整體描述:將本地文件的數(shù)據(jù)整理之后導(dǎo)入到hbase中
成都創(chuàng)新互聯(lián)專(zhuān)注于澄邁企業(yè)網(wǎng)站建設(shè),成都響應(yīng)式網(wǎng)站建設(shè)公司,電子商務(wù)商城網(wǎng)站建設(shè)。澄邁網(wǎng)站建設(shè)公司,為澄邁等地區(qū)提供建站服務(wù)。全流程按需網(wǎng)站建設(shè),專(zhuān)業(yè)設(shè)計(jì),全程項(xiàng)目跟蹤,成都創(chuàng)新互聯(lián)專(zhuān)業(yè)和態(tài)度為您提供的服務(wù)
在HBase中創(chuàng)建表
數(shù)據(jù)格式
MapReduce程序
map程序
package com.hadoop.mapreduce.test.map; import java.io.IOException; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Mapper; public class WordCountHBaseMapper extends Mapper
Reduce程序
package com.hadoop.mapreduce.test.reduce; import java.io.IOException; import java.util.Iterator; import org.apache.hadoop.hbase.client.Put; import org.apache.hadoop.hbase.mapreduce.TableReducer; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.io.Text; public class WordCountHBaseReduce extends TableReducer{ @Override protected void reduce(Text key, Iterable value, Context out) throws IOException, InterruptedException { String keyValue = key.toString(); Iterator valueIterator = value.iterator(); while(valueIterator.hasNext()){ Text valueV = valueIterator.next(); String[] valueArray = valueV.toString().split("#"); Put putRow = new Put(keyValue.getBytes()); putRow.add("address".getBytes(), "baseAddress".getBytes(), valueArray[0].getBytes()); putRow.add("sex".getBytes(), "baseSex".getBytes(), valueArray[1].getBytes()); putRow.add("age".getBytes(), "baseAge".getBytes(), valueArray[2].getBytes()); out.write(NullWritable.get(), putRow); } } }
主程序
package com.hadoop.mapreduce.test; import java.io.IOException; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.hbase.HBaseConfiguration; import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import com.hadoop.mapreduce.test.map.WordCountHBaseMapper; import com.hadoop.mapreduce.test.reduce.WordCountHBaseReduce; /** * 將hdfs上的內(nèi)容讀取到,并插入到hbase的表中,然后讀取hbase表中的內(nèi)容,將統(tǒng)計(jì)結(jié)果插入到hbase中 */ public class WordCountHBase { public static void main(String args[]) throws IOException, InterruptedException, ClassNotFoundException{ Configuration conf = HBaseConfiguration.create(); conf.set("hbase.zookeeper.quorum", "192.168.192.137"); Job job = Job.getInstance(conf, "MapReduceHbaseJob"); //各種class job.setJarByClass(WordCountHBase.class); job.setMapperClass(WordCountHBaseMapper.class); TableMapReduceUtil.initTableReducerJob("userInfo3", WordCountHBaseReduce.class, job); FileInputFormat.addInputPath(job, new Path(args[0])); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); System.exit(job.waitForCompletion(true) ? 0 : 1); } }
結(jié)果:
注:如果運(yùn)行的client沒(méi)有hbase,需要在hadoop里面的lib中加入hbase的lib