spark中filter函数的一个用法

val df1 = sc.parallelize(Seq((1,"abcd"), (2,"defg"), (3, "ghij"),(4,"xyzz"),(5,"lmnop"),(6,"pqrst"),(7,"wxyz"),(8,"lmnoa"),(9,"jklm"))).toDF("c1","c2")
val given_list = List("abcd","defg","ghij")
df1.filter(($"c2").isin(given_list: _*)).show()
//或者
df1.filter(($"c2").isInCollection(given_list)).show()

执行后的情况：

scala> val df1 = sc.parallelize(Seq((1,"abcd"), (2,"defg"), (3, "ghij"),(4,"xyzz"),(5,"lmnop"),(6,"pqrst"),(7,"wxyz"),(8,"lmnoa"),(9,"jklm"))).toDF("c1","c2")
df1: org.apache.spark.sql.DataFrame = [c1: int, c2: string]

scala> val given_list = List("abcd","defg","ghij")
given_list: List[String] = List(abcd, defg, ghij)

scala> df1.filter(($"c2").isin(given_list: _*)).show()
+---+----+                                                                      
| c1|  c2|
+---+----+
|  1|abcd|
|  2|defg|
|  3|ghij|
+---+----+


scala> //或者

scala> df1.filter(($"c2").isInCollection(given_list)).show()
+---+----+
| c1|  c2|
+---+----+
|  1|abcd|
|  2|defg|
|  3|ghij|
+---+----+