MapReduce imports text data into HBase

Overall description: import the data from local files into hbase after collation

Create a table in HBase

Data format

MapReduce program

Map program

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 {public Text keyValue = new Text (); public Text valueValue = new Text (); / / data type is: key@addressValue#ageValue#sexValue @ Override protected void map (Object key, Text value, Context context) throws IOException, InterruptedException {String lineValue = value.toString () If (lineValue! = null) {String [] valuesArray = lineValue.split ("@"); context.write (new Text (valuesArray [0]), new Text (valuesArray [1]));}

Reduce program

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);}

Main program

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 / * read the contents of hdfs and insert them into the hbase table, then read the contents of the hbase table and insert the statistical results into hbase * / 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"); / / various 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);}}

Results:

Note: if the client you are running does not have hbase, you need to add the lib of hbase to the lib in hadoop.