在hbase中插入Spark dataframe

Question

 --------------------
|id | name | address |
|--------------------|
|23 |marry |france   |
|--------------------|
|87 |zied  |italie   |
 --------------------

val tableName = "two"
val conf = HBaseConfiguration.create()
if(!admin.isTableAvailable(tableName)) {
          print("-----------------------------------------------------------------------------------------------------------")
          val tableDesc = new HTableDescriptor(tableName)
          tableDesc.addFamily(new HColumnDescriptor("z1".getBytes()))
          admin.createTable(tableDesc)
        }else{
          print("Table already exists!!--------------------------------------------------------------------------------------")
        }

val myTable = new HTable(conf, tableName)
    for (i <- 0 to 1000) {
      var p = new Put(Bytes.toBytes(""+i))
      p.add("z1".getBytes(), "name".getBytes(), Bytes.toBytes(""+(i*5)))
      p.add("z1".getBytes(), "age".getBytes(), Bytes.toBytes("2017-04-20"))
      p.add("z2".getBytes(), "job".getBytes(), Bytes.toBytes(""+i))
      p.add("z2".getBytes(), "salary".getBytes(), Bytes.toBytes(""+i))
      myTable.put(p)
    }
    myTable.flushCommits()

感谢您的时间和关注

Answer 1

下面是使用Maven中Hortonworks提供的spark hbase连接器的完整示例。

此示例显示

• 如何检查HBase表是否存在
• 如果不存在，则创建HBase表
• 将DataFrame插入HBase表

import org.apache.hadoop.hbase.client.{ColumnFamilyDescriptorBuilder, ConnectionFactory, TableDescriptorBuilder}
import org.apache.hadoop.hbase.{HBaseConfiguration, TableName}
import org.apache.spark.sql.SparkSession
import org.apache.spark.sql.execution.datasources.hbase.HBaseTableCatalog

object Main extends App {

  case class Employee(key: String, fName: String, lName: String, mName: String,
                      addressLine: String, city: String, state: String, zipCode: String)

  // as pre-requisites the table 'employee' with column families 'person' and 'address' should exist
  val tableNameString = "default:employee"
  val colFamilyPString = "person"
  val colFamilyAString = "address"
  val tableName = TableName.valueOf(tableNameString)
  val colFamilyP = colFamilyPString.getBytes
  val colFamilyA = colFamilyAString.getBytes

  val hBaseConf = HBaseConfiguration.create()
  val connection = ConnectionFactory.createConnection(hBaseConf);
  val admin = connection.getAdmin();

  println("Check if table 'employee' exists:")
  val tableExistsCheck: Boolean = admin.tableExists(tableName)
  println(s"Table " + tableName.toString + " exists? " + tableExistsCheck)

  if(tableExistsCheck == false) {
    println("Create Table employee with column families 'person' and 'address'")
    val colFamilyBuild1 = ColumnFamilyDescriptorBuilder.newBuilder(colFamilyP).build()
    val colFamilyBuild2 = ColumnFamilyDescriptorBuilder.newBuilder(colFamilyA).build()
    val tableDescriptorBuild = TableDescriptorBuilder.newBuilder(tableName)
      .setColumnFamily(colFamilyBuild1)
      .setColumnFamily(colFamilyBuild2)
      .build()
    admin.createTable(tableDescriptorBuild)
  }

  // define schema for the dataframe that should be loaded into HBase
  def catalog =
    s"""{
       |"table":{"namespace":"default","name":"employee"},
       |"rowkey":"key",
       |"columns":{
       |"key":{"cf":"rowkey","col":"key","type":"string"},
       |"fName":{"cf":"person","col":"firstName","type":"string"},
       |"lName":{"cf":"person","col":"lastName","type":"string"},
       |"mName":{"cf":"person","col":"middleName","type":"string"},
       |"addressLine":{"cf":"address","col":"addressLine","type":"string"},
       |"city":{"cf":"address","col":"city","type":"string"},
       |"state":{"cf":"address","col":"state","type":"string"},
       |"zipCode":{"cf":"address","col":"zipCode","type":"string"}
       |}
       |}""".stripMargin

  // define some test data
  val data = Seq(
    Employee("1","Horst","Hans","A","12main","NYC","NY","123"),
    Employee("2","Joe","Bill","B","1337ave","LA","CA","456"),
    Employee("3","Mohammed","Mohammed","C","1Apple","SanFran","CA","678")
  )

  // create SparkSession
  val spark: SparkSession = SparkSession.builder()
    .master("local[*]")
    .appName("HBaseConnector")
    .getOrCreate()

  // serialize data
  import spark.implicits._
  val df = spark.sparkContext.parallelize(data).toDF

  // write dataframe into HBase
  df.write.options(
    Map(HBaseTableCatalog.tableCatalog -> catalog, HBaseTableCatalog.newTable -> "3")) // create 3 regions
    .format("org.apache.spark.sql.execution.datasources.hbase")
    .save()

}