sparksql 简单使用

标记一个博客怕找不到了:http://www.cnblogs.com/shishanyuan/p/4723713.html

第一种:
通过case class

package cn.lijie

import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.sql.SQLContext


/**
  * Created by jie on 2017/7/31.
  */
object SparkSql01 {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("sparksql").setMaster("local[2]")
    val sc = new SparkContext(conf)
    val sqlContext = new SQLContext(sc)
    System.setProperty("user.name","bigdata")
    val rdd = sc.textFile("C:\\Users\\jie\\Desktop\\game.txt").map{ x =>{
      val split = x.split(",")
      Game(split(0).toLong,split(1),split(2).toInt)
    }}
    import sqlContext.implicits._
    val df = rdd.toDF
    df.registerTempTable("t_game")
    sqlContext.sql("select * from t_game where id <= 2").write.json("C:\\Users\\jie\\Desktop\\game.json")

val newDf = sqlContext.load("C:\\Users\\jie\\Desktop\\game.json","json")
    newDf.show
  }
}

case class Game(id:Long,name:String,level:Int)

第二种:
通过StructType

package cn.lijie

import org.apache.spark.sql.{Row, SQLContext}
import org.apache.spark.sql.types._
import org.apache.spark.{SparkConf, SparkContext}


/**
  * Created by jie on 2017/7/31.
  */
object SparkSql01 {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("sparksql").setMaster("local[2]")
    System.setProperty("user.name","bigdata")
    val sc = new SparkContext(conf)
    val sqlContext = new SQLContext(sc)
    val rdd = sc.textFile("C:\\Users\\jie\\Desktop\\game.txt")
    val schema = StructType(
      List(
        StructField("id", LongType, true),
        StructField("name", StringType, true),
        StructField("age", IntegerType, true)
      )
    )
    val rowRDD = rdd.map(x => {
      Row(x(0).toLong, x(1), x(2).toInt)
    })

    val df = sqlContext.createDataFrame(rowRDD, schema)
    df.registerTempTable("t_game")
    sqlContext.sql("select * from t_game where id <= 2").write.json("C:\\Users\\jie\\Desktop\\game.json")
    val newDf = sqlContext.load("C:\\Users\\jie\\Desktop\\game.json","json")
    newDf.show
  }
}

case class Game(id: Long, name: String, level: Int)

pom


<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0modelVersion>

    <groupId>spark-sparksqlgroupId>
    <artifactId>spark-sqlartifactId>
    <version>1.0-SNAPSHOTversion>


    <properties>
        <maven.compiler.source>1.7maven.compiler.source>
        <maven.compiler.target>1.7maven.compiler.target>
        <encoding>UTF-8encoding>
        <scala.version>2.10.6scala.version>
        <spark.version>1.6.1spark.version>
        <hadoop.version>2.6.4hadoop.version>
    properties>

    <dependencies>
        <dependency>
            <groupId>org.scala-langgroupId>
            <artifactId>scala-libraryartifactId>
            <version>${scala.version}version>
        dependency>

        <dependency>
            <groupId>org.apache.sparkgroupId>
            <artifactId>spark-core_2.10artifactId>
            <version>${spark.version}version>
        dependency>

        <dependency>
            <groupId>org.apache.sparkgroupId>
            <artifactId>spark-sql_2.10artifactId>
            <version>${spark.version}version>
        dependency>

        <dependency>
            <groupId>org.apache.hadoopgroupId>
            <artifactId>hadoop-clientartifactId>
            <version>${hadoop.version}version>
        dependency>
    dependencies>

    <build>
        <sourceDirectory>src/main/scalasourceDirectory>
        <testSourceDirectory>src/test/scalatestSourceDirectory>
        <plugins>
            <plugin>
                <groupId>net.alchim31.mavengroupId>
                <artifactId>scala-maven-pluginartifactId>
                <version>3.2.2version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compilegoal>
                            <goal>testCompilegoal>
                        goals>
                        <configuration>
                            <args>
                                <arg>-make:transitivearg>
                                <arg>-dependencyfilearg>
                                <arg>${project.build.directory}/.scala_dependenciesarg>
                            args>
                        configuration>
                    execution>
                executions>
            plugin>

            <plugin>
                <groupId>org.apache.maven.pluginsgroupId>
                <artifactId>maven-shade-pluginartifactId>
                <version>2.4.3version>
                <executions>
                    <execution>
                        <phase>packagephase>
                        <goals>
                            <goal>shadegoal>
                        goals>
                        <configuration>
                            <filters>
                                <filter>
                                    <artifact>*:*artifact>
                                    <excludes>
                                        <exclude>META-INF/*.SFexclude>
                                        <exclude>META-INF/*.DSAexclude>
                                        <exclude>META-INF/*.RSAexclude>
                                    excludes>
                                filter>
                            filters>
                            <transformers>
                                <transformer
                                        implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
                                    <mainClass>cn.lijie.SparkSql01mainClass>
                                transformer>
                            transformers>
                        configuration>
                    execution>
                executions>
            plugin>
        plugins>
    build>
project>

你可能感兴趣的:(spark)