实现将 HDFS 中的数据写入到 HBase 表中
Runner类
1 package com.yjsj.hbase_mr2; 2 3 import com.yjsj.hbase_mr2.ReadFruitFromHDFSMapper; 4 import com.yjsj.hbase_mr2.WriteFruitMRFromTxtReducer; 5 import org.apache.hadoop.conf.Configuration; 6 import org.apache.hadoop.conf.Configured; 7 import org.apache.hadoop.fs.Path; 8 import org.apache.hadoop.hbase.HBaseConfiguration; 9 import org.apache.hadoop.hbase.client.Put; 10 import org.apache.hadoop.hbase.io.ImmutableBytesWritable; 11 import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil; 12 import org.apache.hadoop.mapreduce.Job; 13 import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; 14 import org.apache.hadoop.util.Tool; 15 import org.apache.hadoop.util.ToolRunner; 16 17 import java.io.IOException; 18 19 class Txt2FruitRunner extends Configured implements Tool { 20 public int run(String[] args) throws Exception { 21 //得到 Configuration 22 Configuration conf = this.getConf(); 23 //创建 Job 任务 24 Job job = Job.getInstance(conf, this.getClass().getSimpleName()); 25 job.setJarByClass(Txt2FruitRunner.class); 26 Path inPath = new Path("hdfs://master:9000/input_fruit/fruit.tsv"); 27 28 FileInputFormat.addInputPath(job, inPath); 29 //设置 Mapper 30 job.setMapperClass(ReadFruitFromHDFSMapper.class); 31 job.setMapOutputKeyClass(ImmutableBytesWritable.class); 32 job.setMapOutputValueClass(Put.class); 33 //设置 Reducer 34 TableMapReduceUtil.initTableReducerJob("fruit_hdfs", WriteFruitMRFromTxtReducer.class, job); 35 //设置 Reduce 数量,最少 1 个 36 job.setNumReduceTasks(1); 37 boolean isSuccess = job.waitForCompletion(true); 38 if (!isSuccess) { 39 throw new IOException("Job running with error"); 40 } 41 return isSuccess ? 0 : 1; 42 } 43 44 public static void main(String[] args) throws Exception { 45 Configuration conf = HBaseConfiguration.create(); 46 conf = HBaseConfiguration.create(); 47 conf.set("hbase.zookeeper.quorum", "master,node1,node2"); 48 conf.set("hbase.zookeeper.property.clientPort", "2181"); 49 conf.set("hbase.master", "master:60000"); 50 int status = ToolRunner.run(conf, new Txt2FruitRunner(), args); 51 System.exit(status); 52 } 53 }
Mapper类
1 package com.yjsj.hbase_mr2; 2 3 import java.io.IOException; 4 5 import org.apache.hadoop.hbase.client.Put; 6 import org.apache.hadoop.hbase.io.ImmutableBytesWritable; 7 import org.apache.hadoop.hbase.util.Bytes; 8 import org.apache.hadoop.io.LongWritable; 9 import org.apache.hadoop.io.Text; 10 import org.apache.hadoop.mapreduce.Mapper; 11 12 public class ReadFruitFromHDFSMapper extends Mapper<LongWritable, Text, ImmutableBytesWritable, Put> { 13 @Override 14 protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { 15 //从 HDFS 中读取的数据 16 String lineValue = value.toString(); 17 //读取出来的每行数据使用\t 进行分割,存于 String 数组 18 String[] values = lineValue.split("\t"); 19 //根据数据中值的含义取值 20 String rowKey = values[0]; 21 String name = values[1]; 22 String color = values[2]; 23 //初始化 rowKey 24 ImmutableBytesWritable rowKeyWritable = new ImmutableBytesWritable(Bytes.toBytes(rowKey)); 25 //初始化 put 对象 26 Put put = new Put(Bytes.toBytes(rowKey)); 27 //参数分别:列族、列、值 28 put.add(Bytes.toBytes("info"), Bytes.toBytes("name"), Bytes.toBytes(name)); 29 put.add(Bytes.toBytes("info"), Bytes.toBytes("color"), Bytes.toBytes(color)); 30 context.write(rowKeyWritable, put); 31 } 32 }
Reduce类
package com.yjsj.hbase_mr2; import java.io.IOException; import org.apache.hadoop.hbase.client.Put; import org.apache.hadoop.hbase.io.ImmutableBytesWritable; import org.apache.hadoop.hbase.mapreduce.TableReducer; import org.apache.hadoop.io.NullWritable; public class WriteFruitMRFromTxtReducer extends TableReducer<ImmutableBytesWritable, Put, NullWritable> { @Override protected void reduce(ImmutableBytesWritable key, Iterable<Put> values, Context context) throws IOException, InterruptedException { //读出来的每一行数据写入到 fruit_hdfs 表中 for (Put put : values) { context.write(NullWritable.get(), put); } } }
原文地址:https://www.cnblogs.com/pursue339/p/10658127.html
时间: 2024-10-08 21:44:52