Spark 写 Hbase
package com.grady
import org.apache.hadoop.hbase.HBaseConfiguration
import org.apache.hadoop.hbase.client.{Put, Result}
import org.apache.hadoop.hbase.io.ImmutableBytesWritable
import org.apache.hadoop.hbase.mapred.TableOutputFormat
import org.apache.hadoop.hbase.util.Bytes
import org.apache.hadoop.mapred.JobConf
import org.apache.spark.{SparkConf, SparkContext}
object SparkWriteHbase {
def main(args: Array[String]): Unit = {
val sparkConf = new SparkConf().setAppName("SparkWriteHbase")
val sc = new SparkContext(sparkConf)
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")
hbaseConf.set(TableOutputFormat.OUTPUT_TABLE, tablename)
val jobConf = new JobConf(hbaseConf)
jobConf.setOutputFormat(classOf[TableOutputFormat])
val inDataRDD = sc.makeRDD(Array("1,jack,15", "2,Lily,16", "3,mike,16"))
val rdd = inDataRDD.map(_.split(',')).map { arr => {
val put = new Put(Bytes.toBytes(arr(0)))
put.addColumn(Bytes.toBytes("cf"), Bytes.toBytes("name"), Bytes.toBytes(arr(1)))
put.addColumn(Bytes.toBytes("cf"), Bytes.toBytes("age"), Bytes.toBytes(arr(2)))
(new ImmutableBytesWritable, put)
}}
rdd.saveAsHadoopDataset(jobConf)
sc.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.SparkWriteHbase /app/data/appdeploy/usehive1-1.0-SNAPSHOT.jar
日志:
hbase(main):008:0> scan 'jiang:student'
ROW COLUMN+CELL
1 column=cf:age, timestamp=2022-02-08T16:27:01.290, value=15
1 column=cf:name, timestamp=2022-02-08T16:27:01.290, value=jack
2 column=cf:age, timestamp=2022-02-08T16:27:01.290, value=16
2 column=cf:name, timestamp=2022-02-08T16:27:01.290, value=Lily
3 column=cf:age, timestamp=2022-02-08T16:27:01.290, value=16
3 column=cf:name, timestamp=2022-02-08T16:27:01.290, value=mike