[Spark应用]-- spark sql版本的单词统计代码

见下面代码实现

import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.sql.SQLContext
import org.apache.spark.sql.Row
import org.apache.spark.sql.types.DataTypes
import org.apache.spark.sql.types.StructType
import org.apache.spark.sql.types.StringType
import org.apache.spark.sql.types.StructField
/**
 * scala sql版本的单词统计
 */
object WordCount {
  def main(args:Array[String]):Unit={
    //1\获取context
    val sc=new SparkContext(new SparkConf().setAppName("word").setMaster("local[1]"))
    //2\获取sqlContext
    val sqlContext=new SQLContext(sc)
    //3\加载RDD
    val lines=sc.textFile("dataframeword.txt")
    //4\转换rows
    val rows=lines.map { x => Row(x) }
    //5\创建structField
    val field=Array(DataTypes.createStructField("name", DataTypes.StringType, true))
    //6\创建structType
    val structType=DataTypes.createStructType(field)
    //等价于一句话：  val structTy=StructType(Array(StructField("name", StringType, true)))
    //7\创建dataframe
    val df=sqlContext.createDataFrame(rows, structType)
    //8\注册表
    df.registerTempTable("t_word")
    //9\注册函数
    sqlContext.udf.register("str", (name:String)=>1)
    //10sql语句查询返回结果
    sqlContext.sql("select name,str(name) from t_word ").groupBy(df.col("name")).count().show
    //关闭资源
    sc.stop()
  }
}

参考：https://rklicksolutions.wordpress.com/2016/03/03/tutorial-spark-1-6-sql-and-dataframe-operations/