Spark从 Hbase 读写文件

由于 org.apache.hadoop.hbase.mapreduce.TableInputFormat 类的实现，Spark 可以通过Hadoop输入格式访问 HBase。

这个输入格式会返回键值对数据，其中键的类型为org. apache.hadoop.hbase.io.ImmutableBytesWritable，而值的类型为org.apache.hadoop.hbase.client.Result。

1. 导入依赖

<dependencies>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>2.1.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-server</artifactId>
            <version>1.3.1</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-client</artifactId>
            <version>1.3.1</version>
        </dependency>

    </dependencies>

2. Spark从HBase读取数据

import org.apache.hadoop.conf.Configuration
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.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}

/**
  * @author fczheng 
  *
  */
object Spark35_RDD_HBase {
    def main(args: Array[String]): Unit = {
        
        // TODO 1.创建Spark配置对象
        val conf: SparkConf = new SparkConf().setAppName("Spark_HBase").setMaster("local[*]")
        
        // TODO 2.创建Spark环境连接对象
        val sc: SparkContext = new SparkContext(conf)
        
        val hbaseConf: Configuration = HBaseConfiguration.create()
        hbaseConf.set("hbase.zookeeper.quorum", "hadoop102,hadoop103,hadoop104")
        hbaseConf.set(TableInputFormat.INPUT_TABLE,"student")
        
        //TODO 3.从HBase中读取数据
        val hbaseRDD: RDD[(ImmutableBytesWritable, Result)] = sc.newAPIHadoopRDD(
            hbaseConf,
            classOf[TableInputFormat],
            classOf[ImmutableBytesWritable],
            classOf[Result]
        )
    
        val rdd2: RDD[String] = hbaseRDD.map {
            case (_, result) => Bytes.toString(result.getRow)
        }
        rdd2.collect().foreach(println)
        
        // TODO 4. 释放连接
        sc.stop()
       
    }
}

3. Spark向HBase写入数据

import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.hbase.HBaseConfiguration
import org.apache.hadoop.hbase.client.Put
import org.apache.hadoop.hbase.io.ImmutableBytesWritable
import org.apache.hadoop.hbase.mapreduce.TableOutputFormat
import org.apache.hadoop.hbase.util.Bytes
import org.apache.hadoop.mapreduce.Job
import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}

/**
  * @author fczheng 
  *
  */
object Spark36_RDD_HBase1 {
    def main(args: Array[String]): Unit = {
        // TODO 1.创建Spark配置对象
        val conf: SparkConf = new SparkConf().setAppName("Spark_HBase").setMaster("local[*]")
        
        // TODO 2.创建Spark环境连接对象
        val sc: SparkContext = new SparkContext(conf)
        
        val hbaseConf: Configuration = HBaseConfiguration.create()
        hbaseConf.set("hbase.zookeeper.quorum","hadoop102,hadoop103,hadoop104")
        hbaseConf.set(TableOutputFormat.OUTPUT_TABLE,"student")
        
        // TODO 3.通过job来设置输出的格式的类
        
        val job: Job = Job.getInstance(hbaseConf)
        
        job.setOutputFormatClass(classOf[TableOutputFormat[ImmutableBytesWritable]])
        job.setOutputKeyClass(classOf[ImmutableBytesWritable])
        job.setOutputValueClass(classOf[Put])
        
        // TODO 4.向HBase插入数据
        //Put
        val dataRDD: RDD[(String, String, Int)] = sc.parallelize(List(("1003","male",22),("1004","female",88),("1005","female",66)))
        
        //data => put
        val hbaseRDD: RDD[(ImmutableBytesWritable, Put)] = dataRDD.map(x => {
            val put: Put = new Put(Bytes.toBytes(x._1))
        
            put.addColumn(Bytes.toBytes("info"), Bytes.toBytes("sex"), Bytes.toBytes(x._2))
            put.addColumn(Bytes.toBytes("info"), Bytes.toBytes("age"), Bytes.toBytes(x._3))
        
            (new ImmutableBytesWritable(), put)
        })
        
        hbaseRDD.saveAsNewAPIHadoopDataset(job.getConfiguration)
        
        //TODO 5.释放连接
        sc.stop()
    }
}