Spark SQL的简单java api应用

1、创建IDEA的Maven工程

2、引入依赖

    

<?xml version="1.0" encoding="UTF-8"?>
<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>4.0.0</modelVersion>

    <groupId>com.motoon</groupId>
    <artifactId>SparkSql_Demo</artifactId>
    <version>1.0</version>

    <properties>
        <maven.compiler.source>1.7</maven.compiler.source>
        <maven.compiler.target>1.7</maven.compiler.target>
        <encoding>UTF-8</encoding>
        <scala.version>2.10.6</scala.version>
        <scala.compat.version>2.10</scala.compat.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.10</artifactId>
            <version>1.5.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.10</artifactId>
            <version>1.5.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.10</artifactId>
            <version>1.5.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.6.2</version>
        </dependency>

        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.39</version>
        </dependency>
    </dependencies>

    <build>
        <sourceDirectory>src/main/scala</sourceDirectory>
        <testSourceDirectory>src/test/scala</testSourceDirectory>
        <plugins>
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.2.0</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                        <configuration>
                            <args>
                                <arg>-make:transitive</arg>
                                <arg>-dependencyfile</arg>
                                <arg>${project.build.directory}/.scala_dependencies</arg>
                            </args>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-surefire-plugin</artifactId>
                <version>2.18.1</version>
                <configuration>
                    <useFile>false</useFile>
                    <disableXmlReport>true</disableXmlReport>
                    <includes>
                        <include>**/*Test.*</include>
                        <include>**/*Suite.*</include>
                    </includes>
                </configuration>
            </plugin>

            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>2.3</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <filters>
                                <filter>
                                    <artifact>*:*</artifact>
                                    <excludes>
                                        <exclude>META-INF/*.SF</exclude>
                                        <exclude>META-INF/*.DSA</exclude>
                                        <exclude>META-INF/*.RSA</exclude>
                                    </excludes>
                                </filter>
                            </filters>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>


</project>

3、编写测试类

     

package com.motoon.sparksql


import org.apache.spark.sql.types.{DataTypes, StructType}
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.sql.{Row, SQLContext, functions}

object TestSparkSql {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("TestSparkSql").setMaster("local");
    val sc = new SparkContext(conf)
    val sqlContext = new SQLContext(sc)
    val linesRDD = sc.textFile("hdfs://192.168.61.138:9000/test/people.txt")
    val rowRDD = linesRDD.map(line => {
      val splits = line.split(" ")
      Row(splits(0).trim.toInt,splits(1).trim,splits(2).trim.toInt)
    })
    val structType = StructType(Array(
      DataTypes.createStructField("id",DataTypes.IntegerType,true),
      DataTypes.createStructField("name",DataTypes.StringType,true),
      DataTypes.createStructField("age",DataTypes.IntegerType,true)
    ))

    val df = sqlContext.createDataFrame(rowRDD,structType)
    df.registerTempTable("people")
    df.show()
    /**
      * 接下来对df中的数据进行查询
      * 第一个查询年龄的最大值,平均值
      * height的总身高
      * */
    sqlContext.sql("select * from people").show()
    sqlContext.sql("select max(age) from people").show()
    sc.stop()
  }
}