【Spark五十一】Spark读写HBase

最新推荐文章于 2025-05-22 11:11:17 发布

原创最新推荐文章于 2025-05-22 11:11:17 发布 · 120 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#大数据

Spark 专栏收录该内容

109 篇文章

订阅专栏

本文介绍如何使用Apache Spark从HBase中读取数据。通过示例代码展示了配置SparkContext和HBase连接的方式，并实现了一个简单的计数操作来验证读取过程的成功。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

挖个坑

读HBase

import org.apache.spark._
import org.apache.spark.rdd.NewHadoopRDD
import org.apache.hadoop.hbase.{HBaseConfiguration, HTableDescriptor}
import org.apache.hadoop.hbase.client.HBaseAdmin
import org.apache.hadoop.hbase.mapreduce.TableInputFormat


object HBaseTest {
  def main(args: Array[String]) {
    val sc = new SparkContext(args(0), "HBaseTest",
      System.getenv("SPARK_HOME"), SparkContext.jarOfClass(this.getClass))

    val conf = HBaseConfiguration.create()
    conf.set(TableInputFormat.INPUT_TABLE, args(1))

    val hBaseRDD = sc.newAPIHadoopRDD(conf, classOf[TableInputFormat], 
      classOf[org.apache.hadoop.hbase.io.ImmutableBytesWritable],
      classOf[org.apache.hadoop.hbase.client.Result])

    hBaseRDD.count()

    System.exit(0)
  }
}

参见：http://www.iteblog.com/archives/1051

http://www.netfoucs.com/article/u014388509/86933.html

Spark自带的例子

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *    http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package org.apache.spark.examples

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

import org.apache.spark._


object HBaseTest {
  def main(args: Array[String]) {
    val sparkConf = new SparkConf().setAppName("HBaseTest")
    val sc = new SparkContext(sparkConf)
    val conf = HBaseConfiguration.create()
    // Other options for configuring scan behavior are available. More information available at
    // http://hbase.apache.org/apidocs/org/apache/hadoop/hbase/mapreduce/TableInputFormat.html
    conf.set(TableInputFormat.INPUT_TABLE, args(0))

    // Initialize hBase table if necessary
    val admin = new HBaseAdmin(conf)
    if (!admin.isTableAvailable(args(0))) {
      val tableDesc = new HTableDescriptor(args(0))
      admin.createTable(tableDesc)
    }

    val hBaseRDD = sc.newAPIHadoopRDD(conf, classOf[TableInputFormat],
      classOf[org.apache.hadoop.hbase.io.ImmutableBytesWritable],
      classOf[org.apache.hadoop.hbase.client.Result])

    hBaseRDD.count()

    sc.stop()
  }
}

写HBase：

http://wuchong.me/blog/2015/04/06/spark-on-hbase-new-api/