java coalesce_java-Spark：将 DataSet 的两列 coalesce 为一列

以下方法将起作用

import spark.implicits._

val t1 = Seq((1,1),(1,1),(1,3),(2,5),(3,1),(3,2),(3,3))

val t2 = Seq((1,"A"),(2,"B"),(3,"C"),(4,"D"),(5,"E"),(6,"F"),(7,"G"))

val tt1 = sc.parallelize(t1).toDF("id1","id2")

.persist(StorageLevel.MEMORY_AND_DISK)

val tt2 = sc.parallelize(t2).toDF("id", "obj")

.persist(StorageLevel.MEMORY_AND_DISK)

tt1.show()

tt2.show()

tt1.createOrReplaceTempView("table1")

tt2.createOrReplaceTempView("table2")

val output = sqlContext.sql(

"""

|SELECT DISTINCT id, obj

|FROM table1 t1

|JOIN table2 t2 ON(t1.id1 = t2.id) OR (t1.id2 = id)

|ORDER BY id

|""".stripMargin).persist(StorageLevel.MEMORY_AND_DISK)

output.show()