spark sql中进行sechema合并

val sqlContext = new org.apache.spark.sql.SQLContext(sc)

// sqlContext from the previous example is used in this example.
// This is used to implicitly convert an RDD to a DataFrame.
import sqlContext.implicits._

// Create a simple DataFrame, stored into a partition directory
val df1 = sparkContext.makeRDD(1 to 5).map(i => (i, i * 2)).toDF("single", "double")
df1.saveAsParquetFile("data/test_table/key=1")

// Create another DataFrame in a new partition directory,
// adding a new column and dropping an existing column
val df2 = sparkContext.makeRDD(6 to 10).map(i => (i, i * 3)).toDF("single", "triple")
df2.saveAsParquetFile("data/test_table/key=2")

// Read the partitioned table
val df3 = sqlContext.parquetFile("data/test_table")
df3.printSchema()

// The final schema consists of all 3 columns in the Parquet files together
// with the partiioning column appeared in the partition directory paths.
// root
// |-- single: int (nullable = true)
// |-- double: int (nullable = true)
// |-- triple: int (nullable = true)
// |-- key : int (nullable = true)

single double triple key
3      6      null   1  
4      8      null   1  
5      10     null   1  
1      2      null   1  
2      4      null   1  
8      null   24     2  
9      null   27     2  
10     null   30     2  
6      null   18     2  
7      null   21     2