Scala HTableDescriptor类代码示例

//设置package包名称以及导入依赖的类
package com.cloudera.sa.apptrans.setup.hbase

import java.io.File

import org.apache.commons.lang.StringUtils
import org.apache.hadoop.hbase.{HBaseConfiguration, HColumnDescriptor, HTableDescriptor, TableName}
import org.apache.hadoop.hbase.client.ConnectionFactory
import org.apache.hadoop.hbase.io.compress.Compression
import org.apache.hadoop.hbase.regionserver.{BloomType, ConstantSizeRegionSplitPolicy}
import org.apache.hadoop.hbase.util.Bytes

import scala.collection.mutable


object CreateSaltedTable {
  def main(args:Array[String]): Unit = {

    if (args.length == 0) {
      println("<tableName> <columnFamily> <regionCount> <numOfSalts> <hbaseConfigFolder>")
    }
    val tableName = args(0)
    val columnFamilyName = args(1)
    val regionCount = args(2).toInt
    val numOfSalts = args(3).toInt
    val hbaseConfigFolder = args(4)

    val conf = HBaseConfiguration.create()

    conf.addResource(new File(hbaseConfigFolder + "hbase-site.xml").toURI.toURL)

    val connection = ConnectionFactory.createConnection(conf)

    val admin = connection.getAdmin

    val tableDescriptor = new HTableDescriptor(TableName.valueOf(tableName))

    val columnDescriptor = new HColumnDescriptor(columnFamilyName)

    columnDescriptor.setCompressionType(Compression.Algorithm.SNAPPY)
    columnDescriptor.setBlocksize(64 * 1024)
    columnDescriptor.setBloomFilterType(BloomType.ROW)

    tableDescriptor.addFamily(columnDescriptor)

    tableDescriptor.setMaxFileSize(Long.MaxValue)
    tableDescriptor.setRegionSplitPolicyClassName(classOf[ConstantSizeRegionSplitPolicy].getName)

    val splitKeys = new mutable.MutableList[Array[Byte]]
    for (i <- 0 to regionCount) {
      val regionSplitStr = StringUtils.leftPad((i*(numOfSalts/regionCount)).toString, 4, "0")
      splitKeys += Bytes.toBytes(regionSplitStr)
    }
    admin.createTable(tableDescriptor, splitKeys.toArray)
  }
} 

//设置package包名称以及导入依赖的类
import org.apache.spark._
import org.apache.hadoop._

import org.apache.hadoop.hbase.client.{HBaseAdmin, Result}
import org.apache.hadoop.hbase.{ HBaseConfiguration, HTableDescriptor }
import org.apache.hadoop.hbase.mapreduce.TableInputFormat
import org.apache.hadoop.hbase.io.ImmutableBytesWritable

import org.apache.hadoop.hbase.client.{HBaseAdmin,HTable,Put,Get}
import org.apache.hadoop.hbase.util.Bytes

object HBaseHelloWorld {
  def main(args: Array[String]): Unit = {
    val sparkConf = new SparkConf().setAppName("HBaseRead")
    val sc = new SparkContext(sparkConf)
    val conf = HBaseConfiguration.create()
    val tableName = "enterprises"

    conf.set("hbase.master", "localhost:60000")
    conf.setInt("timeout", 120000)
    conf.set(TableInputFormat.INPUT_TABLE, tableName)

    val admin = new HBaseAdmin(conf)
    if (!admin.isTableAvailable(tableName)) {
      val tableDesc = new HTableDescriptor(tableName)
      admin.createTable(tableDesc)
    }

    val hBaseRDD = sc.newAPIHadoopRDD(conf, classOf[TableInputFormat], classOf[ImmutableBytesWritable], classOf[Result])
    println("Number of Records found : " + hBaseRDD.count())

    val pairs = hBaseRDD.map(s => (s, 1))
    val counts = pairs.reduceByKey((a, b) => a + b)

    sc.stop()
  }
} 

//设置package包名称以及导入依赖的类
package com.zaloni.mgohain.sparkHbaseIntegration.services

import org.apache.hadoop.hbase.client.{HBaseAdmin, HTable, Put}
import org.apache.hadoop.hbase.mapreduce.TableOutputFormat
import org.apache.hadoop.hbase.util.Bytes
import org.apache.hadoop.hbase.{HBaseConfiguration, HColumnDescriptor, HTableDescriptor}

object Employee {
  def main(args: Array[String]) {
    if (args.length != 1) {
      System.err.println("In correct number of arguments " + args.length)
      System.out.println("Please provide correct arguments.")
      System.exit(1)
    }
    val hbaseConf = HBaseConfiguration.create()
    val tableName = "employee"
    hbaseConf.set(TableOutputFormat.OUTPUT_TABLE, tableName)
    hbaseConf.set("hbase.zookeeper.quorum","quickstart.cloudera")
    hbaseConf.set("hbase.zookeeper.property.client.port","2181")
    val admin = new HBaseAdmin(hbaseConf)
    val cfProfessionalData = Bytes.toBytes("professional_data")
    val cfPersonalData = Bytes.toBytes("personal_data")
    if (!admin.isTableAvailable(tableName)) {
      val tableDesc = new HTableDescriptor(tableName)
      tableDesc.addFamily(new HColumnDescriptor(cfProfessionalData))
      tableDesc.addFamily(new HColumnDescriptor(cfPersonalData))
    }
    val hTable = new HTable(hbaseConf,tableName)
    //val records = sc.textFile(args(0))
    val put = new Put(Bytes.toBytes("e_1"))
    val eId = Bytes.toBytes("Emp_id")
    val name = Bytes.toBytes("Name")
    val dsgtn = Bytes.toBytes("Designation")
    val doj = Bytes.toBytes("DOJ")
    val addr = Bytes.toBytes("Address")
    val phn = Bytes.toBytes("Phone")
    val dob = Bytes.toBytes("DOB")
    put.add(cfProfessionalData, eId, Bytes.toBytes(1))
    put.add(cfProfessionalData, name, Bytes.toBytes("Mridul Gohain"))
    put.add(cfProfessionalData, dsgtn, Bytes.toBytes("SE"))
    put.add(cfProfessionalData, doj, Bytes.toBytes("15-07-2015"))
    put.add(cfPersonalData, addr, Bytes.toBytes("Chabua"))
    put.add(cfPersonalData, phn, Bytes.toBytes("9859559606"))
    put.add(cfPersonalData, dob, Bytes.toBytes("04-10-1991"))
    hTable.put(put)
    hTable.close()
  }
} 

//设置package包名称以及导入依赖的类
package com.hadooparchitecturebook.taxi360.setup.hbase

import java.io.File

import org.apache.commons.lang.StringUtils
import org.apache.hadoop.hbase.{HBaseConfiguration, HColumnDescriptor, HTableDescriptor, TableName}
import org.apache.hadoop.hbase.client.ConnectionFactory
import org.apache.hadoop.hbase.io.compress.Compression
import org.apache.hadoop.hbase.regionserver.{BloomType, ConstantSizeRegionSplitPolicy}
import org.apache.hadoop.hbase.util.Bytes

import scala.collection.mutable


object CreateSaltedTable {
  def main(args:Array[String]): Unit = {

    if (args.length == 0) {
      println("<tableName> <columnFamily> <regionCount> <numOfSalts> <hbaseConfigFolder>")
    }
    val tableName = args(0)
    val columnFamilyName = args(1)
    val regionCount = args(2).toInt
    val numOfSalts = args(3).toInt
    val hbaseConfigFolder = args(4)

    val conf = HBaseConfiguration.create()

    conf.addResource(new File(hbaseConfigFolder + "hbase-site.xml").toURI.toURL)

    val connection = ConnectionFactory.createConnection(conf)

    val admin = connection.getAdmin

    val tableDescriptor = new HTableDescriptor(TableName.valueOf(tableName))

    val columnDescriptor = new HColumnDescriptor(columnFamilyName)

    columnDescriptor.setCompressionType(Compression.Algorithm.SNAPPY)
    columnDescriptor.setBlocksize(64 * 1024)
    columnDescriptor.setBloomFilterType(BloomType.ROW)

    tableDescriptor.addFamily(columnDescriptor)

    tableDescriptor.setMaxFileSize(Long.MaxValue)
    tableDescriptor.setRegionSplitPolicyClassName(classOf[ConstantSizeRegionSplitPolicy].getName)

    val splitKeys = new mutable.MutableList[Array[Byte]]
    for (i <- 0 to regionCount) {
      val regionSplitStr = StringUtils.leftPad((i*(numOfSalts/regionCount)).toString, 4, "0")
      splitKeys += Bytes.toBytes(regionSplitStr)
    }
    admin.createTable(tableDescriptor, splitKeys.toArray)
  }
} 

//设置package包名称以及导入依赖的类
package uk.co.odinconsultants.bitcoin.hbase

import org.apache.hadoop.hbase.{HColumnDescriptor, HTableDescriptor, TableName}
import org.apache.hadoop.hbase.client.HBaseAdmin

object HBaseSetup {

  val metaTable: String   = "Addresses"
  val tableName: TableName = TableName.valueOf(metaTable)
  val familyName: String  = "familyName"

  def createAddressesTable(admin: HBaseAdmin): Unit = {
    createTable(admin, metaTable, familyName)
  }

  private def createTable(admin: HBaseAdmin, tableName: String, familyName: String): Unit = {
    val tableDescriptor = new HTableDescriptor(tableName)
    val colDescriptor   = new HColumnDescriptor(familyName)
    tableDescriptor.addFamily(colDescriptor)
    if (!admin.tableExists(tableName)) {
      admin.createTable(tableDescriptor)
    }
  }

} 

//设置package包名称以及导入依赖的类
import org.apache.hadoop.hbase.client.{ HBaseAdmin, Result }
import org.apache.hadoop.hbase.HTableDescriptor
import org.apache.hadoop.hbase.mapreduce.TableInputFormat
import org.apache.hadoop.hbase.io.ImmutableBytesWritable
import org.apache.hadoop.hbase.util.Bytes



object HBaseReader {

  def main(args: Array[String]) {

    if(args.size != 1){
      println("Usage: HBaseReader <table name>")
      System.exit(-1)
    }
    
    val tableName = args(0)
    val master = ""

    val sc = Connection.createSparkConf()
    val conf = Connection.createHBaseConf()

    val admin = new HBaseAdmin(conf)
    if (!admin.isTableAvailable(tableName)) {
      val tableDesc = new HTableDescriptor(tableName)
      admin.createTable(tableDesc)
    }
    
    conf.set(TableInputFormat.INPUT_TABLE, tableName)
    val hBaseRDD = sc.newAPIHadoopRDD(conf, classOf[TableInputFormat],
      classOf[ImmutableBytesWritable],
      classOf[Result])

    println("Number of Records found : " + hBaseRDD.count())

    val stocksRdd = hBaseRDD.map {
      case (key: ImmutableBytesWritable, value: Result) =>
        Stock(
          new String(key.get),
          new String(value.getValue(Bytes.toBytes("prices"), Bytes.toBytes("Open"))),
          new String(value.getValue(Bytes.toBytes("prices"), Bytes.toBytes("Close"))),
          new String(value.getValue(Bytes.toBytes("prices"), Bytes.toBytes("High"))),
          new String(value.getValue(Bytes.toBytes("prices"), Bytes.toBytes("Low"))),
          new String(value.getValue(Bytes.toBytes("prices"), Bytes.toBytes("AdjClose"))),
          new String(value.getValue(Bytes.toBytes("volume"), Bytes.toBytes("vol"))))
    }
    stocksRdd.take(10).foreach(println)

  }
}