Spark拉取Kafka的流数据，转插入HBase中

2022-06-08 09:08:39

pom.xml文件样例

<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/maven-v4_0_0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <groupId>com.yys.spark</groupId>
    <artifactId>spark</artifactId>
    <version>1.0</version>
    <inceptionYear>2008</inceptionYear>
    <properties>
        <scala.version>2.11.12</scala.version>
        <kafka.version>0.9.0.1</kafka.version>
        <spark.version>2.2.0</spark.version>
        <hadoop.version>2.7.5</hadoop.version>
        <hbase.version>1.4.0</hbase.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>

        <!-- Kafka 依赖-->

        <dependency>
            <groupId>org.apache.kafka</groupId>
            <artifactId>kafka_2.11</artifactId>
            <version>${kafka.version}</version>
        </dependency>

        <!-- Hadoop 依赖-->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <!-- HBase 依赖-->
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-client</artifactId>
            <version>${hbase.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-server</artifactId>
            <version>${hbase.version}</version>
        </dependency>

        <!-- Spark Streaming 依赖-->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>


        <!-- Spark Streaming整合Flume 依赖-->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-flume_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-flume-sink_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-kafka-0-8_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.commons</groupId>
            <artifactId>commons-lang3</artifactId>
            <version>3.5</version>
        </dependency>

        <!-- Spark SQL 依赖-->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>


        <dependency>
            <groupId>com.fasterxml.jackson.module</groupId>
            <artifactId>jackson-module-scala_2.11</artifactId>
            <version>2.6.5</version>
        </dependency>

        <dependency>
            <groupId>net.jpountz.lz4</groupId>
            <artifactId>lz4</artifactId>
            <version>1.3.0</version>
        </dependency>

        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.44</version>
        </dependency>

        <dependency>
            <groupId>org.apache.flume.flume-ng-clients</groupId>
            <artifactId>flume-ng-log4jappender</artifactId>
            <version>1.8.0</version>
        </dependency>

    </dependencies>

    <build>
        <!--
        <sourceDirectory>src/main/scala</sourceDirectory>
        <testSourceDirectory>src/test/scala</testSourceDirectory>
        -->
        <plugins>
            <plugin>
                <groupId>org.scala-tools</groupId>
                <artifactId>maven-scala-plugin</artifactId>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
                <configuration>
                    <scalaVersion>${scala.version}</scalaVersion>
                    <args>
                        <arg>-target:jvm-1.5</arg>
                    </args>
                </configuration>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-eclipse-plugin</artifactId>
                <configuration>
                    <downloadSources>true</downloadSources>
                    <buildcommands>
                        <buildcommand>ch.epfl.lamp.sdt.core.scalabuilder</buildcommand>
                    </buildcommands>
                    <additionalProjectnatures>
                        <projectnature>ch.epfl.lamp.sdt.core.scalanature</projectnature>
                    </additionalProjectnatures>
                    <classpathContainers>
                        <classpathContainer>org.eclipse.jdt.launching.JRE_CONTAINER</classpathContainer>
                        <classpathContainer>ch.epfl.lamp.sdt.launching.SCALA_CONTAINER</classpathContainer>
                    </classpathContainers>
                </configuration>
            </plugin>
        </plugins>
    </build>
    <reporting>
        <plugins>
            <plugin>
                <groupId>org.scala-tools</groupId>
                <artifactId>maven-scala-plugin</artifactId>
                <configuration>
                    <scalaVersion>${scala.version}</scalaVersion>
                </configuration>
            </plugin>
        </plugins>
    </reporting>
</project>

scala代码：


import org.apache.hadoop.hbase.HBaseConfiguration
import org.apache.hadoop.hbase.HColumnDescriptor
import org.apache.hadoop.hbase.HTableDescriptor
import org.apache.hadoop.hbase.client.HBaseAdmin
import org.apache.hadoop.hbase.client.HTable
import org.apache.hadoop.hbase.client.Put
import org.apache.hadoop.hbase.client.Result
import org.apache.hadoop.hbase.client.Scan
import org.apache.hadoop.hbase.util.Bytes
import org.apache.spark._
import org.apache.spark.SparkContext
import org.apache.hadoop.hbase.client.Get
import org.apache.spark.serializer.KryoSerializer
import org.apache.hadoop.hbase.io.ImmutableBytesWritable
import org.apache.hadoop.hbase.mapreduce.TableInputFormat
import org.apache.hadoop.mapred.JobConf
import org.apache.hadoop.hbase.mapred.TableOutputFormat
import org.apache.spark.rdd.RDD.rddToPairRDDFunctions
import org.apache.hadoop.hbase.util.Bytes

//拉取kafka的数据流，转插入hbase中
object Kafka2Hbase {

  def main(args: Array[String]): Unit = {
    val sparkConf = new SparkConf().setMaster("local").setAppName("HBaseTest")
      .set("spark.serializer", "org.apache.spark.serializer.KryoSerializer");
    val sc = new SparkContext(sparkConf)
    //hbase中的表名称
    var table_name = "create_table_at_first"
    val conf = HBaseConfiguration.create()

    //hbase的配置信息可以从/home/hadoop/HBase/hbase/conf/hbase-site.xml得到
    conf.set("hbase.rootdir", "hdfs://master:9000/hbase_db")
    conf.set("hbase.zookeeper.quorum", "master,Slave1,Slave2")
    conf.set("hbase.zookeeper.property.clientPort", "2181")
    conf.set("hbase.master", "60000")
    conf.set(TableInputFormat.INPUT_TABLE, table_name)

    //初始化jobconf，TableOutputFormat必须是org.apache.hadoop.hbase.mapred包下的！
    val jobConf = new JobConf(conf)
    jobConf.setOutputFormat(classOf[TableOutputFormat])
    jobConf.set(TableOutputFormat.OUTPUT_TABLE, table_name)

    val indataRDD = sc.makeRDD(Array("1,jack15,15", "2,mike16,16"))
    val rdd = indataRDD.map(_.split(',')).map { arr => {
      /*一个Put对象就是一行记录，在构造方法中指定主键
       * 所有插入的数据必须用org.apache.hadoop.hbase.util.Bytes.toBytes方法转换
       * Put.add方法接收三个参数：列族，列名，数据
       * myfamily：为列族名
       */
      val put = new Put(Bytes.toBytes(arr(0).toInt))
      put.add(Bytes.toBytes("myfamily"), Bytes.toBytes("name"), Bytes.toBytes(arr(1)))
      put.add(Bytes.toBytes("myfamily"), Bytes.toBytes("age"), Bytes.toBytes(arr(2).toInt))
      //转化成RDD[(ImmutableBytesWritable,Put)]类型才能调用saveAsHadoopDataset
      (new ImmutableBytesWritable, put)
    }
    }

    rdd.saveAsHadoopDataset(jobConf)

    sc.stop()
    //之后在hbase中，可以get 'create_table_at_first','jack15','myfamily'  查询这条数据即可
  }
}

码农公寓

相关文章