Spark 读 Hbase

package com.grady

import org.apache.hadoop.hbase.HBaseConfiguration
import org.apache.hadoop.hbase.client.Result
import org.apache.hadoop.hbase.io.ImmutableBytesWritable
import org.apache.hadoop.hbase.mapreduce.TableInputFormat
import org.apache.hadoop.hbase.util.Bytes
import org.apache.log4j.{Level, Logger}
import org.apache.spark.sql.SparkSession


object SparkReadHbase {

  def main(args: Array[String]): Unit = {
    Logger.getLogger("org.apache.spark").setLevel(Level.WARN)

//    val sparkConf = new SparkConf().setAppName("SparkReadHbase")
//    val sc = new SparkContext(sparkConf)
    // 也可以通过sparkSession 来后去SparkContext
    val spark = SparkSession.builder().appName("SparkReadHbase").getOrCreate()
    val sc = spark.sparkContext

    val tablename = "jiang:student"

    val hbaseConf = HBaseConfiguration.create()
    hbaseConf.set("hbase.zookeeper.quorum","10.82.232.64")
    hbaseConf.set("hbase.zookeeper.property.clientPort", "2181")
    hbaseConf.set("zookeeper.znode.parent", "/hbase")
    //注意: 这里是INPUT_TABLE, 写是OUTPUT_TABLE
    hbaseConf.set(TableInputFormat.INPUT_TABLE, tablename)

    val hbaseRDD = sc.newAPIHadoopRDD(hbaseConf,
      //TableInputFormat 是 org.apache.hadoop.hbase.mapreduce 包下的
      classOf[TableInputFormat],
      classOf[ImmutableBytesWritable],
      classOf[Result])

    hbaseRDD.foreach{
      case (_, result) =>
        //获取行键
        val key = Bytes.toString(result.getRow)
        //通过列族和列名获取列
        val name = Bytes.toString(result.getValue("cf".getBytes, "name".getBytes))
        val age = Bytes.toString(result.getValue("cf".getBytes, "age".getBytes))
        println("Row key:"+key+"\tcf1.Name:"+name+"\tcf1.Age:"+age)
    }
    spark.stop()
  }

}

pom.xml

<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">
    <parent>
        <artifactId>spark-practise</artifactId>
        <groupId>org.example</groupId>
        <version>1.0-SNAPSHOT</version>
    </parent>
    <modelVersion>4.0.0</modelVersion>
    <artifactId>usehive1</artifactId>

    <repositories>
        <repository>
            <id>scala-tools.org</id>
            <name>Scala-Tools Maven2 Repository</name>
            <url>http://scala-tools.org/repo-releases</url>
        </repository>
    </repositories>

    <pluginRepositories>
        <pluginRepository>
            <id>scala-tools.org</id>
            <name>Scala-Tools Maven2 Repository</name>
            <url>http://scala-tools.org/repo-releases</url>
        </pluginRepository>
    </pluginRepositories>

    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.4</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.specs</groupId>
            <artifactId>specs</artifactId>
            <version>1.2.5</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_${scala.binary.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_${scala.binary.version}</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-client</artifactId>
        </dependency>

        <!-- https://mvnrepository.com/artifact/org.apache.hbase.connectors.spark/hbase-spark -->
        <dependency>
            <groupId>org.apache.hbase.connectors.spark</groupId>
            <artifactId>hbase-spark</artifactId>
        </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-1.8</arg>
                    </args>
                </configuration>
            </plugin>
        </plugins>
    </build>
</project>


执行:spark-submit --master local[2] --num-executors 10 --class com.grady.SparkReadHbase /app/data/appdeploy/usehive1-1.0-SNAPSHOT.jar

日志:

Row key:1       cf1.Name:jack   cf1.Age:15
Row key:2       cf1.Name:Lily   cf1.Age:16
Row key:3       cf1.Name:mike   cf1.Age:16

上一篇:在docker容器中操作es,并给es7.6添加用户鉴权设置密码


下一篇:Mybatis快速入门