spark之路第十课——spark SQL编程

val sc: SparkContext // An existing SparkContext.
val sqlContext = new org.apache.spark.sql.SQLContext(sc)
// createSchemaRDD is used to implicitly convert an RDD to a SchemaRDD.
import sqlContext.createSchemaRDD

// sc is an existing SparkContext.
val sqlContext = new org.apache.spark.sql.SQLContext(sc)
// createSchemaRDD is used to implicitly convert an RDD to a SchemaRDD.
import sqlContext.createSchemaRDD
// Define the schema using a case class.
// Note: Case classes in Scala 2.10 can support only up to 22 fields. To work around this limit,
// you can use custom classes that implement the Product interface.
case class Person(name: String, age: Int)
// Create an RDD of Person objects and register it as a table.
val people = sc.textFile("examples/src/main/resources/people.txt").map(_.split(",")).map(p => Person(p(0), p(1).trim.toInt))
people.registerTempTable("people")
// SQL statements can be run by using the sql methods provided by sqlContext.
val teenagers = sqlContext.sql("SELECT name FROM people WHERE age >= 13 AND age <= 19")
// The results of SQL queries are SchemaRDDs and support all the normal RDD operations.
// The columns of a row in the result can be accessed by ordinal.
teenagers.map(t => "Name: " + t(0)).collect().foreach(println)

// sc is an existing SparkContext.
val sqlContext = new org.apache.spark.sql.SQLContext(sc)
// Create an RDD
val people = sc.textFile("examples/src/main/resources/people.txt")
// The schema is encoded in a string
val schemaString = "name age"
// Import Spark SQL data types and Row.
import org.apache.spark.sql.
// Generate the schema based on the string of schema
val schema =
  StructType(
    schemaString.split(" ").map(fieldName => StructField(fieldName, StringType, true)))
// Convert records of the RDD (people) to Rows.
val rowRDD = people.map(.split(",")).map(p => Row(p(0), p(1).trim))
// Apply the schema to the RDD.
val peopleSchemaRDD = sqlContext.applySchema(rowRDD, schema)
// Register the SchemaRDD as a table.
peopleSchemaRDD.registerTempTable("people")
// SQL statements can be run by using the sql methods provided by sqlContext.
val results = sqlContext.sql("SELECT name FROM people")
// The results of SQL queries are SchemaRDDs and support all the normal RDD operations.
// The columns of a row in the result can be accessed by ordinal.
results.map(t => "Name: " + t(0)).collect().foreach(println)

// sqlContext from the previous example is used in this example.
// createSchemaRDD is used to implicitly convert an RDD to a SchemaRDD.
import sqlContext.createSchemaRDD
val people: RDD[Person] = ... // An RDD of case class objects, from the previous example.
// The RDD is implicitly converted to a SchemaRDD by createSchemaRDD, allowing it to be stored using Parquet.
people.saveAsParquetFile("people.parquet")
// Read in the parquet file created above.  Parquet files are self-describing so the schema is preserved.
// The result of loading a Parquet file is also a SchemaRDD.
val parquetFile = sqlContext.parquetFile("people.parquet")
//Parquet files can also be registered as tables and then used in SQL statements.
parquetFile.registerTempTable("parquetFile")
val teenagers = sqlContext.sql("SELECT name FROM parquetFile WHERE age >= 13 AND age <= 19")
teenagers.map(t => "Name: " + t(0)).collect().foreach(println)