使用 monotonically_increasing_id & row_numer 在两个数据集中添加唯一的id值&使用 id 列以及两个数据集中的必需列，最后从结果数据集中删除id。
请检查下面的代码。

scala> case class schema1(a: Double, b: Double)
defined class schema1

scala> case class schema2(c: Double, d: Double, e: Double, f: Double)
defined class schema2

scala> import org.apache.spark.sql.expressions._
import org.apache.spark.sql.expressions._

scala> val sa = Seq(schema1(11,12),schema1(22,23)).toDF.withColumn("id",monotonically_increasing_id).withColumn("id",row_number().over(Window.orderBy("id")))
sa: org.apache.spark.sql.DataFrame = [a: double, b: double ... 1 more field]

scala> val sb = Seq(schema2(22,23,24,25),schema2(32,33,34,35),schema2(132,133,134,135)).toDF.withColumn("id",monotonically_increasing_id).withColumn("id",row_number().over(Window.orderBy("id")))
sb: org.apache.spark.sql.DataFrame = [c: double, d: double ... 3 more fields]

scala> sa.show(false)
+----+----+---+
|a   |b   |id |
+----+----+---+
|11.0|12.0|0  |
|22.0|23.0|1  |
+----+----+---+

scala> sb.show(false)
+-----+-----+-----+-----+---+
|c    |d    |e    |f    |id |
+-----+-----+-----+-----+---+
|22.0 |23.0 |24.0 |25.0 |0  |
|32.0 |33.0 |34.0 |35.0 |1  |
|132.0|133.0|134.0|135.0|2  |
+-----+-----+-----+-----+---+

scala> sb.select("c","id").join(sa.select("b","id"),Seq("id"),"full").drop("id").show(false)
+-----+----+
|c    |b   |
+-----+----+
|22.0 |12.0|
|32.0 |23.0|
|132.0|null|
+-----+----+