ArrayType].containsNull
+ }
+
+ override def nullSafeEval(a1: Any, a2: Any): Any = {
+ var hasNull = false
+ val arr1 = a1.asInstanceOf[ArrayData]
+ val arr2 = a2.asInstanceOf[ArrayData]
+ if (arr1.numElements() > 0) {
+ val set2 = new mutable.HashSet[Any]
+ arr2.foreach(elementType, (_, v) =>
+ if (v == null) {
+ hasNull = true
+ } else {
+ set2 += v
+ })
+ arr1.foreach(elementType, (_, v1) =>
+ if (v1 == null) {
+ hasNull = true
+ } else if (set2.contains(v1)) {
+ return true
+ }
+ )
+ } else if (containsNull(arr2, right.dataType.asInstanceOf[ArrayType]))
{
+ hasNull = true
+ }
+ if (hasNull) {
+ null
+ } else {
+ false
+ }
+ }
+
+ def containsNull(arr: ArrayData, dt: ArrayType): Boolean = {
+ if (dt.containsNull) {
+ arr.foreach(elementType, (_, v) =>
+ if (v == null) {
+ return true
+ }
+ )
+ }
+ false
+ }
+
+ override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
+ nullSafeCodeGen(ctx, ev, (a1, a2) => {
+ val i1 = ctx.freshName("i")
+ val i2 = ctx.freshName("i")
+ val getValue1 = CodeGenerator.getValue(a1, elementType, i1)
+ val getValue2 = CodeGenerator.getValue(a2, elementType, i2)
+ val leftEmptyCode = if
(right.dataType.asInstanceOf[ArrayType].containsNull) {
+ s"""
+ |else {
+ | for (int $i2 = 0; $i2 < $a2.numElements(); $i2 ++) {
+ | if ($a2.isNullAt($i2)) {
+ | ${ev.isNull} = true;
+ | break;
+ | }
+ | }
+ |}
+ """.stripMargin
+ } else {
+ ""
+ }
+ val javaElementClass = CodeGenerator.boxedType(elementType)
+ val javaSet = classOf[java.util.HashSet[_]].getName
+ val set2 = ctx.freshName("set")
+ s"""
+ |if ($a1.numElements() > 0) {
+ | $javaSet<$javaElementClass> $set2 = new
$javaSet<$javaElementClass>();
+ | for (int $i2 = 0; $i2 < $a2.numElements(); $i2 ++) {
+ |
${nullSafeElementCodegen(right.dataType.asInstanceOf[ArrayType], a2, i2,
+ s"$set2.add($getValue2);", s"${ev.isNull} = true;")}
+ | }
+ | for (int $i1 = 0; $i1 < $a1.numElements(); $i1 ++) {
+ |
${nullSafeElementCodegen(left.dataType.asInstanceOf[ArrayType], a1, i1,
--- End diff --
ditto
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
