[SPARK-23913][SQL] Add array_intersect function

## What changes were proposed in this pull request?

The PR adds the SQL function `array_intersect`. The behavior of the function is based on Presto's one.

This function returns returns an array of the elements in the intersection of array1 and array2.

Note: The order of elements in the result is not defined.

## How was this patch tested?

Added UTs

Author: Kazuaki Ishizaki <[email protected]>

Closes apache#21102 from kiszk/SPARK-23913.

Author: kiszk

python/pyspark/sql/functions.py

@@ -2033,6 +2033,25 @@ def array_distinct(col):
     return Column(sc._jvm.functions.array_distinct(_to_java_column(col)))
 
 
+@ignore_unicode_prefix
+@since(2.4)
+def array_intersect(col1, col2):
+    """
+    Collection function: returns an array of the elements in the intersection of col1 and col2,
+    without duplicates.
+
+    :param col1: name of column containing array
+    :param col2: name of column containing array
+
+    >>> from pyspark.sql import Row
+    >>> df = spark.createDataFrame([Row(c1=["b", "a", "c"], c2=["c", "d", "a", "f"])])
+    >>> df.select(array_intersect(df.c1, df.c2)).collect()
+    [Row(array_intersect(c1, c2)=[u'a', u'c'])]
+    """
+    sc = SparkContext._active_spark_context
+    return Column(sc._jvm.functions.array_intersect(_to_java_column(col1), _to_java_column(col2)))
+
+
 @ignore_unicode_prefix
 @since(2.4)
 def array_union(col1, col2):

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/FunctionRegistry.scala

@@ -411,6 +411,7 @@ object FunctionRegistry {
     expression[CreateArray]("array"),
     expression[ArrayContains]("array_contains"),
     expression[ArraysOverlap]("arrays_overlap"),
+    expression[ArrayIntersect]("array_intersect"),
     expression[ArrayJoin]("array_join"),
     expression[ArrayPosition]("array_position"),
     expression[ArraySort]("array_sort"),