首页 > 其他分享 >spark springboot hbase(读取student、写入student)20221026

spark springboot hbase(读取student、写入student)20221026

时间:2022-10-26 15:12:56浏览次数:54  
标签:springboot 20221026 Bytes hadoop var student apache org hbase

1、pom.xml

  <dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-core_2.11</artifactId>
    <version>1.6.0</version>
    <exclusions>
      <exclusion>
        <groupId>io.netty</groupId>
        <artifactId>netty-all</artifactId>
      </exclusion>
    </exclusions>
  </dependency>
  <dependency>
    <groupId>io.netty</groupId>
    <artifactId>netty-all</artifactId>
    <version>4.1.17.Final</version>
  </dependency>
  <dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-client</artifactId>
    <version>2.6.2</version>
  </dependency>
  <dependency><!--Hbase-->
    <groupId>org.apache.hbase</groupId>
    <artifactId>hbase-client</artifactId>
    <version>1.4.3</version>
  </dependency>
  <dependency>
    <groupId>org.apache.hbase</groupId>
    <artifactId>hbase-common</artifactId>
    <version>1.4.3</version>
  </dependency>
  <dependency>
    <groupId>org.apache.hbase</groupId>
    <artifactId>hbase-server</artifactId>
    <version>1.4.3</version>
  </dependency>
  <dependency><!--mysql-->
    <groupId>mysql</groupId>
    <artifactId>mysql-connector-java</artifactId>
    <scope>runtime</scope>
  </dependency>
  <dependency>
    <groupId>org.apache.spark</groupId>
    <artifactId>spark-sql_2.11</artifactId>
    <version>1.6.0</version>
  </dependency>

 

pom.xml 若hbase-server 无效则如下导入

 

 

 

2、RDDFromHbase.scala

读取hbase表student记录

 

 


import org.apache.hadoop.hbase.{HBaseConfiguration, TableName}
import org.apache.hadoop.hbase.io.ImmutableBytesWritable
import org.apache.hadoop.hbase.mapreduce.TableInputFormat
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.hadoop.hbase.util.Bytes
object RDDFromHbase {

  def main(args: Array[String]): Unit = {
    var conf=HBaseConfiguration.create()
    var sparkConf=new SparkConf().setAppName("读取hbase中的数据").setMaster("local")
    var sc=new SparkContext(sparkConf)
    conf.set("hbase.zookeeper.quorum", "127.0.0.1")
    conf.set("hbase.zookeeper.property.clientPort", "2181")
    //查询表名
    conf.set(TableInputFormat.INPUT_TABLE,"student")

    //如果表不存则创建表
    /* val admin=new HBaseAdmin(conf);
    if(!admin.isTableAvailable("student")){
      var tableDesc=new HTableDescripter(TableName.valueOf("student"))
    }*/


    var RDD=sc.newAPIHadoopRDD(conf,classOf[TableInputFormat],
      classOf[ImmutableBytesWritable],
      classOf[org.apache.hadoop.hbase.client.Result])

    var count=RDD.count()
    println("Students RDD Count:......."+count)
    println(s"count=${RDD.count()}")
    RDD.cache()
    //遍历输出
    RDD.foreach({case (_,result)=>
      val key=Bytes.toString(result.getRow)
      val name=Bytes.toString(result.getValue("info".getBytes,"name".getBytes))
      val gender=Bytes.toString(result.getValue("info".getBytes,"gender".getBytes))
      val age=Bytes.toString(result.getValue("info".getBytes,"age".getBytes))
      println("ROW:"+key+" name: "+name+" Gender: "+gender+" Age: "+age)
    })


    Thread.sleep(100000)//为监控界面,线程休眠
    // sc.stop()
}

}

 

 

 

 

 

 

 

 

 

 

3、RDDToHbase.scala

往hbase表student存记录


  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.mapred.TableOutputFormat
  import org.apache.hadoop.mapred.JobConf
  import org.apache.hadoop.hbase.util.Bytes
  import org.apache.spark.{SparkConf, SparkContext}

  object RDDToHbase {

    def main(args: Array[String]): Unit = {
    var sparkConf=new SparkConf().setAppName("往hbase中写数据").setMaster("local")
    var sc=new SparkContext(sparkConf)
    var tableName="student"
    var conf=HBaseConfiguration.create()

    val jobConf=new JobConf(conf)
    jobConf.setOutputFormat(classOf[TableOutputFormat])
    jobConf.set(TableOutputFormat.OUTPUT_TABLE,tableName)

    //构建新记录
    var dataRDD=sc.makeRDD(Array("5,hadoop,B,29","6,spark,G,46"))
    var rdd=dataRDD.map(_.split(",")).map(x=>{
      var put=new Put(Bytes.toBytes(x(0)))     //行键值 put.add方法接收三个参灵敏:列族,列名,数据
        put.addColumn(Bytes.toBytes("info"),Bytes.toBytes("name"),Bytes.toBytes(x(1)))    //info:name列的值
        put.addColumn(Bytes.toBytes("info"),Bytes.toBytes("gender"),Bytes.toBytes(x(2)))     //info:gender列的值
        put.addColumn(Bytes.toBytes("info"),Bytes.toBytes("age"),Bytes.toBytes(x(3)))      //info:age列的值
        (new ImmutableBytesWritable,put) //转化成RDD[(ImmutableBytesWritable,put)]类型才能调用saveAsHadoopDataset
    })
    rdd.saveAsHadoopDataset(jobConf)
}
}

 

 

 

 

 

 

参考https://www.cnblogs.com/saowei/p/15941613.html

标签:springboot,20221026,Bytes,hadoop,var,student,apache,org,hbase
From: https://www.cnblogs.com/smallfa/p/16828432.html

相关文章